diff -urN oldtree/Documentation/kernel-parameters.txt newtree/Documentation/kernel-parameters.txt
--- oldtree/Documentation/kernel-parameters.txt	2006-01-28 16:36:00.000000000 +0000
+++ newtree/Documentation/kernel-parameters.txt	2006-01-28 17:08:36.081750384 +0000
@@ -71,6 +71,7 @@
 	SERIAL	Serial support is enabled.
 	SMP	The kernel is an SMP kernel.
 	SPARC	Sparc architecture is enabled.
+	SUSPEND2 Suspend2 is enabled.
 	SWSUSP	Software suspend is enabled.
 	TS	Appropriate touchscreen support is enabled.
 	USB	USB support is enabled.
@@ -966,6 +967,8 @@
 	noresume	[SWSUSP] Disables resume and restores original swap
 			space.
 
+	noresume2	[SUSPEND2] Disables resuming and restores original swap signature.
+ 
 	no-scroll	[VGA] Disables scrollback.
 			This is required for the Braillex ib80-piezo Braille
 			reader made by F.H. Papenmeier (Germany).
@@ -1215,6 +1218,11 @@
 	resume=		[SWSUSP]
 			Specify the partition device for software suspend
 
+ 	resume2=	[SUSPEND2] Specify the storage device for Suspend2.
+			Format: <writer>:<writer-parameters>.
+			See Documentation/power/suspend2.txt for details of the
+			formats	for available image writers.
+
 	rhash_entries=	[KNL,NET]
 			Set number of hash buckets for route cache
 
diff -urN oldtree/Documentation/power/internals.txt newtree/Documentation/power/internals.txt
--- oldtree/Documentation/power/internals.txt	1970-01-01 00:00:00.000000000 +0000
+++ newtree/Documentation/power/internals.txt	2006-01-28 17:08:36.082750232 +0000
@@ -0,0 +1,360 @@
+		Software Suspend 2.2 Internal Documentation.
+				Version 1
+
+1.  Introduction.
+
+    Software Suspend 2.2 is an addition to the Linux Kernel, designed to
+    allow the user to quickly shutdown and quickly boot a computer, without
+    needing to close documents or programs. It is equivalent to the
+    hibernate facility in some laptops. This implementation, however,
+    requires no special BIOS or hardware support.
+
+    The code in these files is based upon the original implementation
+    prepared by Gabor Kuti and additional work by Pavel Machek and a
+    host of others. This code has been substantially reworked by Nigel
+    Cunningham, again with the help and testing of many others, not the
+    least of whom is Michael Frank, At its heart, however, the operation is
+    essentially the same as Gabor's version.
+
+2.  Overview of operation.
+
+    The basic sequence of operations is as follows:
+
+	a. Quiesce all other activity.
+	b. Ensure enough memory and storage space are available, and attempt
+	   to free memory/storage if necessary.
+	c. Allocate the required memory and storage space.
+	d. Write the image.
+	e. Power down.
+
+    There are a number of complicating factors which mean that things are
+    not as simple as the above would imply, however...
+
+    o The activity of each process must be stopped at a point where it will
+    not be holding locks necessary for saving the image, or unexpectedly
+    restart operations due to something like a timeout and thereby make
+    our image inconsistent.
+
+    o It is desirous that we sync outstanding I/O to disk before calculating
+    image statistics. This reduces corruption if one should suspend but
+    then not resume, and also makes later parts of the operation safer (see
+    below).
+
+    o We need to get as close as we can to an atomic copy of the data.
+    Inconsistencies in the image will result inconsistent memory contents at
+    resume time, and thus in instability of the system and/or file system
+    corruption. This would appear to imply a maximum image size of one half of
+    the amount of RAM, but we have a solution... (again, below).
+
+    o In 2.6, we must play nicely with the other suspend-to-disk
+    implementations.
+
+3.  Detailed description of internals.
+
+    a. Quiescing activity.
+
+    Safely quiescing the system is achieved using two methods.
+
+    First, we note that the vast majority of processes don't need to run during
+    suspend. They can be 'frozen'. We therefore implement a refrigerator
+    routine, which processes enter and in which they remain until the cycle is
+    complete. In the vanilla kernel, processes enter the refrigerator via
+    try_to_freeze() invocations at appropriate places.  A process cannot be
+    frozen in any old place. It must not be holding locks that will be needed
+    for writing the image or freezing other processes. For this reason,
+    userspace processes generally enter the refrigerator via the signal handling
+    code, and kernel threads at the place in their event loops where they drop
+    locks and yield to other processes or sleep.
+
+    In this revision of Suspend2, Christoph Lameter's todo list concept is
+    utilised to do the freezing. This means that we replace direct invocation of
+    the refrigerator function with a notifier list implementation, allowing
+    other applications of the hooks.
+
+    The second part of our method for quisescing the system involves freezing
+    the filesystems. We use the standard freeze_bdev and thaw_bdev functions to
+    ensure that all of the user's data is synced to disk before we begin to
+    write the image.
+
+    Quiescing the system works most quickly and reliably when we add one more
+    element to the algorithm: separating the freezing of userspace processes
+    from the freezing of kernel space processes, and doing the filesystem freeze
+    in between. The filesystem freeze needs to be done while kernel threads such
+    as kjournald can still run.At the same time, though, everything will be less
+    racy and run more quickly if we stop userspace submitting more I/O work
+    while we're trying to quiesce.
+
+    Quiescing the system is therefore done in three steps:
+	- Freeze userspace
+	- Freeze filesystems
+	- Freeze kernel threads
+
+    If we need to free memory, we thaw kernel threads and filesystems, but not
+    userspace. We can then free caches without worrying about deadlocks due to
+    swap files being on frozen filesystems or such like.
+
+    b. Ensure enough memory & storage are available.
+
+    We have a number of constraints to meet to be able to successfully suspend
+    and resume.
+
+    First, the image will be written in two parts, described below. One of these
+    parts needs to have an atomic copy made, which of course implies a maximum
+    size of one half of the amount of system memory. The other part ('pageset')
+    is not atomically copied, and can therefore be as large or small as desired.
+
+    Second, we have constraints on the amount of storage available. In these
+    calculations, we may also consider any compression that will be done. The
+    cryptoapi plugin allows the user to configure an expected compression ratio.
+   
+    Third, the user can specify an arbitrary limit on the image size, in
+    megabytes. This limit is treated as a soft limit, so that we don't fail the
+    attempt to suspend if we cannot meet this constraint.
+
+    c. Allocate the required memory and storage space.
+
+    Having done the initial freeze, we determine whether the above constraints
+    are met, and seek to allocate the metadata for the image. If the constraints
+    are not met, or we fail to allocate the required space for the metadata, we
+    seek to free the amount of memory that we calculate is needed and try again.
+    We allow up to four iterations of this loop before aborting the cycle. If we
+    do fail, it should only be because of a bug in Suspend's calculations.
+    
+    These steps are merged together in the prepare_image function, found in
+    prepare_image.c. The functions are merged because of the cyclical nature
+    of the problem of calculating how much memory and storage is needed. Since
+    the data structures containing the information about the image must
+    themselves take memory and use storage, the amount of memory and storage
+    required changes as we prepare the image. Since the changes are not large,
+    only one or two iterations will be required to achieve a solution.
+
+    d. Write the image.
+
+    We previously mentioned the need to create an atomic copy of the data, and
+    the half-of-memory limitation that is implied in this. This limitation is
+    circumvented by dividing the memory to be saved into two parts, called
+    pagesets.
+
+    Pageset2 contains the page cache - the pages on the active and inactive
+    lists. These pages are saved first and reloaded last. While saving these
+    pages, the swapwriter plugin carefully ensures that the work of writing
+    the pages doesn't make the image inconsistent. Pages added to the LRU
+    lists are immediately shot down, and careful accounting for available
+    memory aids debugging. No atomic copy of these pages needs to be made.
+
+    Writing the image requires memory, of course, and at this point we have
+    also not yet suspended the drivers. To avoid the possibility of remaining
+    activity corrupting the image, we allocate a special memory pool. Calls
+    to __alloc_pages and __free_pages_ok are then diverted to use our memory
+    pool. Pages in the memory pool are saved as part of pageset1 regardless of
+    whether or not they are used.
+
+    Once pageset2 has been saved, we suspend the drivers and save the CPU
+    context before making an atomic copy of pageset1, resuming the drivers
+    and saving the atomic copy. After saving the two pagesets, we just need to
+    save our metadata before powering down.
+
+    Having saved pageset2 pages, we can safely overwrite their contents with
+    the atomic copy of pageset1. This is how we manage to overcome the half of
+    memory limitation. Pageset2 is normally far larger than pageset1, and
+    pageset1 is normally much smaller than half of the memory, with the result
+    that pageset2 pages can be safely overwritten with the atomic copy of
+    pageset1. This is where we need to be careful about syncing, however.
+    Pageset2 will probably contain filesystem meta data. If this is overwritten
+    with pageset1 and then a sync occurs, the filesystem will be corrupted -
+    at least until resume time and another sync of the restored data. Since
+    there is a possibility that the user might not resume or (may it never be!)
+    that suspend might oops, we do our utmost to avoid syncing filesystems after
+    copying pageset1.
+
+    e. Power down.
+
+    Powering down uses standard kernel routines. Prior to this, however, we
+    suspend drivers again, ensuring that write caches are flushed.
+
+4.  The method of writing the image.
+
+    Suspend2 contains an internal API which is designed to simplify the
+    implementation of new methods of transforming the image to be written and
+    writing the image itself. In early versions of Suspend2, compression support
+    was inlined in the image writing code, and the data structures and code for
+    managing swap were intertwined with the rest of the code. A number of people
+    had expressed interest in implementing image encryption, and alternative
+    methods of storing the image. This internal API makes that possible by
+    implementing 'plugins'.
+
+    A plugin is a single file which encapsulates the functionality needed
+    to transform a pageset of data (encryption or compression, for example),
+    or to write the pageset to a device. The former type of plugin is called
+    a 'page-transformer', the later a 'writer'.
+
+    Plugins are linked together in pipeline fashion. There may be zero or more
+    page transformers in a pipeline, and there is always exactly one writer.
+    The pipeline follows this pattern:
+
+		---------------------------------
+		|          Suspend2 Core        
+		---------------------------------
+				|
+				|
+		---------------------------------
+		|	Page transformer 1	|
+		---------------------------------
+				|
+				|
+		---------------------------------
+		|	Page transformer 2	|
+		---------------------------------
+				|
+				|
+		---------------------------------
+		|            Writer		|
+		---------------------------------
+
+    During the writing of an image, the core code feeds pages one at a time
+    to the first plugin. This plugin performs whatever transformations it
+    implements on the incoming data, completely consuming the incoming data and
+    feeding output in a similar manner to the next plugin. A plugin may buffer
+    its output.
+
+    During reading, the pipeline works in the reverse direction. The core code
+    calls the first plugin with the address of a buffer which should be filled.
+    (Note that the buffer size is always PAGE_SIZE at this time). This plugin
+    will in turn request data from the next plugin and so on down until the
+    writer is made to read from the stored image.
+
+    Part of definition of the structure of a plugin thus looks like this:
+
+	/* Writing the image proper */
+	int (*write_init) (int stream_number);
+	int (*write_chunk) (char *buffer_start);
+	int (*write_cleanup) (void);
+
+	/* Reading the image proper */
+	int (*read_init) (int stream_number);
+	int (*read_chunk) (char *buffer_start, int sync);
+	int (*read_cleanup) (void);
+
+    It should be noted that the _cleanup routines may be called before the
+    full stream of data has been read or written. While writing the image,
+    the user may (depending upon settings) choose to abort suspending, and
+    if we are in the midst of writing the last portion of the image, a portion
+    of the second pageset may be reread.
+
+    In addition to the above routines for writing the data, all plugins have a
+    number of other routines:
+
+    TYPE indicates whether the plugin is a page transformer or a writer.
+    #define TRANSFORMER_PLUGIN 1
+    #define WRITER_PLUGIN 2
+
+    NAME is the name of the plugin, used in generic messages.
+
+    PLUGIN_LIST is used to link the plugin into the list of all plugins.
+
+    MEMORY_NEEDED returns the number of pages of memory required by the plugin
+    to do its work.
+
+    STORAGE_NEEDED returns the number of pages in the suspend header required
+    to store the plugin's configuration data.
+
+    PRINT_DEBUG_INFO fills a buffer with information to be displayed about the
+    operation or settings of the plugin.
+
+    SAVE_CONFIG_INFO returns a buffer of PAGE_SIZE or smaller (the size is the
+    return code), containing the plugin's configuration info. This information
+    will be written in the image header and restored at resume time. Since this
+    buffer is allocated after the atomic copy of the kernel is made, you don't
+    need to worry about the buffer being freed.
+
+    LOAD_CONFIG_INFO gives the plugin a pointer to the the configuration info
+    which was saved during suspending. Once again, the plugin doesn't need to
+    worry about freeing the buffer. The kernel will be overwritten with the
+    original kernel, so no memory leak will occur.
+
+    OPS contains the operations specific to transformers and writers. These are
+    described below.
+
+    The complete definition of struct suspend_plugin_ops is:
+
+	struct suspend_plugin_ops {
+		/* Functions common to transformers and writers */
+		int type;
+		char *name;
+		struct list_head plugin_list;
+		unsigned long (*memory_needed) (void);
+		unsigned long (*storage_needed) (void);
+		int (*print_debug_info) (char *buffer, int size);
+		int (*save_config_info) (char *buffer);
+		void (*load_config_info) (char *buffer, int len);
+	
+		/* Writing the image proper */
+		int (*write_init) (int stream_number);
+		int (*write_chunk) (char *buffer_start);
+		int (*write_cleanup) (void);
+
+		/* Reading the image proper */
+		int (*read_init) (int stream_number);
+		int (*read_chunk) (char *buffer_start, int sync);
+		int (*read_cleanup) (void);
+
+		union {
+			struct suspend_transformer_ops transformer;
+			struct suspend_writer_ops writer;
+		} ops;
+	};
+
+
+	The operations specific to transformers are few in number:
+
+	struct suspend_transformer_ops {
+		int (*expected_compression) (void);
+		struct list_head transformer_list;
+	};
+
+	Expected compression returns the expected ratio between the amount of
+	data sent to this plugin and the amount of data it passes to the next
+	plugin. The value is used by the core code to calculate the amount of
+	space required to write the image. If the ratio is not achieved, the
+	writer will complain when it runs out of space with data still to
+	write, and the core code will abort the suspend.
+
+	transformer_list links together page transformers, in the order in
+	which they register, which is in turn determined by order in the
+	Makefile.
+	
+	There are many more operations specific to a writer:
+
+	struct suspend_writer_ops {
+
+		long (*storage_available) (void);
+	
+		unsigned long (*storage_allocated) (void);
+		
+		int (*release_storage) (void);
+
+		long (*allocate_header_space) (unsigned long space_requested);
+		int (*allocate_storage) (unsigned long space_requested);
+
+		int (*write_header_init) (void);
+		int (*write_header_chunk) (char *buffer_start, int buffer_size);
+		int (*write_header_cleanup) (void);
+
+		int (*read_header_init) (void);
+		int (*read_header_chunk) (char *buffer_start, int buffer_size);
+		int (*read_header_cleanup) (void);
+
+		int (*prepare_save) (void);
+		int (*post_load) (void);
+
+		int (*parse_image_location) (char *buffer);
+
+		int (*image_exists) (void);
+
+		int (*invalidate_image) (void);
+
+		int (*wait_on_io) (int flush_all);
+
+		struct list_head writer_list;
+	};
+
diff -urN oldtree/Documentation/power/kernel_threads.txt newtree/Documentation/power/kernel_threads.txt
--- oldtree/Documentation/power/kernel_threads.txt	2006-01-28 16:36:00.000000000 +0000
+++ newtree/Documentation/power/kernel_threads.txt	2006-01-28 17:08:36.082750232 +0000
@@ -4,15 +4,15 @@
 Freezer
 
 Upon entering a suspended state the system will freeze all
-tasks. This is done by delivering pseudosignals. This affects
-kernel threads, too. To successfully freeze a kernel thread
-the thread has to check for the pseudosignal and enter the
-refrigerator. Code to do this looks like this:
+tasks. This is done by making all processes execute a notifier.
+This affects kernel threads, too. To successfully freeze a kernel thread
+the thread has to check for the notifications and call the notifier
+chain for the process. Code to do this looks like this:
 
 	do {
 		hub_events();
 		wait_event_interruptible(khubd_wait, !list_empty(&hub_event_list));
-		try_to_freeze();
+		try_todo_list();
 	} while (!signal_pending(current));
 
 from drivers/usb/core/hub.c::hub_thread()
diff -urN oldtree/Documentation/power/suspend2.txt newtree/Documentation/power/suspend2.txt
--- oldtree/Documentation/power/suspend2.txt	1970-01-01 00:00:00.000000000 +0000
+++ newtree/Documentation/power/suspend2.txt	2006-01-28 17:08:36.084749928 +0000
@@ -0,0 +1,631 @@
+	--- Suspend2, version 2.1.9 ---
+
+1.  What is it?
+2.  Why would you want it?
+3.  What do you need to use it?
+4.  How do you use it?
+5.  What do all those entries in /proc/suspend2 do?
+6.  How do you get support?
+7.  I think I've found a bug. What should I do?
+8.  When will XXX be supported?
+9.  How does it work?
+10. Who wrote Suspend2?
+
+1. What is it?
+
+   Imagine you're sitting at your computer, working away. For some reason, you
+   need to turn off your computer for a while - perhaps it's time to go home
+   for the day. When you come back to your computer next, you're going to want
+   to carry on where you left off. Now imagine that you could push a button and
+   have your computer store the contents of its memory to disk and power down.
+   Then, when you next start up your computer, it loads that image back into
+   memory and you can carry on from where you were, just as if you'd never
+   turned the computer off. Far less time to start up, no reopening
+   applications and finding what directory you put that file in yesterday.
+   That's what Suspend2 does.
+
+2. Why would you want it?
+
+   Why wouldn't you want it?
+   
+   Being able to save the state of your system and quickly restore it improves
+   your productivity - you get a useful system in far less time than through
+   the normal boot process.
+   
+3. What do you need to use it?
+
+   a. Kernel Support.
+
+   i) The Suspend2 patch.
+   
+   Suspend2 is part of the Linux Kernel. This version is not part of Linus's
+   2.6 tree at the moment, so you will need to download the kernel source and
+   apply the latest patch. Having done that, enable the appropriate options in
+   make [menu|x]config (under General Setup), compile and install your kernel.
+   Suspend2 works with SMP, Highmem, preemption, x86-32, PPC and mac.
+   x86-64 support is coming.
+
+   Suspend2 patches are available from http://suspend2.net.
+
+   ii) Compression and encryption support.
+
+   As of 2.1.9.2, compression and encryption support are implemented via the
+   cryptoapi. You will therefore want to select any Cryptoapi transforms that
+   you want to use on your image from the Cryptoapi menu while configuring
+   your kernel.
+
+   You can also tell Suspend to write it's image to an encrypted and/or
+   compressed filesystem/swap partition. In that case, you don't need to do
+   anything special for Suspend2 when it comes to kernel configuration.
+
+   iii) Configuring other options.
+
+   While you're configuring your kernel, try to configure as much as possible
+   to build as modules. We recommend this because there are a number of drivers
+   that are still in the process of implementing proper power management
+   support. In those cases, the best way to work around their current lack is
+   to build them as modules and remove the modules while suspending. You might
+   also bug the driver authors to get their support up to speed, or even help!
+
+   b. Storage.
+
+   i) Swap.
+
+   Suspend2 can store the suspend image in your swap partition, a swap file or
+   a combination thereof. Whichever combination you choose, you will probably
+   want to create enough swap space to store the largest image you could have,
+   plus the space you'd normally use for swap. A good rule of thumb would be
+   to calculate the amount of swap you'd want without using Suspend2, and then
+   add the amount of memory you have. This swapspace can be arranged in any way
+   you'd like. It can be in one partition or file, or spread over a number. The
+   only requirement is that they be active when you start a suspend cycle.
+   
+   There is one exception to this requirement. Suspend2 has the ability to turn
+   on one swap file or partition at the start of suspending and turn it back off
+   at the end. If you want to ensure you have enough memory to store a image
+   when your memory is fully used, you might want to make one swap partition or
+   file for 'normal' use, and another for Suspend2 to activate & deactivate
+   automatically. (Further details below).
+
+   ii) Normal files.
+
+   As of 2.1.8.5, Suspend2 includes a 'filewriter'. The filewriter can store
+   your image in a simple file. Since Linux has the idea of everything being
+   a file, this is more powerful than it initially sounds. If, for example,
+   you were to set up a network block device file, you could suspend to a
+   network server. This has been tested and works to a point, but nbd itself
+   isn't stateless enough for our purposes.
+
+   Take extra care when setting up the filewriter. If you just type commands
+   without thinking and then try to suspend, you could cause irreversible
+   corruption on your filesystems! Make sure you have backups. Also, because
+   the filewriter is comparatively new, it's not as well tested as the
+   swapwriter. Be aware that there may be bugs that could cause damage to your
+   data even if you are careful! You have been warned!
+
+   Most people will only want to suspend to a local file. To achieve that, do
+   something along the lines of:
+
+   echo Suspend2 > /suspend-file
+   dd if=/dev/zero bs=1M count=512 >> suspend-file
+
+   This will create a 512MB file called /suspend-file. To get Suspend2 to use
+   it:
+
+   echo /suspend-file > /proc/suspend2/filewriter_target
+
+   Then
+
+   cat /proc/suspend2/resume2
+
+   Put the results of this into your bootloader's configuration (see also step
+   C, below:
+
+   ---EXAMPLE-ONLY-DON'T-COPY-AND-PASTE---
+   # cat /proc/suspend2/resume2
+   file:/dev/hda2:0x1e001
+   
+   In this example, we would edit the append= line of our lilo.conf|menu.lst
+   so that it included:
+
+   resume2=file:/dev/hda2:0x1e001
+   ---EXAMPLE-ONLY-DON'T-COPY-AND-PASTE---
+ 
+   For those who are thinking 'Could I make the file sparse?', the answer is
+   'No!'. At the moment, there is no way for Suspend2 to fill in the holes in
+   a sparse file while suspending. In the longer term (post merge!), I'd like
+   to change things so that the file could be dynamically resized as needed.
+   Right now, however, that's not possible.
+
+   c. Bootloader configuration.
+   
+   Using Suspend2 also requires that you add an extra parameter to 
+   your lilo.conf or equivalent. Here's an example for a swap partition:
+
+   append="resume2=swap:/dev/hda1"
+
+   This would tell Suspend2 that /dev/hda1 is a swap partition you 
+   have. Suspend2 will use the swap signature of this partition as a
+   pointer to your data when you suspend. This means that (in this example)
+   /dev/hda1 doesn't need to be _the_ swap partition where all of your data
+   is actually stored. It just needs to be a swap partition that has a
+   valid signature.
+
+   You don't need to have a swap partition for this purpose. Suspend2
+   can also use a swap file, but usage is a little more complex. Having made
+   your swap file, turn it on and do 
+
+   cat /proc/suspend2/headerlocations
+
+   (this assumes you've already compiled your kernel with Suspend2
+   support and booted it). The results of the cat command will tell you
+   what you need to put in lilo.conf:
+
+   For swap partitions like /dev/hda1, simply use resume2=/dev/hda1.
+   For swapfile `swapfile`, use resume2=swap:/dev/hda2:0x242d@4096.
+
+   If the swapfile changes for any reason (it is moved to a different
+   location, it is deleted and recreated, or the filesystem is
+   defragmented) then you will have to check
+   /proc/suspend2/headerlocations for a new resume_block value.
+
+   Once you've compiled and installed the kernel, adjusted your lilo.conf
+   and rerun lilo, you should only need to reboot for the most basic part
+   of Suspend2 to be ready.
+
+   If you only compile in the swapwriter, or only compile in the filewriter,
+   you don't need to add the "swap:" part of the resume2= parameters above.
+   resume2=/dev/hda2:0x242d@4096 will work just as well.
+
+   d. The hibernate script.
+
+   Since the driver model in 2.6 kernels is still being developed, you may need
+   to do more, however. Users of Suspend2 usually start the process via a script
+   which prepares for the suspend, tells the kernel to do its stuff and then
+   restore things afterwards. This script might involve:
+
+   - Switching to a text console and back if X doesn't like the video card
+     status on resume.
+   - Un/reloading PCMCIA support since it doesn't play well with suspend.
+  
+   Note that you might not be able to unload some drivers if there are 
+   processes using them. You might have to kill off processes that hold
+   devices open. Hint: if your X server accesses an USB mouse, doing a
+   'chvt' to a text console releases the device and you can unload the
+   module.
+
+   Check out the latest script (available on suspend2.net).
+   
+4. How do you use it?
+
+   Once your script is properly set up, you should just be able to start it
+   and everything should go like clockwork. Of course things aren't always
+   that easy out of the box.
+
+   Check out (in the kernel source tree) include/linux/suspend2.h for
+   settings you can use to get detailed information about what suspend is doing.
+   The kernel parameters suspend_act, suspend_dbg and suspend_lvl allow you to
+   set the action and debugging parameters prior to starting a suspend and/or
+   at the lilo prompt before resuming. There is also a nice little program that
+   should be available from suspend2.net which makes it easier to turn these
+   debugging settings on and off. Note that to get any debugging output, you
+   need to enable CONFIG_PM_DEBUG when compiling the kernel.
+
+   A neat feature of Suspend2 is that you can press Escape at any time
+   during suspending, and the process will be aborted.
+   
+   Due to the way suspend works, this means you'll have your system back and
+   perfectly usable almost instantly. The only exception is when it's at
+   the very end of writing the image. Then it will need to reload a small
+   (usually 4-50MBs, depending upon the image characteristics) portion first.
+
+   If you run into problems with resuming, adding the "noresume2" option to
+   the kernel command line will let you skip the resume step and recover your
+   system.
+
+5. What do all those entries in /proc/suspend2 do?
+
+   /proc/suspend2 is the directory which contains files you can use to
+   tune and configure Suspend2 to your liking. The exact contents of
+   the directory will depend upon the version of Suspend2 you're
+   running and the options you selected at compile time. In the following
+   descriptions, names in brackets refer to compile time options.
+   (Note that they're all dependant upon you having selected CONFIG_SUSPEND2
+   in the first place!)
+
+   Since the values of these settings can open potential security risks, they
+   are usually accessible only to the root user. You can, however, enable a
+   compile time option which makes all of these files world-accessible. This
+   should only be done if you trust everyone with shell access to this
+   computer!
+  
+   - all_settings:
+
+   This file provides a convenient way to save and restore all of the other
+   settings in one hit. The contents include binary data, so you'll want to
+   redirect the output to a file:
+
+   cat /proc/suspend2/all_settings > /etc/hibernate/all_settings.conf
+
+   cat /etc/hibernate/all_settings.conf > /proc/suspend2/all_settings
+
+   - debug_info:
+  
+   This file returns information about your configuration that may be helpful
+   in diagnosing problems with suspending.
+
+   - debug_sections (CONFIG_PM_DEBUG):
+
+   This value, together with the console log level, controls what debugging
+   information is displayed. The console log level determines the level of
+   detail, and this value determines what detail is displayed. This value is
+   a bit vector, and the meaning of the bits can be found in the kernel tree
+   in include/linux/suspend2.h. It can be overridden using the kernel's
+   command line option suspend_dbg.
+
+   - default_console_level (CONFIG_PM_DEBUG):
+
+   This determines the value of the console log level at the start of a
+   suspend cycle. If debugging is compiled in, the console log level can be
+   changed during a cycle by pressing the digit keys. Meanings are:
+
+   0: Nice display.
+   1: Nice display plus numerical progress.
+   2: Errors only.
+   3: Low level debugging info.
+   4: Medium level debugging info.
+   5: High level debugging info.
+   6: Verbose debugging info.
+
+   This value can be overridden using the kernel command line option 
+   suspend_lvl.
+
+   - disable_*
+
+   This option can be used to temporarily disable various parts of suspend.
+   Note that these flags can be set by restoring all_settings: If the saved
+   settings don't include any information about how a part of suspend should
+   be configured, that section will be disabled.
+
+   - do_resume:
+
+   When anything is written to this file suspend will attempt to read and
+   restore an image. If there is no image, it will return almost immediately.
+   If an image exists, the echo > will never return. Instead, the original
+   kernel context will be restored and the original echo > do_suspend will
+   return.
+
+   - do_suspend:
+
+   When anything is written to this file, the kernel side of Suspend2 will
+   begin to attempt to write an image to disk and power down. You'll normally
+   want to run the hibernate script instead, to get modules unloaded first.
+
+   - enable_escape:
+
+   Setting this to "1" will enable you abort a suspend by
+   pressing escape, "0" (default) disables this feature. Note that enabling
+   this option means that you cannot initiate a suspend and then walk away
+   from your computer, expecting it to be secure. With feature disabled,
+   you can validly have this expectation once Suspend begins to write the
+   image to disk. (Prior to this point, it is possible that Suspend might
+   about because of failure to freeze all processes or because constraints
+   on its ability to save the image are not met).
+
+   - expected_compression:
+
+   These values allow you to set an expected compression ratio, which Software
+   Suspend will use in calculating whether it meets constraints on the image
+   size. If this expected compression ratio is not attained, the suspend will
+   abort, so it is wise to allow some spare. You can see what compression
+   ratio is achieved in the logs after suspending.
+
+   - filewriter_target:
+
+   Read this value to get the current setting. Write to it to point Suspend
+   at a new storage location for the filewriter. See above for details of how
+   to set up the filewriter.
+
+   - headerlocations:
+
+   This option tells you the resume2= options to use for swap devices you
+   currently have activated. It is particularly useful when you only want to
+   use a swap file to store your image. See above for further details.
+
+   - image_exists:
+
+   Can be used in a script to determine whether a valid image exists at the
+   location currently pointed to by resume2=.  Echoing anything to this entry
+   removes any current image.
+
+   - image_size_limit:
+
+   The maximum size of suspend image written to disk, measured in megabytes
+   (1024*1024).
+
+   - interface_version:
+
+   The value returned by this file can be used by scripts and configuration
+   tools to determine what entries should be looked for. The value is
+   incremented whenever an entry in /proc/suspend2 is obsoleted or 
+   added.
+
+   - last_result:
+
+   The result of the last suspend, as defined in
+   include/linux/suspend-debug.h with the values SUSPEND_ABORTED to
+   SUSPEND_KEPT_IMAGE. This is a bitmask.
+
+   - log_everything (CONFIG_PM_DEBUG):
+
+   Setting this option results in all messages printed being logged. Normally,
+   only a subset are logged, so as to not slow the process and not clutter the
+   logs. Useful for debugging. It can be toggled during a cycle by pressing
+   'L'.
+
+   - pause_between_steps (CONFIG_PM_DEBUG):
+
+   This option is used during debugging, to make Suspend2 pause between
+   each step of the process. It is ignored when the nice display is on.
+
+   - powerdown_method:
+
+   Used to select a method by which Suspend2 should powerdown after writing the
+   image. Currently:
+
+   3: Attempt to enter Suspend-to-ram.
+   4: Attempt to enter ACPI S4 mode.
+   5: Normal power down.
+
+   Note that these options are highly dependant upon your hardware & software.
+
+   - progressbar_granularity_limit:
+
+   This option can be used to limit the granularity of the progress bar
+   displayed with a bootsplash screen. The value is the maximum number of
+   steps. That is, 10 will make the progress bar jump in 10% increments.
+
+   - reboot:
+
+   This option causes Suspend2 to reboot rather than powering down
+   at the end of saving an image. It can be toggled during a cycle by pressing
+   'R'.
+
+   - resume_commandline:
+
+   This entry can be read after resuming to see the commandline that was used
+   when resuming began. You might use this to set up two bootloader entries
+   that are the same apart from the fact that one includes a extra append=
+   argument "at_work=1". You could then grep resume_commandline in your
+   post-resume scripts and configure networking (for example) differently
+   depending upon whether you're at home or work. resume_commandline can be
+   set to arbitrary text if you wish to remove sensitive contents.
+
+   - swapfile:
+
+   This entry is used to specify the swapfile or partition that
+   Suspend2 will attempt to swapon/swapoff automatically. Thus, if
+   I normally use /dev/hda1 for swap, and want to use /dev/hda2 for specifically
+   for my suspend image, I would
+  
+   echo /dev/hda2 > /proc/suspend2/swapfile
+
+   /dev/hda2 would then be automatically swapon'd and swapoff'd. Note that the
+   swapon and swapoff occur while other processes are frozen (including kswapd)
+   so this swap file will not be used up when attempting to free memory. The
+   parition/file is also given the highest priority, so other swapfiles/partitions
+   will only be used to save the image when this one is filled.
+
+   The value of this file is used by headerlocations along with any currently
+   activated swapfiles/partitions.
+
+   - toggle_process_nofreeze
+
+   This entry can be used to toggle the NOFREEZE flag on a process, to allow it
+   to run during Suspending. It should be used with extreme caution. There are
+   strict limitations on what a process running during suspend can do. This is
+   really only intended for use by Suspend's helpers (userui in particular).
+
+   - userui_program
+
+   This entry is used to tell Suspend what userspace program to use for
+   providing a user interface while suspending. The program uses a netlink
+   socket to pass messages back and forward to the kernel, allowing all of the
+   functions formerly implemented in the kernel user interface components.
+
+   - version:
+  
+   The version of suspend you have compiled into the currently running kernel.
+
+6. How do you get support?
+
+   Glad you asked. Suspend2 is being actively maintained and supported
+   by Nigel (the guy doing most of the kernel coding at the moment), Bernard
+   (who maintains the hibernate script and userspace user interface components)
+   and its users.
+
+   Resources availble include HowTos, FAQs and a Wiki, all available via
+   suspend2.net.  You can find the mailing lists there.
+
+7. I think I've found a bug. What should I do?
+
+   By far and a way, the most common problems people have with suspend2
+   related to drivers not having adequate power management support. In this
+   case, it is not a bug with suspend2, but we can still help you. As we
+   mentioned above, such issues can usually be worked around by building the
+   functionality as modules and unloading them while suspending. Please visit
+   the Wiki for up-to-date lists of known issues and work arounds.
+
+   If this information doesn't help, try running:
+
+   hibernate --bug-report
+
+   ..and sending the output to the users mailing list.
+
+   Good information on how to provide us with useful information from an
+   oops is found in the file REPORTING-BUGS, in the top level directory
+   of the kernel tree. If you get an oops, please especially note the
+   information about running what is printed on the screen through ksymoops.
+   The raw information is useless.
+
+8. When will XXX be supported?
+
+   Suspend2 currently lacks support for x86-64. It is work in progress, but
+   hasn't been made a great priority because debugging is difficult (Nigel
+   doesn't have access to the hardware). 64GB Highmem and discontig-mem are
+   also not supported at the moment.
+
+   Patches for the other items (and anything that's been missed) are welcome. 
+   Please send to the list.
+
+9. How does it work?
+
+   Suspend2 does its work in a number of steps.
+
+   a. Freezing system activity.
+
+   The first main stage in suspending is to stop all other activity. This is
+   achieved in stages. Processes are considered in fours groups, which we will
+   describe in reverse order for clarity's sake: Threads with the PF_NOFREEZE
+   flag, kernel threads without this flag, userspace processes with the
+   PF_SYNCTHREAD flag and all other processes. The first set (PF_NOFREEZE) are
+   untouched by the refrigerator code. They are allowed to run during suspending
+   and resuming, and are used to support user interaction, storage access or the
+   like. Other kernel threads (those unneeded while suspending) are frozen last.
+   This leaves us with userspace processes that need to be frozen. When a
+   process enters one of the *_sync system calls, we set a PF_SYNCTHREAD flag on
+   that process for the duration of that call. Processes that have this flag are
+   frozen after processes without it, so that we can seek to ensure that dirty
+   data is synced to disk as quickly as possible in a situation where other
+   processes may be submitting writes at the same time. Freezing the processes
+   that are submitting data stops new I/O from being submitted. Syncthreads can
+   then cleanly finish their work. So the order is:
+
+   - Userspace processes without PF_SYNCTHREAD or PF_NOFREEZE;
+   - Userspace processes with PF_SYNCTHREAD (they won't have NOFREEZE);
+   - Kernel processes without PF_NOFREEZE.
+
+   b. Eating memory.
+
+   For a successful suspend, you need to have enough disk space to store the
+   image and enough memory for the various limitations of Suspend2's
+   algorithm. You can also specify a maximum image size. In order to attain
+   to those constraints, Suspend2 may 'eat' memory. If, after freezing
+   processes, the constraints aren't met, Suspend2 will thaw all the
+   other processes and begin to eat memory until its calculations indicate
+   the constraints are met. It will then freeze processes again and recheck
+   its calculations.
+
+   c. Allocation of storage.
+
+   Next, Suspend2 allocates the storage that will be used to save
+   the image.
+
+   The core of Suspend2 knows nothing about how or where pages are stored. We
+   therefore request the active writer (remember you might have compiled in
+   more than one!) to allocate enough storage for our expect image size. If
+   this request cannot be fulfilled, we eat more memory and try again. If it
+   is fulfiled, we seek to allocate additional storage, just in case our
+   expected compression ratio (if any) isn't achieved. This time, however, we
+   just continue if we can't allocate enough storage.
+
+   If these calls to our writer change the characteristics of the image such
+   that we haven't allocated enough memory, we also loop. (The writer may well
+   need to allocate space for its storage information).
+
+   d. Write the first part of the image.
+
+   Suspend2 stores the image in two sets of pages called 'pagesets'.
+   Pageset 2 contains pages on the active and inactive lists; essentially
+   the page cache. Pageset 1 contains all other pages, including the kernel.
+   We use two pagesets for one important reason: We need to make an atomic copy
+   of the kernel to ensure consistency of the image. Without a second pageset,
+   that would limit us to an image that was at most half the amount of memory
+   available. Using two pagesets allows us to store a full image. Since pageset
+   2 pages won't be needed in saving pageset 1, we first save pageset 2 pages.
+   We can then make our atomic copy of the remaining pages using both pageset 2
+   pages and any other pages that are free. While saving both pagesets, we are
+   careful not to corrupt the image. Among other things, we use lowlevel block
+   I/O routines that don't change the pagecache contents.
+
+   The next step, then, is writing pageset 2.
+
+   e. Suspending drivers and storing processor context.
+
+   Having written pageset2, Suspend2 calls the power management functions to
+   notify drivers of the suspend, and saves the processor state in preparation
+   for the atomic copy of memory we are about to make.
+
+   f. Atomic copy.
+
+   At this stage, everything else but the Suspend2 code is halted. Processes
+   are frozen or idling, drivers are quiesced and have stored (ideally and where
+   necessary) their configuration in memory we are about to atomically copy.
+   In our lowlevel architecture specific code, we have saved the CPU state.
+   We can therefore now do our atomic copy before resuming drivers etc.
+
+   g. Save the atomic copy (pageset 1).
+
+   Suspend can then write the atomic copy of the remaining pages. Since we
+   have copied the pages into other locations, we can continue to use the
+   normal block I/O routines without fear of corruption our image.
+
+   f. Save the suspend header.
+
+   Nearly there! We save our settings and other parameters needed for
+   reloading pageset 1 in a 'suspend header'. We also tell our writer to
+   serialise its data at this stage, so that it can reread the image at resume
+   time. Note that the writer can write this data in any format - in the case
+   of the swapwriter, for example, it splits header pages in 4092 byte blocks,
+   using the last four bytes to link pages of data together. This is completely
+   transparent to the core.
+
+   g. Set the image header.
+
+   Finally, we edit the header at our resume2= location. The signature is
+   changed by the writer to reflect the fact that an image exists, and to point
+   to the start of that data if necessary (swapwriter).
+
+   h. Power down.
+
+   Or reboot if we're debugging and the appropriate option is selected.
+
+   Whew!
+
+   Reloading the image.
+   --------------------
+
+   Reloading the image is essentially the reverse of all the above. We load
+   our copy of pageset 1, being careful to choose locations that aren't going
+   to be overwritten as we copy it back (We start very early in the boot
+   process, so there are no other processes to quiesce here). We then copy
+   pageset 1 back to its original location in memory and restore the process
+   context. We are now running with the original kernel. Next, we reload the
+   pageset 2 pages, free the memory and swap used by Suspend2, restore
+   the pageset header and restart processes. Sounds easy in comparison to
+   suspending, doesn't it!
+
+   There is of course more to Suspend2 than this, but this explanation
+   should be a good start. If there's interest, I'll write further
+   documentation on range pages and the low level I/O.
+
+10. Who wrote Suspend2?
+
+   (Answer based on the writings of Florent Chabaud, credits in files and
+   Nigel's limited knowledge; apologies to anyone missed out!)
+
+   The main developers of Suspend2 have been...
+
+   Gabor Kuti
+   Pavel Machek
+   Florent Chabaud
+   Bernard Blackham
+   Nigel Cunningham
+
+   They have been aided in their efforts by a host of hundreds, if not thousands
+   of testers and people who have submitted bug fixes & suggestions. Of special
+   note are the efforts of Michael Frank, who had his computers repetitively
+   suspend and resume for literally tens of thousands of cycles and developed
+   scripts to stress the system and test Suspend2 far beyond the point
+   most of us (Nigel included!) would consider testing. His efforts have
+   contributed as much to Suspend2 as any of the names above.
diff -urN oldtree/Documentation/power/swsusp.txt newtree/Documentation/power/swsusp.txt
--- oldtree/Documentation/power/swsusp.txt	2006-01-28 16:36:00.000000000 +0000
+++ newtree/Documentation/power/swsusp.txt	2006-01-28 17:08:36.084749928 +0000
@@ -130,7 +130,8 @@
 website, and not to the Linux Kernel Mailing List. We are working
 toward merging suspend2 into the mainline kernel.
 
-Q: A kernel thread must voluntarily freeze itself (call 'refrigerator').
+Q: A kernel thread must work on the todo list (call 'run_todo_list')
+to enter the refrigerator.
 I found some kernel threads that don't do it, and they don't freeze
 so the system can't sleep. Is this a known behavior?
 
@@ -139,7 +140,7 @@
 should be held at that point and it must be safe to sleep there), and
 add:
 
-       try_to_freeze();
+       try_todo_list();
 
 If the thread is needed for writing the image to storage, you should
 instead set the PF_NOFREEZE process flag when creating the thread (and
diff -urN oldtree/arch/arm/kernel/signal.c newtree/arch/arm/kernel/signal.c
--- oldtree/arch/arm/kernel/signal.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/arch/arm/kernel/signal.c	2006-01-28 17:08:36.085749776 +0000
@@ -637,7 +637,7 @@
 	if (!user_mode(regs))
 		return 0;
 
-	if (try_to_freeze())
+	if (try_todo_list())
 		goto no_signal;
 
 	if (current->ptrace & PT_SINGLESTEP)
diff -urN oldtree/arch/arm/mm/init.c newtree/arch/arm/mm/init.c
--- oldtree/arch/arm/mm/init.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/arch/arm/mm/init.c	2006-01-28 17:08:36.086749624 +0000
@@ -17,6 +17,7 @@
 #include <linux/mman.h>
 #include <linux/nodemask.h>
 #include <linux/initrd.h>
+#include <linux/suspend.h>
 
 #include <asm/mach-types.h>
 #include <asm/hardware.h>
@@ -86,6 +87,11 @@
 	printk("%d pages swap cached\n", cached);
 }
 
+int page_is_ram(int pfn)
+{
+	return pfn_valid(pfn);
+}
+
 static inline pmd_t *pmd_off(pgd_t *pgd, unsigned long virt)
 {
 	return pmd_offset(pgd, virt);
@@ -660,6 +666,15 @@
 		 */
 		sysctl_overcommit_memory = OVERCOMMIT_ALWAYS;
 	}
+#ifdef CONFIG_SUSPEND2
+	{
+		unsigned long addr;
+		for (addr = &__nosave_begin; addr < &__nosave_end; 
+		     addr += PAGE_SIZE) {
+			SetPageNosave(virt_to_page(addr));
+		}
+	}
+#endif
 }
 
 void free_initmem(void)
diff -urN oldtree/arch/frv/kernel/signal.c newtree/arch/frv/kernel/signal.c
--- oldtree/arch/frv/kernel/signal.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/arch/frv/kernel/signal.c	2006-01-28 17:08:36.086749624 +0000
@@ -535,7 +535,7 @@
 	if (!user_mode(regs))
 		return 1;
 
-	if (try_to_freeze())
+	if (try_todo_list())
 		goto no_signal;
 
 	if (!oldset)
diff -urN oldtree/arch/h8300/kernel/signal.c newtree/arch/h8300/kernel/signal.c
--- oldtree/arch/h8300/kernel/signal.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/arch/h8300/kernel/signal.c	2006-01-28 17:08:36.087749472 +0000
@@ -516,7 +516,7 @@
 	if ((regs->ccr & 0x10))
 		return 1;
 
-	if (try_to_freeze())
+	if (try_todo_list())
 		goto no_signal;
 
 	current->thread.esp0 = (unsigned long) regs;
diff -urN oldtree/arch/i386/kernel/io_apic.c newtree/arch/i386/kernel/io_apic.c
--- oldtree/arch/i386/kernel/io_apic.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/arch/i386/kernel/io_apic.c	2006-01-28 17:08:36.089749168 +0000
@@ -578,7 +578,7 @@
 
 	for ( ; ; ) {
 		time_remaining = schedule_timeout_interruptible(time_remaining);
-		try_to_freeze();
+		try_todo_list();
 		if (time_after(jiffies,
 				prev_balance_time+balanced_irq_interval)) {
 			preempt_disable();
diff -urN oldtree/arch/i386/kernel/signal.c newtree/arch/i386/kernel/signal.c
--- oldtree/arch/i386/kernel/signal.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/arch/i386/kernel/signal.c	2006-01-28 17:08:36.089749168 +0000
@@ -615,7 +615,7 @@
 	if (!user_mode(regs))
 		return 1;
 
-	if (try_to_freeze())
+	if (try_todo_list())
 		goto no_signal;
 
 	if (!oldset)
diff -urN oldtree/arch/i386/kernel/smp.c newtree/arch/i386/kernel/smp.c
--- oldtree/arch/i386/kernel/smp.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/arch/i386/kernel/smp.c	2006-01-28 17:08:36.090749016 +0000
@@ -455,7 +455,7 @@
 }
 EXPORT_SYMBOL(flush_tlb_page);
 
-static void do_flush_tlb_all(void* info)
+void do_flush_tlb_all(void* info)
 {
 	unsigned long cpu = smp_processor_id();
 
diff -urN oldtree/arch/i386/kernel/time.c newtree/arch/i386/kernel/time.c
--- oldtree/arch/i386/kernel/time.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/arch/i386/kernel/time.c	2006-01-28 17:08:36.091748864 +0000
@@ -372,7 +372,8 @@
 	mod_timer(&sync_cmos_timer, jiffies + 1);
 }
 
-static long clock_cmos_diff, sleep_start;
+static long clock_cmos_diff;
+static unsigned long sleep_start;
 
 static struct timer_opts *last_timer;
 static int timer_suspend(struct sys_device *dev, pm_message_t state)
@@ -380,9 +381,11 @@
 	/*
 	 * Estimate time zone so that set_time can update the clock
 	 */
-	clock_cmos_diff = -get_cmos_time();
+	long cmos_time = __get_cmos_time();
+	
+	clock_cmos_diff = -cmos_time;
 	clock_cmos_diff += get_seconds();
-	sleep_start = get_cmos_time();
+	sleep_start = cmos_time;
 	last_timer = cur_timer;
 	cur_timer = &timer_none;
 	if (last_timer->suspend)
@@ -395,14 +398,16 @@
 	unsigned long flags;
 	unsigned long sec;
 	unsigned long sleep_length;
+	unsigned long cmos_time;
 
 #ifdef CONFIG_HPET_TIMER
 	if (is_hpet_enabled())
 		hpet_reenable();
 #endif
+	cmos_time = get_cmos_time();
+	sec = cmos_time + clock_cmos_diff;
+	sleep_length = (cmos_time - sleep_start) * HZ;
 	setup_pit_timer();
-	sec = get_cmos_time() + clock_cmos_diff;
-	sleep_length = (get_cmos_time() - sleep_start) * HZ;
 	write_seqlock_irqsave(&xtime_lock, flags);
 	xtime.tv_sec = sec;
 	xtime.tv_nsec = 0;
diff -urN oldtree/arch/i386/mm/init.c newtree/arch/i386/mm/init.c
--- oldtree/arch/i386/mm/init.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/arch/i386/mm/init.c	2006-01-28 17:08:36.092748712 +0000
@@ -29,6 +29,7 @@
 #include <linux/efi.h>
 #include <linux/memory_hotplug.h>
 #include <linux/initrd.h>
+#include <linux/suspend.h>
 
 #include <asm/processor.h>
 #include <asm/system.h>
@@ -48,6 +49,7 @@
 unsigned long highstart_pfn, highend_pfn;
 
 static int noinline do_test_wp_bit(void);
+int bad_ppro;
 
 /*
  * Creates a middle page table and puts a pointer to it in the
@@ -279,9 +281,12 @@
 {
 	if (page_is_ram(pfn) && !(bad_ppro && page_kills_ppro(pfn))) {
 		ClearPageReserved(page);
+		ClearPageNosave(page);
 		free_new_highpage(page);
-	} else
+	} else {
 		SetPageReserved(page);
+		SetPageNosave(page);
+	}
 }
 
 static int add_one_highpage_hotplug(struct page *page, unsigned long pfn)
@@ -384,7 +389,7 @@
 #endif
 }
 
-#ifdef CONFIG_SOFTWARE_SUSPEND
+#ifdef CONFIG_PM
 /*
  * Swap suspend & friends need this for resume because things like the intel-agp
  * driver might have split up a kernel 4MB mapping.
@@ -570,7 +575,7 @@
 	extern int ppro_with_ram_bug(void);
 	int codesize, reservedpages, datasize, initsize;
 	int tmp;
-	int bad_ppro;
+	struct page *tmp_page;
 
 #ifdef CONFIG_FLATMEM
 	if (!mem_map)
@@ -601,12 +606,23 @@
 	totalram_pages += free_all_bootmem();
 
 	reservedpages = 0;
-	for (tmp = 0; tmp < max_low_pfn; tmp++)
-		/*
-		 * Only count reserved RAM pages
-		 */
-		if (page_is_ram(tmp) && PageReserved(pfn_to_page(tmp)))
-			reservedpages++;
+	for (tmp = 0; tmp < max_low_pfn; tmp++) {
+		if (page_is_ram(tmp)) {
+			/*
+			 * Only count reserved RAM pages
+			 */
+			if (PageReserved(pfn_to_page(tmp)))
+				reservedpages++;
+		} else
+			/*
+			 * Non-RAM pages are always nosave
+			 */
+			SetPageNosave(pfn_to_page(tmp));
+	}
+
+	for (tmp_page = virt_to_page(&__nosave_begin);
+			tmp_page < virt_to_page(&__nosave_end); tmp_page++)
+		SetPageNosave(tmp_page);
 
 	set_highmem_pages_init(bad_ppro);
 
@@ -727,6 +743,7 @@
 	addr = (unsigned long)(&__init_begin);
 	for (; addr < (unsigned long)(&__init_end); addr += PAGE_SIZE) {
 		ClearPageReserved(virt_to_page(addr));
+		ClearPageNosave(virt_to_page(addr));
 		set_page_count(virt_to_page(addr), 1);
 		memset((void *)addr, 0xcc, PAGE_SIZE);
 		free_page(addr);
@@ -742,6 +759,7 @@
 		printk (KERN_INFO "Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
 	for (; start < end; start += PAGE_SIZE) {
 		ClearPageReserved(virt_to_page(start));
+		ClearPageNosave(virt_to_page(start));
 		set_page_count(virt_to_page(start), 1);
 		free_page(start);
 		totalram_pages++;
diff -urN oldtree/arch/m32r/kernel/signal.c newtree/arch/m32r/kernel/signal.c
--- oldtree/arch/m32r/kernel/signal.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/arch/m32r/kernel/signal.c	2006-01-28 17:08:36.092748712 +0000
@@ -370,7 +370,7 @@
 	if (!user_mode(regs))
 		return 1;
 
-	if (try_to_freeze()) 
+	if (try_todo_list())
 		goto no_signal;
 
 	if (!oldset)
diff -urN oldtree/arch/mips/kernel/irixsig.c newtree/arch/mips/kernel/irixsig.c
--- oldtree/arch/mips/kernel/irixsig.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/arch/mips/kernel/irixsig.c	2006-01-28 17:08:36.093748560 +0000
@@ -185,7 +185,7 @@
 	if (!user_mode(regs))
 		return 1;
 
-	if (try_to_freeze())
+	if (try_todo_list())
 		goto no_signal;
 
 	if (!oldset)
diff -urN oldtree/arch/mips/kernel/signal32.c newtree/arch/mips/kernel/signal32.c
--- oldtree/arch/mips/kernel/signal32.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/arch/mips/kernel/signal32.c	2006-01-28 17:08:36.094748408 +0000
@@ -822,7 +822,7 @@
 	if (!user_mode(regs))
 		return 1;
 
-	if (try_to_freeze())
+	if (try_todo_list())
 		goto no_signal;
 
 	if (!oldset)
diff -urN oldtree/arch/powerpc/kernel/signal_32.c newtree/arch/powerpc/kernel/signal_32.c
--- oldtree/arch/powerpc/kernel/signal_32.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/arch/powerpc/kernel/signal_32.c	2006-01-28 17:08:36.095748256 +0000
@@ -1185,7 +1185,7 @@
 	int signr, ret;
 
 #ifdef CONFIG_PPC32
-	if (try_to_freeze()) {
+	if (try_todo_list()) {
 		signr = 0;
 		if (!signal_pending(current))
 			goto no_signal;
diff -urN oldtree/arch/ppc/mm/init.c newtree/arch/ppc/mm/init.c
--- oldtree/arch/ppc/mm/init.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/arch/ppc/mm/init.c	2006-01-28 17:08:36.096748104 +0000
@@ -32,6 +32,7 @@
 #include <linux/highmem.h>
 #include <linux/initrd.h>
 #include <linux/pagemap.h>
+#include <linux/suspend.h>
 
 #include <asm/pgalloc.h>
 #include <asm/prom.h>
@@ -144,6 +145,7 @@
 
 	while (start < end) {
 		ClearPageReserved(virt_to_page(start));
+		ClearPageNosave(virt_to_page(start));
 		set_page_count(virt_to_page(start), 1);
 		free_page(start);
 		cnt++;
@@ -176,6 +178,7 @@
 
 	for (; start < end; start += PAGE_SIZE) {
 		ClearPageReserved(virt_to_page(start));
+		ClearPageNosave(virt_to_page(start));
 		set_page_count(virt_to_page(start), 1);
 		free_page(start);
 		totalram_pages++;
@@ -411,8 +414,10 @@
 	/* if we are booted from BootX with an initial ramdisk,
 	   make sure the ramdisk pages aren't reserved. */
 	if (initrd_start) {
-		for (addr = initrd_start; addr < initrd_end; addr += PAGE_SIZE)
+		for (addr = initrd_start; addr < initrd_end; addr += PAGE_SIZE) {
 			ClearPageReserved(virt_to_page(addr));
+			ClearPageNosave(virt_to_page(addr));
+		}
 	}
 #endif /* CONFIG_BLK_DEV_INITRD */
 
@@ -421,17 +426,27 @@
 	if ( rtas_data )
 		for (addr = (ulong)__va(rtas_data);
 		     addr < PAGE_ALIGN((ulong)__va(rtas_data)+rtas_size) ;
-		     addr += PAGE_SIZE)
+		     addr += PAGE_SIZE) {
 			SetPageReserved(virt_to_page(addr));
+			SetPageNosave(virt_to_page(addr));
+		}
 #endif
 #ifdef CONFIG_PPC_PMAC
-	if (agp_special_page)
+	if (agp_special_page) {
 		SetPageReserved(virt_to_page(agp_special_page));
+		SetPageNosave(virt_to_page(agp_special_page));
+	}
 #endif
 	for (addr = PAGE_OFFSET; addr < (unsigned long)high_memory;
 	     addr += PAGE_SIZE) {
 		if (!PageReserved(virt_to_page(addr)))
 			continue;
+		/*
+		 * Mark nosave pages
+		 */
+		if (addr >= (void *)&__nosave_begin && addr < (void *)&__nosave_end)
+			SetPageNosave(virt_to_page(addr));
+
 		if (addr < (ulong) etext)
 			codepages++;
 		else if (addr >= (unsigned long)&__init_begin
@@ -449,6 +464,7 @@
 			struct page *page = mem_map + pfn;
 
 			ClearPageReserved(page);
+			ClearPageNosave(page);
 			set_page_count(page, 1);
 			__free_page(page);
 			totalhigh_pages++;
diff -urN oldtree/arch/ppc/platforms/pmac_feature.c newtree/arch/ppc/platforms/pmac_feature.c
--- oldtree/arch/ppc/platforms/pmac_feature.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/arch/ppc/platforms/pmac_feature.c	2006-01-28 17:08:36.097747952 +0000
@@ -2301,7 +2301,10 @@
 	},
 	{	"PowerBook5,1",			"PowerBook G4 17\"",
 		PMAC_TYPE_UNKNOWN_INTREPID,	intrepid_features,
-		PMAC_MB_HAS_FW_POWER | PMAC_MB_MOBILE,
+		PMAC_MB_HAS_FW_POWER | PMAC_MB_MOBILE
+#ifdef CONFIG_SOFTWARE_REPLACE_SLEEP
+		| PMAC_MB_CAN_SLEEP,
+#endif
 	},
 	{	"PowerBook5,2",			"PowerBook G4 15\"",
 		PMAC_TYPE_UNKNOWN_INTREPID,	intrepid_features,
diff -urN oldtree/arch/sh/kernel/signal.c newtree/arch/sh/kernel/signal.c
--- oldtree/arch/sh/kernel/signal.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/arch/sh/kernel/signal.c	2006-01-28 17:08:36.098747800 +0000
@@ -578,7 +578,7 @@
 	if (!user_mode(regs))
 		return 1;
 
-	if (try_to_freeze())
+	if (try_todo_list())
 		goto no_signal;
 
 	if (!oldset)
diff -urN oldtree/arch/sh64/kernel/signal.c newtree/arch/sh64/kernel/signal.c
--- oldtree/arch/sh64/kernel/signal.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/arch/sh64/kernel/signal.c	2006-01-28 17:08:36.099747648 +0000
@@ -696,7 +696,7 @@
 	if (!user_mode(regs))
 		return 1;
 
-	if (try_to_freeze())
+	if (try_todo_list())
 		goto no_signal;
 
 	if (!oldset)
diff -urN oldtree/arch/x86_64/kernel/asm-offsets.c newtree/arch/x86_64/kernel/asm-offsets.c
--- oldtree/arch/x86_64/kernel/asm-offsets.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/arch/x86_64/kernel/asm-offsets.c	2006-01-28 17:08:36.099747648 +0000
@@ -61,8 +61,10 @@
 	       offsetof (struct rt_sigframe32, uc.uc_mcontext));
 	BLANK();
 #endif
+#ifdef CONFIG_PM
 	DEFINE(pbe_address, offsetof(struct pbe, address));
 	DEFINE(pbe_orig_address, offsetof(struct pbe, orig_address));
 	DEFINE(pbe_next, offsetof(struct pbe, next));
+#endif
 	return 0;
 }
diff -urN oldtree/arch/x86_64/kernel/e820.c newtree/arch/x86_64/kernel/e820.c
--- oldtree/arch/x86_64/kernel/e820.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/arch/x86_64/kernel/e820.c	2006-01-28 17:08:36.100747496 +0000
@@ -186,6 +186,23 @@
 	return end_pfn;	
 }
 
+int page_is_ram(unsigned long pagenr)
+{
+	unsigned long start = pagenr << PAGE_SHIFT;
+	int i;
+	for (i = 0; i < e820.nr_map; i++) {
+		struct e820entry *ei = &e820.map[i];
+
+		if (ei->addr+ei->size <= start || 
+		    ei->addr >= (start + PAGE_SIZE))
+			continue;
+
+		return (ei->type != E820_RAM);
+	}
+
+	return 0;
+}
+
 /* 
  * Compute how much memory is missing in a range.
  * Unlike the other functions in this file the arguments are in page numbers.
diff -urN oldtree/arch/x86_64/kernel/signal.c newtree/arch/x86_64/kernel/signal.c
--- oldtree/arch/x86_64/kernel/signal.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/arch/x86_64/kernel/signal.c	2006-01-28 17:08:36.101747344 +0000
@@ -443,7 +443,7 @@
 	if (!user_mode(regs))
 		return 1;
 
-	if (try_to_freeze())
+	if (try_todo_list())
 		goto no_signal;
 
 	if (!oldset)
diff -urN oldtree/arch/x86_64/kernel/suspend.c newtree/arch/x86_64/kernel/suspend.c
--- oldtree/arch/x86_64/kernel/suspend.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/arch/x86_64/kernel/suspend.c	2006-01-28 17:08:36.101747344 +0000
@@ -13,6 +13,7 @@
 #include <asm/proto.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
+#include <asm/i387.h>
 
 struct saved_context saved_context;
 
@@ -22,6 +23,8 @@
 unsigned long saved_context_r12, saved_context_r13, saved_context_r14, saved_context_r15;
 unsigned long saved_context_eflags;
 
+void fix_processor_context(void);
+
 void __save_processor_state(struct saved_context *ctxt)
 {
 	kernel_fpu_begin();
@@ -141,7 +144,7 @@
 
 }
 
-#ifdef CONFIG_SOFTWARE_SUSPEND
+#if defined(CONFIG_SOFTWARE_SUSPEND) || defined(CONFIG_SUSPEND2)
 /* Defined in arch/x86_64/kernel/suspend_asm.S */
 extern int restore_image(void);
 
@@ -220,4 +223,9 @@
 	restore_image();
 	return 0;
 }
+
+int suspend2_mapping_prepare(void)
+{
+	return set_up_temporary_mappings();
+}
 #endif /* CONFIG_SOFTWARE_SUSPEND */
diff -urN oldtree/arch/x86_64/kernel/time.c newtree/arch/x86_64/kernel/time.c
--- oldtree/arch/x86_64/kernel/time.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/arch/x86_64/kernel/time.c	2006-01-28 17:08:36.103747040 +0000
@@ -509,11 +509,56 @@
 	return cycles_2_ns(a);
 }
 
+unsigned long __get_cmos_time(void)
+{
+	unsigned int year, mon, day, hour, min, sec;
+
+	/*
+	 * Do we need the spinlock in here too?
+	 *
+	 * If we're called directly (not via get_cmos_time),
+	 * we're in the middle of a sysdev suspend/resume
+	 * and interrupts are disabled, so this 
+	 * should be safe without any locking.
+	 * 				-- NC
+	 */
+
+	do {
+		sec = CMOS_READ(RTC_SECONDS);
+		min = CMOS_READ(RTC_MINUTES);
+		hour = CMOS_READ(RTC_HOURS);
+		day = CMOS_READ(RTC_DAY_OF_MONTH);
+		mon = CMOS_READ(RTC_MONTH);
+		year = CMOS_READ(RTC_YEAR);
+	} while (sec != CMOS_READ(RTC_SECONDS));
+
+	/*
+	 * We know that x86-64 always uses BCD format, no need to check the config
+	 * register.
+	 */
+
+	BCD_TO_BIN(sec);
+	BCD_TO_BIN(min);
+	BCD_TO_BIN(hour);
+	BCD_TO_BIN(day);
+	BCD_TO_BIN(mon);
+	BCD_TO_BIN(year);
+
+	/*
+	 * This will work up to Dec 31, 2069.
+	 */
+
+	if ((year += 1900) < 1970)
+		year += 100;
+
+	return mktime(year, mon, day, hour, min, sec);
+}
+
 unsigned long get_cmos_time(void)
 {
-	unsigned int timeout, year, mon, day, hour, min, sec;
+	unsigned int timeout;
 	unsigned char last, this;
-	unsigned long flags;
+	unsigned long flags, result;
 
 /*
  * The Linux interpretation of the CMOS clock register contents: When the
@@ -534,39 +579,10 @@
 		timeout--;
 	}
 
-/*
- * Here we are safe to assume the registers won't change for a whole second, so
- * we just go ahead and read them.
-	 */
-
-		sec = CMOS_READ(RTC_SECONDS);
-		min = CMOS_READ(RTC_MINUTES);
-		hour = CMOS_READ(RTC_HOURS);
-		day = CMOS_READ(RTC_DAY_OF_MONTH);
-		mon = CMOS_READ(RTC_MONTH);
-		year = CMOS_READ(RTC_YEAR);
-
+	result =  __get_cmos_time();
 	spin_unlock_irqrestore(&rtc_lock, flags);
 
-/*
- * We know that x86-64 always uses BCD format, no need to check the config
- * register.
- */
-
-	    BCD_TO_BIN(sec);
-	    BCD_TO_BIN(min);
-	    BCD_TO_BIN(hour);
-	    BCD_TO_BIN(day);
-	    BCD_TO_BIN(mon);
-	    BCD_TO_BIN(year);
-
-/*
- * x86-64 systems only exists since 2002.
- * This will work up to Dec 31, 2100
- */
-	year += 2000;
-
-	return mktime(year, mon, day, hour, min, sec);
+	return result;
 }
 
 #ifdef CONFIG_CPU_FREQ
@@ -1004,7 +1020,7 @@
 	/*
 	 * Estimate time zone so that set_time can update the clock
 	 */
-	long cmos_time =  get_cmos_time();
+	long cmos_time =  __get_cmos_time();
 
 	clock_cmos_diff = -cmos_time;
 	clock_cmos_diff += get_seconds();
diff -urN oldtree/arch/x86_64/mm/init.c newtree/arch/x86_64/mm/init.c
--- oldtree/arch/x86_64/mm/init.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/arch/x86_64/mm/init.c	2006-01-28 17:08:36.103747040 +0000
@@ -489,6 +489,7 @@
 	addr = (unsigned long)(&__init_begin);
 	for (; addr < (unsigned long)(&__init_end); addr += PAGE_SIZE) {
 		ClearPageReserved(virt_to_page(addr));
+		ClearPageNosave(virt_to_page(addr));
 		set_page_count(virt_to_page(addr), 1);
 		memset((void *)(addr & ~(PAGE_SIZE-1)), 0xcc, PAGE_SIZE); 
 		free_page(addr);
@@ -506,6 +507,7 @@
 	printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
 	for (; start < end; start += PAGE_SIZE) {
 		ClearPageReserved(virt_to_page(start));
+		ClearPageNosave(virt_to_page(start));
 		set_page_count(virt_to_page(start), 1);
 		free_page(start);
 		totalram_pages++;
@@ -617,3 +619,22 @@
 {
 	return (addr >= VSYSCALL_START) && (addr < VSYSCALL_END);
 }
+
+#if defined(CONFIG_SOFTWARE_SUSPEND) || defined(CONFIG_SUSPEND2)
+/*
+ * Software suspend & friends need this for resume because things like the intel-agp
+ * driver might have split up a kernel 4MB mapping.
+ */
+char __nosavedata swsusp_pg_dir[PAGE_SIZE]
+	__attribute__ ((aligned (PAGE_SIZE)));
+
+static inline void save_pg_dir(void)
+{
+	memcpy(swsusp_pg_dir, swapper_pg_dir, PAGE_SIZE);
+}
+#else
+static inline void save_pg_dir(void)
+{
+}
+#endif
+
diff -urN oldtree/block/ll_rw_blk.c newtree/block/ll_rw_blk.c
--- oldtree/block/ll_rw_blk.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/block/ll_rw_blk.c	2006-01-28 17:08:36.105746736 +0000
@@ -27,6 +27,9 @@
 #include <linux/swap.h>
 #include <linux/writeback.h>
 #include <linux/blkdev.h>
+#include <linux/freezer.h>
+#include <linux/mount.h>
+#include <linux/suspend2.h>
 
 /*
  * for max sense size
@@ -2920,12 +2923,26 @@
 	else
 		mod_page_state(pgpgin, count);
 
+	if (unlikely((	bio->bi_flags & (1 << BIO_SUSPEND2)) &&
+			test_action_state(SUSPEND_TEST_BIO) &&
+			(rw & WRITE))) {
+		char b[BDEVNAME_SIZE];
+		printk("FAKEDWRITE: %s(%d): %s block %Lu on %s\n",
+			current->comm, current->pid,
+			(rw & WRITE) ? "WRITE" : "READ",
+			(unsigned long long)bio->bi_sector,
+			bdevname(bio->bi_bdev,b));
+		bio_endio(bio, PAGE_SIZE, 0);
+		return;
+	}
+
 	if (unlikely(block_dump)) {
 		char b[BDEVNAME_SIZE];
-		printk(KERN_DEBUG "%s(%d): %s block %Lu on %s\n",
+		printk(KERN_DEBUG "%s(%d): %s block %Lu size %d on %s\n",
 			current->comm, current->pid,
 			(rw & WRITE) ? "WRITE" : "READ",
 			(unsigned long long)bio->bi_sector,
+			bio->bi_size,
 			bdevname(bio->bi_bdev,b));
 	}
 
@@ -3224,7 +3241,7 @@
 
 int __init blk_dev_init(void)
 {
-	kblockd_workqueue = create_workqueue("kblockd");
+	kblockd_workqueue = create_nofreeze_workqueue("kblockd");
 	if (!kblockd_workqueue)
 		panic("Failed to create kblockd\n");
 
diff -urN oldtree/crypto/Kconfig newtree/crypto/Kconfig
--- oldtree/crypto/Kconfig	2006-01-28 16:36:00.000000000 +0000
+++ newtree/crypto/Kconfig	2006-01-28 17:08:36.106746584 +0000
@@ -285,6 +285,13 @@
 	  
 	  You will most probably want this if using IPSec.
 
+config CRYPTO_LZF
+	tristate "LZF compression algorithm"
+	depends on CRYPTO
+	help
+	  This is the LZF algorithm. It is especially useful for Suspend2,
+	  because it achieves good compression quickly.
+
 config CRYPTO_MICHAEL_MIC
 	tristate "Michael MIC keyed digest algorithm"
 	depends on CRYPTO
diff -urN oldtree/crypto/Makefile newtree/crypto/Makefile
--- oldtree/crypto/Makefile	2006-01-28 16:36:00.000000000 +0000
+++ newtree/crypto/Makefile	2006-01-28 17:08:36.106746584 +0000
@@ -30,5 +30,6 @@
 obj-$(CONFIG_CRYPTO_DEFLATE) += deflate.o
 obj-$(CONFIG_CRYPTO_MICHAEL_MIC) += michael_mic.o
 obj-$(CONFIG_CRYPTO_CRC32C) += crc32c.o
+obj-$(CONFIG_CRYPTO_LZF) += lzf.o
 
 obj-$(CONFIG_CRYPTO_TEST) += tcrypt.o
diff -urN oldtree/crypto/deflate.c newtree/crypto/deflate.c
--- oldtree/crypto/deflate.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/crypto/deflate.c	2006-01-28 17:08:36.107746432 +0000
@@ -143,8 +143,15 @@
 
 	ret = zlib_deflate(stream, Z_FINISH);
 	if (ret != Z_STREAM_END) {
-		ret = -EINVAL;
-		goto out;
+	    	if (!(ret == Z_OK && !stream->avail_in && !stream->avail_out)) {
+			ret = -EINVAL;
+			goto out;
+		} else {
+			u8 zerostuff = 0;
+			stream->next_out = &zerostuff;
+			stream->avail_out = 1; 
+			ret = zlib_deflate(stream, Z_FINISH);
+		}
 	}
 	ret = 0;
 	*dlen = stream->total_out;
diff -urN oldtree/crypto/lzf.c newtree/crypto/lzf.c
--- oldtree/crypto/lzf.c	1970-01-01 00:00:00.000000000 +0000
+++ newtree/crypto/lzf.c	2006-01-28 17:08:36.108746280 +0000
@@ -0,0 +1,335 @@
+/* 
+ * Cryptoapi LZF compression module.
+ *
+ * Copyright (c) 2004-2005 Nigel Cunningham <nigel@suspend2.net>
+ *
+ * based on the deflate.c file:
+ * 
+ * Copyright (c) 2003 James Morris <jmorris@intercode.com.au>
+ * 
+ * and upon the LZF compression module donated to the Suspend2 project with
+ * the following copyright:
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option) 
+ * any later version.
+ * Copyright (c) 2000-2003 Marc Alexander Lehmann <pcg@goof.com>
+ * 
+ * Redistribution and use in source and binary forms, with or without modifica-
+ * tion, are permitted provided that the following conditions are met:
+ * 
+ *   1.  Redistributions of source code must retain the above copyright notice,
+ *       this list of conditions and the following disclaimer.
+ * 
+ *   2.  Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ * 
+ *   3.  The name of the author may not be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ * 
+ * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MER-
+ * CHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.  IN NO
+ * EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPE-
+ * CIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+ * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
+ * OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTH-
+ * ERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED
+ * OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * Alternatively, the contents of this file may be used under the terms of
+ * the GNU General Public License version 2 (the "GPL"), in which case the
+ * provisions of the GPL are applicable instead of the above. If you wish to
+ * allow the use of your version of this file only under the terms of the
+ * GPL and not to allow others to use your version of this file under the
+ * BSD license, indicate your decision by deleting the provisions above and
+ * replace them with the notice and other provisions required by the GPL. If
+ * you do not delete the provisions above, a recipient may use your version
+ * of this file under either the BSD or the GPL.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/crypto.h>
+#include <linux/err.h>
+#include <linux/vmalloc.h>
+#include <asm/string.h>
+
+struct lzf_ctx {
+	void *hbuf;
+	unsigned int bufofs;
+};
+
+/*
+ * size of hashtable is (1 << hlog) * sizeof (char *)
+ * decompression is independent of the hash table size
+ * the difference between 15 and 14 is very small
+ * for small blocks (and 14 is also faster).
+ * For a low-memory configuration, use hlog == 13;
+ * For best compression, use 15 or 16.
+ */
+static const int hlog = 14;
+
+/*
+ * don't play with this unless you benchmark!
+ * decompression is not dependent on the hash function
+ * the hashing function might seem strange, just believe me
+ * it works ;)
+ */
+static inline u16 first(const u8 *p)
+{
+	return ((p[0]) << 8) + p[1];
+}
+
+static inline u16 next(u8 v, const u8 *p)
+{
+	return ((v) << 8) + p[2];
+}
+
+static inline u32 idx(unsigned int h)
+{
+	return (((h ^ (h << 5)) >> (3*8 - hlog)) + h*3) & ((1 << hlog) - 1);
+}
+
+/*
+ * IDX works because it is very similar to a multiplicative hash, e.g.
+ * (h * 57321 >> (3*8 - hlog))
+ * the next one is also quite good, albeit slow ;)
+ * (int)(cos(h & 0xffffff) * 1e6)
+ */
+
+static const int max_lit = (1 <<  5);
+static const int max_off = (1 << 13);
+static const int max_ref = ((1 <<  8) + (1 << 3));
+
+/*
+ * compressed format
+ *
+ * 000LLLLL <L+1>    ; literal
+ * LLLOOOOO oooooooo ; backref L
+ * 111OOOOO LLLLLLLL oooooooo ; backref L+7
+ *
+ */
+
+static void lzf_compress_exit(void *context)
+{
+	struct lzf_ctx *ctx = (struct lzf_ctx *)context;
+
+	if (ctx->hbuf) {
+		vfree(ctx->hbuf);
+		ctx->hbuf = NULL;
+	}
+}
+
+static int lzf_compress_init(void *context)
+{
+	struct lzf_ctx *ctx = (struct lzf_ctx *)context;
+
+	/* Get LZF ready to go */
+	ctx->hbuf = vmalloc_32((1 << hlog) * sizeof(char *));
+	if (!ctx->hbuf) {
+		printk(KERN_WARNING
+		       "Failed to allocate %ld bytes for lzf workspace\n",
+		       (1 << hlog) * sizeof(char *));
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+static int lzf_compress(void *context, const u8 *in_data, unsigned int in_len,
+			u8 *out_data, unsigned int *out_len)
+{
+	struct lzf_ctx *ctx = (struct lzf_ctx *)context;
+	const u8 **htab = ctx->hbuf;
+	const u8 **hslot;
+	const u8 *ip = in_data;
+	u8 *op = out_data;
+	const u8 *in_end = ip + in_len;
+	u8 *out_end = op + *out_len - 3;
+	const u8 *ref;
+
+	unsigned int hval = first(ip);
+	unsigned long off;
+	int lit = 0;
+
+	memset(htab, 0, sizeof(htab));
+
+	for (;;) {
+		if (ip < in_end - 2) {
+			hval = next(hval, ip);
+			hslot = htab + idx(hval);
+			ref = *hslot;
+			*hslot = ip;
+
+			if ((off = ip - ref - 1) < max_off
+			    && ip + 4 < in_end && ref > in_data
+			    && *(u16 *) ref == *(u16 *) ip && ref[2] == ip[2]
+			    ) {
+				/* match found at *ref++ */
+				unsigned int len = 2;
+				unsigned int maxlen = in_end - ip - len;
+				maxlen = maxlen > max_ref ? max_ref : maxlen;
+
+				do
+					len++;
+				while (len < maxlen && ref[len] == ip[len]);
+
+				if (op + lit + 1 + 3 >= out_end) {
+					*out_len = PAGE_SIZE;
+					return 0;
+				}
+
+				if (lit) {
+					*op++ = lit - 1;
+					lit = -lit;
+					do
+						*op++ = ip[lit];
+					while (++lit);
+				}
+
+				len -= 2;
+				ip++;
+
+				if (len < 7) {
+					*op++ = (off >> 8) + (len << 5);
+				} else {
+					*op++ = (off >> 8) + (7 << 5);
+					*op++ = len - 7;
+				}
+
+				*op++ = off;
+
+				ip += len;
+				hval = first(ip);
+				hval = next(hval, ip);
+				htab[idx(hval)] = ip;
+				ip++;
+				continue;
+			}
+		} else if (ip == in_end)
+			break;
+
+		/* one more literal byte we must copy */
+		lit++;
+		ip++;
+
+		if (lit == max_lit) {
+			if (op + 1 + max_lit >= out_end) {
+				*out_len = PAGE_SIZE;
+				return 0;
+			}
+
+			*op++ = max_lit - 1;
+			memcpy(op, ip - max_lit, max_lit);
+			op += max_lit;
+			lit = 0;
+		}
+	}
+
+	if (lit) {
+		if (op + lit + 1 >= out_end) {
+			*out_len = PAGE_SIZE;
+			return 0;
+		}
+
+		*op++ = lit - 1;
+		lit = -lit;
+		do
+			*op++ = ip[lit];
+		while (++lit);
+	}
+
+	*out_len = op - out_data;
+	return 0;
+}
+
+static int lzf_decompress(void *context, const u8 *src, unsigned int slen,
+			  u8 *dst, unsigned int *dlen)
+{
+	u8 const *ip = src;
+	u8 *op = dst;
+	u8 const *const in_end = ip + slen;
+	u8 *const out_end = op + *dlen;
+
+	do {
+		unsigned int ctrl = *ip++;
+
+		if (ctrl < (1 << 5)) {	/* literal run */
+			ctrl++;
+
+			if (op + ctrl > out_end) {
+				*dlen = PAGE_SIZE;
+				return 0;
+			}
+			memcpy(op, ip, ctrl);
+			op += ctrl;
+			ip += ctrl;
+		} else {	/* back reference */
+
+			unsigned int len = ctrl >> 5;
+
+			u8 *ref = op - ((ctrl & 0x1f) << 8) - 1;
+
+			if (len == 7)
+				len += *ip++;
+
+			ref -= *ip++;
+
+			if (op + len + 2 > out_end) {
+				*dlen = PAGE_SIZE;
+				return 0;
+			}
+
+			if (ref < (u8 *) dst) {
+				*dlen = PAGE_SIZE;
+				return 0;
+			}
+
+			*op++ = *ref++;
+			*op++ = *ref++;
+
+			do
+				*op++ = *ref++;
+			while (--len);
+		}
+	}
+	while (op < out_end && ip < in_end);
+
+	*dlen = op - (u8 *) dst;
+	return 0;
+}
+
+static struct crypto_alg alg = {
+	.cra_name = "lzf",
+	.cra_flags = CRYPTO_ALG_TYPE_COMPRESS,
+	.cra_ctxsize = 0,
+	.cra_module = THIS_MODULE,
+	.cra_list = LIST_HEAD_INIT(alg.cra_list),
+	.cra_u = {.compress = {
+			       .coa_init = lzf_compress_init,
+			       .coa_exit = lzf_compress_exit,
+			       .coa_compress = lzf_compress,
+			       .coa_decompress = lzf_decompress}}
+};
+
+static int __init init(void)
+{
+	return crypto_register_alg(&alg);
+}
+
+static void __exit fini(void)
+{
+	crypto_unregister_alg(&alg);
+}
+
+module_init(init);
+module_exit(fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("LZF Compression Algorithm");
+MODULE_AUTHOR("Marc Alexander Lehmann & Nigel Cunningham");
diff -urN oldtree/drivers/acpi/osl.c newtree/drivers/acpi/osl.c
--- oldtree/drivers/acpi/osl.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/acpi/osl.c	2006-01-28 17:08:36.108746280 +0000
@@ -91,7 +91,7 @@
 		       "Access to PCI configuration space unavailable\n");
 		return AE_NULL_ENTRY;
 	}
-	kacpid_wq = create_singlethread_workqueue("kacpid");
+	kacpid_wq = create_nofreeze_singlethread_workqueue("kacpid");
 	BUG_ON(!kacpid_wq);
 
 	return AE_OK;
diff -urN oldtree/drivers/acpi/sleep/proc.c newtree/drivers/acpi/sleep/proc.c
--- oldtree/drivers/acpi/sleep/proc.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/acpi/sleep/proc.c	2006-01-28 17:08:36.109746128 +0000
@@ -58,6 +58,15 @@
 		goto Done;
 	}
 	state = simple_strtoul(str, NULL, 0);
+	
+	/* 
+	 * I used to put this after the CONFIG_SOFTWARE_SUSPEND
+	 * test, but people who compile in suspend2 usually want
+	 * to use it instead of swsusp.   --NC
+	 */
+	if (may_try_suspend2(state))
+		goto Done;
+
 #ifdef CONFIG_SOFTWARE_SUSPEND
 	if (state == 4) {
 		error = software_suspend();
diff -urN oldtree/drivers/base/power/resume.c newtree/drivers/base/power/resume.c
--- oldtree/drivers/base/power/resume.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/base/power/resume.c	2006-01-28 17:08:36.110745976 +0000
@@ -101,6 +101,11 @@
 		list_del_init(entry);
 		list_add_tail(entry, &dpm_active);
 		resume_device(dev);
+		if (!irqs_disabled()) {
+			printk("WARNING: Interrupts reenabled while resuming sysdev driver %s.\n",
+			kobject_name(&dev->kobj));
+			local_irq_disable();
+		}
 		put_device(dev);
 	}
 }
diff -urN oldtree/drivers/base/power/suspend.c newtree/drivers/base/power/suspend.c
--- oldtree/drivers/base/power/suspend.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/base/power/suspend.c	2006-01-28 17:08:36.110745976 +0000
@@ -94,6 +94,12 @@
 
 		error = suspend_device(dev, state);
 
+		if (irqs_disabled()) {
+			printk("WARNING: Interrupts disabled while suspending %s.\n",
+					dev->driver ? dev->driver->name : dev->kobj.name);
+			local_irq_enable();
+		}
+
 		down(&dpm_list_sem);
 
 		/* Check if the device got removed */
diff -urN oldtree/drivers/base/sys.c newtree/drivers/base/sys.c
--- oldtree/drivers/base/sys.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/base/sys.c	2006-01-28 17:08:36.111745824 +0000
@@ -298,16 +298,34 @@
 	if (cls->resume)
 		cls->resume(dev);
 
+	if (!irqs_disabled()) {
+		printk("WARNING: Interrupts reenabled while resuming sysdev class specific driver %s.\n",
+				kobject_name(&dev->kobj));
+		local_irq_disable();
+	}
+
 	/* Call auxillary drivers next. */
 	list_for_each_entry(drv, &cls->drivers, entry) {
-		if (drv->resume)
+		if (drv->resume) {
 			drv->resume(dev);
+			if (!irqs_disabled()) {
+				printk("WARNING: Interrupts reenabled while resuming sysdev class driver %s.\n",
+				kobject_name(&dev->kobj));
+				local_irq_disable();
+			}
+		}
 	}
 
 	/* Call global drivers. */
 	list_for_each_entry(drv, &sysdev_drivers, entry) {
-		if (drv->resume)
+		if (drv->resume) {
 			drv->resume(dev);
+			if (!irqs_disabled()) {
+				printk("WARNING: Interrupts reenabled while resuming sysdev driver %s.\n",
+				kobject_name(&dev->kobj));
+				local_irq_disable();
+			}
+		}
 	}
 }
 
diff -urN oldtree/drivers/block/pktcdvd.c newtree/drivers/block/pktcdvd.c
--- oldtree/drivers/block/pktcdvd.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/block/pktcdvd.c	2006-01-28 17:08:36.112745672 +0000
@@ -1255,8 +1255,7 @@
 			residue = schedule_timeout(min_sleep_time);
 			VPRINTK("kcdrwd: wake up\n");
 
-			/* make swsusp happy with our thread */
-			try_to_freeze();
+			try_todo_list();
 
 			list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
 				if (!pkt->sleep_time)
diff -urN oldtree/drivers/char/agp/agp_suspend.h newtree/drivers/char/agp/agp_suspend.h
--- oldtree/drivers/char/agp/agp_suspend.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/drivers/char/agp/agp_suspend.h	2006-01-28 17:08:36.113745520 +0000
@@ -0,0 +1,43 @@
+/*
+ * Generic routines for suspending and resuming an agp bridge.
+ *
+ * Include "agp.h" first.
+ */
+
+#ifdef CONFIG_PM
+static int agp_common_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+	pci_save_state(pdev);
+	pci_set_power_state(pdev, 3);
+
+	return 0;
+}
+
+static int agp_common_resume(struct pci_dev *pdev,
+			     struct agp_bridge_driver * generic_bridge,
+			     int reconfigure(void))
+{
+	struct agp_bridge_data *bridge = pci_get_drvdata(pdev);
+
+	/* set power state 0 and restore PCI space */
+	pci_set_power_state(pdev, 0);
+	pci_restore_state(pdev);
+
+	/* reconfigure AGP hardware again */
+	if (bridge->driver == generic_bridge)
+		return reconfigure();
+
+	return 0;
+}
+#else
+static int agp_common_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+	return 0;
+}
+
+static int agp_common_resume(struct pci_dev *pdev, _something_ * bridge,
+			     void *reconfigure)
+{
+	return 0;
+}
+#endif
diff -urN oldtree/drivers/char/agp/ati-agp.c newtree/drivers/char/agp/ati-agp.c
--- oldtree/drivers/char/agp/ati-agp.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/char/agp/ati-agp.c	2006-01-28 17:08:36.113745520 +0000
@@ -11,6 +11,7 @@
 #include <linux/agp_backend.h>
 #include <asm/agp.h>
 #include "agp.h"
+#include "agp_suspend.h"
 
 #define ATI_GART_MMBASE_ADDR	0x14
 #define ATI_RS100_APSIZE	0xac
@@ -506,6 +507,17 @@
 	agp_put_bridge(bridge);
 }
 
+static int agp_ati_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+	return (agp_common_suspend(pdev, state));
+}
+
+static int agp_ati_resume(struct pci_dev *pdev)
+{
+	return agp_common_resume(pdev, &ati_generic_bridge,
+				 ati_configure);
+}
+
 static struct pci_device_id agp_ati_pci_table[] = {
 	{
 	.class		= (PCI_CLASS_BRIDGE_HOST << 8),
@@ -525,6 +537,8 @@
 	.id_table	= agp_ati_pci_table,
 	.probe		= agp_ati_probe,
 	.remove		= agp_ati_remove,
+	.suspend	= agp_ati_suspend,
+	.resume		= agp_ati_resume,
 };
 
 static int __init agp_ati_init(void)
diff -urN oldtree/drivers/char/agp/nvidia-agp.c newtree/drivers/char/agp/nvidia-agp.c
--- oldtree/drivers/char/agp/nvidia-agp.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/char/agp/nvidia-agp.c	2006-01-28 17:08:36.114745368 +0000
@@ -12,6 +12,7 @@
 #include <linux/page-flags.h>
 #include <linux/mm.h>
 #include "agp.h"
+#include "agp_suspend.h"
 
 /* NVIDIA registers */
 #define NVIDIA_0_APSIZE		0x80
@@ -397,11 +398,24 @@
 
 MODULE_DEVICE_TABLE(pci, agp_nvidia_pci_table);
 
+static int agp_nvidia_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+	return (agp_common_suspend(pdev, state));
+}
+
+static int agp_nvidia_resume(struct pci_dev *pdev)
+{
+	return agp_common_resume(pdev, &agp_bridge,
+				 nvidia_configure);
+}
+
 static struct pci_driver agp_nvidia_pci_driver = {
 	.name		= "agpgart-nvidia",
 	.id_table	= agp_nvidia_pci_table,
 	.probe		= agp_nvidia_probe,
 	.remove		= agp_nvidia_remove,
+	.suspend	= agp_nvidia_suspend,
+	.resume		= agp_nvidia_resume,
 };
 
 static int __init agp_nvidia_init(void)
diff -urN oldtree/drivers/char/hvc_console.c newtree/drivers/char/hvc_console.c
--- oldtree/drivers/char/hvc_console.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/char/hvc_console.c	2006-01-28 17:08:36.115745216 +0000
@@ -841,7 +841,7 @@
 
 	/* Always start the kthread because there can be hotplug vty adapters
 	 * added later. */
-	hvc_task = kthread_run(khvcd, NULL, "khvcd");
+	hvc_task = kthread_nofreeze_run(khvcd, NULL, "khvcd");
 	if (IS_ERR(hvc_task)) {
 		panic("Couldn't create kthread for console.\n");
 		put_tty_driver(hvc_driver);
diff -urN oldtree/drivers/char/hvcs.c newtree/drivers/char/hvcs.c
--- oldtree/drivers/char/hvcs.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/char/hvcs.c	2006-01-28 17:08:36.116745064 +0000
@@ -1406,7 +1406,7 @@
 		return -ENOMEM;
 	}
 
-	hvcs_task = kthread_run(khvcsd, NULL, "khvcsd");
+	hvcs_task = kthread_nofreeze_run(khvcsd, NULL, "khvcsd");
 	if (IS_ERR(hvcs_task)) {
 		printk(KERN_ERR "HVCS: khvcsd creation failed.  Driver not loaded.\n");
 		kfree(hvcs_pi_buff);
diff -urN oldtree/drivers/ieee1394/ieee1394_core.c newtree/drivers/ieee1394/ieee1394_core.c
--- oldtree/drivers/ieee1394/ieee1394_core.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/ieee1394/ieee1394_core.c	2006-01-28 17:08:36.117744912 +0000
@@ -1032,7 +1032,7 @@
 
 	while (1) {
 		if (down_interruptible(&khpsbpkt_sig)) {
-			if (try_to_freeze())
+			if (try_todo_list())
 				continue;
 			printk("khpsbpkt: received unexpected signal?!\n" );
 			break;
diff -urN oldtree/drivers/ieee1394/nodemgr.c newtree/drivers/ieee1394/nodemgr.c
--- oldtree/drivers/ieee1394/nodemgr.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/ieee1394/nodemgr.c	2006-01-28 17:08:36.118744760 +0000
@@ -1569,7 +1569,7 @@
 
 		if (down_interruptible(&hi->reset_sem) ||
 		    down_interruptible(&nodemgr_serialize)) {
-			if (try_to_freeze())
+			if (try_todo_list())
 				continue;
 			printk("NodeMgr: received unexpected signal?!\n" );
 			break;
diff -urN oldtree/drivers/input/gameport/gameport.c newtree/drivers/input/gameport/gameport.c
--- oldtree/drivers/input/gameport/gameport.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/input/gameport/gameport.c	2006-01-28 17:08:36.147740352 +0000
@@ -442,7 +442,7 @@
 		gameport_handle_event();
 		wait_event_interruptible(gameport_wait,
 			kthread_should_stop() || !list_empty(&gameport_event_list));
-		try_to_freeze();
+		try_todo_list();
 	} while (!kthread_should_stop());
 
 	printk(KERN_DEBUG "gameport: kgameportd exiting\n");
diff -urN oldtree/drivers/input/serio/serio.c newtree/drivers/input/serio/serio.c
--- oldtree/drivers/input/serio/serio.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/input/serio/serio.c	2006-01-28 17:08:36.148740200 +0000
@@ -314,6 +314,12 @@
 
 		serio_remove_duplicate_events(event);
 		serio_free_event(event);
+
+		if (unlikely(todo_list_active())) {
+  			up(&serio_sem);
+			try_todo_list();
+  			down(&serio_sem);
+		}
 	}
 
 	up(&serio_sem);
@@ -377,7 +383,7 @@
 		serio_handle_event();
 		wait_event_interruptible(serio_wait,
 			kthread_should_stop() || !list_empty(&serio_event_list));
-		try_to_freeze();
+		try_todo_list();
 	} while (!kthread_should_stop());
 
 	printk(KERN_DEBUG "serio: kseriod exiting\n");
@@ -899,7 +905,7 @@
 
 static int __init serio_init(void)
 {
-	serio_task = kthread_run(serio_thread, NULL, "kseriod");
+	serio_task = kthread_nofreeze_run(serio_thread, NULL, "kseriod");
 	if (IS_ERR(serio_task)) {
 		printk(KERN_ERR "serio: Failed to start kseriod\n");
 		return PTR_ERR(serio_task);
diff -urN oldtree/drivers/macintosh/Kconfig newtree/drivers/macintosh/Kconfig
--- oldtree/drivers/macintosh/Kconfig	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/macintosh/Kconfig	2006-01-28 17:08:36.149740048 +0000
@@ -192,4 +192,8 @@
 	tristate "Support for ANS LCD display"
 	depends on ADB_CUDA && PPC_PMAC
 
+config SOFTWARE_REPLACE_SLEEP
+	bool "Using Software suspend replace broken sleep function"
+	depends on SUSPEND2
+
 endmenu
diff -urN oldtree/drivers/macintosh/therm_adt746x.c newtree/drivers/macintosh/therm_adt746x.c
--- oldtree/drivers/macintosh/therm_adt746x.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/macintosh/therm_adt746x.c	2006-01-28 17:08:36.150739896 +0000
@@ -328,7 +328,7 @@
 	struct thermostat* th = arg;
 
 	while(!kthread_should_stop()) {
-		try_to_freeze();
+		try_todo_list();
 		msleep_interruptible(2000);
 
 #ifndef DEBUG
diff -urN oldtree/drivers/macintosh/via-pmu.c newtree/drivers/macintosh/via-pmu.c
--- oldtree/drivers/macintosh/via-pmu.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/macintosh/via-pmu.c	2006-01-28 17:08:36.151739744 +0000
@@ -2882,6 +2882,13 @@
 			return -EACCES;
 		if (sleep_in_progress)
 			return -EBUSY;
+#ifdef CONFIG_SOFTWARE_REPLACE_SLEEP
+		{
+		extern void software_suspend_pending(void);
+		software_suspend_pending();
+		return (0);
+		}
+#endif
 		sleep_in_progress = 1;
 		switch (pmu_kind) {
 		case PMU_OHARE_BASED:
diff -urN oldtree/drivers/md/dm-crypt.c newtree/drivers/md/dm-crypt.c
--- oldtree/drivers/md/dm-crypt.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/md/dm-crypt.c	2006-01-28 17:08:36.152739592 +0000
@@ -923,7 +923,7 @@
 	if (!_crypt_io_pool)
 		return -ENOMEM;
 
-	_kcryptd_workqueue = create_workqueue("kcryptd");
+	_kcryptd_workqueue = create_nofreeze_workqueue("kcryptd");
 	if (!_kcryptd_workqueue) {
 		r = -ENOMEM;
 		DMERR(PFX "couldn't create kcryptd");
diff -urN oldtree/drivers/md/md.c newtree/drivers/md/md.c
--- oldtree/drivers/md/md.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/md/md.c	2006-01-28 17:08:36.154739288 +0000
@@ -41,7 +41,6 @@
 #include <linux/sysctl.h>
 #include <linux/devfs_fs_kernel.h>
 #include <linux/buffer_head.h> /* for invalidate_bdev */
-#include <linux/suspend.h>
 
 #include <linux/init.h>
 
@@ -3486,7 +3485,8 @@
 	thread->run = run;
 	thread->mddev = mddev;
 	thread->timeout = MAX_SCHEDULE_TIMEOUT;
-	thread->tsk = kthread_run(md_thread, thread, name, mdname(thread->mddev));
+	thread->tsk = kthread_nofreeze_run(md_thread, thread,
+			name, mdname(thread->mddev));
 	if (IS_ERR(thread->tsk)) {
 		kfree(thread);
 		return NULL;
diff -urN oldtree/drivers/media/dvb/dvb-core/dvb_frontend.c newtree/drivers/media/dvb/dvb-core/dvb_frontend.c
--- oldtree/drivers/media/dvb/dvb-core/dvb_frontend.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/media/dvb/dvb-core/dvb_frontend.c	2006-01-28 17:08:36.155739136 +0000
@@ -392,7 +392,7 @@
 			break;
 		}
 
-		try_to_freeze();
+		try_todo_list();
 
 		if (down_interruptible(&fepriv->sem))
 			break;
diff -urN oldtree/drivers/media/video/msp3400.c newtree/drivers/media/video/msp3400.c
--- oldtree/drivers/media/video/msp3400.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/media/video/msp3400.c	2006-01-28 17:08:36.156738984 +0000
@@ -860,7 +860,7 @@
 	}
 
 	remove_wait_queue(&msp->wq, &wait);
-	try_to_freeze();
+	try_todo_list();
 	return msp->restart;
 }
 
diff -urN oldtree/drivers/media/video/tvaudio.c newtree/drivers/media/video/tvaudio.c
--- oldtree/drivers/media/video/tvaudio.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/media/video/tvaudio.c	2006-01-28 17:08:36.158738680 +0000
@@ -295,7 +295,7 @@
 			schedule();
 		}
 		remove_wait_queue(&chip->wq, &wait);
-		try_to_freeze();
+		try_todo_list();
 		if (chip->done || signal_pending(current))
 			break;
 		tvaudio_dbg("%s: thread wakeup\n", chip->c.name);
diff -urN oldtree/drivers/media/video/video-buf-dvb.c newtree/drivers/media/video/video-buf-dvb.c
--- oldtree/drivers/media/video/video-buf-dvb.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/media/video/video-buf-dvb.c	2006-01-28 17:08:36.158738680 +0000
@@ -62,7 +62,7 @@
 			break;
 		if (kthread_should_stop())
 			break;
-		try_to_freeze();
+		try_todo_list();
 
 		/* feed buffer data to demux */
 		if (buf->state == STATE_DONE)
diff -urN oldtree/drivers/net/8139too.c newtree/drivers/net/8139too.c
--- oldtree/drivers/net/8139too.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/net/8139too.c	2006-01-28 17:08:36.160738376 +0000
@@ -1607,8 +1607,7 @@
 		timeout = next_tick;
 		do {
 			timeout = interruptible_sleep_on_timeout (&tp->thr_wait, timeout);
-			/* make swsusp happy with our thread */
-			try_to_freeze();
+			try_todo_list();
 		} while (!signal_pending (current) && (timeout > 0));
 
 		if (signal_pending (current)) {
diff -urN oldtree/drivers/net/irda/sir_kthread.c newtree/drivers/net/irda/sir_kthread.c
--- oldtree/drivers/net/irda/sir_kthread.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/net/irda/sir_kthread.c	2006-01-28 17:08:36.160738376 +0000
@@ -112,6 +112,7 @@
 	DECLARE_WAITQUEUE(wait, current);
 
 	daemonize("kIrDAd");
+	current->flags |= PF_NOFREEZE;
 
 	irda_rq_queue.thread = current;
 
@@ -134,9 +135,6 @@
 			__set_task_state(current, TASK_RUNNING);
 		remove_wait_queue(&irda_rq_queue.kick, &wait);
 
-		/* make swsusp happy with our thread */
-		try_to_freeze();
-
 		run_irda_queue();
 	}
 
diff -urN oldtree/drivers/net/irda/stir4200.c newtree/drivers/net/irda/stir4200.c
--- oldtree/drivers/net/irda/stir4200.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/net/irda/stir4200.c	2006-01-28 17:08:36.161738224 +0000
@@ -762,7 +762,7 @@
 	{
 #ifdef CONFIG_PM
 		/* if suspending, then power off and wait */
-		if (unlikely(freezing(current))) {
+		if (unlikely(todo_list_active())) {
 			if (stir->receiving)
 				receive_stop(stir);
 			else
@@ -770,7 +770,7 @@
 
 			write_reg(stir, REG_CTRL1, CTRL1_TXPWD|CTRL1_RXPWD);
 
-			refrigerator();
+			run_todo_list();
 
 			if (change_speed(stir, stir->speed))
 				break;
diff -urN oldtree/drivers/net/wireless/airo.c newtree/drivers/net/wireless/airo.c
--- oldtree/drivers/net/wireless/airo.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/net/wireless/airo.c	2006-01-28 17:08:36.165737616 +0000
@@ -2910,7 +2910,7 @@
 			flush_signals(current);
 
 		/* make swsusp happy with our thread */
-		try_to_freeze();
+		try_todo_list();
 
 		if (test_bit(JOB_DIE, &ai->flags))
 			break;
diff -urN oldtree/drivers/pcmcia/cs.c newtree/drivers/pcmcia/cs.c
--- oldtree/drivers/pcmcia/cs.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/pcmcia/cs.c	2006-01-28 17:08:36.166737464 +0000
@@ -691,7 +691,7 @@
 			break;
 
 		schedule();
-		try_to_freeze();
+		try_todo_list();
 	}
 	/* make sure we are running before we exit */
 	set_current_state(TASK_RUNNING);
diff -urN oldtree/drivers/pnp/pnpbios/core.c newtree/drivers/pnp/pnpbios/core.c
--- oldtree/drivers/pnp/pnpbios/core.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/pnp/pnpbios/core.c	2006-01-28 17:08:36.167737312 +0000
@@ -172,7 +172,7 @@
 		msleep_interruptible(2000);
 
 		if(signal_pending(current)) {
-			if (try_to_freeze())
+			if (try_todo_list())
 				continue;
 			break;
 		}
diff -urN oldtree/drivers/scsi/hosts.c newtree/drivers/scsi/hosts.c
--- oldtree/drivers/scsi/hosts.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/scsi/hosts.c	2006-01-28 17:08:36.167737312 +0000
@@ -227,7 +227,7 @@
 	if (shost->transportt->create_work_queue) {
 		snprintf(shost->work_q_name, KOBJ_NAME_LEN, "scsi_wq_%d",
 			shost->host_no);
-		shost->work_q = create_singlethread_workqueue(
+		shost->work_q = create_nofreeze_singlethread_workqueue(
 					shost->work_q_name);
 		if (!shost->work_q)
 			goto out_free_shost_data;
diff -urN oldtree/drivers/scsi/lpfc/lpfc_init.c newtree/drivers/scsi/lpfc/lpfc_init.c
--- oldtree/drivers/scsi/lpfc/lpfc_init.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/scsi/lpfc/lpfc_init.c	2006-01-28 17:08:36.168737160 +0000
@@ -1475,7 +1475,7 @@
 	phba->work_ha_mask |= (HA_RXMASK << (LPFC_ELS_RING * 4));
 
 	/* Startup the kernel thread for this host adapter. */
-	phba->worker_thread = kthread_run(lpfc_do_work, phba,
+	phba->worker_thread = kthread_nofreeze_run(lpfc_do_work, phba,
 				       "lpfc_worker_%d", phba->brd_no);
 	if (IS_ERR(phba->worker_thread)) {
 		error = PTR_ERR(phba->worker_thread);
diff -urN oldtree/drivers/usb/core/hub.c newtree/drivers/usb/core/hub.c
--- oldtree/drivers/usb/core/hub.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/usb/core/hub.c	2006-01-28 17:08:36.170736856 +0000
@@ -2814,7 +2814,7 @@
 		wait_event_interruptible(khubd_wait,
 				!list_empty(&hub_event_list) ||
 				kthread_should_stop());
-		try_to_freeze();
+		try_todo_list();
 	} while (!kthread_should_stop() || !list_empty(&hub_event_list));
 
 	pr_debug("%s: khubd exiting\n", usbcore_name);
diff -urN oldtree/drivers/usb/gadget/file_storage.c newtree/drivers/usb/gadget/file_storage.c
--- oldtree/drivers/usb/gadget/file_storage.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/usb/gadget/file_storage.c	2006-01-28 17:08:36.172736552 +0000
@@ -1550,7 +1550,7 @@
 	rc = wait_event_interruptible(fsg->thread_wqh,
 			fsg->thread_wakeup_needed);
 	fsg->thread_wakeup_needed = 0;
-	try_to_freeze();
+	try_todo_list();
 	return (rc ? -EINTR : 0);
 }
 
diff -urN oldtree/drivers/usb/net/pegasus.c newtree/drivers/usb/net/pegasus.c
--- oldtree/drivers/usb/net/pegasus.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/usb/net/pegasus.c	2006-01-28 17:08:36.173736400 +0000
@@ -1417,7 +1417,7 @@
 static int __init pegasus_init(void)
 {
 	pr_info("%s: %s, " DRIVER_DESC "\n", driver_name, DRIVER_VERSION);
-	pegasus_workqueue = create_singlethread_workqueue("pegasus");
+	pegasus_workqueue = create_nofreeze_singlethread_workqueue("pegasus");
 	if (!pegasus_workqueue)
 		return -ENOMEM;
 	return usb_register(&pegasus_driver);
diff -urN oldtree/drivers/usb/storage/usb.c newtree/drivers/usb/storage/usb.c
--- oldtree/drivers/usb/storage/usb.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/usb/storage/usb.c	2006-01-28 17:08:36.174736248 +0000
@@ -890,7 +890,7 @@
 		wait_event_interruptible_timeout(us->delay_wait,
 				test_bit(US_FLIDX_DISCONNECTING, &us->flags),
 				delay_use * HZ);
-		if (try_to_freeze())
+		if (try_todo_list())
 			goto retry;
 	}
 
diff -urN oldtree/drivers/w1/w1.c newtree/drivers/w1/w1.c
--- oldtree/drivers/w1/w1.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/drivers/w1/w1.c	2006-01-28 17:08:36.175736096 +0000
@@ -720,7 +720,7 @@
 	while (!control_needs_exit || have_to_wait) {
 		have_to_wait = 0;
 
-		try_to_freeze();
+		try_todo_list();
 		msleep_interruptible(w1_control_timeout * 1000);
 
 		if (signal_pending(current))
@@ -796,7 +796,7 @@
 	allow_signal(SIGTERM);
 
 	while (!test_bit(W1_MASTER_NEED_EXIT, &dev->flags)) {
-		try_to_freeze();
+		try_todo_list();
 		msleep_interruptible(w1_timeout * 1000);
 
 		if (signal_pending(current))
diff -urN oldtree/fs/afs/kafsasyncd.c newtree/fs/afs/kafsasyncd.c
--- oldtree/fs/afs/kafsasyncd.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/fs/afs/kafsasyncd.c	2006-01-28 17:08:36.176735944 +0000
@@ -116,7 +116,7 @@
 		remove_wait_queue(&kafsasyncd_sleepq, &myself);
 		set_current_state(TASK_RUNNING);
 
-		try_to_freeze();
+		try_todo_list();
 
 		/* discard pending signals */
 		afs_discard_my_signals();
diff -urN oldtree/fs/afs/kafstimod.c newtree/fs/afs/kafstimod.c
--- oldtree/fs/afs/kafstimod.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/fs/afs/kafstimod.c	2006-01-28 17:08:36.176735944 +0000
@@ -91,7 +91,7 @@
 			complete_and_exit(&kafstimod_dead, 0);
 		}
 
-		try_to_freeze();
+		try_todo_list();
 
 		/* discard pending signals */
 		afs_discard_my_signals();
diff -urN oldtree/fs/jbd/journal.c newtree/fs/jbd/journal.c
--- oldtree/fs/jbd/journal.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/fs/jbd/journal.c	2006-01-28 17:08:36.177735792 +0000
@@ -153,7 +153,7 @@
 	}
 
 	wake_up(&journal->j_wait_done_commit);
-	if (freezing(current)) {
+	if (todo_list_active()) {
 		/*
 		 * The simpler the better. Flushing journal isn't a
 		 * good idea, because that depends on threads that may
@@ -161,7 +161,7 @@
 		 */
 		jbd_debug(1, "Now suspending kjournald\n");
 		spin_unlock(&journal->j_state_lock);
-		refrigerator();
+		run_todo_list();
 		spin_lock(&journal->j_state_lock);
 	} else {
 		/*
diff -urN oldtree/fs/jffs/intrep.c newtree/fs/jffs/intrep.c
--- oldtree/fs/jffs/intrep.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/fs/jffs/intrep.c	2006-01-28 17:08:36.179735488 +0000
@@ -3391,7 +3391,7 @@
 			siginfo_t info;
 			unsigned long signr = 0;
 
-			if (try_to_freeze())
+			if (try_todo_list())
 				continue;
 
 			spin_lock_irq(&current->sighand->siglock);
diff -urN oldtree/fs/jffs2/background.c newtree/fs/jffs2/background.c
--- oldtree/fs/jffs2/background.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/fs/jffs2/background.c	2006-01-28 17:08:36.180735336 +0000
@@ -96,7 +96,7 @@
 			schedule();
 		}
 
-		if (try_to_freeze())
+		if (try_todo_list())
 			continue;
 
 		cond_resched();
diff -urN oldtree/fs/jfs/jfs_logmgr.c newtree/fs/jfs/jfs_logmgr.c
--- oldtree/fs/jfs/jfs_logmgr.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/fs/jfs/jfs_logmgr.c	2006-01-28 17:08:36.181735184 +0000
@@ -2362,9 +2362,9 @@
 			lbmStartIO(bp);
 			spin_lock_irq(&log_redrive_lock);
 		}
-		if (freezing(current)) {
+		if (todo_list_active()) {
 			spin_unlock_irq(&log_redrive_lock);
-			refrigerator();
+			run_todo_list();
 		} else {
 			add_wait_queue(&jfs_IO_thread_wait, &wq);
 			set_current_state(TASK_INTERRUPTIBLE);
diff -urN oldtree/fs/jfs/jfs_txnmgr.c newtree/fs/jfs/jfs_txnmgr.c
--- oldtree/fs/jfs/jfs_txnmgr.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/fs/jfs/jfs_txnmgr.c	2006-01-28 17:08:36.183734880 +0000
@@ -2795,9 +2795,9 @@
 		/* In case a wakeup came while all threads were active */
 		jfs_commit_thread_waking = 0;
 
-		if (freezing(current)) {
+		if (todo_list_active()) {
 			LAZY_UNLOCK(flags);
-			refrigerator();
+			run_todo_list();
 		} else {
 			DECLARE_WAITQUEUE(wq, current);
 
@@ -2994,9 +2994,9 @@
 		/* Add anon_list2 back to anon_list */
 		list_splice_init(&TxAnchor.anon_list2, &TxAnchor.anon_list);
 
-		if (freezing(current)) {
+		if (todo_list_active()) {
 			TXN_UNLOCK();
-			refrigerator();
+			run_todo_list();
 		} else {
 			DECLARE_WAITQUEUE(wq, current);
 
diff -urN oldtree/fs/lockd/clntlock.c newtree/fs/lockd/clntlock.c
--- oldtree/fs/lockd/clntlock.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/fs/lockd/clntlock.c	2006-01-28 17:08:36.183734880 +0000
@@ -237,6 +237,7 @@
 
 		fl->fl_u.nfs_fl.flags &= ~NFS_LCK_RECLAIM;
 		nlmclnt_reclaim(host, fl);
+		try_todo_list();
 		if (signalled())
 			break;
 		goto restart;
diff -urN oldtree/fs/lockd/clntproc.c newtree/fs/lockd/clntproc.c
--- oldtree/fs/lockd/clntproc.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/fs/lockd/clntproc.c	2006-01-28 17:08:36.184734728 +0000
@@ -311,7 +311,7 @@
 	prepare_to_wait(queue, &wait, TASK_INTERRUPTIBLE);
 	if (!signalled ()) {
 		schedule_timeout(NLMCLNT_GRACE_WAIT);
-		try_to_freeze();
+		try_todo_list();
 		if (!signalled ())
 			status = 0;
 	}
diff -urN oldtree/fs/lockd/svc.c newtree/fs/lockd/svc.c
--- oldtree/fs/lockd/svc.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/fs/lockd/svc.c	2006-01-28 17:08:36.185734576 +0000
@@ -138,6 +138,8 @@
 	while ((nlmsvc_users || !signalled()) && nlmsvc_pid == current->pid) {
 		long timeout = MAX_SCHEDULE_TIMEOUT;
 
+		try_todo_list();
+  
 		if (signalled()) {
 			flush_signals(current);
 			if (nlmsvc_ops) {
diff -urN oldtree/fs/xfs/linux-2.6/xfs_buf.c newtree/fs/xfs/linux-2.6/xfs_buf.c
--- oldtree/fs/xfs/linux-2.6/xfs_buf.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/fs/xfs/linux-2.6/xfs_buf.c	2006-01-28 17:08:36.186734424 +0000
@@ -1709,9 +1709,9 @@
 
 	INIT_LIST_HEAD(&tmp);
 	do {
-		if (unlikely(freezing(current))) {
+		if (unlikely(todo_list_active())) {
 			xfsbufd_force_sleep = 1;
-			refrigerator();
+			run_todo_list();
 		} else {
 			xfsbufd_force_sleep = 0;
 		}
diff -urN oldtree/fs/xfs/linux-2.6/xfs_super.c newtree/fs/xfs/linux-2.6/xfs_super.c
--- oldtree/fs/xfs/linux-2.6/xfs_super.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/fs/xfs/linux-2.6/xfs_super.c	2006-01-28 17:08:36.187734272 +0000
@@ -575,7 +575,7 @@
 	for (;;) {
 		timeleft = schedule_timeout_interruptible(timeleft);
 		/* swsusp */
-		try_to_freeze();
+		try_todo_list();
 		if (kthread_should_stop())
 			break;
 
diff -urN oldtree/include/asm-arm/hw_irq.h newtree/include/asm-arm/hw_irq.h
--- oldtree/include/asm-arm/hw_irq.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/include/asm-arm/hw_irq.h	2006-01-28 17:08:36.187734272 +0000
@@ -0,0 +1,4 @@
+#ifndef __ASM_HARDIRQ_H
+#define __ASM_HARDIRQ_H
+#include <asm/hardirq.h>
+#endif
diff -urN oldtree/include/asm-arm/suspend2.h newtree/include/asm-arm/suspend2.h
--- oldtree/include/asm-arm/suspend2.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/include/asm-arm/suspend2.h	2006-01-28 17:08:36.188734120 +0000
@@ -0,0 +1,136 @@
+#ifndef _ASMARM_SUSPEND_H
+#define _ASMARM_SUSPEND_H
+/*
+ * Based on code
+ * Copyright 2005  Sony Corporation
+ * Copyright 2003-2004 Nigel Cunningham <ncunningham@linuxmail.org>
+ * Copyright 2001-2002 Pavel Machek <pavel@suse.cz>
+ * Copyright 2001 Patrick Mochel <mochel@osdl.org>
+ */
+
+/* image of the saved processor state */
+struct suspend2_saved_context {
+	/* general registers */
+	__u32 r[15];
+
+	/* coprocessor 15 registers */
+/*	__u32 ID_code;    read only reg */
+/*	__u32 cache_type; read only reg */
+/*	__u32 TCM_stat;   read only reg */
+	__u32 CR;
+	__u32 TTBR;
+	__u32 DACR;
+	__u32 D_FSR;
+	__u32 I_FSR;
+	__u32 FAR;
+/*	__u32 COR;        write only reg */
+/*	__u32 TLBOR;      write only reg */
+	__u32 D_CLR;
+	__u32 I_CLR;
+	__u32 D_TCMRR;
+	__u32 I_TCMRR;
+	__u32 TLBLR;
+	__u32 FCSE;
+	__u32 CID;
+} __attribute__((packed));
+typedef struct suspend2_saved_context suspend2_saved_context_t;
+
+/* temporary storage */
+extern struct suspend2_saved_context suspend2_saved_context;
+
+static inline void suspend2_arch_save_processor_context(void)
+{
+	/* save general registers */
+	asm volatile ("stmia %0, {r4-r14}"
+		      :: "r" (suspend2_saved_context.r));
+	/* save coprocessor 15 registers */
+	asm volatile ("mrc p15, 0, %0, c1, c0, 0"
+		      : "=r" (suspend2_saved_context.CR));
+	asm volatile ("mrc p15, 0, %0, c3, c0, 0"
+		      : "=r" (suspend2_saved_context.DACR));
+	asm volatile ("mrc p15, 0, %0, c5, c0, 0"
+		      : "=r" (suspend2_saved_context.D_FSR));
+	asm volatile ("mrc p15, 0, %0, c5, c0, 1"
+		      : "=r" (suspend2_saved_context.I_FSR));
+	asm volatile ("mrc p15, 0, %0, c6, c0, 0"
+		      : "=r" (suspend2_saved_context.FAR));
+	asm volatile ("mrc p15, 0, %0, c9, c0, 0"
+		      : "=r" (suspend2_saved_context.D_CLR));
+	asm volatile ("mrc p15, 0, %0, c9, c0, 1"
+		      : "=r" (suspend2_saved_context.I_CLR));
+	asm volatile ("mrc p15, 0, %0, c9, c1, 0"
+		      : "=r" (suspend2_saved_context.D_TCMRR));
+	asm volatile ("mrc p15, 0, %0, c9, c1, 1"
+		      : "=r" (suspend2_saved_context.I_TCMRR));
+	asm volatile ("mrc p15, 0, %0, c10, c0, 0"
+		      : "=r" (suspend2_saved_context.TLBLR));
+	asm volatile ("mrc p15, 0, %0, c13, c0, 0"
+		      : "=r" (suspend2_saved_context.FCSE));
+	asm volatile ("mrc p15, 0, %0, c13, c0, 1"
+		      : "=r" (suspend2_saved_context.CID));
+	asm volatile ("mrc p15, 0, %0, c2, c0, 0"
+		      : "=r" (suspend2_saved_context.TTBR));
+}
+
+static inline void suspend2_arch_restore_processor_context(void)
+{
+	/* restore coprocessor 15 registers */
+	asm volatile ("mcr p15, 0, %0, c2, c0, 0"
+		      :: "r" (suspend2_saved_context.TTBR));
+	asm volatile ("mcr p15, 0, %0, c13, c0, 1"
+		      :: "r" (suspend2_saved_context.CID));
+	asm volatile ("mcr p15, 0, %0, c13, c0, 0"
+		      :: "r" (suspend2_saved_context.FCSE));
+	asm volatile ("mcr p15, 0, %0, c10, c0, 0"
+		      :: "r" (suspend2_saved_context.TLBLR));
+	asm volatile ("mcr p15, 0, %0, c9, c1, 1"
+		      :: "r" (suspend2_saved_context.I_TCMRR));
+	asm volatile ("mcr p15, 0, %0, c9, c1, 0"
+		      :: "r" (suspend2_saved_context.D_TCMRR));
+	asm volatile ("mcr p15, 0, %0, c9, c0, 1"
+		      :: "r" (suspend2_saved_context.I_CLR));
+	asm volatile ("mcr p15, 0, %0, c9, c0, 0"
+		      :: "r" (suspend2_saved_context.D_CLR));
+	asm volatile ("mcr p15, 0, %0, c6, c0, 0"
+		      :: "r" (suspend2_saved_context.FAR));
+	asm volatile ("mcr p15, 0, %0, c5, c0, 1"
+		      :: "r" (suspend2_saved_context.I_FSR));
+	asm volatile ("mcr p15, 0, %0, c5, c0, 0"
+		      :: "r" (suspend2_saved_context.D_FSR));
+	asm volatile ("mcr p15, 0, %0, c3, c0, 0"
+		      :: "r" (suspend2_saved_context.DACR));
+	asm volatile ("mcr p15, 0, %0, c1, c0, 0"
+		      :: "r" (suspend2_saved_context.CR));
+
+	/* restore general registers */
+	asm volatile ("ldmia r3, {r4-r14}" : "=m" (suspend2_saved_context.r));
+}
+
+static inline void save_context(void)
+{
+}
+
+static inline void restore_context(void)
+{
+}
+
+static inline void suspend2_arch_pre_copy(void)
+{
+}
+
+static inline void suspend2_arch_post_copy(void)
+{
+}
+
+static inline void suspend2_arch_pre_copyback(void)
+{
+}
+
+static inline void suspend2_arch_post_copyback(void)
+{
+}
+
+static inline void suspend2_arch_flush_caches(void)
+{
+}
+#endif
diff -urN oldtree/include/asm-i386/mach-default/mach_time.h newtree/include/asm-i386/mach-default/mach_time.h
--- oldtree/include/asm-i386/mach-default/mach_time.h	2006-01-28 16:36:00.000000000 +0000
+++ newtree/include/asm-i386/mach-default/mach_time.h	2006-01-28 17:08:36.207731232 +0000
@@ -79,24 +79,19 @@
 	return retval;
 }
 
-static inline unsigned long mach_get_cmos_time(void)
+/* __get_cmos_time
+ *
+ * Separated out from mach_get_cmos_time so that we can
+ * quickly get the cmos time when we don't care about
+ * whether the second has just started.
+ *
+ * Used from suspend and resume sysdev calls.
+ */
+static inline unsigned long __get_cmos_time(void)
 {
 	unsigned int year, mon, day, hour, min, sec;
-	int i;
 
-	/* The Linux interpretation of the CMOS clock register contents:
-	 * When the Update-In-Progress (UIP) flag goes from 1 to 0, the
-	 * RTC registers show the second which has precisely just started.
-	 * Let's hope other operating systems interpret the RTC the same way.
-	 */
-	/* read RTC exactly on falling edge of update flag */
-	for (i = 0 ; i < 1000000 ; i++)	/* may take up to 1 second... */
-		if (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP)
-			break;
-	for (i = 0 ; i < 1000000 ; i++)	/* must try at least 2.228 ms */
-		if (!(CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP))
-			break;
-	do { /* Isn't this overkill ? UIP above should guarantee consistency */
+	do {
 		sec = CMOS_READ(RTC_SECONDS);
 		min = CMOS_READ(RTC_MINUTES);
 		hour = CMOS_READ(RTC_HOURS);
@@ -104,6 +99,7 @@
 		mon = CMOS_READ(RTC_MONTH);
 		year = CMOS_READ(RTC_YEAR);
 	} while (sec != CMOS_READ(RTC_SECONDS));
+
 	if (!(CMOS_READ(RTC_CONTROL) & RTC_DM_BINARY) || RTC_ALWAYS_BCD)
 	  {
 	    BCD_TO_BIN(sec);
@@ -119,4 +115,24 @@
 	return mktime(year, mon, day, hour, min, sec);
 }
 
+static inline unsigned long mach_get_cmos_time(void)
+{
+	int i;
+
+	/* The Linux interpretation of the CMOS clock register contents:
+	 * When the Update-In-Progress (UIP) flag goes from 1 to 0, the
+	 * RTC registers show the second which has precisely just started.
+	 * Let's hope other operating systems interpret the RTC the same way.
+	 */
+	/* read RTC exactly on falling edge of update flag */
+	for (i = 0 ; i < 1000000 ; i++)	/* may take up to 1 second... */
+		if (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP)
+			break;
+	for (i = 0 ; i < 1000000 ; i++)	/* must try at least 2.228 ms */
+		if (!(CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP))
+			break;
+
+	return __get_cmos_time();
+}
+
 #endif /* !_MACH_TIME_H */
diff -urN oldtree/include/asm-i386/suspend.h newtree/include/asm-i386/suspend.h
--- oldtree/include/asm-i386/suspend.h	2006-01-28 16:36:00.000000000 +0000
+++ newtree/include/asm-i386/suspend.h	2006-01-28 17:08:36.208731080 +0000
@@ -3,6 +3,7 @@
  * Based on code
  * Copyright 2001 Patrick Mochel <mochel@osdl.org>
  */
+#include <linux/errno.h>
 #include <asm/desc.h>
 #include <asm/i387.h>
 
diff -urN oldtree/include/asm-i386/suspend2.h newtree/include/asm-i386/suspend2.h
--- oldtree/include/asm-i386/suspend2.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/include/asm-i386/suspend2.h	2006-01-28 17:08:36.209730928 +0000
@@ -0,0 +1,288 @@
+ /*
+  * Copyright 2003-2005 Nigel Cunningham <nigel@suspend2.net>
+  * Based on code
+  * Copyright 2001-2002 Pavel Machek <pavel@suse.cz>
+  * Based on code
+  * Copyright 2001 Patrick Mochel <mochel@osdl.org>
+  */
+#include <linux/irq.h>
+#include <asm/desc.h>
+#include <asm/i387.h>
+#include <asm/tlbflush.h>
+#include <asm/desc.h>
+#include <asm/processor.h>
+
+/* image of the saved processor states */
+struct suspend2_saved_context {
+	u32 eax, ebx, ecx, edx;
+	u32 esp, ebp, esi, edi;
+	u16 es, fs, gs, ss;
+	u32 cr0, cr2, cr3, cr4;
+	u16 gdt_pad;
+	u16 gdt_limit;
+	u32 gdt_base;
+	u16 idt_pad;
+	u16 idt_limit;
+	u32 idt_base;
+	u16 ldt;
+	u16 tss;
+	u32 tr;
+	u32 safety;
+	u32 return_address;
+	u32 eflags;
+} __attribute__((packed));
+typedef struct suspend2_saved_context suspend2_saved_context_t;
+
+/* temporary storage */
+extern struct suspend2_saved_context suspend2_saved_context;
+
+/*
+ * save_processor_context
+ * 
+ * Save the state of the processor before we go to sleep.
+ *
+ * return_stack is the value of the stack pointer (%esp) as the caller sees it.
+ * A good way could not be found to obtain it from here (don't want to make
+ * _too_ many assumptions about the layout of the stack this far down.) Also,
+ * the handy little __builtin_frame_pointer(level) where level > 0, is blatantly
+ * buggy - it returns the value of the stack at the proper location, not the 
+ * location, like it should (as of gcc 2.91.66)
+ * 
+ * Note that the context and timing of this function is pretty critical.
+ * With a minimal amount of things going on in the caller and in here, gcc
+ * does a good job of being just a dumb compiler.  Watch the assembly output
+ * if anything changes, though, and make sure everything is going in the right
+ * place. 
+ */
+static inline void suspend2_arch_save_processor_context(void)
+{
+	kernel_fpu_begin();
+
+	/*
+	 * descriptor tables
+	 */
+	asm volatile ("sgdt (%0)" : "=m" (suspend2_saved_context.gdt_limit));
+	asm volatile ("sidt (%0)" : "=m" (suspend2_saved_context.idt_limit));
+	asm volatile ("sldt (%0)" : "=m" (suspend2_saved_context.ldt));
+	asm volatile ("str (%0)"  : "=m" (suspend2_saved_context.tr));
+
+	/*
+	 * save the general registers.
+	 * note that gcc has constructs to specify output of certain registers,
+	 * but they're not used here, because it assumes that you want to modify
+	 * those registers, so it tries to be smart and save them beforehand.
+	 * It's really not necessary, and kinda fishy (check the assembly output),
+	 * so it's avoided. 
+	 */
+	asm volatile ("movl %%esp, (%0)" : "=m" (suspend2_saved_context.esp));
+	asm volatile ("movl %%eax, (%0)" : "=m" (suspend2_saved_context.eax));
+	asm volatile ("movl %%ebx, (%0)" : "=m" (suspend2_saved_context.ebx));
+	asm volatile ("movl %%ecx, (%0)" : "=m" (suspend2_saved_context.ecx));
+	asm volatile ("movl %%edx, (%0)" : "=m" (suspend2_saved_context.edx));
+	asm volatile ("movl %%ebp, (%0)" : "=m" (suspend2_saved_context.ebp));
+	asm volatile ("movl %%esi, (%0)" : "=m" (suspend2_saved_context.esi));
+	asm volatile ("movl %%edi, (%0)" : "=m" (suspend2_saved_context.edi));
+
+	/*
+	 * segment registers
+	 */
+	asm volatile ("movw %%es, %0" : "=r" (suspend2_saved_context.es));
+	asm volatile ("movw %%fs, %0" : "=r" (suspend2_saved_context.fs));
+	asm volatile ("movw %%gs, %0" : "=r" (suspend2_saved_context.gs));
+	asm volatile ("movw %%ss, %0" : "=r" (suspend2_saved_context.ss));
+
+	/*
+	 * control registers 
+	 */
+	asm volatile ("movl %%cr0, %0" : "=r" (suspend2_saved_context.cr0));
+	asm volatile ("movl %%cr2, %0" : "=r" (suspend2_saved_context.cr2));
+	asm volatile ("movl %%cr3, %0" : "=r" (suspend2_saved_context.cr3));
+	asm volatile ("movl %%cr4, %0" : "=r" (suspend2_saved_context.cr4));
+
+	/*
+	 * eflags
+	 */
+	asm volatile ("pushfl ; popl (%0)" : "=m" (suspend2_saved_context.eflags));
+}
+
+static void fix_processor_context(void)
+{
+	struct tss_struct *t = &per_cpu(init_tss,0);
+
+	/* This just modifies memory; should not be neccessary. But... This is
+	 * neccessary, because 386 hardware has concept of busy tsc or some
+	 * similar stupidity. */
+	set_tss_desc(0,t);
+	per_cpu(cpu_gdt_table,0)[GDT_ENTRY_TSS].b &= 0xfffffdff;
+
+	load_TR_desc();
+
+	load_LDT(&current->active_mm->context);	/* This does lldt */
+
+	/*
+	 * Now maybe reload the debug registers
+	 */
+	if (current->thread.debugreg[7]){
+		set_debugreg(&current->thread.debugreg[0], 0);
+		set_debugreg(&current->thread.debugreg[1], 1);
+		set_debugreg(&current->thread.debugreg[2], 2);
+		set_debugreg(&current->thread.debugreg[3], 3);
+		/* no 4 and 5 */
+		set_debugreg(&current->thread.debugreg[6], 6);
+		set_debugreg(&current->thread.debugreg[7], 7);
+	}
+
+}
+
+static void do_fpu_end(void)
+{
+	/* restore FPU regs if necessary */
+	/* Do it out of line so that gcc does not move cr0 load to some stupid
+	 * place */
+	kernel_fpu_end();
+}
+
+#if defined(CONFIG_SUSPEND2) || defined(CONFIG_SMP)
+static unsigned long c_loops_per_jiffy_ref __nosavedata;
+#endif
+
+#ifdef CONFIG_SUSPEND2
+#ifndef CONFIG_SMP
+extern unsigned long loops_per_jiffy;
+volatile static unsigned long cpu_khz_ref __nosavedata = 0;
+#endif
+
+static inline void suspend2_arch_pre_copy(void) { }
+static inline void suspend2_arch_post_copy(void) { }
+
+static inline void suspend2_arch_pre_copyback(void)
+{
+	/* We want to run from swsusp_pg_dir, since swsusp_pg_dir is stored in
+	 * constant place in memory.
+	 */
+
+	 __asm__( "movl %%ecx,%%cr3\n" ::"c"(__pa(swsusp_pg_dir)));
+	
+	c_loops_per_jiffy_ref =
+		current_cpu_data.loops_per_jiffy;
+#ifndef CONFIG_SMP
+	cpu_khz_ref = cpu_khz;
+	c_loops_per_jiffy_ref = loops_per_jiffy;
+#endif
+
+}
+
+/*
+ * restore_processor_context
+ * 
+ * Restore the processor context as it was before we went to sleep
+ * - descriptor tables
+ * - control registers
+ * - segment registers
+ * - flags
+ * 
+ * Note that it is critical that this function is declared inline.
+ * It was separated out from restore_state to make that function
+ * a little clearer, but it needs to be inlined because we won't have a
+ * stack when we get here (so we can't push a return address).
+ */
+static inline void suspend2_arch_restore_processor_context(void)
+{
+	/*
+	 * first restore %ds, so we can access our data properly
+	 */
+	asm volatile (".align 4");
+	asm volatile ("movw %0, %%ds" :: "r" ((u16)__KERNEL_DS));
+
+
+	/*
+	 * control registers
+	 */
+	asm volatile ("movl %0, %%cr4" :: "r" (suspend2_saved_context.cr4));
+	asm volatile ("movl %0, %%cr3" :: "r" (suspend2_saved_context.cr3));
+	asm volatile ("movl %0, %%cr2" :: "r" (suspend2_saved_context.cr2));
+	asm volatile ("movl %0, %%cr0" :: "r" (suspend2_saved_context.cr0));
+
+	/*
+	 * segment registers
+	 */
+	asm volatile ("movw %0, %%es" :: "r" (suspend2_saved_context.es));
+	asm volatile ("movw %0, %%fs" :: "r" (suspend2_saved_context.fs));
+	asm volatile ("movw %0, %%gs" :: "r" (suspend2_saved_context.gs));
+	asm volatile ("movw %0, %%ss" :: "r" (suspend2_saved_context.ss));
+
+	/*
+	 * the other general registers
+	 *
+	 * note that even though gcc has constructs to specify memory 
+	 * input into certain registers, it will try to be too smart
+	 * and save them at the beginning of the function.  This is esp.
+	 * bad since we don't have a stack set up when we enter, and we 
+	 * want to preserve the values on exit. So, we set them manually.
+	 */
+	asm volatile ("movl %0, %%esp" :: "m" (suspend2_saved_context.esp));
+	asm volatile ("movl %0, %%ebp" :: "m" (suspend2_saved_context.ebp));
+	asm volatile ("movl %0, %%eax" :: "m" (suspend2_saved_context.eax));
+	asm volatile ("movl %0, %%ebx" :: "m" (suspend2_saved_context.ebx));
+	asm volatile ("movl %0, %%ecx" :: "m" (suspend2_saved_context.ecx));
+	asm volatile ("movl %0, %%edx" :: "m" (suspend2_saved_context.edx));
+	asm volatile ("movl %0, %%esi" :: "m" (suspend2_saved_context.esi));
+	asm volatile ("movl %0, %%edi" :: "m" (suspend2_saved_context.edi));
+
+	/*
+	 * now restore the descriptor tables to their proper values
+	 * ltr is done in fix_processor_context().
+	 */
+
+	asm volatile ("lgdt (%0)" :: "m" (suspend2_saved_context.gdt_limit));
+	asm volatile ("lidt (%0)" :: "m" (suspend2_saved_context.idt_limit));
+	asm volatile ("lldt (%0)" :: "m" (suspend2_saved_context.ldt));
+
+	/* tell gcc that we clobbered all the registers... 
+	 * otherwise it might keep some addresses there.
+	 * Unfortunately gcc 4 thinks it's smart and will
+	 * error out if we tell it we're clobbering ebp as
+	 * well. So we have to lie. 
+	 */
+	asm volatile ("" : : : "esp", "eax", "ebx", "ecx", "edx", "esi", "edi");
+	
+	if (boot_cpu_has(X86_FEATURE_SEP))
+		enable_sep_cpu();
+
+	fix_processor_context();
+
+	/*
+	 * the flags
+	 */
+	asm volatile ("pushl %0 ; popfl" :: "m" (suspend2_saved_context.eflags));
+
+	do_fpu_end();
+
+	mtrr_ap_init();
+	mcheck_init(&boot_cpu_data);
+}
+	
+static inline void suspend2_arch_flush_caches(void)
+{
+#ifdef CONFIG_SMP
+	cpu_clear(0, per_cpu(cpu_tlbstate,
+				0).active_mm->cpu_vm_mask);
+#endif
+	wbinvd();
+	__flush_tlb_all();
+	
+}
+
+static inline void suspend2_arch_post_copyback(void)
+{
+	BUG_ON(!irqs_disabled());
+
+	current_cpu_data.loops_per_jiffy =
+		c_loops_per_jiffy_ref;
+#ifndef CONFIG_SMP
+	loops_per_jiffy = c_loops_per_jiffy_ref;
+	cpu_khz = cpu_khz_ref;
+#endif
+}
+
+#endif
diff -urN oldtree/include/asm-i386/tlbflush.h newtree/include/asm-i386/tlbflush.h
--- oldtree/include/asm-i386/tlbflush.h	2006-01-28 16:36:00.000000000 +0000
+++ newtree/include/asm-i386/tlbflush.h	2006-01-28 17:08:36.209730928 +0000
@@ -84,6 +84,7 @@
 #define flush_tlb() __flush_tlb()
 #define flush_tlb_all() __flush_tlb_all()
 #define local_flush_tlb() __flush_tlb()
+#define local_flush_tlb_all() __flush_tlb_all()
 
 static inline void flush_tlb_mm(struct mm_struct *mm)
 {
@@ -116,6 +117,10 @@
 extern void flush_tlb_current_task(void);
 extern void flush_tlb_mm(struct mm_struct *);
 extern void flush_tlb_page(struct vm_area_struct *, unsigned long);
+extern void do_flush_tlb_all(void *info);
+
+#define local_flush_tlb_all() \
+	do_flush_tlb_all(NULL)
 
 #define flush_tlb()	flush_tlb_current_task()
 
diff -urN oldtree/include/asm-ppc/cpu_context.h newtree/include/asm-ppc/cpu_context.h
--- oldtree/include/asm-ppc/cpu_context.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/include/asm-ppc/cpu_context.h	2006-01-28 17:08:36.209730928 +0000
@@ -0,0 +1,110 @@
+/*
+ * Written by Hu Gang (hugang@soulinfo.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/adb.h>
+#include <linux/pmu.h>
+#include <asm/mmu_context.h>
+
+/* image of the saved processor states */
+struct saved_context {
+	u32 lr, cr, sp, r2;
+	u32 r[20]; /* r12 - r31 */                                                 
+	u32 sprg[4];
+	u32 msr, sdr1, tb1, tb2;
+} __attribute__((packed));
+
+inline static void __save_processor_state(struct saved_context *s)
+{
+	/*asm volatile ("mflr 0; stw 0,%0" : "=m" (s->lr));*/
+	asm volatile ("mfcr 0; stw 0,%0" : "=m" (s->cr));
+	asm volatile ("stw 1,%0" : "=m" (s->sp));
+	asm volatile ("stw 2,%0" : "=m" (s->r2));
+	asm volatile ("stmw 12,%0" : "=m" (s->r));
+
+	/* Save MSR & SDR1 */
+	asm volatile ("mfmsr 4; stw 4,%0" : "=m" (s->msr));
+	asm volatile ("mfsdr1 4; stw 4,%0": "=m" (s->sdr1));
+
+	/* Get a stable timebase and save it */
+	asm volatile ("1:\n"
+		      "mftbu 4;stw 4,%0\n"
+		      "mftb  5;stw 5,%1\n"
+		      "mftbu 3\n"
+		      "cmpw 3,4;\n"
+			  "bne 1b" : 
+			  "=m" (s->tb1),
+			  "=m" (s->tb2));
+		
+	/* Save SPRGs */
+	asm volatile ("mfsprg 4,0; stw 4,%0 " : "=m" (s->sprg[0]));
+	asm volatile ("mfsprg 4,1; stw 4,%0 " : "=m" (s->sprg[1]));
+	asm volatile ("mfsprg 4,2; stw 4,%0 " : "=m" (s->sprg[2]));
+	asm volatile ("mfsprg 4,3; stw 4,%0 " : "=m" (s->sprg[3]));
+}
+
+inline static void __restore_processor_state(struct saved_context *s)
+{
+	/* Restore the BATs, and SDR1 */
+	asm volatile ("lwz 4,%0; mtsdr1 4" : "=m" (s->sdr1));
+	/* asm volatile ("lwz 3,%0" : "=m" (saved_context.msr)); */
+
+	asm volatile ("lwz 4,%0; mtsprg 0,4": "=m" (s->sprg[0]));
+	asm volatile ("lwz 4,%0; mtsprg 1,4": "=m" (s->sprg[1]));
+	asm volatile ("lwz 4,%0; mtsprg 2,4": "=m" (s->sprg[2]));
+	asm volatile ("lwz 4,%0; mtsprg 3,4": "=m" (s->sprg[3]));
+
+	/* Restore TB */
+	asm volatile ("li 3,0; mttbl 3; \n"
+		      "lwz 3,%0\n; lwz 4,%1\n"
+		      "mttbu 3; mttbl 4" :
+		      "=m" (s->tb1),
+		      "=m" (s->tb2));
+
+	/* Restore the callee-saved registers and return */
+	asm volatile ("lmw 12,%0" : "=m" (s->r)); 
+	asm volatile ("lwz 2,%0" : "=m" (s->r2));
+	asm volatile ("lwz 1,%0" : "=m" (s->sp));
+	asm volatile ("lwz 0,%0; mtcr 0" : "=m" (s->cr));
+	
+	/* tell gcc that we clobbered all the registers... 
+	 * otherwise it might keep some addresses there. */
+	asm volatile ("" : : : "r13", "r14", "r15", "r16", "r17", "r18", "r19", "r20", "r21", "r22", "r23", "r24", "r25", "r26", "r27", "r28", "r29", "r30", "r31");
+	/*asm volatile ("lwz 0,%0; mtlr 0" : "=m" (s->lr));*/
+}
+
+static inline void save_context(void)
+{
+#ifdef CONFIG_ADB_PMU
+	printk("pmu suspend\n");
+	pmu_suspend();
+#endif
+}
+
+extern void enable_kernel_altivec(void);
+
+static inline void restore_context(void)
+{
+	printk("set context: <%p>\n", current);
+	set_context(current->active_mm->context,
+			current->active_mm->pgd);
+
+#ifdef CONFIG_ADB_PMU
+	printk("pmu_resume\n");
+	pmu_resume();
+#endif
+
+#ifdef CONFIG_ALTIVEC
+	if (cur_cpu_spec->cpu_features & CPU_FTR_ALTIVEC) {
+		printk("enable altivec\n");
+		enable_kernel_altivec();
+	}
+#endif
+	printk("enable fp\n");
+	enable_kernel_fp();
+}
diff -urN oldtree/include/asm-ppc/suspend2.h newtree/include/asm-ppc/suspend2.h
--- oldtree/include/asm-ppc/suspend2.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/include/asm-ppc/suspend2.h	2006-01-28 17:08:36.210730776 +0000
@@ -0,0 +1,47 @@
+/*
+ * Written by Hu Gang (hugang@soulinfo.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include "asm/cpu_context.h"
+
+typedef struct saved_context suspend2_saved_context_t;
+
+extern struct saved_context suspend2_saved_context;
+
+static inline void suspend2_arch_save_processor_context(void)
+{
+	__save_processor_state(&suspend2_saved_context);
+}
+
+static inline void suspend2_arch_restore_processor_context(void)
+{
+	__restore_processor_state(&suspend2_saved_context);
+
+	restore_context();
+}
+
+static inline void suspend2_arch_pre_copy(void)
+{
+}
+
+static inline void suspend2_arch_post_copy(void)
+{
+}
+
+static inline void suspend2_arch_pre_copyback(void)
+{
+	save_context();
+}
+
+static inline void suspend2_arch_post_copyback(void)
+{
+}
+
+static inline void suspend2_arch_flush_caches(void)
+{
+}
diff -urN oldtree/include/asm-x86_64/suspend.h newtree/include/asm-x86_64/suspend.h
--- oldtree/include/asm-x86_64/suspend.h	2006-01-28 16:36:00.000000000 +0000
+++ newtree/include/asm-x86_64/suspend.h	2006-01-28 17:08:36.210730776 +0000
@@ -43,8 +43,6 @@
                        : /* no output */ \
                        :"r" ((thread)->debugreg##register))
 
-extern void fix_processor_context(void);
-
 #ifdef CONFIG_ACPI_SLEEP
 extern unsigned long saved_eip;
 extern unsigned long saved_esp;
diff -urN oldtree/include/asm-x86_64/suspend2.h newtree/include/asm-x86_64/suspend2.h
--- oldtree/include/asm-x86_64/suspend2.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/include/asm-x86_64/suspend2.h	2006-01-28 17:08:36.211730624 +0000
@@ -0,0 +1,361 @@
+ /*
+  * Copyright 2005 Nigel Cunningham <nigel@suspend2.net>
+  * Based on code
+  * Copyright 2001-2002 Pavel Machek <pavel@suse.cz>
+  * Based on code
+  * Copyright 2001 Patrick Mochel <mochel@osdl.org>
+  */
+
+#include <linux/irq.h>
+#include <asm/desc.h>
+#include <asm/i387.h>
+#include <asm/tlbflush.h>
+#include <asm/desc.h>
+#include <asm/proto.h>
+#include <asm/page.h>
+
+extern pgd_t *temp_level4_pgt;
+extern int suspend2_mapping_prepare(void);
+
+/* image of the saved processor states */
+struct suspend2_saved_context {
+	unsigned long eax, ebx, ecx, edx;
+	unsigned long esp, ebp, esi, edi;
+	unsigned long r8, r9, r10, r11;
+	unsigned long r12, r13, r14, r15;
+
+	u16 ds, es, fs, gs, ss;
+	unsigned long gs_base, gs_kernel_base, fs_base;
+	unsigned long cr0, cr2, cr3, cr4, cr8;
+	u16 gdt_pad;
+	u16 gdt_limit;
+	unsigned long gdt_base;
+	u16 idt_pad;
+	u16 idt_limit;
+	unsigned long idt_base;
+	u16 ldt;
+	u16 tss;
+	unsigned long tr;
+	unsigned long safety;
+	unsigned long return_address;
+	unsigned long eflags;
+} __attribute__((packed));
+
+typedef struct suspend2_saved_context suspend2_saved_context_t;
+
+/* temporary storage */
+extern struct suspend2_saved_context suspend2_saved_context;
+
+/*
+ * save_processor_context
+ * 
+ * Save the state of the processor before we go to sleep.
+ *
+ * return_stack is the value of the stack pointer (%esp) as the caller sees it.
+ * A good way could not be found to obtain it from here (don't want to make _too_
+ * many assumptions about the layout of the stack this far down.) Also, the 
+ * handy little __builtin_frame_pointer(level) where level > 0, is blatantly 
+ * buggy - it returns the value of the stack at the proper location, not the 
+ * location, like it should (as of gcc 2.91.66)
+ * 
+ * Note that the context and timing of this function is pretty critical.
+ * With a minimal amount of things going on in the caller and in here, gcc
+ * does a good job of being just a dumb compiler.  Watch the assembly output
+ * if anything changes, though, and make sure everything is going in the right
+ * place. 
+ */
+static inline void suspend2_arch_save_processor_context(void)
+{
+	kernel_fpu_begin();
+
+	/*
+	 * descriptor tables
+	 */
+	asm volatile ("sgdt %0" : "=m" (suspend2_saved_context.gdt_limit));
+	asm volatile ("sidt %0" : "=m" (suspend2_saved_context.idt_limit));
+	asm volatile ("str %0"  : "=m" (suspend2_saved_context.tr));
+
+	/*
+	 * segment registers
+	 */
+	asm volatile ("movw %%ds, %0" : "=r" (suspend2_saved_context.ds));
+	asm volatile ("movw %%es, %0" : "=r" (suspend2_saved_context.es));
+	asm volatile ("movw %%fs, %0" : "=r" (suspend2_saved_context.fs));
+	asm volatile ("movw %%gs, %0" : "=r" (suspend2_saved_context.gs));
+	asm volatile ("movw %%ss, %0" : "=r" (suspend2_saved_context.ss));
+
+	rdmsrl(MSR_FS_BASE, suspend2_saved_context.fs_base);
+	rdmsrl(MSR_GS_BASE, suspend2_saved_context.gs_base);
+	rdmsrl(MSR_KERNEL_GS_BASE, suspend2_saved_context.gs_kernel_base);
+
+	/*
+	 * control registers 
+	 */
+	asm volatile ("movq %%cr0, %0" : "=r" (suspend2_saved_context.cr0));
+	asm volatile ("movq %%cr2, %0" : "=r" (suspend2_saved_context.cr2));
+	asm volatile ("movq %%cr3, %0" : "=r" (suspend2_saved_context.cr3));
+	asm volatile ("movq %%cr4, %0" : "=r" (suspend2_saved_context.cr4));
+	asm volatile ("movq %%cr8, %0" : "=r" (suspend2_saved_context.cr8));
+	
+	/*
+	 * save the general registers.
+	 * note that gcc has constructs to specify output of certain registers,
+	 * but they're not used here, because it assumes that you want to modify
+	 * those registers, so it tries to be smart and save them beforehand.
+	 * It's really not necessary, and kinda fishy (check the assembly output),
+	 * so it's avoided. 
+	 */
+
+	asm volatile ("movq %%rsp, %0" : "=m" (suspend2_saved_context.esp));
+
+	asm volatile ("movq %%rax, %0" : "=m" (suspend2_saved_context.eax));
+	asm volatile ("movq %%rbx, %0" : "=m" (suspend2_saved_context.ebx));
+	asm volatile ("movq %%rcx, %0" : "=m" (suspend2_saved_context.ecx));
+	asm volatile ("movq %%rdx, %0" : "=m" (suspend2_saved_context.edx));
+	asm volatile ("movq %%rbp, %0" : "=m" (suspend2_saved_context.ebp));
+	asm volatile ("movq %%rsi, %0" : "=m" (suspend2_saved_context.esi));
+	asm volatile ("movq %%rdi, %0" : "=m" (suspend2_saved_context.edi));
+	asm volatile ("movq %%r8, %0" : "=m" (suspend2_saved_context.r8));
+	asm volatile ("movq %%r9, %0" : "=m" (suspend2_saved_context.r9));
+	asm volatile ("movq %%r10, %0" : "=m" (suspend2_saved_context.r10));
+	asm volatile ("movq %%r11, %0" : "=m" (suspend2_saved_context.r11));
+	asm volatile ("movq %%r12, %0" : "=m" (suspend2_saved_context.r12));
+	asm volatile ("movq %%r13, %0" : "=m" (suspend2_saved_context.r13));
+	asm volatile ("movq %%r14, %0" : "=m" (suspend2_saved_context.r14));
+	asm volatile ("movq %%r15, %0" : "=m" (suspend2_saved_context.r15));
+
+	/*
+	 * eflags
+	 */
+	asm volatile ("pushfq ; popq %0" : "=m" (suspend2_saved_context.eflags));
+
+}
+
+static void fix_processor_context(void)
+{
+	struct tss_struct * t = &per_cpu(init_tss,0);
+
+	set_tss_desc(0,t);	/* This just modifies memory; should not be neccessary. But... This is neccessary, because 386 hardware has concept of busy tsc or some similar stupidity. */
+	cpu_gdt_table[0][GDT_ENTRY_TSS].type = 9;
+
+	syscall_init();				/* This sets MSR_*STAR and related */
+	load_TR_desc();
+	load_LDT(&current->active_mm->context);	/* This does lldt */
+
+	/*
+	 * Now maybe reload the debug registers
+	 */
+	if (current->thread.debugreg7){
+		loaddebug(&current->thread, 0);
+		loaddebug(&current->thread, 1);
+		loaddebug(&current->thread, 2);
+		loaddebug(&current->thread, 3);
+		/* no 4 and 5 */
+		loaddebug(&current->thread, 6);
+		loaddebug(&current->thread, 7);
+	}
+}
+
+static void do_fpu_end(void)
+{
+	/* restore FPU regs if necessary */
+	/* Do it out of line so that gcc does not move cr0 load to some stupid place */
+	kernel_fpu_end();
+	mxcsr_feature_mask_init();
+}
+
+/*
+ * restore_processor_context
+ * 
+ * Restore the processor context as it was before we went to sleep
+ * - descriptor tables
+ * - control registers
+ * - segment registers
+ * - flags
+ * 
+ * Note that it is critical that this function is declared inline.
+ * It was separated out from restore_state to make that function
+ * a little clearer, but it needs to be inlined because we won't have a
+ * stack when we get here (so we can't push a return address).
+ */
+static inline void restore_processor_context(void)
+{
+	/* 
+	 * Credit for this goes to the swsusp code. Restoring the
+	 * CPU context is the one thing we still do in the same
+	 * way, and swsusp did it right first.
+	 *
+	 * 0xffffffff80000000UL is __START_KERNEL_map.
+	 */
+
+	__asm__ __volatile__(
+		"leaq	init_level4_pgt(%rip), %rax;		\n"
+		"subq	$0xffffffff80000000, %rax;		\n"
+		"movq	%rax, %cr3;				\n"
+		"movq	mmu_cr4_features(%rip), %rax;		\n"
+		"movq	%rax, %rdx;				\n"
+		"andq	$~(1<<7), %rdx;  # PGE			\n"
+		"movq	%rdx, %cr4;  # turn off PGE		\n"
+		"movq	%cr3, %rcx;  # flush TLB		\n"
+		"movq	%rcx, %cr3;				\n"
+		"movq	%rax, %cr4;  # turn PGE back on;	\n"
+
+		"movl	$24, %eax;				\n"
+		"movl	%eax, %ds				\n");
+	/*
+	 * the other general registers
+	 *
+	 * note that even though gcc has constructs to specify memory 
+	 * input into certain registers, it will try to be too smart
+	 * and save them at the beginning of the function.  This is esp.
+	 * bad since we don't have a stack set up when we enter, and we 
+	 * want to preserve the values on exit. So, we set them manually.
+	 */
+	asm volatile ("movq %0, %%rsp" :: "m" (suspend2_saved_context.esp));
+	asm volatile ("movq %0, %%rbp" :: "m" (suspend2_saved_context.ebp));
+	asm volatile ("movq %0, %%rbx" :: "m" (suspend2_saved_context.ebx));
+	asm volatile ("movq %0, %%rcx" :: "m" (suspend2_saved_context.ecx));
+	asm volatile ("movq %0, %%rdx" :: "m" (suspend2_saved_context.edx));
+	asm volatile ("movq %0, %%rsi" :: "m" (suspend2_saved_context.esi));
+	asm volatile ("movq %0, %%rdi" :: "m" (suspend2_saved_context.edi));
+	asm volatile ("movq %0, %%r8" :: "m" (suspend2_saved_context.r8));
+	asm volatile ("movq %0, %%r9" :: "m" (suspend2_saved_context.r9));
+	asm volatile ("movq %0, %%r10" :: "m" (suspend2_saved_context.r10));
+	asm volatile ("movq %0, %%r11" :: "m" (suspend2_saved_context.r11));
+	asm volatile ("movq %0, %%r12" :: "m" (suspend2_saved_context.r12));
+	asm volatile ("movq %0, %%r13" :: "m" (suspend2_saved_context.r13));
+	asm volatile ("movq %0, %%r14" :: "m" (suspend2_saved_context.r14));
+	asm volatile ("movq %0, %%r15" :: "m" (suspend2_saved_context.r15));
+
+	/*
+	 * the flags
+	 */
+	asm volatile ("pushq %0 ; popfq" :: "m" (suspend2_saved_context.eflags));
+	
+	asm volatile ("xorq	%rax, %rax");
+
+	/*
+	 * control registers
+	 */
+	asm volatile ("movq %0, %%cr8" :: "r" (suspend2_saved_context.cr8));
+	asm volatile ("movq %0, %%cr4" :: "r" (suspend2_saved_context.cr4));
+	asm volatile ("movq %0, %%cr3" :: "r" (suspend2_saved_context.cr3));
+	asm volatile ("movq %0, %%cr2" :: "r" (suspend2_saved_context.cr2));
+	asm volatile ("movq %0, %%cr0" :: "r" (suspend2_saved_context.cr0));
+
+	/*
+	 * now restore the descriptor tables to their proper values
+	 * ltr is done in fix_processor_context().
+	 */
+
+	asm volatile ("lgdt %0" :: "m" (suspend2_saved_context.gdt_limit));
+	asm volatile ("lidt %0" :: "m" (suspend2_saved_context.idt_limit));
+
+	/*
+	 * segment registers
+	 */
+	asm volatile ("movw %0, %%ds" :: "r" (suspend2_saved_context.ds));
+	asm volatile ("movw %0, %%es" :: "r" (suspend2_saved_context.es));
+	asm volatile ("movw %0, %%fs" :: "r" (suspend2_saved_context.fs));
+	load_gs_index(suspend2_saved_context.gs);
+	asm volatile ("movw %0, %%ss" :: "r" (suspend2_saved_context.ss));
+
+	wrmsrl(MSR_FS_BASE, suspend2_saved_context.fs_base);
+	wrmsrl(MSR_GS_BASE, suspend2_saved_context.gs_base);
+	wrmsrl(MSR_KERNEL_GS_BASE, suspend2_saved_context.gs_kernel_base);
+
+	/* tell gcc that we clobbered all the registers... 
+	 * otherwise it might keep some addresses there. */
+	asm volatile ("" : : : "rsp", "rbx", "rcx", "rdx", "rsi", "rdi", "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15");
+
+	fix_processor_context();
+
+	do_fpu_end();
+	
+	mtrr_ap_init();
+	mcheck_init(&boot_cpu_data);
+}
+
+#if defined(CONFIG_SUSPEND2) || defined(CONFIG_SMP)
+extern unsigned char * my_saved_context __nosavedata;
+static unsigned long c_loops_per_jiffy_ref[NR_CPUS] __nosavedata;
+#endif
+
+#ifdef CONFIG_SUSPEND2
+#ifndef CONFIG_SMP
+extern unsigned long loops_per_jiffy;
+volatile static unsigned long cpu_khz_ref __nosavedata = 0;
+#endif
+
+/* 
+ * APIC support: These routines save the APIC
+ * configuration for the CPU on which they are
+ * being executed
+ */
+extern void suspend_apic_save_state(void);
+extern void suspend_apic_reload_state(void);
+
+static inline void suspend2_arch_pre_copy(void)
+{
+}
+
+static inline void suspend2_arch_post_copy(void)
+{
+}
+
+static inline void suspend2_arch_pre_copyback(void)
+{
+	/* We want to run from swsusp_pg_dir, since swsusp_pg_dir is stored in
+	 * constant place in memory.
+	 */
+
+	suspend2_mapping_prepare();
+
+	asm volatile ("movq	$0xffff810000000000, %rdx");
+	asm volatile ("movq	temp_level4_pgt(%rip), %rax");
+	asm volatile ("subq	%rdx, %rax");
+	asm volatile ("movq	%rax, %cr3");
+
+	wbinvd();
+	__flush_tlb_all();
+	
+	c_loops_per_jiffy_ref[0] =
+		current_cpu_data.loops_per_jiffy;
+#ifndef CONFIG_SMP
+	cpu_khz_ref = cpu_khz;
+	c_loops_per_jiffy_ref[0] = loops_per_jiffy;
+#endif
+	
+}
+
+static inline void suspend2_arch_restore_processor_context(void)
+{
+	restore_processor_context();
+}
+	
+static inline void suspend2_arch_flush_caches(void)
+{
+#ifdef CONFIG_SMP
+	clear_bit(0, &read_pda(active_mm)->cpu_vm_mask);
+#endif
+	wbinvd();
+	__flush_tlb_all();
+	
+}
+
+static inline void suspend2_arch_post_copyback(void)
+{
+	/* Get other CPUs to restore their contexts and flush their tlbs. */
+	clear_suspend_state(SUSPEND_FREEZE_SMP);
+	
+	BUG_ON(!irqs_disabled());
+
+	current_cpu_data.loops_per_jiffy =
+		c_loops_per_jiffy_ref[0];
+#ifndef CONFIG_SMP
+	loops_per_jiffy = c_loops_per_jiffy_ref[0];
+	cpu_khz = cpu_khz_ref;
+#endif
+}
+
+#endif
diff -urN oldtree/include/linux/bio.h newtree/include/linux/bio.h
--- oldtree/include/linux/bio.h	2006-01-28 16:36:00.000000000 +0000
+++ newtree/include/linux/bio.h	2006-01-28 17:08:36.212730472 +0000
@@ -124,6 +124,7 @@
 #define BIO_BOUNCED	5	/* bio is a bounce bio */
 #define BIO_USER_MAPPED 6	/* contains user pages */
 #define BIO_EOPNOTSUPP	7	/* not supported */
+#define BIO_SUSPEND2	8	/* Suspend2 bio - for corruption checking */
 #define bio_flagged(bio, flag)	((bio)->bi_flags & (1 << (flag)))
 
 /*
diff -urN oldtree/include/linux/dyn_pageflags.h newtree/include/linux/dyn_pageflags.h
--- oldtree/include/linux/dyn_pageflags.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/include/linux/dyn_pageflags.h	2006-01-28 17:08:36.213730320 +0000
@@ -0,0 +1,66 @@
+/*
+ * include/linux/dyn_pageflags.h
+ *
+ * Copyright (C) 2004-2005 Nigel Cunningham <ncunningham@cyclades.com>
+ *
+ * This file is released under the GPLv2.
+ *
+ * It implements support for dynamically allocated bitmaps that are
+ * used for temporary or infrequently used pageflags, in lieu of
+ * bits in the struct page flags entry.
+ */
+
+#ifndef DYN_PAGEFLAGS_H
+#define DYN_PAGEFLAGS_H
+
+#include <linux/mm.h>
+
+typedef unsigned long *** dyn_pageflags_t;
+
+#define BITNUMBER(page) (page_to_pfn(page))
+
+#if BITS_PER_LONG == 32
+#define UL_SHIFT 5
+#else 
+#if BITS_PER_LONG == 64
+#define UL_SHIFT 6
+#else
+#error Bits per long not 32 or 64?
+#endif
+#endif
+
+#define BIT_NUM_MASK (sizeof(unsigned long) * 8 - 1)
+#define PAGE_NUM_MASK (~((1 << (PAGE_SHIFT + 3)) - 1))
+#define UL_NUM_MASK (~(BIT_NUM_MASK | PAGE_NUM_MASK))
+
+#define BITS_PER_PAGE (PAGE_SIZE << 3)
+#define PAGENUMBER(zone_offset) (zone_offset >> (PAGE_SHIFT + 3))
+#define PAGEINDEX(zone_offset) ((zone_offset & UL_NUM_MASK) >> UL_SHIFT)
+#define PAGEBIT(zone_offset) (zone_offset & BIT_NUM_MASK)
+
+#define PAGE_UL_PTR(bitmap, zone_num, zone_pfn) \
+       ((bitmap[zone_num][PAGENUMBER(zone_pfn)])+PAGEINDEX(zone_pfn))
+
+/* With the above macros defined, you can do...
+
+#define PagePageset1(page) (test_dynpageflag(&pageset1_map, page))
+#define SetPagePageset1(page) (set_dynpageflag(&pageset1_map, page))
+#define ClearPagePageset1(page) (clear_dynpageflag(&pageset1_map, page))
+*/
+
+#define BITMAP_FOR_EACH_SET(bitmap, counter) \
+	for (counter = get_next_bit_on(bitmap, -1); counter < max_pfn; \
+		counter = get_next_bit_on(bitmap, counter))
+
+extern void clear_dyn_pageflags(dyn_pageflags_t pagemap);
+extern int allocate_dyn_pageflags(dyn_pageflags_t *pagemap);
+extern int free_dyn_pageflags(dyn_pageflags_t *pagemap);
+extern int dyn_pageflags_pages_per_bitmap(void);
+extern int get_next_bit_on(dyn_pageflags_t bitmap, int counter);
+extern unsigned long *dyn_pageflags_ul_ptr(dyn_pageflags_t *bitmap,
+		struct page *pg);
+
+extern int test_dynpageflag(dyn_pageflags_t *bitmap, struct page *page);
+extern void set_dynpageflag(dyn_pageflags_t *bitmap, struct page *page);
+extern void clear_dynpageflag(dyn_pageflags_t *bitmap, struct page *page);
+#endif
diff -urN oldtree/include/linux/freezer.h newtree/include/linux/freezer.h
--- oldtree/include/linux/freezer.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/include/linux/freezer.h	2006-01-28 17:08:36.213730320 +0000
@@ -0,0 +1,28 @@
+/* Freezer declarations */
+
+#define FREEZER_ON 0
+#define ABORT_FREEZING 1
+
+#define FREEZER_KERNEL_THREADS 0
+#define FREEZER_ALL_THREADS 1
+
+#ifdef CONFIG_PM
+extern unsigned long freezer_state;
+
+#define test_freezer_state(bit) test_bit(bit, &freezer_state)
+#define set_freezer_state(bit) set_bit(bit, &freezer_state)
+#define clear_freezer_state(bit) clear_bit(bit, &freezer_state)
+
+#define freezer_is_on() (test_freezer_state(FREEZER_ON))
+
+extern void do_freeze_process(struct notifier_block *nl);
+
+#else
+
+#define test_freezer_state(bit) (0)
+#define set_freezer_state(bit) do { } while(0)
+#define clear_freezer_state(bit) do { } while(0)
+
+#define freezer_is_on() (0)
+
+#endif
diff -urN oldtree/include/linux/kernel.h newtree/include/linux/kernel.h
--- oldtree/include/linux/kernel.h	2006-01-28 16:36:00.000000000 +0000
+++ newtree/include/linux/kernel.h	2006-01-28 17:08:36.213730320 +0000
@@ -103,6 +103,8 @@
 	__attribute__ ((format (printf, 2, 0)));
 extern int snprintf(char * buf, size_t size, const char * fmt, ...)
 	__attribute__ ((format (printf, 3, 4)));
+extern int snprintf_used(char *buffer, int buffer_size,
+		const char *fmt, ...);
 extern int vsnprintf(char *buf, size_t size, const char *fmt, va_list args)
 	__attribute__ ((format (printf, 3, 0)));
 extern int scnprintf(char * buf, size_t size, const char * fmt, ...)
diff -urN oldtree/include/linux/kthread.h newtree/include/linux/kthread.h
--- oldtree/include/linux/kthread.h	2006-01-28 16:36:00.000000000 +0000
+++ newtree/include/linux/kthread.h	2006-01-28 17:08:36.214730168 +0000
@@ -23,10 +23,20 @@
  *
  * Returns a task_struct or ERR_PTR(-ENOMEM).
  */
+struct task_struct *__kthread_create(int (*threadfn)(void *data),
+				   void *data,
+				   unsigned long freezer_flags,
+				   const char namefmt[],
+				   va_list * args);
+
 struct task_struct *kthread_create(int (*threadfn)(void *data),
 				   void *data,
 				   const char namefmt[], ...);
 
+struct task_struct *kthread_nofreeze_create(int (*threadfn)(void *data),
+				   void *data,
+				   const char namefmt[], ...);
+
 /**
  * kthread_run: create and wake a thread.
  * @threadfn: the function to run until signal_pending(current).
@@ -35,14 +45,15 @@
  *
  * Description: Convenient wrapper for kthread_create() followed by
  * wake_up_process().  Returns the kthread, or ERR_PTR(-ENOMEM). */
-#define kthread_run(threadfn, data, namefmt, ...)			   \
-({									   \
-	struct task_struct *__k						   \
-		= kthread_create(threadfn, data, namefmt, ## __VA_ARGS__); \
-	if (!IS_ERR(__k))						   \
-		wake_up_process(__k);					   \
-	__k;								   \
-})
+
+extern struct task_struct * kthread_run(int (*threadfn)(void *data),
+					void *data,
+					const char namefmt[], ...);
+
+extern struct task_struct * kthread_nofreeze_run(int (*threadfn)(void *data),
+					void *data,
+					const char namefmt[], ...);
+
 
 /**
  * kthread_bind: bind a just-created kthread to a cpu.
diff -urN oldtree/include/linux/netlink.h newtree/include/linux/netlink.h
--- oldtree/include/linux/netlink.h	2006-01-28 16:36:00.000000000 +0000
+++ newtree/include/linux/netlink.h	2006-01-28 17:08:36.214730168 +0000
@@ -21,6 +21,8 @@
 #define NETLINK_DNRTMSG		14	/* DECnet routing messages */
 #define NETLINK_KOBJECT_UEVENT	15	/* Kernel messages to userspace */
 #define NETLINK_GENERIC		16
+#define NETLINK_SUSPEND2_USERUI	17	/* For suspend2's userui */
+#define NETLINK_SUSPEND2_USM	18	/* For suspend2's userui */
 
 #define MAX_LINKS 32		
 
diff -urN oldtree/include/linux/sched.h newtree/include/linux/sched.h
--- oldtree/include/linux/sched.h	2006-01-28 16:36:00.000000000 +0000
+++ newtree/include/linux/sched.h	2006-01-28 17:08:36.215730016 +0000
@@ -34,6 +34,7 @@
 #include <linux/percpu.h>
 #include <linux/topology.h>
 #include <linux/seccomp.h>
+#include <linux/notifier.h>
 
 #include <linux/auxvec.h>	/* For AT_VECTOR_SIZE */
 
@@ -807,7 +808,10 @@
 	int (*notifier)(void *priv);
 	void *notifier_data;
 	sigset_t *notifier_mask;
-	
+
+	/* todo list to be executed in the context of this thread */
+	struct notifier_block *todo;
+
 	void *security;
 	struct audit_context *audit_context;
 	seccomp_t seccomp;
@@ -898,7 +902,6 @@
 #define PF_MEMALLOC	0x00000800	/* Allocating memory */
 #define PF_FLUSHER	0x00001000	/* responsible for disk writeback */
 #define PF_USED_MATH	0x00002000	/* if unset the fpu must be initialized before use */
-#define PF_FREEZE	0x00004000	/* this task is being frozen for suspend now */
 #define PF_NOFREEZE	0x00008000	/* this thread should not be frozen */
 #define PF_FROZEN	0x00010000	/* frozen for system suspend */
 #define PF_FSTRANS	0x00020000	/* inside a filesystem transaction */
@@ -1385,79 +1388,37 @@
 
 #endif
 
-#ifdef CONFIG_PM
 /*
- * Check if a process has been frozen
+ * Check if there is a todo list request
  */
-static inline int frozen(struct task_struct *p)
+static inline int todo_list_active(void)
 {
-	return p->flags & PF_FROZEN;
+	return current->todo != NULL;
 }
 
-/*
- * Check if there is a request to freeze a process
- */
-static inline int freezing(struct task_struct *p)
+static inline void run_todo_list(void)
 {
-	return p->flags & PF_FREEZE;
+	notifier_call_chain(&current->todo, 0, current);
 }
 
-/*
- * Request that a process be frozen
- * FIXME: SMP problem. We may not modify other process' flags!
- */
-static inline void freeze(struct task_struct *p)
+static inline int try_todo_list(void)
 {
-	p->flags |= PF_FREEZE;
-}
-
-/*
- * Wake up a frozen process
- */
-static inline int thaw_process(struct task_struct *p)
-{
-	if (frozen(p)) {
-		p->flags &= ~PF_FROZEN;
-		wake_up_process(p);
-		return 1;
-	}
-	return 0;
-}
-
-/*
- * freezing is complete, mark process as frozen
- */
-static inline void frozen_process(struct task_struct *p)
-{
-	p->flags = (p->flags & ~PF_FREEZE) | PF_FROZEN;
-}
-
-extern void refrigerator(void);
-extern int freeze_processes(void);
-extern void thaw_processes(void);
-
-static inline int try_to_freeze(void)
-{
-	if (freezing(current)) {
-		refrigerator();
+	if (todo_list_active()) {
+		run_todo_list();
 		return 1;
 	} else
 		return 0;
 }
-#else
-static inline int frozen(struct task_struct *p) { return 0; }
-static inline int freezing(struct task_struct *p) { return 0; }
-static inline void freeze(struct task_struct *p) { BUG(); }
-static inline int thaw_process(struct task_struct *p) { return 1; }
-static inline void frozen_process(struct task_struct *p) { BUG(); }
-
-static inline void refrigerator(void) {}
-static inline int freeze_processes(void) { BUG(); return 0; }
-static inline void thaw_processes(void) {}
 
-static inline int try_to_freeze(void) { return 0; }
+/*
+ * Compatibility definitions to use the suspend checkpoints for the task todo
+ * list. These may be removed once all uses of try_to_free,  refrigerator and
+ * freezing have been removed.
+ */
+#define try_to_freeze try_todo_list
+#define refrigerator run_todo_list
+#define freezing(p) todo_list_active()
 
-#endif /* CONFIG_PM */
 #endif /* __KERNEL__ */
 
 #endif
diff -urN oldtree/include/linux/suspend.h newtree/include/linux/suspend.h
--- oldtree/include/linux/suspend.h	2006-01-28 16:36:00.000000000 +0000
+++ newtree/include/linux/suspend.h	2006-01-28 17:08:36.216729864 +0000
@@ -9,6 +9,7 @@
 #include <linux/config.h>
 #include <linux/init.h>
 #include <linux/pm.h>
+#include <linux/suspend2.h>
 
 /* page backup entry */
 typedef struct pbe {
@@ -50,14 +51,20 @@
 extern int pm_prepare_console(void);
 extern void pm_restore_console(void);
 
+extern int freeze_processes(void);
+extern void thaw_processes(int which_threads);
 #else
 static inline int software_suspend(void)
 {
 	printk("Warning: fake suspend called\n");
 	return -EPERM;
 }
+static inline int freeze_processes(void) { return 0; }
+static inline void thaw_processes(int which_threads) { }
 #endif
 
+extern char resume2_file[256];
+
 #ifdef CONFIG_SUSPEND_SMP
 extern void disable_nonboot_cpus(void);
 extern void enable_nonboot_cpus(void);
@@ -69,8 +76,6 @@
 void save_processor_state(void);
 void restore_processor_state(void);
 struct saved_context;
-void __save_processor_state(struct saved_context *ctxt);
-void __restore_processor_state(struct saved_context *ctxt);
 unsigned long get_safe_page(gfp_t gfp_mask);
 
 /*
diff -urN oldtree/include/linux/suspend2.h newtree/include/linux/suspend2.h
--- oldtree/include/linux/suspend2.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/include/linux/suspend2.h	2006-01-28 17:08:36.217729712 +0000
@@ -0,0 +1,231 @@
+#ifndef _LINUX_SUSPEND2_H
+#define _LINUX_SUSPEND2_H
+
+#include <linux/dyn_pageflags.h>
+#include <linux/init.h>
+#ifdef CONFIG_ACPI
+#include <acpi/acpi_bus.h>
+#include <acpi/acpi_drivers.h>
+#endif
+
+/* arch/i386/mm/init.c */
+extern char __nosave_begin, __nosave_end;
+
+extern char __nosavedata swsusp_pg_dir[PAGE_SIZE]
+                  __attribute__ ((aligned (PAGE_SIZE)));
+
+#define SECTOR_SIZE 512
+
+/* kernel/power/process.c */
+
+/* kernel/power/main.c */
+extern unsigned long suspend_result;
+
+/* kernel/power/process.c */
+extern unsigned long suspend_debug_state;
+
+/* arch/i386/power/suspend2.c */
+extern unsigned long suspend_action;
+extern int suspend_io_time[2][2];
+
+extern dyn_pageflags_t pageset1_map;
+extern dyn_pageflags_t	pageset1_copy_map;
+
+#ifdef CONFIG_PM_DEBUG
+#define test_debug_state(bit) (test_bit(bit, &suspend_debug_state))
+#else
+#define test_debug_state(bit) (0)
+#endif
+
+#define test_result_state(bit) (test_bit(bit, &suspend_result))
+
+/* 
+ * First status register - this is suspend's return code.
+ *
+ * All the rest are in kernel/power/suspend2_common.h
+ */
+#define SUSPEND_ABORTED			0
+
+/* Second status register - ditto */
+#define SUSPEND_RETRY_RESUME		0
+
+/* Debug sections  - if debugging compiled in */
+enum {
+	SUSPEND_ANY_SECTION,
+	SUSPEND_FREEZER,
+	SUSPEND_EAT_MEMORY,
+	SUSPEND_PAGESETS,
+	SUSPEND_IO,
+	SUSPEND_BMAP,
+	SUSPEND_HEADER,
+	SUSPEND_WRITER,
+	SUSPEND_MEMORY,
+	SUSPEND_EXTENTS,
+	SUSPEND_SPINLOCKS,
+	SUSPEND_MEM_POOL,
+	SUSPEND_RANGE_PARANOIA,
+	SUSPEND_NOSAVE,
+	SUSPEND_INTEGRITY
+};
+
+/* debugging levels. */
+#define SUSPEND_STATUS		0
+#define SUSPEND_ERROR		2
+#define SUSPEND_LOW	 	3
+#define SUSPEND_MEDIUM	 	4
+#define SUSPEND_HIGH	  	5
+#define SUSPEND_VERBOSE		6
+
+/* second status register */
+enum {
+	SUSPEND_REBOOT,
+	SUSPEND_PAUSE,
+	SUSPEND_SLOW,
+	SUSPEND_NOPAGESET2,
+	SUSPEND_LOGALL,
+	SUSPEND_CAN_CANCEL,
+	SUSPEND_KEEP_IMAGE,
+	SUSPEND_FREEZER_TEST,
+	SUSPEND_FREEZER_TEST_SHOWALL,
+	SUSPEND_SINGLESTEP,
+	SUSPEND_PAUSE_NEAR_PAGESET_END,
+	SUSPEND_USE_ACPI_S4,
+	SUSPEND_TEST_FILTER_SPEED,
+	SUSPEND_FREEZE_TIMERS,
+	SUSPEND_DISABLE_SYSDEV_SUPPORT,
+	SUSPEND_VGA_POST,
+	SUSPEND_TEST_BIO,
+	SUSPEND_NO_PAGESET2,
+};
+
+#ifdef CONFIG_SUSPEND2
+#define test_action_state(bit) (test_bit(bit, &suspend_action))
+#define set_action_state(bit) (test_and_set_bit(bit, &suspend_action))
+#define clear_action_state(bit) (test_and_clear_bit(bit, &suspend_action))
+#else
+#define test_action_state(bit) (0)
+#endif
+
+extern void __suspend_message(unsigned long section, unsigned long level, int log_normally,
+		const char *fmt, ...);
+
+#ifdef CONFIG_PM_DEBUG
+#define suspend_message(sn, lev, log, fmt, a...) \
+do { \
+	if (test_debug_state(sn)) \
+		__suspend_message(sn, lev, log, fmt, ##a); \
+} while(0)
+#else /* CONFIG_PM_DEBUG */
+#define suspend_message(sn, lev, log, fmt, a...) \
+do { \
+	if (lev == 0) \
+		__suspend_message(sn, lev, log, fmt, ##a); \
+} while(0)
+#endif /* CONFIG_PM_DEBUG */
+  
+/* Suspend 2 */
+
+enum {
+	SUSPEND_DISABLED,
+	SUSPEND_RUNNING,
+	SUSPEND_RESUME_DEVICE_OK,
+	SUSPEND_NORESUME_SPECIFIED,
+	SUSPEND_COMMANDLINE_ERROR,
+	SUSPEND_IGNORE_IMAGE,
+	SUSPEND_SANITY_CHECK_PROMPT,
+	SUSPEND_FREEZER_ON,
+	SUSPEND_BLOCK_PAGE_ALLOCATIONS,
+	SUSPEND_USE_MEMORY_POOL,
+	SUSPEND_STAGE2_CONTINUE,
+	SUSPEND_FREEZE_SMP,
+	SUSPEND_PAGESET2_NOT_LOADED,
+	SUSPEND_CONTINUE_REQ,
+	SUSPEND_RESUMED_BEFORE,
+	SUSPEND_RUNNING_INITRD,
+	SUSPEND_RESUME_NOT_DONE,
+	SUSPEND_BOOT_TIME,
+	SUSPEND_NOW_RESUMING,
+	SUSPEND_SLAB_ALLOC_FALLBACK,
+	SUSPEND_IGNORE_LOGLEVEL,
+	SUSPEND_TIMER_FREEZER_ON,
+	SUSPEND_ACT_USED,
+	SUSPEND_DBG_USED,
+	SUSPEND_LVL_USED,
+	SUSPEND_TRYING_TO_RESUME,
+	SUSPEND_FORK_COPYBACK_THREAD,
+	SUSPEND_TRY_RESUME_RD,
+	SUSPEND_IGNORE_ROOTFS,
+};
+
+#define test_and_set_suspend_state(bit) \
+	(test_and_set_bit(bit, &software_suspend_state))
+
+#define get_suspend_state() 		(software_suspend_state)
+#define restore_suspend_state(saved_state) \
+	do { software_suspend_state = saved_state; } while(0)
+	
+/* --------------------------------------------------------------------- */
+#ifdef CONFIG_SUSPEND2
+
+/* Used in init dir files */
+extern unsigned long software_suspend_state;
+
+extern void suspend2_try_resume(void);
+extern int suspend_early_boot_message 
+	(int can_erase_image, int default_answer, char *warning_reason, ...);
+extern void suspend_handle_keypress(unsigned int keycode, int source);
+extern unsigned long suspend2_update_status (unsigned long value, unsigned long maximum,
+		const char *fmt, ...);
+extern void suspend2_prepare_status (int clearbar, const char *fmt, ...);
+
+#define test_suspend_state(bit) \
+	(test_bit(bit, &software_suspend_state))
+
+#define clear_suspend_state(bit) \
+	(clear_bit(bit, &software_suspend_state))
+
+#define set_suspend_state(bit) \
+	(set_bit(bit, &software_suspend_state))
+
+extern inline void suspend2_copyback_low(void);
+extern inline void suspend2_copyback_high(void);
+
+extern void suspend2_try_suspend(void);
+
+/* --------------------------------------------------------------------- */
+#else
+/* --------------------------------------------------------------------- */
+
+#define software_suspend_state		(0)
+#define clear_suspend_state(bit)	do { } while (0)
+#define test_suspend_state(bit) 	(0)
+#define set_suspend_state(bit)		do { } while(0)
+
+#define suspend2_try_resume()			do { } while(0)
+static inline int suspend_early_boot_message(int a, int b, char *c, ...)	{ return 0; }
+#define suspend_handle_keypress(a, b) 		do { } while(0)
+static inline unsigned long suspend2_update_status(unsigned long value, unsigned long maximum,
+		const char *fmt, ...)
+{
+	return maximum;
+}
+#define suspend2_prepare_status(a, ...)  do { } while(0)
+
+#endif /* CONFIG_SUSPEND2 */
+
+#if defined(CONFIG_SUSPEND2) && defined(CONFIG_ACPI)
+static inline int may_try_suspend2(u32 state)
+{
+	if (state == ACPI_STATE_S4) {
+		suspend2_try_suspend();
+		return 1;
+	}
+	return 0;
+}
+#else
+static inline int may_try_suspend2(u32 state)
+{
+	return 0;
+}
+#endif
+#endif /* _LINUX_SUSPEND2_H */
diff -urN oldtree/include/linux/workqueue.h newtree/include/linux/workqueue.h
--- oldtree/include/linux/workqueue.h	2006-01-28 16:36:00.000000000 +0000
+++ newtree/include/linux/workqueue.h	2006-01-28 17:08:36.217729712 +0000
@@ -51,9 +51,12 @@
 	} while (0)
 
 extern struct workqueue_struct *__create_workqueue(const char *name,
-						    int singlethread);
-#define create_workqueue(name) __create_workqueue((name), 0)
-#define create_singlethread_workqueue(name) __create_workqueue((name), 1)
+						    int singlethread,
+						    unsigned long freezer_flag);
+#define create_workqueue(name) __create_workqueue((name), 0, 0)
+#define create_nofreeze_workqueue(name) __create_workqueue((name), 0, PF_NOFREEZE)
+#define create_singlethread_workqueue(name) __create_workqueue((name), 1, 0)
+#define create_nofreeze_singlethread_workqueue(name) __create_workqueue((name), 1, PF_NOFREEZE)
 
 extern void destroy_workqueue(struct workqueue_struct *wq);
 
diff -urN oldtree/init/do_mounts.c newtree/init/do_mounts.c
--- oldtree/init/do_mounts.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/init/do_mounts.c	2006-01-28 17:08:36.217729712 +0000
@@ -139,11 +139,16 @@
 	char s[32];
 	char *p;
 	dev_t res = 0;
-	int part;
+	int part, mount_result;
 
 #ifdef CONFIG_SYSFS
 	int mkdir_err = sys_mkdir("/sys", 0700);
-	if (sys_mount("sysfs", "/sys", "sysfs", 0, NULL) < 0)
+	/* 
+	 * When changing resume2 parameter for Software Suspend, sysfs may
+	 * already be mounted. 
+	 */
+	mount_result = sys_mount("sysfs", "/sys", "sysfs", 0, NULL);
+	if (mount_result < 0 && mount_result != -EBUSY)
 		goto out;
 #endif
 
@@ -195,7 +200,8 @@
 	res = try_name(s, part);
 done:
 #ifdef CONFIG_SYSFS
-	sys_umount("/sys", 0);
+	if (mount_result >= 0)
+		sys_umount("/sys", 0);
 out:
 	if (!mkdir_err)
 		sys_rmdir("/sys");
@@ -412,9 +418,25 @@
 
 	is_floppy = MAJOR(ROOT_DEV) == FLOPPY_MAJOR;
 
+	/* Suspend2:
+	 * By this point, suspend_early_init has been called to initialise our
+	 * proc interface. If modules are built in, they have registered (all
+	 * of the above via late_initcalls).
+	 * 
+	 * We have not yet looked to see if an image exists, however. If we
+	 * have an initrd, it is expected that the user will have set it up
+	 * to echo > /proc/suspend2/do_resume and thus initiate any
+	 * resume. If they don't do that, we do it immediately after the initrd
+	 * is finished (major issues if they mount filesystems rw from the
+	 * initrd! - they are warned. If there's no usable initrd, we do our
+	 * check next.
+	 */
 	if (initrd_load())
 		goto out;
 
+	if (test_suspend_state(SUSPEND_RESUME_NOT_DONE))
+		suspend2_try_resume();
+	
 	if (is_floppy && rd_doload && rd_load_disk(0))
 		ROOT_DEV = Root_RAM0;
 
diff -urN oldtree/init/do_mounts_initrd.c newtree/init/do_mounts_initrd.c
--- oldtree/init/do_mounts_initrd.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/init/do_mounts_initrd.c	2006-01-28 17:08:36.218729560 +0000
@@ -7,6 +7,7 @@
 #include <linux/romfs_fs.h>
 #include <linux/initrd.h>
 #include <linux/sched.h>
+#include <linux/suspend.h>
 
 #include "do_mounts.h"
 
@@ -58,10 +59,16 @@
 
 	pid = kernel_thread(do_linuxrc, "/linuxrc", SIGCHLD);
 	if (pid > 0) {
-		while (pid != sys_wait4(-1, NULL, 0, NULL))
+		while (pid != sys_wait4(-1, NULL, 0, NULL)) {
 			yield();
+			try_to_freeze();
+		}
 	}
 
+	if (test_suspend_state(SUSPEND_RESUME_NOT_DONE))
+		printk(KERN_ERR "Suspend2: Initrd lacks echo > /proc/suspend2/do_resume.\n");
+	clear_suspend_state(SUSPEND_BOOT_TIME);
+
 	/* move initrd to rootfs' /old */
 	sys_fchdir(old_fd);
 	sys_mount("/", ".", NULL, MS_MOVE, NULL);
diff -urN oldtree/init/main.c newtree/init/main.c
--- oldtree/init/main.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/init/main.c	2006-01-28 17:08:36.219729408 +0000
@@ -694,7 +694,9 @@
 
 	/*
 	 * check if there is an early userspace init.  If yes, let it do all
-	 * the work
+	 * the work. For suspend2, we assume that it will do the right thing
+	 * with regard to trying to resume at the right place. When that
+	 * happens, the BOOT_TIME flag will be cleared.
 	 */
 
 	if (!ramdisk_execute_command)
diff -urN oldtree/kernel/audit.c newtree/kernel/audit.c
--- oldtree/kernel/audit.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/kernel/audit.c	2006-01-28 17:08:36.219729408 +0000
@@ -288,6 +288,9 @@
 			}
 		} else {
 			DECLARE_WAITQUEUE(wait, current);
+			
+			try_todo_list();
+
 			set_current_state(TASK_INTERRUPTIBLE);
 			add_wait_queue(&kauditd_wait, &wait);
 
diff -urN oldtree/kernel/fork.c newtree/kernel/fork.c
--- oldtree/kernel/fork.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/kernel/fork.c	2006-01-28 17:08:36.220729256 +0000
@@ -34,6 +34,7 @@
 #include <linux/swap.h>
 #include <linux/syscalls.h>
 #include <linux/jiffies.h>
+#include <linux/suspend.h>
 #include <linux/futex.h>
 #include <linux/rcupdate.h>
 #include <linux/ptrace.h>
@@ -165,7 +166,13 @@
 	if (!tsk)
 		return NULL;
 
-	ti = alloc_thread_info(tsk);
+	if (test_suspend_state(SUSPEND_FORK_COPYBACK_THREAD)) {
+		extern void * suspend2_get_nonconflicting_pages(int);
+		ti = suspend2_get_nonconflicting_pages(get_order(THREAD_SIZE));
+		printk("Starting a copyback thread %p\n", ti);
+	} else
+		ti = alloc_thread_info(tsk);
+
 	if (!ti) {
 		free_task_struct(tsk);
 		return NULL;
@@ -942,6 +949,8 @@
 	clear_tsk_thread_flag(p, TIF_SIGPENDING);
 	init_sigpending(&p->pending);
 
+	p->todo = NULL;
+
 	p->utime = cputime_zero;
 	p->stime = cputime_zero;
  	p->sched_time = 0;
diff -urN oldtree/kernel/kmod.c newtree/kernel/kmod.c
--- oldtree/kernel/kmod.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/kernel/kmod.c	2006-01-28 17:08:36.221729104 +0000
@@ -36,6 +36,7 @@
 #include <linux/mount.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/freezer.h>
 #include <asm/uaccess.h>
 
 extern int max_threads;
@@ -249,6 +250,9 @@
 	if (!khelper_wq)
 		return -EBUSY;
 
+	if (freezer_is_on())
+		return 0;
+
 	if (path[0] == '\0')
 		return 0;
 
diff -urN oldtree/kernel/kthread.c newtree/kernel/kthread.c
--- oldtree/kernel/kthread.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/kernel/kthread.c	2006-01-28 17:08:36.221729104 +0000
@@ -25,6 +25,7 @@
 	/* Information passed to kthread() from keventd. */
 	int (*threadfn)(void *data);
 	void *data;
+	unsigned long freezer_flags;
 	struct completion started;
 
 	/* Result passed back to kthread_create() from keventd. */
@@ -86,6 +87,10 @@
 	/* By default we can run anywhere, unlike keventd. */
 	set_cpus_allowed(current, CPU_MASK_ALL);
 
+	/* Set our freezer flags */
+	current->flags &= ~PF_NOFREEZE;
+	current->flags |= (create->freezer_flags & PF_NOFREEZE);
+
 	/* OK, tell user we're spawned, wait for stop or wakeup */
 	__set_current_state(TASK_INTERRUPTIBLE);
 	complete(&create->started);
@@ -119,16 +124,18 @@
 	complete(&create->done);
 }
 
-struct task_struct *kthread_create(int (*threadfn)(void *data),
+struct task_struct *__kthread_create(int (*threadfn)(void *data),
 				   void *data,
+				   unsigned long freezer_flags,
 				   const char namefmt[],
-				   ...)
+				   va_list * args)
 {
 	struct kthread_create_info create;
 	DECLARE_WORK(work, keventd_create_kthread, &create);
 
 	create.threadfn = threadfn;
 	create.data = data;
+	create.freezer_flags = freezer_flags;
 	init_completion(&create.started);
 	init_completion(&create.done);
 
@@ -141,18 +148,89 @@
 		queue_work(helper_wq, &work);
 		wait_for_completion(&create.done);
 	}
-	if (!IS_ERR(create.result)) {
-		va_list args;
-		va_start(args, namefmt);
+	if (!IS_ERR(create.result))
 		vsnprintf(create.result->comm, sizeof(create.result->comm),
-			  namefmt, args);
-		va_end(args);
-	}
+			  namefmt, *args);
 
 	return create.result;
 }
+
+struct task_struct *kthread_create(int (*threadfn)(void *data),
+				   void *data,
+				   const char namefmt[], ...)
+{
+	struct task_struct * result;
+
+	va_list args;
+	va_start(args, namefmt);
+	result = __kthread_create(threadfn, data, 0, namefmt, &args);
+	va_end(args);
+	return result;
+}
+
 EXPORT_SYMBOL(kthread_create);
 
+struct task_struct *kthread_nofreeze_create(int (*threadfn)(void *data),
+				   void *data,
+				   const char namefmt[], ...)
+{
+	struct task_struct * result;
+
+	va_list args;
+	va_start(args, namefmt);
+	result = __kthread_create(threadfn, data, PF_NOFREEZE, namefmt, &args);
+	va_end(args);
+	return result;
+}
+
+EXPORT_SYMBOL(kthread_nofreeze_create);
+
+/**
+ * kthread_run: create and wake a thread.
+ * @threadfn: the function to run until signal_pending(current).
+ * @data: data ptr for @threadfn.
+ * @namefmt: printf-style name for the thread.
+ *
+ * Description: Convenient wrapper for kthread_create() followed by
+ * wake_up_process().  Returns the kthread, or ERR_PTR(-ENOMEM).
+ **/
+struct task_struct * kthread_run(int (*threadfn)(void *data),
+		void *data,
+		const char namefmt[], ...)
+{
+	struct task_struct *__k;
+	va_list args;
+
+	va_start(args, namefmt);
+	__k = __kthread_create(threadfn, data, 0, namefmt, &args);
+	va_end(args);
+
+	if(!IS_ERR(__k))
+		wake_up_process(__k);
+
+	return __k;
+}
+
+EXPORT_SYMBOL(kthread_run);
+
+struct task_struct * kthread_nofreeze_run(int (*threadfn)(void *data),
+		void *data,
+		const char namefmt[], ...)
+{
+	struct task_struct *__k;
+	va_list args;
+
+	va_start(args, namefmt);
+	__k = __kthread_create(threadfn, data, PF_NOFREEZE, namefmt, &args);
+	va_end(args);
+
+	if(!IS_ERR(__k))
+		wake_up_process(__k);
+
+	return __k;
+}
+EXPORT_SYMBOL(kthread_nofreeze_run);
+
 void kthread_bind(struct task_struct *k, unsigned int cpu)
 {
 	BUG_ON(k->state != TASK_INTERRUPTIBLE);
diff -urN oldtree/kernel/power/Kconfig newtree/kernel/power/Kconfig
--- oldtree/kernel/power/Kconfig	2006-01-28 16:36:00.000000000 +0000
+++ newtree/kernel/power/Kconfig	2006-01-28 17:08:36.222728952 +0000
@@ -98,3 +98,75 @@
 	bool
 	depends on HOTPLUG_CPU && X86 && PM
 	default y
+
+config SUSPEND_DEBUG_PAGEALLOC
+	bool
+	depends on DEBUG_PAGEALLOC && (SOFTWARE_SUSPEND || SUSPEND2)
+	default y
+
+config SUSPEND2_CRYPTO
+	bool
+	depends on SUSPEND2 && CRYPTO
+	default y
+
+menuconfig SUSPEND2
+	bool "Suspend2"
+	select DYN_PAGEFLAGS
+	depends on PM
+	select HOTPLUG_CPU if SMP
+	---help---
+	  Suspend2 is the 'new and improved' suspend support.
+	  
+	  See the Suspend2 home page (suspend2.net)
+	  for FAQs, HOWTOs and other documentation.
+
+	comment 'Image Storage (you need at least one writer)'
+		depends on SUSPEND2
+	
+	config SUSPEND2_FILEWRITER
+		bool '  File Writer'
+		depends on SUSPEND2
+		---help---
+		  This option enables support for storing an image in a
+		  simple file. This should be possible, but we're still
+		  testing it.
+
+	config SUSPEND2_SWAPWRITER
+		bool '  Swap Writer'
+		depends on SWAP && SUSPEND2
+		---help---
+		  This option enables support for storing an image in your
+		  swap space.
+
+	comment 'General Options'
+		depends on SUSPEND2
+
+	config SUSPEND2_DEFAULT_RESUME2
+		string '  Default resume device name'
+		depends on SUSPEND2
+		---help---
+		  You normally need to add a resume2= parameter to your lilo.conf or
+		  equivalent. With this option properly set, the kernel has a value
+		  to default. No damage will be done if the value is invalid.
+
+	config SUSPEND2_CHECKSUMMING
+		bool '  Checksum images - developer option (SLOW!)'
+		depends on PM_DEBUG && SUSPEND2
+		---help---
+		  This option implements checksumming of images. It is not designed
+		  for everyone to use, but as a development tool.
+
+	config SUSPEND2_KEEP_IMAGE
+		bool '  Allow Keep Image Mode'
+		depends on SUSPEND2
+		---help---
+		  This option allows you to keep and image and reuse it. It is intended
+		  __ONLY__ for use with systems where all filesystems are mounted read-
+		  only (kiosks, for example). To use it, compile this option in and boot
+		  normally. Set the KEEP_IMAGE flag in /proc/suspend2 and suspend.
+		  When you resume, the image will not be removed. You will be unable to turn
+		  off swap partitions (assuming you are using the swap writer), but future
+		  suspends simply do a power-down. The image can be updated using the
+		  kernel command line parameter suspend_act= to turn off the keep image
+		  bit. Keep image mode is a little less user friendly on purpose - it
+		  should not be used without thought!
diff -urN oldtree/kernel/power/Makefile newtree/kernel/power/Makefile
--- oldtree/kernel/power/Makefile	2006-01-28 16:36:00.000000000 +0000
+++ newtree/kernel/power/Makefile	2006-01-28 17:08:36.222728952 +0000
@@ -3,10 +3,33 @@
 EXTRA_CFLAGS	+=	-DDEBUG
 endif
 
+CFLAGS_atomic_copy.o := -O0
+
 obj-y				:= main.o process.o console.o
 obj-$(CONFIG_PM_LEGACY)		+= pm.o
-obj-$(CONFIG_SOFTWARE_SUSPEND)	+= swsusp.o disk.o snapshot.o
 
 obj-$(CONFIG_SUSPEND_SMP)	+= smp.o
 
+# Order is important for compression and encryption - we
+# compress before encrypting.
+
+suspend_core-objs := io.o pagedir.o prepare_image.o \
+		extent.o suspend.o plugins.o \
+		pageflags.o ui.o proc.o \
+		power_off.o atomic_copy.o debug_pagealloc.o \
+		netlink.o
+
+#ifdef CONFIG_NET
+suspend_core-objs += storage.o
+#endif
+obj-$(CONFIG_SUSPEND2)			+= suspend_core.o
+obj-$(CONFIG_SUSPEND2_CRYPTO)		+= compression.o encryption.o
+
+obj-$(CONFIG_SUSPEND2_SWAPWRITER)	+= suspend_block_io.o suspend_swap.o
+obj-$(CONFIG_SUSPEND2_FILEWRITER)	+= suspend_block_io.o suspend_file.o
+
+obj-$(CONFIG_SUSPEND2_CHECKSUMMING)	+= suspend_checksums.o
+
+obj-$(CONFIG_SOFTWARE_SUSPEND)	+= swsusp.o disk.o snapshot.o
+
 obj-$(CONFIG_MAGIC_SYSRQ)	+= poweroff.o
diff -urN oldtree/kernel/power/atomic_copy.c newtree/kernel/power/atomic_copy.c
--- oldtree/kernel/power/atomic_copy.c	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/atomic_copy.c	2006-01-28 17:08:36.223728800 +0000
@@ -0,0 +1,473 @@
+/*
+ */
+
+#include <linux/suspend.h>
+#include <linux/highmem.h>
+#include <linux/kthread.h>
+#include <asm/setup.h>
+#include <asm/suspend2.h>
+#include <asm/param.h>
+#include <asm/thread_info.h>
+#include "suspend2_common.h"
+#include "io.h"
+#include "power_off.h"
+#include "version.h"
+#include "ui.h"
+#include "plugins.h"
+#include "atomic_copy.h"
+#include "suspend2.h"
+#include "checksum.h"
+#include "pageflags.h"
+#include "debug_pagealloc.h"
+#include "storage.h"
+
+volatile static int state1 __nosavedata = 0;
+volatile static int state2 __nosavedata = 0;
+volatile static int state3 __nosavedata = 0;
+volatile static int io_speed_save[2][2] __nosavedata;
+
+static dyn_pageflags_t __nosavedata origmap;
+static dyn_pageflags_t __nosavedata copymap;
+static unsigned long __nosavedata origoffset;
+static unsigned long __nosavedata copyoffset;
+static int __nosavedata loop;
+static __nosavedata int o_zone_num, c_zone_num;
+static __nosavedata int is_resuming;
+
+__nosavedata char resume_commandline[COMMAND_LINE_SIZE];
+
+static atomic_t atomic_copy_hold;
+static atomic_t restore_thread_ready;
+
+suspend2_saved_context_t suspend2_saved_context;	/* temporary storage */
+cpumask_t saved_affinity[NR_IRQS];
+
+struct zone_data {
+	unsigned long start_pfn;
+	unsigned long end_pfn;
+	int is_highmem;
+};
+
+static __nosavedata struct zone_data *zone_nosave;
+static __nosavedata int num_zones;
+
+/*
+ * Zone information might be overwritten during the copy back,
+ * so we copy the fields we need to a non-conflicting page and
+ * use it.
+ */
+static void init_nosave_zone_table(void)
+{
+	struct zone *zone;
+	
+	zone_nosave = (struct zone_data *) suspend2_get_nonconflicting_pages(0);
+
+	BUG_ON(!zone_nosave);
+
+	for_each_zone(zone) {
+		if (zone->spanned_pages) {
+			zone_nosave[num_zones].start_pfn = zone->zone_start_pfn;
+			zone_nosave[num_zones].end_pfn = zone->zone_start_pfn +
+				zone->spanned_pages - 1;
+			zone_nosave[num_zones].is_highmem = is_highmem(zone);
+		}
+		num_zones++;
+	}
+}
+
+/* For Suspend2, where this all has to be inlined */
+static unsigned long __get_next_bit_on(dyn_pageflags_t bitmap, int *zone_num, long counter)
+{
+	unsigned long *ul_ptr = NULL;
+	int reset_ul_ptr = 1;
+	BUG_ON(counter == max_pfn);
+
+	if (counter == -1) {
+		*zone_num = 0;
+
+		/* 
+		 * Test the end because the start can validly
+		 * be zero.
+		 */
+		while (!zone_nosave[*zone_num].end_pfn)
+			*zone_num++;
+		counter = zone_nosave[*zone_num].start_pfn - 1;
+	}
+
+	do {
+		counter++;
+		if (counter > zone_nosave[*zone_num].end_pfn) {
+			(*zone_num)++;
+			while (!zone_nosave[*zone_num].end_pfn && *zone_num < num_zones)
+				(*zone_num)++;
+			
+			if (*zone_num == num_zones)
+				return max_pfn;
+			counter = zone_nosave[*zone_num].start_pfn;
+			reset_ul_ptr = 1;
+		} else
+			if (!(counter & BIT_NUM_MASK))
+				reset_ul_ptr = 1;
+		if (reset_ul_ptr) {
+			reset_ul_ptr = 0;
+			ul_ptr = PAGE_UL_PTR(bitmap, *zone_num,
+					(counter - zone_nosave[*zone_num].start_pfn));
+			if (!*ul_ptr) {
+				counter += BIT_NUM_MASK - 1;
+				continue;
+			}
+		}
+	} while((counter < max_pfn) && !test_bit(PAGEBIT(counter), ul_ptr));
+	return counter;
+}
+
+/**
+ * copyback_prepare
+ * Functionality   : Preparatory steps for copying the original kernel back.
+ * Called From     : do_suspend2_lowlevel
+ **/
+
+static void copyback_prepare(void)
+{
+	int loop;
+
+	state1 = suspend_action;
+	state2 = suspend_debug_state;
+	state3 = console_loglevel;
+	for (loop = 0; loop < 4; loop++)
+		io_speed_save[loop/2][loop%2] = 
+			suspend_io_time[loop/2][loop%2];
+
+	init_nosave_zone_table();
+	
+	memcpy(resume_commandline, saved_command_line, COMMAND_LINE_SIZE);
+
+	suspend2_map_atomic_copy_pages();
+
+	suspend2_deactivate_storage(1);
+
+	/* Arch specific preparation */
+	suspend2_arch_pre_copyback();
+
+	device_suspend(PMSG_FREEZE);
+	local_irq_disable(); /* irqs might have been re-enabled on us by buggy drivers */
+
+	device_power_down(PMSG_FREEZE);
+	
+	barrier();
+	mb();
+}
+
+/*
+ * copyback_post
+ * Functionality   : Steps taken after copying back the original kernel at
+ *                   resume.
+ * Key Assumptions : Will be able to read back secondary pagedir (if 
+ *                   applicable).
+ * Called From     : do_suspend2_lowlevel
+ */
+
+static void copyback_post(void)
+{
+	int loop;
+
+	/* Arch specific code */
+	suspend2_arch_post_copyback();
+
+	suspend_action = state1;
+	suspend_debug_state = state2;
+	console_loglevel = state3;
+
+	for (loop = 0; loop < 4; loop++)
+		suspend_io_time[loop/2][loop%2] =
+			io_speed_save[loop/2][loop%2];
+
+	set_suspend_state(SUSPEND_NOW_RESUMING);
+	set_suspend_state(SUSPEND_PAGESET2_NOT_LOADED);
+
+	suspend2_unmap_atomic_copy_pages();
+
+	local_irq_disable();
+	device_power_up();
+	local_irq_enable();
+
+	device_resume();
+
+	if (pm_ops && pm_ops->finish && suspend2_powerdown_method > 3)
+		pm_ops->finish(suspend2_powerdown_method);
+
+	if (suspend2_activate_storage(1))
+		panic("Failed to reactivate our storage.");
+
+	userui_redraw();
+
+	check_shift_keys(1, "About to reload secondary pagedir.");
+
+	read_pageset2(0);
+	clear_suspend_state(SUSPEND_PAGESET2_NOT_LOADED);
+	
+	suspend2_prepare_status(DONT_CLEAR_BAR, "Cleaning up...");
+}
+
+
+/*
+ * suspend2_pre_copy
+ * Functionality   : Steps taken prior to saving CPU state and the image
+ *                   itself.
+ * Called From     : do_suspend2_lowlevel
+ */
+
+static void suspend2_pre_copy(void)
+{
+	suspend2_arch_pre_copy();
+
+	device_suspend(PMSG_FREEZE);
+
+	mb();
+	barrier();
+
+	local_irq_disable();
+
+	device_power_down(PMSG_FREEZE);
+}
+
+/*
+ * suspend2_post_copy
+ * Functionality   : Steps taken after saving CPU state to save the
+ *                   image and powerdown/reboot or recover on failure.
+ * Key Assumptions : save_image returns zero on success; otherwise we need to
+ *                   clean up and exit. The state on exiting this routine 
+ *                   should be essentially the same as if we have suspended,
+ *                   resumed and reached the end of copyback_post.
+ * Called From     : do_suspend2_lowlevel
+ */
+extern void suspend_power_down(void);
+
+static void suspend2_post_copy(void)
+{
+	suspend2_arch_post_copy();
+
+	if (!save_image_part1()) {
+		int temp_result;
+
+		suspend_power_down();
+
+		temp_result = read_pageset2(1);
+
+		/* If that failed, we're sunk. Panic! */
+		if (temp_result)
+			panic("Attempt to reload pagedir 2 failed. Try rebooting.");
+	}
+
+	if (!test_result_state(SUSPEND_ABORT_REQUESTED) &&
+	    !test_action_state(SUSPEND_TEST_FILTER_SPEED) &&
+	    !test_action_state(SUSPEND_TEST_BIO) &&
+	    suspend2_powerdown_method != PM_SUSPEND_MEM)
+		printk(KERN_EMERG name_suspend
+			"Suspend failed, trying to recover...\n");
+	barrier();
+	mb();
+}
+
+/*
+ * copyback_low
+ */
+
+static void copyback_low(void)
+{
+	unsigned long *origpage;
+	unsigned long *copypage;
+
+	o_zone_num = 0;
+	c_zone_num = 0;
+
+	origmap = pageset1_map;
+	copymap = pageset1_copy_map;
+
+	origoffset = __get_next_bit_on(origmap, &o_zone_num, -1);
+	copyoffset = __get_next_bit_on(copymap, &c_zone_num, -1);
+	
+	while (origoffset < max_pfn) {
+		if (!zone_nosave[o_zone_num].is_highmem) {
+			origpage = (unsigned long *) __va(origoffset << PAGE_SHIFT);
+			copypage = (unsigned long *) __va(copyoffset << PAGE_SHIFT);
+		
+			loop = (PAGE_SIZE / sizeof(unsigned long)) - 1;
+		
+			while (loop >= 0) {
+				*(origpage + loop) = *(copypage + loop);
+				loop--;
+			}
+		}
+		
+		origoffset = __get_next_bit_on(origmap, &o_zone_num, origoffset);
+		copyoffset = __get_next_bit_on(copymap, &c_zone_num, copyoffset);
+	}
+}
+
+/*
+ * copyback_high
+ */
+static void copyback_high(void)
+{
+	unsigned long *origpage;
+	unsigned long *copypage;
+
+	origoffset = get_next_bit_on(origmap, -1);
+	copyoffset = get_next_bit_on(copymap, -1);
+
+	while (origoffset < max_pfn) {
+		if (PageHighMem(pfn_to_page(origoffset))) {
+			origpage = (unsigned long *) kmap_atomic(pfn_to_page(origoffset), KM_USER1);
+			copypage = (unsigned long *) __va(copyoffset << PAGE_SHIFT);
+
+			memcpy(origpage, copypage, PAGE_SIZE);
+
+			kunmap_atomic(origpage, KM_USER1);
+		}
+		
+		origoffset = get_next_bit_on(origmap, origoffset);
+		copyoffset = get_next_bit_on(copymap, copyoffset);
+	}
+}
+
+void do_suspend2_lowlevel(int resume)
+{
+	is_resuming = resume;
+
+	if (resume) {
+		suspend2_arch_save_processor_context();	/* We need to capture registers and memory at "same time" */
+
+		copyback_prepare();
+
+		copyback_low(); /* 0 = use logical addresses */
+
+		suspend2_arch_restore_processor_context();
+	} else {
+		suspend2_pre_copy();
+
+		suspend2_arch_save_processor_context();
+	}
+	
+	if (is_resuming) {
+		suspend2_arch_flush_caches();
+
+		/* Now we are running with our old stack, and with registers copied
+		 * from suspend time. Let's copy back those remaining highmem pages. */
+		copyback_high();
+		suspend2_arch_flush_caches();
+
+		touch_softlockup_watchdog();
+		
+		suspend2_checksum_print_differences();
+
+		copyback_post();
+		
+	} else {
+		suspend2_post_copy();		/* If everything goes okay, this function does not return */
+	}
+}
+
+/* suspend_copy_pageset1
+ *
+ * Description:	Make the atomic copy of pageset1. We can't use copy_page (as we
+ * 		once did) because we can't be sure what side effects it has. On
+ * 		my old Duron, with 3DNOW, kernel_fpu_begin increments preempt
+ * 		count, making our preempt count at resume time 4 instead of 3.
+ * 		
+ * 		We don't want to call kmap_atomic unconditionally because it has
+ * 		the side effect of incrementing the preempt count, which will
+ * 		leave it one too high post resume (the page containing the
+ * 		preempt count will be copied after its incremented. This is
+ * 		essentially the same problem.
+ */
+
+void suspend2_copy_pageset1(void)
+{
+	unsigned long i, source_index, dest_index;
+
+	source_index = get_next_bit_on(pageset1_map, -1);
+	dest_index = get_next_bit_on(pageset1_copy_map, -1);
+
+	for (i = 0; i < pagedir1.pageset_size; i++) {
+		unsigned long *origvirt, *copyvirt;
+		struct page *origpage;
+		int loop = (PAGE_SIZE / sizeof(unsigned long)) - 1;
+
+		origpage = pfn_to_page(source_index);
+		
+		copyvirt = (unsigned long *) page_address(pfn_to_page(dest_index));
+
+	       	if (PageHighMem(origpage))
+			origvirt = kmap_atomic(origpage, KM_USER1);
+		else
+			origvirt = page_address(origpage);
+
+		while (loop >= 0) {
+			*(copyvirt + loop) = *(origvirt + loop);
+			loop--;
+		}
+		
+		if (PageHighMem(origpage))
+			kunmap_atomic(origvirt, KM_USER1);
+		
+		source_index = get_next_bit_on(pageset1_map, source_index);
+		dest_index = get_next_bit_on(pageset1_copy_map, dest_index);
+	}
+}
+
+int __suspend_atomic_restore(void *data)
+{
+	struct page *my_thread_info = virt_to_page(current->thread_info);
+
+	BUG_ON(PagePageset1(my_thread_info));
+	BUG_ON(THREAD_SIZE > PAGE_SIZE && PagePageset1(++my_thread_info));
+
+	atomic_set(&restore_thread_ready, 1);
+
+	while atomic_read(&atomic_copy_hold)
+		yield();
+
+	suspend2_prepare_status(DONT_CLEAR_BAR,	"Copying original kernel back");
+	
+	/* 
+	 * If you're hitting this BUG_ON, you have a process that's
+	 * not freezing which is started prior to this.
+	 */
+	BUG_ON(freeze_processes());
+
+	do_suspend2_lowlevel(1);
+
+	printk("Returned from do_suspend2_lowlevel when resuming?!");
+	BUG();
+	
+	return 0;
+}
+
+void suspend_atomic_restore(void)
+{
+	struct task_struct *work_thread;
+
+	disable_nonboot_cpus();
+
+	yield();
+
+	set_suspend_state(SUSPEND_FORK_COPYBACK_THREAD);
+	BUG_ON(atomic_read(&restore_thread_ready));
+
+	atomic_set(&atomic_copy_hold, 1);
+
+	/* Now start the new thread */
+	work_thread = kthread_run(__suspend_atomic_restore, 0, "kcopyback");
+	BUG_ON(IS_ERR(work_thread));
+
+	while (!atomic_read(&restore_thread_ready))
+		yield();
+
+	atomic_set(&atomic_copy_hold, 0);
+
+	while(1) {
+		try_to_freeze();
+		yield();
+	}
+}
diff -urN oldtree/kernel/power/atomic_copy.h newtree/kernel/power/atomic_copy.h
--- oldtree/kernel/power/atomic_copy.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/atomic_copy.h	2006-01-28 17:08:36.223728800 +0000
@@ -0,0 +1,4 @@
+extern inline void move_stack_to_nonconflicing_area(void);
+extern int save_image_part1(void);
+extern void suspend_atomic_restore(void);
+
diff -urN oldtree/kernel/power/block_io.h newtree/kernel/power/block_io.h
--- oldtree/kernel/power/block_io.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/block_io.h	2006-01-28 17:08:36.224728648 +0000
@@ -0,0 +1,75 @@
+/*
+ * block_io.h
+ *
+ * Copyright 2004-2005 Nigel Cunningham <nigel@suspend2.net>
+ *
+ * Distributed under GPLv2.
+ *
+ * This file contains declarations for functions exported from
+ * block_io.c, which contains low level io functions.
+ */
+
+#include <linux/buffer_head.h>
+#include "extent.h"
+
+/*
+ * submit_params
+ *
+ * The structure we use for tracking submitted I/O.
+ */
+struct submit_params {
+	swp_entry_t swap_address;
+	struct page *page;
+	struct block_device *dev;
+	sector_t block[MAX_BUF_PER_PAGE];
+	int readahead_index;
+	struct submit_params *next;
+	int printme;
+};
+
+struct suspend2_bdev_info {
+	struct block_device *bdev;
+	dev_t dev_t;
+	int bmap_shift;
+	int blocks_per_page;
+};
+
+/* 
+ * Our exported interface so the swapwriter and filewriter don't
+ * need these functions duplicated.
+ */
+struct suspend_bio_ops {
+	int (*submit_io) (int rw, 
+		struct submit_params *submit_info, int syncio);
+	int (*bdev_page_io) (int rw, struct block_device *bdev, long pos,
+			struct page *page);
+	int (*rw_page) (int rw, struct page *page, int readahead_index,
+			int sync);
+	void (*wait_on_readahead) (int readahead_index);
+	void (*check_io_stats) (void);
+	void (*reset_io_stats) (void);
+	void (*finish_all_io) (void);
+	int (*prepare_readahead) (int index);
+	void (*cleanup_readahead) (int index);
+	struct page ** readahead_pages;
+	int (*readahead_ready) (int readahead_index);
+	int *need_extra_next;
+	int (*forward_one_page) (void);
+	void (*set_devinfo) (struct suspend2_bdev_info *info);
+	int (*read_init) (int stream_number);
+	int (*read_chunk) (struct page *buffer_page, int sync);
+	int (*read_cleanup) (void);
+	int (*write_init) (int stream_number);
+	int (*write_chunk) (struct page *buffer_page);
+	int (*write_cleanup) (void);
+	int (*read_header_chunk) (char *buffer, int buffer_size);
+	int (*write_header_chunk) (char *buffer, int buffer_size);
+};
+
+extern struct suspend_bio_ops suspend_bio_ops;
+
+extern char *suspend_writer_buffer;
+extern int suspend_writer_buffer_posn;
+extern int suspend_read_fd;
+extern struct extent_iterate_saved_state suspend_writer_posn_save[3];
+extern struct extent_iterate_state suspend_writer_posn;
diff -urN oldtree/kernel/power/checksum.h newtree/kernel/power/checksum.h
--- oldtree/kernel/power/checksum.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/checksum.h	2006-01-28 17:08:36.224728648 +0000
@@ -0,0 +1,11 @@
+#ifdef CONFIG_SUSPEND2_CHECKSUMS
+extern void suspend2_verify_checksums(void);
+extern void suspend2_checksum_calculate_checksums(void);
+extern void suspend2_checksum_print_differences(void);
+extern int suspend2_allocate_checksum_pages(void);
+#else
+static inline void suspend2_verify_checksums(void) { };
+static inline void suspend2_checksum_calculate_checksums(void) { };
+static inline void suspend2_checksum_print_differences(void) { };
+static inline int suspend2_allocate_checksum_pages(void) { return 0; };
+#endif
diff -urN oldtree/kernel/power/compression.c newtree/kernel/power/compression.c
--- oldtree/kernel/power/compression.c	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/compression.c	2006-01-28 17:08:36.225728496 +0000
@@ -0,0 +1,638 @@
+/*
+ * kernel/power/suspend2_core/compression.c
+ *
+ * Copyright (C) 2003-2005 Nigel Cunningham <nigel@suspend2.net>
+ *
+ * This file is released under the GPLv2.
+ *
+ * This file contains data compression routines for suspend,
+ * using LZH compression.
+ *
+ */
+
+#include <linux/suspend.h>
+#include <linux/module.h>
+#include <linux/highmem.h>
+#include <linux/vmalloc.h>
+#include <linux/crypto.h>
+
+#include "suspend2.h"
+#include "plugins.h"
+#include "proc.h"
+#include "suspend2_common.h"
+#include "io.h"
+
+#define S2C_WRITE 0
+#define S2C_READ 1
+
+static int s2_expected_compression = 0;
+
+static struct suspend_plugin_ops s2_compression_ops;
+static struct suspend_plugin_ops *next_driver;
+
+static char s2_compressor_name[32];
+static struct crypto_tfm *s2_compressor_transform;
+
+static u8 *local_buffer = NULL;
+static u8 *page_buffer = NULL;
+static unsigned int bufofs;
+
+static int position = 0;
+
+/* ---- Local buffer management ---- */
+
+/* allocate_local_buffer
+ *
+ * Description:	Allocates a page of memory for buffering output.
+ * Returns:	Int: Zero if successful, -ENONEM otherwise.
+ */
+
+static int allocate_local_buffer(void)
+{
+	if (!local_buffer) {
+		local_buffer = (char *) get_zeroed_page(GFP_ATOMIC);
+	
+		if (!local_buffer) {
+			printk(KERN_ERR
+				"Failed to allocate the local buffer for "
+				"suspend2 compression driver.\n");
+			return -ENOMEM;
+		}
+	}
+
+	if (!page_buffer) {
+		page_buffer = (char *) get_zeroed_page(GFP_ATOMIC);
+	
+		if (!page_buffer) {
+			printk(KERN_ERR
+				"Failed to allocate the page buffer for "
+				"suspend2 compression driver.\n");
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+/* free_local_buffer
+ *
+ * Description:	Frees memory allocated for buffering output.
+ */
+
+static inline void free_local_buffer(void)
+{
+	if (local_buffer)
+		free_page((unsigned long) local_buffer);
+
+	local_buffer = NULL;
+
+	if (page_buffer)
+		free_page((unsigned long) page_buffer);
+
+	page_buffer = NULL;
+}
+
+/* suspend2_crypto_cleanup
+ *
+ * Description:	Frees memory allocated for our labours.
+ */
+
+static void suspend2_crypto_cleanup(void)
+{
+	if (s2_compressor_transform) {
+		crypto_free_tfm(s2_compressor_transform);
+		s2_compressor_transform = NULL;
+	}
+}
+
+/* suspend2_crypto_prepare
+ *
+ * Description:	Prepare to do some work by allocating buffers and transforms.
+ * Returns:	Int: Zero if successful, -ENONEM otherwise.
+ */
+
+static int s2_compress_crypto_prepare(int mode)
+{
+	if (!*s2_compressor_name) {
+		printk("Suspend2: Compression enabled but no compressor name set.\n");
+		return 1;
+	}
+
+	if (!(s2_compressor_transform = crypto_alloc_tfm(s2_compressor_name, 0))) {
+		printk("Suspend2: Failed to initialise the %s compression transform.\n",
+				s2_compressor_name);
+		return 1;
+	}
+
+	return 0;
+}
+
+/* ---- Exported functions ---- */
+
+/* write_init()
+ *
+ * Description:	Allocate buffers and prepare to compress data.
+ * Arguments:	Stream_number:	Ignored.
+ * Returns:	Zero on success, -ENOMEM if unable to vmalloc.
+ */
+
+static int s2_compress_write_init(int stream_number)
+{
+	int result;
+	
+	next_driver = get_next_filter(&s2_compression_ops);
+
+	if (!next_driver) {
+		printk("Compression Driver: Argh! No one wants my output!");
+		return -ECHILD;
+	}
+
+	if ((result = s2_compress_crypto_prepare(S2C_WRITE))) {
+		return result;
+	}
+	
+	if ((result = allocate_local_buffer()))
+		return result;
+
+	/* Only reset the stats if starting to write an image */
+	if (stream_number == 2)
+		bytes_in = bytes_out = 0;
+	
+	bufofs = 0;
+
+	position = 0;
+
+	return 0;
+}
+
+/* s2_compress_write()
+ *
+ * Description:	Helper function for write_chunk. Write the compressed data.
+ * Arguments:	u8*:		Output buffer to be written.
+ * 		unsigned int:	Length of buffer.
+ * Return:	int:		Result to be passed back to caller.
+ */
+
+static int s2_compress_write (u8 *buffer, unsigned int len)
+{
+	int ret;
+
+	bytes_out += len;
+
+	while (len + bufofs > PAGE_SIZE) {
+		unsigned int chunk = PAGE_SIZE - bufofs;
+		memcpy (local_buffer + bufofs, buffer, chunk);
+		buffer += chunk;
+		len -= chunk;
+		bufofs = 0;
+		if ((ret = next_driver->ops.filter.write_chunk(virt_to_page(local_buffer))) < 0)
+			return ret;
+	}
+	memcpy (local_buffer + bufofs, buffer, len);
+	bufofs += len;
+	return 0;
+}
+
+/* s2_compress_write_chunk()
+ *
+ * Description:	Compress a page of data, buffering output and passing on
+ * 		filled pages to the next plugin in the pipeline.
+ * Arguments:	Buffer_page:	Pointer to a buffer of size PAGE_SIZE, 
+ * 				containing data to be compressed.
+ * Returns:	0 on success. Otherwise the error is that returned by later
+ * 		plugins, -ECHILD if we have a broken pipeline or -EIO if
+ * 		zlib errs.
+ */
+
+static int s2_compress_write_chunk(struct page *buffer_page)
+{
+	int ret; 
+	unsigned int len;
+	u16 len_written;
+	char *buffer_start;
+	
+	if (!s2_compressor_transform)
+		return next_driver->ops.filter.write_chunk(buffer_page);
+
+	buffer_start = kmap(buffer_page);
+
+	bytes_in += PAGE_SIZE;
+
+	len = PAGE_SIZE;
+
+	ret = crypto_comp_compress(s2_compressor_transform,
+			buffer_start, PAGE_SIZE,
+			page_buffer, &len);
+	
+	if (ret) {
+		printk("Compression failed.\n");
+		goto failure;
+	}
+	
+	len_written = (u16) len;
+		
+	if ((ret = s2_compress_write((u8 *)&len_written, 2)) >= 0) {
+		if ((ret = s2_compress_write((u8 *) &position, sizeof(position))))
+			return -EIO;
+		if (len < PAGE_SIZE) { // some compression
+			position += len;
+			ret = s2_compress_write(page_buffer, len);
+		} else {
+			ret = s2_compress_write(buffer_start, PAGE_SIZE);
+			position += PAGE_SIZE;
+		}
+	}
+	position += 2 + sizeof(int);
+
+
+failure:
+	kunmap(buffer_page);
+	return ret;
+}
+
+/* write_cleanup()
+ *
+ * Description: Write unflushed data and free workspace.
+ * Returns:	Result of writing last page.
+ */
+
+static int s2_compress_write_cleanup(void)
+{
+	int ret = 0;
+	
+	if (s2_compressor_transform)
+		ret = next_driver->ops.filter.write_chunk(virt_to_page(local_buffer));
+
+	suspend2_crypto_cleanup();
+	free_local_buffer();
+
+	return ret;
+}
+
+/* read_init()
+ *
+ * Description:	Prepare to read a new stream of data.
+ * Arguments:	int: Section of image about to be read.
+ * Returns:	int: Zero on success, error number otherwise.
+ */
+
+static int s2_compress_read_init(int stream_number)
+{
+	int result;
+
+	next_driver = get_next_filter(&s2_compression_ops);
+
+	if (!next_driver) {
+		printk("Compression Driver: Argh! No one wants "
+				"to feed me data!");
+		return -ECHILD;
+	}
+	
+	if ((result = s2_compress_crypto_prepare(S2C_READ)))
+		return result;
+	
+	if ((result = allocate_local_buffer()))
+		return result;
+
+	bufofs = PAGE_SIZE;
+
+	position = 0;
+
+	return 0;
+}
+
+/* s2_compress_read()
+ *
+ * Description:	Read data into compression buffer.
+ * Arguments:	u8 *:		Address of the buffer.
+ * 		unsigned int:	Length
+ * Returns:	int:		Result of reading the image chunk.
+ */
+
+static int s2_compress_read (u8 *buffer, unsigned int len)
+{
+	int ret;
+
+	while (len + bufofs > PAGE_SIZE) {
+		unsigned int chunk = PAGE_SIZE - bufofs;
+		memcpy(buffer, local_buffer + bufofs, chunk);
+		buffer += chunk;
+		len -= chunk;
+		bufofs = 0;
+		if ((ret = next_driver->ops.filter.read_chunk(
+				virt_to_page(local_buffer), SUSPEND_SYNC)) < 0) {
+			return ret;
+		}
+	}
+	memcpy (buffer, local_buffer + bufofs, len);
+	bufofs += len;
+	return 0;
+}
+
+/* s2_compress_read_chunk()
+ *
+ * Description:	Retrieve data from later plugins and decompress it until the
+ * 		input buffer is filled.
+ * Arguments:	Buffer_start: 	Pointer to a buffer of size PAGE_SIZE.
+ * 		Sync:		Whether the previous plugin (or core) wants its
+ * 				data synchronously.
+ * Returns:	Zero if successful. Error condition from me or from downstream
+ * 		on failure.
+ */
+
+static int s2_compress_read_chunk(struct page *buffer_page, int sync)
+{
+	int ret, position_saved; 
+	unsigned int len;
+	u16 len_written;
+	char *buffer_start;
+
+	if (!s2_compressor_transform)
+		return next_driver->ops.filter.read_chunk(buffer_page, SUSPEND_ASYNC);
+
+	/* 
+	 * All our reads must be synchronous - we can't decompress
+	 * data that hasn't been read yet.
+	 */
+
+	buffer_start = kmap(buffer_page);
+
+	if ((ret = s2_compress_read ((u8 *)&len_written, 2)) >= 0) {
+		len = (unsigned int) len_written;
+		ret = s2_compress_read((u8 *) &position_saved, sizeof(position_saved));
+		if (ret)
+			return ret;
+
+		if (position != position_saved) {
+			printk("Position saved (%d) != position I'm at now (%d).\n",
+					position_saved, position);
+			BUG_ON(1);
+		}
+		if (len >= PAGE_SIZE) { // uncompressed
+			ret = s2_compress_read(buffer_start, PAGE_SIZE);
+			if (ret)
+				return ret;
+
+			position += PAGE_SIZE;
+		} else { // compressed
+			if ((ret = s2_compress_read(page_buffer, len)) >= 0) {
+				int outlen = PAGE_SIZE;
+				/* Important note.
+				 *
+				 * For Deflate, decompression return values may represent
+				 * errors. Deflate complains when everything is alright, so
+				 * we ignore the errors unless the number of output bytes is
+				 * not PAGE_SIZE.
+				 */
+				crypto_comp_decompress(s2_compressor_transform, 
+						page_buffer, len,
+						buffer_start, &outlen);
+				if (outlen != PAGE_SIZE) {
+					printk("Decompression yielded %ld bytes instead of %d.\n", PAGE_SIZE, outlen);
+					ret = -EIO;
+				} else
+					ret = 0;
+			}
+			position += len;
+		}
+		position += 2 + sizeof(int);
+	} else
+		printk("Compress_read returned %d.", ret);
+	kunmap(buffer_page);
+	return ret;
+}
+
+/* read_cleanup()
+ *
+ * Description:	Clean up after reading part or all of a stream of data.
+ * Returns:	int: Always zero. Never fails.
+ */
+
+static int s2_compress_read_cleanup(void)
+{ 
+	suspend2_crypto_cleanup();
+	free_local_buffer();
+	return 0;
+}
+
+/* s2_compress_print_debug_stats
+ *
+ * Description:	Print information to be recorded for debugging purposes into a
+ * 		buffer.
+ * Arguments:	buffer: Pointer to a buffer into which the debug info will be
+ * 			printed.
+ * 		size:	Size of the buffer.
+ * Returns:	Number of characters written to the buffer.
+ */
+
+static int s2_compress_print_debug_stats(char *buffer, int size)
+{
+	int pages_in = bytes_in >> PAGE_SHIFT, 
+		pages_out = bytes_out >> PAGE_SHIFT;
+	int len;
+	
+	/* Output the compression ratio achieved. */
+	len = snprintf_used(buffer, size, "- Compressor %s enabled.\n",
+			s2_compressor_name);
+	if (pages_in)
+		len+= snprintf_used(buffer+len, size - len,
+		  "  Compressed %ld bytes into %ld (%d percent compression).\n",
+		  bytes_in, bytes_out, (pages_in - pages_out) * 100 / pages_in);
+	return len;
+}
+
+/* compression_memory_needed
+ *
+ * Description:	Tell the caller how much memory we need to operate during
+ * 		suspend/resume.
+ * Returns:	Unsigned long. Maximum number of bytes of memory required for
+ * 		operation.
+ */
+
+static unsigned long s2_compress_memory_needed(void)
+{
+	return PAGE_SIZE;
+}
+
+static unsigned long s2_compress_storage_needed(void)
+{
+	return 2 * sizeof(unsigned long) + sizeof(int);
+}
+
+/* s2_compress_save_config_info
+ *
+ * Description:	Save informaton needed when reloading the image at resume time.
+ * Arguments:	Buffer:		Pointer to a buffer of size PAGE_SIZE.
+ * Returns:	Number of bytes used for saving our data.
+ */
+
+static int s2_compress_save_config_info(char *buffer)
+{
+	int namelen = strlen(s2_compressor_name) + 1;
+	int total_len;
+	
+	*((unsigned long *) buffer) = bytes_in;
+	*((unsigned long *) (buffer + 1 * sizeof(unsigned long))) = bytes_out;
+	*((unsigned long *) (buffer + 2 * sizeof(unsigned long))) = s2_expected_compression;
+	*((unsigned long *) (buffer + 3 * sizeof(unsigned long))) = namelen;
+	strncpy(buffer + 4 * sizeof(unsigned long), s2_compressor_name, namelen);
+	total_len = 4 * sizeof(unsigned long) + namelen;
+	return total_len;
+}
+
+/* s2_compress_load_config_info
+ *
+ * Description:	Reload information needed for decompressing the image at 
+ * 		resume time.
+ * Arguments:	Buffer:		Pointer to the start of the data.
+ *		Size:		Number of bytes that were saved.
+ */
+
+static void s2_compress_load_config_info(char *buffer, int size)
+{
+	int namelen;
+	
+	bytes_in = *((unsigned long *) buffer);
+	bytes_out = *((unsigned long *) (buffer + 1 * sizeof(unsigned long)));
+	s2_expected_compression = *((unsigned long *) (buffer + 2 * sizeof(unsigned long)));
+	namelen = *((unsigned long *) (buffer + 3 * sizeof(unsigned long)));
+	strncpy(s2_compressor_name, buffer + 4 * sizeof(unsigned long), namelen);
+	return;
+}
+
+/* suspend2_expected_compression_ratio
+ * 
+ * Description:	Returns the expected ratio between data passed into this plugin
+ * 		and the amount of data output when writing.
+ * Returns:	100 if the plugin is disabled. Otherwise the value set by the
+ * 		user via our proc entry.
+ */
+
+int suspend2_expected_compression_ratio(void)
+{
+	if (s2_compression_ops.disabled)
+		return 100;
+	else
+		return 100 - s2_expected_compression;
+}
+
+static void s2_compressor_disable_if_empty(void)
+{
+	s2_compression_ops.disabled = !(*s2_compressor_name);
+}
+
+static int s2_compress_initialise(int starting_cycle)
+{
+	if (starting_cycle)
+		s2_compressor_disable_if_empty();
+
+	return 0;
+}
+/*
+ * data for our proc entries.
+ */
+
+static struct suspend_proc_data proc_params[] = {
+	{
+		.filename			= "expected_compression",
+		.permissions			= PROC_RW,
+		.type				= SUSPEND_PROC_DATA_INTEGER,
+		.data = {
+			.integer = {
+				.variable	= &s2_expected_compression,
+				.minimum	= 0,
+				.maximum	= 99,
+			}
+		}
+	},
+
+	{
+		.filename			= "disable_compression",
+		.permissions			= PROC_RW,
+		.type				= SUSPEND_PROC_DATA_INTEGER,
+		.data = {
+			.integer = {
+				.variable	= &s2_compression_ops.disabled,
+				.minimum	= 0,
+				.maximum	= 1,
+			}
+		}
+	},
+
+	{
+		.filename			= "compressor",
+		.permissions			= PROC_RW,
+		.type				= SUSPEND_PROC_DATA_STRING,
+		.data = {
+			.string = {
+				.variable	= s2_compressor_name,
+				.max_length	= 31,
+			}
+		},
+		.write_proc			= &s2_compressor_disable_if_empty,
+	}
+};
+
+/*
+ * Ops structure.
+ */
+
+static struct suspend_plugin_ops s2_compression_ops = {
+	.type			= FILTER_PLUGIN,
+	.name			= "Suspend2 Compressor",
+	.module			= THIS_MODULE,
+	.memory_needed 		= s2_compress_memory_needed,
+	.print_debug_info	= s2_compress_print_debug_stats,
+	.save_config_info	= s2_compress_save_config_info,
+	.load_config_info	= s2_compress_load_config_info,
+	.storage_needed		= s2_compress_storage_needed,
+	
+	.initialise		= s2_compress_initialise,
+	
+	.write_init		= s2_compress_write_init,
+	.write_cleanup		= s2_compress_write_cleanup,
+	.read_init		= s2_compress_read_init,
+	.read_cleanup		= s2_compress_read_cleanup,
+
+	.ops = {
+		.filter = {
+			.write_chunk		= s2_compress_write_chunk,
+			.read_chunk		= s2_compress_read_chunk,
+		}
+	}
+};
+
+/* ---- Registration ---- */
+
+static __init int s2_compress_load(void)
+{
+	int result;
+	int i, numfiles = sizeof(proc_params) / sizeof(struct suspend_proc_data);
+
+	printk("Suspend2 Compression Driver loading.\n");
+	if (!(result = suspend_register_plugin(&s2_compression_ops))) {
+		for (i=0; i< numfiles; i++)
+			suspend_register_procfile(&proc_params[i]);
+	} else
+		printk("Suspend2 Compression Driver unable to register!\n");
+	return result;
+}
+
+#ifdef MODULE
+static __exit void s2_compress_unload(void)
+{
+	printk("Suspend2 Compression Driver unloading.\n");
+	for (i=0; i< numfiles; i++)
+		suspend_unregister_procfile(&proc_params[i]);
+	suspend_unregister_plugin(&s2_compression_ops);
+}
+
+
+module_init(s2_compress_load);
+module_exit(s2_compress_unload);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Nigel Cunningham");
+MODULE_DESCRIPTION("Compression Support for Suspend2");
+#else
+late_initcall(s2_compress_load);
+#endif
diff -urN oldtree/kernel/power/debug_pagealloc.c newtree/kernel/power/debug_pagealloc.c
--- oldtree/kernel/power/debug_pagealloc.c	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/debug_pagealloc.c	2006-01-28 17:08:36.226728344 +0000
@@ -0,0 +1,111 @@
+#include <linux/mm.h>
+#ifdef CONFIG_DEBUG_PAGEALLOC
+#include <linux/page-flags.h>
+#include <asm/pgtable.h>
+
+#include "pageflags.h"
+#include "suspend2.h"
+#include "pagedir.h"
+
+
+extern pte_t *lookup_address(unsigned long address);
+
+/* Returns whether it was already in the requested state */
+extern void kernel_map_pages(struct page *page, int numpages, int enable);
+
+static int page_is_kernel_mapped(struct page *page)
+{
+	pte_t *kpte; 
+	unsigned long address;
+
+	if (PageHighMem(page))
+		return 0;
+
+	address = (unsigned long)page_address(page);
+	
+	kpte = lookup_address(address);
+	if (!kpte)
+		return 0;
+
+	if (pte_same(*kpte, mk_pte(page, PAGE_KERNEL)))
+		return 1;
+
+	return 0;
+}
+
+int suspend_map_kernel_page(struct page *page, int enable)
+{
+	int is_already_mapped = page_is_kernel_mapped(page);
+
+	if (enable == is_already_mapped)
+		return 1;
+
+	kernel_map_pages(page, 1, enable);
+
+	return 0;
+}
+
+/*
+ * suspend2_map_atomic_copy_pages
+ *
+ * When DEBUG_PAGEALLOC is enabled, we need to map the pages before
+ * an atomic copy.
+ */
+void suspend2_map_atomic_copy_pages(void)
+{
+	int i = 0, source_index = -1, dest_index = -1;
+
+	for (i = 0; i < pagedir1.pageset_size; i++) {
+		int orig_was_mapped = 1, copy_was_mapped = 1;
+		struct page *origpage, *copypage;
+
+		source_index = get_next_bit_on(pageset1_map, source_index);
+		dest_index = get_next_bit_on(pageset1_copy_map, dest_index);
+
+		origpage = pfn_to_page(source_index);
+		copypage = pfn_to_page(dest_index);
+		
+	       	if (!PageHighMem(origpage)) {
+			orig_was_mapped = suspend_map_kernel_page(origpage, 1);
+			if ((!orig_was_mapped) &&
+			    (!test_suspend_state(SUSPEND_NOW_RESUMING)))
+				SetPageUnmap(origpage);
+		}
+
+		copy_was_mapped = suspend_map_kernel_page(copypage, 1);
+		if ((!copy_was_mapped) &&
+		    (!test_suspend_state(SUSPEND_NOW_RESUMING)))
+			SetPageUnmap(copypage);
+	}
+}
+
+/*
+ * suspend2_unmap_atomic_copy_pages
+ *
+ * We also need to unmap pages when DEBUG_PAGEALLOC is enabled.
+ */
+void suspend2_unmap_atomic_copy_pages(void)
+{
+	int i;
+	struct zone *zone;
+
+	for_each_zone(zone) {
+		if (!zone->present_pages)
+			continue;
+		for (i = 0; i < zone->spanned_pages; i++) {
+			struct page *page = pfn_to_page(zone->zone_start_pfn + i);
+			if (PageUnmap(page))
+				suspend_map_kernel_page(page, 0);
+		}
+	}
+}
+#else
+void suspend2_map_atomic_copy_pages(void) { };
+
+void suspend2_unmap_atomic_copy_pages(void) { };
+
+int suspend_map_kernel_page(struct page *page, int enable)
+{
+	return 1;
+}
+#endif
diff -urN oldtree/kernel/power/debug_pagealloc.h newtree/kernel/power/debug_pagealloc.h
--- oldtree/kernel/power/debug_pagealloc.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/debug_pagealloc.h	2006-01-28 17:08:36.226728344 +0000
@@ -0,0 +1,3 @@
+extern void suspend2_map_atomic_copy_pages(void);
+extern void suspend2_unmap_atomic_copy_pages(void);
+extern int suspend_map_kernel_page(struct page *page, int enable);
diff -urN oldtree/kernel/power/disk.c newtree/kernel/power/disk.c
--- oldtree/kernel/power/disk.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/kernel/power/disk.c	2006-01-28 17:08:36.226728344 +0000
@@ -10,6 +10,7 @@
  */
 
 #include <linux/suspend.h>
+#include <linux/freezer.h>
 #include <linux/syscalls.h>
 #include <linux/reboot.h>
 #include <linux/string.h>
@@ -89,12 +90,16 @@
 	unsigned long pages = 0;
 	char *p = "-\\|/";
 
+	thaw_processes(FREEZER_KERNEL_THREADS);
+
 	printk("Freeing memory...  ");
 	while ((tmp = shrink_all_memory(10000))) {
 		pages += tmp;
 		printk("\b%c", p[i++ % 4]);
 	}
 	printk("\bdone (%li pages freed)\n", pages);
+
+	freeze_processes();
 }
 
 
@@ -130,7 +135,7 @@
 	free_some_memory();
 	return 0;
 thaw:
-	thaw_processes();
+	thaw_processes(FREEZER_ALL_THREADS);
 	enable_nonboot_cpus();
 	pm_restore_console();
 	return error;
@@ -139,7 +144,7 @@
 static void unprepare_processes(void)
 {
 	platform_finish();
-	thaw_processes();
+	thaw_processes(FREEZER_ALL_THREADS);
 	enable_nonboot_cpus();
 	pm_restore_console();
 }
diff -urN oldtree/kernel/power/encryption.c newtree/kernel/power/encryption.c
--- oldtree/kernel/power/encryption.c	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/encryption.c	2006-01-28 17:08:36.227728192 +0000
@@ -0,0 +1,597 @@
+/*
+ * kernel/power/suspend2_core/encryption.c
+ *
+ * Copyright (C) 2003-2005 Nigel Cunningham <nigel@suspend2.net>
+ *
+ * This file is released under the GPLv2.
+ *
+ * This file contains data encryption routines for suspend,
+ * using cryptoapi transforms.
+ *
+ * ToDo:
+ * - Apply min/max_keysize the cipher changes.
+ * - Test.
+ */
+
+#include <linux/suspend.h>
+#include <linux/module.h>
+#include <linux/highmem.h>
+#include <linux/vmalloc.h>
+#include <linux/crypto.h>
+#include <asm/scatterlist.h>
+
+#include "suspend2.h"
+#include "plugins.h"
+#include "proc.h"
+#include "suspend2_common.h"
+#include "io.h"
+
+#define S2C_WRITE 0
+#define S2C_READ 1
+
+static struct suspend_plugin_ops s2_encryption_ops;
+static struct suspend_plugin_ops *next_driver;
+
+static char s2_encryptor_name[32];
+static struct crypto_tfm *s2_encryptor_transform;
+static char s2_encryptor_key[256];
+static int s2_key_len;
+static char s2_encryptor_iv[256];
+static int s2_encryptor_mode;
+static int s2_encryptor_save_key_and_iv;
+
+static u8 *page_buffer = NULL;
+static unsigned int bufofs;
+
+static struct scatterlist s2_crypt_sg[PAGE_SIZE/8];
+
+/* ---- Local buffer management ---- */
+
+/* allocate_local_buffer
+ *
+ * Description:	Allocates a page of memory for buffering output.
+ * Returns:	Int: Zero if successful, -ENONEM otherwise.
+ */
+
+static int allocate_local_buffer(void)
+{
+	if (!page_buffer) {
+		int i;
+		
+		page_buffer = (char *) get_zeroed_page(GFP_ATOMIC);
+	
+		if (!page_buffer) {
+			printk(KERN_ERR
+				"Failed to allocate the page buffer for "
+				"suspend2 encryption driver.\n");
+			return -ENOMEM;
+		}
+
+		for (i=0; i < (PAGE_SIZE / s2_key_len); i++) {
+			s2_crypt_sg[i].page = virt_to_page(page_buffer);
+			s2_crypt_sg[i].offset = s2_key_len * i;
+			s2_crypt_sg[i].length = s2_key_len;
+		}
+	}
+
+	return 0;
+}
+
+/* free_local_buffer
+ *
+ * Description:	Frees memory allocated for buffering output.
+ */
+
+static void free_local_buffer(void)
+{
+	if (page_buffer)
+		free_page((unsigned long) page_buffer);
+
+	page_buffer = NULL;
+}
+
+/* suspend2_crypto_cleanup
+ *
+ * Description:	Frees memory allocated for our labours.
+ */
+
+static void suspend2_crypto_cleanup(void)
+{
+	if (s2_encryptor_transform) {
+		crypto_free_tfm(s2_encryptor_transform);
+		s2_encryptor_transform = NULL;
+	}
+}
+
+/* suspend2_crypto_prepare
+ *
+ * Description:	Prepare to do some work by allocating buffers and transforms.
+ * Returns:	Int: Zero if successful, -ENONEM otherwise.
+ */
+
+static int s2_encrypt_crypto_prepare(int mode)
+{
+	if (!*s2_encryptor_name) {
+		printk("Suspend2: Encryptor enabled but no name set.\n");
+		return 1;
+	}
+
+	if (!(s2_encryptor_transform = crypto_alloc_tfm(s2_encryptor_name,
+					1 << s2_encryptor_mode))) {
+		printk("Suspend2: Failed to initialise the encryption transform (%s, mode %d).\n",
+				s2_encryptor_name, s2_encryptor_mode);
+		return 1;
+	}
+
+	if (mode)
+		bufofs = PAGE_SIZE;
+	else
+		bufofs = 0;
+
+	s2_key_len = strlen(s2_encryptor_key);
+
+	if (crypto_cipher_setkey(s2_encryptor_transform, s2_encryptor_key, 
+				s2_key_len)) {
+		printk("%d is an invalid key length for cipher %s.\n",
+					s2_key_len,
+					s2_encryptor_name);
+		return 1;
+	}
+	
+	if (!mode) {
+		crypto_cipher_set_iv(s2_encryptor_transform,
+				s2_encryptor_iv,
+				crypto_tfm_alg_ivsize(s2_encryptor_transform));
+	}
+		
+	return 0;
+}
+
+/* ---- Exported functions ---- */
+
+/* write_init()
+ *
+ * Description:	Allocate buffers and prepare to encrypt data.
+ * Arguments:	Stream_number:	Ignored.
+ * Returns:	Zero on success, -ENOMEM if unable to vmalloc.
+ */
+
+static int s2_encrypt_write_init(int stream_number)
+{
+	int result;
+	
+	next_driver = get_next_filter(&s2_encryption_ops);
+
+	if (!next_driver) {
+		printk("Encryption Driver: Argh! No one wants my output!");
+		return -ECHILD;
+	}
+
+	if ((result = s2_encrypt_crypto_prepare(S2C_WRITE))) {
+		set_result_state(SUSPEND_ENCRYPTION_SETUP_FAILED);
+		suspend2_crypto_cleanup();
+		return result;
+	}
+	
+	if ((result = allocate_local_buffer()))
+		return result;
+
+	/* Only reset the stats if starting to write an image */
+	if (stream_number == 2)
+		bytes_in = bytes_out = 0;
+	
+	bufofs = 0;
+
+	return 0;
+}
+
+/* s2_encrypt_write_chunk()
+ *
+ * Description:	Encrypt a page of data, buffering output and passing on
+ * 		filled pages to the next plugin in the pipeline.
+ * Arguments:	Buffer_page:	Pointer to a buffer of size PAGE_SIZE, 
+ * 				containing data to be encrypted.
+ * Returns:	0 on success. Otherwise the error is that returned by later
+ * 		plugins, -ECHILD if we have a broken pipeline or -EIO if
+ * 		zlib errs.
+ */
+
+static int s2_encrypt_write_chunk(struct page *buffer_page)
+{
+	int ret; 
+	unsigned int len;
+	u16 len_written;
+	char *buffer_start;
+	
+	if (!s2_encryptor_transform)
+		return next_driver->ops.filter.write_chunk(buffer_page);
+
+	buffer_start = kmap(buffer_page);
+	memcpy(page_buffer, buffer_start, PAGE_SIZE);
+	kunmap(buffer_page);
+	
+	bytes_in += PAGE_SIZE;
+
+	len = PAGE_SIZE;
+
+	ret = crypto_cipher_encrypt(s2_encryptor_transform,
+			s2_crypt_sg, s2_crypt_sg, PAGE_SIZE);
+	
+	if (ret) {
+		printk("Encryption failed.\n");
+		return -EIO;
+	}
+	
+	len_written = (u16) len;
+
+	ret = next_driver->ops.filter.write_chunk(virt_to_page(page_buffer));
+
+	return ret;
+}
+
+/* write_cleanup()
+ *
+ * Description: Write unflushed data and free workspace.
+ * Returns:	Result of writing last page.
+ */
+
+static int s2_encrypt_write_cleanup(void)
+{
+	suspend2_crypto_cleanup();
+	free_local_buffer();
+
+	return 0;
+}
+
+/* read_init()
+ *
+ * Description:	Prepare to read a new stream of data.
+ * Arguments:	int: Section of image about to be read.
+ * Returns:	int: Zero on success, error number otherwise.
+ */
+
+static int s2_encrypt_read_init(int stream_number)
+{
+	int result;
+
+	next_driver = get_next_filter(&s2_encryption_ops);
+
+	if (!next_driver) {
+		printk("Encryption Driver: Argh! No one wants "
+				"to feed me data!");
+		return -ECHILD;
+	}
+	
+	if ((result = s2_encrypt_crypto_prepare(S2C_READ))) {
+		set_result_state(SUSPEND_ENCRYPTION_SETUP_FAILED);
+		suspend2_crypto_cleanup();
+		return result;
+	}
+	
+	if ((result = allocate_local_buffer()))
+		return result;
+
+	bufofs = PAGE_SIZE;
+
+	return 0;
+}
+
+/* s2_encrypt_read_chunk()
+ *
+ * Description:	Retrieve data from later plugins and deencrypt it until the
+ * 		input buffer is filled.
+ * Arguments:	Buffer_start: 	Pointer to a buffer of size PAGE_SIZE.
+ * 		Sync:		Whether the previous plugin (or core) wants its
+ * 				data synchronously.
+ * Returns:	Zero if successful. Error condition from me or from downstream
+ * 		on failure.
+ */
+
+static int s2_encrypt_read_chunk(struct page *buffer_page, int sync)
+{
+	int ret; 
+	char *buffer_start;
+
+	if (!s2_encryptor_transform)
+		return next_driver->ops.filter.read_chunk(buffer_page, sync);
+
+	/* 
+	 * All our reads must be synchronous - we can't deencrypt
+	 * data that hasn't been read yet.
+	 */
+
+	if ((ret = next_driver->ops.filter.read_chunk(
+			virt_to_page(page_buffer), SUSPEND_SYNC)) < 0) {
+		printk("Failed to read an encrypted block.\n");
+		return ret;
+	}
+
+	ret = crypto_cipher_decrypt(s2_encryptor_transform,
+			s2_crypt_sg, s2_crypt_sg, PAGE_SIZE);
+
+	if (ret)
+		printk("Decrypt function returned %d.\n", ret);
+
+	buffer_start = kmap(buffer_page);
+	memcpy(buffer_start, page_buffer, PAGE_SIZE);
+	kunmap(buffer_page);
+	return ret;
+}
+
+/* read_cleanup()
+ *
+ * Description:	Clean up after reading part or all of a stream of data.
+ * Returns:	int: Always zero. Never fails.
+ */
+
+static int s2_encrypt_read_cleanup(void)
+{
+	suspend2_crypto_cleanup();
+	free_local_buffer();
+	return 0;
+}
+
+/* s2_encrypt_print_debug_stats
+ *
+ * Description:	Print information to be recorded for debugging purposes into a
+ * 		buffer.
+ * Arguments:	buffer: Pointer to a buffer into which the debug info will be
+ * 			printed.
+ * 		size:	Size of the buffer.
+ * Returns:	Number of characters written to the buffer.
+ */
+
+static int s2_encrypt_print_debug_stats(char *buffer, int size)
+{
+	int len;
+	
+	len = snprintf_used(buffer, size, "- Encryptor %s enabled.\n",
+			s2_encryptor_name);
+	return len;
+}
+
+/* encryption_memory_needed
+ *
+ * Description:	Tell the caller how much memory we need to operate during
+ * 		suspend/resume.
+ * Returns:	Unsigned long. Maximum number of bytes of memory required for
+ * 		operation.
+ */
+
+static unsigned long s2_encrypt_memory_needed(void)
+{
+	return PAGE_SIZE;
+}
+
+static unsigned long s2_encrypt_storage_needed(void)
+{
+	return 2 * sizeof(unsigned long) + sizeof(int);
+}
+
+/* s2_encrypt_save_config_info
+ *
+ * Description:	Save informaton needed when reloading the image at resume time.
+ * Arguments:	Buffer:		Pointer to a buffer of size PAGE_SIZE.
+ * Returns:	Number of bytes used for saving our data.
+ */
+
+static int s2_encrypt_save_config_info(char *buffer)
+{
+	int buf_offset, str_size;
+
+	str_size = strlen(s2_encryptor_name);
+	*buffer = (char) str_size;
+	strncpy(buffer + 1, s2_encryptor_name, str_size + 1);
+	buf_offset = str_size + 2;
+
+	*(buffer + buf_offset) = (char) s2_encryptor_mode;
+	buf_offset++;
+
+	*(buffer + buf_offset) = (char) s2_encryptor_save_key_and_iv;
+	buf_offset++;
+
+	if (s2_encryptor_save_key_and_iv) {
+		
+		str_size = strlen(s2_encryptor_key);
+		*(buffer + buf_offset) = (char) str_size;
+		strncpy(buffer + buf_offset + 1, s2_encryptor_key, str_size + 1);
+
+		buf_offset+= str_size + 2;
+
+		str_size = strlen(s2_encryptor_iv);
+		*(buffer + buf_offset) = (char) str_size;
+		strncpy(buffer + buf_offset + 1, s2_encryptor_iv, str_size + 1);
+
+		buf_offset += str_size + 2;
+	}
+
+	return buf_offset;
+}
+
+/* s2_encrypt_load_config_info
+ *
+ * Description:	Reload information needed for deencrypting the image at 
+ * 		resume time.
+ * Arguments:	Buffer:		Pointer to the start of the data.
+ *		Size:		Number of bytes that were saved.
+ */
+
+static void s2_encrypt_load_config_info(char *buffer, int size)
+{
+	int buf_offset, str_size;
+
+	str_size = (int) *buffer;
+	strncpy(s2_encryptor_name, buffer + 1, str_size + 1);
+	buf_offset = str_size + 2;
+	
+	s2_encryptor_mode = (int) *(buffer + buf_offset);
+	buf_offset++;
+
+	s2_encryptor_save_key_and_iv = (int) *(buffer + buf_offset);
+	buf_offset++;
+
+	if (s2_encryptor_save_key_and_iv) {
+		str_size = (int) *(buffer + buf_offset);
+		strncpy(s2_encryptor_key, buffer + buf_offset + 1, str_size + 1);
+
+		buf_offset+= str_size + 2;
+
+		str_size = (int) *(buffer + buf_offset);
+		strncpy(s2_encryptor_iv, buffer + buf_offset + 1, str_size + 1);
+
+		buf_offset += str_size + 2;
+	} else {
+		*s2_encryptor_key = 0;
+		*s2_encryptor_iv = 0;
+	}
+	
+	if (buf_offset != size) {
+		printk("Suspend Encryptor config info size mismatch (%d != %d): settings ignored.\n",
+				buf_offset, size);
+		*s2_encryptor_key = 0;
+		*s2_encryptor_iv = 0;
+	}
+	return;
+}
+
+static void s2_encryptor_disable_if_empty(void)
+{
+	s2_encryption_ops.disabled = !(*s2_encryptor_name);
+}
+
+static int s2_encrypt_initialise(int starting_cycle)
+{
+	if (starting_cycle)
+		s2_encryptor_disable_if_empty();
+
+	return 0;
+}
+/*
+ * data for our proc entries.
+ */
+
+static struct suspend_proc_data proc_params[] = {
+	{
+		.filename			= "encryptor",
+		.permissions			= PROC_RW,
+		.type				= SUSPEND_PROC_DATA_STRING,
+		.data = {
+			.string = {
+				.variable	= s2_encryptor_name,
+				.max_length	= 31,
+			}
+		},
+		.write_proc			= s2_encryptor_disable_if_empty,
+	},
+
+	{
+		.filename			= "encryption_mode",
+		.permissions			= PROC_RW,
+		.type				= SUSPEND_PROC_DATA_INTEGER,
+		.data = {
+			.integer = {
+				.variable	= &s2_encryptor_mode,
+				.minimum	= 0,
+				.maximum	= 3,
+			}
+		}
+	},
+
+	{
+		.filename			= "encryption_save_key_and_iv",
+		.permissions			= PROC_RW,
+		.type				= SUSPEND_PROC_DATA_INTEGER,
+		.data = {
+			.integer = {
+				.variable	= &s2_encryptor_save_key_and_iv,
+				.minimum	= 0,
+				.maximum	= 1,
+			}
+		}
+	},
+
+	{
+		.filename			= "encryption_key",
+		.permissions			= PROC_RW,
+		.type				= SUSPEND_PROC_DATA_STRING,
+		.data = {
+			.string = {
+				.variable	= s2_encryptor_key,
+				.max_length	= 255,
+			}
+		}
+	},
+
+	{
+		.filename			= "encryption_iv",
+		.permissions			= PROC_RW,
+		.type				= SUSPEND_PROC_DATA_STRING,
+		.data = {
+			.string = {
+				.variable	= s2_encryptor_iv,
+				.max_length	= 255,
+			}
+		}
+	},
+
+	{
+		.filename			= "disable_encryption",
+		.permissions			= PROC_RW,
+		.type				= SUSPEND_PROC_DATA_INTEGER,
+		.data = {
+			.integer = {
+				.variable	= &s2_encryption_ops.disabled,
+				.minimum	= 0,
+				.maximum	= 1,
+			}
+		}
+	},
+	
+};
+
+/*
+ * Ops structure.
+ */
+
+static struct suspend_plugin_ops s2_encryption_ops = {
+	.type			= FILTER_PLUGIN,
+	.name			= "Encryptor",
+	.module			= THIS_MODULE,
+	.memory_needed 		= s2_encrypt_memory_needed,
+	.print_debug_info	= s2_encrypt_print_debug_stats,
+	.save_config_info	= s2_encrypt_save_config_info,
+	.load_config_info	= s2_encrypt_load_config_info,
+	.storage_needed		= s2_encrypt_storage_needed,
+	
+	.initialise		= s2_encrypt_initialise,
+	
+	.write_init		= s2_encrypt_write_init,
+	.write_cleanup		= s2_encrypt_write_cleanup,
+	.read_init		= s2_encrypt_read_init,
+	.read_cleanup		= s2_encrypt_read_cleanup,
+
+	.ops = {
+		.filter = {
+			.write_chunk		= s2_encrypt_write_chunk,
+			.read_chunk		= s2_encrypt_read_chunk,
+		}
+	}
+};
+
+/* ---- Registration ---- */
+
+static __init int s2_encrypt_load(void)
+{
+	int result;
+	int i, numfiles = sizeof(proc_params) / sizeof(struct suspend_proc_data);
+
+	printk("Suspend2 Encryption Driver loading.\n");
+	if (!(result = suspend_register_plugin(&s2_encryption_ops))) {
+		for (i=0; i< numfiles; i++)
+			suspend_register_procfile(&proc_params[i]);
+	} else
+		printk("Suspend2 Encryption Driver unable to register!\n");
+	return result;
+}
+
+late_initcall(s2_encrypt_load);
diff -urN oldtree/kernel/power/extent.c newtree/kernel/power/extent.c
--- oldtree/kernel/power/extent.c	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/extent.c	2006-01-28 17:08:36.228728040 +0000
@@ -0,0 +1,247 @@
+/* kernel/power/suspend2_core/extent.c
+ * 
+ * (C) 2003-2005 Nigel Cunningham <nigel@suspend2.net>
+ *
+ * Distributed under GPLv2.
+ * 
+ * These functions encapsulate the manipulation of storage metadata. For
+ * pageflags, we use dynamically allocated bitmaps.
+ */
+
+#include <linux/module.h>
+#include <linux/suspend.h>
+#include "plugins.h"
+#include "extent.h"
+#include "ui.h"
+
+int extents_allocated = 0;
+
+/* get_extent
+ *
+ * Returns a free extent. May fail, returning NULL instead.
+ */
+
+static struct extent *get_extent(void)
+{
+	struct extent *result;
+	
+	if (!(result = kmalloc(sizeof(struct extent), GFP_ATOMIC)))
+		return NULL;
+
+	extents_allocated++;
+	result->minimum = result->maximum = 0;
+	result->next = NULL;
+	return result;
+}
+
+/* put_extent.
+ *
+ * Frees an extent. Assumes unlinking is done by the caller.
+ */
+void put_extent(struct extent *extent)
+{
+	BUG_ON(!extent);
+
+	kfree(extent);
+	extents_allocated--;
+}
+
+/* put_extent_chain.
+ *
+ * Frees a whole chain of extents.
+ */
+void put_extent_chain(struct extent_chain *chain)
+{
+	struct extent *this;
+
+	this = chain->first;
+
+	while(this) {
+		struct extent *next = this->next;
+		kfree(this);
+		chain->frees++;
+		extents_allocated --;
+		this = next;
+	}
+	
+	BUG_ON(chain->frees != chain->allocs);
+	chain->first = chain->last = NULL;
+	chain->size = chain->allocs = chain->frees = 0;
+}
+
+/* append_extent_to_extent_chain
+ *
+ * Used where we know a extent is to be added to the end of the list
+ * and does not need merging with the current last extent.
+ */
+
+int append_extent_to_extent_chain(struct extent_chain *chain, 
+		unsigned long minimum, unsigned long maximum)
+{
+	struct extent *newextent = NULL;
+
+	newextent = get_extent();
+	if (!newextent) {
+		printk("Error unable to append a new extent to the chain.\n");
+		return 2;
+	}
+
+	chain->allocs++;
+	chain->size+= (maximum - minimum + 1);
+	newextent->minimum = minimum;
+	newextent->maximum = maximum;
+	newextent->next = NULL;
+
+	if (chain->last) {
+		chain->last->next = newextent;
+		chain->last = newextent;
+	} else 
+		chain->last = chain->first = newextent;
+
+	return 0;
+}
+
+/* serialise_extent_chain
+ *
+ * Write a chain in the image.
+ */
+int serialise_extent_chain(struct extent_chain *chain)
+{
+	struct extent *this;
+	int ret, i = 1;
+	
+	if ((ret = active_writer->ops.writer.write_header_chunk((char *) chain,
+		sizeof(struct extent_chain) - 2 * sizeof(struct extent *))))
+		return ret;
+
+	this = chain->first;
+	while (this) {
+		if ((ret = active_writer->ops.writer.write_header_chunk((char *) this,
+				2 * sizeof(unsigned long))))
+			return ret;
+		this = this->next;
+		i++;
+	}
+	return ret;
+}
+
+/* load_extent_chain
+ *
+ * Read back a chain saved in the image.
+ */
+int load_extent_chain(struct extent_chain *chain)
+{
+	struct extent *this, *last = NULL;
+	int i, ret;
+
+	if (!(ret = active_writer->ops.writer.read_header_chunk((char *) chain,
+		sizeof(struct extent_chain) - 2 * sizeof(struct extent *))))
+		return ret;
+
+	for (i = 0; i < (chain->allocs - chain->frees); i++) {
+		this = kmalloc(sizeof(struct extent), GFP_ATOMIC);
+		BUG_ON(!this); /* Shouldn't run out of memory trying this! */
+		this->next = NULL;
+		if (!(ret = active_writer->ops.writer.read_header_chunk((char *) this,
+				2 * sizeof(unsigned long))))
+			return ret;
+		if (last)
+			last->next = this;
+		else
+			chain->first = this;
+		last = this;
+	}
+	chain->last = last;
+	return ret;
+}
+
+/* extent_state_next
+ *
+ * Given a state, progress to the next valid entry. We may begin in an
+ * invalid state, as we do when invoked from extent_state_goto_start below.
+ */
+unsigned long extent_state_next(struct extent_iterate_state *state)
+{
+	if (state->current_chain > state->num_chains)
+		return 0;
+
+	if (state->current_extent)
+		GET_EXTENT_NEXT(state->current_extent, state->current_offset);
+
+	while(!state->current_extent) {
+		int chain_num = ++(state->current_chain);
+
+		if (chain_num > state->num_chains)
+			return 0;
+
+		state->current_extent = (state->chains + chain_num)->first;
+
+		if (!state->current_extent)
+			continue;
+
+		state->current_offset = state->current_extent->minimum;
+	}
+
+	return state->current_offset;
+}
+
+/* extent_state_goto_start
+ *
+ * Find the first valid value in a group of chains.
+ */
+void extent_state_goto_start(struct extent_iterate_state *state)
+{
+	state->current_chain = -1;
+	state->current_extent = NULL;
+	state->current_offset = 0;
+}
+
+/* extent_start_save
+ *
+ * Given a state and a struct extent_state_store, save the crreutn
+ * position in a format that can be used with relocated chains (at
+ * resume time).
+ */
+
+void extent_state_save(struct extent_iterate_state *state,
+		struct extent_iterate_saved_state *saved_state)
+{
+	struct extent *extent;
+
+	saved_state->chain_num = state->current_chain;
+	saved_state->extent_num = 0;
+	saved_state->offset = state->current_offset;
+
+	if (saved_state->chain_num == -1)
+		return;
+	
+	extent = (state->chains + state->current_chain)->first;
+
+	while (extent != state->current_extent) {
+		saved_state->extent_num++;
+		extent = extent->next;
+	}
+}
+
+/* extent_start_restore
+ *
+ * Restore the position saved by extent_state_save.
+ */
+
+void extent_state_restore(struct extent_iterate_state *state,
+		struct extent_iterate_saved_state *saved_state)
+{
+	int posn = saved_state->extent_num;
+
+	if (saved_state->chain_num == -1) {
+		extent_state_goto_start(state);
+		return;
+	}
+
+	state->current_chain = saved_state->chain_num;
+	state->current_extent = (state->chains + state->current_chain)->first;
+	state->current_offset = saved_state->offset;
+
+	while (posn--)
+		state->current_extent = state->current_extent->next;
+}
diff -urN oldtree/kernel/power/extent.h newtree/kernel/power/extent.h
--- oldtree/kernel/power/extent.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/extent.h	2006-01-28 17:08:36.228728040 +0000
@@ -0,0 +1,105 @@
+/*
+ * kernel/power/extent.h
+ *
+ * Copyright (C) 2004-2005 Nigel Cunningham <nigel@suspend2.net>
+ *
+ * This file is released under the GPLv2.
+ *
+ * It contains declarations related to extents. Extents are
+ * suspend's method of storing some of the metadata for the image.
+ * See extent.c for more info.
+ *
+ */
+
+#ifndef EXTENT_H
+#define EXTENT_H
+struct extent_chain {
+	int size; /* size of the extent ie sum (max-min+1) */
+	int allocs;
+	int frees;
+	int debug;
+	char *name;
+	struct extent *first;
+	struct extent *last;
+};
+
+/*
+ * We rely on extents not fitting evenly into a page.
+ * The last four bytes are used to store the number
+ * of the page, to make saving & reloading pages simpler.
+ */
+struct extent {
+	unsigned long minimum;
+	unsigned long maximum;
+	struct extent *next;
+};
+
+struct extent_iterate_state {
+	struct extent_chain *chains;
+	int num_chains;
+	int current_chain;
+	struct extent *current_extent;
+	unsigned long current_offset;
+};
+
+struct extent_iterate_saved_state {
+	int chain_num;
+	int extent_num;
+	unsigned long offset;
+};
+
+#define extent_state_eof(state) ((state)->num_chains < (state)->current_chain)
+
+#define extent_for_each(extent_chain, extentpointer, value) \
+if ((extent_chain)->first) \
+	for ((extentpointer) = (extent_chain)->first, (value) = \
+			(extentpointer)->minimum; \
+	     ((extentpointer) && ((extentpointer)->next || (value) <= \
+				 (extentpointer)->maximum)); \
+	     (((value) == (extentpointer)->maximum) ? \
+		((extentpointer) = (extentpointer)->next, (value) = \
+		 ((extentpointer) ? (extentpointer)->minimum : 0)) : \
+			(value)++))
+
+/*
+ * When using compression and expected_compression > 0,
+ * we allocate fewer swap entries, so GET_EXTENT_NEXT can
+ * validly run out of data to return.
+ */
+#define GET_EXTENT_NEXT(currentextent, currentval) \
+{ \
+	if (currentextent) { \
+		if ((currentval) == (currentextent)->maximum) { \
+			if ((currentextent)->next) { \
+				(currentextent) = (currentextent)->next; \
+				(currentval) = (currentextent)->minimum; \
+			} else { \
+				(currentextent) = NULL; \
+				(currentval) = 0; \
+			} \
+		} else \
+			currentval++; \
+	} \
+}
+
+extern int extents_allocated;
+void put_extent(struct extent *extent);
+void put_extent_chain(struct extent_chain *chain);
+int append_extent_to_extent_chain(struct extent_chain *chain, 
+		unsigned long minimum, unsigned long maximum);
+int serialise_extent_chain(struct extent_chain *chain);
+int load_extent_chain(struct extent_chain *chain);
+
+/* swap_entry_to_extent_val & extent_val_to_swap_entry: 
+ * We are putting offset in the low bits so consecutive swap entries
+ * make consecutive extent values */
+#define swap_entry_to_extent_val(swp_entry) (swp_entry.val)
+#define extent_val_to_swap_entry(val) (swp_entry_t) { (val) }
+
+void extent_state_save(struct extent_iterate_state *state,
+		struct extent_iterate_saved_state *saved_state);
+void extent_state_restore(struct extent_iterate_state *state,
+		struct extent_iterate_saved_state *saved_state);
+void extent_state_goto_start(struct extent_iterate_state *state);
+unsigned long extent_state_next(struct extent_iterate_state *state);
+#endif
diff -urN oldtree/kernel/power/io.c newtree/kernel/power/io.c
--- oldtree/kernel/power/io.c	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/io.c	2006-01-28 17:08:36.230727736 +0000
@@ -0,0 +1,991 @@
+/*
+ * kernel/power/io.c
+ *
+ * Copyright (C) 1998-2001 Gabor Kuti <seasons@fornax.hu>
+ * Copyright (C) 1998,2001,2002 Pavel Machek <pavel@suse.cz>
+ * Copyright (C) 2002-2003 Florent Chabaud <fchabaud@free.fr>
+ * Copyright (C) 2002-2005 Nigel Cunningham <nigel@suspend2.net>
+ *
+ * This file is released under the GPLv2.
+ *
+ * It contains high level IO routines for suspending.
+ *
+ */
+
+#include <linux/suspend.h>
+#include <linux/version.h>
+#include <linux/utsname.h>
+#include <linux/mount.h>
+#include <linux/suspend2.h>
+
+#include "version.h"
+#include "plugins.h"
+#include "pageflags.h"
+#include "io.h"
+#include "ui.h"
+#include "suspend2_common.h"
+#include "suspend2.h"
+#include "debug_pagealloc.h"
+#include "storage.h"
+
+/* attempt_to_parse_resume_device
+ *
+ * Can we suspend, using the current resume2= parameter?
+ */
+int attempt_to_parse_resume_device(void)
+{
+	struct list_head *writer;
+	struct suspend_plugin_ops *this_writer;
+	int result, returning = 0;
+
+	if (suspend2_activate_storage(0))
+		return 0;
+
+	active_writer = NULL;
+	clear_suspend_state(SUSPEND_RESUME_DEVICE_OK);
+	set_suspend_state(SUSPEND_DISABLED);
+	clear_result_state(SUSPEND_ABORTED);
+
+	if (!num_writers) {
+		printk(name_suspend "No writers have been registered. Suspending will be disabled.\n");
+		goto cleanup;
+	}
+	
+	if (!resume2_file[0]) {
+		printk(name_suspend "Resume2 parameter is empty. Suspending will be disabled.\n");
+		goto cleanup;
+	}
+
+	list_for_each(writer, &suspend_writers) {
+		this_writer = list_entry(writer, struct suspend_plugin_ops,
+				ops.writer.writer_list);
+
+		/* 
+		 * Not sure why you'd want to disable a writer, but
+		 * we should honour the flag if we're providing it
+		 */
+		if (this_writer->disabled) {
+			printk(name_suspend
+					"Writer '%s' is disabled. Ignoring it.\n",
+					this_writer->name);
+			continue;
+		}
+
+		result = this_writer->ops.writer.parse_sig_location(
+				resume2_file, (num_writers == 1));
+
+		switch (result) {
+			case -EINVAL:
+				/* 
+				 * For this writer, but not a valid 
+				 * configuration. Error already printed.
+				 */
+
+				goto cleanup;
+
+			case 0:
+				/*
+				 * For this writer and valid.
+				 */
+
+				active_writer = this_writer;
+
+				set_suspend_state(SUSPEND_RESUME_DEVICE_OK);
+				clear_suspend_state(SUSPEND_DISABLED);
+				printk(name_suspend "Suspending enabled.\n");
+
+				returning = 1;
+				goto cleanup;
+		}
+	}
+	printk(name_suspend "No matching enabled writer found. Suspending disabled.\n");
+cleanup:
+	suspend2_deactivate_storage(0);
+	return returning;
+}
+
+void attempt_to_parse_resume_device2(void)
+{
+	suspend2_prepare_usm();
+	attempt_to_parse_resume_device();
+	suspend2_cleanup_usm();
+}
+
+/* noresume_reset_plugins
+ *
+ * Description:	When we read the start of an image, plugins (and especially the
+ * 		active writer) might need to reset data structures if we decide
+ * 		to invalidate the image rather than resuming from it.
+ */
+
+static void noresume_reset_plugins(void)
+{
+	struct suspend_plugin_ops *this_filter;
+	
+	list_for_each_entry(this_filter, &suspend_filters, ops.filter.filter_list) {
+		if (this_filter->ops.filter.noresume_reset)
+			this_filter->ops.filter.noresume_reset();
+	}
+
+	if (active_writer && active_writer->ops.writer.noresume_reset)
+		active_writer->ops.writer.noresume_reset();
+}
+
+/* fill_suspend_header()
+ * 
+ * Description:	Fill the suspend header structure.
+ * Arguments:	struct suspend_header: Header data structure to be filled.
+ */
+
+static void fill_suspend_header(struct suspend_header *sh)
+{
+	int i;
+	
+	memset((char *)sh, 0, sizeof(*sh));
+
+	sh->version_code = LINUX_VERSION_CODE;
+	sh->num_physpages = num_physpages;
+	sh->orig_mem_free = suspend2_orig_mem_free;
+	strncpy(sh->machine, system_utsname.machine, 65);
+	strncpy(sh->version, system_utsname.version, 65);
+	sh->page_size = PAGE_SIZE;
+	sh->pagedir = pagedir1;
+	sh->pageset_2_size = pagedir2.pageset_size;
+	sh->param0 = suspend_result;
+	sh->param1 = suspend_action;
+	sh->param2 = suspend_debug_state;
+	sh->param3 = console_loglevel;
+	sh->root_fs = current->fs->rootmnt->mnt_sb->s_dev;
+	for (i = 0; i < 4; i++)
+		sh->io_time[i/2][i%2] =
+		       suspend_io_time[i/2][i%2];
+}
+
+/*
+ * rw_init_plugins
+ *
+ * Iterate over plugins, preparing the ones that will be used to read or write
+ * data.
+ */
+static int rw_init_plugins(int write, int which)
+{
+	struct suspend_plugin_ops *this_plugin;
+	/* Initialise page transformers */
+	list_for_each_entry(this_plugin, &suspend_filters,
+			ops.filter.filter_list) {
+		if (this_plugin->disabled)
+			continue;
+		if ((write && this_plugin->write_init &&
+			this_plugin->write_init(which)) ||
+		    (!write && this_plugin->read_init &&
+		     	this_plugin->read_init(which))) {
+			abort_suspend("Failed to initialise the %s filter.",
+				this_plugin->name);
+				return 1;
+		}
+	}
+
+	/* Initialise writer */
+	if ((write && active_writer->write_init(which)) ||
+	    (!write && active_writer->read_init(which))) {
+		abort_suspend("Failed to initialise the writer."); 
+		if (!write)
+			active_writer->ops.writer.invalidate_image();
+		return 1;
+	}
+
+	/* Initialise other plugins */
+	list_for_each_entry(this_plugin, &suspend_plugins, plugin_list) {
+		if (this_plugin->disabled)
+			continue;
+		if ((this_plugin->type == FILTER_PLUGIN) ||
+		    (this_plugin->type == WRITER_PLUGIN))
+			continue;
+		if ((write && this_plugin->write_init &&
+			this_plugin->write_init(which)) ||
+		    (!write && this_plugin->read_init &&
+		     	this_plugin->read_init(which))) {
+				set_result_state(SUSPEND_ABORTED);
+				return 1;
+			}
+	}
+
+	return 0;
+}
+
+/*
+ * rw_cleanup_plugins
+ *
+ * Cleanup components after reading or writing a set of pages.
+ * Only the writer may fail.
+ */
+static int rw_cleanup_plugins(int write)
+{
+	struct suspend_plugin_ops *this_plugin;
+	int result = 0;
+
+	/* Cleanup other plugins */
+	list_for_each_entry(this_plugin, &suspend_plugins, plugin_list) {
+		if (this_plugin->disabled)
+			continue;
+		if ((this_plugin->type == FILTER_PLUGIN) ||
+		    (this_plugin->type == WRITER_PLUGIN))
+			continue;
+		if (write) {
+			if (this_plugin->write_cleanup)
+				result |= this_plugin->write_cleanup();
+		} else
+			if (this_plugin->read_cleanup)
+				result |= this_plugin->read_cleanup();
+	}
+
+	/* Flush data and cleanup */
+	list_for_each_entry(this_plugin, &suspend_filters,
+			ops.filter.filter_list) {
+		if (this_plugin->disabled)
+			continue;
+		if (write) {
+			if (this_plugin->write_cleanup)
+				result |= this_plugin->write_cleanup();
+		} else
+			if (this_plugin->read_cleanup)
+				result |= this_plugin->read_cleanup();
+	}
+
+	if (write)
+		result |= active_writer->write_cleanup();
+	else
+		result |= active_writer->read_cleanup();
+
+	return result;
+}
+
+/*
+ * do_rw_loop
+ *
+ * The main I/O loop for reading or writing pages.
+ */
+static int do_rw_loop(int write, int finish_at, dyn_pageflags_t *pageflags,
+		int base, int barmax)
+{
+	int current_page_index = -1, pc, step = 1, nextupdate = 0, i;
+	int result;
+	struct suspend_plugin_ops *first_filter = get_next_filter(NULL);
+
+	current_page_index = get_next_bit_on(*pageflags, -1);
+
+	pc = finish_at / 5;
+
+	/* Read the pages */
+	for (i=0; i< finish_at; i++) {
+		int was_mapped = 0;
+		struct page *page = pfn_to_page(current_page_index);
+
+		/* Status */
+		if ((i+base) >= nextupdate)
+			nextupdate = suspend2_update_status(i+base, barmax,
+				" %d/%d MB ", MB(base+i+1), MB(barmax));
+
+		if ((i + 1) == pc) {
+			printk("%d%%...", 20 * step);
+			step++;
+			pc = finish_at * step / 5;
+		}
+		
+		was_mapped = suspend_map_kernel_page(page, 1);
+		if (write)
+			result = first_filter->ops.filter.write_chunk(page);
+		else
+			result = first_filter->ops.filter.read_chunk(page,
+					SUSPEND_ASYNC);
+		if (!was_mapped)
+			suspend_map_kernel_page(page, 0);
+
+		if (result) {
+			if (write) {
+				printk("Write chunk returned %d.\n", result);
+				abort_suspend("Failed to write a chunk of the "
+					"image.");
+				return result;
+			} else
+				panic("Failed to read chunk %d/%d of the image. (%d)",
+					i, finish_at, result);
+		}
+
+		/* Interactivity*/
+		check_shift_keys(0, NULL);
+
+		if (test_result_state(SUSPEND_ABORTED) && write)
+			return 1;
+
+		/* Prepare next */
+		current_page_index = get_next_bit_on(*pageflags,
+				current_page_index);
+	}
+
+	printk("done.\n");
+
+	suspend2_update_status(base + finish_at, barmax, " %d/%d MB ",
+			MB(base + finish_at), MB(barmax));
+	return 0;
+}
+
+/* write_pageset()
+ *
+ * Description:	Write a pageset to disk.
+ * Arguments:	pagedir:	Pointer to the pagedir to be saved.
+ * 		whichtowrite:	Controls what debugging output is printed.
+ * Returns:	Zero on success or -1 on failure.
+ */
+
+int write_pageset(struct pagedir *pagedir, int whichtowrite)
+{
+	int finish_at, base = 0, start_time, end_time;
+	int barmax = pagedir1.pageset_size + pagedir2.pageset_size;
+	long error = 0;
+	dyn_pageflags_t *pageflags;
+
+	/* 
+	 * Even if there is nothing to read or write, the writer
+	 * may need the init/cleanup for it's housekeeping.  (eg:
+	 * Pageset1 may start where pageset2 ends when writing).
+	 */
+	finish_at = pagedir->pageset_size;
+
+	if (whichtowrite == 1) {
+		suspend2_prepare_status(DONT_CLEAR_BAR,
+				"Writing kernel & process data...");
+		base = pagedir2.pageset_size;
+		if (test_action_state(SUSPEND_TEST_FILTER_SPEED) ||
+		    test_action_state(SUSPEND_TEST_BIO))
+			pageflags = &pageset1_map;
+		else
+			pageflags = &pageset1_copy_map;
+	} else {
+		suspend2_prepare_status(CLEAR_BAR, "Writing caches...");
+		pageflags = &pageset2_map;
+		bytes_in = bytes_out = 0;
+	}	
+	
+	start_time = jiffies;
+
+	if (!rw_init_plugins(1, whichtowrite))
+		error = do_rw_loop(1, finish_at, pageflags, base, barmax);
+
+	if (rw_cleanup_plugins(1)) {
+		abort_suspend("Failed to cleanup after writing.");
+		error = 1;
+	}
+
+	/* Statistics */
+	end_time = jiffies;
+	
+	if ((end_time - start_time) && (!test_result_state(SUSPEND_ABORTED))) {
+		suspend_io_time[0][0] += finish_at,
+		suspend_io_time[0][1] += (end_time - start_time);
+	}
+
+	return error;
+}
+
+/* read_pageset()
+ *
+ * Description:	Read a pageset from disk.
+ * Arguments:	pagedir:	Pointer to the pagedir to be saved.
+ * 		whichtowrite:	Controls what debugging output is printed.
+ * 		overwrittenpagesonly: Whether to read the whole pageset or
+ * 		only part.
+ * Returns:	Zero on success or -1 on failure.
+ */
+
+static int read_pageset(struct pagedir *pagedir, int whichtoread,
+		int overwrittenpagesonly)
+{
+	int result = 0, base = 0, start_time, end_time;
+	int finish_at = pagedir->pageset_size;
+	int barmax = pagedir1.pageset_size + pagedir2.pageset_size;
+	dyn_pageflags_t *pageflags;
+
+	if (whichtoread == 1) {
+		suspend2_prepare_status(CLEAR_BAR,
+				"Reading kernel & process data...");
+		pageflags = &pageset1_copy_map;
+	} else {
+		suspend2_prepare_status(DONT_CLEAR_BAR, "Reading caches...");
+		if (overwrittenpagesonly)
+			barmax = finish_at = min(pagedir1.pageset_size, 
+						 pagedir2.pageset_size);
+		else {
+			base = pagedir1.pageset_size;
+		}
+		pageflags = &pageset2_map;
+	}	
+	
+	start_time = jiffies;
+
+	if (rw_init_plugins(0, whichtoread)) {
+		active_writer->ops.writer.invalidate_image();
+		result = 1;
+	} else
+		result = do_rw_loop(0, finish_at, pageflags, base, barmax);
+
+	if (rw_cleanup_plugins(0)) {
+		abort_suspend("Failed to cleanup after reading.");
+		result = 1;
+	}
+
+	/* Statistics */
+	end_time=jiffies;
+
+	if ((end_time - start_time) && (!test_result_state(SUSPEND_ABORTED))) {
+		suspend_io_time[1][0] += finish_at,
+		suspend_io_time[1][1] += (end_time - start_time);
+	}
+
+	return result;
+}
+
+/* write_plugin_configs()
+ *
+ * Description:	Store the configuration for each plugin in the image header.
+ * Returns:	Int: Zero on success, Error value otherwise.
+ */
+static int write_plugin_configs(void)
+{
+	struct suspend_plugin_ops *this_plugin;
+	char *buffer = (char *) get_zeroed_page(GFP_ATOMIC);
+	int len, index = 1;
+	struct plugin_header plugin_header;
+
+	if (!buffer) {
+		printk("Failed to allocate a buffer for saving "
+				"plugin configuration info.\n");
+		return -ENOMEM;
+	}
+		
+	/* 
+	 * We have to know which data goes with which plugin, so we at
+	 * least write a length of zero for a plugin. Note that we are
+	 * also assuming every plugin's config data takes <= PAGE_SIZE.
+	 */
+
+	/* For each plugin (in registration order) */
+	list_for_each_entry(this_plugin, &suspend_plugins, plugin_list) {
+
+		/* Get the data from the plugin */
+		len = 0;
+		if (this_plugin->save_config_info)
+			len = this_plugin->save_config_info(buffer);
+
+		/* Save the details of the plugin */
+		plugin_header.disabled = this_plugin->disabled;
+		plugin_header.type = this_plugin->type;
+		plugin_header.index = index++;
+		strncpy(plugin_header.name, this_plugin->name, 
+					sizeof(plugin_header.name));
+		active_writer->ops.writer.write_header_chunk(
+				(char *) &plugin_header,
+				sizeof(plugin_header));
+
+		/* Save the size of the data and any data returned */
+		active_writer->ops.writer.write_header_chunk((char *) &len,
+				sizeof(int));
+		if (len)
+			active_writer->ops.writer.write_header_chunk(
+					buffer, len);
+	}
+
+	/* Write a blank header to terminate the list */
+	plugin_header.name[0] = '\0';
+	active_writer->ops.writer.write_header_chunk(
+			(char *) &plugin_header,
+			sizeof(plugin_header));
+
+	free_page((unsigned long) buffer);
+	return 0;
+}
+
+/* read_plugin_configs()
+ *
+ * Description:	Reload plugin configurations from the image header.
+ * Returns:	Int. Zero on success, error value otherwise.
+ */
+
+static int read_plugin_configs(void)
+{
+	struct suspend_plugin_ops *this_plugin;
+	char *buffer = (char *) get_zeroed_page(GFP_ATOMIC);
+	int len, result = 0;
+	struct plugin_header plugin_header;
+
+	if (!buffer) {
+		printk("Failed to allocate a buffer for reloading plugin "
+				"configuration info.\n");
+		return -ENOMEM;
+	}
+		
+	/* All plugins are initially disabled. That way, if we have a plugin
+	 * loaded now that wasn't loaded when we suspended, it won't be used
+	 * in trying to read the data.
+	 */
+	list_for_each_entry(this_plugin, &suspend_plugins, plugin_list)
+		this_plugin->disabled = 1;
+	
+	/* Get the first plugin header */
+	result = active_writer->ops.writer.read_header_chunk(
+			(char *) &plugin_header, sizeof(plugin_header));
+	if (!result) {
+		printk("Failed to read the next plugin header.\n");
+		free_page((unsigned long) buffer);
+		return -EINVAL;
+	}
+
+	/* For each plugin (in registration order) */
+	while (plugin_header.name[0]) {
+
+		/* Find the plugin */
+		this_plugin = find_plugin_given_name(plugin_header.name);
+
+		if (!this_plugin) {
+			/* 
+			 * Is it used? Only need to worry about filters. The active
+			 * writer must be loaded!
+			 */
+			if ((!plugin_header.disabled) &&
+			    (plugin_header.type == FILTER_PLUGIN)) {
+				suspend_early_boot_message(1, SUSPEND_CONTINUE_REQ,
+					"It looks like we need plugin %s for "
+					"reading the image but it hasn't been "
+					"registered.\n",
+					plugin_header.name);
+				if (!(test_suspend_state(SUSPEND_CONTINUE_REQ))) {
+					active_writer->ops.writer.invalidate_image();
+					result = -EINVAL;
+					noresume_reset_plugins();
+					free_page((unsigned long) buffer);
+					return -EINVAL;
+				}
+			} else
+				printk("Plugin %s configuration data found, but the plugin "
+					"hasn't registered. Looks like it was disabled, so "
+					"we're ignoring it's data.",
+					plugin_header.name);
+		}
+		
+		/* Get the length of the data (if any) */
+		result = active_writer->ops.writer.read_header_chunk(
+				(char *) &len, sizeof(int));
+		if (!result) {
+			printk("Failed to read the length of the plugin %s's"
+					" configuration data.\n",
+					plugin_header.name);
+			free_page((unsigned long) buffer);
+			return -EINVAL;
+		}
+
+		/* Read any data and pass to the plugin (if we found one) */
+		if (len) {
+			active_writer->ops.writer.read_header_chunk(buffer, len);
+			if (this_plugin) {
+				if (!this_plugin->save_config_info) {
+					printk("Huh? Plugin %s appears to have a "
+						"save_config_info, but not a "
+						"load_config_info function!\n",
+						this_plugin->name);
+				} else
+					this_plugin->load_config_info(buffer, len);
+			}
+		}
+
+		if (this_plugin) {
+			/* Now move this plugin to the tail of its lists. This will put it
+			 * in order. Any new plugins will end up at the top of the lists.
+			 * They should have been set to disabled when loaded (people will
+			 * normally not edit an initrd to load a new module and then
+			 * suspend without using it!).
+			 */
+
+			suspend_move_plugin_tail(this_plugin);
+
+			/* 
+			 * We apply the disabled state; plugins don't need to save whether they
+			 * were disabled and if they do, we override them anyway.
+			 */
+			this_plugin->disabled = plugin_header.disabled;
+		}
+
+		/* Get the next plugin header */
+		result = active_writer->ops.writer.read_header_chunk(
+				(char *) &plugin_header, sizeof(plugin_header));
+
+		if (!result) {
+			printk("Failed to read the next plugin header.\n");
+			free_page((unsigned long) buffer);
+			return -EINVAL;
+		}
+
+	}
+
+	free_page((unsigned long) buffer);
+	return 0;
+}
+
+/* write_image_header()
+ *
+ * Description:	Write the image header after write the image proper.
+ * Returns:	Int. Zero on success or -1 on failure.
+ */
+
+int write_image_header(void)
+{
+	int ret;
+	int total = pagedir1.pageset_size + pagedir2.pageset_size+2;
+	char *header_buffer = NULL;
+
+	/* Now prepare to write the header */
+	if ((ret = active_writer->ops.writer.write_header_init())) {
+		abort_suspend("Active writer's write_header_init"
+				" function failed.");
+		goto write_image_header_abort;
+	}
+
+	/* Get a buffer */
+	header_buffer = (char *) get_zeroed_page(GFP_ATOMIC);
+	if (!header_buffer) {
+		abort_suspend("Out of memory when trying to get page "
+				"for header!");
+		goto write_image_header_abort;
+	}
+
+	/* Write suspend header */
+	fill_suspend_header((struct suspend_header *) header_buffer);
+	active_writer->ops.writer.write_header_chunk(header_buffer,
+			sizeof(struct suspend_header));
+
+	free_page((unsigned long) header_buffer);
+
+	/* Write plugin configurations */
+	if ((ret = write_plugin_configs())) {
+		abort_suspend("Failed to write plugin configs.");
+		goto write_image_header_abort;
+	}
+
+	save_dyn_pageflags(pageset1_map);
+
+	if (active_writer->ops.writer.serialise_extents &&
+	    (ret = active_writer->ops.writer.serialise_extents())) {
+		abort_suspend("Active writer's prepare_save_extents "
+				"function failed.");
+		goto write_image_header_abort;
+	}
+
+	/* Flush data and let writer cleanup */
+	if (active_writer->ops.writer.write_header_cleanup()) {
+		abort_suspend("Failed to cleanup writing header.");
+		goto write_image_header_abort_no_cleanup;
+	}
+
+	if (test_result_state(SUSPEND_ABORTED))
+		goto write_image_header_abort_no_cleanup;
+
+	suspend_message(SUSPEND_IO, SUSPEND_VERBOSE, 1, "|\n");
+	suspend2_update_status(total, total, NULL);
+
+	return 0;
+
+write_image_header_abort:
+	active_writer->ops.writer.write_header_cleanup();
+write_image_header_abort_no_cleanup:
+	return -1;
+}
+
+/* sanity_check()
+ *
+ * Description:	Perform a few checks, seeking to ensure that the kernel being
+ * 		booted matches the one suspended. They need to match so we can
+ * 		be _sure_ things will work. It is not absolutely impossible for
+ * 		resuming from a different kernel to work, just not assured.
+ * Arguments:	Struct suspend_header. The header which was saved at suspend
+ * 		time.
+ */
+static char *sanity_check(struct suspend_header *sh)
+{
+	if (sh->version_code != LINUX_VERSION_CODE)
+		return "Incorrect kernel version.";
+	
+	if (sh->num_physpages != num_physpages)
+		return "Incorrect memory size.";
+
+	if (strncmp(sh->machine, system_utsname.machine, 65))
+		return "Incorrect machine type.";
+
+	if (strncmp(sh->version, system_utsname.version, 65))
+		return "Right kernel version but wrong build number.";
+
+	if (sh->page_size != PAGE_SIZE)
+		return "Incorrect PAGE_SIZE.";
+
+	if ((sh->root_fs == current->fs->rootmnt->mnt_sb->s_dev) &&
+	    (!test_suspend_state(SUSPEND_IGNORE_ROOTFS)))
+		return "Root filesystem has been mounted prior to trying to resume.";
+
+	return 0;
+}
+
+/* __read_pageset1
+ *
+ * Description:	Test for the existence of an image and attempt to load it.
+ * Returns:	Int. Zero if image found and pageset1 successfully loaded.
+ * 		Error if no image found or loaded.
+ */
+static int __read_pageset1(void)
+{			
+	int i, result = 0;
+	char *header_buffer = (char *) get_zeroed_page(GFP_ATOMIC), *sanity_error = NULL;
+	struct suspend_header *suspend_header;
+
+	if (!header_buffer)
+		return -ENOMEM;
+	
+	/* Check for an image */
+	if (!(result = active_writer->ops.writer.image_exists())) {
+		result = -ENODATA;
+		noresume_reset_plugins();
+		goto out;
+	}
+
+	/* Check for noresume command line option */
+	if (test_suspend_state(SUSPEND_NORESUME_SPECIFIED)) {
+		active_writer->ops.writer.invalidate_image();
+		result = -EINVAL;
+		noresume_reset_plugins();
+		goto out;
+	}
+
+	/* Check whether we've resumed before */
+	if (test_suspend_state(SUSPEND_RESUMED_BEFORE)) {
+		int resumed_before_default = 0;
+		if (test_suspend_state(SUSPEND_RETRY_RESUME))
+			resumed_before_default = SUSPEND_CONTINUE_REQ;
+		suspend_early_boot_message(1, resumed_before_default, NULL);
+		clear_suspend_state(SUSPEND_RETRY_RESUME);
+		if (!(test_suspend_state(SUSPEND_CONTINUE_REQ))) {
+			active_writer->ops.writer.invalidate_image();
+			result = -EINVAL;
+			noresume_reset_plugins();
+			goto out;
+		}
+	}
+
+	clear_suspend_state(SUSPEND_CONTINUE_REQ);
+
+	/* 
+	 * Prepare the active writer for reading the image header. The
+	 * activate writer might read its own configuration.
+	 * 
+	 * NB: This call may never return because there might be a signature
+	 * for a different image such that we warn the user and they choose
+	 * to reboot. (If the device ids look erroneous (2.4 vs 2.6) or the
+	 * location of the image might be unavailable if it was stored on a
+	 * network connection.
+	 */
+
+	if ((result = active_writer->ops.writer.read_header_init())) {
+		noresume_reset_plugins();
+		goto out;
+	}
+	
+	/* Read suspend header */
+	if ((result = active_writer->ops.writer.read_header_chunk(
+			header_buffer, sizeof(struct suspend_header))) < 0) {
+		noresume_reset_plugins();
+		goto out;
+	}
+	
+	suspend_header = (struct suspend_header *) header_buffer;
+
+	/*
+	 * NB: This call may also result in a reboot rather than returning.
+	 */
+
+	if ((sanity_error = sanity_check(suspend_header)) &&
+	    suspend_early_boot_message(1, SUSPEND_CONTINUE_REQ, sanity_error)) {
+		active_writer->ops.writer.invalidate_image();
+		result = -EINVAL;
+		noresume_reset_plugins();
+		goto out;
+	}
+
+	/*
+	 * We have an image and it looks like it will load okay.
+	 */
+
+	/* Get metadata from header. Don't override commandline parameters.
+	 *
+	 * We don't need to save the image size limit because it's not used
+	 * during resume and will be restored with the image anyway.
+	 */
+	
+	suspend2_orig_mem_free = suspend_header->orig_mem_free;
+	memcpy((char *) &pagedir1,
+		(char *) &suspend_header->pagedir, sizeof(pagedir1));
+	suspend_result = suspend_header->param0;
+	if (!test_suspend_state(SUSPEND_ACT_USED))
+		suspend_action = suspend_header->param1;
+	if (!test_suspend_state(SUSPEND_DBG_USED))
+		suspend_debug_state = suspend_header->param2;
+	if (!test_suspend_state(SUSPEND_LVL_USED))
+		suspend_default_console_level = suspend_header->param3;
+	clear_suspend_state(SUSPEND_IGNORE_LOGLEVEL);
+	pagedir2.pageset_size = suspend_header->pageset_2_size;
+	for (i = 0; i < 4; i++)
+		suspend_io_time[i/2][i%2] =
+			suspend_header->io_time[i/2][i%2];
+
+	/* Read plugin configurations */
+	if ((result = read_plugin_configs())) {
+		noresume_reset_plugins();
+		pagedir1.pageset_size =
+			pagedir2.pageset_size = 0;
+		goto out;
+	}
+
+	suspend2_prepare_console();
+
+	check_shift_keys(1, "About to read original pageset1 locations.");
+	/* Read original pageset1 locations. These are the addresses we can't use for
+	 * the data to be restored */
+	allocate_dyn_pageflags(&pageset1_map);
+	load_dyn_pageflags(pageset1_map);
+
+	allocate_dyn_pageflags(&conflicting_pages_map);
+
+	set_suspend_state(SUSPEND_NOW_RESUMING);
+
+	/* Relocate it so that it's not overwritten while we're using it to
+	 * copy the original contents back */
+	relocate_dyn_pageflags(&pageset1_map);
+	relocate_dyn_pageflags(&conflicting_pages_map);
+	
+	allocate_dyn_pageflags(&pageset1_copy_map);
+	relocate_dyn_pageflags(&pageset1_copy_map);
+
+	/* Read extent pages */
+	if (active_writer->ops.writer.load_extents &&
+	    (result = active_writer->ops.writer.load_extents())) {
+		noresume_reset_plugins();
+		abort_suspend("Active writer's load_extents "
+				"function failed.");
+		goto out_reset_console;
+	}
+
+	/* Clean up after reading the header */
+	if ((result = active_writer->ops.writer.read_header_cleanup())) {
+		noresume_reset_plugins();
+		goto out_reset_console;
+	}
+
+	check_shift_keys(1, "About to read pagedir.");
+
+	/* 
+	 * Get the addresses of pages into which we will load the kernel to
+	 * be copied back
+	 */
+	if (suspend2_get_pageset1_load_addresses()) {
+		result = -ENOMEM;
+		noresume_reset_plugins();
+		goto out_reset_console;
+	}
+
+	/* Read the original kernel back */
+	check_shift_keys(1, "About to read pageset 1.");
+
+	if (read_pageset(&pagedir1, 1, 0)) {
+		suspend2_prepare_status(CLEAR_BAR, "Failed to read pageset 1.");
+		result = -EPERM;
+		noresume_reset_plugins();
+		goto out_reset_console;
+	}
+
+	check_shift_keys(1, "About to restore original kernel.");
+	result = 0;
+
+	if (!test_action_state(SUSPEND_KEEP_IMAGE) &&
+	    active_writer->ops.writer.mark_resume_attempted)
+		active_writer->ops.writer.mark_resume_attempted();
+
+out:
+	free_page((unsigned long) header_buffer);
+	return result;
+
+out_reset_console:
+	free_dyn_pageflags(&pageset1_map);
+	free_dyn_pageflags(&pageset1_copy_map);
+	free_dyn_pageflags(&conflicting_pages_map);
+	suspend2_cleanup_console();
+	goto out;
+}
+
+/* read_pageset1()
+ *
+ * Description:	Attempt to read the header and pageset1 of a suspend image.
+ * 		Handle the outcome, complaining where appropriate.
+ */
+extern int block_dump;
+
+int read_pageset1(void)
+{
+	int error;
+
+	block_dump = 1;
+
+	error = __read_pageset1();
+
+	block_dump = 0;
+	
+	switch (error) {
+		case 0:
+		case -ENODATA:
+		case -EINVAL:	/* non fatal error */
+			return error;
+		case -EIO:
+			printk(KERN_CRIT name_suspend "I/O error\n");
+			break;
+		case -ENOENT:
+			printk(KERN_CRIT name_suspend "No such file or directory\n");
+			break;
+		case -EPERM:
+			printk(KERN_CRIT name_suspend "Sanity check error\n");
+			break;
+		default:
+			printk(KERN_CRIT name_suspend "Error %d resuming\n", error);
+			break;
+	}
+	abort_suspend("Error %d in read_pageset1",error);
+	return error;
+}
+
+/* read_pageset2()
+ *
+ * Description:	Read in part or all of pageset2 of an image, depending upon
+ * 		whether we are suspending and have only overwritten a portion
+ * 		with pageset1 pages, or are resuming and need to read them 
+ * 		all.
+ * Arguments:	Int. Boolean. Read only pages which would have been
+ * 		overwritten by pageset1?
+ * Returns:	Int. Zero if no error, otherwise the error value.
+ */
+int read_pageset2(int overwrittenpagesonly)
+{
+	int result = 0;
+
+	if (!pagedir2.pageset_size)
+		return 0;
+
+	result = read_pageset(&pagedir2, 2, overwrittenpagesonly);
+
+	suspend2_update_status(100, 100, NULL);
+	check_shift_keys(1, "Pagedir 2 read.");
+
+	return result;
+}
diff -urN oldtree/kernel/power/io.h newtree/kernel/power/io.h
--- oldtree/kernel/power/io.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/io.h	2006-01-28 17:08:36.230727736 +0000
@@ -0,0 +1,38 @@
+/*
+ * kernel/power/io.h
+ */
+
+#include "pagedir.h"
+
+/* Non-plugin data saved in our image header */
+struct suspend_header {
+	u32 version_code;
+	unsigned long num_physpages;
+	unsigned long orig_mem_free;
+	char machine[65];
+	char version[65];
+	int num_cpus;
+	int page_size;
+	int pageset_2_size;
+	int param0;
+	int param1;
+	int param2;
+	int param3;
+	int progress0;
+	int progress1;
+	int progress2;
+	int progress3;
+	int io_time[2][2];
+	struct pagedir pagedir;
+	dev_t root_fs;
+};
+
+extern int write_pageset(struct pagedir *pagedir, int whichtowrite);
+extern int write_image_header(void);
+extern int read_pageset1(void);
+extern int read_pageset2(int overwrittenpagesonly);
+
+extern int attempt_to_parse_resume_device(void);
+extern void attempt_to_parse_resume_device2(void);
+extern dev_t name_to_dev_t(char *line);
+extern __nosavedata unsigned long bytes_in, bytes_out;
diff -urN oldtree/kernel/power/main.c newtree/kernel/power/main.c
--- oldtree/kernel/power/main.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/kernel/power/main.c	2006-01-28 17:08:36.231727584 +0000
@@ -9,6 +9,7 @@
  */
 
 #include <linux/suspend.h>
+#include <linux/freezer.h>
 #include <linux/kobject.h>
 #include <linux/string.h>
 #include <linux/delay.h>
@@ -95,7 +96,7 @@
 	if (pm_ops->finish)
 		pm_ops->finish(state);
  Thaw:
-	thaw_processes();
+	thaw_processes(FREEZER_ALL_THREADS);
  Enable_cpu:
 	enable_nonboot_cpus();
 	pm_restore_console();
@@ -103,7 +104,7 @@
 }
 
 
-static int suspend_enter(suspend_state_t state)
+int suspend_enter(suspend_state_t state)
 {
 	int error = 0;
 	unsigned long flags;
@@ -135,7 +136,7 @@
 	device_resume();
 	if (pm_ops && pm_ops->finish)
 		pm_ops->finish(state);
-	thaw_processes();
+	thaw_processes(FREEZER_ALL_THREADS);
 	enable_nonboot_cpus();
 	pm_restore_console();
 }
diff -urN oldtree/kernel/power/netlink.c newtree/kernel/power/netlink.c
--- oldtree/kernel/power/netlink.c	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/netlink.c	2006-01-28 17:08:36.231727584 +0000
@@ -0,0 +1,365 @@
+/*
+ * netlink.c
+ *
+ * Functions for communicating with a userspace helper via netlink.
+ */
+
+
+#include <linux/suspend.h>
+#include "netlink.h"
+
+#ifdef CONFIG_NET
+struct user_helper_data *uhd_list = NULL;
+
+/* 
+ * Refill our pool of SKBs for use in emergencies (eg, when eating memory and none
+ * can be allocated).
+ */
+static void suspend2_fill_skb_pool(struct user_helper_data *uhd)
+{
+	while (uhd->pool_level < uhd->pool_limit) {
+		struct sk_buff *new_skb =
+			alloc_skb(NLMSG_SPACE(uhd->skb_size), GFP_ATOMIC);
+
+		if (!new_skb)
+			break;
+
+		new_skb->next = uhd->emerg_skbs;
+		uhd->emerg_skbs = new_skb;
+		uhd->pool_level++;
+	}
+}
+
+/* 
+ * Try to allocate a single skb. If we can't get one, try to use one from
+ * our pool.
+ */
+static struct sk_buff *suspend2_get_skb(struct user_helper_data *uhd)
+{
+	struct sk_buff *skb =
+		alloc_skb(NLMSG_SPACE(uhd->skb_size), GFP_ATOMIC);
+
+	if (skb)
+		return skb;
+
+	skb = uhd->emerg_skbs;
+	if (skb) {
+		uhd->pool_level--;
+		uhd->emerg_skbs = skb->next;
+		skb->next = NULL;
+	}
+
+	return skb;
+}
+
+static void put_skb(struct user_helper_data *uhd, struct sk_buff *skb)
+{
+	if (uhd->pool_level < uhd->pool_limit) {
+		skb->next = uhd->emerg_skbs;
+		uhd->emerg_skbs = skb;
+	} else
+		kfree_skb(skb);
+}
+
+
+static void suspend2_notify_userspace(void* data)
+{
+	struct task_struct *t;
+	struct user_helper_data *uhd = (struct user_helper_data *) data;
+
+	BUG_ON(!uhd);
+
+	read_lock(&tasklist_lock);
+	if ((t = find_task_by_pid(uhd->pid)))
+		wake_up_process(t);
+	read_unlock(&tasklist_lock);
+}
+
+DECLARE_WORK(suspend2_notify_userspace_work, suspend2_notify_userspace, NULL);
+
+void suspend2_send_netlink_message(struct user_helper_data *uhd,
+		int type, void* params, size_t len)
+{
+	struct sk_buff *skb;
+	struct nlmsghdr *nlh;
+	void *dest;
+
+	skb = suspend2_get_skb(uhd);
+	if (!skb) {
+		printk("suspend_netlink: Can't allocate skb!\n");
+		return;
+	}
+
+	/* NLMSG_PUT contains a hidden goto nlmsg_failure */
+	nlh = NLMSG_PUT(skb, 0, uhd->sock_seq, type, len);
+	uhd->sock_seq++;
+
+	dest = NLMSG_DATA(nlh);
+	if (params && len > 0)
+		memcpy(dest, params, len);
+
+	netlink_unicast(uhd->nl, skb, uhd->pid, 0);
+
+	/* We may be in an interrupt context so defer waking up userspace */
+	suspend2_notify_userspace_work.data = uhd;
+	schedule_work(&suspend2_notify_userspace_work);
+
+	return;
+
+nlmsg_failure:
+	if (skb)
+		put_skb(uhd, skb);
+}
+
+#ifdef CONFIG_PM_DEBUG
+static int is_debugging = 1;
+#else
+static int is_debugging = 0;
+#endif
+
+static void send_whether_debugging(struct user_helper_data *uhd)
+{
+	suspend2_send_netlink_message(uhd, NETLINK_MSG_IS_DEBUGGING,
+			&is_debugging, sizeof(int));
+}
+
+/*
+ * Set the PF_NOFREEZE flag on the given process to ensure it can run whilst we
+ * are suspending.
+ */
+static int nl_set_nofreeze(struct user_helper_data *uhd, int pid)
+{
+	struct task_struct *t;
+
+	read_lock(&tasklist_lock);
+	if ((t = find_task_by_pid(pid)) == NULL) {
+		read_unlock(&tasklist_lock);
+		printk("Strange. Can't find the userspace task %d.\n", pid);
+		return -EINVAL;
+	}
+
+	t->flags |= PF_NOFREEZE;
+
+	read_unlock(&tasklist_lock);
+	uhd->pid = pid;
+
+	suspend2_send_netlink_message(uhd, NETLINK_MSG_NOFREEZE_ACK, NULL, 0);
+
+	return 0;
+}
+
+/*
+ * Called when the userspace process has informed us that it's ready to roll.
+ */
+static int nl_ready(struct user_helper_data *uhd, int version)
+{
+	if (version != uhd->interface_version) {
+		printk("%s userspace process using invalid interface version."
+				" Trying to continue without it.\n",
+				uhd->name);
+		if (uhd->not_ready)
+			uhd->not_ready();
+		return 1;
+	}
+
+	complete(&uhd->wait_for_process);
+
+	return 0;
+}
+
+static int suspend2_nl_gen_rcv_msg(struct user_helper_data *uhd,
+		struct sk_buff *skb, struct nlmsghdr *nlh)
+{
+	int type;
+	int *data;
+	int err;
+
+	/* Let the more specific handler go first. It returns
+	 * 1 for valid messages that it doesn't know. */
+	if ((err = uhd->rcv_msg(skb, nlh)) != 1)
+		return err;
+	
+	type = nlh->nlmsg_type;
+
+	/* Only allow one task to receive NOFREEZE privileges */
+	if (type == NETLINK_MSG_NOFREEZE_ME && uhd->pid != -1) {
+		printk("Received extra nofreeze me requests.\n");
+		return -EBUSY;
+	}
+
+	data = (int*)NLMSG_DATA(nlh);
+
+	switch (type) {
+		case NETLINK_MSG_NOFREEZE_ME:
+			if ((err = nl_set_nofreeze(uhd, nlh->nlmsg_pid)) != 0)
+				return err;
+			break;
+		case NETLINK_MSG_GET_DEBUGGING:
+			send_whether_debugging(uhd);
+			break;
+		case NETLINK_MSG_READY:
+			if (nlh->nlmsg_len < NLMSG_LENGTH(sizeof(int))) {
+				printk("Invalid ready mesage.\n");
+				return -EINVAL;
+			}
+			if ((err = nl_ready(uhd, *data)) != 0)
+				return err;
+			break;
+	}
+
+	return 0;
+}
+
+static void suspend2_user_rcv_skb(struct user_helper_data *uhd,
+				  struct sk_buff *skb)
+{
+	int err;
+	struct nlmsghdr *nlh;
+
+	while (skb->len >= NLMSG_SPACE(0)) {
+		u32 rlen;
+
+		nlh = (struct nlmsghdr *) skb->data;
+		if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len)
+			return;
+
+		rlen = NLMSG_ALIGN(nlh->nlmsg_len);
+		if (rlen > skb->len)
+			rlen = skb->len;
+
+		if ((err = suspend2_nl_gen_rcv_msg(uhd, skb, nlh)) != 0)
+			netlink_ack(skb, nlh, err);
+		else if (nlh->nlmsg_flags & NLM_F_ACK)
+			netlink_ack(skb, nlh, 0);
+		skb_pull(skb, rlen);
+	}
+}
+
+static void suspend2_netlink_input(struct sock *sk, int len)
+{
+	struct user_helper_data *uhd = uhd_list;
+
+	while (uhd && uhd->netlink_id != sk->sk_protocol)
+		uhd= uhd->next;
+
+	BUG_ON(!uhd);
+
+	do {
+		struct sk_buff *skb;
+		while ((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) {
+			suspend2_user_rcv_skb(uhd, skb);
+			put_skb(uhd, skb);
+		}
+	} while (uhd->nl && uhd->nl->sk_receive_queue.qlen);
+}
+
+static int netlink_prepare(struct user_helper_data *uhd)
+{
+	uhd->next = uhd_list;
+	uhd_list = uhd;
+
+	uhd->sock_seq = 0x42c0ffee;
+	uhd->nl = netlink_kernel_create(uhd->netlink_id, 0,
+			suspend2_netlink_input, THIS_MODULE);
+	if (!uhd->nl) {
+		printk("Failed to allocate netlink socket for %s.\n",
+				uhd->name);
+		return -ENOMEM;
+	}
+
+	suspend2_fill_skb_pool(uhd);
+
+	return 0;
+}
+
+void suspend2_netlink_close(struct user_helper_data *uhd)
+{
+	if (uhd->nl) {
+		sock_release(uhd->nl->sk_socket);
+		uhd->nl = NULL;
+	}
+
+	while (uhd->emerg_skbs) {
+		struct sk_buff *next = uhd->emerg_skbs->next;
+		kfree_skb(uhd->emerg_skbs);
+		uhd->emerg_skbs = next;
+	}
+}
+
+static int launch_userpace_program(struct user_helper_data *uhd)
+{
+	int retval;
+	static char *envp[] = {
+			"HOME=/",
+			"TERM=linux",
+			"PATH=/sbin:/usr/sbin:/bin:/usr/bin",
+			NULL };
+	static char *argv[] = { NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL };
+	char *channel = kmalloc(6, GFP_KERNEL);
+	int arg = 0, size;
+	char test_read[255];
+	char *orig_posn = uhd->program;
+
+	if (!strlen(orig_posn))
+		return 1;
+
+	while (arg < 7) {
+		sscanf(orig_posn, "%s", test_read);
+		size = strlen(test_read);
+		if (!(size))
+			break;
+		argv[arg] = kmalloc(size + 1, GFP_ATOMIC);
+		strcpy(argv[arg], test_read);
+		orig_posn += size + 1;
+		*test_read = 0;
+		arg++;
+	}
+	
+	sprintf(channel, "-c%d", uhd->netlink_id);
+	argv[arg] = channel;
+
+	retval = call_usermodehelper(argv[0], argv, envp, 0);
+
+	if (retval)
+		printk("suspend_netlink: Failed to launch userui program: Error %d\n", retval);
+
+	{
+		int i;
+		for (i = 0; i < arg; i++)
+			if (argv[i] && argv[i] != channel)
+				kfree(argv[i]);
+	}
+
+	kfree(channel);
+
+	return retval;
+}
+
+int suspend2_netlink_setup(struct user_helper_data *uhd)
+{
+	if (netlink_prepare(uhd) < 0) {
+		printk("Netlink prepare failed.\n");
+		return 1;
+	}
+
+	if (launch_userpace_program(uhd) < 0) {
+		printk("Launch userspace program failed.\n");
+		suspend2_netlink_close(uhd);
+		return 1;
+	}
+
+	/* Wait 2 seconds for the userspace process to make contact */
+	wait_for_completion_timeout(&uhd->wait_for_process, 2*HZ);
+
+	if (uhd->pid == -1) {
+		printk("%s: Failed to contact userspace process.\n",
+				uhd->name);
+		suspend2_netlink_close(uhd);
+		return 1;
+	}
+
+	return 0;
+}
+
+#else
+#endif
diff -urN oldtree/kernel/power/netlink.h newtree/kernel/power/netlink.h
--- oldtree/kernel/power/netlink.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/netlink.h	2006-01-28 17:08:36.232727432 +0000
@@ -0,0 +1,43 @@
+/*
+ * netlink.h
+ *
+ * Declarations for functions for communicating with a userspace helper
+ * via netlink.
+ */
+
+#include <linux/netlink.h>
+#include <net/sock.h>
+
+#define NETLINK_MSG_BASE 0x10
+
+#define NETLINK_MSG_READY 0x10
+#define	NETLINK_MSG_NOFREEZE_ME 0x16
+#define NETLINK_MSG_GET_DEBUGGING 0x19
+#define NETLINK_MSG_CLEANUP 0x24
+#define NETLINK_MSG_NOFREEZE_ACK 0x27
+#define NETLINK_MSG_IS_DEBUGGING 0x28
+
+struct user_helper_data {
+	int (*rcv_msg) (struct sk_buff *skb, struct nlmsghdr *nlh);
+	void (* not_ready) (void);
+	struct sock *nl;
+	u32 sock_seq;
+	pid_t pid;
+	char *comm;
+	char program[256];
+	int pool_level;
+	int pool_limit;
+	struct sk_buff *emerg_skbs;
+	int skb_size;
+	int netlink_id;	
+	char *name;
+	struct user_helper_data *next;
+	struct completion wait_for_process;
+	int interface_version;
+	int must_init;
+};
+
+void suspend2_send_netlink_message(struct user_helper_data *uhd,
+		int type, void* params, size_t len);
+int suspend2_netlink_setup(struct user_helper_data *uhd);
+void suspend2_netlink_close(struct user_helper_data *uhd);
diff -urN oldtree/kernel/power/pagedir.c newtree/kernel/power/pagedir.c
--- oldtree/kernel/power/pagedir.c	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/pagedir.c	2006-01-28 17:08:36.232727432 +0000
@@ -0,0 +1,370 @@
+/*
+ * kernel/power/pagedir.c
+ *
+ * Copyright (C) 1998-2001 Gabor Kuti <seasons@fornax.hu>
+ * Copyright (C) 1998,2001,2002 Pavel Machek <pavel@suse.cz>
+ * Copyright (C) 2002-2003 Florent Chabaud <fchabaud@free.fr>
+ * Copyright (C) 2002-2005 Nigel Cunningham <nigel@suspend2.net>
+ *
+ * This file is released under the GPLv2.
+ *
+ * Routines for handling pagesets.
+ * Note that pbes aren't actually stored as such. They're stored as
+ * bitmaps and extents.
+ */
+
+#include <linux/suspend.h>
+#include <linux/highmem.h>
+#include <linux/bootmem.h>
+#include <linux/hardirq.h>
+
+#include "pageflags.h"
+#include "ui.h"
+#include "pagedir.h"
+
+int extra_pagedir_pages_allocated = 0;
+
+/* Not static so allocation routine can BUG if recursively called */
+dyn_pageflags_t conflicting_pages_map;
+
+#define PageConflicting(page) (test_dynpageflag(&conflicting_pages_map, page))
+#define SetPageConflicting(page) (set_dynpageflag(&conflicting_pages_map, page))
+#define ClearPageConflicting(page) (clear_dynpageflag(&conflicting_pages_map, page))
+
+/* suspend2_free_extra_pagedir_memory
+ *
+ * Description:	Free a previously pagedir metadata.
+ */
+void suspend2_free_extra_pagedir_memory(void)
+{
+	unsigned long pagenumber;
+
+	free_dyn_pageflags(&pageset1_map);
+	free_dyn_pageflags(&pageset2_map);
+	free_dyn_pageflags(&pageset1_copy_map);
+
+	/* Free allocated pages */
+	if (allocd_pages_map) {
+		BITMAP_FOR_EACH_SET(allocd_pages_map, pagenumber) {
+			struct page *page = pfn_to_page(pagenumber);
+			ClearPageNosave(page);
+			__free_page(page);
+			extra_pagedir_pages_allocated--;
+		}
+		free_dyn_pageflags(&allocd_pages_map);
+	}
+}
+
+/* suspend2_allocate_extra_pagedir_memory
+ *
+ * Description:	Allocate memory for making the atomic copy of pagedir1 in the
+ * 		case where it is bigger than pagedir2.
+ * Arguments:	struct pagedir *: 	The pagedir for which we should 
+ * 					allocate memory.
+ * 		int:			Size of pageset 1.
+ * 		int:			Size of pageset 2.
+ * Result:	int. Zero on success. One if unable to allocate enough memory.
+ */
+int suspend2_allocate_extra_pagedir_memory(struct pagedir *p, int pageset_size,
+		int alloc_from)
+{
+	int num_to_alloc = pageset_size - alloc_from - extra_pagedir_pages_allocated;
+	int j, order;
+
+	if (num_to_alloc < 1)
+		num_to_alloc = 0;
+
+	if (num_to_alloc) {
+		int num_added = 0;
+	
+		order = generic_fls(num_to_alloc);
+		if (order >= MAX_ORDER)
+			order = MAX_ORDER - 1;
+
+		while (num_added < num_to_alloc) {
+			struct page *newpage;
+			unsigned long virt;
+			
+			while ((1 << order) > (num_to_alloc - num_added))
+				order--;
+
+			virt = __get_free_pages(GFP_ATOMIC | __GFP_NOWARN, order);
+			while ((!virt) && (order > 0)) {
+				order--;
+				virt = __get_free_pages(GFP_ATOMIC | __GFP_NOWARN, order);
+			}
+
+			if (!virt) {
+				p->pageset_size += num_added;
+				return 1;
+			}
+
+			newpage = virt_to_page(virt);
+			for (j = 0; j < (1 << order); j++) {
+				SetPageNosave(newpage + j);
+				/* Pages will be freed one at a time. */
+				set_page_count(newpage + j, 1);
+				SetPageAllocd(newpage + j);
+				extra_pagedir_pages_allocated++;
+			}
+			num_added+= (1 << order);
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * suspend2_mark_task_as_pageset1
+ * Functionality   : Marks all the pages belonging to a given process as
+ *                   pageset 1 pages.
+ * Called From     : pagedir.c - mark_pages_for_pageset2
+ *
+ */
+extern struct page *suspend2_follow_page(struct mm_struct *mm, unsigned long address);
+
+void suspend2_mark_task_as_pageset1(struct task_struct *t)
+{
+	struct vm_area_struct *vma;
+	struct mm_struct *mm;
+
+	mm = t->active_mm;
+
+	if (!mm || !mm->mmap) return;
+
+	/* Don't try to take the sem when processes are frozen, 
+	 * drivers are suspended and irqs are disabled. We're
+	 * not racing with anything anyway.  */
+	BUG_ON(in_atomic() && !irqs_disabled());
+
+	if (!irqs_disabled())
+		down_read(&mm->mmap_sem);
+	
+	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+		if (vma->vm_flags & VM_PFNMAP)
+			continue;
+		if (vma->vm_start) {
+			unsigned long posn;
+			for (posn = vma->vm_start; posn < vma->vm_end;
+					posn += PAGE_SIZE) {
+				struct page *page = 
+					suspend2_follow_page(mm, posn);
+				if (page)
+					ClearPagePageset2(page);
+			}
+		}
+	}
+
+	BUG_ON(in_atomic() && !irqs_disabled());
+
+	if (!irqs_disabled())
+		up_read(&mm->mmap_sem);
+}
+
+/* mark_pages_for_pageset2
+ *
+ * Description:	Mark unshared pages in processes not needed for suspend as
+ * 		being able to be written out in a separate pagedir.
+ * 		HighMem pages are simply marked as pageset2. They won't be
+ * 		needed during suspend.
+ */
+
+struct attention_list {
+	struct task_struct *task;
+	struct attention_list *next;
+};
+
+#define HALT_ON(condition) \
+	do { if (unlikely(condition)) { \
+		printk("Suspend2: Halting at line %d. Please report to nigel@suspend2.net.\n", __LINE__); \
+		while(1) \
+			cpu_relax(); \
+		} } while(0)
+
+void suspend2_mark_pages_for_pageset2(void)
+{
+	struct zone *zone;
+	struct task_struct *p;
+	struct attention_list *attention_list = NULL, *last = NULL;
+	unsigned long flags, i;
+
+	HALT_ON(in_atomic() && !irqs_disabled());
+
+	clear_dyn_pageflags(pageset2_map);
+
+	if (test_action_state(SUSPEND_NO_PAGESET2))
+		return;
+
+	/* 
+	 * Note that we don't clear the map to begin with!
+	 * This is because if we eat memory, we loose track
+	 * of LRU pages that are still in use but taken off
+	 * the LRU. If I can figure out how the VM keeps
+	 * track of them, I might be able to tweak this a
+	 * little further and decrease pageset one's size
+	 * further.
+	 *
+	 * (Memory grabbing clears the pageset2 flag on
+	 * pages that are really freed!).
+	 */
+	
+	for_each_zone(zone) {
+		spin_lock_irqsave(&zone->lru_lock, flags);
+		if (zone->nr_inactive) {
+			struct page *page;
+			list_for_each_entry(page, &zone->inactive_list, lru)
+				SetPagePageset2(page);
+		}
+		if (zone->nr_active) {
+			struct page *page;
+			list_for_each_entry(page, &zone->active_list, lru)
+				SetPagePageset2(page);
+		}
+		spin_unlock_irqrestore(&zone->lru_lock, flags);
+	}
+
+	HALT_ON(in_atomic() && !irqs_disabled());
+
+	/* Now we find all userspace process (with task->mm) marked PF_NOFREEZE
+	 * and move them into pageset1.
+	 */
+	read_lock(&tasklist_lock);
+	for_each_process(p)
+		if ((p->mm || p->active_mm) && (p->flags & PF_NOFREEZE)) {
+			struct attention_list *this = kmalloc(sizeof(struct attention_list), GFP_ATOMIC);
+			BUG_ON(!this);
+			this->task = p;
+			this->next = NULL;
+			if (attention_list) {
+				last->next = this;
+				last = this;
+			} else
+				attention_list = last = this;
+		}
+	read_unlock(&tasklist_lock);
+
+	HALT_ON(in_atomic() && !irqs_disabled());
+
+	/* Because the tasks in attention_list are ones related to suspending,
+	 * we know that they won't go away under us.
+	 */
+
+	while (attention_list) {
+		suspend2_mark_task_as_pageset1(attention_list->task);
+		last = attention_list;
+		attention_list = attention_list->next;
+		kfree(last);
+	}
+
+	HALT_ON(in_atomic() && !irqs_disabled());
+
+	for_each_zone(zone) {
+		if (!zone->present_pages)
+			continue;
+		for (i = 0; i < zone->spanned_pages; i++) {
+			struct page *page = pfn_to_page(zone->zone_start_pfn + i);
+			BUG_ON(PagePageset2(page) && PageSlab(page));
+		}
+	}
+
+	HALT_ON(in_atomic() && !irqs_disabled());
+
+}
+
+/* suspend2_get_nonconflicting_pages
+ *
+ * Description: Gets higher-order pages that won't be overwritten
+ *		while copying the original pages.
+ *
+ *		Note that if only one of the allocated pages overlaps
+ *		with the pages that overlap, another set must be
+ *		tried. Therefore, you shouldn't use this function
+ *		much, and not with high orders.
+ */
+
+unsigned long suspend2_get_nonconflicting_pages(const int order)
+{
+	struct page *page;
+	unsigned long new_page, i;
+	int more = 0;
+
+	do {
+		new_page = __get_free_pages(GFP_ATOMIC | __GFP_NOWARN, order);
+		if (!new_page)
+			return 0;
+		page = virt_to_page(new_page);
+		more = 0;
+		for (i = 0; i < (1UL << order); i++) {
+			if (PagePageset1(page + i)) {
+				more = 1;
+				break;
+			}
+		}
+		if (more) {
+			for (i = 0; i < (1UL << order); i++)
+				if (PagePageset1(page + i))
+					SetPageConflicting(page + i);
+				else {
+					set_page_count(page + i, 1);
+					__free_pages(page + i, 0);
+				}
+		}
+	}
+	while (more);
+
+	memset((void*)new_page, 0, PAGE_SIZE * (1<<order));
+	return new_page;
+}
+
+/* relocate_page_if_required
+ *
+ * Description: Given the address of a pointer to a page, we check if the page
+ * 		needs relocating and do so if needs be, adjusting the pointer
+ * 		too.
+ */
+
+void suspend2_relocate_if_required(unsigned long *current_value, unsigned int size)
+{
+	if (PagePageset1(virt_to_page(*current_value))) {
+		unsigned long new_page = suspend2_get_nonconflicting_pages(0);
+		memcpy((char *) new_page, (char *) *current_value, size);
+		if (PageSlab(virt_to_page(*current_value)))
+			kfree((void *) *current_value);
+		else
+			free_page((unsigned long) *current_value);
+		*current_value = new_page;
+	}
+}
+
+/* get_pageset1_load_addresses
+ * 
+ * Description: We check here that pagedir & pages it points to won't collide
+ * 		with pages where we're going to restore from the loaded pages
+ * 		later.
+ * Returns:	Zero on success, one if couldn't find enough pages (shouldn't
+ * 		happen).
+ */
+
+int suspend2_get_pageset1_load_addresses(void)
+{
+	int i, result = 0;
+	void *this;
+
+	/*
+	 * Because we're trying to make this work when we're saving as much
+	 * memory as possible we need to remember the pages we reject here
+	 * and then free them when we're done.
+	 */
+	
+	for(i=0; i < pagedir1.pageset_size; i++) {
+		this = (void *) suspend2_get_nonconflicting_pages(0);
+		if (!this) {
+			abort_suspend("Error: Ran out of memory seeking locations for reloading data.");
+			result = 1;
+			break;
+		}
+		SetPagePageset1Copy(virt_to_page(this));
+	}
+
+	return result;
+}
diff -urN oldtree/kernel/power/pagedir.h newtree/kernel/power/pagedir.h
--- oldtree/kernel/power/pagedir.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/pagedir.h	2006-01-28 17:08:36.233727280 +0000
@@ -0,0 +1,37 @@
+/*
+ * kernel/power/suspend2_core/pagedir.h
+ *
+ * Copyright (C) 2004-2005 Nigel Cunningham <nigel@suspend2.net>
+ *
+ * This file is released under the GPLv2.
+ *
+ * Declarations for routines for handling pagesets.
+ */
+
+/* Pagedir
+ *
+ * Contains the metadata for a set of pages saved in the image.
+ */
+
+struct pagedir {
+	int pageset_size;
+	int lastpageset_size;
+};
+
+extern struct pagedir pagedir1, pagedir2;
+
+extern void suspend2_copy_pageset1(void);
+
+extern void suspend2_free_extra_pagedir_memory(void);
+
+extern int suspend2_allocate_extra_pagedir_memory(struct pagedir *p, int pageset_size, int alloc_from);
+
+extern void suspend2_mark_task_as_pageset1 (struct task_struct *t);
+extern void suspend2_mark_pages_for_pageset2(void);
+
+extern void suspend2_relocate_if_required(unsigned long *current_value, unsigned int size);
+extern int suspend2_get_pageset1_load_addresses(void);
+
+extern int extra_pagedir_pages_allocated;
+
+extern unsigned long suspend2_get_nonconflicting_pages(int order);
diff -urN oldtree/kernel/power/pageflags.c newtree/kernel/power/pageflags.c
--- oldtree/kernel/power/pageflags.c	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/pageflags.c	2006-01-28 17:08:36.233727280 +0000
@@ -0,0 +1,139 @@
+/*
+ * kernel/power/suspend2_core/pageflags.c
+ *
+ * Copyright (C) 2004-2005 Nigel Cunningham <ncunningham@cyclades.com>
+ * 
+ * This file is released under the GPLv2.
+ *
+ * Routines for dynamically allocating and releasing bitmaps
+ * used as pseudo-pageflags.
+ *
+ * Arrays are not contiguous. The first sizeof(void *) bytes are
+ * the pointer to the next page in the bitmap. This allows us to
+ * 1) work under low memory conditions where order 0 might be all
+ *    that's available
+ * 2) save the pages at suspend time, reload and relocate them as
+ *    necessary at resume time without breaking anything (cf
+ *    extent pages).
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/bitops.h>
+#include <linux/list.h>
+#include <linux/suspend.h>
+#include "pageflags.h"
+#include "plugins.h"
+#include "pagedir.h"
+
+/* Maps used in copying the image back are in builtin.c */
+dyn_pageflags_t pageset1_map;
+dyn_pageflags_t pageset1_copy_map;
+dyn_pageflags_t pageset2_map;
+dyn_pageflags_t in_use_map;
+dyn_pageflags_t allocd_pages_map;
+#ifdef CONFIG_DEBUG_PAGEALLOC
+dyn_pageflags_t unmap_map;
+#endif
+dyn_pageflags_t checksum_map;
+
+static int pages_for_zone(struct zone *zone)
+{
+	return (zone->spanned_pages + (PAGE_SIZE << 3) - 1) /
+			(PAGE_SIZE << 3);
+}
+
+/* save_dyn_pageflags
+ *
+ * Description: Save a set of pageflags.
+ * Arguments:   dyn_pageflags_t *: Pointer to the bitmap being saved.
+ */
+
+void save_dyn_pageflags(dyn_pageflags_t pagemap)
+{
+	int i, zone_num = 0;
+	struct zone *zone;
+
+	if (!*pagemap)
+		return;
+
+	for_each_zone(zone) {
+		int size = pages_for_zone(zone);
+		active_writer->ops.writer.write_header_chunk((char *) &zone_num, sizeof(int));
+		active_writer->ops.writer.write_header_chunk((char *) &size, sizeof(int));
+
+		for (i = 0; i < size; i++)
+			active_writer->ops.writer.write_header_chunk((char *) pagemap[zone_num][i], PAGE_SIZE);
+		zone_num++;
+	}
+	zone_num = -1;
+	active_writer->ops.writer.write_header_chunk((char *) &zone_num, sizeof(int));
+}
+
+/* load_dyn_pageflags
+ *
+ * Description: Load a set of pageflags.
+ * Arguments:   dyn_pageflags_t *: Pointer to the bitmap being loaded.
+ *              (It must be allocated before calling this routine).
+ */
+
+void load_dyn_pageflags(dyn_pageflags_t pagemap)
+{
+	int i, zone_num = 0, zone_check = 0;
+	struct zone *zone;
+
+	if (!pagemap)
+		return;
+
+	for_each_zone(zone) {
+		int size = 0;
+		active_writer->ops.writer.read_header_chunk((char *) &zone_check, sizeof(int));
+		if (zone_check != zone_num) {
+			printk("Zone check (%d) != zone_num (%d).\n", zone_check, zone_num);
+			BUG();	       
+		}
+		active_writer->ops.writer.read_header_chunk((char *) &size, sizeof(int));
+
+		for (i = 0; i < size; i++)
+			active_writer->ops.writer.read_header_chunk((char *) pagemap[zone_num][i], PAGE_SIZE);
+		zone_num++;
+	}
+	active_writer->ops.writer.read_header_chunk((char *) &zone_check, sizeof(int));
+	if (zone_check != -1) {
+		printk("Didn't read end of dyn pageflag data marker.(%x)\n", zone_check);
+		BUG();
+	}
+}
+
+/* relocate_dyn_pageflags
+ *
+ * Description: Relocate a set of pageflags to ensure they don't collide with
+ *              pageset 1 data which will get overwritten on copyback.
+ * Arguments:   dyn_pageflags_t *: Pointer to the bitmap being relocated.
+ */
+
+extern int num_zones(void);
+
+void relocate_dyn_pageflags(dyn_pageflags_t *pagemap)
+{
+	int i, zone_num = 0;
+	struct zone *zone;
+
+	if (!*pagemap)
+		return;
+
+	suspend2_relocate_if_required((void *) pagemap, sizeof (void *) * num_zones());
+
+	for_each_zone(zone) {
+		int pages = (zone->spanned_pages + (PAGE_SIZE << 3) - 1) >>
+			(PAGE_SHIFT + 3);
+
+		suspend2_relocate_if_required((void *) &((*pagemap)[zone_num]), sizeof(void *) * pages);
+
+		for (i = 0; i < pages; i++)
+			suspend2_relocate_if_required((void *) &((*pagemap)[zone_num][i]),
+				PAGE_SIZE);
+		zone_num++;
+	}
+}
diff -urN oldtree/kernel/power/pageflags.h newtree/kernel/power/pageflags.h
--- oldtree/kernel/power/pageflags.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/pageflags.h	2006-01-28 17:08:36.233727280 +0000
@@ -0,0 +1,86 @@
+/*
+ * kernel/power/pageflags.h
+ *
+ * Copyright (C) 2004-2005 Nigel Cunningham <nigel@suspend2.net>
+ *
+ * This file is released under the GPLv2.
+ *
+ * Suspend2 needs a few pageflags while working that aren't otherwise
+ * used. To save the struct page pageflags, we dynamically allocate
+ * a bitmap and use that. These are the only non order-0 allocations
+ * we do.
+ *
+ * NOTE!!!
+ * We assume that PAGE_SIZE - sizeof(void *) is a multiple of
+ * sizeof(unsigned long). Is this ever false?
+ */
+
+#include <linux/dyn_pageflags.h>
+#include <linux/suspend.h>
+
+extern dyn_pageflags_t in_use_map;
+extern dyn_pageflags_t allocd_pages_map;
+#ifdef CONFIG_DEBUG_PAGEALLOC
+extern dyn_pageflags_t unmap_map;
+#endif
+extern dyn_pageflags_t pageset2_map;
+extern dyn_pageflags_t conflicting_pages_map;
+extern dyn_pageflags_t checksum_map;
+
+/* 
+ * inusemap is used in two ways: 
+ * - During suspend, to tag pages which are not used (to speed up 
+ *   count_data_pages);
+ * - During resume, to tag pages which are in pagedir1. This does not tag 
+ *   pagedir2 pages, so !== first use.
+ */
+
+#define PageInUse(page) (test_dynpageflag(&in_use_map, page))
+#define SetPageInUse(page) (set_dynpageflag(&in_use_map, page))
+#define ClearPageInUse(page) (clear_dynpageflag(&in_use_map, page))
+
+#define PagePageset1(page) (test_dynpageflag(&pageset1_map, page))
+#define SetPagePageset1(page) (set_dynpageflag(&pageset1_map, page))
+#define ClearPagePageset1(page) (clear_dynpageflag(&pageset1_map, page))
+
+#define PagePageset1Copy(page) (test_dynpageflag(&pageset1_copy_map, page))
+#define SetPagePageset1Copy(page) (set_dynpageflag(&pageset1_copy_map, page))
+#define ClearPagePageset1Copy(page) (clear_dynpageflag(&pageset1_copy_map, page))
+
+#define PagePageset2(page) (test_dynpageflag(&pageset2_map, page))
+#define SetPagePageset2(page) (set_dynpageflag(&pageset2_map, page))
+#define ClearPagePageset2(page) (clear_dynpageflag(&pageset2_map, page))
+
+#define PageAllocd(page) (test_dynpageflag(&allocd_pages_map, page))
+#define SetPageAllocd(page) (set_dynpageflag(&allocd_pages_map, page))
+#define ClearPageAllocd(page) (clear_dynpageflag(&allocd_pages_map, page))
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+#define PagePageUnmap(page) (test_dynpageflag(&unmap_map, page))
+#define SetPagePageUnmap(page) (set_dynpageflag(&unmap_map, page))
+#define ClearPagePageUnmap(page) (clear_dynpageflag(&unmap_map, page))
+#endif
+
+static inline int PageChecksumIgnore(struct page *page)
+{
+	return checksum_map ?
+		test_dynpageflag(&checksum_map, page) :
+		0;
+}
+
+static inline void SetPageChecksumIgnore(struct page *page)
+{
+	if (checksum_map)
+		set_dynpageflag(&checksum_map, page);
+};
+
+static inline void ClearPageChecksumIgnore(struct page *page)
+{
+	if (checksum_map)
+		clear_dynpageflag(&checksum_map, page);
+};
+
+extern void save_dyn_pageflags(dyn_pageflags_t pagemap);
+extern void load_dyn_pageflags(dyn_pageflags_t pagemap);
+void relocate_dyn_pageflags(dyn_pageflags_t *pagemap);
+
diff -urN oldtree/kernel/power/plugins.c newtree/kernel/power/plugins.c
--- oldtree/kernel/power/plugins.c	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/plugins.c	2006-01-28 17:08:36.234727128 +0000
@@ -0,0 +1,312 @@
+/*
+ * kernel/power/plugins.c
+ *
+ * Copyright (C) 2004-2005 Nigel Cunningham <nigel@suspend2.net>
+ *
+ */
+
+#include <linux/suspend.h>
+#include <linux/module.h>
+#include "suspend2.h"
+#include "plugins.h"
+
+struct list_head suspend_filters, suspend_writers, suspend_plugins;
+struct suspend_plugin_ops *active_writer = NULL;
+static int num_filters = 0, num_ui = 0;
+int num_writers = 0, num_plugins = 0;
+
+/*
+ * header_storage_for_plugins
+ *
+ * Returns the amount of space needed to store configuration
+ * data needed by the plugins prior to copying back the original
+ * kernel. We can exclude data for pageset2 because it will be
+ * available anyway once the kernel is copied back.
+ */
+unsigned long header_storage_for_plugins(void)
+{
+	struct suspend_plugin_ops *this_plugin;
+	unsigned long bytes = 0;
+	
+	list_for_each_entry(this_plugin, &suspend_plugins, plugin_list) {
+		if (this_plugin->disabled)
+			continue;
+		if (this_plugin->storage_needed)
+			bytes += this_plugin->storage_needed();
+	}
+
+	return bytes;
+}
+
+/*
+ * memory_for_plugins
+ *
+ * Returns the amount of memory requested by plugins for
+ * doing their work during the cycle.
+ */
+
+unsigned long memory_for_plugins(void)
+{
+	unsigned long bytes = 0;
+	struct suspend_plugin_ops *this_plugin;
+
+	list_for_each_entry(this_plugin, &suspend_plugins, plugin_list) {
+		if (this_plugin->disabled)
+			continue;
+		if (this_plugin->memory_needed)
+			bytes += this_plugin->memory_needed();
+	}
+
+	return ((bytes + PAGE_SIZE - 1) >> PAGE_SHIFT);
+}
+
+/* find_plugin_given_name
+ * Functionality :	Return a plugin (if found), given a pointer
+ * 			to its name
+ */
+
+struct suspend_plugin_ops *find_plugin_given_name(char *name)
+{
+	struct suspend_plugin_ops *this_plugin, *found_plugin = NULL;
+	
+	list_for_each_entry(this_plugin, &suspend_plugins, plugin_list) {
+		if (!strcmp(name, this_plugin->name)) {
+			found_plugin = this_plugin;
+			break;
+		}			
+	}
+
+	return found_plugin;
+}
+
+/*
+ * print_plugin_debug_info
+ * Functionality   : Get debugging info from plugins into a buffer.
+ */
+int print_plugin_debug_info(char *buffer, int buffer_size)
+{
+	struct suspend_plugin_ops *this_plugin;
+	int len = 0;
+
+	list_for_each_entry(this_plugin, &suspend_plugins, plugin_list) {
+		if (this_plugin->disabled)
+			continue;
+		if (this_plugin->print_debug_info) {
+			int result;
+			result = this_plugin->print_debug_info(buffer + len, 
+					buffer_size - len);
+			len += result;
+		}
+	}
+
+	return len;
+}
+
+/*
+ * suspend_register_plugin
+ *
+ * Register a plugin.
+ */
+int suspend_register_plugin(struct suspend_plugin_ops *plugin)
+{
+	if (find_plugin_given_name(plugin->name))
+		return -EBUSY;
+
+	switch (plugin->type) {
+		case FILTER_PLUGIN:
+			list_add_tail(&plugin->ops.filter.filter_list,
+					&suspend_filters);
+			num_filters++;
+			break;
+
+		case WRITER_PLUGIN:
+			list_add_tail(&plugin->ops.writer.writer_list,
+					&suspend_writers);
+			num_writers++;
+			break;
+
+		case MISC_PLUGIN:
+			break;
+
+		default:
+			printk("Hmmm. Plugin '%s' has an invalid type."
+				" It has been ignored.\n", plugin->name);
+			return -EINVAL;
+	}
+	list_add_tail(&plugin->plugin_list, &suspend_plugins);
+	num_plugins++;
+
+	return 0;	
+}
+
+/*
+ * suspend_unregister_plugin
+ *
+ * Remove a plugin.
+ */
+void suspend_unregister_plugin(struct suspend_plugin_ops *plugin)
+{
+	switch (plugin->type) {
+		case FILTER_PLUGIN:
+			list_del(&plugin->ops.filter.filter_list);
+			num_filters--;
+			break;
+
+		case WRITER_PLUGIN:
+			list_del(&plugin->ops.writer.writer_list);
+			num_writers--;
+			if (active_writer == plugin) {
+				active_writer = NULL;
+				set_suspend_state(SUSPEND_DISABLED);
+			}
+			break;
+		
+		case MISC_PLUGIN:
+			break;
+
+		default:
+			printk("Hmmm. Plugin '%s' has an invalid type."
+				" It has been ignored.\n", plugin->name);
+			return;
+	}
+	list_del(&plugin->plugin_list);
+	num_plugins--;
+}
+
+/*
+ * suspend_move_plugin_tail
+ *
+ * Rearrange plugins when reloading the config.
+ */
+void suspend_move_plugin_tail(struct suspend_plugin_ops *plugin)
+{
+	switch (plugin->type) {
+		case FILTER_PLUGIN:
+			if (num_filters > 1)
+				list_move_tail(&plugin->ops.filter.filter_list,
+						&suspend_filters);
+			break;
+
+		case WRITER_PLUGIN:
+			if (num_writers > 1)
+				list_move_tail(&plugin->ops.writer.writer_list,
+						&suspend_writers);
+			break;
+		
+		case MISC_PLUGIN:
+			break;
+		default:
+			printk("Hmmm. Plugin '%s' has an invalid type."
+				" It has been ignored.\n", plugin->name);
+			return;
+	}
+	if ((num_filters + num_writers + num_ui) > 1)
+		list_move_tail(&plugin->plugin_list, &suspend_plugins);
+}
+
+/*
+ * suspend2_initialise_plugins
+ *
+ * Get ready to do some work!
+ */
+int suspend2_initialise_plugins(int starting_cycle)
+{
+	struct suspend_plugin_ops *this_plugin;
+	int result;
+	
+	list_for_each_entry(this_plugin, &suspend_plugins, plugin_list) {
+		if (this_plugin->disabled)
+			continue;
+		if (this_plugin->initialise) {
+			suspend_message(SUSPEND_MEMORY, SUSPEND_MEDIUM, 1,
+				"Initialising plugin %s.\n",
+				this_plugin->name);
+			if ((result = this_plugin->initialise(starting_cycle))) {
+				printk("%s didn't initialise okay.\n",
+						this_plugin->name);
+				return result;
+			}
+		}
+	}
+
+	return 0;
+}
+
+/* 
+ * suspend2_cleanup_plugins
+ *
+ * Tell plugins the work is done.
+ */
+void suspend2_cleanup_plugins(int finishing_cycle)
+{
+	struct suspend_plugin_ops *this_plugin;
+	
+	list_for_each_entry(this_plugin, &suspend_plugins, plugin_list) {
+		if (this_plugin->disabled)
+			continue;
+		if (this_plugin->cleanup) {
+			suspend_message(SUSPEND_MEMORY, SUSPEND_MEDIUM, 1,
+				"Cleaning up plugin %s.\n",
+				this_plugin->name);
+			this_plugin->cleanup(finishing_cycle);
+		}
+	}
+}
+
+/*
+ * get_next_filter
+ *
+ * Get the next filter in the pipeline.
+ */
+struct suspend_plugin_ops *get_next_filter(struct suspend_plugin_ops *filter_sought)
+{
+	struct suspend_plugin_ops *last_filter = NULL, *this_filter = NULL;
+
+	list_for_each_entry(this_filter, &suspend_filters, ops.filter.filter_list) {
+		if (this_filter->disabled)
+			continue;
+		if ((last_filter == filter_sought) || (!filter_sought))
+			return this_filter;
+		last_filter = this_filter;
+	}
+
+	return active_writer;
+}
+
+/* suspend2_get_modules
+ * 
+ * Take a reference to modules so they can't go away under us.
+ */
+
+int suspend2_get_modules(void)
+{
+	struct suspend_plugin_ops *this_plugin;
+	
+	list_for_each_entry(this_plugin, &suspend_plugins, plugin_list) {
+		if (!try_module_get(this_plugin->module)) {
+			/* Failed! Reverse gets and return error */
+			struct suspend_plugin_ops *this_plugin2;
+			list_for_each_entry(this_plugin2, &suspend_plugins, plugin_list) {
+				if (this_plugin == this_plugin2)
+					return -EINVAL;
+				module_put(this_plugin2->module);
+			}
+		}
+	}
+
+	return 0;
+}
+
+/* suspend2_put_modules
+ *
+ * Release our references to modules we used.
+ */
+
+void suspend2_put_modules(void)
+{
+	struct suspend_plugin_ops *this_plugin;
+	
+	list_for_each_entry(this_plugin, &suspend_plugins, plugin_list) {
+		module_put(this_plugin->module);
+	}
+}
diff -urN oldtree/kernel/power/plugins.h newtree/kernel/power/plugins.h
--- oldtree/kernel/power/plugins.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/plugins.h	2006-01-28 17:08:36.235726976 +0000
@@ -0,0 +1,179 @@
+/*
+ * kernel/power/plugin.h
+ *
+ * Copyright (C) 2004-2005 Nigel Cunningham <nigel@suspend2.net>
+ *
+ * This file is released under the GPLv2.
+ *
+ * It contains declarations for plugins. Plugins are additions to
+ * suspend2 that provide facilities such as image compression or
+ * encryption, backends for storage of the image and user interfaces.
+ *
+ */
+
+/* This is the maximum size we store in the image header for a plugin name */
+#define SUSPEND_MAX_PLUGIN_NAME_LENGTH 30
+
+/* Per-plugin metadata */
+struct plugin_header {
+	char name[SUSPEND_MAX_PLUGIN_NAME_LENGTH];
+	int disabled;
+	int type;
+	int index;
+	int data_length;
+	unsigned long signature;
+};
+
+extern int num_plugins, num_writers;
+
+enum {
+	FILTER_PLUGIN,
+	WRITER_PLUGIN,
+	MISC_PLUGIN, // Block writer, eg.
+	CHECKSUM_PLUGIN
+};
+
+enum {
+	SUSPEND_ASYNC,
+	SUSPEND_SYNC
+};
+
+struct suspend_filter_ops {
+	/* Writing the image proper */
+	int (*write_chunk) (struct page *buffer_page);
+
+	/* Reading the image proper */
+	int (*read_chunk) (struct page *buffer_page, int sync);
+
+	/* Reset plugin if image exists but reading aborted */
+	void (*noresume_reset) (void);
+	struct list_head filter_list;
+};
+
+struct suspend_writer_ops {
+	
+	/* Writing the image proper */
+	int (*write_chunk) (struct page *buffer_page);
+
+	/* Reading the image proper */
+	int (*read_chunk) (struct page *buffer_page, int sync);
+
+	/* Reset plugin if image exists but reading aborted */
+	void (*noresume_reset) (void);
+
+	/* Calls for allocating storage */
+
+	int (*storage_available) (void); // Maximum size of image we can save
+					  // (incl. space already allocated).
+	
+	int (*storage_allocated) (void);
+					// Amount of storage already allocated
+	int (*release_storage) (void);
+	
+	/* 
+	 * Header space is allocated separately. Note that allocation
+	 * of space for the header might result in allocated space 
+	 * being stolen from the main pool if there is no unallocated
+	 * space. We have to be able to allocate enough space for
+	 * the header. We can eat memory to ensure there is enough
+	 * for the main pool.
+	 */
+	int (*allocate_header_space) (int space_requested);
+	int (*allocate_storage) (int space_requested);
+	
+	/* Read and write the metadata */	
+	int (*write_header_init) (void);
+	int (*write_header_chunk) (char *buffer_start, int buffer_size);
+	int (*write_header_cleanup) (void);
+
+	int (*read_header_init) (void);
+	int (*read_header_chunk) (char *buffer_start, int buffer_size);
+	int (*read_header_cleanup) (void);
+
+	/* Prepare metadata to be saved (relativise/absolutise extents) */
+	int (*serialise_extents) (void);
+	int (*load_extents) (void);
+	
+	/* Attempt to parse an image location */
+	int (*parse_sig_location) (char *buffer, int only_writer);
+
+	/* Determine whether image exists that we can restore */
+	int (*image_exists) (void);
+	
+	/* Mark the image as having tried to resume */
+	void (*mark_resume_attempted) (void);
+
+	/* Destroy image if one exists */
+	int (*invalidate_image) (void);
+	
+	/* Wait on I/O */
+	int (*wait_on_io) (int flush_all);
+
+	struct list_head writer_list;
+};
+
+struct suspend_plugin_ops {
+	/* Functions common to all plugins */
+	int type;
+	char *name;
+	struct module *module;
+	int disabled;
+	struct list_head plugin_list;
+
+	/* Bytes! */
+	unsigned long (*memory_needed) (void);
+	unsigned long (*storage_needed) (void);
+
+	int (*print_debug_info) (char *buffer, int size);
+	int (*save_config_info) (char *buffer);
+	void (*load_config_info) (char *buffer, int len);
+	
+	/* Initialise & cleanup - general routines called
+	 * at the start and end of a cycle. */
+	int (*initialise) (int starting_cycle);
+	void (*cleanup) (int finishing_cycle);
+
+	int (*write_init) (int stream_number);
+	int (*write_cleanup) (void);
+
+	int (*read_init) (int stream_number);
+	int (*read_cleanup) (void);
+
+	union {
+		struct suspend_filter_ops filter;
+		struct suspend_writer_ops writer;
+	} ops;
+};
+
+extern struct suspend_plugin_ops *active_writer;
+extern struct list_head suspend_filters, suspend_writers, suspend_plugins;
+
+extern void prepare_console_plugins(void);
+extern void cleanup_console_plugins(void);
+
+extern struct suspend_plugin_ops *find_plugin_given_name(char *name);
+extern struct suspend_plugin_ops *get_next_filter(struct suspend_plugin_ops *);
+
+extern int suspend_register_plugin(struct suspend_plugin_ops *plugin);
+extern void suspend_move_plugin_tail(struct suspend_plugin_ops *plugin);
+
+extern unsigned long header_storage_for_plugins(void);
+extern unsigned long memory_for_plugins(void);
+
+extern int print_plugin_debug_info(char *buffer, int buffer_size);
+extern int suspend_register_plugin(struct suspend_plugin_ops *plugin);
+extern void suspend_unregister_plugin(struct suspend_plugin_ops *plugin);
+
+extern int suspend2_initialise_plugins(int starting_cycle);
+extern void suspend2_cleanup_plugins(int finishing_cycle);
+
+int suspend2_get_modules(void);
+void suspend2_put_modules(void);
+
+static inline void suspend_initialise_plugin_lists(void) {
+	INIT_LIST_HEAD(&suspend_filters);
+	INIT_LIST_HEAD(&suspend_writers);
+	INIT_LIST_HEAD(&suspend_plugins);
+}
+
+extern int expected_compression_ratio(void);
diff -urN oldtree/kernel/power/power.h newtree/kernel/power/power.h
--- oldtree/kernel/power/power.h	2006-01-28 16:36:00.000000000 +0000
+++ newtree/kernel/power/power.h	2006-01-28 17:08:36.235726976 +0000
@@ -1,6 +1,8 @@
 #include <linux/suspend.h>
 #include <linux/utsname.h>
 
+#include "suspend.h"
+
 /* With SUSPEND_CONSOLE defined suspend looks *really* cool, but
    we probably do not take enough locks for switching consoles, etc,
    so bad things might happen.
@@ -48,15 +50,12 @@
 
 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 const void __nosave_begin, __nosave_end;
 
 extern unsigned int nr_copy_pages;
 extern suspend_pagedir_t *pagedir_nosave;
diff -urN oldtree/kernel/power/power_off.c newtree/kernel/power/power_off.c
--- oldtree/kernel/power/power_off.c	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/power_off.c	2006-01-28 17:08:36.235726976 +0000
@@ -0,0 +1,79 @@
+/*
+ * kernel/power/suspend2_core/power_off.c
+ *
+ * Copyright (C) 2005 Nigel Cunningham <nigel@suspend2.net>
+ *
+ * This file is released under the GPLv2.
+ *
+ * Support for powering down.
+ */
+
+#include <linux/device.h>
+#include <linux/suspend.h>
+#include <linux/mm.h>
+#include <linux/pm.h>
+#include <linux/reboot.h>
+#include "suspend2_common.h"
+#include "suspend2.h"
+#include "ui.h"
+
+unsigned long suspend2_powerdown_method = 0; /* 0 - Kernel power off */
+
+extern struct pm_ops *pm_ops;
+
+/* Use suspend_enter from main.c */
+extern int suspend_enter(suspend_state_t state);
+
+int try_pm_state_powerdown(void)
+{
+	if (pm_ops && pm_ops->prepare && suspend2_powerdown_method &&
+	    pm_ops->prepare(suspend2_powerdown_method))
+			return 0;
+
+	if (suspend2_powerdown_method > 3)
+		kernel_power_off_prepare();
+	else {
+		if (device_suspend(PMSG_SUSPEND)) {
+			printk(KERN_ERR "Some devices failed to suspend\n");
+			return 0;
+		}
+	}
+
+	if (suspend_enter(suspend2_powerdown_method))
+		return 0;
+
+	device_resume();
+
+	if (pm_ops && pm_ops->finish && suspend2_powerdown_method)
+		pm_ops->finish(suspend2_powerdown_method);
+
+	return 1;
+}
+
+/*
+ * suspend_power_down
+ * Functionality   : Powers down or reboots the computer once the image
+ *                   has been written to disk.
+ * Key Assumptions : Able to reboot/power down via code called or that
+ *                   the warning emitted if the calls fail will be visible
+ *                   to the user (ie printk resumes devices).
+ * Called From     : do_suspend2_suspend_2
+ */
+
+void suspend_power_down(void)
+{
+	if (test_action_state(SUSPEND_REBOOT)) {
+		suspend2_prepare_status(DONT_CLEAR_BAR, "Ready to reboot.");
+		kernel_restart(NULL);
+	}
+
+	if (pm_ops && pm_ops->enter && suspend2_powerdown_method && try_pm_state_powerdown())
+		return;
+
+	lock_kernel();
+	kernel_power_off();
+	suspend2_prepare_status(DONT_CLEAR_BAR, "Powerdown failed");
+	while (1)
+		cpu_relax();
+}
+
diff -urN oldtree/kernel/power/power_off.h newtree/kernel/power/power_off.h
--- oldtree/kernel/power/power_off.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/power_off.h	2006-01-28 17:08:36.236726824 +0000
@@ -0,0 +1,13 @@
+/*
+ * kernel/power/suspend2_core/power_off.h
+ *
+ * Copyright (C) 2005 Nigel Cunningham <nigel@suspend2.net>
+ *
+ * This file is released under the GPLv2.
+ *
+ * Support for the powering down.
+ */
+
+int suspend_pm_state_finish(void);
+void suspend_power_down(void);
+extern unsigned long suspend2_powerdown_method;
diff -urN oldtree/kernel/power/prepare_image.c newtree/kernel/power/prepare_image.c
--- oldtree/kernel/power/prepare_image.c	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/prepare_image.c	2006-01-28 17:08:36.237726672 +0000
@@ -0,0 +1,784 @@
+/*
+ * kernel/power/prepare_image.c
+ *
+ * Copyright (C) 2003-2005 Nigel Cunningham <nigel@suspend.net>
+ *
+ * This file is released under the GPLv2.
+ *
+ * We need to eat memory until we can:
+ * 1. Perform the save without changing anything (RAM_NEEDED < max_pfn)
+ * 2. Fit it all in available space (active_writer->available_space() >=
+ *    storage_needed())
+ * 3. Reload the pagedir and pageset1 to places that don't collide with their
+ *    final destinations, not knowing to what extent the resumed kernel will
+ *    overlap with the one loaded at boot time. I think the resumed kernel
+ *    should overlap completely, but I don't want to rely on this as it is 
+ *    an unproven assumption. We therefore assume there will be no overlap at
+ *    all (worse case).
+ * 4. Meet the user's requested limit (if any) on the size of the image.
+ *    The limit is in MB, so pages/256 (assuming 4K pages).
+ *
+ */
+
+#include <linux/highmem.h>
+#include <linux/freezer.h>
+
+#include "suspend2.h"
+#include "pageflags.h"
+#include "plugins.h"
+#include "suspend2_common.h"
+#include "io.h"
+#include "ui.h"
+#include "extent.h"
+#include "prepare_image.h"
+#include "checksum.h"
+
+static int are_frozen = 0, num_nosave = 0;
+static int header_space_allocated = 0;
+static int storage_allocated = 0;
+static int storage_available = 0;
+int extra_pd1_pages_allowance = 100;
+
+static int num_pcp_pages(void)
+{
+	struct zone *zone;
+	int result = 0, i = 0;
+
+	/* PCP lists */
+	for_each_zone(zone) {
+		struct per_cpu_pageset *pset;
+		int cpu;
+		
+		if (!zone->present_pages)
+			continue;
+		
+		for (cpu = 0; cpu < NR_CPUS; cpu++) {
+			if (!cpu_possible(cpu))
+				continue;
+
+			pset = zone_pcp(zone, cpu);
+
+			for (i = 0; i < ARRAY_SIZE(pset->pcp); i++) {
+				struct per_cpu_pages *pcp;
+
+				pcp = &(pset->pcp[i]);
+				result += pcp->count;
+			}
+		}
+	}
+	return result;
+}
+
+int real_nr_free_pages(void)
+{
+	return nr_free_pages() + num_pcp_pages();
+}
+
+static void get_extra_pd1_allowance(void)
+{
+	int orig_num_free = real_nr_free_pages(), final;
+	
+	suspend2_prepare_status(CLEAR_BAR, "Finding allowance for drivers.");
+	device_suspend(PMSG_FREEZE);
+	local_irq_disable(); /* irqs might have been re-enabled on us */
+	device_power_down(PMSG_FREEZE);
+	
+	final = real_nr_free_pages();
+
+	device_power_up();
+	local_irq_enable();
+
+	device_resume();
+
+	extra_pd1_pages_allowance = orig_num_free - final + 100;
+}
+
+static int main_storage_needed(int use_ecr,
+		int ignore_extra_pd1_allow)
+{
+	return ((pagedir1.pageset_size + pagedir2.pageset_size +
+	  (ignore_extra_pd1_allow ? 0 : extra_pd1_pages_allowance)) *
+	 (use_ecr ? suspend2_expected_compression_ratio() : 100) / 100);
+}
+
+static int header_storage_needed(void)
+{
+	unsigned long bytes = ((extents_allocated * 2 * sizeof(unsigned long)) +
+	 sizeof(struct suspend_header) +
+	 sizeof(struct plugin_header) +
+	 (int) header_storage_for_plugins() +
+	 (dyn_pageflags_pages_per_bitmap() << PAGE_SHIFT) +
+	 num_plugins *
+	 	(sizeof(struct plugin_header) + sizeof(int)));
+
+	return ((int) ((bytes + (int) PAGE_SIZE - 1) >> PAGE_SHIFT));
+}
+	
+static void display_stats(int always, int sub_extra_pd1_allow)
+{ 
+	unsigned long storage_allocated = active_writer->ops.writer.storage_allocated();
+	char buffer[255];
+	snprintf(buffer, 254, 
+		"Free:%d(%d). Sets:%d(%d),%d(%d). Header:%d. Nosave:%d-%d=%d. Storage:%lu/%u(%u). Needed:%d|%d|%d.\n", 
+		
+		/* Free */
+		nr_free_pages(),
+		nr_free_pages() - nr_free_highpages(),
+		
+		/* Sets */
+		pagedir1.pageset_size, pageset1_sizelow,
+		pagedir2.pageset_size, pageset2_sizelow,
+
+		/* Header */
+		header_storage_needed(),
+
+		/* Nosave */
+		num_nosave, extra_pagedir_pages_allocated,
+		num_nosave - extra_pagedir_pages_allocated,
+
+		/* Storage - converted to pages for comparison */
+		storage_allocated,
+		storage_needed(1, sub_extra_pd1_allow),
+		storage_available,
+
+		/* Needed */
+		ram_to_suspend() - nr_free_pages() - nr_free_highpages(),
+		storage_needed(1, sub_extra_pd1_allow) - storage_available, 
+		(image_size_limit > 0) ? (storage_needed(1, sub_extra_pd1_allow) - (image_size_limit << 8)) : 0);
+	if (always)
+		printk(buffer);
+	else
+		suspend_message(SUSPEND_EAT_MEMORY, SUSPEND_MEDIUM, 1, buffer);
+}
+
+/* generate_free_page_map
+ *
+ * Description:	This routine generates a bitmap of free pages from the
+ * 		lists used by the memory manager. We then use the bitmap
+ * 		to quickly calculate which pages to save and in which
+ * 		pagesets.
+ */
+static void generate_free_page_map(void) 
+{
+	int i, order, loop, cpu;
+	struct page *page;
+	unsigned long flags;
+	struct zone *zone;
+	struct per_cpu_pageset *pset;
+
+	for_each_zone(zone) {
+		if (!zone->present_pages)
+			continue;
+		for(i=0; i < zone->spanned_pages; i++)
+			SetPageInUse(pfn_to_page(zone->zone_start_pfn + i));
+	}
+	
+	for_each_zone(zone) {
+		if (!zone->present_pages)
+			continue;
+		spin_lock_irqsave(&zone->lock, flags);
+		for (order = MAX_ORDER - 1; order >= 0; --order) {
+			list_for_each_entry(page, &zone->free_area[order].free_list, lru)
+				for(loop=0; loop < (1 << order); loop++) {
+					ClearPageInUse(page+loop);
+					ClearPagePageset2(page+loop);
+				}
+		}
+
+		
+		for (cpu = 0; cpu < NR_CPUS; cpu++) {
+			if (!cpu_possible(cpu))
+				continue;
+
+			pset = zone_pcp(zone, cpu);
+
+			for (i = 0; i < ARRAY_SIZE(pset->pcp); i++) {
+				struct per_cpu_pages *pcp;
+				struct page *page;
+
+				pcp = &pset->pcp[i];
+				list_for_each_entry(page, &pcp->list, lru) {
+					ClearPageInUse(page);
+					ClearPagePageset2(page);
+				}
+			}
+		}
+		
+		spin_unlock_irqrestore(&zone->lock, flags);
+	}
+}
+
+/* size_of_free_region
+ * 
+ * Description:	Return the number of pages that are free, beginning with and 
+ * 		including this one.
+ */
+static int size_of_free_region(struct page *page)
+{
+	struct zone *zone = page_zone(page);
+	struct page *posn = page, *last_in_zone =
+		zone->zone_mem_map + zone->spanned_pages - 1;
+
+	while (posn < last_in_zone && !PageInUse(posn)) 
+		posn++;
+	return (posn - page);
+}
+
+static struct page *rodata_start, *rodata_end;
+static struct page *rotext_start, *rotext_end;
+static struct page *nosave_start, *nosave_end;
+static struct page *rtas_start, *rtas_end;
+#ifdef CONFIG_PPC_RTAS
+extern char __start_rodata, __end_rodata;
+extern unsigned int rtas_data, rtas_size;
+#endif
+#ifdef CONFIG_PPC
+extern char _etext[];
+#else
+extern char _text[], _etext[];
+#endif
+
+#ifdef CONFIG_X86_32	/* 2.6.15 and later */
+extern int bad_ppro;
+
+/* 
+ * Copied from arch/i386/mm/init.c. It should be moved to
+ * an include file after testing.
+ */
+static inline int page_kills_ppro(unsigned long pagenr)
+{
+	if (pagenr >= 0x70000 && pagenr <= 0x7003F)
+		return 1;
+	return 0;
+}
+
+#else
+#define bad_ppro (0)
+#define page_kills_ppro(pfn) (0)
+#endif
+
+static __init int page_nosave_init(void)
+{
+#ifdef CONFIG_DEBUG_RODATA
+	rodata_start = virt_to_page(&__start_rodata);
+	rodata_end = virt_to_page(&__end_rodata);
+#endif
+#ifdef CONFIG_PPC
+	rotext_start = virt_to_page(PAGE_OFFSET);
+#else
+	rotext_start = virt_to_page(&_text);
+#endif
+	rotext_end = virt_to_page(&_etext);
+
+	nosave_start = virt_to_page(&__nosave_begin);
+	nosave_end = virt_to_page(((char *) &__nosave_end) - 1);
+
+#ifdef CONFIG_PPC_RTAS
+	rtas_start = virt_to_page(__va(rtas_data)); 
+	rtas_end = virt_to_page(__va(rtas_data) + rtas_size);
+#endif
+	return 0;
+}
+
+subsys_initcall(page_nosave_init);
+
+static int Suspend2PageNosave(int pfn)
+{
+	struct page *page = pfn_to_page(pfn);
+
+	return (
+#ifdef CONFIG_DEBUG_RODATA
+		(page >= rodata_start && page <= rodata_end) ||
+#endif
+#ifdef CONFIG_DEBUG_ROTEXT
+		(page >= rotext_start && page <= rotext_end) ||
+#endif
+		(page >= nosave_start && page <= nosave_end) ||
+#ifdef CONFIG_PPC_RTAS
+		(page >= rtas_start && page <= rtas_end) ||
+#endif
+		PageAllocd(page) ||
+#ifdef PPC_PMAC
+		(agp_special_page && page = virt_to_page(agp_special_page)) ||
+#endif
+		!pfn_valid(pfn) || 
+		(bad_ppro && page_kills_ppro(pfn)) ||
+		(PageReserved(page) && PageHighMem(page)) ||
+		(checksum_map && PageChecksumIgnore(page)) ||
+		!page_is_ram(pfn));
+}
+
+/* count_data_pages
+ *
+ * This routine generates our lists of pages to be stored in each
+ * pageset. Since we store the data using extents, and adding new
+ * extents might allocate a new extent page, this routine may well
+ * be called more than once.
+ */
+static struct pageset_sizes_result count_data_pages(void)
+{
+	int chunk_size, loop, num_free = 0;
+	int use_pagedir2;
+	struct pageset_sizes_result result;
+	struct zone *zone;
+
+	result.size1 = 0;
+	result.size1low = 0;
+	result.size2 = 0;
+	result.size2low = 0;
+
+	num_nosave = 0;
+
+	clear_dyn_pageflags(pageset1_map);
+	clear_dyn_pageflags(pageset1_copy_map);
+
+	generate_free_page_map();
+
+	if (test_result_state(SUSPEND_ABORTED))
+		return result;
+
+	/*
+	 * Pages not to be saved are marked Nosave irrespective of being reserved
+	 */
+	for_each_zone(zone) {
+		for (loop = 0; loop < zone->spanned_pages; loop++) {
+			int pfn = zone->zone_start_pfn + loop;
+			struct page *page = pfn_to_page(pfn);
+			
+			int new_nosave =
+			    Suspend2PageNosave(pfn);
+ 
+#if 0
+			int old_nosave = (PageNosave(page) ||
+					  !pfn_valid(pfn) ||
+					  !page_is_ram(pfn) ||
+					  (page >= nosave_start && page <= nosave_end) ||
+					  (PageReserved(page) && PageHighMem(page)));
+			/* Complain loudly so that Nigel hears about it. */
+			if (old_nosave != new_nosave) {
+				suspend2_prepare_status(0,
+					"Page %d oldnosave(%d) [%d|%d|%d|%d] != newnosave(%d) "
+					"[%d|%d|%d|%d|%d|%d|%d|%d|%d]. Page is ram=%d.\n", 
+					pfn,
+					old_nosave,
+					PageNosave(page),
+					!pfn_valid(pfn),
+					(page >= nosave_start && page <= nosave_end),
+					(PageReserved(page) && PageHighMem(page)),
+					new_nosave,
+					!pfn_valid(pfn), 
+					(bad_ppro && page_kills_ppro(pfn)),
+					(page >= rodata_start && page <= rodata_end),
+					(page >= rotext_start && page <= rotext_end),
+					(page >= nosave_start && page <= nosave_end),
+					(page >= rtas_start && page <= rtas_end),
+					PageAllocd(page),
+					(PageReserved(page) && PageHighMem(page)),
+					(checksum_map && PageChecksumIgnore(page)),
+					page_is_ram(pfn));
+			}
+#endif
+
+			if (Suspend2PageNosave(pfn)) {
+				num_nosave++;
+				continue;
+			}
+
+
+			if ((chunk_size=size_of_free_region(page))!=0) {
+				num_free += chunk_size;
+				loop += chunk_size - 1;
+				continue;
+			}
+
+			use_pagedir2 = PagePageset2(page);
+
+			if (use_pagedir2) {
+				result.size2++;
+				if (!PageHighMem(page))
+					result.size2low++;
+				SetPagePageset1Copy(page);
+			} else {
+				result.size1++;
+				SetPagePageset1(page);
+				if (!PageHighMem(page))
+					result.size1low++;
+				}
+		}
+	}
+	
+	suspend_message(SUSPEND_EAT_MEMORY, SUSPEND_MEDIUM, 0,
+		"Count data pages: Set1 (%d) + Set2 (%d) + Nosave (%d) + NumFree (%d) = %d.\n",
+		result.size1, result.size2, num_nosave, num_free,
+		result.size1 + result.size2 + num_nosave + num_free);
+	BITMAP_FOR_EACH_SET(allocd_pages_map, loop)
+		SetPagePageset1Copy(pfn_to_page(loop));
+	return result;
+}
+
+/* amount_needed
+ *
+ * Calculates the amount by which the image size needs to be reduced to meet
+ * our constraints.
+ */
+static int amount_needed(int use_image_size_limit)
+{
+
+	int max1 = max( (int) (ram_to_suspend() - real_nr_free_pages() - 
+			  nr_free_highpages()),
+			((int) (storage_needed(1, 0) -  
+			  storage_available)));
+	if (use_image_size_limit)
+		return max( max1,
+			    (image_size_limit > 0) ? 
+			    ((int) (storage_needed(1, 0) - (image_size_limit << 8))) : 0);
+	return max1;
+}
+
+/* suspend2_recalculate_stats
+ *
+ * Eaten is the number of pages which have been eaten.
+ * Pagedirincluded is the number of pages which have been allocated for the pagedir.
+ */
+struct pageset_sizes_result suspend2_recalculate_stats(int storage_unavailable) 
+{
+	struct pageset_sizes_result result;
+
+	suspend2_mark_pages_for_pageset2();  /* Need to call this before getting pageset1_size! */
+	BUG_ON(in_atomic() && !irqs_disabled());
+	result = count_data_pages();
+	pageset1_sizelow = result.size1low;
+	pageset2_sizelow = result.size2low;
+	pagedir1.lastpageset_size = pagedir1.pageset_size = result.size1;
+	pagedir2.lastpageset_size = pagedir2.pageset_size = result.size2;
+	if (!storage_unavailable) {
+		storage_available = active_writer->ops.writer.storage_available();
+		display_stats(0, 0);
+	}
+	BUG_ON(in_atomic() && !irqs_disabled());
+	return result;
+}
+
+/* update_image
+ *
+ * Allocate [more] memory and storage for the image.
+ */
+static int update_image(void) 
+{ 
+	struct pageset_sizes_result result;
+	int result2, param_used;
+
+	result = suspend2_recalculate_stats(0);
+
+	if (suspend2_allocate_checksum_pages()) {
+		suspend_message(SUSPEND_ANY_SECTION, SUSPEND_LOW, 1,
+			"Still need to get more pages for checksum pages.\n");
+		return 1;
+	}
+
+	/* Include allowance for growth in pagedir1 while writing pagedir 2 */
+	if (suspend2_allocate_extra_pagedir_memory(&pagedir1,
+				pagedir1.pageset_size + extra_pd1_pages_allowance,
+				pageset2_sizelow)) {
+		suspend_message(SUSPEND_EAT_MEMORY, SUSPEND_LOW, 1,
+			"Still need to get more pages for pagedir 1.\n");
+		return 1;
+	}
+
+	thaw_processes(FREEZER_KERNEL_THREADS);
+
+	param_used = main_storage_needed(1, 0);
+	if ((result2 = active_writer->ops.writer.allocate_storage(param_used))) {
+		suspend_message(SUSPEND_EAT_MEMORY, SUSPEND_LOW, 1,
+			"Allocate storage returned %d. Still need to get more storage space for the image proper.\n",
+			result2);
+		storage_allocated = active_writer->ops.writer.storage_allocated();
+		if (freeze_processes()) {
+			set_result_state(SUSPEND_FREEZING_FAILED);
+			set_result_state(SUSPEND_ABORTED);
+		}
+		return 1;
+	}
+
+	param_used = header_storage_needed();
+	if ((result2 = active_writer->ops.writer.allocate_header_space(param_used))) {
+		suspend_message(SUSPEND_EAT_MEMORY, SUSPEND_LOW, 1,
+			"Still need to get more storage space for header.\n");
+		if (freeze_processes()) {
+			set_result_state(SUSPEND_FREEZING_FAILED);
+			set_result_state(SUSPEND_ABORTED);
+		}
+		storage_allocated = active_writer->ops.writer.storage_allocated();
+		return 1;
+	}
+
+	header_space_allocated = param_used;
+
+	/* 
+	 * Allocate remaining storage space, if possible, up to the
+	 * maximum we know we'll need. It's okay to allocate the
+	 * maximum if the writer is the swapwriter, but
+	 * we don't want to grab all available space on an NFS share.
+	 * We therefore ignore the expected compression ratio here,
+	 * thereby trying to allocate the maximum image size we could
+	 * need (assuming compression doesn't expand the image), but
+	 * don't complain if we can't get the full amount we're after.
+	 */
+
+	active_writer->ops.writer.allocate_storage(
+		min(storage_available,
+		    main_storage_needed(0, 1)));
+
+	storage_allocated = active_writer->ops.writer.storage_allocated();
+
+	if (freeze_processes()) {
+		set_result_state(SUSPEND_FREEZING_FAILED);
+		set_result_state(SUSPEND_ABORTED);
+	}
+
+	suspend2_recalculate_stats(0);
+
+	suspend_message(SUSPEND_EAT_MEMORY, SUSPEND_LOW, 1,
+		"Amount still needed (%d) > 0:%d. Header: %d < %d: %d,"
+		" Storage allocd: %d < %d + %d: %d.\n",
+			amount_needed(0),
+			(amount_needed(0) > 0),
+			header_space_allocated, header_storage_needed(),
+			header_space_allocated < header_storage_needed(),
+		 	storage_allocated,
+			header_storage_needed(), main_storage_needed(1, 1),
+			storage_allocated <
+			(header_storage_needed() + main_storage_needed(1, 1)));
+
+	check_shift_keys(0, NULL);
+
+	return ((amount_needed(0) > 0) ||
+		header_space_allocated < header_storage_needed() ||
+		 storage_allocated < 
+		 (header_storage_needed() + main_storage_needed(1, 1)));
+}
+
+/* attempt_to_freeze
+ * 
+ * Try to freeze processes.
+ */
+
+static int attempt_to_freeze(void)
+{
+	int result;
+	
+	/* Stop processes before checking again */
+	thaw_processes(FREEZER_ALL_THREADS);
+	suspend2_prepare_status(CLEAR_BAR, "Freezing processes");
+	result = freeze_processes();
+
+	if (result) {
+		set_result_state(SUSPEND_ABORTED);
+		set_result_state(SUSPEND_FREEZING_FAILED);
+	} else
+		are_frozen = 1;
+
+	return result;
+}
+
+int storage_needed(int use_ecr, int ignore_extra_pd1_allow)
+{
+	return 	(main_storage_needed(use_ecr, ignore_extra_pd1_allow)
+		       + header_storage_needed());
+}
+
+int ram_to_suspend(void)
+{
+	return (1 + 
+		max((pagedir1.pageset_size + extra_pd1_pages_allowance - 
+				pageset2_sizelow), 0) +
+		MIN_FREE_RAM + memory_for_plugins());
+}
+
+
+/* eat_memory
+ *
+ * Try to free some memory, either to meet hard or soft constraints on the image
+ * characteristics.
+ * 
+ * Hard constraints:
+ * - Pageset1 must be < half of memory;
+ * - We must have enough memory free at resume time to have pageset1
+ *   be able to be loaded in pages that don't conflict with where it has to
+ *   be restored.
+ * Soft constraints
+ * - User specificied image size limit.
+ */
+static int eat_memory(void)
+{
+	int orig_memory_still_to_eat, last_amount_needed = 0, times_criteria_met = 0;
+	int free_flags = 0, did_eat_memory = 0;
+	
+	/*
+	 * Note that if we have enough storage space and enough free memory, we may
+	 * exit without eating anything. We give up when the last 10 iterations ate
+	 * no extra pages because we're not going to get much more anyway, but
+	 * the few pages we get will take a lot of time.
+	 *
+	 * We freeze processes before beginning, and then unfreeze them if we
+	 * need to eat memory until we think we have enough. If our attempts
+	 * to freeze fail, we give up and abort.
+	 */
+
+	/* -- Stage 1: Freeze Processes -- */
+
+	
+	suspend2_recalculate_stats(0);
+
+	orig_memory_still_to_eat = amount_needed(1);
+	last_amount_needed = orig_memory_still_to_eat;
+
+	switch (image_size_limit) {
+		case -1: /* Don't eat any memory */
+			if (orig_memory_still_to_eat) {
+				set_result_state(SUSPEND_ABORTED);
+				set_result_state(SUSPEND_WOULD_EAT_MEMORY);
+			}
+			break;
+		case -2:  /* Free caches only */
+			free_flags = GFP_NOIO | __GFP_HIGHMEM;
+			break;
+		default:
+			free_flags = GFP_ATOMIC | __GFP_HIGHMEM;
+	}
+		
+	thaw_processes(FREEZER_KERNEL_THREADS);
+
+	/* -- Stage 2: Eat memory -- */
+
+	while (((amount_needed(1) > 0) || (image_size_limit == -2)) && 
+		(!test_result_state(SUSPEND_ABORTED)) && 
+		(times_criteria_met < 10)) {
+		int amount_freed;
+		int amount_wanted = orig_memory_still_to_eat - amount_needed(1);
+
+		suspend2_prepare_status(CLEAR_BAR, "Seeking to free %dMB of memory.", MB(amount_needed(1)));
+
+		if (amount_wanted < 1)
+			amount_wanted = 1; /* image_size_limit == -2 */
+
+		if (orig_memory_still_to_eat)
+			suspend2_update_status(orig_memory_still_to_eat - amount_needed(1),
+				orig_memory_still_to_eat,
+				" Image size %d ",
+				MB(storage_needed(1, 0)));
+		else
+			suspend2_update_status(0, 1, "Image size %d ",
+					MB(storage_needed(1, 0)));
+		
+		if ((last_amount_needed - amount_needed(1)) < 10)
+			times_criteria_met++;
+		else
+			times_criteria_met = 0;
+		last_amount_needed = amount_needed(1);
+		amount_freed = shrink_all_memory(last_amount_needed);
+		suspend2_recalculate_stats(0);
+
+		did_eat_memory = 1;
+
+		check_shift_keys(0, NULL);
+	}
+
+	if (freeze_processes()) {
+		set_result_state(SUSPEND_FREEZING_FAILED);
+		set_result_state(SUSPEND_ABORTED);
+	}
+	
+	if (did_eat_memory) {
+		unsigned long orig_state = get_suspend_state();
+		/* Freeze_processes will call sys_sync too */
+		restore_suspend_state(orig_state);
+		suspend2_recalculate_stats(0);
+	}
+
+	/* Blank out image size display */
+	suspend2_update_status(100, 100, NULL);
+
+	if (!test_result_state(SUSPEND_ABORTED)) {
+		/* Include image size limit when checking what to report */
+		if (amount_needed(1) - extra_pd1_pages_allowance > 0) 
+			set_result_state(SUSPEND_UNABLE_TO_FREE_ENOUGH_MEMORY);
+
+		/* But don't include it when deciding whether to abort (soft limit) */
+		if ((amount_needed(0) - extra_pd1_pages_allowance > 0)) {
+			printk("Unable to free sufficient memory to suspend. Still need %d pages.\n",
+				amount_needed(1));
+			display_stats(1, 1);
+			set_result_state(SUSPEND_ABORTED);
+		}
+		
+		check_shift_keys(1, "Memory eating completed.");
+	}
+
+	return 0;
+}
+
+/* prepare_image
+ *
+ * Entry point to the whole image preparation section.
+ *
+ * We do four things:
+ * - Freeze processes;
+ * - Ensure image size constraints are met;
+ * - Complete all the preparation for saving the image,
+ *   including allocation of storage. The only memory
+ *   that should be needed when we're finished is that
+ *   for actually storing the image (and we know how
+ *   much is needed for that because the plugins tell
+ *   us).
+ * - Make sure that all dirty buffers are written out.
+ */
+
+#define MAX_TRIES 4
+int suspend2_prepare_image(void)
+{
+	int result = 1, tries = 0;
+
+	are_frozen = 0;
+
+	header_space_allocated = 0;
+
+	if (attempt_to_freeze())
+		return 0;
+
+	if (!extra_pd1_pages_allowance)
+		get_extra_pd1_allowance();
+
+	storage_available = active_writer->ops.writer.storage_available();
+
+	if (!storage_available) {
+		printk(KERN_ERR "You need some storage available to be able to suspend.\n");
+		set_result_state(SUSPEND_ABORTED);
+		set_result_state(SUSPEND_NOSTORAGE_AVAILABLE);
+		return 0;
+	}
+
+	do {
+		suspend2_prepare_status(CLEAR_BAR, "Preparing Image.");
+	
+		if (eat_memory() || test_result_state(SUSPEND_ABORTED))
+			break;
+
+		result = update_image();
+
+		check_shift_keys(0, NULL);
+		
+		tries++;
+
+	} while ((result) && (tries < MAX_TRIES) && (!test_result_state(SUSPEND_ABORTED)) &&
+		(!test_result_state(SUSPEND_UNABLE_TO_FREE_ENOUGH_MEMORY)));
+
+	if (tries == MAX_TRIES) {
+		abort_suspend("Unable to get sufficient storage for the image.\n");
+		display_stats(1, 0);
+	}
+
+	check_shift_keys(1, "Image preparation complete.");
+
+	return !result;
+}
diff -urN oldtree/kernel/power/prepare_image.h newtree/kernel/power/prepare_image.h
--- oldtree/kernel/power/prepare_image.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/prepare_image.h	2006-01-28 17:08:36.237726672 +0000
@@ -0,0 +1,31 @@
+/*
+ * kernel/power/prepare_image.h
+ */
+
+extern int suspend2_prepare_image(void);
+extern struct pageset_sizes_result suspend2_recalculate_stats(int storage_available);
+extern int real_nr_free_pages(void);
+extern int image_size_limit;
+extern int pageset1_sizelow, pageset2_sizelow;
+
+struct pageset_sizes_result {
+	int size1; /* Can't be unsigned - breaks MAX function */
+	int size1low;
+	int size2;
+	int size2low;
+};
+
+#ifdef CONFIG_CRYPTO
+extern int suspend2_expected_compression_ratio(void);
+#else
+static inline int suspend2_expected_compression_ratio(void)
+{
+	return 0;
+};
+#endif
+
+#define MIN_FREE_RAM (max_low_pfn >> 7)
+
+extern int extra_pd1_pages_allowance;
+extern int storage_needed(int use_ecr, int ignore_extra_p1_allowance);
+extern int ram_to_suspend(void);
diff -urN oldtree/kernel/power/proc.c newtree/kernel/power/proc.c
--- oldtree/kernel/power/proc.c	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/proc.c	2006-01-28 17:08:36.238726520 +0000
@@ -0,0 +1,305 @@
+/*
+ * /kernel/power/proc.c
+ *
+ * Copyright (C) 2002-2005 Nigel Cunningham <nigel@suspend2.net>
+ *
+ * This file is released under the GPLv2.
+ *
+ * This file contains support for proc entries for tuning Suspend2.
+ *
+ * We have a generic handler that deals with the most common cases, and
+ * hooks for special handlers to use.
+ */
+
+#include <linux/suspend.h>
+#include <linux/module.h>
+#include <asm/uaccess.h>
+
+#include "proc.h"
+#include "suspend2.h"
+#include "storage.h"
+
+static int suspend_proc_initialised = 0;
+
+static struct list_head suspend_proc_entries;
+static struct proc_dir_entry *suspend_dir;
+static struct suspend_proc_data proc_params[];
+
+extern void __suspend2_try_resume(void);
+extern void suspend2_main(void);
+
+/* suspend2_read_proc
+ *
+ * Generic handling for reading the contents of bits, integers,
+ * unsigned longs and strings.
+ */
+static int suspend2_read_proc(char *page, char **start, off_t off, int count,
+		int *eof, void *data)
+{
+	int len = 0;
+	struct suspend_proc_data *proc_data = (struct suspend_proc_data *) data;
+
+	if (suspend_start_anything(0))
+		return -EBUSY;
+	
+	if (proc_data->needs_storage_manager & 1)
+		suspend2_prepare_usm();
+	
+	switch (proc_data->type) {
+		case SUSPEND_PROC_DATA_CUSTOM:
+			if (proc_data->data.special.read_proc) {
+				read_proc_t *read_proc = proc_data->data.special.read_proc;
+				len = read_proc(page, start, off, count, eof, data);
+			} else
+				len = 0;
+			break;
+		case SUSPEND_PROC_DATA_BIT:
+			len = sprintf(page, "%d\n", 
+				-test_bit(proc_data->data.bit.bit,
+					proc_data->data.bit.bit_vector));
+			break;
+		case SUSPEND_PROC_DATA_INTEGER:
+			{
+				int *variable = proc_data->data.integer.variable;
+				len = sprintf(page, "%d\n", *variable);
+				break;
+			}
+		case SUSPEND_PROC_DATA_UL:
+			{
+				long *variable = proc_data->data.ul.variable;
+				len = sprintf(page, "%lu\n", *variable);
+				break;
+			}
+		case SUSPEND_PROC_DATA_STRING:
+			{
+				char *variable = proc_data->data.string.variable;
+				len = sprintf(page, "%s\n", variable);
+				break;
+			}
+	}
+	/* Side effect routine? */
+	if (proc_data->read_proc)
+		proc_data->read_proc();
+	
+	if (len <= count)
+		*eof = 1;
+	
+	if (proc_data->needs_storage_manager & 1)
+		suspend2_cleanup_usm();
+
+	suspend_finish_anything(0);
+	
+	return len;
+}
+/* suspend2_write_proc
+ *
+ * Generic routine for handling writing to files representing
+ * bits, integers and unsigned longs.
+ */
+
+static int suspend2_write_proc(struct file *file, const char *buffer,
+		unsigned long count, void *data)
+{
+	struct suspend_proc_data *proc_data = (struct suspend_proc_data *) data;
+	char *my_buf = (char *) get_zeroed_page(GFP_ATOMIC);
+	int result = count, assigned_temp_buffer = 0;
+
+	if (!my_buf)
+		return -ENOMEM;
+
+	if (count > PAGE_SIZE)
+		count = PAGE_SIZE;
+
+	if (copy_from_user(my_buf, buffer, count))
+		return -EFAULT;
+	
+	if (suspend_start_anything(proc_data == &proc_params[0]))
+		return -EBUSY;
+
+	my_buf[count] = 0;
+
+	if (proc_data->needs_storage_manager & 2)
+		suspend2_prepare_usm();
+
+	switch (proc_data->type) {
+		case SUSPEND_PROC_DATA_CUSTOM:
+			if (proc_data->data.special.write_proc) {
+				write_proc_t *write_proc = proc_data->data.special.write_proc;
+				result = write_proc(file, buffer, count, data);
+			}
+			break;
+		case SUSPEND_PROC_DATA_BIT:
+			{
+			int value = simple_strtoul(my_buf, NULL, 0);
+			if (value)
+				set_bit(proc_data->data.bit.bit, 
+					(proc_data->data.bit.bit_vector));
+			else
+				clear_bit(proc_data->data.bit.bit,
+					(proc_data->data.bit.bit_vector));
+			}
+			break;
+		case SUSPEND_PROC_DATA_INTEGER:
+			{
+				int *variable = proc_data->data.integer.variable;
+				int minimum = proc_data->data.integer.minimum;
+				int maximum = proc_data->data.integer.maximum;
+				*variable = simple_strtol(my_buf, NULL, 0);
+				if (((*variable) < minimum))
+					*variable = minimum;
+
+				if (((*variable) > maximum))
+					*variable = maximum;
+				break;
+			}
+		case SUSPEND_PROC_DATA_UL:
+			{
+				unsigned long *variable = proc_data->data.ul.variable;
+				unsigned long minimum = proc_data->data.ul.minimum;
+				unsigned long maximum = proc_data->data.ul.maximum;
+				*variable = simple_strtoul(my_buf, NULL, 0);
+				
+				if (minimum && ((*variable) < minimum))
+					*variable = minimum;
+
+				if (maximum && ((*variable) > maximum))
+					*variable = maximum;
+				break;
+			}
+			break;
+		case SUSPEND_PROC_DATA_STRING:
+			{
+				int copy_len = count;
+				char *variable =
+					proc_data->data.string.variable;
+
+				if (proc_data->data.string.max_length &&
+				    (copy_len > proc_data->data.string.max_length))
+					copy_len = proc_data->data.string.max_length;
+
+				if (!variable) {
+					proc_data->data.string.variable =
+						variable = (char *) get_zeroed_page(GFP_ATOMIC);
+					assigned_temp_buffer = 1;
+				}
+				strncpy(variable, my_buf, copy_len);
+				if ((copy_len) &&
+					 (my_buf[copy_len - 1] == '\n'))
+					variable[count - 1] = 0;
+				variable[count] = 0;
+			}
+			break;
+	}
+	free_page((unsigned long) my_buf);
+	/* Side effect routine? */
+	if (proc_data->write_proc)
+		proc_data->write_proc();
+
+	/* Free temporary buffers */
+	if (assigned_temp_buffer) {
+		free_page((unsigned long) proc_data->data.string.variable);
+		proc_data->data.string.variable = NULL;
+	}
+
+	if (proc_data->needs_storage_manager & 2)
+		suspend2_cleanup_usm();
+
+	suspend_finish_anything(proc_data == &proc_params[0]);
+	
+	return result;
+}
+
+/* Non-plugin proc entries.
+ *
+ * This array contains entries that are automatically registered at
+ * boot. Plugins and the console code register their own entries separately.
+ *
+ * NB: If you move do_suspend, change suspend2_write_proc's test so that
+ * suspend_start_anything still gets a 1 when the user echos > do_suspend!
+ */
+
+static struct suspend_proc_data proc_params[] = {
+	{ .filename			= "do_suspend",
+	  .permissions			= PROC_WRITEONLY,
+	  .type				= SUSPEND_PROC_DATA_CUSTOM,
+	  .write_proc			= suspend2_main,
+	  .needs_storage_manager	= 2,
+	},
+
+	{ .filename			= "do_resume",
+	  .permissions			= PROC_WRITEONLY,
+	  .type				= SUSPEND_PROC_DATA_CUSTOM,
+	  .write_proc			= __suspend2_try_resume,
+	  .needs_storage_manager	= 2,
+	},
+};
+
+/* suspend_initialise_proc
+ *
+ * Initialise the /proc/suspend2 directory.
+ */
+
+static void suspend_initialise_proc(void)
+{
+	int i;
+	int numfiles = sizeof(proc_params) / sizeof(struct suspend_proc_data);
+	
+	if (suspend_proc_initialised)
+		return;
+
+	suspend_dir = proc_mkdir("suspend2", NULL);
+	
+	BUG_ON(!suspend_dir);
+
+	INIT_LIST_HEAD(&suspend_proc_entries);
+
+	suspend_proc_initialised = 1;
+
+	for (i=0; i< numfiles; i++)
+		suspend_register_procfile(&proc_params[i]);
+}
+
+/* suspend_register_procfile
+ *
+ * Helper for registering a new /proc/suspend2 entry.
+ */
+
+struct proc_dir_entry *suspend_register_procfile(
+		struct suspend_proc_data *suspend_proc_data)
+{
+	struct proc_dir_entry *new_entry;
+	
+	if (!suspend_proc_initialised)
+		suspend_initialise_proc();
+
+	new_entry = create_proc_entry(
+			suspend_proc_data->filename,
+			suspend_proc_data->permissions, 
+			suspend_dir);
+	if (new_entry) {
+		list_add_tail(&suspend_proc_data->proc_data_list, &suspend_proc_entries);
+		new_entry->read_proc = suspend2_read_proc;
+		new_entry->write_proc = suspend2_write_proc;
+		new_entry->data = suspend_proc_data;
+	} else {
+		printk("Error! create_proc_entry returned NULL.\n");
+		INIT_LIST_HEAD(&suspend_proc_data->proc_data_list);
+	}
+	return new_entry;
+}
+
+/* suspend_unregister_procfile
+ *
+ * Helper for removing unwanted /proc/suspend2 entries.
+ *
+ */
+void suspend_unregister_procfile(struct suspend_proc_data *suspend_proc_data)
+{
+	if (list_empty(&suspend_proc_data->proc_data_list))
+		return;
+
+	remove_proc_entry(
+		suspend_proc_data->filename,
+		suspend_dir);
+	list_del(&suspend_proc_data->proc_data_list);
+}
diff -urN oldtree/kernel/power/proc.h newtree/kernel/power/proc.h
--- oldtree/kernel/power/proc.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/proc.h	2006-01-28 17:08:36.238726520 +0000
@@ -0,0 +1,70 @@
+/*
+ * kernel/power/proc.h
+ *
+ * Copyright (C) 2004-2005 Nigel Cunningham <nigel@suspend2.net>
+ *
+ * This file is released under the GPLv2.
+ *
+ * It provides declarations for suspend to use in managing
+ * /proc/suspend2. When we switch to kobjects,
+ * this will become redundant.
+ *
+ */
+
+#include <linux/proc_fs.h>
+
+struct suspend_proc_data {
+	char *filename;
+	int permissions;
+	int type;
+	int needs_storage_manager;
+	union {
+		struct {
+			unsigned long *bit_vector;
+			int bit;
+		} bit;
+		struct {
+			int *variable;
+			int minimum;
+			int maximum;
+		} integer;
+		struct {
+			unsigned long *variable;
+			unsigned long minimum;
+			unsigned long maximum;
+		} ul;
+		struct {
+			char *variable;
+			int max_length;
+		} string;
+		struct {
+			read_proc_t *read_proc;
+			write_proc_t *write_proc;
+			void *data;
+		} special;
+	} data;
+	
+	/* Side effects routines. Used, eg, for reparsing the
+	 * resume2 entry when it changes */
+	void (*read_proc) (void);
+	void (*write_proc) (void); 
+	struct list_head proc_data_list;
+};
+
+enum {
+	SUSPEND_PROC_DATA_NONE,
+	SUSPEND_PROC_DATA_CUSTOM,
+	SUSPEND_PROC_DATA_BIT,
+	SUSPEND_PROC_DATA_INTEGER,
+	SUSPEND_PROC_DATA_UL,
+	SUSPEND_PROC_DATA_STRING
+};
+
+#define PROC_WRITEONLY 0200
+#define PROC_READONLY 0400
+#define PROC_RW 0600
+
+struct proc_dir_entry *suspend_register_procfile(
+		struct suspend_proc_data *suspend_proc_data);
+void suspend_unregister_procfile(struct suspend_proc_data *suspend_proc_data);
+
diff -urN oldtree/kernel/power/process.c newtree/kernel/power/process.c
--- oldtree/kernel/power/process.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/kernel/power/process.c	2006-01-28 17:08:36.239726368 +0000
@@ -1,134 +1,432 @@
 /*
- * drivers/power/process.c - Functions for starting/stopping processes on 
- *                           suspend transitions.
+ * kernel/power/process.c
  *
- * Originally from swsusp.
+ * Copyright (C) 1998-2001 Gabor Kuti <seasons@fornax.hu>
+ * Copyright (C) 1998,2001,2002 Pavel Machek <pavel@suse.cz>
+ * Copyright (C) 2002-2003 Florent Chabaud <fchabaud@free.fr>
+ * Copyright (C) 2002-2004 Nigel Cunningham <ncunningham@linuxmail.org>
+ *
+ * This file is released under the GPLv2.
+ *
+ * Freeze_and_free contains the routines software suspend uses to freeze other
+ * processes during the suspend cycle and to (if necessary) free up memory in
+ * accordance with limitations on the image size.
+ *
+ * Ideally, the image saved to disk would be an atomic copy of the entire 
+ * contents of all RAM and related hardware state. One of the first 
+ * prerequisites for getting our approximation of this is stopping the activity
+ * of other processes. We can't stop all other processes, however, since some 
+ * are needed in doing the I/O to save the image. Freeze_and_free.c contains 
+ * the routines that control suspension and resuming of these processes.
+ * 
+ * Under high I/O load, we need to be careful about the order in which we
+ * freeze processes. If we freeze processes in the wrong order, we could
+ * deadlock others. The freeze_order array this specifies the order in which
+ * critical processes are frozen. All others are suspended after these have
+ * entered the refrigerator.
+ *
+ * Another complicating factor is that freeing memory requires the processes
+ * to not be frozen, but at the end of freeing memory, they need to be frozen
+ * so that we can be sure we actually have eaten enough memory. This is why
+ * freezing and freeing are in the one file. The freezer is not called from
+ * the main logic, but indirectly, via the code for eating memory. The eat
+ * memory logic is iterative, first freezing processes and checking the stats,
+ * then (if necessary) unfreezing them and eating more memory until it looks 
+ * like the criteria are met (at which point processes are frozen & stats
+ * checked again).
  */
 
-
-#undef DEBUG
-
-#include <linux/smp_lock.h>
-#include <linux/interrupt.h>
 #include <linux/suspend.h>
+#include <linux/freezer.h>
 #include <linux/module.h>
+#include <linux/mount.h>
+#include <linux/namespace.h>
+#include <linux/buffer_head.h>
+#include <asm/tlbflush.h>
+
+unsigned long freezer_state = 0;
+
+#if 0
+//#ifdef CONFIG_PM_DEBUG
+#define freezer_message(msg, a...) do { printk(msg, ##a); } while(0)
+#else
+#define freezer_message(msg, a...) do { } while(0)
+#endif
+
+/* Timeouts when freezing */
+#define FREEZER_TOTAL_TIMEOUT (5 * HZ)
+#define FREEZER_CHECK_TIMEOUT (HZ / 10)
+
+DECLARE_COMPLETION(kernelspace_thaw);
+DECLARE_COMPLETION(userspace_thaw);
+static atomic_t nr_userspace_frozen;
+static atomic_t nr_kernelspace_frozen;
+
+struct frozen_fs
+{
+	struct list_head fsb_list;
+	struct super_block *sb;
+};
+
+LIST_HEAD(frozen_fs_list);
+
+void freezer_make_fses_rw(void)
+{
+	struct frozen_fs *fs, *next_fs;
+
+	list_for_each_entry_safe(fs, next_fs, &frozen_fs_list, fsb_list) {
+		thaw_bdev(fs->sb->s_bdev, fs->sb);
+
+		list_del(&fs->fsb_list);
+		kfree(fs);
+	}
+}
 
 /* 
- * Timeout for stopping processes
+ * Done after userspace is frozen, so there should be no danger of
+ * fses being unmounted while we're in here.
  */
-#define TIMEOUT	(6 * HZ)
+int freezer_make_fses_ro(void)
+{
+	struct frozen_fs *fs;
+	struct super_block *sb;
+
+	/* Generate the list */
+	list_for_each_entry(sb, &super_blocks, s_list) {
+		if (!sb->s_root || !sb->s_bdev ||
+		    (sb->s_frozen == SB_FREEZE_TRANS) ||
+		    (sb->s_flags & MS_RDONLY))
+			continue;
 
+		fs = kmalloc(sizeof(struct frozen_fs), GFP_ATOMIC);
+		fs->sb = sb;
+		list_add_tail(&fs->fsb_list, &frozen_fs_list);
+	};
+
+	/* Do the freezing in reverse order so filesystems dependant
+	 * upon others are frozen in the right order. (Eg loopback
+	 * on ext3). */
+	list_for_each_entry_reverse(fs, &frozen_fs_list, fsb_list)
+		freeze_bdev(fs->sb->s_bdev);
 
-static inline int freezeable(struct task_struct * p)
+	return 0;
+}
+
+/*
+ * freezeable
+ *
+ * Description:	Determine whether a process should be frozen yet.
+ * Parameters:	struct task_struct *	The process to consider.
+ * 		int			Boolean - 0 = userspace else all.
+ * Returns:	int			0 if don't freeze yet, otherwise do.
+ */
+static int freezeable(struct task_struct * p, int all_freezable)
 {
 	if ((p == current) || 
+	    (p->flags & PF_FROZEN) ||
 	    (p->flags & PF_NOFREEZE) ||
 	    (p->exit_state == EXIT_ZOMBIE) ||
 	    (p->exit_state == EXIT_DEAD) ||
 	    (p->state == TASK_STOPPED) ||
-	    (p->state == TASK_TRACED))
+	    (p->state == TASK_TRACED) ||
+	    (!p->mm && !all_freezable))
 		return 0;
 	return 1;
 }
 
-/* Refrigerator is place where frozen processes are stored :-). */
-void refrigerator(void)
+static void __freeze_process(struct completion *completion_handler,
+				atomic_t *nr_frozen)
 {
-	/* Hmm, should we be allowed to suspend when there are realtime
-	   processes around? */
 	long save;
-	save = current->state;
-	pr_debug("%s entered refrigerator\n", current->comm);
-	printk("=");
 
-	frozen_process(current);
-	spin_lock_irq(&current->sighand->siglock);
-	recalc_sigpending(); /* We sent fake signal, clean it up */
-	spin_unlock_irq(&current->sighand->siglock);
-
-	while (frozen(current)) {
-		current->state = TASK_UNINTERRUPTIBLE;
-		schedule();
-	}
-	pr_debug("%s left refrigerator\n", current->comm);
+	freezer_message("%s (%d) frozen.\n",
+			current->comm, current->pid);
+	save = current->state;
+	
+	atomic_inc(nr_frozen);
+	wait_for_completion(completion_handler);
+	atomic_dec(nr_frozen);
+	
 	current->state = save;
+	freezer_message("%s (%d) leaving freezer.\n",
+			current->comm, current->pid);
 }
 
-/* 0 = success, else # of processes that we failed to stop */
-int freeze_processes(void)
+/*
+ * Invoked by the task todo list notifier when the task to be
+ * frozen is running.
+ */
+static int freeze_process(struct notifier_block *nl, unsigned long x, void *v)
 {
-	int todo;
-	unsigned long start_time;
-	struct task_struct *g, *p;
 	unsigned long flags;
 
-	printk( "Stopping tasks: " );
-	start_time = jiffies;
-	do {
-		todo = 0;
-		read_lock(&tasklist_lock);
-		do_each_thread(g, p) {
-			if (!freezeable(p))
-				continue;
-			if (frozen(p))
-				continue;
+	might_sleep();
 
-			freeze(p);
-			spin_lock_irqsave(&p->sighand->siglock, flags);
-			signal_wake_up(p, 0);
-			spin_unlock_irqrestore(&p->sighand->siglock, flags);
-			todo++;
-		} while_each_thread(g, p);
-		read_unlock(&tasklist_lock);
-		yield();			/* Yield is okay here */
-		if (todo && time_after(jiffies, start_time + TIMEOUT)) {
-			printk( "\n" );
-			printk(KERN_ERR " stopping tasks failed (%d tasks remaining)\n", todo );
-			break;
-		}
-	} while(todo);
-
-	/* This does not unfreeze processes that are already frozen
-	 * (we have slightly ugly calling convention in that respect,
-	 * and caller must call thaw_processes() if something fails),
-	 * but it cleans up leftover PF_FREEZE requests.
-	 */
-	if (todo) {
-		read_lock(&tasklist_lock);
-		do_each_thread(g, p)
-			if (freezing(p)) {
-				pr_debug("  clean up: %s\n", p->comm);
-				p->flags &= ~PF_FREEZE;
-				spin_lock_irqsave(&p->sighand->siglock, flags);
-				recalc_sigpending_tsk(p);
-				spin_unlock_irqrestore(&p->sighand->siglock, flags);
-			}
-		while_each_thread(g, p);
-		read_unlock(&tasklist_lock);
-		return todo;
+	/* Locking to handle race against waking the process in
+	 * freeze threads. */
+	spin_lock_irqsave(&current->sighand->siglock, flags);
+	current->flags |= PF_FROZEN;
+
+	if (nl)
+		notifier_chain_unregister(&current->todo, nl);
+
+	recalc_sigpending();
+	spin_unlock_irqrestore(&current->sighand->siglock, flags);
+
+	if (nl)
+		kfree(nl);
+
+	if (test_freezer_state(FREEZER_ON)) {
+		if (current->mm)
+			__freeze_process(&userspace_thaw, &nr_userspace_frozen);
+		else
+			__freeze_process(&kernelspace_thaw,
+					&nr_kernelspace_frozen);
 	}
 
-	printk( "|\n" );
-	BUG_ON(in_atomic());
+	spin_lock_irqsave(&current->sighand->siglock, flags);
+	recalc_sigpending();
+	spin_unlock_irqrestore(&current->sighand->siglock, flags);
+
+	current->flags &= ~PF_FROZEN;
+
 	return 0;
 }
 
-void thaw_processes(void)
+void thaw_processes(int do_all_threads)
 {
+	if (do_all_threads) {
+		clear_freezer_state(FREEZER_ON);
+		clear_freezer_state(ABORT_FREEZING);
+	}
+
+	complete_all(&kernelspace_thaw);
+	while (atomic_read(&nr_kernelspace_frozen) > 0)
+		yield();
+
+	init_completion(&kernelspace_thaw);
+	freezer_make_fses_rw();
+
+	if (do_all_threads) {
+		complete_all(&userspace_thaw);
+		while (atomic_read(&nr_userspace_frozen) > 0)
+			yield();
+		init_completion(&userspace_thaw);
+	}
+}
+
+/*
+ * num_freezeable
+ *
+ * Description:	Determine how many processes of our type are still to be
+ * 		frozen. As a side effect, update the progress bar too.
+ * Parameters:	int	Which type we are trying to freeze.
+ * 		int	Whether we are displaying our progress.
+ */
+static int num_freezeable(int do_all_threads) {
+	
 	struct task_struct *g, *p;
+	int todo_this_type = 0;
 
-	printk( "Restarting tasks..." );
 	read_lock(&tasklist_lock);
 	do_each_thread(g, p) {
-		if (!freezeable(p))
+		if (freezeable(p, do_all_threads))
+			todo_this_type++;
+	} while_each_thread(g, p);
+	read_unlock(&tasklist_lock);
+
+	return todo_this_type;
+}
+
+/*
+ * num_uninterruptible
+ *
+ * Description:	Determine how many processes of our type are in state
+ * 		task uninterruptible.
+ * Parameters:	int	Which type we are trying to freeze.
+ */
+static int num_uninterruptible(int do_all_threads) {
+	
+	struct task_struct *g, *p;
+	int count = 0;
+
+	read_lock(&tasklist_lock);
+	do_each_thread(g, p) {
+		if (freezeable(p, do_all_threads) &&
+			p->state == TASK_UNINTERRUPTIBLE)
+			count++;
+	} while_each_thread(g, p);
+	read_unlock(&tasklist_lock);
+
+	return count;
+}
+
+/*
+ * Tell threads of the type to enter the freezer.
+ */
+static void signal_threads(int do_all_threads)
+{
+	struct task_struct *g, *p;
+	struct notifier_block *n;
+
+	read_lock(&tasklist_lock);
+	do_each_thread(g, p) {
+		if (!freezeable(p, do_all_threads))
 			continue;
-		if (!thaw_process(p))
-			printk(KERN_INFO " Strange, %s not stopped\n", p->comm );
+
+		n = kmalloc(sizeof(struct notifier_block),
+					GFP_ATOMIC);
+
+		if (n) {
+			n->notifier_call = freeze_process;
+			n->priority = 0;
+			notifier_chain_register(&p->todo, n);
+ 		}
 	} while_each_thread(g, p);
+	read_unlock(&tasklist_lock);
+}
+
+/*
+ * Prod processes that haven't entered the refrigerator yet.
+ */
+static void prod_processes(int do_all_threads)
+{
+	struct task_struct *g, *p;
+	unsigned long flags;
+
+	read_lock(&tasklist_lock);
+	do_each_thread(g, p) {
+		if (!freezeable(p, do_all_threads))
+			continue;
+			
+		spin_lock_irqsave(&p->sighand->siglock, flags);
+		if (!(p->flags & PF_FROZEN)) {
+			recalc_sigpending();
+			signal_wake_up(p, 0);
+		}
+		spin_unlock_irqrestore(&p->sighand->siglock, flags);
+	} while_each_thread(g, p);
+	read_unlock(&tasklist_lock);
+}
+
+/*
+ * Freezer failure.
+ *
+ * Check whether we failed to freeze all the processes that
+ * should be frozen. If we find a task that failed to freeze,
+ * we give useful information on what failed and how.
+ */
+static int freezer_failure(int do_all_threads)
+{
+	int result = 0;
+	struct task_struct *g, *p;
+
+	read_lock(&tasklist_lock);
+	do_each_thread(g, p) {
+		if (!freezeable(p, do_all_threads) || 
+				p->state == TASK_UNINTERRUPTIBLE) 
+			continue;
 
+		if (!result) {
+			printk(KERN_ERR	"Stopping tasks failed.\n");
+			printk(KERN_ERR "Tasks that refused to be "
+			 "refrigerated and haven't since exited:\n");
+			set_freezer_state(ABORT_FREEZING);
+			result = 1;
+		}
+
+		if ((freezing(p))) {
+			printk(" - %s (#%d) signalled but "
+				"didn't enter refrigerator.\n",
+				p->comm, p->pid);
+		} else
+			printk(" - %s (#%d) signalled "
+				"and todo list empty.\n",
+				p->comm, p->pid);
+	} while_each_thread(g, p);
 	read_unlock(&tasklist_lock);
-	schedule();
-	printk( " done\n" );
+
+	return result;
+}
+
+/*
+ * freeze_threads
+ *
+ * Freeze a set of threads having particular attributes.
+ *
+ * Types:
+ * 2: User threads.
+ * 3: Kernel threads.
+ */
+static int freeze_threads(int do_all_threads)
+{
+	int result = 0, still_to_do;
+	unsigned long start_time = jiffies;
+
+	if (do_all_threads)	
+		freezer_make_fses_ro();
+
+	signal_threads(do_all_threads);
+
+	/* Watch them do it, wake them if they ignore us. */
+	do {
+		prod_processes(do_all_threads);
+
+		set_task_state(current, TASK_INTERRUPTIBLE);
+		schedule_timeout(FREEZER_CHECK_TIMEOUT);
+
+		still_to_do = num_freezeable(do_all_threads) - 
+			num_uninterruptible(do_all_threads);
+
+	} while(still_to_do && (!test_freezer_state(ABORT_FREEZING)) &&
+		!time_after(jiffies, start_time + FREEZER_TOTAL_TIMEOUT));
+
+	/*
+	 * Did we time out? See if we failed to freeze processes as well.
+	 *
+	 */
+	if ((time_after(jiffies, start_time + FREEZER_TOTAL_TIMEOUT))
+			&& (still_to_do))
+		result = freezer_failure(do_all_threads);
+
+	BUG_ON(in_atomic());
+	
+	return 0; 
+}
+
+/*
+ * freeze_processes - Freeze processes prior to saving an image of memory.
+ * 
+ * Return value: 0 = success, 1 = faulure.
+ */
+int freeze_processes(void)
+{
+	enum system_states old_state = system_state;
+	int result = 0;
+
+	if (!test_freezer_state(FREEZER_ON)) {
+		/* 
+		 * No race. While !FREEZER_ON, processes
+		 * won't enter __freeze_process
+		 */
+		init_completion(&userspace_thaw);
+		init_completion(&kernelspace_thaw);
+		set_freezer_state(FREEZER_ON);
+	}
+
+	/* Now freeze processes that were syncing and are still running */
+	if (freeze_threads(0) || (test_freezer_state(ABORT_FREEZING))) {
+		result = 1;
+		goto out;
+	}
+
+	/* Freeze kernel threads */
+	if (freeze_threads(1) || (test_freezer_state(ABORT_FREEZING)))
+		result = 1;
+
+out:
+	system_state = old_state;
+	return result;
 }
 
-EXPORT_SYMBOL(refrigerator);
+EXPORT_SYMBOL(freezer_state);
diff -urN oldtree/kernel/power/snapshot.c newtree/kernel/power/snapshot.c
--- oldtree/kernel/power/snapshot.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/kernel/power/snapshot.c	2006-01-28 17:08:36.240726216 +0000
@@ -146,7 +146,7 @@
 		return 0;
 
 	page = pfn_to_page(pfn);
-	BUG_ON(PageReserved(page) && PageNosave(page));
+	//BUG_ON(PageReserved(page) && PageNosave(page));
 	if (PageNosave(page))
 		return 0;
 	if (PageReserved(page) && pfn_is_nosave(pfn)) {
diff -urN oldtree/kernel/power/storage.c newtree/kernel/power/storage.c
--- oldtree/kernel/power/storage.c	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/storage.c	2006-01-28 17:08:36.240726216 +0000
@@ -0,0 +1,323 @@
+/*
+ * kernel/power/storage.c
+ *
+ * Copyright (C) 2005 Nigel Cunningham <nigel@suspend2.net>
+ *
+ * This file is released under the GPLv2.
+ *
+ * Routines for talking to a userspace program that manages storage.
+ *
+ * The kernel side:
+ * - starts the userspace program;
+ * - sends messages telling it when to open and close the connection;
+ * - tells it when to quit;
+ *
+ * The user space side:
+ * - passes messages regarding status;
+ *
+ */
+
+#include <linux/suspend.h>
+#include <linux/freezer.h>
+ 
+#include "proc.h"
+#include "plugins.h"
+#include "netlink.h"
+#include "storage.h"
+#include "ui.h"
+
+static struct user_helper_data usm_helper_data;
+static struct suspend_plugin_ops usm_ops;
+static int message_received = 0;
+static int activations = 0;
+static int usm_prepare_count = 0;
+static int storage_manager_last_action = 0;
+static int storage_manager_action = 0;
+
+static int usm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
+{
+	int type;
+	int *data;
+
+	type = nlh->nlmsg_type;
+
+	/* A control message: ignore them */
+	if (type < NETLINK_MSG_BASE)
+		return 0;
+
+	/* Unknown message: reply with EINVAL */
+	if (type >= USM_MSG_MAX)
+		return -EINVAL;
+
+	/* All operations require privileges, even GET */
+	if (security_netlink_recv(skb))
+		return -EPERM;
+
+	/* Only allow one task to receive NOFREEZE privileges */
+	if (type == NETLINK_MSG_NOFREEZE_ME && usm_helper_data.pid != -1)
+		return -EBUSY;
+
+	data = (int*)NLMSG_DATA(nlh);
+
+	switch (type) {
+		case USM_MSG_SUCCESS:
+		case USM_MSG_FAILED:
+			message_received = type;
+			complete(&usm_helper_data.wait_for_process);
+			break;
+		default:
+			printk("Storage manager doesn't recognise message %d.\n", type);
+	}
+
+	return 1;
+}
+
+int suspend2_activate_storage(int force)
+{
+	int tries = 1;
+
+	if (usm_helper_data.pid == -1 || usm_ops.disabled)
+		return 0;
+
+	message_received = 0;
+	activations++;
+
+	if (activations > 1 && !force)
+		return 0;
+
+	while ((!message_received || message_received == USM_MSG_FAILED) && tries < 2) {
+		suspend2_prepare_status(DONT_CLEAR_BAR, "Activate storage attempt %d.\n", tries);
+
+		init_completion(&usm_helper_data.wait_for_process);
+
+		suspend2_send_netlink_message(&usm_helper_data,
+			USM_MSG_CONNECT,
+			NULL, 0);
+
+		/* Wait 2 seconds for the userspace process to make contact */
+		wait_for_completion_timeout(&usm_helper_data.wait_for_process, 2*HZ);
+
+		tries++;
+	}
+
+	return 0;
+}
+
+int suspend2_deactivate_storage(int force)
+{
+	if (usm_helper_data.pid == -1 || usm_ops.disabled)
+		return 0;
+	
+	message_received = 0;
+	activations--;
+
+	if (activations && !force)
+		return 0;
+
+	init_completion(&usm_helper_data.wait_for_process);
+
+	suspend2_send_netlink_message(&usm_helper_data,
+			USM_MSG_DISCONNECT,
+			NULL, 0);
+
+	wait_for_completion_timeout(&usm_helper_data.wait_for_process, 2*HZ);
+
+	if (!message_received || message_received == USM_MSG_FAILED) {
+		printk("Returning failure disconnecting storage.\n");
+		return 1;
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_DEBUG
+static void storage_manager_simulate(void)
+{
+	printk("--- Storage manager simulate ---\n");
+	suspend2_prepare_usm();
+	schedule();
+	printk("--- Deactivate storage 1 ---\n");
+	suspend2_deactivate_storage(1);
+	schedule();
+	printk("--- Activate storage 1 ---\n");
+	suspend2_activate_storage(1);
+	schedule();
+	printk("--- Cleanup usm ---\n");
+	suspend2_cleanup_usm();
+	schedule();
+	printk("--- Storage manager simulate ends ---\n");
+}
+#endif
+
+static unsigned long usm_storage_needed(void)
+{
+	return strlen(usm_helper_data.program);
+}
+
+static int usm_save_config_info(char *buf)
+{
+	int len = strlen(usm_helper_data.program);
+	memcpy(buf, usm_helper_data.program, len);
+	return len;
+}
+
+static void usm_load_config_info(char *buf, int size)
+{
+	/* Don't load the saved path if one has already been set */
+	if (usm_helper_data.program[0])
+		return;
+
+	memcpy(usm_helper_data.program, buf, size);
+}
+
+static unsigned long usm_memory_needed(void)
+{
+	/* ball park figure of 32 pages */
+	return (32 * PAGE_SIZE);
+}
+
+/* suspend2_prepare_usm
+ */
+int suspend2_prepare_usm(void)
+{
+	usm_prepare_count++;
+
+	if (usm_prepare_count > 1 || usm_ops.disabled)
+		return 0;
+	
+	usm_helper_data.pid = -1;
+
+	if (!*usm_helper_data.program)
+		return 0;
+
+	suspend2_netlink_setup(&usm_helper_data);
+
+	if (usm_helper_data.pid == -1)
+		printk("Suspend2 Storage Manager wanted, but couldn't start it.\n");
+
+	suspend2_activate_storage(0);
+
+	return (usm_helper_data.pid != -1);
+}
+
+void suspend2_cleanup_usm(void)
+{
+	usm_prepare_count--;
+
+	if (usm_helper_data.pid > -1 && !usm_prepare_count) {
+		struct task_struct *t;
+
+		suspend2_deactivate_storage(0);
+
+		suspend2_send_netlink_message(&usm_helper_data,
+				NETLINK_MSG_CLEANUP, NULL, 0);
+
+		read_lock(&tasklist_lock);
+		if ((t = find_task_by_pid(usm_helper_data.pid)))
+			t->flags &= ~PF_NOFREEZE;
+		read_unlock(&tasklist_lock);
+
+		suspend2_netlink_close(&usm_helper_data);
+
+		usm_helper_data.pid = -1;
+	}
+}
+
+static void storage_manager_activate(void)
+{
+	if (storage_manager_action == storage_manager_last_action)
+		return;
+
+	if (storage_manager_action)
+		suspend2_prepare_usm();
+	else
+		suspend2_cleanup_usm();
+
+	storage_manager_last_action = storage_manager_action;
+}
+
+/*
+ * User interface specific /proc/suspend entries.
+ */
+
+static struct suspend_proc_data proc_params[] = {
+	{ .filename			= "disable_storage_manager",
+	  .permissions			= PROC_RW,
+	  .type				= SUSPEND_PROC_DATA_INTEGER,
+	  .data = {
+		.integer = {
+			.variable	= &usm_ops.disabled,
+			.minimum	= 0,
+			.maximum	= 1,
+		}
+	  }
+	},
+	{ .filename			= "storage_manager",
+	  .permissions			= PROC_RW,
+	  .type				= SUSPEND_PROC_DATA_STRING,
+	  .data = {
+		.string = {
+			.variable	= usm_helper_data.program,
+			.max_length	= 254,
+		}
+	  }
+	},
+	{ .filename			= "activate_storage",
+	  .permissions			= PROC_RW,
+	  .type				= SUSPEND_PROC_DATA_INTEGER,
+	  .data = {
+		.integer = {
+			.variable	= &storage_manager_action,
+			.minimum	= 0,
+			.maximum	= 1,
+		}
+	  },
+	  .write_proc 			= storage_manager_activate,
+	},
+
+#ifdef CONFIG_PM_DEBUG
+	{ .filename			= "simulate_atomic_copy",
+	  .permissions			= PROC_RW,
+	  .type				= SUSPEND_PROC_DATA_NONE,
+	  .write_proc 			= storage_manager_simulate,
+	}
+#endif
+};
+
+static struct suspend_plugin_ops usm_ops = {
+	.type				= MISC_PLUGIN,
+	.name				= "Userspace Storage Manager",
+	.module				= THIS_MODULE,
+	.storage_needed			= usm_storage_needed,
+	.save_config_info		= usm_save_config_info,
+	.load_config_info		= usm_load_config_info,
+	.memory_needed			= usm_memory_needed,
+};
+
+/* suspend_usm_proc_init
+ * Description: Boot time initialisation for user interface.
+ */
+static __init int suspend_usm_proc_init(void)
+{
+	int result, i, numfiles = sizeof(proc_params) / sizeof(struct suspend_proc_data);
+
+	if (!(result = suspend_register_plugin(&usm_ops)))
+		for (i=0; i< numfiles; i++)
+			suspend_register_procfile(&proc_params[i]);
+
+	usm_helper_data.nl = NULL;
+	usm_helper_data.program[0] = '\0';
+	usm_helper_data.pid = -1;
+	usm_helper_data.skb_size = 0;
+	usm_helper_data.pool_limit = 6;
+	usm_helper_data.netlink_id = NETLINK_SUSPEND2_USM;
+	usm_helper_data.name = "userspace storage manager";
+	usm_helper_data.rcv_msg = usm_user_rcv_msg;
+	usm_helper_data.interface_version = 1;
+	usm_helper_data.must_init = 0;
+	init_completion(&usm_helper_data.wait_for_process);
+
+	return result;
+}
+
+late_initcall(suspend_usm_proc_init);
diff -urN oldtree/kernel/power/storage.h newtree/kernel/power/storage.h
--- oldtree/kernel/power/storage.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/storage.h	2006-01-28 17:08:36.241726064 +0000
@@ -0,0 +1,21 @@
+/*
+ *
+ */
+
+int suspend2_prepare_usm(void);
+void suspend2_cleanup_usm(void);
+
+int suspend2_activate_storage(int force);
+int suspend2_deactivate_storage(int force);
+
+enum {
+	USM_MSG_BASE = 0x10,
+
+	/* Kernel -> Userspace */
+	USM_MSG_CONNECT = 0x30,
+	USM_MSG_DISCONNECT = 0x31,
+	USM_MSG_SUCCESS = 0x40,
+	USM_MSG_FAILED = 0x41,
+
+	USM_MSG_MAX,
+};
diff -urN oldtree/kernel/power/suspend.c newtree/kernel/power/suspend.c
--- oldtree/kernel/power/suspend.c	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/suspend.c	2006-01-28 17:08:36.242725912 +0000
@@ -0,0 +1,1112 @@
+/*
+ * kernel/power/suspend2.c
+ */
+/** \mainpage Suspend2.
+ *
+ * Suspend2 provides support for saving and restoring an image of
+ * system memory to an arbitrary storage device, either on the local computer,
+ * or across some network. The support is entirely OS based, so Suspend2 
+ * works without requiring BIOS, APM or ACPI support. The vast majority of the
+ * code is also architecture independant, so it should be very easy to port
+ * the code to new architectures. Suspend includes support for SMP, 4G HighMem
+ * and preemption. Initramfses and initrds are also supported.
+ *
+ * Suspend2 uses a modular design, in which the method of storing the image is
+ * completely abstracted from the core code, as are transformations on the data
+ * such as compression and/or encryption (multiple 'plugins' can be used to
+ * provide arbitrary combinations of functionality). The user interface is also
+ * modular, so that arbitrarily simple or complex interfaces can be used to
+ * provide anything from debugging information through to eye candy.
+ * 
+ * \section Copyright
+ *
+ * Suspend2 is released under the GPLv2.
+ *
+ * Copyright (C) 1998-2001 Gabor Kuti <seasons@fornax.hu><BR>
+ * Copyright (C) 1998,2001,2002 Pavel Machek <pavel@suse.cz><BR>
+ * Copyright (C) 2002-2003 Florent Chabaud <fchabaud@free.fr><BR>
+ * Copyright (C) 2002-2005 Nigel Cunningham <ncunningham@cyclades.com><BR>
+ *
+ * \section Credits
+ * 
+ * Nigel would like to thank the following people for their work:
+ * 
+ * Pavel Machek <pavel@ucw.cz><BR>
+ * Modifications, defectiveness pointing, being with Gabor at the very beginning,
+ * suspend to swap space, stop all tasks. Port to 2.4.18-ac and 2.5.17.
+ *
+ * Steve Doddi <dirk@loth.demon.co.uk><BR> 
+ * Support the possibility of hardware state restoring.
+ *
+ * Raph <grey.havens@earthling.net><BR>
+ * Support for preserving states of network devices and virtual console
+ * (including X and svgatextmode)
+ *
+ * Kurt Garloff <garloff@suse.de><BR>
+ * Straightened the critical function in order to prevent compilers from
+ * playing tricks with local variables.
+ *
+ * Andreas Mohr <a.mohr@mailto.de>
+ *
+ * Alex Badea <vampire@go.ro><BR>
+ * Fixed runaway init
+ *
+ * Jeff Snyder <je4d@pobox.com><BR>
+ * ACPI patch
+ *
+ * Nathan Friess <natmanz@shaw.ca><BR>
+ * Some patches.
+ *
+ * Michael Frank <mhf@linuxmail.org><BR>
+ * Extensive testing and help with improving stability. Nigel was constantly
+ * amazed by the quality and quantity of Michael's help.
+ *
+ * Bernard Blackham <bernard@blackham.com.au><BR>
+ * Web page & Wiki administration, some coding. Another person without whom
+ * Suspend would not be where it is.
+ *
+ * ..and of course the myriads of Suspend2 users who have helped diagnose
+ * and fix bugs, made suggestions on how to improve the code, proofread
+ * documentation, and donated time and money.
+ *
+ * Thanks also to corporate sponsors:
+ *
+ * <B>Cyclades.com.</B> Nigel's employers from Dec 2004, who allow him to work on
+ * Suspend and PM related issues on company time.
+ * 
+ * <B>LinuxFund.org.</B> Sponsored Nigel's work on Suspend for four months Oct 2003
+ * to Jan 2004.
+ *
+ * <B>LAC Linux.</B> Donated P4 hardware that enabled development and ongoing
+ * maintenance of SMP and Highmem support.
+ *
+ * <B>OSDL.</B> Provided access to various hardware configurations, make occasional
+ * small donations to the project.
+ */
+
+#define SUSPEND_MAIN_C
+
+#include <linux/suspend.h>
+#include <linux/module.h>
+#include <linux/console.h>
+#include <linux/version.h>
+#include <linux/reboot.h>
+#include <linux/mm.h>
+#include <linux/highmem.h>
+#include <linux/freezer.h>
+#include <asm/uaccess.h>
+#include <asm/setup.h>
+
+#include "version.h"
+#include "suspend2.h"
+#include "plugins.h"
+#include "proc.h"
+#include "pageflags.h"
+#include "prepare_image.h"
+#include "io.h"
+#include "ui.h"
+#include "suspend2_common.h"
+#include "extent.h"
+#include "power_off.h"
+#include "atomic_copy.h"
+#include "debug_pagealloc.h"
+#include "storage.h"
+
+#ifdef  CONFIG_X86
+#include <asm/i387.h> /* for kernel_fpu_end */
+#endif
+
+/* Variables to be preserved over suspend */
+int pageset1_sizelow = 0, pageset2_sizelow = 0, image_size_limit = 0;
+unsigned long suspend2_orig_mem_free = 0;
+
+static dyn_pageflags_t pageset1_check_map;
+static dyn_pageflags_t pageset2_check_map;
+static char *debug_info_buffer;
+static char suspend_core_version[] = SUSPEND_CORE_VERSION;
+
+extern void do_suspend2_lowlevel(int resume);
+extern __nosavedata char resume_commandline[COMMAND_LINE_SIZE];
+
+unsigned long suspend_action = 0;
+unsigned long suspend_result = 0;
+unsigned long suspend_debug_state = 0;
+
+/* 
+ * ---  Variables -----
+ * 
+ * The following are used by the arch specific low level routines 
+ * and only needed if suspend2 is compiled in. Other variables,
+ * used by the freezer even if suspend2 is not compiled in, are
+ * found in process.c
+ */
+
+/*! How long I/O took. */
+int suspend_io_time[2][2];
+
+/* Compression ratio */
+__nosavedata unsigned long bytes_in = 0, bytes_out = 0;
+
+/*! Pageset metadata. */
+struct pagedir pagedir1 = { 0, 0}, pagedir2 = { 0, 0}; 
+
+/* Suspend2 variables used by built-in routines. */
+
+/*! The number of suspends we have started (some may have been cancelled) */
+unsigned int nr_suspends = 0;
+
+/*! The console log level we default to. */
+int suspend_default_console_level = 0;
+
+/* 
+ * For resume2= kernel option. It's pointless to compile
+ * suspend2 without any writers, but compilation shouldn't
+ * fail if you do.
+ */
+
+unsigned long software_suspend_state = ((1 << SUSPEND_DISABLED) | (1 << SUSPEND_BOOT_TIME) |
+		(1 << SUSPEND_RESUME_NOT_DONE) | (1 << SUSPEND_IGNORE_LOGLEVEL));
+
+mm_segment_t	oldfs;
+
+char resume2_file[256] = CONFIG_SUSPEND2_DEFAULT_RESUME2;
+
+static atomic_t actions_running;
+
+/*
+ * Basic clean-up routine.
+ */
+void suspend_finish_anything(int finishing_cycle)
+{
+	if (atomic_dec_and_test(&actions_running)) {
+		suspend2_cleanup_plugins(finishing_cycle);
+		suspend2_put_modules();
+		clear_suspend_state(SUSPEND_RUNNING);
+	}
+
+	set_fs(oldfs);
+}
+
+/*
+ * Basic set-up routine.
+ */
+int suspend_start_anything(int starting_cycle)
+{
+	oldfs = get_fs();
+
+	if (atomic_add_return(1, &actions_running) == 1) {
+       		set_fs(KERNEL_DS);
+
+		set_suspend_state(SUSPEND_RUNNING);
+
+		if (suspend2_get_modules()) {
+			printk("Get modules failed!\n");
+			clear_suspend_state(SUSPEND_RUNNING);
+			set_fs(oldfs);
+			return -EBUSY;
+		}
+
+		if (suspend2_initialise_plugins(starting_cycle)) {
+			printk("Initialise plugins failed!\n");
+			suspend_finish_anything(starting_cycle);
+			return -EBUSY;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * save_image
+ * Result code (int): Zero on success, non zero on failure.
+ * Functionality    : High level routine which performs the steps necessary
+ *                    to prepare and save the image after preparatory steps
+ *                    have been taken.
+ * Key Assumptions  : Processes frozen, sufficient memory available, drivers
+ *                    suspended.
+ * Called from      : suspend2_suspend_2
+ */
+
+static int save_image(void)
+{
+	int temp_result;
+
+	suspend_message(SUSPEND_ANY_SECTION, SUSPEND_LOW, 1,
+		" - Final values: %d and %d.\n",
+		pagedir1.pageset_size, 
+		pagedir2.pageset_size);
+
+	check_shift_keys(1, "About to write pagedir2.");
+
+	temp_result = write_pageset(&pagedir2, 2);
+	
+	if (temp_result == -1 || test_result_state(SUSPEND_ABORTED))
+		return -1;
+
+	check_shift_keys(1, "About to copy pageset 1.");
+
+	suspend2_deactivate_storage(1);
+
+	suspend2_prepare_status(DONT_CLEAR_BAR, "Doing atomic copy.");
+	
+	do_suspend2_lowlevel(0);
+
+	return 0;
+}
+
+/*
+ * Save the second part of the image.
+ */
+int save_image_part1(void)
+{
+	int temp_result, old_ps1_size = pagedir1.pageset_size;
+	dyn_pageflags_t temp;
+	
+	/* Quick switch: We want to compare the old stats with the new ones. */
+	temp = pageset1_map;
+	pageset1_map = pageset1_check_map;
+	pageset1_check_map = temp;
+
+	temp = pageset2_map;
+	pageset2_map = pageset2_check_map;
+	pageset2_check_map = temp;
+
+	BUG_ON(!irqs_disabled());
+
+	suspend2_recalculate_stats(1);
+
+	if ((pagedir1.pageset_size - old_ps1_size) > extra_pd1_pages_allowance) {
+		abort_suspend("Pageset1 has grown by %d pages."
+			" Only %d growth is allowed for!\n",
+			pagedir1.pageset_size - old_ps1_size,
+			extra_pd1_pages_allowance);
+		return -1;
+	}
+
+	suspend2_map_atomic_copy_pages();
+
+	BUG_ON(!irqs_disabled());
+
+	if (!test_action_state(SUSPEND_TEST_FILTER_SPEED) &&
+	    !test_action_state(SUSPEND_TEST_BIO))
+		suspend2_copy_pageset1();
+
+	/*
+	 *  ----   FROM HERE ON, NEED TO REREAD PAGESET2 IF ABORTING!!! -----
+	 *  
+	 */
+	
+	suspend2_unmap_atomic_copy_pages();
+
+#ifdef CONFIG_X86
+	kernel_fpu_end();
+#endif
+
+	device_power_up();
+	
+	local_irq_enable();
+
+	device_resume();
+
+	if (suspend2_activate_storage(1))
+		panic("Failed to reactivate our storage.");
+	
+	suspend2_update_status(pagedir2.pageset_size,
+			pagedir1.pageset_size + pagedir2.pageset_size,
+			NULL);
+	
+	if (test_result_state(SUSPEND_ABORTED))
+		goto abort_reloading_pagedir_two;
+
+	check_shift_keys(1, "About to write pageset1.");
+
+	/*
+	 * End of critical section.
+	 */
+	
+	suspend_message(SUSPEND_ANY_SECTION, SUSPEND_LOW, 1,
+			"-- Writing pageset1\n");
+
+	temp_result = write_pageset(&pagedir1, 1);
+
+	/* We didn't overwrite any memory, so no reread needs to be done. */
+	if (test_action_state(SUSPEND_TEST_FILTER_SPEED))
+		return -1;
+
+	if (temp_result == -1 || test_result_state(SUSPEND_ABORTED))
+		goto abort_reloading_pagedir_two;
+
+	check_shift_keys(1, "About to write header.");
+
+	if (test_result_state(SUSPEND_ABORTED))
+		goto abort_reloading_pagedir_two;
+
+	temp_result = write_image_header();
+
+	if (test_action_state(SUSPEND_TEST_BIO))
+		return -1;
+
+	if (temp_result || (test_result_state(SUSPEND_ABORTED)))
+		goto abort_reloading_pagedir_two;
+
+	check_shift_keys(1, "About to power down or reboot.");
+
+	return 0;
+
+abort_reloading_pagedir_two:
+	temp_result = read_pageset2(1);
+
+	/* If that failed, we're sunk. Panic! */
+	if (temp_result)
+		panic("Attempt to reload pagedir 2 while aborting "
+				"a suspend failed.");
+
+	return -1;		
+
+}
+
+#define SNPRINTF(a...) 	len += snprintf_used(debug_info_buffer + len, \
+		PAGE_SIZE - len - 1, ## a)
+
+static int io_MB_per_second(int read_write)
+{
+	if (!suspend_io_time[read_write][1])
+		return 0;
+
+	return MB((unsigned long) suspend_io_time[read_write][0]) * HZ /
+		suspend_io_time[read_write][1];
+}
+
+/* get_debug_info
+ * Functionality:	Store debug info in a buffer.
+ * Called from:		suspend_try_suspend.
+ */
+
+
+static int get_suspend_debug_info(void)
+{
+	int len = 0;
+	if (!debug_info_buffer) {
+		debug_info_buffer = (char *) get_zeroed_page(GFP_ATOMIC);
+		if (!debug_info_buffer) {
+			printk("Error! Unable to allocate buffer for"
+					"software suspend debug info.\n");
+			return 0;
+		}
+	}
+
+	SNPRINTF("Suspend2 debugging info:\n");
+	SNPRINTF("- SUSPEND core   : %s\n", SUSPEND_CORE_VERSION);
+	SNPRINTF("- Kernel Version : %s\n", UTS_RELEASE);
+	SNPRINTF("- Compiler vers. : %d.%d\n", __GNUC__, __GNUC_MINOR__);
+	SNPRINTF("- Attempt number : %d\n", nr_suspends);
+	SNPRINTF("- Parameters     : %ld %ld %ld %d %d %ld\n",
+			suspend_result,
+			suspend_action,
+			suspend_debug_state,
+			suspend_default_console_level,
+			image_size_limit,
+			suspend2_powerdown_method);
+	SNPRINTF("- Overall expected compression percentage: %d.\n",
+			100 - suspend2_expected_compression_ratio());
+	len+= print_plugin_debug_info(debug_info_buffer + len, 
+			PAGE_SIZE - len - 1);
+	if (suspend_io_time[0][1]) {
+		if ((io_MB_per_second(0) < 5) || (io_MB_per_second(1) < 5)) {
+			SNPRINTF("- I/O speed: Write %d KB/s",
+			  (KB((unsigned long) suspend_io_time[0][0]) * HZ /
+			  suspend_io_time[0][1]));
+			if (suspend_io_time[1][1])
+				SNPRINTF(", Read %d KB/s",
+				  (KB((unsigned long) suspend_io_time[1][0]) * HZ /
+				  suspend_io_time[1][1]));
+		} else {
+			SNPRINTF("- I/O speed: Write %d MB/s",
+			 (MB((unsigned long) suspend_io_time[0][0]) * HZ /
+			  suspend_io_time[0][1]));
+			if (suspend_io_time[1][1])
+				SNPRINTF(", Read %d MB/s",
+				 (MB((unsigned long) suspend_io_time[1][0]) * HZ /
+				  suspend_io_time[1][1]));
+		}
+		SNPRINTF(".\n");
+	}
+	else
+		SNPRINTF("- No I/O speed stats available.\n");
+
+	return len;
+}
+
+/*
+ * debuginfo_read_proc
+ * Functionality   : Displays information that may be helpful in debugging
+ *                   software suspend.
+ */
+int debuginfo_read_proc(char *page, char **start, off_t off, int count,
+		int *eof, void *data)
+{
+	int info_len, copy_len;
+
+	info_len = get_suspend_debug_info();
+
+	copy_len = min(info_len - (int) off, count);
+	if (copy_len < 0)
+		copy_len = 0;
+
+	if (copy_len) {
+		memcpy(page, debug_info_buffer + off, copy_len);
+		*start = page;
+	} 
+
+	if (copy_len + off == info_len)
+		*eof = 1;
+
+	free_page((unsigned long) debug_info_buffer);
+	debug_info_buffer = NULL;
+	return copy_len;
+}
+
+static int allocate_bitmaps(void)
+{
+	suspend_message(SUSPEND_MEMORY, SUSPEND_VERBOSE, 1,
+			"Allocating in_use_map\n");
+	if (allocate_dyn_pageflags(&in_use_map) ||
+	    allocate_dyn_pageflags(&pageset1_map) ||
+	    allocate_dyn_pageflags(&pageset1_copy_map) ||
+	    allocate_dyn_pageflags(&allocd_pages_map) ||
+	    allocate_dyn_pageflags(&pageset2_map) ||
+#ifdef CONFIG_DEBUG_PAGEALLOC
+	    allocate_dyn_pageflags(&unmap_map) ||
+#endif	
+	    allocate_dyn_pageflags(&pageset1_check_map) ||
+	    allocate_dyn_pageflags(&pageset2_check_map))
+		return 1;
+
+	return 0;
+}
+
+static void free_metadata(void)
+{
+	free_dyn_pageflags(&pageset1_map);
+	free_dyn_pageflags(&pageset1_copy_map);
+	free_dyn_pageflags(&allocd_pages_map);
+	free_dyn_pageflags(&pageset2_map);
+	free_dyn_pageflags(&in_use_map);
+	free_dyn_pageflags(&pageset1_check_map);
+	free_dyn_pageflags(&pageset2_check_map);
+}
+
+static int check_still_keeping_image(void)
+{
+	if (test_action_state(SUSPEND_KEEP_IMAGE)) {
+		printk("Image already stored: powering down immediately.");
+		suspend_power_down();
+		return 1;	/* Just in case we're using S3 */
+	}
+
+	printk("Invalidating previous image.\n");
+	active_writer->ops.writer.invalidate_image();
+
+	return 0;
+}
+
+static int suspend2_init(void)
+{
+	suspend_result = 0;
+
+	printk(name_suspend "Initiating a software suspend cycle.\n");
+
+	nr_suspends++;
+	clear_suspend_state(SUSPEND_NOW_RESUMING);
+	
+	suspend_io_time[0][0] = suspend_io_time[0][1] = 
+		suspend_io_time[1][0] =
+		suspend_io_time[1][1] = 0;
+
+	suspend2_prepare_console();
+
+	free_metadata();	/* We might have kept it */
+
+	//attempt_to_parse_resume_device();
+	
+	if (test_suspend_state(SUSPEND_DISABLED))
+		return 0;
+	
+	if (allocate_bitmaps())
+		return 0;
+	
+	disable_nonboot_cpus();
+
+	return 1;
+}
+
+void suspend2_cleanup(void)
+{
+	int i;
+
+	i = get_suspend_debug_info();
+
+	suspend2_free_extra_pagedir_memory();
+	
+	pagedir1.pageset_size = pagedir2.pageset_size = 0;
+
+	thaw_processes(FREEZER_KERNEL_THREADS);
+
+#ifdef CONFIG_SUSPEND2_KEEP_IMAGE
+	if (test_action_state(SUSPEND_KEEP_IMAGE) &&
+	    !test_result_state(SUSPEND_ABORTED)) {
+		suspend_message(SUSPEND_ANY_SECTION, SUSPEND_LOW, 1,
+			name_suspend "Not invalidating the image due "
+			"to Keep Image being enabled.\n");
+		set_result_state(SUSPEND_KEPT_IMAGE);
+	} else
+#endif
+		if (active_writer)
+			active_writer->ops.writer.invalidate_image();
+
+	free_metadata();
+
+#ifdef CONFIG_DEBUG_PAGE_ALLOC
+	free_dyn_pageflags(&unmap_map);
+#endif
+
+	if (debug_info_buffer) {
+		/* Printk can only handle 1023 bytes, including
+		 * its level mangling. */
+		for (i = 0; i < 3; i++)
+			printk("%s", debug_info_buffer + (1023 * i));
+		free_page((unsigned long) debug_info_buffer);
+		debug_info_buffer = NULL;
+	}
+
+	thaw_processes(FREEZER_ALL_THREADS);
+
+	suspend2_cleanup_console();
+
+	enable_nonboot_cpus();
+}
+
+static int can_suspend(void)
+{
+	if (test_suspend_state(SUSPEND_DISABLED))
+		attempt_to_parse_resume_device();
+
+	if (test_suspend_state(SUSPEND_DISABLED)) {
+		printk(name_suspend "Software suspend is disabled.\n"
+			"This may be because you haven't put something along the "
+			"lines of\n\nresume2=swap:/dev/hda1\n\n"
+			"in lilo.conf or equivalent. (Where /dev/hda1 is your "
+			"swap partition).\n");
+		set_result_state(SUSPEND_ABORTED);
+		return 0;
+	}
+	
+	return 1;
+}
+
+/*
+ * suspend2_main
+ * Functionality   : First level of code for software suspend invocations.
+ *                   Stores and restores load averages (to avoid a spike),
+ *                   allocates bitmaps, freezes processes and eats memory
+ *                   as required before suspending drivers and invoking
+ *                   the 'low level' code to save the state to disk.
+ *                   By the time we return from do_suspend2_lowlevel, we
+ *                   have either failed to save the image or successfully
+ *                   suspended and reloaded the image. The difference can
+ *                   be discerned by checking SUSPEND_ABORTED.
+ * Called From     : 
+ */
+
+void suspend2_main(void)
+{
+	if (suspend2_activate_storage(0))
+		return;
+
+	if (!can_suspend())
+		goto cleanup;
+
+	/*
+	 * If kept image and still keeping image and suspending to RAM, we will 
+	 * return 1 after suspending and resuming (provided the power doesn't
+	 * run out.
+	 */
+	if (test_result_state(SUSPEND_KEPT_IMAGE) && check_still_keeping_image()) 
+		goto cleanup;
+
+	if (suspend2_init() && suspend2_prepare_image() && !test_result_state(SUSPEND_ABORTED) &&
+		!test_action_state(SUSPEND_FREEZER_TEST))
+	{
+		if (!test_result_state(SUSPEND_ABORTED)) {
+			suspend2_prepare_status(DONT_CLEAR_BAR, "Starting to save the image..");
+			save_image();
+		}
+	}
+	
+	suspend2_cleanup();
+cleanup:
+	suspend2_deactivate_storage(0);
+}
+
+/* image_exists_read
+ * 
+ * Return 0 or 1, depending on whether an image is found.
+ */
+static int image_exists_read(char *page, char **start, off_t off, int count,
+		int *eof, void *data)
+{
+	int len = 0;
+	
+	if (suspend2_activate_storage(0))
+		return count;
+
+	//attempt_to_parse_resume_device();
+
+	if (!active_writer)
+		len = sprintf(page, "-1\n");
+	else
+		len = sprintf(page, "%d\n", active_writer->ops.writer.image_exists());
+
+	*eof = 1;
+
+	suspend2_deactivate_storage(0);
+
+	return len;
+}
+
+/* image_exists_read
+ * 
+ * Return 0 or 1, depending on whether an image is found.
+ */
+static int image_exists_write(struct file *file, const char *buffer,
+		unsigned long count, void *data)
+{
+	if (suspend2_activate_storage(0))
+		return count;
+
+	if (active_writer && active_writer->ops.writer.image_exists())
+		active_writer->ops.writer.invalidate_image();
+
+	suspend2_deactivate_storage(0);
+
+	return count;
+}
+
+/*
+ * Core proc entries that aren't built in.
+ *
+ * This array contains entries that are automatically registered at
+ * boot. Plugins and the console code register their own entries separately.
+ */
+static struct suspend_proc_data proc_params[] = {
+	{ .filename			= "debug_info",
+	  .permissions			= PROC_READONLY,
+	  .type				= SUSPEND_PROC_DATA_CUSTOM,
+	  .data = {
+		  .special = {
+			  .read_proc	= debuginfo_read_proc,
+		  }
+	  }
+	},
+	
+	{ .filename			= "extra_pages_allowance",
+	  .permissions			= PROC_RW,
+	  .type				= SUSPEND_PROC_DATA_INTEGER,
+	  .data = {
+		  .integer = {
+			  .variable	= &extra_pd1_pages_allowance,
+			  .minimum	= 0,
+			  .maximum	= 32767,
+		  }
+	  }
+	},
+	
+	{ .filename			= "ignore_rootfs",
+	  .permissions			= PROC_RW,
+	  .type				= SUSPEND_PROC_DATA_BIT,
+	  .data = {
+		  .bit = {
+			  .bit_vector	= &suspend_action,
+			  .bit		= SUSPEND_IGNORE_ROOTFS,
+		  }
+	  }
+	},
+	
+	{ .filename			= "image_exists",
+	  .permissions			= PROC_RW,
+	  .type				= SUSPEND_PROC_DATA_CUSTOM,
+	  .needs_storage_manager	= 3,
+	  .data = {
+		  .special = {
+			  .read_proc	= image_exists_read,
+			  .write_proc	= image_exists_write,
+		  }
+	  }
+	},
+
+	{ .filename			= "image_size_limit",
+	  .permissions			= PROC_RW,
+	  .type				= SUSPEND_PROC_DATA_INTEGER,
+	  .data = {
+		  .integer = {
+			  .variable	= &image_size_limit,
+			  .minimum	= -2,
+			  .maximum	= 32767,
+		  }
+	  }
+	},
+
+	{ .filename			= "last_result",
+	  .permissions			= PROC_READONLY,
+	  .type				= SUSPEND_PROC_DATA_UL,
+	  .data = {
+		  .ul = {
+			  .variable	=  &suspend_result,
+		  }
+	  }
+	},
+	
+	{ .filename			= "reboot",
+	  .permissions			= PROC_RW,
+	  .type				= SUSPEND_PROC_DATA_BIT,
+	  .data = {
+		  .bit = {
+			  .bit_vector	= &suspend_action,
+			  .bit		= SUSPEND_REBOOT,
+		  }
+	  }
+	},
+	  
+	{ .filename			= "resume2",
+	  .permissions			= PROC_RW,
+	  .type				= SUSPEND_PROC_DATA_STRING,
+	  .needs_storage_manager	= 2,
+	  .data = {
+		  .string = {
+			  .variable	= resume2_file,
+			  .max_length	= 255,
+		  }
+	  },
+	  .write_proc			= attempt_to_parse_resume_device2,
+	},
+
+	{ .filename			= "resume_commandline",
+	  .permissions			= PROC_RW,
+	  .type				= SUSPEND_PROC_DATA_STRING,
+	  .data = {
+		  .string = {
+			  .variable	= resume_commandline,
+			  .max_length	= COMMAND_LINE_SIZE,
+		  }
+	  },
+	},
+
+
+	{ .filename			= "version",
+	  .permissions			= PROC_READONLY,
+	  .type				= SUSPEND_PROC_DATA_STRING,
+	  .data = {
+		  .string = {
+			  .variable	= suspend_core_version,
+		  }
+	  }
+	},
+
+#ifdef CONFIG_PM_DEBUG
+	{ .filename			= "freezer_test",
+	  .permissions			= PROC_RW,
+	  .type				= SUSPEND_PROC_DATA_BIT,
+	  .data = {
+		  .bit = {
+			  .bit_vector	= &suspend_action,
+			  .bit		= SUSPEND_FREEZER_TEST,
+		  }
+	  }
+	},
+
+	{ .filename			= "test_bio",
+	  .permissions			= PROC_RW,
+	  .type				= SUSPEND_PROC_DATA_BIT,
+	  .data = {
+		  .bit = {
+			  .bit_vector	= &suspend_action,
+			  .bit		= SUSPEND_TEST_BIO,
+		  }
+	  }
+	},
+
+	{ .filename			= "test_filter_speed",
+	  .permissions			= PROC_RW,
+	  .type				= SUSPEND_PROC_DATA_BIT,
+	  .data = {
+		  .bit = {
+			  .bit_vector	= &suspend_action,
+			  .bit		= SUSPEND_TEST_FILTER_SPEED,
+		  }
+	  }
+	},
+
+	{ .filename			= "slow",
+	  .permissions			= PROC_RW,
+	  .type				= SUSPEND_PROC_DATA_BIT,
+	  .data = {
+		  .bit = {
+			  .bit_vector	= &suspend_action,
+			  .bit		= SUSPEND_SLOW,
+		  }
+	  }
+	},
+	
+	{ .filename			= "no_pageset2",
+	  .permissions			= PROC_RW,
+	  .type				= SUSPEND_PROC_DATA_BIT,
+	  .data = {
+		  .bit = {
+			  .bit_vector	= &suspend_action,
+			  .bit		= SUSPEND_NO_PAGESET2,
+		  }
+	  }
+	},
+	
+#endif
+	  
+#if defined(CONFIG_ACPI)
+	{ .filename			= "powerdown_method",
+	  .permissions			= PROC_RW,
+	  .type				= SUSPEND_PROC_DATA_UL,
+	  .data = {
+		  .ul = {
+			  .variable	= &suspend2_powerdown_method,
+			  .minimum	= 0,
+			  .maximum	= 5,
+		  }
+	  }
+	},
+#endif
+
+#ifdef CONFIG_SUSPEND2_KEEP_IMAGE
+	{ .filename			= "keep_image",
+	  .permissions			= PROC_RW,
+	  .type				= SUSPEND_PROC_DATA_BIT,
+	  .data = {
+		  .bit = {
+			  .bit_vector	= &suspend_action,
+			  .bit		= SUSPEND_KEEP_IMAGE,
+		  }
+	  }
+	},
+#endif
+};
+
+
+/*
+ * Called from init kernel_thread.
+ * We check if we have an image and if so we try to resume.
+ * We also start ksuspendd if configuration looks right.
+ */
+
+int suspend2_resume(void)
+{
+	int read_image_result = 0;
+
+	if (sizeof(swp_entry_t) != sizeof(long)) {
+		printk(KERN_WARNING name_suspend
+			"The size of swp_entry_t != size of long. "
+			"Please report this!\n");
+		return 1;
+	}
+	
+	if (!resume2_file[0])
+		printk(KERN_WARNING name_suspend
+			"You need to use a resume2= command line parameter to "
+			"tell Suspend2 where to look for an image.\n");
+
+	suspend2_activate_storage(0);
+
+	if (!(test_suspend_state(SUSPEND_RESUME_DEVICE_OK)) &&
+		!attempt_to_parse_resume_device()) {
+		/* 
+		 * Without a usable storage device we can do nothing - 
+		 * even if noresume is given
+		 */
+
+		if (!num_writers)
+			printk(KERN_ALERT name_suspend
+				"No writers have been registered.\n");
+		else
+			printk(KERN_ALERT name_suspend
+				"Missing or invalid storage location "
+				"(resume2= parameter). Please correct and "
+				"rerun lilo (or equivalent) before "
+				"suspending.\n");
+		suspend2_deactivate_storage(0);
+		return 1;
+	}
+
+	suspend2_orig_mem_free = real_nr_free_pages();
+
+	read_image_result = read_pageset1(); /* non fatal error ignored */
+
+	if (test_suspend_state(SUSPEND_NORESUME_SPECIFIED))
+		printk(KERN_WARNING name_suspend "Resuming disabled as requested.\n");
+
+	suspend2_deactivate_storage(0);
+	
+	if (read_image_result)
+		return 1;
+
+	suspend_atomic_restore();
+
+	BUG();
+
+	return 0;
+}
+
+static __init int core_load(void)
+{
+	int i, numfiles = sizeof(proc_params) / sizeof(struct suspend_proc_data);
+
+	printk("Suspend2 Core.\n");
+	
+	suspend_initialise_plugin_lists();
+	
+	for (i=0; i< numfiles; i++)
+		suspend_register_procfile(&proc_params[i]);
+
+	return 0;
+}
+
+/* -- Functions for kickstarting a suspend or resume --- */
+
+/*
+ * Check if we have an image and if so try to resume.
+ */
+
+void __suspend2_try_resume(void)
+{
+	set_suspend_state(SUSPEND_TRYING_TO_RESUME);
+	
+	clear_suspend_state(SUSPEND_RESUME_NOT_DONE);
+
+	suspend2_resume();
+
+	clear_suspend_state(SUSPEND_IGNORE_LOGLEVEL);
+	clear_suspend_state(SUSPEND_TRYING_TO_RESUME);
+}
+
+/* Wrapper for when called from init/do_mounts.c */
+void suspend2_try_resume(void)
+{
+	if (suspend_start_anything(0))
+		return;
+
+	__suspend2_try_resume();
+
+	/* 
+	 * For initramfs, we have to clear the boot time
+	 * flag after trying to resume
+	 */
+	clear_suspend_state(SUSPEND_BOOT_TIME);
+
+	suspend_finish_anything(0);
+}
+
+/*
+ * suspend2_try_suspend
+ * Functionality   : Wrapper around suspend2_main.
+ * Called From     : drivers/acpi/sleep/main.c
+ *                   kernel/reboot.c
+ */
+
+void suspend2_try_suspend(void)
+{
+	if (suspend_start_anything(0))
+		return;
+
+	suspend2_main();
+
+	suspend_finish_anything(0);
+}
+
+/* --  Commandline Parameter Handling ---
+ *
+ * Resume setup: obtain the storage device.
+ */
+
+static int __init resume2_setup(char *str)
+{
+	if (!*str)
+		return 0;
+	
+	strncpy(resume2_file, str, 255);
+	return 0;
+}
+
+/*
+ * Allow the user to set the action parameter from lilo, prior to resuming.
+ */
+static int __init suspend_act_setup(char *str)
+{
+	if(str)
+		suspend_action=simple_strtol(str,NULL,0);
+	set_suspend_state(SUSPEND_ACT_USED);
+	return 0;
+}
+
+/*
+ * Allow the user to set the debug parameter from lilo, prior to resuming.
+ */
+/*
+ * Allow the user to specify that we should ignore any image found and
+ * invalidate the image if necesssary. This is equivalent to running
+ * the task queue and a sync and then turning off the power. The same
+ * precautions should be taken: fsck if you're not journalled.
+ */
+static int __init noresume2_setup(char *str)
+{
+	set_suspend_state(SUSPEND_NORESUME_SPECIFIED);
+	return 0;
+}
+
+static int __init suspend2_retry_resume_setup(char *str)
+{
+	set_suspend_state(SUSPEND_RETRY_RESUME);
+	return 0;
+}
+
+#ifdef CONFIG_PM_DEBUG
+
+static int __init suspend_dbg_setup(char *str)
+{
+	if(str)
+		suspend_debug_state=simple_strtol(str,NULL,0);
+	set_suspend_state(SUSPEND_DBG_USED);
+	return 0;
+}
+
+/*
+ * Allow the user to set the debug level parameter from lilo, prior to
+ * resuming.
+ */
+static int __init suspend_lvl_setup(char *str)
+{
+	if(str)
+		console_loglevel =
+		suspend_default_console_level = 
+			simple_strtol(str,NULL,0);
+	set_suspend_state(SUSPEND_LVL_USED);
+	clear_suspend_state(SUSPEND_IGNORE_LOGLEVEL);
+	return 0;
+}
+
+__setup("suspend_dbg=", suspend_dbg_setup);
+__setup("suspend_lvl=", suspend_lvl_setup);
+#endif
+
+__setup("noresume2", noresume2_setup);
+__setup("resume2=", resume2_setup);
+__setup("suspend_act=", suspend_act_setup);
+__setup("suspend_retry_resume", suspend2_retry_resume_setup);
+
+late_initcall(core_load);
+EXPORT_SYMBOL(software_suspend_state);
diff -urN oldtree/kernel/power/suspend.h newtree/kernel/power/suspend.h
--- oldtree/kernel/power/suspend.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/suspend.h	2006-01-28 17:08:36.243725760 +0000
@@ -0,0 +1,28 @@
+/*
+ * kernel/power/suspend.h
+ *
+ * Copyright (C) 2004-2005 Nigel Cunningham <nigel@suspend2.net>
+ *
+ * This file is released under the GPLv2.
+ *
+ * It contains declarations used throughout swsusp.
+ *
+ */
+
+#ifndef KERNEL_POWER_SUSPEND_H
+#define KERNEL_POWER_SUSPEND_H
+
+#define SUSPEND_PD_PAGES(x)     (((x)*sizeof(struct pbe))/PAGE_SIZE+1)
+   
+/* mm/page_alloc.c */
+extern void drain_local_pages(void);
+
+void save_processor_state(void);
+void restore_processor_state(void);
+struct saved_context;
+void __save_processor_state(struct saved_context *ctxt);
+void __restore_processor_state(struct saved_context *ctxt);
+
+extern suspend_pagedir_t *pagedir_nosave __nosavedata;
+
+#endif
diff -urN oldtree/kernel/power/suspend2.h newtree/kernel/power/suspend2.h
--- oldtree/kernel/power/suspend2.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/suspend2.h	2006-01-28 17:08:36.243725760 +0000
@@ -0,0 +1,31 @@
+/*
+ * kernel/power/suspend2.h
+ *
+ * Copyright (C) 2004-2005 Nigel Cunningham <nigel@suspend2.net>
+ *
+ * This file is released under the GPLv2.
+ *
+ * It contains declarations used throughout swsusp and suspend2.
+ *
+ */
+#ifndef KERNEL_POWER_SUSPEND_CORE_H
+#define KERNEL_POWER_SUSPEND_CORE_H
+
+#include <linux/delay.h>
+#include <linux/bootmem.h>
+
+extern unsigned long suspend2_orig_mem_free;
+
+#define KB(x) ((x) << (PAGE_SHIFT - 10))
+#define MB(x) ((x) >> (20 - PAGE_SHIFT))
+
+extern int suspend_start_anything(int starting_cycle);
+extern void suspend_finish_anything(int finishing_cycle);
+
+#if 1
+#define PRINTK(a...) do { } while(0)
+#else
+#define PRINTK(fmt, arg...) printk(KERN_DEBUG fmt, ##arg)
+#endif
+
+#endif
diff -urN oldtree/kernel/power/suspend2_common.h newtree/kernel/power/suspend2_common.h
--- oldtree/kernel/power/suspend2_common.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/suspend2_common.h	2006-01-28 17:08:36.243725760 +0000
@@ -0,0 +1,28 @@
+#ifdef CONFIG_PM_DEBUG
+#define set_debug_state(bit) (test_and_set_bit(bit, &suspend_debug_state))
+#define clear_debug_state(bit) (test_and_clear_bit(bit, &suspend_debug_state))
+#else
+#define set_debug_state(bit) (0)
+#define clear_debug_state(bit) (0)
+#endif
+
+#define set_result_state(bit) (test_and_set_bit(bit, &suspend_result))
+#define clear_result_state(bit) (test_and_clear_bit(bit, &suspend_result))
+
+enum {
+	SUSPEND_ABORT_REQUESTED = 1,
+	SUSPEND_NOSTORAGE_AVAILABLE,
+	SUSPEND_INSUFFICIENT_STORAGE,
+	SUSPEND_FREEZING_FAILED,
+	SUSPEND_UNEXPECTED_ALLOC,
+	SUSPEND_KEPT_IMAGE,
+	SUSPEND_WOULD_EAT_MEMORY,
+	SUSPEND_UNABLE_TO_FREE_ENOUGH_MEMORY,
+	SUSPEND_ENCRYPTION_SETUP_FAILED
+};
+
+extern int suspend_act_used;
+extern int suspend_lvl_used;
+extern int suspend_dbg_used;
+extern int suspend_default_console_level;
+extern unsigned int nr_suspends;
diff -urN oldtree/kernel/power/suspend_block_io.c newtree/kernel/power/suspend_block_io.c
--- oldtree/kernel/power/suspend_block_io.c	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/suspend_block_io.c	2006-01-28 17:08:36.245725456 +0000
@@ -0,0 +1,1066 @@
+/*
+ * block_io.c
+ *
+ * Copyright 2004-2005 Nigel Cunningham <nigel@suspend2.net>
+ *
+ * Distributed under GPLv2.
+ * 
+ * This file contains block io functions for suspend2. These are
+ * used by the swapwriter and it is planned that they will also
+ * be used by the NFSwriter.
+ *
+ */
+
+#include <linux/suspend.h>
+#include <linux/module.h>
+#include <linux/highmem.h>
+#include <linux/blkdev.h>
+#include <linux/bio.h>
+#include <linux/kthread.h>
+#include <linux/buffer_head.h>
+#include <linux/syscalls.h>
+#include <asm/types.h>
+
+#include "suspend2.h"
+#include "proc.h"
+#include "plugins.h"
+#include "prepare_image.h"
+#include "block_io.h"
+#include "extent.h"
+#include "suspend2_common.h"
+#include "ui.h"
+
+/* Bits in struct io_info->flags */
+enum {
+	IO_WRITING,
+	IO_RESTORE_PAGE_PROT,
+	IO_AWAITING_READ,
+	IO_AWAITING_WRITE,
+	IO_AWAITING_SUBMIT,
+	IO_AWAITING_CLEANUP,
+	IO_HANDLE_PAGE_PROT
+};
+
+#define MAX_OUTSTANDING_IO 2048
+
+/*
+ *
+ *     IO in progress information storage and helpers
+ *
+ */
+
+struct io_info {
+	struct bio *sys_struct;
+	sector_t block[MAX_BUF_PER_PAGE];
+	struct page *buffer_page;
+	struct page *data_page;
+	unsigned long flags;
+	struct block_device *dev;
+	struct list_head list;
+	int readahead_index;
+	struct work_struct work;
+	int printme;
+};
+
+/* Locks separated to allow better SMP support.
+ * An io_struct moves through the lists as follows.
+ * free -> submit_batch -> busy -> ready_for_cleanup -> free
+ */
+static LIST_HEAD(ioinfo_free);
+static DEFINE_SPINLOCK(ioinfo_free_lock);
+
+static LIST_HEAD(ioinfo_ready_for_cleanup);
+static DEFINE_SPINLOCK(ioinfo_ready_lock);
+
+static LIST_HEAD(ioinfo_submit_batch);
+static DEFINE_SPINLOCK(ioinfo_submit_lock);
+
+static LIST_HEAD(ioinfo_busy);
+static DEFINE_SPINLOCK(ioinfo_busy_lock);
+
+static atomic_t submit_batch;
+static int submit_batch_size = 64;
+static int submit_batched(void);
+
+struct task_struct *suspend_bio_task;
+
+/* [Max] number of I/O operations pending */
+static atomic_t outstanding_io;
+static int max_outstanding_io = 0;
+static atomic_t buffer_allocs, buffer_frees;
+
+/* [Max] number of pages used for above struct */
+static int infopages = 0;
+static int maxinfopages = 0;
+
+static volatile unsigned long suspend_readahead_flags[(MAX_OUTSTANDING_IO + BITS_PER_LONG - 1) / BITS_PER_LONG];
+static spinlock_t suspend_readahead_flags_lock = SPIN_LOCK_UNLOCKED;
+static struct page *suspend_readahead_pages[MAX_OUTSTANDING_IO];
+static int readahead_index, readahead_submit_index;
+
+static int current_stream;
+struct extent_iterate_saved_state suspend_writer_posn_save[3];
+
+/* Pointer to current entry being loaded/saved. */
+struct extent_iterate_state suspend_writer_posn;
+
+/* Not static, so that the allocators can setup and complete
+ * writing the header */
+char *suspend_writer_buffer;
+int suspend_writer_buffer_posn;
+
+int suspend_read_fd;
+
+static unsigned long nr_schedule_calls[8];
+
+static char *sch_caller[] = {
+	"get_io_info_struct #1    ",
+	"get_io_info_struct #2    ",
+	"get_io_info_struct #3    ",
+	"suspend_finish_all_io    ",
+	"wait_on_one_page         ",
+	"submit                   ",
+	"start_one                ",
+	"suspend_wait_on_readahead",
+};
+
+static struct suspend2_bdev_info *s2_devinfo;
+int need_extra_next;
+
+/*
+ * suspend_reset_io_stats
+ *
+ * Description:	Reset all our sanity-checking statistics.
+ */
+static void suspend_reset_io_stats(void)
+{
+	int i;
+	
+	max_outstanding_io = 0;
+	maxinfopages = 0;
+	
+	for (i = 0; i < 8; i++)
+		nr_schedule_calls[i] = 0;
+}
+
+/*
+ * suspend_check_io_stats
+ *
+ * Description:	Check that our statistics look right and print
+ * 		any debugging info wanted.
+ */
+static void suspend_check_io_stats(void)
+{
+	int i;
+
+	BUG_ON(atomic_read(&outstanding_io));
+	BUG_ON(infopages);
+	BUG_ON(!list_empty(&ioinfo_submit_batch));
+	BUG_ON(!list_empty(&ioinfo_busy));
+	BUG_ON(!list_empty(&ioinfo_ready_for_cleanup));
+	BUG_ON(!list_empty(&ioinfo_free));
+	BUG_ON(atomic_read(&buffer_allocs) != atomic_read(&buffer_frees));
+
+	suspend_message(SUSPEND_WRITER, SUSPEND_LOW, 0,
+			"Maximum outstanding_io was %d.\n",
+			max_outstanding_io);
+	suspend_message(SUSPEND_WRITER, SUSPEND_LOW, 0,
+			"Max info pages was %d.\n",
+			maxinfopages);
+	if (atomic_read(&buffer_allocs) != atomic_read(&buffer_frees))
+		suspend_message(SUSPEND_WRITER, SUSPEND_MEDIUM, 0,
+			"Buffer allocs (%d) != buffer frees (%d)",
+				atomic_read(&buffer_allocs),
+				atomic_read(&buffer_frees));
+	for(i = 0; i < 8; i++)
+		suspend_message(SUSPEND_WRITER, SUSPEND_MEDIUM, 0,
+			"Nr schedule calls %s: %lu.\n", sch_caller[i], nr_schedule_calls[i]);
+}
+
+/*
+ * cleanup_one
+ * 
+ * Description: Clean up after completing I/O on a page.
+ * Arguments:	struct io_info:	Data for I/O to be completed.
+ */
+static void __suspend_bio_cleanup_one(struct io_info *io_info)
+{
+	struct page *buffer_page;
+	struct page *data_page;
+	char *buffer_address, *data_address;
+	int reading;
+
+	buffer_page = io_info->buffer_page;
+	data_page = io_info->data_page;
+
+	reading = test_bit(IO_AWAITING_READ, &io_info->flags);
+	suspend_message(SUSPEND_WRITER, SUSPEND_HIGH, 0,
+		"Cleanup IO: [%p]\n", 
+		io_info);
+
+	if (reading && io_info->readahead_index == -1) {
+		/*
+		 * Copy the page we read into the buffer our caller provided.
+		 */
+		data_address = (char *) kmap(data_page);
+		buffer_address = (char *) kmap(buffer_page);
+		memcpy(data_address, buffer_address, PAGE_SIZE);
+		kunmap(data_page);
+		kunmap(buffer_page);
+	
+	}
+
+	if (!reading || io_info->readahead_index == -1) {
+		/* Sanity check */
+		if (page_count(buffer_page) != 2)
+			printk(KERN_EMERG "Cleanup IO: Page count on page %p is %d. Not good!\n",
+					buffer_page, page_count(buffer_page));
+		put_page(buffer_page);
+		__free_page(buffer_page);
+		atomic_inc(&buffer_frees);
+	} else
+		put_page(buffer_page);
+	
+	bio_put(io_info->sys_struct);
+	io_info->sys_struct = NULL;
+	io_info->flags = 0;
+}
+
+/* __suspend_io_cleanup
+ */
+
+static int suspend_bio_cleanup_one(void *data)
+{
+	struct io_info *io_info = (struct io_info *) data;
+	int readahead_index;
+	unsigned long flags;
+
+	/*
+	 * If this I/O was a readahead, remember its index.
+	 */
+	readahead_index = io_info->readahead_index;
+
+	/*
+	 * Add it to the free list.
+	 */
+	list_del_init(&io_info->list);
+	
+	/*
+	 * Do the cleanup.
+	 */
+	__suspend_bio_cleanup_one(io_info);
+
+	/*
+	 * Record the readahead as done.
+	 */
+	if (readahead_index > -1) {
+		int index = readahead_index/BITS_PER_LONG;
+		int bit = readahead_index - (index * BITS_PER_LONG);
+		spin_lock_irqsave(&suspend_readahead_flags_lock, flags);
+		set_bit(bit, &suspend_readahead_flags[index]);
+		spin_unlock_irqrestore(&suspend_readahead_flags_lock, flags);
+	}
+
+	spin_lock_irqsave(&ioinfo_free_lock, flags);
+	list_add_tail(&io_info->list, &ioinfo_free);
+	spin_unlock_irqrestore(&ioinfo_free_lock, flags);
+	
+	/* Important: Must be last thing we do to avoid a race with
+	 * finish_all_io when using keventd to do the cleanup */
+	atomic_dec(&outstanding_io);
+
+	return 0;
+}
+
+/* suspend_cleanup_some_completed_io
+ *
+ * NB: This is designed so that multiple callers can be in here simultaneously.
+ */
+
+static void suspend_cleanup_some_completed_io(void)
+{
+	int num_cleaned = 0;
+	struct io_info *first;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ioinfo_ready_lock, flags);
+	while(!list_empty(&ioinfo_ready_for_cleanup)) {
+		int result;
+		first = list_entry(ioinfo_ready_for_cleanup.next, struct io_info, list);
+
+		BUG_ON(!test_and_clear_bit(IO_AWAITING_CLEANUP, &first->flags));
+
+		list_del_init(&first->list);
+
+		spin_unlock_irqrestore(&ioinfo_ready_lock, flags);
+
+		result = suspend_bio_cleanup_one((void *) first);
+
+		spin_lock_irqsave(&ioinfo_ready_lock, flags);
+		if (result)
+			continue;
+		num_cleaned++;
+		if (num_cleaned == submit_batch_size)
+			break;
+	}
+	spin_unlock_irqrestore(&ioinfo_ready_lock, flags);
+}
+
+/* do_bio_wait
+ *
+ * Actions taken when we want some I/O to get run.
+ * 
+ * Submit any I/O that's batched up (if we're not already doing
+ * that, unplug queues, schedule and clean up whatever we can.
+ */
+static void do_bio_wait(int caller)
+{
+	int num_submitted = 0;
+
+	nr_schedule_calls[caller]++;
+	
+	/* Don't want to wait on I/O we haven't submitted! */
+	num_submitted = submit_batched();
+
+	kblockd_flush();
+	
+	io_schedule();
+
+	suspend_cleanup_some_completed_io();
+}
+
+/*
+ * suspend_finish_all_io
+ *
+ * Description:	Finishes all IO and frees all IO info struct pages.
+ */
+static void suspend_finish_all_io(void)
+{
+	struct io_info *this, *next = NULL;
+	unsigned long flags;
+
+	/* Wait for all I/O to complete. */
+	while (atomic_read(&outstanding_io))
+		do_bio_wait(2);
+
+	spin_lock_irqsave(&ioinfo_free_lock, flags);
+	
+	/* 
+	 * Two stages, to avoid using freed pages.
+	 *
+	 * First free all io_info structs on a page except the first.
+	 */
+	list_for_each_entry_safe(this, next, &ioinfo_free, list) {
+		if (((unsigned long) this) & ~PAGE_MASK)
+			list_del(&this->list);
+	}
+
+	/* 
+	 * Now we have only one reference to each page, and can safely
+	 * free pages, knowing we're not going to be trying to access the
+	 * same page after freeing it.
+	 */
+	list_for_each_entry_safe(this, next, &ioinfo_free, list) {
+		list_del(&this->list);
+		free_page((unsigned long) this);
+		infopages--;
+		suspend_message(SUSPEND_MEMORY, SUSPEND_VERBOSE, 0,
+				"[FreedIOPage %lx]", this);
+	}
+	
+	spin_unlock_irqrestore(&ioinfo_free_lock, flags);
+}
+
+/*
+ * wait_on_one_page
+ *
+ * Description:	Wait for a particular I/O to complete.
+ */
+static void wait_on_one_page(struct io_info *io_info)
+{
+	do { do_bio_wait(3); } while (io_info->flags);
+}
+
+/*
+ * wait_on_readahead
+ *
+ * Wait until a particular readahead is ready.
+ */
+static void suspend_wait_on_readahead(int readahead_index)
+{
+	int index = readahead_index / BITS_PER_LONG;
+	int bit = readahead_index - index * BITS_PER_LONG;
+
+	/* read_ahead_index is the one we want to return */
+	while (!test_bit(bit, &suspend_readahead_flags[index]))
+		do_bio_wait(6);
+}
+
+/*
+ * readahead_done
+ *
+ * Returns whether the readahead requested is ready.
+ */
+
+static int suspend_readahead_ready(int readahead_index)
+{
+	int index = readahead_index / BITS_PER_LONG;
+	int bit = readahead_index - (index * BITS_PER_LONG);
+
+	return test_bit(bit, &suspend_readahead_flags[index]);
+}
+
+/* suspend_readahead_prepare
+ * Set up for doing readahead on an image */
+static int suspend_prepare_readahead(int index)
+{
+	unsigned long new_page = get_zeroed_page(GFP_ATOMIC);
+
+	if(!new_page)
+		return -ENOMEM;
+
+	suspend_readahead_pages[index] = virt_to_page(new_page);
+	return 0;
+}
+
+/* suspend_readahead_cleanup
+ * Clean up structures used for readahead */
+static void suspend_cleanup_readahead(int page)
+{
+	__free_page(suspend_readahead_pages[page]);
+	suspend_readahead_pages[page] = 0;
+	return;
+}
+
+/*
+ * suspend_end_bio
+ *
+ * Description:	Function called by block driver from interrupt context when I/O
+ * 		is completed. This is the reason we use spinlocks in
+ * 		manipulating the io_info lists. 		
+ * 		Nearly the fs/buffer.c version, but we want to mark the page as 
+ * 		done in our own structures too.
+ */
+
+static int suspend_end_bio(struct bio *bio, unsigned int num, int err)
+{
+	struct io_info *io_info = bio->bi_private;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ioinfo_busy_lock, flags);
+	list_del_init(&io_info->list);
+	spin_unlock_irqrestore(&ioinfo_busy_lock, flags);
+
+	set_bit(IO_AWAITING_CLEANUP, &io_info->flags);
+		
+	spin_lock_irqsave(&ioinfo_ready_lock, flags);
+	list_add_tail(&io_info->list, &ioinfo_ready_for_cleanup);
+	spin_unlock_irqrestore(&ioinfo_ready_lock, flags);
+	return 0;
+}
+
+/**
+ *	submit - submit BIO request.
+ *	@rw:	READ or WRITE.
+ *	@io_info: IO info structure.
+ *
+ * 	Based on Patrick's pmdisk code from long ago:
+ *	"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 carry on."
+ *
+ *	With a twist, though - we handle block_size != PAGE_SIZE.
+ *	Caller has already checked that our page is not fragmented.
+ */
+
+static int submit(int rw, struct io_info *io_info)
+{
+	int error = 0;
+	struct bio *bio = NULL;
+	unsigned long flags;
+
+	while (!bio) {
+		bio = bio_alloc(GFP_ATOMIC,1);
+		if (!bio)
+			do_bio_wait(4);
+	}
+
+	bio->bi_bdev = io_info->dev;
+	bio->bi_sector = io_info->block[0];
+	bio->bi_private = io_info;
+	bio->bi_end_io = suspend_end_bio;
+	bio->bi_flags |= (1 << BIO_SUSPEND2);
+	io_info->sys_struct = bio;
+	if (io_info->printme)
+		PRINTK("%s dev %p block %ld => sector %ld\n",
+			rw ? "Write" : "Read",
+			bio->bi_bdev, io_info->block[0],
+			(unsigned long) bio->bi_sector);
+
+	if (bio_add_page(bio, io_info->buffer_page, PAGE_SIZE, 0) < PAGE_SIZE) {
+		printk("ERROR: adding page to bio at %lld\n",
+				(unsigned long long) io_info->block[0]);
+		bio_put(bio);
+		return -EFAULT;
+	}
+
+	if (rw == WRITE)
+		bio_set_pages_dirty(bio);
+
+	spin_lock_irqsave(&ioinfo_busy_lock, flags);
+	list_add_tail(&io_info->list, &ioinfo_busy);
+	spin_unlock_irqrestore(&ioinfo_busy_lock, flags);
+	
+	submit_bio(rw,bio);
+
+	return error;
+}
+
+/* 
+ * submit a batch. The submit function can wait on I/O, so we have
+ * simple locking to avoid infinite recursion.
+ */
+static int submit_batched(void)
+{
+	static int running_already = 0;
+	struct io_info *first;
+	unsigned long flags;
+	int num_submitted = 0;
+
+	running_already = 1;
+	spin_lock_irqsave(&ioinfo_submit_lock, flags);
+	while(!list_empty(&ioinfo_submit_batch)) {
+		first = list_entry(ioinfo_submit_batch.next, struct io_info, list);
+
+		BUG_ON(!test_and_clear_bit(IO_AWAITING_SUBMIT, &first->flags));
+
+		list_del_init(&first->list);
+
+		atomic_dec(&submit_batch);
+
+		spin_unlock_irqrestore(&ioinfo_submit_lock, flags);
+
+		if (test_bit(IO_AWAITING_READ, &first->flags))
+			submit(READ, first);
+		else
+			submit(WRITE, first);
+
+		spin_lock_irqsave(&ioinfo_submit_lock, flags);
+		
+		num_submitted++;
+		if (num_submitted == submit_batch_size)
+			break;
+	}
+	spin_unlock_irqrestore(&ioinfo_submit_lock, flags);
+	running_already = 0;
+
+	return num_submitted;
+}
+
+static void add_to_batch(struct io_info *io_info)
+{
+	unsigned long flags;
+	
+	set_bit(IO_AWAITING_SUBMIT, &io_info->flags);
+
+	/* Put our prepared I/O struct on the batch list. */
+	spin_lock_irqsave(&ioinfo_submit_lock, flags);
+	list_add_tail(&io_info->list, &ioinfo_submit_batch);
+	spin_unlock_irqrestore(&ioinfo_submit_lock, flags);
+
+	atomic_inc(&submit_batch);
+
+	if ((!suspend_bio_task) && (atomic_read(&submit_batch) >= submit_batch_size))
+		submit_batched();
+}
+
+/*
+ * get_io_info_struct
+ *
+ * Description:	Get an I/O struct.
+ * Returns:	Pointer to the struct prepared for use.
+ */
+static struct io_info *get_io_info_struct(void)
+{
+	unsigned long newpage = 0, flags;
+	struct io_info *this = NULL;
+	int remaining = 0;
+
+	do {
+		while (atomic_read(&outstanding_io) >= MAX_OUTSTANDING_IO)
+			do_bio_wait(0);
+
+		/* Can start a new I/O. Is there a free one? */
+		if (!list_empty(&ioinfo_free)) {
+			/* Yes. Grab it. */
+			spin_lock_irqsave(&ioinfo_free_lock, flags);
+			break;
+		}
+
+		/* No. Need to allocate a new page for I/O info structs. */
+		newpage = get_zeroed_page(GFP_ATOMIC);
+		if (!newpage) {
+			do_bio_wait(1);
+			continue;
+		}
+
+		suspend_message(SUSPEND_MEMORY, SUSPEND_VERBOSE, 0,
+				"[NewIOPage %lx]", newpage);
+		infopages++;
+		if (infopages > maxinfopages)
+			maxinfopages++;
+
+		/* Prepare the new page for use. */
+		this = (struct io_info *) newpage;
+		remaining = PAGE_SIZE;
+		spin_lock_irqsave(&ioinfo_free_lock, flags);
+		while (remaining >= (sizeof(struct io_info))) {
+			list_add_tail(&this->list, &ioinfo_free);
+			this = (struct io_info *) (((char *) this) + 
+					sizeof(struct io_info));
+			remaining -= sizeof(struct io_info);
+		}
+		break;
+	} while (1);
+
+	/*
+	 * We have an I/O info struct. Remove it from the free list.
+	 * It will be added to the submit or busy list later.
+	 */
+	this = list_entry(ioinfo_free.next, struct io_info, list);
+	list_del_init(&this->list);
+	spin_unlock_irqrestore(&ioinfo_free_lock, flags);
+	return this;
+}
+
+/*
+ * start_one
+ *
+ * Description:	Prepare and start a read or write operation.
+ * 		Note that we use our own buffer for reading or writing.
+ * 		This simplifies doing readahead and asynchronous writing.
+ * 		We can begin a read without knowing the location into which
+ * 		the data will eventually be placed, and the buffer passed
+ * 		for a write can be reused immediately (essential for the
+ * 		plugins system).
+ * 		Failure? What's that?
+ * Returns:	The io_info struct created.
+ */
+static struct io_info *start_one(int rw, struct submit_params *submit_info)
+{
+	struct io_info *io_info = get_io_info_struct();
+	unsigned long buffer_virt = 0;
+	char *to, *from;
+	struct page *buffer_page;
+
+	if (!io_info)
+		return NULL;
+
+	/* Get our local buffer */
+	suspend_message(SUSPEND_WRITER, SUSPEND_HIGH, 1,
+			"Start_IO: [%p]", io_info);
+	
+	/* Copy settings to the io_info struct */
+	io_info->data_page = submit_info->page;
+	io_info->readahead_index = submit_info->readahead_index;
+	io_info->printme = submit_info->printme;
+
+	if (io_info->readahead_index == -1) {
+		while (!(buffer_virt = get_zeroed_page(GFP_ATOMIC)))
+			do_bio_wait(5);
+
+		atomic_inc(&buffer_allocs);
+		suspend_message(SUSPEND_WRITER, SUSPEND_HIGH, 0,
+				"[ALLOC BUFFER]->%d",
+				real_nr_free_pages());
+		buffer_page = virt_to_page(buffer_virt);
+	
+		io_info->buffer_page = buffer_page;
+	} else {
+		unsigned long flags;
+		int index = io_info->readahead_index / BITS_PER_LONG;
+		int bit = io_info->readahead_index - index * BITS_PER_LONG;
+
+		spin_lock_irqsave(&suspend_readahead_flags_lock, flags);
+		clear_bit(bit, &suspend_readahead_flags[index]);
+		spin_unlock_irqrestore(&suspend_readahead_flags_lock, flags);
+
+		io_info->buffer_page = buffer_page = submit_info->page;
+	}
+
+	/* If writing, copy our data. The data is probably in
+	 * lowmem, but we cannot be certain. If there is no
+	 * compression/encryption, we might be passed the
+	 * actual source page's address. */
+	if (rw == WRITE) {
+		set_bit(IO_WRITING, &io_info->flags);
+
+		to = (char *) buffer_virt;
+		from = kmap_atomic(io_info->data_page, KM_USER1);
+		memcpy(to, from, PAGE_SIZE);
+		kunmap_atomic(from, KM_USER1);
+	}
+
+	/* Submit the page */
+	get_page(buffer_page);
+	
+	io_info->dev = submit_info->dev;
+	io_info->block[0] = submit_info->block[0];
+
+	if (rw == READ)
+		set_bit(IO_AWAITING_READ, &io_info->flags);
+	else
+		set_bit(IO_AWAITING_WRITE, &io_info->flags);
+
+	suspend_message(SUSPEND_WRITER, SUSPEND_HIGH, 1,
+			"-> (PRE BRW) %d\n",
+			real_nr_free_pages());
+
+	if (submit_batch_size > 1)
+		add_to_batch(io_info);
+	else
+	 	submit(rw, io_info);
+	
+	atomic_inc(&outstanding_io);
+	if (atomic_read(&outstanding_io) > max_outstanding_io)
+		max_outstanding_io++;
+	
+	return io_info;
+}
+
+static int suspend_do_io(int rw, 
+		struct submit_params *submit_info, int syncio)
+{
+	struct io_info *io_info;
+
+	if(!submit_info->dev) {
+		printk("Suspend do io called with null bdev.\n");
+		return 1;
+	}
+	
+	io_info = start_one(rw, submit_info);
+
+	if (!io_info)
+		return 1;
+	else if (syncio)
+		wait_on_one_page(io_info);
+
+	/* If we were the only one, clean everything up */
+	if (!atomic_read(&outstanding_io))
+		suspend_finish_all_io();
+	return 0;
+} 
+
+/* We used to use bread here, but it doesn't correctly handle
+ * blocksize != PAGE_SIZE. Now we create a submit_info to get the data we
+ * want and use our normal routines (synchronously).
+ */
+
+static int suspend_bdev_page_io(int rw, struct block_device *bdev, long pos,
+		struct page *page)
+{
+	struct submit_params submit_info;
+
+	if (!bdev) {
+		printk("Suspend_bdev_page_io got null device.\n");
+		return 0;
+	}
+
+	submit_info.page = page;
+	submit_info.dev = bdev;
+	submit_info.block[0] = pos;
+	submit_info.readahead_index = -1;
+	return suspend_do_io(rw, &submit_info, 1);
+}
+
+static unsigned long suspend_bio_memory_needed(void)
+{
+	/* We want to have at least enough memory so as to have
+	 * MAX_OUTSTANDING_IO transactions on the fly at once. If we 
+	 * can to more, fine. */
+	return (MAX_OUTSTANDING_IO * (PAGE_SIZE + sizeof(struct request) +
+				sizeof(struct bio) + sizeof(struct io_info)));
+}
+
+static void suspend_set_devinfo(struct suspend2_bdev_info *info)
+{
+	s2_devinfo = info;
+}
+
+static int forward_one_page(void)
+{
+	int i, j;
+
+	for (j = 0; j < need_extra_next + 1; j++) {
+		extent_state_next(&suspend_writer_posn);
+	
+		/* Have to go forward one to ensure we're on the right chain,
+		 * before we can know how many more blocks to skip.*/
+		for (i = 1; i < s2_devinfo[suspend_writer_posn.current_chain].blocks_per_page; i++)
+			extent_state_next(&suspend_writer_posn);
+
+		if (extent_state_eof(&suspend_writer_posn)) {
+			printk("Extent state eof.\n");
+			return -ENODATA;
+		}
+	}
+
+	need_extra_next = 0;
+
+	return 0;
+}
+
+static int suspend_rw_page(int rw, struct page *page,
+		int readahead_index, int sync)
+{
+	int i, current_chain;
+	struct submit_params submit_params;
+
+	if (test_action_state(SUSPEND_TEST_FILTER_SPEED))
+		return 0;
+		
+	submit_params.readahead_index = readahead_index;
+	submit_params.page = page;
+	
+	if (forward_one_page())
+		return -ENODATA;
+
+	current_chain = suspend_writer_posn.current_chain;
+	submit_params.dev = s2_devinfo[current_chain].bdev;
+	submit_params.block[0] = (suspend_writer_posn.current_offset -
+		       s2_devinfo[current_chain].blocks_per_page + 1) <<
+		s2_devinfo[current_chain].bmap_shift;
+
+	//printk("%s: %lx:%d.\n", rw ? "Write" : "Read", submit_params.dev->bd_dev, submit_params.block[0]);
+
+	i = suspend_do_io(rw, &submit_params, sync);
+
+	if (i)
+		return -EIO;
+
+	return 0;
+}
+
+static int suspend_bio_read_chunk(struct page *buffer_page, int sync)
+{
+	static int last_result;
+	unsigned long *virt;
+
+	if (sync == SUSPEND_ASYNC)
+		return suspend_rw_page(READ, buffer_page, -1, sync);
+
+	/* Start new readahead while we wait for our page */
+	if (readahead_index == -1) {
+		last_result = 0;
+		readahead_index = readahead_submit_index = 0;
+	}
+
+	/* Start a new readahead? */
+	if (last_result) {
+		/* We failed to submit a read, and have cleaned up
+		 * all the readahead previously submitted */
+		if (readahead_submit_index == readahead_index)
+			return -EPERM;
+		goto wait;
+	}
+	
+	do {
+		if (suspend_prepare_readahead(readahead_submit_index))
+			break;
+
+		last_result = suspend_rw_page(
+			READ,
+			suspend_readahead_pages[readahead_submit_index], 
+			readahead_submit_index, SUSPEND_ASYNC);
+		if (last_result) {
+			printk("Begin read chunk for page %d returned %d.\n",
+				readahead_submit_index, last_result);
+			suspend_cleanup_readahead(readahead_submit_index);
+			break;
+		}
+
+		readahead_submit_index++;
+
+		if (readahead_submit_index == MAX_OUTSTANDING_IO)
+			readahead_submit_index = 0;
+
+	} while((!last_result) && (readahead_submit_index != readahead_index) &&
+			(!suspend_readahead_ready(readahead_index)));
+
+wait:
+	suspend_wait_on_readahead(readahead_index);
+
+	virt = kmap_atomic(buffer_page, KM_USER1);
+	memcpy(virt, page_address(suspend_readahead_pages[readahead_index]),
+			PAGE_SIZE);
+	kunmap_atomic(virt, KM_USER1);
+
+	suspend_cleanup_readahead(readahead_index);
+
+	readahead_index++;
+	if (readahead_index == MAX_OUTSTANDING_IO)
+		readahead_index = 0;
+
+	return 0;
+}
+
+static int suspend_read_init(int stream_number)
+{
+	current_stream = stream_number;
+	extent_state_restore(&suspend_writer_posn,
+			&suspend_writer_posn_save[current_stream]);
+
+	BUG_ON(!suspend_writer_posn.current_extent);
+
+	suspend_reset_io_stats();
+
+	readahead_index = readahead_submit_index = -1;
+
+	return 0;
+}
+
+static int suspend_read_cleanup(void)
+{
+	suspend_finish_all_io();
+	while (readahead_index != readahead_submit_index) {
+		suspend_cleanup_readahead(readahead_index);
+		readahead_index++;
+		if (readahead_index == MAX_OUTSTANDING_IO)
+			readahead_index = 0;
+	}
+	suspend_check_io_stats();
+	return 0;
+}
+
+static int suspend_write_init(int stream_number)
+{
+	extent_state_restore(&suspend_writer_posn,
+			&suspend_writer_posn_save[stream_number]);
+	current_stream = stream_number;
+
+	BUG_ON(!suspend_writer_posn.current_extent);
+
+	suspend_reset_io_stats();
+
+	return 0;
+}
+
+static int suspend_write_cleanup(void)
+{
+	if (current_stream == 2)
+		extent_state_save(&suspend_writer_posn,
+				&suspend_writer_posn_save[1]);
+	
+	suspend_finish_all_io();
+	
+	suspend_check_io_stats();
+
+	return 0;
+}
+
+static int suspend_write_chunk(struct page *buffer_page)
+{
+	return suspend_rw_page(WRITE, buffer_page, -1, 0);
+}
+
+static int suspend_rw_header_chunk(int rw, char *buffer, int buffer_size)
+{
+	int bytes_left = buffer_size;
+	
+	/* Read a chunk of the header */
+	while (bytes_left) {
+		char *source_start = buffer + buffer_size - bytes_left;
+		char *dest_start = suspend_writer_buffer + suspend_writer_buffer_posn;
+		int capacity = PAGE_SIZE - suspend_writer_buffer_posn;
+		char *to = rw ? dest_start : source_start;
+		char *from = rw ? source_start : dest_start;
+
+		if (bytes_left <= capacity) {
+			memcpy(to, from, bytes_left);
+			suspend_writer_buffer_posn += bytes_left;
+			return rw ? 0 : buffer_size;
+		}
+
+		/* Next to read the next page */
+		memcpy(to, from, capacity);
+		bytes_left -= capacity;
+
+		if (rw == READ && test_suspend_state(SUSPEND_TRY_RESUME_RD))
+			sys_read(suspend_read_fd,
+				suspend_writer_buffer, BLOCK_SIZE);
+		else {
+			if (suspend_rw_page(rw,
+					virt_to_page(suspend_writer_buffer),
+					-1, !rw))
+				return -EIO;
+		}
+
+		suspend_writer_buffer_posn = 0;
+		check_shift_keys(0, NULL);
+	}
+
+	return rw ? 0 : buffer_size;
+}
+
+static int read_header_chunk(char *buffer, int buffer_size)
+{
+	return suspend_rw_header_chunk(READ, buffer, buffer_size);
+}
+
+static int write_header_chunk(char *buffer, int buffer_size)
+{
+	return suspend_rw_header_chunk(WRITE, buffer, buffer_size);
+}
+
+struct suspend_bio_ops suspend_bio_ops = {
+	.submit_io = suspend_do_io,
+	.bdev_page_io = suspend_bdev_page_io,
+	.rw_page = suspend_rw_page,
+	.wait_on_readahead = suspend_wait_on_readahead,
+	.check_io_stats = suspend_check_io_stats,
+	.reset_io_stats = suspend_reset_io_stats,
+	.finish_all_io = suspend_finish_all_io,
+	.prepare_readahead = suspend_prepare_readahead,
+	.cleanup_readahead = suspend_cleanup_readahead,
+	.readahead_pages = suspend_readahead_pages,
+	.readahead_ready = suspend_readahead_ready,
+	.need_extra_next = &need_extra_next,
+	.forward_one_page = forward_one_page,
+	.set_devinfo = suspend_set_devinfo,
+	.read_init = suspend_read_init,
+	.read_chunk = suspend_bio_read_chunk,
+	.read_cleanup = suspend_read_cleanup,
+	.write_init = suspend_write_init,
+	.write_chunk = suspend_write_chunk,
+	.write_cleanup = suspend_write_cleanup,
+	.read_header_chunk = read_header_chunk,
+	.write_header_chunk = write_header_chunk,
+};
+
+static struct suspend_plugin_ops suspend_blockwriter_ops = 
+{
+	.name					= "Block I/O",
+	.type					= MISC_PLUGIN,
+	.module					= THIS_MODULE,
+	.memory_needed				= suspend_bio_memory_needed,
+};
+
+static __init int suspend_block_io_load(void)
+{
+	return suspend_register_plugin(&suspend_blockwriter_ops);
+}
+
+#ifdef MODULE
+static __exit void suspend_block_io_unload(void)
+{
+	suspend_unregister_plugin(&suspend_blockwriter_ops);
+}
+
+module_init(suspend_block_io_load);
+module_exit(suspend_block_io_unload);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Nigel Cunningham");
+MODULE_DESCRIPTION("Suspend2 block io functions");
+#else
+late_initcall(suspend_block_io_load);
+#endif
diff -urN oldtree/kernel/power/suspend_checksums.c newtree/kernel/power/suspend_checksums.c
--- oldtree/kernel/power/suspend_checksums.c	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/suspend_checksums.c	2006-01-28 17:08:36.245725456 +0000
@@ -0,0 +1,509 @@
+#include <linux/suspend.h>
+#include <linux/highmem.h>
+#ifdef CONFIG_KDB
+#include <linux/kdb.h>
+#include <linux/kdbprivate.h>
+#endif
+#include <linux/module.h>
+
+#include "suspend.h"
+#include "plugins.h"
+#include "pageflags.h"
+#include "proc.h"
+#include "pagedir.h"
+#include "ui.h"
+
+#define CHECKSUMS_PER_PAGE ((PAGE_SIZE - sizeof(void *)) / sizeof(unsigned long))
+#define NEXT_CHECKSUM_PAGE(page) *((unsigned long *) (((char *) (page)) + PAGE_SIZE - sizeof(void *)))
+
+static int checksum_pages;
+static unsigned long *first_checksum_page, *last_checksum_page;
+static int num_reload_pages = 0;
+
+struct reload_data
+{
+	int pageset;
+	int pagenumber;
+	struct page *page_address;
+	char *base_version;
+	char *compared_version;
+	struct reload_data *next;
+};
+
+static struct reload_data *first_reload_data, *last_reload_data;
+
+unsigned long suspend_page_checksum(struct page *page)
+{
+	unsigned long *virt;
+	int i;
+	unsigned long value = 0;
+
+	virt = (unsigned long *) kmap_atomic(page, KM_USER0);
+	for (i = 0; i < (PAGE_SIZE / sizeof(unsigned long)); i++)
+		value += *(virt + i);
+	kunmap_atomic(virt, KM_USER0);
+	return value;
+}
+
+extern void get_first_pbe(struct pbe *pbe, struct pagedir *pagedir);
+extern void get_next_pbe(struct pbe *pbe);
+
+void __suspend_calculate_checksums(dyn_pageflags_t map, unsigned long **current_checksum_page,
+		int *page_index)
+{
+	int page_number;
+	
+	BITMAP_FOR_EACH_SET(map, page_number) {
+		*(*current_checksum_page + *page_index) =
+			suspend_page_checksum(pfn_to_page(page_number));
+		*page_index++;
+		if (*page_index == CHECKSUMS_PER_PAGE) {
+			*page_index = 0;
+			*current_checksum_page = (unsigned long *)
+				NEXT_CHECKSUM_PAGE(*current_checksum_page);
+		}
+	};
+}
+
+void suspend_calculate_checksums(void)
+{
+	int page_index = 0;
+	unsigned long *current_checksum_page = first_checksum_page;
+	
+	if (!first_checksum_page) {
+		suspend2_prepare_status(1, 0, "Unable to checksum at this point.");
+		return;
+	}
+
+	suspend2_prepare_status(1, 0, "Calculating checksums... ");
+
+	__suspend_calculate_checksums(pageset1_map, &current_checksum_page,
+			&page_index);
+	
+	__suspend_calculate_checksums(pageset2_map, &current_checksum_page,
+			&page_index);
+
+	suspend2_prepare_status(1, 0, "Checksums done.");
+}
+
+int __suspend_check_checksums(int whichpagedir, unsigned long **current_checksum_page,
+		int *page_index, struct reload_data **next_reload_data)
+{
+	int page_number, num_differences = 0;
+	unsigned long sum_now;
+	dyn_pageflags_t map;
+
+	if (whichpagedir == 1)
+		map = pageset1_map;
+	else
+		map = pageset2_map;
+
+	BITMAP_FOR_EACH_SET(map, page_number) {
+		/* Also ignore the page containing our variables */
+		if (!PageChecksumIgnore(pfn_to_page(page_number))) {
+			/* Also ignore the page containing our variables */
+			sum_now = suspend_page_checksum(pfn_to_page(page_number));
+			if (sum_now != *(*current_checksum_page + *page_index)) {
+				num_differences++;
+				if (next_reload_data) {
+					char *virt;
+					struct reload_data *this = *next_reload_data;
+					this->pageset = whichpagedir;
+					this->pagenumber = page_number;
+					this->page_address = pfn_to_page(page_number);
+					virt = kmap_atomic(pfn_to_page(page_number), KM_USER0);
+					memcpy(this->compared_version,
+						virt, PAGE_SIZE);
+					kunmap_atomic(virt, KM_USER0);
+					*next_reload_data = this->next;
+				}
+			}
+		}
+
+		*page_index++;
+		if (*page_index == CHECKSUMS_PER_PAGE) {
+			*page_index = 0;
+			*current_checksum_page = (unsigned long *) 
+				NEXT_CHECKSUM_PAGE(*current_checksum_page);
+		}
+	}
+
+	return num_differences;
+}
+
+void suspend_check_checksums(void)
+{
+	int page_index = 0, num_differences = 0;
+	unsigned long *current_checksum_page = first_checksum_page;
+	struct reload_data *next_reload_data = first_reload_data;
+
+	if (!first_checksum_page) {
+		suspend2_prepare_status(1, 0, "Unable to checksum at this point.");
+		return;
+	}
+
+	num_differences += __suspend_check_checksums(1, &current_checksum_page,
+			&page_index, &next_reload_data);
+
+	num_differences += __suspend_check_checksums(2, &current_checksum_page,
+			&page_index, &next_reload_data);
+}
+
+/*
+ * free_reload_data.
+ *
+ * Reload data begins on a page boundary.
+ */
+void suspend_free_reload_data(void)
+{
+	struct reload_data *this_data = first_reload_data;
+	struct reload_data *prev_reload_data = this_data;
+	
+	while (this_data) {
+		if (this_data->compared_version)
+		  free_pages((unsigned long) this_data->compared_version, 0);
+
+		if (this_data->base_version)
+			free_pages((unsigned long) this_data->base_version, 0);
+
+		this_data = this_data->next;
+
+		if (!(((unsigned long) this_data) & ~PAGE_MASK)) {
+			prev_reload_data->next = this_data;
+			prev_reload_data = this_data;
+		}
+	}
+
+	this_data = first_reload_data;
+	while (this_data) {
+		prev_reload_data = this_data;
+		this_data = this_data->next;
+		free_pages((unsigned long) prev_reload_data, 0);
+		num_reload_pages--;
+	}
+
+	first_reload_data = last_reload_data = NULL;
+
+}
+
+/* suspend_reread_pages()
+ *
+ * Description:	Reread pages from an image for diagnosing differences.
+ * Arguments:	page_list:	A list containing information on pages
+ *                              to be reloaded, sorted by pageset and
+ *                              page index.
+ * Returns:	Zero on success or -1 on failure.
+ */
+
+int suspend_reread_pages(struct reload_data *page_list)
+{
+	int result = 0, whichtoread, pageset_offset = -1;
+	long i = 0;
+	struct suspend_plugin_ops *this_filter, *first_filter = get_next_filter(NULL);
+	dyn_pageflags_t *pageflags = &pageset1_map;
+
+	if (!page_list)
+		return 0;
+
+	for (whichtoread = page_list->pageset; whichtoread <= 2; whichtoread++) {
+		struct pagedir *pagedir;
+
+		switch (whichtoread) {
+			case 1:
+				pagedir = &pagedir1;
+				break;
+			case 2:
+				pagedir = &pagedir2;
+				pageflags = &pageset2_map;
+				pageset_offset = -1;
+				i = -1;
+				break;
+			default:
+				goto out;
+		}
+
+		suspend_message(SUSPEND_IO, SUSPEND_LOW, 0,
+			"Reread pages from pagedir %d.\n", whichtoread);
+
+		/* Initialise page transformers */
+		list_for_each_entry(this_filter, &suspend_filters, ops.filter.filter_list) {
+			if (this_filter->disabled)
+				continue;
+			if (this_filter->read_init && 
+				this_filter->read_init(whichtoread)) {
+				abort_suspend("Failed to initialise a filter.");
+				return 1;
+			}
+		}
+
+		/* Initialise writer */
+		if (active_writer->read_init(whichtoread)) {
+			abort_suspend("Failed to initialise the writer."); 
+			result = 1;
+			goto reread_free_buffers;
+		}
+
+		/* Read the pages */
+		while(i <= page_list->pagenumber) {
+			/* Read */
+			result = first_filter->ops.filter.read_chunk(
+					virt_to_page(page_list->base_version),
+					SUSPEND_SYNC);
+
+			if (result) {
+				abort_suspend("Failed to read a chunk of the image.");
+				goto reread_free_buffers;
+			}
+
+			/* Interactivity*/
+			check_shift_keys(0, NULL);
+
+			/* Prepare next */
+			pageset_offset = get_next_bit_on(*pageflags, pageset_offset);
+
+			/* Got the one we're after? */
+			i++;
+
+			if (i == page_list->pagenumber)
+				page_list = page_list->next;
+
+			if (page_list->pageset != whichtoread)
+				break;
+		}
+		
+reread_free_buffers:
+
+		/* Cleanup reads from this pageset. */
+		list_for_each_entry(this_filter, &suspend_plugins, plugin_list) {
+			if (this_filter->disabled)
+				continue;
+			if (this_filter->read_cleanup &&
+				this_filter->read_cleanup()) {
+				abort_suspend("Failed to cleanup a filter.");
+				result = 1;
+			}
+		}
+
+		if (active_writer->read_cleanup()) {
+			abort_suspend("Failed to cleanup the writer.");
+			result = 1;
+		}
+	}
+out:
+	printk("\n");
+
+	return result;
+}
+void suspend_free_checksum_pages(void)
+{
+	unsigned long *next_checksum_page;
+
+	while(first_checksum_page) {
+		next_checksum_page =
+		  (unsigned long *) NEXT_CHECKSUM_PAGE(first_checksum_page);
+		free_pages((unsigned long) first_checksum_page, 0);
+		first_checksum_page = next_checksum_page;
+	}
+	last_checksum_page = NULL;
+	checksum_pages = 0;
+}
+
+#define PRINTABLE(a) (((a) < 32 || (a) > 122) ? '.' : (a))
+static void local_print_location(
+		unsigned char *real,
+		unsigned char *original,
+		unsigned char *resumetime)
+{
+	int i;
+
+	for (i = 0; i < 8; i++)
+		if (*(original + i) != *(resumetime + i))
+			break;
+	if (i == 8)
+		return;
+	
+	suspend_message(SUSPEND_INTEGRITY, SUSPEND_HIGH, 1, "%p", real);
+	if (PageChecksumIgnore(virt_to_page(real)))
+		suspend_message(SUSPEND_INTEGRITY, SUSPEND_HIGH, 1,
+			" [NoSave]");
+	if (PageSlab(virt_to_page(real)))
+		suspend_message(SUSPEND_INTEGRITY, SUSPEND_HIGH, 1,
+			" [Slab]");
+	suspend_message(SUSPEND_INTEGRITY, SUSPEND_HIGH, 1, "\n");
+
+#ifdef CONFIG_KDB
+	for (i = 0; i < 8; i++) {
+		static const char *last_sym = NULL;
+		if (*(original + i) != *(resumetime + i)) {
+			kdb_symtab_t symtab;
+
+			kdbnearsym((unsigned long) real + i,
+					&symtab);
+
+			if ((!symtab.sym_name) ||
+					(symtab.sym_name == last_sym))
+				continue;
+
+			last_sym = symtab.sym_name;
+
+			suspend_message(SUSPEND_INTEGRITY, SUSPEND_LOW, 1,
+				"%p = %s\n",
+				symtab.sym_start,
+				symtab.sym_name);
+		}
+	}
+#endif
+
+	for (i = 0; i < 8; i++)
+		suspend_message(SUSPEND_INTEGRITY, SUSPEND_HIGH, 1,
+			"%2x ", *(original + i));
+	suspend_message(SUSPEND_INTEGRITY, SUSPEND_HIGH, 1, "    ");
+	for (i = 0; i < 8; i++)
+		suspend_message(SUSPEND_INTEGRITY, SUSPEND_HIGH, 1,
+			"%c", PRINTABLE(*(original + i)));
+	suspend_message(SUSPEND_INTEGRITY, SUSPEND_HIGH, 1, "    ");
+	
+	for (i = 0; i < 8; i++)
+		suspend_message(SUSPEND_INTEGRITY, SUSPEND_HIGH, 1,
+			"%2x ", *(resumetime + i));
+	suspend_message(SUSPEND_INTEGRITY, SUSPEND_HIGH, 1, "    ");
+	for (i = 0; i < 8; i++)
+		suspend_message(SUSPEND_INTEGRITY, SUSPEND_HIGH, 1,
+			"%c", PRINTABLE(*(resumetime + i)));
+	suspend_message(SUSPEND_INTEGRITY, SUSPEND_HIGH, 1, "\n\n");
+}
+
+int suspend_allocate_reload_data(int pages)
+{
+	struct reload_data *this_data;
+	unsigned long data_start;
+	int i;
+
+	if (num_reload_pages >= pages)
+		return 0;
+
+	for (i = 1; i <= pages; i++) {
+		data_start = get_zeroed_page(GFP_ATOMIC);
+
+		if (!data_start)
+			return -ENOMEM;
+
+		SetPageChecksumIgnore(virt_to_page(data_start));
+		this_data = (struct reload_data *) data_start; 
+		num_reload_pages++;
+
+		while (data_start == 
+		  ((((unsigned long) (this_data + 1)) - 1) & PAGE_MASK)) {
+			struct page *page;
+			unsigned long virt;
+
+			virt = get_zeroed_page(GFP_ATOMIC);
+			if (!virt) {
+				printk("Couldn't get a page in which to store "
+					"a changed page.\n");
+				return -ENOMEM;
+			}
+			page = virt_to_page(virt);
+
+			this_data->compared_version = (char *) virt;
+			SetPageChecksumIgnore(page);
+			
+			virt = get_zeroed_page(GFP_ATOMIC);
+			if (!virt) {
+				printk("Couldn't get a page in which to store "
+					"a baseline page.\n");
+				return -ENOMEM;
+			}
+			page = virt_to_page(virt);
+
+			this_data->base_version = (char *) virt;
+			SetPageChecksumIgnore(page);
+
+			if (last_reload_data)
+				last_reload_data->next = this_data;
+			else
+				first_reload_data = this_data;
+			
+			last_reload_data = this_data;
+
+			this_data++;
+		}
+
+		check_shift_keys(0, NULL);
+	}
+
+	return 0;
+}
+
+void suspend_print_differences(void)
+{
+	struct reload_data *this_data = first_reload_data;
+	int i;
+
+	suspend_reread_pages(first_reload_data);
+	
+	while (this_data) {
+		if (this_data->pageset && 
+		    this_data->pagenumber) {
+			suspend_message(SUSPEND_INTEGRITY, SUSPEND_MEDIUM, 1,
+				"Pagedir %d. Page %d. Address %p."
+				" Base %p. Copy %p.\n",
+				this_data->pageset,
+				this_data->pagenumber,
+				page_address(this_data->page_address),
+				this_data->base_version,
+				this_data->compared_version);
+			for (i= 0; i < (PAGE_SIZE / 8); i++) {
+				local_print_location(
+					page_address(this_data->page_address) + i * 8,
+					this_data->base_version + i * 8,
+					this_data->compared_version + i * 8);
+				check_shift_keys(0, NULL);
+			}
+			check_shift_keys(1, NULL);
+		} else
+			return;
+		this_data = this_data->next;
+	}
+}
+
+int __suspend_allocate_checksum_pages(void)
+{
+	int pages_required =
+		(pagedir1.pageset_size + pagedir2.pageset_size) / CHECKSUMS_PER_PAGE;
+	unsigned long this_page;
+
+	while (checksum_pages <= pages_required) {
+		this_page = get_zeroed_page(GFP_ATOMIC);
+		if (!this_page)
+			return -ENOMEM;
+
+		if (!first_checksum_page)
+			first_checksum_page = 
+				(unsigned long *) this_page;
+		else
+			NEXT_CHECKSUM_PAGE(last_checksum_page) = this_page;
+		
+		last_checksum_page = (unsigned long *) this_page;
+		SetPageChecksumIgnore(virt_to_page(this_page));
+		checksum_pages++;
+	}
+
+	return suspend_allocate_reload_data(2);
+}
+
+int suspend_checksum_init(void)
+{
+	if (suspend_allocate_dyn_pageflags(&checksum_map))
+		return 1;
+	return 0;
+}
+
+
+void suspend_checksum_cleanup(void)
+{
+	suspend_free_reload_data();
+	suspend_free_checksum_pages();
+	
+	suspend_free_dyn_pageflags(&checksum_map);
+}
diff -urN oldtree/kernel/power/suspend_file.c newtree/kernel/power/suspend_file.c
--- oldtree/kernel/power/suspend_file.c	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/suspend_file.c	2006-01-28 17:08:36.247725152 +0000
@@ -0,0 +1,1069 @@
+/*
+ * Filewriter.c
+ *
+ * Copyright 2005 Nigel Cunningham <nigel@suspend2.net>
+ *
+ * Distributed under GPLv2.
+ * 
+ * This file encapsulates functions for usage of a simple file as a
+ * backing store. It is based upon the swapwriter, and shares the
+ * same basic working. Here, though, we have nothing to do with
+ * swapspace, and only one device to worry about.
+ *
+ * The user can just
+ *
+ * echo Suspend2 > /path/to/my_file
+ *
+ * and
+ *
+ * echo /path/to/my_file > /proc/software_suspend/filewriter_target
+ *
+ * then put what they find in /proc/software_suspend/resume2
+ * as their resume2= parameter in lilo.conf (and rerun lilo if using it).
+ *
+ * Having done this, they're ready to suspend and resume.
+ *
+ * TODO:
+ * - File resizing.
+ */
+
+#include <linux/suspend.h>
+#include <linux/module.h>
+#include <linux/blkdev.h>
+#include <linux/file.h>
+#include <linux/stat.h>
+#include <linux/mount.h>
+#include <linux/statfs.h>
+#include <linux/syscalls.h>
+#include <linux/namei.h>
+#include <linux/fs.h>
+
+#include "suspend2.h"
+#include "suspend2_common.h"
+#include "version.h"
+#include "proc.h"
+#include "plugins.h"
+#include "ui.h"
+#include "extent.h"
+#include "io.h"
+#include "storage.h"
+#include "block_io.h"
+
+static struct suspend_plugin_ops filewriterops;
+
+/* Details of our target.  */
+
+char filewriter_target[256];
+static struct inode *target_inode;
+static struct file *target_file;
+static struct block_device *target_bdev;
+static int used_devt = 0;
+static sector_t target_firstblock = 0;
+static int target_storage_available = 0;
+static int target_claim = 0;
+
+static char HaveImage[] = "HaveImage\n";
+static char NoImage[] =   "Suspend2\n";
+static const int resumed_before_byte = sizeof(HaveImage) + 1;
+#define sig_size resumed_before_byte
+
+extern dev_t ROOT_DEV;
+extern char *__initdata root_device_name;
+
+/* Header_pages must be big enough for signature */
+static int header_pages, main_pages;
+
+#define target_is_normal_file() (S_ISREG(target_inode->i_mode))
+
+static struct suspend2_bdev_info devinfo;
+
+static void set_devinfo(struct block_device *bdev, int target_blkbits)
+{
+	devinfo.bdev = bdev;
+	if (!target_blkbits) {
+		devinfo.bmap_shift = devinfo.blocks_per_page = 0;
+	} else {
+		devinfo.bmap_shift = target_blkbits - 9;
+		devinfo.blocks_per_page = (1 << (PAGE_SHIFT - target_blkbits));
+	}
+}
+
+/* Extent chain for blocks */
+static struct extent_chain block_chain;
+
+/* Signature operations */
+enum {
+	GET_IMAGE_EXISTS,
+	INVALIDATE,
+	MARK_RESUME_ATTEMPTED,
+};
+
+/* Helpers. */
+
+static int filewriter_storage_available(void)
+{
+	int result = 0;
+
+	if (!target_inode)
+		return 0;
+
+	switch (target_inode->i_mode & S_IFMT) {
+		case S_IFSOCK:
+		case S_IFCHR:
+		case S_IFIFO: /* Socket, Char, Fifo */
+			return -1;
+		case S_IFREG: /* Regular file: current size - holes + free space on part */
+			result = target_storage_available;
+			break;
+		case S_IFBLK: /* Block device */
+			if (target_bdev->bd_disk) {
+				if (target_bdev->bd_part)
+					result = (unsigned long)target_bdev->bd_part->nr_sects >> (PAGE_SHIFT - 9);
+				else
+					result = (unsigned long)target_bdev->bd_disk->capacity >> (PAGE_SHIFT - 9);
+			} else {
+				printk("bdev->bd_disk null.\n");
+				return 0;
+			}
+	}
+
+	return result;
+}
+
+static int has_contiguous_blocks(int page_num)
+{
+	int j;
+	sector_t last = 0;
+
+	for (j = 0; j < devinfo.blocks_per_page; j++) {
+		sector_t this = bmap(target_inode,
+				page_num * devinfo.blocks_per_page + j);
+
+		if (!this || (last && (last + 1) != this))
+			break;
+
+		last = this;
+	}
+			
+	return (j == devinfo.blocks_per_page);
+}
+
+/*
+ * Ramdisk access variables
+ */
+
+static int size_ignoring_sparseness(void)
+{
+	int mappable = 0, i;
+	
+	if (target_is_normal_file()) {
+		for (i = 0; i < (target_inode->i_size >> PAGE_SHIFT) ; i++)
+			if (has_contiguous_blocks(i))
+				mappable++;
+	
+		return mappable;
+	} else
+		return filewriter_storage_available();
+}
+
+static void get_main_pool_phys_params(void)
+{
+	int i;
+	
+	if (block_chain.first)
+		put_extent_chain(&block_chain);
+
+	if (target_is_normal_file()) {
+		int extent_min = -1, extent_max = -1;
+
+		for (i = 0;
+		     i < (target_inode->i_size >> PAGE_SHIFT);
+		     i++) {
+			sector_t new_sector;
+
+			if (!has_contiguous_blocks(i))
+				continue;
+
+			new_sector = bmap(target_inode,
+				(i * devinfo.blocks_per_page));
+
+			/* 
+			 * I'd love to be able to fill in holes and resize 
+			 * files, but not yet...
+			 */
+
+			if (new_sector == extent_max + 1)
+				extent_max+= devinfo.blocks_per_page;
+			else {
+				if (extent_min > -1) {
+					if (test_action_state(SUSPEND_TEST_BIO))
+						printk("Adding extent %d-%d.\n",
+							extent_min << devinfo.bmap_shift,
+						        ((extent_max + 1) << devinfo.bmap_shift) - 1);
+					append_extent_to_extent_chain(
+						&block_chain,
+						extent_min,
+						extent_max);
+				}
+				extent_min = new_sector;
+				extent_max = extent_min + devinfo.blocks_per_page - 1;
+			}
+		}
+		if (extent_min > -1) {
+			append_extent_to_extent_chain(&block_chain,
+				       extent_min, extent_max);
+			if (test_action_state(SUSPEND_TEST_BIO))
+				printk("Adding extent %d-%d.\n",
+					extent_min << devinfo.bmap_shift,
+					((extent_max + 1) << devinfo.bmap_shift) - 1);
+		}
+
+	} else
+		if (target_storage_available > 0) {
+			append_extent_to_extent_chain(&block_chain,
+			 0, 
+			 min(main_pages, target_storage_available) * devinfo.blocks_per_page - 1);
+		}
+}
+
+static void get_target_info(int get_size)
+{
+	if (!target_bdev || IS_ERR(target_bdev)) {
+		target_inode = NULL;
+		set_devinfo(NULL, 0);
+		target_storage_available = 0;
+	} else {
+		if (!target_inode)
+			target_inode = target_bdev->bd_inode;
+		set_devinfo(target_bdev, target_inode->i_blkbits);
+		if (get_size)
+			target_storage_available = size_ignoring_sparseness();
+	}	
+}
+
+static void filewriter_cleanup(int finishing_cycle)
+{
+	if (target_bdev) {
+		if (target_claim) {
+			bd_release(target_bdev);
+			target_claim = 0;
+		}
+
+		if (used_devt) {
+			blkdev_put(target_bdev);
+			used_devt = 0;
+		}
+		target_bdev = NULL;
+		get_target_info(0);
+	}
+
+	if (target_file > 0) {
+		filp_close(target_file, NULL);
+		target_file = NULL;
+	}
+}
+
+static void filewriter_get_target_info(char *target, int get_size,
+		int resume2)
+{
+	if (target_file)
+		filewriter_cleanup(0);
+
+	if (!target || !strlen(target))
+		return;
+
+	target_file = filp_open(target, O_RDWR, 0);
+
+	if (IS_ERR(target_file) || !target_file) {
+		dev_t resume_dev_t;
+
+		if (!resume2) {
+			printk("Open file %s returned %p.\n", target, target_file);
+			target_file = NULL;
+			return;
+		}
+
+		target_file = NULL;
+		resume_dev_t = name_to_dev_t(target);
+		if (!resume_dev_t) {
+			printk("Open file %s returned %p and name_to_devt failed.\n", target, target_file);
+			if (!resume_dev_t) {
+				struct kstat stat;
+				int error = vfs_stat(target, &stat);
+				if (error) {
+					printk("Stating the file also failed. Nothing more we can do.\n");
+					return;
+				}
+				resume_dev_t = stat.rdev;
+			}
+			return;
+		}
+	     	target_bdev = open_by_devnum(resume_dev_t, FMODE_READ);
+		if (IS_ERR(target_bdev)) {
+			printk("Got a dev_num (%lx) but failed to open it.\n",
+					(unsigned long) resume_dev_t);
+			return;
+		}
+		used_devt = 1;
+		target_inode = target_bdev->bd_inode;
+	} else
+		target_inode = target_file->f_mapping->host;
+
+	if (S_ISLNK(target_inode->i_mode) ||
+	    S_ISDIR(target_inode->i_mode) ||
+	    S_ISSOCK(target_inode->i_mode) ||
+	    S_ISFIFO(target_inode->i_mode)) {
+		printk("The filewriter works with regular files, character files and block devices.\n");
+		goto cleanup;
+	}
+
+	if (!used_devt) {
+		if (S_ISBLK(target_inode->i_mode)) {
+			target_bdev = I_BDEV(target_inode);
+			if (!bd_claim(target_bdev, &filewriterops))
+				target_claim = 1;
+		} else
+			target_bdev = target_inode->i_sb->s_bdev;
+	}
+
+	get_target_info(get_size);
+
+	if (!resume2)
+		target_firstblock = bmap(target_inode, 0) << devinfo.bmap_shift;
+	
+	return;
+cleanup:
+	target_inode = NULL;
+	if (target_file) {
+		filp_close(target_file, NULL);
+		target_file = NULL;
+	}
+	get_target_info(0);
+}
+
+int parse_signature(char *header)
+{
+	int have_image = !memcmp(HaveImage, header, sizeof(HaveImage) - 1);
+	int no_image_header = !memcmp(NoImage, header, sizeof(NoImage) - 1);
+
+	if (no_image_header)
+		return 0;
+
+	if (!have_image)
+		return -1;
+
+	if (header[resumed_before_byte] & 1)
+		set_suspend_state(SUSPEND_RESUMED_BEFORE);
+	else
+		clear_suspend_state(SUSPEND_RESUMED_BEFORE);
+
+	return 1;
+}
+
+/* prepare_signature */
+
+static int prepare_signature(char *current_header)
+{
+	/* 
+	 * Explicitly put the \0 that clears the 'tried to resume from
+	 * this image before' flag.
+	 */
+	strncpy(current_header, HaveImage, sizeof(HaveImage));
+	current_header[resumed_before_byte] = 0;
+	return 0;
+}
+
+static int filewriter_storage_allocated(void)
+{
+	int result;
+
+	if (!target_inode)
+		return 0;
+
+	if (target_is_normal_file()) {
+		result = (int) target_storage_available;
+	} else
+		result = header_pages + main_pages;
+
+	return result;
+}
+
+static int filewriter_release_storage(void)
+{
+	if ((test_action_state(SUSPEND_KEEP_IMAGE)) &&
+	     test_suspend_state(SUSPEND_NOW_RESUMING))
+		return 0;
+
+	put_extent_chain(&block_chain);
+
+	header_pages = main_pages = 0;
+	return 0;
+}
+
+static int filewriter_allocate_header_space(int space_requested)
+{
+	int i;
+
+	/* We only steal pages from the main pool. If it doesn't have any yet... */
+	
+	if (!block_chain.first)
+		return 0;
+
+	extent_state_goto_start(&suspend_writer_posn);
+	
+	for (i = 0; i < space_requested; i++) {
+		if (suspend_bio_ops.forward_one_page())
+			return -ENOSPC;
+	}
+
+	/* The end of header pages will be the start of pageset 2 */
+	extent_state_save(&suspend_writer_posn, &suspend_writer_posn_save[2]);
+	header_pages = space_requested;
+	return 0;
+}
+
+static int filewriter_allocate_storage(int space_requested)
+{
+	int result = 0, prev_header_pages;
+	/* FIXME This looks wrong */
+	int blocks_to_get = (space_requested << devinfo.bmap_shift) - block_chain.size;
+	
+	/* Only release_storage reduces the size */
+	if (blocks_to_get < 1)
+		return 0;
+
+	main_pages = space_requested;
+
+	get_main_pool_phys_params();
+
+	suspend_message(SUSPEND_WRITER, SUSPEND_MEDIUM, 0,
+		"Finished with block_chain.size == %d.\n",
+		block_chain.size);
+
+	if (block_chain.size < (header_pages + main_pages))
+		result = -ENOSPC;
+
+	prev_header_pages = header_pages;
+	header_pages = 0;
+	filewriter_allocate_header_space(prev_header_pages);
+	return result;
+}
+
+static int filewriter_write_header_init(void)
+{
+	char new_sig[sig_size];
+	
+	suspend_writer_buffer = (char *) get_zeroed_page(GFP_ATOMIC);
+	suspend_writer_buffer_posn = 0;
+
+	/* We change it once the whole header is written */
+	strcpy(new_sig, NoImage);
+	suspend_bio_ops.write_header_chunk(new_sig, sig_size);
+
+	extent_state_goto_start(&suspend_writer_posn);
+
+	/* Info needed to bootstrap goes at the start of the header.
+	 * First we save the basic info needed for reading, including the number
+	 * of header pages. Then we save the structs containing data needed
+	 * for reading the header pages back.
+	 * Note that even if header pages take more than one page, when we
+	 * read back the info, we will have restored the location of the
+	 * next header page by the time we go to use it.
+	 */
+	suspend_bio_ops.write_header_chunk((char *) &suspend_writer_posn_save, 
+			3 * sizeof(struct extent_iterate_saved_state));
+
+	serialise_extent_chain(&block_chain);
+	
+	return 0;
+}
+
+static int filewriter_write_header_cleanup(void)
+{
+	/* Write any unsaved data */
+	if (suspend_writer_buffer_posn) {
+		if (suspend_bio_ops.rw_page(WRITE,
+				virt_to_page(suspend_writer_buffer),
+				-1, 0))
+			return -EIO;
+	}
+
+	suspend_bio_ops.finish_all_io();
+
+	extent_state_goto_start(&suspend_writer_posn);
+	extent_state_next(&suspend_writer_posn);
+
+	/* Adjust image header */
+	suspend_bio_ops.bdev_page_io(READ, target_bdev,
+			target_firstblock,
+			virt_to_page(suspend_writer_buffer));
+
+	prepare_signature(suspend_writer_buffer);
+		
+	suspend_bio_ops.bdev_page_io(WRITE, target_bdev,
+			target_firstblock,
+			virt_to_page(suspend_writer_buffer));
+
+	free_page((unsigned long) suspend_writer_buffer);
+	suspend_writer_buffer = NULL;
+	
+	suspend_bio_ops.finish_all_io();
+
+	return 0;
+}
+
+/* HEADER READING */
+
+#ifdef CONFIG_DEVFS_FS
+int  create_dev(char *name, dev_t dev, char *devfs_name);
+#else
+static int create_dev(char *name, dev_t dev, char *devfs_name)
+{
+	sys_unlink(name);
+	return sys_mknod(name, S_IFBLK|0600, new_encode_dev(dev));
+}
+#endif
+
+static int rd_init(void)
+{
+	suspend_writer_buffer_posn = 0;
+
+	create_dev("/dev/root", ROOT_DEV, root_device_name);
+	create_dev("/dev/ram", MKDEV(RAMDISK_MAJOR, 0), NULL);
+
+	suspend_read_fd = sys_open("/dev/root", O_RDONLY, 0);
+	if (suspend_read_fd < 0)
+		goto out;
+	
+	sys_read(suspend_read_fd, suspend_writer_buffer, BLOCK_SIZE);
+
+	memcpy(&suspend_writer_posn_save,
+		suspend_writer_buffer + suspend_writer_buffer_posn,
+		sizeof(suspend_writer_posn_save));
+	
+	suspend_writer_buffer_posn += sizeof(suspend_writer_posn_save);
+
+	return 0;
+out:
+	sys_unlink("/dev/ram");
+	sys_unlink("/dev/root");
+	return -EIO;
+}
+
+static int file_init(void)
+{
+	suspend_writer_buffer_posn = sig_size;
+
+	/* Read filewriter configuration */
+	suspend_bio_ops.bdev_page_io(READ, target_bdev,
+			target_firstblock,
+			virt_to_page((unsigned long) suspend_writer_buffer));
+	
+	return 0;
+}
+
+/*
+ * read_header_init()
+ * 
+ * Ramdisk support based heavily on init/do_mounts_rd.c
+ *
+ * Description:
+ * 1. Attempt to read the device specified with resume2=.
+ * 2. Check the contents of the header for our signature.
+ * 3. Warn, ignore, reset and/or continue as appropriate.
+ * 4. If continuing, read the filewriter configuration section
+ *    of the header and set up block device info so we can read
+ *    the rest of the header & image.
+ *
+ * Returns:
+ * May not return if user choose to reboot at a warning.
+ * -EINVAL if cannot resume at this time. Booting should continue
+ * normally.
+ */
+
+static int filewriter_read_header_init(void)
+{
+	int result;
+
+	*(suspend_bio_ops.need_extra_next) = 1;
+
+	suspend_writer_buffer = (char *) get_zeroed_page(GFP_ATOMIC);
+	
+	if (test_suspend_state(SUSPEND_TRY_RESUME_RD))
+		result = rd_init();
+	else
+		result = file_init();
+	
+	if (result)
+		return result;
+
+	suspend_writer_buffer_posn = sig_size;
+	memcpy(&suspend_writer_posn_save,
+			suspend_writer_buffer + suspend_writer_buffer_posn,
+			3 * sizeof(struct extent_iterate_saved_state));
+	
+	suspend_writer_buffer_posn += 3 * sizeof(struct extent_iterate_saved_state);
+
+	extent_state_goto_start(&suspend_writer_posn);
+	load_extent_chain(&block_chain);
+
+	return 0;
+}
+
+static int filewriter_read_header_cleanup(void)
+{
+	free_page((unsigned long) suspend_writer_buffer);
+	suspend_writer_buffer = NULL;
+	return 0;
+}
+
+static int filewriter_signature_op(int op)
+{
+	char *cur;
+	int result = 0, changed = 0;
+	
+	if(target_bdev <= 0)
+		return -1;
+
+	cur = (char *) get_zeroed_page(GFP_ATOMIC);
+	if (!cur) {
+		printk("Unable to allocate a page for reading the image signature.\n");
+		return -ENOMEM;
+	}
+
+	suspend_bio_ops.bdev_page_io(READ, target_bdev,
+			target_firstblock,
+			virt_to_page(cur));
+
+	result = parse_signature(cur);
+		
+	switch (op) {
+		case INVALIDATE:
+			if (result == -1)
+				goto out;
+
+			strcpy(cur, NoImage);
+			cur[resumed_before_byte] = 0;
+			result = changed = 1;
+			break;
+		case MARK_RESUME_ATTEMPTED:
+			if (result == 1) {
+				cur[resumed_before_byte] |= 1;
+				changed = 1;
+			}
+			break;
+	}
+
+	if (changed)
+		suspend_bio_ops.bdev_page_io(WRITE, target_bdev,
+				target_firstblock,
+				virt_to_page(cur));
+
+out:
+	suspend_bio_ops.finish_all_io();
+	free_page((unsigned long) cur);
+	return result;
+}
+
+/*
+ * workspace_size
+ *
+ * Description:
+ * Returns the number of bytes of RAM needed for this
+ * code to do its work. (Used when calculating whether
+ * we have enough memory to be able to suspend & resume).
+ *
+ */
+static unsigned long filewriter_memory_needed(void)
+{
+	return 0;
+}
+
+/* Print debug info
+ *
+ * Description:
+ */
+
+static int filewriter_print_debug_stats(char *buffer, int size)
+{
+	int len = 0;
+	
+	if (active_writer != &filewriterops) {
+		len = snprintf_used(buffer, size, "- Filewriter inactive.\n");
+		return len;
+	}
+
+	len = snprintf_used(buffer, size, "- Filewriter active.\n");
+
+	len+= snprintf_used(buffer+len, size-len, "  Storage available for image: %ld pages.\n",
+			filewriter_storage_allocated());
+
+	return len;
+}
+
+/*
+ * Storage needed
+ *
+ * Returns amount of space in the image header required
+ * for the filewriter's data.
+ *
+ * We ensure the space is allocated, but actually save the
+ * data from write_header_init and therefore don't also define a
+ * save_config_info routine.
+ */
+static unsigned long filewriter_storage_needed(void)
+{
+	return strlen(filewriter_target) + 1;
+}
+
+/* 
+ * filewriter_invalidate_image
+ * 
+ */
+static int filewriter_invalidate_image(void)
+{
+	int result;
+
+	if (nr_suspends > 0)
+		filewriter_release_storage();
+
+	result = filewriter_signature_op(INVALIDATE);
+	if (result == 1 && !nr_suspends)
+		printk(KERN_WARNING name_suspend "Image invalidated.\n");
+
+	return result;
+}
+
+/*
+ * Image_exists
+ *
+ */
+
+static int filewriter_image_exists(void)
+{
+	return filewriter_signature_op(GET_IMAGE_EXISTS);
+}
+
+/*
+ * Mark resume attempted.
+ *
+ * Record that we tried to resume from this image.
+ */
+
+static void filewriter_mark_resume_attempted(void)
+{
+	filewriter_signature_op(MARK_RESUME_ATTEMPTED);
+}
+
+static void filewriter_set_resume2(void)
+{
+	char *buffer = (char *) get_zeroed_page(GFP_ATOMIC);
+	char *buffer2 = (char *) get_zeroed_page(GFP_ATOMIC);
+	unsigned long sector = bmap(target_inode, 0);
+	int offset = 0;
+
+	if (target_bdev) {
+		set_devinfo(target_bdev, target_inode->i_blkbits);
+
+		bdevname(target_bdev, buffer2);
+		offset += snprintf(buffer + offset, PAGE_SIZE - offset, 
+				"/dev/%s", buffer2);
+		
+		if (sector)
+			offset += snprintf(buffer + offset, PAGE_SIZE - offset,
+				":0x%lx", sector << devinfo.bmap_shift);
+	} else
+		offset += snprintf(buffer + offset, PAGE_SIZE - offset,
+				"%s is not a valid target.", filewriter_target);
+			
+	sprintf(resume2_file, "file:%s", buffer);
+
+	free_page((unsigned long) buffer);
+	free_page((unsigned long) buffer2);
+
+	attempt_to_parse_resume_device();
+}
+
+static int __test_filewriter_target(char *target, int resume_time)
+{
+	filewriter_get_target_info(filewriter_target, 0, 0);
+	if (filewriter_signature_op(GET_IMAGE_EXISTS) > -1) {
+		printk(name_suspend "Filewriter: File signature found.\n");
+		if (!resume_time)
+			filewriter_set_resume2();
+		
+		suspend_bio_ops.set_devinfo(&devinfo);
+		suspend_writer_posn.chains = &block_chain;
+		suspend_writer_posn.num_chains = 1;
+
+		return 0;
+	}
+
+	if (*filewriter_target)
+		printk(KERN_ERR name_suspend
+			"Filewriter: Sorry. No signature found at %s.\n",
+			filewriter_target);
+	else
+		printk(KERN_ERR name_suspend
+			"Filewriter: Sorry. No signature found.\n");
+
+	return 1;
+}
+
+static void test_filewriter_target(void)
+{
+	__test_filewriter_target(filewriter_target, 0);
+}
+
+/*
+ * Parse Image Location
+ *
+ * Attempt to parse a resume2= parameter.
+ * Swap Writer accepts:
+ * resume2=file:DEVNAME[:FIRSTBLOCK]
+ *
+ * Where:
+ * DEVNAME is convertable to a dev_t by name_to_dev_t
+ * FIRSTBLOCK is the location of the first block in the file.
+ * BLOCKSIZE is the logical blocksize >= SECTOR_SIZE & <= PAGE_SIZE, 
+ * mod SECTOR_SIZE == 0 of the device.
+ * Data is validated by attempting to read a header from the
+ * location given. Failure will result in filewriter refusing to
+ * save an image, and a reboot with correct parameters will be
+ * necessary.
+ */
+
+static int filewriter_parse_sig_location(char *commandline, int only_writer)
+{
+	char *thischar, *devstart = NULL, *colon = NULL, *at_symbol = NULL;
+	int result = -EINVAL, target_blocksize = 0;
+
+	if (strncmp(commandline, "file:", 5)) {
+		if (!only_writer)
+			return 1;
+	} else
+		commandline += 5;
+
+	/* 
+	 * Don't check signature again if we're beginning a cycle. If we already
+	 * did the initialisation successfully, assume we'll be okay when it comes
+	 * to resuming.
+	 */
+	if (target_bdev)
+		return 0;
+	
+	devstart = thischar = commandline;
+	while ((*thischar != ':') && (*thischar != '@') &&
+		((thischar - commandline) < 250) && (*thischar))
+		thischar++;
+
+	if (*thischar == ':') {
+		colon = thischar;
+		*colon = 0;
+		thischar++;
+	}
+
+	while ((*thischar != '@') && ((thischar - commandline) < 250) && (*thischar))
+		thischar++;
+
+	if (*thischar == '@') {
+		at_symbol = thischar;
+		*at_symbol = 0;
+	}
+	
+	if (colon)
+		target_firstblock = (int) simple_strtoul(colon + 1, NULL, 0);
+	else
+		target_firstblock = 0;
+
+	if (at_symbol) {
+		target_blocksize = (int) simple_strtoul(at_symbol + 1, NULL, 0);
+		if (target_blocksize & (SECTOR_SIZE - 1)) {
+			printk("Filewriter: Blocksizes are multiples of %d.\n", SECTOR_SIZE);
+			result = -EINVAL;
+			goto out;
+		}
+	}
+	
+	filewriter_get_target_info(commandline, 0, 1);
+
+	if (!target_bdev || IS_ERR(target_bdev)) {
+		target_bdev = NULL;
+		result = -1;
+		goto out;
+	}
+
+	if (target_blocksize)
+		set_devinfo(target_bdev, generic_ffs(target_blocksize));
+
+	result = __test_filewriter_target(commandline, 1);
+
+out:
+	if (colon)
+		*colon = ':';
+	if (at_symbol)
+		*at_symbol = '@';
+
+	return result;
+}
+
+/* filewriter_save_config_info
+ *
+ * Description:	Save the target's name, not for resume time, but for all_settings.
+ * Arguments:	Buffer:		Pointer to a buffer of size PAGE_SIZE.
+ * Returns:	Number of bytes used for saving our data.
+ */
+
+static int filewriter_save_config_info(char *buffer)
+{
+	strcpy(buffer, filewriter_target);
+	return strlen(filewriter_target) + 1;
+}
+
+/* filewriter_load_config_info
+ *
+ * Description:	Reload target's name.
+ * Arguments:	Buffer:		Pointer to the start of the data.
+ *		Size:		Number of bytes that were saved.
+ */
+
+static void filewriter_load_config_info(char *buffer, int size)
+{
+	strcpy(filewriter_target, buffer);
+}
+
+static int filewriter_initialise(int starting_cycle)
+{
+	int result = 0;
+
+	if (starting_cycle) {
+	       if (active_writer != &filewriterops)
+			return 0;
+
+		if (!*filewriter_target) {
+			printk("Filewriter is the active writer,  but no filename has been set.\n");
+			return 1;
+		}
+	}
+
+	if (filewriter_target)
+		filewriter_get_target_info(filewriter_target, starting_cycle, 0);
+
+	if (starting_cycle && (filewriter_image_exists() == -1)) {
+		printk("%s is does not have a valid signature for suspending.\n",
+				filewriter_target);
+		result = 1;
+	}
+
+	return result;
+}
+
+static struct suspend_proc_data filewriter_proc_data[] = {
+
+	{
+	 .filename			= "filewriter_target",
+	 .permissions			= PROC_RW,
+	 .type				= SUSPEND_PROC_DATA_STRING,
+	 .needs_storage_manager		= 2,
+	 .data = {
+		 .string = {
+			 .variable	= filewriter_target,
+			 .max_length	= 256,
+		 }
+	 },
+	 .write_proc			= test_filewriter_target,
+	},
+
+	{ .filename			= "disable_filewriter",
+	  .permissions			= PROC_RW,
+	  .type				= SUSPEND_PROC_DATA_INTEGER,
+	  .data = {
+		.integer = {
+			.variable	= &filewriterops.disabled,
+			.minimum	= 0,
+			.maximum	= 1,
+		}
+	  },
+	  .write_proc			= attempt_to_parse_resume_device2,
+	}
+};
+
+static struct suspend_plugin_ops filewriterops = {
+	.type					= WRITER_PLUGIN,
+	.name					= "File Writer",
+	.module					= THIS_MODULE,
+	.memory_needed				= filewriter_memory_needed,
+	.print_debug_info			= filewriter_print_debug_stats,
+	.save_config_info			= filewriter_save_config_info,
+	.load_config_info			= filewriter_load_config_info,
+	.storage_needed				= filewriter_storage_needed,
+	.initialise				= filewriter_initialise,
+	.cleanup				= filewriter_cleanup,
+
+	.ops = {
+		.writer = {
+		 .storage_available 	= filewriter_storage_available,
+		 .storage_allocated	= filewriter_storage_allocated,
+		 .release_storage	= filewriter_release_storage,
+		 .allocate_header_space	= filewriter_allocate_header_space,
+		 .allocate_storage	= filewriter_allocate_storage,
+		 .image_exists		= filewriter_image_exists,
+		 .mark_resume_attempted	= filewriter_mark_resume_attempted,
+		 .write_header_init	= filewriter_write_header_init,
+		 .write_header_cleanup	= filewriter_write_header_cleanup,
+		 .read_header_init	= filewriter_read_header_init,
+		 .read_header_cleanup	= filewriter_read_header_cleanup,
+		 .invalidate_image	= filewriter_invalidate_image,
+		 .parse_sig_location	= filewriter_parse_sig_location,
+		}
+	}
+};
+
+/* ---- Registration ---- */
+static __init int filewriter_load(void)
+{
+	int result;
+	int i, numfiles = sizeof(filewriter_proc_data) / sizeof(struct suspend_proc_data);
+	
+	printk("Suspend2 FileWriter loading.\n");
+
+	filewriterops.read_init = suspend_bio_ops.read_init;
+	filewriterops.ops.writer.read_chunk = suspend_bio_ops.read_chunk;
+	filewriterops.read_cleanup = suspend_bio_ops.read_cleanup;
+	filewriterops.write_init = suspend_bio_ops.write_init;
+	filewriterops.ops.writer.write_chunk = suspend_bio_ops.write_chunk;
+	filewriterops.write_cleanup = suspend_bio_ops.write_cleanup;
+	filewriterops.ops.writer.read_header_chunk =
+		suspend_bio_ops.read_header_chunk;
+	filewriterops.ops.writer.write_header_chunk =
+		suspend_bio_ops.write_header_chunk;
+
+	if (!(result = suspend_register_plugin(&filewriterops))) {
+		for (i=0; i< numfiles; i++)
+			suspend_register_procfile(&filewriter_proc_data[i]);
+	} else
+		printk("Suspend2 FileWriter unable to register!\n");
+
+	return result;
+}
+
+#ifdef MODULE
+static __exit void filewriter_unload(void)
+{
+	int i, numfiles = sizeof(filewriter_proc_data) / sizeof(struct suspend_proc_data);
+
+	printk("Suspend2 FileWriter unloading.\n");
+
+	for (i=0; i< numfiles; i++)
+		suspend_unregister_procfile(&filewriter_proc_data[i]);
+	suspend_unregister_plugin(&filewriterops);
+}
+
+module_init(filewriter_load);
+module_exit(filewriter_unload);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Nigel Cunningham");
+MODULE_DESCRIPTION("Suspend2 filewriter");
+#else
+late_initcall(filewriter_load);
+#endif
diff -urN oldtree/kernel/power/suspend_swap.c newtree/kernel/power/suspend_swap.c
--- oldtree/kernel/power/suspend_swap.c	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/suspend_swap.c	2006-01-28 17:08:36.249724848 +0000
@@ -0,0 +1,1238 @@
+/*
+ * Swapwriter.c
+ *
+ * Copyright 2004-2005 Nigel Cunningham <nigel@suspend2.net>
+ *
+ * Distributed under GPLv2.
+ * 
+ * This file encapsulates functions for usage of swap space as a
+ * backing store.
+ */
+
+#include <linux/suspend.h>
+#include <linux/module.h>
+#include <linux/blkdev.h>
+#include <linux/swapops.h>
+#include <linux/swap.h>
+
+#include "suspend2.h"
+#include "suspend2_common.h"
+#include "version.h"
+#include "proc.h"
+#include "plugins.h"
+#include "io.h"
+#include "ui.h"
+#include "extent.h"
+#include "block_io.h"
+
+static struct suspend_plugin_ops swapwriterops;
+
+#define SIGNATURE_VER 6
+
+/* --- Struct of pages stored on disk */
+
+union diskpage {
+	union swap_header swh;	/* swh.magic is the only member used */
+};
+
+union p_diskpage {
+	union diskpage *pointer;
+	char *ptr;
+        unsigned long address;
+};
+
+/* Devices used for swap */
+static struct suspend2_bdev_info devinfo[MAX_SWAPFILES];
+
+/* Extent chains for swap & blocks */
+struct extent_chain swapextents;
+struct extent_chain block_chain[MAX_SWAPFILES];
+
+static dev_t header_dev_t;
+static struct block_device *header_block_device;
+static unsigned long headerblock;
+
+/* For swapfile automatically swapon/off'd. */
+static char swapfilename[SWAP_FILENAME_MAXLENGTH] = "";
+extern asmlinkage long sys_swapon(const char *specialfile, int swap_flags);
+extern asmlinkage long sys_swapoff(const char *specialfile);
+static int suspend_swapon_status;
+
+/* Header Page Information */
+static int header_pages_allocated;
+
+/* User Specified Parameters. */
+
+static unsigned long resume_firstblock;
+static int resume_blocksize;
+static dev_t resume_dev_t;
+static struct block_device *resume_block_device;
+
+struct sysinfo swapinfo;
+static int swapwriter_invalidate_image(void);
+
+/* Block devices open. */
+struct bdev_opened
+{
+	dev_t device;
+	struct block_device *bdev;
+	int set_swapinfo;
+	int claimed;
+};
+
+/* 
+ * Entry MAX_SWAPFILES is the resume block device, which may
+ * not be a swap device enabled when we suspend.
+ * Entry MAX_SWAPFILES + 1 is the header block device, which
+ * is needed before we find out which slot it occupies.
+ */
+static struct bdev_opened *bdev_info_list[MAX_SWAPFILES + 2];
+
+static void close_bdev(int i)
+{
+	struct bdev_opened *this = bdev_info_list[i];
+
+	if (this->claimed)
+		bd_release(this->bdev);
+
+	/* Release our reference. */
+	blkdev_put(this->bdev);
+
+	if (this->set_swapinfo)
+		swap_info[i].bdev = NULL;
+
+	/* Free our info. */
+	kfree(this);
+
+	bdev_info_list[i] = NULL;
+}
+
+static void close_bdevs(void)
+{
+	int i;
+
+	for (i = 0; i < MAX_SWAPFILES; i++)
+		if (bdev_info_list[i])
+			close_bdev(i);
+
+	resume_block_device = header_block_device = NULL;
+}
+
+static struct block_device *open_bdev(int index, dev_t device)
+{
+	struct bdev_opened *this;
+	struct block_device *bdev;
+
+	if (bdev_info_list[index] && (bdev_info_list[index]->device == device)) {
+		bdev = bdev_info_list[index]->bdev;
+		return bdev;
+	}
+	
+	if (bdev_info_list[index] && bdev_info_list[index]->device != device)
+		close_bdev(index);
+
+	bdev = open_by_devnum(device, FMODE_READ);
+
+	if (IS_ERR(bdev) || !bdev) {
+		if (suspend_early_boot_message(1,SUSPEND_CONTINUE_REQ,  
+				"Failed to get access to block device "
+				"%d.\n You could be "
+				"booting with a 2.6 kernel when you "
+				"suspended a 2.4 kernel."), device)
+			swapwriter_invalidate_image();
+		return ERR_PTR(-EINVAL);
+	}
+
+	this = kmalloc(sizeof(struct bdev_opened), GFP_KERNEL);
+	BUG_ON(!this);
+
+	bdev_info_list[index] = this;
+	this->device = device;
+	this->bdev = bdev;
+	if ((index < MAX_SWAPFILES) && !swap_info[index].bdev) {
+		this->set_swapinfo = 1;
+		devinfo[index].bdev = swap_info[index].bdev = bdev;
+	}
+
+	return bdev;
+}
+
+/* Must be silent - might be called from cat /proc/suspend/debug_info
+ * Returns 0 if was off, -EBUSY if was on, error value otherwise.
+ */
+static int enable_swapfile(void)
+{
+	int activateswapresult = -EINVAL;
+
+	if (suspend_swapon_status)
+		return 0;
+
+	if (swapfilename[0]) {
+		/* Attempt to swap on with maximum priority */
+		activateswapresult = sys_swapon(swapfilename, 0xFFFF);
+		if ((activateswapresult) && (activateswapresult != -EBUSY))
+			printk(name_suspend
+				"The swapfile/partition specified by "
+				"/proc/suspend/swapfile (%s) could not"
+				" be turned on (error %d). Attempting "
+				"to continue.\n",
+				swapfilename, activateswapresult);
+		if (!activateswapresult)
+			suspend_swapon_status = 1;
+	}
+	return activateswapresult;
+}
+
+/* Returns 0 if was on, -EINVAL if was off, error value otherwise */
+static int disable_swapfile(void)
+{
+	int result = -EINVAL;
+	
+	if (!suspend_swapon_status)
+		return 0;
+
+	if (swapfilename[0]) {
+		result = sys_swapoff(swapfilename);
+		if (result == -EINVAL)
+	 		return 0;	/* Wasn't on */
+		if (!result)
+			suspend_swapon_status = 0;
+	}
+
+	return result;
+}
+
+static int try_to_parse_resume_device(char *commandline)
+{
+	struct kstat stat;
+	int error;
+
+	resume_dev_t = name_to_dev_t(commandline);
+
+	if (!resume_dev_t) {
+		error = vfs_stat(commandline, &stat);
+		if (!error)
+			resume_dev_t = stat.rdev;
+	}
+
+	if (!resume_dev_t) {
+		if (test_suspend_state(SUSPEND_TRYING_TO_RESUME))
+			suspend_early_boot_message(1, SUSPEND_CONTINUE_REQ,
+			  "Failed to translate \"%s\" into a device id.\n",
+			  commandline);
+		else
+			printk(name_suspend
+			  "Can't translate \"%s\" into a device id yet.\n",
+			  commandline);
+		return 1;
+	}
+
+	if (IS_ERR(resume_block_device =
+	     open_bdev(MAX_SWAPFILES, resume_dev_t))) {
+		suspend_early_boot_message(1, SUSPEND_CONTINUE_REQ,
+			"Failed to get access to \"%s\", where"
+			" the swap header should be found.",
+			commandline);
+		return 1;
+	}
+
+	return 0;
+}
+
+/* 
+ * If we have read part of the image, we might have filled  memory with
+ * data that should be zeroed out.
+ */
+static void swapwriter_noresume_reset(void)
+{
+	memset((char *) &devinfo, 0, sizeof(devinfo));
+	close_bdevs();
+}
+
+static int parse_signature(char *header, int restore)
+{
+	int type = -1;
+	
+	if (!memcmp("SWAP-SPACE",header,10))
+		return 0;
+	else if (!memcmp("SWAPSPACE2",header,10))
+		return 1;
+
+	else if (!memcmp("S1SUSP",header,6))
+		type = 4;
+	else if (!memcmp("S2SUSP",header,6))
+		type = 5;
+	
+	else if (!memcmp("z",header,1))
+		type = 12;
+	else if (!memcmp("Z",header,1))
+		type = 13;
+	
+	/* 
+	 * Put bdev of suspend header in last byte of swap header
+	 * (unsigned short)
+	 */
+	if (type > 11) {
+		dev_t *header_ptr = (dev_t *) &header[1];
+		unsigned char *headerblocksize_ptr =
+			(unsigned char *) &header[5];
+		u32 *headerblock_ptr = (u32 *) &header[6];
+		header_dev_t = *header_ptr;
+		/* 
+		 * We are now using the highest bit of the char to indicate
+		 * whether we have attempted to resume from this image before.
+		 */
+		clear_suspend_state(SUSPEND_RESUMED_BEFORE);
+		if (((int) *headerblocksize_ptr) & 0x80)
+			set_suspend_state(SUSPEND_RESUMED_BEFORE);
+		headerblock = (unsigned long) *headerblock_ptr;
+	}
+
+	if ((restore) && (type > 5)) {
+		/* We only reset our own signatures */
+		if (type & 1)
+			memcpy(header,"SWAPSPACE2",10);
+		else
+			memcpy(header,"SWAP-SPACE",10);
+	}
+
+	return type;
+}
+
+/*
+ * prepare_signature
+ */
+
+static int prepare_signature(dev_t bdev, unsigned long block,
+		char *current_header)
+{
+	int current_type = parse_signature(current_header, 0);
+	dev_t *header_ptr = (dev_t *) (&current_header[1]);
+	unsigned long *headerblock_ptr =
+		(unsigned long *) (&current_header[6]);
+
+	if ((current_type > 1) && (current_type < 6))
+		return 1;
+
+	/* At the moment, I don't have a way to handle the block being
+	 * > 32 bits. Not enough room in the signature and no way to
+	 * safely put the data elsewhere. */
+
+	if (BITS_PER_LONG == 64 && ffs(block) > 31) {
+		suspend2_prepare_status(DONT_CLEAR_BAR,
+			"Header sector requires 33+ bits. "
+			"Would not be able to resume.");
+		return 1;
+	}
+
+	if (current_type & 1)
+		current_header[0] = 'Z';
+	else
+		current_header[0] = 'z';
+	*header_ptr = bdev;
+	/* prev is the first/last swap page of the resume area */
+	*headerblock_ptr = (unsigned long) block; 
+	return 0;
+}
+
+static int swapwriter_allocate_storage(int space_requested);
+
+static int swapwriter_allocate_header_space(int space_requested)
+{
+	int i;
+
+	if (!swapextents.size)
+		swapwriter_allocate_storage(space_requested);
+
+	extent_state_goto_start(&suspend_writer_posn);
+	
+	for (i = 0; i < space_requested; i++) {
+		if (suspend_bio_ops.forward_one_page()) {
+			printk("Out of space while seeking to allocate header pages,\n");
+			return -ENOSPC;
+		}
+
+		header_pages_allocated++;
+	}
+
+	/* The end of header pages will be the start of pageset 2 */
+	extent_state_save(&suspend_writer_posn, &suspend_writer_posn_save[2]);
+	return 0;
+}
+
+static void get_main_pool_phys_params(void)
+{
+	struct extent *extentpointer = NULL;
+	unsigned long address;
+	int i, extent_min = -1, extent_max = -1, last_chain = -1;
+	int prev_header_pages_allocated;
+
+	for (i = 0; i < MAX_SWAPFILES; i++)
+		if (block_chain[i].first)
+			put_extent_chain(&block_chain[i]);
+
+	extent_for_each(&swapextents, extentpointer, address) {
+		swp_entry_t swap_address = extent_val_to_swap_entry(address);
+		unsigned swapfilenum = swp_type(swap_address);
+		pgoff_t offset = swp_offset(swap_address);
+		struct swap_info_struct *sis = get_swap_info_struct(swapfilenum);
+		sector_t new_sector = map_swap_page(sis, offset);
+
+		if ((new_sector == extent_max + 1) &&
+		    (last_chain == swapfilenum))
+			extent_max++;
+		else {
+			if (extent_min > -1) {
+				if (test_action_state(SUSPEND_TEST_BIO))
+					printk("Adding extent %d-%d.\n",
+						extent_min <<
+							devinfo[last_chain].bmap_shift,
+						extent_max <<
+							devinfo[last_chain].bmap_shift);
+						
+				append_extent_to_extent_chain(
+					&block_chain[last_chain],
+					extent_min, extent_max);
+			}
+			extent_min = extent_max = new_sector;
+			last_chain = swapfilenum;
+		}
+	}
+
+	if (extent_min > -1) {
+		if (test_action_state(SUSPEND_TEST_BIO))
+			printk("Adding extent %d-%d.\n",
+				extent_min <<
+					devinfo[last_chain].bmap_shift,
+				extent_max <<
+					devinfo[last_chain].bmap_shift);
+		append_extent_to_extent_chain(
+			&block_chain[last_chain],
+			extent_min, extent_max);
+	}
+
+	prev_header_pages_allocated = header_pages_allocated;
+	header_pages_allocated = 0;
+	swapwriter_allocate_header_space(prev_header_pages_allocated);
+}
+
+static int swapwriter_storage_allocated(void)
+{
+	return swapextents.size;
+}
+
+static int swapwriter_storage_available(void)
+{
+	int result;
+	si_swapinfo(&swapinfo);
+	result = swapinfo.freeswap + swapwriter_storage_allocated();
+	return result;
+}
+
+static int swapwriter_initialise(int starting_cycle)
+{
+	if (starting_cycle)
+		enable_swapfile();
+
+	if (resume_dev_t && !resume_block_device &&
+	    IS_ERR(resume_block_device =
+	    	open_bdev(MAX_SWAPFILES, resume_dev_t)))
+		return 1;
+	
+	return 0;
+}
+
+static void swapwriter_cleanup(int ending_cycle)
+{
+	if (ending_cycle)
+		disable_swapfile();
+	
+	close_bdevs();
+}
+
+static int swapwriter_release_storage(void)
+{
+	int i = 0;
+
+	if ((test_action_state(SUSPEND_KEEP_IMAGE)) &&
+			test_suspend_state(SUSPEND_NOW_RESUMING))
+		return 0;
+
+	header_pages_allocated = 0;
+	
+	if (swapextents.first) {
+		/* Free swap entries */
+		struct extent *extentpointer;
+		unsigned long extentvalue, start = 0, last = 0;
+		int first = 1;
+		swp_entry_t entry;
+		extent_for_each(&swapextents, extentpointer, 
+				extentvalue) {
+			if (first) {
+				start = last = extentvalue;
+				first = 0;
+			} else {
+				if (last + 1 == extentvalue)
+					last++;
+				else
+					start = last = extentvalue;
+			}
+			entry = extent_val_to_swap_entry(extentvalue);
+			swap_free(entry);
+		}
+
+		put_extent_chain(&swapextents);
+		
+		for (i = 0; i < MAX_SWAPFILES; i++)
+			if (block_chain[i].first)
+				put_extent_chain(&block_chain[i]);
+	}
+	
+	return 0;
+}
+
+static int swapwriter_allocate_storage(int space_requested)
+{
+	int i, result = 0, first = 1;
+	int pages_to_get = space_requested - swapextents.size;
+	unsigned long extent_min = 0, extent_max = 0;
+	
+	if (pages_to_get < 1)
+		return 0;
+
+	for (i=0; i < MAX_SWAPFILES; i++) {
+		if ((devinfo[i].bdev = swap_info[i].bdev))
+			devinfo[i].dev_t = swap_info[i].bdev->bd_dev;
+		devinfo[i].bmap_shift = 3;
+		devinfo[i].blocks_per_page = 1;
+	}
+
+	for(i=0; i < pages_to_get; i++) {
+		swp_entry_t entry;
+		unsigned long new_value;
+
+		entry = get_swap_page();
+		if (!entry.val) {
+			printk("Failed to get a swap page.\n");
+			result = -ENOSPC;
+			break;
+		}
+		
+		new_value = swap_entry_to_extent_val(entry);
+		if (first) {
+			first = 0;
+			extent_min = extent_max = new_value;
+		} else {
+			if (new_value == extent_max + 1)
+				extent_max++;
+			else {
+				append_extent_to_extent_chain(
+					&swapextents,
+					extent_min, extent_max);
+				extent_min = extent_max = new_value;
+			}
+		}
+	}
+
+	append_extent_to_extent_chain(
+		&swapextents,
+	       extent_min, extent_max);
+
+	get_main_pool_phys_params();
+	return result;
+}
+
+static int swapwriter_write_header_init(void)
+{
+	int i, result;
+
+	extent_state_goto_start(&suspend_writer_posn);
+	/* Forward one page will be done prior to the read */
+
+	for (i = 0; i < MAX_SWAPFILES; i++)
+		if (swap_info[i].swap_file)
+			devinfo[i].dev_t = swap_info[i].bdev->bd_dev;
+		else
+			devinfo[i].dev_t = (dev_t) 0;
+
+	suspend_writer_buffer = (char *) get_zeroed_page(GFP_ATOMIC);
+	if (!suspend_writer_buffer) {
+		printk("Failed to get swapwriter buffer.\n");
+		return -ENOMEM;
+	}
+
+	suspend_writer_buffer_posn = 0;
+
+	/* Info needed to bootstrap goes at the start of the header.
+	 * First we save the positions and devinfo, including the number
+	 * of header pages. Then we save the structs containing data needed
+	 * for reading the header pages back.
+	 * Note that even if header pages take more than one page, when we
+	 * read back the info, we will have restored the location of the
+	 * next header page by the time we go to use it.
+	 */
+	if ((result = suspend_bio_ops.write_header_chunk((char *) &suspend_writer_posn_save, 
+			sizeof(suspend_writer_posn_save))))
+		return result;
+
+	if ((result = suspend_bio_ops.write_header_chunk((char *) &devinfo, 
+			sizeof(devinfo))))
+		return result;
+
+	for (i=0; i < MAX_SWAPFILES; i++)
+		serialise_extent_chain(&block_chain[i]);
+
+	return 0;
+}
+
+static int swapwriter_write_header_cleanup(void)
+{
+	int result;
+
+	/* Write any unsaved data */
+	if (suspend_writer_buffer_posn) {
+		struct submit_params submit_params;
+		int current_chain;
+
+		if (suspend_bio_ops.forward_one_page())
+			return -EIO;
+		
+		current_chain = suspend_writer_posn.current_chain;
+		submit_params.readahead_index = -1;
+		submit_params.dev = swap_info[suspend_writer_posn.current_chain].bdev;
+		submit_params.block[0] = suspend_writer_posn.current_offset <<
+			devinfo[current_chain].bmap_shift;
+		submit_params.page = virt_to_page(suspend_writer_buffer);
+
+		suspend_bio_ops.submit_io(WRITE, &submit_params, 0);
+	}
+
+	extent_state_goto_start(&suspend_writer_posn);
+	suspend_bio_ops.forward_one_page();
+
+	/* Adjust swap header */
+	suspend_bio_ops.bdev_page_io(READ, resume_block_device,
+			resume_firstblock,
+			virt_to_page(suspend_writer_buffer));
+
+	result = prepare_signature(swap_info[suspend_writer_posn.current_chain].bdev->bd_dev,
+			suspend_writer_posn.current_offset,
+		((union swap_header *) suspend_writer_buffer)->magic.magic);
+		
+	if (!result)
+		suspend_bio_ops.bdev_page_io(WRITE, resume_block_device,
+			resume_firstblock,
+			virt_to_page(suspend_writer_buffer));
+
+	free_page((unsigned long) suspend_writer_buffer);
+	suspend_writer_buffer = NULL;
+	
+	suspend_bio_ops.finish_all_io();
+
+	return result;
+}
+
+/* ------------------------- HEADER READING ------------------------- */
+
+/*
+ * read_header_init()
+ * 
+ * Description:
+ * 1. Attempt to read the device specified with resume2=.
+ * 2. Check the contents of the swap header for our signature.
+ * 3. Warn, ignore, reset and/or continue as appropriate.
+ * 4. If continuing, read the swapwriter configuration section
+ *    of the header and set up block device info so we can read
+ *    the rest of the header & image.
+ *
+ * Returns:
+ * May not return if user choose to reboot at a warning.
+ * -EINVAL if cannot resume at this time. Booting should continue
+ * normally.
+ */
+
+static int swapwriter_read_header_init(void)
+{
+	int i;
+	
+	BUG_ON(!resume_block_device);
+	BUG_ON(!resume_dev_t);
+
+	suspend_writer_buffer = (char *) get_zeroed_page(GFP_ATOMIC);
+
+	BUG_ON(!suspend_writer_buffer);
+
+	if (!header_dev_t) {
+		printk("read_header_init called when we haven't "
+				"verified there is an image!\n");
+		return -EINVAL;
+	}
+
+	/* 
+	 * If the header is not on the resume_dev_t, get the resume device first.
+	 */
+	if (header_dev_t != resume_dev_t) {
+		header_block_device = open_bdev(MAX_SWAPFILES + 1,
+				header_dev_t);
+
+		if (IS_ERR(header_block_device))
+			return PTR_ERR(header_block_device);
+	} else
+		header_block_device = resume_block_device;
+
+	/* 
+	 * Read swapwriter configuration.
+	 * Headerblock size taken into account already.
+	 */
+	suspend_bio_ops.bdev_page_io(READ, header_block_device,
+			headerblock << 3,
+			virt_to_page((unsigned long) suspend_writer_buffer));
+	
+	memcpy(&suspend_writer_posn_save, suspend_writer_buffer, 3 * sizeof(struct extent_iterate_saved_state));
+	
+	suspend_writer_buffer_posn = 3 * sizeof(struct extent_iterate_saved_state);
+
+	memcpy(&devinfo, suspend_writer_buffer + suspend_writer_buffer_posn, sizeof(devinfo));
+	
+	suspend_writer_buffer_posn += sizeof(devinfo);
+
+	/* Restore device info */
+	for (i = 0; i < MAX_SWAPFILES; i++) {
+		dev_t thisdevice = devinfo[i].dev_t;
+		struct block_device *result;
+
+		devinfo[i].bdev = swap_info[i].bdev = NULL;
+
+		if (!thisdevice)
+			continue;
+
+		if (thisdevice == resume_dev_t) {
+			devinfo[i].bdev = swap_info[i].bdev = resume_block_device;
+			bdev_info_list[i] = bdev_info_list[MAX_SWAPFILES];
+			BUG_ON(!bdev_info_list[i]);
+			bdev_info_list[i]->set_swapinfo = 1;
+			bdev_info_list[MAX_SWAPFILES] = NULL;
+			continue;
+		}
+
+		if (thisdevice == header_dev_t) {
+			devinfo[i].bdev = swap_info[i].bdev = header_block_device;
+			bdev_info_list[i] = bdev_info_list[MAX_SWAPFILES + 1];
+			BUG_ON(!bdev_info_list[i]);
+			bdev_info_list[i]->set_swapinfo = 1;
+			bdev_info_list[MAX_SWAPFILES + 1] = NULL;
+			continue;
+		}
+
+		result = open_bdev(i, thisdevice);
+		if (IS_ERR(result)) {
+			close_bdevs();
+			return PTR_ERR(result);
+		}
+	}
+
+	extent_state_goto_start(&suspend_writer_posn);
+	*(suspend_bio_ops.need_extra_next) = 1;
+
+	for (i = 0; i < MAX_SWAPFILES; i++)
+		load_extent_chain(&block_chain[i]);
+
+	return 0;
+}
+
+static int swapwriter_read_header_cleanup(void)
+{
+	free_page((unsigned long) suspend_writer_buffer);
+	return 0;
+}
+
+/* swapwriter_invalidate_image
+ * 
+ */
+static int swapwriter_invalidate_image(void)
+{
+	union p_diskpage cur;
+	int result = 0;
+	char newsig[11];
+	
+	cur.address = get_zeroed_page(GFP_ATOMIC);
+	if (!cur.address) {
+		printk("Unable to allocate a page for restoring the swap signature.\n");
+		return -ENOMEM;
+	}
+
+	/*
+	 * If nr_suspends == 0, we must be booting, so no swap pages
+	 * will be recorded as used yet.
+	 */
+
+	if (nr_suspends > 0)
+		swapwriter_release_storage();
+
+	/* 
+	 * We don't do a sanity check here: we want to restore the swap 
+	 * whatever version of kernel made the suspend image.
+	 * 
+	 * We need to write swap, but swap may not be enabled so
+	 * we write the device directly
+	 */
+	
+	suspend_bio_ops.bdev_page_io(READ, resume_block_device,
+			resume_firstblock,
+			virt_to_page(cur.pointer));
+
+	result = parse_signature(cur.pointer->swh.magic.magic, 1);
+		
+	if (result < 4)
+		goto out;
+
+	strncpy(newsig, cur.pointer->swh.magic.magic, 10);
+	newsig[10] = 0;
+
+	suspend_bio_ops.bdev_page_io(WRITE, resume_block_device,
+			resume_firstblock,
+			virt_to_page(cur.pointer));
+
+	if (!nr_suspends)
+		printk(KERN_WARNING name_suspend "Image invalidated.\n");
+out:
+	suspend_bio_ops.finish_all_io();
+	free_page(cur.address);
+	return 0;
+}
+
+/*
+ * workspace_size
+ *
+ * Description:
+ * Returns the number of bytes of RAM needed for this
+ * code to do its work. (Used when calculating whether
+ * we have enough memory to be able to suspend & resume).
+ *
+ */
+static unsigned long swapwriter_memory_needed(void)
+{
+	return 1;
+}
+
+/* Print debug info
+ *
+ * Description:
+ */
+
+static int swapwriter_print_debug_stats(char *buffer, int size)
+{
+	int len = 0;
+	struct sysinfo sysinfo;
+	
+	if (active_writer != &swapwriterops) {
+		len = snprintf_used(buffer, size, "- Swapwriter inactive.\n");
+		return len;
+	}
+
+	len = snprintf_used(buffer, size, "- Swapwriter active.\n");
+	if (swapfilename[0])
+		len+= snprintf_used(buffer+len, size-len,
+			"  Attempting to automatically swapon: %s.\n", swapfilename);
+
+	si_swapinfo(&sysinfo);
+	
+	len+= snprintf_used(buffer+len, size-len, "  Swap available for image: %ld pages.\n",
+			sysinfo.freeswap + swapwriter_storage_allocated());
+
+	return len;
+}
+
+/*
+ * Storage needed
+ *
+ * Returns amount of space in the swap header required
+ * for the swapwriter's data. This ignores the links between
+ * pages, which we factor in when allocating the space.
+ *
+ * We ensure the space is allocated, but actually save the
+ * data from write_header_init and therefore don't also define a
+ * save_config_info routine.
+ */
+static unsigned long swapwriter_storage_needed(void)
+{
+	return sizeof(suspend_writer_posn_save) + sizeof(devinfo);
+}
+
+/*
+ * Image_exists
+ */
+
+static int swapwriter_image_exists(void)
+{
+	int signature_found;
+	union p_diskpage diskpage;
+	
+	if (!resume_dev_t) {
+		printk("Not even trying to read header "
+				"because resume_dev_t is not set.\n");
+		return 0;
+	}
+	
+	if (!resume_block_device &&
+	    IS_ERR(open_bdev(MAX_SWAPFILES, resume_dev_t)))
+		return 0;
+
+	diskpage.address = get_zeroed_page(GFP_ATOMIC);
+
+	suspend_bio_ops.bdev_page_io(READ, resume_block_device,
+			resume_firstblock,
+			virt_to_page(diskpage.ptr));
+	suspend_bio_ops.finish_all_io();
+
+	signature_found = parse_signature(diskpage.pointer->swh.magic.magic, 0);
+	free_page(diskpage.address);
+
+	if (signature_found < 2) {
+		return 0;	/* Normal swap space */
+	} else if (signature_found == -1) {
+		printk(KERN_ERR name_suspend
+			"Unable to find a signature. Could you have moved "
+			"a swap file?\n");
+		return 0;
+	} else if (signature_found < 6) {
+		if ((!(test_suspend_state(SUSPEND_NORESUME_SPECIFIED)))
+				&& suspend_early_boot_message(1,
+				SUSPEND_CONTINUE_REQ,
+				"Detected the signature of an alternate "
+				"implementation.\n"))
+			set_suspend_state(SUSPEND_NORESUME_SPECIFIED);
+		return 0;
+	} else if ((signature_found >> 1) != SIGNATURE_VER) {
+		if ((!(test_suspend_state(SUSPEND_NORESUME_SPECIFIED))) &&
+			suspend_early_boot_message(1, SUSPEND_CONTINUE_REQ,
+			 "Found a different style suspend image signature."))
+			set_suspend_state(SUSPEND_NORESUME_SPECIFIED);
+	}
+
+	return 1;
+}
+
+/*
+ * Mark resume attempted.
+ *
+ * Record that we tried to resume from this image.
+ */
+
+static void swapwriter_mark_resume_attempted(void)
+{
+	union p_diskpage diskpage;
+	int signature_found;
+	
+	if (!resume_dev_t) {
+		printk("Not even trying to record attempt at resuming"
+				" because resume_dev_t is not set.\n");
+		return;
+	}
+	
+	diskpage.address = get_zeroed_page(GFP_ATOMIC);
+
+	suspend_bio_ops.bdev_page_io(READ, resume_block_device,
+			resume_firstblock,
+			virt_to_page(diskpage.ptr));
+	signature_found = parse_signature(diskpage.pointer->swh.magic.magic, 0);
+
+	switch (signature_found) {
+		case 12:
+		case 13:
+			diskpage.pointer->swh.magic.magic[5] |= 0x80;
+			break;
+	}
+	
+	suspend_bio_ops.bdev_page_io(WRITE, resume_block_device,
+			resume_firstblock,
+			virt_to_page(diskpage.ptr));
+	suspend_bio_ops.finish_all_io();
+	free_page(diskpage.address);
+	
+	close_bdevs();
+	return;
+}
+
+/*
+ * Parse Image Location
+ *
+ * Attempt to parse a resume2= parameter.
+ * Swap Writer accepts:
+ * resume2=swap:DEVNAME[:FIRSTBLOCK][@BLOCKSIZE]
+ *
+ * Where:
+ * DEVNAME is convertable to a dev_t by name_to_dev_t
+ * FIRSTBLOCK is the location of the first block in the swap file
+ * (specifying for a swap partition is nonsensical but not prohibited).
+ * Data is validated by attempting to read a swap header from the
+ * location given. Failure will result in swapwriter refusing to
+ * save an image, and a reboot with correct parameters will be
+ * necessary.
+ */
+
+static int swapwriter_parse_sig_location(char *commandline, int only_writer)
+{
+	char *thischar, *devstart, *colon = NULL, *at_symbol = NULL;
+	union p_diskpage diskpage;
+	int signature_found, result = -EINVAL, temp_result;
+
+	if (strncmp(commandline, "swap:", 5)) {
+		if (!only_writer)
+			return 1;
+	} else
+		commandline += 5;
+
+	devstart = thischar = commandline;
+	while ((*thischar != ':') && (*thischar != '@') &&
+		((thischar - commandline) < 250) && (*thischar))
+		thischar++;
+
+	if (*thischar == ':') {
+		colon = thischar;
+		*colon = 0;
+		thischar++;
+	}
+
+	while ((*thischar != '@') && ((thischar - commandline) < 250) && (*thischar))
+		thischar++;
+
+	if (*thischar == '@') {
+		at_symbol = thischar;
+		*at_symbol = 0;
+	}
+	
+	if (colon)
+		resume_firstblock = (int) simple_strtoul(colon + 1, NULL, 0);
+	else
+		resume_firstblock = 0;
+
+	/* Legacy */
+	if (at_symbol) {
+		resume_blocksize = (int) simple_strtoul(at_symbol + 1, NULL, 0);
+		if (resume_blocksize & (SECTOR_SIZE - 1)) {
+			printk("Swapwriter: Blocksizes are multiples of %d!\n", SECTOR_SIZE);
+			return -EINVAL;
+		}
+		resume_firstblock = resume_firstblock * (resume_blocksize / SECTOR_SIZE);
+	}
+	
+	temp_result = try_to_parse_resume_device(devstart);
+
+	if (colon)
+		*colon = ':';
+	if (at_symbol)
+		*at_symbol = '@';
+
+	if (temp_result)
+		return -EINVAL;
+
+	diskpage.address = get_zeroed_page(GFP_ATOMIC);
+	if (!diskpage.address) {
+		printk(KERN_ERR name_suspend "Swapwriter: Failed to allocate a diskpage for I/O.\n");
+		return -ENOMEM;
+	}
+
+	temp_result = suspend_bio_ops.bdev_page_io(READ,
+			resume_block_device,
+			resume_firstblock,
+			virt_to_page(diskpage.ptr));
+
+	suspend_bio_ops.finish_all_io();
+	
+	if (temp_result) {
+		printk(KERN_ERR name_suspend "Swapwriter: Failed to submit I/O.\n");
+		goto invalid;
+	}
+	
+	signature_found = parse_signature(diskpage.pointer->swh.magic.magic, 0);
+
+	if (signature_found != -1) {
+		printk(name_suspend "Swapwriter: Signature found.\n");
+		result = 0;
+
+		suspend_bio_ops.set_devinfo(devinfo);
+		suspend_writer_posn.chains = &block_chain[0];
+		suspend_writer_posn.num_chains = MAX_SWAPFILES;
+	} else
+		printk(KERN_ERR name_suspend "Swapwriter: No swap signature found at specified location.\n");
+invalid:
+	free_page((unsigned long) diskpage.address);
+	return result;
+
+}
+
+static int header_locations_read_proc(char *page, char **start, off_t off, int count,
+		int *eof, void *data)
+{
+	int i, printedpartitionsmessage = 0, len = 0, haveswap = 0;
+	struct inode *swapf = 0;
+	int zone;
+	char *path_page = (char *) __get_free_page(GFP_KERNEL);
+	char *path;
+	int path_len;
+	
+	*eof = 1;
+	if (!page)
+		return 0;
+
+	for (i = 0; i < MAX_SWAPFILES; i++) {
+		if (!swap_info[i].swap_file)
+			continue;
+		
+		if (S_ISBLK(swap_info[i].swap_file->f_mapping->host->i_mode)) {
+			haveswap = 1;
+			if (!printedpartitionsmessage) {
+				len += sprintf(page + len, 
+					"For swap partitions, simply use the format: resume2=swap:/dev/hda1.\n");
+				printedpartitionsmessage = 1;
+			}
+		} else {
+			path_len = 0;
+			
+			path = d_path(	swap_info[i].swap_file->f_dentry,
+				swap_info[i].swap_file->f_vfsmnt,
+				path_page,
+				PAGE_SIZE);
+			path_len = snprintf(path_page, 31, "%s", path);
+			
+			haveswap = 1;
+			swapf = swap_info[i].swap_file->f_mapping->host;
+			if (!(zone = bmap(swapf,0))) {
+				len+= sprintf(page + len, 
+					"Swapfile %s has been corrupted. Reuse mkswap on it and try again.\n",
+					path_page);
+			} else {
+				char name_buffer[255];
+				len+= sprintf(page + len, "For swapfile `%s`, use resume2=swap:/dev/%s:0x%x.\n",
+						path_page,
+						bdevname(swap_info[i].bdev, name_buffer),
+						zone << (swapf->i_blkbits - 9));
+			}
+
+		}
+	}
+	
+	if (!haveswap)
+		len = sprintf(page, "You need to turn on swap partitions before examining this file.\n");
+
+	free_page((unsigned long) path_page);
+	return len;
+}
+
+static struct suspend_proc_data swapwriter_proc_data[] = {
+	{
+	 .filename			= "swapfilename",
+	 .permissions			= PROC_RW,
+	 .type				= SUSPEND_PROC_DATA_STRING,
+	 .data = {
+		.string = {
+			.variable	= swapfilename,
+			.max_length	= 255,
+		}
+	 }
+	},
+
+	{
+	 .filename			= "headerlocations",
+	 .permissions			= PROC_READONLY,
+	 .type				= SUSPEND_PROC_DATA_CUSTOM,
+	 .data = {
+		 .special = {
+			.read_proc 	= header_locations_read_proc,
+		}
+	 }
+	},
+
+	{ .filename			= "disable_swapwriter",
+	  .permissions			= PROC_RW,
+	  .type				= SUSPEND_PROC_DATA_INTEGER,
+	  .data = {
+		.integer = {
+			.variable	= &swapwriterops.disabled,
+			.minimum	= 0,
+			.maximum	= 1,
+		}
+	  },
+	  .write_proc			= attempt_to_parse_resume_device2,
+	}
+};
+
+static struct suspend_plugin_ops swapwriterops = {
+	.type					= WRITER_PLUGIN,
+	.name					= "Swap Writer",
+	.module					= THIS_MODULE,
+	.memory_needed				= swapwriter_memory_needed,
+	.print_debug_info			= swapwriter_print_debug_stats,
+	.storage_needed				= swapwriter_storage_needed,
+	.initialise				= swapwriter_initialise,
+	.cleanup				= swapwriter_cleanup,
+
+	.ops = {
+		.writer = {
+		 .noresume_reset	= swapwriter_noresume_reset,
+		 .storage_available 	= swapwriter_storage_available,
+		 .storage_allocated	= swapwriter_storage_allocated,
+		 .release_storage	= swapwriter_release_storage,
+		 .allocate_header_space	= swapwriter_allocate_header_space,
+		 .allocate_storage	= swapwriter_allocate_storage,
+		 .image_exists		= swapwriter_image_exists,
+		 .mark_resume_attempted	= swapwriter_mark_resume_attempted,
+		 .write_header_init	= swapwriter_write_header_init,
+		 .write_header_cleanup	= swapwriter_write_header_cleanup,
+		 .read_header_init	= swapwriter_read_header_init,
+		 .read_header_cleanup	= swapwriter_read_header_cleanup,
+		 .invalidate_image	= swapwriter_invalidate_image,
+		 .parse_sig_location	= swapwriter_parse_sig_location,
+		}
+	}
+};
+
+/* ---- Registration ---- */
+static __init int swapwriter_load(void)
+{
+	int result;
+	int i, numfiles = sizeof(swapwriter_proc_data) / sizeof(struct suspend_proc_data);
+	
+	printk("Suspend2 Swap Writer loading.\n");
+
+	swapwriterops.read_init = suspend_bio_ops.read_init;
+	swapwriterops.ops.writer.read_chunk = suspend_bio_ops.read_chunk;
+	swapwriterops.read_cleanup = suspend_bio_ops.read_cleanup;
+	swapwriterops.write_init = suspend_bio_ops.write_init;
+	swapwriterops.ops.writer.write_chunk = suspend_bio_ops.write_chunk;
+	swapwriterops.write_cleanup = suspend_bio_ops.write_cleanup;
+	swapwriterops.ops.writer.read_header_chunk =
+		suspend_bio_ops.read_header_chunk;
+	swapwriterops.ops.writer.write_header_chunk =
+		suspend_bio_ops.write_header_chunk;
+
+	if (!(result = suspend_register_plugin(&swapwriterops))) {
+
+		for (i=0; i< numfiles; i++)
+			suspend_register_procfile(&swapwriter_proc_data[i]);
+	} else
+		printk("Suspend2 Swap Writer unable to register!\n");
+	return result;
+}
+
+#ifdef MODULE
+static __exit void swapwriter_unload(void)
+{
+	int i, numfiles = sizeof(swapwriter_proc_data) / sizeof(struct suspend_proc_data);
+
+	printk("Suspend2 Swap Writer unloading.\n");
+
+	for (i=0; i< numfiles; i++)
+		suspend_unregister_procfile(&swapwriter_proc_data[i]);
+	suspend_unregister_plugin(&swapwriterops);
+}
+
+module_init(swapwriter_load);
+module_exit(swapwriter_unload);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Nigel Cunningham");
+MODULE_DESCRIPTION("Suspend2 swap writer");
+#else
+late_initcall(swapwriter_load);
+#endif
diff -urN oldtree/kernel/power/swsusp.c newtree/kernel/power/swsusp.c
--- oldtree/kernel/power/swsusp.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/kernel/power/swsusp.c	2006-01-28 17:08:36.271721504 +0000
@@ -49,9 +49,7 @@
 #include <linux/bitops.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>
@@ -72,6 +70,8 @@
 #include <asm/scatterlist.h>
 
 #include "power.h"
+#include "swsusp.h"
+#include "suspend.h"
 
 #ifdef CONFIG_HIGHMEM
 int save_highmem(void);
diff -urN oldtree/kernel/power/swsusp.h newtree/kernel/power/swsusp.h
--- oldtree/kernel/power/swsusp.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/swsusp.h	2006-01-28 17:08:36.272721352 +0000
@@ -0,0 +1,24 @@
+
+struct suspend_header {
+	u32 version_code;
+	unsigned long num_physpages;
+	unsigned long orig_mem_free;
+	char machine[65];
+	char version[65];
+	int num_cpus;
+	int page_size;
+	int pageset_2_size;
+	int param0;
+	int param1;
+	int param2;
+	int param3;
+	int progress0;
+	int progress1;
+	int progress2;
+	int progress3;
+	int io_time[2][2];
+	
+	suspend_pagedir_t *suspend_pagedir;
+	unsigned int num_pbes;
+};
+
diff -urN oldtree/kernel/power/ui.c newtree/kernel/power/ui.c
--- oldtree/kernel/power/ui.c	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/ui.c	2006-01-28 17:08:36.273721200 +0000
@@ -0,0 +1,853 @@
+/*
+ * kernel/power/ui.c
+ *
+ * Copyright (C) 1998-2001 Gabor Kuti <seasons@fornax.hu>
+ * Copyright (C) 1998,2001,2002 Pavel Machek <pavel@suse.cz>
+ * Copyright (C) 2002-2003 Florent Chabaud <fchabaud@free.fr>
+ * Copyright (C) 2002-2005 Nigel Cunningham <nigel@suspend2.net>
+ *
+ * This file is released under the GPLv2.
+ *
+ * Routines for Suspend2's user interface.
+ *
+ * The user interface code talks to a userspace program via a
+ * netlink socket.
+ *
+ * The kernel side:
+ * - starts the userui program;
+ * - sends text messages and progress bar status;
+ *
+ * The user space side:
+ * - passes messages regarding user requests (abort, toggle reboot etc)
+ *
+ */
+
+#define __KERNEL_SYSCALLS__
+
+#include <linux/suspend.h>
+#include <linux/freezer.h>
+#include <linux/console.h>
+#include <linux/ctype.h>
+#include <linux/tty.h>
+#include <linux/vt_kern.h>
+#include <linux/module.h>
+#include <linux/reboot.h>
+#include <linux/kmod.h>
+#include <linux/security.h>
+#include <linux/syscalls.h>
+ 
+#include "proc.h"
+#include "plugins.h"
+#include "suspend2.h"
+#include "suspend2_common.h"
+#include "ui.h"
+#include "version.h"
+#include "netlink.h"
+#include "power.h"
+
+static char local_printf_buf[1024];	/* Same as printk - should be safe */
+
+#ifdef CONFIG_NET
+static struct user_helper_data ui_helper_data;
+static struct suspend_plugin_ops userui_ops;
+static int orig_loglevel;
+static int orig_default_message_loglevel;
+static int orig_kmsg;
+
+static char lastheader[512];
+static int lastheader_message_len = 0;
+
+/* Number of distinct progress amounts that userspace can display */
+static int progress_granularity = 50;
+
+DECLARE_WAIT_QUEUE_HEAD(userui_wait_for_key);
+
+static void ui_nl_set_state(int n)
+{
+	/* Only let them change certain settings */
+	static const int suspend_action_mask =
+		(1 << SUSPEND_REBOOT) | (1 << SUSPEND_PAUSE) | (1 << SUSPEND_SLOW) |
+		(1 << SUSPEND_LOGALL) | (1 << SUSPEND_SINGLESTEP) |
+		(1 << SUSPEND_PAUSE_NEAR_PAGESET_END);
+
+	suspend_action = (suspend_action & (~suspend_action_mask)) |
+		(n & suspend_action_mask);
+
+	if (!test_action_state(SUSPEND_PAUSE) &&
+			!test_action_state(SUSPEND_SINGLESTEP))
+		wake_up_interruptible(&userui_wait_for_key);
+}
+
+void userui_redraw(void)
+{
+	if (ui_helper_data.pid == -1)
+		return;
+
+	suspend2_send_netlink_message(&ui_helper_data,
+			USERUI_MSG_REDRAW, NULL, 0);
+}
+
+/* request_abort_suspend
+ *
+ * Description:	Handle the user requesting the cancellation of a suspend by
+ * 		pressing escape.
+ * Callers:	Invoked from a netlink packet from userspace when the user presses
+ * 	 	escape.
+ */
+void request_abort_suspend(void)
+{
+	if (test_suspend_state(SUSPEND_NOW_RESUMING) || (test_result_state(SUSPEND_ABORT_REQUESTED)))
+		return;
+
+	suspend2_prepare_status(CLEAR_BAR, "--- ESCAPE PRESSED :"
+				" ABORTING PROCESS ---");
+	set_result_state(SUSPEND_ABORTED);
+	set_result_state(SUSPEND_ABORT_REQUESTED);
+	
+	wake_up_interruptible(&userui_wait_for_key);
+}
+
+static int userui_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
+{
+	int type;
+	int *data;
+
+	type = nlh->nlmsg_type;
+
+	/* A control message: ignore them */
+	if (type < NETLINK_MSG_BASE)
+		return 0;
+
+	/* Unknown message: reply with EINVAL */
+	if (type >= USERUI_MSG_MAX)
+		return -EINVAL;
+
+	/* All operations require privileges, even GET */
+	if (security_netlink_recv(skb))
+		return -EPERM;
+
+	/* Only allow one task to receive NOFREEZE privileges */
+	if (type == NETLINK_MSG_NOFREEZE_ME && ui_helper_data.pid != -1)
+		return -EBUSY;
+
+	data = (int*)NLMSG_DATA(nlh);
+
+	switch (type) {
+		case USERUI_MSG_ABORT:
+			request_abort_suspend();
+			break;
+		case USERUI_MSG_GET_STATE:
+			suspend2_send_netlink_message(&ui_helper_data, 
+					USERUI_MSG_GET_STATE, &suspend_action,
+					sizeof(suspend_action));
+			break;
+		case USERUI_MSG_GET_DEBUG_STATE:
+			suspend2_send_netlink_message(&ui_helper_data,
+					USERUI_MSG_GET_DEBUG_STATE,
+					&suspend_debug_state,
+					sizeof(suspend_debug_state));
+			break;
+		case USERUI_MSG_SET_STATE:
+			if (nlh->nlmsg_len < NLMSG_LENGTH(sizeof(int)))
+				return -EINVAL;
+			ui_nl_set_state(*data);
+			break;
+		case USERUI_MSG_SET_DEBUG_STATE:
+			if (nlh->nlmsg_len < NLMSG_LENGTH(sizeof(int)))
+				return -EINVAL;
+			suspend_debug_state = (*data);
+			break;
+		case USERUI_MSG_SPACE:
+			wake_up_interruptible(&userui_wait_for_key);
+			break;
+	}
+
+	return 1;
+}
+
+static unsigned long userui_storage_needed(void)
+{
+	return sizeof(ui_helper_data.program);
+}
+
+static int userui_save_config_info(char *buf)
+{
+	*((int *) buf) = progress_granularity;
+	memcpy(buf + sizeof(int), ui_helper_data.program, sizeof(ui_helper_data.program));
+	return sizeof(ui_helper_data.program) + sizeof(int);
+}
+
+static void userui_load_config_info(char *buf, int size)
+{
+	/* Don't load the saved path if one has already been set */
+	if (ui_helper_data.program[0])
+		return;
+
+	progress_granularity = *((int *) buf);
+	size -= sizeof(int);
+	
+	if (size > sizeof(ui_helper_data.program))
+		size = sizeof(ui_helper_data.program);
+
+	memcpy(ui_helper_data.program, buf + sizeof(int), size);
+	ui_helper_data.program[sizeof(ui_helper_data.program)-1] = '\0';
+}
+
+static unsigned long userui_memory_needed(void)
+{
+	/* ball park figure of 128 pages */
+	return (128 * PAGE_SIZE);
+}
+
+unsigned long userui_update_progress(unsigned long value, unsigned long maximum,
+		const char *fmt, va_list args)
+{
+	static int last_step = -1;
+	struct userui_msg_params msg;
+	int bitshift;
+	int this_step;
+	unsigned long next_update;
+
+	if (ui_helper_data.pid == -1)
+		return 0;
+
+	if ((!maximum) || (!progress_granularity))
+		return maximum;
+
+	if (value < 0)
+		value = 0;
+
+	if (value > maximum)
+		value = maximum;
+
+	/* Try to avoid math problems - we can't do 64 bit math here
+	 * (and shouldn't need it - anyone got screen resolution
+	 * of 65536 pixels or more?) */
+	bitshift = generic_fls(maximum) - 16;
+	if (bitshift > 0) {
+		unsigned long temp_maximum = maximum >> bitshift;
+		unsigned long temp_value = value >> bitshift;
+		this_step = (int)
+			(temp_value * progress_granularity / temp_maximum);
+		next_update = (((this_step + 1) * temp_maximum /
+					progress_granularity) + 1) << bitshift;
+	} else {
+		this_step = (int) (value * progress_granularity / maximum);
+		next_update = ((this_step + 1) * maximum /
+				progress_granularity) + 1;
+	}
+
+	if (this_step == last_step)
+		return next_update;
+
+	memset(&msg, 0, sizeof(msg));
+
+	msg.a = this_step;
+	msg.b = progress_granularity;
+
+	if (fmt) {
+		vsnprintf(msg.text, sizeof(msg.text), fmt, args);
+		msg.text[sizeof(msg.text)-1] = '\0';
+	}
+
+	suspend2_send_netlink_message(&ui_helper_data, USERUI_MSG_PROGRESS,
+			&msg, sizeof(msg));
+	last_step = this_step;
+
+	return next_update;
+}
+
+/* __suspend_message.
+ *
+ * Description:	This function is intended to do the same job as printk, but
+ * 		without normally logging what is printed. The point is to be
+ * 		able to get debugging info on screen without filling the logs
+ * 		with "1/534. ^M 2/534^M. 3/534^M"
+ *
+ * 		It may be called from an interrupt context - can't sleep!
+ *
+ * Arguments:	int mask: The debugging section(s) this message belongs to.
+ * 		int level: The level of verbosity of this message.
+ * 		int restartline: Whether to output a \r or \n with this line
+ * 			(\n if we're logging all output).
+ * 		const char *fmt, ...: Message to be displayed a la printk.
+ */
+void __suspend_message(unsigned long section, unsigned long level,
+		int normally_logged,
+		const char *fmt, ...)
+{
+	struct userui_msg_params msg;
+
+	va_list args;
+
+	if ((level) && (level > console_loglevel))
+		return;
+
+	if (ui_helper_data.pid == -1)
+		return;
+
+	memset(&msg, 0, sizeof(msg));
+
+	msg.a = section;
+	msg.b = level;
+	msg.c = normally_logged;
+
+	if (fmt) {
+		va_start(args, fmt);
+		vsnprintf(msg.text, sizeof(msg.text), fmt, args);
+		va_end(args);
+		msg.text[sizeof(msg.text)-1] = '\0';
+	}
+
+	if (test_action_state(SUSPEND_LOGALL))
+		printk("%s\n", msg.text);
+
+	suspend2_send_netlink_message(&ui_helper_data, USERUI_MSG_MESSAGE,
+			&msg, sizeof(msg));
+}
+
+static void wait_for_key_via_userui(void)
+{
+	DECLARE_WAITQUEUE(wait, current);
+
+	add_wait_queue(&userui_wait_for_key, &wait);
+	set_current_state(TASK_INTERRUPTIBLE);
+
+	interruptible_sleep_on(&userui_wait_for_key);
+
+	set_current_state(TASK_RUNNING);
+	remove_wait_queue(&userui_wait_for_key, &wait);
+}
+
+char suspend_wait_for_keypress(int timeout)
+{
+	int fd;
+	char key = '\0';
+	struct termios t, t_backup;
+
+	if (ui_helper_data.pid != -1) {
+		wait_for_key_via_userui();
+		key = ' ';
+		goto out;
+	}
+	
+	/* We should be guaranteed /dev/console exists after populate_rootfs() in
+	 * init/main.c
+	 */
+	if ((fd = sys_open("/dev/console", O_RDONLY, 0)) < 0) {
+		printk("Couldn't open /dev/console.\n");
+		goto out;
+	}
+
+	if (sys_ioctl(fd, TCGETS, (long)&t) < 0)
+		goto out_close;
+
+	memcpy(&t_backup, &t, sizeof(t));
+
+	t.c_lflag &= ~(ISIG|ICANON|ECHO);
+	t.c_cc[VMIN] = 0;
+	if (timeout)
+		t.c_cc[VTIME] = timeout*10;
+
+	if (sys_ioctl(fd, TCSETS, (long)&t) < 0)
+		goto out_restore;
+
+	while (1) {
+		if (sys_read(fd, &key, 1) <= 0) {
+			key = '\0';
+			break;
+		}
+		key = tolower(key);
+		if (test_suspend_state(SUSPEND_SANITY_CHECK_PROMPT)) {
+			if (key == 'c') {
+				set_suspend_state(SUSPEND_CONTINUE_REQ);
+				break;
+			} else if (key == ' ')
+				break;
+		} else
+			break;
+	}
+
+out_restore:
+	sys_ioctl(fd, TCSETS, (long)&t_backup);
+
+out_close:
+	sys_close(fd);
+out:
+	return key;
+}
+
+/* abort_suspend
+ *
+ * Description: Begin to abort a cycle. If this wasn't at the user's request
+ * 		(and we're displaying output), tell the user why and wait for
+ * 		them to acknowledge the message.
+ * Arguments:	A parameterised string (imagine this is printk) to display,
+ *	 	telling the user why we're aborting.
+ */
+
+void abort_suspend(const char *fmt, ...)
+{
+	va_list args;
+	int printed_len = 0;
+
+	if (!test_result_state(SUSPEND_ABORTED)) {
+		if (!test_result_state(SUSPEND_ABORT_REQUESTED)) {
+			va_start(args, fmt);
+			printed_len = vsnprintf(local_printf_buf, 
+					sizeof(local_printf_buf), fmt, args);
+			va_end(args);
+			if (ui_helper_data.pid != -1)
+				printed_len = sprintf(local_printf_buf + printed_len,
+					" (Press SPACE to continue)");
+			suspend2_prepare_status(CLEAR_BAR, local_printf_buf);
+
+			/* 
+			 * Make sure message seen - wait for shift to be
+			 * released if being pressed 
+			 */
+			if (ui_helper_data.pid != -1)
+				suspend_wait_for_keypress(0);
+		}
+		/* Turn on aborting flag */
+		set_result_state(SUSPEND_ABORTED);
+	}
+}
+
+/* suspend2_prepare_status
+ * Description:	Prepare the 'nice display', drawing the header and version,
+ * 		along with the current action and perhaps also resetting the
+ * 		progress bar.
+ * Arguments:	
+ * 		int clearbar: Whether to reset the progress bar.
+ * 		const char *fmt, ...: The action to be displayed.
+ */
+void suspend2_prepare_status(int clearbar, const char *fmt, ...)
+{
+	va_list args;
+
+	if (fmt) {
+		va_start(args, fmt);
+		lastheader_message_len = vsnprintf(lastheader, 512, fmt, args);
+		va_end(args);
+	}
+
+	if (clearbar)
+		userui_update_progress(0, 1, NULL, NULL);
+
+	__suspend_message(0, SUSPEND_STATUS, 1, lastheader, NULL);
+
+	if (ui_helper_data.pid == -1)
+		printk(KERN_EMERG "%s\n", lastheader);
+}
+
+/* update_status
+ *
+ * Description: Update the progress bar and (if on) in-bar message.
+ * Arguments:	UL value, maximum: Current progress percentage (value/max).
+ * 		const char *fmt, ...: Message to be displayed in the middle
+ * 		of the progress bar.
+ * 		Note that a NULL message does not mean that any previous
+ * 		message is erased! For that, you need suspend2_prepare_status with
+ * 		clearbar on.
+ * Returns:	Unsigned long: The next value where status needs to be updated.
+ * 		This is to reduce unnecessary calls to update_status.
+ */
+unsigned long suspend2_update_status(unsigned long value, unsigned long maximum,
+		const char *fmt, ...)
+{
+	unsigned long next_update = maximum;
+	va_list args;
+
+	if (!maximum)
+		return maximum;
+
+	if (value < 0)
+		value = 0;
+
+	if (value > maximum)
+		value = maximum;
+
+	va_start(args, fmt);
+
+	next_update = userui_update_progress(value, maximum, fmt, args);
+
+	va_end(args);
+
+	return next_update;
+}
+
+/* check_shift_keys
+ * 
+ * Description:	Potentially pause and wait for the user to tell us to continue.
+ * 		We normally only pause when @pause is set.
+ * Arguments:	int pause: Whether we normally pause.
+ * 		char *message: The message to display. Not parameterised
+ * 		 because it's normally a constant.
+ */
+
+void check_shift_keys(int pause, char *message)
+{
+#ifdef CONFIG_PM_DEBUG
+	int displayed_message = 0, last_key = 0;
+	
+	while (last_key != 32 &&
+		ui_helper_data.pid != -1 &&
+		(!test_result_state(SUSPEND_ABORTED)) &&
+		((test_action_state(SUSPEND_PAUSE) && pause) || 
+		 (test_action_state(SUSPEND_SINGLESTEP)))) {
+		if (!displayed_message) {
+			suspend2_prepare_status(DONT_CLEAR_BAR, 
+			   "%s Press SPACE to continue.%s",
+			   message ? message : "",
+			   (test_action_state(SUSPEND_SINGLESTEP)) ? 
+			   " Single step on." : "");
+			displayed_message = 1;
+		}
+		last_key = suspend_wait_for_keypress(0);
+	}
+#endif
+	schedule();
+}
+
+extern asmlinkage long sys_ioctl(unsigned int fd, unsigned int cmd, 
+		unsigned long arg);
+
+/* suspend2_prepare_console
+ *
+ * Description:	Prepare a console for use, save current settings.
+ * Returns:	Boolean: Whether an error occured. Errors aren't
+ * 		treated as fatal, but a warning is printed.
+ */
+void suspend2_prepare_console(void)
+{
+	orig_loglevel = console_loglevel;
+	orig_default_message_loglevel = default_message_loglevel;
+	orig_kmsg = kmsg_redirect;
+	kmsg_redirect = fg_console + 1;
+	default_message_loglevel = 1;
+	console_loglevel = suspend_default_console_level;
+
+	ui_helper_data.pid = -1;
+
+	if (userui_ops.disabled)
+		return;
+
+	if (!*ui_helper_data.program) {
+		printk("suspend_userui: program not configured. suspend_userui disabled.\n");
+		return;
+	}
+
+	suspend2_netlink_setup(&ui_helper_data);
+
+	return;
+}
+
+/* suspend2_restore_console
+ *
+ * Description: Restore the settings we saved above.
+ */
+
+void suspend2_cleanup_console(void)
+{
+	suspend_default_console_level = console_loglevel;
+
+	if (ui_helper_data.pid > -1) {
+		struct task_struct *t;
+
+		suspend2_send_netlink_message(&ui_helper_data,
+				NETLINK_MSG_CLEANUP, NULL, 0);
+
+		read_lock(&tasklist_lock);
+		if ((t = find_task_by_pid(ui_helper_data.pid)))
+			t->flags &= ~PF_NOFREEZE;
+		read_unlock(&tasklist_lock);
+
+		suspend2_netlink_close(&ui_helper_data);
+
+		ui_helper_data.pid = -1;
+	}
+
+	console_loglevel = orig_loglevel;
+	kmsg_redirect = orig_kmsg;
+	default_message_loglevel = orig_default_message_loglevel;
+}
+#else
+static char suspend_wait_for_keypress(int timeout)
+{
+	return 0;
+}
+
+unsigned long suspend2_update_status(unsigned long value, unsigned long maximum,
+		const char *fmt, ...)
+{
+	return maximum;
+}
+
+void __suspend_message(unsigned long section, unsigned long level,
+		int normally_logged,
+		const char *fmt, ...)  { }
+void suspend2_prepare_status(int clearbar, const char *fmt, ...) { }
+void check_shift_keys(int pause, char *message) { }
+void abort_suspend(const char *fmt, ...) { }
+void suspend2_prepare_console(void) { }
+void suspend2_cleanup_console(void) { }
+void userui_redraw(void) { }
+#endif
+
+/* suspend_early_boot_message()
+ * Description:	Handle errors early in the process of booting.
+ * 		The user may press C to continue booting, perhaps
+ * 		invalidating the image,  or space to reboot. 
+ * 		This works from either the serial console or normally 
+ * 		attached keyboard.
+ *
+ * 		Note that we come in here from init, while the kernel is
+ * 		locked. If we want to get events from the serial console,
+ * 		we need to temporarily unlock the kernel.
+ *
+ * 		suspend_early_boot_message may also be called post-boot.
+ * 		In this case, it simply printks the message and returns.
+ *
+ * Arguments:	int	Whether we are able to erase the image.
+ * 		int	default_answer. What to do when we timeout. This
+ * 			will normally be continue, but the user might
+ * 			provide command line options (__setup) to override
+ * 			particular cases.
+ * 		Char *. Pointer to a string explaining why we're moaning.
+ */
+
+#define say(message, a...) printk(KERN_EMERG message, ##a)
+#define message_timeout 25 /* message_timeout * 10 must fit in 8 bits */
+
+int suspend_early_boot_message(int message_detail, int default_answer, char *warning_reason, ...)
+{
+	unsigned long orig_state = get_suspend_state(), continue_req = 0;
+	va_list args;
+	int printed_len;
+
+	if (warning_reason) {
+		va_start(args, warning_reason);
+		printed_len = vsnprintf(local_printf_buf, 
+				sizeof(local_printf_buf), 
+				warning_reason,
+				args);
+		va_end(args);
+	}
+
+	if (!test_suspend_state(SUSPEND_BOOT_TIME)) {
+		printk(name_suspend "%s\n", local_printf_buf);
+		return default_answer;
+	}
+
+	/* We might be called directly from do_mounts_initrd if the
+	 * user fails to set up their initrd properly. We need to
+	 * enable the keyboard handler by setting the running flag */
+	set_suspend_state(SUSPEND_RUNNING);
+
+#if defined(CONFIG_VT) || defined(CONFIG_SERIAL_CONSOLE)
+	console_loglevel = 7;
+
+	say("=== Suspend2 ===\n\n");
+	if (warning_reason) {
+		say("BIG FAT WARNING!! %s\n\n", local_printf_buf);
+		switch (message_detail) {
+		 case 0:
+			say("If you continue booting, note that any image WILL NOT BE REMOVED.\n");
+			say("Suspend is unable to do so because the appropriate modules aren't\n");
+			say("loaded. You should manually remove the image to avoid any\n");
+			say("possibility of corrupting your filesystem(s) later.\n");
+			break;
+		 case 1:
+			say("If you want to use the current suspend image, reboot and try\n");
+			say("again with the same kernel that you suspended from. If you want\n");
+			say("to forget that image, continue and the image will be erased.\n");
+			break;
+		}
+		say("Press SPACE to reboot or C to continue booting with this kernel\n\n");
+		say("Default action if you don't select one in %d seconds is: %s.\n",
+			message_timeout,
+			default_answer == SUSPEND_CONTINUE_REQ ?
+			"continue booting" : "reboot");
+	} else {
+		say("BIG FAT WARNING!!\n\n");
+		say("You have tried to resume from this image before.\n");
+		say("If it failed once, it may well fail again.\n");
+		say("Would you like to remove the image and boot normally?\n");
+		say("This will be equivalent to entering noresume2 on the\n");
+		say("kernel command line.\n\n");
+		say("Press SPACE to remove the image or C to continue resuming.\n\n");
+		say("Default action if you don't select one in %d seconds is: %s.\n",
+			message_timeout,
+			!!default_answer ?
+			"continue resuming" : "remove the image");
+	}
+	
+	set_suspend_state(SUSPEND_SANITY_CHECK_PROMPT);
+	clear_suspend_state(SUSPEND_CONTINUE_REQ);
+
+	if (suspend_wait_for_keypress(message_timeout) == 0) /* We timed out */
+		continue_req = !!default_answer;
+	else
+		continue_req = test_suspend_state(SUSPEND_CONTINUE_REQ);
+
+	if ((warning_reason) && (!continue_req))
+		machine_restart(NULL);
+	
+	restore_suspend_state(orig_state);
+	if (continue_req)
+		set_suspend_state(SUSPEND_CONTINUE_REQ);
+
+#endif // CONFIG_VT or CONFIG_SERIAL_CONSOLE
+	return -EPERM;
+}
+#undef say
+
+/*
+ * User interface specific /proc/suspend entries.
+ */
+
+static struct suspend_proc_data proc_params[] = {
+#ifdef CONFIG_NET
+#ifdef CONFIG_PROC_FS
+	{ .filename			= "default_console_level",
+	  .permissions			= PROC_RW,
+	  .type				= SUSPEND_PROC_DATA_INTEGER,
+	  .data = {
+		  .integer = {
+			  .variable	= &suspend_default_console_level,
+			  .minimum	= 0,
+#ifdef CONFIG_PM_DEBUG
+			  .maximum	= 7,
+#else
+			  .maximum	= 1,
+#endif
+
+		  }
+	  }
+	},
+
+	{ .filename			= "enable_escape",
+	  .permissions			= PROC_RW,
+	  .type				= SUSPEND_PROC_DATA_BIT,
+	  .data = {
+		  .bit = {
+			  .bit_vector	= &suspend_action,
+			  .bit		= SUSPEND_CAN_CANCEL,
+		  }
+	  }
+	},
+
+#ifdef CONFIG_PM_DEBUG
+	{ .filename			= "debug_sections",
+	  .permissions			= PROC_RW,
+	  .type				= SUSPEND_PROC_DATA_UL,
+	  .data = {
+		  .ul = {
+			  .variable	= &suspend_debug_state,
+			  .minimum	= 0,
+			  .maximum	= 2 << 30,
+		  }
+	  }
+	},
+
+	{ .filename			= "log_everything",
+	  .permissions			= PROC_RW,
+	  .type				= SUSPEND_PROC_DATA_BIT,
+	  .data = {
+		  .bit = {
+			  .bit_vector	= &suspend_action,
+			  .bit		= SUSPEND_LOGALL,
+		  }
+	  }
+	},
+	  
+	{ .filename			= "pause_between_steps",
+	  .permissions			= PROC_RW,
+	  .type				= SUSPEND_PROC_DATA_BIT,
+	  .data = {
+		  .bit = {
+			  .bit_vector	= &suspend_action,
+			  .bit		= SUSPEND_PAUSE,
+		  }
+	  }
+	},
+#endif
+	{ .filename			= "disable_userui_support",
+	  .permissions			= PROC_RW,
+	  .type				= SUSPEND_PROC_DATA_INTEGER,
+	  .data = {
+		.integer = {
+			.variable	= &userui_ops.disabled,
+			.minimum	= 0,
+			.maximum	= 1,
+		}
+	  }
+	},
+	{ .filename			= "userui_progress_granularity",
+	  .permissions			= PROC_RW,
+	  .type				= SUSPEND_PROC_DATA_INTEGER,
+	  .data = {
+		.integer = {
+			.variable	= &progress_granularity,
+			.minimum	= 1,
+			.maximum	= 2048,
+		}
+	  }
+	},
+	{ .filename			= "userui_program",
+	  .permissions			= PROC_RW,
+	  .type				= SUSPEND_PROC_DATA_STRING,
+	  .data = {
+		.string = {
+			.variable	= ui_helper_data.program,
+			.max_length	= 255,
+		}
+	  }
+	}
+#endif
+#endif
+};
+
+static struct suspend_plugin_ops userui_ops = {
+	.type				= MISC_PLUGIN,
+	.name				= "Userspace UI Support",
+	.module				= THIS_MODULE,
+#ifdef CONFIG_NET
+	.storage_needed			= userui_storage_needed,
+	.save_config_info		= userui_save_config_info,
+	.load_config_info		= userui_load_config_info,
+	.memory_needed			= userui_memory_needed,
+#endif
+};
+
+/* suspend_console_proc_init
+ * Description: Boot time initialisation for user interface.
+ */
+static __init int suspend_console_proc_init(void)
+{
+	int result, i, numfiles = sizeof(proc_params) / sizeof(struct suspend_proc_data);
+
+	if (!(result = suspend_register_plugin(&userui_ops)))
+		for (i=0; i< numfiles; i++)
+			suspend_register_procfile(&proc_params[i]);
+
+#ifdef CONFIG_NET
+	ui_helper_data.nl = NULL;
+	ui_helper_data.program[0] = '\0';
+#endif
+	ui_helper_data.pid = -1;
+	ui_helper_data.skb_size = sizeof(struct userui_msg_params);
+	ui_helper_data.pool_limit = 6;
+	ui_helper_data.netlink_id = NETLINK_SUSPEND2_USERUI;
+	ui_helper_data.name = "userspace ui";
+	ui_helper_data.rcv_msg = userui_user_rcv_msg;
+	ui_helper_data.interface_version = 6;
+	ui_helper_data.must_init = 0;
+	ui_helper_data.not_ready = suspend2_cleanup_console;
+	init_completion(&ui_helper_data.wait_for_process);
+
+	return result;
+}
+
+late_initcall(suspend_console_proc_init);
diff -urN oldtree/kernel/power/ui.h newtree/kernel/power/ui.h
--- oldtree/kernel/power/ui.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/ui.h	2006-01-28 17:08:36.273721200 +0000
@@ -0,0 +1,44 @@
+/*
+ *
+ */
+
+extern void suspend2_prepare_console(void);
+extern void suspend2_cleanup_console(void);
+
+extern void check_shift_keys(int pause, char *message);
+extern unsigned long suspend2_update_status(unsigned long value, unsigned long maximum,
+		const char *fmt, ...);
+
+extern void abort_suspend(const char *fmt, ...);
+
+extern void userui_redraw(void);
+
+enum {
+	DONT_CLEAR_BAR,
+	CLEAR_BAR
+};
+
+enum {
+	/* Userspace -> Kernel */
+	USERUI_MSG_ABORT = 0x11,
+	USERUI_MSG_SET_STATE = 0x12,
+	USERUI_MSG_GET_STATE = 0x13,
+	USERUI_MSG_GET_DEBUG_STATE = 0x14,
+	USERUI_MSG_SET_DEBUG_STATE = 0x15,
+	USERUI_MSG_SET_PROGRESS_GRANULARITY = 0x17,
+	USERUI_MSG_SPACE = 0x18,
+
+	/* Kernel -> Userspace */
+	USERUI_MSG_MESSAGE = 0x21,
+	USERUI_MSG_PROGRESS = 0x22,
+	USERUI_MSG_REDRAW = 0x25,
+	USERUI_MSG_KEYPRESS = 0x26,
+	USERUI_MSG_DEBUG_STATE = 0x29,
+
+	USERUI_MSG_MAX,
+};
+
+struct userui_msg_params {
+	unsigned long a, b, c, d;
+	char text[255];
+};
diff -urN oldtree/kernel/power/version.h newtree/kernel/power/version.h
--- oldtree/kernel/power/version.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/version.h	2006-01-28 17:08:36.273721200 +0000
@@ -0,0 +1,2 @@
+#define SUSPEND_CORE_VERSION "2.2-rc16"
+#define name_suspend "Suspend2 " SUSPEND_CORE_VERSION ": "
diff -urN oldtree/kernel/sched.c newtree/kernel/sched.c
--- oldtree/kernel/sched.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/kernel/sched.c	2006-01-28 17:08:36.276720744 +0000
@@ -4549,7 +4549,7 @@
 		struct list_head *head;
 		migration_req_t *req;
 
-		try_to_freeze();
+		try_todo_list();
 
 		spin_lock_irq(&rq->lock);
 
@@ -4765,7 +4765,6 @@
 		p = kthread_create(migration_thread, hcpu, "migration/%d",cpu);
 		if (IS_ERR(p))
 			return NOTIFY_BAD;
-		p->flags |= PF_NOFREEZE;
 		kthread_bind(p, cpu);
 		/* Must be high prio: stop_machine expects to yield to it. */
 		rq = task_rq_lock(p, &flags);
diff -urN oldtree/kernel/signal.c newtree/kernel/signal.c
--- oldtree/kernel/signal.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/kernel/signal.c	2006-01-28 17:08:36.277720592 +0000
@@ -213,7 +213,7 @@
 fastcall void recalc_sigpending_tsk(struct task_struct *t)
 {
 	if (t->signal->group_stop_count > 0 ||
-	    (freezing(t)) ||
+	    (t->todo) ||
 	    PENDING(&t->pending, &t->blocked) ||
 	    PENDING(&t->signal->shared_pending, &t->blocked))
 		set_tsk_thread_flag(t, TIF_SIGPENDING);
@@ -2212,7 +2212,7 @@
 
 			timeout = schedule_timeout_interruptible(timeout);
 
-			try_to_freeze();
+			try_todo_list();
 			spin_lock_irq(&current->sighand->siglock);
 			sig = dequeue_signal(current, &these, &info);
 			current->blocked = current->real_blocked;
diff -urN oldtree/kernel/softirq.c newtree/kernel/softirq.c
--- oldtree/kernel/softirq.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/kernel/softirq.c	2006-01-28 17:08:36.278720440 +0000
@@ -350,7 +350,6 @@
 static int ksoftirqd(void * __bind_cpu)
 {
 	set_user_nice(current, 19);
-	current->flags |= PF_NOFREEZE;
 
 	set_current_state(TASK_INTERRUPTIBLE);
 
@@ -456,7 +455,7 @@
 	case CPU_UP_PREPARE:
 		BUG_ON(per_cpu(tasklet_vec, hotcpu).list);
 		BUG_ON(per_cpu(tasklet_hi_vec, hotcpu).list);
-		p = kthread_create(ksoftirqd, hcpu, "ksoftirqd/%d", hotcpu);
+		p = kthread_nofreeze_create(ksoftirqd, hcpu, "ksoftirqd/%d", hotcpu);
 		if (IS_ERR(p)) {
 			printk("ksoftirqd for %i failed\n", hotcpu);
 			return NOTIFY_BAD;
diff -urN oldtree/kernel/sys.c newtree/kernel/sys.c
--- oldtree/kernel/sys.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/kernel/sys.c	2006-01-28 17:08:36.279720288 +0000
@@ -173,15 +173,18 @@
 {
 	int ret=NOTIFY_DONE;
 	struct notifier_block *nb = *n;
+	struct notifier_block *next;
 
 	while(nb)
 	{
-		ret=nb->notifier_call(nb,val,v);
+		/* Determining next here allows the notifier to unregister itself */
+		next = nb->next;
+		ret = nb->notifier_call(nb,val,v);
 		if(ret&NOTIFY_STOP_MASK)
 		{
 			return ret;
 		}
-		nb=nb->next;
+		nb = next;
 	}
 	return ret;
 }
@@ -530,12 +533,12 @@
 		unlock_kernel();
 		return -EINVAL;
 
-#ifdef CONFIG_SOFTWARE_SUSPEND
+#ifdef CONFIG_SUSPEND2
 	case LINUX_REBOOT_CMD_SW_SUSPEND:
 		{
-			int ret = software_suspend();
+			suspend2_try_suspend();
 			unlock_kernel();
-			return ret;
+			return 0;
 		}
 #endif
 
diff -urN oldtree/kernel/workqueue.c newtree/kernel/workqueue.c
--- oldtree/kernel/workqueue.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/kernel/workqueue.c	2006-01-28 17:08:36.280720136 +0000
@@ -188,8 +188,6 @@
 	struct k_sigaction sa;
 	sigset_t blocked;
 
-	current->flags |= PF_NOFREEZE;
-
 	set_user_nice(current, -5);
 
 	/* Block and flush all signals */
@@ -210,6 +208,7 @@
 			schedule();
 		else
 			__set_current_state(TASK_RUNNING);
+		try_todo_list();
 		remove_wait_queue(&cwq->more_work, &wait);
 
 		if (!list_empty(&cwq->worklist))
@@ -279,7 +278,8 @@
 }
 
 static struct task_struct *create_workqueue_thread(struct workqueue_struct *wq,
-						   int cpu)
+						   int cpu,
+						   unsigned long freezer_flags)
 {
 	struct cpu_workqueue_struct *cwq = per_cpu_ptr(wq->cpu_wq, cpu);
 	struct task_struct *p;
@@ -293,10 +293,21 @@
 	init_waitqueue_head(&cwq->more_work);
 	init_waitqueue_head(&cwq->work_done);
 
-	if (is_single_threaded(wq))
-		p = kthread_create(worker_thread, cwq, "%s", wq->name);
-	else
-		p = kthread_create(worker_thread, cwq, "%s/%d", wq->name, cpu);
+	if (is_single_threaded(wq)) {
+		if (freezer_flags)
+			p = kthread_nofreeze_create(worker_thread, cwq,
+					"%s", wq->name);
+		else
+			p = kthread_create(worker_thread, cwq,
+					"%s", wq->name);
+	} else {
+		if (freezer_flags)
+			p = kthread_nofreeze_create(worker_thread, cwq,
+					"%s/%d", wq->name, cpu);
+		else
+			p = kthread_create(worker_thread, cwq,
+					"%s/%d", wq->name, cpu);
+	}
 	if (IS_ERR(p))
 		return NULL;
 	cwq->thread = p;
@@ -304,7 +315,8 @@
 }
 
 struct workqueue_struct *__create_workqueue(const char *name,
-					    int singlethread)
+					    int singlethread,
+					    unsigned long freezer_flags)
 {
 	int cpu, destroy = 0;
 	struct workqueue_struct *wq;
@@ -320,7 +332,8 @@
 	lock_cpu_hotplug();
 	if (singlethread) {
 		INIT_LIST_HEAD(&wq->list);
-		p = create_workqueue_thread(wq, any_online_cpu(cpu_online_map));
+		p = create_workqueue_thread(wq, any_online_cpu(cpu_online_map),
+				freezer_flags);
 		if (!p)
 			destroy = 1;
 		else
@@ -330,7 +343,7 @@
 		list_add(&wq->list, &workqueues);
 		spin_unlock(&workqueue_lock);
 		for_each_online_cpu(cpu) {
-			p = create_workqueue_thread(wq, cpu);
+			p = create_workqueue_thread(wq, cpu, freezer_flags);
 			if (p) {
 				kthread_bind(p, cpu);
 				wake_up_process(p);
@@ -502,7 +515,7 @@
 	case CPU_UP_PREPARE:
 		/* Create a new workqueue thread for it. */
 		list_for_each_entry(wq, &workqueues, list) {
-			if (!create_workqueue_thread(wq, hotcpu)) {
+			if (!create_workqueue_thread(wq, hotcpu, 0)) {
 				printk("workqueue for %i failed\n", hotcpu);
 				return NOTIFY_BAD;
 			}
@@ -544,7 +557,7 @@
 void init_workqueues(void)
 {
 	hotcpu_notifier(workqueue_cpu_callback, 0);
-	keventd_wq = create_workqueue("events");
+	keventd_wq = create_nofreeze_workqueue("events");
 	BUG_ON(!keventd_wq);
 }
 
diff -urN oldtree/lib/Kconfig newtree/lib/Kconfig
--- oldtree/lib/Kconfig	2006-01-28 16:36:00.000000000 +0000
+++ newtree/lib/Kconfig	2006-01-28 17:08:36.281719984 +0000
@@ -38,6 +38,9 @@
 	  require M here.  See Castagnoli93.
 	  Module will be libcrc32c.
 
+config DYN_PAGEFLAGS
+	bool
+
 #
 # compression support is select'ed if needed
 #
diff -urN oldtree/lib/Makefile newtree/lib/Makefile
--- oldtree/lib/Makefile	2006-01-28 16:36:00.000000000 +0000
+++ newtree/lib/Makefile	2006-01-28 17:08:36.281719984 +0000
@@ -28,6 +28,8 @@
   lib-y += dec_and_lock.o
 endif
 
+obj-$(CONFIG_DYN_PAGEFLAGS) += dyn_pageflags.o
+
 obj-$(CONFIG_CRC_CCITT)	+= crc-ccitt.o
 obj-$(CONFIG_CRC16)	+= crc16.o
 obj-$(CONFIG_CRC32)	+= crc32.o
diff -urN oldtree/lib/dyn_pageflags.c newtree/lib/dyn_pageflags.c
--- oldtree/lib/dyn_pageflags.c	1970-01-01 00:00:00.000000000 +0000
+++ newtree/lib/dyn_pageflags.c	2006-01-28 17:08:36.282719832 +0000
@@ -0,0 +1,267 @@
+/*
+ * lib/dyn_pageflags.c
+ *
+ * Copyright (C) 2004-2005 Nigel Cunningham <ncunningham@cyclades.com>
+ * 
+ * This file is released under the GPLv2.
+ *
+ * Routines for dynamically allocating and releasing bitmaps
+ * used as pseudo-pageflags.
+ *
+ * Arrays are not contiguous. The first sizeof(void *) bytes are
+ * the pointer to the next page in the bitmap. This allows us to
+ * work under low memory conditions where order 0 might be all
+ * that's available. In their original use (suspend2), it also
+ * lets us save the pages at suspend time, reload and relocate them
+ * as necessary at resume time without much effort.
+ */
+
+#include <linux/module.h>
+#include <linux/dyn_pageflags.h>
+#include <linux/suspend2.h>
+#include <linux/bootmem.h>
+
+#define page_to_zone_offset(pg) (page_to_pfn(pg) - page_zone(pg)->zone_start_pfn)
+
+int num_zones(void)
+{
+	int result = 0;
+	struct zone *zone;
+
+	for_each_zone(zone)
+		result++;
+
+	return result;
+}
+
+int pages_for_zone(struct zone *zone)
+{
+	return (zone->spanned_pages + (PAGE_SIZE << 3) - 1) >>
+			(PAGE_SHIFT + 3);
+}
+
+int page_zone_number(struct page *page)
+{
+	struct zone *zone, *zone_sought = page_zone(page);
+	int zone_num = 0;
+
+	for_each_zone(zone)
+		if (zone == zone_sought)
+			return zone_num;
+		else
+			zone_num++;
+
+	printk("Was looking for a zone for page %p.\n", page);
+	BUG_ON(1);
+
+	return 0;
+}
+
+/*
+ * dyn_pageflags_pages_per_bitmap
+ *
+ * Number of pages needed for a bitmap covering all zones.
+ */
+int dyn_pageflags_pages_per_bitmap(void)
+{
+	int total = 0;
+	struct zone *zone;
+
+	for_each_zone(zone)
+		total += pages_for_zone(zone);
+
+	return total;
+}
+
+/* clear_map
+ *
+ * Description:	Clear an array used to store local page flags.
+ * Arguments:	dyn_pageflags_t:	The pagemap to be cleared.
+ */
+
+void clear_dyn_pageflags(dyn_pageflags_t pagemap)
+{
+	int i = 0, zone_num = 0;
+	struct zone *zone;
+	
+	for_each_zone(zone) {
+		for (i = 0; i < pages_for_zone(zone); i++)
+			memset((pagemap[zone_num][i]), 0, PAGE_SIZE);
+		zone_num++;
+	}
+}
+
+/* allocate_local_pageflags
+ *
+ * Description:	Allocate a bitmap for local page flags.
+ * Arguments:	dyn_pageflags_t *:	Pointer to the bitmap.
+ */
+int allocate_dyn_pageflags(dyn_pageflags_t *pagemap)
+{
+	int i, zone_num = 0;
+	struct zone *zone;
+
+	BUG_ON(*pagemap);
+
+	*pagemap = kmalloc(sizeof(void *) * num_zones(), GFP_ATOMIC);
+
+	if (!*pagemap)
+		return 1;
+
+	for_each_zone(zone) {
+		int zone_pages = pages_for_zone(zone);
+		(*pagemap)[zone_num] = kmalloc(sizeof(void *) * zone_pages,
+					       GFP_ATOMIC);
+
+		if (!(*pagemap)[zone_num]) {
+			kfree (*pagemap);
+			return 1;
+		}
+
+		for (i = 0; i < zone_pages; i++) {
+			unsigned long address = get_zeroed_page(GFP_ATOMIC);
+			(*pagemap)[zone_num][i] = (unsigned long *) address;
+			if (!(*pagemap)[zone_num][i]) {
+				printk("Error. Unable to allocate memory for "
+					"dynamic pageflags.");
+				free_dyn_pageflags(pagemap);
+				return 1;
+			}
+		}
+		zone_num++;
+	}
+
+	return 0;
+}
+
+/* free_dyn_pageflags
+ *
+ * Description:	Free a dynamically allocated pageflags bitmap.
+ * Arguments:	dyn_pageflags_t *: Pointer to the bitmap being freed.
+ */
+int free_dyn_pageflags(dyn_pageflags_t *pagemap)
+{
+	int i = 0, zone_num = 0;
+	struct zone *zone;
+
+	if (!*pagemap)
+		return 1;
+	
+	for_each_zone(zone) {
+		int zone_pages = pages_for_zone(zone);
+
+		if (!((*pagemap)[zone_num]))
+			continue;
+		for (i = 0; i < zone_pages; i++)
+			if ((*pagemap)[zone_num][i])
+				free_page((unsigned long) (*pagemap)[zone_num][i]);
+	
+		if (PageSlab(virt_to_page((*pagemap)[zone_num])))
+			kfree((*pagemap)[zone_num]);
+		else
+			free_page((unsigned long) (*pagemap)[zone_num]);
+
+		zone_num++;
+	}
+
+	if (PageSlab(virt_to_page((*pagemap))))
+		kfree(*pagemap);
+	else
+		free_page((unsigned long) (*pagemap));
+
+	*pagemap = NULL;
+	return 0;
+}
+
+/*
+ *
+ */
+
+unsigned long *dyn_pageflags_ul_ptr(dyn_pageflags_t *bitmap, struct page *pg)
+{
+	int zone_pfn = page_to_zone_offset(pg);
+	int zone_num = page_zone_number(pg);
+	int pagenum = PAGENUMBER(zone_pfn);
+	int page_offset = PAGEINDEX(zone_pfn);
+	return ((*bitmap)[zone_num][pagenum]) + page_offset;
+}
+
+int test_dynpageflag(dyn_pageflags_t *bitmap, struct page *page)
+{
+	unsigned long *ul = dyn_pageflags_ul_ptr(bitmap, page);
+	int zone_offset = page_to_zone_offset(page);
+	int bit = PAGEBIT(zone_offset);
+	
+	return test_bit(bit, ul);
+}
+
+void set_dynpageflag(dyn_pageflags_t *bitmap, struct page *page)
+{
+	unsigned long *ul = dyn_pageflags_ul_ptr(bitmap, page);
+	int zone_offset = page_to_zone_offset(page);
+	int bit = PAGEBIT(zone_offset);
+	set_bit(bit, ul);
+}
+
+void clear_dynpageflag(dyn_pageflags_t *bitmap, struct page *page)
+{
+	unsigned long *ul = dyn_pageflags_ul_ptr(bitmap, page);
+	int zone_offset = page_to_zone_offset(page);
+	int bit = PAGEBIT(zone_offset);
+	clear_bit(bit, ul);
+}
+
+int get_next_bit_on(dyn_pageflags_t bitmap, int counter)
+{
+	struct page *page;
+	struct zone *zone;
+	unsigned long *ul;
+	int zone_offset, pagebit, zone_num, first;
+
+	BUG_ON(counter == max_pfn);
+
+	first = (counter == -1);
+	
+	if (first)
+		counter = pgdat_list->node_zones->zone_start_pfn;
+
+	page = pfn_to_page(counter);
+	zone = page_zone(page);
+	zone_num = page_zone_number(page);
+
+	if (!first)
+		counter++;
+	
+	zone_offset = counter - zone->zone_start_pfn;
+
+	do {
+		if (zone_offset >= zone->spanned_pages) {
+			do {
+				zone = next_zone(zone);
+				if (!zone)
+					return max_pfn;
+				zone_num++;
+			} while(!zone->spanned_pages);
+
+			counter = zone->zone_start_pfn;
+			zone_offset = 0;
+			page = pfn_to_page(counter);
+		}
+		
+		/*
+		 * This could be optimised, but there are more
+		 * important things and the code is simple at
+		 * the moment 
+		 */
+		ul = (bitmap[zone_num][PAGENUMBER(zone_offset)]) + PAGEINDEX(zone_offset);
+		
+		pagebit = PAGEBIT(zone_offset);
+
+		counter++;
+		zone_offset++;
+		page = pfn_to_page(counter);
+	
+	} while((counter <= max_pfn) && (!test_bit(pagebit, ul)));
+	return counter - 1;
+}
+
diff -urN oldtree/lib/vsprintf.c newtree/lib/vsprintf.c
--- oldtree/lib/vsprintf.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/lib/vsprintf.c	2006-01-28 17:08:36.282719832 +0000
@@ -236,6 +236,34 @@
 	return buf;
 }
 
+/*
+ * vsnprintf_used
+ *
+ * Functionality    : Print a string with parameters to a buffer of a 
+ *                    limited size. Unlike vsnprintf, we return the number
+ *                    of bytes actually put in the buffer, not the number
+ *                    that would have been put in if it was big enough.
+ */
+int snprintf_used(char *buffer, int buffer_size, const char *fmt, ...)
+{
+	int result;
+	va_list args;
+
+	if (!buffer_size) {
+		return 0;
+	}
+
+	va_start(args, fmt);
+	result = vsnprintf(buffer, buffer_size, fmt, args);
+	va_end(args);
+
+	if (result > buffer_size) {
+		return buffer_size;
+	}
+
+	return result;
+}
+
 /**
  * vsnprintf - Format a string and place it in a buffer
  * @buf: The buffer to place the result into
diff -urN oldtree/mm/bootmem.c newtree/mm/bootmem.c
--- oldtree/mm/bootmem.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/mm/bootmem.c	2006-01-28 17:08:36.283719680 +0000
@@ -301,12 +301,14 @@
 			page = pfn_to_page(pfn);
 			count += BITS_PER_LONG;
 			__ClearPageReserved(page);
+			ClearPageNosave(page);
 			order = ffs(BITS_PER_LONG) - 1;
 			set_page_refs(page, order);
 			for (j = 1; j < BITS_PER_LONG; j++) {
 				if (j + 16 < BITS_PER_LONG)
 					prefetchw(page + j + 16);
 				__ClearPageReserved(page + j);
+				ClearPageNosave(page + j);
 				set_page_count(page + j, 0);
 			}
 			__free_pages(page, order);
@@ -320,6 +322,7 @@
 				if (v & m) {
 					count++;
 					__ClearPageReserved(page);
+					ClearPageNosave(page);
 					set_page_refs(page, 0);
 					__free_page(page);
 				}
@@ -340,6 +343,7 @@
 	for (i = 0; i < ((bdata->node_low_pfn-(bdata->node_boot_start >> PAGE_SHIFT))/8 + PAGE_SIZE-1)/PAGE_SIZE; i++,page++) {
 		count++;
 		__ClearPageReserved(page);
+		ClearPageNosave(page);
 		set_page_count(page, 1);
 		__free_page(page);
 	}
diff -urN oldtree/mm/memory.c newtree/mm/memory.c
--- oldtree/mm/memory.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/mm/memory.c	2006-01-28 17:08:36.284719528 +0000
@@ -950,6 +950,15 @@
 	return page;
 }
 
+/*
+ * We want the address of the page for Suspend2 to mark as being in pageset1. 
+ */
+
+struct page *suspend2_follow_page(struct mm_struct *mm, unsigned long address)
+{
+	return follow_page(mm->mmap, address, 0);
+}
+
 int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		unsigned long start, int len, int write, int force,
 		struct page **pages, struct vm_area_struct **vmas)
diff -urN oldtree/mm/page_alloc.c newtree/mm/page_alloc.c
--- oldtree/mm/page_alloc.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/mm/page_alloc.c	2006-01-28 17:08:36.285719376 +0000
@@ -25,6 +25,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/suspend.h>
+#include <linux/freezer.h>
 #include <linux/pagevec.h>
 #include <linux/blkdev.h>
 #include <linux/slab.h>
@@ -920,8 +921,8 @@
 
 	/* This allocation should allow future memory freeing. */
 
-	if (((p->flags & PF_MEMALLOC) || unlikely(test_thread_flag(TIF_MEMDIE)))
-			&& !in_interrupt()) {
+	if ((((p->flags & PF_MEMALLOC) || unlikely(test_thread_flag(TIF_MEMDIE))) && 
+				!in_interrupt()) || (test_freezer_state(FREEZER_ON))) {
 		if (!(gfp_mask & __GFP_NOMEMALLOC)) {
 nofail_alloc:
 			/* go through the zonelist yet again, ignoring mins */
@@ -992,6 +993,7 @@
 			do_retry = 1;
 	}
 	if (do_retry) {
+		try_todo_list();
 		blk_congestion_wait(WRITE, HZ/50);
 		goto rebalance;
 	}
diff -urN oldtree/mm/pdflush.c newtree/mm/pdflush.c
--- oldtree/mm/pdflush.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/mm/pdflush.c	2006-01-28 17:08:36.286719224 +0000
@@ -106,7 +106,7 @@
 		spin_unlock_irq(&pdflush_lock);
 
 		schedule();
-		if (try_to_freeze()) {
+		if (try_todo_list()) {
 			spin_lock_irq(&pdflush_lock);
 			continue;
 		}
diff -urN oldtree/mm/swapfile.c newtree/mm/swapfile.c
--- oldtree/mm/swapfile.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/mm/swapfile.c	2006-01-28 17:08:36.287719072 +0000
@@ -1155,6 +1155,7 @@
 	swap_file = p->swap_file;
 	p->swap_file = NULL;
 	p->max = 0;
+	p->bdev = NULL;
 	swap_map = p->swap_map;
 	p->swap_map = NULL;
 	p->flags = 0;
diff -urN oldtree/mm/vmscan.c newtree/mm/vmscan.c
--- oldtree/mm/vmscan.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/mm/vmscan.c	2006-01-28 17:08:36.288718920 +0000
@@ -1244,7 +1244,8 @@
 	for ( ; ; ) {
 		unsigned long new_order;
 
-		try_to_freeze();
+		if (try_todo_list())
+			pgdat->kswapd_max_order = 0;
 
 		prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
 		new_order = pgdat->kswapd_max_order;
diff -urN oldtree/net/rxrpc/krxiod.c newtree/net/rxrpc/krxiod.c
--- oldtree/net/rxrpc/krxiod.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/net/rxrpc/krxiod.c	2006-01-28 17:08:36.289718768 +0000
@@ -138,7 +138,7 @@
 
 		_debug("### End Work");
 
-		try_to_freeze();
+		try_todo_list();
 
                 /* discard pending signals */
 		rxrpc_discard_my_signals();
diff -urN oldtree/net/rxrpc/krxsecd.c newtree/net/rxrpc/krxsecd.c
--- oldtree/net/rxrpc/krxsecd.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/net/rxrpc/krxsecd.c	2006-01-28 17:08:36.289718768 +0000
@@ -107,7 +107,7 @@
 
 		_debug("### End Inbound Calls");
 
-		try_to_freeze();
+		try_todo_list();
 
                 /* discard pending signals */
 		rxrpc_discard_my_signals();
diff -urN oldtree/net/rxrpc/krxtimod.c newtree/net/rxrpc/krxtimod.c
--- oldtree/net/rxrpc/krxtimod.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/net/rxrpc/krxtimod.c	2006-01-28 17:08:36.290718616 +0000
@@ -90,7 +90,7 @@
 			complete_and_exit(&krxtimod_dead, 0);
 		}
 
-		try_to_freeze();
+		try_todo_list();
 
 		/* discard pending signals */
 		rxrpc_discard_my_signals();
diff -urN oldtree/net/sunrpc/sched.c newtree/net/sunrpc/sched.c
--- oldtree/net/sunrpc/sched.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/net/sunrpc/sched.c	2006-01-28 17:08:36.290718616 +0000
@@ -656,6 +656,9 @@
 
 		/* sync task: sleep here */
 		dprintk("RPC: %4d sync task going to sleep\n", task->tk_pid);
+
+		try_todo_list();
+
 		/* Note: Caller should be using rpc_clnt_sigmask() */
 		status = out_of_line_wait_on_bit(&task->tk_runstate,
 				RPC_TASK_QUEUED, rpc_wait_bit_interruptible,
@@ -698,6 +701,7 @@
 {
 	BUG_ON(task->tk_active);
 
+	try_todo_list();
 	task->tk_active = 1;
 	rpc_set_running(task);
 	return __rpc_execute(task);
diff -urN oldtree/net/sunrpc/svcsock.c newtree/net/sunrpc/svcsock.c
--- oldtree/net/sunrpc/svcsock.c	2006-01-28 16:36:00.000000000 +0000
+++ newtree/net/sunrpc/svcsock.c	2006-01-28 17:08:36.291718464 +0000
@@ -1177,7 +1177,7 @@
 	arg->len = (pages-1)*PAGE_SIZE;
 	arg->tail[0].iov_len = 0;
 
-	try_to_freeze();
+	try_todo_list();
 	cond_resched();
 	if (signalled())
 		return -EINTR;
@@ -1219,7 +1219,7 @@
 
 		schedule_timeout(timeout);
 
-		try_to_freeze();
+		try_todo_list();
 
 		spin_lock_bh(&serv->sv_lock);
 		remove_wait_queue(&rqstp->rq_wait, &wait);