Merge branches 'topic/fix/asoc', 'topic/fix/hda', 'topic/fix/misc' and 'topic/pci-ioremap-bar' into for-linus

.mailmap

@@ -66,6 +66,7 @@ Kenneth W Chen <kenneth.w.chen@intel.com>
 Koushik <raghavendra.koushik@neterion.com>
 Leonid I Ananiev <leonid.i.ananiev@intel.com>
 Linas Vepstas <linas@austin.ibm.com>
+Mark Brown <broonie@sirena.org.uk>
 Matthieu CASTET <castet.matthieu@free.fr>
 Michael Buesch <mb@bu3sch.de>
 Michael Buesch <mbuesch@freenet.de>

CREDITS

@@ -1653,14 +1653,14 @@ S: Chapel Hill, North Carolina 27514-4818
 S: USA
 
 N: Dave Jones
-E: davej@codemonkey.org.uk
+E: davej@redhat.com
 W: http://www.codemonkey.org.uk
-D: x86 errata/setup maintenance.
+D: Assorted VIA x86 support.
-D: AGPGART driver.
+D: 2.5 AGPGART overhaul.
 D: CPUFREQ maintenance.
-D: Backport/Forwardport merge monkey.
+D: Fedora kernel maintainence.
-D: Various Janitor work.
+D: Misc/Other.
-S: United Kingdom
+S: 314 Littleton Rd, Westford, MA 01886, USA
 
 N: Martin Josfsson
 E: gandalf@wlug.westbo.se

Documentation/DocBook/kernel-hacking.tmpl

@@ -1105,7 +1105,7 @@ static struct block_device_operations opt_fops = {
     </listitem>
     <listitem>
      <para>
-      Function names as strings (__FUNCTION__).
+      Function names as strings (__func__).
      </para>
     </listitem>
     <listitem>

Documentation/MSI-HOWTO.txt

@@ -236,10 +236,8 @@ software system can set different pages for controlling accesses to the
 MSI-X structure. The implementation of MSI support requires the PCI
 subsystem, not a device driver, to maintain full control of the MSI-X
 table/MSI-X PBA (Pending Bit Array) and MMIO address space of the MSI-X
-table/MSI-X PBA.  A device driver is prohibited from requesting the MMIO
+table/MSI-X PBA.  A device driver should not access the MMIO address
-address space of the MSI-X table/MSI-X PBA. Otherwise, the PCI subsystem
+space of the MSI-X table/MSI-X PBA.
-will fail enabling MSI-X on its hardware device when it calls the function
-pci_enable_msix().
 
 5.3.2 API pci_enable_msix
 

Documentation/PCI/pci.txt

@@ -163,6 +163,10 @@ need pass only as many optional fields as necessary:
 	o class and classmask fields default to 0
 	o driver_data defaults to 0UL.
 
+Note that driver_data must match the value used by any of the pci_device_id
+entries defined in the driver. This makes the driver_data field mandatory
+if all the pci_device_id entries have a non-zero driver_data value.
+
 Once added, the driver probe routine will be invoked for any unclaimed
 PCI devices listed in its (newly updated) pci_ids list.
 

Documentation/PCI/pcieaer-howto.txt

@@ -203,22 +203,17 @@ to mmio_enabled.
 
 3.3 helper functions
 
-3.3.1 int pci_find_aer_capability(struct pci_dev *dev);
+3.3.1 int pci_enable_pcie_error_reporting(struct pci_dev *dev);
-pci_find_aer_capability locates the PCI Express AER capability
-in the device configuration space. If the device doesn't support
-PCI-Express AER, the function returns 0.
-
-3.3.2 int pci_enable_pcie_error_reporting(struct pci_dev *dev);
 pci_enable_pcie_error_reporting enables the device to send error
 messages to root port when an error is detected. Note that devices
 don't enable the error reporting by default, so device drivers need
 call this function to enable it.
 
-3.3.3 int pci_disable_pcie_error_reporting(struct pci_dev *dev);
+3.3.2 int pci_disable_pcie_error_reporting(struct pci_dev *dev);
 pci_disable_pcie_error_reporting disables the device to send error
 messages to root port when an error is detected.
 
-3.3.4 int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev);
+3.3.3 int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev);
 pci_cleanup_aer_uncorrect_error_status cleanups the uncorrectable
 error status register.
 

Documentation/cgroups/freezer-subsystem.txt

@@ -0,0 +1,99 @@
+	The cgroup freezer is useful to batch job management system which start
+and stop sets of tasks in order to schedule the resources of a machine
+according to the desires of a system administrator. This sort of program
+is often used on HPC clusters to schedule access to the cluster as a
+whole. The cgroup freezer uses cgroups to describe the set of tasks to
+be started/stopped by the batch job management system. It also provides
+a means to start and stop the tasks composing the job.
+
+	The cgroup freezer will also be useful for checkpointing running groups
+of tasks. The freezer allows the checkpoint code to obtain a consistent
+image of the tasks by attempting to force the tasks in a cgroup into a
+quiescent state. Once the tasks are quiescent another task can
+walk /proc or invoke a kernel interface to gather information about the
+quiesced tasks. Checkpointed tasks can be restarted later should a
+recoverable error occur. This also allows the checkpointed tasks to be
+migrated between nodes in a cluster by copying the gathered information
+to another node and restarting the tasks there.
+
+	Sequences of SIGSTOP and SIGCONT are not always sufficient for stopping
+and resuming tasks in userspace. Both of these signals are observable
+from within the tasks we wish to freeze. While SIGSTOP cannot be caught,
+blocked, or ignored it can be seen by waiting or ptracing parent tasks.
+SIGCONT is especially unsuitable since it can be caught by the task. Any
+programs designed to watch for SIGSTOP and SIGCONT could be broken by
+attempting to use SIGSTOP and SIGCONT to stop and resume tasks. We can
+demonstrate this problem using nested bash shells:
+
+	$ echo $$
+	16644
+	$ bash
+	$ echo $$
+	16690
+
+	From a second, unrelated bash shell:
+	$ kill -SIGSTOP 16690
+	$ kill -SIGCONT 16990
+
+	<at this point 16990 exits and causes 16644 to exit too>
+
+	This happens because bash can observe both signals and choose how it
+responds to them.
+
+	Another example of a program which catches and responds to these
+signals is gdb. In fact any program designed to use ptrace is likely to
+have a problem with this method of stopping and resuming tasks.
+
+	 In contrast, the cgroup freezer uses the kernel freezer code to
+prevent the freeze/unfreeze cycle from becoming visible to the tasks
+being frozen. This allows the bash example above and gdb to run as
+expected.
+
+	The freezer subsystem in the container filesystem defines a file named
+freezer.state. Writing "FROZEN" to the state file will freeze all tasks in the
+cgroup. Subsequently writing "THAWED" will unfreeze the tasks in the cgroup.
+Reading will return the current state.
+
+* Examples of usage :
+
+   # mkdir /containers/freezer
+   # mount -t cgroup -ofreezer freezer  /containers
+   # mkdir /containers/0
+   # echo $some_pid > /containers/0/tasks
+
+to get status of the freezer subsystem :
+
+   # cat /containers/0/freezer.state
+   THAWED
+
+to freeze all tasks in the container :
+
+   # echo FROZEN > /containers/0/freezer.state
+   # cat /containers/0/freezer.state
+   FREEZING
+   # cat /containers/0/freezer.state
+   FROZEN
+
+to unfreeze all tasks in the container :
+
+   # echo THAWED > /containers/0/freezer.state
+   # cat /containers/0/freezer.state
+   THAWED
+
+This is the basic mechanism which should do the right thing for user space task
+in a simple scenario.
+
+It's important to note that freezing can be incomplete. In that case we return
+EBUSY. This means that some tasks in the cgroup are busy doing something that
+prevents us from completely freezing the cgroup at this time. After EBUSY,
+the cgroup will remain partially frozen -- reflected by freezer.state reporting
+"FREEZING" when read. The state will remain "FREEZING" until one of these
+things happens:
+
+	1) Userspace cancels the freezing operation by writing "THAWED" to
+		the freezer.state file
+	2) Userspace retries the freezing operation by writing "FROZEN" to
+		the freezer.state file (writing "FREEZING" is not legal
+		and returns EIO)
+	3) The tasks that blocked the cgroup from entering the "FROZEN"
+		state disappear from the cgroup's set of tasks.

Documentation/controllers/memory.txt

@@ -112,14 +112,22 @@ the per cgroup LRU.
 
 2.2.1 Accounting details
 
-All mapped pages (RSS) and unmapped user pages (Page Cache) are accounted.
+All mapped anon pages (RSS) and cache pages (Page Cache) are accounted.
-RSS pages are accounted at the time of page_add_*_rmap() unless they've already
+(some pages which never be reclaimable and will not be on global LRU
-been accounted for earlier. A file page will be accounted for as Page Cache;
+ are not accounted. we just accounts pages under usual vm management.)
-it's mapped into the page tables of a process, duplicate accounting is carefully
+
-avoided. Page Cache pages are accounted at the time of add_to_page_cache().
+RSS pages are accounted at page_fault unless they've already been accounted
-The corresponding routines that remove a page from the page tables or removes
+for earlier. A file page will be accounted for as Page Cache when it's
-a page from Page Cache is used to decrement the accounting counters of the
+inserted into inode (radix-tree). While it's mapped into the page tables of
-cgroup.
+processes, duplicate accounting is carefully avoided.
+
+A RSS page is unaccounted when it's fully unmapped. A PageCache page is
+unaccounted when it's removed from radix-tree.
+
+At page migration, accounting information is kept.
+
+Note: we just account pages-on-lru because our purpose is to control amount
+of used pages. not-on-lru pages are tend to be out-of-control from vm view.
 
 2.3 Shared Page Accounting
 

Documentation/cpusets.txt

@@ -48,7 +48,7 @@ hooks, beyond what is already present, required to manage dynamic
 job placement on large systems.
 
 Cpusets use the generic cgroup subsystem described in
-Documentation/cgroup.txt.
+Documentation/cgroups/cgroups.txt.
 
 Requests by a task, using the sched_setaffinity(2) system call to
 include CPUs in its CPU affinity mask, and using the mbind(2) and

Documentation/filesystems/ext3.txt

@@ -96,6 +96,11 @@ errors=remount-ro(*)	Remount the filesystem read-only on an error.
 errors=continue		Keep going on a filesystem error.
 errors=panic		Panic and halt the machine if an error occurs.
 
+data_err=ignore(*)	Just print an error message if an error occurs
+			in a file data buffer in ordered mode.
+data_err=abort		Abort the journal if an error occurs in a file
+			data buffer in ordered mode.
+
 grpid			Give objects the same group ID as their creator.
 bsdgroups
 

Documentation/filesystems/proc.txt

@@ -1384,15 +1384,18 @@ causes the kernel to prefer to reclaim dentries and inodes.
 dirty_background_ratio
 ----------------------
 
-Contains, as a percentage of total system memory, the number of pages at which
+Contains, as a percentage of the dirtyable system memory (free pages + mapped
-the pdflush background writeback daemon will start writing out dirty data.
+pages + file cache, not including locked pages and HugePages), the number of
+pages at which the pdflush background writeback daemon will start writing out
+dirty data.
 
 dirty_ratio
 -----------------
 
-Contains, as a percentage of total system memory, the number of pages at which
+Contains, as a percentage of the dirtyable system memory (free pages + mapped
-a process which is generating disk writes will itself start writing out dirty
+pages + file cache, not including locked pages and HugePages), the number of
-data.
+pages at which a process which is generating disk writes will itself start
+writing out dirty data.
 
 dirty_writeback_centisecs
 -------------------------
@@ -2412,24 +2415,29 @@ will be dumped when the <pid> process is dumped. coredump_filter is a bitmask
 of memory types. If a bit of the bitmask is set, memory segments of the
 corresponding memory type are dumped, otherwise they are not dumped.
 
-The following 4 memory types are supported:
+The following 7 memory types are supported:
   - (bit 0) anonymous private memory
   - (bit 1) anonymous shared memory
   - (bit 2) file-backed private memory
   - (bit 3) file-backed shared memory
   - (bit 4) ELF header pages in file-backed private memory areas (it is
             effective only if the bit 2 is cleared)
+  - (bit 5) hugetlb private memory
+  - (bit 6) hugetlb shared memory
 
   Note that MMIO pages such as frame buffer are never dumped and vDSO pages
   are always dumped regardless of the bitmask status.
 
-Default value of coredump_filter is 0x3; this means all anonymous memory
+  Note bit 0-4 doesn't effect any hugetlb memory. hugetlb memory are only
-segments are dumped.
+  effected by bit 5-6.
+
+Default value of coredump_filter is 0x23; this means all anonymous memory
+segments and hugetlb private memory are dumped.
 
 If you don't want to dump all shared memory segments attached to pid 1234,
-write 1 to the process's proc file.
+write 0x21 to the process's proc file.
 
-  $ echo 0x1 > /proc/1234/coredump_filter
+  $ echo 0x21 > /proc/1234/coredump_filter
 
 When a new process is created, the process inherits the bitmask status from its
 parent. It is useful to set up coredump_filter before the program runs.

Documentation/filesystems/ubifs.txt

@@ -86,6 +86,15 @@ norm_unmount (*)	commit on unmount; the journal is committed
 fast_unmount		do not commit on unmount; this option makes
 			unmount faster, but the next mount slower
 			because of the need to replay the journal.
+bulk_read		read more in one go to take advantage of flash
+			media that read faster sequentially
+no_bulk_read (*)	do not bulk-read
+no_chk_data_crc		skip checking of CRCs on data nodes in order to
+			improve read performance. Use this option only
+			if the flash media is highly reliable. The effect
+			of this option is that corruption of the contents
+			of a file can go unnoticed.
+chk_data_crc (*)	do not skip checking CRCs on data nodes
 
 
 Quick usage instructions

Documentation/kernel-parameters.txt

@@ -101,6 +101,7 @@ parameter is applicable:
 	X86-64	X86-64 architecture is enabled.
 			More X86-64 boot options can be found in
 			Documentation/x86_64/boot-options.txt .
+	X86	Either 32bit or 64bit x86 (same as X86-32+X86-64)
 
 In addition, the following text indicates that the option:
 
@@ -690,7 +691,7 @@ and is between 256 and 4096 characters. It is defined in the file
 			See Documentation/block/as-iosched.txt and
 			Documentation/block/deadline-iosched.txt for details.
 
-	elfcorehdr=	[X86-32, X86_64]
+	elfcorehdr=	[IA64,PPC,SH,X86-32,X86_64]
 			Specifies physical address of start of kernel core
 			image elf header. Generally kexec loader will
 			pass this option to capture kernel.
@@ -796,6 +797,8 @@ and is between 256 and 4096 characters. It is defined in the file
 			Defaults to the default architecture's huge page size
 			if not specified.
 
+	hlt		[BUGS=ARM,SH]
+
 	i8042.debug	[HW] Toggle i8042 debug mode
 	i8042.direct	[HW] Put keyboard port into non-translated mode
 	i8042.dumbkbd	[HW] Pretend that controller can only read data from
@@ -1211,6 +1214,10 @@ and is between 256 and 4096 characters. It is defined in the file
 	mem=nopentium	[BUGS=X86-32] Disable usage of 4MB pages for kernel
 			memory.
 
+	memchunk=nn[KMG]
+			[KNL,SH] Allow user to override the default size for
+			per-device physically contiguous DMA buffers.
+
 	memmap=exactmap	[KNL,X86-32,X86_64] Enable setting of an exact
 			E820 memory map, as specified by the user.
 			Such memmap=exactmap lines can be constructed based on
@@ -1393,6 +1400,8 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	nodisconnect	[HW,SCSI,M68K] Disables SCSI disconnects.
 
+	nodsp		[SH] Disable hardware DSP at boot time.
+
 	noefi		[X86-32,X86-64] Disable EFI runtime services support.
 
 	noexec		[IA-64]
@@ -1409,13 +1418,15 @@ and is between 256 and 4096 characters. It is defined in the file
 			noexec32=off: disable non-executable mappings
 				read implies executable mappings
 
+	nofpu		[SH] Disable hardware FPU at boot time.
+
 	nofxsr		[BUGS=X86-32] Disables x86 floating point extended
 			register save and restore. The kernel will only save
 			legacy floating-point registers on task switch.
 
 	noclflush	[BUGS=X86] Don't use the CLFLUSH instruction
 
-	nohlt		[BUGS=ARM]
+	nohlt		[BUGS=ARM,SH]
 
 	no-hlt		[BUGS=X86-32] Tells the kernel that the hlt
 			instruction doesn't work correctly and not to
@@ -1578,7 +1589,7 @@ and is between 256 and 4096 characters. It is defined in the file
 			See also Documentation/paride.txt.
 
 	pci=option[,option...]	[PCI] various PCI subsystem options:
-		off		[X86-32] don't probe for the PCI bus
+		off		[X86] don't probe for the PCI bus
 		bios		[X86-32] force use of PCI BIOS, don't access
 				the hardware directly. Use this if your machine
 				has a non-standard PCI host bridge.
@@ -1586,9 +1597,9 @@ and is between 256 and 4096 characters. It is defined in the file
 				hardware access methods are allowed. Use this
 				if you experience crashes upon bootup and you
 				suspect they are caused by the BIOS.
-		conf1		[X86-32] Force use of PCI Configuration
+		conf1		[X86] Force use of PCI Configuration
 				Mechanism 1.
-		conf2		[X86-32] Force use of PCI Configuration
+		conf2		[X86] Force use of PCI Configuration
 				Mechanism 2.
 		noaer		[PCIE] If the PCIEAER kernel config parameter is
 				enabled, this kernel boot option can be used to
@@ -1608,37 +1619,37 @@ and is between 256 and 4096 characters. It is defined in the file
 				this option if the kernel is unable to allocate
 				IRQs or discover secondary PCI buses on your
 				motherboard.
-		rom		[X86-32] Assign address space to expansion ROMs.
+		rom		[X86] Assign address space to expansion ROMs.
 				Use with caution as certain devices share
 				address decoders between ROMs and other
 				resources.
-		norom		[X86-32,X86_64] Do not assign address space to
+		norom		[X86] Do not assign address space to
 				expansion ROMs that do not already have
 				BIOS assigned address ranges.
-		irqmask=0xMMMM	[X86-32] Set a bit mask of IRQs allowed to be
+		irqmask=0xMMMM	[X86] 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	[X86-32] Specify the physical address
+		pirqaddr=0xAAAAA	[X86] Specify the physical address
 				of the PIRQ table (normally generated
 				by the BIOS) if it is outside the
 				F0000h-100000h range.
-		lastbus=N	[X86-32] Scan all buses thru bus #N. Can be
+		lastbus=N	[X86] 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	[X86-32] Always assign all PCI bus
+		assign-busses	[X86] Always assign all PCI bus
 				numbers ourselves, overriding
 				whatever the firmware may have done.
-		usepirqmask	[X86-32] Honor the possible IRQ mask stored
+		usepirqmask	[X86] 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		[X86-32] Do not use ACPI for IRQ routing
+		noacpi		[X86] Do not use ACPI for IRQ routing
 				or for PCI scanning.
-		use_crs		[X86-32] Use _CRS for PCI resource
+		use_crs		[X86] Use _CRS for PCI resource
 				allocation.
 		routeirq	Do IRQ routing for all PCI devices.
 				This is normally done in pci_enable_device(),
@@ -1667,6 +1678,12 @@ and is between 256 and 4096 characters. It is defined in the file
 				reserved for the CardBus bridge's memory
 				window. The default value is 64 megabytes.
 
+	pcie_aspm=	[PCIE] Forcibly enable or disable PCIe Active State Power
+			Management.
+		off	Disable ASPM.
+		force	Enable ASPM even on devices that claim not to support it.
+			WARNING: Forcing ASPM on may cause system lockups.
+
 	pcmv=		[HW,PCMCIA] BadgePAD 4
 
 	pd.		[PARIDE]

Documentation/markers.txt

@@ -50,10 +50,12 @@ Connecting a function (probe) to a marker is done by providing a probe (function
 to call) for the specific marker through marker_probe_register() and can be
 activated by calling marker_arm(). Marker deactivation can be done by calling
 marker_disarm() as many times as marker_arm() has been called. Removing a probe
-is done through marker_probe_unregister(); it will disarm the probe and make
+is done through marker_probe_unregister(); it will disarm the probe.
-sure there is no caller left using the probe when it returns. Probe removal is
+marker_synchronize_unregister() must be called before the end of the module exit
-preempt-safe because preemption is disabled around the probe call. See the
+function to make sure there is no caller left using the probe. This, and the
-"Probe example" section below for a sample probe module.
+fact that preemption is disabled around the probe call, make sure that probe
+removal and module unload are safe. See the "Probe example" section below for a
+sample probe module.
 
 The marker mechanism supports inserting multiple instances of the same marker.
 Markers can be put in inline functions, inlined static functions, and

Documentation/mtd/nand_ecc.txt

@@ -0,0 +1,714 @@
+Introduction
+============
+
+Having looked at the linux mtd/nand driver and more specific at nand_ecc.c
+I felt there was room for optimisation. I bashed the code for a few hours
+performing tricks like table lookup removing superfluous code etc.
+After that the speed was increased by 35-40%.
+Still I was not too happy as I felt there was additional room for improvement.
+
+Bad! I was hooked.
+I decided to annotate my steps in this file. Perhaps it is useful to someone
+or someone learns something from it.
+
+
+The problem
+===========
+
+NAND flash (at least SLC one) typically has sectors of 256 bytes.
+However NAND flash is not extremely reliable so some error detection
+(and sometimes correction) is needed.
+
+This is done by means of a Hamming code. I'll try to explain it in
+laymans terms (and apologies to all the pro's in the field in case I do
+not use the right terminology, my coding theory class was almost 30
+years ago, and I must admit it was not one of my favourites).
+
+As I said before the ecc calculation is performed on sectors of 256
+bytes. This is done by calculating several parity bits over the rows and
+columns. The parity used is even parity which means that the parity bit = 1
+if the data over which the parity is calculated is 1 and the parity bit = 0
+if the data over which the parity is calculated is 0. So the total
+number of bits over the data over which the parity is calculated + the
+parity bit is even. (see wikipedia if you can't follow this).
+Parity is often calculated by means of an exclusive or operation,
+sometimes also referred to as xor. In C the operator for xor is ^
+
+Back to ecc.
+Let's give a small figure:
+
+byte   0:  bit7 bit6 bit5 bit4 bit3 bit2 bit1 bit0   rp0 rp2 rp4 ... rp14
+byte   1:  bit7 bit6 bit5 bit4 bit3 bit2 bit1 bit0   rp1 rp2 rp4 ... rp14
+byte   2:  bit7 bit6 bit5 bit4 bit3 bit2 bit1 bit0   rp0 rp3 rp4 ... rp14
+byte   3:  bit7 bit6 bit5 bit4 bit3 bit2 bit1 bit0   rp1 rp3 rp4 ... rp14
+byte   4:  bit7 bit6 bit5 bit4 bit3 bit2 bit1 bit0   rp0 rp2 rp5 ... rp14
+....
+byte 254:  bit7 bit6 bit5 bit4 bit3 bit2 bit1 bit0   rp0 rp3 rp5 ... rp15
+byte 255:  bit7 bit6 bit5 bit4 bit3 bit2 bit1 bit0   rp1 rp3 rp5 ... rp15
+           cp1  cp0  cp1  cp0  cp1  cp0  cp1  cp0
+           cp3  cp3  cp2  cp2  cp3  cp3  cp2  cp2
+           cp5  cp5  cp5  cp5  cp4  cp4  cp4  cp4
+
+This figure represents a sector of 256 bytes.
+cp is my abbreviaton for column parity, rp for row parity.
+
+Let's start to explain column parity.
+cp0 is the parity that belongs to all bit0, bit2, bit4, bit6.
+so the sum of all bit0, bit2, bit4 and bit6 values + cp0 itself is even.
+Similarly cp1 is the sum of all bit1, bit3, bit5 and bit7.
+cp2 is the parity over bit0, bit1, bit4 and bit5
+cp3 is the parity over bit2, bit3, bit6 and bit7.
+cp4 is the parity over bit0, bit1, bit2 and bit3.
+cp5 is the parity over bit4, bit5, bit6 and bit7.
+Note that each of cp0 .. cp5 is exactly one bit.
+
+Row parity actually works almost the same.
+rp0 is the parity of all even bytes (0, 2, 4, 6, ... 252, 254)
+rp1 is the parity of all odd bytes (1, 3, 5, 7, ..., 253, 255)
+rp2 is the parity of all bytes 0, 1, 4, 5, 8, 9, ...
+(so handle two bytes, then skip 2 bytes).
+rp3 is covers the half rp2 does not cover (bytes 2, 3, 6, 7, 10, 11, ...)
+for rp4 the rule is cover 4 bytes, skip 4 bytes, cover 4 bytes, skip 4 etc.
+so rp4 calculates parity over bytes 0, 1, 2, 3, 8, 9, 10, 11, 16, ...)
+and rp5 covers the other half, so bytes 4, 5, 6, 7, 12, 13, 14, 15, 20, ..
+The story now becomes quite boring. I guess you get the idea.
+rp6 covers 8 bytes then skips 8 etc
+rp7 skips 8 bytes then covers 8 etc
+rp8 covers 16 bytes then skips 16 etc
+rp9 skips 16 bytes then covers 16 etc
+rp10 covers 32 bytes then skips 32 etc
+rp11 skips 32 bytes then covers 32 etc
+rp12 covers 64 bytes then skips 64 etc
+rp13 skips 64 bytes then covers 64 etc
+rp14 covers 128 bytes then skips 128
+rp15 skips 128 bytes then covers 128
+
+In the end the parity bits are grouped together in three bytes as
+follows:
+ECC    Bit 7 Bit 6 Bit 5 Bit 4 Bit 3 Bit 2 Bit 1 Bit 0
+ECC 0   rp07  rp06  rp05  rp04  rp03  rp02  rp01  rp00
+ECC 1   rp15  rp14  rp13  rp12  rp11  rp10  rp09  rp08
+ECC 2   cp5   cp4   cp3   cp2   cp1   cp0      1     1
+
+I detected after writing this that ST application note AN1823
+(http://www.st.com/stonline/books/pdf/docs/10123.pdf) gives a much
+nicer picture.(but they use line parity as term where I use row parity)
+Oh well, I'm graphically challenged, so suffer with me for a moment :-)
+And I could not reuse the ST picture anyway for copyright reasons.
+
+
+Attempt 0
+=========
+
+Implementing the parity calculation is pretty simple.
+In C pseudocode:
+for (i = 0; i < 256; i++)
+{
+    if (i & 0x01)
+       rp1 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp1;
+    else
+       rp0 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp1;
+    if (i & 0x02)
+       rp3 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp3;
+    else
+       rp2 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp2;
+    if (i & 0x04)
+      rp5 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp5;
+    else
+      rp4 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp4;
+    if (i & 0x08)
+      rp7 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp7;
+    else
+      rp6 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp6;
+    if (i & 0x10)
+      rp9 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp9;
+    else
+      rp8 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp8;
+    if (i & 0x20)
+      rp11 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp11;
+    else
+    rp10 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp10;
+    if (i & 0x40)
+      rp13 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp13;
+    else
+      rp12 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp12;
+    if (i & 0x80)
+      rp15 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp15;
+    else
+      rp14 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp14;
+    cp0 = bit6 ^ bit4 ^ bit2 ^ bit0 ^ cp0;
+    cp1 = bit7 ^ bit5 ^ bit3 ^ bit1 ^ cp1;
+    cp2 = bit5 ^ bit4 ^ bit1 ^ bit0 ^ cp2;
+    cp3 = bit7 ^ bit6 ^ bit3 ^ bit2 ^ cp3
+    cp4 = bit3 ^ bit2 ^ bit1 ^ bit0 ^ cp4
+    cp5 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ cp5
+}
+
+
+Analysis 0
+==========
+
+C does have bitwise operators but not really operators to do the above
+efficiently (and most hardware has no such instructions either).
+Therefore without implementing this it was clear that the code above was
+not going to bring me a Nobel prize :-)
+
+Fortunately the exclusive or operation is commutative, so we can combine
+the values in any order. So instead of calculating all the bits
+individually, let us try to rearrange things.
+For the column parity this is easy. We can just xor the bytes and in the
+end filter out the relevant bits. This is pretty nice as it will bring
+all cp calculation out of the if loop.
+
+Similarly we can first xor the bytes for the various rows.
+This leads to:
+
+
+Attempt 1
+=========
+
+const char parity[256] = {
+    0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,
+    1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1,
+    1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1,
+    0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,
+    1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1,
+    0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,
+    0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,
+    1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1,
+    1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1,
+    0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,
+    0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,
+    1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1,
+    0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,
+    1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1,
+    1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1,
+    0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0
+};
+
+void ecc1(const unsigned char *buf, unsigned char *code)
+{
+    int i;
+    const unsigned char *bp = buf;
+    unsigned char cur;
+    unsigned char rp0, rp1, rp2, rp3, rp4, rp5, rp6, rp7;
+    unsigned char rp8, rp9, rp10, rp11, rp12, rp13, rp14, rp15;
+    unsigned char par;
+
+    par = 0;
+    rp0 = 0; rp1 = 0; rp2 = 0; rp3 = 0;
+    rp4 = 0; rp5 = 0; rp6 = 0; rp7 = 0;
+    rp8 = 0; rp9 = 0; rp10 = 0; rp11 = 0;
+    rp12 = 0; rp13 = 0; rp14 = 0; rp15 = 0;
+
+    for (i = 0; i < 256; i++)
+    {
+        cur = *bp++;
+        par ^= cur;
+        if (i & 0x01) rp1 ^= cur; else rp0 ^= cur;
+        if (i & 0x02) rp3 ^= cur; else rp2 ^= cur;
+        if (i & 0x04) rp5 ^= cur; else rp4 ^= cur;
+        if (i & 0x08) rp7 ^= cur; else rp6 ^= cur;
+        if (i & 0x10) rp9 ^= cur; else rp8 ^= cur;
+        if (i & 0x20) rp11 ^= cur; else rp10 ^= cur;
+        if (i & 0x40) rp13 ^= cur; else rp12 ^= cur;
+        if (i & 0x80) rp15 ^= cur; else rp14 ^= cur;
+    }
+    code[0] =
+        (parity[rp7] << 7) |
+        (parity[rp6] << 6) |
+        (parity[rp5] << 5) |
+        (parity[rp4] << 4) |
+        (parity[rp3] << 3) |
+        (parity[rp2] << 2) |
+        (parity[rp1] << 1) |
+        (parity[rp0]);
+    code[1] =
+        (parity[rp15] << 7) |
+        (parity[rp14] << 6) |
+        (parity[rp13] << 5) |
+        (parity[rp12] << 4) |
+        (parity[rp11] << 3) |
+        (parity[rp10] << 2) |
+        (parity[rp9]  << 1) |
+        (parity[rp8]);
+    code[2] =
+        (parity[par & 0xf0] << 7) |
+        (parity[par & 0x0f] << 6) |
+        (parity[par & 0xcc] << 5) |
+        (parity[par & 0x33] << 4) |
+        (parity[par & 0xaa] << 3) |
+        (parity[par & 0x55] << 2);
+    code[0] = ~code[0];
+    code[1] = ~code[1];
+    code[2] = ~code[2];
+}
+
+Still pretty straightforward. The last three invert statements are there to
+give a checksum of 0xff 0xff 0xff for an empty flash. In an empty flash
+all data is 0xff, so the checksum then matches.
+
+I also introduced the parity lookup. I expected this to be the fastest
+way to calculate the parity, but I will investigate alternatives later
+on.
+
+
+Analysis 1
+==========
+
+The code works, but is not terribly efficient. On my system it took
+almost 4 times as much time as the linux driver code. But hey, if it was
+*that* easy this would have been done long before.
+No pain. no gain.
+
+Fortunately there is plenty of room for improvement.
+
+In step 1 we moved from bit-wise calculation to byte-wise calculation.
+However in C we can also use the unsigned long data type and virtually
+every modern microprocessor supports 32 bit operations, so why not try
+to write our code in such a way that we process data in 32 bit chunks.
+
+Of course this means some modification as the row parity is byte by
+byte. A quick analysis:
+for the column parity we use the par variable. When extending to 32 bits
+we can in the end easily calculate p0 and p1 from it.
+(because par now consists of 4 bytes, contributing to rp1, rp0, rp1, rp0
+respectively)
+also rp2 and rp3 can be easily retrieved from par as rp3 covers the
+first two bytes and rp2 the last two bytes.
+
+Note that of course now the loop is executed only 64 times (256/4).
+And note that care must taken wrt byte ordering. The way bytes are
+ordered in a long is machine dependent, and might affect us.
+Anyway, if there is an issue: this code is developed on x86 (to be
+precise: a DELL PC with a D920 Intel CPU)
+
+And of course the performance might depend on alignment, but I expect
+that the I/O buffers in the nand driver are aligned properly (and
+otherwise that should be fixed to get maximum performance).
+
+Let's give it a try...
+
+
+Attempt 2
+=========
+
+extern const char parity[256];
+
+void ecc2(const unsigned char *buf, unsigned char *code)
+{
+    int i;
+    const unsigned long *bp = (unsigned long *)buf;
+    unsigned long cur;
+    unsigned long rp0, rp1, rp2, rp3, rp4, rp5, rp6, rp7;
+    unsigned long rp8, rp9, rp10, rp11, rp12, rp13, rp14, rp15;
+    unsigned long par;
+
+    par = 0;
+    rp0 = 0; rp1 = 0; rp2 = 0; rp3 = 0;
+    rp4 = 0; rp5 = 0; rp6 = 0; rp7 = 0;
+    rp8 = 0; rp9 = 0; rp10 = 0; rp11 = 0;
+    rp12 = 0; rp13 = 0; rp14 = 0; rp15 = 0;
+
+    for (i = 0; i < 64; i++)
+    {
+        cur = *bp++;
+        par ^= cur;
+        if (i & 0x01) rp5 ^= cur; else rp4 ^= cur;
+        if (i & 0x02) rp7 ^= cur; else rp6 ^= cur;
+        if (i & 0x04) rp9 ^= cur; else rp8 ^= cur;
+        if (i & 0x08) rp11 ^= cur; else rp10 ^= cur;
+        if (i & 0x10) rp13 ^= cur; else rp12 ^= cur;
+        if (i & 0x20) rp15 ^= cur; else rp14 ^= cur;
+    }
+    /*
+       we need to adapt the code generation for the fact that rp vars are now
+       long; also the column parity calculation needs to be changed.
+       we'll bring rp4 to 15 back to single byte entities by shifting and
+       xoring
+    */
+    rp4 ^= (rp4 >> 16); rp4 ^= (rp4 >> 8); rp4 &= 0xff;
+    rp5 ^= (rp5 >> 16); rp5 ^= (rp5 >> 8); rp5 &= 0xff;
+    rp6 ^= (rp6 >> 16); rp6 ^= (rp6 >> 8); rp6 &= 0xff;
+    rp7 ^= (rp7 >> 16); rp7 ^= (rp7 >> 8); rp7 &= 0xff;
+    rp8 ^= (rp8 >> 16); rp8 ^= (rp8 >> 8); rp8 &= 0xff;
+    rp9 ^= (rp9 >> 16); rp9 ^= (rp9 >> 8); rp9 &= 0xff;
+    rp10 ^= (rp10 >> 16); rp10 ^= (rp10 >> 8); rp10 &= 0xff;
+    rp11 ^= (rp11 >> 16); rp11 ^= (rp11 >> 8); rp11 &= 0xff;
+    rp12 ^= (rp12 >> 16); rp12 ^= (rp12 >> 8); rp12 &= 0xff;
+    rp13 ^= (rp13 >> 16); rp13 ^= (rp13 >> 8); rp13 &= 0xff;
+    rp14 ^= (rp14 >> 16); rp14 ^= (rp14 >> 8); rp14 &= 0xff;
+    rp15 ^= (rp15 >> 16); rp15 ^= (rp15 >> 8); rp15 &= 0xff;
+    rp3 = (par >> 16); rp3 ^= (rp3 >> 8); rp3 &= 0xff;
+    rp2 = par & 0xffff; rp2 ^= (rp2 >> 8); rp2 &= 0xff;
+    par ^= (par >> 16);
+    rp1 = (par >> 8); rp1 &= 0xff;
+    rp0 = (par & 0xff);
+    par ^= (par >> 8); par &= 0xff;
+
+    code[0] =
+        (parity[rp7] << 7) |
+        (parity[rp6] << 6) |
+        (parity[rp5] << 5) |
+        (parity[rp4] << 4) |
+        (parity[rp3] << 3) |
+        (parity[rp2] << 2) |
+        (parity[rp1] << 1) |
+        (parity[rp0]);
+    code[1] =
+        (parity[rp15] << 7) |
+        (parity[rp14] << 6) |
+        (parity[rp13] << 5) |
+        (parity[rp12] << 4) |
+        (parity[rp11] << 3) |
+        (parity[rp10] << 2) |
+        (parity[rp9]  << 1) |
+        (parity[rp8]);
+    code[2] =
+        (parity[par & 0xf0] << 7) |
+        (parity[par & 0x0f] << 6) |
+        (parity[par & 0xcc] << 5) |
+        (parity[par & 0x33] << 4) |
+        (parity[par & 0xaa] << 3) |
+        (parity[par & 0x55] << 2);
+    code[0] = ~code[0];
+    code[1] = ~code[1];
+    code[2] = ~code[2];
+}
+
+The parity array is not shown any more. Note also that for these
+examples I kinda deviated from my regular programming style by allowing
+multiple statements on a line, not using { } in then and else blocks
+with only a single statement and by using operators like ^=
+
+
+Analysis 2
+==========
+
+The code (of course) works, and hurray: we are a little bit faster than
+the linux driver code (about 15%). But wait, don't cheer too quickly.
+THere is more to be gained.
+If we look at e.g. rp14 and rp15 we see that we either xor our data with
+rp14 or with rp15. However we also have par which goes over all data.
+This means there is no need to calculate rp14 as it can be calculated from
+rp15 through rp14 = par ^ rp15;
+(or if desired we can avoid calculating rp15 and calculate it from
+rp14).  That is why some places refer to inverse parity.
+Of course the same thing holds for rp4/5, rp6/7, rp8/9, rp10/11 and rp12/13.
+Effectively this means we can eliminate the else clause from the if
+statements. Also we can optimise the calculation in the end a little bit
+by going from long to byte first. Actually we can even avoid the table
+lookups
+
+Attempt 3
+=========
+
+Odd replaced:
+        if (i & 0x01) rp5 ^= cur; else rp4 ^= cur;
+        if (i & 0x02) rp7 ^= cur; else rp6 ^= cur;
+        if (i & 0x04) rp9 ^= cur; else rp8 ^= cur;
+        if (i & 0x08) rp11 ^= cur; else rp10 ^= cur;
+        if (i & 0x10) rp13 ^= cur; else rp12 ^= cur;
+        if (i & 0x20) rp15 ^= cur; else rp14 ^= cur;
+with
+        if (i & 0x01) rp5 ^= cur;
+        if (i & 0x02) rp7 ^= cur;
+        if (i & 0x04) rp9 ^= cur;
+        if (i & 0x08) rp11 ^= cur;
+        if (i & 0x10) rp13 ^= cur;
+        if (i & 0x20) rp15 ^= cur;
+
+        and outside the loop added:
+    rp4  = par ^ rp5;
+    rp6  = par ^ rp7;
+    rp8  = par ^ rp9;
+    rp10  = par ^ rp11;
+    rp12  = par ^ rp13;
+    rp14  = par ^ rp15;
+
+And after that the code takes about 30% more time, although the number of
+statements is reduced. This is also reflected in the assembly code.
+
+
+Analysis 3
+==========
+
+Very weird. Guess it has to do with caching or instruction parallellism
+or so. I also tried on an eeePC (Celeron, clocked at 900 Mhz). Interesting
+observation was that this one is only 30% slower (according to time)
+executing the code as my 3Ghz D920 processor.
+
+Well, it was expected not to be easy so maybe instead move to a
+different track: let's move back to the code from attempt2 and do some
+loop unrolling. This will eliminate a few if statements. I'll try
+different amounts of unrolling to see what works best.
+
+
+Attempt 4
+=========
+
+Unrolled the loop 1, 2, 3 and 4 times.
+For 4 the code starts with:
+
+    for (i = 0; i < 4; i++)
+    {
+        cur = *bp++;
+        par ^= cur;
+        rp4 ^= cur;
+        rp6 ^= cur;
+        rp8 ^= cur;
+        rp10 ^= cur;
+        if (i & 0x1) rp13 ^= cur; else rp12 ^= cur;
+        if (i & 0x2) rp15 ^= cur; else rp14 ^= cur;
+        cur = *bp++;
+        par ^= cur;
+        rp5 ^= cur;
+        rp6 ^= cur;
+        ...
+
+
+Analysis 4
+==========
+
+Unrolling once gains about 15%
+Unrolling twice keeps the gain at about 15%
+Unrolling three times gives a gain of 30% compared to attempt 2.
+Unrolling four times gives a marginal improvement compared to unrolling
+three times.
+
+I decided to proceed with a four time unrolled loop anyway. It was my gut
+feeling that in the next steps I would obtain additional gain from it.
+
+The next step was triggered by the fact that par contains the xor of all
+bytes and rp4 and rp5 each contain the xor of half of the bytes.
+So in effect par = rp4 ^ rp5. But as xor is commutative we can also say
+that rp5 = par ^ rp4. So no need to keep both rp4 and rp5 around. We can
+eliminate rp5 (or rp4, but I already foresaw another optimisation).
+The same holds for rp6/7, rp8/9, rp10/11 rp12/13 and rp14/15.
+
+
+Attempt 5
+=========
+
+Effectively so all odd digit rp assignments in the loop were removed.
+This included the else clause of the if statements.
+Of course after the loop we need to correct things by adding code like:
+    rp5 = par ^ rp4;
+Also the initial assignments (rp5 = 0; etc) could be removed.
+Along the line I also removed the initialisation of rp0/1/2/3.
+
+
+Analysis 5
+==========
+
+Measurements showed this was a good move. The run-time roughly halved
+compared with attempt 4 with 4 times unrolled, and we only require 1/3rd
+of the processor time compared to the current code in the linux kernel.
+
+However, still I thought there was more. I didn't like all the if
+statements. Why not keep a running parity and only keep the last if
+statement. Time for yet another version!
+
+
+Attempt 6
+=========
+
+THe code within the for loop was changed to:
+
+    for (i = 0; i < 4; i++)
+    {
+        cur = *bp++; tmppar  = cur; rp4 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp6 ^= tmppar;
+        cur = *bp++; tmppar ^= cur; rp4 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp8 ^= tmppar;
+
+        cur = *bp++; tmppar ^= cur; rp4 ^= cur; rp6 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp6 ^= cur;
+	    cur = *bp++; tmppar ^= cur; rp4 ^= cur;
+	    cur = *bp++; tmppar ^= cur; rp10 ^= tmppar;
+
+	    cur = *bp++; tmppar ^= cur; rp4 ^= cur; rp6 ^= cur; rp8 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp6 ^= cur; rp8 ^= cur;
+	    cur = *bp++; tmppar ^= cur; rp4 ^= cur; rp8 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp8 ^= cur;
+
+        cur = *bp++; tmppar ^= cur; rp4 ^= cur; rp6 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp6 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp4 ^= cur;
+        cur = *bp++; tmppar ^= cur;
+
+	    par ^= tmppar;
+        if ((i & 0x1) == 0) rp12 ^= tmppar;
+        if ((i & 0x2) == 0) rp14 ^= tmppar;
+    }
+
+As you can see tmppar is used to accumulate the parity within a for
+iteration. In the last 3 statements is is added to par and, if needed,
+to rp12 and rp14.
+
+While making the changes I also found that I could exploit that tmppar
+contains the running parity for this iteration. So instead of having:
+rp4 ^= cur; rp6 = cur;
+I removed the rp6 = cur; statement and did rp6 ^= tmppar; on next
+statement. A similar change was done for rp8 and rp10
+
+
+Analysis 6
+==========
+
+Measuring this code again showed big gain. When executing the original
+linux code 1 million times, this took about 1 second on my system.
+(using time to measure the performance). After this iteration I was back
+to 0.075 sec. Actually I had to decide to start measuring over 10
+million interations in order not to loose too much accuracy. This one
+definitely seemed to be the jackpot!
+
+There is a little bit more room for improvement though. There are three
+places with statements:
+rp4 ^= cur; rp6 ^= cur;
+It seems more efficient to also maintain a variable rp4_6 in the while
+loop; This eliminates 3 statements per loop. Of course after the loop we
+need to correct by adding:
+    rp4 ^= rp4_6;
+    rp6 ^= rp4_6
+Furthermore there are 4 sequential assingments to rp8. This can be
+encoded slightly more efficient by saving tmppar before those 4 lines
+and later do rp8 = rp8 ^ tmppar ^ notrp8;
+(where notrp8 is the value of rp8 before those 4 lines).
+Again a use of the commutative property of xor.
+Time for a new test!
+
+
+Attempt 7
+=========
+
+The new code now looks like:
+
+    for (i = 0; i < 4; i++)
+    {
+        cur = *bp++; tmppar  = cur; rp4 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp6 ^= tmppar;
+        cur = *bp++; tmppar ^= cur; rp4 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp8 ^= tmppar;
+
+        cur = *bp++; tmppar ^= cur; rp4_6 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp6 ^= cur;
+	    cur = *bp++; tmppar ^= cur; rp4 ^= cur;
+	    cur = *bp++; tmppar ^= cur; rp10 ^= tmppar;
+
+	    notrp8 = tmppar;
+	    cur = *bp++; tmppar ^= cur; rp4_6 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp6 ^= cur;
+	    cur = *bp++; tmppar ^= cur; rp4 ^= cur;
+        cur = *bp++; tmppar ^= cur;
+	    rp8 = rp8 ^ tmppar ^ notrp8;
+
+        cur = *bp++; tmppar ^= cur; rp4_6 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp6 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp4 ^= cur;
+        cur = *bp++; tmppar ^= cur;
+
+	    par ^= tmppar;
+        if ((i & 0x1) == 0) rp12 ^= tmppar;
+        if ((i & 0x2) == 0) rp14 ^= tmppar;
+    }
+    rp4 ^= rp4_6;
+    rp6 ^= rp4_6;
+
+
+Not a big change, but every penny counts :-)
+
+
+Analysis 7
+==========
+
+Acutally this made things worse. Not very much, but I don't want to move
+into the wrong direction. Maybe something to investigate later. Could
+have to do with caching again.
+
+Guess that is what there is to win within the loop. Maybe unrolling one
+more time will help. I'll keep the optimisations from 7 for now.
+
+
+Attempt 8
+=========
+
+Unrolled the loop one more time.
+
+
+Analysis 8
+==========
+
+This makes things worse. Let's stick with attempt 6 and continue from there.
+Although it seems that the code within the loop cannot be optimised
+further there is still room to optimize the generation of the ecc codes.
+We can simply calcualate the total parity. If this is 0 then rp4 = rp5
+etc. If the parity is 1, then rp4 = !rp5;
+But if rp4 = rp5 we do not need rp5 etc. We can just write the even bits
+in the result byte and then do something like
+    code[0] |= (code[0] << 1);
+Lets test this.
+
+
+Attempt 9
+=========
+
+Changed the code but again this slightly degrades performance. Tried all
+kind of other things, like having dedicated parity arrays to avoid the
+shift after parity[rp7] << 7; No gain.
+Change the lookup using the parity array by using shift operators (e.g.
+replace parity[rp7] << 7 with:
+rp7 ^= (rp7 << 4);
+rp7 ^= (rp7 << 2);
+rp7 ^= (rp7 << 1);
+rp7 &= 0x80;
+No gain.
+
+The only marginal change was inverting the parity bits, so we can remove
+the last three invert statements.
+
+Ah well, pity this does not deliver more. Then again 10 million
+iterations using the linux driver code takes between 13 and 13.5
+seconds, whereas my code now takes about 0.73 seconds for those 10
+million iterations. So basically I've improved the performance by a
+factor 18 on my system. Not that bad. Of course on different hardware
+you will get different results. No warranties!
+
+But of course there is no such thing as a free lunch. The codesize almost
+tripled (from 562 bytes to 1434 bytes). Then again, it is not that much.
+
+
+Correcting errors
+=================
+
+For correcting errors I again used the ST application note as a starter,
+but I also peeked at the existing code.
+The algorithm itself is pretty straightforward. Just xor the given and
+the calculated ecc. If all bytes are 0 there is no problem. If 11 bits
+are 1 we have one correctable bit error. If there is 1 bit 1, we have an
+error in the given ecc code.
+It proved to be fastest to do some table lookups. Performance gain
+introduced by this is about a factor 2 on my system when a repair had to
+be done, and 1% or so if no repair had to be done.
+Code size increased from 330 bytes to 686 bytes for this function.
+(gcc 4.2, -O3)
+
+
+Conclusion
+==========
+
+The gain when calculating the ecc is tremendous. Om my development hardware
+a speedup of a factor of 18 for ecc calculation was achieved. On a test on an
+embedded system with a MIPS core a factor 7 was obtained.
+On  a test with a Linksys NSLU2 (ARMv5TE processor) the speedup was a factor
+5 (big endian mode, gcc 4.1.2, -O3)
+For correction not much gain could be obtained (as bitflips are rare). Then
+again there are also much less cycles spent there.
+
+It seems there is not much more gain possible in this, at least when
+programmed in C. Of course it might be possible to squeeze something more
+out of it with an assembler program, but due to pipeline behaviour etc
+this is very tricky (at least for intel hw).
+
+Author: Frans Meulenbroeks
+Copyright (C) 2008 Koninklijke Philips Electronics NV.

Documentation/sysrq.txt

@@ -95,7 +95,9 @@ On all -  write a character to /proc/sysrq-trigger.  e.g.:
 
 'p'     - Will dump the current registers and flags to your console.
 
-'q'     - Will dump a list of all running timers.
+'q'     - Will dump per CPU lists of all armed hrtimers (but NOT regular
+          timer_list timers) and detailed information about all
+          clockevent devices.
 
 'r'     - Turns off keyboard raw mode and sets it to XLATE.
 

Documentation/tracepoints.txt

@@ -0,0 +1,101 @@
+	             Using the Linux Kernel Tracepoints
+
+			    Mathieu Desnoyers
+
+
+This document introduces Linux Kernel Tracepoints and their use. It provides
+examples of how to insert tracepoints in the kernel and connect probe functions
+to them and provides some examples of probe functions.
+
+
+* Purpose of tracepoints
+
+A tracepoint placed in code provides a hook to call a function (probe) that you
+can provide at runtime. A tracepoint can be "on" (a probe is connected to it) or
+"off" (no probe is attached). When a tracepoint is "off" it has no effect,
+except for adding a tiny time penalty (checking a condition for a branch) and
+space penalty (adding a few bytes for the function call at the end of the
+instrumented function and adds a data structure in a separate section).  When a
+tracepoint is "on", the function you provide is called each time the tracepoint
+is executed, in the execution context of the caller. When the function provided
+ends its execution, it returns to the caller (continuing from the tracepoint
+site).
+
+You can put tracepoints at important locations in the code. They are
+lightweight hooks that can pass an arbitrary number of parameters,
+which prototypes are described in a tracepoint declaration placed in a header
+file.
+
+They can be used for tracing and performance accounting.
+
+
+* Usage
+
+Two elements are required for tracepoints :
+
+- A tracepoint definition, placed in a header file.
+- The tracepoint statement, in C code.
+
+In order to use tracepoints, you should include linux/tracepoint.h.
+
+In include/trace/subsys.h :
+
+#include <linux/tracepoint.h>
+
+DEFINE_TRACE(subsys_eventname,
+	TPPTOTO(int firstarg, struct task_struct *p),
+	TPARGS(firstarg, p));
+
+In subsys/file.c (where the tracing statement must be added) :
+
+#include <trace/subsys.h>
+
+void somefct(void)
+{
+	...
+	trace_subsys_eventname(arg, task);
+	...
+}
+
+Where :
+- subsys_eventname is an identifier unique to your event
+    - subsys is the name of your subsystem.
+    - eventname is the name of the event to trace.
+- TPPTOTO(int firstarg, struct task_struct *p) is the prototype of the function
+  called by this tracepoint.
+- TPARGS(firstarg, p) are the parameters names, same as found in the prototype.
+
+Connecting a function (probe) to a tracepoint is done by providing a probe
+(function to call) for the specific tracepoint through
+register_trace_subsys_eventname().  Removing a probe is done through
+unregister_trace_subsys_eventname(); it will remove the probe sure there is no
+caller left using the probe when it returns. Probe removal is preempt-safe
+because preemption is disabled around the probe call. See the "Probe example"
+section below for a sample probe module.
+
+The tracepoint mechanism supports inserting multiple instances of the same
+tracepoint, but a single definition must be made of a given tracepoint name over
+all the kernel to make sure no type conflict will occur. Name mangling of the
+tracepoints is done using the prototypes to make sure typing is correct.
+Verification of probe type correctness is done at the registration site by the
+compiler. Tracepoints can be put in inline functions, inlined static functions,
+and unrolled loops as well as regular functions.
+
+The naming scheme "subsys_event" is suggested here as a convention intended
+to limit collisions. Tracepoint names are global to the kernel: they are
+considered as being the same whether they are in the core kernel image or in
+modules.
+
+
+* Probe / tracepoint example
+
+See the example provided in samples/tracepoints/src
+
+Compile them with your kernel.
+
+Run, as root :
+modprobe tracepoint-example (insmod order is not important)
+modprobe tracepoint-probe-example
+cat /proc/tracepoint-example (returns an expected error)
+rmmod tracepoint-example tracepoint-probe-example
+dmesg

Documentation/tracers/mmiotrace.txt

@@ -36,7 +36,7 @@ $ mount -t debugfs debugfs /debug
 $ echo mmiotrace > /debug/tracing/current_tracer
 $ cat /debug/tracing/trace_pipe > mydump.txt &
 Start X or whatever.
-$ echo "X is up" > /debug/tracing/marker
+$ echo "X is up" > /debug/tracing/trace_marker
 $ echo none > /debug/tracing/current_tracer
 Check for lost events.
 
@@ -59,9 +59,8 @@ The 'cat' process should stay running (sleeping) in the background.
 Load the driver you want to trace and use it. Mmiotrace will only catch MMIO
 accesses to areas that are ioremapped while mmiotrace is active.
 
-[Unimplemented feature:]
 During tracing you can place comments (markers) into the trace by
-$ echo "X is up" > /debug/tracing/marker
+$ echo "X is up" > /debug/tracing/trace_marker
 This makes it easier to see which part of the (huge) trace corresponds to
 which action. It is recommended to place descriptive markers about what you
 do.

Documentation/vm/unevictable-lru.txt

@@ -0,0 +1,615 @@
+
+This document describes the Linux memory management "Unevictable LRU"
+infrastructure and the use of this infrastructure to manage several types
+of "unevictable" pages.  The document attempts to provide the overall
+rationale behind this mechanism and the rationale for some of the design
+decisions that drove the implementation.  The latter design rationale is
+discussed in the context of an implementation description.  Admittedly, one
+can obtain the implementation details--the "what does it do?"--by reading the
+code.  One hopes that the descriptions below add value by provide the answer
+to "why does it do that?".
+
+Unevictable LRU Infrastructure:
+
+The Unevictable LRU adds an additional LRU list to track unevictable pages
+and to hide these pages from vmscan.  This mechanism is based on a patch by
+Larry Woodman of Red Hat to address several scalability problems with page
+reclaim in Linux.  The problems have been observed at customer sites on large
+memory x86_64 systems.  For example, a non-numal x86_64 platform with 128GB
+of main memory will have over 32 million 4k pages in a single zone.  When a
+large fraction of these pages are not evictable for any reason [see below],
+vmscan will spend a lot of time scanning the LRU lists looking for the small
+fraction of pages that are evictable.  This can result in a situation where
+all cpus are spending 100% of their time in vmscan for hours or days on end,
+with the system completely unresponsive.
+
+The Unevictable LRU infrastructure addresses the following classes of
+unevictable pages:
+
++ page owned by ramfs
++ page mapped into SHM_LOCKed shared memory regions
++ page mapped into VM_LOCKED [mlock()ed] vmas
+
+The infrastructure might be able to handle other conditions that make pages
+unevictable, either by definition or by circumstance, in the future.
+
+
+The Unevictable LRU List
+
+The Unevictable LRU infrastructure consists of an additional, per-zone, LRU list
+called the "unevictable" list and an associated page flag, PG_unevictable, to
+indicate that the page is being managed on the unevictable list.  The
+PG_unevictable flag is analogous to, and mutually exclusive with, the PG_active
+flag in that it indicates on which LRU list a page resides when PG_lru is set.
+The unevictable LRU list is source configurable based on the UNEVICTABLE_LRU
+Kconfig option.
+
+The Unevictable LRU infrastructure maintains unevictable pages on an additional
+LRU list for a few reasons:
+
+1) We get to "treat unevictable pages just like we treat other pages in the
+   system, which means we get to use the same code to manipulate them, the
+   same code to isolate them (for migrate, etc.), the same code to keep track
+   of the statistics, etc..." [Rik van Riel]
+
+2) We want to be able to migrate unevictable pages between nodes--for memory
+   defragmentation, workload management and memory hotplug.  The linux kernel
+   can only migrate pages that it can successfully isolate from the lru lists.
+   If we were to maintain pages elsewise than on an lru-like list, where they
+   can be found by isolate_lru_page(), we would prevent their migration, unless
+   we reworked migration code to find the unevictable pages.
+
+
+The unevictable LRU list does not differentiate between file backed and swap
+backed [anon] pages.  This differentiation is only important while the pages
+are, in fact, evictable.
+
+The unevictable LRU list benefits from the "arrayification" of the per-zone
+LRU lists and statistics originally proposed and posted by Christoph Lameter.
+
+The unevictable list does not use the lru pagevec mechanism. Rather,
+unevictable pages are placed directly on the page's zone's unevictable
+list under the zone lru_lock.  The reason for this is to prevent stranding
+of pages on the unevictable list when one task has the page isolated from the
+lru and other tasks are changing the "evictability" state of the page.
+
+
+Unevictable LRU and Memory Controller Interaction
+
+The memory controller data structure automatically gets a per zone unevictable
+lru list as a result of the "arrayification" of the per-zone LRU lists.  The
+memory controller tracks the movement of pages to and from the unevictable list.
+When a memory control group comes under memory pressure, the controller will
+not attempt to reclaim pages on the unevictable list.  This has a couple of
+effects.  Because the pages are "hidden" from reclaim on the unevictable list,
+the reclaim process can be more efficient, dealing only with pages that have
+a chance of being reclaimed.  On the other hand, if too many of the pages
+charged to the control group are unevictable, the evictable portion of the
+working set of the tasks in the control group may not fit into the available
+memory.  This can cause the control group to thrash or to oom-kill tasks.
+
+
+Unevictable LRU:  Detecting Unevictable Pages
+
+The function page_evictable(page, vma) in vmscan.c determines whether a
+page is evictable or not.  For ramfs pages and pages in SHM_LOCKed regions,
+page_evictable() tests a new address space flag, AS_UNEVICTABLE, in the page's
+address space using a wrapper function.  Wrapper functions are used to set,
+clear and test the flag to reduce the requirement for #ifdef's throughout the
+source code.  AS_UNEVICTABLE is set on ramfs inode/mapping when it is created.
+This flag remains for the life of the inode.
+
+For shared memory regions, AS_UNEVICTABLE is set when an application
+successfully SHM_LOCKs the region and is removed when the region is
+SHM_UNLOCKed.  Note that shmctl(SHM_LOCK, ...) does not populate the page
+tables for the region as does, for example, mlock().   So, we make no special
+effort to push any pages in the SHM_LOCKed region to the unevictable list.
+Vmscan will do this when/if it encounters the pages during reclaim.  On
+SHM_UNLOCK, shmctl() scans the pages in the region and "rescues" them from the
+unevictable list if no other condition keeps them unevictable.  If a SHM_LOCKed
+region is destroyed, the pages are also "rescued" from the unevictable list in
+the process of freeing them.
+
+page_evictable() detects mlock()ed pages by testing an additional page flag,
+PG_mlocked via the PageMlocked() wrapper.  If the page is NOT mlocked, and a
+non-NULL vma is supplied, page_evictable() will check whether the vma is
+VM_LOCKED via is_mlocked_vma().  is_mlocked_vma() will SetPageMlocked() and
+update the appropriate statistics if the vma is VM_LOCKED.  This method allows
+efficient "culling" of pages in the fault path that are being faulted in to
+VM_LOCKED vmas.
+
+
+Unevictable Pages and Vmscan [shrink_*_list()]
+
+If unevictable pages are culled in the fault path, or moved to the unevictable
+list at mlock() or mmap() time, vmscan will never encounter the pages until
+they have become evictable again, for example, via munlock() and have been
+"rescued" from the unevictable list.  However, there may be situations where we
+decide, for the sake of expediency, to leave a unevictable page on one of the
+regular active/inactive LRU lists for vmscan to deal with.  Vmscan checks for
+such pages in all of the shrink_{active|inactive|page}_list() functions and
+will "cull" such pages that it encounters--that is, it diverts those pages to
+the unevictable list for the zone being scanned.
+
+There may be situations where a page is mapped into a VM_LOCKED vma, but the
+page is not marked as PageMlocked.  Such pages will make it all the way to
+shrink_page_list() where they will be detected when vmscan walks the reverse
+map in try_to_unmap().  If try_to_unmap() returns SWAP_MLOCK, shrink_page_list()
+will cull the page at that point.
+
+Note that for anonymous pages, shrink_page_list() attempts to add the page to
+the swap cache before it tries to unmap the page.  To avoid this unnecessary
+consumption of swap space, shrink_page_list() calls try_to_munlock() to check
+whether any VM_LOCKED vmas map the page without attempting to unmap the page.
+If try_to_munlock() returns SWAP_MLOCK, shrink_page_list() will cull the page
+without consuming swap space.  try_to_munlock() will be described below.
+
+To "cull" an unevictable page, vmscan simply puts the page back on the lru
+list using putback_lru_page()--the inverse operation to isolate_lru_page()--
+after dropping the page lock.  Because the condition which makes the page
+unevictable may change once the page is unlocked, putback_lru_page() will
+recheck the unevictable state of a page that it places on the unevictable lru
+list.  If the page has become unevictable, putback_lru_page() removes it from
+the list and retries, including the page_unevictable() test.  Because such a
+race is a rare event and movement of pages onto the unevictable list should be
+rare, these extra evictabilty checks should not occur in the majority of calls
+to putback_lru_page().
+
+
+Mlocked Page:  Prior Work
+
+The "Unevictable Mlocked Pages" infrastructure is based on work originally
+posted by Nick Piggin in an RFC patch entitled "mm: mlocked pages off LRU".
+Nick posted his patch as an alternative to a patch posted by Christoph
+Lameter to achieve the same objective--hiding mlocked pages from vmscan.
+In Nick's patch, he used one of the struct page lru list link fields as a count
+of VM_LOCKED vmas that map the page.  This use of the link field for a count
+prevented the management of the pages on an LRU list.  Thus, mlocked pages were
+not migratable as isolate_lru_page() could not find them and the lru list link
+field was not available to the migration subsystem.  Nick resolved this by
+putting mlocked pages back on the lru list before attempting to isolate them,
+thus abandoning the count of VM_LOCKED vmas.  When Nick's patch was integrated
+with the Unevictable LRU work, the count was replaced by walking the reverse
+map to determine whether any VM_LOCKED vmas mapped the page.  More on this
+below.
+
+
+Mlocked Pages:  Basic Management
+
+Mlocked pages--pages mapped into a VM_LOCKED vma--represent one class of
+unevictable pages.  When such a page has been "noticed" by the memory
+management subsystem, the page is marked with the PG_mlocked [PageMlocked()]
+flag.  A PageMlocked() page will be placed on the unevictable LRU list when
+it is added to the LRU.   Pages can be "noticed" by memory management in
+several places:
+
+1) in the mlock()/mlockall() system call handlers.
+2) in the mmap() system call handler when mmap()ing a region with the
+   MAP_LOCKED flag, or mmap()ing a region in a task that has called
+   mlockall() with the MCL_FUTURE flag.  Both of these conditions result
+   in the VM_LOCKED flag being set for the vma.
+3) in the fault path, if mlocked pages are "culled" in the fault path,
+   and when a VM_LOCKED stack segment is expanded.
+4) as mentioned above, in vmscan:shrink_page_list() with attempting to
+   reclaim a page in a VM_LOCKED vma--via try_to_unmap() or try_to_munlock().
+
+Mlocked pages become unlocked and rescued from the unevictable list when:
+
+1) mapped in a range unlocked via the munlock()/munlockall() system calls.
+2) munmapped() out of the last VM_LOCKED vma that maps the page, including
+   unmapping at task exit.
+3) when the page is truncated from the last VM_LOCKED vma of an mmap()ed file.
+4) before a page is COWed in a VM_LOCKED vma.
+
+
+Mlocked Pages:  mlock()/mlockall() System Call Handling
+
+Both [do_]mlock() and [do_]mlockall() system call handlers call mlock_fixup()
+for each vma in the range specified by the call.  In the case of mlockall(),
+this is the entire active address space of the task.  Note that mlock_fixup()
+is used for both mlock()ing and munlock()ing a range of memory.  A call to
+mlock() an already VM_LOCKED vma, or to munlock() a vma that is not VM_LOCKED
+is treated as a no-op--mlock_fixup() simply returns.
+
+If the vma passes some filtering described in "Mlocked Pages:  Filtering Vmas"
+below, mlock_fixup() will attempt to merge the vma with its neighbors or split
+off a subset of the vma if the range does not cover the entire vma.  Once the
+vma has been merged or split or neither, mlock_fixup() will call
+__mlock_vma_pages_range() to fault in the pages via get_user_pages() and
+to mark the pages as mlocked via mlock_vma_page().
+
+Note that the vma being mlocked might be mapped with PROT_NONE.  In this case,
+get_user_pages() will be unable to fault in the pages.  That's OK.  If pages
+do end up getting faulted into this VM_LOCKED vma, we'll handle them in the
+fault path or in vmscan.
+
+Also note that a page returned by get_user_pages() could be truncated or
+migrated out from under us, while we're trying to mlock it.  To detect
+this, __mlock_vma_pages_range() tests the page_mapping after acquiring
+the page lock.  If the page is still associated with its mapping, we'll
+go ahead and call mlock_vma_page().  If the mapping is gone, we just
+unlock the page and move on.  Worse case, this results in page mapped
+in a VM_LOCKED vma remaining on a normal LRU list without being
+PageMlocked().  Again, vmscan will detect and cull such pages.
+
+mlock_vma_page(), called with the page locked [N.B., not "mlocked"], will
+TestSetPageMlocked() for each page returned by get_user_pages().  We use
+TestSetPageMlocked() because the page might already be mlocked by another
+task/vma and we don't want to do extra work.  We especially do not want to
+count an mlocked page more than once in the statistics.  If the page was
+already mlocked, mlock_vma_page() is done.
+
+If the page was NOT already mlocked, mlock_vma_page() attempts to isolate the
+page from the LRU, as it is likely on the appropriate active or inactive list
+at that time.  If the isolate_lru_page() succeeds, mlock_vma_page() will
+putback the page--putback_lru_page()--which will notice that the page is now
+mlocked and divert the page to the zone's unevictable LRU list.  If
+mlock_vma_page() is unable to isolate the page from the LRU, vmscan will handle
+it later if/when it attempts to reclaim the page.
+
+
+Mlocked Pages:  Filtering Special Vmas
+
+mlock_fixup() filters several classes of "special" vmas:
+
+1) vmas with VM_IO|VM_PFNMAP set are skipped entirely.  The pages behind
+   these mappings are inherently pinned, so we don't need to mark them as
+   mlocked.  In any case, most of the pages have no struct page in which to
+   so mark the page.  Because of this, get_user_pages() will fail for these
+   vmas, so there is no sense in attempting to visit them.
+
+2) vmas mapping hugetlbfs page are already effectively pinned into memory.
+   We don't need nor want to mlock() these pages.  However, to preserve the
+   prior behavior of mlock()--before the unevictable/mlock changes--mlock_fixup()
+   will call make_pages_present() in the hugetlbfs vma range to allocate the
+   huge pages and populate the ptes.
+
+3) vmas with VM_DONTEXPAND|VM_RESERVED are generally user space mappings of
+   kernel pages, such as the vdso page, relay channel pages, etc.  These pages
+   are inherently unevictable and are not managed on the LRU lists.
+   mlock_fixup() treats these vmas the same as hugetlbfs vmas.  It calls
+   make_pages_present() to populate the ptes.
+
+Note that for all of these special vmas, mlock_fixup() does not set the
+VM_LOCKED flag.  Therefore, we won't have to deal with them later during
+munlock() or munmap()--for example, at task exit.  Neither does mlock_fixup()
+account these vmas against the task's "locked_vm".
+
+Mlocked Pages:  Downgrading the Mmap Semaphore.
+
+mlock_fixup() must be called with the mmap semaphore held for write, because
+it may have to merge or split vmas.  However, mlocking a large region of
+memory can take a long time--especially if vmscan must reclaim pages to
+satisfy the regions requirements.  Faulting in a large region with the mmap
+semaphore held for write can hold off other faults on the address space, in
+the case of a multi-threaded task.  It can also hold off scans of the task's
+address space via /proc.  While testing under heavy load, it was observed that
+the ps(1) command could be held off for many minutes while a large segment was
+mlock()ed down.
+
+To address this issue, and to make the system more responsive during mlock()ing
+of large segments, mlock_fixup() downgrades the mmap semaphore to read mode
+during the call to __mlock_vma_pages_range().  This works fine.  However, the
+callers of mlock_fixup() expect the semaphore to be returned in write mode.
+So, mlock_fixup() "upgrades" the semphore to write mode.  Linux does not
+support an atomic upgrade_sem() call, so mlock_fixup() must drop the semaphore
+and reacquire it in write mode.  In a multi-threaded task, it is possible for
+the task memory map to change while the semaphore is dropped.  Therefore,
+mlock_fixup() looks up the vma at the range start address after reacquiring
+the semaphore in write mode and verifies that it still covers the original
+range.  If not, mlock_fixup() returns an error [-EAGAIN].  All callers of
+mlock_fixup() have been changed to deal with this new error condition.
+
+Note:  when munlocking a region, all of the pages should already be resident--
+unless we have racing threads mlocking() and munlocking() regions.  So,
+unlocking should not have to wait for page allocations nor faults  of any kind.
+Therefore mlock_fixup() does not downgrade the semaphore for munlock().
+
+
+Mlocked Pages:  munlock()/munlockall() System Call Handling
+
+The munlock() and munlockall() system calls are handled by the same functions--
+do_mlock[all]()--as the mlock() and mlockall() system calls with the unlock
+vs lock operation indicated by an argument.  So, these system calls are also
+handled by mlock_fixup().  Again, if called for an already munlock()ed vma,
+mlock_fixup() simply returns.  Because of the vma filtering discussed above,
+VM_LOCKED will not be set in any "special" vmas.  So, these vmas will be
+ignored for munlock.
+
+If the vma is VM_LOCKED, mlock_fixup() again attempts to merge or split off
+the specified range.  The range is then munlocked via the function
+__mlock_vma_pages_range()--the same function used to mlock a vma range--
+passing a flag to indicate that munlock() is being performed.
+
+Because the vma access protections could have been changed to PROT_NONE after
+faulting in and mlocking some pages, get_user_pages() was unreliable for visiting
+these pages for munlocking.  Because we don't want to leave pages mlocked(),
+get_user_pages() was enhanced to accept a flag to ignore the permissions when
+fetching the pages--all of which should be resident as a result of previous
+mlock()ing.
+
+For munlock(), __mlock_vma_pages_range() unlocks individual pages by calling
+munlock_vma_page().  munlock_vma_page() unconditionally clears the PG_mlocked
+flag using TestClearPageMlocked().  As with mlock_vma_page(), munlock_vma_page()
+use the Test*PageMlocked() function to handle the case where the page might
+have already been unlocked by another task.  If the page was mlocked,
+munlock_vma_page() updates that zone statistics for the number of mlocked
+pages.  Note, however, that at this point we haven't checked whether the page
+is mapped by other VM_LOCKED vmas.
+
+We can't call try_to_munlock(), the function that walks the reverse map to check
+for other VM_LOCKED vmas, without first isolating the page from the LRU.
+try_to_munlock() is a variant of try_to_unmap() and thus requires that the page
+not be on an lru list.  [More on these below.]  However, the call to
+isolate_lru_page() could fail, in which case we couldn't try_to_munlock().
+So, we go ahead and clear PG_mlocked up front, as this might be the only chance
+we have.  If we can successfully isolate the page, we go ahead and
+try_to_munlock(), which will restore the PG_mlocked flag and update the zone
+page statistics if it finds another vma holding the page mlocked.  If we fail
+to isolate the page, we'll have left a potentially mlocked page on the LRU.
+This is fine, because we'll catch it later when/if vmscan tries to reclaim the
+page.  This should be relatively rare.
+
+Mlocked Pages:  Migrating Them...
+
+A page that is being migrated has been isolated from the lru lists and is
+held locked across unmapping of the page, updating the page's mapping
+[address_space] entry and copying the contents and state, until the
+page table entry has been replaced with an entry that refers to the new
+page.  Linux supports migration of mlocked pages and other unevictable
+pages.  This involves simply moving the PageMlocked and PageUnevictable states
+from the old page to the new page.
+
+Note that page migration can race with mlocking or munlocking of the same
+page.  This has been discussed from the mlock/munlock perspective in the
+respective sections above.  Both processes [migration, m[un]locking], hold
+the page locked.  This provides the first level of synchronization.  Page
+migration zeros out the page_mapping of the old page before unlocking it,
+so m[un]lock can skip these pages by testing the page mapping under page
+lock.
+
+When completing page migration, we place the new and old pages back onto the
+lru after dropping the page lock.  The "unneeded" page--old page on success,
+new page on failure--will be freed when the reference count held by the
+migration process is released.  To ensure that we don't strand pages on the
+unevictable list because of a race between munlock and migration, page
+migration uses the putback_lru_page() function to add migrated pages back to
+the lru.
+
+
+Mlocked Pages:  mmap(MAP_LOCKED) System Call Handling
+
+In addition the the mlock()/mlockall() system calls, an application can request
+that a region of memory be mlocked using the MAP_LOCKED flag with the mmap()
+call.  Furthermore, any mmap() call or brk() call that expands the heap by a
+task that has previously called mlockall() with the MCL_FUTURE flag will result
+in the newly mapped memory being mlocked.  Before the unevictable/mlock changes,
+the kernel simply called make_pages_present() to allocate pages and populate
+the page table.
+
+To mlock a range of memory under the unevictable/mlock infrastructure, the
+mmap() handler and task address space expansion functions call
+mlock_vma_pages_range() specifying the vma and the address range to mlock.
+mlock_vma_pages_range() filters vmas like mlock_fixup(), as described above in
+"Mlocked Pages:  Filtering Vmas".  It will clear the VM_LOCKED flag, which will
+have already been set by the caller, in filtered vmas.  Thus these vma's need
+not be visited for munlock when the region is unmapped.
+
+For "normal" vmas, mlock_vma_pages_range() calls __mlock_vma_pages_range() to
+fault/allocate the pages and mlock them.  Again, like mlock_fixup(),
+mlock_vma_pages_range() downgrades the mmap semaphore to read mode before
+attempting to fault/allocate and mlock the pages; and "upgrades" the semaphore
+back to write mode before returning.
+
+The callers of mlock_vma_pages_range() will have already added the memory
+range to be mlocked to the task's "locked_vm".  To account for filtered vmas,
+mlock_vma_pages_range() returns the number of pages NOT mlocked.  All of the
+callers then subtract a non-negative return value from the task's locked_vm.
+A negative return value represent an error--for example, from get_user_pages()
+attempting to fault in a vma with PROT_NONE access.  In this case, we leave
+the memory range accounted as locked_vm, as the protections could be changed
+later and pages allocated into that region.
+
+
+Mlocked Pages:  munmap()/exit()/exec() System Call Handling
+
+When unmapping an mlocked region of memory, whether by an explicit call to
+munmap() or via an internal unmap from exit() or exec() processing, we must
+munlock the pages if we're removing the last VM_LOCKED vma that maps the pages.
+Before the unevictable/mlock changes, mlocking did not mark the pages in any way,
+so unmapping them required no processing.
+
+To munlock a range of memory under the unevictable/mlock infrastructure, the
+munmap() hander and task address space tear down function call
+munlock_vma_pages_all().  The name reflects the observation that one always
+specifies the entire vma range when munlock()ing during unmap of a region.
+Because of the vma filtering when mlocking() regions, only "normal" vmas that
+actually contain mlocked pages will be passed to munlock_vma_pages_all().
+
+munlock_vma_pages_all() clears the VM_LOCKED vma flag and, like mlock_fixup()
+for the munlock case, calls __munlock_vma_pages_range() to walk the page table
+for the vma's memory range and munlock_vma_page() each resident page mapped by
+the vma.  This effectively munlocks the page, only if this is the last
+VM_LOCKED vma that maps the page.
+
+
+Mlocked Page:  try_to_unmap()
+
+[Note:  the code changes represented by this section are really quite small
+compared to the text to describe what happening and why, and to discuss the
+implications.]
+
+Pages can, of course, be mapped into multiple vmas.  Some of these vmas may
+have VM_LOCKED flag set.  It is possible for a page mapped into one or more
+VM_LOCKED vmas not to have the PG_mlocked flag set and therefore reside on one
+of the active or inactive LRU lists.  This could happen if, for example, a
+task in the process of munlock()ing the page could not isolate the page from
+the LRU.  As a result, vmscan/shrink_page_list() might encounter such a page
+as described in "Unevictable Pages and Vmscan [shrink_*_list()]".  To
+handle this situation, try_to_unmap() has been enhanced to check for VM_LOCKED
+vmas while it is walking a page's reverse map.
+
+try_to_unmap() is always called, by either vmscan for reclaim or for page
+migration, with the argument page locked and isolated from the LRU.  BUG_ON()
+assertions enforce this requirement.  Separate functions handle anonymous and
+mapped file pages, as these types of pages have different reverse map
+mechanisms.
+
+	try_to_unmap_anon()
+
+To unmap anonymous pages, each vma in the list anchored in the anon_vma must be
+visited--at least until a VM_LOCKED vma is encountered.  If the page is being
+unmapped for migration, VM_LOCKED vmas do not stop the process because mlocked
+pages are migratable.  However, for reclaim, if the page is mapped into a
+VM_LOCKED vma, the scan stops.  try_to_unmap() attempts to acquire the mmap
+semphore of the mm_struct to which the vma belongs in read mode.  If this is
+successful, try_to_unmap() will mlock the page via mlock_vma_page()--we
+wouldn't have gotten to try_to_unmap() if the page were already mlocked--and
+will return SWAP_MLOCK, indicating that the page is unevictable.  If the
+mmap semaphore cannot be acquired, we are not sure whether the page is really
+unevictable or not.  In this case, try_to_unmap() will return SWAP_AGAIN.
+
+	try_to_unmap_file() -- linear mappings
+
+Unmapping of a mapped file page works the same, except that the scan visits
+all vmas that maps the page's index/page offset in the page's mapping's
+reverse map priority search tree.  It must also visit each vma in the page's
+mapping's non-linear list, if the list is non-empty.  As for anonymous pages,
+on encountering a VM_LOCKED vma for a mapped file page, try_to_unmap() will
+attempt to acquire the associated mm_struct's mmap semaphore to mlock the page,
+returning SWAP_MLOCK if this is successful, and SWAP_AGAIN, if not.
+
+	try_to_unmap_file() -- non-linear mappings
+
+If a page's mapping contains a non-empty non-linear mapping vma list, then
+try_to_un{map|lock}() must also visit each vma in that list to determine
+whether the page is mapped in a VM_LOCKED vma.  Again, the scan must visit
+all vmas in the non-linear list to ensure that the pages is not/should not be
+mlocked.  If a VM_LOCKED vma is found in the list, the scan could terminate.
+However, there is no easy way to determine whether the page is actually mapped
+in a given vma--either for unmapping or testing whether the VM_LOCKED vma
+actually pins the page.
+
+So, try_to_unmap_file() handles non-linear mappings by scanning a certain
+number of pages--a "cluster"--in each non-linear vma associated with the page's
+mapping, for each file mapped page that vmscan tries to unmap.  If this happens
+to unmap the page we're trying to unmap, try_to_unmap() will notice this on
+return--(page_mapcount(page) == 0)--and return SWAP_SUCCESS.  Otherwise, it
+will return SWAP_AGAIN, causing vmscan to recirculate this page.  We take
+advantage of the cluster scan in try_to_unmap_cluster() as follows:
+
+For each non-linear vma, try_to_unmap_cluster() attempts to acquire the mmap
+semaphore of the associated mm_struct for read without blocking.  If this
+attempt is successful and the vma is VM_LOCKED, try_to_unmap_cluster() will
+retain the mmap semaphore for the scan; otherwise it drops it here.  Then,
+for each page in the cluster, if we're holding the mmap semaphore for a locked
+vma, try_to_unmap_cluster() calls mlock_vma_page() to mlock the page.  This
+call is a no-op if the page is already locked, but will mlock any pages in
+the non-linear mapping that happen to be unlocked.  If one of the pages so
+mlocked is the page passed in to try_to_unmap(), try_to_unmap_cluster() will
+return SWAP_MLOCK, rather than the default SWAP_AGAIN.  This will allow vmscan
+to cull the page, rather than recirculating it on the inactive list.  Again,
+if try_to_unmap_cluster() cannot acquire the vma's mmap sem, it returns
+SWAP_AGAIN, indicating that the page is mapped by a VM_LOCKED vma, but
+couldn't be mlocked.
+
+
+Mlocked pages:  try_to_munlock() Reverse Map Scan
+
+TODO/FIXME:  a better name might be page_mlocked()--analogous to the
+page_referenced() reverse map walker--especially if we continue to call this
+from shrink_page_list().  See related TODO/FIXME below.
+
+When munlock_vma_page()--see "Mlocked Pages:  munlock()/munlockall() System
+Call Handling" above--tries to munlock a page, or when shrink_page_list()
+encounters an anonymous page that is not yet in the swap cache, they need to
+determine whether or not the page is mapped by any VM_LOCKED vma, without
+actually attempting to unmap all ptes from the page.  For this purpose, the
+unevictable/mlock infrastructure introduced a variant of try_to_unmap() called
+try_to_munlock().
+
+try_to_munlock() calls the same functions as try_to_unmap() for anonymous and
+mapped file pages with an additional argument specifing unlock versus unmap
+processing.  Again, these functions walk the respective reverse maps looking
+for VM_LOCKED vmas.  When such a vma is found for anonymous pages and file
+pages mapped in linear VMAs, as in the try_to_unmap() case, the functions
+attempt to acquire the associated mmap semphore, mlock the page via
+mlock_vma_page() and return SWAP_MLOCK.  This effectively undoes the
+pre-clearing of the page's PG_mlocked done by munlock_vma_page() and informs
+shrink_page_list() that the anonymous page should be culled rather than added
+to the swap cache in preparation for a try_to_unmap() that will almost
+certainly fail.
+
+If try_to_unmap() is unable to acquire a VM_LOCKED vma's associated mmap
+semaphore, it will return SWAP_AGAIN.  This will allow shrink_page_list()
+to recycle the page on the inactive list and hope that it has better luck
+with the page next time.
+
+For file pages mapped into non-linear vmas, the try_to_munlock() logic works
+slightly differently.  On encountering a VM_LOCKED non-linear vma that might
+map the page, try_to_munlock() returns SWAP_AGAIN without actually mlocking
+the page.  munlock_vma_page() will just leave the page unlocked and let
+vmscan deal with it--the usual fallback position.
+
+Note that try_to_munlock()'s reverse map walk must visit every vma in a pages'
+reverse map to determine that a page is NOT mapped into any VM_LOCKED vma.
+However, the scan can terminate when it encounters a VM_LOCKED vma and can
+successfully acquire the vma's mmap semphore for read and mlock the page.
+Although try_to_munlock() can be called many [very many!] times when
+munlock()ing a large region or tearing down a large address space that has been
+mlocked via mlockall(), overall this is a fairly rare event.  In addition,
+although shrink_page_list() calls try_to_munlock() for every anonymous page that
+it handles that is not yet in the swap cache, on average anonymous pages will
+have very short reverse map lists.
+
+Mlocked Page:  Page Reclaim in shrink_*_list()
+
+shrink_active_list() culls any obviously unevictable pages--i.e.,
+!page_evictable(page, NULL)--diverting these to the unevictable lru
+list.  However, shrink_active_list() only sees unevictable pages that
+made it onto the active/inactive lru lists.  Note that these pages do not
+have PageUnevictable set--otherwise, they would be on the unevictable list and
+shrink_active_list would never see them.
+
+Some examples of these unevictable pages on the LRU lists are:
+
+1) ramfs pages that have been placed on the lru lists when first allocated.
+
+2) SHM_LOCKed shared memory pages.  shmctl(SHM_LOCK) does not attempt to
+   allocate or fault in the pages in the shared memory region.  This happens
+   when an application accesses the page the first time after SHM_LOCKing
+   the segment.
+
+3) Mlocked pages that could not be isolated from the lru and moved to the
+   unevictable list in mlock_vma_page().
+
+3) Pages mapped into multiple VM_LOCKED vmas, but try_to_munlock() couldn't
+   acquire the vma's mmap semaphore to test the flags and set PageMlocked.
+   munlock_vma_page() was forced to let the page back on to the normal
+   LRU list for vmscan to handle.
+
+shrink_inactive_list() also culls any unevictable pages that it finds
+on the inactive lists, again diverting them to the appropriate zone's unevictable
+lru list.  shrink_inactive_list() should only see SHM_LOCKed pages that became
+SHM_LOCKed after shrink_active_list() had moved them to the inactive list, or
+pages mapped into VM_LOCKED vmas that munlock_vma_page() couldn't isolate from
+the lru to recheck via try_to_munlock().  shrink_inactive_list() won't notice
+the latter, but will pass on to shrink_page_list().
+
+shrink_page_list() again culls obviously unevictable pages that it could
+encounter for similar reason to shrink_inactive_list().  As already discussed,
+shrink_page_list() proactively looks for anonymous pages that should have
+PG_mlocked set but don't--these would not be detected by page_evictable()--to
+avoid adding them to the swap cache unnecessarily.  File pages mapped into
+VM_LOCKED vmas but without PG_mlocked set will make it all the way to
+try_to_unmap().  shrink_page_list() will divert them to the unevictable list when
+try_to_unmap() returns SWAP_MLOCK, as discussed above.
+
+TODO/FIXME:  If we can enhance the swap cache to reliably remove entries
+with page_count(page) > 2, as long as all ptes are mapped to the page and
+not the swap entry, we can probably remove the call to try_to_munlock() in
+shrink_page_list() and just remove the page from the swap cache when
+try_to_unmap() returns SWAP_MLOCK.   Currently, remove_exclusive_swap_page()
+doesn't seem to allow that.
+
+

MAINTAINERS

@@ -1198,7 +1198,7 @@ S:	Maintained
 
 CPU FREQUENCY DRIVERS
 P:	Dave Jones
-M:	davej@codemonkey.org.uk
+M:	davej@redhat.com
 L:	cpufreq@vger.kernel.org
 W:	http://www.codemonkey.org.uk/projects/cpufreq/
 T:	git kernel.org/pub/scm/linux/kernel/git/davej/cpufreq.git

arch/alpha/Kconfig

@@ -70,6 +70,7 @@ config AUTO_IRQ_AFFINITY
 	default y
 
 source "init/Kconfig"
+source "kernel/Kconfig.freezer"
 
 
 menu "System setup"

arch/alpha/include/asm/thread_info.h

@@ -74,12 +74,14 @@ register struct thread_info *__current_thread_info __asm__("$8");
 #define TIF_UAC_SIGBUS		7
 #define TIF_MEMDIE		8
 #define TIF_RESTORE_SIGMASK	9	/* restore signal mask in do_signal */
+#define TIF_FREEZE		16	/* is freezing for suspend */
 
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
 #define _TIF_SIGPENDING		(1<<TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1<<TIF_NEED_RESCHED)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
 #define _TIF_RESTORE_SIGMASK	(1<<TIF_RESTORE_SIGMASK)
+#define _TIF_FREEZE		(1<<TIF_FREEZE)
 
 /* Work to do on interrupt/exception return.  */
 #define _TIF_WORK_MASK		(_TIF_SIGPENDING | _TIF_NEED_RESCHED)

arch/alpha/kernel/core_marvel.c

@@ -655,7 +655,7 @@ __marvel_rtc_io(u8 b, unsigned long addr, int write)
 
 	case 0x71:					/* RTC_PORT(1) */
 		rtc_access.index = index;
-		rtc_access.data = BCD_TO_BIN(b);
+		rtc_access.data = bcd2bin(b);
 		rtc_access.function = 0x48 + !write;	/* GET/PUT_TOY */
 
 #ifdef CONFIG_SMP
@@ -668,7 +668,7 @@ __marvel_rtc_io(u8 b, unsigned long addr, int write)
 #else
 		__marvel_access_rtc(&rtc_access);
 #endif
-		ret = BIN_TO_BCD(rtc_access.data);
+		ret = bin2bcd(rtc_access.data);
 		break;
 
 	default:

arch/alpha/kernel/sys_sable.c

@@ -47,7 +47,7 @@ typedef struct irq_swizzle_struct
 
 static irq_swizzle_t *sable_lynx_irq_swizzle;
 
-static void sable_lynx_init_irq(int nr_irqs);
+static void sable_lynx_init_irq(int nr_of_irqs);
 
 #if defined(CONFIG_ALPHA_GENERIC) || defined(CONFIG_ALPHA_SABLE)
 
@@ -530,11 +530,11 @@ sable_lynx_srm_device_interrupt(unsigned long vector)
 }
 
 static void __init
-sable_lynx_init_irq(int nr_irqs)
+sable_lynx_init_irq(int nr_of_irqs)
 {
 	long i;
 
-	for (i = 0; i < nr_irqs; ++i) {
+	for (i = 0; i < nr_of_irqs; ++i) {
 		irq_desc[i].status = IRQ_DISABLED | IRQ_LEVEL;
 		irq_desc[i].chip = &sable_lynx_irq_type;
 	}

arch/alpha/kernel/time.c

@@ -346,12 +346,12 @@ time_init(void)
 	year = CMOS_READ(RTC_YEAR);
 
 	if (!(CMOS_READ(RTC_CONTROL) & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
-		BCD_TO_BIN(sec);
+		sec = bcd2bin(sec);
-		BCD_TO_BIN(min);
+		min = bcd2bin(min);
-		BCD_TO_BIN(hour);
+		hour = bcd2bin(hour);
-		BCD_TO_BIN(day);
+		day = bcd2bin(day);
-		BCD_TO_BIN(mon);
+		mon = bcd2bin(mon);
-		BCD_TO_BIN(year);
+		year = bcd2bin(year);
 	}
 
 	/* PC-like is standard; used for year >= 70 */
@@ -525,7 +525,7 @@ set_rtc_mmss(unsigned long nowtime)
 
 	cmos_minutes = CMOS_READ(RTC_MINUTES);
 	if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD)
-		BCD_TO_BIN(cmos_minutes);
+		cmos_minutes = bcd2bin(cmos_minutes);
 
 	/*
 	 * since we're only adjusting minutes and seconds,
@@ -543,8 +543,8 @@ set_rtc_mmss(unsigned long nowtime)
 
 	if (abs(real_minutes - cmos_minutes) < 30) {
 		if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
-			BIN_TO_BCD(real_seconds);
+			real_seconds = bin2bcd(real_seconds);
-			BIN_TO_BCD(real_minutes);
+			real_minutes = bin2bcd(real_minutes);
 		}
 		CMOS_WRITE(real_seconds,RTC_SECONDS);
 		CMOS_WRITE(real_minutes,RTC_MINUTES);

arch/arm/Kconfig

@@ -192,6 +192,8 @@ config VECTORS_BASE
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 menu "System Type"
 
 choice

arch/arm/mach-iop13xx/include/mach/time.h

@@ -41,7 +41,7 @@ static inline unsigned long iop13xx_core_freq(void)
 		return 1200000000;
 	default:
 		printk("%s: warning unknown frequency, defaulting to 800Mhz\n",
-			__FUNCTION__);
+			__func__);
 	}
 
 	return 800000000;
@@ -60,7 +60,7 @@ static inline unsigned long iop13xx_xsi_bus_ratio(void)
 		return 4;
 	default:
 		printk("%s: warning unknown ratio, defaulting to 2\n",
-			__FUNCTION__);
+			__func__);
 	}
 
 	return 2;

arch/arm/mach-ixp2000/ixdp2x00.c

@@ -143,7 +143,7 @@ static struct irq_chip ixdp2x00_cpld_irq_chip = {
 	.unmask	= ixdp2x00_irq_unmask
 };
 
-void __init ixdp2x00_init_irq(volatile unsigned long *stat_reg, volatile unsigned long *mask_reg, unsigned long nr_irqs)
+void __init ixdp2x00_init_irq(volatile unsigned long *stat_reg, volatile unsigned long *mask_reg, unsigned long nr_of_irqs)
 {
 	unsigned int irq;
 
@@ -154,7 +154,7 @@ void __init ixdp2x00_init_irq(volatile unsigned long *stat_reg, volatile unsigne
 
 	board_irq_stat = stat_reg;
 	board_irq_mask = mask_reg;
-	board_irq_count = nr_irqs;
+	board_irq_count = nr_of_irqs;
 
 	*board_irq_mask = 0xffffffff;
 

arch/arm/mach-omap2/irq.c

@@ -119,7 +119,7 @@ static void __init omap_irq_bank_init_one(struct omap_irq_bank *bank)
 
 void __init omap_init_irq(void)
 {
-	unsigned long nr_irqs = 0;
+	unsigned long nr_of_irqs = 0;
 	unsigned int nr_banks = 0;
 	int i;
 
@@ -133,14 +133,14 @@ void __init omap_init_irq(void)
 
 		omap_irq_bank_init_one(bank);
 
-		nr_irqs += bank->nr_irqs;
+		nr_of_irqs += bank->nr_irqs;
 		nr_banks++;
 	}
 
 	printk(KERN_INFO "Total of %ld interrupts on %d active controller%s\n",
-	       nr_irqs, nr_banks, nr_banks > 1 ? "s" : "");
+	       nr_of_irqs, nr_banks, nr_banks > 1 ? "s" : "");
 
-	for (i = 0; i < nr_irqs; i++) {
+	for (i = 0; i < nr_of_irqs; i++) {
 		set_irq_chip(i, &omap_irq_chip);
 		set_irq_handler(i, handle_level_irq);
 		set_irq_flags(i, IRQF_VALID);

arch/arm/mach-pxa/include/mach/pxa3xx_nand.h

@@ -4,6 +4,43 @@
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
 
+struct pxa3xx_nand_timing {
+	unsigned int	tCH;  /* Enable signal hold time */
+	unsigned int	tCS;  /* Enable signal setup time */
+	unsigned int	tWH;  /* ND_nWE high duration */
+	unsigned int	tWP;  /* ND_nWE pulse time */
+	unsigned int	tRH;  /* ND_nRE high duration */
+	unsigned int	tRP;  /* ND_nRE pulse width */
+	unsigned int	tR;   /* ND_nWE high to ND_nRE low for read */
+	unsigned int	tWHR; /* ND_nWE high to ND_nRE low for status read */
+	unsigned int	tAR;  /* ND_ALE low to ND_nRE low delay */
+};
+
+struct pxa3xx_nand_cmdset {
+	uint16_t	read1;
+	uint16_t	read2;
+	uint16_t	program;
+	uint16_t	read_status;
+	uint16_t	read_id;
+	uint16_t	erase;
+	uint16_t	reset;
+	uint16_t	lock;
+	uint16_t	unlock;
+	uint16_t	lock_status;
+};
+
+struct pxa3xx_nand_flash {
+	const struct pxa3xx_nand_timing *timing; /* NAND Flash timing */
+	const struct pxa3xx_nand_cmdset *cmdset;
+
+	uint32_t page_per_block;/* Pages per block (PG_PER_BLK) */
+	uint32_t page_size;	/* Page size in bytes (PAGE_SZ) */
+	uint32_t flash_width;	/* Width of Flash memory (DWIDTH_M) */
+	uint32_t dfc_width;	/* Width of flash controller(DWIDTH_C) */
+	uint32_t num_blocks;	/* Number of physical blocks in Flash */
+	uint32_t chip_id;
+};
+
 struct pxa3xx_nand_platform_data {
 
 	/* the data flash bus is shared between the Static Memory
@@ -12,8 +49,11 @@ struct pxa3xx_nand_platform_data {
 	 */
 	int	enable_arbiter;
 
-	struct mtd_partition *parts;
+	const struct mtd_partition		*parts;
-	unsigned int	nr_parts;
+	unsigned int				nr_parts;
+
+	const struct pxa3xx_nand_flash * 	flash;
+	size_t					num_flash;
 };
 
 extern void pxa3xx_set_nand_info(struct pxa3xx_nand_platform_data *info);

arch/arm/mach-pxa/include/mach/tosa.h

@@ -59,8 +59,6 @@
  * TC6393XB GPIOs
  */
 #define TOSA_TC6393XB_GPIO_BASE		(NR_BUILTIN_GPIO + 2 * 12)
-#define TOSA_TC6393XB_GPIO(i)		(TOSA_TC6393XB_GPIO_BASE + (i))
-#define TOSA_TC6393XB_GPIO_BIT(gpio)	(1 << (gpio - TOSA_TC6393XB_GPIO_BASE))
 
 #define TOSA_GPIO_TG_ON			(TOSA_TC6393XB_GPIO_BASE + 0)
 #define TOSA_GPIO_L_MUTE		(TOSA_TC6393XB_GPIO_BASE + 1)

arch/arm/mach-pxa/include/mach/zylonite.h

@@ -30,7 +30,7 @@ extern void zylonite_pxa300_init(void);
 static inline void zylonite_pxa300_init(void)
 {
 	if (cpu_is_pxa300() || cpu_is_pxa310())
-		panic("%s: PXA300/PXA310 not supported\n", __FUNCTION__);
+		panic("%s: PXA300/PXA310 not supported\n", __func__);
 }
 #endif
 
@@ -40,7 +40,7 @@ extern void zylonite_pxa320_init(void);
 static inline void zylonite_pxa320_init(void)
 {
 	if (cpu_is_pxa320())
-		panic("%s: PXA320 not supported\n", __FUNCTION__);
+		panic("%s: PXA320 not supported\n", __func__);
 }
 #endif
 

arch/arm/mach-pxa/tosa.c

@@ -706,16 +706,39 @@ static struct tmio_nand_data tosa_tc6393xb_nand_config = {
 	.badblock_pattern = &tosa_tc6393xb_nand_bbt,
 };
 
-static struct tc6393xb_platform_data tosa_tc6393xb_setup = {
+static int tosa_tc6393xb_setup(struct platform_device *dev)
+{
+	int rc;
+
+	rc = gpio_request(TOSA_GPIO_CARD_VCC_ON, "CARD_VCC_ON");
+	if (rc)
+		goto err_req;
+
+	rc = gpio_direction_output(TOSA_GPIO_CARD_VCC_ON, 1);
+	if (rc)
+		goto err_dir;
+
+	return rc;
+
+err_dir:
+	gpio_free(TOSA_GPIO_CARD_VCC_ON);
+err_req:
+	return rc;
+}
+
+static void tosa_tc6393xb_teardown(struct platform_device *dev)
+{
+	gpio_free(TOSA_GPIO_CARD_VCC_ON);
+}
+
+static struct tc6393xb_platform_data tosa_tc6393xb_data = {
 	.scr_pll2cr	= 0x0cc1,
 	.scr_gper	= 0x3300,
-	.scr_gpo_dsr	=
-		TOSA_TC6393XB_GPIO_BIT(TOSA_GPIO_CARD_VCC_ON),
-	.scr_gpo_doecr	=
-		TOSA_TC6393XB_GPIO_BIT(TOSA_GPIO_CARD_VCC_ON),
 
 	.irq_base	= IRQ_BOARD_START,
 	.gpio_base	= TOSA_TC6393XB_GPIO_BASE,
+	.setup		= tosa_tc6393xb_setup,
+	.teardown	= tosa_tc6393xb_teardown,
 
 	.enable		= tosa_tc6393xb_enable,
 	.disable	= tosa_tc6393xb_disable,
@@ -723,6 +746,8 @@ static struct tc6393xb_platform_data tosa_tc6393xb_setup = {
 	.resume		= tosa_tc6393xb_resume,
 
 	.nand_data	= &tosa_tc6393xb_nand_config,
+
+	.resume_restore = 1,
 };
 
 
@@ -730,7 +755,7 @@ static struct platform_device tc6393xb_device = {
 	.name	= "tc6393xb",
 	.id	= -1,
 	.dev	= {
-		.platform_data	= &tosa_tc6393xb_setup,
+		.platform_data	= &tosa_tc6393xb_data,
 	},
 	.num_resources	= ARRAY_SIZE(tc6393xb_resources),
 	.resource	= tc6393xb_resources,

arch/arm/mach-sa1100/include/mach/ide.h

@@ -1,75 +0,0 @@
-/*
- * arch/arm/mach-sa1100/include/mach/ide.h
- *
- * Copyright (c) 1998 Hugo Fiennes & Nicolas Pitre
- *
- * 18-aug-2000: Cleanup by Erik Mouw (J.A.K.Mouw@its.tudelft.nl)
- *              Get rid of the special ide_init_hwif_ports() functions
- *              and make a generalised function that can be used by all
- *              architectures.
- */
-
-#include <asm/irq.h>
-#include <mach/hardware.h>
-#include <asm/mach-types.h>
-
-#error "This code is broken and needs update to match with current ide support"
-
-
-/*
- * Set up a hw structure for a specified data port, control port and IRQ.
- * This should follow whatever the default interface uses.
- */
-static inline void ide_init_hwif_ports(hw_regs_t *hw, unsigned long data_port,
-				       unsigned long ctrl_port, int *irq)
-{
-	unsigned long reg = data_port;
-	int i;
-	int regincr = 1;
-
-	/* The Empeg board has the first two address lines unused */
-	if (machine_is_empeg())
-		regincr = 1 << 2;
-
-	/* The LART doesn't use A0 for IDE */
-	if (machine_is_lart())
-		regincr = 1 << 1;
-
-	memset(hw, 0, sizeof(*hw));
-
-	for (i = 0; i <= 7; i++) {
-		hw->io_ports_array[i] = reg;
-		reg += regincr;
-	}
-
-	hw->io_ports.ctl_addr = ctrl_port;
-
-	if (irq)
-		*irq = 0;
-}
-
-/*
- * This registers the standard ports for this architecture with the IDE
- * driver.
- */
-static __inline__ void
-ide_init_default_hwifs(void)
-{
-    if (machine_is_lart()) {
-#ifdef CONFIG_SA1100_LART
-        hw_regs_t hw;
-
-        /* Enable GPIO as interrupt line */
-        GPDR &= ~LART_GPIO_IDE;
-	set_irq_type(LART_IRQ_IDE, IRQ_TYPE_EDGE_RISING);
-
-        /* set PCMCIA interface timing */
-        MECR = 0x00060006;
-
-        /* init the interface */
-	ide_init_hwif_ports(&hw, PCMCIA_IO_0_BASE + 0x0000, PCMCIA_IO_0_BASE + 0x1000, NULL);
-        hw.irq = LART_IRQ_IDE;
-        ide_register_hw(&hw);
-#endif
-    }
-}

arch/arm/plat-mxc/include/mach/mxc_nand.h

@@ -0,0 +1,27 @@
+/*
+ * Copyright 2004-2007 Freescale Semiconductor, Inc. All Rights Reserved.
+ * Copyright 2008 Sascha Hauer, kernel@pengutronix.de
+ *
+ * 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.
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#ifndef __ASM_ARCH_NAND_H
+#define __ASM_ARCH_NAND_H
+
+struct mxc_nand_platform_data {
+	int width;	/* data bus width in bytes */
+	int hw_ecc;	/* 0 if supress hardware ECC */
+};
+#endif /* __ASM_ARCH_NAND_H */

arch/arm/plat-omap/include/mach/onenand.h

@@ -16,6 +16,10 @@ struct omap_onenand_platform_data {
 	int			gpio_irq;
 	struct mtd_partition	*parts;
 	int			nr_parts;
-	int                     (*onenand_setup)(void __iomem *);
+	int                     (*onenand_setup)(void __iomem *, int freq);
 	int			dma_channel;
 };
+
+int omap2_onenand_rephase(void);
+
+#define ONENAND_MAX_PARTITIONS 8

arch/avr32/Kconfig

@@ -72,6 +72,8 @@ config GENERIC_BUG
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 menu "System Type and features"
 
 source "kernel/time/Kconfig"

arch/avr32/include/asm/thread_info.h

@@ -96,6 +96,7 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_MEMDIE		(1 << TIF_MEMDIE)
 #define _TIF_RESTORE_SIGMASK	(1 << TIF_RESTORE_SIGMASK)
 #define _TIF_CPU_GOING_TO_SLEEP (1 << TIF_CPU_GOING_TO_SLEEP)
+#define _TIF_FREEZE		(1 << TIF_FREEZE)
 
 /* Note: The masks below must never span more than 16 bits! */
 

arch/avr32/mach-at32ap/extint.c

@@ -191,7 +191,7 @@ static int __init eic_probe(struct platform_device *pdev)
 	struct eic *eic;
 	struct resource *regs;
 	unsigned int i;
-	unsigned int nr_irqs;
+	unsigned int nr_of_irqs;
 	unsigned int int_irq;
 	int ret;
 	u32 pattern;
@@ -224,7 +224,7 @@ static int __init eic_probe(struct platform_device *pdev)
 	eic_writel(eic, IDR, ~0UL);
 	eic_writel(eic, MODE, ~0UL);
 	pattern = eic_readl(eic, MODE);
-	nr_irqs = fls(pattern);
+	nr_of_irqs = fls(pattern);
 
 	/* Trigger on low level unless overridden by driver */
 	eic_writel(eic, EDGE, 0UL);
@@ -232,7 +232,7 @@ static int __init eic_probe(struct platform_device *pdev)
 
 	eic->chip = &eic_chip;
 
-	for (i = 0; i < nr_irqs; i++) {
+	for (i = 0; i < nr_of_irqs; i++) {
 		set_irq_chip_and_handler(eic->first_irq + i, &eic_chip,
 					 handle_level_irq);
 		set_irq_chip_data(eic->first_irq + i, eic);
@@ -256,7 +256,7 @@ static int __init eic_probe(struct platform_device *pdev)
 		 eic->regs, int_irq);
 	dev_info(&pdev->dev,
 		 "Handling %u external IRQs, starting with IRQ %u\n",
-		 nr_irqs, eic->first_irq);
+		 nr_of_irqs, eic->first_irq);
 
 	return 0;
 

arch/blackfin/Kconfig

@@ -64,8 +64,11 @@ config HARDWARE_PM
 	depends on OPROFILE
 
 source "init/Kconfig"
+
 source "kernel/Kconfig.preempt"
 
+source "kernel/Kconfig.freezer"
+
 menu "Blackfin Processor Options"
 
 comment "Processor and Board Settings"

arch/cris/Kconfig

@@ -62,6 +62,8 @@ config HZ
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 menu "General setup"
 
 source "fs/Kconfig.binfmt"

arch/cris/arch-v10/drivers/ds1302.c

@@ -215,12 +215,12 @@ get_rtc_time(struct rtc_time *rtc_tm)
 
 	local_irq_restore(flags);
 	
-	BCD_TO_BIN(rtc_tm->tm_sec);
+	rtc_tm->tm_sec = bcd2bin(rtc_tm->tm_sec);
-	BCD_TO_BIN(rtc_tm->tm_min);
+	rtc_tm->tm_min = bcd2bin(rtc_tm->tm_min);
-	BCD_TO_BIN(rtc_tm->tm_hour);
+	rtc_tm->tm_hour = bcd2bin(rtc_tm->tm_hour);
-	BCD_TO_BIN(rtc_tm->tm_mday);
+	rtc_tm->tm_mday = bcd2bin(rtc_tm->tm_mday);
-	BCD_TO_BIN(rtc_tm->tm_mon);
+	rtc_tm->tm_mon = bcd2bin(rtc_tm->tm_mon);
-	BCD_TO_BIN(rtc_tm->tm_year);
+	rtc_tm->tm_year = bcd2bin(rtc_tm->tm_year);
 
 	/*
 	 * Account for differences between how the RTC uses the values
@@ -295,12 +295,12 @@ rtc_ioctl(struct inode *inode, struct file *file, unsigned int cmd,
 			else
 				yrs -= 1900;	/* RTC (70, 71, ... 99) */
 
-			BIN_TO_BCD(sec);
+			sec = bin2bcd(sec);
-			BIN_TO_BCD(min);
+			min = bin2bcd(min);
-			BIN_TO_BCD(hrs);
+			hrs = bin2bcd(hrs);
-			BIN_TO_BCD(day);
+			day = bin2bcd(day);
-			BIN_TO_BCD(mon);
+			mon = bin2bcd(mon);
-			BIN_TO_BCD(yrs);
+			yrs = bin2bcd(yrs);
 
 			local_irq_save(flags);
 			CMOS_WRITE(yrs, RTC_YEAR);

arch/cris/arch-v10/drivers/pcf8563.c

@@ -122,7 +122,7 @@ get_rtc_time(struct rtc_time *tm)
 		       "information is no longer guaranteed!\n", PCF8563_NAME);
 	}
 
-	tm->tm_year  = BCD_TO_BIN(tm->tm_year) +
+	tm->tm_year  = bcd2bin(tm->tm_year) +
 		       ((tm->tm_mon & 0x80) ? 100 : 0);
 	tm->tm_sec  &= 0x7F;
 	tm->tm_min  &= 0x7F;
@@ -131,11 +131,11 @@ get_rtc_time(struct rtc_time *tm)
 	tm->tm_wday &= 0x07; /* Not coded in BCD. */
 	tm->tm_mon  &= 0x1F;
 
-	BCD_TO_BIN(tm->tm_sec);
+	tm->tm_sec = bcd2bin(tm->tm_sec);
-	BCD_TO_BIN(tm->tm_min);
+	tm->tm_min = bcd2bin(tm->tm_min);
-	BCD_TO_BIN(tm->tm_hour);
+	tm->tm_hour = bcd2bin(tm->tm_hour);
-	BCD_TO_BIN(tm->tm_mday);
+	tm->tm_mday = bcd2bin(tm->tm_mday);
-	BCD_TO_BIN(tm->tm_mon);
+	tm->tm_mon = bcd2bin(tm->tm_mon);
 	tm->tm_mon--; /* Month is 1..12 in RTC but 0..11 in linux */
 }
 
@@ -282,12 +282,12 @@ int pcf8563_ioctl(struct inode *inode, struct file *filp, unsigned int cmd,
 		century = (tm.tm_year >= 2000) ? 0x80 : 0;
 		tm.tm_year = tm.tm_year % 100;
 
-		BIN_TO_BCD(tm.tm_year);
+		tm.tm_year = bin2bcd(tm.tm_year);
-		BIN_TO_BCD(tm.tm_mon);
+		tm.tm_mon = bin2bcd(tm.tm_mon);
-		BIN_TO_BCD(tm.tm_mday);
+		tm.tm_mday = bin2bcd(tm.tm_mday);
-		BIN_TO_BCD(tm.tm_hour);
+		tm.tm_hour = bin2bcd(tm.tm_hour);
-		BIN_TO_BCD(tm.tm_min);
+		tm.tm_min = bin2bcd(tm.tm_min);
-		BIN_TO_BCD(tm.tm_sec);
+		tm.tm_sec = bin2bcd(tm.tm_sec);
 		tm.tm_mon |= century;
 
 		mutex_lock(&rtc_lock);

arch/cris/arch-v32/drivers/pcf8563.c

@@ -118,7 +118,7 @@ get_rtc_time(struct rtc_time *tm)
 		       "information is no longer guaranteed!\n", PCF8563_NAME);
 	}
 
-	tm->tm_year  = BCD_TO_BIN(tm->tm_year) +
+	tm->tm_year  = bcd2bin(tm->tm_year) +
 		       ((tm->tm_mon & 0x80) ? 100 : 0);
 	tm->tm_sec  &= 0x7F;
 	tm->tm_min  &= 0x7F;
@@ -127,11 +127,11 @@ get_rtc_time(struct rtc_time *tm)
 	tm->tm_wday &= 0x07; /* Not coded in BCD. */
 	tm->tm_mon  &= 0x1F;
 
-	BCD_TO_BIN(tm->tm_sec);
+	tm->tm_sec = bcd2bin(tm->tm_sec);
-	BCD_TO_BIN(tm->tm_min);
+	tm->tm_min = bcd2bin(tm->tm_min);
-	BCD_TO_BIN(tm->tm_hour);
+	tm->tm_hour = bcd2bin(tm->tm_hour);
-	BCD_TO_BIN(tm->tm_mday);
+	tm->tm_mday = bcd2bin(tm->tm_mday);
-	BCD_TO_BIN(tm->tm_mon);
+	tm->tm_mon = bcd2bin(tm->tm_mon);
 	tm->tm_mon--; /* Month is 1..12 in RTC but 0..11 in linux */
 }
 
@@ -279,12 +279,12 @@ int pcf8563_ioctl(struct inode *inode, struct file *filp, unsigned int cmd,
 		century = (tm.tm_year >= 2000) ? 0x80 : 0;
 		tm.tm_year = tm.tm_year % 100;
 
-		BIN_TO_BCD(tm.tm_year);
+		tm.tm_year = bin2bcd(tm.tm_year);
-		BIN_TO_BCD(tm.tm_mon);
+		tm.tm_mon = bin2bcd(tm.tm_mon);
-		BIN_TO_BCD(tm.tm_mday);
+		tm.tm_mday = bin2bcd(tm.tm_mday);
-		BIN_TO_BCD(tm.tm_hour);
+		tm.tm_hour = bin2bcd(tm.tm_hour);
-		BIN_TO_BCD(tm.tm_min);
+		tm.tm_min = bin2bcd(tm.tm_min);
-		BIN_TO_BCD(tm.tm_sec);
+		tm.tm_sec = bin2bcd(tm.tm_sec);
 		tm.tm_mon |= century;
 
 		mutex_lock(&rtc_lock);

arch/cris/kernel/time.c

@@ -127,7 +127,7 @@ int set_rtc_mmss(unsigned long nowtime)
 		return 0;
 
 	cmos_minutes = CMOS_READ(RTC_MINUTES);
-	BCD_TO_BIN(cmos_minutes);
+	cmos_minutes = bcd2bin(cmos_minutes);
 
 	/*
 	 * since we're only adjusting minutes and seconds,
@@ -142,8 +142,8 @@ int set_rtc_mmss(unsigned long nowtime)
 	real_minutes %= 60;
 
 	if (abs(real_minutes - cmos_minutes) < 30) {
-		BIN_TO_BCD(real_seconds);
+		real_seconds = bin2bcd(real_seconds);
-		BIN_TO_BCD(real_minutes);
+		real_minutes = bin2bcd(real_minutes);
 		CMOS_WRITE(real_seconds,RTC_SECONDS);
 		CMOS_WRITE(real_minutes,RTC_MINUTES);
 	} else {
@@ -170,12 +170,12 @@ get_cmos_time(void)
 	mon = CMOS_READ(RTC_MONTH);
 	year = CMOS_READ(RTC_YEAR);
 
-	BCD_TO_BIN(sec);
+	sec = bcd2bin(sec);
-	BCD_TO_BIN(min);
+	min = bcd2bin(min);
-	BCD_TO_BIN(hour);
+	hour = bcd2bin(hour);
-	BCD_TO_BIN(day);
+	day = bcd2bin(day);
-	BCD_TO_BIN(mon);
+	mon = bcd2bin(mon);
-	BCD_TO_BIN(year);
+	year = bcd2bin(year);
 
 	if ((year += 1900) < 1970)
 		year += 100;

arch/frv/Kconfig

@@ -66,6 +66,8 @@ mainmenu "Fujitsu FR-V Kernel Configuration"
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 
 menu "Fujitsu FR-V system setup"
 

arch/h8300/Kconfig

@@ -90,6 +90,8 @@ config HZ
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 source "arch/h8300/Kconfig.cpu"
 
 menu "Executable file formats"

arch/h8300/include/asm/thread_info.h

@@ -89,6 +89,7 @@ static inline struct thread_info *current_thread_info(void)
 					   TIF_NEED_RESCHED */
 #define TIF_MEMDIE		4
 #define TIF_RESTORE_SIGMASK	5	/* restore signal mask in do_signal() */
+#define TIF_FREEZE		16	/* is freezing for suspend */
 
 /* as above, but as bit values */
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
@@ -96,6 +97,7 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_NEED_RESCHED	(1<<TIF_NEED_RESCHED)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
 #define _TIF_RESTORE_SIGMASK	(1<<TIF_RESTORE_SIGMASK)
+#define _TIF_FREEZE		(1<<TIF_FREEZE)
 
 #define _TIF_WORK_MASK		0x0000FFFE	/* work to do on interrupt/exception return */
 

arch/ia64/Kconfig

@@ -7,6 +7,8 @@ mainmenu "IA-64 Linux Kernel Configuration"
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 menu "Processor type and features"
 
 config IA64

arch/ia64/hp/common/sba_iommu.c

@@ -2070,14 +2070,13 @@ sba_init(void)
 	if (!ia64_platform_is("hpzx1") && !ia64_platform_is("hpzx1_swiotlb"))
 		return 0;
 
-#if defined(CONFIG_IA64_GENERIC) && defined(CONFIG_CRASH_DUMP) && \
+#if defined(CONFIG_IA64_GENERIC)
-        defined(CONFIG_PROC_FS)
 	/* If we are booting a kdump kernel, the sba_iommu will
 	 * cause devices that were not shutdown properly to MCA
 	 * as soon as they are turned back on.  Our only option for
 	 * a successful kdump kernel boot is to use the swiotlb.
 	 */
-	if (elfcorehdr_addr < ELFCORE_ADDR_MAX) {
+	if (is_kdump_kernel()) {
 		if (swiotlb_late_init_with_default_size(64 * (1<<20)) != 0)
 			panic("Unable to initialize software I/O TLB:"
 				  " Try machvec=dig boot option");

arch/ia64/include/asm/pci.h

@@ -95,16 +95,8 @@ extern int pci_mmap_page_range (struct pci_dev *dev, struct vm_area_struct *vma,
 				enum pci_mmap_state mmap_state, int write_combine);
 #define HAVE_PCI_LEGACY
 extern int pci_mmap_legacy_page_range(struct pci_bus *bus,
-				      struct vm_area_struct *vma);
+				      struct vm_area_struct *vma,
-extern ssize_t pci_read_legacy_io(struct kobject *kobj,
+				      enum pci_mmap_state mmap_state);
-				  struct bin_attribute *bin_attr,
-				  char *buf, loff_t off, size_t count);
-extern ssize_t pci_write_legacy_io(struct kobject *kobj,
-				   struct bin_attribute *bin_attr,
-				   char *buf, loff_t off, size_t count);
-extern int pci_mmap_legacy_mem(struct kobject *kobj,
-			       struct bin_attribute *attr,
-			       struct vm_area_struct *vma);
 
 #define pci_get_legacy_mem platform_pci_get_legacy_mem
 #define pci_legacy_read platform_pci_legacy_read

arch/ia64/kernel/crash_dump.c

@@ -8,10 +8,14 @@
 
 #include <linux/errno.h>
 #include <linux/types.h>
+#include <linux/crash_dump.h>
 
 #include <asm/page.h>
 #include <asm/uaccess.h>
 
+/* Stores the physical address of elf header of crash image. */
+unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX;
+
 /**
  * copy_oldmem_page - copy one page from "oldmem"
  * @pfn: page frame number to be copied

arch/ia64/kernel/efi.c

@@ -1335,7 +1335,7 @@ kdump_find_rsvd_region (unsigned long size, struct rsvd_region *r, int n)
 }
 #endif
 
-#ifdef CONFIG_PROC_VMCORE
+#ifdef CONFIG_CRASH_DUMP
 /* locate the size find a the descriptor at a certain address */
 unsigned long __init
 vmcore_find_descriptor_size (unsigned long address)

arch/ia64/kernel/setup.c

@@ -352,7 +352,7 @@ reserve_memory (void)
 	}
 #endif
 
-#ifdef CONFIG_PROC_VMCORE
+#ifdef CONFIG_CRASH_KERNEL
 	if (reserve_elfcorehdr(&rsvd_region[n].start,
 			       &rsvd_region[n].end) == 0)
 		n++;
@@ -478,7 +478,12 @@ static __init int setup_nomca(char *s)
 }
 early_param("nomca", setup_nomca);
 
-#ifdef CONFIG_PROC_VMCORE
+/*
+ * Note: elfcorehdr_addr is not just limited to vmcore. It is also used by
+ * is_kdump_kernel() to determine if we are booting after a panic. Hence
+ * ifdef it under CONFIG_CRASH_DUMP and not CONFIG_PROC_VMCORE.
+ */
+#ifdef CONFIG_CRASH_DUMP
 /* elfcorehdr= specifies the location of elf core header
  * stored by the crashed kernel.
  */
@@ -502,11 +507,11 @@ int __init reserve_elfcorehdr(unsigned long *start, unsigned long *end)
 	 * to work properly.
 	 */
 
-	if (elfcorehdr_addr >= ELFCORE_ADDR_MAX)
+	if (!is_vmcore_usable())
 		return -EINVAL;
 
 	if ((length = vmcore_find_descriptor_size(elfcorehdr_addr)) == 0) {
-		elfcorehdr_addr = ELFCORE_ADDR_MAX;
+		vmcore_unusable();
 		return -EINVAL;
 	}
 

arch/ia64/mm/init.c

@@ -700,23 +700,6 @@ int arch_add_memory(int nid, u64 start, u64 size)
 
 	return ret;
 }
-#ifdef CONFIG_MEMORY_HOTREMOVE
-int remove_memory(u64 start, u64 size)
-{
-	unsigned long start_pfn, end_pfn;
-	unsigned long timeout = 120 * HZ;
-	int ret;
-	start_pfn = start >> PAGE_SHIFT;
-	end_pfn = start_pfn + (size >> PAGE_SHIFT);
-	ret = offline_pages(start_pfn, end_pfn, timeout);
-	if (ret)
-		goto out;
-	/* we can free mem_map at this point */
-out:
-	return ret;
-}
-EXPORT_SYMBOL_GPL(remove_memory);
-#endif /* CONFIG_MEMORY_HOTREMOVE */
 #endif
 
 /*

arch/ia64/pci/pci.c

@@ -614,12 +614,17 @@ char *ia64_pci_get_legacy_mem(struct pci_bus *bus)
  * vector to get the base address.
  */
 int
-pci_mmap_legacy_page_range(struct pci_bus *bus, struct vm_area_struct *vma)
+pci_mmap_legacy_page_range(struct pci_bus *bus, struct vm_area_struct *vma,
+			   enum pci_mmap_state mmap_state)
 {
 	unsigned long size = vma->vm_end - vma->vm_start;
 	pgprot_t prot;
 	char *addr;
 
+	/* We only support mmap'ing of legacy memory space */
+	if (mmap_state != pci_mmap_mem)
+		return -ENOSYS;
+
 	/*
 	 * Avoid attribute aliasing.  See Documentation/ia64/aliasing.txt
 	 * for more details.

arch/m32r/Kconfig

@@ -42,6 +42,8 @@ config HZ
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 
 menu "Processor type and features"
 

arch/m32r/kernel/smpboot.c

@@ -40,6 +40,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/cpu.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>

arch/m68k/Kconfig

@@ -62,6 +62,8 @@ mainmenu "Linux/68k Kernel Configuration"
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 menu "Platform dependent setup"
 
 config EISA

arch/m68k/bvme6000/rtc.c

@@ -18,7 +18,6 @@
 #include <linux/poll.h>
 #include <linux/module.h>
 #include <linux/mc146818rtc.h>	/* For struct rtc_time and ioctls, etc */
-#include <linux/smp_lock.h>
 #include <linux/bcd.h>
 #include <asm/bvme6000hw.h>
 

arch/m68knommu/Kconfig

@@ -75,6 +75,8 @@ config NO_IOPORT
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 menu "Processor type and features"
 
 choice

arch/m68knommu/include/asm/thread_info.h

@@ -84,12 +84,14 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_POLLING_NRFLAG	3	/* true if poll_idle() is polling
 					   TIF_NEED_RESCHED */
 #define TIF_MEMDIE		4
+#define TIF_FREEZE		16	/* is freezing for suspend */
 
 /* as above, but as bit values */
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
 #define _TIF_SIGPENDING		(1<<TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1<<TIF_NEED_RESCHED)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
+#define _TIF_FREEZE		(1<<TIF_FREEZE)
 
 #define _TIF_WORK_MASK		0x0000FFFE	/* work to do on interrupt/exception return */
 

arch/mips/Kconfig

@@ -1885,6 +1885,8 @@ config PROBE_INITRD_HEADER
 	  add initrd or initramfs image to the kernel image.
 	  Otherwise, say N.
 
+source "kernel/Kconfig.freezer"
+
 menu "Bus options (PCI, PCMCIA, EISA, ISA, TC)"
 
 config HW_HAS_EISA

arch/mips/dec/time.c

@@ -45,12 +45,12 @@ unsigned long read_persistent_clock(void)
 	spin_unlock_irqrestore(&rtc_lock, flags);
 
 	if (!(CMOS_READ(RTC_CONTROL) & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
-		sec = BCD2BIN(sec);
+		sec = bcd2bin(sec);
-		min = BCD2BIN(min);
+		min = bcd2bin(min);
-		hour = BCD2BIN(hour);
+		hour = bcd2bin(hour);
-		day = BCD2BIN(day);
+		day = bcd2bin(day);
-		mon = BCD2BIN(mon);
+		mon = bcd2bin(mon);
-		year = BCD2BIN(year);
+		year = bcd2bin(year);
 	}
 
 	year += real_year - 72 + 2000;
@@ -83,7 +83,7 @@ int rtc_mips_set_mmss(unsigned long nowtime)
 
 	cmos_minutes = CMOS_READ(RTC_MINUTES);
 	if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD)
-		cmos_minutes = BCD2BIN(cmos_minutes);
+		cmos_minutes = bcd2bin(cmos_minutes);
 
 	/*
 	 * since we're only adjusting minutes and seconds,
@@ -99,8 +99,8 @@ int rtc_mips_set_mmss(unsigned long nowtime)
 
 	if (abs(real_minutes - cmos_minutes) < 30) {
 		if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
-			real_seconds = BIN2BCD(real_seconds);
+			real_seconds = bin2bcd(real_seconds);
-			real_minutes = BIN2BCD(real_minutes);
+			real_minutes = bin2bcd(real_minutes);
 		}
 		CMOS_WRITE(real_seconds, RTC_SECONDS);
 		CMOS_WRITE(real_minutes, RTC_MINUTES);

arch/mips/include/asm/mc146818-time.h

@@ -44,7 +44,7 @@ static inline int mc146818_set_rtc_mmss(unsigned long nowtime)
 
 	cmos_minutes = CMOS_READ(RTC_MINUTES);
 	if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD)
-		BCD_TO_BIN(cmos_minutes);
+		cmos_minutes = bcd2bin(cmos_minutes);
 
 	/*
 	 * since we're only adjusting minutes and seconds,
@@ -60,8 +60,8 @@ static inline int mc146818_set_rtc_mmss(unsigned long nowtime)
 
 	if (abs(real_minutes - cmos_minutes) < 30) {
 		if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
-			BIN_TO_BCD(real_seconds);
+			real_seconds = bin2bcd(real_seconds);
-			BIN_TO_BCD(real_minutes);
+			real_minutes = bin2bcd(real_minutes);
 		}
 		CMOS_WRITE(real_seconds, RTC_SECONDS);
 		CMOS_WRITE(real_minutes, RTC_MINUTES);
@@ -103,12 +103,12 @@ static inline unsigned long mc146818_get_cmos_time(void)
 	} while (sec != CMOS_READ(RTC_SECONDS));
 
 	if (!(CMOS_READ(RTC_CONTROL) & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
-		BCD_TO_BIN(sec);
+		sec = bcd2bin(sec);
-		BCD_TO_BIN(min);
+		min = bcd2bin(min);
-		BCD_TO_BIN(hour);
+		hour = bcd2bin(hour);
-		BCD_TO_BIN(day);
+		day = bcd2bin(day);
-		BCD_TO_BIN(mon);
+		mon = bcd2bin(mon);
-		BCD_TO_BIN(year);
+		year = bcd2bin(year);
 	}
 	spin_unlock_irqrestore(&rtc_lock, flags);
 	year = mc146818_decode_year(year);

arch/mips/pmc-sierra/yosemite/setup.c

@@ -79,14 +79,14 @@ unsigned long read_persistent_clock(void)
 	/* Stop the update to the time */
 	m48t37_base->control = 0x40;
 
-	year = BCD2BIN(m48t37_base->year);
+	year = bcd2bin(m48t37_base->year);
-	year += BCD2BIN(m48t37_base->century) * 100;
+	year += bcd2bin(m48t37_base->century) * 100;
 
-	month = BCD2BIN(m48t37_base->month);
+	month = bcd2bin(m48t37_base->month);
-	day = BCD2BIN(m48t37_base->date);
+	day = bcd2bin(m48t37_base->date);
-	hour = BCD2BIN(m48t37_base->hour);
+	hour = bcd2bin(m48t37_base->hour);
-	min = BCD2BIN(m48t37_base->min);
+	min = bcd2bin(m48t37_base->min);
-	sec = BCD2BIN(m48t37_base->sec);
+	sec = bcd2bin(m48t37_base->sec);
 
 	/* Start the update to the time again */
 	m48t37_base->control = 0x00;
@@ -113,22 +113,22 @@ int rtc_mips_set_time(unsigned long tim)
 	m48t37_base->control = 0x80;
 
 	/* year */
-	m48t37_base->year = BIN2BCD(tm.tm_year % 100);
+	m48t37_base->year = bin2bcd(tm.tm_year % 100);
-	m48t37_base->century = BIN2BCD(tm.tm_year / 100);
+	m48t37_base->century = bin2bcd(tm.tm_year / 100);
 
 	/* month */
-	m48t37_base->month = BIN2BCD(tm.tm_mon);
+	m48t37_base->month = bin2bcd(tm.tm_mon);
 
 	/* day */
-	m48t37_base->date = BIN2BCD(tm.tm_mday);
+	m48t37_base->date = bin2bcd(tm.tm_mday);
 
 	/* hour/min/sec */
-	m48t37_base->hour = BIN2BCD(tm.tm_hour);
+	m48t37_base->hour = bin2bcd(tm.tm_hour);
-	m48t37_base->min = BIN2BCD(tm.tm_min);
+	m48t37_base->min = bin2bcd(tm.tm_min);
-	m48t37_base->sec = BIN2BCD(tm.tm_sec);
+	m48t37_base->sec = bin2bcd(tm.tm_sec);
 
 	/* day of week -- not really used, but let's keep it up-to-date */
-	m48t37_base->day = BIN2BCD(tm.tm_wday + 1);
+	m48t37_base->day = bin2bcd(tm.tm_wday + 1);
 
 	/* disable writing */
 	m48t37_base->control = 0x00;

arch/mips/sibyte/swarm/rtc_m41t81.c

@@ -156,32 +156,32 @@ int m41t81_set_time(unsigned long t)
 	 */
 
 	spin_lock_irqsave(&rtc_lock, flags);
-	tm.tm_sec = BIN2BCD(tm.tm_sec);
+	tm.tm_sec = bin2bcd(tm.tm_sec);
 	m41t81_write(M41T81REG_SC, tm.tm_sec);
 
-	tm.tm_min = BIN2BCD(tm.tm_min);
+	tm.tm_min = bin2bcd(tm.tm_min);
 	m41t81_write(M41T81REG_MN, tm.tm_min);
 
-	tm.tm_hour = BIN2BCD(tm.tm_hour);
+	tm.tm_hour = bin2bcd(tm.tm_hour);
 	tm.tm_hour = (tm.tm_hour & 0x3f) | (m41t81_read(M41T81REG_HR) & 0xc0);
 	m41t81_write(M41T81REG_HR, tm.tm_hour);
 
 	/* tm_wday starts from 0 to 6 */
 	if (tm.tm_wday == 0) tm.tm_wday = 7;
-	tm.tm_wday = BIN2BCD(tm.tm_wday);
+	tm.tm_wday = bin2bcd(tm.tm_wday);
 	m41t81_write(M41T81REG_DY, tm.tm_wday);
 
-	tm.tm_mday = BIN2BCD(tm.tm_mday);
+	tm.tm_mday = bin2bcd(tm.tm_mday);
 	m41t81_write(M41T81REG_DT, tm.tm_mday);
 
 	/* tm_mon starts from 0, *ick* */
 	tm.tm_mon ++;
-	tm.tm_mon = BIN2BCD(tm.tm_mon);
+	tm.tm_mon = bin2bcd(tm.tm_mon);
 	m41t81_write(M41T81REG_MO, tm.tm_mon);
 
 	/* we don't do century, everything is beyond 2000 */
 	tm.tm_year %= 100;
-	tm.tm_year = BIN2BCD(tm.tm_year);
+	tm.tm_year = bin2bcd(tm.tm_year);
 	m41t81_write(M41T81REG_YR, tm.tm_year);
 	spin_unlock_irqrestore(&rtc_lock, flags);
 
@@ -209,12 +209,12 @@ unsigned long m41t81_get_time(void)
 	year = m41t81_read(M41T81REG_YR);
 	spin_unlock_irqrestore(&rtc_lock, flags);
 
-	sec = BCD2BIN(sec);
+	sec = bcd2bin(sec);
-	min = BCD2BIN(min);
+	min = bcd2bin(min);
-	hour = BCD2BIN(hour);
+	hour = bcd2bin(hour);
-	day = BCD2BIN(day);
+	day = bcd2bin(day);
-	mon = BCD2BIN(mon);
+	mon = bcd2bin(mon);
-	year = BCD2BIN(year);
+	year = bcd2bin(year);
 
 	year += 2000;
 

arch/mips/sibyte/swarm/rtc_xicor1241.c

@@ -124,18 +124,18 @@ int xicor_set_time(unsigned long t)
 	xicor_write(X1241REG_SR, X1241REG_SR_WEL | X1241REG_SR_RWEL);
 
 	/* trivial ones */
-	tm.tm_sec = BIN2BCD(tm.tm_sec);
+	tm.tm_sec = bin2bcd(tm.tm_sec);
 	xicor_write(X1241REG_SC, tm.tm_sec);
 
-	tm.tm_min = BIN2BCD(tm.tm_min);
+	tm.tm_min = bin2bcd(tm.tm_min);
 	xicor_write(X1241REG_MN, tm.tm_min);
 
-	tm.tm_mday = BIN2BCD(tm.tm_mday);
+	tm.tm_mday = bin2bcd(tm.tm_mday);
 	xicor_write(X1241REG_DT, tm.tm_mday);
 
 	/* tm_mon starts from 0, *ick* */
 	tm.tm_mon ++;
-	tm.tm_mon = BIN2BCD(tm.tm_mon);
+	tm.tm_mon = bin2bcd(tm.tm_mon);
 	xicor_write(X1241REG_MO, tm.tm_mon);
 
 	/* year is split */
@@ -148,7 +148,7 @@ int xicor_set_time(unsigned long t)
 	tmp = xicor_read(X1241REG_HR);
 	if (tmp & X1241REG_HR_MIL) {
 		/* 24 hour format */
-		tm.tm_hour = BIN2BCD(tm.tm_hour);
+		tm.tm_hour = bin2bcd(tm.tm_hour);
 		tmp = (tmp & ~0x3f) | (tm.tm_hour & 0x3f);
 	} else {
 		/* 12 hour format, with 0x2 for pm */
@@ -157,7 +157,7 @@ int xicor_set_time(unsigned long t)
 			tmp |= 0x20;
 			tm.tm_hour -= 12;
 		}
-		tm.tm_hour = BIN2BCD(tm.tm_hour);
+		tm.tm_hour = bin2bcd(tm.tm_hour);
 		tmp |= tm.tm_hour;
 	}
 	xicor_write(X1241REG_HR, tmp);
@@ -191,13 +191,13 @@ unsigned long xicor_get_time(void)
 	y2k = xicor_read(X1241REG_Y2K);
 	spin_unlock_irqrestore(&rtc_lock, flags);
 
-	sec = BCD2BIN(sec);
+	sec = bcd2bin(sec);
-	min = BCD2BIN(min);
+	min = bcd2bin(min);
-	hour = BCD2BIN(hour);
+	hour = bcd2bin(hour);
-	day = BCD2BIN(day);
+	day = bcd2bin(day);
-	mon = BCD2BIN(mon);
+	mon = bcd2bin(mon);
-	year = BCD2BIN(year);
+	year = bcd2bin(year);
-	y2k = BCD2BIN(y2k);
+	y2k = bcd2bin(y2k);
 
 	year += (y2k * 100);
 

arch/mn10300/Kconfig

@@ -68,6 +68,8 @@ mainmenu "Matsushita MN10300/AM33 Kernel Configuration"
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 
 menu "Matsushita MN10300 system setup"
 

arch/mn10300/kernel/rtc.c

@@ -67,7 +67,7 @@ static int set_rtc_mmss(unsigned long nowtime)
 
 	cmos_minutes = CMOS_READ(RTC_MINUTES);
 	if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD)
-		BCD_TO_BIN(cmos_minutes);
+		cmos_minutes = bcd2bin(cmos_minutes);
 
 	/*
 	 * since we're only adjusting minutes and seconds,
@@ -84,8 +84,8 @@ static int set_rtc_mmss(unsigned long nowtime)
 
 	if (abs(real_minutes - cmos_minutes) < 30) {
 		if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
-			BIN_TO_BCD(real_seconds);
+			real_seconds = bin2bcd(real_seconds);
-			BIN_TO_BCD(real_minutes);
+			real_minutes = bin2bcd(real_minutes);
 		}
 		CMOS_WRITE(real_seconds, RTC_SECONDS);
 		CMOS_WRITE(real_minutes, RTC_MINUTES);

arch/parisc/Kconfig

@@ -9,6 +9,8 @@ config PARISC
 	def_bool y
 	select HAVE_IDE
 	select HAVE_OPROFILE
+	select RTC_CLASS
+	select RTC_DRV_PARISC
 	help
 	  The PA-RISC microprocessor is designed by Hewlett-Packard and used
 	  in many of their workstations & servers (HP9000 700 and 800 series,
@@ -90,6 +92,8 @@ config ARCH_MAY_HAVE_PC_FDC
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 
 menu "Processor type and features"