diff -urN oldtree/Documentation/kernel-parameters.txt newtree/Documentation/kernel-parameters.txt
--- oldtree/Documentation/kernel-parameters.txt	2006-02-18 15:18:20.484203176 +0000
+++ newtree/Documentation/kernel-parameters.txt	2006-02-18 15:24:31.288832304 +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.
@@ -1039,6 +1040,8 @@
 	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).
@@ -1296,6 +1299,11 @@
 	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/kernel-parameters.txt.orig newtree/Documentation/kernel-parameters.txt.orig
--- oldtree/Documentation/kernel-parameters.txt.orig	1970-01-01 00:00:00.000000000 +0000
+++ newtree/Documentation/kernel-parameters.txt.orig	2006-02-18 15:18:20.000000000 +0000
@@ -0,0 +1,1664 @@
+February 2003             Kernel Parameters                     v2.5.59
+                          ~~~~~~~~~~~~~~~~~
+
+The following is a consolidated list of the kernel parameters as implemented
+(mostly) by the __setup() macro and sorted into English Dictionary order
+(defined as ignoring all punctuation and sorting digits before letters in a
+case insensitive manner), and with descriptions where known.
+
+Module parameters for loadable modules are specified only as the
+parameter name with optional '=' and value as appropriate, such as:
+
+	modprobe usbcore blinkenlights=1
+
+Module parameters for modules that are built into the kernel image
+are specified on the kernel command line with the module name plus
+'.' plus parameter name, with '=' and value if appropriate, such as:
+
+	usbcore.blinkenlights=1
+
+The text in square brackets at the beginning of the description states the
+restrictions on the kernel for the said kernel parameter to be valid. The
+restrictions referred to are that the relevant option is valid if:
+
+	ACPI	ACPI support is enabled.
+	ALSA	ALSA sound support is enabled.
+	APIC	APIC support is enabled.
+	APM	Advanced Power Management support is enabled.
+	AX25	Appropriate AX.25 support is enabled.
+	CD	Appropriate CD support is enabled.
+	DEVFS	devfs support is enabled.
+	DRM	Direct Rendering Management support is enabled.
+	EDD	BIOS Enhanced Disk Drive Services (EDD) is enabled
+	EFI	EFI Partitioning (GPT) is enabled
+	EIDE	EIDE/ATAPI support is enabled.
+	FB	The frame buffer device is enabled.
+	HW	Appropriate hardware is enabled.
+	IA-32	IA-32 aka i386 architecture is enabled.
+	IA-64	IA-64 architecture is enabled.
+	IOSCHED	More than one I/O scheduler is enabled.
+	IP_PNP	IP DHCP, BOOTP, or RARP is enabled.
+	ISAPNP	ISA PnP code is enabled.
+	ISDN	Appropriate ISDN support is enabled.
+	JOY	Appropriate joystick support is enabled.
+	LP	Printer support is enabled.
+	LOOP	Loopback device support is enabled.
+	M68k	M68k architecture is enabled.
+			These options have more detailed description inside of
+			Documentation/m68k/kernel-options.txt.
+	MCA	MCA bus support is enabled.
+	MDA	MDA console support is enabled.
+	MOUSE	Appropriate mouse support is enabled.
+	MTD	MTD support is enabled.
+	NET	Appropriate network support is enabled.
+	NUMA	NUMA support is enabled.
+	NFS	Appropriate NFS support is enabled.
+	OSS	OSS sound support is enabled.
+	PARIDE	The ParIDE subsystem is enabled.
+	PARISC	The PA-RISC architecture is enabled.
+	PCI	PCI bus support is enabled.
+	PCMCIA	The PCMCIA subsystem is enabled.
+	PNP	Plug & Play support is enabled.
+	PPC	PowerPC architecture is enabled.
+	PPT	Parallel port support is enabled.
+	PS2	Appropriate PS/2 support is enabled.
+	RAM	RAM disk support is enabled.
+	S390	S390 architecture is enabled.
+	SCSI	Appropriate SCSI support is enabled.
+			A lot of drivers has their options described inside of
+			Documentation/scsi/.
+	SELINUX SELinux support is enabled.
+	SERIAL	Serial support is enabled.
+	SMP	The kernel is an SMP kernel.
+	SPARC	Sparc architecture is enabled.
+	SWSUSP	Software suspend is enabled.
+	TS	Appropriate touchscreen support is enabled.
+	USB	USB support is enabled.
+	USBHID	USB Human Interface Device support is enabled.
+	V4L	Video For Linux support is enabled.
+	VGA	The VGA console has been enabled.
+	VT	Virtual terminal support is enabled.
+	WDT	Watchdog support is enabled.
+	XT	IBM PC/XT MFM hard disk support is enabled.
+	X86-64	X86-64 architecture is enabled.
+			More X86-64 boot options can be found in
+			Documentation/x86_64/boot-options.txt .
+
+In addition, the following text indicates that the option:
+
+	BUGS=	Relates to possible processor bugs on the said processor.
+	KNL	Is a kernel start-up parameter.
+	BOOT	Is a boot loader parameter.
+
+Parameters denoted with BOOT are actually interpreted by the boot
+loader, and have no meaning to the kernel directly.
+Do not modify the syntax of boot loader parameters without extreme
+need or coordination with <Documentation/i386/boot.txt>.
+
+Note that ALL kernel parameters listed below are CASE SENSITIVE, and that
+a trailing = on the name of any parameter states that that parameter will
+be entered as an environment variable, whereas its absence indicates that
+it will appear as a kernel argument readable via /proc/cmdline by programs
+running once the system is up.
+
+	53c7xx=		[HW,SCSI] Amiga SCSI controllers
+			See header of drivers/scsi/53c7xx.c.
+			See also Documentation/scsi/ncr53c7xx.txt.
+
+	acpi=		[HW,ACPI] Advanced Configuration and Power Interface
+			Format: { force | off | ht | strict | noirq }
+			force -- enable ACPI if default was off
+			off -- disable ACPI if default was on
+			noirq -- do not use ACPI for IRQ routing
+			ht -- run only enough ACPI to enable Hyper Threading
+			strict -- Be less tolerant of platforms that are not
+				strictly ACPI specification compliant.
+
+			See also Documentation/pm.txt, pci=noacpi
+
+	acpi_sleep=	[HW,ACPI] Sleep options
+			Format: { s3_bios, s3_mode }
+			See Documentation/power/video.txt
+
+	acpi_sci=	[HW,ACPI] ACPI System Control Interrupt trigger mode
+			Format: { level | edge | high | low }
+
+	acpi_irq_balance [HW,ACPI]
+			ACPI will balance active IRQs
+			default in APIC mode
+
+	acpi_irq_nobalance [HW,ACPI]
+			ACPI will not move active IRQs (default)
+			default in PIC mode
+
+	acpi_irq_pci=	[HW,ACPI] If irq_balance, clear listed IRQs for
+			use by PCI
+			Format: <irq>,<irq>...
+
+	acpi_irq_isa=	[HW,ACPI] If irq_balance, mark listed IRQs used by ISA
+			Format: <irq>,<irq>...
+
+	acpi_osi=	[HW,ACPI] empty param disables _OSI
+
+	acpi_serialize	[HW,ACPI] force serialization of AML methods
+
+	acpi_skip_timer_override [HW,ACPI]
+			Recognize and ignore IRQ0/pin2 Interrupt Override.
+			For broken nForce2 BIOS resulting in XT-PIC timer.
+
+	acpi_dbg_layer=	[HW,ACPI]
+			Format: <int>
+			Each bit of the <int> indicates an ACPI debug layer,
+			1: enable, 0: disable. It is useful for boot time
+			debugging. After system has booted up, it can be set
+			via /proc/acpi/debug_layer.
+
+	acpi_dbg_level=	[HW,ACPI]
+			Format: <int>
+			Each bit of the <int> indicates an ACPI debug level,
+			1: enable, 0: disable. It is useful for boot time
+			debugging. After system has booted up, it can be set
+			via /proc/acpi/debug_level.
+
+	acpi_fake_ecdt	[HW,ACPI] Workaround failure due to BIOS lacking ECDT
+
+	acpi_generic_hotkey [HW,ACPI]
+			Allow consolidated generic hotkey driver to
+			override platform specific driver.
+			See also Documentation/acpi-hotkey.txt.
+
+	enable_timer_pin_1 [i386,x86-64]
+			Enable PIN 1 of APIC timer
+			Can be useful to work around chipset bugs
+			(in particular on some ATI chipsets).
+			The kernel tries to set a reasonable default.
+
+	disable_timer_pin_1 [i386,x86-64]
+			Disable PIN 1 of APIC timer
+			Can be useful to work around chipset bugs.
+
+	ad1816=		[HW,OSS]
+			Format: <io>,<irq>,<dma>,<dma2>
+			See also Documentation/sound/oss/AD1816.
+
+	ad1848=		[HW,OSS]
+			Format: <io>,<irq>,<dma>,<dma2>,<type>
+
+	adlib=		[HW,OSS]
+			Format: <io>
+
+	advansys=	[HW,SCSI]
+			See header of drivers/scsi/advansys.c.
+
+	advwdt=		[HW,WDT] Advantech WDT
+			Format: <iostart>,<iostop>
+
+	aedsp16=	[HW,OSS] Audio Excel DSP 16
+			Format: <io>,<irq>,<dma>,<mss_io>,<mpu_io>,<mpu_irq>
+			See also header of sound/oss/aedsp16.c.
+
+	aha152x=	[HW,SCSI]
+			See Documentation/scsi/aha152x.txt.
+
+	aha1542=	[HW,SCSI]
+			Format: <portbase>[,<buson>,<busoff>[,<dmaspeed>]]
+
+	aic7xxx=	[HW,SCSI]
+			See Documentation/scsi/aic7xxx.txt.
+
+	aic79xx=	[HW,SCSI]
+			See Documentation/scsi/aic79xx.txt.
+
+	amijoy.map=	[HW,JOY] Amiga joystick support
+			Map of devices attached to JOY0DAT and JOY1DAT
+			Format: <a>,<b>
+			See also Documentation/kernel/input/joystick.txt
+
+	analog.map=	[HW,JOY] Analog joystick and gamepad support
+			Specifies type or capabilities of an analog joystick
+			connected to one of 16 gameports
+			Format: <type1>,<type2>,..<type16>
+
+	apc=		[HW,SPARC]
+			Power management functions (SPARCstation-4/5 + deriv.)
+			Format: noidle
+			Disable APC CPU standby support. SPARCstation-Fox does
+			not play well with APC CPU idle - disable it if you have
+			APC and your system crashes randomly.
+
+	apic=		[APIC,i386] Change the output verbosity whilst booting
+			Format: { quiet (default) | verbose | debug }
+			Change the amount of debugging information output
+			when initialising the APIC and IO-APIC components.
+
+	apm=		[APM] Advanced Power Management
+			See header of arch/i386/kernel/apm.c.
+
+	applicom=	[HW]
+			Format: <mem>,<irq>
+
+	arcrimi=	[HW,NET] ARCnet - "RIM I" (entirely mem-mapped) cards
+			Format: <io>,<irq>,<nodeID>
+
+	ataflop=	[HW,M68k]
+
+	atarimouse=	[HW,MOUSE] Atari Mouse
+
+	atascsi=	[HW,SCSI] Atari SCSI
+
+	atkbd.extra=	[HW] Enable extra LEDs and keys on IBM RapidAccess,
+			EzKey and similar keyboards
+
+	atkbd.reset=	[HW] Reset keyboard during initialization
+
+	atkbd.set=	[HW] Select keyboard code set
+			Format: <int> (2 = AT (default), 3 = PS/2)
+
+	atkbd.scroll=	[HW] Enable scroll wheel on MS Office and similar
+			keyboards
+
+	atkbd.softraw=	[HW] Choose between synthetic and real raw mode
+			Format: <bool> (0 = real, 1 = synthetic (default))
+
+	atkbd.softrepeat= [HW]
+			Use software keyboard repeat
+
+	autotest	[IA64]
+
+	awe=		[HW,OSS] AWE32/SB32/AWE64 wave table synth
+			Format: <io>,<memsize>,<isapnp>
+
+	aztcd=		[HW,CD] Aztech CD268 CDROM driver
+			Format: <io>,0x79 (?)
+
+	baycom_epp=	[HW,AX25]
+			Format: <io>,<mode>
+
+	baycom_par=	[HW,AX25] BayCom Parallel Port AX.25 Modem
+			Format: <io>,<mode>
+			See header of drivers/net/hamradio/baycom_par.c.
+
+	baycom_ser_fdx=	[HW,AX25]
+			BayCom Serial Port AX.25 Modem (Full Duplex Mode)
+			Format: <io>,<irq>,<mode>[,<baud>]
+			See header of drivers/net/hamradio/baycom_ser_fdx.c.
+
+	baycom_ser_hdx=	[HW,AX25]
+			BayCom Serial Port AX.25 Modem (Half Duplex Mode)
+			Format: <io>,<irq>,<mode>
+			See header of drivers/net/hamradio/baycom_ser_hdx.c.
+
+	blkmtd_device=	[HW,MTD]
+	blkmtd_erasesz=
+	blkmtd_ro=
+	blkmtd_bs=
+	blkmtd_count=
+
+	bttv.card=	[HW,V4L] bttv (bt848 + bt878 based grabber cards)
+	bttv.radio=	Most important insmod options are available as
+			kernel args too.
+	bttv.pll=	See Documentation/video4linux/bttv/Insmod-options
+	bttv.tuner=	and Documentation/video4linux/bttv/CARDLIST
+
+	BusLogic=	[HW,SCSI]
+			See drivers/scsi/BusLogic.c, comment before function
+			BusLogic_ParseDriverOptions().
+
+	c101=		[NET] Moxa C101 synchronous serial card
+
+	cachesize=	[BUGS=IA-32] Override level 2 CPU cache size detection.
+			Sometimes CPU hardware bugs make them report the cache
+			size incorrectly. The kernel will attempt work arounds
+			to fix known problems, but for some CPUs it is not
+			possible to determine what the correct size should be.
+			This option provides an override for these situations.
+
+	cdu31a=		[HW,CD]
+			Format: <io>,<irq>[,PAS]
+			See header of drivers/cdrom/cdu31a.c.
+
+	chandev=	[HW,NET] Generic channel device initialisation
+
+	checkreqprot	[SELINUX] Set initial checkreqprot flag value.
+			Format: { "0" | "1" }
+			See security/selinux/Kconfig help text.
+			0 -- check protection applied by kernel (includes
+				any implied execute protection).
+			1 -- check protection requested by application.
+			Default value is set via a kernel config option.
+			Value can be changed at runtime via
+				/selinux/checkreqprot.
+
+ 	clock=		[BUGS=IA-32,HW] gettimeofday timesource override.
+			Forces specified timesource (if avaliable) to be used
+			when calculating gettimeofday(). If specicified
+			timesource is not avalible, it defaults to PIT.
+			Format: { pit | tsc | cyclone | pmtmr }
+
+	hpet=		[IA-32,HPET] option to disable HPET and use PIT.
+			Format: disable
+
+	cm206=		[HW,CD]
+			Format: { auto | [<io>,][<irq>] }
+
+	com20020=	[HW,NET] ARCnet - COM20020 chipset
+			Format:
+			<io>[,<irq>[,<nodeID>[,<backplane>[,<ckp>[,<timeout>]]]]]
+
+	com90io=	[HW,NET] ARCnet - COM90xx chipset (IO-mapped buffers)
+			Format: <io>[,<irq>]
+
+	com90xx=	[HW,NET]
+			ARCnet - COM90xx chipset (memory-mapped buffers)
+			Format: <io>[,<irq>[,<memstart>]]
+
+	condev=		[HW,S390] console device
+	conmode=
+
+	console=	[KNL] Output console device and options.
+
+		tty<n>	Use the virtual console device <n>.
+
+		ttyS<n>[,options]
+			Use the specified serial port.  The options are of
+			the form "bbbbpn", where "bbbb" is the baud rate,
+			"p" is parity ("n", "o", or "e"), and "n" is bits.
+			Default is "9600n8".
+
+			See also Documentation/serial-console.txt.
+
+		uart,io,<addr>[,options]
+		uart,mmio,<addr>[,options]
+			Start an early, polled-mode console on the 8250/16550
+			UART at the specified I/O port or MMIO address,
+			switching to the matching ttyS device later.  The
+			options are the same as for ttyS, above.
+
+	cpcihp_generic=	[HW,PCI] Generic port I/O CompactPCI driver
+			Format:
+			<first_slot>,<last_slot>,<port>,<enum_bit>[,<debug>]
+
+	cpia_pp=	[HW,PPT]
+			Format: { parport<nr> | auto | none }
+
+	crashkernel=nn[KMG]@ss[KMG]
+			[KNL] Reserve a chunk of physical memory to
+			hold a kernel to switch to with kexec on panic.
+
+	cs4232=		[HW,OSS]
+			Format: <io>,<irq>,<dma>,<dma2>,<mpuio>,<mpuirq>
+
+	cs89x0_dma=	[HW,NET]
+			Format: <dma>
+
+	cs89x0_media=	[HW,NET]
+			Format: { rj45 | aui | bnc }
+
+	cyclades=	[HW,SERIAL] Cyclades multi-serial port adapter.
+
+	dasd=		[HW,NET]
+			See header of drivers/s390/block/dasd_devmap.c.
+
+	db9.dev[2|3]=	[HW,JOY] Multisystem joystick support via parallel port
+			(one device per port)
+			Format: <port#>,<type>
+			See also Documentation/input/joystick-parport.txt
+
+	debug		[KNL] Enable kernel debugging (events log level).
+
+	decnet=		[HW,NET]
+			Format: <area>[,<node>]
+			See also Documentation/networking/decnet.txt.
+
+	devfs=		[DEVFS]
+			See Documentation/filesystems/devfs/boot-options.
+
+	dhash_entries=	[KNL]
+			Set number of hash buckets for dentry cache.
+
+	digi=		[HW,SERIAL]
+			IO parameters + enable/disable command.
+
+	digiepca=	[HW,SERIAL]
+			See drivers/char/README.epca and
+			Documentation/digiepca.txt.
+
+	dmascc=		[HW,AX25,SERIAL] AX.25 Z80SCC driver with DMA
+			support available.
+			Format: <io_dev0>[,<io_dev1>[,..<io_dev32>]]
+
+	dmasound=	[HW,OSS] Sound subsystem buffers
+
+	dscc4.setup=	[NET]
+
+	dtc3181e=	[HW,SCSI]
+
+	earlyprintk=	[IA-32,X86-64]
+			earlyprintk=vga
+			earlyprintk=serial[,ttySn[,baudrate]]
+
+			Append ",keep" to not disable it when the real console
+			takes over.
+
+			Only vga or serial at a time, not both.
+
+			Currently only ttyS0 and ttyS1 are supported.
+
+			Interaction with the standard serial driver is not
+			very good.
+
+			The VGA output is eventually overwritten by the real
+			console.
+
+	eata=		[HW,SCSI]
+
+	ec_intr=	[HW,ACPI] ACPI Embedded Controller interrupt mode
+			Format: <int>
+			0: polling mode
+			non-0: interrupt mode (default)
+
+	eda=		[HW,PS2]
+
+	edb=		[HW,PS2]
+
+	edd=		[EDD]
+			Format: {"of[f]" | "sk[ipmbr]"}
+			See comment in arch/i386/boot/edd.S
+
+	eicon=		[HW,ISDN]
+			Format: <id>,<membase>,<irq>
+
+	eisa_irq_edge=	[PARISC,HW]
+			See header of drivers/parisc/eisa.c.
+
+	elanfreq=	[IA-32]
+			See comment before function elanfreq_setup() in
+			arch/i386/kernel/cpu/cpufreq/elanfreq.c.
+
+	elevator=	[IOSCHED]
+			Format: {"anticipatory" | "cfq" | "deadline" | "noop"}
+			See Documentation/block/as-iosched.txt and
+			Documentation/block/deadline-iosched.txt for details.
+
+	elfcorehdr=	[IA-32, X86_64]
+			Specifies physical address of start of kernel core
+			image elf header. Generally kexec loader will
+			pass this option to capture kernel.
+			See Documentation/kdump/kdump.txt for details.
+
+	enforcing	[SELINUX] Set initial enforcing status.
+			Format: {"0" | "1"}
+			See security/selinux/Kconfig help text.
+			0 -- permissive (log only, no denials).
+			1 -- enforcing (deny and log).
+			Default value is 0.
+			Value can be changed at runtime via /selinux/enforce.
+
+	es1370=		[HW,OSS]
+			Format: <lineout>[,<micbias>]
+			See also header of sound/oss/es1370.c.
+
+	es1371=		[HW,OSS]
+			Format: <spdif>,[<nomix>,[<amplifier>]]
+			See also header of sound/oss/es1371.c.
+
+	ether=		[HW,NET] Ethernet cards parameters
+			This option is obsoleted by the "netdev=" option, which
+			has equivalent usage. See its documentation for details.
+
+	eurwdt=		[HW,WDT] Eurotech CPU-1220/1410 onboard watchdog.
+			Format: <io>[,<irq>]
+
+	fd_mcs=		[HW,SCSI]
+			See header of drivers/scsi/fd_mcs.c.
+
+	fdomain=	[HW,SCSI]
+			See header of drivers/scsi/fdomain.c.
+
+	floppy=		[HW]
+			See Documentation/floppy.txt.
+
+	ftape=		[HW] Floppy Tape subsystem debugging options.
+			See Documentation/ftape.txt.
+
+	gamecon.map[2|3]=
+			[HW,JOY] Multisystem joystick and NES/SNES/PSX pad
+			support via parallel port (up to 5 devices per port)
+			Format: <port#>,<pad1>,<pad2>,<pad3>,<pad4>,<pad5>
+			See also Documentation/input/joystick-parport.txt
+
+	gamma=		[HW,DRM]
+
+	gdth=		[HW,SCSI]
+			See header of drivers/scsi/gdth.c.
+
+	gpt		[EFI] Forces disk with valid GPT signature but
+			invalid Protective MBR to be treated as GPT.
+
+	gscd=		[HW,CD]
+			Format: <io>
+
+	gt96100eth=	[NET] MIPS GT96100 Advanced Communication Controller
+
+	gus=		[HW,OSS]
+			Format: <io>,<irq>,<dma>,<dma16>
+
+	gvp11=		[HW,SCSI]
+
+	hashdist=	[KNL,NUMA] Large hashes allocated during boot
+			are distributed across NUMA nodes.  Defaults on
+			for IA-64, off otherwise.
+			Format: 0 | 1 (for off | on)
+
+	hcl=		[IA-64] SGI's Hardware Graph compatibility layer
+
+	hd=		[EIDE] (E)IDE hard drive subsystem geometry
+			Format: <cyl>,<head>,<sect>
+
+	hd?=		[HW] (E)IDE subsystem
+	hd?lun=		See Documentation/ide.txt.
+
+	highmem=nn[KMG]	[KNL,BOOT] forces the highmem zone to have an exact
+			size of <nn>. This works even on boxes that have no
+			highmem otherwise. This also works to reduce highmem
+			size on bigger boxes.
+
+	hisax=		[HW,ISDN]
+			See Documentation/isdn/README.HiSax.
+
+	hugepages=	[HW,IA-32,IA-64] Maximal number of HugeTLB pages.
+
+	noirqbalance	[IA-32,SMP,KNL] Disable kernel irq balancing
+
+	i8042.direct	[HW] Put keyboard port into non-translated mode
+	i8042.dumbkbd	[HW] Pretend that controlled can only read data from
+			     keyboard and can not control its state
+			     (Don't attempt to blink the leds)
+	i8042.noaux	[HW] Don't check for auxiliary (== mouse) port
+	i8042.nokbd	[HW] Don't check/create keyboard port
+	i8042.nomux	[HW] Don't check presence of an active multiplexing
+			     controller
+	i8042.nopnp	[HW] Don't use ACPIPnP / PnPBIOS to discover KBD/AUX
+			     controllers
+	i8042.panicblink=
+			[HW] Frequency with which keyboard LEDs should blink
+			     when kernel panics (default is 0.5 sec)
+	i8042.reset	[HW] Reset the controller during init and cleanup
+	i8042.unlock	[HW] Unlock (ignore) the keylock
+
+	i810=		[HW,DRM]
+
+	i8k.ignore_dmi	[HW] Continue probing hardware even if DMI data
+			indicates that the driver is running on unsupported
+			hardware.
+	i8k.force	[HW] Activate i8k driver even if SMM BIOS signature
+			does not match list of supported models.
+	i8k.power_status
+			[HW] Report power status in /proc/i8k
+			(disabled by default)
+	i8k.restricted	[HW] Allow controlling fans only if SYS_ADMIN
+			capability is set.
+
+	ibmmcascsi=	[HW,MCA,SCSI] IBM MicroChannel SCSI adapter
+			See Documentation/mca.txt.
+
+	icn=		[HW,ISDN]
+			Format: <io>[,<membase>[,<icn_id>[,<icn_id2>]]]
+
+	ide=		[HW] (E)IDE subsystem
+			Format: ide=nodma or ide=doubler or ide=reverse
+			See Documentation/ide.txt.
+
+	ide?=		[HW] (E)IDE subsystem
+			Format: ide?=noprobe or chipset specific parameters.
+			See Documentation/ide.txt.
+
+	idebus=		[HW] (E)IDE subsystem - VLB/PCI bus speed
+			See Documentation/ide.txt.
+
+	idle=		[HW]
+			Format: idle=poll or idle=halt
+
+	ihash_entries=	[KNL]
+			Set number of hash buckets for inode cache.
+
+	in2000=		[HW,SCSI]
+			See header of drivers/scsi/in2000.c.
+
+	init=		[KNL]
+			Format: <full_path>
+			Run specified binary instead of /sbin/init as init
+			process.
+
+	initcall_debug	[KNL] Trace initcalls as they are executed.  Useful
+			for working out where the kernel is dying during
+			startup.
+
+	initrd=		[BOOT] Specify the location of the initial ramdisk
+
+	inport.irq=	[HW] Inport (ATI XL and Microsoft) busmouse driver
+			Format: <irq>
+
+	combined_mode=	[HW] control which driver uses IDE ports in combined
+			mode: legacy IDE driver, libata, or both
+			(in the libata case, libata.atapi_enabled=1 may be
+			useful as well).  Note that using the ide or libata
+			options may affect your device naming (e.g. by
+			changing hdc to sdb).
+			Format: combined (default), ide, or libata
+
+	inttest=	[IA64]
+
+	io7=		[HW] IO7 for Marvel based alpha systems
+			See comment before marvel_specify_io7 in
+			arch/alpha/kernel/core_marvel.c.
+
+	ip=		[IP_PNP]
+			See Documentation/nfsroot.txt.
+
+	ip2=		[HW] Set IO/IRQ pairs for up to 4 IntelliPort boards
+			See comment before ip2_setup() in drivers/char/ip2.c.
+
+	ips=		[HW,SCSI] Adaptec / IBM ServeRAID controller
+			See header of drivers/scsi/ips.c.
+
+	irqfixup	[HW]
+			When an interrupt is not handled search all handlers
+			for it. Intended to get systems with badly broken
+			firmware running.
+
+	irqpoll		[HW]
+			When an interrupt is not handled search all handlers
+			for it. Also check all handlers each timer
+			interrupt. Intended to get systems with badly broken
+			firmware running.
+
+	isapnp=		[ISAPNP]
+			Format: <RDP>,<reset>,<pci_scan>,<verbosity>
+
+	isolcpus=	[KNL,SMP] Isolate CPUs from the general scheduler.
+			Format: <cpu number>,...,<cpu number>
+			This option can be used to specify one or more CPUs
+			to isolate from the general SMP balancing and scheduling
+			algorithms. The only way to move a process onto or off
+			an "isolated" CPU is via the CPU affinity syscalls.
+			<cpu number> begins at 0 and the maximum value is
+			"number of CPUs in system - 1".
+
+			This option is the preferred way to isolate CPUs. The
+			alternative -- manually setting the CPU mask of all
+			tasks in the system -- can cause problems and
+			suboptimal load balancer performance.
+
+	isp16=		[HW,CD]
+			Format: <io>,<irq>,<dma>,<setup>
+
+	iucv=		[HW,NET]
+
+	js=		[HW,JOY] Analog joystick
+			See Documentation/input/joystick.txt.
+
+	keepinitrd	[HW,ARM]
+
+	kstack=N	[IA-32,X86-64] Print N words from the kernel stack
+			in oops dumps.
+
+	l2cr=		[PPC]
+
+	lapic		[IA-32,APIC] Enable the local APIC even if BIOS
+			disabled it.
+
+	lasi=		[HW,SCSI] PARISC LASI driver for the 53c700 chip
+			Format: addr:<io>,irq:<irq>
+
+	llsc*=		[IA64] See function print_params() in
+			arch/ia64/sn/kernel/llsc4.c.
+
+	load_ramdisk=	[RAM] List of ramdisks to load from floppy
+			See Documentation/ramdisk.txt.
+
+	lockd.nlm_grace_period=P  [NFS] Assign grace period.
+			Format: <integer>
+
+	lockd.nlm_tcpport=N	[NFS] Assign TCP port.
+			Format: <integer>
+
+	lockd.nlm_timeout=T	[NFS] Assign timeout value.
+			Format: <integer>
+
+	lockd.nlm_udpport=M	[NFS] Assign UDP port.
+			Format: <integer>
+
+	logibm.irq=	[HW,MOUSE] Logitech Bus Mouse Driver
+			Format: <irq>
+
+	loglevel=	All Kernel Messages with a loglevel smaller than the
+			console loglevel will be printed to the console. It can
+			also be changed with klogd or other programs. The
+			loglevels are defined as follows:
+
+			0 (KERN_EMERG)		system is unusable
+			1 (KERN_ALERT)		action must be taken immediately
+			2 (KERN_CRIT)		critical conditions
+			3 (KERN_ERR)		error conditions
+			4 (KERN_WARNING)	warning conditions
+			5 (KERN_NOTICE)		normal but significant condition
+			6 (KERN_INFO)		informational
+			7 (KERN_DEBUG)		debug-level messages
+
+	log_buf_len=n	Sets the size of the printk ring buffer, in bytes.
+			Format: { n | nk | nM }
+			n must be a power of two.  The default size
+			is set in the kernel config file.
+
+	lp=0		[LP]	Specify parallel ports to use, e.g,
+	lp=port[,port...]	lp=none,parport0 (lp0 not configured, lp1 uses
+	lp=reset		first parallel port). 'lp=0' disables the
+	lp=auto			printer driver. 'lp=reset' (which can be
+				specified in addition to the ports) causes
+				attached printers to be reset. Using
+				lp=port1,port2,... specifies the parallel ports
+				to associate lp devices with, starting with
+				lp0. A port specification may be 'none' to skip
+				that lp device, or a parport name such as
+				'parport0'. Specifying 'lp=auto' instead of a
+				port specification list means that device IDs
+				from each port should be examined, to see if
+				an IEEE 1284-compliant printer is attached; if
+				so, the driver will manage that printer.
+				See also header of drivers/char/lp.c.
+
+	lpj=n		[KNL]
+			Sets loops_per_jiffy to given constant, thus avoiding
+			time-consuming boot-time autodetection (up to 250 ms per
+			CPU). 0 enables autodetection (default). To determine
+			the correct value for your kernel, boot with normal
+			autodetection and see what value is printed. Note that
+			on SMP systems the preset will be applied to all CPUs,
+			which is likely to cause problems if your CPUs need
+			significantly divergent settings. An incorrect value
+			will cause delays in the kernel to be wrong, leading to
+			unpredictable I/O errors and other breakage. Although
+			unlikely, in the extreme case this might damage your
+			hardware.
+
+	ltpc=		[NET]
+			Format: <io>,<irq>,<dma>
+
+	mac5380=	[HW,SCSI] Format:
+			<can_queue>,<cmd_per_lun>,<sg_tablesize>,<hostid>,<use_tags>
+
+	mac53c9x=	[HW,SCSI] Format:
+			<num_esps>,<disconnect>,<nosync>,<can_queue>,<cmd_per_lun>,<sg_tablesize>,<hostid>,<use_tags>
+
+	machvec=	[IA64] Force the use of a particular machine-vector
+			(machvec) in a generic kernel.
+			Example: machvec=hpzx1_swiotlb
+
+	mad16=		[HW,OSS] Format:
+			<io>,<irq>,<dma>,<dma16>,<mpu_io>,<mpu_irq>,<joystick>
+
+	maui=		[HW,OSS]
+			Format: <io>,<irq>
+
+	max_loop=	[LOOP] Maximum number of loopback devices that can
+			be mounted
+			Format: <1-256>
+
+	maxcpus=	[SMP] Maximum number of processors that	an SMP kernel
+			should make use of
+
+	max_addr=[KMG]	[KNL,BOOT,ia64] All physical memory greater than or
+			equal to this physical address is ignored.
+
+	max_luns=	[SCSI] Maximum number of LUNs to probe.
+			Should be between 1 and 2^32-1.
+
+	max_report_luns=
+			[SCSI] Maximum number of LUNs received.
+			Should be between 1 and 16384.
+
+	mca-pentium	[BUGS=IA-32]
+
+	mcatest=	[IA-64]
+
+	mcd=		[HW,CD]
+			Format: <port>,<irq>,<mitsumi_bug_93_wait>
+
+	mcdx=		[HW,CD]
+
+	mce		[IA-32] Machine Check Exception
+
+	md=		[HW] RAID subsystems devices and level
+			See Documentation/md.txt.
+
+	mdacon=		[MDA]
+			Format: <first>,<last>
+			Specifies range of consoles to be captured by the MDA.
+
+	mem=nn[KMG]	[KNL,BOOT] Force usage of a specific amount of memory
+			Amount of memory to be used when the kernel is not able
+			to see the whole system memory or for test.
+			[IA-32] Use together with memmap= to avoid physical
+			address space collisions. Without memmap= PCI devices
+			could be placed at addresses belonging to unused RAM.
+
+	mem=nopentium	[BUGS=IA-32] Disable usage of 4MB pages for kernel
+			memory.
+
+	memmap=exactmap	[KNL,IA-32,X86_64] Enable setting of an exact
+			E820 memory map, as specified by the user.
+			Such memmap=exactmap lines can be constructed based on
+			BIOS output or other requirements. See the memmap=nn@ss
+			option description.
+
+	memmap=nn[KMG]@ss[KMG]
+			[KNL] Force usage of a specific region of memory
+			Region of memory to be used, from ss to ss+nn.
+
+	memmap=nn[KMG]#ss[KMG]
+			[KNL,ACPI] Mark specific memory as ACPI data.
+			Region of memory to be used, from ss to ss+nn.
+
+	memmap=nn[KMG]$ss[KMG]
+			[KNL,ACPI] Mark specific memory as reserved.
+			Region of memory to be used, from ss to ss+nn.
+
+	meye.*=		[HW] Set MotionEye Camera parameters
+			See Documentation/video4linux/meye.txt.
+
+	mga=		[HW,DRM]
+
+	migration_cost=
+			[KNL,SMP] debug: override scheduler migration costs
+			Format: <level-1-usecs>,<level-2-usecs>,...
+			This debugging option can be used to override the
+			default scheduler migration cost matrix. The numbers
+			are indexed by 'CPU domain distance'.
+			E.g. migration_cost=1000,2000,3000 on an SMT NUMA
+			box will set up an intra-core migration cost of
+			1 msec, an inter-core migration cost of 2 msecs,
+			and an inter-node migration cost of 3 msecs.
+
+			WARNING: using the wrong values here can break
+			scheduler performance, so it's only for scheduler
+			development purposes, not production environments.
+
+	migration_debug=
+			[KNL,SMP] migration cost auto-detect verbosity
+			Format=<0|1|2>
+			If a system's migration matrix reported at bootup
+			seems erroneous then this option can be used to
+			increase verbosity of the detection process.
+			We default to 0 (no extra messages), 1 will print
+			some more information, and 2 will be really
+			verbose (probably only useful if you also have a
+			serial console attached to the system).
+
+	migration_factor=
+			[KNL,SMP] multiply/divide migration costs by a factor
+			Format=<percent>
+			This debug option can be used to proportionally
+			increase or decrease the auto-detected migration
+			costs for all entries of the migration matrix.
+			E.g. migration_factor=150 will increase migration
+			costs by 50%. (and thus the scheduler will be less
+			eager migrating cache-hot tasks)
+			migration_factor=80 will decrease migration costs
+			by 20%. (thus the scheduler will be more eager to
+			migrate tasks)
+
+			WARNING: using the wrong values here can break
+			scheduler performance, so it's only for scheduler
+			development purposes, not production environments.
+
+	mousedev.tap_time=
+			[MOUSE] Maximum time between finger touching and
+			leaving touchpad surface for touch to be considered
+			a tap and be reported as a left button click (for
+			touchpads working in absolute mode only).
+			Format: <msecs>
+	mousedev.xres=	[MOUSE] Horizontal screen resolution, used for devices
+			reporting absolute coordinates, such as tablets
+	mousedev.yres=	[MOUSE] Vertical screen resolution, used for devices
+			reporting absolute coordinates, such as tablets
+
+	mpu401=		[HW,OSS]
+			Format: <io>,<irq>
+
+	MTD_Partition=	[MTD]
+			Format: <name>,<region-number>,<size>,<offset>
+
+	MTD_Region=	[MTD] Format:
+			<name>,<region-number>[,<base>,<size>,<buswidth>,<altbuswidth>]
+
+	mtdparts=	[MTD]
+			See drivers/mtd/cmdline.c.
+
+	mtouchusb.raw_coordinates=
+			[HW] Make the MicroTouch USB driver use raw coordinates
+			('y', default) or cooked coordinates ('n')
+
+	n2=		[NET] SDL Inc. RISCom/N2 synchronous serial card
+
+	NCR_D700=	[HW,SCSI]
+			See header of drivers/scsi/NCR_D700.c.
+
+	ncr5380=	[HW,SCSI]
+
+	ncr53c400=	[HW,SCSI]
+
+	ncr53c400a=	[HW,SCSI]
+
+	ncr53c406a=	[HW,SCSI]
+
+	ncr53c8xx=	[HW,SCSI]
+
+	netdev=		[NET] Network devices parameters
+			Format: <irq>,<io>,<mem_start>,<mem_end>,<name>
+			Note that mem_start is often overloaded to mean
+			something different and driver-specific.
+			This usage is only documented in each driver source
+			file if at all.
+
+	nfsaddrs=	[NFS]
+			See Documentation/nfsroot.txt.
+
+	nfsroot=	[NFS] nfs root filesystem for disk-less boxes.
+			See Documentation/nfsroot.txt.
+
+	nfs.callback_tcpport=
+			[NFS] set the TCP port on which the NFSv4 callback
+			channel should listen.
+
+	nfs.idmap_cache_timeout=
+			[NFS] set the maximum lifetime for idmapper cache
+			entries.
+
+	nmi_watchdog=	[KNL,BUGS=IA-32] Debugging features for SMP kernels
+
+	no387		[BUGS=IA-32] Tells the kernel to use the 387 maths
+			emulation library even if a 387 maths coprocessor
+			is present.
+
+	noalign		[KNL,ARM]
+
+	noapic		[SMP,APIC] Tells the kernel to not make use of any
+			IOAPICs that may be present in the system.
+
+	noasync		[HW,M68K] Disables async and sync negotiation for
+			all devices.
+
+	nobats		[PPC] Do not use BATs for mapping kernel lowmem
+			on "Classic" PPC cores.
+
+	nocache		[ARM]
+
+	nodisconnect	[HW,SCSI,M68K] Disables SCSI disconnects.
+
+	noexec		[IA-64]
+
+	noexec		[IA-32,X86-64]
+			noexec=on: enable non-executable mappings (default)
+			noexec=off: disable nn-executable mappings
+
+	nofxsr		[BUGS=IA-32]
+
+	nohlt		[BUGS=ARM]
+
+	no-hlt		[BUGS=IA-32] Tells the kernel that the hlt
+			instruction doesn't work correctly and not to
+			use it.
+
+	nohalt		[IA-64] Tells the kernel not to use the power saving
+			function PAL_HALT_LIGHT when idle. This increases
+			power-consumption. On the positive side, it reduces
+			interrupt wake-up latency, which may improve performance
+			in certain environments such as networked servers or
+			real-time systems.
+
+	noirqdebug	[IA-32] Disables the code which attempts to detect and
+			disable unhandled interrupt sources.
+
+	noisapnp	[ISAPNP] Disables ISA PnP code.
+
+	noinitrd	[RAM] Tells the kernel not to load any configured
+			initial RAM disk.
+
+	nointroute	[IA-64]
+
+	nolapic		[IA-32,APIC] Do not enable or use the local APIC.
+
+	noltlbs		[PPC] Do not use large page/tlb entries for kernel
+			lowmem mapping on PPC40x.
+
+	nomce		[IA-32] Machine Check Exception
+
+	noresidual	[PPC] Don't use residual data on PReP machines.
+
+	noresume	[SWSUSP] Disables resume and restores original swap
+			space.
+
+	no-scroll	[VGA] Disables scrollback.
+			This is required for the Braillex ib80-piezo Braille
+			reader made by F.H. Papenmeier (Germany).
+
+	nosbagart	[IA-64]
+
+	nosmp		[SMP] Tells an SMP kernel to act as a UP kernel.
+
+	nosync		[HW,M68K] Disables sync negotiation for all devices.
+
+	notsc		[BUGS=IA-32] Disable Time Stamp Counter
+
+	nousb		[USB] Disable the USB subsystem
+
+	nowb		[ARM]
+
+	nr_uarts=	[SERIAL] maximum number of UARTs to be registered.
+
+	opl3=		[HW,OSS]
+			Format: <io>
+
+	opl3sa=		[HW,OSS]
+			Format: <io>,<irq>,<dma>,<dma2>,<mpu_io>,<mpu_irq>
+
+	opl3sa2=	[HW,OSS] Format:
+			<io>,<irq>,<dma>,<dma2>,<mss_io>,<mpu_io>,<ymode>,<loopback>[,<isapnp>,<multiple]
+
+	oprofile.timer=	[HW]
+			Use timer interrupt instead of performance counters
+
+	optcd=		[HW,CD]
+			Format: <io>
+
+	osst=		[HW,SCSI] SCSI Tape Driver
+			Format: <buffer_size>,<write_threshold>
+			See also Documentation/scsi/st.txt.
+
+	panic=		[KNL] Kernel behaviour on panic
+			Format: <timeout>
+
+	parkbd.port=	[HW] Parallel port number the keyboard adapter is
+			connected to, default is 0.
+			Format: <parport#>
+	parkbd.mode=	[HW] Parallel port keyboard adapter mode of operation,
+			0 for XT, 1 for AT (default is AT).
+			Format: <mode>
+
+	parport=	[HW,PPT] Specify parallel ports. 0 disables.
+			Format: { 0 | auto | 0xBBB[,IRQ[,DMA]] }
+			Use 'auto' to force the driver to use any
+			IRQ/DMA settings detected (the default is to
+			ignore detected IRQ/DMA settings because of
+			possible conflicts). You can specify the base
+			address, IRQ, and DMA settings; IRQ and DMA
+			should be numbers, or 'auto' (for using detected
+			settings on that particular port), or 'nofifo'
+			(to avoid using a FIFO even if it is detected).
+			Parallel ports are assigned in the order they
+			are specified on the command line, starting
+			with parport0.
+
+	parport_init_mode=	[HW,PPT]
+			Configure VIA parallel port to operate in
+			a specific mode. This is necessary on Pegasos
+			computer where firmware has no options for setting
+			up parallel port mode and sets it to spp.
+			Currently this function knows 686a and 8231 chips.
+			Format: [spp|ps2|epp|ecp|ecpepp]
+
+	pas2=		[HW,OSS] Format:
+			<io>,<irq>,<dma>,<dma16>,<sb_io>,<sb_irq>,<sb_dma>,<sb_dma16>
+
+	pas16=		[HW,SCSI]
+			See header of drivers/scsi/pas16.c.
+
+	pcbit=		[HW,ISDN]
+
+	pcd.		[PARIDE]
+			See header of drivers/block/paride/pcd.c.
+			See also Documentation/paride.txt.
+
+	pci=option[,option...]	[PCI] various PCI subsystem options:
+		off		[IA-32] don't probe for the PCI bus
+		bios		[IA-32] force use of PCI BIOS, don't access
+				the hardware directly. Use this if your machine
+				has a non-standard PCI host bridge.
+		nobios		[IA-32] disallow use of PCI BIOS, only direct
+				hardware access methods are allowed. Use this
+				if you experience crashes upon bootup and you
+				suspect they are caused by the BIOS.
+		conf1		[IA-32] Force use of PCI Configuration
+				Mechanism 1.
+		conf2		[IA-32] Force use of PCI Configuration
+				Mechanism 2.
+		nommconf	[IA-32,X86_64] Disable use of MMCONFIG for PCI
+				Configuration
+		nosort		[IA-32] Don't sort PCI devices according to
+				order given by the PCI BIOS. This sorting is
+				done to get a device order compatible with
+				older kernels.
+		biosirq		[IA-32] Use PCI BIOS calls to get the interrupt
+				routing table. These calls are known to be buggy
+				on several machines and they hang the machine
+				when used, but on other computers it's the only
+				way to get the interrupt routing table. Try
+				this option if the kernel is unable to allocate
+				IRQs or discover secondary PCI buses on your
+				motherboard.
+		rom		[IA-32] Assign address space to expansion ROMs.
+				Use with caution as certain devices share
+				address decoders between ROMs and other
+				resources.
+		irqmask=0xMMMM	[IA-32] Set a bit mask of IRQs allowed to be
+				assigned automatically to PCI devices. You can
+				make the kernel exclude IRQs of your ISA cards
+				this way.
+		pirqaddr=0xAAAAA	[IA-32] Specify the physical address
+				of the PIRQ table (normally generated
+				by the BIOS) if it is outside the
+				F0000h-100000h range.
+		lastbus=N	[IA-32] Scan all buses thru bus #N. Can be
+				useful if the kernel is unable to find your
+				secondary buses and you want to tell it
+				explicitly which ones they are.
+		assign-busses	[IA-32] Always assign all PCI bus
+				numbers ourselves, overriding
+				whatever the firmware may have done.
+		usepirqmask	[IA-32] Honor the possible IRQ mask stored
+				in the BIOS $PIR table. This is needed on
+				some systems with broken BIOSes, notably
+				some HP Pavilion N5400 and Omnibook XE3
+				notebooks. This will have no effect if ACPI
+				IRQ routing is enabled.
+		noacpi		[IA-32] Do not use ACPI for IRQ routing
+				or for PCI scanning.
+		routeirq	Do IRQ routing for all PCI devices.
+				This is normally done in pci_enable_device(),
+				so this option is a temporary workaround
+				for broken drivers that don't call it.
+		firmware	[ARM] Do not re-enumerate the bus but instead
+				just use the configuration from the
+				bootloader. This is currently used on
+				IXP2000 systems where the bus has to be
+				configured a certain way for adjunct CPUs.
+
+	pcmv=		[HW,PCMCIA] BadgePAD 4
+
+	pd.		[PARIDE]
+			See Documentation/paride.txt.
+
+	pdcchassis=	[PARISC,HW] Disable/Enable PDC Chassis Status codes at
+			boot time.
+			Format: { 0 | 1 }
+			See arch/parisc/kernel/pdc_chassis.c
+
+	pf.		[PARIDE]
+			See Documentation/paride.txt.
+
+	pg.		[PARIDE]
+			See Documentation/paride.txt.
+
+	pirq=		[SMP,APIC] Manual mp-table setup
+			See Documentation/i386/IO-APIC.txt.
+
+	plip=		[PPT,NET] Parallel port network link
+			Format: { parport<nr> | timid | 0 }
+			See also Documentation/parport.txt.
+
+	pnpacpi=	[ACPI]
+			{ off }
+
+	pnpbios=	[ISAPNP]
+			{ on | off | curr | res | no-curr | no-res }
+
+	pnp_reserve_irq=
+			[ISAPNP] Exclude IRQs for the autoconfiguration
+
+	pnp_reserve_dma=
+			[ISAPNP] Exclude DMAs for the autoconfiguration
+
+	pnp_reserve_io=	[ISAPNP] Exclude I/O ports for the autoconfiguration
+			Ranges are in pairs (I/O port base and size).
+
+	pnp_reserve_mem=
+			[ISAPNP] Exclude memory regions for the
+			autoconfiguration.
+			Ranges are in pairs (memory base and size).
+
+	profile=	[KNL] Enable kernel profiling via /proc/profile
+			Format: [schedule,]<number>
+			Param: "schedule" - profile schedule points.
+			Param: <number> - step/bucket size as a power of 2 for
+				statistical time based profiling.
+
+	processor.max_cstate=	[HW,ACPI]
+			Limit processor to maximum C-state
+			max_cstate=9 overrides any DMI blacklist limit.
+
+	processor.nocst	[HW,ACPI]
+			Ignore the _CST method to determine C-states,
+			instead using the legacy FADT method
+
+	prompt_ramdisk=	[RAM] List of RAM disks to prompt for floppy disk
+			before loading.
+			See Documentation/ramdisk.txt.
+
+	psmouse.proto=	[HW,MOUSE] Highest PS2 mouse protocol extension to
+			probe for; one of (bare|imps|exps|lifebook|any).
+	psmouse.rate=	[HW,MOUSE] Set desired mouse report rate, in reports
+			per second.
+	psmouse.resetafter=	[HW,MOUSE]
+			Try to reset the device after so many bad packets
+			(0 = never).
+	psmouse.resolution=
+			[HW,MOUSE] Set desired mouse resolution, in dpi.
+	psmouse.smartscroll=
+			[HW,MOUSE] Controls Logitech smartscroll autorepeat.
+			0 = disabled, 1 = enabled (default).
+
+	pss=		[HW,OSS] Personal Sound System (ECHO ESC614)
+			Format:
+			<io>,<mss_io>,<mss_irq>,<mss_dma>,<mpu_io>,<mpu_irq>
+
+	pt.		[PARIDE]
+			See Documentation/paride.txt.
+
+	quiet=		[KNL] Disable log messages
+
+	r128=		[HW,DRM]
+
+	raid=		[HW,RAID]
+			See Documentation/md.txt.
+
+	ramdisk=	[RAM] Sizes of RAM disks in kilobytes [deprecated]
+			See Documentation/ramdisk.txt.
+
+	ramdisk_blocksize=	[RAM]
+			See Documentation/ramdisk.txt.
+
+	ramdisk_size=	[RAM] Sizes of RAM disks in kilobytes
+			New name for the ramdisk parameter.
+			See Documentation/ramdisk.txt.
+
+	rdinit=		[KNL]
+			Format: <full_path>
+			Run specified binary instead of /init from the ramdisk,
+			used for early userspace startup. See initrd.
+
+	reboot=		[BUGS=IA-32,BUGS=ARM,BUGS=IA-64] Rebooting mode
+			Format: <reboot_mode>[,<reboot_mode2>[,...]]
+			See arch/*/kernel/reboot.c.
+
+	reserve=	[KNL,BUGS] Force the kernel to ignore some iomem area
+
+	resume=		[SWSUSP]
+			Specify the partition device for software suspend
+
+	rhash_entries=	[KNL,NET]
+			Set number of hash buckets for route cache
+
+	riscom8=	[HW,SERIAL]
+			Format: <io_board1>[,<io_board2>[,...<io_boardN>]]
+
+	ro		[KNL] Mount root device read-only on boot
+
+	root=		[KNL] Root filesystem
+
+	rootdelay=	[KNL] Delay (in seconds) to pause before attempting to
+			mount the root filesystem
+
+	rootflags=	[KNL] Set root filesystem mount option string
+
+	rootfstype=	[KNL] Set root filesystem type
+
+	rw		[KNL] Mount root device read-write on boot
+
+	S		[KNL] Run init in single mode
+
+	sa1100ir	[NET]
+			See drivers/net/irda/sa1100_ir.c.
+
+	sb=		[HW,OSS]
+			Format: <io>,<irq>,<dma>,<dma2>
+
+	sbni=		[NET] Granch SBNI12 leased line adapter
+
+	sbpcd=		[HW,CD] Soundblaster CD adapter
+			Format: <io>,<type>
+			See a comment before function sbpcd_setup() in
+			drivers/cdrom/sbpcd.c.
+
+	sc1200wdt=	[HW,WDT] SC1200 WDT (watchdog) driver
+			Format: <io>[,<timeout>[,<isapnp>]]
+
+	scsi_debug_*=	[SCSI]
+			See drivers/scsi/scsi_debug.c.
+
+	scsi_default_dev_flags=
+			[SCSI] SCSI default device flags
+			Format: <integer>
+
+	scsi_dev_flags=	[SCSI] Black/white list entry for vendor and model
+			Format: <vendor>:<model>:<flags>
+			(flags are integer value)
+
+	scsi_logging=	[SCSI]
+
+	selinux		[SELINUX] Disable or enable SELinux at boot time.
+			Format: { "0" | "1" }
+			See security/selinux/Kconfig help text.
+			0 -- disable.
+			1 -- enable.
+			Default value is set via kernel config option.
+			If enabled at boot time, /selinux/disable can be used
+			later to disable prior to initial policy load.
+
+	serialnumber	[BUGS=IA-32]
+
+	sg_def_reserved_size=	[SCSI]
+
+	sgalaxy=	[HW,OSS]
+			Format: <io>,<irq>,<dma>,<dma2>,<sgbase>
+
+	shapers=	[NET]
+			Maximal number of shapers.
+
+	sim710=		[SCSI,HW]
+			See header of drivers/scsi/sim710.c.
+
+	simeth=		[IA-64]
+	simscsi=
+
+	sjcd=		[HW,CD]
+			Format: <io>,<irq>,<dma>
+			See header of drivers/cdrom/sjcd.c.
+
+	slram=		[HW,MTD]
+
+	smart2=		[HW]
+			Format: <io1>[,<io2>[,...,<io8>]]
+
+	snd-ad1816a=	[HW,ALSA]
+
+	snd-ad1848=	[HW,ALSA]
+
+	snd-ali5451=	[HW,ALSA]
+
+	snd-als100=	[HW,ALSA]
+
+	snd-als4000=	[HW,ALSA]
+
+	snd-azt2320=	[HW,ALSA]
+
+	snd-cmi8330=	[HW,ALSA]
+
+	snd-cmipci=	[HW,ALSA]
+
+	snd-cs4231=	[HW,ALSA]
+
+	snd-cs4232=	[HW,ALSA]
+
+	snd-cs4236=	[HW,ALSA]
+
+	snd-cs4281=	[HW,ALSA]
+
+	snd-cs46xx=	[HW,ALSA]
+
+	snd-dt019x=	[HW,ALSA]
+
+	snd-dummy=	[HW,ALSA]
+
+	snd-emu10k1=	[HW,ALSA]
+
+	snd-ens1370=	[HW,ALSA]
+
+	snd-ens1371=	[HW,ALSA]
+
+	snd-es968=	[HW,ALSA]
+
+	snd-es1688=	[HW,ALSA]
+
+	snd-es18xx=	[HW,ALSA]
+
+	snd-es1938=	[HW,ALSA]
+
+	snd-es1968=	[HW,ALSA]
+
+	snd-fm801=	[HW,ALSA]
+
+	snd-gusclassic=	[HW,ALSA]
+
+	snd-gusextreme=	[HW,ALSA]
+
+	snd-gusmax=	[HW,ALSA]
+
+	snd-hdsp=	[HW,ALSA]
+
+	snd-ice1712=	[HW,ALSA]
+
+	snd-intel8x0=	[HW,ALSA]
+
+	snd-interwave=	[HW,ALSA]
+
+	snd-interwave-stb=
+			[HW,ALSA]
+
+	snd-korg1212=	[HW,ALSA]
+
+	snd-maestro3=	[HW,ALSA]
+
+	snd-mpu401=	[HW,ALSA]
+
+	snd-mtpav=	[HW,ALSA]
+
+	snd-nm256=	[HW,ALSA]
+
+	snd-opl3sa2=	[HW,ALSA]
+
+	snd-opti92x-ad1848=
+			[HW,ALSA]
+
+	snd-opti92x-cs4231=
+			[HW,ALSA]
+
+	snd-opti93x=	[HW,ALSA]
+
+	snd-pmac=	[HW,ALSA]
+
+	snd-rme32=	[HW,ALSA]
+
+	snd-rme96=	[HW,ALSA]
+
+	snd-rme9652=	[HW,ALSA]
+
+	snd-sb8=	[HW,ALSA]
+
+	snd-sb16=	[HW,ALSA]
+
+	snd-sbawe=	[HW,ALSA]
+
+	snd-serial=	[HW,ALSA]
+
+	snd-sgalaxy=	[HW,ALSA]
+
+	snd-sonicvibes=	[HW,ALSA]
+
+	snd-sun-amd7930=
+			[HW,ALSA]
+
+	snd-sun-cs4231=	[HW,ALSA]
+
+	snd-trident=	[HW,ALSA]
+
+	snd-usb-audio=	[HW,ALSA,USB]
+
+	snd-via82xx=	[HW,ALSA]
+
+	snd-virmidi=	[HW,ALSA]
+
+	snd-wavefront=	[HW,ALSA]
+
+	snd-ymfpci=	[HW,ALSA]
+
+	sonicvibes=	[HW,OSS]
+			Format: <reverb>
+
+	sonycd535=	[HW,CD]
+			Format: <io>[,<irq>]
+
+	sonypi.*=	[HW] Sony Programmable I/O Control Device driver
+			See Documentation/sonypi.txt
+
+	specialix=	[HW,SERIAL] Specialix multi-serial port adapter
+			See Documentation/specialix.txt.
+
+	spia_io_base=	[HW,MTD]
+	spia_fio_base=
+	spia_pedr=
+	spia_peddr=
+
+	sscape=		[HW,OSS]
+			Format: <io>,<irq>,<dma>,<mpu_io>,<mpu_irq>
+
+	st=		[HW,SCSI] SCSI tape parameters (buffers, etc.)
+			See Documentation/scsi/st.txt.
+
+	st0x=		[HW,SCSI]
+			See header of drivers/scsi/seagate.c.
+
+	sti=		[PARISC,HW]
+			Format: <num>
+			Set the STI (builtin display/keyboard on the HP-PARISC
+			machines) console (graphic card) which should be used
+			as the initial boot-console.
+			See also comment in drivers/video/console/sticore.c.
+
+	sti_font=	[HW]
+			See comment in drivers/video/console/sticore.c.
+
+	stifb=		[HW]
+			Format: bpp:<bpp1>[:<bpp2>[:<bpp3>...]]
+
+	swiotlb=	[IA-64] Number of I/O TLB slabs
+
+	switches=	[HW,M68k]
+
+	sym53c416=	[HW,SCSI]
+			See header of drivers/scsi/sym53c416.c.
+
+	t128=		[HW,SCSI]
+			See header of drivers/scsi/t128.c.
+
+	tdfx=		[HW,DRM]
+
+	thash_entries=	[KNL,NET]
+			Set number of hash buckets for TCP connection
+
+	time		Show timing data prefixed to each printk message line
+
+	tipar.timeout=	[HW,PPT]
+			Set communications timeout in tenths of a second
+			(default 15).
+
+	tipar.delay=	[HW,PPT]
+			Set inter-bit delay in microseconds (default 10).
+
+	tmc8xx=		[HW,SCSI]
+			See header of drivers/scsi/seagate.c.
+
+	tmscsim=	[HW,SCSI]
+			See comment before function dc390_setup() in
+			drivers/scsi/tmscsim.c.
+
+	tp720=		[HW,PS2]
+
+	trix=		[HW,OSS] MediaTrix AudioTrix Pro
+			Format:
+			<io>,<irq>,<dma>,<dma2>,<sb_io>,<sb_irq>,<sb_dma>,<mpu_io>,<mpu_irq>
+
+	tsdev.xres=	[TS] Horizontal screen resolution.
+	tsdev.yres=	[TS] Vertical screen resolution.
+
+	turbografx.map[2|3]=	[HW,JOY]
+			TurboGraFX parallel port interface
+			Format:
+			<port#>,<js1>,<js2>,<js3>,<js4>,<js5>,<js6>,<js7>
+			See also Documentation/input/joystick-parport.txt
+
+	u14-34f=	[HW,SCSI] UltraStor 14F/34F SCSI host adapter
+			See header of drivers/scsi/u14-34f.c.
+
+	uart401=	[HW,OSS]
+			Format: <io>,<irq>
+
+	uart6850=	[HW,OSS]
+			Format: <io>,<irq>
+
+	usbhid.mousepoll=
+			[USBHID] The interval which mice are to be polled at.
+
+	video=		[FB] Frame buffer configuration
+			See Documentation/fb/modedb.txt.
+
+	vga=		[BOOT,IA-32] Select a particular video mode
+			See Documentation/i386/boot.txt and
+			Documentation/svga.txt.
+			Use vga=ask for menu.
+			This is actually a boot loader parameter; the value is
+			passed to the kernel using a special protocol.
+
+	vmalloc=nn[KMG]	[KNL,BOOT] Forces the vmalloc area to have an exact
+			size of <nn>. This can be used to increase the
+			minimum size (128MB on x86). It can also be used to
+			decrease the size and leave more room for directly
+			mapped kernel RAM.
+
+	vmhalt=		[KNL,S390]
+
+	vmpoff=		[KNL,S390]
+
+	waveartist=	[HW,OSS]
+			Format: <io>,<irq>,<dma>,<dma2>
+
+	wd33c93=	[HW,SCSI]
+			See header of drivers/scsi/wd33c93.c.
+
+	wd7000=		[HW,SCSI]
+			See header of drivers/scsi/wd7000.c.
+
+	wdt=		[WDT] Watchdog
+			See Documentation/watchdog/watchdog.txt.
+
+	xd=		[HW,XT] Original XT pre-IDE (RLL encoded) disks.
+	xd_geo=		See header of drivers/block/xd.c.
+
+	xirc2ps_cs=	[NET,PCMCIA]
+			Format:
+			<irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]]
+
+	norandmaps	Don't use address space randomization
+			Equivalent to echo 0 > /proc/sys/kernel/randomize_va_space
+
+
+______________________________________________________________________
+Changelog:
+
+2000-06-??	Mr. Unknown
+	The last known update (for 2.4.0) - the changelog was not kept before.
+
+2002-11-24	Petr Baudis <pasky@ucw.cz>
+		Randy Dunlap <randy.dunlap@verizon.net>
+	Update for 2.5.49, description for most of the options introduced,
+	references to other documentation (C files, READMEs, ..), added S390,
+	PPC, SPARC, MTD, ALSA and OSS category. Minor corrections and
+	reformatting.
+
+2005-10-19	Randy Dunlap <rdunlap@xenotime.net>
+	Lots of typos, whitespace, some reformatting.
+
+TODO:
+
+	Add documentation for ALSA options.
+	Add more DRM drivers.
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	2006-02-18 15:24:31.290832000 +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	2006-01-03 03:21:10.000000000 +0000
+++ newtree/Documentation/power/kernel_threads.txt	2006-02-18 15:24:31.291831848 +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	2006-02-18 15:24:31.293831544 +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	2006-02-18 15:18:20.508199528 +0000
+++ newtree/Documentation/power/swsusp.txt	2006-02-18 15:24:31.294831392 +0000
@@ -135,7 +135,8 @@
 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?
 
@@ -144,7 +145,7 @@
 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/mm/init.c newtree/arch/arm/mm/init.c
--- oldtree/arch/arm/mm/init.c	2006-01-03 03:21:10.000000000 +0000
+++ newtree/arch/arm/mm/init.c	2006-02-18 15:24:31.295831240 +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/i386/kernel/time.c newtree/arch/i386/kernel/time.c
--- oldtree/arch/i386/kernel/time.c	2006-02-18 15:18:21.711016672 +0000
+++ newtree/arch/i386/kernel/time.c	2006-02-18 15:24:31.296831088 +0000
@@ -378,7 +378,8 @@
 	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)
@@ -386,9 +387,11 @@
 	/*
 	 * 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)
@@ -401,14 +404,16 @@
 	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	2006-02-18 15:18:21.723014848 +0000
+++ newtree/arch/i386/mm/init.c	2006-02-18 15:24:31.297830936 +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);
@@ -766,6 +783,7 @@
 		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/ppc/mm/init.c newtree/arch/ppc/mm/init.c
--- oldtree/arch/ppc/mm/init.c	2006-02-18 15:18:23.343768456 +0000
+++ newtree/arch/ppc/mm/init.c	2006-02-18 15:24:31.299830632 +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>
@@ -140,6 +141,7 @@
 
 	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++;
@@ -172,6 +174,7 @@
 
 	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++;
@@ -407,8 +410,10 @@
 	/* 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 */
 
@@ -417,13 +422,21 @@
 	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
 	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
@@ -441,6 +454,7 @@
 			struct page *page = mem_map + pfn;
 
 			ClearPageReserved(page);
+			ClearPageNosave(page);
 			set_page_count(page, 1);
 			__free_page(page);
 			totalhigh_pages++;
diff -urN oldtree/arch/x86_64/kernel/e820.c newtree/arch/x86_64/kernel/e820.c
--- oldtree/arch/x86_64/kernel/e820.c	2006-02-18 15:18:23.852691088 +0000
+++ newtree/arch/x86_64/kernel/e820.c	2006-02-18 15:24:31.300830480 +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/suspend.c newtree/arch/x86_64/kernel/suspend.c
--- oldtree/arch/x86_64/kernel/suspend.c	2006-02-18 15:18:23.891685160 +0000
+++ newtree/arch/x86_64/kernel/suspend.c	2006-02-18 15:24:31.301830328 +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 in arch/x86_64/kernel/suspend_asm.S */
 extern int restore_image(void);
 
@@ -220,4 +223,5 @@
 	restore_image();
 	return 0;
 }
+
 #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	2006-02-18 15:18:23.894684704 +0000
+++ newtree/arch/x86_64/kernel/time.c	2006-02-18 15:24:31.302830176 +0000
@@ -510,11 +510,10 @@
 	return cycles_2_ns(a);
 }
 
-static unsigned long get_cmos_time(void)
+static unsigned long __get_cmos_time(void)
 {
 	unsigned int timeout = 1000000, year, mon, day, hour, min, sec;
 	unsigned char uip = 0, this = 0;
-	unsigned long flags;
 
 /*
  * The Linux interpretation of the CMOS clock register contents: When the
@@ -524,8 +523,6 @@
  * standard 8.3 MHz ISA bus.
  */
 
-	spin_lock_irqsave(&rtc_lock, flags);
-
 	while (timeout && (!uip || this)) {
 		uip |= this;
 		this = CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP;
@@ -543,8 +540,6 @@
 	mon = CMOS_READ(RTC_MONTH);
 	year = CMOS_READ(RTC_YEAR);
 
-	spin_unlock_irqrestore(&rtc_lock, flags);
-
 	/*
 	 * We know that x86-64 always uses BCD format, no need to check the
 	 * config register.
@@ -566,6 +561,20 @@
 	return mktime(year, mon, day, hour, min, sec);
 }
 
+static unsigned long get_cmos_time(void)
+{
+	unsigned long flags;
+	unsigned long result;
+
+	spin_lock_irqsave(&rtc_lock, flags);
+
+	result = __get_cmos_time();
+
+	spin_unlock_irqrestore(&rtc_lock, flags);
+
+	return result;
+}
+
 #ifdef CONFIG_CPU_FREQ
 
 /* Frequency scaling support. Adjust the TSC based timer when the cpu frequency
@@ -1029,7 +1038,7 @@
 	/*
 	 * 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	2006-02-18 15:18:23.914681664 +0000
+++ newtree/arch/x86_64/mm/init.c	2006-02-18 15:24:31.303830024 +0000
@@ -592,6 +592,7 @@
 	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);
@@ -632,6 +633,7 @@
 	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++;
@@ -743,3 +745,22 @@
 {
 	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	2006-02-18 15:18:23.959674824 +0000
+++ newtree/block/ll_rw_blk.c	2006-02-18 15:24:31.306829568 +0000
@@ -28,6 +28,9 @@
 #include <linux/writeback.h>
 #include <linux/interrupt.h>
 #include <linux/cpu.h>
+#include <linux/freezer.h>
+#include <linux/mount.h>
+#include <linux/suspend2.h>
 
 /*
  * for max sense size
@@ -3037,12 +3040,26 @@
 	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));
 	}
 
@@ -3434,7 +3451,7 @@
 {
 	int i;
 
-	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	2006-02-18 15:18:23.961674520 +0000
+++ newtree/crypto/Kconfig	2006-02-18 15:24:31.307829416 +0000
@@ -316,6 +316,13 @@
 	  
 	  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	2006-01-03 03:21:10.000000000 +0000
+++ newtree/crypto/Makefile	2006-02-18 15:24:31.308829264 +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	2006-01-03 03:21:10.000000000 +0000
+++ newtree/crypto/deflate.c	2006-02-18 15:24:31.308829264 +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	2006-02-18 15:24:31.310828960 +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",
+		       (long) ((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	2006-02-18 15:18:24.099653544 +0000
+++ newtree/drivers/acpi/osl.c	2006-02-18 15:24:31.311828808 +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	2006-01-03 03:21:10.000000000 +0000
+++ newtree/drivers/acpi/sleep/proc.c	2006-02-18 15:24:31.312828656 +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/sys.c newtree/drivers/base/sys.c
--- oldtree/drivers/base/sys.c	2006-02-18 15:18:24.249630744 +0000
+++ newtree/drivers/base/sys.c	2006-02-18 15:24:31.313828504 +0000
@@ -302,16 +302,14 @@
 		cls->resume(dev);
 
 	/* Call auxillary drivers next. */
-	list_for_each_entry(drv, &cls->drivers, entry) {
+	list_for_each_entry(drv, &cls->drivers, entry)
 		if (drv->resume)
 			drv->resume(dev);
-	}
 
 	/* Call global drivers. */
-	list_for_each_entry(drv, &sysdev_drivers, entry) {
+	list_for_each_entry(drv, &sysdev_drivers, entry)
 		if (drv->resume)
 			drv->resume(dev);
-	}
 }
 
 /**
diff -urN oldtree/drivers/char/hvc_console.c newtree/drivers/char/hvc_console.c
--- oldtree/drivers/char/hvc_console.c	2006-02-18 15:18:24.472596848 +0000
+++ newtree/drivers/char/hvc_console.c	2006-02-18 15:24:31.314828352 +0000
@@ -839,7 +839,7 @@
 
 	/* 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	2006-02-18 15:18:24.474596544 +0000
+++ newtree/drivers/char/hvcs.c	2006-02-18 15:24:31.316828048 +0000
@@ -1404,7 +1404,7 @@
 		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/input/serio/serio.c newtree/drivers/input/serio/serio.c
--- oldtree/drivers/input/serio/serio.c	2006-02-18 15:18:25.080504432 +0000
+++ newtree/drivers/input/serio/serio.c	2006-02-18 15:24:31.317827896 +0000
@@ -901,7 +901,7 @@
 
 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	2006-02-18 15:18:25.159492424 +0000
+++ newtree/drivers/macintosh/Kconfig	2006-02-18 15:24:31.318827744 +0000
@@ -200,4 +200,8 @@
 	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/via-pmu.c newtree/drivers/macintosh/via-pmu.c
--- oldtree/drivers/macintosh/via-pmu.c	2006-02-18 15:18:25.197486648 +0000
+++ newtree/drivers/macintosh/via-pmu.c	2006-02-18 15:24:31.320827440 +0000
@@ -2653,6 +2653,13 @@
 			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	2006-02-18 15:18:25.219483304 +0000
+++ newtree/drivers/md/dm-crypt.c	2006-02-18 15:24:31.321827288 +0000
@@ -928,7 +928,7 @@
 	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	2006-02-18 15:18:25.238480416 +0000
+++ newtree/drivers/md/md.c	2006-02-18 15:24:31.325826680 +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/poll.h>
 
 #include <linux/init.h>
@@ -3972,7 +3971,8 @@
 	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/net/irda/sir_kthread.c newtree/drivers/net/irda/sir_kthread.c
--- oldtree/drivers/net/irda/sir_kthread.c	2006-02-18 15:18:28.421996448 +0000
+++ newtree/drivers/net/irda/sir_kthread.c	2006-02-18 15:24:31.326826528 +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/scsi/hosts.c newtree/drivers/scsi/hosts.c
--- oldtree/drivers/scsi/hosts.c	2006-02-18 15:18:28.787940816 +0000
+++ newtree/drivers/scsi/hosts.c	2006-02-18 15:24:31.327826376 +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	2006-02-18 15:18:28.820935800 +0000
+++ newtree/drivers/scsi/lpfc/lpfc_init.c	2006-02-18 15:24:31.343823944 +0000
@@ -1521,7 +1521,7 @@
 	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/net/pegasus.c newtree/drivers/usb/net/pegasus.c
--- oldtree/drivers/usb/net/pegasus.c	2006-02-18 15:18:29.111891568 +0000
+++ newtree/drivers/usb/net/pegasus.c	2006-02-18 15:24:31.344823792 +0000
@@ -1451,7 +1451,7 @@
 	pr_info("%s: %s, " DRIVER_DESC "\n", driver_name, DRIVER_VERSION);
 	if (devid)
 		parse_id(devid);
-	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/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	2006-02-18 15:24:31.345823640 +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	2006-02-18 15:24:31.346823488 +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	2006-01-03 03:21:10.000000000 +0000
+++ newtree/include/asm-i386/mach-default/mach_time.h	2006-02-18 15:24:31.348823184 +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/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	2006-02-18 15:24:31.349823032 +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-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	2006-02-18 15:24:31.350822880 +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	2006-02-18 15:24:31.351822728 +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/page.h newtree/include/asm-x86_64/page.h
--- oldtree/include/asm-x86_64/page.h	2006-02-18 15:18:29.866776808 +0000
+++ newtree/include/asm-x86_64/page.h	2006-02-18 15:24:31.352822576 +0000
@@ -105,6 +105,8 @@
 
 #include <asm/bug.h>
 
+extern int page_is_ram(unsigned long pagenr);
+
 #endif /* __ASSEMBLY__ */
 
 #define PAGE_OFFSET		((unsigned long)__PAGE_OFFSET)
diff -urN oldtree/include/asm-x86_64/suspend.h newtree/include/asm-x86_64/suspend.h
--- oldtree/include/asm-x86_64/suspend.h	2006-01-03 03:21:10.000000000 +0000
+++ newtree/include/asm-x86_64/suspend.h	2006-02-18 15:24:31.353822424 +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	2006-02-18 15:24:31.354822272 +0000
@@ -0,0 +1,427 @@
+ /*
+  * 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>
+
+static 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;
+
+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();
+	
+}
+
+/*
+ * 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(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();
+	
+	suspend2_arch_flush_caches();
+
+	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)
+{
+}
+
+/* Based on the version from swsusp */
+static int res_phys_pud_init(pud_t *pud, unsigned long address, unsigned long end)
+{
+	long i, j;
+
+	i = pud_index(address);
+	pud = pud + i;
+	for (; i < PTRS_PER_PUD; pud++, i++) {
+		unsigned long paddr;
+		pmd_t *pmd;
+
+		paddr = address + i*PUD_SIZE;
+		if (paddr >= end)
+			break;
+
+		pmd = (pmd_t *)suspend_get_nonconflicting_pages(0);
+		if (!pmd)
+			return -ENOMEM;
+		set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
+		for (j = 0; j < PTRS_PER_PMD; pmd++, j++, paddr += PMD_SIZE) {
+			unsigned long pe;
+
+			if (paddr >= end)
+				break;
+			pe = _PAGE_NX | _PAGE_PSE | _KERNPG_TABLE | paddr;
+			pe &= __supported_pte_mask;
+			set_pmd(pmd, __pmd(pe));
+		}
+	}
+	return 0;
+}
+
+static int set_up_temporary_mappings_suspend2(void)
+{
+	unsigned long start, end, next;
+	int error;
+
+	temp_level4_pgt = (pgd_t *)suspend_get_nonconflicting_pages(0);
+	if (!temp_level4_pgt)
+		return -ENOMEM;
+
+	/* It is safe to reuse the original kernel mapping */
+	set_pgd(temp_level4_pgt + pgd_index(__START_KERNEL_map),
+		init_level4_pgt[pgd_index(__START_KERNEL_map)]);
+
+	/* Set up the direct mapping from scratch */
+	start = (unsigned long)pfn_to_kaddr(0);
+	end = (unsigned long)pfn_to_kaddr(end_pfn);
+
+	for (; start < end; start = next) {
+		pud_t *pud = (pud_t *)suspend_get_nonconflicting_pages(0);
+		if (!pud)
+			return -ENOMEM;
+		next = start + PGDIR_SIZE;
+		if (next > end)
+			next = end;
+		if ((error = res_phys_pud_init(pud, __pa(start), __pa(next))))
+			return error;
+		set_pgd(temp_level4_pgt + pgd_index(start),
+			mk_kernel_pgd(__pa(pud)));
+	}
+	return 0;
+}
+
+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.
+	 */
+
+	set_up_temporary_mappings_suspend2();
+
+	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_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	2006-02-18 15:18:29.878774984 +0000
+++ newtree/include/linux/bio.h	2006-02-18 15:24:31.355822120 +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	2006-02-18 15:24:31.356821968 +0000
@@ -0,0 +1,66 @@
+/*
+ * include/linux/dyn_pageflags.h
+ *
+ * Copyright (C) 2004-2006 Nigel Cunningham <nigel@suspend2.net>
+ *
+ * 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 void 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	2006-02-18 15:24:31.357821816 +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	2006-02-18 15:18:29.909770272 +0000
+++ newtree/include/linux/kernel.h	2006-02-18 15:24:31.358821664 +0000
@@ -105,6 +105,8 @@
 	__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	2006-01-03 03:21:10.000000000 +0000
+++ newtree/include/linux/kthread.h	2006-02-18 15:24:31.359821512 +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	2006-02-18 15:18:29.937766016 +0000
+++ newtree/include/linux/netlink.h	2006-02-18 15:24:31.360821360 +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	2006-02-18 15:18:29.959762672 +0000
+++ newtree/include/linux/sched.h	2006-02-18 15:24:31.363820904 +0000
@@ -1436,7 +1436,7 @@
 
 extern void refrigerator(void);
 extern int freeze_processes(void);
-extern void thaw_processes(void);
+extern void thaw_processes(int which_threads);
 
 static inline int try_to_freeze(void)
 {
@@ -1455,7 +1455,7 @@
 
 static inline void refrigerator(void) {}
 static inline int freeze_processes(void) { BUG(); return 0; }
-static inline void thaw_processes(void) {}
+static inline void thaw_processes(int which_threads) {}
 
 static inline int try_to_freeze(void) { return 0; }
 
diff -urN oldtree/include/linux/sched.h.orig newtree/include/linux/sched.h.orig
--- oldtree/include/linux/sched.h.orig	1970-01-01 00:00:00.000000000 +0000
+++ newtree/include/linux/sched.h.orig	2006-02-18 15:18:29.000000000 +0000
@@ -0,0 +1,1465 @@
+#ifndef _LINUX_SCHED_H
+#define _LINUX_SCHED_H
+
+#include <asm/param.h>	/* for HZ */
+
+#include <linux/config.h>
+#include <linux/capability.h>
+#include <linux/threads.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/timex.h>
+#include <linux/jiffies.h>
+#include <linux/rbtree.h>
+#include <linux/thread_info.h>
+#include <linux/cpumask.h>
+#include <linux/errno.h>
+#include <linux/nodemask.h>
+
+#include <asm/system.h>
+#include <asm/semaphore.h>
+#include <asm/page.h>
+#include <asm/ptrace.h>
+#include <asm/mmu.h>
+#include <asm/cputime.h>
+
+#include <linux/smp.h>
+#include <linux/sem.h>
+#include <linux/signal.h>
+#include <linux/securebits.h>
+#include <linux/fs_struct.h>
+#include <linux/compiler.h>
+#include <linux/completion.h>
+#include <linux/pid.h>
+#include <linux/percpu.h>
+#include <linux/topology.h>
+#include <linux/seccomp.h>
+#include <linux/rcupdate.h>
+
+#include <linux/auxvec.h>	/* For AT_VECTOR_SIZE */
+
+struct exec_domain;
+
+/*
+ * cloning flags:
+ */
+#define CSIGNAL		0x000000ff	/* signal mask to be sent at exit */
+#define CLONE_VM	0x00000100	/* set if VM shared between processes */
+#define CLONE_FS	0x00000200	/* set if fs info shared between processes */
+#define CLONE_FILES	0x00000400	/* set if open files shared between processes */
+#define CLONE_SIGHAND	0x00000800	/* set if signal handlers and blocked signals shared */
+#define CLONE_PTRACE	0x00002000	/* set if we want to let tracing continue on the child too */
+#define CLONE_VFORK	0x00004000	/* set if the parent wants the child to wake it up on mm_release */
+#define CLONE_PARENT	0x00008000	/* set if we want to have the same parent as the cloner */
+#define CLONE_THREAD	0x00010000	/* Same thread group? */
+#define CLONE_NEWNS	0x00020000	/* New namespace group? */
+#define CLONE_SYSVSEM	0x00040000	/* share system V SEM_UNDO semantics */
+#define CLONE_SETTLS	0x00080000	/* create a new TLS for the child */
+#define CLONE_PARENT_SETTID	0x00100000	/* set the TID in the parent */
+#define CLONE_CHILD_CLEARTID	0x00200000	/* clear the TID in the child */
+#define CLONE_DETACHED		0x00400000	/* Unused, ignored */
+#define CLONE_UNTRACED		0x00800000	/* set if the tracing process can't force CLONE_PTRACE on this clone */
+#define CLONE_CHILD_SETTID	0x01000000	/* set the TID in the child */
+#define CLONE_STOPPED		0x02000000	/* Start in stopped state */
+
+/*
+ * List of flags we want to share for kernel threads,
+ * if only because they are not used by them anyway.
+ */
+#define CLONE_KERNEL	(CLONE_FS | CLONE_FILES | CLONE_SIGHAND)
+
+/*
+ * These are the constant used to fake the fixed-point load-average
+ * counting. Some notes:
+ *  - 11 bit fractions expand to 22 bits by the multiplies: this gives
+ *    a load-average precision of 10 bits integer + 11 bits fractional
+ *  - if you want to count load-averages more often, you need more
+ *    precision, or rounding will get you. With 2-second counting freq,
+ *    the EXP_n values would be 1981, 2034 and 2043 if still using only
+ *    11 bit fractions.
+ */
+extern unsigned long avenrun[];		/* Load averages */
+
+#define FSHIFT		11		/* nr of bits of precision */
+#define FIXED_1		(1<<FSHIFT)	/* 1.0 as fixed-point */
+#define LOAD_FREQ	(5*HZ)		/* 5 sec intervals */
+#define EXP_1		1884		/* 1/exp(5sec/1min) as fixed-point */
+#define EXP_5		2014		/* 1/exp(5sec/5min) */
+#define EXP_15		2037		/* 1/exp(5sec/15min) */
+
+#define CALC_LOAD(load,exp,n) \
+	load *= exp; \
+	load += n*(FIXED_1-exp); \
+	load >>= FSHIFT;
+
+extern unsigned long total_forks;
+extern int nr_threads;
+extern int last_pid;
+DECLARE_PER_CPU(unsigned long, process_counts);
+extern int nr_processes(void);
+extern unsigned long nr_running(void);
+extern unsigned long nr_uninterruptible(void);
+extern unsigned long nr_iowait(void);
+
+#include <linux/time.h>
+#include <linux/param.h>
+#include <linux/resource.h>
+#include <linux/timer.h>
+#include <linux/hrtimer.h>
+
+#include <asm/processor.h>
+
+/*
+ * Task state bitmask. NOTE! These bits are also
+ * encoded in fs/proc/array.c: get_task_state().
+ *
+ * We have two separate sets of flags: task->state
+ * is about runnability, while task->exit_state are
+ * about the task exiting. Confusing, but this way
+ * modifying one set can't modify the other one by
+ * mistake.
+ */
+#define TASK_RUNNING		0
+#define TASK_INTERRUPTIBLE	1
+#define TASK_UNINTERRUPTIBLE	2
+#define TASK_STOPPED		4
+#define TASK_TRACED		8
+/* in tsk->exit_state */
+#define EXIT_ZOMBIE		16
+#define EXIT_DEAD		32
+/* in tsk->state again */
+#define TASK_NONINTERACTIVE	64
+
+#define __set_task_state(tsk, state_value)		\
+	do { (tsk)->state = (state_value); } while (0)
+#define set_task_state(tsk, state_value)		\
+	set_mb((tsk)->state, (state_value))
+
+/*
+ * set_current_state() includes a barrier so that the write of current->state
+ * is correctly serialised wrt the caller's subsequent test of whether to
+ * actually sleep:
+ *
+ *	set_current_state(TASK_UNINTERRUPTIBLE);
+ *	if (do_i_need_to_sleep())
+ *		schedule();
+ *
+ * If the caller does not need such serialisation then use __set_current_state()
+ */
+#define __set_current_state(state_value)			\
+	do { current->state = (state_value); } while (0)
+#define set_current_state(state_value)		\
+	set_mb(current->state, (state_value))
+
+/* Task command name length */
+#define TASK_COMM_LEN 16
+
+/*
+ * Scheduling policies
+ */
+#define SCHED_NORMAL		0
+#define SCHED_FIFO		1
+#define SCHED_RR		2
+#define SCHED_BATCH		3
+
+struct sched_param {
+	int sched_priority;
+};
+
+#ifdef __KERNEL__
+
+#include <linux/spinlock.h>
+
+/*
+ * This serializes "schedule()" and also protects
+ * the run-queue from deletions/modifications (but
+ * _adding_ to the beginning of the run-queue has
+ * a separate lock).
+ */
+extern rwlock_t tasklist_lock;
+extern spinlock_t mmlist_lock;
+
+typedef struct task_struct task_t;
+
+extern void sched_init(void);
+extern void sched_init_smp(void);
+extern void init_idle(task_t *idle, int cpu);
+
+extern cpumask_t nohz_cpu_mask;
+
+extern void show_state(void);
+extern void show_regs(struct pt_regs *);
+
+/*
+ * TASK is a pointer to the task whose backtrace we want to see (or NULL for current
+ * task), SP is the stack pointer of the first frame that should be shown in the back
+ * trace (or NULL if the entire call-chain of the task should be shown).
+ */
+extern void show_stack(struct task_struct *task, unsigned long *sp);
+
+void io_schedule(void);
+long io_schedule_timeout(long timeout);
+
+extern void cpu_init (void);
+extern void trap_init(void);
+extern void update_process_times(int user);
+extern void scheduler_tick(void);
+
+#ifdef CONFIG_DETECT_SOFTLOCKUP
+extern void softlockup_tick(struct pt_regs *regs);
+extern void spawn_softlockup_task(void);
+extern void touch_softlockup_watchdog(void);
+#else
+static inline void softlockup_tick(struct pt_regs *regs)
+{
+}
+static inline void spawn_softlockup_task(void)
+{
+}
+static inline void touch_softlockup_watchdog(void)
+{
+}
+#endif
+
+
+/* Attach to any functions which should be ignored in wchan output. */
+#define __sched		__attribute__((__section__(".sched.text")))
+/* Is this address in the __sched functions? */
+extern int in_sched_functions(unsigned long addr);
+
+#define	MAX_SCHEDULE_TIMEOUT	LONG_MAX
+extern signed long FASTCALL(schedule_timeout(signed long timeout));
+extern signed long schedule_timeout_interruptible(signed long timeout);
+extern signed long schedule_timeout_uninterruptible(signed long timeout);
+asmlinkage void schedule(void);
+
+struct namespace;
+
+/* Maximum number of active map areas.. This is a random (large) number */
+#define DEFAULT_MAX_MAP_COUNT	65536
+
+extern int sysctl_max_map_count;
+
+#include <linux/aio.h>
+
+extern unsigned long
+arch_get_unmapped_area(struct file *, unsigned long, unsigned long,
+		       unsigned long, unsigned long);
+extern unsigned long
+arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
+			  unsigned long len, unsigned long pgoff,
+			  unsigned long flags);
+extern void arch_unmap_area(struct mm_struct *, unsigned long);
+extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long);
+
+#if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS
+/*
+ * The mm counters are not protected by its page_table_lock,
+ * so must be incremented atomically.
+ */
+#define set_mm_counter(mm, member, value) atomic_long_set(&(mm)->_##member, value)
+#define get_mm_counter(mm, member) ((unsigned long)atomic_long_read(&(mm)->_##member))
+#define add_mm_counter(mm, member, value) atomic_long_add(value, &(mm)->_##member)
+#define inc_mm_counter(mm, member) atomic_long_inc(&(mm)->_##member)
+#define dec_mm_counter(mm, member) atomic_long_dec(&(mm)->_##member)
+typedef atomic_long_t mm_counter_t;
+
+#else  /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */
+/*
+ * The mm counters are protected by its page_table_lock,
+ * so can be incremented directly.
+ */
+#define set_mm_counter(mm, member, value) (mm)->_##member = (value)
+#define get_mm_counter(mm, member) ((mm)->_##member)
+#define add_mm_counter(mm, member, value) (mm)->_##member += (value)
+#define inc_mm_counter(mm, member) (mm)->_##member++
+#define dec_mm_counter(mm, member) (mm)->_##member--
+typedef unsigned long mm_counter_t;
+
+#endif /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */
+
+#define get_mm_rss(mm)					\
+	(get_mm_counter(mm, file_rss) + get_mm_counter(mm, anon_rss))
+#define update_hiwater_rss(mm)	do {			\
+	unsigned long _rss = get_mm_rss(mm);		\
+	if ((mm)->hiwater_rss < _rss)			\
+		(mm)->hiwater_rss = _rss;		\
+} while (0)
+#define update_hiwater_vm(mm)	do {			\
+	if ((mm)->hiwater_vm < (mm)->total_vm)		\
+		(mm)->hiwater_vm = (mm)->total_vm;	\
+} while (0)
+
+struct mm_struct {
+	struct vm_area_struct * mmap;		/* list of VMAs */
+	struct rb_root mm_rb;
+	struct vm_area_struct * mmap_cache;	/* last find_vma result */
+	unsigned long (*get_unmapped_area) (struct file *filp,
+				unsigned long addr, unsigned long len,
+				unsigned long pgoff, unsigned long flags);
+	void (*unmap_area) (struct mm_struct *mm, unsigned long addr);
+        unsigned long mmap_base;		/* base of mmap area */
+        unsigned long cached_hole_size;         /* if non-zero, the largest hole below free_area_cache */
+	unsigned long free_area_cache;		/* first hole of size cached_hole_size or larger */
+	pgd_t * pgd;
+	atomic_t mm_users;			/* How many users with user space? */
+	atomic_t mm_count;			/* How many references to "struct mm_struct" (users count as 1) */
+	int map_count;				/* number of VMAs */
+	struct rw_semaphore mmap_sem;
+	spinlock_t page_table_lock;		/* Protects page tables and some counters */
+
+	struct list_head mmlist;		/* List of maybe swapped mm's.  These are globally strung
+						 * together off init_mm.mmlist, and are protected
+						 * by mmlist_lock
+						 */
+
+	/* Special counters, in some configurations protected by the
+	 * page_table_lock, in other configurations by being atomic.
+	 */
+	mm_counter_t _file_rss;
+	mm_counter_t _anon_rss;
+
+	unsigned long hiwater_rss;	/* High-watermark of RSS usage */
+	unsigned long hiwater_vm;	/* High-water virtual memory usage */
+
+	unsigned long total_vm, locked_vm, shared_vm, exec_vm;
+	unsigned long stack_vm, reserved_vm, def_flags, nr_ptes;
+	unsigned long start_code, end_code, start_data, end_data;
+	unsigned long start_brk, brk, start_stack;
+	unsigned long arg_start, arg_end, env_start, env_end;
+
+	unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */
+
+	unsigned dumpable:2;
+	cpumask_t cpu_vm_mask;
+
+	/* Architecture-specific MM context */
+	mm_context_t context;
+
+	/* Token based thrashing protection. */
+	unsigned long swap_token_time;
+	char recent_pagein;
+
+	/* coredumping support */
+	int core_waiters;
+	struct completion *core_startup_done, core_done;
+
+	/* aio bits */
+	rwlock_t		ioctx_list_lock;
+	struct kioctx		*ioctx_list;
+};
+
+struct sighand_struct {
+	atomic_t		count;
+	struct k_sigaction	action[_NSIG];
+	spinlock_t		siglock;
+	struct rcu_head		rcu;
+};
+
+extern void sighand_free_cb(struct rcu_head *rhp);
+
+static inline void sighand_free(struct sighand_struct *sp)
+{
+	call_rcu(&sp->rcu, sighand_free_cb);
+}
+
+/*
+ * NOTE! "signal_struct" does not have it's own
+ * locking, because a shared signal_struct always
+ * implies a shared sighand_struct, so locking
+ * sighand_struct is always a proper superset of
+ * the locking of signal_struct.
+ */
+struct signal_struct {
+	atomic_t		count;
+	atomic_t		live;
+
+	wait_queue_head_t	wait_chldexit;	/* for wait4() */
+
+	/* current thread group signal load-balancing target: */
+	task_t			*curr_target;
+
+	/* shared signal handling: */
+	struct sigpending	shared_pending;
+
+	/* thread group exit support */
+	int			group_exit_code;
+	/* overloaded:
+	 * - notify group_exit_task when ->count is equal to notify_count
+	 * - everyone except group_exit_task is stopped during signal delivery
+	 *   of fatal signals, group_exit_task processes the signal.
+	 */
+	struct task_struct	*group_exit_task;
+	int			notify_count;
+
+	/* thread group stop support, overloads group_exit_code too */
+	int			group_stop_count;
+	unsigned int		flags; /* see SIGNAL_* flags below */
+
+	/* POSIX.1b Interval Timers */
+	struct list_head posix_timers;
+
+	/* ITIMER_REAL timer for the process */
+	struct hrtimer real_timer;
+	ktime_t it_real_incr;
+
+	/* ITIMER_PROF and ITIMER_VIRTUAL timers for the process */
+	cputime_t it_prof_expires, it_virt_expires;
+	cputime_t it_prof_incr, it_virt_incr;
+
+	/* job control IDs */
+	pid_t pgrp;
+	pid_t tty_old_pgrp;
+	pid_t session;
+	/* boolean value for session group leader */
+	int leader;
+
+	struct tty_struct *tty; /* NULL if no tty */
+
+	/*
+	 * Cumulative resource counters for dead threads in the group,
+	 * and for reaped dead child processes forked by this group.
+	 * Live threads maintain their own counters and add to these
+	 * in __exit_signal, except for the group leader.
+	 */
+	cputime_t utime, stime, cutime, cstime;
+	unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
+	unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
+
+	/*
+	 * Cumulative ns of scheduled CPU time for dead threads in the
+	 * group, not including a zombie group leader.  (This only differs
+	 * from jiffies_to_ns(utime + stime) if sched_clock uses something
+	 * other than jiffies.)
+	 */
+	unsigned long long sched_time;
+
+	/*
+	 * We don't bother to synchronize most readers of this at all,
+	 * because there is no reader checking a limit that actually needs
+	 * to get both rlim_cur and rlim_max atomically, and either one
+	 * alone is a single word that can safely be read normally.
+	 * getrlimit/setrlimit use task_lock(current->group_leader) to
+	 * protect this instead of the siglock, because they really
+	 * have no need to disable irqs.
+	 */
+	struct rlimit rlim[RLIM_NLIMITS];
+
+	struct list_head cpu_timers[3];
+
+	/* keep the process-shared keyrings here so that they do the right
+	 * thing in threads created with CLONE_THREAD */
+#ifdef CONFIG_KEYS
+	struct key *session_keyring;	/* keyring inherited over fork */
+	struct key *process_keyring;	/* keyring private to this process */
+#endif
+};
+
+/* Context switch must be unlocked if interrupts are to be enabled */
+#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
+# define __ARCH_WANT_UNLOCKED_CTXSW
+#endif
+
+/*
+ * Bits in flags field of signal_struct.
+ */
+#define SIGNAL_STOP_STOPPED	0x00000001 /* job control stop in effect */
+#define SIGNAL_STOP_DEQUEUED	0x00000002 /* stop signal dequeued */
+#define SIGNAL_STOP_CONTINUED	0x00000004 /* SIGCONT since WCONTINUED reap */
+#define SIGNAL_GROUP_EXIT	0x00000008 /* group exit in progress */
+
+
+/*
+ * Priority of a process goes from 0..MAX_PRIO-1, valid RT
+ * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH
+ * tasks are in the range MAX_RT_PRIO..MAX_PRIO-1. Priority
+ * values are inverted: lower p->prio value means higher priority.
+ *
+ * The MAX_USER_RT_PRIO value allows the actual maximum
+ * RT priority to be separate from the value exported to
+ * user-space.  This allows kernel threads to set their
+ * priority to a value higher than any user task. Note:
+ * MAX_RT_PRIO must not be smaller than MAX_USER_RT_PRIO.
+ */
+
+#define MAX_USER_RT_PRIO	100
+#define MAX_RT_PRIO		MAX_USER_RT_PRIO
+
+#define MAX_PRIO		(MAX_RT_PRIO + 40)
+
+#define rt_task(p)		(unlikely((p)->prio < MAX_RT_PRIO))
+
+/*
+ * Some day this will be a full-fledged user tracking system..
+ */
+struct user_struct {
+	atomic_t __count;	/* reference count */
+	atomic_t processes;	/* How many processes does this user have? */
+	atomic_t files;		/* How many open files does this user have? */
+	atomic_t sigpending;	/* How many pending signals does this user have? */
+#ifdef CONFIG_INOTIFY
+	atomic_t inotify_watches; /* How many inotify watches does this user have? */
+	atomic_t inotify_devs;	/* How many inotify devs does this user have opened? */
+#endif
+	/* protected by mq_lock	*/
+	unsigned long mq_bytes;	/* How many bytes can be allocated to mqueue? */
+	unsigned long locked_shm; /* How many pages of mlocked shm ? */
+
+#ifdef CONFIG_KEYS
+	struct key *uid_keyring;	/* UID specific keyring */
+	struct key *session_keyring;	/* UID's default session keyring */
+#endif
+
+	/* Hash table maintenance information */
+	struct list_head uidhash_list;
+	uid_t uid;
+};
+
+extern struct user_struct *find_user(uid_t);
+
+extern struct user_struct root_user;
+#define INIT_USER (&root_user)
+
+typedef struct prio_array prio_array_t;
+struct backing_dev_info;
+struct reclaim_state;
+
+#ifdef CONFIG_SCHEDSTATS
+struct sched_info {
+	/* cumulative counters */
+	unsigned long	cpu_time,	/* time spent on the cpu */
+			run_delay,	/* time spent waiting on a runqueue */
+			pcnt;		/* # of timeslices run on this cpu */
+
+	/* timestamps */
+	unsigned long	last_arrival,	/* when we last ran on a cpu */
+			last_queued;	/* when we were last queued to run */
+};
+
+extern struct file_operations proc_schedstat_operations;
+#endif
+
+enum idle_type
+{
+	SCHED_IDLE,
+	NOT_IDLE,
+	NEWLY_IDLE,
+	MAX_IDLE_TYPES
+};
+
+/*
+ * sched-domains (multiprocessor balancing) declarations:
+ */
+#ifdef CONFIG_SMP
+#define SCHED_LOAD_SCALE	128UL	/* increase resolution of load */
+
+#define SD_LOAD_BALANCE		1	/* Do load balancing on this domain. */
+#define SD_BALANCE_NEWIDLE	2	/* Balance when about to become idle */
+#define SD_BALANCE_EXEC		4	/* Balance on exec */
+#define SD_BALANCE_FORK		8	/* Balance on fork, clone */
+#define SD_WAKE_IDLE		16	/* Wake to idle CPU on task wakeup */
+#define SD_WAKE_AFFINE		32	/* Wake task to waking CPU */
+#define SD_WAKE_BALANCE		64	/* Perform balancing at task wakeup */
+#define SD_SHARE_CPUPOWER	128	/* Domain members share cpu power */
+
+struct sched_group {
+	struct sched_group *next;	/* Must be a circular list */
+	cpumask_t cpumask;
+
+	/*
+	 * CPU power of this group, SCHED_LOAD_SCALE being max power for a
+	 * single CPU. This is read only (except for setup, hotplug CPU).
+	 */
+	unsigned long cpu_power;
+};
+
+struct sched_domain {
+	/* These fields must be setup */
+	struct sched_domain *parent;	/* top domain must be null terminated */
+	struct sched_group *groups;	/* the balancing groups of the domain */
+	cpumask_t span;			/* span of all CPUs in this domain */
+	unsigned long min_interval;	/* Minimum balance interval ms */
+	unsigned long max_interval;	/* Maximum balance interval ms */
+	unsigned int busy_factor;	/* less balancing by factor if busy */
+	unsigned int imbalance_pct;	/* No balance until over watermark */
+	unsigned long long cache_hot_time; /* Task considered cache hot (ns) */
+	unsigned int cache_nice_tries;	/* Leave cache hot tasks for # tries */
+	unsigned int per_cpu_gain;	/* CPU % gained by adding domain cpus */
+	unsigned int busy_idx;
+	unsigned int idle_idx;
+	unsigned int newidle_idx;
+	unsigned int wake_idx;
+	unsigned int forkexec_idx;
+	int flags;			/* See SD_* */
+
+	/* Runtime fields. */
+	unsigned long last_balance;	/* init to jiffies. units in jiffies */
+	unsigned int balance_interval;	/* initialise to 1. units in ms. */
+	unsigned int nr_balance_failed; /* initialise to 0 */
+
+#ifdef CONFIG_SCHEDSTATS
+	/* load_balance() stats */
+	unsigned long lb_cnt[MAX_IDLE_TYPES];
+	unsigned long lb_failed[MAX_IDLE_TYPES];
+	unsigned long lb_balanced[MAX_IDLE_TYPES];
+	unsigned long lb_imbalance[MAX_IDLE_TYPES];
+	unsigned long lb_gained[MAX_IDLE_TYPES];
+	unsigned long lb_hot_gained[MAX_IDLE_TYPES];
+	unsigned long lb_nobusyg[MAX_IDLE_TYPES];
+	unsigned long lb_nobusyq[MAX_IDLE_TYPES];
+
+	/* Active load balancing */
+	unsigned long alb_cnt;
+	unsigned long alb_failed;
+	unsigned long alb_pushed;
+
+	/* SD_BALANCE_EXEC stats */
+	unsigned long sbe_cnt;
+	unsigned long sbe_balanced;
+	unsigned long sbe_pushed;
+
+	/* SD_BALANCE_FORK stats */
+	unsigned long sbf_cnt;
+	unsigned long sbf_balanced;
+	unsigned long sbf_pushed;
+
+	/* try_to_wake_up() stats */
+	unsigned long ttwu_wake_remote;
+	unsigned long ttwu_move_affine;
+	unsigned long ttwu_move_balance;
+#endif
+};
+
+extern void partition_sched_domains(cpumask_t *partition1,
+				    cpumask_t *partition2);
+
+/*
+ * Maximum cache size the migration-costs auto-tuning code will
+ * search from:
+ */
+extern unsigned int max_cache_size;
+
+#endif	/* CONFIG_SMP */
+
+
+struct io_context;			/* See blkdev.h */
+void exit_io_context(void);
+struct cpuset;
+
+#define NGROUPS_SMALL		32
+#define NGROUPS_PER_BLOCK	((int)(PAGE_SIZE / sizeof(gid_t)))
+struct group_info {
+	int ngroups;
+	atomic_t usage;
+	gid_t small_block[NGROUPS_SMALL];
+	int nblocks;
+	gid_t *blocks[0];
+};
+
+/*
+ * get_group_info() must be called with the owning task locked (via task_lock())
+ * when task != current.  The reason being that the vast majority of callers are
+ * looking at current->group_info, which can not be changed except by the
+ * current task.  Changing current->group_info requires the task lock, too.
+ */
+#define get_group_info(group_info) do { \
+	atomic_inc(&(group_info)->usage); \
+} while (0)
+
+#define put_group_info(group_info) do { \
+	if (atomic_dec_and_test(&(group_info)->usage)) \
+		groups_free(group_info); \
+} while (0)
+
+extern struct group_info *groups_alloc(int gidsetsize);
+extern void groups_free(struct group_info *group_info);
+extern int set_current_groups(struct group_info *group_info);
+extern int groups_search(struct group_info *group_info, gid_t grp);
+/* access the groups "array" with this macro */
+#define GROUP_AT(gi, i) \
+    ((gi)->blocks[(i)/NGROUPS_PER_BLOCK][(i)%NGROUPS_PER_BLOCK])
+
+#ifdef ARCH_HAS_PREFETCH_SWITCH_STACK
+extern void prefetch_stack(struct task_struct*);
+#else
+static inline void prefetch_stack(struct task_struct *t) { }
+#endif
+
+struct audit_context;		/* See audit.c */
+struct mempolicy;
+
+struct task_struct {
+	volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */
+	struct thread_info *thread_info;
+	atomic_t usage;
+	unsigned long flags;	/* per process flags, defined below */
+	unsigned long ptrace;
+
+	int lock_depth;		/* BKL lock depth */
+
+#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
+	int oncpu;
+#endif
+	int prio, static_prio;
+	struct list_head run_list;
+	prio_array_t *array;
+
+	unsigned short ioprio;
+
+	unsigned long sleep_avg;
+	unsigned long long timestamp, last_ran;
+	unsigned long long sched_time; /* sched_clock time spent running */
+	int activated;
+
+	unsigned long policy;
+	cpumask_t cpus_allowed;
+	unsigned int time_slice, first_time_slice;
+
+#ifdef CONFIG_SCHEDSTATS
+	struct sched_info sched_info;
+#endif
+
+	struct list_head tasks;
+	/*
+	 * ptrace_list/ptrace_children forms the list of my children
+	 * that were stolen by a ptracer.
+	 */
+	struct list_head ptrace_children;
+	struct list_head ptrace_list;
+
+	struct mm_struct *mm, *active_mm;
+
+/* task state */
+	struct linux_binfmt *binfmt;
+	long exit_state;
+	int exit_code, exit_signal;
+	int pdeath_signal;  /*  The signal sent when the parent dies  */
+	/* ??? */
+	unsigned long personality;
+	unsigned did_exec:1;
+	pid_t pid;
+	pid_t tgid;
+	/* 
+	 * pointers to (original) parent process, youngest child, younger sibling,
+	 * older sibling, respectively.  (p->father can be replaced with 
+	 * p->parent->pid)
+	 */
+	struct task_struct *real_parent; /* real parent process (when being debugged) */
+	struct task_struct *parent;	/* parent process */
+	/*
+	 * children/sibling forms the list of my children plus the
+	 * tasks I'm ptracing.
+	 */
+	struct list_head children;	/* list of my children */
+	struct list_head sibling;	/* linkage in my parent's children list */
+	struct task_struct *group_leader;	/* threadgroup leader */
+
+	/* PID/PID hash table linkage. */
+	struct pid pids[PIDTYPE_MAX];
+
+	struct completion *vfork_done;		/* for vfork() */
+	int __user *set_child_tid;		/* CLONE_CHILD_SETTID */
+	int __user *clear_child_tid;		/* CLONE_CHILD_CLEARTID */
+
+	unsigned long rt_priority;
+	cputime_t utime, stime;
+	unsigned long nvcsw, nivcsw; /* context switch counts */
+	struct timespec start_time;
+/* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */
+	unsigned long min_flt, maj_flt;
+
+  	cputime_t it_prof_expires, it_virt_expires;
+	unsigned long long it_sched_expires;
+	struct list_head cpu_timers[3];
+
+/* process credentials */
+	uid_t uid,euid,suid,fsuid;
+	gid_t gid,egid,sgid,fsgid;
+	struct group_info *group_info;
+	kernel_cap_t   cap_effective, cap_inheritable, cap_permitted;
+	unsigned keep_capabilities:1;
+	struct user_struct *user;
+#ifdef CONFIG_KEYS
+	struct key *request_key_auth;	/* assumed request_key authority */
+	struct key *thread_keyring;	/* keyring private to this thread */
+	unsigned char jit_keyring;	/* default keyring to attach requested keys to */
+#endif
+	int oomkilladj; /* OOM kill score adjustment (bit shift). */
+	char comm[TASK_COMM_LEN]; /* executable name excluding path
+				     - access with [gs]et_task_comm (which lock
+				       it with task_lock())
+				     - initialized normally by flush_old_exec */
+/* file system info */
+	int link_count, total_link_count;
+/* ipc stuff */
+	struct sysv_sem sysvsem;
+/* CPU-specific state of this task */
+	struct thread_struct thread;
+/* filesystem information */
+	struct fs_struct *fs;
+/* open file information */
+	struct files_struct *files;
+/* namespace */
+	struct namespace *namespace;
+/* signal handlers */
+	struct signal_struct *signal;
+	struct sighand_struct *sighand;
+
+	sigset_t blocked, real_blocked;
+	sigset_t saved_sigmask;		/* To be restored with TIF_RESTORE_SIGMASK */
+	struct sigpending pending;
+
+	unsigned long sas_ss_sp;
+	size_t sas_ss_size;
+	int (*notifier)(void *priv);
+	void *notifier_data;
+	sigset_t *notifier_mask;
+	
+	void *security;
+	struct audit_context *audit_context;
+	seccomp_t seccomp;
+
+/* Thread group tracking */
+   	u32 parent_exec_id;
+   	u32 self_exec_id;
+/* Protection of (de-)allocation: mm, files, fs, tty, keyrings */
+	spinlock_t alloc_lock;
+/* Protection of proc_dentry: nesting proc_lock, dcache_lock, write_lock_irq(&tasklist_lock); */
+	spinlock_t proc_lock;
+
+#ifdef CONFIG_DEBUG_MUTEXES
+	/* mutex deadlock detection */
+	struct mutex_waiter *blocked_on;
+#endif
+
+/* journalling filesystem info */
+	void *journal_info;
+
+/* VM state */
+	struct reclaim_state *reclaim_state;
+
+	struct dentry *proc_dentry;
+	struct backing_dev_info *backing_dev_info;
+
+	struct io_context *io_context;
+
+	unsigned long ptrace_message;
+	siginfo_t *last_siginfo; /* For ptrace use.  */
+/*
+ * current io wait handle: wait queue entry to use for io waits
+ * If this thread is processing aio, this points at the waitqueue
+ * inside the currently handled kiocb. It may be NULL (i.e. default
+ * to a stack based synchronous wait) if its doing sync IO.
+ */
+	wait_queue_t *io_wait;
+/* i/o counters(bytes read/written, #syscalls */
+	u64 rchar, wchar, syscr, syscw;
+#if defined(CONFIG_BSD_PROCESS_ACCT)
+	u64 acct_rss_mem1;	/* accumulated rss usage */
+	u64 acct_vm_mem1;	/* accumulated virtual memory usage */
+	clock_t acct_stimexpd;	/* clock_t-converted stime since last update */
+#endif
+#ifdef CONFIG_NUMA
+  	struct mempolicy *mempolicy;
+	short il_next;
+#endif
+#ifdef CONFIG_CPUSETS
+	struct cpuset *cpuset;
+	nodemask_t mems_allowed;
+	int cpuset_mems_generation;
+#endif
+	atomic_t fs_excl;	/* holding fs exclusive resources */
+	struct rcu_head rcu;
+};
+
+static inline pid_t process_group(struct task_struct *tsk)
+{
+	return tsk->signal->pgrp;
+}
+
+/**
+ * pid_alive - check that a task structure is not stale
+ * @p: Task structure to be checked.
+ *
+ * Test if a process is not yet dead (at most zombie state)
+ * If pid_alive fails, then pointers within the task structure
+ * can be stale and must not be dereferenced.
+ */
+static inline int pid_alive(struct task_struct *p)
+{
+	return p->pids[PIDTYPE_PID].nr != 0;
+}
+
+extern void free_task(struct task_struct *tsk);
+extern void __put_task_struct(struct task_struct *tsk);
+#define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0)
+
+extern void __put_task_struct_cb(struct rcu_head *rhp);
+
+static inline void put_task_struct(struct task_struct *t)
+{
+	if (atomic_dec_and_test(&t->usage))
+		call_rcu(&t->rcu, __put_task_struct_cb);
+}
+
+/*
+ * Per process flags
+ */
+#define PF_ALIGNWARN	0x00000001	/* Print alignment warning msgs */
+					/* Not implemented yet, only for 486*/
+#define PF_STARTING	0x00000002	/* being created */
+#define PF_EXITING	0x00000004	/* getting shut down */
+#define PF_DEAD		0x00000008	/* Dead */
+#define PF_FORKNOEXEC	0x00000040	/* forked but didn't exec */
+#define PF_SUPERPRIV	0x00000100	/* used super-user privileges */
+#define PF_DUMPCORE	0x00000200	/* dumped core */
+#define PF_SIGNALED	0x00000400	/* killed by a signal */
+#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 */
+#define PF_KSWAPD	0x00040000	/* I am kswapd */
+#define PF_SWAPOFF	0x00080000	/* I am in swapoff */
+#define PF_LESS_THROTTLE 0x00100000	/* Throttle me less: I clean memory */
+#define PF_SYNCWRITE	0x00200000	/* I am doing a sync write */
+#define PF_BORROWED_MM	0x00400000	/* I am a kthread doing use_mm */
+#define PF_RANDOMIZE	0x00800000	/* randomize virtual address space */
+#define PF_SWAPWRITE	0x01000000	/* Allowed to write to swap */
+
+/*
+ * Only the _current_ task can read/write to tsk->flags, but other
+ * tasks can access tsk->flags in readonly mode for example
+ * with tsk_used_math (like during threaded core dumping).
+ * There is however an exception to this rule during ptrace
+ * or during fork: the ptracer task is allowed to write to the
+ * child->flags of its traced child (same goes for fork, the parent
+ * can write to the child->flags), because we're guaranteed the
+ * child is not running and in turn not changing child->flags
+ * at the same time the parent does it.
+ */
+#define clear_stopped_child_used_math(child) do { (child)->flags &= ~PF_USED_MATH; } while (0)
+#define set_stopped_child_used_math(child) do { (child)->flags |= PF_USED_MATH; } while (0)
+#define clear_used_math() clear_stopped_child_used_math(current)
+#define set_used_math() set_stopped_child_used_math(current)
+#define conditional_stopped_child_used_math(condition, child) \
+	do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= (condition) ? PF_USED_MATH : 0; } while (0)
+#define conditional_used_math(condition) \
+	conditional_stopped_child_used_math(condition, current)
+#define copy_to_stopped_child_used_math(child) \
+	do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= current->flags & PF_USED_MATH; } while (0)
+/* NOTE: this will return 0 or PF_USED_MATH, it will never return 1 */
+#define tsk_used_math(p) ((p)->flags & PF_USED_MATH)
+#define used_math() tsk_used_math(current)
+
+#ifdef CONFIG_SMP
+extern int set_cpus_allowed(task_t *p, cpumask_t new_mask);
+#else
+static inline int set_cpus_allowed(task_t *p, cpumask_t new_mask)
+{
+	if (!cpu_isset(0, new_mask))
+		return -EINVAL;
+	return 0;
+}
+#endif
+
+extern unsigned long long sched_clock(void);
+extern unsigned long long current_sched_time(const task_t *current_task);
+
+/* sched_exec is called by processes performing an exec */
+#ifdef CONFIG_SMP
+extern void sched_exec(void);
+#else
+#define sched_exec()   {}
+#endif
+
+#ifdef CONFIG_HOTPLUG_CPU
+extern void idle_task_exit(void);
+#else
+static inline void idle_task_exit(void) {}
+#endif
+
+extern void sched_idle_next(void);
+extern void set_user_nice(task_t *p, long nice);
+extern int task_prio(const task_t *p);
+extern int task_nice(const task_t *p);
+extern int can_nice(const task_t *p, const int nice);
+extern int task_curr(const task_t *p);
+extern int idle_cpu(int cpu);
+extern int sched_setscheduler(struct task_struct *, int, struct sched_param *);
+extern task_t *idle_task(int cpu);
+extern task_t *curr_task(int cpu);
+extern void set_curr_task(int cpu, task_t *p);
+
+void yield(void);
+
+/*
+ * The default (Linux) execution domain.
+ */
+extern struct exec_domain	default_exec_domain;
+
+union thread_union {
+	struct thread_info thread_info;
+	unsigned long stack[THREAD_SIZE/sizeof(long)];
+};
+
+#ifndef __HAVE_ARCH_KSTACK_END
+static inline int kstack_end(void *addr)
+{
+	/* Reliable end of stack detection:
+	 * Some APM bios versions misalign the stack
+	 */
+	return !(((unsigned long)addr+sizeof(void*)-1) & (THREAD_SIZE-sizeof(void*)));
+}
+#endif
+
+extern union thread_union init_thread_union;
+extern struct task_struct init_task;
+
+extern struct   mm_struct init_mm;
+
+#define find_task_by_pid(nr)	find_task_by_pid_type(PIDTYPE_PID, nr)
+extern struct task_struct *find_task_by_pid_type(int type, int pid);
+extern void set_special_pids(pid_t session, pid_t pgrp);
+extern void __set_special_pids(pid_t session, pid_t pgrp);
+
+/* per-UID process charging. */
+extern struct user_struct * alloc_uid(uid_t);
+static inline struct user_struct *get_uid(struct user_struct *u)
+{
+	atomic_inc(&u->__count);
+	return u;
+}
+extern void free_uid(struct user_struct *);
+extern void switch_uid(struct user_struct *);
+
+#include <asm/current.h>
+
+extern void do_timer(struct pt_regs *);
+
+extern int FASTCALL(wake_up_state(struct task_struct * tsk, unsigned int state));
+extern int FASTCALL(wake_up_process(struct task_struct * tsk));
+extern void FASTCALL(wake_up_new_task(struct task_struct * tsk,
+						unsigned long clone_flags));
+#ifdef CONFIG_SMP
+ extern void kick_process(struct task_struct *tsk);
+#else
+ static inline void kick_process(struct task_struct *tsk) { }
+#endif
+extern void FASTCALL(sched_fork(task_t * p, int clone_flags));
+extern void FASTCALL(sched_exit(task_t * p));
+
+extern int in_group_p(gid_t);
+extern int in_egroup_p(gid_t);
+
+extern void proc_caches_init(void);
+extern void flush_signals(struct task_struct *);
+extern void flush_signal_handlers(struct task_struct *, int force_default);
+extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info);
+
+static inline int dequeue_signal_lock(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&tsk->sighand->siglock, flags);
+	ret = dequeue_signal(tsk, mask, info);
+	spin_unlock_irqrestore(&tsk->sighand->siglock, flags);
+
+	return ret;
+}	
+
+extern void block_all_signals(int (*notifier)(void *priv), void *priv,
+			      sigset_t *mask);
+extern void unblock_all_signals(void);
+extern void release_task(struct task_struct * p);
+extern int send_sig_info(int, struct siginfo *, struct task_struct *);
+extern int send_group_sig_info(int, struct siginfo *, struct task_struct *);
+extern int force_sigsegv(int, struct task_struct *);
+extern int force_sig_info(int, struct siginfo *, struct task_struct *);
+extern int __kill_pg_info(int sig, struct siginfo *info, pid_t pgrp);
+extern int kill_pg_info(int, struct siginfo *, pid_t);
+extern int kill_proc_info(int, struct siginfo *, pid_t);
+extern int kill_proc_info_as_uid(int, struct siginfo *, pid_t, uid_t, uid_t);
+extern void do_notify_parent(struct task_struct *, int);
+extern void force_sig(int, struct task_struct *);
+extern void force_sig_specific(int, struct task_struct *);
+extern int send_sig(int, struct task_struct *, int);
+extern void zap_other_threads(struct task_struct *p);
+extern int kill_pg(pid_t, int, int);
+extern int kill_sl(pid_t, int, int);
+extern int kill_proc(pid_t, int, int);
+extern struct sigqueue *sigqueue_alloc(void);
+extern void sigqueue_free(struct sigqueue *);
+extern int send_sigqueue(int, struct sigqueue *,  struct task_struct *);
+extern int send_group_sigqueue(int, struct sigqueue *,  struct task_struct *);
+extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *);
+extern int do_sigaltstack(const stack_t __user *, stack_t __user *, unsigned long);
+
+/* These can be the second arg to send_sig_info/send_group_sig_info.  */
+#define SEND_SIG_NOINFO ((struct siginfo *) 0)
+#define SEND_SIG_PRIV	((struct siginfo *) 1)
+#define SEND_SIG_FORCED	((struct siginfo *) 2)
+
+static inline int is_si_special(const struct siginfo *info)
+{
+	return info <= SEND_SIG_FORCED;
+}
+
+/* True if we are on the alternate signal stack.  */
+
+static inline int on_sig_stack(unsigned long sp)
+{
+	return (sp - current->sas_ss_sp < current->sas_ss_size);
+}
+
+static inline int sas_ss_flags(unsigned long sp)
+{
+	return (current->sas_ss_size == 0 ? SS_DISABLE
+		: on_sig_stack(sp) ? SS_ONSTACK : 0);
+}
+
+/*
+ * Routines for handling mm_structs
+ */
+extern struct mm_struct * mm_alloc(void);
+
+/* mmdrop drops the mm and the page tables */
+extern void FASTCALL(__mmdrop(struct mm_struct *));
+static inline void mmdrop(struct mm_struct * mm)
+{
+	if (atomic_dec_and_test(&mm->mm_count))
+		__mmdrop(mm);
+}
+
+/* mmput gets rid of the mappings and all user-space */
+extern void mmput(struct mm_struct *);
+/* Grab a reference to a task's mm, if it is not already going away */
+extern struct mm_struct *get_task_mm(struct task_struct *task);
+/* Remove the current tasks stale references to the old mm_struct */
+extern void mm_release(struct task_struct *, struct mm_struct *);
+
+extern int  copy_thread(int, unsigned long, unsigned long, unsigned long, struct task_struct *, struct pt_regs *);
+extern void flush_thread(void);
+extern void exit_thread(void);
+
+extern void exit_files(struct task_struct *);
+extern void exit_signal(struct task_struct *);
+extern void __exit_signal(struct task_struct *);
+extern void exit_sighand(struct task_struct *);
+extern void __exit_sighand(struct task_struct *);
+extern void exit_itimers(struct signal_struct *);
+
+extern NORET_TYPE void do_group_exit(int);
+
+extern void daemonize(const char *, ...);
+extern int allow_signal(int);
+extern int disallow_signal(int);
+extern task_t *child_reaper;
+
+extern int do_execve(char *, char __user * __user *, char __user * __user *, struct pt_regs *);
+extern long do_fork(unsigned long, unsigned long, struct pt_regs *, unsigned long, int __user *, int __user *);
+task_t *fork_idle(int);
+
+extern void set_task_comm(struct task_struct *tsk, char *from);
+extern void get_task_comm(char *to, struct task_struct *tsk);
+
+#ifdef CONFIG_SMP
+extern void wait_task_inactive(task_t * p);
+#else
+#define wait_task_inactive(p)	do { } while (0)
+#endif
+
+#define remove_parent(p)	list_del_init(&(p)->sibling)
+#define add_parent(p, parent)	list_add_tail(&(p)->sibling,&(parent)->children)
+
+#define REMOVE_LINKS(p) do {					\
+	if (thread_group_leader(p))				\
+		list_del_init(&(p)->tasks);			\
+	remove_parent(p);					\
+	} while (0)
+
+#define SET_LINKS(p) do {					\
+	if (thread_group_leader(p))				\
+		list_add_tail(&(p)->tasks,&init_task.tasks);	\
+	add_parent(p, (p)->parent);				\
+	} while (0)
+
+#define next_task(p)	list_entry((p)->tasks.next, struct task_struct, tasks)
+#define prev_task(p)	list_entry((p)->tasks.prev, struct task_struct, tasks)
+
+#define for_each_process(p) \
+	for (p = &init_task ; (p = next_task(p)) != &init_task ; )
+
+/*
+ * Careful: do_each_thread/while_each_thread is a double loop so
+ *          'break' will not work as expected - use goto instead.
+ */
+#define do_each_thread(g, t) \
+	for (g = t = &init_task ; (g = t = next_task(g)) != &init_task ; ) do
+
+#define while_each_thread(g, t) \
+	while ((t = next_thread(t)) != g)
+
+extern task_t * FASTCALL(next_thread(const task_t *p));
+
+#define thread_group_leader(p)	(p->pid == p->tgid)
+
+static inline int thread_group_empty(task_t *p)
+{
+	return list_empty(&p->pids[PIDTYPE_TGID].pid_list);
+}
+
+#define delay_group_leader(p) \
+		(thread_group_leader(p) && !thread_group_empty(p))
+
+extern void unhash_process(struct task_struct *p);
+
+/*
+ * Protects ->fs, ->files, ->mm, ->ptrace, ->group_info, ->comm, keyring
+ * subscriptions and synchronises with wait4().  Also used in procfs.  Also
+ * pins the final release of task.io_context.  Also protects ->cpuset.
+ *
+ * Nests both inside and outside of read_lock(&tasklist_lock).
+ * It must not be nested with write_lock_irq(&tasklist_lock),
+ * neither inside nor outside.
+ */
+static inline void task_lock(struct task_struct *p)
+{
+	spin_lock(&p->alloc_lock);
+}
+
+static inline void task_unlock(struct task_struct *p)
+{
+	spin_unlock(&p->alloc_lock);
+}
+
+#ifndef __HAVE_THREAD_FUNCTIONS
+
+#define task_thread_info(task) (task)->thread_info
+#define task_stack_page(task) ((void*)((task)->thread_info))
+
+static inline void setup_thread_stack(struct task_struct *p, struct task_struct *org)
+{
+	*task_thread_info(p) = *task_thread_info(org);
+	task_thread_info(p)->task = p;
+}
+
+static inline unsigned long *end_of_stack(struct task_struct *p)
+{
+	return (unsigned long *)(p->thread_info + 1);
+}
+
+#endif
+
+/* set thread flags in other task's structures
+ * - see asm/thread_info.h for TIF_xxxx flags available
+ */
+static inline void set_tsk_thread_flag(struct task_struct *tsk, int flag)
+{
+	set_ti_thread_flag(task_thread_info(tsk), flag);
+}
+
+static inline void clear_tsk_thread_flag(struct task_struct *tsk, int flag)
+{
+	clear_ti_thread_flag(task_thread_info(tsk), flag);
+}
+
+static inline int test_and_set_tsk_thread_flag(struct task_struct *tsk, int flag)
+{
+	return test_and_set_ti_thread_flag(task_thread_info(tsk), flag);
+}
+
+static inline int test_and_clear_tsk_thread_flag(struct task_struct *tsk, int flag)
+{
+	return test_and_clear_ti_thread_flag(task_thread_info(tsk), flag);
+}
+
+static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag)
+{
+	return test_ti_thread_flag(task_thread_info(tsk), flag);
+}
+
+static inline void set_tsk_need_resched(struct task_struct *tsk)
+{
+	set_tsk_thread_flag(tsk,TIF_NEED_RESCHED);
+}
+
+static inline void clear_tsk_need_resched(struct task_struct *tsk)
+{
+	clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED);
+}
+
+static inline int signal_pending(struct task_struct *p)
+{
+	return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING));
+}
+  
+static inline int need_resched(void)
+{
+	return unlikely(test_thread_flag(TIF_NEED_RESCHED));
+}
+
+/*
+ * cond_resched() and cond_resched_lock(): latency reduction via
+ * explicit rescheduling in places that are safe. The return
+ * value indicates whether a reschedule was done in fact.
+ * cond_resched_lock() will drop the spinlock before scheduling,
+ * cond_resched_softirq() will enable bhs before scheduling.
+ */
+extern int cond_resched(void);
+extern int cond_resched_lock(spinlock_t * lock);
+extern int cond_resched_softirq(void);
+
+/*
+ * Does a critical section need to be broken due to another
+ * task waiting?:
+ */
+#if defined(CONFIG_PREEMPT) && defined(CONFIG_SMP)
+# define need_lockbreak(lock) ((lock)->break_lock)
+#else
+# define need_lockbreak(lock) 0
+#endif
+
+/*
+ * Does a critical section need to be broken due to another
+ * task waiting or preemption being signalled:
+ */
+static inline int lock_need_resched(spinlock_t *lock)
+{
+	if (need_lockbreak(lock) || need_resched())
+		return 1;
+	return 0;
+}
+
+/* Reevaluate whether the task has signals pending delivery.
+   This is required every time the blocked sigset_t changes.
+   callers must hold sighand->siglock.  */
+
+extern FASTCALL(void recalc_sigpending_tsk(struct task_struct *t));
+extern void recalc_sigpending(void);
+
+extern void signal_wake_up(struct task_struct *t, int resume_stopped);
+
+/*
+ * Wrappers for p->thread_info->cpu access. No-op on UP.
+ */
+#ifdef CONFIG_SMP
+
+static inline unsigned int task_cpu(const struct task_struct *p)
+{
+	return task_thread_info(p)->cpu;
+}
+
+static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)
+{
+	task_thread_info(p)->cpu = cpu;
+}
+
+#else
+
+static inline unsigned int task_cpu(const struct task_struct *p)
+{
+	return 0;
+}
+
+static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)
+{
+}
+
+#endif /* CONFIG_SMP */
+
+#ifdef HAVE_ARCH_PICK_MMAP_LAYOUT
+extern void arch_pick_mmap_layout(struct mm_struct *mm);
+#else
+static inline void arch_pick_mmap_layout(struct mm_struct *mm)
+{
+	mm->mmap_base = TASK_UNMAPPED_BASE;
+	mm->get_unmapped_area = arch_get_unmapped_area;
+	mm->unmap_area = arch_unmap_area;
+}
+#endif
+
+extern long sched_setaffinity(pid_t pid, cpumask_t new_mask);
+extern long sched_getaffinity(pid_t pid, cpumask_t *mask);
+
+extern void normalize_rt_tasks(void);
+
+#ifdef CONFIG_PM
+/*
+ * Check if a process has been frozen
+ */
+static inline int frozen(struct task_struct *p)
+{
+	return p->flags & PF_FROZEN;
+}
+
+/*
+ * Check if there is a request to freeze a process
+ */
+static inline int freezing(struct task_struct *p)
+{
+	return p->flags & PF_FREEZE;
+}
+
+/*
+ * Request that a process be frozen
+ * FIXME: SMP problem. We may not modify other process' flags!
+ */
+static inline void freeze(struct task_struct *p)
+{
+	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();
+		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; }
+
+#endif /* CONFIG_PM */
+#endif /* __KERNEL__ */
+
+#endif
diff -urN oldtree/include/linux/suspend.h newtree/include/linux/suspend.h
--- oldtree/include/linux/suspend.h	2006-02-18 15:18:29.971760848 +0000
+++ newtree/include/linux/suspend.h	2006-02-18 15:24:31.365820600 +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 {
@@ -46,6 +47,8 @@
 #if defined(CONFIG_VT) && defined(CONFIG_VT_CONSOLE)
 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 pm_prepare_console(void) { return 0; }
 static inline void pm_restore_console(void) {}
@@ -56,8 +59,12 @@
 	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 /* CONFIG_PM */
 
+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	2006-02-18 15:24:31.366820448 +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 suspend_update_status (unsigned long value, unsigned long maximum,
+		const char *fmt, ...);
+extern void suspend_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 suspend_copyback_low(void);
+extern inline void suspend_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 suspend_update_status(unsigned long value, unsigned long maximum,
+		const char *fmt, ...)
+{
+	return maximum;
+}
+#define suspend_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	2006-02-18 15:18:29.983759024 +0000
+++ newtree/include/linux/workqueue.h	2006-02-18 15:24:31.367820296 +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	2006-01-03 03:21:10.000000000 +0000
+++ newtree/init/do_mounts.c	2006-02-18 15:24:31.368820144 +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	2006-01-03 03:21:10.000000000 +0000
+++ newtree/init/do_mounts_initrd.c	2006-02-18 15:24:31.369819992 +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	2006-02-18 15:18:30.056747928 +0000
+++ newtree/init/main.c	2006-02-18 15:24:31.370819840 +0000
@@ -688,7 +688,9 @@
 
 	/*
 	 * 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	2006-02-18 15:18:30.061747168 +0000
+++ newtree/kernel/audit.c	2006-02-18 15:24:31.371819688 +0000
@@ -288,6 +288,9 @@
 			}
 		} else {
 			DECLARE_WAITQUEUE(wait, current);
+			
+			try_to_freeze();
+
 			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	2006-02-18 15:18:30.074745192 +0000
+++ newtree/kernel/fork.c	2006-02-18 15:24:31.373819384 +0000
@@ -35,6 +35,7 @@
 #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>
@@ -166,7 +167,13 @@
 	if (!tsk)
 		return NULL;
 
-	ti = alloc_thread_info(tsk);
+	if (test_suspend_state(SUSPEND_FORK_COPYBACK_THREAD)) {
+		extern void * suspend_get_nonconflicting_pages(int);
+		ti = suspend_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;
diff -urN oldtree/kernel/kmod.c newtree/kernel/kmod.c
--- oldtree/kernel/kmod.c	2006-01-03 03:21:10.000000000 +0000
+++ newtree/kernel/kmod.c	2006-02-18 15:24:31.374819232 +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	2006-01-03 03:21:10.000000000 +0000
+++ newtree/kernel/kthread.c	2006-02-18 15:24:31.375819080 +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	2006-02-18 15:18:30.086743368 +0000
+++ newtree/kernel/power/Kconfig	2006-02-18 15:24:31.376818928 +0000
@@ -98,3 +98,76 @@
 	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 SUSPEND2
+		select SWAP
+		---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	2006-01-03 03:21:10.000000000 +0000
+++ newtree/kernel/power/Makefile	2006-02-18 15:24:31.377818776 +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 modules.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	2006-02-18 15:24:31.378818624 +0000
@@ -0,0 +1,473 @@
+/*
+ */
+
+#include <linux/suspend.h>
+#include <linux/highmem.h>
+#include <linux/kthread.h>
+#include <asm/setup.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 "modules.h"
+#include "atomic_copy.h"
+#include "suspend2.h"
+#include "checksum.h"
+#include "pageflags.h"
+#include "debug_pagealloc.h"
+#include "storage.h"
+
+#include <asm/suspend2.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 */
+
+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 *) suspend_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 inline __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);
+
+	suspend_map_atomic_copy_pages();
+
+	suspend_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);
+
+	suspend_unmap_atomic_copy_pages();
+
+	local_irq_disable();
+	device_power_up();
+	local_irq_enable();
+
+	device_resume();
+
+	if (pm_ops && pm_ops->finish && suspend_powerdown_method > 3)
+		pm_ops->finish(suspend_powerdown_method);
+
+	if (suspend_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);
+	
+	suspend_prepare_status(DONT_CLEAR_BAR, "Cleaning up...");
+}
+
+
+/*
+ * suspend_pre_copy
+ * Functionality   : Steps taken prior to saving CPU state and the image
+ *                   itself.
+ * Called From     : do_suspend2_lowlevel
+ */
+
+static void suspend_pre_copy(void)
+{
+	suspend2_arch_pre_copy();
+
+	device_suspend(PMSG_FREEZE);
+
+	mb();
+	barrier();
+
+	local_irq_disable();
+
+	device_power_down(PMSG_FREEZE);
+}
+
+/*
+ * suspend_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 suspend_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) &&
+	    suspend_powerdown_method != PM_SUSPEND_MEM)
+		printk(KERN_EMERG name_suspend
+			"Suspend failed, trying to recover...\n");
+	barrier();
+	mb();
+}
+
+/*
+ * copyback_low
+ */
+
+static inline 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) {
+		copyback_prepare();
+
+		suspend2_arch_save_processor_context();
+
+		copyback_low(); /* 0 = use logical addresses */
+
+		suspend2_arch_restore_processor_context();
+	} else {
+		suspend_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();
+		
+		suspend_checksum_print_differences();
+
+		copyback_post();
+		
+	} else {
+		suspend_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 suspend_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();
+
+	suspend_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	2006-02-18 15:24:31.379818472 +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	2006-02-18 15:24:31.380818320 +0000
@@ -0,0 +1,76 @@
+/*
+ * 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 suspend_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 suspend_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);
+	int (*write_header_chunk_finish) (void);
+};
+
+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	2006-02-18 15:24:31.380818320 +0000
@@ -0,0 +1,11 @@
+#ifdef CONFIG_SUSPEND2_CHECKSUMS
+extern void suspend_verify_checksums(void);
+extern void suspend_checksum_calculate_checksums(void);
+extern void suspend_checksum_print_differences(void);
+extern int suspend_allocate_checksum_pages(void);
+#else
+static inline void suspend_verify_checksums(void) { };
+static inline void suspend_checksum_calculate_checksums(void) { };
+static inline void suspend_checksum_print_differences(void) { };
+static inline int suspend_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	2006-02-18 15:24:31.382818016 +0000
@@ -0,0 +1,638 @@
+/*
+ * kernel/power/suspend_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 "modules.h"
+#include "proc.h"
+#include "suspend2_common.h"
+#include "io.h"
+
+#define S2C_WRITE 0
+#define S2C_READ 1
+
+static int suspend_expected_compression = 0;
+
+static struct suspend_module_ops suspend_compression_ops;
+static struct suspend_module_ops *next_driver;
+
+static char suspend_compressor_name[32];
+static struct crypto_tfm *suspend_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;
+}
+
+/* suspend_crypto_cleanup
+ *
+ * Description:	Frees memory allocated for our labours.
+ */
+
+static void suspend_crypto_cleanup(void)
+{
+	if (suspend_compressor_transform) {
+		crypto_free_tfm(suspend_compressor_transform);
+		suspend_compressor_transform = NULL;
+	}
+}
+
+/* suspend_crypto_prepare
+ *
+ * Description:	Prepare to do some work by allocating buffers and transforms.
+ * Returns:	Int: Zero if successful, -ENONEM otherwise.
+ */
+
+static int suspend_compress_crypto_prepare(int mode)
+{
+	if (!*suspend_compressor_name) {
+		printk("Suspend2: Compression enabled but no compressor name set.\n");
+		return 1;
+	}
+
+	if (!(suspend_compressor_transform = crypto_alloc_tfm(suspend_compressor_name, 0))) {
+		printk("Suspend2: Failed to initialise the %s compression transform.\n",
+				suspend_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 suspend_compress_write_init(int stream_number)
+{
+	int result;
+	
+	next_driver = suspend_get_next_filter(&suspend_compression_ops);
+
+	if (!next_driver) {
+		printk("Compression Driver: Argh! No one wants my output!");
+		return -ECHILD;
+	}
+
+	if ((result = suspend_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;
+}
+
+/* suspend_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 suspend_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;
+}
+
+/* suspend_compress_write_chunk()
+ *
+ * Description:	Compress a page of data, buffering output and passing on
+ * 		filled pages to the next module 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
+ * 		modules, -ECHILD if we have a broken pipeline or -EIO if
+ * 		zlib errs.
+ */
+
+static int suspend_compress_write_chunk(struct page *buffer_page)
+{
+	int ret; 
+	unsigned int len;
+	u16 len_written;
+	char *buffer_start;
+	
+	if (!suspend_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(suspend_compressor_transform,
+			buffer_start, PAGE_SIZE,
+			page_buffer, &len);
+	
+	if (ret) {
+		printk("Compression failed.\n");
+		goto failure;
+	}
+	
+	len_written = (u16) len;
+		
+	if ((ret = suspend_compress_write((u8 *)&len_written, 2)) >= 0) {
+		if ((ret = suspend_compress_write((u8 *) &position, sizeof(position))))
+			return -EIO;
+		if (len < PAGE_SIZE) { // some compression
+			position += len;
+			ret = suspend_compress_write(page_buffer, len);
+		} else {
+			ret = suspend_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 suspend_compress_write_cleanup(void)
+{
+	int ret = 0;
+	
+	if (suspend_compressor_transform)
+		ret = next_driver->ops.filter.write_chunk(virt_to_page(local_buffer));
+
+	suspend_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 suspend_compress_read_init(int stream_number)
+{
+	int result;
+
+	next_driver = suspend_get_next_filter(&suspend_compression_ops);
+
+	if (!next_driver) {
+		printk("Compression Driver: Argh! No one wants "
+				"to feed me data!");
+		return -ECHILD;
+	}
+	
+	if ((result = suspend_compress_crypto_prepare(S2C_READ)))
+		return result;
+	
+	if ((result = allocate_local_buffer()))
+		return result;
+
+	bufofs = PAGE_SIZE;
+
+	position = 0;
+
+	return 0;
+}
+
+/* suspend_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 suspend_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;
+}
+
+/* suspend_compress_read_chunk()
+ *
+ * Description:	Retrieve data from later modules and decompress it until the
+ * 		input buffer is filled.
+ * Arguments:	Buffer_start: 	Pointer to a buffer of size PAGE_SIZE.
+ * 		Sync:		Whether the previous module (or core) wants its
+ * 				data synchronously.
+ * Returns:	Zero if successful. Error condition from me or from downstream
+ * 		on failure.
+ */
+
+static int suspend_compress_read_chunk(struct page *buffer_page, int sync)
+{
+	int ret, position_saved; 
+	unsigned int len;
+	u16 len_written;
+	char *buffer_start;
+
+	if (!suspend_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 = suspend_compress_read ((u8 *)&len_written, 2)) >= 0) {
+		len = (unsigned int) len_written;
+		ret = suspend_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 = suspend_compress_read(buffer_start, PAGE_SIZE);
+			if (ret)
+				return ret;
+
+			position += PAGE_SIZE;
+		} else { // compressed
+			if ((ret = suspend_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(suspend_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 suspend_compress_read_cleanup(void)
+{ 
+	suspend_crypto_cleanup();
+	free_local_buffer();
+	return 0;
+}
+
+/* suspend_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 suspend_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",
+			suspend_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 suspend_compress_memory_needed(void)
+{
+	return PAGE_SIZE;
+}
+
+static unsigned long suspend_compress_storage_needed(void)
+{
+	return 2 * sizeof(unsigned long) + sizeof(int);
+}
+
+/* suspend_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 suspend_compress_save_config_info(char *buffer)
+{
+	int namelen = strlen(suspend_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))) = suspend_expected_compression;
+	*((unsigned long *) (buffer + 3 * sizeof(unsigned long))) = namelen;
+	strncpy(buffer + 4 * sizeof(unsigned long), suspend_compressor_name, namelen);
+	total_len = 4 * sizeof(unsigned long) + namelen;
+	return total_len;
+}
+
+/* suspend_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 suspend_compress_load_config_info(char *buffer, int size)
+{
+	int namelen;
+	
+	bytes_in = *((unsigned long *) buffer);
+	bytes_out = *((unsigned long *) (buffer + 1 * sizeof(unsigned long)));
+	suspend_expected_compression = *((unsigned long *) (buffer + 2 * sizeof(unsigned long)));
+	namelen = *((unsigned long *) (buffer + 3 * sizeof(unsigned long)));
+	strncpy(suspend_compressor_name, buffer + 4 * sizeof(unsigned long), namelen);
+	return;
+}
+
+/* suspend_expected_compression_ratio
+ * 
+ * Description:	Returns the expected ratio between data passed into this module
+ * 		and the amount of data output when writing.
+ * Returns:	100 if the module is disabled. Otherwise the value set by the
+ * 		user via our proc entry.
+ */
+
+int suspend_expected_compression_ratio(void)
+{
+	if (suspend_compression_ops.disabled)
+		return 100;
+	else
+		return 100 - suspend_expected_compression;
+}
+
+static void suspend_compressor_disable_if_empty(void)
+{
+	suspend_compression_ops.disabled = !(*suspend_compressor_name);
+}
+
+static int suspend_compress_initialise(int starting_cycle)
+{
+	if (starting_cycle)
+		suspend_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	= &suspend_expected_compression,
+				.minimum	= 0,
+				.maximum	= 99,
+			}
+		}
+	},
+
+	{
+		.filename			= "disable_compression",
+		.permissions			= PROC_RW,
+		.type				= SUSPEND_PROC_DATA_INTEGER,
+		.data = {
+			.integer = {
+				.variable	= &suspend_compression_ops.disabled,
+				.minimum	= 0,
+				.maximum	= 1,
+			}
+		}
+	},
+
+	{
+		.filename			= "compressor",
+		.permissions			= PROC_RW,
+		.type				= SUSPEND_PROC_DATA_STRING,
+		.data = {
+			.string = {
+				.variable	= suspend_compressor_name,
+				.max_length	= 31,
+			}
+		},
+		.write_proc			= &suspend_compressor_disable_if_empty,
+	}
+};
+
+/*
+ * Ops structure.
+ */
+
+static struct suspend_module_ops suspend_compression_ops = {
+	.type			= FILTER_PLUGIN,
+	.name			= "Suspend2 Compressor",
+	.module			= THIS_MODULE,
+	.memory_needed 		= suspend_compress_memory_needed,
+	.print_debug_info	= suspend_compress_print_debug_stats,
+	.save_config_info	= suspend_compress_save_config_info,
+	.load_config_info	= suspend_compress_load_config_info,
+	.storage_needed		= suspend_compress_storage_needed,
+	
+	.initialise		= suspend_compress_initialise,
+	
+	.write_init		= suspend_compress_write_init,
+	.write_cleanup		= suspend_compress_write_cleanup,
+	.read_init		= suspend_compress_read_init,
+	.read_cleanup		= suspend_compress_read_cleanup,
+
+	.ops = {
+		.filter = {
+			.write_chunk		= suspend_compress_write_chunk,
+			.read_chunk		= suspend_compress_read_chunk,
+		}
+	}
+};
+
+/* ---- Registration ---- */
+
+static __init int suspend_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_module(&suspend_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 suspend_compress_unload(void)
+{
+	printk("Suspend2 Compression Driver unloading.\n");
+	for (i=0; i< numfiles; i++)
+		suspend_unregister_procfile(&proc_params[i]);
+	suspend_unregister_module(&suspend_compression_ops);
+}
+
+
+module_init(suspend_compress_load);
+module_exit(suspend_compress_unload);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Nigel Cunningham");
+MODULE_DESCRIPTION("Compression Support for Suspend2");
+#else
+late_initcall(suspend_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	2006-02-18 15:24:31.383817864 +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;
+}
+
+/*
+ * suspend_map_atomic_copy_pages
+ *
+ * When DEBUG_PAGEALLOC is enabled, we need to map the pages before
+ * an atomic copy.
+ */
+void suspend_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);
+	}
+}
+
+/*
+ * suspend_unmap_atomic_copy_pages
+ *
+ * We also need to unmap pages when DEBUG_PAGEALLOC is enabled.
+ */
+void suspend_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 suspend_map_atomic_copy_pages(void) { };
+
+void suspend_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	2006-02-18 15:24:31.384817712 +0000
@@ -0,0 +1,3 @@
+extern void suspend_map_atomic_copy_pages(void);
+extern void suspend_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	2006-02-18 15:18:30.087743216 +0000
+++ newtree/kernel/power/disk.c	2006-02-18 15:24:31.385817560 +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>
@@ -99,7 +100,7 @@
 	if (!(error = swsusp_shrink_memory()))
 		return 0;
 thaw:
-	thaw_processes();
+	thaw_processes(FREEZER_ALL_THREADS);
 	enable_nonboot_cpus();
 	pm_restore_console();
 	return error;
@@ -108,7 +109,7 @@
 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	2006-02-18 15:24:31.386817408 +0000
@@ -0,0 +1,597 @@
+/*
+ * kernel/power/suspend_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 "modules.h"
+#include "proc.h"
+#include "suspend2_common.h"
+#include "io.h"
+
+#define S2C_WRITE 0
+#define S2C_READ 1
+
+static struct suspend_module_ops suspend_encryption_ops;
+static struct suspend_module_ops *next_driver;
+
+static char suspend_encryptor_name[32];
+static struct crypto_tfm *suspend_encryptor_transform;
+static char suspend_encryptor_key[256];
+static int suspend_key_len;
+static char suspend_encryptor_iv[256];
+static int suspend_encryptor_mode;
+static int suspend_encryptor_save_key_and_iv;
+
+static u8 *page_buffer = NULL;
+static unsigned int bufofs;
+
+static struct scatterlist suspend_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 / suspend_key_len); i++) {
+			suspend_crypt_sg[i].page = virt_to_page(page_buffer);
+			suspend_crypt_sg[i].offset = suspend_key_len * i;
+			suspend_crypt_sg[i].length = suspend_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;
+}
+
+/* suspend_crypto_cleanup
+ *
+ * Description:	Frees memory allocated for our labours.
+ */
+
+static void suspend_crypto_cleanup(void)
+{
+	if (suspend_encryptor_transform) {
+		crypto_free_tfm(suspend_encryptor_transform);
+		suspend_encryptor_transform = NULL;
+	}
+}
+
+/* suspend_crypto_prepare
+ *
+ * Description:	Prepare to do some work by allocating buffers and transforms.
+ * Returns:	Int: Zero if successful, -ENONEM otherwise.
+ */
+
+static int suspend_encrypt_crypto_prepare(int mode)
+{
+	if (!*suspend_encryptor_name) {
+		printk("Suspend2: Encryptor enabled but no name set.\n");
+		return 1;
+	}
+
+	if (!(suspend_encryptor_transform = crypto_alloc_tfm(suspend_encryptor_name,
+					1 << suspend_encryptor_mode))) {
+		printk("Suspend2: Failed to initialise the encryption transform (%s, mode %d).\n",
+				suspend_encryptor_name, suspend_encryptor_mode);
+		return 1;
+	}
+
+	if (mode)
+		bufofs = PAGE_SIZE;
+	else
+		bufofs = 0;
+
+	suspend_key_len = strlen(suspend_encryptor_key);
+
+	if (crypto_cipher_setkey(suspend_encryptor_transform, suspend_encryptor_key, 
+				suspend_key_len)) {
+		printk("%d is an invalid key length for cipher %s.\n",
+					suspend_key_len,
+					suspend_encryptor_name);
+		return 1;
+	}
+	
+	if (!mode) {
+		crypto_cipher_set_iv(suspend_encryptor_transform,
+				suspend_encryptor_iv,
+				crypto_tfm_alg_ivsize(suspend_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 suspend_encrypt_write_init(int stream_number)
+{
+	int result;
+	
+	next_driver = suspend_get_next_filter(&suspend_encryption_ops);
+
+	if (!next_driver) {
+		printk("Encryption Driver: Argh! No one wants my output!");
+		return -ECHILD;
+	}
+
+	if ((result = suspend_encrypt_crypto_prepare(S2C_WRITE))) {
+		set_result_state(SUSPEND_ENCRYPTION_SETUP_FAILED);
+		suspend_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;
+}
+
+/* suspend_encrypt_write_chunk()
+ *
+ * Description:	Encrypt a page of data, buffering output and passing on
+ * 		filled pages to the next module 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
+ * 		modules, -ECHILD if we have a broken pipeline or -EIO if
+ * 		zlib errs.
+ */
+
+static int suspend_encrypt_write_chunk(struct page *buffer_page)
+{
+	int ret; 
+	unsigned int len;
+	u16 len_written;
+	char *buffer_start;
+	
+	if (!suspend_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(suspend_encryptor_transform,
+			suspend_crypt_sg, suspend_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 suspend_encrypt_write_cleanup(void)
+{
+	suspend_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 suspend_encrypt_read_init(int stream_number)
+{
+	int result;
+
+	next_driver = suspend_get_next_filter(&suspend_encryption_ops);
+
+	if (!next_driver) {
+		printk("Encryption Driver: Argh! No one wants "
+				"to feed me data!");
+		return -ECHILD;
+	}
+	
+	if ((result = suspend_encrypt_crypto_prepare(S2C_READ))) {
+		set_result_state(SUSPEND_ENCRYPTION_SETUP_FAILED);
+		suspend_crypto_cleanup();
+		return result;
+	}
+	
+	if ((result = allocate_local_buffer()))
+		return result;
+
+	bufofs = PAGE_SIZE;
+
+	return 0;
+}
+
+/* suspend_encrypt_read_chunk()
+ *
+ * Description:	Retrieve data from later modules and deencrypt it until the
+ * 		input buffer is filled.
+ * Arguments:	Buffer_start: 	Pointer to a buffer of size PAGE_SIZE.
+ * 		Sync:		Whether the previous module (or core) wants its
+ * 				data synchronously.
+ * Returns:	Zero if successful. Error condition from me or from downstream
+ * 		on failure.
+ */
+
+static int suspend_encrypt_read_chunk(struct page *buffer_page, int sync)
+{
+	int ret; 
+	char *buffer_start;
+
+	if (!suspend_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(suspend_encryptor_transform,
+			suspend_crypt_sg, suspend_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 suspend_encrypt_read_cleanup(void)
+{
+	suspend_crypto_cleanup();
+	free_local_buffer();
+	return 0;
+}
+
+/* suspend_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 suspend_encrypt_print_debug_stats(char *buffer, int size)
+{
+	int len;
+	
+	len = snprintf_used(buffer, size, "- Encryptor %s enabled.\n",
+			suspend_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 suspend_encrypt_memory_needed(void)
+{
+	return PAGE_SIZE;
+}
+
+static unsigned long suspend_encrypt_storage_needed(void)
+{
+	return 2 * sizeof(unsigned long) + sizeof(int);
+}
+
+/* suspend_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 suspend_encrypt_save_config_info(char *buffer)
+{
+	int buf_offset, str_size;
+
+	str_size = strlen(suspend_encryptor_name);
+	*buffer = (char) str_size;
+	strncpy(buffer + 1, suspend_encryptor_name, str_size + 1);
+	buf_offset = str_size + 2;
+
+	*(buffer + buf_offset) = (char) suspend_encryptor_mode;
+	buf_offset++;
+
+	*(buffer + buf_offset) = (char) suspend_encryptor_save_key_and_iv;
+	buf_offset++;
+
+	if (suspend_encryptor_save_key_and_iv) {
+		
+		str_size = strlen(suspend_encryptor_key);
+		*(buffer + buf_offset) = (char) str_size;
+		strncpy(buffer + buf_offset + 1, suspend_encryptor_key, str_size + 1);
+
+		buf_offset+= str_size + 2;
+
+		str_size = strlen(suspend_encryptor_iv);
+		*(buffer + buf_offset) = (char) str_size;
+		strncpy(buffer + buf_offset + 1, suspend_encryptor_iv, str_size + 1);
+
+		buf_offset += str_size + 2;
+	}
+
+	return buf_offset;
+}
+
+/* suspend_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 suspend_encrypt_load_config_info(char *buffer, int size)
+{
+	int buf_offset, str_size;
+
+	str_size = (int) *buffer;
+	strncpy(suspend_encryptor_name, buffer + 1, str_size + 1);
+	buf_offset = str_size + 2;
+	
+	suspend_encryptor_mode = (int) *(buffer + buf_offset);
+	buf_offset++;
+
+	suspend_encryptor_save_key_and_iv = (int) *(buffer + buf_offset);
+	buf_offset++;
+
+	if (suspend_encryptor_save_key_and_iv) {
+		str_size = (int) *(buffer + buf_offset);
+		strncpy(suspend_encryptor_key, buffer + buf_offset + 1, str_size + 1);
+
+		buf_offset+= str_size + 2;
+
+		str_size = (int) *(buffer + buf_offset);
+		strncpy(suspend_encryptor_iv, buffer + buf_offset + 1, str_size + 1);
+
+		buf_offset += str_size + 2;
+	} else {
+		*suspend_encryptor_key = 0;
+		*suspend_encryptor_iv = 0;
+	}
+	
+	if (buf_offset != size) {
+		printk("Suspend Encryptor config info size mismatch (%d != %d): settings ignored.\n",
+				buf_offset, size);
+		*suspend_encryptor_key = 0;
+		*suspend_encryptor_iv = 0;
+	}
+	return;
+}
+
+static void suspend_encryptor_disable_if_empty(void)
+{
+	suspend_encryption_ops.disabled = !(*suspend_encryptor_name);
+}
+
+static int suspend_encrypt_initialise(int starting_cycle)
+{
+	if (starting_cycle)
+		suspend_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	= suspend_encryptor_name,
+				.max_length	= 31,
+			}
+		},
+		.write_proc			= suspend_encryptor_disable_if_empty,
+	},
+
+	{
+		.filename			= "encryption_mode",
+		.permissions			= PROC_RW,
+		.type				= SUSPEND_PROC_DATA_INTEGER,
+		.data = {
+			.integer = {
+				.variable	= &suspend_encryptor_mode,
+				.minimum	= 0,
+				.maximum	= 3,
+			}
+		}
+	},
+
+	{
+		.filename			= "encryption_save_key_and_iv",
+		.permissions			= PROC_RW,
+		.type				= SUSPEND_PROC_DATA_INTEGER,
+		.data = {
+			.integer = {
+				.variable	= &suspend_encryptor_save_key_and_iv,
+				.minimum	= 0,
+				.maximum	= 1,
+			}
+		}
+	},
+
+	{
+		.filename			= "encryption_key",
+		.permissions			= PROC_RW,
+		.type				= SUSPEND_PROC_DATA_STRING,
+		.data = {
+			.string = {
+				.variable	= suspend_encryptor_key,
+				.max_length	= 255,
+			}
+		}
+	},
+
+	{
+		.filename			= "encryption_iv",
+		.permissions			= PROC_RW,
+		.type				= SUSPEND_PROC_DATA_STRING,
+		.data = {
+			.string = {
+				.variable	= suspend_encryptor_iv,
+				.max_length	= 255,
+			}
+		}
+	},
+
+	{
+		.filename			= "disable_encryption",
+		.permissions			= PROC_RW,
+		.type				= SUSPEND_PROC_DATA_INTEGER,
+		.data = {
+			.integer = {
+				.variable	= &suspend_encryption_ops.disabled,
+				.minimum	= 0,
+				.maximum	= 1,
+			}
+		}
+	},
+	
+};
+
+/*
+ * Ops structure.
+ */
+
+static struct suspend_module_ops suspend_encryption_ops = {
+	.type			= FILTER_PLUGIN,
+	.name			= "Encryptor",
+	.module			= THIS_MODULE,
+	.memory_needed 		= suspend_encrypt_memory_needed,
+	.print_debug_info	= suspend_encrypt_print_debug_stats,
+	.save_config_info	= suspend_encrypt_save_config_info,
+	.load_config_info	= suspend_encrypt_load_config_info,
+	.storage_needed		= suspend_encrypt_storage_needed,
+	
+	.initialise		= suspend_encrypt_initialise,
+	
+	.write_init		= suspend_encrypt_write_init,
+	.write_cleanup		= suspend_encrypt_write_cleanup,
+	.read_init		= suspend_encrypt_read_init,
+	.read_cleanup		= suspend_encrypt_read_cleanup,
+
+	.ops = {
+		.filter = {
+			.write_chunk		= suspend_encrypt_write_chunk,
+			.read_chunk		= suspend_encrypt_read_chunk,
+		}
+	}
+};
+
+/* ---- Registration ---- */
+
+static __init int suspend_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_module(&suspend_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(suspend_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	2006-02-18 15:24:31.387817256 +0000
@@ -0,0 +1,247 @@
+/* kernel/power/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 "modules.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 = suspend_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 = suspend_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 = suspend_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 = suspend_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	2006-02-18 15:24:31.388817104 +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	2006-02-18 15:24:31.390816800 +0000
@@ -0,0 +1,1026 @@
+/*
+ * 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 "modules.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_module_ops *this_writer;
+	int result, returning = 0;
+
+	if (suspend_activate_storage(0))
+		return 0;
+
+	suspend_active_writer = NULL;
+	clear_suspend_state(SUSPEND_RESUME_DEVICE_OK);
+	set_suspend_state(SUSPEND_DISABLED);
+	clear_result_state(SUSPEND_ABORTED);
+
+	if (!suspend_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_module_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, (suspend_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.
+				 */
+
+				suspend_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:
+	suspend_deactivate_storage(0);
+	return returning;
+}
+
+void attempt_to_parse_resume_device2(void)
+{
+	suspend_prepare_usm();
+	attempt_to_parse_resume_device();
+	suspend_cleanup_usm();
+}
+
+/* noresume_reset_modules
+ *
+ * Description:	When we read the start of an image, modules (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_modules(void)
+{
+	struct suspend_module_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 (suspend_active_writer && suspend_active_writer->ops.writer.noresume_reset)
+		suspend_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 = suspend_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_modules
+ *
+ * Iterate over modules, preparing the ones that will be used to read or write
+ * data.
+ */
+static int rw_init_modules(int write, int which)
+{
+	struct suspend_module_ops *this_module;
+	/* Initialise page transformers */
+	list_for_each_entry(this_module, &suspend_filters,
+			ops.filter.filter_list) {
+		if (this_module->disabled)
+			continue;
+		if ((write && this_module->write_init &&
+			this_module->write_init(which)) ||
+		    (!write && this_module->read_init &&
+		     	this_module->read_init(which))) {
+			abort_suspend("Failed to initialise the %s filter.",
+				this_module->name);
+				return 1;
+		}
+	}
+
+	/* Initialise writer */
+	if ((write && suspend_active_writer->write_init(which)) ||
+	    (!write && suspend_active_writer->read_init(which))) {
+		abort_suspend("Failed to initialise the writer."); 
+		if (!write)
+			suspend_active_writer->ops.writer.invalidate_image();
+		return 1;
+	}
+
+	/* Initialise other modules */
+	list_for_each_entry(this_module, &suspend_modules, module_list) {
+		if (this_module->disabled)
+			continue;
+		if ((this_module->type == FILTER_PLUGIN) ||
+		    (this_module->type == WRITER_PLUGIN))
+			continue;
+		if ((write && this_module->write_init &&
+			this_module->write_init(which)) ||
+		    (!write && this_module->read_init &&
+		     	this_module->read_init(which))) {
+				set_result_state(SUSPEND_ABORTED);
+				return 1;
+			}
+	}
+
+	return 0;
+}
+
+/*
+ * rw_cleanup_modules
+ *
+ * Cleanup components after reading or writing a set of pages.
+ * Only the writer may fail.
+ */
+static int rw_cleanup_modules(int write)
+{
+	struct suspend_module_ops *this_module;
+	int result = 0;
+
+	/* Cleanup other modules */
+	list_for_each_entry(this_module, &suspend_modules, module_list) {
+		if (this_module->disabled)
+			continue;
+		if ((this_module->type == FILTER_PLUGIN) ||
+		    (this_module->type == WRITER_PLUGIN))
+			continue;
+		if (write) {
+			if (this_module->write_cleanup)
+				result |= this_module->write_cleanup();
+		} else
+			if (this_module->read_cleanup)
+				result |= this_module->read_cleanup();
+	}
+
+	/* Flush data and cleanup */
+	list_for_each_entry(this_module, &suspend_filters,
+			ops.filter.filter_list) {
+		if (this_module->disabled)
+			continue;
+		if (write) {
+			if (this_module->write_cleanup)
+				result |= this_module->write_cleanup();
+		} else
+			if (this_module->read_cleanup)
+				result |= this_module->read_cleanup();
+	}
+
+	if (write)
+		result |= suspend_active_writer->write_cleanup();
+	else
+		result |= suspend_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_module_ops *first_filter = suspend_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 = suspend_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");
+
+	suspend_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) {
+		suspend_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 {
+		suspend_prepare_status(CLEAR_BAR, "Writing caches...");
+		pageflags = &pageset2_map;
+		bytes_in = bytes_out = 0;
+	}	
+	
+	start_time = jiffies;
+
+	if (!rw_init_modules(1, whichtowrite))
+		error = do_rw_loop(1, finish_at, pageflags, base, barmax);
+
+	if (rw_cleanup_modules(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) {
+		suspend_prepare_status(CLEAR_BAR,
+				"Reading kernel & process data...");
+		pageflags = &pageset1_copy_map;
+	} else {
+		suspend_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_modules(0, whichtoread)) {
+		suspend_active_writer->ops.writer.invalidate_image();
+		result = 1;
+	} else
+		result = do_rw_loop(0, finish_at, pageflags, base, barmax);
+
+	if (rw_cleanup_modules(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_module_configs()
+ *
+ * Description:	Store the configuration for each module in the image header.
+ * Returns:	Int: Zero on success, Error value otherwise.
+ */
+static int write_module_configs(void)
+{
+	struct suspend_module_ops *this_module;
+	char *buffer = (char *) get_zeroed_page(GFP_ATOMIC);
+	int len, index = 1;
+	struct suspend_module_header suspend_module_header;
+
+	if (!buffer) {
+		printk("Failed to allocate a buffer for saving "
+				"module configuration info.\n");
+		return -ENOMEM;
+	}
+		
+	/* 
+	 * We have to know which data goes with which module, so we at
+	 * least write a length of zero for a module. Note that we are
+	 * also assuming every module's config data takes <= PAGE_SIZE.
+	 */
+
+	/* For each module (in registration order) */
+	list_for_each_entry(this_module, &suspend_modules, module_list) {
+
+		/* Get the data from the module */
+		len = 0;
+		if (this_module->save_config_info)
+			len = this_module->save_config_info(buffer);
+
+		/* Save the details of the module */
+		suspend_module_header.disabled = this_module->disabled;
+		suspend_module_header.type = this_module->type;
+		suspend_module_header.index = index++;
+		strncpy(suspend_module_header.name, this_module->name, 
+					sizeof(suspend_module_header.name));
+		suspend_active_writer->ops.writer.write_header_chunk(
+				(char *) &suspend_module_header,
+				sizeof(suspend_module_header));
+
+		/* Save the size of the data and any data returned */
+		suspend_active_writer->ops.writer.write_header_chunk((char *) &len,
+				sizeof(int));
+		if (len)
+			suspend_active_writer->ops.writer.write_header_chunk(
+					buffer, len);
+	}
+
+	/* Write a blank header to terminate the list */
+	suspend_module_header.name[0] = '\0';
+	suspend_active_writer->ops.writer.write_header_chunk(
+			(char *) &suspend_module_header,
+			sizeof(suspend_module_header));
+
+	free_page((unsigned long) buffer);
+	return 0;
+}
+
+/* read_module_configs()
+ *
+ * Description:	Reload module configurations from the image header.
+ * Returns:	Int. Zero on success, error value otherwise.
+ */
+
+static int read_module_configs(void)
+{
+	struct suspend_module_ops *this_module;
+	char *buffer = (char *) get_zeroed_page(GFP_ATOMIC);
+	int len, result = 0;
+	struct suspend_module_header suspend_module_header;
+
+	if (!buffer) {
+		printk("Failed to allocate a buffer for reloading module "
+				"configuration info.\n");
+		return -ENOMEM;
+	}
+		
+	/* All modules are initially disabled. That way, if we have a module
+	 * 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_module, &suspend_modules, module_list)
+		this_module->disabled = 1;
+	
+	/* Get the first module header */
+	result = suspend_active_writer->ops.writer.read_header_chunk(
+			(char *) &suspend_module_header, sizeof(suspend_module_header));
+	if (!result) {
+		printk("Failed to read the next module header.\n");
+		free_page((unsigned long) buffer);
+		return -EINVAL;
+	}
+
+	/* For each module (in registration order) */
+	while (suspend_module_header.name[0]) {
+
+		/* Find the module */
+		this_module = suspend_find_module_given_name(suspend_module_header.name);
+
+		if (!this_module) {
+			/* 
+			 * Is it used? Only need to worry about filters. The active
+			 * writer must be loaded!
+			 */
+			if ((!suspend_module_header.disabled) &&
+			    (suspend_module_header.type == FILTER_PLUGIN)) {
+				suspend_early_boot_message(1, SUSPEND_CONTINUE_REQ,
+					"It looks like we need module %s for "
+					"reading the image but it hasn't been "
+					"registered.\n",
+					suspend_module_header.name);
+				if (!(test_suspend_state(SUSPEND_CONTINUE_REQ))) {
+					suspend_active_writer->ops.writer.invalidate_image();
+					result = -EINVAL;
+					noresume_reset_modules();
+					free_page((unsigned long) buffer);
+					return -EINVAL;
+				}
+			} else
+				printk("Plugin %s configuration data found, but the module "
+					"hasn't registered. Looks like it was disabled, so "
+					"we're ignoring it's data.",
+					suspend_module_header.name);
+		}
+		
+		/* Get the length of the data (if any) */
+		result = suspend_active_writer->ops.writer.read_header_chunk(
+				(char *) &len, sizeof(int));
+		if (!result) {
+			printk("Failed to read the length of the module %s's"
+					" configuration data.\n",
+					suspend_module_header.name);
+			free_page((unsigned long) buffer);
+			return -EINVAL;
+		}
+
+		/* Read any data and pass to the module (if we found one) */
+		if (len) {
+			suspend_active_writer->ops.writer.read_header_chunk(buffer, len);
+			if (this_module) {
+				if (!this_module->save_config_info) {
+					printk("Huh? Plugin %s appears to have a "
+						"save_config_info, but not a "
+						"load_config_info function!\n",
+						this_module->name);
+				} else
+					this_module->load_config_info(buffer, len);
+			}
+		}
+
+		if (this_module) {
+			/* Now move this module to the tail of its lists. This will put it
+			 * in order. Any new modules 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_module_tail(this_module);
+
+			/* 
+			 * We apply the disabled state; modules don't need to save whether they
+			 * were disabled and if they do, we override them anyway.
+			 */
+			this_module->disabled = suspend_module_header.disabled;
+		}
+
+		/* Get the next module header */
+		result = suspend_active_writer->ops.writer.read_header_chunk(
+				(char *) &suspend_module_header,
+				sizeof(suspend_module_header));
+
+		if (!result) {
+			printk("Failed to read the next module 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 = suspend_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);
+	suspend_active_writer->ops.writer.write_header_chunk(header_buffer,
+			sizeof(struct suspend_header));
+
+	free_page((unsigned long) header_buffer);
+
+	/* Write module configurations */
+	if ((ret = write_module_configs())) {
+		abort_suspend("Failed to write module configs.");
+		goto write_image_header_abort;
+	}
+
+	save_dyn_pageflags(pageset1_map);
+
+	if (suspend_active_writer->ops.writer.serialise_extents &&
+	    (ret = suspend_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 (suspend_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");
+	suspend_update_status(total, total, NULL);
+
+	return 0;
+
+write_image_header_abort:
+	suspend_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 = suspend_active_writer->ops.writer.image_exists())) {
+		result = -ENODATA;
+		noresume_reset_modules();
+		goto out;
+	}
+
+	/* Check for noresume command line option */
+	if (test_suspend_state(SUSPEND_NORESUME_SPECIFIED)) {
+		suspend_active_writer->ops.writer.invalidate_image();
+		result = -EINVAL;
+		noresume_reset_modules();
+		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))) {
+			suspend_active_writer->ops.writer.invalidate_image();
+			result = -EINVAL;
+			noresume_reset_modules();
+			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 = suspend_active_writer->ops.writer.read_header_init())) {
+		noresume_reset_modules();
+		goto out;
+	}
+	
+	/* Read suspend header */
+	if ((result = suspend_active_writer->ops.writer.read_header_chunk(
+			header_buffer, sizeof(struct suspend_header))) < 0) {
+		noresume_reset_modules();
+		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)) {
+		suspend_active_writer->ops.writer.invalidate_image();
+		result = -EINVAL;
+		noresume_reset_modules();
+		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.
+	 */
+	
+	suspend_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 module configurations */
+	if ((result = read_module_configs())) {
+		noresume_reset_modules();
+		pagedir1.pageset_size =
+			pagedir2.pageset_size = 0;
+		goto out;
+	}
+
+	suspend_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 (suspend_active_writer->ops.writer.load_extents &&
+	    (result = suspend_active_writer->ops.writer.load_extents())) {
+		noresume_reset_modules();
+		abort_suspend("Active writer's load_extents "
+				"function failed.");
+		goto out_reset_console;
+	}
+
+	/* Clean up after reading the header */
+	if ((result = suspend_active_writer->ops.writer.read_header_cleanup())) {
+		noresume_reset_modules();
+		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 (suspend_get_pageset1_load_addresses()) {
+		result = -ENOMEM;
+		noresume_reset_modules();
+		goto out_reset_console;
+	}
+
+	/* Read the original kernel back */
+	check_shift_keys(1, "About to read pageset 1.");
+
+	if (read_pageset(&pagedir1, 1, 0)) {
+		suspend_prepare_status(CLEAR_BAR, "Failed to read pageset 1.");
+		result = -EPERM;
+		noresume_reset_modules();
+		goto out_reset_console;
+	}
+
+	check_shift_keys(1, "About to restore original kernel.");
+	result = 0;
+
+	if (!test_action_state(SUSPEND_KEEP_IMAGE) &&
+	    suspend_active_writer->ops.writer.mark_resume_attempted)
+		suspend_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);
+	suspend_cleanup_console();
+	goto out;
+}
+
+/* read_pageset1()
+ *
+ * Description:	Attempt to read the header and pageset1 of a suspend image.
+ * 		Handle the outcome, complaining where appropriate.
+ */
+
+int read_pageset1(void)
+{
+	int error;
+
+	error = __read_pageset1();
+
+	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;
+}
+
+/*
+ * get_have_image_data()
+ */
+
+char *get_have_image_data(void)
+{
+	char *output_buffer = (char *) get_zeroed_page(GFP_ATOMIC);
+	struct suspend_header *suspend_header;
+
+	if (!output_buffer) {
+		printk("Output buffer null.\n");
+		return NULL;
+	}
+
+	/* Check for an image */
+	if (!suspend_active_writer->ops.writer.image_exists() ||
+	    suspend_active_writer->ops.writer.read_header_init() ||
+	    suspend_active_writer->ops.writer.read_header_chunk(
+			output_buffer, sizeof(struct suspend_header)) !=
+	    		sizeof(struct suspend_header)) {
+		sprintf(output_buffer, "0\n");
+		goto out;
+	}
+
+	suspend_header = (struct suspend_header *) output_buffer;
+
+	sprintf(output_buffer, "1\n%s\n%s\n",
+			suspend_header->machine,
+			suspend_header->version);
+
+	/* Check whether we've resumed before */
+	if (test_suspend_state(SUSPEND_RESUMED_BEFORE))
+		strcat(output_buffer, "Resumed before.\n");
+
+out:
+	noresume_reset_modules();
+	return output_buffer;
+}
+
+/* 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);
+
+	suspend_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	2006-02-18 15:24:31.391816648 +0000
@@ -0,0 +1,38 @@
+/*
+ * kernel/power/io.h
+ */
+
+#include "pagedir.h"
+
+/* Non-module 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	2006-02-18 15:18:30.087743216 +0000
+++ newtree/kernel/power/main.c	2006-02-18 15:24:31.392816496 +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;
@@ -133,7 +134,7 @@
 static void suspend_finish(suspend_state_t state)
 {
 	device_resume();
-	thaw_processes();
+	thaw_processes(FREEZER_ALL_THREADS);
 	enable_nonboot_cpus();
 	if (pm_ops && pm_ops->finish)
 		pm_ops->finish(state);
@@ -146,7 +147,7 @@
 static char *pm_states[PM_SUSPEND_MAX] = {
 	[PM_SUSPEND_STANDBY]	= "standby",
 	[PM_SUSPEND_MEM]	= "mem",
-#ifdef CONFIG_SOFTWARE_SUSPEND
+#if defined(CONFIG_SOFTWARE_SUSPEND) || defined(CONFIG_SUSPEND2)
 	[PM_SUSPEND_DISK]	= "disk",
 #endif
 };
@@ -177,7 +178,7 @@
 
 static int enter_state(suspend_state_t state)
 {
-	int error;
+	int error = 0;
 
 	if (!valid_state(state))
 		return -ENODEV;
diff -urN oldtree/kernel/power/modules.c newtree/kernel/power/modules.c
--- oldtree/kernel/power/modules.c	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/modules.c	2006-02-18 15:24:31.393816344 +0000
@@ -0,0 +1,312 @@
+/*
+ * kernel/power/modules.c
+ *
+ * Copyright (C) 2004-2005 Nigel Cunningham <nigel@suspend2.net>
+ *
+ */
+
+#include <linux/suspend.h>
+#include <linux/module.h>
+#include "suspend2.h"
+#include "modules.h"
+
+struct list_head suspend_filters, suspend_writers, suspend_modules;
+struct suspend_module_ops *suspend_active_writer;
+static int suspend_num_filters;
+int suspend_num_writers, suspend_num_modules;
+
+/*
+ * suspend_header_storage_for_modules
+ *
+ * Returns the amount of space needed to store configuration
+ * data needed by the modules 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 suspend_header_storage_for_modules(void)
+{
+	struct suspend_module_ops *this_module;
+	unsigned long bytes = 0;
+	
+	list_for_each_entry(this_module, &suspend_modules, module_list) {
+		if (this_module->disabled)
+			continue;
+		if (this_module->storage_needed)
+			bytes += this_module->storage_needed();
+	}
+
+	return bytes;
+}
+
+/*
+ * suspend_memory_for_modules
+ *
+ * Returns the amount of memory requested by modules for
+ * doing their work during the cycle.
+ */
+
+unsigned long suspend_memory_for_modules(void)
+{
+	unsigned long bytes = 0;
+	struct suspend_module_ops *this_module;
+
+	list_for_each_entry(this_module, &suspend_modules, module_list) {
+		if (this_module->disabled)
+			continue;
+		if (this_module->memory_needed)
+			bytes += this_module->memory_needed();
+	}
+
+	return ((bytes + PAGE_SIZE - 1) >> PAGE_SHIFT);
+}
+
+/* suspend_find_module_given_name
+ * Functionality :	Return a module (if found), given a pointer
+ * 			to its name
+ */
+
+struct suspend_module_ops *suspend_find_module_given_name(char *name)
+{
+	struct suspend_module_ops *this_module, *found_module = NULL;
+	
+	list_for_each_entry(this_module, &suspend_modules, module_list) {
+		if (!strcmp(name, this_module->name)) {
+			found_module = this_module;
+			break;
+		}			
+	}
+
+	return found_module;
+}
+
+/*
+ * suspend_print_module_debug_info
+ * Functionality   : Get debugging info from modules into a buffer.
+ */
+int suspend_print_module_debug_info(char *buffer, int buffer_size)
+{
+	struct suspend_module_ops *this_module;
+	int len = 0;
+
+	list_for_each_entry(this_module, &suspend_modules, module_list) {
+		if (this_module->disabled)
+			continue;
+		if (this_module->print_debug_info) {
+			int result;
+			result = this_module->print_debug_info(buffer + len, 
+					buffer_size - len);
+			len += result;
+		}
+	}
+
+	return len;
+}
+
+/*
+ * suspend_register_module
+ *
+ * Register a module.
+ */
+int suspend_register_module(struct suspend_module_ops *module)
+{
+	if (suspend_find_module_given_name(module->name))
+		return -EBUSY;
+
+	switch (module->type) {
+		case FILTER_PLUGIN:
+			list_add_tail(&module->ops.filter.filter_list,
+					&suspend_filters);
+			suspend_num_filters++;
+			break;
+
+		case WRITER_PLUGIN:
+			list_add_tail(&module->ops.writer.writer_list,
+					&suspend_writers);
+			suspend_num_writers++;
+			break;
+
+		case MISC_PLUGIN:
+			break;
+
+		default:
+			printk("Hmmm. Plugin '%s' has an invalid type."
+				" It has been ignored.\n", module->name);
+			return -EINVAL;
+	}
+	list_add_tail(&module->module_list, &suspend_modules);
+	suspend_num_modules++;
+
+	return 0;	
+}
+
+/*
+ * suspend_unregister_module
+ *
+ * Remove a module.
+ */
+void suspend_unregister_module(struct suspend_module_ops *module)
+{
+	switch (module->type) {
+		case FILTER_PLUGIN:
+			list_del(&module->ops.filter.filter_list);
+			suspend_num_filters--;
+			break;
+
+		case WRITER_PLUGIN:
+			list_del(&module->ops.writer.writer_list);
+			suspend_num_writers--;
+			if (suspend_active_writer == module) {
+				suspend_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", module->name);
+			return;
+	}
+	list_del(&module->module_list);
+	suspend_num_modules--;
+}
+
+/*
+ * suspend_move_module_tail
+ *
+ * Rearrange modules when reloading the config.
+ */
+void suspend_move_module_tail(struct suspend_module_ops *module)
+{
+	switch (module->type) {
+		case FILTER_PLUGIN:
+			if (suspend_num_filters > 1)
+				list_move_tail(&module->ops.filter.filter_list,
+						&suspend_filters);
+			break;
+
+		case WRITER_PLUGIN:
+			if (suspend_num_writers > 1)
+				list_move_tail(&module->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", module->name);
+			return;
+	}
+	if ((suspend_num_filters + suspend_num_writers) > 1)
+		list_move_tail(&module->module_list, &suspend_modules);
+}
+
+/*
+ * suspend_initialise_modules
+ *
+ * Get ready to do some work!
+ */
+int suspend_initialise_modules(int starting_cycle)
+{
+	struct suspend_module_ops *this_module;
+	int result;
+	
+	list_for_each_entry(this_module, &suspend_modules, module_list) {
+		if (this_module->disabled)
+			continue;
+		if (this_module->initialise) {
+			suspend_message(SUSPEND_MEMORY, SUSPEND_MEDIUM, 1,
+				"Initialising module %s.\n",
+				this_module->name);
+			if ((result = this_module->initialise(starting_cycle))) {
+				printk("%s didn't initialise okay.\n",
+						this_module->name);
+				return result;
+			}
+		}
+	}
+
+	return 0;
+}
+
+/* 
+ * suspend_cleanup_modules
+ *
+ * Tell modules the work is done.
+ */
+void suspend_cleanup_modules(int finishing_cycle)
+{
+	struct suspend_module_ops *this_module;
+	
+	list_for_each_entry(this_module, &suspend_modules, module_list) {
+		if (this_module->disabled)
+			continue;
+		if (this_module->cleanup) {
+			suspend_message(SUSPEND_MEMORY, SUSPEND_MEDIUM, 1,
+				"Cleaning up module %s.\n",
+				this_module->name);
+			this_module->cleanup(finishing_cycle);
+		}
+	}
+}
+
+/*
+ * suspend_get_next_filter
+ *
+ * Get the next filter in the pipeline.
+ */
+struct suspend_module_ops *suspend_get_next_filter(struct suspend_module_ops *filter_sought)
+{
+	struct suspend_module_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 suspend_active_writer;
+}
+
+/* suspend_get_modules
+ * 
+ * Take a reference to modules so they can't go away under us.
+ */
+
+int suspend_get_modules(void)
+{
+	struct suspend_module_ops *this_module;
+	
+	list_for_each_entry(this_module, &suspend_modules, module_list) {
+		if (!try_module_get(this_module->module)) {
+			/* Failed! Reverse gets and return error */
+			struct suspend_module_ops *this_module2;
+			list_for_each_entry(this_module2, &suspend_modules, module_list) {
+				if (this_module == this_module2)
+					return -EINVAL;
+				module_put(this_module2->module);
+			}
+		}
+	}
+
+	return 0;
+}
+
+/* suspend_put_modules
+ *
+ * Release our references to modules we used.
+ */
+
+void suspend_put_modules(void)
+{
+	struct suspend_module_ops *this_module;
+	
+	list_for_each_entry(this_module, &suspend_modules, module_list) {
+		module_put(this_module->module);
+	}
+}
diff -urN oldtree/kernel/power/modules.h newtree/kernel/power/modules.h
--- oldtree/kernel/power/modules.h	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/modules.h	2006-02-18 15:24:31.394816192 +0000
@@ -0,0 +1,180 @@
+/*
+ * kernel/power/modules.h
+ *
+ * Copyright (C) 2004-2005 Nigel Cunningham <nigel@suspend2.net>
+ *
+ * This file is released under the GPLv2.
+ *
+ * It contains declarations for modules. 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 module name */
+#define SUSPEND_MAX_PLUGIN_NAME_LENGTH 30
+
+/* Per-module metadata */
+struct suspend_module_header {
+	char name[SUSPEND_MAX_PLUGIN_NAME_LENGTH];
+	int disabled;
+	int type;
+	int index;
+	int data_length;
+	unsigned long signature;
+};
+
+extern int suspend_num_modules, suspend_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 module 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 module if image exists but reading aborted */
+	void (*noresume_reset) (void);
+
+	/* Calls for allocating storage */
+
+	/* Maximum size of image we can save (incl. space already allocated).*/
+	int (*storage_available) (void);
+	
+	/* Amount of storage already allocated */
+	int (*storage_allocated) (void);
+
+	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_module_ops {
+	/* Functions common to all modules */
+	int type;
+	char *name;
+	struct module *module;
+	int disabled;
+	struct list_head module_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_module_ops *suspend_active_writer;
+extern struct list_head suspend_filters, suspend_writers, suspend_modules;
+
+extern void suspend_prepare_console_modules(void);
+extern void suspend_cleanup_console_modules(void);
+
+extern struct suspend_module_ops *suspend_find_module_given_name(char *name),
+	*suspend_get_next_filter(struct suspend_module_ops *);
+
+extern int suspend_register_module(struct suspend_module_ops *module);
+extern void suspend_move_module_tail(struct suspend_module_ops *module);
+
+extern unsigned long suspend_header_storage_for_modules(void);
+extern unsigned long suspend_memory_for_modules(void);
+
+extern int suspend_print_module_debug_info(char *buffer, int buffer_size);
+extern int suspend_register_module(struct suspend_module_ops *module);
+extern void suspend_unregister_module(struct suspend_module_ops *module);
+
+extern int suspend_initialise_modules(int starting_cycle);
+extern void suspend_cleanup_modules(int finishing_cycle);
+
+int suspend_get_modules(void);
+void suspend_put_modules(void);
+
+static inline void suspend_initialise_module_lists(void) {
+	INIT_LIST_HEAD(&suspend_filters);
+	INIT_LIST_HEAD(&suspend_writers);
+	INIT_LIST_HEAD(&suspend_modules);
+}
+
+extern int suspend_expected_compression_ratio(void);
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	2006-02-18 15:24:31.395816040 +0000
@@ -0,0 +1,370 @@
+/*
+ * 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 suspend_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 *suspend_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 suspend_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(suspend_notify_userspace_work, suspend_notify_userspace, NULL);
+
+void suspend_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 = suspend_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 */
+	suspend_notify_userspace_work.data = uhd;
+	schedule_work(&suspend_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)
+{
+	suspend_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;
+
+	suspend_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 suspend_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 suspend_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 = suspend_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 suspend_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) {
+			suspend_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,
+			suspend_netlink_input, THIS_MODULE);
+	if (!uhd->nl) {
+		printk("Failed to allocate netlink socket for %s.\n",
+				uhd->name);
+		return -ENOMEM;
+	}
+
+	suspend_fill_skb_pool(uhd);
+
+	return 0;
+}
+
+void suspend_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;
+	}
+}
+
+int suspend2_launch_userspace_program(char *command, int channel_no)
+{
+	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 = command;
+
+	if (!strlen(orig_posn))
+		return 1;
+
+	/* Up to 7 args supported */
+	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++;
+	}
+	
+	if (channel_no) {
+		sprintf(channel, "-c%d", channel_no);
+		argv[arg] = channel;
+	} else
+		arg--;
+
+	retval = call_usermodehelper(argv[0], argv, envp, 0);
+
+	if (retval)
+		printk("Failed to launch userspace program '%s': Error %d\n",
+				command, retval);
+
+	{
+		int i;
+		for (i = 0; i < arg; i++)
+			if (argv[i] && argv[i] != channel)
+				kfree(argv[i]);
+	}
+
+	kfree(channel);
+
+	return retval;
+}
+
+int suspend_netlink_setup(struct user_helper_data *uhd)
+{
+	if (netlink_prepare(uhd) < 0) {
+		printk("Netlink prepare failed.\n");
+		return 1;
+	}
+
+	if (suspend2_launch_userspace_program(uhd->program, uhd->netlink_id) < 0) {
+		printk("Launch userspace program failed.\n");
+		suspend_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);
+		suspend_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	2006-02-18 15:24:31.396815888 +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 suspend_send_netlink_message(struct user_helper_data *uhd,
+		int type, void* params, size_t len);
+int suspend_netlink_setup(struct user_helper_data *uhd);
+void suspend_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	2006-02-18 15:24:31.397815736 +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))
+
+/* suspend_free_extra_pagedir_memory
+ *
+ * Description:	Free a previously pagedir metadata.
+ */
+void suspend_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);
+	}
+}
+
+/* suspend_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 suspend_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;
+}
+
+/*
+ * suspend_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 suspend_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 suspend_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) {
+		suspend_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());
+
+}
+
+/* suspend_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 suspend_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 suspend_relocate_if_required(unsigned long *current_value, unsigned int size)
+{
+	if (PagePageset1(virt_to_page(*current_value))) {
+		unsigned long new_page = suspend_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 suspend_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 *) suspend_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	2006-02-18 15:24:31.398815584 +0000
@@ -0,0 +1,37 @@
+/*
+ * kernel/power/suspend_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 suspend_copy_pageset1(void);
+
+extern void suspend_free_extra_pagedir_memory(void);
+
+extern int suspend_allocate_extra_pagedir_memory(struct pagedir *p, int pageset_size, int alloc_from);
+
+extern void suspend_mark_task_as_pageset1 (struct task_struct *t);
+extern void suspend_mark_pages_for_pageset2(void);
+
+extern void suspend_relocate_if_required(unsigned long *current_value, unsigned int size);
+extern int suspend_get_pageset1_load_addresses(void);
+
+extern int extra_pagedir_pages_allocated;
+
+extern unsigned long suspend_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	2006-02-18 15:24:31.399815432 +0000
@@ -0,0 +1,150 @@
+/*
+ * kernel/power/suspend_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 "modules.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 num_zones(void)
+{
+	int result = 0;
+	struct zone *zone;
+
+	for_each_zone(zone)
+		result++;
+
+	return result;
+}
+
+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);
+		suspend_active_writer->ops.writer.write_header_chunk((char *) &zone_num, sizeof(int));
+		suspend_active_writer->ops.writer.write_header_chunk((char *) &size, sizeof(int));
+
+		for (i = 0; i < size; i++)
+			suspend_active_writer->ops.writer.write_header_chunk((char *) pagemap[zone_num][i], PAGE_SIZE);
+		zone_num++;
+	}
+	zone_num = -1;
+	suspend_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;
+		suspend_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();	       
+		}
+		suspend_active_writer->ops.writer.read_header_chunk((char *) &size, sizeof(int));
+
+		for (i = 0; i < size; i++)
+			suspend_active_writer->ops.writer.read_header_chunk((char *) pagemap[zone_num][i], PAGE_SIZE);
+		zone_num++;
+	}
+	suspend_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;
+
+	suspend_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);
+
+		suspend_relocate_if_required((void *) &((*pagemap)[zone_num]), sizeof(void *) * pages);
+
+		for (i = 0; i < pages; i++)
+			suspend_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	2006-02-18 15:24:31.400815280 +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 PageUnmap(page) (test_dynpageflag(&unmap_map, page))
+#define SetPageUnmap(page) (set_dynpageflag(&unmap_map, page))
+#define ClearPageUnmap(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/power.h newtree/kernel/power/power.h
--- oldtree/kernel/power/power.h	2006-02-18 15:18:30.087743216 +0000
+++ newtree/kernel/power/power.h	2006-02-18 15:24:31.401815128 +0000
@@ -1,6 +1,8 @@
 #include <linux/suspend.h>
 #include <linux/utsname.h>
 
+#include "suspend.h"
+
 struct swsusp_info {
 	struct new_utsname	uts;
 	u32			version_code;
@@ -35,7 +37,7 @@
 extern struct subsystem power_subsys;
 
 /* 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 struct pbe *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	2006-02-18 15:24:31.402814976 +0000
@@ -0,0 +1,78 @@
+/*
+ * kernel/power/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 suspend_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 && suspend_powerdown_method &&
+	    pm_ops->prepare(suspend_powerdown_method))
+			return 0;
+
+	if (suspend_powerdown_method > 3)
+		kernel_shutdown_prepare(SYSTEM_SUSPEND_DISK);
+	else {
+		if (device_suspend(PMSG_SUSPEND)) {
+			printk(KERN_ERR "Some devices failed to suspend\n");
+			return 0;
+		}
+	}
+
+	if (suspend_enter(suspend_powerdown_method))
+		return 0;
+
+	device_resume();
+
+	if (pm_ops && pm_ops->finish && suspend_powerdown_method)
+		pm_ops->finish(suspend_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)) {
+		suspend_prepare_status(DONT_CLEAR_BAR, "Ready to reboot.");
+		kernel_restart(NULL);
+	}
+
+	if (pm_ops && pm_ops->enter && suspend_powerdown_method && try_pm_state_powerdown())
+		return;
+
+	kernel_power_off();
+	suspend_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	2006-02-18 15:24:31.403814824 +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 suspend_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	2006-02-18 15:24:31.404814672 +0000
@@ -0,0 +1,751 @@
+/*
+ * 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 (suspend_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 <linux/hardirq.h>
+
+#include "suspend2.h"
+#include "pageflags.h"
+#include "modules.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;
+	
+	suspend_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 ? suspend_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 suspend_module_header) +
+	 (int) suspend_header_storage_for_modules() +
+	 (dyn_pageflags_pages_per_bitmap() << PAGE_SHIFT) +
+	 suspend_num_modules *
+	 	(sizeof(struct suspend_module_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 = suspend_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 *rotext_start, *rotext_end;
+static struct page *nosave_start, *nosave_end;
+#ifdef CONFIG_DEBUG_RODATA
+static struct page *rtas_start, *rtas_end;
+static struct page *rodata_start, *rodata_end;
+extern char __start_rodata, __end_rodata;
+#endif
+#ifdef CONFIG_PPC_RTAS
+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);
+
+/* 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, num_free = 0;
+	unsigned long loop;
+	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++) {
+			unsigned long pfn = zone->zone_start_pfn + loop;
+			struct page *page = pfn_to_page(pfn);
+
+			if (
+#if 0
+#ifdef CONFIG_DEBUG_RODATA
+			    (page >= rodata_start && page <= rodata_end) ||
+#endif
+#ifdef CONFIG_DEBUG_ROTEXT
+			    (page >= rotext_start && page <= rotext_end) ||
+#endif
+#ifdef CONFIG_PPC_RTAS
+			    (page >= rtas_start && page <= rtas_end) ||
+#endif
+			    !pfn_valid(pfn) || 
+			    (bad_ppro && page_kills_ppro(pfn)) ||
+			    (checksum_map && PageChecksumIgnore(page)) ||
+			    !page_is_ram(pfn)) {
+#endif
+			    (page >= nosave_start && page <= nosave_end) ||
+			    PageAllocd(page)) {
+				num_nosave++;
+				continue;
+			}
+			if (!PageReserved(page)) {
+				if ((chunk_size=size_of_free_region(page))!=0) {
+					num_free += chunk_size;
+					loop += chunk_size - 1;
+					continue;
+				}
+			} else {
+				if (PageHighMem(page)) {
+					/* HighMem pages may be marked Reserved. We ignore them. */
+					num_nosave++;
+					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;
+}
+
+/* suspend_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 suspend_recalculate_stats(int storage_unavailable) 
+{
+	struct pageset_sizes_result result;
+
+	suspend_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 = suspend_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 = suspend_recalculate_stats(0);
+
+	if (suspend_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 (suspend_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 = suspend_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 = suspend_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 = suspend_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 = suspend_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.
+	 */
+
+	suspend_active_writer->ops.writer.allocate_storage(
+		min(storage_available,
+		    main_storage_needed(0, 1)));
+
+	storage_allocated = suspend_active_writer->ops.writer.storage_allocated();
+
+	if (freeze_processes()) {
+		set_result_state(SUSPEND_FREEZING_FAILED);
+		set_result_state(SUSPEND_ABORTED);
+	}
+
+	suspend_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);
+	suspend_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 + suspend_memory_for_modules());
+}
+
+
+/* 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 -- */
+
+	
+	suspend_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);
+
+		suspend_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)
+			suspend_update_status(orig_memory_still_to_eat - amount_needed(1),
+				orig_memory_still_to_eat,
+				" Image size %d ",
+				MB(storage_needed(1, 0)));
+		else
+			suspend_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);
+		suspend_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);
+		suspend_recalculate_stats(0);
+	}
+
+	/* Blank out image size display */
+	suspend_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 modules tell
+ *   us).
+ * - Make sure that all dirty buffers are written out.
+ */
+
+#define MAX_TRIES 4
+int suspend_prepare_image(void)
+{
+	int result = 1, tries = 0;
+
+	are_frozen = 0;
+
+	header_space_allocated = 0;
+
+	if (attempt_to_freeze())
+		return 1;
+
+	if (!extra_pd1_pages_allowance)
+		get_extra_pd1_allowance();
+
+	storage_available = suspend_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 1;
+	}
+
+	do {
+		suspend_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 successfully prepare 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	2006-02-18 15:24:31.405814520 +0000
@@ -0,0 +1,31 @@
+/*
+ * kernel/power/prepare_image.h
+ */
+
+extern int suspend_prepare_image(void);
+extern struct pageset_sizes_result suspend_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 suspend_expected_compression_ratio(void);
+#else
+static inline int suspend_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	2006-02-18 15:24:31.406814368 +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 __suspend_try_resume(void);
+extern void suspend_main(void);
+
+/* suspend_read_proc
+ *
+ * Generic handling for reading the contents of bits, integers,
+ * unsigned longs and strings.
+ */
+static int suspend_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)
+		suspend_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)
+		suspend_cleanup_usm();
+
+	suspend_finish_anything(0);
+	
+	return len;
+}
+/* suspend_write_proc
+ *
+ * Generic routine for handling writing to files representing
+ * bits, integers and unsigned longs.
+ */
+
+static int suspend_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)
+		suspend_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)
+		suspend_cleanup_usm();
+
+	suspend_finish_anything(proc_data == &proc_params[0]);
+	
+	return result;
+}
+
+/* Non-module 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 suspend_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			= suspend_main,
+	  .needs_storage_manager	= 2,
+	},
+
+	{ .filename			= "do_resume",
+	  .permissions			= PROC_WRITEONLY,
+	  .type				= SUSPEND_PROC_DATA_CUSTOM,
+	  .write_proc			= __suspend_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 = suspend_read_proc;
+		new_entry->write_proc = suspend_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	2006-02-18 15:24:31.407814216 +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	2006-01-03 03:21:10.000000000 +0000
+++ newtree/kernel/power/process.c	2006-02-18 15:24:31.409813912 +0000
@@ -1,134 +1,422 @@
 /*
- * 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 <nigel@suspend2.net>
+ *
+ * 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 <linux/hardirq.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;
+
+	freezer_message("%s (%d) frozen.\n",
+			current->comm, current->pid);
 	save = current->state;
-	pr_debug("%s entered refrigerator\n", current->comm);
-	printk("=");
+	
+	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);
+}
+
+/*
+ * Refrigerator
+ */
+void refrigerator(void)
+{
+	unsigned long flags;
 
+	might_sleep();
+
+	/* Locking to handle race against waking the process in
+	 * freeze threads. */
+	spin_lock_irqsave(&current->sighand->siglock, flags);
 	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();
+
+	recalc_sigpending();
+	spin_unlock_irqrestore(&current->sighand->siglock, flags);
+
+	if (test_freezer_state(FREEZER_ON)) {
+		if (current->mm)
+			__freeze_process(&userspace_thaw, &nr_userspace_frozen);
+		else
+			__freeze_process(&kernelspace_thaw,
+					&nr_kernelspace_frozen);
 	}
-	pr_debug("%s left refrigerator\n", current->comm);
-	current->state = save;
+
+	spin_lock_irqsave(&current->sighand->siglock, flags);
+	recalc_sigpending();
+	current->flags &= ~PF_FROZEN;
+	spin_unlock_irqrestore(&current->sighand->siglock, flags);
+
+	return;
 }
 
-/* 0 = success, else # of processes that we failed to stop */
-int freeze_processes(void)
+void thaw_processes(int do_all_threads)
 {
-	int todo;
-	unsigned long start_time;
+	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;
-	unsigned long flags;
+	int todo_this_type = 0;
 
-	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;
+	read_lock(&tasklist_lock);
+	do_each_thread(g, p) {
+		if (freezeable(p, do_all_threads))
+			todo_this_type++;
+	} while_each_thread(g, p);
+	read_unlock(&tasklist_lock);
 
-			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);
+	return todo_this_type;
+}
 
-	/* 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;
-	}
+/*
+ * 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;
 
-	printk( "|\n" );
-	BUG_ON(in_atomic());
-	return 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;
 }
 
-void thaw_processes(void)
+/*
+ * Tell threads of the type to enter the freezer.
+ */
+static void signal_threads(int do_all_threads)
 {
 	struct task_struct *g, *p;
+	unsigned long flags;
 
-	printk( "Restarting tasks..." );
 	read_lock(&tasklist_lock);
 	do_each_thread(g, p) {
-		if (!freezeable(p))
+		if (!freezeable(p, do_all_threads))
 			continue;
-		if (!thaw_process(p))
-			printk(KERN_INFO " Strange, %s not stopped\n", p->comm );
+
+		freeze(p);
+		spin_lock_irqsave(&p->sighand->siglock, flags);
+		signal_wake_up(p, 0);
+		spin_unlock_irqrestore(&p->sighand->siglock, flags);
 	} 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);
-	schedule();
-	printk( " done\n" );
 }
 
+/*
+ * 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);
+
+	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(freezer_state);
 EXPORT_SYMBOL(refrigerator);
diff -urN oldtree/kernel/power/snapshot.c newtree/kernel/power/snapshot.c
--- oldtree/kernel/power/snapshot.c	2006-02-18 15:18:30.088743064 +0000
+++ newtree/kernel/power/snapshot.c	2006-02-18 15:24:31.410813760 +0000
@@ -172,7 +172,7 @@
 		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/snapshot.c.orig newtree/kernel/power/snapshot.c.orig
--- oldtree/kernel/power/snapshot.c.orig	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/snapshot.c.orig	2006-02-18 15:18:30.000000000 +0000
@@ -0,0 +1,510 @@
+/*
+ * linux/kernel/power/snapshot.c
+ *
+ * This file provide system snapshot/restore functionality.
+ *
+ * Copyright (C) 1998-2005 Pavel Machek <pavel@suse.cz>
+ *
+ * This file is released under the GPLv2, and is based on swsusp.c.
+ *
+ */
+
+
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/suspend.h>
+#include <linux/smp_lock.h>
+#include <linux/delay.h>
+#include <linux/bitops.h>
+#include <linux/spinlock.h>
+#include <linux/kernel.h>
+#include <linux/pm.h>
+#include <linux/device.h>
+#include <linux/bootmem.h>
+#include <linux/syscalls.h>
+#include <linux/console.h>
+#include <linux/highmem.h>
+
+#include <asm/uaccess.h>
+#include <asm/mmu_context.h>
+#include <asm/pgtable.h>
+#include <asm/tlbflush.h>
+#include <asm/io.h>
+
+#include "power.h"
+
+struct pbe *pagedir_nosave;
+unsigned int nr_copy_pages;
+
+#ifdef CONFIG_HIGHMEM
+unsigned int count_highmem_pages(void)
+{
+	struct zone *zone;
+	unsigned long zone_pfn;
+	unsigned int n = 0;
+
+	for_each_zone (zone)
+		if (is_highmem(zone)) {
+			mark_free_pages(zone);
+			for (zone_pfn = 0; zone_pfn < zone->spanned_pages; zone_pfn++) {
+				struct page *page;
+				unsigned long pfn = zone_pfn + zone->zone_start_pfn;
+				if (!pfn_valid(pfn))
+					continue;
+				page = pfn_to_page(pfn);
+				if (PageReserved(page))
+					continue;
+				if (PageNosaveFree(page))
+					continue;
+				n++;
+			}
+		}
+	return n;
+}
+
+struct highmem_page {
+	char *data;
+	struct page *page;
+	struct highmem_page *next;
+};
+
+static struct highmem_page *highmem_copy;
+
+static int save_highmem_zone(struct zone *zone)
+{
+	unsigned long zone_pfn;
+	mark_free_pages(zone);
+	for (zone_pfn = 0; zone_pfn < zone->spanned_pages; ++zone_pfn) {
+		struct page *page;
+		struct highmem_page *save;
+		void *kaddr;
+		unsigned long pfn = zone_pfn + zone->zone_start_pfn;
+
+		if (!(pfn%1000))
+			printk(".");
+		if (!pfn_valid(pfn))
+			continue;
+		page = pfn_to_page(pfn);
+		/*
+		 * This condition results from rvmalloc() sans vmalloc_32()
+		 * and architectural memory reservations. This should be
+		 * corrected eventually when the cases giving rise to this
+		 * are better understood.
+		 */
+		if (PageReserved(page))
+			continue;
+		BUG_ON(PageNosave(page));
+		if (PageNosaveFree(page))
+			continue;
+		save = kmalloc(sizeof(struct highmem_page), GFP_ATOMIC);
+		if (!save)
+			return -ENOMEM;
+		save->next = highmem_copy;
+		save->page = page;
+		save->data = (void *) get_zeroed_page(GFP_ATOMIC);
+		if (!save->data) {
+			kfree(save);
+			return -ENOMEM;
+		}
+		kaddr = kmap_atomic(page, KM_USER0);
+		memcpy(save->data, kaddr, PAGE_SIZE);
+		kunmap_atomic(kaddr, KM_USER0);
+		highmem_copy = save;
+	}
+	return 0;
+}
+
+int save_highmem(void)
+{
+	struct zone *zone;
+	int res = 0;
+
+	pr_debug("swsusp: Saving Highmem\n");
+	for_each_zone (zone) {
+		if (is_highmem(zone))
+			res = save_highmem_zone(zone);
+		if (res)
+			return res;
+	}
+	return 0;
+}
+
+int restore_highmem(void)
+{
+	printk("swsusp: Restoring Highmem\n");
+	while (highmem_copy) {
+		struct highmem_page *save = highmem_copy;
+		void *kaddr;
+		highmem_copy = save->next;
+
+		kaddr = kmap_atomic(save->page, KM_USER0);
+		memcpy(kaddr, save->data, PAGE_SIZE);
+		kunmap_atomic(kaddr, KM_USER0);
+		free_page((long) save->data);
+		kfree(save);
+	}
+	return 0;
+}
+#endif
+
+static int pfn_is_nosave(unsigned long pfn)
+{
+	unsigned long nosave_begin_pfn = __pa(&__nosave_begin) >> PAGE_SHIFT;
+	unsigned long nosave_end_pfn = PAGE_ALIGN(__pa(&__nosave_end)) >> PAGE_SHIFT;
+	return (pfn >= nosave_begin_pfn) && (pfn < nosave_end_pfn);
+}
+
+/**
+ *	saveable - Determine whether a page should be cloned or not.
+ *	@pfn:	The page
+ *
+ *	We save a page if it's Reserved, and not in the range of pages
+ *	statically defined as 'unsaveable', or if it isn't reserved, and
+ *	isn't part of a free chunk of pages.
+ */
+
+static int saveable(struct zone *zone, unsigned long *zone_pfn)
+{
+	unsigned long pfn = *zone_pfn + zone->zone_start_pfn;
+	struct page *page;
+
+	if (!pfn_valid(pfn))
+		return 0;
+
+	page = pfn_to_page(pfn);
+	BUG_ON(PageReserved(page) && PageNosave(page));
+	if (PageNosave(page))
+		return 0;
+	if (PageReserved(page) && pfn_is_nosave(pfn))
+		return 0;
+	if (PageNosaveFree(page))
+		return 0;
+
+	return 1;
+}
+
+unsigned int count_data_pages(void)
+{
+	struct zone *zone;
+	unsigned long zone_pfn;
+	unsigned int n = 0;
+
+	for_each_zone (zone) {
+		if (is_highmem(zone))
+			continue;
+		mark_free_pages(zone);
+		for (zone_pfn = 0; zone_pfn < zone->spanned_pages; ++zone_pfn)
+			n += saveable(zone, &zone_pfn);
+	}
+	return n;
+}
+
+static void copy_data_pages(struct pbe *pblist)
+{
+	struct zone *zone;
+	unsigned long zone_pfn;
+	struct pbe *pbe, *p;
+
+	pbe = pblist;
+	for_each_zone (zone) {
+		if (is_highmem(zone))
+			continue;
+		mark_free_pages(zone);
+		/* This is necessary for swsusp_free() */
+		for_each_pb_page (p, pblist)
+			SetPageNosaveFree(virt_to_page(p));
+		for_each_pbe (p, pblist)
+			SetPageNosaveFree(virt_to_page(p->address));
+		for (zone_pfn = 0; zone_pfn < zone->spanned_pages; ++zone_pfn) {
+			if (saveable(zone, &zone_pfn)) {
+				struct page *page;
+				page = pfn_to_page(zone_pfn + zone->zone_start_pfn);
+				BUG_ON(!pbe);
+				pbe->orig_address = (unsigned long)page_address(page);
+				/* copy_page is not usable for copying task structs. */
+				memcpy((void *)pbe->address, (void *)pbe->orig_address, PAGE_SIZE);
+				pbe = pbe->next;
+			}
+		}
+	}
+	BUG_ON(pbe);
+}
+
+
+/**
+ *	free_pagedir - free pages allocated with alloc_pagedir()
+ */
+
+void free_pagedir(struct pbe *pblist)
+{
+	struct pbe *pbe;
+
+	while (pblist) {
+		pbe = (pblist + PB_PAGE_SKIP)->next;
+		ClearPageNosave(virt_to_page(pblist));
+		ClearPageNosaveFree(virt_to_page(pblist));
+		free_page((unsigned long)pblist);
+		pblist = pbe;
+	}
+}
+
+/**
+ *	fill_pb_page - Create a list of PBEs on a given memory page
+ */
+
+static inline void fill_pb_page(struct pbe *pbpage)
+{
+	struct pbe *p;
+
+	p = pbpage;
+	pbpage += PB_PAGE_SKIP;
+	do
+		p->next = p + 1;
+	while (++p < pbpage);
+}
+
+/**
+ *	create_pbe_list - Create a list of PBEs on top of a given chain
+ *	of memory pages allocated with alloc_pagedir()
+ */
+
+static inline void create_pbe_list(struct pbe *pblist, unsigned int nr_pages)
+{
+	struct pbe *pbpage, *p;
+	unsigned int num = PBES_PER_PAGE;
+
+	for_each_pb_page (pbpage, pblist) {
+		if (num >= nr_pages)
+			break;
+
+		fill_pb_page(pbpage);
+		num += PBES_PER_PAGE;
+	}
+	if (pbpage) {
+		for (num -= PBES_PER_PAGE - 1, p = pbpage; num < nr_pages; p++, num++)
+			p->next = p + 1;
+		p->next = NULL;
+	}
+}
+
+/**
+ *	On resume it is necessary to trace and eventually free the unsafe
+ *	pages that have been allocated, because they are needed for I/O
+ *	(on x86-64 we likely will "eat" these pages once again while
+ *	creating the temporary page translation tables)
+ */
+
+struct eaten_page {
+	struct eaten_page *next;
+	char padding[PAGE_SIZE - sizeof(void *)];
+};
+
+static struct eaten_page *eaten_pages = NULL;
+
+void release_eaten_pages(void)
+{
+	struct eaten_page *p, *q;
+
+	p = eaten_pages;
+	while (p) {
+		q = p->next;
+		/* We don't want swsusp_free() to free this page again */
+		ClearPageNosave(virt_to_page(p));
+		free_page((unsigned long)p);
+		p = q;
+	}
+	eaten_pages = NULL;
+}
+
+/**
+ *	@safe_needed - on resume, for storing the PBE list and the image,
+ *	we can only use memory pages that do not conflict with the pages
+ *	which had been used before suspend.
+ *
+ *	The unsafe pages are marked with the PG_nosave_free flag
+ *
+ *	Allocated but unusable (ie eaten) memory pages should be marked
+ *	so that swsusp_free() can release them
+ */
+
+static inline void *alloc_image_page(gfp_t gfp_mask, int safe_needed)
+{
+	void *res;
+
+	if (safe_needed)
+		do {
+			res = (void *)get_zeroed_page(gfp_mask);
+			if (res && PageNosaveFree(virt_to_page(res))) {
+				/* This is for swsusp_free() */
+				SetPageNosave(virt_to_page(res));
+				((struct eaten_page *)res)->next = eaten_pages;
+				eaten_pages = res;
+			}
+		} while (res && PageNosaveFree(virt_to_page(res)));
+	else
+		res = (void *)get_zeroed_page(gfp_mask);
+	if (res) {
+		SetPageNosave(virt_to_page(res));
+		SetPageNosaveFree(virt_to_page(res));
+	}
+	return res;
+}
+
+unsigned long get_safe_page(gfp_t gfp_mask)
+{
+	return (unsigned long)alloc_image_page(gfp_mask, 1);
+}
+
+/**
+ *	alloc_pagedir - Allocate the page directory.
+ *
+ *	First, determine exactly how many pages we need and
+ *	allocate them.
+ *
+ *	We arrange the pages in a chain: each page is an array of PBES_PER_PAGE
+ *	struct pbe elements (pbes) and the last element in the page points
+ *	to the next page.
+ *
+ *	On each page we set up a list of struct_pbe elements.
+ */
+
+struct pbe *alloc_pagedir(unsigned int nr_pages, gfp_t gfp_mask, int safe_needed)
+{
+	unsigned int num;
+	struct pbe *pblist, *pbe;
+
+	if (!nr_pages)
+		return NULL;
+
+	pr_debug("alloc_pagedir(): nr_pages = %d\n", nr_pages);
+	pblist = alloc_image_page(gfp_mask, safe_needed);
+	/* FIXME: rewrite this ugly loop */
+	for (pbe = pblist, num = PBES_PER_PAGE; pbe && num < nr_pages;
+        		pbe = pbe->next, num += PBES_PER_PAGE) {
+		pbe += PB_PAGE_SKIP;
+		pbe->next = alloc_image_page(gfp_mask, safe_needed);
+	}
+	if (!pbe) { /* get_zeroed_page() failed */
+		free_pagedir(pblist);
+		pblist = NULL;
+        } else
+        	create_pbe_list(pblist, nr_pages);
+	return pblist;
+}
+
+/**
+ * Free pages we allocated for suspend. Suspend pages are alocated
+ * before atomic copy, so we need to free them after resume.
+ */
+
+void swsusp_free(void)
+{
+	struct zone *zone;
+	unsigned long zone_pfn;
+
+	for_each_zone(zone) {
+		for (zone_pfn = 0; zone_pfn < zone->spanned_pages; ++zone_pfn)
+			if (pfn_valid(zone_pfn + zone->zone_start_pfn)) {
+				struct page *page;
+				page = pfn_to_page(zone_pfn + zone->zone_start_pfn);
+				if (PageNosave(page) && PageNosaveFree(page)) {
+					ClearPageNosave(page);
+					ClearPageNosaveFree(page);
+					free_page((long) page_address(page));
+				}
+			}
+	}
+}
+
+
+/**
+ *	enough_free_mem - Make sure we enough free memory to snapshot.
+ *
+ *	Returns TRUE or FALSE after checking the number of available
+ *	free pages.
+ */
+
+static int enough_free_mem(unsigned int nr_pages)
+{
+	struct zone *zone;
+	unsigned int n = 0;
+
+	for_each_zone (zone)
+		if (!is_highmem(zone))
+			n += zone->free_pages;
+	pr_debug("swsusp: available memory: %u pages\n", n);
+	return n > (nr_pages + PAGES_FOR_IO +
+		(nr_pages + PBES_PER_PAGE - 1) / PBES_PER_PAGE);
+}
+
+int alloc_data_pages(struct pbe *pblist, gfp_t gfp_mask, int safe_needed)
+{
+	struct pbe *p;
+
+	for_each_pbe (p, pblist) {
+		p->address = (unsigned long)alloc_image_page(gfp_mask, safe_needed);
+		if (!p->address)
+			return -ENOMEM;
+	}
+	return 0;
+}
+
+static struct pbe *swsusp_alloc(unsigned int nr_pages)
+{
+	struct pbe *pblist;
+
+	if (!(pblist = alloc_pagedir(nr_pages, GFP_ATOMIC | __GFP_COLD, 0))) {
+		printk(KERN_ERR "suspend: Allocating pagedir failed.\n");
+		return NULL;
+	}
+
+	if (alloc_data_pages(pblist, GFP_ATOMIC | __GFP_COLD, 0)) {
+		printk(KERN_ERR "suspend: Allocating image pages failed.\n");
+		swsusp_free();
+		return NULL;
+	}
+
+	return pblist;
+}
+
+asmlinkage int swsusp_save(void)
+{
+	unsigned int nr_pages;
+
+	pr_debug("swsusp: critical section: \n");
+
+	drain_local_pages();
+	nr_pages = count_data_pages();
+	printk("swsusp: Need to copy %u pages\n", nr_pages);
+
+	pr_debug("swsusp: pages needed: %u + %lu + %u, free: %u\n",
+		 nr_pages,
+		 (nr_pages + PBES_PER_PAGE - 1) / PBES_PER_PAGE,
+		 PAGES_FOR_IO, nr_free_pages());
+
+	if (!enough_free_mem(nr_pages)) {
+		printk(KERN_ERR "swsusp: Not enough free memory\n");
+		return -ENOMEM;
+	}
+
+	pagedir_nosave = swsusp_alloc(nr_pages);
+	if (!pagedir_nosave)
+		return -ENOMEM;
+
+	/* During allocating of suspend pagedir, new cold pages may appear.
+	 * Kill them.
+	 */
+	drain_local_pages();
+	copy_data_pages(pagedir_nosave);
+
+	/*
+	 * End of critical section. From now on, we can write to memory,
+	 * but we should not touch disk. This specially means we must _not_
+	 * touch swap space! Except we must write out our image of course.
+	 */
+
+	nr_copy_pages = nr_pages;
+
+	printk("swsusp: critical section/: done (%d pages copied)\n", nr_pages);
+	return 0;
+}
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	2006-02-18 15:24:31.412813456 +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 "modules.h"
+#include "netlink.h"
+#include "storage.h"
+#include "ui.h"
+
+static struct user_helper_data usm_helper_data;
+static struct suspend_module_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 suspend_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) {
+		suspend_prepare_status(DONT_CLEAR_BAR, "Activate storage attempt %d.\n", tries);
+
+		init_completion(&usm_helper_data.wait_for_process);
+
+		suspend_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 suspend_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);
+
+	suspend_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");
+	suspend_prepare_usm();
+	schedule();
+	printk("--- Deactivate storage 1 ---\n");
+	suspend_deactivate_storage(1);
+	schedule();
+	printk("--- Activate storage 1 ---\n");
+	suspend_activate_storage(1);
+	schedule();
+	printk("--- Cleanup usm ---\n");
+	suspend_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);
+}
+
+/* suspend_prepare_usm
+ */
+int suspend_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;
+
+	suspend_netlink_setup(&usm_helper_data);
+
+	if (usm_helper_data.pid == -1)
+		printk("Suspend2 Storage Manager wanted, but couldn't start it.\n");
+
+	suspend_activate_storage(0);
+
+	return (usm_helper_data.pid != -1);
+}
+
+void suspend_cleanup_usm(void)
+{
+	usm_prepare_count--;
+
+	if (usm_helper_data.pid > -1 && !usm_prepare_count) {
+		struct task_struct *t;
+
+		suspend_deactivate_storage(0);
+
+		suspend_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);
+
+		suspend_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)
+		suspend_prepare_usm();
+	else
+		suspend_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_module_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_module(&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	2006-02-18 15:24:31.413813304 +0000
@@ -0,0 +1,21 @@
+/*
+ *
+ */
+
+int suspend_prepare_usm(void);
+void suspend_cleanup_usm(void);
+
+int suspend_activate_storage(int force);
+int suspend_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	2006-02-18 15:24:31.415813000 +0000
@@ -0,0 +1,1132 @@
+/*
+ * 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 'modules' 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 "modules.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 suspend_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;
+
+extern int block_dump;
+
+int block_dump_save;
+
+/*
+ * Basic clean-up routine.
+ */
+void suspend_finish_anything(int finishing_cycle)
+{
+	if (atomic_dec_and_test(&actions_running)) {
+		suspend_cleanup_modules(finishing_cycle);
+		suspend_put_modules();
+		clear_suspend_state(SUSPEND_RUNNING);
+	}
+
+	set_fs(oldfs);
+
+	if (finishing_cycle)
+		block_dump = block_dump_save;
+}
+
+/*
+ * 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 (suspend_get_modules()) {
+			printk("Get modules failed!\n");
+			clear_suspend_state(SUSPEND_RUNNING);
+			set_fs(oldfs);
+			return -EBUSY;
+		}
+
+		if (suspend_initialise_modules(starting_cycle)) {
+			printk("Initialise modules failed!\n");
+			suspend_finish_anything(starting_cycle);
+			return -EBUSY;
+		}
+
+		if (starting_cycle) {
+			block_dump_save = block_dump;
+			block_dump = 0;
+		}
+	}
+
+	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      : suspend_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.");
+
+	suspend_deactivate_storage(1);
+
+	suspend_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());
+
+	suspend_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;
+	}
+
+	suspend_map_atomic_copy_pages();
+
+	BUG_ON(!irqs_disabled());
+
+	if (!test_action_state(SUSPEND_TEST_FILTER_SPEED) &&
+	    !test_action_state(SUSPEND_TEST_BIO))
+		suspend_copy_pageset1();
+
+	/*
+	 *  ----   FROM HERE ON, NEED TO REREAD PAGESET2 IF ABORTING!!! -----
+	 *  
+	 */
+	
+	suspend_unmap_atomic_copy_pages();
+
+#ifdef CONFIG_X86
+	kernel_fpu_end();
+#endif
+
+	device_power_up();
+	
+	local_irq_enable();
+
+	device_resume();
+
+	if (suspend_activate_storage(1))
+		panic("Failed to reactivate our storage.");
+	
+	suspend_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:		suspend2_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,
+			suspend_powerdown_method);
+	SNPRINTF("- Overall expected compression percentage: %d.\n",
+			100 - suspend_expected_compression_ratio());
+	len+= suspend_print_module_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");
+	suspend_active_writer->ops.writer.invalidate_image();
+
+	return 0;
+}
+
+static int suspend_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;
+
+	suspend_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 suspend_cleanup(void)
+{
+	int i;
+
+	i = get_suspend_debug_info();
+
+	suspend_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 (suspend_active_writer)
+			suspend_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);
+
+	suspend_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;
+}
+
+/*
+ * suspend_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 suspend_main(void)
+{
+	if (suspend_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 (suspend_init() && !suspend_prepare_image() && !test_result_state(SUSPEND_ABORTED) &&
+		!test_action_state(SUSPEND_FREEZER_TEST)) {
+		suspend_prepare_status(DONT_CLEAR_BAR, "Starting to save the image..");
+		save_image();
+	}
+	
+	suspend_cleanup();
+cleanup:
+	suspend_deactivate_storage(0);
+}
+
+/* image_exists_read
+ * 
+ * Return 0 or 1, depending on whether an image is found.
+ */
+
+char *get_have_image_data(void);
+
+static int image_exists_read(char *page, char **start, off_t off, int count,
+		int *eof, void *data)
+{
+	int len = 0;
+	char *result;
+	
+	if (suspend_activate_storage(0))
+		return count;
+
+	if (!test_suspend_state(SUSPEND_RESUME_DEVICE_OK))
+		attempt_to_parse_resume_device();
+
+	if (!suspend_active_writer) {
+		len = sprintf(page, "-1\n");
+	} else {
+		result = get_have_image_data();
+		printk("get_have_image_data returned %p.\n", result);
+		if (result) {
+			len = sprintf(page, "%s",  result);
+			free_page((unsigned long) result);
+		}
+	}
+
+	*eof = 1;
+
+	suspend_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 (suspend_activate_storage(0))
+		return count;
+
+	if (suspend_active_writer && suspend_active_writer->ops.writer.image_exists())
+		suspend_active_writer->ops.writer.invalidate_image();
+
+	suspend_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	= &suspend_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 suspend_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");
+
+	suspend_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 (!suspend_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");
+		suspend_deactivate_storage(0);
+		return 1;
+	}
+
+	suspend_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");
+
+	suspend_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_module_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 __suspend_try_resume(void)
+{
+	set_suspend_state(SUSPEND_TRYING_TO_RESUME);
+	
+	clear_suspend_state(SUSPEND_RESUME_NOT_DONE);
+
+	suspend_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;
+
+	__suspend_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 suspend_main.
+ * Called From     : drivers/acpi/sleep/main.c
+ *                   kernel/reboot.c
+ */
+
+void suspend2_try_suspend(void)
+{
+	if (suspend_start_anything(0))
+		return;
+
+	suspend_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 suspend_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", suspend_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	2006-02-18 15:24:31.416812848 +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	2006-02-18 15:24:31.417812696 +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 suspend_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	2006-02-18 15:24:31.417812696 +0000
@@ -0,0 +1,25 @@
+#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_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	2006-02-18 15:24:31.419812392 +0000
@@ -0,0 +1,1086 @@
+/*
+ * 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 "modules.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 suspend_bdev_info *suspend_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
+ * 		modules 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)
+		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)
+		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 suspend_bdev_info *info)
+{
+	suspend_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 < suspend_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 debug)
+{
+	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 = suspend_devinfo[current_chain].bdev;
+	submit_params.block[0] = (suspend_writer_posn.current_offset -
+		       suspend_devinfo[current_chain].blocks_per_page + 1) <<
+		suspend_devinfo[current_chain].bmap_shift;
+
+	if (debug)
+		printk("%s: %lx:%lx.\n", rw ? "Write" : "Read",
+				(long) submit_params.dev->bd_dev,
+				(long) submit_params.block[0]);
+
+	i = suspend_do_io(rw, &submit_params, sync);
+
+	if (i)
+		return -EIO;
+
+	return 0;
+}
+
+static int suspend_rw_page(int rw, struct page *page,
+		int readahead_index, int sync)
+{
+	return __suspend_rw_page(rw, page, readahead_index, sync, 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) {
+			if (test_debug_state(SUSPEND_HEADER))
+				printk("Copy %d bytes from %p to %p.\n",
+						bytes_left, to, from);
+			memcpy(to, from, bytes_left);
+			suspend_writer_buffer_posn += bytes_left;
+			return rw ? 0 : buffer_size;
+		}
+
+		/* Next to read the next page */
+		if (test_debug_state(SUSPEND_HEADER))
+			printk("Copy %d bytes from %p to %p.\n",
+					capacity, to, from);
+		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,
+					test_debug_state(SUSPEND_HEADER)))
+				return -EIO;
+		}
+
+		suspend_writer_buffer_posn = 0;
+		check_shift_keys(0, NULL);
+	}
+
+	return rw ? 0 : buffer_size;
+}
+
+static int write_header_chunk_finish(void)
+{
+	return __suspend_rw_page(WRITE,
+		virt_to_page(suspend_writer_buffer),
+		-1, 0, test_debug_state(SUSPEND_HEADER)) ? -EIO : 0;
+}
+
+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,
+	.write_header_chunk_finish = write_header_chunk_finish,
+};
+
+static struct suspend_module_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_module(&suspend_blockwriter_ops);
+}
+
+#ifdef MODULE
+static __exit void suspend_block_io_unload(void)
+{
+	suspend_unregister_module(&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	2006-02-18 15:24:31.421812088 +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 "modules.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) {
+		suspend_prepare_status(1, 0, "Unable to checksum at this point.");
+		return;
+	}
+
+	suspend_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);
+
+	suspend_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) {
+		suspend_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_module_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_modules, module_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	2006-02-18 15:24:31.422811936 +0000
@@ -0,0 +1,1077 @@
+/*
+ * 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 "modules.h"
+#include "ui.h"
+#include "extent.h"
+#include "io.h"
+#include "storage.h"
+#include "block_io.h"
+
+static struct suspend_module_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 suspend_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];
+	
+	extent_state_goto_start(&suspend_writer_posn);
+
+	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);
+
+	/* 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));
+
+	suspend_bio_ops.write_header_chunk((char *) &devinfo,
+			sizeof(devinfo));
+
+	serialise_extent_chain(&block_chain);
+	
+	return 0;
+}
+
+static int filewriter_write_header_cleanup(void)
+{
+	/* Write any unsaved data */
+	if (suspend_writer_buffer_posn)
+		suspend_bio_ops.write_header_chunk_finish();
+
+	suspend_bio_ops.finish_all_io();
+
+	extent_state_goto_start(&suspend_writer_posn);
+	suspend_bio_ops.forward_one_page();
+
+	/* 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;
+	struct block_device *tmp;
+
+	*(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);
+
+	tmp = devinfo.bdev;
+
+	memcpy(&devinfo,
+			suspend_writer_buffer + suspend_writer_buffer_posn,
+			sizeof(struct suspend_bdev_info));
+	devinfo.bdev = tmp;
+	suspend_writer_buffer_posn += sizeof(struct suspend_bdev_info);
+
+	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 (suspend_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 (suspend_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_module_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_module(&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_module(&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	2006-02-18 15:24:31.424811632 +0000
@@ -0,0 +1,1213 @@
+/*
+ * 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 "modules.h"
+#include "io.h"
+#include "ui.h"
+#include "extent.h"
+#include "block_io.h"
+
+static struct suspend_module_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 suspend_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) {
+		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.");
+		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) {
+		suspend_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)
+{
+	si_swapinfo(&swapinfo);
+	return swapinfo.freeswap + swapwriter_storage_allocated();
+}
+
+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;
+		swp_entry_t entry;
+		extent_for_each(&swapextents, extentpointer, 
+				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;
+			}
+		}
+	}
+
+	if (!first)
+		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)
+		suspend_bio_ops.write_header_chunk_finish();
+
+	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 (suspend_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(resume_block_device = 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_module_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_module(&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_module(&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	2006-02-18 15:18:30.089742912 +0000
+++ newtree/kernel/power/swsusp.c	2006-02-18 15:24:31.427811176 +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>
@@ -60,6 +58,7 @@
 #include <linux/syscalls.h>
 #include <linux/highmem.h>
 #include <linux/bio.h>
+#include <linux/freezer.h>
 
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
@@ -68,6 +67,8 @@
 #include <asm/io.h>
 
 #include "power.h"
+#include "swsusp.h"
+#include "suspend.h"
 
 /*
  * Preferred image size in bytes (tunable via /sys/power/image_size).
@@ -573,6 +574,8 @@
 	unsigned int i = 0;
 	char *p = "-\\|/";
 
+	thaw_processes(FREEZER_KERNEL_THREADS);
+
 	printk("Shrinking memory...  ");
 	do {
 		size = 2 * count_highmem_pages();
@@ -596,6 +599,8 @@
 	} while (tmp > 0);
 	printk("\bdone (%lu pages freed)\n", pages);
 
+	freeze_processes();
+
 	return 0;
 }
 
diff -urN oldtree/kernel/power/swsusp.c.orig newtree/kernel/power/swsusp.c.orig
--- oldtree/kernel/power/swsusp.c.orig	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/power/swsusp.c.orig	2006-02-18 15:18:30.000000000 +0000
@@ -0,0 +1,1038 @@
+/*
+ * linux/kernel/power/swsusp.c
+ *
+ * This file provides code to write suspend image to swap and read it back.
+ *
+ * Copyright (C) 1998-2001 Gabor Kuti <seasons@fornax.hu>
+ * Copyright (C) 1998,2001-2005 Pavel Machek <pavel@suse.cz>
+ *
+ * This file is released under the GPLv2.
+ *
+ * I'd like to thank the following people for their work:
+ *
+ * Pavel Machek <pavel@ucw.cz>:
+ * Modifications, defectiveness pointing, being with me 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>:
+ * Support the possibility of hardware state restoring.
+ *
+ * Raph <grey.havens@earthling.net>:
+ * Support for preserving states of network devices and virtual console
+ * (including X and svgatextmode)
+ *
+ * Kurt Garloff <garloff@suse.de>:
+ * 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>:
+ * Fixed runaway init
+ *
+ * Rafael J. Wysocki <rjw@sisk.pl>
+ * Added the swap map data structure and reworked the handling of swap
+ *
+ * More state savers are welcome. Especially for the scsi layer...
+ *
+ * For TODOs,FIXMEs also look in Documentation/power/swsusp.txt
+ */
+
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/suspend.h>
+#include <linux/smp_lock.h>
+#include <linux/file.h>
+#include <linux/utsname.h>
+#include <linux/version.h>
+#include <linux/delay.h>
+#include <linux/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>
+#include <linux/swapops.h>
+#include <linux/bootmem.h>
+#include <linux/syscalls.h>
+#include <linux/highmem.h>
+#include <linux/bio.h>
+
+#include <asm/uaccess.h>
+#include <asm/mmu_context.h>
+#include <asm/pgtable.h>
+#include <asm/tlbflush.h>
+#include <asm/io.h>
+
+#include "power.h"
+
+/*
+ * Preferred image size in bytes (tunable via /sys/power/image_size).
+ * When it is set to N, swsusp will do its best to ensure the image
+ * size will not exceed N bytes, but if that is impossible, it will
+ * try to create the smallest image possible.
+ */
+unsigned long image_size = 500 * 1024 * 1024;
+
+#ifdef CONFIG_HIGHMEM
+unsigned int count_highmem_pages(void);
+int save_highmem(void);
+int restore_highmem(void);
+#else
+static int save_highmem(void) { return 0; }
+static int restore_highmem(void) { return 0; }
+static unsigned int count_highmem_pages(void) { return 0; }
+#endif
+
+extern char resume_file[];
+
+#define SWSUSP_SIG	"S1SUSPEND"
+
+static struct swsusp_header {
+	char reserved[PAGE_SIZE - 20 - sizeof(swp_entry_t)];
+	swp_entry_t image;
+	char	orig_sig[10];
+	char	sig[10];
+} __attribute__((packed, aligned(PAGE_SIZE))) swsusp_header;
+
+static struct swsusp_info swsusp_info;
+
+/*
+ * Saving part...
+ */
+
+static unsigned short root_swap = 0xffff;
+
+static int mark_swapfiles(swp_entry_t start)
+{
+	int error;
+
+	rw_swap_page_sync(READ,
+			  swp_entry(root_swap, 0),
+			  virt_to_page((unsigned long)&swsusp_header));
+	if (!memcmp("SWAP-SPACE",swsusp_header.sig, 10) ||
+	    !memcmp("SWAPSPACE2",swsusp_header.sig, 10)) {
+		memcpy(swsusp_header.orig_sig,swsusp_header.sig, 10);
+		memcpy(swsusp_header.sig,SWSUSP_SIG, 10);
+		swsusp_header.image = start;
+		error = rw_swap_page_sync(WRITE,
+					  swp_entry(root_swap, 0),
+					  virt_to_page((unsigned long)
+						       &swsusp_header));
+	} else {
+		pr_debug("swsusp: Partition is not swap space.\n");
+		error = -ENODEV;
+	}
+	return error;
+}
+
+/*
+ * Check whether the swap device is the specified resume
+ * device, irrespective of whether they are specified by
+ * identical names.
+ *
+ * (Thus, device inode aliasing is allowed.  You can say /dev/hda4
+ * instead of /dev/ide/host0/bus0/target0/lun0/part4 [if using devfs]
+ * and they'll be considered the same device.  This is *necessary* for
+ * devfs, since the resume code can only recognize the form /dev/hda4,
+ * but the suspend code would see the long name.)
+ */
+static inline int is_resume_device(const struct swap_info_struct *swap_info)
+{
+	struct file *file = swap_info->swap_file;
+	struct inode *inode = file->f_dentry->d_inode;
+
+	return S_ISBLK(inode->i_mode) &&
+		swsusp_resume_device == MKDEV(imajor(inode), iminor(inode));
+}
+
+static int swsusp_swap_check(void) /* This is called before saving image */
+{
+	int i;
+
+	spin_lock(&swap_lock);
+	for (i = 0; i < MAX_SWAPFILES; i++) {
+		if (!(swap_info[i].flags & SWP_WRITEOK))
+			continue;
+		if (!swsusp_resume_device || is_resume_device(swap_info + i)) {
+			spin_unlock(&swap_lock);
+			root_swap = i;
+			return 0;
+		}
+	}
+	spin_unlock(&swap_lock);
+	return -ENODEV;
+}
+
+/**
+ *	write_page - Write one page to a fresh swap location.
+ *	@addr:	Address we're writing.
+ *	@loc:	Place to store the entry we used.
+ *
+ *	Allocate a new swap entry and 'sync' it. Note we discard -EIO
+ *	errors. That is an artifact left over from swsusp. It did not
+ *	check the return of rw_swap_page_sync() at all, since most pages
+ *	written back to swap would return -EIO.
+ *	This is a partial improvement, since we will at least return other
+ *	errors, though we need to eventually fix the damn code.
+ */
+static int write_page(unsigned long addr, swp_entry_t *loc)
+{
+	swp_entry_t entry;
+	int error = -ENOSPC;
+
+	entry = get_swap_page_of_type(root_swap);
+	if (swp_offset(entry)) {
+		error = rw_swap_page_sync(WRITE, entry, virt_to_page(addr));
+		if (!error || error == -EIO)
+			*loc = entry;
+	}
+	return error;
+}
+
+/**
+ *	Swap map-handling functions
+ *
+ *	The swap map is a data structure used for keeping track of each page
+ *	written to the swap.  It consists of many swap_map_page structures
+ *	that contain each an array of MAP_PAGE_SIZE swap entries.
+ *	These structures are linked together with the help of either the
+ *	.next (in memory) or the .next_swap (in swap) member.
+ *
+ *	The swap map is created during suspend.  At that time we need to keep
+ *	it in memory, because we have to free all of the allocated swap
+ *	entries if an error occurs.  The memory needed is preallocated
+ *	so that we know in advance if there's enough of it.
+ *
+ *	The first swap_map_page structure is filled with the swap entries that
+ *	correspond to the first MAP_PAGE_SIZE data pages written to swap and
+ *	so on.  After the all of the data pages have been written, the order
+ *	of the swap_map_page structures in the map is reversed so that they
+ *	can be read from swap in the original order.  This causes the data
+ *	pages to be loaded in exactly the same order in which they have been
+ *	saved.
+ *
+ *	During resume we only need to use one swap_map_page structure
+ *	at a time, which means that we only need to use two memory pages for
+ *	reading the image - one for reading the swap_map_page structures
+ *	and the second for reading the data pages from swap.
+ */
+
+#define MAP_PAGE_SIZE	((PAGE_SIZE - sizeof(swp_entry_t) - sizeof(void *)) \
+			/ sizeof(swp_entry_t))
+
+struct swap_map_page {
+	swp_entry_t		entries[MAP_PAGE_SIZE];
+	swp_entry_t		next_swap;
+	struct swap_map_page	*next;
+};
+
+static inline void free_swap_map(struct swap_map_page *swap_map)
+{
+	struct swap_map_page *swp;
+
+	while (swap_map) {
+		swp = swap_map->next;
+		free_page((unsigned long)swap_map);
+		swap_map = swp;
+	}
+}
+
+static struct swap_map_page *alloc_swap_map(unsigned int nr_pages)
+{
+	struct swap_map_page *swap_map, *swp;
+	unsigned n = 0;
+
+	if (!nr_pages)
+		return NULL;
+
+	pr_debug("alloc_swap_map(): nr_pages = %d\n", nr_pages);
+	swap_map = (struct swap_map_page *)get_zeroed_page(GFP_ATOMIC);
+	swp = swap_map;
+	for (n = MAP_PAGE_SIZE; n < nr_pages; n += MAP_PAGE_SIZE) {
+		swp->next = (struct swap_map_page *)get_zeroed_page(GFP_ATOMIC);
+		swp = swp->next;
+		if (!swp) {
+			free_swap_map(swap_map);
+			return NULL;
+		}
+	}
+	return swap_map;
+}
+
+/**
+ *	reverse_swap_map - reverse the order of pages in the swap map
+ *	@swap_map
+ */
+
+static inline struct swap_map_page *reverse_swap_map(struct swap_map_page *swap_map)
+{
+	struct swap_map_page *prev, *next;
+
+	prev = NULL;
+	while (swap_map) {
+		next = swap_map->next;
+		swap_map->next = prev;
+		prev = swap_map;
+		swap_map = next;
+	}
+	return prev;
+}
+
+/**
+ *	free_swap_map_entries - free the swap entries allocated to store
+ *	the swap map @swap_map (this is only called in case of an error)
+ */
+static inline void free_swap_map_entries(struct swap_map_page *swap_map)
+{
+	while (swap_map) {
+		if (swap_map->next_swap.val)
+			swap_free(swap_map->next_swap);
+		swap_map = swap_map->next;
+	}
+}
+
+/**
+ *	save_swap_map - save the swap map used for tracing the data pages
+ *	stored in the swap
+ */
+
+static int save_swap_map(struct swap_map_page *swap_map, swp_entry_t *start)
+{
+	swp_entry_t entry = (swp_entry_t){0};
+	int error;
+
+	while (swap_map) {
+		swap_map->next_swap = entry;
+		if ((error = write_page((unsigned long)swap_map, &entry)))
+			return error;
+		swap_map = swap_map->next;
+	}
+	*start = entry;
+	return 0;
+}
+
+/**
+ *	free_image_entries - free the swap entries allocated to store
+ *	the image data pages (this is only called in case of an error)
+ */
+
+static inline void free_image_entries(struct swap_map_page *swp)
+{
+	unsigned k;
+
+	while (swp) {
+		for (k = 0; k < MAP_PAGE_SIZE; k++)
+			if (swp->entries[k].val)
+				swap_free(swp->entries[k]);
+		swp = swp->next;
+	}
+}
+
+/**
+ *	The swap_map_handle structure is used for handling the swap map in
+ *	a file-alike way
+ */
+
+struct swap_map_handle {
+	struct swap_map_page *cur;
+	unsigned int k;
+};
+
+static inline void init_swap_map_handle(struct swap_map_handle *handle,
+                                        struct swap_map_page *map)
+{
+	handle->cur = map;
+	handle->k = 0;
+}
+
+static inline int swap_map_write_page(struct swap_map_handle *handle,
+                                      unsigned long addr)
+{
+	int error;
+
+	error = write_page(addr, handle->cur->entries + handle->k);
+	if (error)
+		return error;
+	if (++handle->k >= MAP_PAGE_SIZE) {
+		handle->cur = handle->cur->next;
+		handle->k = 0;
+	}
+	return 0;
+}
+
+/**
+ *	save_image_data - save the data pages pointed to by the PBEs
+ *	from the list @pblist using the swap map handle @handle
+ *	(assume there are @nr_pages data pages to save)
+ */
+
+static int save_image_data(struct pbe *pblist,
+                           struct swap_map_handle *handle,
+                           unsigned int nr_pages)
+{
+	unsigned int m;
+	struct pbe *p;
+	int error = 0;
+
+	printk("Saving image data pages (%u pages) ...     ", nr_pages);
+	m = nr_pages / 100;
+	if (!m)
+		m = 1;
+	nr_pages = 0;
+	for_each_pbe (p, pblist) {
+		error = swap_map_write_page(handle, p->address);
+		if (error)
+			break;
+		if (!(nr_pages % m))
+			printk("\b\b\b\b%3d%%", nr_pages / m);
+		nr_pages++;
+	}
+	if (!error)
+		printk("\b\b\b\bdone\n");
+	return error;
+}
+
+static void dump_info(void)
+{
+	pr_debug(" swsusp: Version: %u\n",swsusp_info.version_code);
+	pr_debug(" swsusp: Num Pages: %ld\n",swsusp_info.num_physpages);
+	pr_debug(" swsusp: UTS Sys: %s\n",swsusp_info.uts.sysname);
+	pr_debug(" swsusp: UTS Node: %s\n",swsusp_info.uts.nodename);
+	pr_debug(" swsusp: UTS Release: %s\n",swsusp_info.uts.release);
+	pr_debug(" swsusp: UTS Version: %s\n",swsusp_info.uts.version);
+	pr_debug(" swsusp: UTS Machine: %s\n",swsusp_info.uts.machine);
+	pr_debug(" swsusp: UTS Domain: %s\n",swsusp_info.uts.domainname);
+	pr_debug(" swsusp: CPUs: %d\n",swsusp_info.cpus);
+	pr_debug(" swsusp: Image: %ld Pages\n",swsusp_info.image_pages);
+	pr_debug(" swsusp: Total: %ld Pages\n", swsusp_info.pages);
+}
+
+static void init_header(unsigned int nr_pages)
+{
+	memset(&swsusp_info, 0, sizeof(swsusp_info));
+	swsusp_info.version_code = LINUX_VERSION_CODE;
+	swsusp_info.num_physpages = num_physpages;
+	memcpy(&swsusp_info.uts, &system_utsname, sizeof(system_utsname));
+
+	swsusp_info.cpus = num_online_cpus();
+	swsusp_info.image_pages = nr_pages;
+	swsusp_info.pages = nr_pages +
+		((nr_pages * sizeof(long) + PAGE_SIZE - 1) >> PAGE_SHIFT) + 1;
+}
+
+/**
+ *	pack_orig_addresses - the .orig_address fields of the PBEs from the
+ *	list starting at @pbe are stored in the array @buf[] (1 page)
+ */
+
+static inline struct pbe *pack_orig_addresses(unsigned long *buf,
+                                              struct pbe *pbe)
+{
+	int j;
+
+	for (j = 0; j < PAGE_SIZE / sizeof(long) && pbe; j++) {
+		buf[j] = pbe->orig_address;
+		pbe = pbe->next;
+	}
+	if (!pbe)
+		for (; j < PAGE_SIZE / sizeof(long); j++)
+			buf[j] = 0;
+	return pbe;
+}
+
+/**
+ *	save_image_metadata - save the .orig_address fields of the PBEs
+ *	from the list @pblist using the swap map handle @handle
+ */
+
+static int save_image_metadata(struct pbe *pblist,
+                               struct swap_map_handle *handle)
+{
+	unsigned long *buf;
+	unsigned int n = 0;
+	struct pbe *p;
+	int error = 0;
+
+	printk("Saving image metadata ... ");
+	buf = (unsigned long *)get_zeroed_page(GFP_ATOMIC);
+	if (!buf)
+		return -ENOMEM;
+	p = pblist;
+	while (p) {
+		p = pack_orig_addresses(buf, p);
+		error = swap_map_write_page(handle, (unsigned long)buf);
+		if (error)
+			break;
+		n++;
+	}
+	free_page((unsigned long)buf);
+	if (!error)
+		printk("done (%u pages saved)\n", n);
+	return error;
+}
+
+/**
+ *	enough_swap - Make sure we have enough swap to save the image.
+ *
+ *	Returns TRUE or FALSE after checking the total amount of swap
+ *	space avaiable from the resume partition.
+ */
+
+static int enough_swap(unsigned int nr_pages)
+{
+	unsigned int free_swap = swap_info[root_swap].pages -
+		swap_info[root_swap].inuse_pages;
+
+	pr_debug("swsusp: free swap pages: %u\n", free_swap);
+	return free_swap > (nr_pages + PAGES_FOR_IO +
+		(nr_pages + PBES_PER_PAGE - 1) / PBES_PER_PAGE);
+}
+
+/**
+ *	swsusp_write - Write entire image and metadata.
+ *
+ *	It is important _NOT_ to umount filesystems at this point. We want
+ *	them synced (in case something goes wrong) but we DO not want to mark
+ *	filesystem clean: it is not. (And it does not matter, if we resume
+ *	correctly, we'll mark system clean, anyway.)
+ */
+
+int swsusp_write(struct pbe *pblist, unsigned int nr_pages)
+{
+	struct swap_map_page *swap_map;
+	struct swap_map_handle handle;
+	swp_entry_t start;
+	int error;
+
+	if ((error = swsusp_swap_check())) {
+		printk(KERN_ERR "swsusp: Cannot find swap device, try swapon -a.\n");
+		return error;
+	}
+	if (!enough_swap(nr_pages)) {
+		printk(KERN_ERR "swsusp: Not enough free swap\n");
+		return -ENOSPC;
+	}
+
+	init_header(nr_pages);
+	swap_map = alloc_swap_map(swsusp_info.pages);
+	if (!swap_map)
+		return -ENOMEM;
+	init_swap_map_handle(&handle, swap_map);
+
+	error = swap_map_write_page(&handle, (unsigned long)&swsusp_info);
+	if (!error)
+		error = save_image_metadata(pblist, &handle);
+	if (!error)
+		error = save_image_data(pblist, &handle, nr_pages);
+	if (error)
+		goto Free_image_entries;
+
+	swap_map = reverse_swap_map(swap_map);
+	error = save_swap_map(swap_map, &start);
+	if (error)
+		goto Free_map_entries;
+
+	dump_info();
+	printk( "S" );
+	error = mark_swapfiles(start);
+	printk( "|\n" );
+	if (error)
+		goto Free_map_entries;
+
+Free_swap_map:
+	free_swap_map(swap_map);
+	return error;
+
+Free_map_entries:
+	free_swap_map_entries(swap_map);
+Free_image_entries:
+	free_image_entries(swap_map);
+	goto Free_swap_map;
+}
+
+/**
+ *	swsusp_shrink_memory -  Try to free as much memory as needed
+ *
+ *	... but do not OOM-kill anyone
+ *
+ *	Notice: all userland should be stopped before it is called, or
+ *	livelock is possible.
+ */
+
+#define SHRINK_BITE	10000
+
+int swsusp_shrink_memory(void)
+{
+	long size, tmp;
+	struct zone *zone;
+	unsigned long pages = 0;
+	unsigned int i = 0;
+	char *p = "-\\|/";
+
+	printk("Shrinking memory...  ");
+	do {
+		size = 2 * count_highmem_pages();
+		size += size / 50 + count_data_pages();
+		size += (size + PBES_PER_PAGE - 1) / PBES_PER_PAGE +
+			PAGES_FOR_IO;
+		tmp = size;
+		for_each_zone (zone)
+			if (!is_highmem(zone))
+				tmp -= zone->free_pages;
+		if (tmp > 0) {
+			tmp = shrink_all_memory(SHRINK_BITE);
+			if (!tmp)
+				return -ENOMEM;
+			pages += tmp;
+		} else if (size > image_size / PAGE_SIZE) {
+			tmp = shrink_all_memory(SHRINK_BITE);
+			pages += tmp;
+		}
+		printk("\b%c", p[i++%4]);
+	} while (tmp > 0);
+	printk("\bdone (%lu pages freed)\n", pages);
+
+	return 0;
+}
+
+int swsusp_suspend(void)
+{
+	int error;
+
+	if ((error = arch_prepare_suspend()))
+		return error;
+	local_irq_disable();
+	/* At this point, device_suspend() has been called, but *not*
+	 * device_power_down(). We *must* device_power_down() now.
+	 * Otherwise, drivers for some devices (e.g. interrupt controllers)
+	 * become desynchronized with the actual state of the hardware
+	 * at resume time, and evil weirdness ensues.
+	 */
+	if ((error = device_power_down(PMSG_FREEZE))) {
+		printk(KERN_ERR "Some devices failed to power down, aborting suspend\n");
+		goto Enable_irqs;
+	}
+
+	if ((error = save_highmem())) {
+		printk(KERN_ERR "swsusp: Not enough free pages for highmem\n");
+		goto Restore_highmem;
+	}
+
+	save_processor_state();
+	if ((error = swsusp_arch_suspend()))
+		printk(KERN_ERR "Error %d suspending\n", error);
+	/* Restore control flow magically appears here */
+	restore_processor_state();
+Restore_highmem:
+	restore_highmem();
+	device_power_up();
+Enable_irqs:
+	local_irq_enable();
+	return error;
+}
+
+int swsusp_resume(void)
+{
+	int error;
+	local_irq_disable();
+	if (device_power_down(PMSG_FREEZE))
+		printk(KERN_ERR "Some devices failed to power down, very bad\n");
+	/* We'll ignore saved state, but this gets preempt count (etc) right */
+	save_processor_state();
+	error = swsusp_arch_resume();
+	/* Code below is only ever reached in case of failure. Otherwise
+	 * execution continues at place where swsusp_arch_suspend was called
+         */
+	BUG_ON(!error);
+	/* The only reason why swsusp_arch_resume() can fail is memory being
+	 * very tight, so we have to free it as soon as we can to avoid
+	 * subsequent failures
+	 */
+	swsusp_free();
+	restore_processor_state();
+	restore_highmem();
+	touch_softlockup_watchdog();
+	device_power_up();
+	local_irq_enable();
+	return error;
+}
+
+/**
+ *	mark_unsafe_pages - mark the pages that cannot be used for storing
+ *	the image during resume, because they conflict with the pages that
+ *	had been used before suspend
+ */
+
+static void mark_unsafe_pages(struct pbe *pblist)
+{
+	struct zone *zone;
+	unsigned long zone_pfn;
+	struct pbe *p;
+
+	if (!pblist) /* a sanity check */
+		return;
+
+	/* Clear page flags */
+	for_each_zone (zone) {
+		for (zone_pfn = 0; zone_pfn < zone->spanned_pages; ++zone_pfn)
+			if (pfn_valid(zone_pfn + zone->zone_start_pfn))
+				ClearPageNosaveFree(pfn_to_page(zone_pfn +
+					zone->zone_start_pfn));
+	}
+
+	/* Mark orig addresses */
+	for_each_pbe (p, pblist)
+		SetPageNosaveFree(virt_to_page(p->orig_address));
+
+}
+
+static void copy_page_backup_list(struct pbe *dst, struct pbe *src)
+{
+	/* We assume both lists contain the same number of elements */
+	while (src) {
+		dst->orig_address = src->orig_address;
+		dst = dst->next;
+		src = src->next;
+	}
+}
+
+/*
+ *	Using bio to read from swap.
+ *	This code requires a bit more work than just using buffer heads
+ *	but, it is the recommended way for 2.5/2.6.
+ *	The following are to signal the beginning and end of I/O. Bios
+ *	finish asynchronously, while we want them to happen synchronously.
+ *	A simple atomic_t, and a wait loop take care of this problem.
+ */
+
+static atomic_t io_done = ATOMIC_INIT(0);
+
+static int end_io(struct bio *bio, unsigned int num, int err)
+{
+	if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
+		panic("I/O error reading memory image");
+	atomic_set(&io_done, 0);
+	return 0;
+}
+
+static struct block_device *resume_bdev;
+
+/**
+ *	submit - submit BIO request.
+ *	@rw:	READ or WRITE.
+ *	@off	physical offset of page.
+ *	@page:	page we're reading or writing.
+ *
+ *	Straight from the textbook - allocate and initialize the bio.
+ *	If we're writing, make sure the page is marked as dirty.
+ *	Then submit it and wait.
+ */
+
+static int submit(int rw, pgoff_t page_off, void *page)
+{
+	int error = 0;
+	struct bio *bio;
+
+	bio = bio_alloc(GFP_ATOMIC, 1);
+	if (!bio)
+		return -ENOMEM;
+	bio->bi_sector = page_off * (PAGE_SIZE >> 9);
+	bio->bi_bdev = resume_bdev;
+	bio->bi_end_io = end_io;
+
+	if (bio_add_page(bio, virt_to_page(page), PAGE_SIZE, 0) < PAGE_SIZE) {
+		printk("swsusp: ERROR: adding page to bio at %ld\n",page_off);
+		error = -EFAULT;
+		goto Done;
+	}
+
+
+	atomic_set(&io_done, 1);
+	submit_bio(rw | (1 << BIO_RW_SYNC), bio);
+	while (atomic_read(&io_done))
+		yield();
+	if (rw == READ)
+		bio_set_pages_dirty(bio);
+ Done:
+	bio_put(bio);
+	return error;
+}
+
+static int bio_read_page(pgoff_t page_off, void *page)
+{
+	return submit(READ, page_off, page);
+}
+
+static int bio_write_page(pgoff_t page_off, void *page)
+{
+	return submit(WRITE, page_off, page);
+}
+
+/**
+ *	The following functions allow us to read data using a swap map
+ *	in a file-alike way
+ */
+
+static inline void release_swap_map_reader(struct swap_map_handle *handle)
+{
+	if (handle->cur)
+		free_page((unsigned long)handle->cur);
+	handle->cur = NULL;
+}
+
+static inline int get_swap_map_reader(struct swap_map_handle *handle,
+                                      swp_entry_t start)
+{
+	int error;
+
+	if (!swp_offset(start))
+		return -EINVAL;
+	handle->cur = (struct swap_map_page *)get_zeroed_page(GFP_ATOMIC);
+	if (!handle->cur)
+		return -ENOMEM;
+	error = bio_read_page(swp_offset(start), handle->cur);
+	if (error) {
+		release_swap_map_reader(handle);
+		return error;
+	}
+	handle->k = 0;
+	return 0;
+}
+
+static inline int swap_map_read_page(struct swap_map_handle *handle, void *buf)
+{
+	unsigned long offset;
+	int error;
+
+	if (!handle->cur)
+		return -EINVAL;
+	offset = swp_offset(handle->cur->entries[handle->k]);
+	if (!offset)
+		return -EINVAL;
+	error = bio_read_page(offset, buf);
+	if (error)
+		return error;
+	if (++handle->k >= MAP_PAGE_SIZE) {
+		handle->k = 0;
+		offset = swp_offset(handle->cur->next_swap);
+		if (!offset)
+			release_swap_map_reader(handle);
+		else
+			error = bio_read_page(offset, handle->cur);
+	}
+	return error;
+}
+
+static int check_header(void)
+{
+	char *reason = NULL;
+
+	dump_info();
+	if (swsusp_info.version_code != LINUX_VERSION_CODE)
+		reason = "kernel version";
+	if (swsusp_info.num_physpages != num_physpages)
+		reason = "memory size";
+	if (strcmp(swsusp_info.uts.sysname,system_utsname.sysname))
+		reason = "system type";
+	if (strcmp(swsusp_info.uts.release,system_utsname.release))
+		reason = "kernel release";
+	if (strcmp(swsusp_info.uts.version,system_utsname.version))
+		reason = "version";
+	if (strcmp(swsusp_info.uts.machine,system_utsname.machine))
+		reason = "machine";
+	if (reason) {
+		printk(KERN_ERR "swsusp: Resume mismatch: %s\n", reason);
+		return -EPERM;
+	}
+	return 0;
+}
+
+/**
+ *	load_image_data - load the image data using the swap map handle
+ *	@handle and store them using the page backup list @pblist
+ *	(assume there are @nr_pages pages to load)
+ */
+
+static int load_image_data(struct pbe *pblist,
+                           struct swap_map_handle *handle,
+                           unsigned int nr_pages)
+{
+	int error;
+	unsigned int m;
+	struct pbe *p;
+
+	if (!pblist)
+		return -EINVAL;
+	printk("Loading image data pages (%u pages) ...     ", nr_pages);
+	m = nr_pages / 100;
+	if (!m)
+		m = 1;
+	nr_pages = 0;
+	p = pblist;
+	while (p) {
+		error = swap_map_read_page(handle, (void *)p->address);
+		if (error)
+			break;
+		p = p->next;
+		if (!(nr_pages % m))
+			printk("\b\b\b\b%3d%%", nr_pages / m);
+		nr_pages++;
+	}
+	if (!error)
+		printk("\b\b\b\bdone\n");
+	return error;
+}
+
+/**
+ *	unpack_orig_addresses - copy the elements of @buf[] (1 page) to
+ *	the PBEs in the list starting at @pbe
+ */
+
+static inline struct pbe *unpack_orig_addresses(unsigned long *buf,
+                                                struct pbe *pbe)
+{
+	int j;
+
+	for (j = 0; j < PAGE_SIZE / sizeof(long) && pbe; j++) {
+		pbe->orig_address = buf[j];
+		pbe = pbe->next;
+	}
+	return pbe;
+}
+
+/**
+ *	load_image_metadata - load the image metadata using the swap map
+ *	handle @handle and put them into the PBEs in the list @pblist
+ */
+
+static int load_image_metadata(struct pbe *pblist, struct swap_map_handle *handle)
+{
+	struct pbe *p;
+	unsigned long *buf;
+	unsigned int n = 0;
+	int error = 0;
+
+	printk("Loading image metadata ... ");
+	buf = (unsigned long *)get_zeroed_page(GFP_ATOMIC);
+	if (!buf)
+		return -ENOMEM;
+	p = pblist;
+	while (p) {
+		error = swap_map_read_page(handle, buf);
+		if (error)
+			break;
+		p = unpack_orig_addresses(buf, p);
+		n++;
+	}
+	free_page((unsigned long)buf);
+	if (!error)
+		printk("done (%u pages loaded)\n", n);
+	return error;
+}
+
+int swsusp_read(struct pbe **pblist_ptr)
+{
+	int error;
+	struct pbe *p, *pblist;
+	struct swap_map_handle handle;
+	unsigned int nr_pages;
+
+	if (IS_ERR(resume_bdev)) {
+		pr_debug("swsusp: block device not initialised\n");
+		return PTR_ERR(resume_bdev);
+	}
+
+	error = get_swap_map_reader(&handle, swsusp_header.image);
+	if (!error)
+		error = swap_map_read_page(&handle, &swsusp_info);
+	if (!error)
+		error = check_header();
+	if (error)
+		return error;
+	nr_pages = swsusp_info.image_pages;
+	p = alloc_pagedir(nr_pages, GFP_ATOMIC, 0);
+	if (!p)
+		return -ENOMEM;
+	error = load_image_metadata(p, &handle);
+	if (!error) {
+		mark_unsafe_pages(p);
+		pblist = alloc_pagedir(nr_pages, GFP_ATOMIC, 1);
+		if (pblist)
+			copy_page_backup_list(pblist, p);
+		free_pagedir(p);
+		if (!pblist)
+			error = -ENOMEM;
+
+		/* Allocate memory for the image and read the data from swap */
+		if (!error)
+			error = alloc_data_pages(pblist, GFP_ATOMIC, 1);
+		if (!error) {
+			release_eaten_pages();
+			error = load_image_data(pblist, &handle, nr_pages);
+		}
+		if (!error)
+			*pblist_ptr = pblist;
+	}
+	release_swap_map_reader(&handle);
+
+	blkdev_put(resume_bdev);
+
+	if (!error)
+		pr_debug("swsusp: Reading resume file was successful\n");
+	else
+		pr_debug("swsusp: Error %d resuming\n", error);
+	return error;
+}
+
+/**
+ *      swsusp_check - Check for swsusp signature in the resume device
+ */
+
+int swsusp_check(void)
+{
+	int error;
+
+	resume_bdev = open_by_devnum(swsusp_resume_device, FMODE_READ);
+	if (!IS_ERR(resume_bdev)) {
+		set_blocksize(resume_bdev, PAGE_SIZE);
+		memset(&swsusp_header, 0, sizeof(swsusp_header));
+		if ((error = bio_read_page(0, &swsusp_header)))
+			return error;
+		if (!memcmp(SWSUSP_SIG, swsusp_header.sig, 10)) {
+			memcpy(swsusp_header.sig, swsusp_header.orig_sig, 10);
+			/* Reset swap signature now */
+			error = bio_write_page(0, &swsusp_header);
+		} else {
+			return -EINVAL;
+		}
+		if (error)
+			blkdev_put(resume_bdev);
+		else
+			pr_debug("swsusp: Signature found, resuming\n");
+	} else {
+		error = PTR_ERR(resume_bdev);
+	}
+
+	if (error)
+		pr_debug("swsusp: Error %d check for resume file\n", error);
+
+	return error;
+}
+
+/**
+ *	swsusp_close - close swap device.
+ */
+
+void swsusp_close(void)
+{
+	if (IS_ERR(resume_bdev)) {
+		pr_debug("swsusp: block device not initialised\n");
+		return;
+	}
+
+	blkdev_put(resume_bdev);
+}
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	2006-02-18 15:24:31.428811024 +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	2006-02-18 15:24:31.430810720 +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 "modules.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_module_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;
+
+	suspend_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;
+
+	suspend_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:
+			suspend_send_netlink_message(&ui_helper_data, 
+					USERUI_MSG_GET_STATE, &suspend_action,
+					sizeof(suspend_action));
+			break;
+		case USERUI_MSG_GET_DEBUG_STATE:
+			suspend_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';
+	}
+
+	suspend_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;
+
+	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);
+
+	if (ui_helper_data.pid == -1)
+		return;
+
+	suspend_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)");
+			suspend_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);
+	}
+}
+
+/* suspend_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 suspend_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 suspend_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 suspend_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) {
+			suspend_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);
+
+/* suspend_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 suspend_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;
+	}
+
+	suspend_netlink_setup(&ui_helper_data);
+
+	return;
+}
+
+/* suspend_restore_console
+ *
+ * Description: Restore the settings we saved above.
+ */
+
+void suspend_cleanup_console(void)
+{
+	suspend_default_console_level = console_loglevel;
+
+	if (ui_helper_data.pid > -1) {
+		struct task_struct *t;
+
+		suspend_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);
+
+		suspend_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 suspend_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 suspend_prepare_status(int clearbar, const char *fmt, ...) { }
+void check_shift_keys(int pause, char *message) { }
+void abort_suspend(const char *fmt, ...) { }
+void suspend_prepare_console(void) { }
+void suspend_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_module_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_module(&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 = suspend_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	2006-02-18 15:24:31.431810568 +0000
@@ -0,0 +1,44 @@
+/*
+ *
+ */
+
+extern void suspend_prepare_console(void);
+extern void suspend_cleanup_console(void);
+
+extern void check_shift_keys(int pause, char *message);
+extern unsigned long suspend_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	2006-02-18 15:24:31.431810568 +0000
@@ -0,0 +1,2 @@
+#define SUSPEND_CORE_VERSION "2.2.0.1"
+#define name_suspend "Suspend2 " SUSPEND_CORE_VERSION ": "
diff -urN oldtree/kernel/sched.c newtree/kernel/sched.c
--- oldtree/kernel/sched.c	2006-02-18 15:18:30.095742000 +0000
+++ newtree/kernel/sched.c	2006-02-18 15:24:31.435809960 +0000
@@ -4704,7 +4704,6 @@
 		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/sched.c.orig newtree/kernel/sched.c.orig
--- oldtree/kernel/sched.c.orig	1970-01-01 00:00:00.000000000 +0000
+++ newtree/kernel/sched.c.orig	2006-02-18 15:18:30.000000000 +0000
@@ -0,0 +1,6166 @@
+/*
+ *  kernel/sched.c
+ *
+ *  Kernel scheduler and related syscalls
+ *
+ *  Copyright (C) 1991-2002  Linus Torvalds
+ *
+ *  1996-12-23  Modified by Dave Grothe to fix bugs in semaphores and
+ *		make semaphores SMP safe
+ *  1998-11-19	Implemented schedule_timeout() and related stuff
+ *		by Andrea Arcangeli
+ *  2002-01-04	New ultra-scalable O(1) scheduler by Ingo Molnar:
+ *		hybrid priority-list and round-robin design with
+ *		an array-switch method of distributing timeslices
+ *		and per-CPU runqueues.  Cleanups and useful suggestions
+ *		by Davide Libenzi, preemptible kernel bits by Robert Love.
+ *  2003-09-03	Interactivity tuning by Con Kolivas.
+ *  2004-04-02	Scheduler domains code by Nick Piggin
+ */
+
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/nmi.h>
+#include <linux/init.h>
+#include <asm/uaccess.h>
+#include <linux/highmem.h>
+#include <linux/smp_lock.h>
+#include <asm/mmu_context.h>
+#include <linux/interrupt.h>
+#include <linux/capability.h>
+#include <linux/completion.h>
+#include <linux/kernel_stat.h>
+#include <linux/security.h>
+#include <linux/notifier.h>
+#include <linux/profile.h>
+#include <linux/suspend.h>
+#include <linux/vmalloc.h>
+#include <linux/blkdev.h>
+#include <linux/delay.h>
+#include <linux/smp.h>
+#include <linux/threads.h>
+#include <linux/timer.h>
+#include <linux/rcupdate.h>
+#include <linux/cpu.h>
+#include <linux/cpuset.h>
+#include <linux/percpu.h>
+#include <linux/kthread.h>
+#include <linux/seq_file.h>
+#include <linux/syscalls.h>
+#include <linux/times.h>
+#include <linux/acct.h>
+#include <asm/tlb.h>
+
+#include <asm/unistd.h>
+
+/*
+ * Convert user-nice values [ -20 ... 0 ... 19 ]
+ * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
+ * and back.
+ */
+#define NICE_TO_PRIO(nice)	(MAX_RT_PRIO + (nice) + 20)
+#define PRIO_TO_NICE(prio)	((prio) - MAX_RT_PRIO - 20)
+#define TASK_NICE(p)		PRIO_TO_NICE((p)->static_prio)
+
+/*
+ * 'User priority' is the nice value converted to something we
+ * can work with better when scaling various scheduler parameters,
+ * it's a [ 0 ... 39 ] range.
+ */
+#define USER_PRIO(p)		((p)-MAX_RT_PRIO)
+#define TASK_USER_PRIO(p)	USER_PRIO((p)->static_prio)
+#define MAX_USER_PRIO		(USER_PRIO(MAX_PRIO))
+
+/*
+ * Some helpers for converting nanosecond timing to jiffy resolution
+ */
+#define NS_TO_JIFFIES(TIME)	((TIME) / (1000000000 / HZ))
+#define JIFFIES_TO_NS(TIME)	((TIME) * (1000000000 / HZ))
+
+/*
+ * These are the 'tuning knobs' of the scheduler:
+ *
+ * Minimum timeslice is 5 msecs (or 1 jiffy, whichever is larger),
+ * default timeslice is 100 msecs, maximum timeslice is 800 msecs.
+ * Timeslices get refilled after they expire.
+ */
+#define MIN_TIMESLICE		max(5 * HZ / 1000, 1)
+#define DEF_TIMESLICE		(100 * HZ / 1000)
+#define ON_RUNQUEUE_WEIGHT	 30
+#define CHILD_PENALTY		 95
+#define PARENT_PENALTY		100
+#define EXIT_WEIGHT		  3
+#define PRIO_BONUS_RATIO	 25
+#define MAX_BONUS		(MAX_USER_PRIO * PRIO_BONUS_RATIO / 100)
+#define INTERACTIVE_DELTA	  2
+#define MAX_SLEEP_AVG		(DEF_TIMESLICE * MAX_BONUS)
+#define STARVATION_LIMIT	(MAX_SLEEP_AVG)
+#define NS_MAX_SLEEP_AVG	(JIFFIES_TO_NS(MAX_SLEEP_AVG))
+
+/*
+ * If a task is 'interactive' then we reinsert it in the active
+ * array after it has expired its current timeslice. (it will not
+ * continue to run immediately, it will still roundrobin with
+ * other interactive tasks.)
+ *
+ * This part scales the interactivity limit depending on niceness.
+ *
+ * We scale it linearly, offset by the INTERACTIVE_DELTA delta.
+ * Here are a few examples of different nice levels:
+ *
+ *  TASK_INTERACTIVE(-20): [1,1,1,1,1,1,1,1,1,0,0]
+ *  TASK_INTERACTIVE(-10): [1,1,1,1,1,1,1,0,0,0,0]
+ *  TASK_INTERACTIVE(  0): [1,1,1,1,0,0,0,0,0,0,0]
+ *  TASK_INTERACTIVE( 10): [1,1,0,0,0,0,0,0,0,0,0]
+ *  TASK_INTERACTIVE( 19): [0,0,0,0,0,0,0,0,0,0,0]
+ *
+ * (the X axis represents the possible -5 ... 0 ... +5 dynamic
+ *  priority range a task can explore, a value of '1' means the
+ *  task is rated interactive.)
+ *
+ * Ie. nice +19 tasks can never get 'interactive' enough to be
+ * reinserted into the active array. And only heavily CPU-hog nice -20
+ * tasks will be expired. Default nice 0 tasks are somewhere between,
+ * it takes some effort for them to get interactive, but it's not
+ * too hard.
+ */
+
+#define CURRENT_BONUS(p) \
+	(NS_TO_JIFFIES((p)->sleep_avg) * MAX_BONUS / \
+		MAX_SLEEP_AVG)
+
+#define GRANULARITY	(10 * HZ / 1000 ? : 1)
+
+#ifdef CONFIG_SMP
+#define TIMESLICE_GRANULARITY(p)	(GRANULARITY * \
+		(1 << (((MAX_BONUS - CURRENT_BONUS(p)) ? : 1) - 1)) * \
+			num_online_cpus())
+#else
+#define TIMESLICE_GRANULARITY(p)	(GRANULARITY * \
+		(1 << (((MAX_BONUS - CURRENT_BONUS(p)) ? : 1) - 1)))
+#endif
+
+#define SCALE(v1,v1_max,v2_max) \
+	(v1) * (v2_max) / (v1_max)
+
+#define DELTA(p) \
+	(SCALE(TASK_NICE(p), 40, MAX_BONUS) + INTERACTIVE_DELTA)
+
+#define TASK_INTERACTIVE(p) \
+	((p)->prio <= (p)->static_prio - DELTA(p))
+
+#define INTERACTIVE_SLEEP(p) \
+	(JIFFIES_TO_NS(MAX_SLEEP_AVG * \
+		(MAX_BONUS / 2 + DELTA((p)) + 1) / MAX_BONUS - 1))
+
+#define TASK_PREEMPTS_CURR(p, rq) \
+	((p)->prio < (rq)->curr->prio)
+
+/*
+ * task_timeslice() scales user-nice values [ -20 ... 0 ... 19 ]
+ * to time slice values: [800ms ... 100ms ... 5ms]
+ *
+ * The higher a thread's priority, the bigger timeslices
+ * it gets during one round of execution. But even the lowest
+ * priority thread gets MIN_TIMESLICE worth of execution time.
+ */
+
+#define SCALE_PRIO(x, prio) \
+	max(x * (MAX_PRIO - prio) / (MAX_USER_PRIO/2), MIN_TIMESLICE)
+
+static unsigned int task_timeslice(task_t *p)
+{
+	if (p->static_prio < NICE_TO_PRIO(0))
+		return SCALE_PRIO(DEF_TIMESLICE*4, p->static_prio);
+	else
+		return SCALE_PRIO(DEF_TIMESLICE, p->static_prio);
+}
+#define task_hot(p, now, sd) ((long long) ((now) - (p)->last_ran)	\
+				< (long long) (sd)->cache_hot_time)
+
+void __put_task_struct_cb(struct rcu_head *rhp)
+{
+	__put_task_struct(container_of(rhp, struct task_struct, rcu));
+}
+
+EXPORT_SYMBOL_GPL(__put_task_struct_cb);
+
+/*
+ * These are the runqueue data structures:
+ */
+
+#define BITMAP_SIZE ((((MAX_PRIO+1+7)/8)+sizeof(long)-1)/sizeof(long))
+
+typedef struct runqueue runqueue_t;
+
+struct prio_array {
+	unsigned int nr_active;
+	unsigned long bitmap[BITMAP_SIZE];
+	struct list_head queue[MAX_PRIO];
+};
+
+/*
+ * This is the main, per-CPU runqueue data structure.
+ *
+ * Locking rule: those places that want to lock multiple runqueues
+ * (such as the load balancing or the thread migration code), lock
+ * acquire operations must be ordered by ascending &runqueue.
+ */
+struct runqueue {
+	spinlock_t lock;
+
+	/*
+	 * nr_running and cpu_load should be in the same cacheline because
+	 * remote CPUs use both these fields when doing load calculation.
+	 */
+	unsigned long nr_running;
+#ifdef CONFIG_SMP
+	unsigned long cpu_load[3];
+#endif
+	unsigned long long nr_switches;
+
+	/*
+	 * This is part of a global counter where only the total sum
+	 * over all CPUs matters. A task can increase this counter on
+	 * one CPU and if it got migrated afterwards it may decrease
+	 * it on another CPU. Always updated under the runqueue lock:
+	 */
+	unsigned long nr_uninterruptible;
+
+	unsigned long expired_timestamp;
+	unsigned long long timestamp_last_tick;
+	task_t *curr, *idle;
+	struct mm_struct *prev_mm;
+	prio_array_t *active, *expired, arrays[2];
+	int best_expired_prio;
+	atomic_t nr_iowait;
+
+#ifdef CONFIG_SMP
+	struct sched_domain *sd;
+
+	/* For active balancing */
+	int active_balance;
+	int push_cpu;
+
+	task_t *migration_thread;
+	struct list_head migration_queue;
+#endif
+
+#ifdef CONFIG_SCHEDSTATS
+	/* latency stats */
+	struct sched_info rq_sched_info;
+
+	/* sys_sched_yield() stats */
+	unsigned long yld_exp_empty;
+	unsigned long yld_act_empty;
+	unsigned long yld_both_empty;
+	unsigned long yld_cnt;
+
+	/* schedule() stats */
+	unsigned long sched_switch;
+	unsigned long sched_cnt;
+	unsigned long sched_goidle;
+
+	/* try_to_wake_up() stats */
+	unsigned long ttwu_cnt;
+	unsigned long ttwu_local;
+#endif
+};
+
+static DEFINE_PER_CPU(struct runqueue, runqueues);
+
+/*
+ * The domain tree (rq->sd) is protected by RCU's quiescent state transition.
+ * See detach_destroy_domains: synchronize_sched for details.
+ *
+ * The domain tree of any CPU may only be accessed from within
+ * preempt-disabled sections.
+ */
+#define for_each_domain(cpu, domain) \
+for (domain = rcu_dereference(cpu_rq(cpu)->sd); domain; domain = domain->parent)
+
+#define cpu_rq(cpu)		(&per_cpu(runqueues, (cpu)))
+#define this_rq()		(&__get_cpu_var(runqueues))
+#define task_rq(p)		cpu_rq(task_cpu(p))
+#define cpu_curr(cpu)		(cpu_rq(cpu)->curr)
+
+#ifndef prepare_arch_switch
+# define prepare_arch_switch(next)	do { } while (0)
+#endif
+#ifndef finish_arch_switch
+# define finish_arch_switch(prev)	do { } while (0)
+#endif
+
+#ifndef __ARCH_WANT_UNLOCKED_CTXSW
+static inline int task_running(runqueue_t *rq, task_t *p)
+{
+	return rq->curr == p;
+}
+
+static inline void prepare_lock_switch(runqueue_t *rq, task_t *next)
+{
+}
+
+static inline void finish_lock_switch(runqueue_t *rq, task_t *prev)
+{
+#ifdef CONFIG_DEBUG_SPINLOCK
+	/* this is a valid case when another task releases the spinlock */
+	rq->lock.owner = current;
+#endif
+	spin_unlock_irq(&rq->lock);
+}
+
+#else /* __ARCH_WANT_UNLOCKED_CTXSW */
+static inline int task_running(runqueue_t *rq, task_t *p)
+{
+#ifdef CONFIG_SMP
+	return p->oncpu;
+#else
+	return rq->curr == p;
+#endif
+}
+
+static inline void prepare_lock_switch(runqueue_t *rq, task_t *next)
+{
+#ifdef CONFIG_SMP
+	/*
+	 * We can optimise this out completely for !SMP, because the
+	 * SMP rebalancing from interrupt is the only thing that cares
+	 * here.
+	 */
+	next->oncpu = 1;
+#endif
+#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
+	spin_unlock_irq(&rq->lock);
+#else
+	spin_unlock(&rq->lock);
+#endif
+}
+
+static inline void finish_lock_switch(runqueue_t *rq, task_t *prev)
+{
+#ifdef CONFIG_SMP
+	/*
+	 * After ->oncpu is cleared, the task can be moved to a different CPU.
+	 * We must ensure this doesn't happen until the switch is completely
+	 * finished.
+	 */
+	smp_wmb();
+	prev->oncpu = 0;
+#endif
+#ifndef __ARCH_WANT_INTERRUPTS_ON_CTXSW
+	local_irq_enable();
+#endif
+}
+#endif /* __ARCH_WANT_UNLOCKED_CTXSW */
+
+/*
+ * task_rq_lock - lock the runqueue a given task resides on and disable
+ * interrupts.  Note the ordering: we can safely lookup the task_rq without
+ * explicitly disabling preemption.
+ */
+static inline runqueue_t *task_rq_lock(task_t *p, unsigned long *flags)
+	__acquires(rq->lock)
+{
+	struct runqueue *rq;
+
+repeat_lock_task:
+	local_irq_save(*flags);
+	rq = task_rq(p);
+	spin_lock(&rq->lock);
+	if (unlikely(rq != task_rq(p))) {
+		spin_unlock_irqrestore(&rq->lock, *flags);
+		goto repeat_lock_task;
+	}
+	return rq;
+}
+
+static inline void task_rq_unlock(runqueue_t *rq, unsigned long *flags)
+	__releases(rq->lock)
+{
+	spin_unlock_irqrestore(&rq->lock, *flags);
+}
+
+#ifdef CONFIG_SCHEDSTATS
+/*
+ * bump this up when changing the output format or the meaning of an existing
+ * format, so that tools can adapt (or abort)
+ */
+#define SCHEDSTAT_VERSION 12
+
+static int show_schedstat(struct seq_file *seq, void *v)
+{
+	int cpu;
+
+	seq_printf(seq, "version %d\n", SCHEDSTAT_VERSION);
+	seq_printf(seq, "timestamp %lu\n", jiffies);
+	for_each_online_cpu(cpu) {
+		runqueue_t *rq = cpu_rq(cpu);
+#ifdef CONFIG_SMP
+		struct sched_domain *sd;
+		int dcnt = 0;
+#endif
+
+		/* runqueue-specific stats */
+		seq_printf(seq,
+		    "cpu%d %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu",
+		    cpu, rq->yld_both_empty,
+		    rq->yld_act_empty, rq->yld_exp_empty, rq->yld_cnt,
+		    rq->sched_switch, rq->sched_cnt, rq->sched_goidle,
+		    rq->ttwu_cnt, rq->ttwu_local,
+		    rq->rq_sched_info.cpu_time,
+		    rq->rq_sched_info.run_delay, rq->rq_sched_info.pcnt);
+
+		seq_printf(seq, "\n");
+
+#ifdef CONFIG_SMP
+		/* domain-specific stats */
+		preempt_disable();
+		for_each_domain(cpu, sd) {
+			enum idle_type itype;
+			char mask_str[NR_CPUS];
+
+			cpumask_scnprintf(mask_str, NR_CPUS, sd->span);
+			seq_printf(seq, "domain%d %s", dcnt++, mask_str);
+			for (itype = SCHED_IDLE; itype < MAX_IDLE_TYPES;
+					itype++) {
+				seq_printf(seq, " %lu %lu %lu %lu %lu %lu %lu %lu",
+				    sd->lb_cnt[itype],
+				    sd->lb_balanced[itype],
+				    sd->lb_failed[itype],
+				    sd->lb_imbalance[itype],
+				    sd->lb_gained[itype],
+				    sd->lb_hot_gained[itype],
+				    sd->lb_nobusyq[itype],
+				    sd->lb_nobusyg[itype]);
+			}
+			seq_printf(seq, " %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu\n",
+			    sd->alb_cnt, sd->alb_failed, sd->alb_pushed,
+			    sd->sbe_cnt, sd->sbe_balanced, sd->sbe_pushed,
+			    sd->sbf_cnt, sd->sbf_balanced, sd->sbf_pushed,
+			    sd->ttwu_wake_remote, sd->ttwu_move_affine, sd->ttwu_move_balance);
+		}
+		preempt_enable();
+#endif
+	}
+	return 0;
+}
+
+static int schedstat_open(struct inode *inode, struct file *file)
+{
+	unsigned int size = PAGE_SIZE * (1 + num_online_cpus() / 32);
+	char *buf = kmalloc(size, GFP_KERNEL);
+	struct seq_file *m;
+	int res;
+
+	if (!buf)
+		return -ENOMEM;
+	res = single_open(file, show_schedstat, NULL);
+	if (!res) {
+		m = file->private_data;
+		m->buf = buf;
+		m->size = size;
+	} else
+		kfree(buf);
+	return res;
+}
+
+struct file_operations proc_schedstat_operations = {
+	.open    = schedstat_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = single_release,
+};
+
+# define schedstat_inc(rq, field)	do { (rq)->field++; } while (0)
+# define schedstat_add(rq, field, amt)	do { (rq)->field += (amt); } while (0)
+#else /* !CONFIG_SCHEDSTATS */
+# define schedstat_inc(rq, field)	do { } while (0)
+# define schedstat_add(rq, field, amt)	do { } while (0)
+#endif
+
+/*
+ * rq_lock - lock a given runqueue and disable interrupts.
+ */
+static inline runqueue_t *this_rq_lock(void)
+	__acquires(rq->lock)
+{
+	runqueue_t *rq;
+
+	local_irq_disable();
+	rq = this_rq();
+	spin_lock(&rq->lock);
+
+	return rq;
+}
+
+#ifdef CONFIG_SCHEDSTATS
+/*
+ * Called when a process is dequeued from the active array and given
+ * the cpu.  We should note that with the exception of interactive
+ * tasks, the expired queue will become the active queue after the active
+ * queue is empty, without explicitly dequeuing and requeuing tasks in the
+ * expired queue.  (Interactive tasks may be requeued directly to the
+ * active queue, thus delaying tasks in the expired queue from running;
+ * see scheduler_tick()).
+ *
+ * This function is only called from sched_info_arrive(), rather than
+ * dequeue_task(). Even though a task may be queued and dequeued multiple
+ * times as it is shuffled about, we're really interested in knowing how
+ * long it was from the *first* time it was queued to the time that it
+ * finally hit a cpu.
+ */
+static inline void sched_info_dequeued(task_t *t)
+{
+	t->sched_info.last_queued = 0;
+}
+
+/*
+ * Called when a task finally hits the cpu.  We can now calculate how
+ * long it was waiting to run.  We also note when it began so that we
+ * can keep stats on how long its timeslice is.
+ */
+static void sched_info_arrive(task_t *t)
+{
+	unsigned long now = jiffies, diff = 0;
+	struct runqueue *rq = task_rq(t);
+
+	if (t->sched_info.last_queued)
+		diff = now - t->sched_info.last_queued;
+	sched_info_dequeued(t);
+	t->sched_info.run_delay += diff;
+	t->sched_info.last_arrival = now;
+	t->sched_info.pcnt++;
+
+	if (!rq)
+		return;
+
+	rq->rq_sched_info.run_delay += diff;
+	rq->rq_sched_info.pcnt++;
+}
+
+/*
+ * Called when a process is queued into either the active or expired
+ * array.  The time is noted and later used to determine how long we
+ * had to wait for us to reach the cpu.  Since the expired queue will
+ * become the active queue after active queue is empty, without dequeuing
+ * and requeuing any tasks, we are interested in queuing to either. It
+ * is unusual but not impossible for tasks to be dequeued and immediately
+ * requeued in the same or another array: this can happen in sched_yield(),
+ * set_user_nice(), and even load_balance() as it moves tasks from runqueue
+ * to runqueue.
+ *
+ * This function is only called from enqueue_task(), but also only updates
+ * the timestamp if it is already not set.  It's assumed that
+ * sched_info_dequeued() will clear that stamp when appropriate.
+ */
+static inline void sched_info_queued(task_t *t)
+{
+	if (!t->sched_info.last_queued)
+		t->sched_info.last_queued = jiffies;
+}
+
+/*
+ * Called when a process ceases being the active-running process, either
+ * voluntarily or involuntarily.  Now we can calculate how long we ran.
+ */
+static inline void sched_info_depart(task_t *t)
+{
+	struct runqueue *rq = task_rq(t);
+	unsigned long diff = jiffies - t->sched_info.last_arrival;
+
+	t->sched_info.cpu_time += diff;
+
+	if (rq)
+		rq->rq_sched_info.cpu_time += diff;
+}
+
+/*
+ * Called when tasks are switched involuntarily due, typically, to expiring
+ * their time slice.  (This may also be called when switching to or from
+ * the idle task.)  We are only called when prev != next.
+ */
+static inline void sched_info_switch(task_t *prev, task_t *next)
+{
+	struct runqueue *rq = task_rq(prev);
+
+	/*
+	 * prev now departs the cpu.  It's not interesting to record
+	 * stats about how efficient we were at scheduling the idle
+	 * process, however.
+	 */
+	if (prev != rq->idle)
+		sched_info_depart(prev);
+
+	if (next != rq->idle)
+		sched_info_arrive(next);
+}
+#else
+#define sched_info_queued(t)		do { } while (0)
+#define sched_info_switch(t, next)	do { } while (0)
+#endif /* CONFIG_SCHEDSTATS */
+
+/*
+ * Adding/removing a task to/from a priority array:
+ */
+static void dequeue_task(struct task_struct *p, prio_array_t *array)
+{
+	array->nr_active--;
+	list_del(&p->run_list);
+	if (list_empty(array->queue + p->prio))
+		__clear_bit(p->prio, array->bitmap);
+}
+
+static void enqueue_task(struct task_struct *p, prio_array_t *array)
+{
+	sched_info_queued(p);
+	list_add_tail(&p->run_list, array->queue + p->prio);
+	__set_bit(p->prio, array->bitmap);
+	array->nr_active++;
+	p->array = array;
+}
+
+/*
+ * Put task to the end of the run list without the overhead of dequeue
+ * followed by enqueue.
+ */
+static void requeue_task(struct task_struct *p, prio_array_t *array)
+{
+	list_move_tail(&p->run_list, array->queue + p->prio);
+}
+
+static inline void enqueue_task_head(struct task_struct *p, prio_array_t *array)
+{
+	list_add(&p->run_list, array->queue + p->prio);
+	__set_bit(p->prio, array->bitmap);
+	array->nr_active++;
+	p->array = array;
+}
+
+/*
+ * effective_prio - return the priority that is based on the static
+ * priority but is modified by bonuses/penalties.
+ *
+ * We scale the actual sleep average [0 .... MAX_SLEEP_AVG]
+ * into the -5 ... 0 ... +5 bonus/penalty range.
+ *
+ * We use 25% of the full 0...39 priority range so that:
+ *
+ * 1) nice +19 interactive tasks do not preempt nice 0 CPU hogs.
+ * 2) nice -20 CPU hogs do not get preempted by nice 0 tasks.
+ *
+ * Both properties are important to certain workloads.
+ */
+static int effective_prio(task_t *p)
+{
+	int bonus, prio;
+
+	if (rt_task(p))
+		return p->prio;
+
+	bonus = CURRENT_BONUS(p) - MAX_BONUS / 2;
+
+	prio = p->static_prio - bonus;
+	if (prio < MAX_RT_PRIO)
+		prio = MAX_RT_PRIO;
+	if (prio > MAX_PRIO-1)
+		prio = MAX_PRIO-1;
+	return prio;
+}
+
+/*
+ * __activate_task - move a task to the runqueue.
+ */
+static inline void __activate_task(task_t *p, runqueue_t *rq)
+{
+	enqueue_task(p, rq->active);
+	rq->nr_running++;
+}
+
+/*
+ * __activate_idle_task - move idle task to the _front_ of runqueue.
+ */
+static inline void __activate_idle_task(task_t *p, runqueue_t *rq)
+{
+	enqueue_task_head(p, rq->active);
+	rq->nr_running++;
+}
+
+static int recalc_task_prio(task_t *p, unsigned long long now)
+{
+	/* Caller must always ensure 'now >= p->timestamp' */
+	unsigned long long __sleep_time = now - p->timestamp;
+	unsigned long sleep_time;
+
+	if (unlikely(p->policy == SCHED_BATCH))
+		sleep_time = 0;
+	else {
+		if (__sleep_time > NS_MAX_SLEEP_AVG)
+			sleep_time = NS_MAX_SLEEP_AVG;
+		else
+			sleep_time = (unsigned long)__sleep_time;
+	}
+
+	if (likely(sleep_time > 0)) {
+		/*
+		 * User tasks that sleep a long time are categorised as
+		 * idle and will get just interactive status to stay active &
+		 * prevent them suddenly becoming cpu hogs and starving
+		 * other processes.
+		 */
+		if (p->mm && p->activated != -1 &&
+			sleep_time > INTERACTIVE_SLEEP(p)) {
+				p->sleep_avg = JIFFIES_TO_NS(MAX_SLEEP_AVG -
+						DEF_TIMESLICE);
+		} else {
+			/*
+			 * The lower the sleep avg a task has the more
+			 * rapidly it will rise with sleep time.
+			 */
+			sleep_time *= (MAX_BONUS - CURRENT_BONUS(p)) ? : 1;
+
+			/*
+			 * Tasks waking from uninterruptible sleep are
+			 * limited in their sleep_avg rise as they
+			 * are likely to be waiting on I/O
+			 */
+			if (p->activated == -1 && p->mm) {
+				if (p->sleep_avg >= INTERACTIVE_SLEEP(p))
+					sleep_time = 0;
+				else if (p->sleep_avg + sleep_time >=
+						INTERACTIVE_SLEEP(p)) {
+					p->sleep_avg = INTERACTIVE_SLEEP(p);
+					sleep_time = 0;
+				}
+			}
+
+			/*
+			 * This code gives a bonus to interactive tasks.
+			 *
+			 * The boost works by updating the 'average sleep time'
+			 * value here, based on ->timestamp. The more time a
+			 * task spends sleeping, the higher the average gets -
+			 * and the higher the priority boost gets as well.
+			 */
+			p->sleep_avg += sleep_time;
+
+			if (p->sleep_avg > NS_MAX_SLEEP_AVG)
+				p->sleep_avg = NS_MAX_SLEEP_AVG;
+		}
+	}
+
+	return effective_prio(p);
+}
+
+/*
+ * activate_task - move a task to the runqueue and do priority recalculation
+ *
+ * Update all the scheduling statistics stuff. (sleep average
+ * calculation, priority modifiers, etc.)
+ */
+static void activate_task(task_t *p, runqueue_t *rq, int local)
+{
+	unsigned long long now;
+
+	now = sched_clock();
+#ifdef CONFIG_SMP
+	if (!local) {
+		/* Compensate for drifting sched_clock */
+		runqueue_t *this_rq = this_rq();
+		now = (now - this_rq->timestamp_last_tick)
+			+ rq->timestamp_last_tick;
+	}
+#endif
+
+	if (!rt_task(p))
+		p->prio = recalc_task_prio(p, now);
+
+	/*
+	 * This checks to make sure it's not an uninterruptible task
+	 * that is now waking up.
+	 */
+	if (!p->activated) {
+		/*
+		 * Tasks which were woken up by interrupts (ie. hw events)
+		 * are most likely of interactive nature. So we give them
+		 * the credit of extending their sleep time to the period
+		 * of time they spend on the runqueue, waiting for execution
+		 * on a CPU, first time around:
+		 */
+		if (in_interrupt())
+			p->activated = 2;
+		else {
+			/*
+			 * Normal first-time wakeups get a credit too for
+			 * on-runqueue time, but it will be weighted down:
+			 */
+			p->activated = 1;
+		}
+	}
+	p->timestamp = now;
+
+	__activate_task(p, rq);
+}
+
+/*
+ * deactivate_task - remove a task from the runqueue.
+ */
+static void deactivate_task(struct task_struct *p, runqueue_t *rq)
+{
+	rq->nr_running--;
+	dequeue_task(p, p->array);
+	p->array = NULL;
+}
+
+/*
+ * resched_task - mark a task 'to be rescheduled now'.
+ *
+ * On UP this means the setting of the need_resched flag, on SMP it
+ * might also involve a cross-CPU call to trigger the scheduler on
+ * the target CPU.
+ */
+#ifdef CONFIG_SMP
+static void resched_task(task_t *p)
+{
+	int cpu;
+
+	assert_spin_locked(&task_rq(p)->lock);
+
+	if (unlikely(test_tsk_thread_flag(p, TIF_NEED_RESCHED)))
+		return;
+
+	set_tsk_thread_flag(p, TIF_NEED_RESCHED);
+
+	cpu = task_cpu(p);
+	if (cpu == smp_processor_id())
+		return;
+
+	/* NEED_RESCHED must be visible before we test POLLING_NRFLAG */
+	smp_mb();
+	if (!test_tsk_thread_flag(p, TIF_POLLING_NRFLAG))
+		smp_send_reschedule(cpu);
+}
+#else
+static inline void resched_task(task_t *p)
+{
+	assert_spin_locked(&task_rq(p)->lock);
+	set_tsk_need_resched(p);
+}
+#endif
+
+/**
+ * task_curr - is this task currently executing on a CPU?
+ * @p: the task in question.
+ */
+inline int task_curr(const task_t *p)
+{
+	return cpu_curr(task_cpu(p)) == p;
+}
+
+#ifdef CONFIG_SMP
+typedef struct {
+	struct list_head list;
+
+	task_t *task;
+	int dest_cpu;
+
+	struct completion done;
+} migration_req_t;
+
+/*
+ * The task's runqueue lock must be held.
+ * Returns true if you have to wait for migration thread.
+ */
+static int migrate_task(task_t *p, int dest_cpu, migration_req_t *req)
+{
+	runqueue_t *rq = task_rq(p);
+
+	/*
+	 * If the task is not on a runqueue (and not running), then
+	 * it is sufficient to simply update the task's cpu field.
+	 */
+	if (!p->array && !task_running(rq, p)) {
+		set_task_cpu(p, dest_cpu);
+		return 0;
+	}
+
+	init_completion(&req->done);
+	req->task = p;
+	req->dest_cpu = dest_cpu;
+	list_add(&req->list, &rq->migration_queue);
+	return 1;
+}
+
+/*
+ * wait_task_inactive - wait for a thread to unschedule.
+ *
+ * The caller must ensure that the task *will* unschedule sometime soon,
+ * else this function might spin for a *long* time. This function can't
+ * be called with interrupts off, or it may introduce deadlock with
+ * smp_call_function() if an IPI is sent by the same process we are
+ * waiting to become inactive.
+ */
+void wait_task_inactive(task_t *p)
+{
+	unsigned long flags;
+	runqueue_t *rq;
+	int preempted;
+
+repeat:
+	rq = task_rq_lock(p, &flags);
+	/* Must be off runqueue entirely, not preempted. */
+	if (unlikely(p->array || task_running(rq, p))) {
+		/* If it's preempted, we yield.  It could be a while. */
+		preempted = !task_running(rq, p);
+		task_rq_unlock(rq, &flags);
+		cpu_relax();
+		if (preempted)
+			yield();
+		goto repeat;
+	}
+	task_rq_unlock(rq, &flags);
+}
+
+/***
+ * kick_process - kick a running thread to enter/exit the kernel
+ * @p: the to-be-kicked thread
+ *
+ * Cause a process which is running on another CPU to enter
+ * kernel-mode, without any delay. (to get signals handled.)
+ *
+ * NOTE: this function doesnt have to take the runqueue lock,
+ * because all it wants to ensure is that the remote task enters
+ * the kernel. If the IPI races and the task has been migrated
+ * to another CPU then no harm is done and the purpose has been
+ * achieved as well.
+ */
+void kick_process(task_t *p)
+{
+	int cpu;
+
+	preempt_disable();
+	cpu = task_cpu(p);
+	if ((cpu != smp_processor_id()) && task_curr(p))
+		smp_send_reschedule(cpu);
+	preempt_enable();
+}
+
+/*
+ * Return a low guess at the load of a migration-source cpu.
+ *
+ * We want to under-estimate the load of migration sources, to
+ * balance conservatively.
+ */
+static inline unsigned long source_load(int cpu, int type)
+{
+	runqueue_t *rq = cpu_rq(cpu);
+	unsigned long load_now = rq->nr_running * SCHED_LOAD_SCALE;
+	if (type == 0)
+		return load_now;
+
+	return min(rq->cpu_load[type-1], load_now);
+}
+
+/*
+ * Return a high guess at the load of a migration-target cpu
+ */
+static inline unsigned long target_load(int cpu, int type)
+{
+	runqueue_t *rq = cpu_rq(cpu);
+	unsigned long load_now = rq->nr_running * SCHED_LOAD_SCALE;
+	if (type == 0)
+		return load_now;
+
+	return max(rq->cpu_load[type-1], load_now);
+}
+
+/*
+ * find_idlest_group finds and returns the least busy CPU group within the
+ * domain.
+ */
+static struct sched_group *
+find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
+{
+	struct sched_group *idlest = NULL, *this = NULL, *group = sd->groups;
+	unsigned long min_load = ULONG_MAX, this_load = 0;
+	int load_idx = sd->forkexec_idx;
+	int imbalance = 100 + (sd->imbalance_pct-100)/2;
+
+	do {
+		unsigned long load, avg_load;
+		int local_group;
+		int i;
+
+		/* Skip over this group if it has no CPUs allowed */
+		if (!cpus_intersects(group->cpumask, p->cpus_allowed))
+			goto nextgroup;
+
+		local_group = cpu_isset(this_cpu, group->cpumask);
+
+		/* Tally up the load of all CPUs in the group */
+		avg_load = 0;
+
+		for_each_cpu_mask(i, group->cpumask) {
+			/* Bias balancing toward cpus of our domain */
+			if (local_group)
+				load = source_load(i, load_idx);
+			else
+				load = target_load(i, load_idx);
+
+			avg_load += load;
+		}
+
+		/* Adjust by relative CPU power of the group */
+		avg_load = (avg_load * SCHED_LOAD_SCALE) / group->cpu_power;
+
+		if (local_group) {
+			this_load = avg_load;
+			this = group;
+		} else if (avg_load < min_load) {
+			min_load = avg_load;
+			idlest = group;
+		}
+nextgroup:
+		group = group->next;
+	} while (group != sd->groups);
+
+	if (!idlest || 100*this_load < imbalance*min_load)
+		return NULL;
+	return idlest;
+}
+
+/*
+ * find_idlest_queue - find the idlest runqueue among the cpus in group.
+ */
+static int
+find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
+{
+	cpumask_t tmp;
+	unsigned long load, min_load = ULONG_MAX;
+	int idlest = -1;
+	int i;
+
+	/* Traverse only the allowed CPUs */
+	cpus_and(tmp, group->cpumask, p->cpus_allowed);
+
+	for_each_cpu_mask(i, tmp) {
+		load = source_load(i, 0);
+
+		if (load < min_load || (load == min_load && i == this_cpu)) {
+			min_load = load;
+			idlest = i;
+		}
+	}
+
+	return idlest;
+}
+
+/*
+ * sched_balance_self: balance the current task (running on cpu) in domains
+ * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and
+ * SD_BALANCE_EXEC.
+ *
+ * Balance, ie. select the least loaded group.
+ *
+ * Returns the target CPU number, or the same CPU if no balancing is needed.
+ *
+ * preempt must be disabled.
+ */
+static int sched_balance_self(int cpu, int flag)
+{
+	struct task_struct *t = current;
+	struct sched_domain *tmp, *sd = NULL;
+
+	for_each_domain(cpu, tmp)
+		if (tmp->flags & flag)
+			sd = tmp;
+
+	while (sd) {
+		cpumask_t span;
+		struct sched_group *group;
+		int new_cpu;
+		int weight;
+
+		span = sd->span;
+		group = find_idlest_group(sd, t, cpu);
+		if (!group)
+			goto nextlevel;
+
+		new_cpu = find_idlest_cpu(group, t, cpu);
+		if (new_cpu == -1 || new_cpu == cpu)
+			goto nextlevel;
+
+		/* Now try balancing at a lower domain level */
+		cpu = new_cpu;
+nextlevel:
+		sd = NULL;
+		weight = cpus_weight(span);
+		for_each_domain(cpu, tmp) {
+			if (weight <= cpus_weight(tmp->span))
+				break;
+			if (tmp->flags & flag)
+				sd = tmp;
+		}
+		/* while loop will break here if sd == NULL */
+	}
+
+	return cpu;
+}
+
+#endif /* CONFIG_SMP */
+
+/*
+ * wake_idle() will wake a task on an idle cpu if task->cpu is
+ * not idle and an idle cpu is available.  The span of cpus to
+ * search starts with cpus closest then further out as needed,
+ * so we always favor a closer, idle cpu.
+ *
+ * Returns the CPU we should wake onto.
+ */
+#if defined(ARCH_HAS_SCHED_WAKE_IDLE)
+static int wake_idle(int cpu, task_t *p)
+{
+	cpumask_t tmp;
+	struct sched_domain *sd;
+	int i;
+
+	if (idle_cpu(cpu))
+		return cpu;
+
+	for_each_domain(cpu, sd) {
+		if (sd->flags & SD_WAKE_IDLE) {
+			cpus_and(tmp, sd->span, p->cpus_allowed);
+			for_each_cpu_mask(i, tmp) {
+				if (idle_cpu(i))
+					return i;
+			}
+		}
+		else
+			break;
+	}
+	return cpu;
+}
+#else
+static inline int wake_idle(int cpu, task_t *p)
+{
+	return cpu;
+}
+#endif
+
+/***
+ * try_to_wake_up - wake up a thread
+ * @p: the to-be-woken-up thread
+ * @state: the mask of task states that can be woken
+ * @sync: do a synchronous wakeup?
+ *
+ * Put it on the run-queue if it's not already there. The "current"
+ * thread is always on the run-queue (except when the actual
+ * re-schedule is in progress), and as such you're allowed to do
+ * the simpler "current->state = TASK_RUNNING" to mark yourself
+ * runnable without the overhead of this.
+ *
+ * returns failure only if the task is already active.
+ */
+static int try_to_wake_up(task_t *p, unsigned int state, int sync)
+{
+	int cpu, this_cpu, success = 0;
+	unsigned long flags;
+	long old_state;
+	runqueue_t *rq;
+#ifdef CONFIG_SMP
+	unsigned long load, this_load;
+	struct sched_domain *sd, *this_sd = NULL;
+	int new_cpu;
+#endif
+
+	rq = task_rq_lock(p, &flags);
+	old_state = p->state;
+	if (!(old_state & state))
+		goto out;
+
+	if (p->array)
+		goto out_running;
+
+	cpu = task_cpu(p);
+	this_cpu = smp_processor_id();
+
+#ifdef CONFIG_SMP
+	if (unlikely(task_running(rq, p)))
+		goto out_activate;
+
+	new_cpu = cpu;
+
+	schedstat_inc(rq, ttwu_cnt);
+	if (cpu == this_cpu) {
+		schedstat_inc(rq, ttwu_local);
+		goto out_set_cpu;
+	}
+
+	for_each_domain(this_cpu, sd) {
+		if (cpu_isset(cpu, sd->span)) {
+			schedstat_inc(sd, ttwu_wake_remote);
+			this_sd = sd;
+			break;
+		}
+	}
+
+	if (unlikely(!cpu_isset(this_cpu, p->cpus_allowed)))
+		goto out_set_cpu;
+
+	/*
+	 * Check for affine wakeup and passive balancing possibilities.
+	 */
+	if (this_sd) {
+		int idx = this_sd->wake_idx;
+		unsigned int imbalance;
+
+		imbalance = 100 + (this_sd->imbalance_pct - 100) / 2;
+
+		load = source_load(cpu, idx);
+		this_load = target_load(this_cpu, idx);
+
+		new_cpu = this_cpu; /* Wake to this CPU if we can */
+
+		if (this_sd->flags & SD_WAKE_AFFINE) {
+			unsigned long tl = this_load;
+			/*
+			 * If sync wakeup then subtract the (maximum possible)
+			 * effect of the currently running task from the load
+			 * of the current CPU:
+			 */
+			if (sync)
+				tl -= SCHED_LOAD_SCALE;
+
+			if ((tl <= load &&
+				tl + target_load(cpu, idx) <= SCHED_LOAD_SCALE) ||
+				100*(tl + SCHED_LOAD_SCALE) <= imbalance*load) {
+				/*
+				 * This domain has SD_WAKE_AFFINE and
+				 * p is cache cold in this domain, and
+				 * there is no bad imbalance.
+				 */
+				schedstat_inc(this_sd, ttwu_move_affine);
+				goto out_set_cpu;
+			}
+		}
+
+		/*
+		 * Start passive balancing when half the imbalance_pct
+		 * limit is reached.
+		 */
+		if (this_sd->flags & SD_WAKE_BALANCE) {
+			if (imbalance*this_load <= 100*load) {
+				schedstat_inc(this_sd, ttwu_move_balance);
+				goto out_set_cpu;
+			}
+		}
+	}
+
+	new_cpu = cpu; /* Could not wake to this_cpu. Wake to cpu instead */
+out_set_cpu:
+	new_cpu = wake_idle(new_cpu, p);
+	if (new_cpu != cpu) {
+		set_task_cpu(p, new_cpu);
+		task_rq_unlock(rq, &flags);
+		/* might preempt at this point */
+		rq = task_rq_lock(p, &flags);
+		old_state = p->state;
+		if (!(old_state & state))
+			goto out;
+		if (p->array)
+			goto out_running;
+
+		this_cpu = smp_processor_id();
+		cpu = task_cpu(p);
+	}
+
+out_activate:
+#endif /* CONFIG_SMP */
+	if (old_state == TASK_UNINTERRUPTIBLE) {
+		rq->nr_uninterruptible--;
+		/*
+		 * Tasks on involuntary sleep don't earn
+		 * sleep_avg beyond just interactive state.
+		 */
+		p->activated = -1;
+	}
+
+	/*
+	 * Tasks that have marked their sleep as noninteractive get
+	 * woken up without updating their sleep average. (i.e. their
+	 * sleep is handled in a priority-neutral manner, no priority
+	 * boost and no penalty.)
+	 */
+	if (old_state & TASK_NONINTERACTIVE)
+		__activate_task(p, rq);
+	else
+		activate_task(p, rq, cpu == this_cpu);
+	/*
+	 * Sync wakeups (i.e. those types of wakeups where the waker
+	 * has indicated that it will leave the CPU in short order)
+	 * don't trigger a preemption, if the woken up task will run on
+	 * this cpu. (in this case the 'I will reschedule' promise of
+	 * the waker guarantees that the freshly woken up task is going
+	 * to be considered on this CPU.)
+	 */
+	if (!sync || cpu != this_cpu) {
+		if (TASK_PREEMPTS_CURR(p, rq))
+			resched_task(rq->curr);
+	}
+	success = 1;
+
+out_running:
+	p->state = TASK_RUNNING;
+out:
+	task_rq_unlock(rq, &flags);
+
+	return success;
+}
+
+int fastcall wake_up_process(task_t *p)
+{
+	return try_to_wake_up(p, TASK_STOPPED | TASK_TRACED |
+				 TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE, 0);
+}
+
+EXPORT_SYMBOL(wake_up_process);
+
+int fastcall wake_up_state(task_t *p, unsigned int state)
+{
+	return try_to_wake_up(p, state, 0);
+}
+
+/*
+ * Perform scheduler related setup for a newly forked process p.
+ * p is forked by current.
+ */
+void fastcall sched_fork(task_t *p, int clone_flags)
+{
+	int cpu = get_cpu();
+
+#ifdef CONFIG_SMP
+	cpu = sched_balance_self(cpu, SD_BALANCE_FORK);
+#endif
+	set_task_cpu(p, cpu);
+
+	/*
+	 * We mark the process as running here, but have not actually
+	 * inserted it onto the runqueue yet. This guarantees that
+	 * nobody will actually run it, and a signal or other external
+	 * event cannot wake it up and insert it on the runqueue either.
+	 */
+	p->state = TASK_RUNNING;
+	INIT_LIST_HEAD(&p->run_list);
+	p->array = NULL;
+#ifdef CONFIG_SCHEDSTATS
+	memset(&p->sched_info, 0, sizeof(p->sched_info));
+#endif
+#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
+	p->oncpu = 0;
+#endif
+#ifdef CONFIG_PREEMPT
+	/* Want to start with kernel preemption disabled. */
+	task_thread_info(p)->preempt_count = 1;
+#endif
+	/*
+	 * Share the timeslice between parent and child, thus the
+	 * total amount of pending timeslices in the system doesn't change,
+	 * resulting in more scheduling fairness.
+	 */
+	local_irq_disable();
+	p->time_slice = (current->time_slice + 1) >> 1;
+	/*
+	 * The remainder of the first timeslice might be recovered by
+	 * the parent if the child exits early enough.
+	 */
+	p->first_time_slice = 1;
+	current->time_slice >>= 1;
+	p->timestamp = sched_clock();
+	if (unlikely(!current->time_slice)) {
+		/*
+		 * This case is rare, it happens when the parent has only
+		 * a single jiffy left from its timeslice. Taking the
+		 * runqueue lock is not a problem.
+		 */
+		current->time_slice = 1;
+		scheduler_tick();
+	}
+	local_irq_enable();
+	put_cpu();
+}
+
+/*
+ * wake_up_new_task - wake up a newly created task for the first time.
+ *
+ * This function will do some initial scheduler statistics housekeeping
+ * that must be done for every newly created context, then puts the task
+ * on the runqueue and wakes it.
+ */
+void fastcall wake_up_new_task(task_t *p, unsigned long clone_flags)
+{
+	unsigned long flags;
+	int this_cpu, cpu;
+	runqueue_t *rq, *this_rq;
+
+	rq = task_rq_lock(p, &flags);
+	BUG_ON(p->state != TASK_RUNNING);
+	this_cpu = smp_processor_id();
+	cpu = task_cpu(p);
+
+	/*
+	 * We decrease the sleep average of forking parents
+	 * and children as well, to keep max-interactive tasks
+	 * from forking tasks that are max-interactive. The parent
+	 * (current) is done further down, under its lock.
+	 */
+	p->sleep_avg = JIFFIES_TO_NS(CURRENT_BONUS(p) *
+		CHILD_PENALTY / 100 * MAX_SLEEP_AVG / MAX_BONUS);
+
+	p->prio = effective_prio(p);
+
+	if (likely(cpu == this_cpu)) {
+		if (!(clone_flags & CLONE_VM)) {
+			/*
+			 * The VM isn't cloned, so we're in a good position to
+			 * do child-runs-first in anticipation of an exec. This
+			 * usually avoids a lot of COW overhead.
+			 */
+			if (unlikely(!current->array))
+				__activate_task(p, rq);
+			else {
+				p->prio = current->prio;
+				list_add_tail(&p->run_list, &current->run_list);
+				p->array = current->array;
+				p->array->nr_active++;
+				rq->nr_running++;
+			}
+			set_need_resched();
+		} else
+			/* Run child last */
+			__activate_task(p, rq);
+		/*
+		 * We skip the following code due to cpu == this_cpu
+	 	 *
+		 *   task_rq_unlock(rq, &flags);
+		 *   this_rq = task_rq_lock(current, &flags);
+		 */
+		this_rq = rq;
+	} else {
+		this_rq = cpu_rq(this_cpu);
+
+		/*
+		 * Not the local CPU - must adjust timestamp. This should
+		 * get optimised away in the !CONFIG_SMP case.
+		 */
+		p->timestamp = (p->timestamp - this_rq->timestamp_last_tick)
+					+ rq->timestamp_last_tick;
+		__activate_task(p, rq);
+		if (TASK_PREEMPTS_CURR(p, rq))
+			resched_task(rq->curr);
+
+		/*
+		 * Parent and child are on different CPUs, now get the
+		 * parent runqueue to update the parent's ->sleep_avg:
+		 */
+		task_rq_unlock(rq, &flags);
+		this_rq = task_rq_lock(current, &flags);
+	}
+	current->sleep_avg = JIFFIES_TO_NS(CURRENT_BONUS(current) *
+		PARENT_PENALTY / 100 * MAX_SLEEP_AVG / MAX_BONUS);
+	task_rq_unlock(this_rq, &flags);
+}
+
+/*
+ * Potentially available exiting-child timeslices are
+ * retrieved here - this way the parent does not get
+ * penalized for creating too many threads.
+ *
+ * (this cannot be used to 'generate' timeslices
+ * artificially, because any timeslice recovered here
+ * was given away by the parent in the first place.)
+ */
+void fastcall sched_exit(task_t *p)
+{
+	unsigned long flags;
+	runqueue_t *rq;
+
+	/*
+	 * If the child was a (relative-) CPU hog then decrease
+	 * the sleep_avg of the parent as well.
+	 */
+	rq = task_rq_lock(p->parent, &flags);
+	if (p->first_time_slice && task_cpu(p) == task_cpu(p->parent)) {
+		p->parent->time_slice += p->time_slice;
+		if (unlikely(p->parent->time_slice > task_timeslice(p)))
+			p->parent->time_slice = task_timeslice(p);
+	}
+	if (p->sleep_avg < p->parent->sleep_avg)
+		p->parent->sleep_avg = p->parent->sleep_avg /
+		(EXIT_WEIGHT + 1) * EXIT_WEIGHT + p->sleep_avg /
+		(EXIT_WEIGHT + 1);
+	task_rq_unlock(rq, &flags);
+}
+
+/**
+ * prepare_task_switch - prepare to switch tasks
+ * @rq: the runqueue preparing to switch
+ * @next: the task we are going to switch to.
+ *
+ * This is called with the rq lock held and interrupts off. It must
+ * be paired with a subsequent finish_task_switch after the context
+ * switch.
+ *
+ * prepare_task_switch sets up locking and calls architecture specific
+ * hooks.
+ */
+static inline void prepare_task_switch(runqueue_t *rq, task_t *next)
+{
+	prepare_lock_switch(rq, next);
+	prepare_arch_switch(next);
+}
+
+/**
+ * finish_task_switch - clean up after a task-switch
+ * @rq: runqueue associated with task-switch
+ * @prev: the thread we just switched away from.
+ *
+ * finish_task_switch must be called after the context switch, paired
+ * with a prepare_task_switch call before the context switch.
+ * finish_task_switch will reconcile locking set up by prepare_task_switch,
+ * and do any other architecture-specific cleanup actions.
+ *
+ * Note that we may have delayed dropping an mm in context_switch(). If
+ * so, we finish that here outside of the runqueue lock.  (Doing it
+ * with the lock held can cause deadlocks; see schedule() for
+ * details.)
+ */
+static inline void finish_task_switch(runqueue_t *rq, task_t *prev)
+	__releases(rq->lock)
+{
+	struct mm_struct *mm = rq->prev_mm;
+	unsigned long prev_task_flags;
+
+	rq->prev_mm = NULL;
+
+	/*
+	 * A task struct has one reference for the use as "current".
+	 * If a task dies, then it sets EXIT_ZOMBIE in tsk->exit_state and
+	 * calls schedule one last time. The schedule call will never return,
+	 * and the scheduled task must drop that reference.
+	 * The test for EXIT_ZOMBIE must occur while the runqueue locks are
+	 * still held, otherwise prev could be scheduled on another cpu, die
+	 * there before we look at prev->state, and then the reference would
+	 * be dropped twice.
+	 *		Manfred Spraul <manfred@colorfullife.com>
+	 */
+	prev_task_flags = prev->flags;
+	finish_arch_switch(prev);
+	finish_lock_switch(rq, prev);
+	if (mm)
+		mmdrop(mm);
+	if (unlikely(prev_task_flags & PF_DEAD))
+		put_task_struct(prev);
+}
+
+/**
+ * schedule_tail - first thing a freshly forked thread must call.
+ * @prev: the thread we just switched away from.
+ */
+asmlinkage void schedule_tail(task_t *prev)
+	__releases(rq->lock)
+{
+	runqueue_t *rq = this_rq();
+	finish_task_switch(rq, prev);
+#ifdef __ARCH_WANT_UNLOCKED_CTXSW
+	/* In this case, finish_task_switch does not reenable preemption */
+	preempt_enable();
+#endif
+	if (current->set_child_tid)
+		put_user(current->pid, current->set_child_tid);
+}
+
+/*
+ * context_switch - switch to the new MM and the new
+ * thread's register state.
+ */
+static inline
+task_t * context_switch(runqueue_t *rq, task_t *prev, task_t *next)
+{
+	struct mm_struct *mm = next->mm;
+	struct mm_struct *oldmm = prev->active_mm;
+
+	if (unlikely(!mm)) {
+		next->active_mm = oldmm;
+		atomic_inc(&oldmm->mm_count);
+		enter_lazy_tlb(oldmm, next);
+	} else
+		switch_mm(oldmm, mm, next);
+
+	if (unlikely(!prev->mm)) {
+		prev->active_mm = NULL;
+		WARN_ON(rq->prev_mm);
+		rq->prev_mm = oldmm;
+	}
+
+	/* Here we just switch the register state and the stack. */
+	switch_to(prev, next, prev);
+
+	return prev;
+}
+
+/*
+ * nr_running, nr_uninterruptible and nr_context_switches:
+ *
+ * externally visible scheduler statistics: current number of runnable
+ * threads, current number of uninterruptible-sleeping threads, total
+ * number of context switches performed since bootup.
+ */
+unsigned long nr_running(void)
+{
+	unsigned long i, sum = 0;
+
+	for_each_online_cpu(i)
+		sum += cpu_rq(i)->nr_running;
+
+	return sum;
+}
+
+unsigned long nr_uninterruptible(void)
+{
+	unsigned long i, sum = 0;
+
+	for_each_cpu(i)
+		sum += cpu_rq(i)->nr_uninterruptible;
+
+	/*
+	 * Since we read the counters lockless, it might be slightly
+	 * inaccurate. Do not allow it to go below zero though:
+	 */
+	if (unlikely((long)sum < 0))
+		sum = 0;
+
+	return sum;
+}
+
+unsigned long long nr_context_switches(void)
+{
+	unsigned long long i, sum = 0;
+
+	for_each_cpu(i)
+		sum += cpu_rq(i)->nr_switches;
+
+	return sum;
+}
+
+unsigned long nr_iowait(void)
+{
+	unsigned long i, sum = 0;
+
+	for_each_cpu(i)
+		sum += atomic_read(&cpu_rq(i)->nr_iowait);
+
+	return sum;
+}
+
+#ifdef CONFIG_SMP
+
+/*
+ * double_rq_lock - safely lock two runqueues
+ *
+ * Note this does not disable interrupts like task_rq_lock,
+ * you need to do so manually before calling.
+ */
+static void double_rq_lock(runqueue_t *rq1, runqueue_t *rq2)
+	__acquires(rq1->lock)
+	__acquires(rq2->lock)
+{
+	if (rq1 == rq2) {
+		spin_lock(&rq1->lock);
+		__acquire(rq2->lock);	/* Fake it out ;) */
+	} else {
+		if (rq1 < rq2) {
+			spin_lock(&rq1->lock);
+			spin_lock(&rq2->lock);
+		} else {
+			spin_lock(&rq2->lock);
+			spin_lock(&rq1->lock);
+		}
+	}
+}
+
+/*
+ * double_rq_unlock - safely unlock two runqueues
+ *
+ * Note this does not restore interrupts like task_rq_unlock,
+ * you need to do so manually after calling.
+ */
+static void double_rq_unlock(runqueue_t *rq1, runqueue_t *rq2)
+	__releases(rq1->lock)
+	__releases(rq2->lock)
+{
+	spin_unlock(&rq1->lock);
+	if (rq1 != rq2)
+		spin_unlock(&rq2->lock);
+	else
+		__release(rq2->lock);
+}
+
+/*
+ * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
+ */
+static void double_lock_balance(runqueue_t *this_rq, runqueue_t *busiest)
+	__releases(this_rq->lock)
+	__acquires(busiest->lock)
+	__acquires(this_rq->lock)
+{
+	if (unlikely(!spin_trylock(&busiest->lock))) {
+		if (busiest < this_rq) {
+			spin_unlock(&this_rq->lock);
+			spin_lock(&busiest->lock);
+			spin_lock(&this_rq->lock);
+		} else
+			spin_lock(&busiest->lock);
+	}
+}
+
+/*
+ * If dest_cpu is allowed for this process, migrate the task to it.
+ * This is accomplished by forcing the cpu_allowed mask to only
+ * allow dest_cpu, which will force the cpu onto dest_cpu.  Then
+ * the cpu_allowed mask is restored.
+ */
+static void sched_migrate_task(task_t *p, int dest_cpu)
+{
+	migration_req_t req;
+	runqueue_t *rq;
+	unsigned long flags;
+
+	rq = task_rq_lock(p, &flags);
+	if (!cpu_isset(dest_cpu, p->cpus_allowed)
+	    || unlikely(cpu_is_offline(dest_cpu)))
+		goto out;
+
+	/* force the process onto the specified CPU */
+	if (migrate_task(p, dest_cpu, &req)) {
+		/* Need to wait for migration thread (might exit: take ref). */
+		struct task_struct *mt = rq->migration_thread;
+		get_task_struct(mt);
+		task_rq_unlock(rq, &flags);
+		wake_up_process(mt);
+		put_task_struct(mt);
+		wait_for_completion(&req.done);
+		return;
+	}
+out:
+	task_rq_unlock(rq, &flags);
+}
+
+/*
+ * sched_exec - execve() is a valuable balancing opportunity, because at
+ * this point the task has the smallest effective memory and cache footprint.
+ */
+void sched_exec(void)
+{
+	int new_cpu, this_cpu = get_cpu();
+	new_cpu = sched_balance_self(this_cpu, SD_BALANCE_EXEC);
+	put_cpu();
+	if (new_cpu != this_cpu)
+		sched_migrate_task(current, new_cpu);
+}
+
+/*
+ * pull_task - move a task from a remote runqueue to the local runqueue.
+ * Both runqueues must be locked.
+ */
+static
+void pull_task(runqueue_t *src_rq, prio_array_t *src_array, task_t *p,
+	       runqueue_t *this_rq, prio_array_t *this_array, int this_cpu)
+{
+	dequeue_task(p, src_array);
+	src_rq->nr_running--;
+	set_task_cpu(p, this_cpu);
+	this_rq->nr_running++;
+	enqueue_task(p, this_array);
+	p->timestamp = (p->timestamp - src_rq->timestamp_last_tick)
+				+ this_rq->timestamp_last_tick;
+	/*
+	 * Note that idle threads have a prio of MAX_PRIO, for this test
+	 * to be always true for them.
+	 */
+	if (TASK_PREEMPTS_CURR(p, this_rq))
+		resched_task(this_rq->curr);
+}
+
+/*
+ * can_migrate_task - may task p from runqueue rq be migrated to this_cpu?
+ */
+static
+int can_migrate_task(task_t *p, runqueue_t *rq, int this_cpu,
+		     struct sched_domain *sd, enum idle_type idle,
+		     int *all_pinned)
+{
+	/*
+	 * We do not migrate tasks that are:
+	 * 1) running (obviously), or
+	 * 2) cannot be migrated to this CPU due to cpus_allowed, or
+	 * 3) are cache-hot on their current CPU.
+	 */
+	if (!cpu_isset(this_cpu, p->cpus_allowed))
+		return 0;
+	*all_pinned = 0;
+
+	if (task_running(rq, p))
+		return 0;
+
+	/*
+	 * Aggressive migration if:
+	 * 1) task is cache cold, or
+	 * 2) too many balance attempts have failed.
+	 */
+
+	if (sd->nr_balance_failed > sd->cache_nice_tries)
+		return 1;
+
+	if (task_hot(p, rq->timestamp_last_tick, sd))
+		return 0;
+	return 1;
+}
+
+/*
+ * move_tasks tries to move up to max_nr_move tasks from busiest to this_rq,
+ * as part of a balancing operation within "domain". Returns the number of
+ * tasks moved.
+ *
+ * Called with both runqueues locked.
+ */
+static int move_tasks(runqueue_t *this_rq, int this_cpu, runqueue_t *busiest,
+		      unsigned long max_nr_move, struct sched_domain *sd,
+		      enum idle_type idle, int *all_pinned)
+{
+	prio_array_t *array, *dst_array;
+	struct list_head *head, *curr;
+	int idx, pulled = 0, pinned = 0;
+	task_t *tmp;
+
+	if (max_nr_move == 0)
+		goto out;
+
+	pinned = 1;
+
+	/*
+	 * We first consider expired tasks. Those will likely not be
+	 * executed in the near future, and they are most likely to
+	 * be cache-cold, thus switching CPUs has the least effect
+	 * on them.
+	 */
+	if (busiest->expired->nr_active) {
+		array = busiest->expired;
+		dst_array = this_rq->expired;
+	} else {
+		array = busiest->active;
+		dst_array = this_rq->active;
+	}
+
+new_array:
+	/* Start searching at priority 0: */
+	idx = 0;
+skip_bitmap:
+	if (!idx)
+		idx = sched_find_first_bit(array->bitmap);
+	else
+		idx = find_next_bit(array->bitmap, MAX_PRIO, idx);
+	if (idx >= MAX_PRIO) {
+		if (array == busiest->expired && busiest->active->nr_active) {
+			array = busiest->active;
+			dst_array = this_rq->active;
+			goto new_array;
+		}
+		goto out;
+	}
+
+	head = array->queue + idx;
+	curr = head->prev;
+skip_queue:
+	tmp = list_entry(curr, task_t, run_list);
+
+	curr = curr->prev;
+
+	if (!can_migrate_task(tmp, busiest, this_cpu, sd, idle, &pinned)) {
+		if (curr != head)
+			goto skip_queue;
+		idx++;
+		goto skip_bitmap;
+	}
+
+#ifdef CONFIG_SCHEDSTATS
+	if (task_hot(tmp, busiest->timestamp_last_tick, sd))
+		schedstat_inc(sd, lb_hot_gained[idle]);
+#endif
+
+	pull_task(busiest, array, tmp, this_rq, dst_array, this_cpu);
+	pulled++;
+
+	/* We only want to steal up to the prescribed number of tasks. */
+	if (pulled < max_nr_move) {
+		if (curr != head)
+			goto skip_queue;
+		idx++;
+		goto skip_bitmap;
+	}
+out:
+	/*
+	 * Right now, this is the only place pull_task() is called,
+	 * so we can safely collect pull_task() stats here rather than
+	 * inside pull_task().
+	 */
+	schedstat_add(sd, lb_gained[idle], pulled);
+
+	if (all_pinned)
+		*all_pinned = pinned;
+	return pulled;
+}
+
+/*
+ * find_busiest_group finds and returns the busiest CPU group within the
+ * domain. It calculates and returns the number of tasks which should be
+ * moved to restore balance via the imbalance parameter.
+ */
+static struct sched_group *
+find_busiest_group(struct sched_domain *sd, int this_cpu,
+		   unsigned long *imbalance, enum idle_type idle, int *sd_idle)
+{
+	struct sched_group *busiest = NULL, *this = NULL, *group = sd->groups;
+	unsigned long max_load, avg_load, total_load, this_load, total_pwr;
+	unsigned long max_pull;
+	int load_idx;
+
+	max_load = this_load = total_load = total_pwr = 0;
+	if (idle == NOT_IDLE)
+		load_idx = sd->busy_idx;
+	else if (idle == NEWLY_IDLE)
+		load_idx = sd->newidle_idx;
+	else
+		load_idx = sd->idle_idx;
+
+	do {
+		unsigned long load;
+		int local_group;
+		int i;
+
+		local_group = cpu_isset(this_cpu, group->cpumask);
+
+		/* Tally up the load of all CPUs in the group */
+		avg_load = 0;
+
+		for_each_cpu_mask(i, group->cpumask) {
+			if (*sd_idle && !idle_cpu(i))
+				*sd_idle = 0;
+
+			/* Bias balancing toward cpus of our domain */
+			if (local_group)
+				load = target_load(i, load_idx);
+			else
+				load = source_load(i, load_idx);
+
+			avg_load += load;
+		}
+
+		total_load += avg_load;
+		total_pwr += group->cpu_power;
+
+		/* Adjust by relative CPU power of the group */
+		avg_load = (avg_load * SCHED_LOAD_SCALE) / group->cpu_power;
+
+		if (local_group) {
+			this_load = avg_load;
+			this = group;
+		} else if (avg_load > max_load) {
+			max_load = avg_load;
+			busiest = group;
+		}
+		group = group->next;
+	} while (group != sd->groups);
+
+	if (!busiest || this_load >= max_load || max_load <= SCHED_LOAD_SCALE)
+		goto out_balanced;
+
+	avg_load = (SCHED_LOAD_SCALE * total_load) / total_pwr;
+
+	if (this_load >= avg_load ||
+			100*max_load <= sd->imbalance_pct*this_load)
+		goto out_balanced;
+
+	/*
+	 * We're trying to get all the cpus to the average_load, so we don't
+	 * want to push ourselves above the average load, nor do we wish to
+	 * reduce the max loaded cpu below the average load, as either of these
+	 * actions would just result in more rebalancing later, and ping-pong
+	 * tasks around. Thus we look for the minimum possible imbalance.
+	 * Negative imbalances (*we* are more loaded than anyone else) will
+	 * be counted as no imbalance for these purposes -- we can't fix that
+	 * by pulling tasks to us.  Be careful of negative numbers as they'll
+	 * appear as very large values with unsigned longs.
+	 */
+
+	/* Don't want to pull so many tasks that a group would go idle */
+	max_pull = min(max_load - avg_load, max_load - SCHED_LOAD_SCALE);
+
+	/* How much load to actually move to equalise the imbalance */
+	*imbalance = min(max_pull * busiest->cpu_power,
+				(avg_load - this_load) * this->cpu_power)
+			/ SCHED_LOAD_SCALE;
+
+	if (*imbalance < SCHED_LOAD_SCALE) {
+		unsigned long pwr_now = 0, pwr_move = 0;
+		unsigned long tmp;
+
+		if (max_load - this_load >= SCHED_LOAD_SCALE*2) {
+			*imbalance = 1;
+			return busiest;
+		}
+
+		/*
+		 * OK, we don't have enough imbalance to justify moving tasks,
+		 * however we may be able to increase total CPU power used by
+		 * moving them.
+		 */
+
+		pwr_now += busiest->cpu_power*min(SCHED_LOAD_SCALE, max_load);
+		pwr_now += this->cpu_power*min(SCHED_LOAD_SCALE, this_load);
+		pwr_now /= SCHED_LOAD_SCALE;
+
+		/* Amount of load we'd subtract */
+		tmp = SCHED_LOAD_SCALE*SCHED_LOAD_SCALE/busiest->cpu_power;
+		if (max_load > tmp)
+			pwr_move += busiest->cpu_power*min(SCHED_LOAD_SCALE,
+							max_load - tmp);
+
+		/* Amount of load we'd add */
+		if (max_load*busiest->cpu_power <
+				SCHED_LOAD_SCALE*SCHED_LOAD_SCALE)
+			tmp = max_load*busiest->cpu_power/this->cpu_power;
+		else
+			tmp = SCHED_LOAD_SCALE*SCHED_LOAD_SCALE/this->cpu_power;
+		pwr_move += this->cpu_power*min(SCHED_LOAD_SCALE, this_load + tmp);
+		pwr_move /= SCHED_LOAD_SCALE;
+
+		/* Move if we gain throughput */
+		if (pwr_move <= pwr_now)
+			goto out_balanced;
+
+		*imbalance = 1;
+		return busiest;
+	}
+
+	/* Get rid of the scaling factor, rounding down as we divide */
+	*imbalance = *imbalance / SCHED_LOAD_SCALE;
+	return busiest;
+
+out_balanced:
+
+	*imbalance = 0;
+	return NULL;
+}
+
+/*
+ * find_busiest_queue - find the busiest runqueue among the cpus in group.
+ */
+static runqueue_t *find_busiest_queue(struct sched_group *group,
+	enum idle_type idle)
+{
+	unsigned long load, max_load = 0;
+	runqueue_t *busiest = NULL;
+	int i;
+
+	for_each_cpu_mask(i, group->cpumask) {
+		load = source_load(i, 0);
+
+		if (load > max_load) {
+			max_load = load;
+			busiest = cpu_rq(i);
+		}
+	}
+
+	return busiest;
+}
+
+/*
+ * Max backoff if we encounter pinned tasks. Pretty arbitrary value, but
+ * so long as it is large enough.
+ */
+#define MAX_PINNED_INTERVAL	512
+
+/*
+ * Check this_cpu to ensure it is balanced within domain. Attempt to move
+ * tasks if there is an imbalance.
+ *
+ * Called with this_rq unlocked.
+ */
+static int load_balance(int this_cpu, runqueue_t *this_rq,
+			struct sched_domain *sd, enum idle_type idle)
+{
+	struct sched_group *group;
+	runqueue_t *busiest;
+	unsigned long imbalance;
+	int nr_moved, all_pinned = 0;
+	int active_balance = 0;
+	int sd_idle = 0;
+
+	if (idle != NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER)
+		sd_idle = 1;
+
+	schedstat_inc(sd, lb_cnt[idle]);
+
+	group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle);
+	if (!group) {
+		schedstat_inc(sd, lb_nobusyg[idle]);
+		goto out_balanced;
+	}
+
+	busiest = find_busiest_queue(group, idle);
+	if (!busiest) {
+		schedstat_inc(sd, lb_nobusyq[idle]);
+		goto out_balanced;
+	}
+
+	BUG_ON(busiest == this_rq);
+
+	schedstat_add(sd, lb_imbalance[idle], imbalance);
+
+	nr_moved = 0;
+	if (busiest->nr_running > 1) {
+		/*
+		 * Attempt to move tasks. If find_busiest_group has found
+		 * an imbalance but busiest->nr_running <= 1, the group is
+		 * still unbalanced. nr_moved simply stays zero, so it is
+		 * correctly treated as an imbalance.
+		 */
+		double_rq_lock(this_rq, busiest);
+		nr_moved = move_tasks(this_rq, this_cpu, busiest,
+					imbalance, sd, idle, &all_pinned);
+		double_rq_unlock(this_rq, busiest);
+
+		/* All tasks on this runqueue were pinned by CPU affinity */
+		if (unlikely(all_pinned))
+			goto out_balanced;
+	}
+
+	if (!nr_moved) {
+		schedstat_inc(sd, lb_failed[idle]);
+		sd->nr_balance_failed++;
+
+		if (unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2)) {
+
+			spin_lock(&busiest->lock);
+
+			/* don't kick the migration_thread, if the curr
+			 * task on busiest cpu can't be moved to this_cpu
+			 */
+			if (!cpu_isset(this_cpu, busiest->curr->cpus_allowed)) {
+				spin_unlock(&busiest->lock);
+				all_pinned = 1;
+				goto out_one_pinned;
+			}
+
+			if (!busiest->active_balance) {
+				busiest->active_balance = 1;
+				busiest->push_cpu = this_cpu;
+				active_balance = 1;
+			}
+			spin_unlock(&busiest->lock);
+			if (active_balance)
+				wake_up_process(busiest->migration_thread);
+
+			/*
+			 * We've kicked active balancing, reset the failure
+			 * counter.
+			 */
+			sd->nr_balance_failed = sd->cache_nice_tries+1;
+		}
+	} else
+		sd->nr_balance_failed = 0;
+
+	if (likely(!active_balance)) {
+		/* We were unbalanced, so reset the balancing interval */
+		sd->balance_interval = sd->min_interval;
+	} else {
+		/*
+		 * If we've begun active balancing, start to back off. This
+		 * case may not be covered by the all_pinned logic if there
+		 * is only 1 task on the busy runqueue (because we don't call
+		 * move_tasks).
+		 */
+		if (sd->balance_interval < sd->max_interval)
+			sd->balance_interval *= 2;
+	}
+
+	if (!nr_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER)
+		return -1;
+	return nr_moved;
+
+out_balanced:
+	schedstat_inc(sd, lb_balanced[idle]);
+
+	sd->nr_balance_failed = 0;
+
+out_one_pinned:
+	/* tune up the balancing interval */
+	if ((all_pinned && sd->balance_interval < MAX_PINNED_INTERVAL) ||
+			(sd->balance_interval < sd->max_interval))
+		sd->balance_interval *= 2;
+
+	if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER)
+		return -1;
+	return 0;
+}
+
+/*
+ * Check this_cpu to ensure it is balanced within domain. Attempt to move
+ * tasks if there is an imbalance.
+ *
+ * Called from schedule when this_rq is about to become idle (NEWLY_IDLE).
+ * this_rq is locked.
+ */
+static int load_balance_newidle(int this_cpu, runqueue_t *this_rq,
+				struct sched_domain *sd)
+{
+	struct sched_group *group;
+	runqueue_t *busiest = NULL;
+	unsigned long imbalance;
+	int nr_moved = 0;
+	int sd_idle = 0;
+
+	if (sd->flags & SD_SHARE_CPUPOWER)
+		sd_idle = 1;
+
+	schedstat_inc(sd, lb_cnt[NEWLY_IDLE]);
+	group = find_busiest_group(sd, this_cpu, &imbalance, NEWLY_IDLE, &sd_idle);
+	if (!group) {
+		schedstat_inc(sd, lb_nobusyg[NEWLY_IDLE]);
+		goto out_balanced;
+	}
+
+	busiest = find_busiest_queue(group, NEWLY_IDLE);
+	if (!busiest) {
+		schedstat_inc(sd, lb_nobusyq[NEWLY_IDLE]);
+		goto out_balanced;
+	}
+
+	BUG_ON(busiest == this_rq);
+
+	schedstat_add(sd, lb_imbalance[NEWLY_IDLE], imbalance);
+
+	nr_moved = 0;
+	if (busiest->nr_running > 1) {
+		/* Attempt to move tasks */
+		double_lock_balance(this_rq, busiest);
+		nr_moved = move_tasks(this_rq, this_cpu, busiest,
+					imbalance, sd, NEWLY_IDLE, NULL);
+		spin_unlock(&busiest->lock);
+	}
+
+	if (!nr_moved) {
+		schedstat_inc(sd, lb_failed[NEWLY_IDLE]);
+		if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER)
+			return -1;
+	} else
+		sd->nr_balance_failed = 0;
+
+	return nr_moved;
+
+out_balanced:
+	schedstat_inc(sd, lb_balanced[NEWLY_IDLE]);
+	if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER)
+		return -1;
+	sd->nr_balance_failed = 0;
+	return 0;
+}
+
+/*
+ * idle_balance is called by schedule() if this_cpu is about to become
+ * idle. Attempts to pull tasks from other CPUs.
+ */
+static void idle_balance(int this_cpu, runqueue_t *this_rq)
+{
+	struct sched_domain *sd;
+
+	for_each_domain(this_cpu, sd) {
+		if (sd->flags & SD_BALANCE_NEWIDLE) {
+			if (load_balance_newidle(this_cpu, this_rq, sd)) {
+				/* We've pulled tasks over so stop searching */
+				break;
+			}
+		}
+	}
+}
+
+/*
+ * active_load_balance is run by migration threads. It pushes running tasks
+ * off the busiest CPU onto idle CPUs. It requires at least 1 task to be
+ * running on each physical CPU where possible, and avoids physical /
+ * logical imbalances.
+ *
+ * Called with busiest_rq locked.
+ */
+static void active_load_balance(runqueue_t *busiest_rq, int busiest_cpu)
+{
+	struct sched_domain *sd;
+	runqueue_t *target_rq;
+	int target_cpu = busiest_rq->push_cpu;
+
+	if (busiest_rq->nr_running <= 1)
+		/* no task to move */
+		return;
+
+	target_rq = cpu_rq(target_cpu);
+
+	/*
+	 * This condition is "impossible", if it occurs
+	 * we need to fix it.  Originally reported by
+	 * Bjorn Helgaas on a 128-cpu setup.
+	 */
+	BUG_ON(busiest_rq == target_rq);
+
+	/* move a task from busiest_rq to target_rq */
+	double_lock_balance(busiest_rq, target_rq);
+
+	/* Search for an sd spanning us and the target CPU. */
+	for_each_domain(target_cpu, sd)
+		if ((sd->flags & SD_LOAD_BALANCE) &&
+			cpu_isset(busiest_cpu, sd->span))
+				break;
+
+	if (unlikely(sd == NULL))
+		goto out;
+
+	schedstat_inc(sd, alb_cnt);
+
+	if (move_tasks(target_rq, target_cpu, busiest_rq, 1, sd, SCHED_IDLE, NULL))
+		schedstat_inc(sd, alb_pushed);
+	else
+		schedstat_inc(sd, alb_failed);
+out:
+	spin_unlock(&target_rq->lock);
+}
+
+/*
+ * rebalance_tick will get called every timer tick, on every CPU.
+ *
+ * It checks each scheduling domain to see if it is due to be balanced,
+ * and initiates a balancing operation if so.
+ *
+ * Balancing parameters are set up in arch_init_sched_domains.
+ */
+
+/* Don't have all balancing operations going off at once */
+#define CPU_OFFSET(cpu) (HZ * cpu / NR_CPUS)
+
+static void rebalance_tick(int this_cpu, runqueue_t *this_rq,
+			   enum idle_type idle)
+{
+	unsigned long old_load, this_load;
+	unsigned long j = jiffies + CPU_OFFSET(this_cpu);
+	struct sched_domain *sd;
+	int i;
+
+	this_load = this_rq->nr_running * SCHED_LOAD_SCALE;
+	/* Update our load */
+	for (i = 0; i < 3; i++) {
+		unsigned long new_load = this_load;
+		int scale = 1 << i;
+		old_load = this_rq->cpu_load[i];
+		/*
+		 * Round up the averaging division if load is increasing. This
+		 * prevents us from getting stuck on 9 if the load is 10, for
+		 * example.
+		 */
+		if (new_load > old_load)
+			new_load += scale-1;
+		this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) / scale;
+	}
+
+	for_each_domain(this_cpu, sd) {
+		unsigned long interval;
+
+		if (!(sd->flags & SD_LOAD_BALANCE))
+			continue;
+
+		interval = sd->balance_interval;
+		if (idle != SCHED_IDLE)
+			interval *= sd->busy_factor;
+
+		/* scale ms to jiffies */
+		interval = msecs_to_jiffies(interval);
+		if (unlikely(!interval))
+			interval = 1;
+
+		if (j - sd->last_balance >= interval) {
+			if (load_balance(this_cpu, this_rq, sd, idle)) {
+				/*
+				 * We've pulled tasks over so either we're no
+				 * longer idle, or one of our SMT siblings is
+				 * not idle.
+				 */
+				idle = NOT_IDLE;
+			}
+			sd->last_balance += interval;
+		}
+	}
+}
+#else
+/*
+ * on UP we do not need to balance between CPUs:
+ */
+static inline void rebalance_tick(int cpu, runqueue_t *rq, enum idle_type idle)
+{
+}
+static inline void idle_balance(int cpu, runqueue_t *rq)
+{
+}
+#endif
+
+static inline int wake_priority_sleeper(runqueue_t *rq)
+{
+	int ret = 0;
+#ifdef CONFIG_SCHED_SMT
+	spin_lock(&rq->lock);
+	/*
+	 * If an SMT sibling task has been put to sleep for priority
+	 * reasons reschedule the idle task to see if it can now run.
+	 */
+	if (rq->nr_running) {
+		resched_task(rq->idle);
+		ret = 1;
+	}
+	spin_unlock(&rq->lock);
+#endif
+	return ret;
+}
+
+DEFINE_PER_CPU(struct kernel_stat, kstat);
+
+EXPORT_PER_CPU_SYMBOL(kstat);
+
+/*
+ * This is called on clock ticks and on context switches.
+ * Bank in p->sched_time the ns elapsed since the last tick or switch.
+ */
+static inline void update_cpu_clock(task_t *p, runqueue_t *rq,
+				    unsigned long long now)
+{
+	unsigned long long last = max(p->timestamp, rq->timestamp_last_tick);
+	p->sched_time += now - last;
+}
+
+/*
+ * Return current->sched_time plus any more ns on the sched_clock
+ * that have not yet been banked.
+ */
+unsigned long long current_sched_time(const task_t *tsk)
+{
+	unsigned long long ns;
+	unsigned long flags;
+	local_irq_save(flags);
+	ns = max(tsk->timestamp, task_rq(tsk)->timestamp_last_tick);
+	ns = tsk->sched_time + (sched_clock() - ns);
+	local_irq_restore(flags);
+	return ns;
+}
+
+/*
+ * We place interactive tasks back into the active array, if possible.
+ *
+ * To guarantee that this does not starve expired tasks we ignore the
+ * interactivity of a task if the first expired task had to wait more
+ * than a 'reasonable' amount of time. This deadline timeout is
+ * load-dependent, as the frequency of array switched decreases with
+ * increasing number of running tasks. We also ignore the interactivity
+ * if a better static_prio task has expired:
+ */
+#define EXPIRED_STARVING(rq) \
+	((STARVATION_LIMIT && ((rq)->expired_timestamp && \
+		(jiffies - (rq)->expired_timestamp >= \
+			STARVATION_LIMIT * ((rq)->nr_running) + 1))) || \
+			((rq)->curr->static_prio > (rq)->best_expired_prio))
+
+/*
+ * Account user cpu time to a process.
+ * @p: the process that the cpu time gets accounted to
+ * @hardirq_offset: the offset to subtract from hardirq_count()
+ * @cputime: the cpu time spent in user space since the last update
+ */
+void account_user_time(struct task_struct *p, cputime_t cputime)
+{
+	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+	cputime64_t tmp;
+
+	p->utime = cputime_add(p->utime, cputime);
+
+	/* Add user time to cpustat. */
+	tmp = cputime_to_cputime64(cputime);
+	if (TASK_NICE(p) > 0)
+		cpustat->nice = cputime64_add(cpustat->nice, tmp);
+	else
+		cpustat->user = cputime64_add(cpustat->user, tmp);
+}
+
+/*
+ * Account system cpu time to a process.
+ * @p: the process that the cpu time gets accounted to
+ * @hardirq_offset: the offset to subtract from hardirq_count()
+ * @cputime: the cpu time spent in kernel space since the last update
+ */
+void account_system_time(struct task_struct *p, int hardirq_offset,
+			 cputime_t cputime)
+{
+	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+	runqueue_t *rq = this_rq();
+	cputime64_t tmp;
+
+	p->stime = cputime_add(p->stime, cputime);
+
+	/* Add system time to cpustat. */
+	tmp = cputime_to_cputime64(cputime);
+	if (hardirq_count() - hardirq_offset)
+		cpustat->irq = cputime64_add(cpustat->irq, tmp);
+	else if (softirq_count())
+		cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
+	else if (p != rq->idle)
+		cpustat->system = cputime64_add(cpustat->system, tmp);
+	else if (atomic_read(&rq->nr_iowait) > 0)
+		cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
+	else
+		cpustat->idle = cputime64_add(cpustat->idle, tmp);
+	/* Account for system time used */
+	acct_update_integrals(p);
+}
+
+/*
+ * Account for involuntary wait time.
+ * @p: the process from which the cpu time has been stolen
+ * @steal: the cpu time spent in involuntary wait
+ */
+void account_steal_time(struct task_struct *p, cputime_t steal)
+{
+	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+	cputime64_t tmp = cputime_to_cputime64(steal);
+	runqueue_t *rq = this_rq();
+
+	if (p == rq->idle) {
+		p->stime = cputime_add(p->stime, steal);
+		if (atomic_read(&rq->nr_iowait) > 0)
+			cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
+		else
+			cpustat->idle = cputime64_add(cpustat->idle, tmp);
+	} else
+		cpustat->steal = cputime64_add(cpustat->steal, tmp);
+}
+
+/*
+ * This function gets called by the timer code, with HZ frequency.
+ * We call it with interrupts disabled.
+ *
+ * It also gets called by the fork code, when changing the parent's
+ * timeslices.
+ */
+void scheduler_tick(void)
+{
+	int cpu = smp_processor_id();
+	runqueue_t *rq = this_rq();
+	task_t *p = current;
+	unsigned long long now = sched_clock();
+
+	update_cpu_clock(p, rq, now);
+
+	rq->timestamp_last_tick = now;
+
+	if (p == rq->idle) {
+		if (wake_priority_sleeper(rq))
+			goto out;
+		rebalance_tick(cpu, rq, SCHED_IDLE);
+		return;
+	}
+
+	/* Task might have expired already, but not scheduled off yet */
+	if (p->array != rq->active) {
+		set_tsk_need_resched(p);
+		goto out;
+	}
+	spin_lock(&rq->lock);
+	/*
+	 * The task was running during this tick - update the
+	 * time slice counter. Note: we do not update a thread's
+	 * priority until it either goes to sleep or uses up its
+	 * timeslice. This makes it possible for interactive tasks
+	 * to use up their timeslices at their highest priority levels.
+	 */
+	if (rt_task(p)) {
+		/*
+		 * RR tasks need a special form of timeslice management.
+		 * FIFO tasks have no timeslices.
+		 */
+		if ((p->policy == SCHED_RR) && !--p->time_slice) {
+			p->time_slice = task_timeslice(p);
+			p->first_time_slice = 0;
+			set_tsk_need_resched(p);
+
+			/* put it at the end of the queue: */
+			requeue_task(p, rq->active);
+		}
+		goto out_unlock;
+	}
+	if (!--p->time_slice) {
+		dequeue_task(p, rq->active);
+		set_tsk_need_resched(p);
+		p->prio = effective_prio(p);
+		p->time_slice = task_timeslice(p);
+		p->first_time_slice = 0;
+
+		if (!rq->expired_timestamp)
+			rq->expired_timestamp = jiffies;
+		if (!TASK_INTERACTIVE(p) || EXPIRED_STARVING(rq)) {
+			enqueue_task(p, rq->expired);
+			if (p->static_prio < rq->best_expired_prio)
+				rq->best_expired_prio = p->static_prio;
+		} else
+			enqueue_task(p, rq->active);
+	} else {
+		/*
+		 * Prevent a too long timeslice allowing a task to monopolize
+		 * the CPU. We do this by splitting up the timeslice into
+		 * smaller pieces.
+		 *
+		 * Note: this does not mean the task's timeslices expire or
+		 * get lost in any way, they just might be preempted by
+		 * another task of equal priority. (one with higher
+		 * priority would have preempted this task already.) We
+		 * requeue this task to the end of the list on this priority
+		 * level, which is in essence a round-robin of tasks with
+		 * equal priority.
+		 *
+		 * This only applies to tasks in the interactive
+		 * delta range with at least TIMESLICE_GRANULARITY to requeue.
+		 */
+		if (TASK_INTERACTIVE(p) && !((task_timeslice(p) -
+			p->time_slice) % TIMESLICE_GRANULARITY(p)) &&
+			(p->time_slice >= TIMESLICE_GRANULARITY(p)) &&
+			(p->array == rq->active)) {
+
+			requeue_task(p, rq->active);
+			set_tsk_need_resched(p);
+		}
+	}
+out_unlock:
+	spin_unlock(&rq->lock);
+out:
+	rebalance_tick(cpu, rq, NOT_IDLE);
+}
+
+#ifdef CONFIG_SCHED_SMT
+static inline void wakeup_busy_runqueue(runqueue_t *rq)
+{
+	/* If an SMT runqueue is sleeping due to priority reasons wake it up */
+	if (rq->curr == rq->idle && rq->nr_running)
+		resched_task(rq->idle);
+}
+
+static void wake_sleeping_dependent(int this_cpu, runqueue_t *this_rq)
+{
+	struct sched_domain *tmp, *sd = NULL;
+	cpumask_t sibling_map;
+	int i;
+
+	for_each_domain(this_cpu, tmp)
+		if (tmp->flags & SD_SHARE_CPUPOWER)
+			sd = tmp;
+
+	if (!sd)
+		return;
+
+	/*
+	 * Unlock the current runqueue because we have to lock in
+	 * CPU order to avoid deadlocks. Caller knows that we might
+	 * unlock. We keep IRQs disabled.
+	 */
+	spin_unlock(&this_rq->lock);
+
+	sibling_map = sd->span;
+
+	for_each_cpu_mask(i, sibling_map)
+		spin_lock(&cpu_rq(i)->lock);
+	/*
+	 * We clear this CPU from the mask. This both simplifies the
+	 * inner loop and keps this_rq locked when we exit:
+	 */
+	cpu_clear(this_cpu, sibling_map);
+
+	for_each_cpu_mask(i, sibling_map) {
+		runqueue_t *smt_rq = cpu_rq(i);
+
+		wakeup_busy_runqueue(smt_rq);
+	}
+
+	for_each_cpu_mask(i, sibling_map)
+		spin_unlock(&cpu_rq(i)->lock);
+	/*
+	 * We exit with this_cpu's rq still held and IRQs
+	 * still disabled:
+	 */
+}
+
+/*
+ * number of 'lost' timeslices this task wont be able to fully
+ * utilize, if another task runs on a sibling. This models the
+ * slowdown effect of other tasks running on siblings:
+ */
+static inline unsigned long smt_slice(task_t *p, struct sched_domain *sd)
+{
+	return p->time_slice * (100 - sd->per_cpu_gain) / 100;
+}
+
+static int dependent_sleeper(int this_cpu, runqueue_t *this_rq)
+{
+	struct sched_domain *tmp, *sd = NULL;
+	cpumask_t sibling_map;
+	prio_array_t *array;
+	int ret = 0, i;
+	task_t *p;
+
+	for_each_domain(this_cpu, tmp)
+		if (tmp->flags & SD_SHARE_CPUPOWER)
+			sd = tmp;
+
+	if (!sd)
+		return 0;
+
+	/*
+	 * The same locking rules and details apply as for
+	 * wake_sleeping_dependent():
+	 */
+	spin_unlock(&this_rq->lock);
+	sibling_map = sd->span;
+	for_each_cpu_mask(i, sibling_map)
+		spin_lock(&cpu_rq(i)->lock);
+	cpu_clear(this_cpu, sibling_map);
+
+	/*
+	 * Establish next task to be run - it might have gone away because
+	 * we released the runqueue lock above:
+	 */
+	if (!this_rq->nr_running)
+		goto out_unlock;
+	array = this_rq->active;
+	if (!array->nr_active)
+		array = this_rq->expired;
+	BUG_ON(!array->nr_active);
+
+	p = list_entry(array->queue[sched_find_first_bit(array->bitmap)].next,
+		task_t, run_list);
+
+	for_each_cpu_mask(i, sibling_map) {
+		runqueue_t *smt_rq = cpu_rq(i);
+		task_t *smt_curr = smt_rq->curr;
+
+		/* Kernel threads do not participate in dependent sleeping */
+		if (!p->mm || !smt_curr->mm || rt_task(p))
+			goto check_smt_task;
+
+		/*
+		 * If a user task with lower static priority than the
+		 * running task on the SMT sibling is trying to schedule,
+		 * delay it till there is proportionately less timeslice
+		 * left of the sibling task to prevent a lower priority
+		 * task from using an unfair proportion of the
+		 * physical cpu's resources. -ck
+		 */
+		if (rt_task(smt_curr)) {
+			/*
+			 * With real time tasks we run non-rt tasks only
+			 * per_cpu_gain% of the time.
+			 */
+			if ((jiffies % DEF_TIMESLICE) >
+				(sd->per_cpu_gain * DEF_TIMESLICE / 100))
+					ret = 1;
+		} else
+			if (smt_curr->static_prio < p->static_prio &&
+				!TASK_PREEMPTS_CURR(p, smt_rq) &&
+				smt_slice(smt_curr, sd) > task_timeslice(p))
+					ret = 1;
+
+check_smt_task:
+		if ((!smt_curr->mm && smt_curr != smt_rq->idle) ||
+			rt_task(smt_curr))
+				continue;
+		if (!p->mm) {
+			wakeup_busy_runqueue(smt_rq);
+			continue;
+		}
+
+		/*
+		 * Reschedule a lower priority task on the SMT sibling for
+		 * it to be put to sleep, or wake it up if it has been put to
+		 * sleep for priority reasons to see if it should run now.
+		 */
+		if (rt_task(p)) {
+			if ((jiffies % DEF_TIMESLICE) >
+				(sd->per_cpu_gain * DEF_TIMESLICE / 100))
+					resched_task(smt_curr);
+		} else {
+			if (TASK_PREEMPTS_CURR(p, smt_rq) &&
+				smt_slice(p, sd) > task_timeslice(smt_curr))
+					resched_task(smt_curr);
+			else
+				wakeup_busy_runqueue(smt_rq);
+		}
+	}
+out_unlock:
+	for_each_cpu_mask(i, sibling_map)
+		spin_unlock(&cpu_rq(i)->lock);
+	return ret;
+}
+#else
+static inline void wake_sleeping_dependent(int this_cpu, runqueue_t *this_rq)
+{
+}
+
+static inline int dependent_sleeper(int this_cpu, runqueue_t *this_rq)
+{
+	return 0;
+}
+#endif
+
+#if defined(CONFIG_PREEMPT) && defined(CONFIG_DEBUG_PREEMPT)
+
+void fastcall add_preempt_count(int val)
+{
+	/*
+	 * Underflow?
+	 */
+	BUG_ON((preempt_count() < 0));
+	preempt_count() += val;
+	/*
+	 * Spinlock count overflowing soon?
+	 */
+	BUG_ON((preempt_count() & PREEMPT_MASK) >= PREEMPT_MASK-10);
+}
+EXPORT_SYMBOL(add_preempt_count);
+
+void fastcall sub_preempt_count(int val)
+{
+	/*
+	 * Underflow?
+	 */
+	BUG_ON(val > preempt_count());
+	/*
+	 * Is the spinlock portion underflowing?
+	 */
+	BUG_ON((val < PREEMPT_MASK) && !(preempt_count() & PREEMPT_MASK));
+	preempt_count() -= val;
+}
+EXPORT_SYMBOL(sub_preempt_count);
+
+#endif
+
+/*
+ * schedule() is the main scheduler function.
+ */
+asmlinkage void __sched schedule(void)
+{
+	long *switch_count;
+	task_t *prev, *next;
+	runqueue_t *rq;
+	prio_array_t *array;
+	struct list_head *queue;
+	unsigned long long now;
+	unsigned long run_time;
+	int cpu, idx, new_prio;
+
+	/*
+	 * Test if we are atomic.  Since do_exit() needs to call into
+	 * schedule() atomically, we ignore that path for now.
+	 * Otherwise, whine if we are scheduling when we should not be.
+	 */
+	if (likely(!current->exit_state)) {
+		if (unlikely(in_atomic())) {
+			printk(KERN_ERR "scheduling while atomic: "
+				"%s/0x%08x/%d\n",
+				current->comm, preempt_count(), current->pid);
+			dump_stack();
+		}
+	}
+	profile_hit(SCHED_PROFILING, __builtin_return_address(0));
+
+need_resched:
+	preempt_disable();
+	prev = current;
+	release_kernel_lock(prev);
+need_resched_nonpreemptible:
+	rq = this_rq();
+
+	/*
+	 * The idle thread is not allowed to schedule!
+	 * Remove this check after it has been exercised a bit.
+	 */
+	if (unlikely(prev == rq->idle) && prev->state != TASK_RUNNING) {
+		printk(KERN_ERR "bad: scheduling from the idle thread!\n");
+		dump_stack();
+	}
+
+	schedstat_inc(rq, sched_cnt);
+	now = sched_clock();
+	if (likely((long long)(now - prev->timestamp) < NS_MAX_SLEEP_AVG)) {
+		run_time = now - prev->timestamp;
+		if (unlikely((long long)(now - prev->timestamp) < 0))
+			run_time = 0;
+	} else
+		run_time = NS_MAX_SLEEP_AVG;
+
+	/*
+	 * Tasks charged proportionately less run_time at high sleep_avg to
+	 * delay them losing their interactive status
+	 */
+	run_time /= (CURRENT_BONUS(prev) ? : 1);
+
+	spin_lock_irq(&rq->lock);
+
+	if (unlikely(prev->flags & PF_DEAD))
+		prev->state = EXIT_DEAD;
+
+	switch_count = &prev->nivcsw;
+	if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
+		switch_count = &prev->nvcsw;
+		if (unlikely((prev->state & TASK_INTERRUPTIBLE) &&
+				unlikely(signal_pending(prev))))
+			prev->state = TASK_RUNNING;
+		else {
+			if (prev->state == TASK_UNINTERRUPTIBLE)
+				rq->nr_uninterruptible++;
+			deactivate_task(prev, rq);
+		}
+	}
+
+	cpu = smp_processor_id();
+	if (unlikely(!rq->nr_running)) {
+go_idle:
+		idle_balance(cpu, rq);
+		if (!rq->nr_running) {
+			next = rq->idle;
+			rq->expired_timestamp = 0;
+			wake_sleeping_dependent(cpu, rq);
+			/*
+			 * wake_sleeping_dependent() might have released
+			 * the runqueue, so break out if we got new
+			 * tasks meanwhile:
+			 */
+			if (!rq->nr_running)
+				goto switch_tasks;
+		}
+	} else {
+		if (dependent_sleeper(cpu, rq)) {
+			next = rq->idle;
+			goto switch_tasks;
+		}
+		/*
+		 * dependent_sleeper() releases and reacquires the runqueue
+		 * lock, hence go into the idle loop if the rq went
+		 * empty meanwhile:
+		 */
+		if (unlikely(!rq->nr_running))
+			goto go_idle;
+	}
+
+	array = rq->active;
+	if (unlikely(!array->nr_active)) {
+		/*
+		 * Switch the active and expired arrays.
+		 */
+		schedstat_inc(rq, sched_switch);
+		rq->active = rq->expired;
+		rq->expired = array;
+		array = rq->active;
+		rq->expired_timestamp = 0;
+		rq->best_expired_prio = MAX_PRIO;
+	}
+
+	idx = sched_find_first_bit(array->bitmap);
+	queue = array->queue + idx;
+	next = list_entry(queue->next, task_t, run_list);
+
+	if (!rt_task(next) && next->activated > 0) {
+		unsigned long long delta = now - next->timestamp;
+		if (unlikely((long long)(now - next->timestamp) < 0))
+			delta = 0;
+
+		if (next->activated == 1)
+			delta = delta * (ON_RUNQUEUE_WEIGHT * 128 / 100) / 128;
+
+		array = next->array;
+		new_prio = recalc_task_prio(next, next->timestamp + delta);
+
+		if (unlikely(next->prio != new_prio)) {
+			dequeue_task(next, array);
+			next->prio = new_prio;
+			enqueue_task(next, array);
+		} else
+			requeue_task(next, array);
+	}
+	next->activated = 0;
+switch_tasks:
+	if (next == rq->idle)
+		schedstat_inc(rq, sched_goidle);
+	prefetch(next);
+	prefetch_stack(next);
+	clear_tsk_need_resched(prev);
+	rcu_qsctr_inc(task_cpu(prev));
+
+	update_cpu_clock(prev, rq, now);
+
+	prev->sleep_avg -= run_time;
+	if ((long)prev->sleep_avg <= 0)
+		prev->sleep_avg = 0;
+	prev->timestamp = prev->last_ran = now;
+
+	sched_info_switch(prev, next);
+	if (likely(prev != next)) {
+		next->timestamp = now;
+		rq->nr_switches++;
+		rq->curr = next;
+		++*switch_count;
+
+		prepare_task_switch(rq, next);
+		prev = context_switch(rq, prev, next);
+		barrier();
+		/*
+		 * this_rq must be evaluated again because prev may have moved
+		 * CPUs since it called schedule(), thus the 'rq' on its stack
+		 * frame will be invalid.
+		 */
+		finish_task_switch(this_rq(), prev);
+	} else
+		spin_unlock_irq(&rq->lock);
+
+	prev = current;
+	if (unlikely(reacquire_kernel_lock(prev) < 0))
+		goto need_resched_nonpreemptible;
+	preempt_enable_no_resched();
+	if (unlikely(test_thread_flag(TIF_NEED_RESCHED)))
+		goto need_resched;
+}
+
+EXPORT_SYMBOL(schedule);
+
+#ifdef CONFIG_PREEMPT
+/*
+ * this is is the entry point to schedule() from in-kernel preemption
+ * off of preempt_enable.  Kernel preemptions off return from interrupt
+ * occur there and call schedule directly.
+ */
+asmlinkage void __sched preempt_schedule(void)
+{
+	struct thread_info *ti = current_thread_info();
+#ifdef CONFIG_PREEMPT_BKL
+	struct task_struct *task = current;
+	int saved_lock_depth;
+#endif
+	/*
+	 * If there is a non-zero preempt_count or interrupts are disabled,
+	 * we do not want to preempt the current task.  Just return..
+	 */
+	if (unlikely(ti->preempt_count || irqs_disabled()))
+		return;
+
+need_resched:
+	add_preempt_count(PREEMPT_ACTIVE);
+	/*
+	 * We keep the big kernel semaphore locked, but we
+	 * clear ->lock_depth so that schedule() doesnt
+	 * auto-release the semaphore:
+	 */
+#ifdef CONFIG_PREEMPT_BKL
+	saved_lock_depth = task->lock_depth;
+	task->lock_depth = -1;
+#endif
+	schedule();
+#ifdef CONFIG_PREEMPT_BKL
+	task->lock_depth = saved_lock_depth;
+#endif
+	sub_preempt_count(PREEMPT_ACTIVE);
+
+	/* we could miss a preemption opportunity between schedule and now */
+	barrier();
+	if (unlikely(test_thread_flag(TIF_NEED_RESCHED)))
+		goto need_resched;
+}
+
+EXPORT_SYMBOL(preempt_schedule);
+
+/*
+ * this is is the entry point to schedule() from kernel preemption
+ * off of irq context.
+ * Note, that this is called and return with irqs disabled. This will
+ * protect us against recursive calling from irq.
+ */
+asmlinkage void __sched preempt_schedule_irq(void)
+{
+	struct thread_info *ti = current_thread_info();
+#ifdef CONFIG_PREEMPT_BKL
+	struct task_struct *task = current;
+	int saved_lock_depth;
+#endif
+	/* Catch callers which need to be fixed*/
+	BUG_ON(ti->preempt_count || !irqs_disabled());
+
+need_resched:
+	add_preempt_count(PREEMPT_ACTIVE);
+	/*
+	 * We keep the big kernel semaphore locked, but we
+	 * clear ->lock_depth so that schedule() doesnt
+	 * auto-release the semaphore:
+	 */
+#ifdef CONFIG_PREEMPT_BKL
+	saved_lock_depth = task->lock_depth;
+	task->lock_depth = -1;
+#endif
+	local_irq_enable();
+	schedule();
+	local_irq_disable();
+#ifdef CONFIG_PREEMPT_BKL
+	task->lock_depth = saved_lock_depth;
+#endif
+	sub_preempt_count(PREEMPT_ACTIVE);
+
+	/* we could miss a preemption opportunity between schedule and now */
+	barrier();
+	if (unlikely(test_thread_flag(TIF_NEED_RESCHED)))
+		goto need_resched;
+}
+
+#endif /* CONFIG_PREEMPT */
+
+int default_wake_function(wait_queue_t *curr, unsigned mode, int sync,
+			  void *key)
+{
+	task_t *p = curr->private;
+	return try_to_wake_up(p, mode, sync);
+}
+
+EXPORT_SYMBOL(default_wake_function);
+
+/*
+ * The core wakeup function.  Non-exclusive wakeups (nr_exclusive == 0) just
+ * wake everything up.  If it's an exclusive wakeup (nr_exclusive == small +ve
+ * number) then we wake all the non-exclusive tasks and one exclusive task.
+ *
+ * There are circumstances in which we can try to wake a task which has already
+ * started to run but is not in state TASK_RUNNING.  try_to_wake_up() returns
+ * zero in this (rare) case, and we handle it by continuing to scan the queue.
+ */
+static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
+			     int nr_exclusive, int sync, void *key)
+{
+	struct list_head *tmp, *next;
+
+	list_for_each_safe(tmp, next, &q->task_list) {
+		wait_queue_t *curr;
+		unsigned flags;
+		curr = list_entry(tmp, wait_queue_t, task_list);
+		flags = curr->flags;
+		if (curr->func(curr, mode, sync, key) &&
+		    (flags & WQ_FLAG_EXCLUSIVE) &&
+		    !--nr_exclusive)
+			break;
+	}
+}
+
+/**
+ * __wake_up - wake up threads blocked on a waitqueue.
+ * @q: the waitqueue
+ * @mode: which threads
+ * @nr_exclusive: how many wake-one or wake-many threads to wake up
+ * @key: is directly passed to the wakeup function
+ */
+void fastcall __wake_up(wait_queue_head_t *q, unsigned int mode,
+			int nr_exclusive, void *key)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&q->lock, flags);
+	__wake_up_common(q, mode, nr_exclusive, 0, key);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+
+EXPORT_SYMBOL(__wake_up);
+
+/*
+ * Same as __wake_up but called with the spinlock in wait_queue_head_t held.
+ */
+void fastcall __wake_up_locked(wait_queue_head_t *q, unsigned int mode)
+{
+	__wake_up_common(q, mode, 1, 0, NULL);
+}
+
+/**
+ * __wake_up_sync - wake up threads blocked on a waitqueue.
+ * @q: the waitqueue
+ * @mode: which threads
+ * @nr_exclusive: how many wake-one or wake-many threads to wake up
+ *
+ * The sync wakeup differs that the waker knows that it will schedule
+ * away soon, so while the target thread will be woken up, it will not
+ * be migrated to another CPU - ie. the two threads are 'synchronized'
+ * with each other. This can prevent needless bouncing between CPUs.
+ *
+ * On UP it can prevent extra preemption.
+ */
+void fastcall
+__wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
+{
+	unsigned long flags;
+	int sync = 1;
+
+	if (unlikely(!q))
+		return;
+
+	if (unlikely(!nr_exclusive))
+		sync = 0;
+
+	spin_lock_irqsave(&q->lock, flags);
+	__wake_up_common(q, mode, nr_exclusive, sync, NULL);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL_GPL(__wake_up_sync);	/* For internal use only */
+
+void fastcall complete(struct completion *x)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&x->wait.lock, flags);
+	x->done++;
+	__wake_up_common(&x->wait, TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE,
+			 1, 0, NULL);
+	spin_unlock_irqrestore(&x->wait.lock, flags);
+}
+EXPORT_SYMBOL(complete);
+
+void fastcall complete_all(struct completion *x)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&x->wait.lock, flags);
+	x->done += UINT_MAX/2;
+	__wake_up_common(&x->wait, TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE,
+			 0, 0, NULL);
+	spin_unlock_irqrestore(&x->wait.lock, flags);
+}
+EXPORT_SYMBOL(complete_all);
+
+void fastcall __sched wait_for_completion(struct completion *x)
+{
+	might_sleep();
+	spin_lock_irq(&x->wait.lock);
+	if (!x->done) {
+		DECLARE_WAITQUEUE(wait, current);
+
+		wait.flags |= WQ_FLAG_EXCLUSIVE;
+		__add_wait_queue_tail(&x->wait, &wait);
+		do {
+			__set_current_state(TASK_UNINTERRUPTIBLE);
+			spin_unlock_irq(&x->wait.lock);
+			schedule();
+			spin_lock_irq(&x->wait.lock);
+		} while (!x->done);
+		__remove_wait_queue(&x->wait, &wait);
+	}
+	x->done--;
+	spin_unlock_irq(&x->wait.lock);
+}
+EXPORT_SYMBOL(wait_for_completion);
+
+unsigned long fastcall __sched
+wait_for_completion_timeout(struct completion *x, unsigned long timeout)
+{
+	might_sleep();
+
+	spin_lock_irq(&x->wait.lock);
+	if (!x->done) {
+		DECLARE_WAITQUEUE(wait, current);
+
+		wait.flags |= WQ_FLAG_EXCLUSIVE;
+		__add_wait_queue_tail(&x->wait, &wait);
+		do {
+			__set_current_state(TASK_UNINTERRUPTIBLE);
+			spin_unlock_irq(&x->wait.lock);
+			timeout = schedule_timeout(timeout);
+			spin_lock_irq(&x->wait.lock);
+			if (!timeout) {
+				__remove_wait_queue(&x->wait, &wait);
+				goto out;
+			}
+		} while (!x->done);
+		__remove_wait_queue(&x->wait, &wait);
+	}
+	x->done--;
+out:
+	spin_unlock_irq(&x->wait.lock);
+	return timeout;
+}
+EXPORT_SYMBOL(wait_for_completion_timeout);
+
+int fastcall __sched wait_for_completion_interruptible(struct completion *x)
+{
+	int ret = 0;
+
+	might_sleep();
+
+	spin_lock_irq(&x->wait.lock);
+	if (!x->done) {
+		DECLARE_WAITQUEUE(wait, current);
+
+		wait.flags |= WQ_FLAG_EXCLUSIVE;
+		__add_wait_queue_tail(&x->wait, &wait);
+		do {
+			if (signal_pending(current)) {
+				ret = -ERESTARTSYS;
+				__remove_wait_queue(&x->wait, &wait);
+				goto out;
+			}
+			__set_current_state(TASK_INTERRUPTIBLE);
+			spin_unlock_irq(&x->wait.lock);
+			schedule();
+			spin_lock_irq(&x->wait.lock);
+		} while (!x->done);
+		__remove_wait_queue(&x->wait, &wait);
+	}
+	x->done--;
+out:
+	spin_unlock_irq(&x->wait.lock);
+
+	return ret;
+}
+EXPORT_SYMBOL(wait_for_completion_interruptible);
+
+unsigned long fastcall __sched
+wait_for_completion_interruptible_timeout(struct completion *x,
+					  unsigned long timeout)
+{
+	might_sleep();
+
+	spin_lock_irq(&x->wait.lock);
+	if (!x->done) {
+		DECLARE_WAITQUEUE(wait, current);
+
+		wait.flags |= WQ_FLAG_EXCLUSIVE;
+		__add_wait_queue_tail(&x->wait, &wait);
+		do {
+			if (signal_pending(current)) {
+				timeout = -ERESTARTSYS;
+				__remove_wait_queue(&x->wait, &wait);
+				goto out;
+			}
+			__set_current_state(TASK_INTERRUPTIBLE);
+			spin_unlock_irq(&x->wait.lock);
+			timeout = schedule_timeout(timeout);
+			spin_lock_irq(&x->wait.lock);
+			if (!timeout) {
+				__remove_wait_queue(&x->wait, &wait);
+				goto out;
+			}
+		} while (!x->done);
+		__remove_wait_queue(&x->wait, &wait);
+	}
+	x->done--;
+out:
+	spin_unlock_irq(&x->wait.lock);
+	return timeout;
+}
+EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);
+
+
+#define	SLEEP_ON_VAR					\
+	unsigned long flags;				\
+	wait_queue_t wait;				\
+	init_waitqueue_entry(&wait, current);
+
+#define SLEEP_ON_HEAD					\
+	spin_lock_irqsave(&q->lock,flags);		\
+	__add_wait_queue(q, &wait);			\
+	spin_unlock(&q->lock);
+
+#define	SLEEP_ON_TAIL					\
+	spin_lock_irq(&q->lock);			\
+	__remove_wait_queue(q, &wait);			\
+	spin_unlock_irqrestore(&q->lock, flags);
+
+void fastcall __sched interruptible_sleep_on(wait_queue_head_t *q)
+{
+	SLEEP_ON_VAR
+
+	current->state = TASK_INTERRUPTIBLE;
+
+	SLEEP_ON_HEAD
+	schedule();
+	SLEEP_ON_TAIL
+}
+
+EXPORT_SYMBOL(interruptible_sleep_on);
+
+long fastcall __sched
+interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout)
+{
+	SLEEP_ON_VAR
+
+	current->state = TASK_INTERRUPTIBLE;
+
+	SLEEP_ON_HEAD
+	timeout = schedule_timeout(timeout);
+	SLEEP_ON_TAIL
+
+	return timeout;
+}
+
+EXPORT_SYMBOL(interruptible_sleep_on_timeout);
+
+void fastcall __sched sleep_on(wait_queue_head_t *q)
+{
+	SLEEP_ON_VAR
+
+	current->state = TASK_UNINTERRUPTIBLE;
+
+	SLEEP_ON_HEAD
+	schedule();
+	SLEEP_ON_TAIL
+}
+
+EXPORT_SYMBOL(sleep_on);
+
+long fastcall __sched sleep_on_timeout(wait_queue_head_t *q, long timeout)
+{
+	SLEEP_ON_VAR
+
+	current->state = TASK_UNINTERRUPTIBLE;
+
+	SLEEP_ON_HEAD
+	timeout = schedule_timeout(timeout);
+	SLEEP_ON_TAIL
+
+	return timeout;
+}
+
+EXPORT_SYMBOL(sleep_on_timeout);
+
+void set_user_nice(task_t *p, long nice)
+{
+	unsigned long flags;
+	prio_array_t *array;
+	runqueue_t *rq;
+	int old_prio, new_prio, delta;
+
+	if (TASK_NICE(p) == nice || nice < -20 || nice > 19)
+		return;
+	/*
+	 * We have to be careful, if called from sys_setpriority(),
+	 * the task might be in the middle of scheduling on another CPU.
+	 */
+	rq = task_rq_lock(p, &flags);
+	/*
+	 * The RT priorities are set via sched_setscheduler(), but we still
+	 * allow the 'normal' nice value to be set - but as expected
+	 * it wont have any effect on scheduling until the task is
+	 * not SCHED_NORMAL/SCHED_BATCH:
+	 */
+	if (rt_task(p)) {
+		p->static_prio = NICE_TO_PRIO(nice);
+		goto out_unlock;
+	}
+	array = p->array;
+	if (array)
+		dequeue_task(p, array);
+
+	old_prio = p->prio;
+	new_prio = NICE_TO_PRIO(nice);
+	delta = new_prio - old_prio;
+	p->static_prio = NICE_TO_PRIO(nice);
+	p->prio += delta;
+
+	if (array) {
+		enqueue_task(p, array);
+		/*
+		 * If the task increased its priority or is running and
+		 * lowered its priority, then reschedule its CPU:
+		 */
+		if (delta < 0 || (delta > 0 && task_running(rq, p)))
+			resched_task(rq->curr);
+	}
+out_unlock:
+	task_rq_unlock(rq, &flags);
+}
+
+EXPORT_SYMBOL(set_user_nice);
+
+/*
+ * can_nice - check if a task can reduce its nice value
+ * @p: task
+ * @nice: nice value
+ */
+int can_nice(const task_t *p, const int nice)
+{
+	/* convert nice value [19,-20] to rlimit style value [1,40] */
+	int nice_rlim = 20 - nice;
+	return (nice_rlim <= p->signal->rlim[RLIMIT_NICE].rlim_cur ||
+		capable(CAP_SYS_NICE));
+}
+
+#ifdef __ARCH_WANT_SYS_NICE
+
+/*
+ * sys_nice - change the priority of the current process.
+ * @increment: priority increment
+ *
+ * sys_setpriority is a more generic, but much slower function that
+ * does similar things.
+ */
+asmlinkage long sys_nice(int increment)
+{
+	int retval;
+	long nice;
+
+	/*
+	 * Setpriority might change our priority at the same moment.
+	 * We don't have to worry. Conceptually one call occurs first
+	 * and we have a single winner.
+	 */
+	if (increment < -40)
+		increment = -40;
+	if (increment > 40)
+		increment = 40;
+
+	nice = PRIO_TO_NICE(current->static_prio) + increment;
+	if (nice < -20)
+		nice = -20;
+	if (nice > 19)
+		nice = 19;
+
+	if (increment < 0 && !can_nice(current, nice))
+		return -EPERM;
+
+	retval = security_task_setnice(current, nice);
+	if (retval)
+		return retval;
+
+	set_user_nice(current, nice);
+	return 0;
+}
+
+#endif
+
+/**
+ * task_prio - return the priority value of a given task.
+ * @p: the task in question.
+ *
+ * This is the priority value as seen by users in /proc.
+ * RT tasks are offset by -200. Normal tasks are centered
+ * around 0, value goes from -16 to +15.
+ */
+int task_prio(const task_t *p)
+{
+	return p->prio - MAX_RT_PRIO;
+}
+
+/**
+ * task_nice - return the nice value of a given task.
+ * @p: the task in question.
+ */
+int task_nice(const task_t *p)
+{
+	return TASK_NICE(p);
+}
+EXPORT_SYMBOL_GPL(task_nice);
+
+/**
+ * idle_cpu - is a given cpu idle currently?
+ * @cpu: the processor in question.
+ */
+int idle_cpu(int cpu)
+{
+	return cpu_curr(cpu) == cpu_rq(cpu)->idle;
+}
+
+/**
+ * idle_task - return the idle task for a given cpu.
+ * @cpu: the processor in question.
+ */
+task_t *idle_task(int cpu)
+{
+	return cpu_rq(cpu)->idle;
+}
+
+/**
+ * find_process_by_pid - find a process with a matching PID value.
+ * @pid: the pid in question.
+ */
+static inline task_t *find_process_by_pid(pid_t pid)
+{
+	return pid ? find_task_by_pid(pid) : current;
+}
+
+/* Actually do priority change: must hold rq lock. */
+static void __setscheduler(struct task_struct *p, int policy, int prio)
+{
+	BUG_ON(p->array);
+	p->policy = policy;
+	p->rt_priority = prio;
+	if (policy != SCHED_NORMAL && policy != SCHED_BATCH) {
+		p->prio = MAX_RT_PRIO-1 - p->rt_priority;
+	} else {
+		p->prio = p->static_prio;
+		/*
+		 * SCHED_BATCH tasks are treated as perpetual CPU hogs:
+		 */
+		if (policy == SCHED_BATCH)
+			p->sleep_avg = 0;
+	}
+}
+
+/**
+ * sched_setscheduler - change the scheduling policy and/or RT priority of
+ * a thread.
+ * @p: the task in question.
+ * @policy: new policy.
+ * @param: structure containing the new RT priority.
+ */
+int sched_setscheduler(struct task_struct *p, int policy,
+		       struct sched_param *param)
+{
+	int retval;
+	int oldprio, oldpolicy = -1;
+	prio_array_t *array;
+	unsigned long flags;
+	runqueue_t *rq;
+
+recheck:
+	/* double check policy once rq lock held */
+	if (policy < 0)
+		policy = oldpolicy = p->policy;
+	else if (policy != SCHED_FIFO && policy != SCHED_RR &&
+			policy != SCHED_NORMAL && policy != SCHED_BATCH)
+		return -EINVAL;
+	/*
+	 * Valid priorities for SCHED_FIFO and SCHED_RR are
+	 * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL and
+	 * SCHED_BATCH is 0.
+	 */
+	if (param->sched_priority < 0 ||
+	    (p->mm && param->sched_priority > MAX_USER_RT_PRIO-1) ||
+	    (!p->mm && param->sched_priority > MAX_RT_PRIO-1))
+		return -EINVAL;
+	if ((policy == SCHED_NORMAL || policy == SCHED_BATCH)
+					!= (param->sched_priority == 0))
+		return -EINVAL;
+
+	/*
+	 * Allow unprivileged RT tasks to decrease priority:
+	 */
+	if (!capable(CAP_SYS_NICE)) {
+		/*
+		 * can't change policy, except between SCHED_NORMAL
+		 * and SCHED_BATCH:
+		 */
+		if (((policy != SCHED_NORMAL && p->policy != SCHED_BATCH) &&
+			(policy != SCHED_BATCH && p->policy != SCHED_NORMAL)) &&
+				!p->signal->rlim[RLIMIT_RTPRIO].rlim_cur)
+			return -EPERM;
+		/* can't increase priority */
+		if ((policy != SCHED_NORMAL && policy != SCHED_BATCH) &&
+		    param->sched_priority > p->rt_priority &&
+		    param->sched_priority >
+				p->signal->rlim[RLIMIT_RTPRIO].rlim_cur)
+			return -EPERM;
+		/* can't change other user's priorities */
+		if ((current->euid != p->euid) &&
+		    (current->euid != p->uid))
+			return -EPERM;
+	}
+
+	retval = security_task_setscheduler(p, policy, param);
+	if (retval)
+		return retval;
+	/*
+	 * To be able to change p->policy safely, the apropriate
+	 * runqueue lock must be held.
+	 */
+	rq = task_rq_lock(p, &flags);
+	/* recheck policy now with rq lock held */
+	if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
+		policy = oldpolicy = -1;
+		task_rq_unlock(rq, &flags);
+		goto recheck;
+	}
+	array = p->array;
+	if (array)
+		deactivate_task(p, rq);
+	oldprio = p->prio;
+	__setscheduler(p, policy, param->sched_priority);
+	if (array) {
+		__activate_task(p, rq);
+		/*
+		 * Reschedule if we are currently running on this runqueue and
+		 * our priority decreased, or if we are not currently running on
+		 * this runqueue and our priority is higher than the current's
+		 */
+		if (task_running(rq, p)) {
+			if (p->prio > oldprio)
+				resched_task(rq->curr);
+		} else if (TASK_PREEMPTS_CURR(p, rq))
+			resched_task(rq->curr);
+	}
+	task_rq_unlock(rq, &flags);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(sched_setscheduler);
+
+static int
+do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
+{
+	int retval;
+	struct sched_param lparam;
+	struct task_struct *p;
+
+	if (!param || pid < 0)
+		return -EINVAL;
+	if (copy_from_user(&lparam, param, sizeof(struct sched_param)))
+		return -EFAULT;
+	read_lock_irq(&tasklist_lock);
+	p = find_process_by_pid(pid);
+	if (!p) {
+		read_unlock_irq(&tasklist_lock);
+		return -ESRCH;
+	}
+	retval = sched_setscheduler(p, policy, &lparam);
+	read_unlock_irq(&tasklist_lock);
+	return retval;
+}
+
+/**
+ * sys_sched_setscheduler - set/change the scheduler policy and RT priority
+ * @pid: the pid in question.
+ * @policy: new policy.
+ * @param: structure containing the new RT priority.
+ */
+asmlinkage long sys_sched_setscheduler(pid_t pid, int policy,
+				       struct sched_param __user *param)
+{
+	/* negative values for policy are not valid */
+	if (policy < 0)
+		return -EINVAL;
+
+	return do_sched_setscheduler(pid, policy, param);
+}
+
+/**
+ * sys_sched_setparam - set/change the RT priority of a thread
+ * @pid: the pid in question.
+ * @param: structure containing the new RT priority.
+ */
+asmlinkage long sys_sched_setparam(pid_t pid, struct sched_param __user *param)
+{
+	return do_sched_setscheduler(pid, -1, param);
+}
+
+/**
+ * sys_sched_getscheduler - get the policy (scheduling class) of a thread
+ * @pid: the pid in question.
+ */
+asmlinkage long sys_sched_getscheduler(pid_t pid)
+{
+	int retval = -EINVAL;
+	task_t *p;
+
+	if (pid < 0)
+		goto out_nounlock;
+
+	retval = -ESRCH;
+	read_lock(&tasklist_lock);
+	p = find_process_by_pid(pid);
+	if (p) {
+		retval = security_task_getscheduler(p);
+		if (!retval)
+			retval = p->policy;
+	}
+	read_unlock(&tasklist_lock);
+
+out_nounlock:
+	return retval;
+}
+
+/**
+ * sys_sched_getscheduler - get the RT priority of a thread
+ * @pid: the pid in question.
+ * @param: structure containing the RT priority.
+ */
+asmlinkage long sys_sched_getparam(pid_t pid, struct sched_param __user *param)
+{
+	struct sched_param lp;
+	int retval = -EINVAL;
+	task_t *p;
+
+	if (!param || pid < 0)
+		goto out_nounlock;
+
+	read_lock(&tasklist_lock);
+	p = find_process_by_pid(pid);
+	retval = -ESRCH;
+	if (!p)
+		goto out_unlock;
+
+	retval = security_task_getscheduler(p);
+	if (retval)
+		goto out_unlock;
+
+	lp.sched_priority = p->rt_priority;
+	read_unlock(&tasklist_lock);
+
+	/*
+	 * This one might sleep, we cannot do it with a spinlock held ...
+	 */
+	retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0;
+
+out_nounlock:
+	return retval;
+
+out_unlock:
+	read_unlock(&tasklist_lock);
+	return retval;
+}
+
+long sched_setaffinity(pid_t pid, cpumask_t new_mask)
+{
+	task_t *p;
+	int retval;
+	cpumask_t cpus_allowed;
+
+	lock_cpu_hotplug();
+	read_lock(&tasklist_lock);
+
+	p = find_process_by_pid(pid);
+	if (!p) {
+		read_unlock(&tasklist_lock);
+		unlock_cpu_hotplug();
+		return -ESRCH;
+	}
+
+	/*
+	 * It is not safe to call set_cpus_allowed with the
+	 * tasklist_lock held.  We will bump the task_struct's
+	 * usage count and then drop tasklist_lock.
+	 */
+	get_task_struct(p);
+	read_unlock(&tasklist_lock);
+
+	retval = -EPERM;
+	if ((current->euid != p->euid) && (current->euid != p->uid) &&
+			!capable(CAP_SYS_NICE))
+		goto out_unlock;
+
+	cpus_allowed = cpuset_cpus_allowed(p);
+	cpus_and(new_mask, new_mask, cpus_allowed);
+	retval = set_cpus_allowed(p, new_mask);
+
+out_unlock:
+	put_task_struct(p);
+	unlock_cpu_hotplug();
+	return retval;
+}
+
+static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len,
+			     cpumask_t *new_mask)
+{
+	if (len < sizeof(cpumask_t)) {
+		memset(new_mask, 0, sizeof(cpumask_t));
+	} else if (len > sizeof(cpumask_t)) {
+		len = sizeof(cpumask_t);
+	}
+	return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0;
+}
+
+/**
+ * sys_sched_setaffinity - set the cpu affinity of a process
+ * @pid: pid of the process
+ * @len: length in bytes of the bitmask pointed to by user_mask_ptr
+ * @user_mask_ptr: user-space pointer to the new cpu mask
+ */
+asmlinkage long sys_sched_setaffinity(pid_t pid, unsigned int len,
+				      unsigned long __user *user_mask_ptr)
+{
+	cpumask_t new_mask;
+	int retval;
+
+	retval = get_user_cpu_mask(user_mask_ptr, len, &new_mask);
+	if (retval)
+		return retval;
+
+	return sched_setaffinity(pid, new_mask);
+}
+
+/*
+ * Represents all cpu's present in the system
+ * In systems capable of hotplug, this map could dynamically grow
+ * as new cpu's are detected in the system via any platform specific
+ * method, such as ACPI for e.g.
+ */
+
+cpumask_t cpu_present_map __read_mostly;
+EXPORT_SYMBOL(cpu_present_map);
+
+#ifndef CONFIG_SMP
+cpumask_t cpu_online_map __read_mostly = CPU_MASK_ALL;
+cpumask_t cpu_possible_map __read_mostly = CPU_MASK_ALL;
+#endif
+
+long sched_getaffinity(pid_t pid, cpumask_t *mask)
+{
+	int retval;
+	task_t *p;
+
+	lock_cpu_hotplug();
+	read_lock(&tasklist_lock);
+
+	retval = -ESRCH;
+	p = find_process_by_pid(pid);
+	if (!p)
+		goto out_unlock;
+
+	retval = 0;
+	cpus_and(*mask, p->cpus_allowed, cpu_online_map);
+
+out_unlock:
+	read_unlock(&tasklist_lock);
+	unlock_cpu_hotplug();
+	if (retval)
+		return retval;
+
+	return 0;
+}
+
+/**
+ * sys_sched_getaffinity - get the cpu affinity of a process
+ * @pid: pid of the process
+ * @len: length in bytes of the bitmask pointed to by user_mask_ptr
+ * @user_mask_ptr: user-space pointer to hold the current cpu mask
+ */
+asmlinkage long sys_sched_getaffinity(pid_t pid, unsigned int len,
+				      unsigned long __user *user_mask_ptr)
+{
+	int ret;
+	cpumask_t mask;
+
+	if (len < sizeof(cpumask_t))
+		return -EINVAL;
+
+	ret = sched_getaffinity(pid, &mask);
+	if (ret < 0)
+		return ret;
+
+	if (copy_to_user(user_mask_ptr, &mask, sizeof(cpumask_t)))
+		return -EFAULT;
+
+	return sizeof(cpumask_t);
+}
+
+/**
+ * sys_sched_yield - yield the current processor to other threads.
+ *
+ * this function yields the current CPU by moving the calling thread
+ * to the expired array. If there are no other threads running on this
+ * CPU then this function will return.
+ */
+asmlinkage long sys_sched_yield(void)
+{
+	runqueue_t *rq = this_rq_lock();
+	prio_array_t *array = current->array;
+	prio_array_t *target = rq->expired;
+
+	schedstat_inc(rq, yld_cnt);
+	/*
+	 * We implement yielding by moving the task into the expired
+	 * queue.
+	 *
+	 * (special rule: RT tasks will just roundrobin in the active
+	 *  array.)
+	 */
+	if (rt_task(current))
+		target = rq->active;
+
+	if (array->nr_active == 1) {
+		schedstat_inc(rq, yld_act_empty);
+		if (!rq->expired->nr_active)
+			schedstat_inc(rq, yld_both_empty);
+	} else if (!rq->expired->nr_active)
+		schedstat_inc(rq, yld_exp_empty);
+
+	if (array != target) {
+		dequeue_task(current, array);
+		enqueue_task(current, target);
+	} else
+		/*
+		 * requeue_task is cheaper so perform that if possible.
+		 */
+		requeue_task(current, array);
+
+	/*
+	 * Since we are going to call schedule() anyway, there's
+	 * no need to preempt or enable interrupts:
+	 */
+	__release(rq->lock);
+	_raw_spin_unlock(&rq->lock);
+	preempt_enable_no_resched();
+
+	schedule();
+
+	return 0;
+}
+
+static inline void __cond_resched(void)
+{
+	/*
+	 * The BKS might be reacquired before we have dropped
+	 * PREEMPT_ACTIVE, which could trigger a second
+	 * cond_resched() call.
+	 */
+	if (unlikely(preempt_count()))
+		return;
+	do {
+		add_preempt_count(PREEMPT_ACTIVE);
+		schedule();
+		sub_preempt_count(PREEMPT_ACTIVE);
+	} while (need_resched());
+}
+
+int __sched cond_resched(void)
+{
+	if (need_resched()) {
+		__cond_resched();
+		return 1;
+	}
+	return 0;
+}
+
+EXPORT_SYMBOL(cond_resched);
+
+/*
+ * cond_resched_lock() - if a reschedule is pending, drop the given lock,
+ * call schedule, and on return reacquire the lock.
+ *
+ * This works OK both with and without CONFIG_PREEMPT.  We do strange low-level
+ * operations here to prevent schedule() from being called twice (once via
+ * spin_unlock(), once by hand).
+ */
+int cond_resched_lock(spinlock_t *lock)
+{
+	int ret = 0;
+
+	if (need_lockbreak(lock)) {
+		spin_unlock(lock);
+		cpu_relax();
+		ret = 1;
+		spin_lock(lock);
+	}
+	if (need_resched()) {
+		_raw_spin_unlock(lock);
+		preempt_enable_no_resched();
+		__cond_resched();
+		ret = 1;
+		spin_lock(lock);
+	}
+	return ret;
+}
+
+EXPORT_SYMBOL(cond_resched_lock);
+
+int __sched cond_resched_softirq(void)
+{
+	BUG_ON(!in_softirq());
+
+	if (need_resched()) {
+		__local_bh_enable();
+		__cond_resched();
+		local_bh_disable();
+		return 1;
+	}
+	return 0;
+}
+
+EXPORT_SYMBOL(cond_resched_softirq);
+
+
+/**
+ * yield - yield the current processor to other threads.
+ *
+ * this is a shortcut for kernel-space yielding - it marks the
+ * thread runnable and calls sys_sched_yield().
+ */
+void __sched yield(void)
+{
+	set_current_state(TASK_RUNNING);
+	sys_sched_yield();
+}
+
+EXPORT_SYMBOL(yield);
+
+/*
+ * This task is about to go to sleep on IO.  Increment rq->nr_iowait so
+ * that process accounting knows that this is a task in IO wait state.
+ *
+ * But don't do that if it is a deliberate, throttling IO wait (this task
+ * has set its backing_dev_info: the queue against which it should throttle)
+ */
+void __sched io_schedule(void)
+{
+	struct runqueue *rq = &per_cpu(runqueues, raw_smp_processor_id());
+
+	atomic_inc(&rq->nr_iowait);
+	schedule();
+	atomic_dec(&rq->nr_iowait);
+}
+
+EXPORT_SYMBOL(io_schedule);
+
+long __sched io_schedule_timeout(long timeout)
+{
+	struct runqueue *rq = &per_cpu(runqueues, raw_smp_processor_id());
+	long ret;
+
+	atomic_inc(&rq->nr_iowait);
+	ret = schedule_timeout(timeout);
+	atomic_dec(&rq->nr_iowait);
+	return ret;
+}
+
+/**
+ * sys_sched_get_priority_max - return maximum RT priority.
+ * @policy: scheduling class.
+ *
+ * this syscall returns the maximum rt_priority that can be used
+ * by a given scheduling class.
+ */
+asmlinkage long sys_sched_get_priority_max(int policy)
+{
+	int ret = -EINVAL;
+
+	switch (policy) {
+	case SCHED_FIFO:
+	case SCHED_RR:
+		ret = MAX_USER_RT_PRIO-1;
+		break;
+	case SCHED_NORMAL:
+	case SCHED_BATCH:
+		ret = 0;
+		break;
+	}
+	return ret;
+}
+
+/**
+ * sys_sched_get_priority_min - return minimum RT priority.
+ * @policy: scheduling class.
+ *
+ * this syscall returns the minimum rt_priority that can be used
+ * by a given scheduling class.
+ */
+asmlinkage long sys_sched_get_priority_min(int policy)
+{
+	int ret = -EINVAL;
+
+	switch (policy) {
+	case SCHED_FIFO:
+	case SCHED_RR:
+		ret = 1;
+		break;
+	case SCHED_NORMAL:
+	case SCHED_BATCH:
+		ret = 0;
+	}
+	return ret;
+}
+
+/**
+ * sys_sched_rr_get_interval - return the default timeslice of a process.
+ * @pid: pid of the process.
+ * @interval: userspace pointer to the timeslice value.
+ *
+ * this syscall writes the default timeslice value of a given process
+ * into the user-space timespec buffer. A value of '0' means infinity.
+ */
+asmlinkage
+long sys_sched_rr_get_interval(pid_t pid, struct timespec __user *interval)
+{
+	int retval = -EINVAL;
+	struct timespec t;
+	task_t *p;
+
+	if (pid < 0)
+		goto out_nounlock;
+
+	retval = -ESRCH;
+	read_lock(&tasklist_lock);
+	p = find_process_by_pid(pid);
+	if (!p)
+		goto out_unlock;
+
+	retval = security_task_getscheduler(p);
+	if (retval)
+		goto out_unlock;
+
+	jiffies_to_timespec(p->policy & SCHED_FIFO ?
+				0 : task_timeslice(p), &t);
+	read_unlock(&tasklist_lock);
+	retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0;
+out_nounlock:
+	return retval;
+out_unlock:
+	read_unlock(&tasklist_lock);
+	return retval;
+}
+
+static inline struct task_struct *eldest_child(struct task_struct *p)
+{
+	if (list_empty(&p->children)) return NULL;
+	return list_entry(p->children.next,struct task_struct,sibling);
+}
+
+static inline struct task_struct *older_sibling(struct task_struct *p)
+{
+	if (p->sibling.prev==&p->parent->children) return NULL;
+	return list_entry(p->sibling.prev,struct task_struct,sibling);
+}
+
+static inline struct task_struct *younger_sibling(struct task_struct *p)
+{
+	if (p->sibling.next==&p->parent->children) return NULL;
+	return list_entry(p->sibling.next,struct task_struct,sibling);
+}
+
+static void show_task(task_t *p)
+{
+	task_t *relative;
+	unsigned state;
+	unsigned long free = 0;
+	static const char *stat_nam[] = { "R", "S", "D", "T", "t", "Z", "X" };
+
+	printk("%-13.13s ", p->comm);
+	state = p->state ? __ffs(p->state) + 1 : 0;
+	if (state < ARRAY_SIZE(stat_nam))
+		printk(stat_nam[state]);
+	else
+		printk("?");
+#if (BITS_PER_LONG == 32)
+	if (state == TASK_RUNNING)
+		printk(" running ");
+	else
+		printk(" %08lX ", thread_saved_pc(p));
+#else
+	if (state == TASK_RUNNING)
+		printk("  running task   ");
+	else
+		printk(" %016lx ", thread_saved_pc(p));
+#endif
+#ifdef CONFIG_DEBUG_STACK_USAGE
+	{
+		unsigned long *n = end_of_stack(p);
+		while (!*n)
+			n++;
+		free = (unsigned long)n - (unsigned long)end_of_stack(p);
+	}
+#endif
+	printk("%5lu %5d %6d ", free, p->pid, p->parent->pid);
+	if ((relative = eldest_child(p)))
+		printk("%5d ", relative->pid);
+	else
+		printk("      ");
+	if ((relative = younger_sibling(p)))
+		printk("%7d", relative->pid);
+	else
+		printk("       ");
+	if ((relative = older_sibling(p)))
+		printk(" %5d", relative->pid);
+	else
+		printk("      ");
+	if (!p->mm)
+		printk(" (L-TLB)\n");
+	else
+		printk(" (NOTLB)\n");
+
+	if (state != TASK_RUNNING)
+		show_stack(p, NULL);
+}
+
+void show_state(void)
+{
+	task_t *g, *p;
+
+#if (BITS_PER_LONG == 32)
+	printk("\n"
+	       "                                               sibling\n");
+	printk("  task             PC      pid father child younger older\n");
+#else
+	printk("\n"
+	       "                                                       sibling\n");
+	printk("  task                 PC          pid father child younger older\n");
+#endif
+	read_lock(&tasklist_lock);
+	do_each_thread(g, p) {
+		/*
+		 * reset the NMI-timeout, listing all files on a slow
+		 * console might take alot of time:
+		 */
+		touch_nmi_watchdog();
+		show_task(p);
+	} while_each_thread(g, p);
+
+	read_unlock(&tasklist_lock);
+	mutex_debug_show_all_locks();
+}
+
+/**
+ * init_idle - set up an idle thread for a given CPU
+ * @idle: task in question
+ * @cpu: cpu the idle task belongs to
+ *
+ * NOTE: this function does not set the idle thread's NEED_RESCHED
+ * flag, to make booting more robust.
+ */
+void __devinit init_idle(task_t *idle, int cpu)
+{
+	runqueue_t *rq = cpu_rq(cpu);
+	unsigned long flags;
+
+	idle->sleep_avg = 0;
+	idle->array = NULL;
+	idle->prio = MAX_PRIO;
+	idle->state = TASK_RUNNING;
+	idle->cpus_allowed = cpumask_of_cpu(cpu);
+	set_task_cpu(idle, cpu);
+
+	spin_lock_irqsave(&rq->lock, flags);
+	rq->curr = rq->idle = idle;
+#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
+	idle->oncpu = 1;
+#endif
+	spin_unlock_irqrestore(&rq->lock, flags);
+
+	/* Set the preempt count _outside_ the spinlocks! */
+#if defined(CONFIG_PREEMPT) && !defined(CONFIG_PREEMPT_BKL)
+	task_thread_info(idle)->preempt_count = (idle->lock_depth >= 0);
+#else
+	task_thread_info(idle)->preempt_count = 0;
+#endif
+}
+
+/*
+ * In a system that switches off the HZ timer nohz_cpu_mask
+ * indicates which cpus entered this state. This is used
+ * in the rcu update to wait only for active cpus. For system
+ * which do not switch off the HZ timer nohz_cpu_mask should
+ * always be CPU_MASK_NONE.
+ */
+cpumask_t nohz_cpu_mask = CPU_MASK_NONE;
+
+#ifdef CONFIG_SMP
+/*
+ * This is how migration works:
+ *
+ * 1) we queue a migration_req_t structure in the source CPU's
+ *    runqueue and wake up that CPU's migration thread.
+ * 2) we down() the locked semaphore => thread blocks.
+ * 3) migration thread wakes up (implicitly it forces the migrated
+ *    thread off the CPU)
+ * 4) it gets the migration request and checks whether the migrated
+ *    task is still in the wrong runqueue.
+ * 5) if it's in the wrong runqueue then the migration thread removes
+ *    it and puts it into the right queue.
+ * 6) migration thread up()s the semaphore.
+ * 7) we wake up and the migration is done.
+ */
+
+/*
+ * Change a given task's CPU affinity. Migrate the thread to a
+ * proper CPU and schedule it away if the CPU it's executing on
+ * is removed from the allowed bitmask.
+ *
+ * NOTE: the caller must have a valid reference to the task, the
+ * task must not exit() & deallocate itself prematurely.  The
+ * call is not atomic; no spinlocks may be held.
+ */
+int set_cpus_allowed(task_t *p, cpumask_t new_mask)
+{
+	unsigned long flags;
+	int ret = 0;
+	migration_req_t req;
+	runqueue_t *rq;
+
+	rq = task_rq_lock(p, &flags);
+	if (!cpus_intersects(new_mask, cpu_online_map)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	p->cpus_allowed = new_mask;
+	/* Can the task run on the task's current CPU? If so, we're done */
+	if (cpu_isset(task_cpu(p), new_mask))
+		goto out;
+
+	if (migrate_task(p, any_online_cpu(new_mask), &req)) {
+		/* Need help from migration thread: drop lock and wait. */
+		task_rq_unlock(rq, &flags);
+		wake_up_process(rq->migration_thread);
+		wait_for_completion(&req.done);
+		tlb_migrate_finish(p->mm);
+		return 0;
+	}
+out:
+	task_rq_unlock(rq, &flags);
+	return ret;
+}
+
+EXPORT_SYMBOL_GPL(set_cpus_allowed);
+
+/*
+ * Move (not current) task off this cpu, onto dest cpu.  We're doing
+ * this because either it can't run here any more (set_cpus_allowed()
+ * away from this CPU, or CPU going down), or because we're
+ * attempting to rebalance this task on exec (sched_exec).
+ *
+ * So we race with normal scheduler movements, but that's OK, as long
+ * as the task is no longer on this CPU.
+ */
+static void __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
+{
+	runqueue_t *rq_dest, *rq_src;
+
+	if (unlikely(cpu_is_offline(dest_cpu)))
+		return;
+
+	rq_src = cpu_rq(src_cpu);
+	rq_dest = cpu_rq(dest_cpu);
+
+	double_rq_lock(rq_src, rq_dest);
+	/* Already moved. */
+	if (task_cpu(p) != src_cpu)
+		goto out;
+	/* Affinity changed (again). */
+	if (!cpu_isset(dest_cpu, p->cpus_allowed))
+		goto out;
+
+	set_task_cpu(p, dest_cpu);
+	if (p->array) {
+		/*
+		 * Sync timestamp with rq_dest's before activating.
+		 * The same thing could be achieved by doing this step
+		 * afterwards, and pretending it was a local activate.
+		 * This way is cleaner and logically correct.
+		 */
+		p->timestamp = p->timestamp - rq_src->timestamp_last_tick
+				+ rq_dest->timestamp_last_tick;
+		deactivate_task(p, rq_src);
+		activate_task(p, rq_dest, 0);
+		if (TASK_PREEMPTS_CURR(p, rq_dest))
+			resched_task(rq_dest->curr);
+	}
+
+out:
+	double_rq_unlock(rq_src, rq_dest);
+}
+
+/*
+ * migration_thread - this is a highprio system thread that performs
+ * thread migration by bumping thread off CPU then 'pushing' onto
+ * another runqueue.
+ */
+static int migration_thread(void *data)
+{
+	runqueue_t *rq;
+	int cpu = (long)data;
+
+	rq = cpu_rq(cpu);
+	BUG_ON(rq->migration_thread != current);
+
+	set_current_state(TASK_INTERRUPTIBLE);
+	while (!kthread_should_stop()) {
+		struct list_head *head;
+		migration_req_t *req;
+
+		try_to_freeze();
+
+		spin_lock_irq(&rq->lock);
+
+		if (cpu_is_offline(cpu)) {
+			spin_unlock_irq(&rq->lock);
+			goto wait_to_die;
+		}
+
+		if (rq->active_balance) {
+			active_load_balance(rq, cpu);
+			rq->active_balance = 0;
+		}
+
+		head = &rq->migration_queue;
+
+		if (list_empty(head)) {
+			spin_unlock_irq(&rq->lock);
+			schedule();
+			set_current_state(TASK_INTERRUPTIBLE);
+			continue;
+		}
+		req = list_entry(head->next, migration_req_t, list);
+		list_del_init(head->next);
+
+		spin_unlock(&rq->lock);
+		__migrate_task(req->task, cpu, req->dest_cpu);
+		local_irq_enable();
+
+		complete(&req->done);
+	}
+	__set_current_state(TASK_RUNNING);
+	return 0;
+
+wait_to_die:
+	/* Wait for kthread_stop */
+	set_current_state(TASK_INTERRUPTIBLE);
+	while (!kthread_should_stop()) {
+		schedule();
+		set_current_state(TASK_INTERRUPTIBLE);
+	}
+	__set_current_state(TASK_RUNNING);
+	return 0;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+/* Figure out where task on dead CPU should go, use force if neccessary. */
+static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *tsk)
+{
+	int dest_cpu;
+	cpumask_t mask;
+
+	/* On same node? */
+	mask = node_to_cpumask(cpu_to_node(dead_cpu));
+	cpus_and(mask, mask, tsk->cpus_allowed);
+	dest_cpu = any_online_cpu(mask);
+
+	/* On any allowed CPU? */
+	if (dest_cpu == NR_CPUS)
+		dest_cpu = any_online_cpu(tsk->cpus_allowed);
+
+	/* No more Mr. Nice Guy. */
+	if (dest_cpu == NR_CPUS) {
+		cpus_setall(tsk->cpus_allowed);
+		dest_cpu = any_online_cpu(tsk->cpus_allowed);
+
+		/*
+		 * Don't tell them about moving exiting tasks or
+		 * kernel threads (both mm NULL), since they never
+		 * leave kernel.
+		 */
+		if (tsk->mm && printk_ratelimit())
+			printk(KERN_INFO "process %d (%s) no "
+			       "longer affine to cpu%d\n",
+			       tsk->pid, tsk->comm, dead_cpu);
+	}
+	__migrate_task(tsk, dead_cpu, dest_cpu);
+}
+
+/*
+ * While a dead CPU has no uninterruptible tasks queued at this point,
+ * it might still have a nonzero ->nr_uninterruptible counter, because
+ * for performance reasons the counter is not stricly tracking tasks to
+ * their home CPUs. So we just add the counter to another CPU's counter,
+ * to keep the global sum constant after CPU-down:
+ */
+static void migrate_nr_uninterruptible(runqueue_t *rq_src)
+{
+	runqueue_t *rq_dest = cpu_rq(any_online_cpu(CPU_MASK_ALL));
+	unsigned long flags;
+
+	local_irq_save(flags);
+	double_rq_lock(rq_src, rq_dest);
+	rq_dest->nr_uninterruptible += rq_src->nr_uninterruptible;
+	rq_src->nr_uninterruptible = 0;
+	double_rq_unlock(rq_src, rq_dest);
+	local_irq_restore(flags);
+}
+
+/* Run through task list and migrate tasks from the dead cpu. */
+static void migrate_live_tasks(int src_cpu)
+{
+	struct task_struct *tsk, *t;
+
+	write_lock_irq(&tasklist_lock);
+
+	do_each_thread(t, tsk) {
+		if (tsk == current)
+			continue;
+
+		if (task_cpu(tsk) == src_cpu)
+			move_task_off_dead_cpu(src_cpu, tsk);
+	} while_each_thread(t, tsk);
+
+	write_unlock_irq(&tasklist_lock);
+}
+
+/* Schedules idle task to be the next runnable task on current CPU.
+ * It does so by boosting its priority to highest possible and adding it to
+ * the _front_ of runqueue. Used by CPU offline code.
+ */
+void sched_idle_next(void)
+{
+	int cpu = smp_processor_id();
+	runqueue_t *rq = this_rq();
+	struct task_struct *p = rq->idle;
+	unsigned long flags;
+
+	/* cpu has to be offline */
+	BUG_ON(cpu_online(cpu));
+
+	/* Strictly not necessary since rest of the CPUs are stopped by now
+	 * and interrupts disabled on current cpu.
+	 */
+	spin_lock_irqsave(&rq->lock, flags);
+
+	__setscheduler(p, SCHED_FIFO, MAX_RT_PRIO-1);
+	/* Add idle task to _front_ of it's priority queue */
+	__activate_idle_task(p, rq);
+
+	spin_unlock_irqrestore(&rq->lock, flags);
+}
+
+/* Ensures that the idle task is using init_mm right before its cpu goes
+ * offline.
+ */
+void idle_task_exit(void)
+{
+	struct mm_struct *mm = current->active_mm;
+
+	BUG_ON(cpu_online(smp_processor_id()));
+
+	if (mm != &init_mm)
+		switch_mm(mm, &init_mm, current);
+	mmdrop(mm);
+}
+
+static void migrate_dead(unsigned int dead_cpu, task_t *tsk)
+{
+	struct runqueue *rq = cpu_rq(dead_cpu);
+
+	/* Must be exiting, otherwise would be on tasklist. */
+	BUG_ON(tsk->exit_state != EXIT_ZOMBIE && tsk->exit_state != EXIT_DEAD);
+
+	/* Cannot have done final schedule yet: would have vanished. */
+	BUG_ON(tsk->flags & PF_DEAD);
+
+	get_task_struct(tsk);
+
+	/*
+	 * Drop lock around migration; if someone else moves it,
+	 * that's OK.  No task can be added to this CPU, so iteration is
+	 * fine.
+	 */
+	spin_unlock_irq(&rq->lock);
+	move_task_off_dead_cpu(dead_cpu, tsk);
+	spin_lock_irq(&rq->lock);
+
+	put_task_struct(tsk);
+}
+
+/* release_task() removes task from tasklist, so we won't find dead tasks. */
+static void migrate_dead_tasks(unsigned int dead_cpu)
+{
+	unsigned arr, i;
+	struct runqueue *rq = cpu_rq(dead_cpu);
+
+	for (arr = 0; arr < 2; arr++) {
+		for (i = 0; i < MAX_PRIO; i++) {
+			struct list_head *list = &rq->arrays[arr].queue[i];
+			while (!list_empty(list))
+				migrate_dead(dead_cpu,
+					     list_entry(list->next, task_t,
+							run_list));
+		}
+	}
+}
+#endif /* CONFIG_HOTPLUG_CPU */
+
+/*
+ * migration_call - callback that gets triggered when a CPU is added.
+ * Here we can start up the necessary migration thread for the new CPU.
+ */
+static int migration_call(struct notifier_block *nfb, unsigned long action,
+			  void *hcpu)
+{
+	int cpu = (long)hcpu;
+	struct task_struct *p;
+	struct runqueue *rq;
+	unsigned long flags;
+
+	switch (action) {
+	case CPU_UP_PREPARE:
+		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);
+		__setscheduler(p, SCHED_FIFO, MAX_RT_PRIO-1);
+		task_rq_unlock(rq, &flags);
+		cpu_rq(cpu)->migration_thread = p;
+		break;
+	case CPU_ONLINE:
+		/* Strictly unneccessary, as first user will wake it. */
+		wake_up_process(cpu_rq(cpu)->migration_thread);
+		break;
+#ifdef CONFIG_HOTPLUG_CPU
+	case CPU_UP_CANCELED:
+		/* Unbind it from offline cpu so it can run.  Fall thru. */
+		kthread_bind(cpu_rq(cpu)->migration_thread,
+			     any_online_cpu(cpu_online_map));
+		kthread_stop(cpu_rq(cpu)->migration_thread);
+		cpu_rq(cpu)->migration_thread = NULL;
+		break;
+	case CPU_DEAD:
+		migrate_live_tasks(cpu);
+		rq = cpu_rq(cpu);
+		kthread_stop(rq->migration_thread);
+		rq->migration_thread = NULL;
+		/* Idle task back to normal (off runqueue, low prio) */
+		rq = task_rq_lock(rq->idle, &flags);
+		deactivate_task(rq->idle, rq);
+		rq->idle->static_prio = MAX_PRIO;
+		__setscheduler(rq->idle, SCHED_NORMAL, 0);
+		migrate_dead_tasks(cpu);
+		task_rq_unlock(rq, &flags);
+		migrate_nr_uninterruptible(rq);
+		BUG_ON(rq->nr_running != 0);
+
+		/* No need to migrate the tasks: it was best-effort if
+		 * they didn't do lock_cpu_hotplug().  Just wake up
+		 * the requestors. */
+		spin_lock_irq(&rq->lock);
+		while (!list_empty(&rq->migration_queue)) {
+			migration_req_t *req;
+			req = list_entry(rq->migration_queue.next,
+					 migration_req_t, list);
+			list_del_init(&req->list);
+			complete(&req->done);
+		}
+		spin_unlock_irq(&rq->lock);
+		break;
+#endif
+	}
+	return NOTIFY_OK;
+}
+
+/* Register at highest priority so that task migration (migrate_all_tasks)
+ * happens before everything else.
+ */
+static struct notifier_block __devinitdata migration_notifier = {
+	.notifier_call = migration_call,
+	.priority = 10
+};
+
+int __init migration_init(void)
+{
+	void *cpu = (void *)(long)smp_processor_id();
+	/* Start one for boot CPU. */
+	migration_call(&migration_notifier, CPU_UP_PREPARE, cpu);
+	migration_call(&migration_notifier, CPU_ONLINE, cpu);
+	register_cpu_notifier(&migration_notifier);
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_SMP
+#undef SCHED_DOMAIN_DEBUG
+#ifdef SCHED_DOMAIN_DEBUG
+static void sched_domain_debug(struct sched_domain *sd, int cpu)
+{
+	int level = 0;
+
+	if (!sd) {
+		printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu);
+		return;
+	}
+
+	printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);
+
+	do {
+		int i;
+		char str[NR_CPUS];
+		struct sched_group *group = sd->groups;
+		cpumask_t groupmask;
+
+		cpumask_scnprintf(str, NR_CPUS, sd->span);
+		cpus_clear(groupmask);
+
+		printk(KERN_DEBUG);
+		for (i = 0; i < level + 1; i++)
+			printk(" ");
+		printk("domain %d: ", level);
+
+		if (!(sd->flags & SD_LOAD_BALANCE)) {
+			printk("does not load-balance\n");
+			if (sd->parent)
+				printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain has parent");
+			break;
+		}
+
+		printk("span %s\n", str);
+
+		if (!cpu_isset(cpu, sd->span))
+			printk(KERN_ERR "ERROR: domain->span does not contain CPU%d\n", cpu);
+		if (!cpu_isset(cpu, group->cpumask))
+			printk(KERN_ERR "ERROR: domain->groups does not contain CPU%d\n", cpu);
+
+		printk(KERN_DEBUG);
+		for (i = 0; i < level + 2; i++)
+			printk(" ");
+		printk("groups:");
+		do {
+			if (!group) {
+				printk("\n");
+				printk(KERN_ERR "ERROR: group is NULL\n");
+				break;
+			}
+
+			if (!group->cpu_power) {
+				printk("\n");
+				printk(KERN_ERR "ERROR: domain->cpu_power not set\n");
+			}
+
+			if (!cpus_weight(group->cpumask)) {
+				printk("\n");
+				printk(KERN_ERR "ERROR: empty group\n");
+			}
+
+			if (cpus_intersects(groupmask, group->cpumask)) {
+				printk("\n");
+				printk(KERN_ERR "ERROR: repeated CPUs\n");
+			}
+
+			cpus_or(groupmask, groupmask, group->cpumask);
+
+			cpumask_scnprintf(str, NR_CPUS, group->cpumask);
+			printk(" %s", str);
+
+			group = group->next;
+		} while (group != sd->groups);
+		printk("\n");
+
+		if (!cpus_equal(sd->span, groupmask))
+			printk(KERN_ERR "ERROR: groups don't span domain->span\n");
+
+		level++;
+		sd = sd->parent;
+
+		if (sd) {
+			if (!cpus_subset(groupmask, sd->span))
+				printk(KERN_ERR "ERROR: parent span is not a superset of domain->span\n");
+		}
+
+	} while (sd);
+}
+#else
+#define sched_domain_debug(sd, cpu) {}
+#endif
+
+static int sd_degenerate(struct sched_domain *sd)
+{
+	if (cpus_weight(sd->span) == 1)
+		return 1;
+
+	/* Following flags need at least 2 groups */
+	if (sd->flags & (SD_LOAD_BALANCE |
+			 SD_BALANCE_NEWIDLE |
+			 SD_BALANCE_FORK |
+			 SD_BALANCE_EXEC)) {
+		if (sd->groups != sd->groups->next)
+			return 0;
+	}
+
+	/* Following flags don't use groups */
+	if (sd->flags & (SD_WAKE_IDLE |
+			 SD_WAKE_AFFINE |
+			 SD_WAKE_BALANCE))
+		return 0;
+
+	return 1;
+}
+
+static int sd_parent_degenerate(struct sched_domain *sd,
+						struct sched_domain *parent)
+{
+	unsigned long cflags = sd->flags, pflags = parent->flags;
+
+	if (sd_degenerate(parent))
+		return 1;
+
+	if (!cpus_equal(sd->span, parent->span))
+		return 0;
+
+	/* Does parent contain flags not in child? */
+	/* WAKE_BALANCE is a subset of WAKE_AFFINE */
+	if (cflags & SD_WAKE_AFFINE)
+		pflags &= ~SD_WAKE_BALANCE;
+	/* Flags needing groups don't count if only 1 group in parent */
+	if (parent->groups == parent->groups->next) {
+		pflags &= ~(SD_LOAD_BALANCE |
+				SD_BALANCE_NEWIDLE |
+				SD_BALANCE_FORK |
+				SD_BALANCE_EXEC);
+	}
+	if (~cflags & pflags)
+		return 0;
+
+	return 1;
+}
+
+/*
+ * Attach the domain 'sd' to 'cpu' as its base domain.  Callers must
+ * hold the hotplug lock.
+ */
+static void cpu_attach_domain(struct sched_domain *sd, int cpu)
+{
+	runqueue_t *rq = cpu_rq(cpu);
+	struct sched_domain *tmp;
+
+	/* Remove the sched domains which do not contribute to scheduling. */
+	for (tmp = sd; tmp; tmp = tmp->parent) {
+		struct sched_domain *parent = tmp->parent;
+		if (!parent)
+			break;
+		if (sd_parent_degenerate(tmp, parent))
+			tmp->parent = parent->parent;
+	}
+
+	if (sd && sd_degenerate(sd))
+		sd = sd->parent;
+
+	sched_domain_debug(sd, cpu);
+
+	rcu_assign_pointer(rq->sd, sd);
+}
+
+/* cpus with isolated domains */
+static cpumask_t __devinitdata cpu_isolated_map = CPU_MASK_NONE;
+
+/* Setup the mask of cpus configured for isolated domains */
+static int __init isolated_cpu_setup(char *str)
+{
+	int ints[NR_CPUS], i;
+
+	str = get_options(str, ARRAY_SIZE(ints), ints);
+	cpus_clear(cpu_isolated_map);
+	for (i = 1; i <= ints[0]; i++)
+		if (ints[i] < NR_CPUS)
+			cpu_set(ints[i], cpu_isolated_map);
+	return 1;
+}
+
+__setup ("isolcpus=", isolated_cpu_setup);
+
+/*
+ * init_sched_build_groups takes an array of groups, the cpumask we wish
+ * to span, and a pointer to a function which identifies what group a CPU
+ * belongs to. The return value of group_fn must be a valid index into the
+ * groups[] array, and must be >= 0 and < NR_CPUS (due to the fact that we
+ * keep track of groups covered with a cpumask_t).
+ *
+ * init_sched_build_groups will build a circular linked list of the groups
+ * covered by the given span, and will set each group's ->cpumask correctly,
+ * and ->cpu_power to 0.
+ */
+static void init_sched_build_groups(struct sched_group groups[], cpumask_t span,
+				    int (*group_fn)(int cpu))
+{
+	struct sched_group *first = NULL, *last = NULL;
+	cpumask_t covered = CPU_MASK_NONE;
+	int i;
+
+	for_each_cpu_mask(i, span) {
+		int group = group_fn(i);
+		struct sched_group *sg = &groups[group];
+		int j;
+
+		if (cpu_isset(i, covered))
+			continue;
+
+		sg->cpumask = CPU_MASK_NONE;
+		sg->cpu_power = 0;
+
+		for_each_cpu_mask(j, span) {
+			if (group_fn(j) != group)
+				continue;
+
+			cpu_set(j, covered);
+			cpu_set(j, sg->cpumask);
+		}
+		if (!first)
+			first = sg;
+		if (last)
+			last->next = sg;
+		last = sg;
+	}
+	last->next = first;
+}
+
+#define SD_NODES_PER_DOMAIN 16
+
+/*
+ * Self-tuning task migration cost measurement between source and target CPUs.
+ *
+ * This is done by measuring the cost of manipulating buffers of varying
+ * sizes. For a given buffer-size here are the steps that are taken:
+ *
+ * 1) the source CPU reads+dirties a shared buffer
+ * 2) the target CPU reads+dirties the same shared buffer
+ *
+ * We measure how long they take, in the following 4 scenarios:
+ *
+ *  - source: CPU1, target: CPU2 | cost1
+ *  - source: CPU2, target: CPU1 | cost2
+ *  - source: CPU1, target: CPU1 | cost3
+ *  - source: CPU2, target: CPU2 | cost4
+ *
+ * We then calculate the cost3+cost4-cost1-cost2 difference - this is
+ * the cost of migration.
+ *
+ * We then start off from a small buffer-size and iterate up to larger
+ * buffer sizes, in 5% steps - measuring each buffer-size separately, and
+ * doing a maximum search for the cost. (The maximum cost for a migration
+ * normally occurs when the working set size is around the effective cache
+ * size.)
+ */
+#define SEARCH_SCOPE		2
+#define MIN_CACHE_SIZE		(64*1024U)
+#define DEFAULT_CACHE_SIZE	(5*1024*1024U)
+#define ITERATIONS		1
+#define SIZE_THRESH		130
+#define COST_THRESH		130
+
+/*
+ * The migration cost is a function of 'domain distance'. Domain
+ * distance is the number of steps a CPU has to iterate down its
+ * domain tree to share a domain with the other CPU. The farther
+ * two CPUs are from each other, the larger the distance gets.
+ *
+ * Note that we use the distance only to cache measurement results,
+ * the distance value is not used numerically otherwise. When two
+ * CPUs have the same distance it is assumed that the migration
+ * cost is the same. (this is a simplification but quite practical)
+ */
+#define MAX_DOMAIN_DISTANCE 32
+
+static unsigned long long migration_cost[MAX_DOMAIN_DISTANCE] =
+		{ [ 0 ... MAX_DOMAIN_DISTANCE-1 ] =
+/*
+ * Architectures may override the migration cost and thus avoid
+ * boot-time calibration. Unit is nanoseconds. Mostly useful for
+ * virtualized hardware:
+ */
+#ifdef CONFIG_DEFAULT_MIGRATION_COST
+			CONFIG_DEFAULT_MIGRATION_COST
+#else
+			-1LL
+#endif
+};
+
+/*
+ * Allow override of migration cost - in units of microseconds.
+ * E.g. migration_cost=1000,2000,3000 will set up a level-1 cost
+ * of 1 msec, level-2 cost of 2 msecs and level3 cost of 3 msecs:
+ */
+static int __init migration_cost_setup(char *str)
+{
+	int ints[MAX_DOMAIN_DISTANCE+1], i;
+
+	str = get_options(str, ARRAY_SIZE(ints), ints);
+
+	printk("#ints: %d\n", ints[0]);
+	for (i = 1; i <= ints[0]; i++) {
+		migration_cost[i-1] = (unsigned long long)ints[i]*1000;
+		printk("migration_cost[%d]: %Ld\n", i-1, migration_cost[i-1]);
+	}
+	return 1;
+}
+
+__setup ("migration_cost=", migration_cost_setup);
+
+/*
+ * Global multiplier (divisor) for migration-cutoff values,
+ * in percentiles. E.g. use a value of 150 to get 1.5 times
+ * longer cache-hot cutoff times.
+ *
+ * (We scale it from 100 to 128 to long long handling easier.)
+ */
+
+#define MIGRATION_FACTOR_SCALE 128
+
+static unsigned int migration_factor = MIGRATION_FACTOR_SCALE;
+
+static int __init setup_migration_factor(char *str)
+{
+	get_option(&str, &migration_factor);
+	migration_factor = migration_factor * MIGRATION_FACTOR_SCALE / 100;
+	return 1;
+}
+
+__setup("migration_factor=", setup_migration_factor);
+
+/*
+ * Estimated distance of two CPUs, measured via the number of domains
+ * we have to pass for the two CPUs to be in the same span:
+ */
+static unsigned long domain_distance(int cpu1, int cpu2)
+{
+	unsigned long distance = 0;
+	struct sched_domain *sd;
+
+	for_each_domain(cpu1, sd) {
+		WARN_ON(!cpu_isset(cpu1, sd->span));
+		if (cpu_isset(cpu2, sd->span))
+			return distance;
+		distance++;
+	}
+	if (distance >= MAX_DOMAIN_DISTANCE) {
+		WARN_ON(1);
+		distance = MAX_DOMAIN_DISTANCE-1;
+	}
+
+	return distance;
+}
+
+static unsigned int migration_debug;
+
+static int __init setup_migration_debug(char *str)
+{
+	get_option(&str, &migration_debug);
+	return 1;
+}
+
+__setup("migration_debug=", setup_migration_debug);
+
+/*
+ * Maximum cache-size that the scheduler should try to measure.
+ * Architectures with larger caches should tune this up during
+ * bootup. Gets used in the domain-setup code (i.e. during SMP
+ * bootup).
+ */
+unsigned int max_cache_size;
+
+static int __init setup_max_cache_size(char *str)
+{
+	get_option(&str, &max_cache_size);
+	return 1;
+}
+
+__setup("max_cache_size=", setup_max_cache_size);
+
+/*
+ * Dirty a big buffer in a hard-to-predict (for the L2 cache) way. This
+ * is the operation that is timed, so we try to generate unpredictable
+ * cachemisses that still end up filling the L2 cache:
+ */
+static void touch_cache(void *__cache, unsigned long __size)
+{
+	unsigned long size = __size/sizeof(long), chunk1 = size/3,
+			chunk2 = 2*size/3;
+	unsigned long *cache = __cache;
+	int i;
+
+	for (i = 0; i < size/6; i += 8) {
+		switch (i % 6) {
+			case 0: cache[i]++;
+			case 1: cache[size-1-i]++;
+			case 2: cache[chunk1-i]++;
+			case 3: cache[chunk1+i]++;
+			case 4: cache[chunk2-i]++;
+			case 5: cache[chunk2+i]++;
+		}
+	}
+}
+
+/*
+ * Measure the cache-cost of one task migration. Returns in units of nsec.
+ */
+static unsigned long long measure_one(void *cache, unsigned long size,
+				      int source, int target)
+{
+	cpumask_t mask, saved_mask;
+	unsigned long long t0, t1, t2, t3, cost;
+
+	saved_mask = current->cpus_allowed;
+
+	/*
+	 * Flush source caches to RAM and invalidate them:
+	 */
+	sched_cacheflush();
+
+	/*
+	 * Migrate to the source CPU:
+	 */
+	mask = cpumask_of_cpu(source);
+	set_cpus_allowed(current, mask);
+	WARN_ON(smp_processor_id() != source);
+
+	/*
+	 * Dirty the working set:
+	 */
+	t0 = sched_clock();
+	touch_cache(cache, size);
+	t1 = sched_clock();
+
+	/*
+	 * Migrate to the target CPU, dirty the L2 cache and access
+	 * the shared buffer. (which represents the working set
+	 * of a migrated task.)
+	 */
+	mask = cpumask_of_cpu(target);
+	set_cpus_allowed(current, mask);
+	WARN_ON(smp_processor_id() != target);
+
+	t2 = sched_clock();
+	touch_cache(cache, size);
+	t3 = sched_clock();
+
+	cost = t1-t0 + t3-t2;
+
+	if (migration_debug >= 2)
+		printk("[%d->%d]: %8Ld %8Ld %8Ld => %10Ld.\n",
+			source, target, t1-t0, t1-t0, t3-t2, cost);
+	/*
+	 * Flush target caches to RAM and invalidate them:
+	 */
+	sched_cacheflush();
+
+	set_cpus_allowed(current, saved_mask);
+
+	return cost;
+}
+
+/*
+ * Measure a series of task migrations and return the average
+ * result. Since this code runs early during bootup the system
+ * is 'undisturbed' and the average latency makes sense.
+ *
+ * The algorithm in essence auto-detects the relevant cache-size,
+ * so it will properly detect different cachesizes for different
+ * cache-hierarchies, depending on how the CPUs are connected.
+ *
+ * Architectures can prime the upper limit of the search range via
+ * max_cache_size, otherwise the search range defaults to 20MB...64K.
+ */
+static unsigned long long
+measure_cost(int cpu1, int cpu2, void *cache, unsigned int size)
+{
+	unsigned long long cost1, cost2;
+	int i;
+
+	/*
+	 * Measure the migration cost of 'size' bytes, over an
+	 * average of 10 runs:
+	 *
+	 * (We perturb the cache size by a small (0..4k)
+	 *  value to compensate size/alignment related artifacts.
+	 *  We also subtract the cost of the operation done on
+	 *  the same CPU.)
+	 */
+	cost1 = 0;
+
+	/*
+	 * dry run, to make sure we start off cache-cold on cpu1,
+	 * and to get any vmalloc pagefaults in advance:
+	 */
+	measure_one(cache, size, cpu1, cpu2);
+	for (i = 0; i < ITERATIONS; i++)
+		cost1 += measure_one(cache, size - i*1024, cpu1, cpu2);
+
+	measure_one(cache, size, cpu2, cpu1);
+	for (i = 0; i < ITERATIONS; i++)
+		cost1 += measure_one(cache, size - i*1024, cpu2, cpu1);
+
+	/*
+	 * (We measure the non-migrating [cached] cost on both
+	 *  cpu1 and cpu2, to handle CPUs with different speeds)
+	 */
+	cost2 = 0;
+
+	measure_one(cache, size, cpu1, cpu1);
+	for (i = 0; i < ITERATIONS; i++)
+		cost2 += measure_one(cache, size - i*1024, cpu1, cpu1);
+
+	measure_one(cache, size, cpu2, cpu2);
+	for (i = 0; i < ITERATIONS; i++)
+		cost2 += measure_one(cache, size - i*1024, cpu2, cpu2);
+
+	/*
+	 * Get the per-iteration migration cost:
+	 */
+	do_div(cost1, 2*ITERATIONS);
+	do_div(cost2, 2*ITERATIONS);
+
+	return cost1 - cost2;
+}
+
+static unsigned long long measure_migration_cost(int cpu1, int cpu2)
+{
+	unsigned long long max_cost = 0, fluct = 0, avg_fluct = 0;
+	unsigned int max_size, size, size_found = 0;
+	long long cost = 0, prev_cost;
+	void *cache;
+
+	/*
+	 * Search from max_cache_size*5 down to 64K - the real relevant
+	 * cachesize has to lie somewhere inbetween.
+	 */
+	if (max_cache_size) {
+		max_size = max(max_cache_size * SEARCH_SCOPE, MIN_CACHE_SIZE);
+		size = max(max_cache_size / SEARCH_SCOPE, MIN_CACHE_SIZE);
+	} else {
+		/*
+		 * Since we have no estimation about the relevant
+		 * search range
+		 */
+		max_size = DEFAULT_CACHE_SIZE * SEARCH_SCOPE;
+		size = MIN_CACHE_SIZE;
+	}
+
+	if (!cpu_online(cpu1) || !cpu_online(cpu2)) {
+		printk("cpu %d and %d not both online!\n", cpu1, cpu2);
+		return 0;
+	}
+
+	/*
+	 * Allocate the working set:
+	 */
+	cache = vmalloc(max_size);
+	if (!cache) {
+		printk("could not vmalloc %d bytes for cache!\n", 2*max_size);
+		return 1000000; // return 1 msec on very small boxen
+	}
+
+	while (size <= max_size) {
+		prev_cost = cost;
+		cost = measure_cost(cpu1, cpu2, cache, size);
+
+		/*
+		 * Update the max:
+		 */
+		if (cost > 0) {
+			if (max_cost < cost) {
+				max_cost = cost;
+				size_found = size;
+			}
+		}
+		/*
+		 * Calculate average fluctuation, we use this to prevent
+		 * noise from triggering an early break out of the loop:
+		 */
+		fluct = abs(cost - prev_cost);
+		avg_fluct = (avg_fluct + fluct)/2;
+
+		if (migration_debug)
+			printk("-> [%d][%d][%7d] %3ld.%ld [%3ld.%ld] (%ld): (%8Ld %8Ld)\n",
+				cpu1, cpu2, size,
+				(long)cost / 1000000,
+				((long)cost / 100000) % 10,
+				(long)max_cost / 1000000,
+				((long)max_cost / 100000) % 10,
+				domain_distance(cpu1, cpu2),
+				cost, avg_fluct);
+
+		/*
+		 * If we iterated at least 20% past the previous maximum,
+		 * and the cost has dropped by more than 20% already,
+		 * (taking fluctuations into account) then we assume to
+		 * have found the maximum and break out of the loop early:
+		 */
+		if (size_found && (size*100 > size_found*SIZE_THRESH))
+			if (cost+avg_fluct <= 0 ||
+				max_cost*100 > (cost+avg_fluct)*COST_THRESH) {
+
+				if (migration_debug)
+					printk("-> found max.\n");
+				break;
+			}
+		/*
+		 * Increase the cachesize in 10% steps:
+		 */
+		size = size * 10 / 9;
+	}
+
+	if (migration_debug)
+		printk("[%d][%d] working set size found: %d, cost: %Ld\n",
+			cpu1, cpu2, size_found, max_cost);
+
+	vfree(cache);
+
+	/*
+	 * A task is considered 'cache cold' if at least 2 times
+	 * the worst-case cost of migration has passed.
+	 *
+	 * (this limit is only listened to if the load-balancing
+	 * situation is 'nice' - if there is a large imbalance we
+	 * ignore it for the sake of CPU utilization and
+	 * processing fairness.)
+	 */
+	return 2 * max_cost * migration_factor / MIGRATION_FACTOR_SCALE;
+}
+
+static void calibrate_migration_costs(const cpumask_t *cpu_map)
+{
+	int cpu1 = -1, cpu2 = -1, cpu, orig_cpu = raw_smp_processor_id();
+	unsigned long j0, j1, distance, max_distance = 0;
+	struct sched_domain *sd;
+
+	j0 = jiffies;
+
+	/*
+	 * First pass - calculate the cacheflush times:
+	 */
+	for_each_cpu_mask(cpu1, *cpu_map) {
+		for_each_cpu_mask(cpu2, *cpu_map) {
+			if (cpu1 == cpu2)
+				continue;
+			distance = domain_distance(cpu1, cpu2);
+			max_distance = max(max_distance, distance);
+			/*
+			 * No result cached yet?
+			 */
+			if (migration_cost[distance] == -1LL)
+				migration_cost[distance] =
+					measure_migration_cost(cpu1, cpu2);
+		}
+	}
+	/*
+	 * Second pass - update the sched domain hierarchy with
+	 * the new cache-hot-time estimations:
+	 */
+	for_each_cpu_mask(cpu, *cpu_map) {
+		distance = 0;
+		for_each_domain(cpu, sd) {
+			sd->cache_hot_time = migration_cost[distance];
+			distance++;
+		}
+	}
+	/*
+	 * Print the matrix:
+	 */
+	if (migration_debug)
+		printk("migration: max_cache_size: %d, cpu: %d MHz:\n",
+			max_cache_size,
+#ifdef CONFIG_X86
+			cpu_khz/1000
+#else
+			-1
+#endif
+		);
+	if (system_state == SYSTEM_BOOTING) {
+		printk("migration_cost=");
+		for (distance = 0; distance <= max_distance; distance++) {
+			if (distance)
+				printk(",");
+			printk("%ld", (long)migration_cost[distance] / 1000);
+		}
+		printk("\n");
+	}
+	j1 = jiffies;
+	if (migration_debug)
+		printk("migration: %ld seconds\n", (j1-j0)/HZ);
+
+	/*
+	 * Move back to the original CPU. NUMA-Q gets confused
+	 * if we migrate to another quad during bootup.
+	 */
+	if (raw_smp_processor_id() != orig_cpu) {
+		cpumask_t mask = cpumask_of_cpu(orig_cpu),
+			saved_mask = current->cpus_allowed;
+
+		set_cpus_allowed(current, mask);
+		set_cpus_allowed(current, saved_mask);
+	}
+}
+
+#ifdef CONFIG_NUMA
+
+/**
+ * find_next_best_node - find the next node to include in a sched_domain
+ * @node: node whose sched_domain we're building
+ * @used_nodes: nodes already in the sched_domain
+ *
+ * Find the next node to include in a given scheduling domain.  Simply
+ * finds the closest node not already in the @used_nodes map.
+ *
+ * Should use nodemask_t.
+ */
+static int find_next_best_node(int node, unsigned long *used_nodes)
+{
+	int i, n, val, min_val, best_node = 0;
+
+	min_val = INT_MAX;
+
+	for (i = 0; i < MAX_NUMNODES; i++) {
+		/* Start at @node */
+		n = (node + i) % MAX_NUMNODES;
+
+		if (!nr_cpus_node(n))
+			continue;
+
+		/* Skip already used nodes */
+		if (test_bit(n, used_nodes))
+			continue;
+
+		/* Simple min distance search */
+		val = node_distance(node, n);
+
+		if (val < min_val) {
+			min_val = val;
+			best_node = n;
+		}
+	}
+
+	set_bit(best_node, used_nodes);
+	return best_node;
+}
+
+/**
+ * sched_domain_node_span - get a cpumask for a node's sched_domain
+ * @node: node whose cpumask we're constructing
+ * @size: number of nodes to include in this span
+ *
+ * Given a node, construct a good cpumask for its sched_domain to span.  It
+ * should be one that prevents unnecessary balancing, but also spreads tasks
+ * out optimally.
+ */
+static cpumask_t sched_domain_node_span(int node)
+{
+	int i;
+	cpumask_t span, nodemask;
+	DECLARE_BITMAP(used_nodes, MAX_NUMNODES);
+
+	cpus_clear(span);
+	bitmap_zero(used_nodes, MAX_NUMNODES);
+
+	nodemask = node_to_cpumask(node);
+	cpus_or(span, span, nodemask);
+	set_bit(node, used_nodes);
+
+	for (i = 1; i < SD_NODES_PER_DOMAIN; i++) {
+		int next_node = find_next_best_node(node, used_nodes);
+		nodemask = node_to_cpumask(next_node);
+		cpus_or(span, span, nodemask);
+	}
+
+	return span;
+}
+#endif
+
+/*
+ * At the moment, CONFIG_SCHED_SMT is never defined, but leave it in so we
+ * can switch it on easily if needed.
+ */
+#ifdef CONFIG_SCHED_SMT
+static DEFINE_PER_CPU(struct sched_domain, cpu_domains);
+static struct sched_group sched_group_cpus[NR_CPUS];
+static int cpu_to_cpu_group(int cpu)
+{
+	return cpu;
+}
+#endif
+
+static DEFINE_PER_CPU(struct sched_domain, phys_domains);
+static struct sched_group sched_group_phys[NR_CPUS];
+static int cpu_to_phys_group(int cpu)
+{
+#ifdef CONFIG_SCHED_SMT
+	return first_cpu(cpu_sibling_map[cpu]);
+#else
+	return cpu;
+#endif
+}
+
+#ifdef CONFIG_NUMA
+/*
+ * The init_sched_build_groups can't handle what we want to do with node
+ * groups, so roll our own. Now each node has its own list of groups which
+ * gets dynamically allocated.
+ */
+static DEFINE_PER_CPU(struct sched_domain, node_domains);
+static struct sched_group **sched_group_nodes_bycpu[NR_CPUS];
+
+static DEFINE_PER_CPU(struct sched_domain, allnodes_domains);
+static struct sched_group *sched_group_allnodes_bycpu[NR_CPUS];
+
+static int cpu_to_allnodes_group(int cpu)
+{
+	return cpu_to_node(cpu);
+}
+#endif
+
+/*
+ * Build sched domains for a given set of cpus and attach the sched domains
+ * to the individual cpus
+ */
+void build_sched_domains(const cpumask_t *cpu_map)
+{
+	int i;
+#ifdef CONFIG_NUMA
+	struct sched_group **sched_group_nodes = NULL;
+	struct sched_group *sched_group_allnodes = NULL;
+
+	/*
+	 * Allocate the per-node list of sched groups
+	 */
+	sched_group_nodes = kmalloc(sizeof(struct sched_group*)*MAX_NUMNODES,
+					   GFP_ATOMIC);
+	if (!sched_group_nodes) {
+		printk(KERN_WARNING "Can not alloc sched group node list\n");
+		return;
+	}
+	sched_group_nodes_bycpu[first_cpu(*cpu_map)] = sched_group_nodes;
+#endif
+
+	/*
+	 * Set up domains for cpus specified by the cpu_map.
+	 */
+	for_each_cpu_mask(i, *cpu_map) {
+		int group;
+		struct sched_domain *sd = NULL, *p;
+		cpumask_t nodemask = node_to_cpumask(cpu_to_node(i));
+
+		cpus_and(nodemask, nodemask, *cpu_map);
+
+#ifdef CONFIG_NUMA
+		if (cpus_weight(*cpu_map)
+				> SD_NODES_PER_DOMAIN*cpus_weight(nodemask)) {
+			if (!sched_group_allnodes) {
+				sched_group_allnodes
+					= kmalloc(sizeof(struct sched_group)
+							* MAX_NUMNODES,
+						  GFP_KERNEL);
+				if (!sched_group_allnodes) {
+					printk(KERN_WARNING
+					"Can not alloc allnodes sched group\n");
+					break;
+				}
+				sched_group_allnodes_bycpu[i]
+						= sched_group_allnodes;
+			}
+			sd = &per_cpu(allnodes_domains, i);
+			*sd = SD_ALLNODES_INIT;
+			sd->span = *cpu_map;
+			group = cpu_to_allnodes_group(i);
+			sd->groups = &sched_group_allnodes[group];
+			p = sd;
+		} else
+			p = NULL;
+
+		sd = &per_cpu(node_domains, i);
+		*sd = SD_NODE_INIT;
+		sd->span = sched_domain_node_span(cpu_to_node(i));
+		sd->parent = p;
+		cpus_and(sd->span, sd->span, *cpu_map);
+#endif
+
+		p = sd;
+		sd = &per_cpu(phys_domains, i);
+		group = cpu_to_phys_group(i);
+		*sd = SD_CPU_INIT;
+		sd->span = nodemask;
+		sd->parent = p;
+		sd->groups = &sched_group_phys[group];
+
+#ifdef CONFIG_SCHED_SMT
+		p = sd;
+		sd = &per_cpu(cpu_domains, i);
+		group = cpu_to_cpu_group(i);
+		*sd = SD_SIBLING_INIT;
+		sd->span = cpu_sibling_map[i];
+		cpus_and(sd->span, sd->span, *cpu_map);
+		sd->parent = p;
+		sd->groups = &sched_group_cpus[group];
+#endif
+	}
+
+#ifdef CONFIG_SCHED_SMT
+	/* Set up CPU (sibling) groups */
+	for_each_cpu_mask(i, *cpu_map) {
+		cpumask_t this_sibling_map = cpu_sibling_map[i];
+		cpus_and(this_sibling_map, this_sibling_map, *cpu_map);
+		if (i != first_cpu(this_sibling_map))
+			continue;
+
+		init_sched_build_groups(sched_group_cpus, this_sibling_map,
+						&cpu_to_cpu_group);
+	}
+#endif
+
+	/* Set up physical groups */
+	for (i = 0; i < MAX_NUMNODES; i++) {
+		cpumask_t nodemask = node_to_cpumask(i);
+
+		cpus_and(nodemask, nodemask, *cpu_map);
+		if (cpus_empty(nodemask))
+			continue;
+
+		init_sched_build_groups(sched_group_phys, nodemask,
+						&cpu_to_phys_group);
+	}
+
+#ifdef CONFIG_NUMA
+	/* Set up node groups */
+	if (sched_group_allnodes)
+		init_sched_build_groups(sched_group_allnodes, *cpu_map,
+					&cpu_to_allnodes_group);
+
+	for (i = 0; i < MAX_NUMNODES; i++) {
+		/* Set up node groups */
+		struct sched_group *sg, *prev;
+		cpumask_t nodemask = node_to_cpumask(i);
+		cpumask_t domainspan;
+		cpumask_t covered = CPU_MASK_NONE;
+		int j;
+
+		cpus_and(nodemask, nodemask, *cpu_map);
+		if (cpus_empty(nodemask)) {
+			sched_group_nodes[i] = NULL;
+			continue;
+		}
+
+		domainspan = sched_domain_node_span(i);
+		cpus_and(domainspan, domainspan, *cpu_map);
+
+		sg = kmalloc(sizeof(struct sched_group), GFP_KERNEL);
+		sched_group_nodes[i] = sg;
+		for_each_cpu_mask(j, nodemask) {
+			struct sched_domain *sd;
+			sd = &per_cpu(node_domains, j);
+			sd->groups = sg;
+			if (sd->groups == NULL) {
+				/* Turn off balancing if we have no groups */
+				sd->flags = 0;
+			}
+		}
+		if (!sg) {
+			printk(KERN_WARNING
+			"Can not alloc domain group for node %d\n", i);
+			continue;
+		}
+		sg->cpu_power = 0;
+		sg->cpumask = nodemask;
+		cpus_or(covered, covered, nodemask);
+		prev = sg;
+
+		for (j = 0; j < MAX_NUMNODES; j++) {
+			cpumask_t tmp, notcovered;
+			int n = (i + j) % MAX_NUMNODES;
+
+			cpus_complement(notcovered, covered);
+			cpus_and(tmp, notcovered, *cpu_map);
+			cpus_and(tmp, tmp, domainspan);
+			if (cpus_empty(tmp))
+				break;
+
+			nodemask = node_to_cpumask(n);
+			cpus_and(tmp, tmp, nodemask);
+			if (cpus_empty(tmp))
+				continue;
+
+			sg = kmalloc(sizeof(struct sched_group), GFP_KERNEL);
+			if (!sg) {
+				printk(KERN_WARNING
+				"Can not alloc domain group for node %d\n", j);
+				break;
+			}
+			sg->cpu_power = 0;
+			sg->cpumask = tmp;
+			cpus_or(covered, covered, tmp);
+			prev->next = sg;
+			prev = sg;
+		}
+		prev->next = sched_group_nodes[i];
+	}
+#endif
+
+	/* Calculate CPU power for physical packages and nodes */
+	for_each_cpu_mask(i, *cpu_map) {
+		int power;
+		struct sched_domain *sd;
+#ifdef CONFIG_SCHED_SMT
+		sd = &per_cpu(cpu_domains, i);
+		power = SCHED_LOAD_SCALE;
+		sd->groups->cpu_power = power;
+#endif
+
+		sd = &per_cpu(phys_domains, i);
+		power = SCHED_LOAD_SCALE + SCHED_LOAD_SCALE *
+				(cpus_weight(sd->groups->cpumask)-1) / 10;
+		sd->groups->cpu_power = power;
+
+#ifdef CONFIG_NUMA
+		sd = &per_cpu(allnodes_domains, i);
+		if (sd->groups) {
+			power = SCHED_LOAD_SCALE + SCHED_LOAD_SCALE *
+				(cpus_weight(sd->groups->cpumask)-1) / 10;
+			sd->groups->cpu_power = power;
+		}
+#endif
+	}
+
+#ifdef CONFIG_NUMA
+	for (i = 0; i < MAX_NUMNODES; i++) {
+		struct sched_group *sg = sched_group_nodes[i];
+		int j;
+
+		if (sg == NULL)
+			continue;
+next_sg:
+		for_each_cpu_mask(j, sg->cpumask) {
+			struct sched_domain *sd;
+			int power;
+
+			sd = &per_cpu(phys_domains, j);
+			if (j != first_cpu(sd->groups->cpumask)) {
+				/*
+				 * Only add "power" once for each
+				 * physical package.
+				 */
+				continue;
+			}
+			power = SCHED_LOAD_SCALE + SCHED_LOAD_SCALE *
+				(cpus_weight(sd->groups->cpumask)-1) / 10;
+
+			sg->cpu_power += power;
+		}
+		sg = sg->next;
+		if (sg != sched_group_nodes[i])
+			goto next_sg;
+	}
+#endif
+
+	/* Attach the domains */
+	for_each_cpu_mask(i, *cpu_map) {
+		struct sched_domain *sd;
+#ifdef CONFIG_SCHED_SMT
+		sd = &per_cpu(cpu_domains, i);
+#else
+		sd = &per_cpu(phys_domains, i);
+#endif
+		cpu_attach_domain(sd, i);
+	}
+	/*
+	 * Tune cache-hot values:
+	 */
+	calibrate_migration_costs(cpu_map);
+}
+/*
+ * Set up scheduler domains and groups.  Callers must hold the hotplug lock.
+ */
+static void arch_init_sched_domains(const cpumask_t *cpu_map)
+{
+	cpumask_t cpu_default_map;
+
+	/*
+	 * Setup mask for cpus without special case scheduling requirements.
+	 * For now this just excludes isolated cpus, but could be used to
+	 * exclude other special cases in the future.
+	 */
+	cpus_andnot(cpu_default_map, *cpu_map, cpu_isolated_map);
+
+	build_sched_domains(&cpu_default_map);
+}
+
+static void arch_destroy_sched_domains(const cpumask_t *cpu_map)
+{
+#ifdef CONFIG_NUMA
+	int i;
+	int cpu;
+
+	for_each_cpu_mask(cpu, *cpu_map) {
+		struct sched_group *sched_group_allnodes
+			= sched_group_allnodes_bycpu[cpu];
+		struct sched_group **sched_group_nodes
+			= sched_group_nodes_bycpu[cpu];
+
+		if (sched_group_allnodes) {
+			kfree(sched_group_allnodes);
+			sched_group_allnodes_bycpu[cpu] = NULL;
+		}
+
+		if (!sched_group_nodes)
+			continue;
+
+		for (i = 0; i < MAX_NUMNODES; i++) {
+			cpumask_t nodemask = node_to_cpumask(i);
+			struct sched_group *oldsg, *sg = sched_group_nodes[i];
+
+			cpus_and(nodemask, nodemask, *cpu_map);
+			if (cpus_empty(nodemask))
+				continue;
+
+			if (sg == NULL)
+				continue;
+			sg = sg->next;
+next_sg:
+			oldsg = sg;
+			sg = sg->next;
+			kfree(oldsg);
+			if (oldsg != sched_group_nodes[i])
+				goto next_sg;
+		}
+		kfree(sched_group_nodes);
+		sched_group_nodes_bycpu[cpu] = NULL;
+	}
+#endif
+}
+
+/*
+ * Detach sched domains from a group of cpus specified in cpu_map
+ * These cpus will now be attached to the NULL domain
+ */
+static void detach_destroy_domains(const cpumask_t *cpu_map)
+{
+	int i;
+
+	for_each_cpu_mask(i, *cpu_map)
+		cpu_attach_domain(NULL, i);
+	synchronize_sched();
+	arch_destroy_sched_domains(cpu_map);
+}
+
+/*
+ * Partition sched domains as specified by the cpumasks below.
+ * This attaches all cpus from the cpumasks to the NULL domain,
+ * waits for a RCU quiescent period, recalculates sched
+ * domain information and then attaches them back to the
+ * correct sched domains
+ * Call with hotplug lock held
+ */
+void partition_sched_domains(cpumask_t *partition1, cpumask_t *partition2)
+{
+	cpumask_t change_map;
+
+	cpus_and(*partition1, *partition1, cpu_online_map);
+	cpus_and(*partition2, *partition2, cpu_online_map);
+	cpus_or(change_map, *partition1, *partition2);
+
+	/* Detach sched domains from all of the affected cpus */
+	detach_destroy_domains(&change_map);
+	if (!cpus_empty(*partition1))
+		build_sched_domains(partition1);
+	if (!cpus_empty(*partition2))
+		build_sched_domains(partition2);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+/*
+ * Force a reinitialization of the sched domains hierarchy.  The domains
+ * and groups cannot be updated in place without racing with the balancing
+ * code, so we temporarily attach all running cpus to the NULL domain
+ * which will prevent rebalancing while the sched domains are recalculated.
+ */
+static int update_sched_domains(struct notifier_block *nfb,
+				unsigned long action, void *hcpu)
+{
+	switch (action) {
+	case CPU_UP_PREPARE:
+	case CPU_DOWN_PREPARE:
+		detach_destroy_domains(&cpu_online_map);
+		return NOTIFY_OK;
+
+	case CPU_UP_CANCELED:
+	case CPU_DOWN_FAILED:
+	case CPU_ONLINE:
+	case CPU_DEAD:
+		/*
+		 * Fall through and re-initialise the domains.
+		 */
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	/* The hotplug lock is already held by cpu_up/cpu_down */
+	arch_init_sched_domains(&cpu_online_map);
+
+	return NOTIFY_OK;
+}
+#endif
+
+void __init sched_init_smp(void)
+{
+	lock_cpu_hotplug();
+	arch_init_sched_domains(&cpu_online_map);
+	unlock_cpu_hotplug();
+	/* XXX: Theoretical race here - CPU may be hotplugged now */
+	hotcpu_notifier(update_sched_domains, 0);
+}
+#else
+void __init sched_init_smp(void)
+{
+}
+#endif /* CONFIG_SMP */
+
+int in_sched_functions(unsigned long addr)
+{
+	/* Linker adds these: start and end of __sched functions */
+	extern char __sched_text_start[], __sched_text_end[];
+	return in_lock_functions(addr) ||
+		(addr >= (unsigned long)__sched_text_start
+		&& addr < (unsigned long)__sched_text_end);
+}
+
+void __init sched_init(void)
+{
+	runqueue_t *rq;
+	int i, j, k;
+
+	for_each_cpu(i) {
+		prio_array_t *array;
+
+		rq = cpu_rq(i);
+		spin_lock_init(&rq->lock);
+		rq->nr_running = 0;
+		rq->active = rq->arrays;
+		rq->expired = rq->arrays + 1;
+		rq->best_expired_prio = MAX_PRIO;
+
+#ifdef CONFIG_SMP
+		rq->sd = NULL;
+		for (j = 1; j < 3; j++)
+			rq->cpu_load[j] = 0;
+		rq->active_balance = 0;
+		rq->push_cpu = 0;
+		rq->migration_thread = NULL;
+		INIT_LIST_HEAD(&rq->migration_queue);
+#endif
+		atomic_set(&rq->nr_iowait, 0);
+
+		for (j = 0; j < 2; j++) {
+			array = rq->arrays + j;
+			for (k = 0; k < MAX_PRIO; k++) {
+				INIT_LIST_HEAD(array->queue + k);
+				__clear_bit(k, array->bitmap);
+			}
+			// delimiter for bitsearch
+			__set_bit(MAX_PRIO, array->bitmap);
+		}
+	}
+
+	/*
+	 * The boot idle thread does lazy MMU switching as well:
+	 */
+	atomic_inc(&init_mm.mm_count);
+	enter_lazy_tlb(&init_mm, current);
+
+	/*
+	 * Make us the idle thread. Technically, schedule() should not be
+	 * called from this thread, however somewhere below it might be,
+	 * but because we are the idle thread, we just pick up running again
+	 * when this runqueue becomes "idle".
+	 */
+	init_idle(current, smp_processor_id());
+}
+
+#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
+void __might_sleep(char *file, int line)
+{
+#if defined(in_atomic)
+	static unsigned long prev_jiffy;	/* ratelimiting */
+
+	if ((in_atomic() || irqs_disabled()) &&
+	    system_state == SYSTEM_RUNNING && !oops_in_progress) {
+		if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
+			return;
+		prev_jiffy = jiffies;
+		printk(KERN_ERR "Debug: sleeping function called from invalid"
+				" context at %s:%d\n", file, line);
+		printk("in_atomic():%d, irqs_disabled():%d\n",
+			in_atomic(), irqs_disabled());
+		dump_stack();
+	}
+#endif
+}
+EXPORT_SYMBOL(__might_sleep);
+#endif
+
+#ifdef CONFIG_MAGIC_SYSRQ
+void normalize_rt_tasks(void)
+{
+	struct task_struct *p;
+	prio_array_t *array;
+	unsigned long flags;
+	runqueue_t *rq;
+
+	read_lock_irq(&tasklist_lock);
+	for_each_process (p) {
+		if (!rt_task(p))
+			continue;
+
+		rq = task_rq_lock(p, &flags);
+
+		array = p->array;
+		if (array)
+			deactivate_task(p, task_rq(p));
+		__setscheduler(p, SCHED_NORMAL, 0);
+		if (array) {
+			__activate_task(p, task_rq(p));
+			resched_task(rq->curr);
+		}
+
+		task_rq_unlock(rq, &flags);
+	}
+	read_unlock_irq(&tasklist_lock);
+}
+
+#endif /* CONFIG_MAGIC_SYSRQ */
+
+#ifdef CONFIG_IA64
+/*
+ * These functions are only useful for the IA64 MCA handling.
+ *
+ * They can only be called when the whole system has been
+ * stopped - every CPU needs to be quiescent, and no scheduling
+ * activity can take place. Using them for anything else would
+ * be a serious bug, and as a result, they aren't even visible
+ * under any other configuration.
+ */
+
+/**
+ * curr_task - return the current task for a given cpu.
+ * @cpu: the processor in question.
+ *
+ * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
+ */
+task_t *curr_task(int cpu)
+{
+	return cpu_curr(cpu);
+}
+
+/**
+ * set_curr_task - set the current task for a given cpu.
+ * @cpu: the processor in question.
+ * @p: the task pointer to set.
+ *
+ * Description: This function must only be used when non-maskable interrupts
+ * are serviced on a separate stack.  It allows the architecture to switch the
+ * notion of the current task on a cpu in a non-blocking manner.  This function
+ * must be called with all CPU's synchronized, and interrupts disabled, the
+ * and caller must save the original value of the current task (see
+ * curr_task() above) and restore that value before reenabling interrupts and
+ * re-starting the system.
+ *
+ * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
+ */
+void set_curr_task(int cpu, task_t *p)
+{
+	cpu_curr(cpu) = p;
+}
+
+#endif
diff -urN oldtree/kernel/softirq.c newtree/kernel/softirq.c
--- oldtree/kernel/softirq.c	2006-01-03 03:21:10.000000000 +0000
+++ newtree/kernel/softirq.c	2006-02-18 15:24:31.436809808 +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	2006-02-18 15:18:30.099741392 +0000
+++ newtree/kernel/sys.c	2006-02-18 15:24:31.438809504 +0000
@@ -174,15 +174,18 @@
 {
 	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;
 }
@@ -544,12 +547,12 @@
 		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	2006-02-18 15:18:30.103740784 +0000
+++ newtree/kernel/workqueue.c	2006-02-18 15:24:31.439809352 +0000
@@ -191,8 +191,6 @@
 	struct k_sigaction sa;
 	sigset_t blocked;
 
-	current->flags |= PF_NOFREEZE;
-
 	set_user_nice(current, -5);
 
 	/* Block and flush all signals */
@@ -213,6 +211,7 @@
 			schedule();
 		else
 			__set_current_state(TASK_RUNNING);
+		try_to_freeze();
 		remove_wait_queue(&cwq->more_work, &wait);
 
 		if (!list_empty(&cwq->worklist))
@@ -282,7 +281,8 @@
 }
 
 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;
@@ -296,10 +296,21 @@
 	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;
@@ -307,7 +318,8 @@
 }
 
 struct workqueue_struct *__create_workqueue(const char *name,
-					    int singlethread)
+					    int singlethread,
+					    unsigned long freezer_flags)
 {
 	int cpu, destroy = 0;
 	struct workqueue_struct *wq;
@@ -328,7 +340,7 @@
 	lock_cpu_hotplug();
 	if (singlethread) {
 		INIT_LIST_HEAD(&wq->list);
-		p = create_workqueue_thread(wq, singlethread_cpu);
+		p = create_workqueue_thread(wq, singlethread_cpu, freezer_flags);
 		if (!p)
 			destroy = 1;
 		else
@@ -338,7 +350,7 @@
 		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);
@@ -529,7 +541,7 @@
 	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;
 			}
@@ -572,7 +584,7 @@
 {
 	singlethread_cpu = first_cpu(cpu_possible_map);
 	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	2006-01-03 03:21:10.000000000 +0000
+++ newtree/lib/Kconfig	2006-02-18 15:24:31.440809200 +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	2006-02-18 15:18:30.104740632 +0000
+++ newtree/lib/Makefile	2006-02-18 15:24:31.441809048 +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	2006-02-18 15:24:31.442808896 +0000
@@ -0,0 +1,330 @@
+/*
+ * lib/dyn_pageflags.c
+ *
+ * Copyright (C) 2004-2006 Nigel Cunningham <nigel@suspend2.net>
+ * 
+ * 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/bootmem.h>
+
+#define page_to_zone_offset(pg) (page_to_pfn(pg) - page_zone(pg)->zone_start_pfn)
+
+/* 
+ * num_zones
+ * 
+ * How many zones are there?
+ *
+ */
+
+static int num_zones(void)
+{
+	int result = 0;
+	struct zone *zone;
+
+	for_each_zone(zone)
+		result++;
+
+	return result;
+}
+
+/* 
+ * pages_for_zone(struct zone *zone)
+ * 
+ * How many pages do we need for a bitmap for this zone?
+ *
+ */
+
+static int pages_for_zone(struct zone *zone)
+{
+	return (zone->spanned_pages + (PAGE_SIZE << 3) - 1) >>
+			(PAGE_SHIFT + 3);
+}
+
+/*
+ * page_zone_number(struct page *page)
+ *
+ * Which zone index does the page match?
+ *
+ */
+
+static 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_dyn_pageflags(dyn_pageflags_t pagemap)
+ *
+ * Clear an array used to store local page flags.
+ *
+ */
+
+void clear_dyn_pageflags(dyn_pageflags_t pagemap)
+{
+	int i = 0, zone_num = 0;
+	struct zone *zone;
+	
+	BUG_ON(!pagemap);
+
+	for_each_zone(zone) {
+		for (i = 0; i < pages_for_zone(zone); i++)
+			memset((pagemap[zone_num][i]), 0, PAGE_SIZE);
+		zone_num++;
+	}
+}
+
+/* 
+ * allocate_dyn_pageflags(dyn_pageflags_t *pagemap)
+ *
+ * Allocate a bitmap for dynamic page flags.
+ *
+ */
+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 -ENOMEM;
+
+	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 -ENOMEM;
+		}
+
+		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 -ENOMEM;
+			}
+		}
+		zone_num++;
+	}
+
+	return 0;
+}
+
+/* 
+ * free_dyn_pageflags(dyn_pageflags_t *pagemap)
+ *
+ * Free a dynamically allocated pageflags bitmap. For Suspend2 usage, we
+ * support data being relocated from slab to pages that don't conflict
+ * with the image that will be copied back. This is the reason for the
+ * PageSlab tests below.
+ *
+ */
+void free_dyn_pageflags(dyn_pageflags_t *pagemap)
+{
+	int i = 0, zone_num = 0;
+	struct zone *zone;
+
+	if (!*pagemap)
+		return;
+	
+	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;
+}
+
+/*
+ * dyn_pageflags_ul_ptr(dyn_pageflags_t *bitmap, struct page *pg)
+ *
+ * Get a pointer to the unsigned long containing the flag in the bitmap
+ * for the given page.
+ *
+ */
+
+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;
+}
+
+/*
+ * test_dynpageflag(dyn_pageflags_t *bitmap, struct page *page)
+ *
+ * Is the page flagged in the given bitmap?
+ *
+ */
+
+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);
+}
+
+/*
+ * set_dynpageflag(dyn_pageflags_t *bitmap, struct page *page)
+ *
+ * Set the flag for the page in the given bitmap.
+ *
+ */
+
+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);
+}
+
+/*
+ * clear_dynpageflags(dyn_pageflags_t *bitmap, struct page *page)
+ *
+ * Clear the flag for the page in the given bitmap.
+ *
+ */
+
+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);
+}
+
+/*
+ * get_next_bit_on(dyn_pageflags_t bitmap, int counter)
+ *
+ * Given a pfn (possibly -1), find the next pfn in the bitmap that
+ * is set. If there are no more flags set, return max_pfn.
+ *
+ */
+
+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	2006-01-03 03:21:10.000000000 +0000
+++ newtree/lib/vsprintf.c	2006-02-18 15:24:31.443808744 +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/memory.c newtree/mm/memory.c
--- oldtree/mm/memory.c	2006-02-18 15:18:30.117738656 +0000
+++ newtree/mm/memory.c	2006-02-18 15:24:31.445808440 +0000
@@ -960,6 +960,15 @@
 	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/memory.c.orig newtree/mm/memory.c.orig
--- oldtree/mm/memory.c.orig	1970-01-01 00:00:00.000000000 +0000
+++ newtree/mm/memory.c.orig	2006-02-18 15:18:30.000000000 +0000
@@ -0,0 +1,2446 @@
+/*
+ *  linux/mm/memory.c
+ *
+ *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
+ */
+
+/*
+ * demand-loading started 01.12.91 - seems it is high on the list of
+ * things wanted, and it should be easy to implement. - Linus
+ */
+
+/*
+ * Ok, demand-loading was easy, shared pages a little bit tricker. Shared
+ * pages started 02.12.91, seems to work. - Linus.
+ *
+ * Tested sharing by executing about 30 /bin/sh: under the old kernel it
+ * would have taken more than the 6M I have free, but it worked well as
+ * far as I could see.
+ *
+ * Also corrected some "invalidate()"s - I wasn't doing enough of them.
+ */
+
+/*
+ * Real VM (paging to/from disk) started 18.12.91. Much more work and
+ * thought has to go into this. Oh, well..
+ * 19.12.91  -  works, somewhat. Sometimes I get faults, don't know why.
+ *		Found it. Everything seems to work now.
+ * 20.12.91  -  Ok, making the swap-device changeable like the root.
+ */
+
+/*
+ * 05.04.94  -  Multi-page memory management added for v1.1.
+ * 		Idea by Alex Bligh (alex@cconcepts.co.uk)
+ *
+ * 16.07.99  -  Support of BIGMEM added by Gerhard Wichert, Siemens AG
+ *		(Gerhard.Wichert@pdb.siemens.de)
+ *
+ * Aug/Sep 2004 Changed to four level page tables (Andi Kleen)
+ */
+
+#include <linux/kernel_stat.h>
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <linux/mman.h>
+#include <linux/swap.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+#include <linux/rmap.h>
+#include <linux/module.h>
+#include <linux/init.h>
+
+#include <asm/pgalloc.h>
+#include <asm/uaccess.h>
+#include <asm/tlb.h>
+#include <asm/tlbflush.h>
+#include <asm/pgtable.h>
+
+#include <linux/swapops.h>
+#include <linux/elf.h>
+
+#ifndef CONFIG_NEED_MULTIPLE_NODES
+/* use the per-pgdat data instead for discontigmem - mbligh */
+unsigned long max_mapnr;
+struct page *mem_map;
+
+EXPORT_SYMBOL(max_mapnr);
+EXPORT_SYMBOL(mem_map);
+#endif
+
+unsigned long num_physpages;
+/*
+ * A number of key systems in x86 including ioremap() rely on the assumption
+ * that high_memory defines the upper bound on direct map memory, then end
+ * of ZONE_NORMAL.  Under CONFIG_DISCONTIG this means that max_low_pfn and
+ * highstart_pfn must be the same; there must be no gap between ZONE_NORMAL
+ * and ZONE_HIGHMEM.
+ */
+void * high_memory;
+unsigned long vmalloc_earlyreserve;
+
+EXPORT_SYMBOL(num_physpages);
+EXPORT_SYMBOL(high_memory);
+EXPORT_SYMBOL(vmalloc_earlyreserve);
+
+int randomize_va_space __read_mostly = 1;
+
+static int __init disable_randmaps(char *s)
+{
+	randomize_va_space = 0;
+	return 0;
+}
+__setup("norandmaps", disable_randmaps);
+
+
+/*
+ * If a p?d_bad entry is found while walking page tables, report
+ * the error, before resetting entry to p?d_none.  Usually (but
+ * very seldom) called out from the p?d_none_or_clear_bad macros.
+ */
+
+void pgd_clear_bad(pgd_t *pgd)
+{
+	pgd_ERROR(*pgd);
+	pgd_clear(pgd);
+}
+
+void pud_clear_bad(pud_t *pud)
+{
+	pud_ERROR(*pud);
+	pud_clear(pud);
+}
+
+void pmd_clear_bad(pmd_t *pmd)
+{
+	pmd_ERROR(*pmd);
+	pmd_clear(pmd);
+}
+
+/*
+ * Note: this doesn't free the actual pages themselves. That
+ * has been handled earlier when unmapping all the memory regions.
+ */
+static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd)
+{
+	struct page *page = pmd_page(*pmd);
+	pmd_clear(pmd);
+	pte_lock_deinit(page);
+	pte_free_tlb(tlb, page);
+	dec_page_state(nr_page_table_pages);
+	tlb->mm->nr_ptes--;
+}
+
+static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
+				unsigned long addr, unsigned long end,
+				unsigned long floor, unsigned long ceiling)
+{
+	pmd_t *pmd;
+	unsigned long next;
+	unsigned long start;
+
+	start = addr;
+	pmd = pmd_offset(pud, addr);
+	do {
+		next = pmd_addr_end(addr, end);
+		if (pmd_none_or_clear_bad(pmd))
+			continue;
+		free_pte_range(tlb, pmd);
+	} while (pmd++, addr = next, addr != end);
+
+	start &= PUD_MASK;
+	if (start < floor)
+		return;
+	if (ceiling) {
+		ceiling &= PUD_MASK;
+		if (!ceiling)
+			return;
+	}
+	if (end - 1 > ceiling - 1)
+		return;
+
+	pmd = pmd_offset(pud, start);
+	pud_clear(pud);
+	pmd_free_tlb(tlb, pmd);
+}
+
+static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
+				unsigned long addr, unsigned long end,
+				unsigned long floor, unsigned long ceiling)
+{
+	pud_t *pud;
+	unsigned long next;
+	unsigned long start;
+
+	start = addr;
+	pud = pud_offset(pgd, addr);
+	do {
+		next = pud_addr_end(addr, end);
+		if (pud_none_or_clear_bad(pud))
+			continue;
+		free_pmd_range(tlb, pud, addr, next, floor, ceiling);
+	} while (pud++, addr = next, addr != end);
+
+	start &= PGDIR_MASK;
+	if (start < floor)
+		return;
+	if (ceiling) {
+		ceiling &= PGDIR_MASK;
+		if (!ceiling)
+			return;
+	}
+	if (end - 1 > ceiling - 1)
+		return;
+
+	pud = pud_offset(pgd, start);
+	pgd_clear(pgd);
+	pud_free_tlb(tlb, pud);
+}
+
+/*
+ * This function frees user-level page tables of a process.
+ *
+ * Must be called with pagetable lock held.
+ */
+void free_pgd_range(struct mmu_gather **tlb,
+			unsigned long addr, unsigned long end,
+			unsigned long floor, unsigned long ceiling)
+{
+	pgd_t *pgd;
+	unsigned long next;
+	unsigned long start;
+
+	/*
+	 * The next few lines have given us lots of grief...
+	 *
+	 * Why are we testing PMD* at this top level?  Because often
+	 * there will be no work to do at all, and we'd prefer not to
+	 * go all the way down to the bottom just to discover that.
+	 *
+	 * Why all these "- 1"s?  Because 0 represents both the bottom
+	 * of the address space and the top of it (using -1 for the
+	 * top wouldn't help much: the masks would do the wrong thing).
+	 * The rule is that addr 0 and floor 0 refer to the bottom of
+	 * the address space, but end 0 and ceiling 0 refer to the top
+	 * Comparisons need to use "end - 1" and "ceiling - 1" (though
+	 * that end 0 case should be mythical).
+	 *
+	 * Wherever addr is brought up or ceiling brought down, we must
+	 * be careful to reject "the opposite 0" before it confuses the
+	 * subsequent tests.  But what about where end is brought down
+	 * by PMD_SIZE below? no, end can't go down to 0 there.
+	 *
+	 * Whereas we round start (addr) and ceiling down, by different
+	 * masks at different levels, in order to test whether a table
+	 * now has no other vmas using it, so can be freed, we don't
+	 * bother to round floor or end up - the tests don't need that.
+	 */
+
+	addr &= PMD_MASK;
+	if (addr < floor) {
+		addr += PMD_SIZE;
+		if (!addr)
+			return;
+	}
+	if (ceiling) {
+		ceiling &= PMD_MASK;
+		if (!ceiling)
+			return;
+	}
+	if (end - 1 > ceiling - 1)
+		end -= PMD_SIZE;
+	if (addr > end - 1)
+		return;
+
+	start = addr;
+	pgd = pgd_offset((*tlb)->mm, addr);
+	do {
+		next = pgd_addr_end(addr, end);
+		if (pgd_none_or_clear_bad(pgd))
+			continue;
+		free_pud_range(*tlb, pgd, addr, next, floor, ceiling);
+	} while (pgd++, addr = next, addr != end);
+
+	if (!(*tlb)->fullmm)
+		flush_tlb_pgtables((*tlb)->mm, start, end);
+}
+
+void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *vma,
+		unsigned long floor, unsigned long ceiling)
+{
+	while (vma) {
+		struct vm_area_struct *next = vma->vm_next;
+		unsigned long addr = vma->vm_start;
+
+		/*
+		 * Hide vma from rmap and vmtruncate before freeing pgtables
+		 */
+		anon_vma_unlink(vma);
+		unlink_file_vma(vma);
+
+		if (is_hugepage_only_range(vma->vm_mm, addr, HPAGE_SIZE)) {
+			hugetlb_free_pgd_range(tlb, addr, vma->vm_end,
+				floor, next? next->vm_start: ceiling);
+		} else {
+			/*
+			 * Optimization: gather nearby vmas into one call down
+			 */
+			while (next && next->vm_start <= vma->vm_end + PMD_SIZE
+			  && !is_hugepage_only_range(vma->vm_mm, next->vm_start,
+							HPAGE_SIZE)) {
+				vma = next;
+				next = vma->vm_next;
+				anon_vma_unlink(vma);
+				unlink_file_vma(vma);
+			}
+			free_pgd_range(tlb, addr, vma->vm_end,
+				floor, next? next->vm_start: ceiling);
+		}
+		vma = next;
+	}
+}
+
+int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address)
+{
+	struct page *new = pte_alloc_one(mm, address);
+	if (!new)
+		return -ENOMEM;
+
+	pte_lock_init(new);
+	spin_lock(&mm->page_table_lock);
+	if (pmd_present(*pmd)) {	/* Another has populated it */
+		pte_lock_deinit(new);
+		pte_free(new);
+	} else {
+		mm->nr_ptes++;
+		inc_page_state(nr_page_table_pages);
+		pmd_populate(mm, pmd, new);
+	}
+	spin_unlock(&mm->page_table_lock);
+	return 0;
+}
+
+int __pte_alloc_kernel(pmd_t *pmd, unsigned long address)
+{
+	pte_t *new = pte_alloc_one_kernel(&init_mm, address);
+	if (!new)
+		return -ENOMEM;
+
+	spin_lock(&init_mm.page_table_lock);
+	if (pmd_present(*pmd))		/* Another has populated it */
+		pte_free_kernel(new);
+	else
+		pmd_populate_kernel(&init_mm, pmd, new);
+	spin_unlock(&init_mm.page_table_lock);
+	return 0;
+}
+
+static inline void add_mm_rss(struct mm_struct *mm, int file_rss, int anon_rss)
+{
+	if (file_rss)
+		add_mm_counter(mm, file_rss, file_rss);
+	if (anon_rss)
+		add_mm_counter(mm, anon_rss, anon_rss);
+}
+
+/*
+ * This function is called to print an error when a bad pte
+ * is found. For example, we might have a PFN-mapped pte in
+ * a region that doesn't allow it.
+ *
+ * The calling function must still handle the error.
+ */
+void print_bad_pte(struct vm_area_struct *vma, pte_t pte, unsigned long vaddr)
+{
+	printk(KERN_ERR "Bad pte = %08llx, process = %s, "
+			"vm_flags = %lx, vaddr = %lx\n",
+		(long long)pte_val(pte),
+		(vma->vm_mm == current->mm ? current->comm : "???"),
+		vma->vm_flags, vaddr);
+	dump_stack();
+}
+
+static inline int is_cow_mapping(unsigned int flags)
+{
+	return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
+}
+
+/*
+ * This function gets the "struct page" associated with a pte.
+ *
+ * NOTE! Some mappings do not have "struct pages". A raw PFN mapping
+ * will have each page table entry just pointing to a raw page frame
+ * number, and as far as the VM layer is concerned, those do not have
+ * pages associated with them - even if the PFN might point to memory
+ * that otherwise is perfectly fine and has a "struct page".
+ *
+ * The way we recognize those mappings is through the rules set up
+ * by "remap_pfn_range()": the vma will have the VM_PFNMAP bit set,
+ * and the vm_pgoff will point to the first PFN mapped: thus every
+ * page that is a raw mapping will always honor the rule
+ *
+ *	pfn_of_page == vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT)
+ *
+ * and if that isn't true, the page has been COW'ed (in which case it
+ * _does_ have a "struct page" associated with it even if it is in a
+ * VM_PFNMAP range).
+ */
+struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte)
+{
+	unsigned long pfn = pte_pfn(pte);
+
+	if (vma->vm_flags & VM_PFNMAP) {
+		unsigned long off = (addr - vma->vm_start) >> PAGE_SHIFT;
+		if (pfn == vma->vm_pgoff + off)
+			return NULL;
+		if (!is_cow_mapping(vma->vm_flags))
+			return NULL;
+	}
+
+	/*
+	 * Add some anal sanity checks for now. Eventually,
+	 * we should just do "return pfn_to_page(pfn)", but
+	 * in the meantime we check that we get a valid pfn,
+	 * and that the resulting page looks ok.
+	 *
+	 * Remove this test eventually!
+	 */
+	if (unlikely(!pfn_valid(pfn))) {
+		print_bad_pte(vma, pte, addr);
+		return NULL;
+	}
+
+	/*
+	 * NOTE! We still have PageReserved() pages in the page 
+	 * tables. 
+	 *
+	 * The PAGE_ZERO() pages and various VDSO mappings can
+	 * cause them to exist.
+	 */
+	return pfn_to_page(pfn);
+}
+
+/*
+ * copy one vm_area from one task to the other. Assumes the page tables
+ * already present in the new task to be cleared in the whole range
+ * covered by this vma.
+ */
+
+static inline void
+copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+		pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma,
+		unsigned long addr, int *rss)
+{
+	unsigned long vm_flags = vma->vm_flags;
+	pte_t pte = *src_pte;
+	struct page *page;
+
+	/* pte contains position in swap or file, so copy. */
+	if (unlikely(!pte_present(pte))) {
+		if (!pte_file(pte)) {
+			swap_duplicate(pte_to_swp_entry(pte));
+			/* make sure dst_mm is on swapoff's mmlist. */
+			if (unlikely(list_empty(&dst_mm->mmlist))) {
+				spin_lock(&mmlist_lock);
+				if (list_empty(&dst_mm->mmlist))
+					list_add(&dst_mm->mmlist,
+						 &src_mm->mmlist);
+				spin_unlock(&mmlist_lock);
+			}
+		}
+		goto out_set_pte;
+	}
+
+	/*
+	 * If it's a COW mapping, write protect it both
+	 * in the parent and the child
+	 */
+	if (is_cow_mapping(vm_flags)) {
+		ptep_set_wrprotect(src_mm, addr, src_pte);
+		pte = *src_pte;
+	}
+
+	/*
+	 * If it's a shared mapping, mark it clean in
+	 * the child
+	 */
+	if (vm_flags & VM_SHARED)
+		pte = pte_mkclean(pte);
+	pte = pte_mkold(pte);
+
+	page = vm_normal_page(vma, addr, pte);
+	if (page) {
+		get_page(page);
+		page_dup_rmap(page);
+		rss[!!PageAnon(page)]++;
+	}
+
+out_set_pte:
+	set_pte_at(dst_mm, addr, dst_pte, pte);
+}
+
+static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+		pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma,
+		unsigned long addr, unsigned long end)
+{
+	pte_t *src_pte, *dst_pte;
+	spinlock_t *src_ptl, *dst_ptl;
+	int progress = 0;
+	int rss[2];
+
+again:
+	rss[1] = rss[0] = 0;
+	dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl);
+	if (!dst_pte)
+		return -ENOMEM;
+	src_pte = pte_offset_map_nested(src_pmd, addr);
+	src_ptl = pte_lockptr(src_mm, src_pmd);
+	spin_lock(src_ptl);
+
+	do {
+		/*
+		 * We are holding two locks at this point - either of them
+		 * could generate latencies in another task on another CPU.
+		 */
+		if (progress >= 32) {
+			progress = 0;
+			if (need_resched() ||
+			    need_lockbreak(src_ptl) ||
+			    need_lockbreak(dst_ptl))
+				break;
+		}
+		if (pte_none(*src_pte)) {
+			progress++;
+			continue;
+		}
+		copy_one_pte(dst_mm, src_mm, dst_pte, src_pte, vma, addr, rss);
+		progress += 8;
+	} while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);
+
+	spin_unlock(src_ptl);
+	pte_unmap_nested(src_pte - 1);
+	add_mm_rss(dst_mm, rss[0], rss[1]);
+	pte_unmap_unlock(dst_pte - 1, dst_ptl);
+	cond_resched();
+	if (addr != end)
+		goto again;
+	return 0;
+}
+
+static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+		pud_t *dst_pud, pud_t *src_pud, struct vm_area_struct *vma,
+		unsigned long addr, unsigned long end)
+{
+	pmd_t *src_pmd, *dst_pmd;
+	unsigned long next;
+
+	dst_pmd = pmd_alloc(dst_mm, dst_pud, addr);
+	if (!dst_pmd)
+		return -ENOMEM;
+	src_pmd = pmd_offset(src_pud, addr);
+	do {
+		next = pmd_addr_end(addr, end);
+		if (pmd_none_or_clear_bad(src_pmd))
+			continue;
+		if (copy_pte_range(dst_mm, src_mm, dst_pmd, src_pmd,
+						vma, addr, next))
+			return -ENOMEM;
+	} while (dst_pmd++, src_pmd++, addr = next, addr != end);
+	return 0;
+}
+
+static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+		pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma,
+		unsigned long addr, unsigned long end)
+{
+	pud_t *src_pud, *dst_pud;
+	unsigned long next;
+
+	dst_pud = pud_alloc(dst_mm, dst_pgd, addr);
+	if (!dst_pud)
+		return -ENOMEM;
+	src_pud = pud_offset(src_pgd, addr);
+	do {
+		next = pud_addr_end(addr, end);
+		if (pud_none_or_clear_bad(src_pud))
+			continue;
+		if (copy_pmd_range(dst_mm, src_mm, dst_pud, src_pud,
+						vma, addr, next))
+			return -ENOMEM;
+	} while (dst_pud++, src_pud++, addr = next, addr != end);
+	return 0;
+}
+
+int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+		struct vm_area_struct *vma)
+{
+	pgd_t *src_pgd, *dst_pgd;
+	unsigned long next;
+	unsigned long addr = vma->vm_start;
+	unsigned long end = vma->vm_end;
+
+	/*
+	 * Don't copy ptes where a page fault will fill them correctly.
+	 * Fork becomes much lighter when there are big shared or private
+	 * readonly mappings. The tradeoff is that copy_page_range is more
+	 * efficient than faulting.
+	 */
+	if (!(vma->vm_flags & (VM_HUGETLB|VM_NONLINEAR|VM_PFNMAP|VM_INSERTPAGE))) {
+		if (!vma->anon_vma)
+			return 0;
+	}
+
+	if (is_vm_hugetlb_page(vma))
+		return copy_hugetlb_page_range(dst_mm, src_mm, vma);
+
+	dst_pgd = pgd_offset(dst_mm, addr);
+	src_pgd = pgd_offset(src_mm, addr);
+	do {
+		next = pgd_addr_end(addr, end);
+		if (pgd_none_or_clear_bad(src_pgd))
+			continue;
+		if (copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd,
+						vma, addr, next))
+			return -ENOMEM;
+	} while (dst_pgd++, src_pgd++, addr = next, addr != end);
+	return 0;
+}
+
+static unsigned long zap_pte_range(struct mmu_gather *tlb,
+				struct vm_area_struct *vma, pmd_t *pmd,
+				unsigned long addr, unsigned long end,
+				long *zap_work, struct zap_details *details)
+{
+	struct mm_struct *mm = tlb->mm;
+	pte_t *pte;
+	spinlock_t *ptl;
+	int file_rss = 0;
+	int anon_rss = 0;
+
+	pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+	do {
+		pte_t ptent = *pte;
+		if (pte_none(ptent)) {
+			(*zap_work)--;
+			continue;
+		}
+		if (pte_present(ptent)) {
+			struct page *page;
+
+			(*zap_work) -= PAGE_SIZE;
+
+			page = vm_normal_page(vma, addr, ptent);
+			if (unlikely(details) && page) {
+				/*
+				 * unmap_shared_mapping_pages() wants to
+				 * invalidate cache without truncating:
+				 * unmap shared but keep private pages.
+				 */
+				if (details->check_mapping &&
+				    details->check_mapping != page->mapping)
+					continue;
+				/*
+				 * Each page->index must be checked when
+				 * invalidating or truncating nonlinear.
+				 */
+				if (details->nonlinear_vma &&
+				    (page->index < details->first_index ||
+				     page->index > details->last_index))
+					continue;
+			}
+			ptent = ptep_get_and_clear_full(mm, addr, pte,
+							tlb->fullmm);
+			tlb_remove_tlb_entry(tlb, pte, addr);
+			if (unlikely(!page))
+				continue;
+			if (unlikely(details) && details->nonlinear_vma
+			    && linear_page_index(details->nonlinear_vma,
+						addr) != page->index)
+				set_pte_at(mm, addr, pte,
+					   pgoff_to_pte(page->index));
+			if (PageAnon(page))
+				anon_rss--;
+			else {
+				if (pte_dirty(ptent))
+					set_page_dirty(page);
+				if (pte_young(ptent))
+					mark_page_accessed(page);
+				file_rss--;
+			}
+			page_remove_rmap(page);
+			tlb_remove_page(tlb, page);
+			continue;
+		}
+		/*
+		 * If details->check_mapping, we leave swap entries;
+		 * if details->nonlinear_vma, we leave file entries.
+		 */
+		if (unlikely(details))
+			continue;
+		if (!pte_file(ptent))
+			free_swap_and_cache(pte_to_swp_entry(ptent));
+		pte_clear_full(mm, addr, pte, tlb->fullmm);
+	} while (pte++, addr += PAGE_SIZE, (addr != end && *zap_work > 0));
+
+	add_mm_rss(mm, file_rss, anon_rss);
+	pte_unmap_unlock(pte - 1, ptl);
+
+	return addr;
+}
+
+static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
+				struct vm_area_struct *vma, pud_t *pud,
+				unsigned long addr, unsigned long end,
+				long *zap_work, struct zap_details *details)
+{
+	pmd_t *pmd;
+	unsigned long next;
+
+	pmd = pmd_offset(pud, addr);
+	do {
+		next = pmd_addr_end(addr, end);
+		if (pmd_none_or_clear_bad(pmd)) {
+			(*zap_work)--;
+			continue;
+		}
+		next = zap_pte_range(tlb, vma, pmd, addr, next,
+						zap_work, details);
+	} while (pmd++, addr = next, (addr != end && *zap_work > 0));
+
+	return addr;
+}
+
+static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
+				struct vm_area_struct *vma, pgd_t *pgd,
+				unsigned long addr, unsigned long end,
+				long *zap_work, struct zap_details *details)
+{
+	pud_t *pud;
+	unsigned long next;
+
+	pud = pud_offset(pgd, addr);
+	do {
+		next = pud_addr_end(addr, end);
+		if (pud_none_or_clear_bad(pud)) {
+			(*zap_work)--;
+			continue;
+		}
+		next = zap_pmd_range(tlb, vma, pud, addr, next,
+						zap_work, details);
+	} while (pud++, addr = next, (addr != end && *zap_work > 0));
+
+	return addr;
+}
+
+static unsigned long unmap_page_range(struct mmu_gather *tlb,
+				struct vm_area_struct *vma,
+				unsigned long addr, unsigned long end,
+				long *zap_work, struct zap_details *details)
+{
+	pgd_t *pgd;
+	unsigned long next;
+
+	if (details && !details->check_mapping && !details->nonlinear_vma)
+		details = NULL;
+
+	BUG_ON(addr >= end);
+	tlb_start_vma(tlb, vma);
+	pgd = pgd_offset(vma->vm_mm, addr);
+	do {
+		next = pgd_addr_end(addr, end);
+		if (pgd_none_or_clear_bad(pgd)) {
+			(*zap_work)--;
+			continue;
+		}
+		next = zap_pud_range(tlb, vma, pgd, addr, next,
+						zap_work, details);
+	} while (pgd++, addr = next, (addr != end && *zap_work > 0));
+	tlb_end_vma(tlb, vma);
+
+	return addr;
+}
+
+#ifdef CONFIG_PREEMPT
+# define ZAP_BLOCK_SIZE	(8 * PAGE_SIZE)
+#else
+/* No preempt: go for improved straight-line efficiency */
+# define ZAP_BLOCK_SIZE	(1024 * PAGE_SIZE)
+#endif
+
+/**
+ * unmap_vmas - unmap a range of memory covered by a list of vma's
+ * @tlbp: address of the caller's struct mmu_gather
+ * @vma: the starting vma
+ * @start_addr: virtual address at which to start unmapping
+ * @end_addr: virtual address at which to end unmapping
+ * @nr_accounted: Place number of unmapped pages in vm-accountable vma's here
+ * @details: details of nonlinear truncation or shared cache invalidation
+ *
+ * Returns the end address of the unmapping (restart addr if interrupted).
+ *
+ * Unmap all pages in the vma list.
+ *
+ * We aim to not hold locks for too long (for scheduling latency reasons).
+ * So zap pages in ZAP_BLOCK_SIZE bytecounts.  This means we need to
+ * return the ending mmu_gather to the caller.
+ *
+ * Only addresses between `start' and `end' will be unmapped.
+ *
+ * The VMA list must be sorted in ascending virtual address order.
+ *
+ * unmap_vmas() assumes that the caller will flush the whole unmapped address
+ * range after unmap_vmas() returns.  So the only responsibility here is to
+ * ensure that any thus-far unmapped pages are flushed before unmap_vmas()
+ * drops the lock and schedules.
+ */
+unsigned long unmap_vmas(struct mmu_gather **tlbp,
+		struct vm_area_struct *vma, unsigned long start_addr,
+		unsigned long end_addr, unsigned long *nr_accounted,
+		struct zap_details *details)
+{
+	long zap_work = ZAP_BLOCK_SIZE;
+	unsigned long tlb_start = 0;	/* For tlb_finish_mmu */
+	int tlb_start_valid = 0;
+	unsigned long start = start_addr;
+	spinlock_t *i_mmap_lock = details? details->i_mmap_lock: NULL;
+	int fullmm = (*tlbp)->fullmm;
+
+	for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) {
+		unsigned long end;
+
+		start = max(vma->vm_start, start_addr);
+		if (start >= vma->vm_end)
+			continue;
+		end = min(vma->vm_end, end_addr);
+		if (end <= vma->vm_start)
+			continue;
+
+		if (vma->vm_flags & VM_ACCOUNT)
+			*nr_accounted += (end - start) >> PAGE_SHIFT;
+
+		while (start != end) {
+			if (!tlb_start_valid) {
+				tlb_start = start;
+				tlb_start_valid = 1;
+			}
+
+			if (unlikely(is_vm_hugetlb_page(vma))) {
+				unmap_hugepage_range(vma, start, end);
+				zap_work -= (end - start) /
+						(HPAGE_SIZE / PAGE_SIZE);
+				start = end;
+			} else
+				start = unmap_page_range(*tlbp, vma,
+						start, end, &zap_work, details);
+
+			if (zap_work > 0) {
+				BUG_ON(start != end);
+				break;
+			}
+
+			tlb_finish_mmu(*tlbp, tlb_start, start);
+
+			if (need_resched() ||
+				(i_mmap_lock && need_lockbreak(i_mmap_lock))) {
+				if (i_mmap_lock) {
+					*tlbp = NULL;
+					goto out;
+				}
+				cond_resched();
+			}
+
+			*tlbp = tlb_gather_mmu(vma->vm_mm, fullmm);
+			tlb_start_valid = 0;
+			zap_work = ZAP_BLOCK_SIZE;
+		}
+	}
+out:
+	return start;	/* which is now the end (or restart) address */
+}
+
+/**
+ * zap_page_range - remove user pages in a given range
+ * @vma: vm_area_struct holding the applicable pages
+ * @address: starting address of pages to zap
+ * @size: number of bytes to zap
+ * @details: details of nonlinear truncation or shared cache invalidation
+ */
+unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address,
+		unsigned long size, struct zap_details *details)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	struct mmu_gather *tlb;
+	unsigned long end = address + size;
+	unsigned long nr_accounted = 0;
+
+	lru_add_drain();
+	tlb = tlb_gather_mmu(mm, 0);
+	update_hiwater_rss(mm);
+	end = unmap_vmas(&tlb, vma, address, end, &nr_accounted, details);
+	if (tlb)
+		tlb_finish_mmu(tlb, address, end);
+	return end;
+}
+
+/*
+ * Do a quick page-table lookup for a single page.
+ */
+struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
+			unsigned int flags)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *ptep, pte;
+	spinlock_t *ptl;
+	struct page *page;
+	struct mm_struct *mm = vma->vm_mm;
+
+	page = follow_huge_addr(mm, address, flags & FOLL_WRITE);
+	if (!IS_ERR(page)) {
+		BUG_ON(flags & FOLL_GET);
+		goto out;
+	}
+
+	page = NULL;
+	pgd = pgd_offset(mm, address);
+	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
+		goto no_page_table;
+
+	pud = pud_offset(pgd, address);
+	if (pud_none(*pud) || unlikely(pud_bad(*pud)))
+		goto no_page_table;
+	
+	pmd = pmd_offset(pud, address);
+	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
+		goto no_page_table;
+
+	if (pmd_huge(*pmd)) {
+		BUG_ON(flags & FOLL_GET);
+		page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE);
+		goto out;
+	}
+
+	ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
+	if (!ptep)
+		goto out;
+
+	pte = *ptep;
+	if (!pte_present(pte))
+		goto unlock;
+	if ((flags & FOLL_WRITE) && !pte_write(pte))
+		goto unlock;
+	page = vm_normal_page(vma, address, pte);
+	if (unlikely(!page))
+		goto unlock;
+
+	if (flags & FOLL_GET)
+		get_page(page);
+	if (flags & FOLL_TOUCH) {
+		if ((flags & FOLL_WRITE) &&
+		    !pte_dirty(pte) && !PageDirty(page))
+			set_page_dirty(page);
+		mark_page_accessed(page);
+	}
+unlock:
+	pte_unmap_unlock(ptep, ptl);
+out:
+	return page;
+
+no_page_table:
+	/*
+	 * When core dumping an enormous anonymous area that nobody
+	 * has touched so far, we don't want to allocate page tables.
+	 */
+	if (flags & FOLL_ANON) {
+		page = ZERO_PAGE(address);
+		if (flags & FOLL_GET)
+			get_page(page);
+		BUG_ON(flags & FOLL_WRITE);
+	}
+	return page;
+}
+
+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)
+{
+	int i;
+	unsigned int vm_flags;
+
+	/* 
+	 * Require read or write permissions.
+	 * If 'force' is set, we only require the "MAY" flags.
+	 */
+	vm_flags  = write ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
+	vm_flags &= force ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
+	i = 0;
+
+	do {
+		struct vm_area_struct *vma;
+		unsigned int foll_flags;
+
+		vma = find_extend_vma(mm, start);
+		if (!vma && in_gate_area(tsk, start)) {
+			unsigned long pg = start & PAGE_MASK;
+			struct vm_area_struct *gate_vma = get_gate_vma(tsk);
+			pgd_t *pgd;
+			pud_t *pud;
+			pmd_t *pmd;
+			pte_t *pte;
+			if (write) /* user gate pages are read-only */
+				return i ? : -EFAULT;
+			if (pg > TASK_SIZE)
+				pgd = pgd_offset_k(pg);
+			else
+				pgd = pgd_offset_gate(mm, pg);
+			BUG_ON(pgd_none(*pgd));
+			pud = pud_offset(pgd, pg);
+			BUG_ON(pud_none(*pud));
+			pmd = pmd_offset(pud, pg);
+			if (pmd_none(*pmd))
+				return i ? : -EFAULT;
+			pte = pte_offset_map(pmd, pg);
+			if (pte_none(*pte)) {
+				pte_unmap(pte);
+				return i ? : -EFAULT;
+			}
+			if (pages) {
+				struct page *page = vm_normal_page(gate_vma, start, *pte);
+				pages[i] = page;
+				if (page)
+					get_page(page);
+			}
+			pte_unmap(pte);
+			if (vmas)
+				vmas[i] = gate_vma;
+			i++;
+			start += PAGE_SIZE;
+			len--;
+			continue;
+		}
+
+		if (!vma || (vma->vm_flags & (VM_IO | VM_PFNMAP))
+				|| !(vm_flags & vma->vm_flags))
+			return i ? : -EFAULT;
+
+		if (is_vm_hugetlb_page(vma)) {
+			i = follow_hugetlb_page(mm, vma, pages, vmas,
+						&start, &len, i);
+			continue;
+		}
+
+		foll_flags = FOLL_TOUCH;
+		if (pages)
+			foll_flags |= FOLL_GET;
+		if (!write && !(vma->vm_flags & VM_LOCKED) &&
+		    (!vma->vm_ops || !vma->vm_ops->nopage))
+			foll_flags |= FOLL_ANON;
+
+		do {
+			struct page *page;
+
+			if (write)
+				foll_flags |= FOLL_WRITE;
+
+			cond_resched();
+			while (!(page = follow_page(vma, start, foll_flags))) {
+				int ret;
+				ret = __handle_mm_fault(mm, vma, start,
+						foll_flags & FOLL_WRITE);
+				/*
+				 * The VM_FAULT_WRITE bit tells us that do_wp_page has
+				 * broken COW when necessary, even if maybe_mkwrite
+				 * decided not to set pte_write. We can thus safely do
+				 * subsequent page lookups as if they were reads.
+				 */
+				if (ret & VM_FAULT_WRITE)
+					foll_flags &= ~FOLL_WRITE;
+				
+				switch (ret & ~VM_FAULT_WRITE) {
+				case VM_FAULT_MINOR:
+					tsk->min_flt++;
+					break;
+				case VM_FAULT_MAJOR:
+					tsk->maj_flt++;
+					break;
+				case VM_FAULT_SIGBUS:
+					return i ? i : -EFAULT;
+				case VM_FAULT_OOM:
+					return i ? i : -ENOMEM;
+				default:
+					BUG();
+				}
+			}
+			if (pages) {
+				pages[i] = page;
+				flush_dcache_page(page);
+			}
+			if (vmas)
+				vmas[i] = vma;
+			i++;
+			start += PAGE_SIZE;
+			len--;
+		} while (len && start < vma->vm_end);
+	} while (len);
+	return i;
+}
+EXPORT_SYMBOL(get_user_pages);
+
+static int zeromap_pte_range(struct mm_struct *mm, pmd_t *pmd,
+			unsigned long addr, unsigned long end, pgprot_t prot)
+{
+	pte_t *pte;
+	spinlock_t *ptl;
+
+	pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
+	if (!pte)
+		return -ENOMEM;
+	do {
+		struct page *page = ZERO_PAGE(addr);
+		pte_t zero_pte = pte_wrprotect(mk_pte(page, prot));
+		page_cache_get(page);
+		page_add_file_rmap(page);
+		inc_mm_counter(mm, file_rss);
+		BUG_ON(!pte_none(*pte));
+		set_pte_at(mm, addr, pte, zero_pte);
+	} while (pte++, addr += PAGE_SIZE, addr != end);
+	pte_unmap_unlock(pte - 1, ptl);
+	return 0;
+}
+
+static inline int zeromap_pmd_range(struct mm_struct *mm, pud_t *pud,
+			unsigned long addr, unsigned long end, pgprot_t prot)
+{
+	pmd_t *pmd;
+	unsigned long next;
+
+	pmd = pmd_alloc(mm, pud, addr);
+	if (!pmd)
+		return -ENOMEM;
+	do {
+		next = pmd_addr_end(addr, end);
+		if (zeromap_pte_range(mm, pmd, addr, next, prot))
+			return -ENOMEM;
+	} while (pmd++, addr = next, addr != end);
+	return 0;
+}
+
+static inline int zeromap_pud_range(struct mm_struct *mm, pgd_t *pgd,
+			unsigned long addr, unsigned long end, pgprot_t prot)
+{
+	pud_t *pud;
+	unsigned long next;
+
+	pud = pud_alloc(mm, pgd, addr);
+	if (!pud)
+		return -ENOMEM;
+	do {
+		next = pud_addr_end(addr, end);
+		if (zeromap_pmd_range(mm, pud, addr, next, prot))
+			return -ENOMEM;
+	} while (pud++, addr = next, addr != end);
+	return 0;
+}
+
+int zeromap_page_range(struct vm_area_struct *vma,
+			unsigned long addr, unsigned long size, pgprot_t prot)
+{
+	pgd_t *pgd;
+	unsigned long next;
+	unsigned long end = addr + size;
+	struct mm_struct *mm = vma->vm_mm;
+	int err;
+
+	BUG_ON(addr >= end);
+	pgd = pgd_offset(mm, addr);
+	flush_cache_range(vma, addr, end);
+	do {
+		next = pgd_addr_end(addr, end);
+		err = zeromap_pud_range(mm, pgd, addr, next, prot);
+		if (err)
+			break;
+	} while (pgd++, addr = next, addr != end);
+	return err;
+}
+
+pte_t * fastcall get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl)
+{
+	pgd_t * pgd = pgd_offset(mm, addr);
+	pud_t * pud = pud_alloc(mm, pgd, addr);
+	if (pud) {
+		pmd_t * pmd = pmd_alloc(mm, pud, addr);
+		if (pmd)
+			return pte_alloc_map_lock(mm, pmd, addr, ptl);
+	}
+	return NULL;
+}
+
+/*
+ * This is the old fallback for page remapping.
+ *
+ * For historical reasons, it only allows reserved pages. Only
+ * old drivers should use this, and they needed to mark their
+ * pages reserved for the old functions anyway.
+ */
+static int insert_page(struct mm_struct *mm, unsigned long addr, struct page *page, pgprot_t prot)
+{
+	int retval;
+	pte_t *pte;
+	spinlock_t *ptl;  
+
+	retval = -EINVAL;
+	if (PageAnon(page))
+		goto out;
+	retval = -ENOMEM;
+	flush_dcache_page(page);
+	pte = get_locked_pte(mm, addr, &ptl);
+	if (!pte)
+		goto out;
+	retval = -EBUSY;
+	if (!pte_none(*pte))
+		goto out_unlock;
+
+	/* Ok, finally just insert the thing.. */
+	get_page(page);
+	inc_mm_counter(mm, file_rss);
+	page_add_file_rmap(page);
+	set_pte_at(mm, addr, pte, mk_pte(page, prot));
+
+	retval = 0;
+out_unlock:
+	pte_unmap_unlock(pte, ptl);
+out:
+	return retval;
+}
+
+/*
+ * This allows drivers to insert individual pages they've allocated
+ * into a user vma.
+ *
+ * The page has to be a nice clean _individual_ kernel allocation.
+ * If you allocate a compound page, you need to have marked it as
+ * such (__GFP_COMP), or manually just split the page up yourself
+ * (which is mainly an issue of doing "set_page_count(page, 1)" for
+ * each sub-page, and then freeing them one by one when you free
+ * them rather than freeing it as a compound page).
+ *
+ * NOTE! Traditionally this was done with "remap_pfn_range()" which
+ * took an arbitrary page protection parameter. This doesn't allow
+ * that. Your vma protection will have to be set up correctly, which
+ * means that if you want a shared writable mapping, you'd better
+ * ask for a shared writable mapping!
+ *
+ * The page does not need to be reserved.
+ */
+int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page)
+{
+	if (addr < vma->vm_start || addr >= vma->vm_end)
+		return -EFAULT;
+	if (!page_count(page))
+		return -EINVAL;
+	vma->vm_flags |= VM_INSERTPAGE;
+	return insert_page(vma->vm_mm, addr, page, vma->vm_page_prot);
+}
+EXPORT_SYMBOL(vm_insert_page);
+
+/*
+ * maps a range of physical memory into the requested pages. the old
+ * mappings are removed. any references to nonexistent pages results
+ * in null mappings (currently treated as "copy-on-access")
+ */
+static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
+			unsigned long addr, unsigned long end,
+			unsigned long pfn, pgprot_t prot)
+{
+	pte_t *pte;
+	spinlock_t *ptl;
+
+	pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
+	if (!pte)
+		return -ENOMEM;
+	do {
+		BUG_ON(!pte_none(*pte));
+		set_pte_at(mm, addr, pte, pfn_pte(pfn, prot));
+		pfn++;
+	} while (pte++, addr += PAGE_SIZE, addr != end);
+	pte_unmap_unlock(pte - 1, ptl);
+	return 0;
+}
+
+static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
+			unsigned long addr, unsigned long end,
+			unsigned long pfn, pgprot_t prot)
+{
+	pmd_t *pmd;
+	unsigned long next;
+
+	pfn -= addr >> PAGE_SHIFT;
+	pmd = pmd_alloc(mm, pud, addr);
+	if (!pmd)
+		return -ENOMEM;
+	do {
+		next = pmd_addr_end(addr, end);
+		if (remap_pte_range(mm, pmd, addr, next,
+				pfn + (addr >> PAGE_SHIFT), prot))
+			return -ENOMEM;
+	} while (pmd++, addr = next, addr != end);
+	return 0;
+}
+
+static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd,
+			unsigned long addr, unsigned long end,
+			unsigned long pfn, pgprot_t prot)
+{
+	pud_t *pud;
+	unsigned long next;
+
+	pfn -= addr >> PAGE_SHIFT;
+	pud = pud_alloc(mm, pgd, addr);
+	if (!pud)
+		return -ENOMEM;
+	do {
+		next = pud_addr_end(addr, end);
+		if (remap_pmd_range(mm, pud, addr, next,
+				pfn + (addr >> PAGE_SHIFT), prot))
+			return -ENOMEM;
+	} while (pud++, addr = next, addr != end);
+	return 0;
+}
+
+/*  Note: this is only safe if the mm semaphore is held when called. */
+int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
+		    unsigned long pfn, unsigned long size, pgprot_t prot)
+{
+	pgd_t *pgd;
+	unsigned long next;
+	unsigned long end = addr + PAGE_ALIGN(size);
+	struct mm_struct *mm = vma->vm_mm;
+	int err;
+
+	/*
+	 * Physically remapped pages are special. Tell the
+	 * rest of the world about it:
+	 *   VM_IO tells people not to look at these pages
+	 *	(accesses can have side effects).
+	 *   VM_RESERVED is specified all over the place, because
+	 *	in 2.4 it kept swapout's vma scan off this vma; but
+	 *	in 2.6 the LRU scan won't even find its pages, so this
+	 *	flag means no more than count its pages in reserved_vm,
+	 * 	and omit it from core dump, even when VM_IO turned off.
+	 *   VM_PFNMAP tells the core MM that the base pages are just
+	 *	raw PFN mappings, and do not have a "struct page" associated
+	 *	with them.
+	 *
+	 * There's a horrible special case to handle copy-on-write
+	 * behaviour that some programs depend on. We mark the "original"
+	 * un-COW'ed pages by matching them up with "vma->vm_pgoff".
+	 */
+	if (is_cow_mapping(vma->vm_flags)) {
+		if (addr != vma->vm_start || end != vma->vm_end)
+			return -EINVAL;
+		vma->vm_pgoff = pfn;
+	}
+
+	vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
+
+	BUG_ON(addr >= end);
+	pfn -= addr >> PAGE_SHIFT;
+	pgd = pgd_offset(mm, addr);
+	flush_cache_range(vma, addr, end);
+	do {
+		next = pgd_addr_end(addr, end);
+		err = remap_pud_range(mm, pgd, addr, next,
+				pfn + (addr >> PAGE_SHIFT), prot);
+		if (err)
+			break;
+	} while (pgd++, addr = next, addr != end);
+	return err;
+}
+EXPORT_SYMBOL(remap_pfn_range);
+
+/*
+ * handle_pte_fault chooses page fault handler according to an entry
+ * which was read non-atomically.  Before making any commitment, on
+ * those architectures or configurations (e.g. i386 with PAE) which
+ * might give a mix of unmatched parts, do_swap_page and do_file_page
+ * must check under lock before unmapping the pte and proceeding
+ * (but do_wp_page is only called after already making such a check;
+ * and do_anonymous_page and do_no_page can safely check later on).
+ */
+static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd,
+				pte_t *page_table, pte_t orig_pte)
+{
+	int same = 1;
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT)
+	if (sizeof(pte_t) > sizeof(unsigned long)) {
+		spinlock_t *ptl = pte_lockptr(mm, pmd);
+		spin_lock(ptl);
+		same = pte_same(*page_table, orig_pte);
+		spin_unlock(ptl);
+	}
+#endif
+	pte_unmap(page_table);
+	return same;
+}
+
+/*
+ * Do pte_mkwrite, but only if the vma says VM_WRITE.  We do this when
+ * servicing faults for write access.  In the normal case, do always want
+ * pte_mkwrite.  But get_user_pages can cause write faults for mappings
+ * that do not have writing enabled, when used by access_process_vm.
+ */
+static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
+{
+	if (likely(vma->vm_flags & VM_WRITE))
+		pte = pte_mkwrite(pte);
+	return pte;
+}
+
+static inline void cow_user_page(struct page *dst, struct page *src, unsigned long va)
+{
+	/*
+	 * If the source page was a PFN mapping, we don't have
+	 * a "struct page" for it. We do a best-effort copy by
+	 * just copying from the original user address. If that
+	 * fails, we just zero-fill it. Live with it.
+	 */
+	if (unlikely(!src)) {
+		void *kaddr = kmap_atomic(dst, KM_USER0);
+		void __user *uaddr = (void __user *)(va & PAGE_MASK);
+
+		/*
+		 * This really shouldn't fail, because the page is there
+		 * in the page tables. But it might just be unreadable,
+		 * in which case we just give up and fill the result with
+		 * zeroes.
+		 */
+		if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE))
+			memset(kaddr, 0, PAGE_SIZE);
+		kunmap_atomic(kaddr, KM_USER0);
+		return;
+		
+	}
+	copy_user_highpage(dst, src, va);
+}
+
+/*
+ * This routine handles present pages, when users try to write
+ * to a shared page. It is done by copying the page to a new address
+ * and decrementing the shared-page counter for the old page.
+ *
+ * Note that this routine assumes that the protection checks have been
+ * done by the caller (the low-level page fault routine in most cases).
+ * Thus we can safely just mark it writable once we've done any necessary
+ * COW.
+ *
+ * We also mark the page dirty at this point even though the page will
+ * change only once the write actually happens. This avoids a few races,
+ * and potentially makes it more efficient.
+ *
+ * We enter with non-exclusive mmap_sem (to exclude vma changes,
+ * but allow concurrent faults), with pte both mapped and locked.
+ * We return with mmap_sem still held, but pte unmapped and unlocked.
+ */
+static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
+		unsigned long address, pte_t *page_table, pmd_t *pmd,
+		spinlock_t *ptl, pte_t orig_pte)
+{
+	struct page *old_page, *new_page;
+	pte_t entry;
+	int ret = VM_FAULT_MINOR;
+
+	old_page = vm_normal_page(vma, address, orig_pte);
+	if (!old_page)
+		goto gotten;
+
+	if (PageAnon(old_page) && !TestSetPageLocked(old_page)) {
+		int reuse = can_share_swap_page(old_page);
+		unlock_page(old_page);
+		if (reuse) {
+			flush_cache_page(vma, address, pte_pfn(orig_pte));
+			entry = pte_mkyoung(orig_pte);
+			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+			ptep_set_access_flags(vma, address, page_table, entry, 1);
+			update_mmu_cache(vma, address, entry);
+			lazy_mmu_prot_update(entry);
+			ret |= VM_FAULT_WRITE;
+			goto unlock;
+		}
+	}
+
+	/*
+	 * Ok, we need to copy. Oh, well..
+	 */
+	page_cache_get(old_page);
+gotten:
+	pte_unmap_unlock(page_table, ptl);
+
+	if (unlikely(anon_vma_prepare(vma)))
+		goto oom;
+	if (old_page == ZERO_PAGE(address)) {
+		new_page = alloc_zeroed_user_highpage(vma, address);
+		if (!new_page)
+			goto oom;
+	} else {
+		new_page = alloc_page_vma(GFP_HIGHUSER, vma, address);
+		if (!new_page)
+			goto oom;
+		cow_user_page(new_page, old_page, address);
+	}
+
+	/*
+	 * Re-check the pte - we dropped the lock
+	 */
+	page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
+	if (likely(pte_same(*page_table, orig_pte))) {
+		if (old_page) {
+			page_remove_rmap(old_page);
+			if (!PageAnon(old_page)) {
+				dec_mm_counter(mm, file_rss);
+				inc_mm_counter(mm, anon_rss);
+			}
+		} else
+			inc_mm_counter(mm, anon_rss);
+		flush_cache_page(vma, address, pte_pfn(orig_pte));
+		entry = mk_pte(new_page, vma->vm_page_prot);
+		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+		ptep_establish(vma, address, page_table, entry);
+		update_mmu_cache(vma, address, entry);
+		lazy_mmu_prot_update(entry);
+		lru_cache_add_active(new_page);
+		page_add_new_anon_rmap(new_page, vma, address);
+
+		/* Free the old page.. */
+		new_page = old_page;
+		ret |= VM_FAULT_WRITE;
+	}
+	if (new_page)
+		page_cache_release(new_page);
+	if (old_page)
+		page_cache_release(old_page);
+unlock:
+	pte_unmap_unlock(page_table, ptl);
+	return ret;
+oom:
+	if (old_page)
+		page_cache_release(old_page);
+	return VM_FAULT_OOM;
+}
+
+/*
+ * Helper functions for unmap_mapping_range().
+ *
+ * __ Notes on dropping i_mmap_lock to reduce latency while unmapping __
+ *
+ * We have to restart searching the prio_tree whenever we drop the lock,
+ * since the iterator is only valid while the lock is held, and anyway
+ * a later vma might be split and reinserted earlier while lock dropped.
+ *
+ * The list of nonlinear vmas could be handled more efficiently, using
+ * a placeholder, but handle it in the same way until a need is shown.
+ * It is important to search the prio_tree before nonlinear list: a vma
+ * may become nonlinear and be shifted from prio_tree to nonlinear list
+ * while the lock is dropped; but never shifted from list to prio_tree.
+ *
+ * In order to make forward progress despite restarting the search,
+ * vm_truncate_count is used to mark a vma as now dealt with, so we can
+ * quickly skip it next time around.  Since the prio_tree search only
+ * shows us those vmas affected by unmapping the range in question, we
+ * can't efficiently keep all vmas in step with mapping->truncate_count:
+ * so instead reset them all whenever it wraps back to 0 (then go to 1).
+ * mapping->truncate_count and vma->vm_truncate_count are protected by
+ * i_mmap_lock.
+ *
+ * In order to make forward progress despite repeatedly restarting some
+ * large vma, note the restart_addr from unmap_vmas when it breaks out:
+ * and restart from that address when we reach that vma again.  It might
+ * have been split or merged, shrunk or extended, but never shifted: so
+ * restart_addr remains valid so long as it remains in the vma's range.
+ * unmap_mapping_range forces truncate_count to leap over page-aligned
+ * values so we can save vma's restart_addr in its truncate_count field.
+ */
+#define is_restart_addr(truncate_count) (!((truncate_count) & ~PAGE_MASK))
+
+static void reset_vma_truncate_counts(struct address_space *mapping)
+{
+	struct vm_area_struct *vma;
+	struct prio_tree_iter iter;
+
+	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, 0, ULONG_MAX)
+		vma->vm_truncate_count = 0;
+	list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list)
+		vma->vm_truncate_count = 0;
+}
+
+static int unmap_mapping_range_vma(struct vm_area_struct *vma,
+		unsigned long start_addr, unsigned long end_addr,
+		struct zap_details *details)
+{
+	unsigned long restart_addr;
+	int need_break;
+
+again:
+	restart_addr = vma->vm_truncate_count;
+	if (is_restart_addr(restart_addr) && start_addr < restart_addr) {
+		start_addr = restart_addr;
+		if (start_addr >= end_addr) {
+			/* Top of vma has been split off since last time */
+			vma->vm_truncate_count = details->truncate_count;
+			return 0;
+		}
+	}
+
+	restart_addr = zap_page_range(vma, start_addr,
+					end_addr - start_addr, details);
+	need_break = need_resched() ||
+			need_lockbreak(details->i_mmap_lock);
+
+	if (restart_addr >= end_addr) {
+		/* We have now completed this vma: mark it so */
+		vma->vm_truncate_count = details->truncate_count;
+		if (!need_break)
+			return 0;
+	} else {
+		/* Note restart_addr in vma's truncate_count field */
+		vma->vm_truncate_count = restart_addr;
+		if (!need_break)
+			goto again;
+	}
+
+	spin_unlock(details->i_mmap_lock);
+	cond_resched();
+	spin_lock(details->i_mmap_lock);
+	return -EINTR;
+}
+
+static inline void unmap_mapping_range_tree(struct prio_tree_root *root,
+					    struct zap_details *details)
+{
+	struct vm_area_struct *vma;
+	struct prio_tree_iter iter;
+	pgoff_t vba, vea, zba, zea;
+
+restart:
+	vma_prio_tree_foreach(vma, &iter, root,
+			details->first_index, details->last_index) {
+		/* Skip quickly over those we have already dealt with */
+		if (vma->vm_truncate_count == details->truncate_count)
+			continue;
+
+		vba = vma->vm_pgoff;
+		vea = vba + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) - 1;
+		/* Assume for now that PAGE_CACHE_SHIFT == PAGE_SHIFT */
+		zba = details->first_index;
+		if (zba < vba)
+			zba = vba;
+		zea = details->last_index;
+		if (zea > vea)
+			zea = vea;
+
+		if (unmap_mapping_range_vma(vma,
+			((zba - vba) << PAGE_SHIFT) + vma->vm_start,
+			((zea - vba + 1) << PAGE_SHIFT) + vma->vm_start,
+				details) < 0)
+			goto restart;
+	}
+}
+
+static inline void unmap_mapping_range_list(struct list_head *head,
+					    struct zap_details *details)
+{
+	struct vm_area_struct *vma;
+
+	/*
+	 * In nonlinear VMAs there is no correspondence between virtual address
+	 * offset and file offset.  So we must perform an exhaustive search
+	 * across *all* the pages in each nonlinear VMA, not just the pages
+	 * whose virtual address lies outside the file truncation point.
+	 */
+restart:
+	list_for_each_entry(vma, head, shared.vm_set.list) {
+		/* Skip quickly over those we have already dealt with */
+		if (vma->vm_truncate_count == details->truncate_count)
+			continue;
+		details->nonlinear_vma = vma;
+		if (unmap_mapping_range_vma(vma, vma->vm_start,
+					vma->vm_end, details) < 0)
+			goto restart;
+	}
+}
+
+/**
+ * unmap_mapping_range - unmap the portion of all mmaps
+ * in the specified address_space corresponding to the specified
+ * page range in the underlying file.
+ * @mapping: the address space containing mmaps to be unmapped.
+ * @holebegin: byte in first page to unmap, relative to the start of
+ * the underlying file.  This will be rounded down to a PAGE_SIZE
+ * boundary.  Note that this is different from vmtruncate(), which
+ * must keep the partial page.  In contrast, we must get rid of
+ * partial pages.
+ * @holelen: size of prospective hole in bytes.  This will be rounded
+ * up to a PAGE_SIZE boundary.  A holelen of zero truncates to the
+ * end of the file.
+ * @even_cows: 1 when truncating a file, unmap even private COWed pages;
+ * but 0 when invalidating pagecache, don't throw away private data.
+ */
+void unmap_mapping_range(struct address_space *mapping,
+		loff_t const holebegin, loff_t const holelen, int even_cows)
+{
+	struct zap_details details;
+	pgoff_t hba = holebegin >> PAGE_SHIFT;
+	pgoff_t hlen = (holelen + PAGE_SIZE - 1) >> PAGE_SHIFT;
+
+	/* Check for overflow. */
+	if (sizeof(holelen) > sizeof(hlen)) {
+		long long holeend =
+			(holebegin + holelen + PAGE_SIZE - 1) >> PAGE_SHIFT;
+		if (holeend & ~(long long)ULONG_MAX)
+			hlen = ULONG_MAX - hba + 1;
+	}
+
+	details.check_mapping = even_cows? NULL: mapping;
+	details.nonlinear_vma = NULL;
+	details.first_index = hba;
+	details.last_index = hba + hlen - 1;
+	if (details.last_index < details.first_index)
+		details.last_index = ULONG_MAX;
+	details.i_mmap_lock = &mapping->i_mmap_lock;
+
+	spin_lock(&mapping->i_mmap_lock);
+
+	/* serialize i_size write against truncate_count write */
+	smp_wmb();
+	/* Protect against page faults, and endless unmapping loops */
+	mapping->truncate_count++;
+	/*
+	 * For archs where spin_lock has inclusive semantics like ia64
+	 * this smp_mb() will prevent to read pagetable contents
+	 * before the truncate_count increment is visible to
+	 * other cpus.
+	 */
+	smp_mb();
+	if (unlikely(is_restart_addr(mapping->truncate_count))) {
+		if (mapping->truncate_count == 0)
+			reset_vma_truncate_counts(mapping);
+		mapping->truncate_count++;
+	}
+	details.truncate_count = mapping->truncate_count;
+
+	if (unlikely(!prio_tree_empty(&mapping->i_mmap)))
+		unmap_mapping_range_tree(&mapping->i_mmap, &details);
+	if (unlikely(!list_empty(&mapping->i_mmap_nonlinear)))
+		unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details);
+	spin_unlock(&mapping->i_mmap_lock);
+}
+EXPORT_SYMBOL(unmap_mapping_range);
+
+/*
+ * Handle all mappings that got truncated by a "truncate()"
+ * system call.
+ *
+ * NOTE! We have to be ready to update the memory sharing
+ * between the file and the memory map for a potential last
+ * incomplete page.  Ugly, but necessary.
+ */
+int vmtruncate(struct inode * inode, loff_t offset)
+{
+	struct address_space *mapping = inode->i_mapping;
+	unsigned long limit;
+
+	if (inode->i_size < offset)
+		goto do_expand;
+	/*
+	 * truncation of in-use swapfiles is disallowed - it would cause
+	 * subsequent swapout to scribble on the now-freed blocks.
+	 */
+	if (IS_SWAPFILE(inode))
+		goto out_busy;
+	i_size_write(inode, offset);
+	unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
+	truncate_inode_pages(mapping, offset);
+	goto out_truncate;
+
+do_expand:
+	limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
+	if (limit != RLIM_INFINITY && offset > limit)
+		goto out_sig;
+	if (offset > inode->i_sb->s_maxbytes)
+		goto out_big;
+	i_size_write(inode, offset);
+
+out_truncate:
+	if (inode->i_op && inode->i_op->truncate)
+		inode->i_op->truncate(inode);
+	return 0;
+out_sig:
+	send_sig(SIGXFSZ, current, 0);
+out_big:
+	return -EFBIG;
+out_busy:
+	return -ETXTBSY;
+}
+EXPORT_SYMBOL(vmtruncate);
+
+int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end)
+{
+	struct address_space *mapping = inode->i_mapping;
+
+	/*
+	 * If the underlying filesystem is not going to provide
+	 * a way to truncate a range of blocks (punch a hole) -
+	 * we should return failure right now.
+	 */
+	if (!inode->i_op || !inode->i_op->truncate_range)
+		return -ENOSYS;
+
+	mutex_lock(&inode->i_mutex);
+	down_write(&inode->i_alloc_sem);
+	unmap_mapping_range(mapping, offset, (end - offset), 1);
+	truncate_inode_pages_range(mapping, offset, end);
+	inode->i_op->truncate_range(inode, offset, end);
+	up_write(&inode->i_alloc_sem);
+	mutex_unlock(&inode->i_mutex);
+
+	return 0;
+}
+EXPORT_SYMBOL(vmtruncate_range);
+
+/* 
+ * Primitive swap readahead code. We simply read an aligned block of
+ * (1 << page_cluster) entries in the swap area. This method is chosen
+ * because it doesn't cost us any seek time.  We also make sure to queue
+ * the 'original' request together with the readahead ones...  
+ *
+ * This has been extended to use the NUMA policies from the mm triggering
+ * the readahead.
+ *
+ * Caller must hold down_read on the vma->vm_mm if vma is not NULL.
+ */
+void swapin_readahead(swp_entry_t entry, unsigned long addr,struct vm_area_struct *vma)
+{
+#ifdef CONFIG_NUMA
+	struct vm_area_struct *next_vma = vma ? vma->vm_next : NULL;
+#endif
+	int i, num;
+	struct page *new_page;
+	unsigned long offset;
+
+	/*
+	 * Get the number of handles we should do readahead io to.
+	 */
+	num = valid_swaphandles(entry, &offset);
+	for (i = 0; i < num; offset++, i++) {
+		/* Ok, do the async read-ahead now */
+		new_page = read_swap_cache_async(swp_entry(swp_type(entry),
+							   offset), vma, addr);
+		if (!new_page)
+			break;
+		page_cache_release(new_page);
+#ifdef CONFIG_NUMA
+		/*
+		 * Find the next applicable VMA for the NUMA policy.
+		 */
+		addr += PAGE_SIZE;
+		if (addr == 0)
+			vma = NULL;
+		if (vma) {
+			if (addr >= vma->vm_end) {
+				vma = next_vma;
+				next_vma = vma ? vma->vm_next : NULL;
+			}
+			if (vma && addr < vma->vm_start)
+				vma = NULL;
+		} else {
+			if (next_vma && addr >= next_vma->vm_start) {
+				vma = next_vma;
+				next_vma = vma->vm_next;
+			}
+		}
+#endif
+	}
+	lru_add_drain();	/* Push any new pages onto the LRU now */
+}
+
+/*
+ * We enter with non-exclusive mmap_sem (to exclude vma changes,
+ * but allow concurrent faults), and pte mapped but not yet locked.
+ * We return with mmap_sem still held, but pte unmapped and unlocked.
+ */
+static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
+		unsigned long address, pte_t *page_table, pmd_t *pmd,
+		int write_access, pte_t orig_pte)
+{
+	spinlock_t *ptl;
+	struct page *page;
+	swp_entry_t entry;
+	pte_t pte;
+	int ret = VM_FAULT_MINOR;
+
+	if (!pte_unmap_same(mm, pmd, page_table, orig_pte))
+		goto out;
+
+	entry = pte_to_swp_entry(orig_pte);
+again:
+	page = lookup_swap_cache(entry);
+	if (!page) {
+ 		swapin_readahead(entry, address, vma);
+ 		page = read_swap_cache_async(entry, vma, address);
+		if (!page) {
+			/*
+			 * Back out if somebody else faulted in this pte
+			 * while we released the pte lock.
+			 */
+			page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
+			if (likely(pte_same(*page_table, orig_pte)))
+				ret = VM_FAULT_OOM;
+			goto unlock;
+		}
+
+		/* Had to read the page from swap area: Major fault */
+		ret = VM_FAULT_MAJOR;
+		inc_page_state(pgmajfault);
+		grab_swap_token();
+	}
+
+	mark_page_accessed(page);
+	lock_page(page);
+	if (!PageSwapCache(page)) {
+		/* Page migration has occured */
+		unlock_page(page);
+		page_cache_release(page);
+		goto again;
+	}
+
+	/*
+	 * Back out if somebody else already faulted in this pte.
+	 */
+	page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
+	if (unlikely(!pte_same(*page_table, orig_pte)))
+		goto out_nomap;
+
+	if (unlikely(!PageUptodate(page))) {
+		ret = VM_FAULT_SIGBUS;
+		goto out_nomap;
+	}
+
+	/* The page isn't present yet, go ahead with the fault. */
+
+	inc_mm_counter(mm, anon_rss);
+	pte = mk_pte(page, vma->vm_page_prot);
+	if (write_access && can_share_swap_page(page)) {
+		pte = maybe_mkwrite(pte_mkdirty(pte), vma);
+		write_access = 0;
+	}
+
+	flush_icache_page(vma, page);
+	set_pte_at(mm, address, page_table, pte);
+	page_add_anon_rmap(page, vma, address);
+
+	swap_free(entry);
+	if (vm_swap_full())
+		remove_exclusive_swap_page(page);
+	unlock_page(page);
+
+	if (write_access) {
+		if (do_wp_page(mm, vma, address,
+				page_table, pmd, ptl, pte) == VM_FAULT_OOM)
+			ret = VM_FAULT_OOM;
+		goto out;
+	}
+
+	/* No need to invalidate - it was non-present before */
+	update_mmu_cache(vma, address, pte);
+	lazy_mmu_prot_update(pte);
+unlock:
+	pte_unmap_unlock(page_table, ptl);
+out:
+	return ret;
+out_nomap:
+	pte_unmap_unlock(page_table, ptl);
+	unlock_page(page);
+	page_cache_release(page);
+	return ret;
+}
+
+/*
+ * We enter with non-exclusive mmap_sem (to exclude vma changes,
+ * but allow concurrent faults), and pte mapped but not yet locked.
+ * We return with mmap_sem still held, but pte unmapped and unlocked.
+ */
+static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
+		unsigned long address, pte_t *page_table, pmd_t *pmd,
+		int write_access)
+{
+	struct page *page;
+	spinlock_t *ptl;
+	pte_t entry;
+
+	if (write_access) {
+		/* Allocate our own private page. */
+		pte_unmap(page_table);
+
+		if (unlikely(anon_vma_prepare(vma)))
+			goto oom;
+		page = alloc_zeroed_user_highpage(vma, address);
+		if (!page)
+			goto oom;
+
+		entry = mk_pte(page, vma->vm_page_prot);
+		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+
+		page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
+		if (!pte_none(*page_table))
+			goto release;
+		inc_mm_counter(mm, anon_rss);
+		lru_cache_add_active(page);
+		page_add_new_anon_rmap(page, vma, address);
+	} else {
+		/* Map the ZERO_PAGE - vm_page_prot is readonly */
+		page = ZERO_PAGE(address);
+		page_cache_get(page);
+		entry = mk_pte(page, vma->vm_page_prot);
+
+		ptl = pte_lockptr(mm, pmd);
+		spin_lock(ptl);
+		if (!pte_none(*page_table))
+			goto release;
+		inc_mm_counter(mm, file_rss);
+		page_add_file_rmap(page);
+	}
+
+	set_pte_at(mm, address, page_table, entry);
+
+	/* No need to invalidate - it was non-present before */
+	update_mmu_cache(vma, address, entry);
+	lazy_mmu_prot_update(entry);
+unlock:
+	pte_unmap_unlock(page_table, ptl);
+	return VM_FAULT_MINOR;
+release:
+	page_cache_release(page);
+	goto unlock;
+oom:
+	return VM_FAULT_OOM;
+}
+
+/*
+ * do_no_page() tries to create a new page mapping. It aggressively
+ * tries to share with existing pages, but makes a separate copy if
+ * the "write_access" parameter is true in order to avoid the next
+ * page fault.
+ *
+ * As this is called only for pages that do not currently exist, we
+ * do not need to flush old virtual caches or the TLB.
+ *
+ * We enter with non-exclusive mmap_sem (to exclude vma changes,
+ * but allow concurrent faults), and pte mapped but not yet locked.
+ * We return with mmap_sem still held, but pte unmapped and unlocked.
+ */
+static int do_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
+		unsigned long address, pte_t *page_table, pmd_t *pmd,
+		int write_access)
+{
+	spinlock_t *ptl;
+	struct page *new_page;
+	struct address_space *mapping = NULL;
+	pte_t entry;
+	unsigned int sequence = 0;
+	int ret = VM_FAULT_MINOR;
+	int anon = 0;
+
+	pte_unmap(page_table);
+	BUG_ON(vma->vm_flags & VM_PFNMAP);
+
+	if (vma->vm_file) {
+		mapping = vma->vm_file->f_mapping;
+		sequence = mapping->truncate_count;
+		smp_rmb(); /* serializes i_size against truncate_count */
+	}
+retry:
+	new_page = vma->vm_ops->nopage(vma, address & PAGE_MASK, &ret);
+	/*
+	 * No smp_rmb is needed here as long as there's a full
+	 * spin_lock/unlock sequence inside the ->nopage callback
+	 * (for the pagecache lookup) that acts as an implicit
+	 * smp_mb() and prevents the i_size read to happen
+	 * after the next truncate_count read.
+	 */
+
+	/* no page was available -- either SIGBUS or OOM */
+	if (new_page == NOPAGE_SIGBUS)
+		return VM_FAULT_SIGBUS;
+	if (new_page == NOPAGE_OOM)
+		return VM_FAULT_OOM;
+
+	/*
+	 * Should we do an early C-O-W break?
+	 */
+	if (write_access && !(vma->vm_flags & VM_SHARED)) {
+		struct page *page;
+
+		if (unlikely(anon_vma_prepare(vma)))
+			goto oom;
+		page = alloc_page_vma(GFP_HIGHUSER, vma, address);
+		if (!page)
+			goto oom;
+		copy_user_highpage(page, new_page, address);
+		page_cache_release(new_page);
+		new_page = page;
+		anon = 1;
+	}
+
+	page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
+	/*
+	 * For a file-backed vma, someone could have truncated or otherwise
+	 * invalidated this page.  If unmap_mapping_range got called,
+	 * retry getting the page.
+	 */
+	if (mapping && unlikely(sequence != mapping->truncate_count)) {
+		pte_unmap_unlock(page_table, ptl);
+		page_cache_release(new_page);
+		cond_resched();
+		sequence = mapping->truncate_count;
+		smp_rmb();
+		goto retry;
+	}
+
+	/*
+	 * This silly early PAGE_DIRTY setting removes a race
+	 * due to the bad i386 page protection. But it's valid
+	 * for other architectures too.
+	 *
+	 * Note that if write_access is true, we either now have
+	 * an exclusive copy of the page, or this is a shared mapping,
+	 * so we can make it writable and dirty to avoid having to
+	 * handle that later.
+	 */
+	/* Only go through if we didn't race with anybody else... */
+	if (pte_none(*page_table)) {
+		flush_icache_page(vma, new_page);
+		entry = mk_pte(new_page, vma->vm_page_prot);
+		if (write_access)
+			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+		set_pte_at(mm, address, page_table, entry);
+		if (anon) {
+			inc_mm_counter(mm, anon_rss);
+			lru_cache_add_active(new_page);
+			page_add_new_anon_rmap(new_page, vma, address);
+		} else {
+			inc_mm_counter(mm, file_rss);
+			page_add_file_rmap(new_page);
+		}
+	} else {
+		/* One of our sibling threads was faster, back out. */
+		page_cache_release(new_page);
+		goto unlock;
+	}
+
+	/* no need to invalidate: a not-present page shouldn't be cached */
+	update_mmu_cache(vma, address, entry);
+	lazy_mmu_prot_update(entry);
+unlock:
+	pte_unmap_unlock(page_table, ptl);
+	return ret;
+oom:
+	page_cache_release(new_page);
+	return VM_FAULT_OOM;
+}
+
+/*
+ * Fault of a previously existing named mapping. Repopulate the pte
+ * from the encoded file_pte if possible. This enables swappable
+ * nonlinear vmas.
+ *
+ * We enter with non-exclusive mmap_sem (to exclude vma changes,
+ * but allow concurrent faults), and pte mapped but not yet locked.
+ * We return with mmap_sem still held, but pte unmapped and unlocked.
+ */
+static int do_file_page(struct mm_struct *mm, struct vm_area_struct *vma,
+		unsigned long address, pte_t *page_table, pmd_t *pmd,
+		int write_access, pte_t orig_pte)
+{
+	pgoff_t pgoff;
+	int err;
+
+	if (!pte_unmap_same(mm, pmd, page_table, orig_pte))
+		return VM_FAULT_MINOR;
+
+	if (unlikely(!(vma->vm_flags & VM_NONLINEAR))) {
+		/*
+		 * Page table corrupted: show pte and kill process.
+		 */
+		print_bad_pte(vma, orig_pte, address);
+		return VM_FAULT_OOM;
+	}
+	/* We can then assume vm->vm_ops && vma->vm_ops->populate */
+
+	pgoff = pte_to_pgoff(orig_pte);
+	err = vma->vm_ops->populate(vma, address & PAGE_MASK, PAGE_SIZE,
+					vma->vm_page_prot, pgoff, 0);
+	if (err == -ENOMEM)
+		return VM_FAULT_OOM;
+	if (err)
+		return VM_FAULT_SIGBUS;
+	return VM_FAULT_MAJOR;
+}
+
+/*
+ * These routines also need to handle stuff like marking pages dirty
+ * and/or accessed for architectures that don't do it in hardware (most
+ * RISC architectures).  The early dirtying is also good on the i386.
+ *
+ * There is also a hook called "update_mmu_cache()" that architectures
+ * with external mmu caches can use to update those (ie the Sparc or
+ * PowerPC hashed page tables that act as extended TLBs).
+ *
+ * We enter with non-exclusive mmap_sem (to exclude vma changes,
+ * but allow concurrent faults), and pte mapped but not yet locked.
+ * We return with mmap_sem still held, but pte unmapped and unlocked.
+ */
+static inline int handle_pte_fault(struct mm_struct *mm,
+		struct vm_area_struct *vma, unsigned long address,
+		pte_t *pte, pmd_t *pmd, int write_access)
+{
+	pte_t entry;
+	pte_t old_entry;
+	spinlock_t *ptl;
+
+	old_entry = entry = *pte;
+	if (!pte_present(entry)) {
+		if (pte_none(entry)) {
+			if (!vma->vm_ops || !vma->vm_ops->nopage)
+				return do_anonymous_page(mm, vma, address,
+					pte, pmd, write_access);
+			return do_no_page(mm, vma, address,
+					pte, pmd, write_access);
+		}
+		if (pte_file(entry))
+			return do_file_page(mm, vma, address,
+					pte, pmd, write_access, entry);
+		return do_swap_page(mm, vma, address,
+					pte, pmd, write_access, entry);
+	}
+
+	ptl = pte_lockptr(mm, pmd);
+	spin_lock(ptl);
+	if (unlikely(!pte_same(*pte, entry)))
+		goto unlock;
+	if (write_access) {
+		if (!pte_write(entry))
+			return do_wp_page(mm, vma, address,
+					pte, pmd, ptl, entry);
+		entry = pte_mkdirty(entry);
+	}
+	entry = pte_mkyoung(entry);
+	if (!pte_same(old_entry, entry)) {
+		ptep_set_access_flags(vma, address, pte, entry, write_access);
+		update_mmu_cache(vma, address, entry);
+		lazy_mmu_prot_update(entry);
+	} else {
+		/*
+		 * This is needed only for protection faults but the arch code
+		 * is not yet telling us if this is a protection fault or not.
+		 * This still avoids useless tlb flushes for .text page faults
+		 * with threads.
+		 */
+		if (write_access)
+			flush_tlb_page(vma, address);
+	}
+unlock:
+	pte_unmap_unlock(pte, ptl);
+	return VM_FAULT_MINOR;
+}
+
+/*
+ * By the time we get here, we already hold the mm semaphore
+ */
+int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
+		unsigned long address, int write_access)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	__set_current_state(TASK_RUNNING);
+
+	inc_page_state(pgfault);
+
+	if (unlikely(is_vm_hugetlb_page(vma)))
+		return hugetlb_fault(mm, vma, address, write_access);
+
+	pgd = pgd_offset(mm, address);
+	pud = pud_alloc(mm, pgd, address);
+	if (!pud)
+		return VM_FAULT_OOM;
+	pmd = pmd_alloc(mm, pud, address);
+	if (!pmd)
+		return VM_FAULT_OOM;
+	pte = pte_alloc_map(mm, pmd, address);
+	if (!pte)
+		return VM_FAULT_OOM;
+
+	return handle_pte_fault(mm, vma, address, pte, pmd, write_access);
+}
+
+EXPORT_SYMBOL_GPL(__handle_mm_fault);
+
+#ifndef __PAGETABLE_PUD_FOLDED
+/*
+ * Allocate page upper directory.
+ * We've already handled the fast-path in-line.
+ */
+int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
+{
+	pud_t *new = pud_alloc_one(mm, address);
+	if (!new)
+		return -ENOMEM;
+
+	spin_lock(&mm->page_table_lock);
+	if (pgd_present(*pgd))		/* Another has populated it */
+		pud_free(new);
+	else
+		pgd_populate(mm, pgd, new);
+	spin_unlock(&mm->page_table_lock);
+	return 0;
+}
+#else
+/* Workaround for gcc 2.96 */
+int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
+{
+	return 0;
+}
+#endif /* __PAGETABLE_PUD_FOLDED */
+
+#ifndef __PAGETABLE_PMD_FOLDED
+/*
+ * Allocate page middle directory.
+ * We've already handled the fast-path in-line.
+ */
+int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
+{
+	pmd_t *new = pmd_alloc_one(mm, address);
+	if (!new)
+		return -ENOMEM;
+
+	spin_lock(&mm->page_table_lock);
+#ifndef __ARCH_HAS_4LEVEL_HACK
+	if (pud_present(*pud))		/* Another has populated it */
+		pmd_free(new);
+	else
+		pud_populate(mm, pud, new);
+#else
+	if (pgd_present(*pud))		/* Another has populated it */
+		pmd_free(new);
+	else
+		pgd_populate(mm, pud, new);
+#endif /* __ARCH_HAS_4LEVEL_HACK */
+	spin_unlock(&mm->page_table_lock);
+	return 0;
+}
+#else
+/* Workaround for gcc 2.96 */
+int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
+{
+	return 0;
+}
+#endif /* __PAGETABLE_PMD_FOLDED */
+
+int make_pages_present(unsigned long addr, unsigned long end)
+{
+	int ret, len, write;
+	struct vm_area_struct * vma;
+
+	vma = find_vma(current->mm, addr);
+	if (!vma)
+		return -1;
+	write = (vma->vm_flags & VM_WRITE) != 0;
+	if (addr >= end)
+		BUG();
+	if (end > vma->vm_end)
+		BUG();
+	len = (end+PAGE_SIZE-1)/PAGE_SIZE-addr/PAGE_SIZE;
+	ret = get_user_pages(current, current->mm, addr,
+			len, write, 0, NULL, NULL);
+	if (ret < 0)
+		return ret;
+	return ret == len ? 0 : -1;
+}
+
+/* 
+ * Map a vmalloc()-space virtual address to the physical page.
+ */
+struct page * vmalloc_to_page(void * vmalloc_addr)
+{
+	unsigned long addr = (unsigned long) vmalloc_addr;
+	struct page *page = NULL;
+	pgd_t *pgd = pgd_offset_k(addr);
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *ptep, pte;
+  
+	if (!pgd_none(*pgd)) {
+		pud = pud_offset(pgd, addr);
+		if (!pud_none(*pud)) {
+			pmd = pmd_offset(pud, addr);
+			if (!pmd_none(*pmd)) {
+				ptep = pte_offset_map(pmd, addr);
+				pte = *ptep;
+				if (pte_present(pte))
+					page = pte_page(pte);
+				pte_unmap(ptep);
+			}
+		}
+	}
+	return page;
+}
+
+EXPORT_SYMBOL(vmalloc_to_page);
+
+/*
+ * Map a vmalloc()-space virtual address to the physical page frame number.
+ */
+unsigned long vmalloc_to_pfn(void * vmalloc_addr)
+{
+	return page_to_pfn(vmalloc_to_page(vmalloc_addr));
+}
+
+EXPORT_SYMBOL(vmalloc_to_pfn);
+
+#if !defined(__HAVE_ARCH_GATE_AREA)
+
+#if defined(AT_SYSINFO_EHDR)
+static struct vm_area_struct gate_vma;
+
+static int __init gate_vma_init(void)
+{
+	gate_vma.vm_mm = NULL;
+	gate_vma.vm_start = FIXADDR_USER_START;
+	gate_vma.vm_end = FIXADDR_USER_END;
+	gate_vma.vm_page_prot = PAGE_READONLY;
+	gate_vma.vm_flags = 0;
+	return 0;
+}
+__initcall(gate_vma_init);
+#endif
+
+struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
+{
+#ifdef AT_SYSINFO_EHDR
+	return &gate_vma;
+#else
+	return NULL;
+#endif
+}
+
+int in_gate_area_no_task(unsigned long addr)
+{
+#ifdef AT_SYSINFO_EHDR
+	if ((addr >= FIXADDR_USER_START) && (addr < FIXADDR_USER_END))
+		return 1;
+#endif
+	return 0;
+}
+
+#endif	/* __HAVE_ARCH_GATE_AREA */
diff -urN oldtree/mm/page_alloc.c newtree/mm/page_alloc.c
--- oldtree/mm/page_alloc.c	2006-02-18 15:18:30.125737440 +0000
+++ newtree/mm/page_alloc.c	2006-02-18 15:24:31.449807832 +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>
@@ -447,6 +448,7 @@
 {
 	if (order == 0) {
 		__ClearPageReserved(page);
+		ClearPageNosave(page);
 		set_page_count(page, 0);
 
 		free_hot_cold_page(page, 0);
@@ -460,6 +462,7 @@
 			if (loop + 16 < BITS_PER_LONG)
 				prefetchw(p + 16);
 			__ClearPageReserved(p);
+			ClearPageNosave(p);
 			set_page_count(p, 0);
 		}
 
@@ -961,8 +964,8 @@
 
 	/* 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 */
diff -urN oldtree/mm/page_alloc.c.orig newtree/mm/page_alloc.c.orig
--- oldtree/mm/page_alloc.c.orig	1970-01-01 00:00:00.000000000 +0000
+++ newtree/mm/page_alloc.c.orig	2006-02-18 15:18:30.000000000 +0000
@@ -0,0 +1,2732 @@
+/*
+ *  linux/mm/page_alloc.c
+ *
+ *  Manages the free list, the system allocates free pages here.
+ *  Note that kmalloc() lives in slab.c
+ *
+ *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
+ *  Swap reorganised 29.12.95, Stephen Tweedie
+ *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
+ *  Reshaped it to be a zoned allocator, Ingo Molnar, Red Hat, 1999
+ *  Discontiguous memory support, Kanoj Sarcar, SGI, Nov 1999
+ *  Zone balancing, Kanoj Sarcar, SGI, Jan 2000
+ *  Per cpu hot/cold page lists, bulk allocation, Martin J. Bligh, Sept 2002
+ *          (lots of bits borrowed from Ingo Molnar & Andrew Morton)
+ */
+
+#include <linux/config.h>
+#include <linux/stddef.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/interrupt.h>
+#include <linux/pagemap.h>
+#include <linux/bootmem.h>
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/suspend.h>
+#include <linux/pagevec.h>
+#include <linux/blkdev.h>
+#include <linux/slab.h>
+#include <linux/notifier.h>
+#include <linux/topology.h>
+#include <linux/sysctl.h>
+#include <linux/cpu.h>
+#include <linux/cpuset.h>
+#include <linux/memory_hotplug.h>
+#include <linux/nodemask.h>
+#include <linux/vmalloc.h>
+#include <linux/mempolicy.h>
+
+#include <asm/tlbflush.h>
+#include "internal.h"
+
+/*
+ * MCD - HACK: Find somewhere to initialize this EARLY, or make this
+ * initializer cleaner
+ */
+nodemask_t node_online_map __read_mostly = { { [0] = 1UL } };
+EXPORT_SYMBOL(node_online_map);
+nodemask_t node_possible_map __read_mostly = NODE_MASK_ALL;
+EXPORT_SYMBOL(node_possible_map);
+struct pglist_data *pgdat_list __read_mostly;
+unsigned long totalram_pages __read_mostly;
+unsigned long totalhigh_pages __read_mostly;
+long nr_swap_pages;
+int percpu_pagelist_fraction;
+
+static void fastcall free_hot_cold_page(struct page *page, int cold);
+static void __free_pages_ok(struct page *page, unsigned int order);
+
+/*
+ * results with 256, 32 in the lowmem_reserve sysctl:
+ *	1G machine -> (16M dma, 800M-16M normal, 1G-800M high)
+ *	1G machine -> (16M dma, 784M normal, 224M high)
+ *	NORMAL allocation will leave 784M/256 of ram reserved in the ZONE_DMA
+ *	HIGHMEM allocation will leave 224M/32 of ram reserved in ZONE_NORMAL
+ *	HIGHMEM allocation will (224M+784M)/256 of ram reserved in ZONE_DMA
+ *
+ * TBD: should special case ZONE_DMA32 machines here - in those we normally
+ * don't need any ZONE_NORMAL reservation
+ */
+int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1] = { 256, 256, 32 };
+
+EXPORT_SYMBOL(totalram_pages);
+
+/*
+ * Used by page_zone() to look up the address of the struct zone whose
+ * id is encoded in the upper bits of page->flags
+ */
+struct zone *zone_table[1 << ZONETABLE_SHIFT] __read_mostly;
+EXPORT_SYMBOL(zone_table);
+
+static char *zone_names[MAX_NR_ZONES] = { "DMA", "DMA32", "Normal", "HighMem" };
+int min_free_kbytes = 1024;
+
+unsigned long __initdata nr_kernel_pages;
+unsigned long __initdata nr_all_pages;
+
+#ifdef CONFIG_DEBUG_VM
+static int page_outside_zone_boundaries(struct zone *zone, struct page *page)
+{
+	int ret = 0;
+	unsigned seq;
+	unsigned long pfn = page_to_pfn(page);
+
+	do {
+		seq = zone_span_seqbegin(zone);
+		if (pfn >= zone->zone_start_pfn + zone->spanned_pages)
+			ret = 1;
+		else if (pfn < zone->zone_start_pfn)
+			ret = 1;
+	} while (zone_span_seqretry(zone, seq));
+
+	return ret;
+}
+
+static int page_is_consistent(struct zone *zone, struct page *page)
+{
+#ifdef CONFIG_HOLES_IN_ZONE
+	if (!pfn_valid(page_to_pfn(page)))
+		return 0;
+#endif
+	if (zone != page_zone(page))
+		return 0;
+
+	return 1;
+}
+/*
+ * Temporary debugging check for pages not lying within a given zone.
+ */
+static int bad_range(struct zone *zone, struct page *page)
+{
+	if (page_outside_zone_boundaries(zone, page))
+		return 1;
+	if (!page_is_consistent(zone, page))
+		return 1;
+
+	return 0;
+}
+
+#else
+static inline int bad_range(struct zone *zone, struct page *page)
+{
+	return 0;
+}
+#endif
+
+static void bad_page(struct page *page)
+{
+	printk(KERN_EMERG "Bad page state in process '%s'\n"
+		KERN_EMERG "page:%p flags:0x%0*lx mapping:%p mapcount:%d count:%d\n"
+		KERN_EMERG "Trying to fix it up, but a reboot is needed\n"
+		KERN_EMERG "Backtrace:\n",
+		current->comm, page, (int)(2*sizeof(unsigned long)),
+		(unsigned long)page->flags, page->mapping,
+		page_mapcount(page), page_count(page));
+	dump_stack();
+	page->flags &= ~(1 << PG_lru	|
+			1 << PG_private |
+			1 << PG_locked	|
+			1 << PG_active	|
+			1 << PG_dirty	|
+			1 << PG_reclaim |
+			1 << PG_slab    |
+			1 << PG_swapcache |
+			1 << PG_writeback );
+	set_page_count(page, 0);
+	reset_page_mapcount(page);
+	page->mapping = NULL;
+	add_taint(TAINT_BAD_PAGE);
+}
+
+/*
+ * Higher-order pages are called "compound pages".  They are structured thusly:
+ *
+ * The first PAGE_SIZE page is called the "head page".
+ *
+ * The remaining PAGE_SIZE pages are called "tail pages".
+ *
+ * All pages have PG_compound set.  All pages have their ->private pointing at
+ * the head page (even the head page has this).
+ *
+ * The first tail page's ->lru.next holds the address of the compound page's
+ * put_page() function.  Its ->lru.prev holds the order of allocation.
+ * This usage means that zero-order pages may not be compound.
+ */
+
+static void free_compound_page(struct page *page)
+{
+	__free_pages_ok(page, (unsigned long)page[1].lru.prev);
+}
+
+static void prep_compound_page(struct page *page, unsigned long order)
+{
+	int i;
+	int nr_pages = 1 << order;
+
+	page[1].lru.next = (void *)free_compound_page;	/* set dtor */
+	page[1].lru.prev = (void *)order;
+	for (i = 0; i < nr_pages; i++) {
+		struct page *p = page + i;
+
+		SetPageCompound(p);
+		set_page_private(p, (unsigned long)page);
+	}
+}
+
+static void destroy_compound_page(struct page *page, unsigned long order)
+{
+	int i;
+	int nr_pages = 1 << order;
+
+	if (unlikely((unsigned long)page[1].lru.prev != order))
+		bad_page(page);
+
+	for (i = 0; i < nr_pages; i++) {
+		struct page *p = page + i;
+
+		if (unlikely(!PageCompound(p) |
+				(page_private(p) != (unsigned long)page)))
+			bad_page(page);
+		ClearPageCompound(p);
+	}
+}
+
+/*
+ * function for dealing with page's order in buddy system.
+ * zone->lock is already acquired when we use these.
+ * So, we don't need atomic page->flags operations here.
+ */
+static inline unsigned long page_order(struct page *page) {
+	return page_private(page);
+}
+
+static inline void set_page_order(struct page *page, int order) {
+	set_page_private(page, order);
+	__SetPagePrivate(page);
+}
+
+static inline void rmv_page_order(struct page *page)
+{
+	__ClearPagePrivate(page);
+	set_page_private(page, 0);
+}
+
+/*
+ * Locate the struct page for both the matching buddy in our
+ * pair (buddy1) and the combined O(n+1) page they form (page).
+ *
+ * 1) Any buddy B1 will have an order O twin B2 which satisfies
+ * the following equation:
+ *     B2 = B1 ^ (1 << O)
+ * For example, if the starting buddy (buddy2) is #8 its order
+ * 1 buddy is #10:
+ *     B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10
+ *
+ * 2) Any buddy B will have an order O+1 parent P which
+ * satisfies the following equation:
+ *     P = B & ~(1 << O)
+ *
+ * Assumption: *_mem_map is contigious at least up to MAX_ORDER
+ */
+static inline struct page *
+__page_find_buddy(struct page *page, unsigned long page_idx, unsigned int order)
+{
+	unsigned long buddy_idx = page_idx ^ (1 << order);
+
+	return page + (buddy_idx - page_idx);
+}
+
+static inline unsigned long
+__find_combined_index(unsigned long page_idx, unsigned int order)
+{
+	return (page_idx & ~(1 << order));
+}
+
+/*
+ * This function checks whether a page is free && is the buddy
+ * we can do coalesce a page and its buddy if
+ * (a) the buddy is not in a hole &&
+ * (b) the buddy is free &&
+ * (c) the buddy is on the buddy system &&
+ * (d) a page and its buddy have the same order.
+ * for recording page's order, we use page_private(page) and PG_private.
+ *
+ */
+static inline int page_is_buddy(struct page *page, int order)
+{
+#ifdef CONFIG_HOLES_IN_ZONE
+	if (!pfn_valid(page_to_pfn(page)))
+		return 0;
+#endif
+
+       if (PagePrivate(page)           &&
+           (page_order(page) == order) &&
+            page_count(page) == 0)
+               return 1;
+       return 0;
+}
+
+/*
+ * Freeing function for a buddy system allocator.
+ *
+ * The concept of a buddy system is to maintain direct-mapped table
+ * (containing bit values) for memory blocks of various "orders".
+ * The bottom level table contains the map for the smallest allocatable
+ * units of memory (here, pages), and each level above it describes
+ * pairs of units from the levels below, hence, "buddies".
+ * At a high level, all that happens here is marking the table entry
+ * at the bottom level available, and propagating the changes upward
+ * as necessary, plus some accounting needed to play nicely with other
+ * parts of the VM system.
+ * At each level, we keep a list of pages, which are heads of continuous
+ * free pages of length of (1 << order) and marked with PG_Private.Page's
+ * order is recorded in page_private(page) field.
+ * So when we are allocating or freeing one, we can derive the state of the
+ * other.  That is, if we allocate a small block, and both were   
+ * free, the remainder of the region must be split into blocks.   
+ * If a block is freed, and its buddy is also free, then this
+ * triggers coalescing into a block of larger size.            
+ *
+ * -- wli
+ */
+
+static inline void __free_one_page(struct page *page,
+		struct zone *zone, unsigned int order)
+{
+	unsigned long page_idx;
+	int order_size = 1 << order;
+
+	if (unlikely(PageCompound(page)))
+		destroy_compound_page(page, order);
+
+	page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1);
+
+	BUG_ON(page_idx & (order_size - 1));
+	BUG_ON(bad_range(zone, page));
+
+	zone->free_pages += order_size;
+	while (order < MAX_ORDER-1) {
+		unsigned long combined_idx;
+		struct free_area *area;
+		struct page *buddy;
+
+		buddy = __page_find_buddy(page, page_idx, order);
+		if (!page_is_buddy(buddy, order))
+			break;		/* Move the buddy up one level. */
+
+		list_del(&buddy->lru);
+		area = zone->free_area + order;
+		area->nr_free--;
+		rmv_page_order(buddy);
+		combined_idx = __find_combined_index(page_idx, order);
+		page = page + (combined_idx - page_idx);
+		page_idx = combined_idx;
+		order++;
+	}
+	set_page_order(page, order);
+	list_add(&page->lru, &zone->free_area[order].free_list);
+	zone->free_area[order].nr_free++;
+}
+
+static inline int free_pages_check(struct page *page)
+{
+	if (unlikely(page_mapcount(page) |
+		(page->mapping != NULL)  |
+		(page_count(page) != 0)  |
+		(page->flags & (
+			1 << PG_lru	|
+			1 << PG_private |
+			1 << PG_locked	|
+			1 << PG_active	|
+			1 << PG_reclaim	|
+			1 << PG_slab	|
+			1 << PG_swapcache |
+			1 << PG_writeback |
+			1 << PG_reserved ))))
+		bad_page(page);
+	if (PageDirty(page))
+		__ClearPageDirty(page);
+	/*
+	 * For now, we report if PG_reserved was found set, but do not
+	 * clear it, and do not free the page.  But we shall soon need
+	 * to do more, for when the ZERO_PAGE count wraps negative.
+	 */
+	return PageReserved(page);
+}
+
+/*
+ * Frees a list of pages. 
+ * Assumes all pages on list are in same zone, and of same order.
+ * count is the number of pages to free.
+ *
+ * If the zone was previously in an "all pages pinned" state then look to
+ * see if this freeing clears that state.
+ *
+ * And clear the zone's pages_scanned counter, to hold off the "all pages are
+ * pinned" detection logic.
+ */
+static void free_pages_bulk(struct zone *zone, int count,
+					struct list_head *list, int order)
+{
+	spin_lock(&zone->lock);
+	zone->all_unreclaimable = 0;
+	zone->pages_scanned = 0;
+	while (count--) {
+		struct page *page;
+
+		BUG_ON(list_empty(list));
+		page = list_entry(list->prev, struct page, lru);
+		/* have to delete it as __free_one_page list manipulates */
+		list_del(&page->lru);
+		__free_one_page(page, zone, order);
+	}
+	spin_unlock(&zone->lock);
+}
+
+static void free_one_page(struct zone *zone, struct page *page, int order)
+{
+	LIST_HEAD(list);
+	list_add(&page->lru, &list);
+	free_pages_bulk(zone, 1, &list, order);
+}
+
+static void __free_pages_ok(struct page *page, unsigned int order)
+{
+	unsigned long flags;
+	int i;
+	int reserved = 0;
+
+	arch_free_page(page, order);
+	if (!PageHighMem(page))
+		mutex_debug_check_no_locks_freed(page_address(page),
+						 PAGE_SIZE<<order);
+
+#ifndef CONFIG_MMU
+	for (i = 1 ; i < (1 << order) ; ++i)
+		__put_page(page + i);
+#endif
+
+	for (i = 0 ; i < (1 << order) ; ++i)
+		reserved += free_pages_check(page + i);
+	if (reserved)
+		return;
+
+	kernel_map_pages(page, 1 << order, 0);
+	local_irq_save(flags);
+	__mod_page_state(pgfree, 1 << order);
+	free_one_page(page_zone(page), page, order);
+	local_irq_restore(flags);
+}
+
+/*
+ * permit the bootmem allocator to evade page validation on high-order frees
+ */
+void fastcall __init __free_pages_bootmem(struct page *page, unsigned int order)
+{
+	if (order == 0) {
+		__ClearPageReserved(page);
+		set_page_count(page, 0);
+
+		free_hot_cold_page(page, 0);
+	} else {
+		LIST_HEAD(list);
+		int loop;
+
+		for (loop = 0; loop < BITS_PER_LONG; loop++) {
+			struct page *p = &page[loop];
+
+			if (loop + 16 < BITS_PER_LONG)
+				prefetchw(p + 16);
+			__ClearPageReserved(p);
+			set_page_count(p, 0);
+		}
+
+		arch_free_page(page, order);
+
+		mod_page_state(pgfree, 1 << order);
+
+		list_add(&page->lru, &list);
+		kernel_map_pages(page, 1 << order, 0);
+		free_pages_bulk(page_zone(page), 1, &list, order);
+	}
+}
+
+
+/*
+ * The order of subdivision here is critical for the IO subsystem.
+ * Please do not alter this order without good reasons and regression
+ * testing. Specifically, as large blocks of memory are subdivided,
+ * the order in which smaller blocks are delivered depends on the order
+ * they're subdivided in this function. This is the primary factor
+ * influencing the order in which pages are delivered to the IO
+ * subsystem according to empirical testing, and this is also justified
+ * by considering the behavior of a buddy system containing a single
+ * large block of memory acted on by a series of small allocations.
+ * This behavior is a critical factor in sglist merging's success.
+ *
+ * -- wli
+ */
+static inline void expand(struct zone *zone, struct page *page,
+ 	int low, int high, struct free_area *area)
+{
+	unsigned long size = 1 << high;
+
+	while (high > low) {
+		area--;
+		high--;
+		size >>= 1;
+		BUG_ON(bad_range(zone, &page[size]));
+		list_add(&page[size].lru, &area->free_list);
+		area->nr_free++;
+		set_page_order(&page[size], high);
+	}
+}
+
+/*
+ * This page is about to be returned from the page allocator
+ */
+static int prep_new_page(struct page *page, int order)
+{
+	if (unlikely(page_mapcount(page) |
+		(page->mapping != NULL)  |
+		(page_count(page) != 0)  |
+		(page->flags & (
+			1 << PG_lru	|
+			1 << PG_private	|
+			1 << PG_locked	|
+			1 << PG_active	|
+			1 << PG_dirty	|
+			1 << PG_reclaim	|
+			1 << PG_slab    |
+			1 << PG_swapcache |
+			1 << PG_writeback |
+			1 << PG_reserved ))))
+		bad_page(page);
+
+	/*
+	 * For now, we report if PG_reserved was found set, but do not
+	 * clear it, and do not allocate the page: as a safety net.
+	 */
+	if (PageReserved(page))
+		return 1;
+
+	page->flags &= ~(1 << PG_uptodate | 1 << PG_error |
+			1 << PG_referenced | 1 << PG_arch_1 |
+			1 << PG_checked | 1 << PG_mappedtodisk);
+	set_page_private(page, 0);
+	set_page_refs(page, order);
+	kernel_map_pages(page, 1 << order, 1);
+	return 0;
+}
+
+/* 
+ * Do the hard work of removing an element from the buddy allocator.
+ * Call me with the zone->lock already held.
+ */
+static struct page *__rmqueue(struct zone *zone, unsigned int order)
+{
+	struct free_area * area;
+	unsigned int current_order;
+	struct page *page;
+
+	for (current_order = order; current_order < MAX_ORDER; ++current_order) {
+		area = zone->free_area + current_order;
+		if (list_empty(&area->free_list))
+			continue;
+
+		page = list_entry(area->free_list.next, struct page, lru);
+		list_del(&page->lru);
+		rmv_page_order(page);
+		area->nr_free--;
+		zone->free_pages -= 1UL << order;
+		expand(zone, page, order, current_order, area);
+		return page;
+	}
+
+	return NULL;
+}
+
+/* 
+ * Obtain a specified number of elements from the buddy allocator, all under
+ * a single hold of the lock, for efficiency.  Add them to the supplied list.
+ * Returns the number of new pages which were placed at *list.
+ */
+static int rmqueue_bulk(struct zone *zone, unsigned int order, 
+			unsigned long count, struct list_head *list)
+{
+	int i;
+	
+	spin_lock(&zone->lock);
+	for (i = 0; i < count; ++i) {
+		struct page *page = __rmqueue(zone, order);
+		if (unlikely(page == NULL))
+			break;
+		list_add_tail(&page->lru, list);
+	}
+	spin_unlock(&zone->lock);
+	return i;
+}
+
+#ifdef CONFIG_NUMA
+/* Called from the slab reaper to drain remote pagesets */
+void drain_remote_pages(void)
+{
+	struct zone *zone;
+	int i;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	for_each_zone(zone) {
+		struct per_cpu_pageset *pset;
+
+		/* Do not drain local pagesets */
+		if (zone->zone_pgdat->node_id == numa_node_id())
+			continue;
+
+		pset = zone_pcp(zone, smp_processor_id());
+		for (i = 0; i < ARRAY_SIZE(pset->pcp); i++) {
+			struct per_cpu_pages *pcp;
+
+			pcp = &pset->pcp[i];
+			free_pages_bulk(zone, pcp->count, &pcp->list, 0);
+			pcp->count = 0;
+		}
+	}
+	local_irq_restore(flags);
+}
+#endif
+
+#if defined(CONFIG_PM) || defined(CONFIG_HOTPLUG_CPU)
+static void __drain_pages(unsigned int cpu)
+{
+	unsigned long flags;
+	struct zone *zone;
+	int i;
+
+	for_each_zone(zone) {
+		struct per_cpu_pageset *pset;
+
+		pset = zone_pcp(zone, cpu);
+		for (i = 0; i < ARRAY_SIZE(pset->pcp); i++) {
+			struct per_cpu_pages *pcp;
+
+			pcp = &pset->pcp[i];
+			local_irq_save(flags);
+			free_pages_bulk(zone, pcp->count, &pcp->list, 0);
+			pcp->count = 0;
+			local_irq_restore(flags);
+		}
+	}
+}
+#endif /* CONFIG_PM || CONFIG_HOTPLUG_CPU */
+
+#ifdef CONFIG_PM
+
+void mark_free_pages(struct zone *zone)
+{
+	unsigned long zone_pfn, flags;
+	int order;
+	struct list_head *curr;
+
+	if (!zone->spanned_pages)
+		return;
+
+	spin_lock_irqsave(&zone->lock, flags);
+	for (zone_pfn = 0; zone_pfn < zone->spanned_pages; ++zone_pfn)
+		ClearPageNosaveFree(pfn_to_page(zone_pfn + zone->zone_start_pfn));
+
+	for (order = MAX_ORDER - 1; order >= 0; --order)
+		list_for_each(curr, &zone->free_area[order].free_list) {
+			unsigned long start_pfn, i;
+
+			start_pfn = page_to_pfn(list_entry(curr, struct page, lru));
+
+			for (i=0; i < (1<<order); i++)
+				SetPageNosaveFree(pfn_to_page(start_pfn+i));
+	}
+	spin_unlock_irqrestore(&zone->lock, flags);
+}
+
+/*
+ * Spill all of this CPU's per-cpu pages back into the buddy allocator.
+ */
+void drain_local_pages(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);	
+	__drain_pages(smp_processor_id());
+	local_irq_restore(flags);	
+}
+#endif /* CONFIG_PM */
+
+static void zone_statistics(struct zonelist *zonelist, struct zone *z, int cpu)
+{
+#ifdef CONFIG_NUMA
+	pg_data_t *pg = z->zone_pgdat;
+	pg_data_t *orig = zonelist->zones[0]->zone_pgdat;
+	struct per_cpu_pageset *p;
+
+	p = zone_pcp(z, cpu);
+	if (pg == orig) {
+		p->numa_hit++;
+	} else {
+		p->numa_miss++;
+		zone_pcp(zonelist->zones[0], cpu)->numa_foreign++;
+	}
+	if (pg == NODE_DATA(numa_node_id()))
+		p->local_node++;
+	else
+		p->other_node++;
+#endif
+}
+
+/*
+ * Free a 0-order page
+ */
+static void fastcall free_hot_cold_page(struct page *page, int cold)
+{
+	struct zone *zone = page_zone(page);
+	struct per_cpu_pages *pcp;
+	unsigned long flags;
+
+	arch_free_page(page, 0);
+
+	if (PageAnon(page))
+		page->mapping = NULL;
+	if (free_pages_check(page))
+		return;
+
+	kernel_map_pages(page, 1, 0);
+
+	pcp = &zone_pcp(zone, get_cpu())->pcp[cold];
+	local_irq_save(flags);
+	__inc_page_state(pgfree);
+	list_add(&page->lru, &pcp->list);
+	pcp->count++;
+	if (pcp->count >= pcp->high) {
+		free_pages_bulk(zone, pcp->batch, &pcp->list, 0);
+		pcp->count -= pcp->batch;
+	}
+	local_irq_restore(flags);
+	put_cpu();
+}
+
+void fastcall free_hot_page(struct page *page)
+{
+	free_hot_cold_page(page, 0);
+}
+	
+void fastcall free_cold_page(struct page *page)
+{
+	free_hot_cold_page(page, 1);
+}
+
+static inline void prep_zero_page(struct page *page, int order, gfp_t gfp_flags)
+{
+	int i;
+
+	BUG_ON((gfp_flags & (__GFP_WAIT | __GFP_HIGHMEM)) == __GFP_HIGHMEM);
+	for(i = 0; i < (1 << order); i++)
+		clear_highpage(page + i);
+}
+
+/*
+ * Really, prep_compound_page() should be called from __rmqueue_bulk().  But
+ * we cheat by calling it from here, in the order > 0 path.  Saves a branch
+ * or two.
+ */
+static struct page *buffered_rmqueue(struct zonelist *zonelist,
+			struct zone *zone, int order, gfp_t gfp_flags)
+{
+	unsigned long flags;
+	struct page *page;
+	int cold = !!(gfp_flags & __GFP_COLD);
+	int cpu;
+
+again:
+	cpu  = get_cpu();
+	if (likely(order == 0)) {
+		struct per_cpu_pages *pcp;
+
+		pcp = &zone_pcp(zone, cpu)->pcp[cold];
+		local_irq_save(flags);
+		if (!pcp->count) {
+			pcp->count += rmqueue_bulk(zone, 0,
+						pcp->batch, &pcp->list);
+			if (unlikely(!pcp->count))
+				goto failed;
+		}
+		page = list_entry(pcp->list.next, struct page, lru);
+		list_del(&page->lru);
+		pcp->count--;
+	} else {
+		spin_lock_irqsave(&zone->lock, flags);
+		page = __rmqueue(zone, order);
+		spin_unlock(&zone->lock);
+		if (!page)
+			goto failed;
+	}
+
+	__mod_page_state_zone(zone, pgalloc, 1 << order);
+	zone_statistics(zonelist, zone, cpu);
+	local_irq_restore(flags);
+	put_cpu();
+
+	BUG_ON(bad_range(zone, page));
+	if (prep_new_page(page, order))
+		goto again;
+
+	if (gfp_flags & __GFP_ZERO)
+		prep_zero_page(page, order, gfp_flags);
+
+	if (order && (gfp_flags & __GFP_COMP))
+		prep_compound_page(page, order);
+	return page;
+
+failed:
+	local_irq_restore(flags);
+	put_cpu();
+	return NULL;
+}
+
+#define ALLOC_NO_WATERMARKS	0x01 /* don't check watermarks at all */
+#define ALLOC_WMARK_MIN		0x02 /* use pages_min watermark */
+#define ALLOC_WMARK_LOW		0x04 /* use pages_low watermark */
+#define ALLOC_WMARK_HIGH	0x08 /* use pages_high watermark */
+#define ALLOC_HARDER		0x10 /* try to alloc harder */
+#define ALLOC_HIGH		0x20 /* __GFP_HIGH set */
+#define ALLOC_CPUSET		0x40 /* check for correct cpuset */
+
+/*
+ * Return 1 if free pages are above 'mark'. This takes into account the order
+ * of the allocation.
+ */
+int zone_watermark_ok(struct zone *z, int order, unsigned long mark,
+		      int classzone_idx, int alloc_flags)
+{
+	/* free_pages my go negative - that's OK */
+	long min = mark, free_pages = z->free_pages - (1 << order) + 1;
+	int o;
+
+	if (alloc_flags & ALLOC_HIGH)
+		min -= min / 2;
+	if (alloc_flags & ALLOC_HARDER)
+		min -= min / 4;
+
+	if (free_pages <= min + z->lowmem_reserve[classzone_idx])
+		return 0;
+	for (o = 0; o < order; o++) {
+		/* At the next order, this order's pages become unavailable */
+		free_pages -= z->free_area[o].nr_free << o;
+
+		/* Require fewer higher order pages to be free */
+		min >>= 1;
+
+		if (free_pages <= min)
+			return 0;
+	}
+	return 1;
+}
+
+/*
+ * get_page_from_freeliest goes through the zonelist trying to allocate
+ * a page.
+ */
+static struct page *
+get_page_from_freelist(gfp_t gfp_mask, unsigned int order,
+		struct zonelist *zonelist, int alloc_flags)
+{
+	struct zone **z = zonelist->zones;
+	struct page *page = NULL;
+	int classzone_idx = zone_idx(*z);
+
+	/*
+	 * Go through the zonelist once, looking for a zone with enough free.
+	 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
+	 */
+	do {
+		if ((alloc_flags & ALLOC_CPUSET) &&
+				!cpuset_zone_allowed(*z, gfp_mask))
+			continue;
+
+		if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {
+			unsigned long mark;
+			if (alloc_flags & ALLOC_WMARK_MIN)
+				mark = (*z)->pages_min;
+			else if (alloc_flags & ALLOC_WMARK_LOW)
+				mark = (*z)->pages_low;
+			else
+				mark = (*z)->pages_high;
+			if (!zone_watermark_ok(*z, order, mark,
+				    classzone_idx, alloc_flags))
+				if (!zone_reclaim_mode ||
+				    !zone_reclaim(*z, gfp_mask, order))
+					continue;
+		}
+
+		page = buffered_rmqueue(zonelist, *z, order, gfp_mask);
+		if (page) {
+			break;
+		}
+	} while (*(++z) != NULL);
+	return page;
+}
+
+/*
+ * This is the 'heart' of the zoned buddy allocator.
+ */
+struct page * fastcall
+__alloc_pages(gfp_t gfp_mask, unsigned int order,
+		struct zonelist *zonelist)
+{
+	const gfp_t wait = gfp_mask & __GFP_WAIT;
+	struct zone **z;
+	struct page *page;
+	struct reclaim_state reclaim_state;
+	struct task_struct *p = current;
+	int do_retry;
+	int alloc_flags;
+	int did_some_progress;
+
+	might_sleep_if(wait);
+
+restart:
+	z = zonelist->zones;  /* the list of zones suitable for gfp_mask */
+
+	if (unlikely(*z == NULL)) {
+		/* Should this ever happen?? */
+		return NULL;
+	}
+
+	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
+				zonelist, ALLOC_WMARK_LOW|ALLOC_CPUSET);
+	if (page)
+		goto got_pg;
+
+	do {
+		wakeup_kswapd(*z, order);
+	} while (*(++z));
+
+	/*
+	 * OK, we're below the kswapd watermark and have kicked background
+	 * reclaim. Now things get more complex, so set up alloc_flags according
+	 * to how we want to proceed.
+	 *
+	 * The caller may dip into page reserves a bit more if the caller
+	 * cannot run direct reclaim, or if the caller has realtime scheduling
+	 * policy or is asking for __GFP_HIGH memory.  GFP_ATOMIC requests will
+	 * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH).
+	 */
+	alloc_flags = ALLOC_WMARK_MIN;
+	if ((unlikely(rt_task(p)) && !in_interrupt()) || !wait)
+		alloc_flags |= ALLOC_HARDER;
+	if (gfp_mask & __GFP_HIGH)
+		alloc_flags |= ALLOC_HIGH;
+	alloc_flags |= ALLOC_CPUSET;
+
+	/*
+	 * Go through the zonelist again. Let __GFP_HIGH and allocations
+	 * coming from realtime tasks go deeper into reserves.
+	 *
+	 * This is the last chance, in general, before the goto nopage.
+	 * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
+	 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
+	 */
+	page = get_page_from_freelist(gfp_mask, order, zonelist, alloc_flags);
+	if (page)
+		goto got_pg;
+
+	/* This allocation should allow future memory freeing. */
+
+	if (((p->flags & PF_MEMALLOC) || unlikely(test_thread_flag(TIF_MEMDIE)))
+			&& !in_interrupt()) {
+		if (!(gfp_mask & __GFP_NOMEMALLOC)) {
+nofail_alloc:
+			/* go through the zonelist yet again, ignoring mins */
+			page = get_page_from_freelist(gfp_mask, order,
+				zonelist, ALLOC_NO_WATERMARKS);
+			if (page)
+				goto got_pg;
+			if (gfp_mask & __GFP_NOFAIL) {
+				blk_congestion_wait(WRITE, HZ/50);
+				goto nofail_alloc;
+			}
+		}
+		goto nopage;
+	}
+
+	/* Atomic allocations - we can't balance anything */
+	if (!wait)
+		goto nopage;
+
+rebalance:
+	cond_resched();
+
+	/* We now go into synchronous reclaim */
+	cpuset_memory_pressure_bump();
+	p->flags |= PF_MEMALLOC;
+	reclaim_state.reclaimed_slab = 0;
+	p->reclaim_state = &reclaim_state;
+
+	did_some_progress = try_to_free_pages(zonelist->zones, gfp_mask);
+
+	p->reclaim_state = NULL;
+	p->flags &= ~PF_MEMALLOC;
+
+	cond_resched();
+
+	if (likely(did_some_progress)) {
+		page = get_page_from_freelist(gfp_mask, order,
+						zonelist, alloc_flags);
+		if (page)
+			goto got_pg;
+	} else if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
+		/*
+		 * Go through the zonelist yet one more time, keep
+		 * very high watermark here, this is only to catch
+		 * a parallel oom killing, we must fail if we're still
+		 * under heavy pressure.
+		 */
+		page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
+				zonelist, ALLOC_WMARK_HIGH|ALLOC_CPUSET);
+		if (page)
+			goto got_pg;
+
+		out_of_memory(gfp_mask, order);
+		goto restart;
+	}
+
+	/*
+	 * Don't let big-order allocations loop unless the caller explicitly
+	 * requests that.  Wait for some write requests to complete then retry.
+	 *
+	 * In this implementation, __GFP_REPEAT means __GFP_NOFAIL for order
+	 * <= 3, but that may not be true in other implementations.
+	 */
+	do_retry = 0;
+	if (!(gfp_mask & __GFP_NORETRY)) {
+		if ((order <= 3) || (gfp_mask & __GFP_REPEAT))
+			do_retry = 1;
+		if (gfp_mask & __GFP_NOFAIL)
+			do_retry = 1;
+	}
+	if (do_retry) {
+		blk_congestion_wait(WRITE, HZ/50);
+		goto rebalance;
+	}
+
+nopage:
+	if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit()) {
+		printk(KERN_WARNING "%s: page allocation failure."
+			" order:%d, mode:0x%x\n",
+			p->comm, order, gfp_mask);
+		dump_stack();
+		show_mem();
+	}
+got_pg:
+	return page;
+}
+
+EXPORT_SYMBOL(__alloc_pages);
+
+/*
+ * Common helper functions.
+ */
+fastcall unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order)
+{
+	struct page * page;
+	page = alloc_pages(gfp_mask, order);
+	if (!page)
+		return 0;
+	return (unsigned long) page_address(page);
+}
+
+EXPORT_SYMBOL(__get_free_pages);
+
+fastcall unsigned long get_zeroed_page(gfp_t gfp_mask)
+{
+	struct page * page;
+
+	/*
+	 * get_zeroed_page() returns a 32-bit address, which cannot represent
+	 * a highmem page
+	 */
+	BUG_ON((gfp_mask & __GFP_HIGHMEM) != 0);
+
+	page = alloc_pages(gfp_mask | __GFP_ZERO, 0);
+	if (page)
+		return (unsigned long) page_address(page);
+	return 0;
+}
+
+EXPORT_SYMBOL(get_zeroed_page);
+
+void __pagevec_free(struct pagevec *pvec)
+{
+	int i = pagevec_count(pvec);
+
+	while (--i >= 0)
+		free_hot_cold_page(pvec->pages[i], pvec->cold);
+}
+
+fastcall void __free_pages(struct page *page, unsigned int order)
+{
+	if (put_page_testzero(page)) {
+		if (order == 0)
+			free_hot_page(page);
+		else
+			__free_pages_ok(page, order);
+	}
+}
+
+EXPORT_SYMBOL(__free_pages);
+
+fastcall void free_pages(unsigned long addr, unsigned int order)
+{
+	if (addr != 0) {
+		BUG_ON(!virt_addr_valid((void *)addr));
+		__free_pages(virt_to_page((void *)addr), order);
+	}
+}
+
+EXPORT_SYMBOL(free_pages);
+
+/*
+ * Total amount of free (allocatable) RAM:
+ */
+unsigned int nr_free_pages(void)
+{
+	unsigned int sum = 0;
+	struct zone *zone;
+
+	for_each_zone(zone)
+		sum += zone->free_pages;
+
+	return sum;
+}
+
+EXPORT_SYMBOL(nr_free_pages);
+
+#ifdef CONFIG_NUMA
+unsigned int nr_free_pages_pgdat(pg_data_t *pgdat)
+{
+	unsigned int i, sum = 0;
+
+	for (i = 0; i < MAX_NR_ZONES; i++)
+		sum += pgdat->node_zones[i].free_pages;
+
+	return sum;
+}
+#endif
+
+static unsigned int nr_free_zone_pages(int offset)
+{
+	/* Just pick one node, since fallback list is circular */
+	pg_data_t *pgdat = NODE_DATA(numa_node_id());
+	unsigned int sum = 0;
+
+	struct zonelist *zonelist = pgdat->node_zonelists + offset;
+	struct zone **zonep = zonelist->zones;
+	struct zone *zone;
+
+	for (zone = *zonep++; zone; zone = *zonep++) {
+		unsigned long size = zone->present_pages;
+		unsigned long high = zone->pages_high;
+		if (size > high)
+			sum += size - high;
+	}
+
+	return sum;
+}
+
+/*
+ * Amount of free RAM allocatable within ZONE_DMA and ZONE_NORMAL
+ */
+unsigned int nr_free_buffer_pages(void)
+{
+	return nr_free_zone_pages(gfp_zone(GFP_USER));
+}
+
+/*
+ * Amount of free RAM allocatable within all zones
+ */
+unsigned int nr_free_pagecache_pages(void)
+{
+	return nr_free_zone_pages(gfp_zone(GFP_HIGHUSER));
+}
+
+#ifdef CONFIG_HIGHMEM
+unsigned int nr_free_highpages (void)
+{
+	pg_data_t *pgdat;
+	unsigned int pages = 0;
+
+	for_each_pgdat(pgdat)
+		pages += pgdat->node_zones[ZONE_HIGHMEM].free_pages;
+
+	return pages;
+}
+#endif
+
+#ifdef CONFIG_NUMA
+static void show_node(struct zone *zone)
+{
+	printk("Node %d ", zone->zone_pgdat->node_id);
+}
+#else
+#define show_node(zone)	do { } while (0)
+#endif
+
+/*
+ * Accumulate the page_state information across all CPUs.
+ * The result is unavoidably approximate - it can change
+ * during and after execution of this function.
+ */
+static DEFINE_PER_CPU(struct page_state, page_states) = {0};
+
+atomic_t nr_pagecache = ATOMIC_INIT(0);
+EXPORT_SYMBOL(nr_pagecache);
+#ifdef CONFIG_SMP
+DEFINE_PER_CPU(long, nr_pagecache_local) = 0;
+#endif
+
+static void __get_page_state(struct page_state *ret, int nr, cpumask_t *cpumask)
+{
+	int cpu = 0;
+
+	memset(ret, 0, nr * sizeof(unsigned long));
+	cpus_and(*cpumask, *cpumask, cpu_online_map);
+
+	cpu = first_cpu(*cpumask);
+	while (cpu < NR_CPUS) {
+		unsigned long *in, *out, off;
+
+		if (!cpu_isset(cpu, *cpumask))
+			continue;
+
+		in = (unsigned long *)&per_cpu(page_states, cpu);
+
+		cpu = next_cpu(cpu, *cpumask);
+
+		if (likely(cpu < NR_CPUS))
+			prefetch(&per_cpu(page_states, cpu));
+
+		out = (unsigned long *)ret;
+		for (off = 0; off < nr; off++)
+			*out++ += *in++;
+	}
+}
+
+void get_page_state_node(struct page_state *ret, int node)
+{
+	int nr;
+	cpumask_t mask = node_to_cpumask(node);
+
+	nr = offsetof(struct page_state, GET_PAGE_STATE_LAST);
+	nr /= sizeof(unsigned long);
+
+	__get_page_state(ret, nr+1, &mask);
+}
+
+void get_page_state(struct page_state *ret)
+{
+	int nr;
+	cpumask_t mask = CPU_MASK_ALL;
+
+	nr = offsetof(struct page_state, GET_PAGE_STATE_LAST);
+	nr /= sizeof(unsigned long);
+
+	__get_page_state(ret, nr + 1, &mask);
+}
+
+void get_full_page_state(struct page_state *ret)
+{
+	cpumask_t mask = CPU_MASK_ALL;
+
+	__get_page_state(ret, sizeof(*ret) / sizeof(unsigned long), &mask);
+}
+
+unsigned long read_page_state_offset(unsigned long offset)
+{
+	unsigned long ret = 0;
+	int cpu;
+
+	for_each_online_cpu(cpu) {
+		unsigned long in;
+
+		in = (unsigned long)&per_cpu(page_states, cpu) + offset;
+		ret += *((unsigned long *)in);
+	}
+	return ret;
+}
+
+void __mod_page_state_offset(unsigned long offset, unsigned long delta)
+{
+	void *ptr;
+
+	ptr = &__get_cpu_var(page_states);
+	*(unsigned long *)(ptr + offset) += delta;
+}
+EXPORT_SYMBOL(__mod_page_state_offset);
+
+void mod_page_state_offset(unsigned long offset, unsigned long delta)
+{
+	unsigned long flags;
+	void *ptr;
+
+	local_irq_save(flags);
+	ptr = &__get_cpu_var(page_states);
+	*(unsigned long *)(ptr + offset) += delta;
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(mod_page_state_offset);
+
+void __get_zone_counts(unsigned long *active, unsigned long *inactive,
+			unsigned long *free, struct pglist_data *pgdat)
+{
+	struct zone *zones = pgdat->node_zones;
+	int i;
+
+	*active = 0;
+	*inactive = 0;
+	*free = 0;
+	for (i = 0; i < MAX_NR_ZONES; i++) {
+		*active += zones[i].nr_active;
+		*inactive += zones[i].nr_inactive;
+		*free += zones[i].free_pages;
+	}
+}
+
+void get_zone_counts(unsigned long *active,
+		unsigned long *inactive, unsigned long *free)
+{
+	struct pglist_data *pgdat;
+
+	*active = 0;
+	*inactive = 0;
+	*free = 0;
+	for_each_pgdat(pgdat) {
+		unsigned long l, m, n;
+		__get_zone_counts(&l, &m, &n, pgdat);
+		*active += l;
+		*inactive += m;
+		*free += n;
+	}
+}
+
+void si_meminfo(struct sysinfo *val)
+{
+	val->totalram = totalram_pages;
+	val->sharedram = 0;
+	val->freeram = nr_free_pages();
+	val->bufferram = nr_blockdev_pages();
+#ifdef CONFIG_HIGHMEM
+	val->totalhigh = totalhigh_pages;
+	val->freehigh = nr_free_highpages();
+#else
+	val->totalhigh = 0;
+	val->freehigh = 0;
+#endif
+	val->mem_unit = PAGE_SIZE;
+}
+
+EXPORT_SYMBOL(si_meminfo);
+
+#ifdef CONFIG_NUMA
+void si_meminfo_node(struct sysinfo *val, int nid)
+{
+	pg_data_t *pgdat = NODE_DATA(nid);
+
+	val->totalram = pgdat->node_present_pages;
+	val->freeram = nr_free_pages_pgdat(pgdat);
+	val->totalhigh = pgdat->node_zones[ZONE_HIGHMEM].present_pages;
+	val->freehigh = pgdat->node_zones[ZONE_HIGHMEM].free_pages;
+	val->mem_unit = PAGE_SIZE;
+}
+#endif
+
+#define K(x) ((x) << (PAGE_SHIFT-10))
+
+/*
+ * Show free area list (used inside shift_scroll-lock stuff)
+ * We also calculate the percentage fragmentation. We do this by counting the
+ * memory on each free list with the exception of the first item on the list.
+ */
+void show_free_areas(void)
+{
+	struct page_state ps;
+	int cpu, temperature;
+	unsigned long active;
+	unsigned long inactive;
+	unsigned long free;
+	struct zone *zone;
+
+	for_each_zone(zone) {
+		show_node(zone);
+		printk("%s per-cpu:", zone->name);
+
+		if (!populated_zone(zone)) {
+			printk(" empty\n");
+			continue;
+		} else
+			printk("\n");
+
+		for_each_online_cpu(cpu) {
+			struct per_cpu_pageset *pageset;
+
+			pageset = zone_pcp(zone, cpu);
+
+			for (temperature = 0; temperature < 2; temperature++)
+				printk("cpu %d %s: high %d, batch %d used:%d\n",
+					cpu,
+					temperature ? "cold" : "hot",
+					pageset->pcp[temperature].high,
+					pageset->pcp[temperature].batch,
+					pageset->pcp[temperature].count);
+		}
+	}
+
+	get_page_state(&ps);
+	get_zone_counts(&active, &inactive, &free);
+
+	printk("Free pages: %11ukB (%ukB HighMem)\n",
+		K(nr_free_pages()),
+		K(nr_free_highpages()));
+
+	printk("Active:%lu inactive:%lu dirty:%lu writeback:%lu "
+		"unstable:%lu free:%u slab:%lu mapped:%lu pagetables:%lu\n",
+		active,
+		inactive,
+		ps.nr_dirty,
+		ps.nr_writeback,
+		ps.nr_unstable,
+		nr_free_pages(),
+		ps.nr_slab,
+		ps.nr_mapped,
+		ps.nr_page_table_pages);
+
+	for_each_zone(zone) {
+		int i;
+
+		show_node(zone);
+		printk("%s"
+			" free:%lukB"
+			" min:%lukB"
+			" low:%lukB"
+			" high:%lukB"
+			" active:%lukB"
+			" inactive:%lukB"
+			" present:%lukB"
+			" pages_scanned:%lu"
+			" all_unreclaimable? %s"
+			"\n",
+			zone->name,
+			K(zone->free_pages),
+			K(zone->pages_min),
+			K(zone->pages_low),
+			K(zone->pages_high),
+			K(zone->nr_active),
+			K(zone->nr_inactive),
+			K(zone->present_pages),
+			zone->pages_scanned,
+			(zone->all_unreclaimable ? "yes" : "no")
+			);
+		printk("lowmem_reserve[]:");
+		for (i = 0; i < MAX_NR_ZONES; i++)
+			printk(" %lu", zone->lowmem_reserve[i]);
+		printk("\n");
+	}
+
+	for_each_zone(zone) {
+ 		unsigned long nr, flags, order, total = 0;
+
+		show_node(zone);
+		printk("%s: ", zone->name);
+		if (!populated_zone(zone)) {
+			printk("empty\n");
+			continue;
+		}
+
+		spin_lock_irqsave(&zone->lock, flags);
+		for (order = 0; order < MAX_ORDER; order++) {
+			nr = zone->free_area[order].nr_free;
+			total += nr << order;
+			printk("%lu*%lukB ", nr, K(1UL) << order);
+		}
+		spin_unlock_irqrestore(&zone->lock, flags);
+		printk("= %lukB\n", K(total));
+	}
+
+	show_swap_cache_info();
+}
+
+/*
+ * Builds allocation fallback zone lists.
+ *
+ * Add all populated zones of a node to the zonelist.
+ */
+static int __init build_zonelists_node(pg_data_t *pgdat,
+			struct zonelist *zonelist, int nr_zones, int zone_type)
+{
+	struct zone *zone;
+
+	BUG_ON(zone_type > ZONE_HIGHMEM);
+
+	do {
+		zone = pgdat->node_zones + zone_type;
+		if (populated_zone(zone)) {
+#ifndef CONFIG_HIGHMEM
+			BUG_ON(zone_type > ZONE_NORMAL);
+#endif
+			zonelist->zones[nr_zones++] = zone;
+			check_highest_zone(zone_type);
+		}
+		zone_type--;
+
+	} while (zone_type >= 0);
+	return nr_zones;
+}
+
+static inline int highest_zone(int zone_bits)
+{
+	int res = ZONE_NORMAL;
+	if (zone_bits & (__force int)__GFP_HIGHMEM)
+		res = ZONE_HIGHMEM;
+	if (zone_bits & (__force int)__GFP_DMA32)
+		res = ZONE_DMA32;
+	if (zone_bits & (__force int)__GFP_DMA)
+		res = ZONE_DMA;
+	return res;
+}
+
+#ifdef CONFIG_NUMA
+#define MAX_NODE_LOAD (num_online_nodes())
+static int __initdata node_load[MAX_NUMNODES];
+/**
+ * find_next_best_node - find the next node that should appear in a given node's fallback list
+ * @node: node whose fallback list we're appending
+ * @used_node_mask: nodemask_t of already used nodes
+ *
+ * We use a number of factors to determine which is the next node that should
+ * appear on a given node's fallback list.  The node should not have appeared
+ * already in @node's fallback list, and it should be the next closest node
+ * according to the distance array (which contains arbitrary distance values
+ * from each node to each node in the system), and should also prefer nodes
+ * with no CPUs, since presumably they'll have very little allocation pressure
+ * on them otherwise.
+ * It returns -1 if no node is found.
+ */
+static int __init find_next_best_node(int node, nodemask_t *used_node_mask)
+{
+	int n, val;
+	int min_val = INT_MAX;
+	int best_node = -1;
+
+	/* Use the local node if we haven't already */
+	if (!node_isset(node, *used_node_mask)) {
+		node_set(node, *used_node_mask);
+		return node;
+	}
+
+	for_each_online_node(n) {
+		cpumask_t tmp;
+
+		/* Don't want a node to appear more than once */
+		if (node_isset(n, *used_node_mask))
+			continue;
+
+		/* Use the distance array to find the distance */
+		val = node_distance(node, n);
+
+		/* Penalize nodes under us ("prefer the next node") */
+		val += (n < node);
+
+		/* Give preference to headless and unused nodes */
+		tmp = node_to_cpumask(n);
+		if (!cpus_empty(tmp))
+			val += PENALTY_FOR_NODE_WITH_CPUS;
+
+		/* Slight preference for less loaded node */
+		val *= (MAX_NODE_LOAD*MAX_NUMNODES);
+		val += node_load[n];
+
+		if (val < min_val) {
+			min_val = val;
+			best_node = n;
+		}
+	}
+
+	if (best_node >= 0)
+		node_set(best_node, *used_node_mask);
+
+	return best_node;
+}
+
+static void __init build_zonelists(pg_data_t *pgdat)
+{
+	int i, j, k, node, local_node;
+	int prev_node, load;
+	struct zonelist *zonelist;
+	nodemask_t used_mask;
+
+	/* initialize zonelists */
+	for (i = 0; i < GFP_ZONETYPES; i++) {
+		zonelist = pgdat->node_zonelists + i;
+		zonelist->zones[0] = NULL;
+	}
+
+	/* NUMA-aware ordering of nodes */
+	local_node = pgdat->node_id;
+	load = num_online_nodes();
+	prev_node = local_node;
+	nodes_clear(used_mask);
+	while ((node = find_next_best_node(local_node, &used_mask)) >= 0) {
+		int distance = node_distance(local_node, node);
+
+		/*
+		 * If another node is sufficiently far away then it is better
+		 * to reclaim pages in a zone before going off node.
+		 */
+		if (distance > RECLAIM_DISTANCE)
+			zone_reclaim_mode = 1;
+
+		/*
+		 * We don't want to pressure a particular node.
+		 * So adding penalty to the first node in same
+		 * distance group to make it round-robin.
+		 */
+
+		if (distance != node_distance(local_node, prev_node))
+			node_load[node] += load;
+		prev_node = node;
+		load--;
+		for (i = 0; i < GFP_ZONETYPES; i++) {
+			zonelist = pgdat->node_zonelists + i;
+			for (j = 0; zonelist->zones[j] != NULL; j++);
+
+			k = highest_zone(i);
+
+	 		j = build_zonelists_node(NODE_DATA(node), zonelist, j, k);
+			zonelist->zones[j] = NULL;
+		}
+	}
+}
+
+#else	/* CONFIG_NUMA */
+
+static void __init build_zonelists(pg_data_t *pgdat)
+{
+	int i, j, k, node, local_node;
+
+	local_node = pgdat->node_id;
+	for (i = 0; i < GFP_ZONETYPES; i++) {
+		struct zonelist *zonelist;
+
+		zonelist = pgdat->node_zonelists + i;
+
+		j = 0;
+		k = highest_zone(i);
+ 		j = build_zonelists_node(pgdat, zonelist, j, k);
+ 		/*
+ 		 * Now we build the zonelist so that it contains the zones
+ 		 * of all the other nodes.
+ 		 * We don't want to pressure a particular node, so when
+ 		 * building the zones for node N, we make sure that the
+ 		 * zones coming right after the local ones are those from
+ 		 * node N+1 (modulo N)
+ 		 */
+		for (node = local_node + 1; node < MAX_NUMNODES; node++) {
+			if (!node_online(node))
+				continue;
+			j = build_zonelists_node(NODE_DATA(node), zonelist, j, k);
+		}
+		for (node = 0; node < local_node; node++) {
+			if (!node_online(node))
+				continue;
+			j = build_zonelists_node(NODE_DATA(node), zonelist, j, k);
+		}
+
+		zonelist->zones[j] = NULL;
+	}
+}
+
+#endif	/* CONFIG_NUMA */
+
+void __init build_all_zonelists(void)
+{
+	int i;
+
+	for_each_online_node(i)
+		build_zonelists(NODE_DATA(i));
+	printk("Built %i zonelists\n", num_online_nodes());
+	cpuset_init_current_mems_allowed();
+}
+
+/*
+ * Helper functions to size the waitqueue hash table.
+ * Essentially these want to choose hash table sizes sufficiently
+ * large so that collisions trying to wait on pages are rare.
+ * But in fact, the number of active page waitqueues on typical
+ * systems is ridiculously low, less than 200. So this is even
+ * conservative, even though it seems large.
+ *
+ * The constant PAGES_PER_WAITQUEUE specifies the ratio of pages to
+ * waitqueues, i.e. the size of the waitq table given the number of pages.
+ */
+#define PAGES_PER_WAITQUEUE	256
+
+static inline unsigned long wait_table_size(unsigned long pages)
+{
+	unsigned long size = 1;
+
+	pages /= PAGES_PER_WAITQUEUE;
+
+	while (size < pages)
+		size <<= 1;
+
+	/*
+	 * Once we have dozens or even hundreds of threads sleeping
+	 * on IO we've got bigger problems than wait queue collision.
+	 * Limit the size of the wait table to a reasonable size.
+	 */
+	size = min(size, 4096UL);
+
+	return max(size, 4UL);
+}
+
+/*
+ * This is an integer logarithm so that shifts can be used later
+ * to extract the more random high bits from the multiplicative
+ * hash function before the remainder is taken.
+ */
+static inline unsigned long wait_table_bits(unsigned long size)
+{
+	return ffz(~size);
+}
+
+#define LONG_ALIGN(x) (((x)+(sizeof(long))-1)&~((sizeof(long))-1))
+
+static void __init calculate_zone_totalpages(struct pglist_data *pgdat,
+		unsigned long *zones_size, unsigned long *zholes_size)
+{
+	unsigned long realtotalpages, totalpages = 0;
+	int i;
+
+	for (i = 0; i < MAX_NR_ZONES; i++)
+		totalpages += zones_size[i];
+	pgdat->node_spanned_pages = totalpages;
+
+	realtotalpages = totalpages;
+	if (zholes_size)
+		for (i = 0; i < MAX_NR_ZONES; i++)
+			realtotalpages -= zholes_size[i];
+	pgdat->node_present_pages = realtotalpages;
+	printk(KERN_DEBUG "On node %d totalpages: %lu\n", pgdat->node_id, realtotalpages);
+}
+
+
+/*
+ * Initially all pages are reserved - free ones are freed
+ * up by free_all_bootmem() once the early boot process is
+ * done. Non-atomic initialization, single-pass.
+ */
+void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
+		unsigned long start_pfn)
+{
+	struct page *page;
+	unsigned long end_pfn = start_pfn + size;
+	unsigned long pfn;
+
+	for (pfn = start_pfn; pfn < end_pfn; pfn++) {
+		if (!early_pfn_valid(pfn))
+			continue;
+		page = pfn_to_page(pfn);
+		set_page_links(page, zone, nid, pfn);
+		set_page_count(page, 1);
+		reset_page_mapcount(page);
+		SetPageReserved(page);
+		INIT_LIST_HEAD(&page->lru);
+#ifdef WANT_PAGE_VIRTUAL
+		/* The shift won't overflow because ZONE_NORMAL is below 4G. */
+		if (!is_highmem_idx(zone))
+			set_page_address(page, __va(pfn << PAGE_SHIFT));
+#endif
+	}
+}
+
+void zone_init_free_lists(struct pglist_data *pgdat, struct zone *zone,
+				unsigned long size)
+{
+	int order;
+	for (order = 0; order < MAX_ORDER ; order++) {
+		INIT_LIST_HEAD(&zone->free_area[order].free_list);
+		zone->free_area[order].nr_free = 0;
+	}
+}
+
+#define ZONETABLE_INDEX(x, zone_nr)	((x << ZONES_SHIFT) | zone_nr)
+void zonetable_add(struct zone *zone, int nid, int zid, unsigned long pfn,
+		unsigned long size)
+{
+	unsigned long snum = pfn_to_section_nr(pfn);
+	unsigned long end = pfn_to_section_nr(pfn + size);
+
+	if (FLAGS_HAS_NODE)
+		zone_table[ZONETABLE_INDEX(nid, zid)] = zone;
+	else
+		for (; snum <= end; snum++)
+			zone_table[ZONETABLE_INDEX(snum, zid)] = zone;
+}
+
+#ifndef __HAVE_ARCH_MEMMAP_INIT
+#define memmap_init(size, nid, zone, start_pfn) \
+	memmap_init_zone((size), (nid), (zone), (start_pfn))
+#endif
+
+static int __cpuinit zone_batchsize(struct zone *zone)
+{
+	int batch;
+
+	/*
+	 * The per-cpu-pages pools are set to around 1000th of the
+	 * size of the zone.  But no more than 1/2 of a meg.
+	 *
+	 * OK, so we don't know how big the cache is.  So guess.
+	 */
+	batch = zone->present_pages / 1024;
+	if (batch * PAGE_SIZE > 512 * 1024)
+		batch = (512 * 1024) / PAGE_SIZE;
+	batch /= 4;		/* We effectively *= 4 below */
+	if (batch < 1)
+		batch = 1;
+
+	/*
+	 * Clamp the batch to a 2^n - 1 value. Having a power
+	 * of 2 value was found to be more likely to have
+	 * suboptimal cache aliasing properties in some cases.
+	 *
+	 * For example if 2 tasks are alternately allocating
+	 * batches of pages, one task can end up with a lot
+	 * of pages of one half of the possible page colors
+	 * and the other with pages of the other colors.
+	 */
+	batch = (1 << (fls(batch + batch/2)-1)) - 1;
+
+	return batch;
+}
+
+inline void setup_pageset(struct per_cpu_pageset *p, unsigned long batch)
+{
+	struct per_cpu_pages *pcp;
+
+	memset(p, 0, sizeof(*p));
+
+	pcp = &p->pcp[0];		/* hot */
+	pcp->count = 0;
+	pcp->high = 6 * batch;
+	pcp->batch = max(1UL, 1 * batch);
+	INIT_LIST_HEAD(&pcp->list);
+
+	pcp = &p->pcp[1];		/* cold*/
+	pcp->count = 0;
+	pcp->high = 2 * batch;
+	pcp->batch = max(1UL, batch/2);
+	INIT_LIST_HEAD(&pcp->list);
+}
+
+/*
+ * setup_pagelist_highmark() sets the high water mark for hot per_cpu_pagelist
+ * to the value high for the pageset p.
+ */
+
+static void setup_pagelist_highmark(struct per_cpu_pageset *p,
+				unsigned long high)
+{
+	struct per_cpu_pages *pcp;
+
+	pcp = &p->pcp[0]; /* hot list */
+	pcp->high = high;
+	pcp->batch = max(1UL, high/4);
+	if ((high/4) > (PAGE_SHIFT * 8))
+		pcp->batch = PAGE_SHIFT * 8;
+}
+
+
+#ifdef CONFIG_NUMA
+/*
+ * Boot pageset table. One per cpu which is going to be used for all
+ * zones and all nodes. The parameters will be set in such a way
+ * that an item put on a list will immediately be handed over to
+ * the buddy list. This is safe since pageset manipulation is done
+ * with interrupts disabled.
+ *
+ * Some NUMA counter updates may also be caught by the boot pagesets.
+ *
+ * The boot_pagesets must be kept even after bootup is complete for
+ * unused processors and/or zones. They do play a role for bootstrapping
+ * hotplugged processors.
+ *
+ * zoneinfo_show() and maybe other functions do
+ * not check if the processor is online before following the pageset pointer.
+ * Other parts of the kernel may not check if the zone is available.
+ */
+static struct per_cpu_pageset boot_pageset[NR_CPUS];
+
+/*
+ * Dynamically allocate memory for the
+ * per cpu pageset array in struct zone.
+ */
+static int __cpuinit process_zones(int cpu)
+{
+	struct zone *zone, *dzone;
+
+	for_each_zone(zone) {
+
+		zone_pcp(zone, cpu) = kmalloc_node(sizeof(struct per_cpu_pageset),
+					 GFP_KERNEL, cpu_to_node(cpu));
+		if (!zone_pcp(zone, cpu))
+			goto bad;
+
+		setup_pageset(zone_pcp(zone, cpu), zone_batchsize(zone));
+
+		if (percpu_pagelist_fraction)
+			setup_pagelist_highmark(zone_pcp(zone, cpu),
+			 	(zone->present_pages / percpu_pagelist_fraction));
+	}
+
+	return 0;
+bad:
+	for_each_zone(dzone) {
+		if (dzone == zone)
+			break;
+		kfree(zone_pcp(dzone, cpu));
+		zone_pcp(dzone, cpu) = NULL;
+	}
+	return -ENOMEM;
+}
+
+static inline void free_zone_pagesets(int cpu)
+{
+	struct zone *zone;
+
+	for_each_zone(zone) {
+		struct per_cpu_pageset *pset = zone_pcp(zone, cpu);
+
+		zone_pcp(zone, cpu) = NULL;
+		kfree(pset);
+	}
+}
+
+static int __cpuinit pageset_cpuup_callback(struct notifier_block *nfb,
+		unsigned long action,
+		void *hcpu)
+{
+	int cpu = (long)hcpu;
+	int ret = NOTIFY_OK;
+
+	switch (action) {
+		case CPU_UP_PREPARE:
+			if (process_zones(cpu))
+				ret = NOTIFY_BAD;
+			break;
+		case CPU_UP_CANCELED:
+		case CPU_DEAD:
+			free_zone_pagesets(cpu);
+			break;
+		default:
+			break;
+	}
+	return ret;
+}
+
+static struct notifier_block pageset_notifier =
+	{ &pageset_cpuup_callback, NULL, 0 };
+
+void __init setup_per_cpu_pageset(void)
+{
+	int err;
+
+	/* Initialize per_cpu_pageset for cpu 0.
+	 * A cpuup callback will do this for every cpu
+	 * as it comes online
+	 */
+	err = process_zones(smp_processor_id());
+	BUG_ON(err);
+	register_cpu_notifier(&pageset_notifier);
+}
+
+#endif
+
+static __meminit
+void zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages)
+{
+	int i;
+	struct pglist_data *pgdat = zone->zone_pgdat;
+
+	/*
+	 * The per-page waitqueue mechanism uses hashed waitqueues
+	 * per zone.
+	 */
+	zone->wait_table_size = wait_table_size(zone_size_pages);
+	zone->wait_table_bits =	wait_table_bits(zone->wait_table_size);
+	zone->wait_table = (wait_queue_head_t *)
+		alloc_bootmem_node(pgdat, zone->wait_table_size
+					* sizeof(wait_queue_head_t));
+
+	for(i = 0; i < zone->wait_table_size; ++i)
+		init_waitqueue_head(zone->wait_table + i);
+}
+
+static __meminit void zone_pcp_init(struct zone *zone)
+{
+	int cpu;
+	unsigned long batch = zone_batchsize(zone);
+
+	for (cpu = 0; cpu < NR_CPUS; cpu++) {
+#ifdef CONFIG_NUMA
+		/* Early boot. Slab allocator not functional yet */
+		zone_pcp(zone, cpu) = &boot_pageset[cpu];
+		setup_pageset(&boot_pageset[cpu],0);
+#else
+		setup_pageset(zone_pcp(zone,cpu), batch);
+#endif
+	}
+	printk(KERN_DEBUG "  %s zone: %lu pages, LIFO batch:%lu\n",
+		zone->name, zone->present_pages, batch);
+}
+
+static __meminit void init_currently_empty_zone(struct zone *zone,
+		unsigned long zone_start_pfn, unsigned long size)
+{
+	struct pglist_data *pgdat = zone->zone_pgdat;
+
+	zone_wait_table_init(zone, size);
+	pgdat->nr_zones = zone_idx(zone) + 1;
+
+	zone->zone_mem_map = pfn_to_page(zone_start_pfn);
+	zone->zone_start_pfn = zone_start_pfn;
+
+	memmap_init(size, pgdat->node_id, zone_idx(zone), zone_start_pfn);
+
+	zone_init_free_lists(pgdat, zone, zone->spanned_pages);
+}
+
+/*
+ * Set up the zone data structures:
+ *   - mark all pages reserved
+ *   - mark all memory queues empty
+ *   - clear the memory bitmaps
+ */
+static void __init free_area_init_core(struct pglist_data *pgdat,
+		unsigned long *zones_size, unsigned long *zholes_size)
+{
+	unsigned long j;
+	int nid = pgdat->node_id;
+	unsigned long zone_start_pfn = pgdat->node_start_pfn;
+
+	pgdat_resize_init(pgdat);
+	pgdat->nr_zones = 0;
+	init_waitqueue_head(&pgdat->kswapd_wait);
+	pgdat->kswapd_max_order = 0;
+	
+	for (j = 0; j < MAX_NR_ZONES; j++) {
+		struct zone *zone = pgdat->node_zones + j;
+		unsigned long size, realsize;
+
+		realsize = size = zones_size[j];
+		if (zholes_size)
+			realsize -= zholes_size[j];
+
+		if (j < ZONE_HIGHMEM)
+			nr_kernel_pages += realsize;
+		nr_all_pages += realsize;
+
+		zone->spanned_pages = size;
+		zone->present_pages = realsize;
+		zone->name = zone_names[j];
+		spin_lock_init(&zone->lock);
+		spin_lock_init(&zone->lru_lock);
+		zone_seqlock_init(zone);
+		zone->zone_pgdat = pgdat;
+		zone->free_pages = 0;
+
+		zone->temp_priority = zone->prev_priority = DEF_PRIORITY;
+
+		zone_pcp_init(zone);
+		INIT_LIST_HEAD(&zone->active_list);
+		INIT_LIST_HEAD(&zone->inactive_list);
+		zone->nr_scan_active = 0;
+		zone->nr_scan_inactive = 0;
+		zone->nr_active = 0;
+		zone->nr_inactive = 0;
+		atomic_set(&zone->reclaim_in_progress, 0);
+		if (!size)
+			continue;
+
+		zonetable_add(zone, nid, j, zone_start_pfn, size);
+		init_currently_empty_zone(zone, zone_start_pfn, size);
+		zone_start_pfn += size;
+	}
+}
+
+static void __init alloc_node_mem_map(struct pglist_data *pgdat)
+{
+	/* Skip empty nodes */
+	if (!pgdat->node_spanned_pages)
+		return;
+
+#ifdef CONFIG_FLAT_NODE_MEM_MAP
+	/* ia64 gets its own node_mem_map, before this, without bootmem */
+	if (!pgdat->node_mem_map) {
+		unsigned long size;
+		struct page *map;
+
+		size = (pgdat->node_spanned_pages + 1) * sizeof(struct page);
+		map = alloc_remap(pgdat->node_id, size);
+		if (!map)
+			map = alloc_bootmem_node(pgdat, size);
+		pgdat->node_mem_map = map;
+	}
+#ifdef CONFIG_FLATMEM
+	/*
+	 * With no DISCONTIG, the global mem_map is just set as node 0's
+	 */
+	if (pgdat == NODE_DATA(0))
+		mem_map = NODE_DATA(0)->node_mem_map;
+#endif
+#endif /* CONFIG_FLAT_NODE_MEM_MAP */
+}
+
+void __init free_area_init_node(int nid, struct pglist_data *pgdat,
+		unsigned long *zones_size, unsigned long node_start_pfn,
+		unsigned long *zholes_size)
+{
+	pgdat->node_id = nid;
+	pgdat->node_start_pfn = node_start_pfn;
+	calculate_zone_totalpages(pgdat, zones_size, zholes_size);
+
+	alloc_node_mem_map(pgdat);
+
+	free_area_init_core(pgdat, zones_size, zholes_size);
+}
+
+#ifndef CONFIG_NEED_MULTIPLE_NODES
+static bootmem_data_t contig_bootmem_data;
+struct pglist_data contig_page_data = { .bdata = &contig_bootmem_data };
+
+EXPORT_SYMBOL(contig_page_data);
+#endif
+
+void __init free_area_init(unsigned long *zones_size)
+{
+	free_area_init_node(0, NODE_DATA(0), zones_size,
+			__pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL);
+}
+
+#ifdef CONFIG_PROC_FS
+
+#include <linux/seq_file.h>
+
+static void *frag_start(struct seq_file *m, loff_t *pos)
+{
+	pg_data_t *pgdat;
+	loff_t node = *pos;
+
+	for (pgdat = pgdat_list; pgdat && node; pgdat = pgdat->pgdat_next)
+		--node;
+
+	return pgdat;
+}
+
+static void *frag_next(struct seq_file *m, void *arg, loff_t *pos)
+{
+	pg_data_t *pgdat = (pg_data_t *)arg;
+
+	(*pos)++;
+	return pgdat->pgdat_next;
+}
+
+static void frag_stop(struct seq_file *m, void *arg)
+{
+}
+
+/* 
+ * This walks the free areas for each zone.
+ */
+static int frag_show(struct seq_file *m, void *arg)
+{
+	pg_data_t *pgdat = (pg_data_t *)arg;
+	struct zone *zone;
+	struct zone *node_zones = pgdat->node_zones;
+	unsigned long flags;
+	int order;
+
+	for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) {
+		if (!populated_zone(zone))
+			continue;
+
+		spin_lock_irqsave(&zone->lock, flags);
+		seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name);
+		for (order = 0; order < MAX_ORDER; ++order)
+			seq_printf(m, "%6lu ", zone->free_area[order].nr_free);
+		spin_unlock_irqrestore(&zone->lock, flags);
+		seq_putc(m, '\n');
+	}
+	return 0;
+}
+
+struct seq_operations fragmentation_op = {
+	.start	= frag_start,
+	.next	= frag_next,
+	.stop	= frag_stop,
+	.show	= frag_show,
+};
+
+/*
+ * Output information about zones in @pgdat.
+ */
+static int zoneinfo_show(struct seq_file *m, void *arg)
+{
+	pg_data_t *pgdat = arg;
+	struct zone *zone;
+	struct zone *node_zones = pgdat->node_zones;
+	unsigned long flags;
+
+	for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; zone++) {
+		int i;
+
+		if (!populated_zone(zone))
+			continue;
+
+		spin_lock_irqsave(&zone->lock, flags);
+		seq_printf(m, "Node %d, zone %8s", pgdat->node_id, zone->name);
+		seq_printf(m,
+			   "\n  pages free     %lu"
+			   "\n        min      %lu"
+			   "\n        low      %lu"
+			   "\n        high     %lu"
+			   "\n        active   %lu"
+			   "\n        inactive %lu"
+			   "\n        scanned  %lu (a: %lu i: %lu)"
+			   "\n        spanned  %lu"
+			   "\n        present  %lu",
+			   zone->free_pages,
+			   zone->pages_min,
+			   zone->pages_low,
+			   zone->pages_high,
+			   zone->nr_active,
+			   zone->nr_inactive,
+			   zone->pages_scanned,
+			   zone->nr_scan_active, zone->nr_scan_inactive,
+			   zone->spanned_pages,
+			   zone->present_pages);
+		seq_printf(m,
+			   "\n        protection: (%lu",
+			   zone->lowmem_reserve[0]);
+		for (i = 1; i < ARRAY_SIZE(zone->lowmem_reserve); i++)
+			seq_printf(m, ", %lu", zone->lowmem_reserve[i]);
+		seq_printf(m,
+			   ")"
+			   "\n  pagesets");
+		for_each_online_cpu(i) {
+			struct per_cpu_pageset *pageset;
+			int j;
+
+			pageset = zone_pcp(zone, i);
+			for (j = 0; j < ARRAY_SIZE(pageset->pcp); j++) {
+				if (pageset->pcp[j].count)
+					break;
+			}
+			if (j == ARRAY_SIZE(pageset->pcp))
+				continue;
+			for (j = 0; j < ARRAY_SIZE(pageset->pcp); j++) {
+				seq_printf(m,
+					   "\n    cpu: %i pcp: %i"
+					   "\n              count: %i"
+					   "\n              high:  %i"
+					   "\n              batch: %i",
+					   i, j,
+					   pageset->pcp[j].count,
+					   pageset->pcp[j].high,
+					   pageset->pcp[j].batch);
+			}
+#ifdef CONFIG_NUMA
+			seq_printf(m,
+				   "\n            numa_hit:       %lu"
+				   "\n            numa_miss:      %lu"
+				   "\n            numa_foreign:   %lu"
+				   "\n            interleave_hit: %lu"
+				   "\n            local_node:     %lu"
+				   "\n            other_node:     %lu",
+				   pageset->numa_hit,
+				   pageset->numa_miss,
+				   pageset->numa_foreign,
+				   pageset->interleave_hit,
+				   pageset->local_node,
+				   pageset->other_node);
+#endif
+		}
+		seq_printf(m,
+			   "\n  all_unreclaimable: %u"
+			   "\n  prev_priority:     %i"
+			   "\n  temp_priority:     %i"
+			   "\n  start_pfn:         %lu",
+			   zone->all_unreclaimable,
+			   zone->prev_priority,
+			   zone->temp_priority,
+			   zone->zone_start_pfn);
+		spin_unlock_irqrestore(&zone->lock, flags);
+		seq_putc(m, '\n');
+	}
+	return 0;
+}
+
+struct seq_operations zoneinfo_op = {
+	.start	= frag_start, /* iterate over all zones. The same as in
+			       * fragmentation. */
+	.next	= frag_next,
+	.stop	= frag_stop,
+	.show	= zoneinfo_show,
+};
+
+static char *vmstat_text[] = {
+	"nr_dirty",
+	"nr_writeback",
+	"nr_unstable",
+	"nr_page_table_pages",
+	"nr_mapped",
+	"nr_slab",
+
+	"pgpgin",
+	"pgpgout",
+	"pswpin",
+	"pswpout",
+
+	"pgalloc_high",
+	"pgalloc_normal",
+	"pgalloc_dma32",
+	"pgalloc_dma",
+
+	"pgfree",
+	"pgactivate",
+	"pgdeactivate",
+
+	"pgfault",
+	"pgmajfault",
+
+	"pgrefill_high",
+	"pgrefill_normal",
+	"pgrefill_dma32",
+	"pgrefill_dma",
+
+	"pgsteal_high",
+	"pgsteal_normal",
+	"pgsteal_dma32",
+	"pgsteal_dma",
+
+	"pgscan_kswapd_high",
+	"pgscan_kswapd_normal",
+	"pgscan_kswapd_dma32",
+	"pgscan_kswapd_dma",
+
+	"pgscan_direct_high",
+	"pgscan_direct_normal",
+	"pgscan_direct_dma32",
+	"pgscan_direct_dma",
+
+	"pginodesteal",
+	"slabs_scanned",
+	"kswapd_steal",
+	"kswapd_inodesteal",
+	"pageoutrun",
+	"allocstall",
+
+	"pgrotated",
+	"nr_bounce",
+};
+
+static void *vmstat_start(struct seq_file *m, loff_t *pos)
+{
+	struct page_state *ps;
+
+	if (*pos >= ARRAY_SIZE(vmstat_text))
+		return NULL;
+
+	ps = kmalloc(sizeof(*ps), GFP_KERNEL);
+	m->private = ps;
+	if (!ps)
+		return ERR_PTR(-ENOMEM);
+	get_full_page_state(ps);
+	ps->pgpgin /= 2;		/* sectors -> kbytes */
+	ps->pgpgout /= 2;
+	return (unsigned long *)ps + *pos;
+}
+
+static void *vmstat_next(struct seq_file *m, void *arg, loff_t *pos)
+{
+	(*pos)++;
+	if (*pos >= ARRAY_SIZE(vmstat_text))
+		return NULL;
+	return (unsigned long *)m->private + *pos;
+}
+
+static int vmstat_show(struct seq_file *m, void *arg)
+{
+	unsigned long *l = arg;
+	unsigned long off = l - (unsigned long *)m->private;
+
+	seq_printf(m, "%s %lu\n", vmstat_text[off], *l);
+	return 0;
+}
+
+static void vmstat_stop(struct seq_file *m, void *arg)
+{
+	kfree(m->private);
+	m->private = NULL;
+}
+
+struct seq_operations vmstat_op = {
+	.start	= vmstat_start,
+	.next	= vmstat_next,
+	.stop	= vmstat_stop,
+	.show	= vmstat_show,
+};
+
+#endif /* CONFIG_PROC_FS */
+
+#ifdef CONFIG_HOTPLUG_CPU
+static int page_alloc_cpu_notify(struct notifier_block *self,
+				 unsigned long action, void *hcpu)
+{
+	int cpu = (unsigned long)hcpu;
+	long *count;
+	unsigned long *src, *dest;
+
+	if (action == CPU_DEAD) {
+		int i;
+
+		/* Drain local pagecache count. */
+		count = &per_cpu(nr_pagecache_local, cpu);
+		atomic_add(*count, &nr_pagecache);
+		*count = 0;
+		local_irq_disable();
+		__drain_pages(cpu);
+
+		/* Add dead cpu's page_states to our own. */
+		dest = (unsigned long *)&__get_cpu_var(page_states);
+		src = (unsigned long *)&per_cpu(page_states, cpu);
+
+		for (i = 0; i < sizeof(struct page_state)/sizeof(unsigned long);
+				i++) {
+			dest[i] += src[i];
+			src[i] = 0;
+		}
+
+		local_irq_enable();
+	}
+	return NOTIFY_OK;
+}
+#endif /* CONFIG_HOTPLUG_CPU */
+
+void __init page_alloc_init(void)
+{
+	hotcpu_notifier(page_alloc_cpu_notify, 0);
+}
+
+/*
+ * setup_per_zone_lowmem_reserve - called whenever
+ *	sysctl_lower_zone_reserve_ratio changes.  Ensures that each zone
+ *	has a correct pages reserved value, so an adequate number of
+ *	pages are left in the zone after a successful __alloc_pages().
+ */
+static void setup_per_zone_lowmem_reserve(void)
+{
+	struct pglist_data *pgdat;
+	int j, idx;
+
+	for_each_pgdat(pgdat) {
+		for (j = 0; j < MAX_NR_ZONES; j++) {
+			struct zone *zone = pgdat->node_zones + j;
+			unsigned long present_pages = zone->present_pages;
+
+			zone->lowmem_reserve[j] = 0;
+
+			for (idx = j-1; idx >= 0; idx--) {
+				struct zone *lower_zone;
+
+				if (sysctl_lowmem_reserve_ratio[idx] < 1)
+					sysctl_lowmem_reserve_ratio[idx] = 1;
+
+				lower_zone = pgdat->node_zones + idx;
+				lower_zone->lowmem_reserve[j] = present_pages /
+					sysctl_lowmem_reserve_ratio[idx];
+				present_pages += lower_zone->present_pages;
+			}
+		}
+	}
+}
+
+/*
+ * setup_per_zone_pages_min - called when min_free_kbytes changes.  Ensures 
+ *	that the pages_{min,low,high} values for each zone are set correctly 
+ *	with respect to min_free_kbytes.
+ */
+void setup_per_zone_pages_min(void)
+{
+	unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10);
+	unsigned long lowmem_pages = 0;
+	struct zone *zone;
+	unsigned long flags;
+
+	/* Calculate total number of !ZONE_HIGHMEM pages */
+	for_each_zone(zone) {
+		if (!is_highmem(zone))
+			lowmem_pages += zone->present_pages;
+	}
+
+	for_each_zone(zone) {
+		unsigned long tmp;
+		spin_lock_irqsave(&zone->lru_lock, flags);
+		tmp = (pages_min * zone->present_pages) / lowmem_pages;
+		if (is_highmem(zone)) {
+			/*
+			 * __GFP_HIGH and PF_MEMALLOC allocations usually don't
+			 * need highmem pages, so cap pages_min to a small
+			 * value here.
+			 *
+			 * The (pages_high-pages_low) and (pages_low-pages_min)
+			 * deltas controls asynch page reclaim, and so should
+			 * not be capped for highmem.
+			 */
+			int min_pages;
+
+			min_pages = zone->present_pages / 1024;
+			if (min_pages < SWAP_CLUSTER_MAX)
+				min_pages = SWAP_CLUSTER_MAX;
+			if (min_pages > 128)
+				min_pages = 128;
+			zone->pages_min = min_pages;
+		} else {
+			/*
+			 * If it's a lowmem zone, reserve a number of pages
+			 * proportionate to the zone's size.
+			 */
+			zone->pages_min = tmp;
+		}
+
+		zone->pages_low   = zone->pages_min + tmp / 4;
+		zone->pages_high  = zone->pages_min + tmp / 2;
+		spin_unlock_irqrestore(&zone->lru_lock, flags);
+	}
+}
+
+/*
+ * Initialise min_free_kbytes.
+ *
+ * For small machines we want it small (128k min).  For large machines
+ * we want it large (64MB max).  But it is not linear, because network
+ * bandwidth does not increase linearly with machine size.  We use
+ *
+ * 	min_free_kbytes = 4 * sqrt(lowmem_kbytes), for better accuracy:
+ *	min_free_kbytes = sqrt(lowmem_kbytes * 16)
+ *
+ * which yields
+ *
+ * 16MB:	512k
+ * 32MB:	724k
+ * 64MB:	1024k
+ * 128MB:	1448k
+ * 256MB:	2048k
+ * 512MB:	2896k
+ * 1024MB:	4096k
+ * 2048MB:	5792k
+ * 4096MB:	8192k
+ * 8192MB:	11584k
+ * 16384MB:	16384k
+ */
+static int __init init_per_zone_pages_min(void)
+{
+	unsigned long lowmem_kbytes;
+
+	lowmem_kbytes = nr_free_buffer_pages() * (PAGE_SIZE >> 10);
+
+	min_free_kbytes = int_sqrt(lowmem_kbytes * 16);
+	if (min_free_kbytes < 128)
+		min_free_kbytes = 128;
+	if (min_free_kbytes > 65536)
+		min_free_kbytes = 65536;
+	setup_per_zone_pages_min();
+	setup_per_zone_lowmem_reserve();
+	return 0;
+}
+module_init(init_per_zone_pages_min)
+
+/*
+ * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so 
+ *	that we can call two helper functions whenever min_free_kbytes
+ *	changes.
+ */
+int min_free_kbytes_sysctl_handler(ctl_table *table, int write, 
+	struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+{
+	proc_dointvec(table, write, file, buffer, length, ppos);
+	setup_per_zone_pages_min();
+	return 0;
+}
+
+/*
+ * lowmem_reserve_ratio_sysctl_handler - just a wrapper around
+ *	proc_dointvec() so that we can call setup_per_zone_lowmem_reserve()
+ *	whenever sysctl_lowmem_reserve_ratio changes.
+ *
+ * The reserve ratio obviously has absolutely no relation with the
+ * pages_min watermarks. The lowmem reserve ratio can only make sense
+ * if in function of the boot time zone sizes.
+ */
+int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write,
+	struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+{
+	proc_dointvec_minmax(table, write, file, buffer, length, ppos);
+	setup_per_zone_lowmem_reserve();
+	return 0;
+}
+
+/*
+ * percpu_pagelist_fraction - changes the pcp->high for each zone on each
+ * cpu.  It is the fraction of total pages in each zone that a hot per cpu pagelist
+ * can have before it gets flushed back to buddy allocator.
+ */
+
+int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write,
+	struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+{
+	struct zone *zone;
+	unsigned int cpu;
+	int ret;
+
+	ret = proc_dointvec_minmax(table, write, file, buffer, length, ppos);
+	if (!write || (ret == -EINVAL))
+		return ret;
+	for_each_zone(zone) {
+		for_each_online_cpu(cpu) {
+			unsigned long  high;
+			high = zone->present_pages / percpu_pagelist_fraction;
+			setup_pagelist_highmark(zone_pcp(zone, cpu), high);
+		}
+	}
+	return 0;
+}
+
+__initdata int hashdist = HASHDIST_DEFAULT;
+
+#ifdef CONFIG_NUMA
+static int __init set_hashdist(char *str)
+{
+	if (!str)
+		return 0;
+	hashdist = simple_strtoul(str, &str, 0);
+	return 1;
+}
+__setup("hashdist=", set_hashdist);
+#endif
+
+/*
+ * allocate a large system hash table from bootmem
+ * - it is assumed that the hash table must contain an exact power-of-2
+ *   quantity of entries
+ * - limit is the number of hash buckets, not the total allocation size
+ */
+void *__init alloc_large_system_hash(const char *tablename,
+				     unsigned long bucketsize,
+				     unsigned long numentries,
+				     int scale,
+				     int flags,
+				     unsigned int *_hash_shift,
+				     unsigned int *_hash_mask,
+				     unsigned long limit)
+{
+	unsigned long long max = limit;
+	unsigned long log2qty, size;
+	void *table = NULL;
+
+	/* allow the kernel cmdline to have a say */
+	if (!numentries) {
+		/* round applicable memory size up to nearest megabyte */
+		numentries = (flags & HASH_HIGHMEM) ? nr_all_pages : nr_kernel_pages;
+		numentries += (1UL << (20 - PAGE_SHIFT)) - 1;
+		numentries >>= 20 - PAGE_SHIFT;
+		numentries <<= 20 - PAGE_SHIFT;
+
+		/* limit to 1 bucket per 2^scale bytes of low memory */
+		if (scale > PAGE_SHIFT)
+			numentries >>= (scale - PAGE_SHIFT);
+		else
+			numentries <<= (PAGE_SHIFT - scale);
+	}
+	/* rounded up to nearest power of 2 in size */
+	numentries = 1UL << (long_log2(numentries) + 1);
+
+	/* limit allocation size to 1/16 total memory by default */
+	if (max == 0) {
+		max = ((unsigned long long)nr_all_pages << PAGE_SHIFT) >> 4;
+		do_div(max, bucketsize);
+	}
+
+	if (numentries > max)
+		numentries = max;
+
+	log2qty = long_log2(numentries);
+
+	do {
+		size = bucketsize << log2qty;
+		if (flags & HASH_EARLY)
+			table = alloc_bootmem(size);
+		else if (hashdist)
+			table = __vmalloc(size, GFP_ATOMIC, PAGE_KERNEL);
+		else {
+			unsigned long order;
+			for (order = 0; ((1UL << order) << PAGE_SHIFT) < size; order++)
+				;
+			table = (void*) __get_free_pages(GFP_ATOMIC, order);
+		}
+	} while (!table && size > PAGE_SIZE && --log2qty);
+
+	if (!table)
+		panic("Failed to allocate %s hash table\n", tablename);
+
+	printk("%s hash table entries: %d (order: %d, %lu bytes)\n",
+	       tablename,
+	       (1U << log2qty),
+	       long_log2(size) - PAGE_SHIFT,
+	       size);
+
+	if (_hash_shift)
+		*_hash_shift = log2qty;
+	if (_hash_mask)
+		*_hash_mask = (1 << log2qty) - 1;
+
+	return table;
+}
diff -urN oldtree/mm/swapfile.c newtree/mm/swapfile.c
--- oldtree/mm/swapfile.c	2006-02-18 15:18:30.137735616 +0000
+++ newtree/mm/swapfile.c	2006-02-18 15:24:31.451807528 +0000
@@ -1193,6 +1193,7 @@
 	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	2006-02-18 15:18:30.140735160 +0000
+++ newtree/mm/vmscan.c	2006-02-18 15:24:31.453807224 +0000
@@ -1724,7 +1724,8 @@
 	for ( ; ; ) {
 		unsigned long new_order;
 
-		try_to_freeze();
+		if (try_to_freeze())
+			pgdat->kswapd_max_order = 0;
 
 		prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
 		new_order = pgdat->kswapd_max_order;