Merge 3.1-rc1 into usb-linus

Gives us a good starting point to base patches off of. Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-08-07 21:08:28 -07:00 · 2011-08-07 21:08:28 -07:00 · b6741d1fe9
parent acab460b0f 322a8b0340
commit b6741d1fe9
604 changed files with 14798 additions and 7933 deletions
--- a/Documentation/ABI/testing/pstore
+++ b/Documentation/ABI/testing/pstore
@ -39,3 +39,9 @@ Description:	Generic interface to platform dependent persistent storage.
 		multiple) files based on the record size of the underlying
 		persistent storage until at least this amount is reached.
 		Default is 10 Kbytes.
+
+		Pstore only supports one backend at a time. If multiple
+		backends are available, the preferred backend may be
+		set by passing the pstore.backend= argument to the kernel at
+		boot time.
+
--- a/Documentation/ABI/testing/sysfs-platform-ideapad-laptop
+++ b/Documentation/ABI/testing/sysfs-platform-ideapad-laptop
@ -4,3 +4,20 @@ KernelVersion:	2.6.37
 Contact:	"Ike Panhc <ike.pan@canonical.com>"
 Description:
 		Control the power of camera module. 1 means on, 0 means off.
+
+What:		/sys/devices/platform/ideapad/cfg
+Date:		Jun 2011
+KernelVersion:	3.1
+Contact:	"Ike Panhc <ike.pan@canonical.com>"
+Description:
+		Ideapad capability bits.
+		Bit 8-10: 1 - Intel graphic only
+		          2 - ATI graphic only
+		          3 - Nvidia graphic only
+		          4 - Intel and ATI graphic
+		          5 - Intel and Nvidia graphic
+		Bit 16: Bluetooth exist (1 for exist)
+		Bit 17: 3G exist (1 for exist)
+		Bit 18: Wifi exist (1 for exist)
+		Bit 19: Camera exist (1 for exist)
+
--- a/Documentation/CodingStyle
+++ b/Documentation/CodingStyle
@ -80,22 +80,13 @@ available tools.
 The limit on the length of lines is 80 columns and this is a strongly
 preferred limit.

-Statements longer than 80 columns will be broken into sensible chunks.
-Descendants are always substantially shorter than the parent and are placed
-substantially to the right. The same applies to function headers with a long
-argument list. Long strings are as well broken into shorter strings. The
-only exception to this is where exceeding 80 columns significantly increases
-readability and does not hide information.
+Statements longer than 80 columns will be broken into sensible chunks, unless
+exceeding 80 columns significantly increases readability and does not hide
+information. Descendants are always substantially shorter than the parent and
+are placed substantially to the right. The same applies to function headers
+with a long argument list. However, never break user-visible strings such as
+printk messages, because that breaks the ability to grep for them.

-void fun(int a, int b, int c)
-{
-	if (condition)
-		printk(KERN_WARNING "Warning this is a long printk with "
-						"3 parameters a: %u b: %u "
-						"c: %u \n", a, b, c);
-	else
-		next_statement;
-}

 		Chapter 3: Placing Braces and Spaces

--- a/Documentation/acpi/apei/einj.txt
+++ b/Documentation/acpi/apei/einj.txt
@ -48,12 +48,19 @@ directory apei/einj. The following files are provided.
 - param1
  This file is used to set the first error parameter value. Effect of
  parameter depends on error_type specified. For memory error, this is
-  physical memory address.
+  physical memory address.  Only available if param_extension module
+  parameter is specified.

 - param2
  This file is used to set the second error parameter value. Effect of
  parameter depends on error_type specified. For memory error, this is
-  physical memory address mask.
+  physical memory address mask.  Only available if param_extension
+  module parameter is specified.
+
+Injecting parameter support is a BIOS version specific extension, that
+is, it only works on some BIOS version.  If you want to use it, please
+make sure your BIOS version has the proper support and specify
+"param_extension=y" in module parameter.

 For more information about EINJ, please refer to ACPI specification
 version 4.0, section 17.5.
--- a/Documentation/device-mapper/dm-crypt.txt
+++ b/Documentation/device-mapper/dm-crypt.txt
@ -4,7 +4,8 @@ dm-crypt
 Device-Mapper's "crypt" target provides transparent encryption of block devices
 using the kernel crypto API.

-Parameters: <cipher> <key> <iv_offset> <device path> <offset>
+Parameters: <cipher> <key> <iv_offset> <device path> \
+	      <offset> [<#opt_params> <opt_params>]

 <cipher>
    Encryption cipher and an optional IV generation mode.
@ -37,6 +38,24 @@ Parameters: <cipher> <key> <iv_offset> <device path> <offset>
 <offset>
    Starting sector within the device where the encrypted data begins.

+<#opt_params>
+    Number of optional parameters. If there are no optional parameters,
+    the optional paramaters section can be skipped or #opt_params can be zero.
+    Otherwise #opt_params is the number of following arguments.
+
+    Example of optional parameters section:
+        1 allow_discards
+
+allow_discards
+    Block discard requests (a.k.a. TRIM) are passed through the crypt device.
+    The default is to ignore discard requests.
+
+    WARNING: Assess the specific security risks carefully before enabling this
+    option.  For example, allowing discards on encrypted devices may lead to
+    the leak of information about the ciphertext device (filesystem type,
+    used space etc.) if the discarded blocks can be located easily on the
+    device later.
+
 Example scripts
 ===============
 LUKS (Linux Unified Key Setup) is now the preferred way to set up disk
--- a/Documentation/device-mapper/dm-flakey.txt
+++ b/Documentation/device-mapper/dm-flakey.txt
@ -1,17 +1,53 @@
 dm-flakey
 =========

-This target is the same as the linear target except that it returns I/O
-errors periodically.  It's been found useful in simulating failing
-devices for testing purposes.
+This target is the same as the linear target except that it exhibits
+unreliable behaviour periodically.  It's been found useful in simulating
+failing devices for testing purposes.

 Starting from the time the table is loaded, the device is available for
-<up interval> seconds, then returns errors for <down interval> seconds,
-and then this cycle repeats.
+<up interval> seconds, then exhibits unreliable behaviour for <down
+interval> seconds, and then this cycle repeats.

-Parameters: <dev path> <offset> <up interval> <down interval>
+Also, consider using this in combination with the dm-delay target too,
+which can delay reads and writes and/or send them to different
+underlying devices.
+
+Table parameters
+----------------
+  <dev path> <offset> <up interval> <down interval> \
+    [<num_features> [<feature arguments>]]
+
+Mandatory parameters:
    <dev path>: Full pathname to the underlying block-device, or a
                "major:minor" device-number.
    <offset>: Starting sector within the device.
    <up interval>: Number of seconds device is available.
    <down interval>: Number of seconds device returns errors.
+
+Optional feature parameters:
+  If no feature parameters are present, during the periods of
+  unreliability, all I/O returns errors.
+
+  drop_writes:
+	All write I/O is silently ignored.
+	Read I/O is handled correctly.
+
+  corrupt_bio_byte <Nth_byte> <direction> <value> <flags>:
+	During <down interval>, replace <Nth_byte> of the data of
+	each matching bio with <value>.
+
+    <Nth_byte>: The offset of the byte to replace.
+		Counting starts at 1, to replace the first byte.
+    <direction>: Either 'r' to corrupt reads or 'w' to corrupt writes.
+		 'w' is incompatible with drop_writes.
+    <value>: The value (from 0-255) to write.
+    <flags>: Perform the replacement only if bio->bi_rw has all the
+	     selected flags set.
+
+Examples:
+  corrupt_bio_byte 32 r 1 0
+	- replaces the 32nd byte of READ bios with the value 1
+
+  corrupt_bio_byte 224 w 0 32
+	- replaces the 224th byte of REQ_META (=32) bios with the value 0
--- a/Documentation/device-mapper/dm-raid.txt
+++ b/Documentation/device-mapper/dm-raid.txt
@ -1,70 +1,108 @@
-Device-mapper RAID (dm-raid) is a bridge from DM to MD.  It
-provides a way to use device-mapper interfaces to access the MD RAID
-drivers.
+dm-raid
+-------

-As with all device-mapper targets, the nominal public interfaces are the
-constructor (CTR) tables and the status outputs (both STATUSTYPE_INFO
-and STATUSTYPE_TABLE).  The CTR table looks like the following:
+The device-mapper RAID (dm-raid) target provides a bridge from DM to MD.
+It allows the MD RAID drivers to be accessed using a device-mapper
+interface.

-1: <s> <l> raid \
-2:      <raid_type> <#raid_params> <raid_params> \
-3:      <#raid_devs> <meta_dev1> <dev1> .. <meta_devN> <devN>
+The target is named "raid" and it accepts the following parameters:

-Line 1 contains the standard first three arguments to any device-mapper
-target - the start, length, and target type fields.  The target type in
-this case is "raid".
+  <raid_type> <#raid_params> <raid_params> \
+    <#raid_devs> <metadata_dev0> <dev0> [.. <metadata_devN> <devN>]

-Line 2 contains the arguments that define the particular raid
-type/personality/level, the required arguments for that raid type, and
-any optional arguments.  Possible raid types include: raid4, raid5_la,
-raid5_ls, raid5_rs, raid6_zr, raid6_nr, and raid6_nc.  (raid1 is
-planned for the future.)  The list of required and optional parameters
-is the same for all the current raid types.  The required parameters are
-positional, while the optional parameters are given as key/value pairs.
-The possible parameters are as follows:
- <chunk_size>           Chunk size in sectors.
- [[no]sync]             Force/Prevent RAID initialization
- [rebuild <idx>]        Rebuild the drive indicated by the index
- [daemon_sleep <ms>]    Time between bitmap daemon work to clear bits
- [min_recovery_rate <kB/sec/disk>]      Throttle RAID initialization
- [max_recovery_rate <kB/sec/disk>]      Throttle RAID initialization
- [max_write_behind <sectors>]           See '-write-behind=' (man mdadm)
- [stripe_cache <sectors>]               Stripe cache size for higher RAIDs
+<raid_type>:
+  raid1		RAID1 mirroring
+  raid4		RAID4 dedicated parity disk
+  raid5_la	RAID5 left asymmetric
+		- rotating parity 0 with data continuation
+  raid5_ra	RAID5 right asymmetric
+		- rotating parity N with data continuation
+  raid5_ls	RAID5 left symmetric
+		- rotating parity 0 with data restart
+  raid5_rs 	RAID5 right symmetric
+		- rotating parity N with data restart
+  raid6_zr	RAID6 zero restart
+		- rotating parity zero (left-to-right) with data restart
+  raid6_nr	RAID6 N restart
+		- rotating parity N (right-to-left) with data restart
+  raid6_nc	RAID6 N continue
+		- rotating parity N (right-to-left) with data continuation

-Line 3 contains the list of devices that compose the array in
-metadata/data device pairs.  If the metadata is stored separately, a '-'
-is given for the metadata device position.  If a drive has failed or is
-missing at creation time, a '-' can be given for both the metadata and
-data drives for a given position.
+  Refererence: Chapter 4 of
+  http://www.snia.org/sites/default/files/SNIA_DDF_Technical_Position_v2.0.pdf

-NB. Currently all metadata devices must be specified as '-'.
+<#raid_params>: The number of parameters that follow.

-Examples:
-# RAID4 - 4 data drives, 1 parity
+<raid_params> consists of
+    Mandatory parameters:
+        <chunk_size>: Chunk size in sectors.  This parameter is often known as
+		      "stripe size".  It is the only mandatory parameter and
+		      is placed first.
+
+    followed by optional parameters (in any order):
+	[sync|nosync]   Force or prevent RAID initialization.
+
+	[rebuild <idx>]	Rebuild drive number idx (first drive is 0).
+
+	[daemon_sleep <ms>]
+		Interval between runs of the bitmap daemon that
+		clear bits.  A longer interval means less bitmap I/O but
+		resyncing after a failure is likely to take longer.
+
+	[min_recovery_rate <kB/sec/disk>]  Throttle RAID initialization
+	[max_recovery_rate <kB/sec/disk>]  Throttle RAID initialization
+	[write_mostly <idx>]		   Drive index is write-mostly
+	[max_write_behind <sectors>]       See '-write-behind=' (man mdadm)
+	[stripe_cache <sectors>]           Stripe cache size (higher RAIDs only)
+	[region_size <sectors>]
+		The region_size multiplied by the number of regions is the
+		logical size of the array.  The bitmap records the device
+		synchronisation state for each region.
+
+<#raid_devs>: The number of devices composing the array.
+	Each device consists of two entries.  The first is the device
+	containing the metadata (if any); the second is the one containing the
+	data.
+
+	If a drive has failed or is missing at creation time, a '-' can be
+	given for both the metadata and data drives for a given position.
+
+
+Example tables
+--------------
+# RAID4 - 4 data drives, 1 parity (no metadata devices)
 # No metadata devices specified to hold superblock/bitmap info
 # Chunk size of 1MiB
 # (Lines separated for easy reading)
+
 0 1960893648 raid \
        raid4 1 2048 \
        5 - 8:17 - 8:33 - 8:49 - 8:65 - 8:81

-# RAID4 - 4 data drives, 1 parity (no metadata devices)
+# RAID4 - 4 data drives, 1 parity (with metadata devices)
 # Chunk size of 1MiB, force RAID initialization,
 #       min recovery rate at 20 kiB/sec/disk
+
 0 1960893648 raid \
-        raid4 4 2048 min_recovery_rate 20 sync\
-        5 - 8:17 - 8:33 - 8:49 - 8:65 - 8:81
+        raid4 4 2048 sync min_recovery_rate 20 \
+        5 8:17 8:18 8:33 8:34 8:49 8:50 8:65 8:66 8:81 8:82

-Performing a 'dmsetup table' should display the CTR table used to
-construct the mapping (with possible reordering of optional
-parameters).
+'dmsetup table' displays the table used to construct the mapping.
+The optional parameters are always printed in the order listed
+above with "sync" or "nosync" always output ahead of the other
+arguments, regardless of the order used when originally loading the table.
+Arguments that can be repeated are ordered by value.

-Performing a 'dmsetup status' will yield information on the state and
-health of the array.  The output is as follows:
+'dmsetup status' yields information on the state and health of the
+array.
+The output is as follows:
 1: <s> <l> raid \
 2:      <raid_type> <#devices> <1 health char for each dev> <resync_ratio>

-Line 1 is standard DM output.  Line 2 is best shown by example:
+Line 1 is the standard output produced by device-mapper.
+Line 2 is produced by the raid target, and best explained by example:
        0 1960893648 raid raid4 5 AAAAA 2/490221568
 Here we can see the RAID type is raid4, there are 5 devices - all of
 which are 'A'live, and the array is 2/490221568 complete with recovery.
+Faulty or missing devices are marked 'D'.  Devices that are out-of-sync
+are marked 'a'.
--- a/Documentation/devicetree/bindings/gpio/gpio_keys.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio_keys.txt
@ -10,7 +10,7 @@ Optional properties:
 Each button (key) is represented as a sub-node of "gpio-keys":
 Subnode properties:

-	- gpios: OF devcie-tree gpio specificatin.
+	- gpios: OF device-tree gpio specification.
 	- label: Descriptive name of the key.
 	- linux,code: Keycode to emit.

--- a/Documentation/devicetree/bindings/input/fsl-mma8450.txt
+++ b/Documentation/devicetree/bindings/input/fsl-mma8450.txt
@ -0,0 +1,11 @@
+* Freescale MMA8450 3-Axis Accelerometer
+
+Required properties:
+- compatible : "fsl,mma8450".
+
+Example:
+
+accelerometer: mma8450@1c {
+	compatible = "fsl,mma8450";
+	reg = <0x1c>;
+};
--- a/Documentation/dmaengine.txt
+++ b/Documentation/dmaengine.txt
@ -10,87 +10,181 @@ NOTE: For DMA Engine usage in async_tx please see:
 Below is a guide to device driver writers on how to use the Slave-DMA API of the
 DMA Engine. This is applicable only for slave DMA usage only.

-The slave DMA usage consists of following steps
+The slave DMA usage consists of following steps:
 1. Allocate a DMA slave channel
 2. Set slave and controller specific parameters
 3. Get a descriptor for transaction
-4. Submit the transaction and wait for callback notification
+4. Submit the transaction
+5. Issue pending requests and wait for callback notification

 1. Allocate a DMA slave channel
-Channel allocation is slightly different in the slave DMA context, client
-drivers typically need a channel from a particular DMA controller only and even
-in some cases a specific channel is desired. To request a channel
-dma_request_channel() API is used.

-Interface:
-struct dma_chan *dma_request_channel(dma_cap_mask_t mask,
-		dma_filter_fn filter_fn,
-		void *filter_param);
-where dma_filter_fn is defined as:
-typedef bool (*dma_filter_fn)(struct dma_chan *chan, void *filter_param);
+   Channel allocation is slightly different in the slave DMA context,
+   client drivers typically need a channel from a particular DMA
+   controller only and even in some cases a specific channel is desired.
+   To request a channel dma_request_channel() API is used.

-When the optional 'filter_fn' parameter is set to NULL dma_request_channel
-simply returns the first channel that satisfies the capability mask.  Otherwise,
-when the mask parameter is insufficient for specifying the necessary channel,
-the filter_fn routine can be used to disposition the available channels in the
-system. The filter_fn routine is called once for each free channel in the
-system.  Upon seeing a suitable channel filter_fn returns DMA_ACK which flags
-that channel to be the return value from dma_request_channel.  A channel
-allocated via this interface is exclusive to the caller, until
-dma_release_channel() is called.
+   Interface:
+	struct dma_chan *dma_request_channel(dma_cap_mask_t mask,
+			dma_filter_fn filter_fn,
+			void *filter_param);
+   where dma_filter_fn is defined as:
+	typedef bool (*dma_filter_fn)(struct dma_chan *chan, void *filter_param);
+
+   The 'filter_fn' parameter is optional, but highly recommended for
+   slave and cyclic channels as they typically need to obtain a specific
+   DMA channel.
+
+   When the optional 'filter_fn' parameter is NULL, dma_request_channel()
+   simply returns the first channel that satisfies the capability mask.
+
+   Otherwise, the 'filter_fn' routine will be called once for each free
+   channel which has a capability in 'mask'.  'filter_fn' is expected to
+   return 'true' when the desired DMA channel is found.
+
+   A channel allocated via this interface is exclusive to the caller,
+   until dma_release_channel() is called.

 2. Set slave and controller specific parameters
-Next step is always to pass some specific information to the DMA driver. Most of
-the generic information which a slave DMA can use is in struct dma_slave_config.
-It allows the clients to specify DMA direction, DMA addresses, bus widths, DMA
-burst lengths etc. If some DMA controllers have more parameters to be sent then
-they should try to embed struct dma_slave_config in their controller specific
-structure. That gives flexibility to client to pass more parameters, if
-required.

-Interface:
-int dmaengine_slave_config(struct dma_chan *chan,
-					  struct dma_slave_config *config)
+   Next step is always to pass some specific information to the DMA
+   driver.  Most of the generic information which a slave DMA can use
+   is in struct dma_slave_config.  This allows the clients to specify
+   DMA direction, DMA addresses, bus widths, DMA burst lengths etc
+   for the peripheral.
+
+   If some DMA controllers have more parameters to be sent then they
+   should try to embed struct dma_slave_config in their controller
+   specific structure. That gives flexibility to client to pass more
+   parameters, if required.
+
+   Interface:
+	int dmaengine_slave_config(struct dma_chan *chan,
+				  struct dma_slave_config *config)
+
+   Please see the dma_slave_config structure definition in dmaengine.h
+   for a detailed explaination of the struct members.  Please note
+   that the 'direction' member will be going away as it duplicates the
+   direction given in the prepare call.

 3. Get a descriptor for transaction
-For slave usage the various modes of slave transfers supported by the
-DMA-engine are:
-slave_sg	- DMA a list of scatter gather buffers from/to a peripheral
-dma_cyclic	- Perform a cyclic DMA operation from/to a peripheral till the
+
+   For slave usage the various modes of slave transfers supported by the
+   DMA-engine are:
+
+   slave_sg	- DMA a list of scatter gather buffers from/to a peripheral
+   dma_cyclic	- Perform a cyclic DMA operation from/to a peripheral till the
 		  operation is explicitly stopped.
-The non NULL return of this transfer API represents a "descriptor" for the given
-transaction.

-Interface:
-struct dma_async_tx_descriptor *(*chan->device->device_prep_dma_sg)(
-		struct dma_chan *chan,
-		struct scatterlist *dst_sg, unsigned int dst_nents,
-		struct scatterlist *src_sg, unsigned int src_nents,
+   A non-NULL return of this transfer API represents a "descriptor" for
+   the given transaction.
+
+   Interface:
+	struct dma_async_tx_descriptor *(*chan->device->device_prep_slave_sg)(
+		struct dma_chan *chan, struct scatterlist *sgl,
+		unsigned int sg_len, enum dma_data_direction direction,
 		unsigned long flags);
-struct dma_async_tx_descriptor *(*chan->device->device_prep_dma_cyclic)(
+
+	struct dma_async_tx_descriptor *(*chan->device->device_prep_dma_cyclic)(
 		struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
 		size_t period_len, enum dma_data_direction direction);

-4. Submit the transaction and wait for callback notification
-To schedule the transaction to be scheduled by dma device, the "descriptor"
-returned in above (3) needs to be submitted.
-To tell the dma driver that a transaction is ready to be serviced, the
-descriptor->submit() callback needs to be invoked. This chains the descriptor to
-the pending queue.
-The transactions in the pending queue can be activated by calling the
-issue_pending API. If channel is idle then the first transaction in queue is
-started and subsequent ones queued up.
-On completion of the DMA operation the next in queue is submitted and a tasklet
-triggered. The tasklet would then call the client driver completion callback
-routine for notification, if set.
-Interface:
-void dma_async_issue_pending(struct dma_chan *chan);
+   The peripheral driver is expected to have mapped the scatterlist for
+   the DMA operation prior to calling device_prep_slave_sg, and must
+   keep the scatterlist mapped until the DMA operation has completed.
+   The scatterlist must be mapped using the DMA struct device.  So,
+   normal setup should look like this:

-==============================================================================
+	nr_sg = dma_map_sg(chan->device->dev, sgl, sg_len);
+	if (nr_sg == 0)
+		/* error */

-Additional usage notes for dma driver writers
-1/ Although DMA engine specifies that completion callback routines cannot submit
-any new operations, but typically for slave DMA subsequent transaction may not
-be available for submit prior to callback routine being called. This requirement
-is not a requirement for DMA-slave devices. But they should take care to drop
-the spin-lock they might be holding before calling the callback routine
+	desc = chan->device->device_prep_slave_sg(chan, sgl, nr_sg,
+			direction, flags);
+
+   Once a descriptor has been obtained, the callback information can be
+   added and the descriptor must then be submitted.  Some DMA engine
+   drivers may hold a spinlock between a successful preparation and
+   submission so it is important that these two operations are closely
+   paired.
+
+   Note:
+	Although the async_tx API specifies that completion callback
+	routines cannot submit any new operations, this is not the
+	case for slave/cyclic DMA.
+
+	For slave DMA, the subsequent transaction may not be available
+	for submission prior to callback function being invoked, so
+	slave DMA callbacks are permitted to prepare and submit a new
+	transaction.
+
+	For cyclic DMA, a callback function may wish to terminate the
+	DMA via dmaengine_terminate_all().
+
+	Therefore, it is important that DMA engine drivers drop any
+	locks before calling the callback function which may cause a
+	deadlock.
+
+	Note that callbacks will always be invoked from the DMA
+	engines tasklet, never from interrupt context.
+
+4. Submit the transaction
+
+   Once the descriptor has been prepared and the callback information
+   added, it must be placed on the DMA engine drivers pending queue.
+
+   Interface:
+	dma_cookie_t dmaengine_submit(struct dma_async_tx_descriptor *desc)
+
+   This returns a cookie can be used to check the progress of DMA engine
+   activity via other DMA engine calls not covered in this document.
+
+   dmaengine_submit() will not start the DMA operation, it merely adds
+   it to the pending queue.  For this, see step 5, dma_async_issue_pending.
+
+5. Issue pending DMA requests and wait for callback notification
+
+   The transactions in the pending queue can be activated by calling the
+   issue_pending API. If channel is idle then the first transaction in
+   queue is started and subsequent ones queued up.
+
+   On completion of each DMA operation, the next in queue is started and
+   a tasklet triggered. The tasklet will then call the client driver
+   completion callback routine for notification, if set.
+
+   Interface:
+	void dma_async_issue_pending(struct dma_chan *chan);
+
+Further APIs:
+
+1. int dmaengine_terminate_all(struct dma_chan *chan)
+
+   This causes all activity for the DMA channel to be stopped, and may
+   discard data in the DMA FIFO which hasn't been fully transferred.
+   No callback functions will be called for any incomplete transfers.
+
+2. int dmaengine_pause(struct dma_chan *chan)
+
+   This pauses activity on the DMA channel without data loss.
+
+3. int dmaengine_resume(struct dma_chan *chan)
+
+   Resume a previously paused DMA channel.  It is invalid to resume a
+   channel which is not currently paused.
+
+4. enum dma_status dma_async_is_tx_complete(struct dma_chan *chan,
+        dma_cookie_t cookie, dma_cookie_t *last, dma_cookie_t *used)
+
+   This can be used to check the status of the channel.  Please see
+   the documentation in include/linux/dmaengine.h for a more complete
+   description of this API.
+
+   This can be used in conjunction with dma_async_is_complete() and
+   the cookie returned from 'descriptor->submit()' to check for
+   completion of a specific DMA transaction.
+
+   Note:
+	Not all DMA engine drivers can return reliable information for
+	a running DMA channel.  It is recommended that DMA engine users
+	pause or stop (via dmaengine_terminate_all) the channel before
+	using this API.
--- a/Documentation/fault-injection/fault-injection.txt
+++ b/Documentation/fault-injection/fault-injection.txt
@ -143,8 +143,7 @@ o provide a way to configure fault attributes
  failslab, fail_page_alloc, and fail_make_request use this way.
  Helper functions:

-	init_fault_attr_dentries(entries, attr, name);
-	void cleanup_fault_attr_dentries(entries);
+	fault_create_debugfs_attr(name, parent, attr);

 - module parameters

--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@ -296,15 +296,6 @@ Who:	Ravikiran Thirumalai <kiran@scalex86.org>

 ---------------------------

-What:	CONFIG_THERMAL_HWMON
-When:	January 2009
-Why:	This option was introduced just to allow older lm-sensors userspace
-	to keep working over the upgrade to 2.6.26. At the scheduled time of
-	removal fixed lm-sensors (2.x or 3.x) should be readily available.
-Who:	Rene Herman <rene.herman@gmail.com>
-
---------------------------
-
 What:	Code that is now under CONFIG_WIRELESS_EXT_SYSFS
 	(in net/core/net-sysfs.c)
 When:	After the only user (hal) has seen a release with the patches
@ -590,3 +581,14 @@ Why:	This driver has been superseded by g_mass_storage.
 Who:	Alan Stern <stern@rowland.harvard.edu>

 ----------------------------
+
+What:   threeg and interface sysfs files in /sys/devices/platform/acer-wmi
+When:   2012
+Why:    In 3.0, we can now autodetect internal 3G device and already have
+	the threeg rfkill device. So, we plan to remove threeg sysfs support
+	for it's no longer necessary.
+
+	We also plan to remove interface sysfs file that exposed which ACPI-WMI
+	interface that was used by acer-wmi driver. It will replaced by
+	information log when acer-wmi initial.
+Who:    Lee, Chun-Yi <jlee@novell.com>
--- a/Documentation/frv/booting.txt
+++ b/Documentation/frv/booting.txt
@ -106,13 +106,20 @@ separated by spaces:
      To use the first on-chip serial port at baud rate 115200, no parity, 8
      bits, and no flow control.

-  (*) root=/dev/<xxxx>
+  (*) root=<xxxx>

-      This specifies the device upon which the root filesystem resides. For
-      example:
+      This specifies the device upon which the root filesystem resides. It
+      may be specified by major and minor number, device path, or even
+      partition uuid, if supported.  For example:

 	/dev/nfs	NFS root filesystem
 	/dev/mtdblock3	Fourth RedBoot partition on the System Flash
+	PARTUUID=00112233-4455-6677-8899-AABBCCDDEEFF/PARTNROFF=1
+		first partition after the partition with the given UUID
+	253:0		Device with major 253 and minor 0
+
+      Authoritative information can be found in
+      "Documentation/kernel-parameters.txt".

  (*) rw

--- a/Documentation/ioctl/ioctl-number.txt
+++ b/Documentation/ioctl/ioctl-number.txt
@ -292,6 +292,7 @@ Code  Seq#(hex)	Include File		Comments
 					<mailto:buk@buks.ipn.de>
 0xA0	all	linux/sdp/sdp.h		Industrial Device Project
 					<mailto:kenji@bitgate.com>
+0xA2	00-0F	arch/tile/include/asm/hardwall.h
 0xA3	80-8F	Port ACL		in development:
 					<mailto:tlewis@mindspring.com>
 0xA3	90-9F	linux/dtlk.h
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@ -163,6 +163,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted.

 			See also Documentation/power/pm.txt, pci=noacpi

+	acpi_rsdp=	[ACPI,EFI,KEXEC]
+			Pass the RSDP address to the kernel, mostly used
+			on machines running EFI runtime service to boot the
+			second kernel for kdump.
+
 	acpi_apic_instance=	[ACPI, IOAPIC]
 			Format: <int>
 			2: use 2nd APIC table, if available
@ -546,6 +551,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			/proc/<pid>/coredump_filter.
 			See also Documentation/filesystems/proc.txt.

+	cpuidle.off=1	[CPU_IDLE]
+			disable the cpuidle sub-system
+
 	cpcihp_generic=	[HW,PCI] Generic port I/O CompactPCI driver
 			Format:
 			<first_slot>,<last_slot>,<port>,<enum_bit>[,<debug>]
@ -2153,6 +2161,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			[HW,MOUSE] Controls Logitech smartscroll autorepeat.
 			0 = disabled, 1 = enabled (default).

+	pstore.backend=	Specify the name of the pstore backend to use
+
 	pt.		[PARIDE]
 			See Documentation/blockdev/paride.txt.

@ -2238,6 +2248,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	ro		[KNL] Mount root device read-only on boot

 	root=		[KNL] Root filesystem
+			See name_to_dev_t comment in init/do_mounts.c.

 	rootdelay=	[KNL] Delay (in seconds) to pause before attempting to
 			mount the root filesystem
--- a/Documentation/m68k/kernel-options.txt
+++ b/Documentation/m68k/kernel-options.txt
@ -129,6 +129,20 @@ decimal 11 is the major of SCSI CD-ROMs, and the minor 0 stands for
 the first of these. You can find out all valid major numbers by
 looking into include/linux/major.h.

+In addition to major and minor numbers, if the device containing your
+root partition uses a partition table format with unique partition
+identifiers, then you may use them.  For instance,
+"root=PARTUUID=00112233-4455-6677-8899-AABBCCDDEEFF".  It is also
+possible to reference another partition on the same device using a
+known partition UUID as the starting point.  For example,
+if partition 5 of the device has the UUID of
+00112233-4455-6677-8899-AABBCCDDEEFF then partition 3 may be found as
+follows:
+  PARTUUID=00112233-4455-6677-8899-AABBCCDDEEFF/PARTNROFF=-2
+
+Authoritative information can be found in
+"Documentation/kernel-parameters.txt".
+

 2.2) ro, rw
 -----------
--- a/Documentation/networking/bonding.txt
+++ b/Documentation/networking/bonding.txt
@ -599,7 +599,7 @@ num_unsol_na
 	affect only the active-backup mode.  These options were added for
 	bonding versions 3.3.0 and 3.4.0 respectively.

-	From Linux 2.6.40 and bonding version 3.7.1, these notifications
+	From Linux 3.0 and bonding version 3.7.1, these notifications
 	are generated by the ipv4 and ipv6 code and the numbers of
 	repetitions cannot be set independently.

--- a/Documentation/power/runtime_pm.txt
+++ b/Documentation/power/runtime_pm.txt
@ -54,11 +54,10 @@ referred to as subsystem-level callbacks in what follows.
 By default, the callbacks are always invoked in process context with interrupts
 enabled.  However, subsystems can use the pm_runtime_irq_safe() helper function
 to tell the PM core that a device's ->runtime_suspend() and ->runtime_resume()
-callbacks should be invoked in atomic context with interrupts disabled
-(->runtime_idle() is still invoked the default way).  This implies that these
-callback routines must not block or sleep, but it also means that the
-synchronous helper functions listed at the end of Section 4 can be used within
-an interrupt handler or in an atomic context.
+callbacks should be invoked in atomic context with interrupts disabled.
+This implies that these callback routines must not block or sleep, but it also
+means that the synchronous helper functions listed at the end of Section 4 can
+be used within an interrupt handler or in an atomic context.

 The subsystem-level suspend callback is _entirely_ _responsible_ for handling
 the suspend of the device as appropriate, which may, but need not include
@ -483,6 +482,7 @@ pm_runtime_suspend()
 pm_runtime_autosuspend()
 pm_runtime_resume()
 pm_runtime_get_sync()
+pm_runtime_put_sync()
 pm_runtime_put_sync_suspend()

 5. Runtime PM Initialization, Device Probing and Removal
--- a/18
+++ b/18
@ -2643,9 +2643,8 @@ S:	Maintained
 F:	arch/x86/math-emu/

 FRAME RELAY DLCI/FRAD (Sangoma drivers too)
-M:	Mike McLagan <mike.mclagan@linux.org>
 L:	netdev@vger.kernel.org
-S:	Maintained
+S:	Orphan
 F:	drivers/net/wan/dlci.c
 F:	drivers/net/wan/sdla.c

@ -3367,6 +3366,12 @@ F:	drivers/net/ixgb/
 F:	drivers/net/ixgbe/
 F:	drivers/net/ixgbevf/

+INTEL MRST PMU DRIVER
+M:	Len Brown <len.brown@intel.com>
+L:	linux-pm@lists.linux-foundation.org
+S:	Supported
+F:	arch/x86/platform/mrst/pmu.*
+
 INTEL PRO/WIRELESS 2100 NETWORK CONNECTION SUPPORT
 L:	linux-wireless@vger.kernel.org
 S:	Orphan
@ -4409,10 +4414,10 @@ F:	net/*/netfilter/
 F:	net/netfilter/

 NETLABEL
-M:	Paul Moore <paul.moore@hp.com>
+M:	Paul Moore <paul@paul-moore.com>
 W:	http://netlabel.sf.net
 L:	netdev@vger.kernel.org
-S:	Supported
+S:	Maintained
 F:	Documentation/netlabel/
 F:	include/net/netlabel.h
 F:	net/netlabel/
@ -4457,7 +4462,6 @@ F:	include/linux/netdevice.h
 NETWORKING [IPv4/IPv6]
 M:	"David S. Miller" <davem@davemloft.net>
 M:	Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
-M:	"Pekka Savola (ipv6)" <pekkas@netcore.fi>
 M:	James Morris <jmorris@namei.org>
 M:	Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
 M:	Patrick McHardy <kaber@trash.net>
@ -4470,7 +4474,7 @@ F:	include/net/ip*
 F:	arch/x86/net/*

 NETWORKING [LABELED] (NetLabel, CIPSO, Labeled IPsec, SECMARK)
-M:	Paul Moore <paul.moore@hp.com>
+M:	Paul Moore <paul@paul-moore.com>
 L:	netdev@vger.kernel.org
 S:	Maintained

@ -4722,6 +4726,7 @@ S:	Maintained
 F:	drivers/of
 F:	include/linux/of*.h
 K:	of_get_property
+K:	of_match_table

 OPENRISC ARCHITECTURE
 M:	Jonas Bonn <jonas@southpole.se>
@ -6318,6 +6323,7 @@ F:	include/linux/sysv_fs.h
 TARGET SUBSYSTEM
 M:	Nicholas A. Bellinger <nab@linux-iscsi.org>
 L:	linux-scsi@vger.kernel.org
+L:	target-devel@vger.kernel.org
 L:	http://groups.google.com/group/linux-iscsi-target-dev
 W:	http://www.linux-iscsi.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/nab/lio-core-2.6.git master
--- a/4
+++ b/4
@ -1,7 +1,7 @@
 VERSION = 3
-PATCHLEVEL = 0
+PATCHLEVEL = 1
 SUBLEVEL = 0
-EXTRAVERSION =
+EXTRAVERSION = -rc1
 NAME = Sneaky Weasel

 # *DOCUMENTATION*
--- a/arch/Kconfig
+++ b/arch/Kconfig
@ -178,4 +178,7 @@ config HAVE_ARCH_MUTEX_CPU_RELAX
 config HAVE_RCU_TABLE_FREE
 	bool

+config ARCH_HAVE_NMI_SAFE_CMPXCHG
+	bool
+
 source "kernel/gcov/Kconfig"
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@ -14,6 +14,7 @@ config ALPHA
 	select AUTO_IRQ_AFFINITY if SMP
 	select GENERIC_IRQ_SHOW
 	select ARCH_WANT_OPTIONAL_GPIOLIB
+	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	help
 	  The Alpha is a 64-bit general-purpose processor designed and
 	  marketed by the Digital Equipment Corporation of blessed memory,
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@ -112,9 +112,6 @@ EXPORT_SYMBOL(__put_user_4);
 EXPORT_SYMBOL(__put_user_8);
 #endif

-	/* crypto hash */
-EXPORT_SYMBOL(sha_transform);
-
 	/* gcc lib functions */
 EXPORT_SYMBOL(__ashldi3);
 EXPORT_SYMBOL(__ashrdi3);
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@ -30,6 +30,7 @@
 #include <linux/uaccess.h>
 #include <linux/random.h>
 #include <linux/hw_breakpoint.h>
+#include <linux/cpuidle.h>

 #include <asm/cacheflush.h>
 #include <asm/leds.h>
@ -196,7 +197,8 @@ void cpu_idle(void)
 				cpu_relax();
 			} else {
 				stop_critical_timings();
-				pm_idle();
+				if (cpuidle_idle_call())
+					pm_idle();
 				start_critical_timings();
 				/*
 				 * This will eventually be removed - pm_idle
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile
@ -12,7 +12,7 @@ lib-y		:= backtrace.o changebit.o csumipv6.o csumpartial.o   \
 		   strchr.o strrchr.o                                 \
 		   testchangebit.o testclearbit.o testsetbit.o        \
 		   ashldi3.o ashrdi3.o lshrdi3.o muldi3.o             \
-		   ucmpdi2.o lib1funcs.o div64.o sha1.o               \
+		   ucmpdi2.o lib1funcs.o div64.o                      \
 		   io-readsb.o io-writesb.o io-readsl.o io-writesl.o

 mmu-y	:= clear_user.o copy_page.o getuser.o putuser.o
--- a/arch/arm/lib/sha1.S
+++ b/arch/arm/lib/sha1.S
@ -1,211 +0,0 @@
-/*
- *  linux/arch/arm/lib/sha1.S
- *
- *  SHA transform optimized for ARM
- *
- *  Copyright:	(C) 2005 by Nicolas Pitre <nico@fluxnic.net>
- *  Created:	September 17, 2005
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License version 2 as
- *  published by the Free Software Foundation.
- *
- *  The reference implementation for this code is linux/lib/sha1.c
- */
-
-#include <linux/linkage.h>
-
-	.text
-
-
-/*
- * void sha_transform(__u32 *digest, const char *in, __u32 *W)
- *
- * Note: the "in" ptr may be unaligned.
- */
-
-ENTRY(sha_transform)
-
-	stmfd	sp!, {r4 - r8, lr}
-
-	@ for (i = 0; i < 16; i++)
-	@         W[i] = be32_to_cpu(in[i]);
-
-#ifdef __ARMEB__
-	mov	r4, r0
-	mov	r0, r2
-	mov	r2, #64
-	bl	memcpy
-	mov	r2, r0
-	mov	r0, r4
-#else
-	mov	r3, r2
-	mov	lr, #16
-1:	ldrb	r4, [r1], #1
-	ldrb	r5, [r1], #1
-	ldrb	r6, [r1], #1
-	ldrb	r7, [r1], #1
-	subs	lr, lr, #1
-	orr	r5, r5, r4, lsl #8
-	orr	r6, r6, r5, lsl #8
-	orr	r7, r7, r6, lsl #8
-	str	r7, [r3], #4
-	bne	1b
-#endif
-
-	@ for (i = 0; i < 64; i++)
-	@         W[i+16] = ror(W[i+13] ^ W[i+8] ^ W[i+2] ^ W[i], 31);
-
-	sub	r3, r2, #4
-	mov	lr, #64
-2:	ldr	r4, [r3, #4]!
-	subs	lr, lr, #1
-	ldr	r5, [r3, #8]
-	ldr	r6, [r3, #32]
-	ldr	r7, [r3, #52]
-	eor	r4, r4, r5
-	eor	r4, r4, r6
-	eor	r4, r4, r7
-	mov	r4, r4, ror #31
-	str	r4, [r3, #64]
-	bne	2b
-
-	/*
-	 * The SHA functions are:
-	 *
-	 * f1(B,C,D) = (D ^ (B & (C ^ D)))
-	 * f2(B,C,D) = (B ^ C ^ D)
-	 * f3(B,C,D) = ((B & C) | (D & (B | C)))
-	 *
-	 * Then the sub-blocks are processed as follows:
-	 *
-	 * A' = ror(A, 27) + f(B,C,D) + E + K + *W++
-	 * B' = A
-	 * C' = ror(B, 2)
-	 * D' = C
-	 * E' = D
-	 *
-	 * We therefore unroll each loop 5 times to avoid register shuffling.
-	 * Also the ror for C (and also D and E which are successivelyderived
-	 * from it) is applied in place to cut on an additional mov insn for
-	 * each round.
-	 */
-
-	.macro	sha_f1, A, B, C, D, E
-	ldr	r3, [r2], #4
-	eor	ip, \C, \D
-	add	\E, r1, \E, ror #2
-	and	ip, \B, ip, ror #2
-	add	\E, \E, \A, ror #27
-	eor	ip, ip, \D, ror #2
-	add	\E, \E, r3
-	add	\E, \E, ip
-	.endm
-
-	.macro	sha_f2, A, B, C, D, E
-	ldr	r3, [r2], #4
-	add	\E, r1, \E, ror #2
-	eor	ip, \B, \C, ror #2
-	add	\E, \E, \A, ror #27
-	eor	ip, ip, \D, ror #2
-	add	\E, \E, r3
-	add	\E, \E, ip
-	.endm
-
-	.macro	sha_f3, A, B, C, D, E
-	ldr	r3, [r2], #4
-	add	\E, r1, \E, ror #2
-	orr	ip, \B, \C, ror #2
-	add	\E, \E, \A, ror #27
-	and	ip, ip, \D, ror #2
-	add	\E, \E, r3
-	and	r3, \B, \C, ror #2
-	orr	ip, ip, r3
-	add	\E, \E, ip
-	.endm
-
-	ldmia	r0, {r4 - r8}
-
-	mov	lr, #4
-	ldr	r1, .L_sha_K + 0
-
-	/* adjust initial values */
-	mov	r6, r6, ror #30
-	mov	r7, r7, ror #30
-	mov	r8, r8, ror #30
-
-3:	subs	lr, lr, #1
-	sha_f1	r4, r5, r6, r7, r8
-	sha_f1	r8, r4, r5, r6, r7
-	sha_f1	r7, r8, r4, r5, r6
-	sha_f1	r6, r7, r8, r4, r5
-	sha_f1	r5, r6, r7, r8, r4
-	bne	3b
-
-	ldr	r1, .L_sha_K + 4
-	mov	lr, #4
-
-4:	subs	lr, lr, #1
-	sha_f2	r4, r5, r6, r7, r8
-	sha_f2	r8, r4, r5, r6, r7
-	sha_f2	r7, r8, r4, r5, r6
-	sha_f2	r6, r7, r8, r4, r5
-	sha_f2	r5, r6, r7, r8, r4
-	bne	4b
-
-	ldr	r1, .L_sha_K + 8
-	mov	lr, #4
-
-5:	subs	lr, lr, #1
-	sha_f3	r4, r5, r6, r7, r8
-	sha_f3	r8, r4, r5, r6, r7
-	sha_f3	r7, r8, r4, r5, r6
-	sha_f3	r6, r7, r8, r4, r5
-	sha_f3	r5, r6, r7, r8, r4
-	bne	5b
-
-	ldr	r1, .L_sha_K + 12
-	mov	lr, #4
-
-6:	subs	lr, lr, #1
-	sha_f2	r4, r5, r6, r7, r8
-	sha_f2	r8, r4, r5, r6, r7
-	sha_f2	r7, r8, r4, r5, r6
-	sha_f2	r6, r7, r8, r4, r5
-	sha_f2	r5, r6, r7, r8, r4
-	bne	6b
-
-	ldmia	r0, {r1, r2, r3, ip, lr}
-	add	r4, r1, r4
-	add	r5, r2, r5
-	add	r6, r3, r6, ror #2
-	add	r7, ip, r7, ror #2
-	add	r8, lr, r8, ror #2
-	stmia	r0, {r4 - r8}
-
-	ldmfd	sp!, {r4 - r8, pc}
-
-ENDPROC(sha_transform)
-
-	.align	2
-.L_sha_K:
-	.word	0x5a827999, 0x6ed9eba1, 0x8f1bbcdc, 0xca62c1d6
-
-
-/*
- * void sha_init(__u32 *buf)
- */
-
-	.align	2
-.L_sha_initial_digest:
-	.word	0x67452301, 0xefcdab89, 0x98badcfe, 0x10325476, 0xc3d2e1f0
-
-ENTRY(sha_init)
-
-	str	lr, [sp, #-4]!
-	adr	r1, .L_sha_initial_digest
-	ldmia	r1, {r1, r2, r3, ip, lr}
-	stmia	r0, {r1, r2, r3, ip, lr}
-	ldr	pc, [sp], #4
-
-ENDPROC(sha_init)
--- a/arch/avr32/Kconfig
+++ b/arch/avr32/Kconfig
@ -10,6 +10,7 @@ config AVR32
 	select GENERIC_IRQ_PROBE
 	select HARDIRQS_SW_RESEND
 	select GENERIC_IRQ_SHOW
+	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	help
 	  AVR32 is a high-performance 32-bit RISC microprocessor core,
 	  designed for cost-sensitive embedded applications, with particular
--- a/arch/cris/arch-v10/drivers/sync_serial.c
+++ b/arch/cris/arch-v10/drivers/sync_serial.c
@ -158,7 +158,7 @@ static int sync_serial_open(struct inode *inode, struct file *file);
 static int sync_serial_release(struct inode *inode, struct file *file);
 static unsigned int sync_serial_poll(struct file *filp, poll_table *wait);

-static int sync_serial_ioctl(struct file *file,
+static long sync_serial_ioctl(struct file *file,
 	unsigned int cmd, unsigned long arg);
 static ssize_t sync_serial_write(struct file *file, const char *buf,
 	size_t count, loff_t *ppos);
@ -625,11 +625,11 @@ static int sync_serial_open(struct inode *inode, struct file *file)
 			*R_IRQ_MASK1_SET = 1 << port->data_avail_bit;
 		DEBUG(printk(KERN_DEBUG "sser%d rec started\n", dev));
 	}
-	ret = 0;
+	err = 0;
 	
 out:
 	mutex_unlock(&sync_serial_mutex);
-	return ret;
+	return err;
 }

 static int sync_serial_release(struct inode *inode, struct file *file)
--- a/arch/cris/arch-v10/kernel/irq.c
+++ b/arch/cris/arch-v10/kernel/irq.c
@ -20,6 +20,9 @@
 #define crisv10_mask_irq(irq_nr) (*R_VECT_MASK_CLR = 1 << (irq_nr));
 #define crisv10_unmask_irq(irq_nr) (*R_VECT_MASK_SET = 1 << (irq_nr));

+extern void kgdb_init(void);
+extern void breakpoint(void);
+
 /* don't use set_int_vector, it bypasses the linux interrupt handlers. it is
 * global just so that the kernel gdb can use it.
 */
--- a/arch/cris/include/asm/thread_info.h
+++ b/arch/cris/include/asm/thread_info.h
@ -11,8 +11,6 @@

 #ifdef __KERNEL__

-#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR
-
 #ifndef __ASSEMBLY__
 #include <asm/types.h>
 #include <asm/processor.h>
@ -67,8 +65,10 @@ struct thread_info {

 #define init_thread_info	(init_thread_union.thread_info)

+#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR
 /* thread information allocation */
-#define alloc_thread_info(tsk, node) ((struct thread_info *) __get_free_pages(GFP_KERNEL,1))
+#define alloc_thread_info_node(tsk, node)	\
+	((struct thread_info *) __get_free_pages(GFP_KERNEL, 1))
 #define free_thread_info(ti) free_pages((unsigned long) (ti), 1)

 #endif /* !__ASSEMBLY__ */
--- a/arch/frv/Kconfig
+++ b/arch/frv/Kconfig
@ -7,6 +7,7 @@ config FRV
 	select HAVE_PERF_EVENTS
 	select HAVE_GENERIC_HARDIRQS
 	select GENERIC_IRQ_SHOW
+	select ARCH_HAVE_NMI_SAFE_CMPXCHG

 config ZONE_DMA
 	bool
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@ -27,6 +27,8 @@ config IA64
 	select GENERIC_PENDING_IRQ if SMP
 	select IRQ_PER_CPU
 	select GENERIC_IRQ_SHOW
+	select ARCH_WANT_OPTIONAL_GPIOLIB
+	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	default y
 	help
 	  The Itanium Processor Family is Intel's 64-bit successor to
@ -89,6 +91,9 @@ config GENERIC_TIME_VSYSCALL
 config HAVE_SETUP_PER_CPU_AREA
 	def_bool y

+config GENERIC_GPIO
+	def_bool y
+
 config DMI
 	bool
 	default y
--- a/arch/ia64/include/asm/gpio.h
+++ b/arch/ia64/include/asm/gpio.h
@ -0,0 +1,55 @@
+/*
+ * Generic GPIO API implementation for IA-64.
+ *
+ * A stright copy of that for PowerPC which was:
+ *
+ * Copyright (c) 2007-2008  MontaVista Software, Inc.
+ *
+ * Author: Anton Vorontsov <avorontsov@ru.mvista.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef _ASM_IA64_GPIO_H
+#define _ASM_IA64_GPIO_H
+
+#include <linux/errno.h>
+#include <asm-generic/gpio.h>
+
+#ifdef CONFIG_GPIOLIB
+
+/*
+ * We don't (yet) implement inlined/rapid versions for on-chip gpios.
+ * Just call gpiolib.
+ */
+static inline int gpio_get_value(unsigned int gpio)
+{
+	return __gpio_get_value(gpio);
+}
+
+static inline void gpio_set_value(unsigned int gpio, int value)
+{
+	__gpio_set_value(gpio, value);
+}
+
+static inline int gpio_cansleep(unsigned int gpio)
+{
+	return __gpio_cansleep(gpio);
+}
+
+static inline int gpio_to_irq(unsigned int gpio)
+{
+	return __gpio_to_irq(gpio);
+}
+
+static inline int irq_to_gpio(unsigned int irq)
+{
+	return -EINVAL;
+}
+
+#endif /* CONFIG_GPIOLIB */
+
+#endif /* _ASM_IA64_GPIO_H */
--- a/arch/ia64/kernel/efi.c
+++ b/arch/ia64/kernel/efi.c
@ -156,7 +156,7 @@ prefix##_get_next_variable (unsigned long *name_size, efi_char16_t *name,      \
 #define STUB_SET_VARIABLE(prefix, adjust_arg)				       \
 static efi_status_t							       \
 prefix##_set_variable (efi_char16_t *name, efi_guid_t *vendor,		       \
-		       unsigned long attr, unsigned long data_size,	       \
+		       u32 attr, unsigned long data_size,		       \
 		       void *data)					       \
 {									       \
 	struct ia64_fpreg fr[6];					       \
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@ -6,6 +6,7 @@ config M68K
 	select GENERIC_ATOMIC64 if MMU
 	select HAVE_GENERIC_HARDIRQS if !MMU
 	select GENERIC_IRQ_SHOW if !MMU
+	select ARCH_HAVE_NMI_SAFE_CMPXCHG if RMW_INSNS

 config RWSEM_GENERIC_SPINLOCK
 	bool
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@ -15,6 +15,7 @@ config PARISC
 	select HAVE_GENERIC_HARDIRQS
 	select GENERIC_IRQ_PROBE
 	select IRQ_PER_CPU
+	select ARCH_HAVE_NMI_SAFE_CMPXCHG

 	help
 	  The PA-RISC microprocessor is designed by Hewlett-Packard and used
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@ -258,10 +258,10 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)

 #define ATOMIC64_INIT(i) ((atomic64_t) { (i) })

-static __inline__ int
+static __inline__ s64
 __atomic64_add_return(s64 i, atomic64_t *v)
 {
-	int ret;
+	s64 ret;
 	unsigned long flags;
 	_atomic_spin_lock_irqsave(v, flags);

--- a/arch/parisc/include/asm/futex.h
+++ b/arch/parisc/include/asm/futex.h
@ -5,11 +5,14 @@

 #include <linux/futex.h>
 #include <linux/uaccess.h>
+#include <asm/atomic.h>
 #include <asm/errno.h>

 static inline int
 futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 {
+	unsigned long int flags;
+	u32 val;
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
 	int oparg = (encoded_op << 8) >> 20;
@ -18,21 +21,58 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;

-	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(*uaddr)))
 		return -EFAULT;

 	pagefault_disable();

+	_atomic_spin_lock_irqsave(uaddr, flags);
+
 	switch (op) {
 	case FUTEX_OP_SET:
+		/* *(int *)UADDR2 = OPARG; */
+		ret = get_user(oldval, uaddr);
+		if (!ret)
+			ret = put_user(oparg, uaddr);
+		break;
 	case FUTEX_OP_ADD:
+		/* *(int *)UADDR2 += OPARG; */
+		ret = get_user(oldval, uaddr);
+		if (!ret) {
+			val = oldval + oparg;
+			ret = put_user(val, uaddr);
+		}
+		break;
 	case FUTEX_OP_OR:
+		/* *(int *)UADDR2 |= OPARG; */
+		ret = get_user(oldval, uaddr);
+		if (!ret) {
+			val = oldval | oparg;
+			ret = put_user(val, uaddr);
+		}
+		break;
 	case FUTEX_OP_ANDN:
+		/* *(int *)UADDR2 &= ~OPARG; */
+		ret = get_user(oldval, uaddr);
+		if (!ret) {
+			val = oldval & ~oparg;
+			ret = put_user(val, uaddr);
+		}
+		break;
 	case FUTEX_OP_XOR:
+		/* *(int *)UADDR2 ^= OPARG; */
+		ret = get_user(oldval, uaddr);
+		if (!ret) {
+			val = oldval ^ oparg;
+			ret = put_user(val, uaddr);
+		}
+		break;
 	default:
 		ret = -ENOSYS;
 	}

+	_atomic_spin_unlock_irqrestore(uaddr, flags);
+
 	pagefault_enable();

 	if (!ret) {
@ -54,7 +94,9 @@ static inline int
 futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 			      u32 oldval, u32 newval)
 {
+	int ret;
 	u32 val;
+	unsigned long flags;

 	/* futex.c wants to do a cmpxchg_inatomic on kernel NULL, which is
 	 * our gateway page, and causes no end of trouble...
@ -65,12 +107,24 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;

-	if (get_user(val, uaddr))
-		return -EFAULT;
-	if (val == oldval && put_user(newval, uaddr))
-		return -EFAULT;
+	/* HPPA has no cmpxchg in hardware and therefore the
+	 * best we can do here is use an array of locks. The
+	 * lock selected is based on a hash of the userspace
+	 * address. This should scale to a couple of CPUs.
+	 */
+
+	_atomic_spin_lock_irqsave(uaddr, flags);
+
+	ret = get_user(val, uaddr);
+
+	if (!ret && val == oldval)
+		ret = put_user(newval, uaddr);
+
 	*uval = val;
-	return 0;
+
+	_atomic_spin_unlock_irqrestore(uaddr, flags);
+
+	return ret;
 }

 #endif /*__KERNEL__*/
--- a/arch/parisc/include/asm/unistd.h
+++ b/arch/parisc/include/asm/unistd.h
@ -821,8 +821,9 @@
 #define __NR_open_by_handle_at	(__NR_Linux + 326)
 #define __NR_syncfs		(__NR_Linux + 327)
 #define __NR_setns		(__NR_Linux + 328)
+#define __NR_sendmmsg		(__NR_Linux + 329)

-#define __NR_Linux_syscalls	(__NR_setns + 1)
+#define __NR_Linux_syscalls	(__NR_sendmmsg + 1)


 #define __IGNORE_select		/* newselect */
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@ -427,6 +427,7 @@
 	ENTRY_COMP(open_by_handle_at)
 	ENTRY_SAME(syncfs)
 	ENTRY_SAME(setns)
+	ENTRY_COMP(sendmmsg)

 	/* Nothing yet */

--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@ -136,6 +136,7 @@ config PPC
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_BPF_JIT if (PPC64 && NET)
 	select HAVE_ARCH_JUMP_LABEL
+	select ARCH_HAVE_NMI_SAFE_CMPXCHG

 config EARLY_PRINTK
 	bool
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@ -81,6 +81,7 @@ config S390
 	select INIT_ALL_POSSIBLE
 	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
+	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_LZMA
@ -273,11 +274,11 @@ config MARCH_Z10
 	  on older machines.

 config MARCH_Z196
-	bool "IBM zEnterprise 196"
+	bool "IBM zEnterprise 114 and 196"
 	help
-	  Select this to enable optimizations for IBM zEnterprise 196
-	  (2817 series). The kernel will be slightly faster but will not work
-	  on older machines.
+	  Select this to enable optimizations for IBM zEnterprise 114 and 196
+	  (2818 and 2817 series). The kernel will be slightly faster but will
+	  not work on older machines.

 endchoice

--- a/arch/s390/include/asm/ipl.h
+++ b/arch/s390/include/asm/ipl.h
@ -167,5 +167,6 @@ enum diag308_rc {
 };

 extern int diag308(unsigned long subcode, void *addr);
+extern void diag308_reset(void);

 #endif /* _ASM_S390_IPL_H */
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@ -18,6 +18,7 @@ void system_call(void);
 void pgm_check_handler(void);
 void mcck_int_handler(void);
 void io_int_handler(void);
+void psw_restart_int_handler(void);

 #ifdef CONFIG_32BIT

@ -150,7 +151,10 @@ struct _lowcore {
 	 */
 	__u32	ipib;				/* 0x0e00 */
 	__u32	ipib_checksum;			/* 0x0e04 */
-	__u8	pad_0x0e08[0x0f00-0x0e08];	/* 0x0e08 */
+
+	/* 64 bit save area */
+	__u64	save_area_64;			/* 0x0e08 */
+	__u8	pad_0x0e10[0x0f00-0x0e10];	/* 0x0e10 */

 	/* Extended facility list */
 	__u64	stfle_fac_list[32];		/* 0x0f00 */
@ -286,7 +290,10 @@ struct _lowcore {
 	 */
 	__u64	ipib;				/* 0x0e00 */
 	__u32	ipib_checksum;			/* 0x0e08 */
-	__u8	pad_0x0e0c[0x0f00-0x0e0c];	/* 0x0e0c */
+
+	/* 64 bit save area */
+	__u64	save_area_64;			/* 0x0e0c */
+	__u8	pad_0x0e14[0x0f00-0x0e14];	/* 0x0e14 */

 	/* Extended facility list */
 	__u64	stfle_fac_list[32];		/* 0x0f00 */
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@ -119,14 +119,12 @@ struct stack_frame {
 * Do necessary setup to start up a new thread.
 */
 #define start_thread(regs, new_psw, new_stackp) do {		\
-	set_fs(USER_DS);					\
 	regs->psw.mask	= psw_user_bits;			\
 	regs->psw.addr	= new_psw | PSW_ADDR_AMODE;		\
 	regs->gprs[15]	= new_stackp;				\
 } while (0)

 #define start_thread31(regs, new_psw, new_stackp) do {		\
-	set_fs(USER_DS);					\
 	regs->psw.mask	= psw_user32_bits;			\
 	regs->psw.addr	= new_psw | PSW_ADDR_AMODE;		\
 	regs->gprs[15]	= new_stackp;				\
--- a/arch/s390/include/asm/system.h
+++ b/arch/s390/include/asm/system.h
@ -113,6 +113,7 @@ extern void pfault_fini(void);

 extern void cmma_init(void);
 extern int memcpy_real(void *, void *, size_t);
+extern void copy_to_absolute_zero(void *dest, void *src, size_t count);

 #define finish_arch_switch(prev) do {					     \
 	set_fs(current->thread.mm_segment);				     \
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@ -27,12 +27,9 @@ int main(void)
 	BLANK();
 	DEFINE(__TASK_pid, offsetof(struct task_struct, pid));
 	BLANK();
-	DEFINE(__THREAD_per_cause,
-	       offsetof(struct task_struct, thread.per_event.cause));
-	DEFINE(__THREAD_per_address,
-	       offsetof(struct task_struct, thread.per_event.address));
-	DEFINE(__THREAD_per_paid,
-	       offsetof(struct task_struct, thread.per_event.paid));
+	DEFINE(__THREAD_per_cause, offsetof(struct task_struct, thread.per_event.cause));
+	DEFINE(__THREAD_per_address, offsetof(struct task_struct, thread.per_event.address));
+	DEFINE(__THREAD_per_paid, offsetof(struct task_struct, thread.per_event.paid));
 	BLANK();
 	DEFINE(__TI_task, offsetof(struct thread_info, task));
 	DEFINE(__TI_domain, offsetof(struct thread_info, exec_domain));
@ -142,6 +139,7 @@ int main(void)
 	DEFINE(__LC_FPREGS_SAVE_AREA, offsetof(struct _lowcore, floating_pt_save_area));
 	DEFINE(__LC_GPREGS_SAVE_AREA, offsetof(struct _lowcore, gpregs_save_area));
 	DEFINE(__LC_CREGS_SAVE_AREA, offsetof(struct _lowcore, cregs_save_area));
+	DEFINE(__LC_SAVE_AREA_64, offsetof(struct _lowcore, save_area_64));
 #ifdef CONFIG_32BIT
 	DEFINE(SAVE_AREA_BASE, offsetof(struct _lowcore, extended_save_area_addr));
 #else /* CONFIG_32BIT */
--- a/arch/s390/kernel/base.S
+++ b/arch/s390/kernel/base.S
@ -76,6 +76,42 @@ s390_base_pgm_handler_fn:
 	.quad	0
 	.previous

+#
+# Calls diag 308 subcode 1 and continues execution
+#
+# The following conditions must be ensured before calling this function:
+# * Prefix register = 0
+# * Lowcore protection is disabled
+#
+ENTRY(diag308_reset)
+	larl	%r4,.Lctlregs		# Save control registers
+	stctg	%c0,%c15,0(%r4)
+	larl	%r4,.Lrestart_psw	# Setup restart PSW at absolute 0
+	lghi	%r3,0
+	lg	%r4,0(%r4)		# Save PSW
+	sturg	%r4,%r3			# Use sturg, because of large pages
+	lghi	%r1,1
+	diag	%r1,%r1,0x308
+.Lrestart_part2:
+	lhi	%r0,0			# Load r0 with zero
+	lhi	%r1,2			# Use mode 2 = ESAME (dump)
+	sigp	%r1,%r0,0x12		# Switch to ESAME mode
+	sam64				# Switch to 64 bit addressing mode
+	larl	%r4,.Lctlregs		# Restore control registers
+	lctlg	%c0,%c15,0(%r4)
+	br	%r14
+.align 16
+.Lrestart_psw:
+	.long	0x00080000,0x80000000 + .Lrestart_part2
+
+	.section .bss
+.align 8
+.Lctlregs:
+	.rept	16
+	.quad	0
+	.endr
+	.previous
+
 #else /* CONFIG_64BIT */

 ENTRY(s390_base_mcck_handler)
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@ -380,20 +380,13 @@ asmlinkage long sys32_sigreturn(void)
 		goto badframe;
 	if (__copy_from_user(&set.sig, &frame->sc.oldmask, _SIGMASK_COPY_SIZE32))
 		goto badframe;
-
 	sigdelsetmask(&set, ~_BLOCKABLE);
-	spin_lock_irq(&current->sighand->siglock);
-	current->blocked = set;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
-
+	set_current_blocked(&set);
 	if (restore_sigregs32(regs, &frame->sregs))
 		goto badframe;
 	if (restore_sigregs_gprs_high(regs, frame->gprs_high))
 		goto badframe;
-
 	return regs->gprs[2];
-
 badframe:
 	force_sig(SIGSEGV, current);
 	return 0;
@ -413,31 +406,22 @@ asmlinkage long sys32_rt_sigreturn(void)
 		goto badframe;
 	if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
 		goto badframe;
-
 	sigdelsetmask(&set, ~_BLOCKABLE);
-	spin_lock_irq(&current->sighand->siglock);
-	current->blocked = set;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
-
+	set_current_blocked(&set);
 	if (restore_sigregs32(regs, &frame->uc.uc_mcontext))
 		goto badframe;
 	if (restore_sigregs_gprs_high(regs, frame->gprs_high))
 		goto badframe;
-
 	err = __get_user(ss_sp, &frame->uc.uc_stack.ss_sp);
 	st.ss_sp = compat_ptr(ss_sp);
 	err |= __get_user(st.ss_size, &frame->uc.uc_stack.ss_size);
 	err |= __get_user(st.ss_flags, &frame->uc.uc_stack.ss_flags);
 	if (err)
 		goto badframe; 
-
 	set_fs (KERNEL_DS);
 	do_sigaltstack((stack_t __force __user *)&st, NULL, regs->gprs[15]);
 	set_fs (old_fs);
-
 	return regs->gprs[2];
-
 badframe:
 	force_sig(SIGSEGV, current);
 	return 0;
@ -605,10 +589,10 @@ give_sigsegv:
 * OK, we're invoking a handler
 */	

-int
-handle_signal32(unsigned long sig, struct k_sigaction *ka,
-		siginfo_t *info, sigset_t *oldset, struct pt_regs * regs)
+int handle_signal32(unsigned long sig, struct k_sigaction *ka,
+		    siginfo_t *info, sigset_t *oldset, struct pt_regs *regs)
 {
+	sigset_t blocked;
 	int ret;

 	/* Set up the stack frame */
@ -616,15 +600,12 @@ handle_signal32(unsigned long sig, struct k_sigaction *ka,
 		ret = setup_rt_frame32(sig, ka, info, oldset, regs);
 	else
 		ret = setup_frame32(sig, ka, oldset, regs);
-
-	if (ret == 0) {
-		spin_lock_irq(&current->sighand->siglock);
-		sigorsets(&current->blocked,&current->blocked,&ka->sa.sa_mask);
-		if (!(ka->sa.sa_flags & SA_NODEFER))
-			sigaddset(&current->blocked,sig);
-		recalc_sigpending();
-		spin_unlock_irq(&current->sighand->siglock);
-	}
-	return ret;
+	if (ret)
+		return ret;
+	sigorsets(&blocked, &current->blocked, &ka->sa.sa_mask);
+	if (!(ka->sa.sa_flags & SA_NODEFER))
+		sigaddset(&blocked, sig);
+	set_current_blocked(&blocked);
+	return 0;
 }

--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@ -849,6 +849,34 @@ restart_crash:
 restart_go:
 #endif

+#
+# PSW restart interrupt handler
+#
+ENTRY(psw_restart_int_handler)
+	st	%r15,__LC_SAVE_AREA_64(%r0)	# save r15
+	basr	%r15,0
+0:	l	%r15,.Lrestart_stack-0b(%r15)	# load restart stack
+	l	%r15,0(%r15)
+	ahi	%r15,-SP_SIZE			# make room for pt_regs
+	stm	%r0,%r14,SP_R0(%r15)		# store gprs %r0-%r14 to stack
+	mvc	SP_R15(4,%r15),__LC_SAVE_AREA_64(%r0)# store saved %r15 to stack
+	mvc	SP_PSW(8,%r15),__LC_RST_OLD_PSW(%r0) # store restart old psw
+	xc	__SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) # set backchain to 0
+	basr	%r14,0
+1:	l	%r14,.Ldo_restart-1b(%r14)
+	basr	%r14,%r14
+
+	basr	%r14,0				# load disabled wait PSW if
+2:	lpsw	restart_psw_crash-2b(%r14)	# do_restart returns
+	.align 4
+.Ldo_restart:
+	.long	do_restart
+.Lrestart_stack:
+	.long	restart_stack
+	.align 8
+restart_psw_crash:
+	.long	0x000a0000,0x00000000 + restart_psw_crash
+
 	.section .kprobes.text, "ax"

 #ifdef CONFIG_CHECK_STACK
--- a/arch/s390/kernel/entry64.S
+++ b/arch/s390/kernel/entry64.S
@ -865,6 +865,26 @@ restart_crash:
 restart_go:
 #endif

+#
+# PSW restart interrupt handler
+#
+ENTRY(psw_restart_int_handler)
+	stg	%r15,__LC_SAVE_AREA_64(%r0)	# save r15
+	larl	%r15,restart_stack		# load restart stack
+	lg	%r15,0(%r15)
+	aghi	%r15,-SP_SIZE			# make room for pt_regs
+	stmg	%r0,%r14,SP_R0(%r15)		# store gprs %r0-%r14 to stack
+	mvc	SP_R15(8,%r15),__LC_SAVE_AREA_64(%r0)# store saved %r15 to stack
+	mvc	SP_PSW(16,%r15),__LC_RST_OLD_PSW(%r0)# store restart old psw
+	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) # set backchain to 0
+	brasl	%r14,do_restart
+
+	larl	%r14,restart_psw_crash		# load disabled wait PSW if
+	lpswe	0(%r14)				# do_restart returns
+	.align 8
+restart_psw_crash:
+	.quad	0x0002000080000000,0x0000000000000000 + restart_psw_crash
+
 	.section .kprobes.text, "ax"

 #ifdef CONFIG_CHECK_STACK
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@ -45,11 +45,13 @@
 * - halt
 * - power off
 * - reipl
+ * - restart
 */
 #define ON_PANIC_STR		"on_panic"
 #define ON_HALT_STR		"on_halt"
 #define ON_POFF_STR		"on_poff"
 #define ON_REIPL_STR		"on_reboot"
+#define ON_RESTART_STR		"on_restart"

 struct shutdown_action;
 struct shutdown_trigger {
@ -1544,17 +1546,20 @@ static char vmcmd_on_reboot[128];
 static char vmcmd_on_panic[128];
 static char vmcmd_on_halt[128];
 static char vmcmd_on_poff[128];
+static char vmcmd_on_restart[128];

 DEFINE_IPL_ATTR_STR_RW(vmcmd, on_reboot, "%s\n", "%s\n", vmcmd_on_reboot);
 DEFINE_IPL_ATTR_STR_RW(vmcmd, on_panic, "%s\n", "%s\n", vmcmd_on_panic);
 DEFINE_IPL_ATTR_STR_RW(vmcmd, on_halt, "%s\n", "%s\n", vmcmd_on_halt);
 DEFINE_IPL_ATTR_STR_RW(vmcmd, on_poff, "%s\n", "%s\n", vmcmd_on_poff);
+DEFINE_IPL_ATTR_STR_RW(vmcmd, on_restart, "%s\n", "%s\n", vmcmd_on_restart);

 static struct attribute *vmcmd_attrs[] = {
 	&sys_vmcmd_on_reboot_attr.attr,
 	&sys_vmcmd_on_panic_attr.attr,
 	&sys_vmcmd_on_halt_attr.attr,
 	&sys_vmcmd_on_poff_attr.attr,
+	&sys_vmcmd_on_restart_attr.attr,
 	NULL,
 };

@ -1576,6 +1581,8 @@ static void vmcmd_run(struct shutdown_trigger *trigger)
 		cmd = vmcmd_on_halt;
 	else if (strcmp(trigger->name, ON_POFF_STR) == 0)
 		cmd = vmcmd_on_poff;
+	else if (strcmp(trigger->name, ON_RESTART_STR) == 0)
+		cmd = vmcmd_on_restart;
 	else
 		return;

@ -1707,6 +1714,34 @@ static void do_panic(void)
 	stop_run(&on_panic_trigger);
 }

+/* on restart */
+
+static struct shutdown_trigger on_restart_trigger = {ON_RESTART_STR,
+	&reipl_action};
+
+static ssize_t on_restart_show(struct kobject *kobj,
+			       struct kobj_attribute *attr, char *page)
+{
+	return sprintf(page, "%s\n", on_restart_trigger.action->name);
+}
+
+static ssize_t on_restart_store(struct kobject *kobj,
+				struct kobj_attribute *attr,
+				const char *buf, size_t len)
+{
+	return set_trigger(buf, &on_restart_trigger, len);
+}
+
+static struct kobj_attribute on_restart_attr =
+	__ATTR(on_restart, 0644, on_restart_show, on_restart_store);
+
+void do_restart(void)
+{
+	smp_send_stop();
+	on_restart_trigger.action->fn(&on_restart_trigger);
+	stop_run(&on_restart_trigger);
+}
+
 /* on halt */

 static struct shutdown_trigger on_halt_trigger = {ON_HALT_STR, &stop_action};
@ -1783,7 +1818,9 @@ static void __init shutdown_triggers_init(void)
 	if (sysfs_create_file(&shutdown_actions_kset->kobj,
 			      &on_poff_attr.attr))
 		goto fail;
-
+	if (sysfs_create_file(&shutdown_actions_kset->kobj,
+			      &on_restart_attr.attr))
+		goto fail;
 	return;
 fail:
 	panic("shutdown_triggers_init failed\n");
@ -1959,6 +1996,12 @@ static void do_reset_calls(void)
 {
 	struct reset_call *reset;

+#ifdef CONFIG_64BIT
+	if (diag308_set_works) {
+		diag308_reset();
+		return;
+	}
+#endif
 	list_for_each_entry(reset, &rcall, list)
 		reset->fn();
 }
--- a/arch/s390/kernel/reipl64.S
+++ b/arch/s390/kernel/reipl64.S
@ -1,5 +1,5 @@
 /*
- *    Copyright IBM Corp 2000,2009
+ *    Copyright IBM Corp 2000,2011
 *    Author(s): Holger Smolinski <Holger.Smolinski@de.ibm.com>,
 *		 Denis Joseph Barrow,
 */
@ -7,6 +7,64 @@
 #include <linux/linkage.h>
 #include <asm/asm-offsets.h>

+#
+# store_status
+#
+# Prerequisites to run this function:
+# - Prefix register is set to zero
+# - Original prefix register is stored in "dump_prefix_page"
+# - Lowcore protection is off
+#
+ENTRY(store_status)
+	/* Save register one and load save area base */
+	stg	%r1,__LC_SAVE_AREA_64(%r0)
+	lghi	%r1,SAVE_AREA_BASE
+	/* General purpose registers */
+	stmg	%r0,%r15,__LC_GPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	lg	%r2,__LC_SAVE_AREA_64(%r0)
+	stg	%r2,__LC_GPREGS_SAVE_AREA-SAVE_AREA_BASE+8(%r1)
+	/* Control registers */
+	stctg	%c0,%c15,__LC_CREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	/* Access registers */
+	stam	%a0,%a15,__LC_AREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	/* Floating point registers */
+	std	%f0, 0x00 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	std	%f1, 0x08 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	std	%f2, 0x10 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	std	%f3, 0x18 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	std	%f4, 0x20 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	std	%f5, 0x28 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	std	%f6, 0x30 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	std	%f7, 0x38 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	std	%f8, 0x40 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	std	%f9, 0x48 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	std	%f10,0x50 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	std	%f11,0x58 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	std	%f12,0x60 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	std	%f13,0x68 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	std	%f14,0x70 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	std	%f15,0x78 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	/* Floating point control register */
+	stfpc	__LC_FP_CREG_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	/* CPU timer */
+	stpt	__LC_CPU_TIMER_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	/* Saved prefix register */
+	larl	%r2,dump_prefix_page
+	mvc	__LC_PREFIX_SAVE_AREA-SAVE_AREA_BASE(4,%r1),0(%r2)
+	/* Clock comparator - seven bytes */
+	larl	%r2,.Lclkcmp
+	stckc	0(%r2)
+	mvc	__LC_CLOCK_COMP_SAVE_AREA-SAVE_AREA_BASE + 1(7,%r1),1(%r2)
+	/* Program status word */
+	epsw	%r2,%r3
+	st	%r2,__LC_PSW_SAVE_AREA-SAVE_AREA_BASE + 0(%r1)
+	st	%r3,__LC_PSW_SAVE_AREA-SAVE_AREA_BASE + 4(%r1)
+	larl	%r2,store_status
+	stg	%r2,__LC_PSW_SAVE_AREA-SAVE_AREA_BASE + 8(%r1)
+	br	%r14
+.align	8
+.Lclkcmp:	.quad	0x0000000000000000
+
 #
 # do_reipl_asm
 # Parameter: r2 = schid of reipl device
@ -15,22 +73,7 @@
 ENTRY(do_reipl_asm)
 		basr	%r13,0
 .Lpg0:		lpswe	.Lnewpsw-.Lpg0(%r13)
-.Lpg1:		# do store status of all registers
-
-		stg	%r1,.Lregsave-.Lpg0(%r13)
-		lghi	%r1,0x1000
-		stmg	%r0,%r15,__LC_GPREGS_SAVE_AREA-0x1000(%r1)
-		lg	%r0,.Lregsave-.Lpg0(%r13)
-		stg	%r0,__LC_GPREGS_SAVE_AREA-0x1000+8(%r1)
-		stctg	%c0,%c15,__LC_CREGS_SAVE_AREA-0x1000(%r1)
-		stam	%a0,%a15,__LC_AREGS_SAVE_AREA-0x1000(%r1)
-		lg	%r10,.Ldump_pfx-.Lpg0(%r13)
-		mvc	__LC_PREFIX_SAVE_AREA-0x1000(4,%r1),0(%r10)
-		stfpc	__LC_FP_CREG_SAVE_AREA-0x1000(%r1)
-		stckc	.Lclkcmp-.Lpg0(%r13)
-		mvc	__LC_CLOCK_COMP_SAVE_AREA-0x1000(7,%r1),.Lclkcmp-.Lpg0(%r13)
-		stpt	__LC_CPU_TIMER_SAVE_AREA-0x1000(%r1)
-		stg	%r13, __LC_PSW_SAVE_AREA-0x1000+8(%r1)
+.Lpg1:		brasl	%r14,store_status

 		lctlg	%c6,%c6,.Lall-.Lpg0(%r13)
 		lgr	%r1,%r2
@ -67,10 +110,7 @@ ENTRY(do_reipl_asm)
 		st	%r14,.Ldispsw+12-.Lpg0(%r13)
 		lpswe	.Ldispsw-.Lpg0(%r13)
 		.align	8
-.Lclkcmp:	.quad	0x0000000000000000
 .Lall:		.quad	0x00000000ff000000
-.Ldump_pfx:	.quad	dump_prefix_page
-.Lregsave:	.quad	0x0000000000000000
 		.align	16
 /*
 * These addresses have to be 31 bit otherwise
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@ -346,7 +346,7 @@ setup_lowcore(void)
 	lc = __alloc_bootmem_low(LC_PAGES * PAGE_SIZE, LC_PAGES * PAGE_SIZE, 0);
 	lc->restart_psw.mask = PSW_BASE_BITS | PSW_DEFAULT_KEY;
 	lc->restart_psw.addr =
-		PSW_ADDR_AMODE | (unsigned long) restart_int_handler;
+		PSW_ADDR_AMODE | (unsigned long) psw_restart_int_handler;
 	if (user_mode != HOME_SPACE_MODE)
 		lc->restart_psw.mask |= PSW_ASC_HOME;
 	lc->external_new_psw.mask = psw_kernel_bits;
@ -529,6 +529,27 @@ static void __init setup_memory_end(void)
 		memory_end = memory_size;
 }

+void *restart_stack __attribute__((__section__(".data")));
+
+/*
+ * Setup new PSW and allocate stack for PSW restart interrupt
+ */
+static void __init setup_restart_psw(void)
+{
+	psw_t psw;
+
+	restart_stack = __alloc_bootmem(ASYNC_SIZE, ASYNC_SIZE, 0);
+	restart_stack += ASYNC_SIZE;
+
+	/*
+	 * Setup restart PSW for absolute zero lowcore. This is necesary
+	 * if PSW restart is done on an offline CPU that has lowcore zero
+	 */
+	psw.mask = PSW_BASE_BITS | PSW_DEFAULT_KEY;
+	psw.addr = PSW_ADDR_AMODE | (unsigned long) psw_restart_int_handler;
+	copy_to_absolute_zero(&S390_lowcore.restart_psw, &psw, sizeof(psw));
+}
+
 static void __init
 setup_memory(void)
 {
@ -731,6 +752,7 @@ static void __init setup_hwcaps(void)
 		strcpy(elf_platform, "z10");
 		break;
 	case 0x2817:
+	case 0x2818:
 		strcpy(elf_platform, "z196");
 		break;
 	}
@ -792,6 +814,7 @@ setup_arch(char **cmdline_p)
 	setup_addressing_mode();
 	setup_memory();
 	setup_resources();
+	setup_restart_psw();
 	setup_lowcore();

        cpu_init();
--- a/arch/s390/kernel/signal.c
+++ b/arch/s390/kernel/signal.c
@ -57,17 +57,15 @@ typedef struct
 */
 SYSCALL_DEFINE3(sigsuspend, int, history0, int, history1, old_sigset_t, mask)
 {
-	mask &= _BLOCKABLE;
-	spin_lock_irq(&current->sighand->siglock);
-	current->saved_sigmask = current->blocked;
-	siginitset(&current->blocked, mask);
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+	sigset_t blocked;

+	current->saved_sigmask = current->blocked;
+	mask &= _BLOCKABLE;
+	siginitset(&blocked, mask);
+	set_current_blocked(&blocked);
 	set_current_state(TASK_INTERRUPTIBLE);
 	schedule();
-	set_thread_flag(TIF_RESTORE_SIGMASK);
-
+	set_restore_sigmask();
 	return -ERESTARTNOHAND;
 }

@ -172,18 +170,11 @@ SYSCALL_DEFINE0(sigreturn)
 		goto badframe;
 	if (__copy_from_user(&set.sig, &frame->sc.oldmask, _SIGMASK_COPY_SIZE))
 		goto badframe;
-
 	sigdelsetmask(&set, ~_BLOCKABLE);
-	spin_lock_irq(&current->sighand->siglock);
-	current->blocked = set;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
-
+	set_current_blocked(&set);
 	if (restore_sigregs(regs, &frame->sregs))
 		goto badframe;
-
 	return regs->gprs[2];
-
 badframe:
 	force_sig(SIGSEGV, current);
 	return 0;
@ -199,21 +190,14 @@ SYSCALL_DEFINE0(rt_sigreturn)
 		goto badframe;
 	if (__copy_from_user(&set.sig, &frame->uc.uc_sigmask, sizeof(set)))
 		goto badframe;
-
 	sigdelsetmask(&set, ~_BLOCKABLE);
-	spin_lock_irq(&current->sighand->siglock);
-	current->blocked = set;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
-
+	set_current_blocked(&set);
 	if (restore_sigregs(regs, &frame->uc.uc_mcontext))
 		goto badframe;
-
 	if (do_sigaltstack(&frame->uc.uc_stack, NULL,
 			   regs->gprs[15]) == -EFAULT)
 		goto badframe;
 	return regs->gprs[2];
-
 badframe:
 	force_sig(SIGSEGV, current);
 	return 0;
@ -385,14 +369,11 @@ give_sigsegv:
 	return -EFAULT;
 }

-/*
- * OK, we're invoking a handler
- */	
-
-static int
-handle_signal(unsigned long sig, struct k_sigaction *ka,
-	      siginfo_t *info, sigset_t *oldset, struct pt_regs * regs)
+static int handle_signal(unsigned long sig, struct k_sigaction *ka,
+			 siginfo_t *info, sigset_t *oldset,
+			 struct pt_regs *regs)
 {
+	sigset_t blocked;
 	int ret;

 	/* Set up the stack frame */
@ -400,17 +381,13 @@ handle_signal(unsigned long sig, struct k_sigaction *ka,
 		ret = setup_rt_frame(sig, ka, info, oldset, regs);
 	else
 		ret = setup_frame(sig, ka, oldset, regs);
-
-	if (ret == 0) {
-		spin_lock_irq(&current->sighand->siglock);
-		sigorsets(&current->blocked,&current->blocked,&ka->sa.sa_mask);
-		if (!(ka->sa.sa_flags & SA_NODEFER))
-			sigaddset(&current->blocked,sig);
-		recalc_sigpending();
-		spin_unlock_irq(&current->sighand->siglock);
-	}
-
-	return ret;
+	if (ret)
+		return ret;
+	sigorsets(&blocked, &current->blocked, &ka->sa.sa_mask);
+	if (!(ka->sa.sa_flags & SA_NODEFER))
+		sigaddset(&blocked, sig);
+	set_current_blocked(&blocked);
+	return 0;
 }

 /*
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@ -452,23 +452,27 @@ out:
 */
 int __cpuinit start_secondary(void *cpuvoid)
 {
-	/* Setup the cpu */
 	cpu_init();
 	preempt_disable();
-	/* Enable TOD clock interrupts on the secondary cpu. */
 	init_cpu_timer();
-	/* Enable cpu timer interrupts on the secondary cpu. */
 	init_cpu_vtimer();
-	/* Enable pfault pseudo page faults on this cpu. */
 	pfault_init();

-	/* call cpu notifiers */
 	notify_cpu_starting(smp_processor_id());
-	/* Mark this cpu as online */
 	ipi_call_lock();
 	set_cpu_online(smp_processor_id(), true);
 	ipi_call_unlock();
-	/* Switch on interrupts */
+	__ctl_clear_bit(0, 28); /* Disable lowcore protection */
+	S390_lowcore.restart_psw.mask = PSW_BASE_BITS | PSW_DEFAULT_KEY;
+	S390_lowcore.restart_psw.addr =
+		PSW_ADDR_AMODE | (unsigned long) psw_restart_int_handler;
+	__ctl_set_bit(0, 28); /* Enable lowcore protection */
+	/*
+	 * Wait until the cpu which brought this one up marked it
+	 * active before enabling interrupts.
+	 */
+	while (!cpumask_test_cpu(smp_processor_id(), cpu_active_mask))
+		cpu_relax();
 	local_irq_enable();
 	/* cpu_idle will call schedule for us */
 	cpu_idle();
@ -507,7 +511,11 @@ static int __cpuinit smp_alloc_lowcore(int cpu)
 	memset((char *)lowcore + 512, 0, sizeof(*lowcore) - 512);
 	lowcore->async_stack = async_stack + ASYNC_SIZE;
 	lowcore->panic_stack = panic_stack + PAGE_SIZE;
-
+	lowcore->restart_psw.mask = PSW_BASE_BITS | PSW_DEFAULT_KEY;
+	lowcore->restart_psw.addr =
+		PSW_ADDR_AMODE | (unsigned long) restart_int_handler;
+	if (user_mode != HOME_SPACE_MODE)
+		lowcore->restart_psw.mask |= PSW_ASC_HOME;
 #ifndef CONFIG_64BIT
 	if (MACHINE_HAS_IEEE) {
 		unsigned long save_area;
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@ -85,3 +85,19 @@ int memcpy_real(void *dest, void *src, size_t count)
 	arch_local_irq_restore(flags);
 	return rc;
 }
+
+/*
+ * Copy memory to absolute zero
+ */
+void copy_to_absolute_zero(void *dest, void *src, size_t count)
+{
+	unsigned long cr0;
+
+	BUG_ON((unsigned long) dest + count >= sizeof(struct _lowcore));
+	preempt_disable();
+	__ctl_store(cr0, 0, 0);
+	__ctl_clear_bit(0, 28); /* disable lowcore protection */
+	memcpy_real(dest + store_prefix(), src, count);
+	__ctl_load(cr0, 0, 0);
+	preempt_enable();
+}
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@ -528,6 +528,7 @@ static inline void page_table_free_pgste(unsigned long *table)
 static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm,
 						    unsigned long vmaddr)
 {
+	return NULL;
 }

 static inline void page_table_free_pgste(unsigned long *table)
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@ -11,6 +11,7 @@ config SUPERH
 	select HAVE_DMA_ATTRS
 	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
+	select ARCH_HAVE_NMI_SAFE_CMPXCHG if (GUSA_RB || CPU_SH4A)
 	select PERF_USE_VMALLOC
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_BZIP2
--- a/arch/sh/kernel/idle.c
+++ b/arch/sh/kernel/idle.c
@ -16,12 +16,13 @@
 #include <linux/thread_info.h>
 #include <linux/irqflags.h>
 #include <linux/smp.h>
+#include <linux/cpuidle.h>
 #include <asm/pgalloc.h>
 #include <asm/system.h>
 #include <linux/atomic.h>
 #include <asm/smp.h>

-void (*pm_idle)(void) = NULL;
+static void (*pm_idle)(void);

 static int hlt_counter;

@ -100,7 +101,8 @@ void cpu_idle(void)
 			local_irq_disable();
 			/* Don't trace irqs off for idle */
 			stop_critical_timings();
-			pm_idle();
+			if (cpuidle_idle_call())
+				pm_idle();
 			/*
 			 * Sanity check to ensure that pm_idle() returns
 			 * with IRQs enabled
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@ -54,6 +54,7 @@ config SPARC64
 	select HAVE_PERF_EVENTS
 	select PERF_USE_VMALLOC
 	select IRQ_PREFLOW_FASTEOI
+	select ARCH_HAVE_NMI_SAFE_CMPXCHG

 config ARCH_DEFCONFIG
 	string
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@ -16,3 +16,8 @@ header-y += traps.h
 header-y += uctx.h
 header-y += utrap.h
 header-y += watchdog.h
+
+generic-y += div64.h
+generic-y += local64.h
+generic-y += irq_regs.h
+generic-y += local.h
--- a/arch/sparc/include/asm/bitops_64.h
+++ b/arch/sparc/include/asm/bitops_64.h
@ -26,61 +26,28 @@ extern void change_bit(unsigned long nr, volatile unsigned long *addr);
 #define smp_mb__before_clear_bit()	barrier()
 #define smp_mb__after_clear_bit()	barrier()

-#include <asm-generic/bitops/ffz.h>
-#include <asm-generic/bitops/__ffs.h>
 #include <asm-generic/bitops/fls.h>
 #include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/fls64.h>

 #ifdef __KERNEL__

+extern int ffs(int x);
+extern unsigned long __ffs(unsigned long);
+
+#include <asm-generic/bitops/ffz.h>
 #include <asm-generic/bitops/sched.h>
-#include <asm-generic/bitops/ffs.h>

 /*
 * hweightN: returns the hamming weight (i.e. the number
 * of bits set) of a N-bit word
 */

-#ifdef ULTRA_HAS_POPULATION_COUNT
+extern unsigned long __arch_hweight64(__u64 w);
+extern unsigned int __arch_hweight32(unsigned int w);
+extern unsigned int __arch_hweight16(unsigned int w);
+extern unsigned int __arch_hweight8(unsigned int w);

-static inline unsigned int __arch_hweight64(unsigned long w)
-{
-	unsigned int res;
-
-	__asm__ ("popc %1,%0" : "=r" (res) : "r" (w));
-	return res;
-}
-
-static inline unsigned int __arch_hweight32(unsigned int w)
-{
-	unsigned int res;
-
-	__asm__ ("popc %1,%0" : "=r" (res) : "r" (w & 0xffffffff));
-	return res;
-}
-
-static inline unsigned int __arch_hweight16(unsigned int w)
-{
-	unsigned int res;
-
-	__asm__ ("popc %1,%0" : "=r" (res) : "r" (w & 0xffff));
-	return res;
-}
-
-static inline unsigned int __arch_hweight8(unsigned int w)
-{
-	unsigned int res;
-
-	__asm__ ("popc %1,%0" : "=r" (res) : "r" (w & 0xff));
-	return res;
-}
-
-#else
-
-#include <asm-generic/bitops/arch_hweight.h>
-
-#endif
 #include <asm-generic/bitops/const_hweight.h>
 #include <asm-generic/bitops/lock.h>
 #endif /* __KERNEL__ */
--- a/arch/sparc/include/asm/div64.h
+++ b/arch/sparc/include/asm/div64.h
@ -1 +0,0 @@
-#include <asm-generic/div64.h>
--- a/arch/sparc/include/asm/elf_64.h
+++ b/arch/sparc/include/asm/elf_64.h
@ -59,15 +59,33 @@
 #define R_SPARC_6		45

 /* Bits present in AT_HWCAP, primarily for Sparc32.  */
+#define HWCAP_SPARC_FLUSH       0x00000001
+#define HWCAP_SPARC_STBAR       0x00000002
+#define HWCAP_SPARC_SWAP        0x00000004
+#define HWCAP_SPARC_MULDIV      0x00000008
+#define HWCAP_SPARC_V9		0x00000010
+#define HWCAP_SPARC_ULTRA3	0x00000020
+#define HWCAP_SPARC_BLKINIT	0x00000040
+#define HWCAP_SPARC_N2		0x00000080

-#define HWCAP_SPARC_FLUSH       1    /* CPU supports flush instruction. */
-#define HWCAP_SPARC_STBAR       2
-#define HWCAP_SPARC_SWAP        4
-#define HWCAP_SPARC_MULDIV      8
-#define HWCAP_SPARC_V9		16
-#define HWCAP_SPARC_ULTRA3	32
-#define HWCAP_SPARC_BLKINIT	64
-#define HWCAP_SPARC_N2		128
+/* Solaris compatible AT_HWCAP bits. */
+#define AV_SPARC_MUL32		0x00000100 /* 32x32 multiply is efficient */
+#define AV_SPARC_DIV32		0x00000200 /* 32x32 divide is efficient */
+#define AV_SPARC_FSMULD		0x00000400 /* 'fsmuld' is efficient */
+#define AV_SPARC_V8PLUS		0x00000800 /* v9 insn available to 32bit */
+#define AV_SPARC_POPC		0x00001000 /* 'popc' is efficient */
+#define AV_SPARC_VIS		0x00002000 /* VIS insns available */
+#define AV_SPARC_VIS2		0x00004000 /* VIS2 insns available */
+#define AV_SPARC_ASI_BLK_INIT	0x00008000 /* block init ASIs available */
+#define AV_SPARC_FMAF		0x00010000 /* fused multiply-add */
+#define AV_SPARC_VIS3		0x00020000 /* VIS3 insns available */
+#define AV_SPARC_HPC		0x00040000 /* HPC insns available */
+#define AV_SPARC_RANDOM		0x00080000 /* 'random' insn available */
+#define AV_SPARC_TRANS		0x00100000 /* transaction insns available */
+#define AV_SPARC_FJFMAU		0x00200000 /* unfused multiply-add */
+#define AV_SPARC_IMA		0x00400000 /* integer multiply-add */
+#define AV_SPARC_ASI_CACHE_SPARING \
+				0x00800000 /* cache sparing ASIs available */

 #define CORE_DUMP_USE_REGSET

@ -162,33 +180,8 @@ typedef struct {
 #define ELF_ET_DYN_BASE		0x0000010000000000UL
 #define COMPAT_ELF_ET_DYN_BASE	0x0000000070000000UL

-
-/* This yields a mask that user programs can use to figure out what
-   instruction set this cpu supports.  */
-
-/* On Ultra, we support all of the v8 capabilities. */
-static inline unsigned int sparc64_elf_hwcap(void)
-{
-	unsigned int cap = (HWCAP_SPARC_FLUSH | HWCAP_SPARC_STBAR |
-			    HWCAP_SPARC_SWAP | HWCAP_SPARC_MULDIV |
-			    HWCAP_SPARC_V9);
-
-	if (tlb_type == cheetah || tlb_type == cheetah_plus)
-		cap |= HWCAP_SPARC_ULTRA3;
-	else if (tlb_type == hypervisor) {
-		if (sun4v_chip_type == SUN4V_CHIP_NIAGARA1 ||
-		    sun4v_chip_type == SUN4V_CHIP_NIAGARA2 ||
-		    sun4v_chip_type == SUN4V_CHIP_NIAGARA3)
-			cap |= HWCAP_SPARC_BLKINIT;
-		if (sun4v_chip_type == SUN4V_CHIP_NIAGARA2 ||
-		    sun4v_chip_type == SUN4V_CHIP_NIAGARA3)
-			cap |= HWCAP_SPARC_N2;
-	}
-
-	return cap;
-}
-
-#define ELF_HWCAP	sparc64_elf_hwcap()
+extern unsigned long sparc64_elf_hwcap;
+#define ELF_HWCAP	sparc64_elf_hwcap

 /* This yields a string that ld.so will use to load implementation
   specific libraries for optimization.  This is more specific in
--- a/arch/sparc/include/asm/hypervisor.h
+++ b/arch/sparc/include/asm/hypervisor.h
@ -2927,6 +2927,13 @@ extern unsigned long sun4v_ncs_request(unsigned long request,
 #define HV_FAST_FIRE_GET_PERFREG	0x120
 #define HV_FAST_FIRE_SET_PERFREG	0x121

+#define HV_FAST_REBOOT_DATA_SET		0x172
+
+#ifndef __ASSEMBLY__
+extern unsigned long sun4v_reboot_data_set(unsigned long ra,
+					   unsigned long len);
+#endif
+
 /* Function numbers for HV_CORE_TRAP.  */
 #define HV_CORE_SET_VER			0x00
 #define HV_CORE_PUTCHAR			0x01
@ -2940,11 +2947,17 @@ extern unsigned long sun4v_ncs_request(unsigned long request,
 #define HV_GRP_CORE			0x0001
 #define HV_GRP_INTR			0x0002
 #define HV_GRP_SOFT_STATE		0x0003
+#define HV_GRP_TM			0x0080
 #define HV_GRP_PCI			0x0100
 #define HV_GRP_LDOM			0x0101
 #define HV_GRP_SVC_CHAN			0x0102
 #define HV_GRP_NCS			0x0103
 #define HV_GRP_RNG			0x0104
+#define HV_GRP_PBOOT			0x0105
+#define HV_GRP_TPM			0x0107
+#define HV_GRP_SDIO			0x0108
+#define HV_GRP_SDIO_ERR			0x0109
+#define HV_GRP_REBOOT_DATA		0x0110
 #define HV_GRP_NIAG_PERF		0x0200
 #define HV_GRP_FIRE_PERF		0x0201
 #define HV_GRP_N2_CPU			0x0202
--- a/arch/sparc/include/asm/irq_regs.h
+++ b/arch/sparc/include/asm/irq_regs.h
@ -1 +0,0 @@
-#include <asm-generic/irq_regs.h>
--- a/arch/sparc/include/asm/local.h
+++ b/arch/sparc/include/asm/local.h
@ -1,6 +0,0 @@
-#ifndef _SPARC_LOCAL_H
-#define _SPARC_LOCAL_H
-
-#include <asm-generic/local.h>
-
-#endif
--- a/arch/sparc/include/asm/local64.h
+++ b/arch/sparc/include/asm/local64.h
@ -1 +0,0 @@
-#include <asm-generic/local64.h>
--- a/arch/sparc/include/asm/tsb.h
+++ b/arch/sparc/include/asm/tsb.h
@ -133,29 +133,6 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	sub	TSB, 0x8, TSB;   \
 	TSB_STORE(TSB, TAG);

-#define KTSB_LOAD_QUAD(TSB, REG) \
-	ldda		[TSB] ASI_NUCLEUS_QUAD_LDD, REG;
-
-#define KTSB_STORE(ADDR, VAL) \
-	stxa		VAL, [ADDR] ASI_N;
-
-#define KTSB_LOCK_TAG(TSB, REG1, REG2)	\
-99:	lduwa	[TSB] ASI_N, REG1;	\
-	sethi	%hi(TSB_TAG_LOCK_HIGH), REG2;\
-	andcc	REG1, REG2, %g0;	\
-	bne,pn	%icc, 99b;		\
-	 nop;				\
-	casa	[TSB] ASI_N, REG1, REG2;\
-	cmp	REG1, REG2;		\
-	bne,pn	%icc, 99b;		\
-	 nop;				\
-
-#define KTSB_WRITE(TSB, TTE, TAG) \
-	add	TSB, 0x8, TSB;   \
-	stxa	TTE, [TSB] ASI_N;     \
-	sub	TSB, 0x8, TSB;   \
-	stxa	TAG, [TSB] ASI_N;
-
 	/* Do a kernel page table walk.  Leaves physical PTE pointer in
 	 * REG1.  Jumps to FAIL_LABEL on early page table walk termination.
 	 * VADDR will not be clobbered, but REG2 will.
@ -239,6 +216,8 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	(KERNEL_TSB_SIZE_BYTES / 16)
 #define KERNEL_TSB4M_NENTRIES	4096

+#define KTSB_PHYS_SHIFT		15
+
 	/* Do a kernel TSB lookup at tl>0 on VADDR+TAG, branch to OK_LABEL
 	 * on TSB hit.  REG1, REG2, REG3, and REG4 are used as temporaries
 	 * and the found TTE will be left in REG1.  REG3 and REG4 must
@ -247,13 +226,22 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	 * VADDR and TAG will be preserved and not clobbered by this macro.
 	 */
 #define KERN_TSB_LOOKUP_TL1(VADDR, TAG, REG1, REG2, REG3, REG4, OK_LABEL) \
-	sethi		%hi(swapper_tsb), REG1; \
+661:	sethi		%hi(swapper_tsb), REG1;			\
 	or		REG1, %lo(swapper_tsb), REG1; \
+	.section	.swapper_tsb_phys_patch, "ax"; \
+	.word		661b; \
+	.previous; \
+661:	nop; \
+	.section	.tsb_ldquad_phys_patch, "ax"; \
+	.word		661b; \
+	sllx		REG1, KTSB_PHYS_SHIFT, REG1; \
+	sllx		REG1, KTSB_PHYS_SHIFT, REG1; \
+	.previous; \
 	srlx		VADDR, PAGE_SHIFT, REG2; \
 	and		REG2, (KERNEL_TSB_NENTRIES - 1), REG2; \
 	sllx		REG2, 4, REG2; \
 	add		REG1, REG2, REG2; \
-	KTSB_LOAD_QUAD(REG2, REG3); \
+	TSB_LOAD_QUAD(REG2, REG3); \
 	cmp		REG3, TAG; \
 	be,a,pt		%xcc, OK_LABEL; \
 	 mov		REG4, REG1;
@ -263,12 +251,21 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	 * we can make use of that for the index computation.
 	 */
 #define KERN_TSB4M_LOOKUP_TL1(TAG, REG1, REG2, REG3, REG4, OK_LABEL) \
-	sethi		%hi(swapper_4m_tsb), REG1; \
+661:	sethi		%hi(swapper_4m_tsb), REG1;	     \
 	or		REG1, %lo(swapper_4m_tsb), REG1; \
+	.section	.swapper_4m_tsb_phys_patch, "ax"; \
+	.word		661b; \
+	.previous; \
+661:	nop; \
+	.section	.tsb_ldquad_phys_patch, "ax"; \
+	.word		661b; \
+	sllx		REG1, KTSB_PHYS_SHIFT, REG1; \
+	sllx		REG1, KTSB_PHYS_SHIFT, REG1; \
+	.previous; \
 	and		TAG, (KERNEL_TSB4M_NENTRIES - 1), REG2; \
 	sllx		REG2, 4, REG2; \
 	add		REG1, REG2, REG2; \
-	KTSB_LOAD_QUAD(REG2, REG3); \
+	TSB_LOAD_QUAD(REG2, REG3); \
 	cmp		REG3, TAG; \
 	be,a,pt		%xcc, OK_LABEL; \
 	 mov		REG4, REG1;
--- a/arch/sparc/kernel/cpu.c
+++ b/arch/sparc/kernel/cpu.c
@ -396,6 +396,7 @@ static int show_cpuinfo(struct seq_file *m, void *__unused)
 		   , cpu_data(0).clock_tick
 #endif
 		);
+	cpucap_info(m);
 #ifdef CONFIG_SMP
 	smp_bogo(m);
 #endif
--- a/arch/sparc/kernel/ds.c
+++ b/arch/sparc/kernel/ds.c
@ -15,12 +15,15 @@
 #include <linux/reboot.h>
 #include <linux/cpu.h>

+#include <asm/hypervisor.h>
 #include <asm/ldc.h>
 #include <asm/vio.h>
 #include <asm/mdesc.h>
 #include <asm/head.h>
 #include <asm/irq.h>

+#include "kernel.h"
+
 #define DRV_MODULE_NAME		"ds"
 #define PFX DRV_MODULE_NAME	": "
 #define DRV_MODULE_VERSION	"1.0"
@ -828,18 +831,32 @@ void ldom_set_var(const char *var, const char *value)
 	}
 }

+static char full_boot_str[256] __attribute__((aligned(32)));
+static int reboot_data_supported;
+
 void ldom_reboot(const char *boot_command)
 {
 	/* Don't bother with any of this if the boot_command
 	 * is empty.
 	 */
 	if (boot_command && strlen(boot_command)) {
-		char full_boot_str[256];
+		unsigned long len;

 		strcpy(full_boot_str, "boot ");
 		strcpy(full_boot_str + strlen("boot "), boot_command);
+		len = strlen(full_boot_str);

-		ldom_set_var("reboot-command", full_boot_str);
+		if (reboot_data_supported) {
+			unsigned long ra = kimage_addr_to_ra(full_boot_str);
+			unsigned long hv_ret;
+
+			hv_ret = sun4v_reboot_data_set(ra, len);
+			if (hv_ret != HV_EOK)
+				pr_err("SUN4V: Unable to set reboot data "
+				       "hv_ret=%lu\n", hv_ret);
+		} else {
+			ldom_set_var("reboot-command", full_boot_str);
+		}
 	}
 	sun4v_mach_sir();
 }
@ -1237,6 +1254,15 @@ static struct vio_driver ds_driver = {

 static int __init ds_init(void)
 {
+	unsigned long hv_ret, major, minor;
+
+	hv_ret = sun4v_get_version(HV_GRP_REBOOT_DATA, &major, &minor);
+	if (hv_ret == HV_EOK) {
+		pr_info("SUN4V: Reboot data supported (maj=%lu,min=%lu).\n",
+			major, minor);
+		reboot_data_supported = 1;
+	}
+
 	kthread_run(ds_thread, NULL, "kldomd");

 	return vio_register_driver(&ds_driver);
--- a/arch/sparc/kernel/entry.h
+++ b/arch/sparc/kernel/entry.h
@ -42,6 +42,20 @@ extern void fpsave(unsigned long *fpregs, unsigned long *fsr,
 extern void fpload(unsigned long *fpregs, unsigned long *fsr);

 #else /* CONFIG_SPARC32 */
+struct popc_3insn_patch_entry {
+	unsigned int	addr;
+	unsigned int	insns[3];
+};
+extern struct popc_3insn_patch_entry __popc_3insn_patch,
+	__popc_3insn_patch_end;
+
+struct popc_6insn_patch_entry {
+	unsigned int	addr;
+	unsigned int	insns[6];
+};
+extern struct popc_6insn_patch_entry __popc_6insn_patch,
+	__popc_6insn_patch_end;
+
 extern void __init per_cpu_patch(void);
 extern void __init sun4v_patch(void);
 extern void __init boot_cpu_id_too_large(int cpu);
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@ -559,7 +559,7 @@ niagara2_patch:
 	 nop
 	call	niagara_patch_bzero
 	 nop
-	call	niagara2_patch_pageops
+	call	niagara_patch_pageops
 	 nop

 	ba,a,pt	%xcc, 80f
--- a/arch/sparc/kernel/hvapi.c
+++ b/arch/sparc/kernel/hvapi.c
@ -28,11 +28,17 @@ static struct api_info api_table[] = {
 	{ .group = HV_GRP_CORE,		.flags = FLAG_PRE_API	},
 	{ .group = HV_GRP_INTR,					},
 	{ .group = HV_GRP_SOFT_STATE,				},
+	{ .group = HV_GRP_TM,					},
 	{ .group = HV_GRP_PCI,		.flags = FLAG_PRE_API	},
 	{ .group = HV_GRP_LDOM,					},
 	{ .group = HV_GRP_SVC_CHAN,	.flags = FLAG_PRE_API	},
 	{ .group = HV_GRP_NCS,		.flags = FLAG_PRE_API	},
 	{ .group = HV_GRP_RNG,					},
+	{ .group = HV_GRP_PBOOT,				},
+	{ .group = HV_GRP_TPM,					},
+	{ .group = HV_GRP_SDIO,					},
+	{ .group = HV_GRP_SDIO_ERR,				},
+	{ .group = HV_GRP_REBOOT_DATA,				},
 	{ .group = HV_GRP_NIAG_PERF,	.flags = FLAG_PRE_API	},
 	{ .group = HV_GRP_FIRE_PERF,				},
 	{ .group = HV_GRP_N2_CPU,				},
--- a/arch/sparc/kernel/hvcalls.S
+++ b/arch/sparc/kernel/hvcalls.S
@ -798,3 +798,10 @@ ENTRY(sun4v_niagara2_setperf)
 	retl
 	 nop
 ENDPROC(sun4v_niagara2_setperf)
+
+ENTRY(sun4v_reboot_data_set)
+	mov	HV_FAST_REBOOT_DATA_SET, %o5
+	ta	HV_FAST_TRAP
+	retl
+	 nop
+ENDPROC(sun4v_reboot_data_set)
--- a/arch/sparc/kernel/kernel.h
+++ b/arch/sparc/kernel/kernel.h
@ -4,12 +4,27 @@
 #include <linux/interrupt.h>

 #include <asm/traps.h>
+#include <asm/head.h>
+#include <asm/io.h>

 /* cpu.c */
 extern const char *sparc_pmu_type;
 extern unsigned int fsr_storage;
 extern int ncpus_probed;

+#ifdef CONFIG_SPARC64
+/* setup_64.c */
+struct seq_file;
+extern void cpucap_info(struct seq_file *);
+
+static inline unsigned long kimage_addr_to_ra(const char *p)
+{
+	unsigned long val = (unsigned long) p;
+
+	return kern_base + (val - KERNBASE);
+}
+#endif
+
 #ifdef CONFIG_SPARC32
 /* cpu.c */
 extern void cpu_probe(void);
--- a/arch/sparc/kernel/ktlb.S
+++ b/arch/sparc/kernel/ktlb.S
@ -47,16 +47,16 @@ kvmap_itlb_tsb_miss:
 kvmap_itlb_vmalloc_addr:
 	KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_itlb_longpath)

-	KTSB_LOCK_TAG(%g1, %g2, %g7)
+	TSB_LOCK_TAG(%g1, %g2, %g7)

 	/* Load and check PTE.  */
 	ldxa		[%g5] ASI_PHYS_USE_EC, %g5
 	mov		1, %g7
 	sllx		%g7, TSB_TAG_INVALID_BIT, %g7
 	brgez,a,pn	%g5, kvmap_itlb_longpath
-	 KTSB_STORE(%g1, %g7)
+	 TSB_STORE(%g1, %g7)

-	KTSB_WRITE(%g1, %g5, %g6)
+	TSB_WRITE(%g1, %g5, %g6)

 	/* fallthrough to TLB load */

@ -102,9 +102,9 @@ kvmap_itlb_longpath:
 kvmap_itlb_obp:
 	OBP_TRANS_LOOKUP(%g4, %g5, %g2, %g3, kvmap_itlb_longpath)

-	KTSB_LOCK_TAG(%g1, %g2, %g7)
+	TSB_LOCK_TAG(%g1, %g2, %g7)

-	KTSB_WRITE(%g1, %g5, %g6)
+	TSB_WRITE(%g1, %g5, %g6)

 	ba,pt		%xcc, kvmap_itlb_load
 	 nop
@ -112,17 +112,17 @@ kvmap_itlb_obp:
 kvmap_dtlb_obp:
 	OBP_TRANS_LOOKUP(%g4, %g5, %g2, %g3, kvmap_dtlb_longpath)

-	KTSB_LOCK_TAG(%g1, %g2, %g7)
+	TSB_LOCK_TAG(%g1, %g2, %g7)

-	KTSB_WRITE(%g1, %g5, %g6)
+	TSB_WRITE(%g1, %g5, %g6)

 	ba,pt		%xcc, kvmap_dtlb_load
 	 nop

 	.align		32
 kvmap_dtlb_tsb4m_load:
-	KTSB_LOCK_TAG(%g1, %g2, %g7)
-	KTSB_WRITE(%g1, %g5, %g6)
+	TSB_LOCK_TAG(%g1, %g2, %g7)
+	TSB_WRITE(%g1, %g5, %g6)
 	ba,pt		%xcc, kvmap_dtlb_load
 	 nop

@ -222,16 +222,16 @@ kvmap_linear_patch:
 kvmap_dtlb_vmalloc_addr:
 	KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_dtlb_longpath)

-	KTSB_LOCK_TAG(%g1, %g2, %g7)
+	TSB_LOCK_TAG(%g1, %g2, %g7)

 	/* Load and check PTE.  */
 	ldxa		[%g5] ASI_PHYS_USE_EC, %g5
 	mov		1, %g7
 	sllx		%g7, TSB_TAG_INVALID_BIT, %g7
 	brgez,a,pn	%g5, kvmap_dtlb_longpath
-	 KTSB_STORE(%g1, %g7)
+	 TSB_STORE(%g1, %g7)

-	KTSB_WRITE(%g1, %g5, %g6)
+	TSB_WRITE(%g1, %g5, %g6)

 	/* fallthrough to TLB load */

--- a/arch/sparc/kernel/mdesc.c
+++ b/arch/sparc/kernel/mdesc.c
@ -508,6 +508,8 @@ const char *mdesc_node_name(struct mdesc_handle *hp, u64 node)
 }
 EXPORT_SYMBOL(mdesc_node_name);

+static u64 max_cpus = 64;
+
 static void __init report_platform_properties(void)
 {
 	struct mdesc_handle *hp = mdesc_grab();
@ -543,8 +545,10 @@ static void __init report_platform_properties(void)
 	if (v)
 		printk("PLATFORM: watchdog-max-timeout [%llu ms]\n", *v);
 	v = mdesc_get_property(hp, pn, "max-cpus", NULL);
-	if (v)
-		printk("PLATFORM: max-cpus [%llu]\n", *v);
+	if (v) {
+		max_cpus = *v;
+		printk("PLATFORM: max-cpus [%llu]\n", max_cpus);
+	}

 #ifdef CONFIG_SMP
 	{
@ -715,7 +719,7 @@ static void __cpuinit set_proc_ids(struct mdesc_handle *hp)
 }

 static void __cpuinit get_one_mondo_bits(const u64 *p, unsigned int *mask,
-					 unsigned char def)
+					 unsigned long def, unsigned long max)
 {
 	u64 val;

@ -726,6 +730,9 @@ static void __cpuinit get_one_mondo_bits(const u64 *p, unsigned int *mask,
 	if (!val || val >= 64)
 		goto use_default;

+	if (val > max)
+		val = max;
+
 	*mask = ((1U << val) * 64U) - 1U;
 	return;

@ -736,19 +743,28 @@ use_default:
 static void __cpuinit get_mondo_data(struct mdesc_handle *hp, u64 mp,
 				     struct trap_per_cpu *tb)
 {
+	static int printed;
 	const u64 *val;

 	val = mdesc_get_property(hp, mp, "q-cpu-mondo-#bits", NULL);
-	get_one_mondo_bits(val, &tb->cpu_mondo_qmask, 7);
+	get_one_mondo_bits(val, &tb->cpu_mondo_qmask, 7, ilog2(max_cpus * 2));

 	val = mdesc_get_property(hp, mp, "q-dev-mondo-#bits", NULL);
-	get_one_mondo_bits(val, &tb->dev_mondo_qmask, 7);
+	get_one_mondo_bits(val, &tb->dev_mondo_qmask, 7, 8);

 	val = mdesc_get_property(hp, mp, "q-resumable-#bits", NULL);
-	get_one_mondo_bits(val, &tb->resum_qmask, 6);
+	get_one_mondo_bits(val, &tb->resum_qmask, 6, 7);

 	val = mdesc_get_property(hp, mp, "q-nonresumable-#bits", NULL);
-	get_one_mondo_bits(val, &tb->nonresum_qmask, 2);
+	get_one_mondo_bits(val, &tb->nonresum_qmask, 2, 2);
+	if (!printed++) {
+		pr_info("SUN4V: Mondo queue sizes "
+			"[cpu(%u) dev(%u) r(%u) nr(%u)]\n",
+			tb->cpu_mondo_qmask + 1,
+			tb->dev_mondo_qmask + 1,
+			tb->resum_qmask + 1,
+			tb->nonresum_qmask + 1);
+	}
 }

 static void * __cpuinit mdesc_iterate_over_cpus(void *(*func)(struct mdesc_handle *, u64, int, void *), void *arg, cpumask_t *mask)
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@ -29,6 +29,7 @@
 #include <linux/interrupt.h>
 #include <linux/cpu.h>
 #include <linux/initrd.h>
+#include <linux/module.h>

 #include <asm/system.h>
 #include <asm/io.h>
@ -46,6 +47,8 @@
 #include <asm/mmu.h>
 #include <asm/ns87303.h>
 #include <asm/btext.h>
+#include <asm/elf.h>
+#include <asm/mdesc.h>

 #ifdef CONFIG_IP_PNP
 #include <net/ipconfig.h>
@ -269,6 +272,40 @@ void __init sun4v_patch(void)
 	sun4v_hvapi_init();
 }

+static void __init popc_patch(void)
+{
+	struct popc_3insn_patch_entry *p3;
+	struct popc_6insn_patch_entry *p6;
+
+	p3 = &__popc_3insn_patch;
+	while (p3 < &__popc_3insn_patch_end) {
+		unsigned long i, addr = p3->addr;
+
+		for (i = 0; i < 3; i++) {
+			*(unsigned int *) (addr +  (i * 4)) = p3->insns[i];
+			wmb();
+			__asm__ __volatile__("flush	%0"
+					     : : "r" (addr +  (i * 4)));
+		}
+
+		p3++;
+	}
+
+	p6 = &__popc_6insn_patch;
+	while (p6 < &__popc_6insn_patch_end) {
+		unsigned long i, addr = p6->addr;
+
+		for (i = 0; i < 6; i++) {
+			*(unsigned int *) (addr +  (i * 4)) = p6->insns[i];
+			wmb();
+			__asm__ __volatile__("flush	%0"
+					     : : "r" (addr +  (i * 4)));
+		}
+
+		p6++;
+	}
+}
+
 #ifdef CONFIG_SMP
 void __init boot_cpu_id_too_large(int cpu)
 {
@ -278,6 +315,154 @@ void __init boot_cpu_id_too_large(int cpu)
 }
 #endif

+/* On Ultra, we support all of the v8 capabilities. */
+unsigned long sparc64_elf_hwcap = (HWCAP_SPARC_FLUSH | HWCAP_SPARC_STBAR |
+				   HWCAP_SPARC_SWAP | HWCAP_SPARC_MULDIV |
+				   HWCAP_SPARC_V9);
+EXPORT_SYMBOL(sparc64_elf_hwcap);
+
+static const char *hwcaps[] = {
+	"flush", "stbar", "swap", "muldiv", "v9",
+	"ultra3", "blkinit", "n2",
+
+	/* These strings are as they appear in the machine description
+	 * 'hwcap-list' property for cpu nodes.
+	 */
+	"mul32", "div32", "fsmuld", "v8plus", "popc", "vis", "vis2",
+	"ASIBlkInit", "fmaf", "vis3", "hpc", "random", "trans", "fjfmau",
+	"ima", "cspare",
+};
+
+void cpucap_info(struct seq_file *m)
+{
+	unsigned long caps = sparc64_elf_hwcap;
+	int i, printed = 0;
+
+	seq_puts(m, "cpucaps\t\t: ");
+	for (i = 0; i < ARRAY_SIZE(hwcaps); i++) {
+		unsigned long bit = 1UL << i;
+		if (caps & bit) {
+			seq_printf(m, "%s%s",
+				   printed ? "," : "", hwcaps[i]);
+			printed++;
+		}
+	}
+	seq_putc(m, '\n');
+}
+
+static void __init report_hwcaps(unsigned long caps)
+{
+	int i, printed = 0;
+
+	printk(KERN_INFO "CPU CAPS: [");
+	for (i = 0; i < ARRAY_SIZE(hwcaps); i++) {
+		unsigned long bit = 1UL << i;
+		if (caps & bit) {
+			printk(KERN_CONT "%s%s",
+			       printed ? "," : "", hwcaps[i]);
+			if (++printed == 8) {
+				printk(KERN_CONT "]\n");
+				printk(KERN_INFO "CPU CAPS: [");
+				printed = 0;
+			}
+		}
+	}
+	printk(KERN_CONT "]\n");
+}
+
+static unsigned long __init mdesc_cpu_hwcap_list(void)
+{
+	struct mdesc_handle *hp;
+	unsigned long caps = 0;
+	const char *prop;
+	int len;
+	u64 pn;
+
+	hp = mdesc_grab();
+	if (!hp)
+		return 0;
+
+	pn = mdesc_node_by_name(hp, MDESC_NODE_NULL, "cpu");
+	if (pn == MDESC_NODE_NULL)
+		goto out;
+
+	prop = mdesc_get_property(hp, pn, "hwcap-list", &len);
+	if (!prop)
+		goto out;
+
+	while (len) {
+		int i, plen;
+
+		for (i = 0; i < ARRAY_SIZE(hwcaps); i++) {
+			unsigned long bit = 1UL << i;
+
+			if (!strcmp(prop, hwcaps[i])) {
+				caps |= bit;
+				break;
+			}
+		}
+
+		plen = strlen(prop) + 1;
+		prop += plen;
+		len -= plen;
+	}
+
+out:
+	mdesc_release(hp);
+	return caps;
+}
+
+/* This yields a mask that user programs can use to figure out what
+ * instruction set this cpu supports.
+ */
+static void __init init_sparc64_elf_hwcap(void)
+{
+	unsigned long cap = sparc64_elf_hwcap;
+	unsigned long mdesc_caps;
+
+	if (tlb_type == cheetah || tlb_type == cheetah_plus)
+		cap |= HWCAP_SPARC_ULTRA3;
+	else if (tlb_type == hypervisor) {
+		if (sun4v_chip_type == SUN4V_CHIP_NIAGARA1 ||
+		    sun4v_chip_type == SUN4V_CHIP_NIAGARA2 ||
+		    sun4v_chip_type == SUN4V_CHIP_NIAGARA3)
+			cap |= HWCAP_SPARC_BLKINIT;
+		if (sun4v_chip_type == SUN4V_CHIP_NIAGARA2 ||
+		    sun4v_chip_type == SUN4V_CHIP_NIAGARA3)
+			cap |= HWCAP_SPARC_N2;
+	}
+
+	cap |= (AV_SPARC_MUL32 | AV_SPARC_DIV32 | AV_SPARC_V8PLUS);
+
+	mdesc_caps = mdesc_cpu_hwcap_list();
+	if (!mdesc_caps) {
+		if (tlb_type == spitfire)
+			cap |= AV_SPARC_VIS;
+		if (tlb_type == cheetah || tlb_type == cheetah_plus)
+			cap |= AV_SPARC_VIS | AV_SPARC_VIS2;
+		if (tlb_type == cheetah_plus)
+			cap |= AV_SPARC_POPC;
+		if (tlb_type == hypervisor) {
+			if (sun4v_chip_type == SUN4V_CHIP_NIAGARA1)
+				cap |= AV_SPARC_ASI_BLK_INIT;
+			if (sun4v_chip_type == SUN4V_CHIP_NIAGARA2 ||
+			    sun4v_chip_type == SUN4V_CHIP_NIAGARA3)
+				cap |= (AV_SPARC_VIS | AV_SPARC_VIS2 |
+					AV_SPARC_ASI_BLK_INIT |
+					AV_SPARC_POPC);
+			if (sun4v_chip_type == SUN4V_CHIP_NIAGARA3)
+				cap |= (AV_SPARC_VIS3 | AV_SPARC_HPC |
+					AV_SPARC_FMAF);
+		}
+	}
+	sparc64_elf_hwcap = cap | mdesc_caps;
+
+	report_hwcaps(sparc64_elf_hwcap);
+
+	if (sparc64_elf_hwcap & AV_SPARC_POPC)
+		popc_patch();
+}
+
 void __init setup_arch(char **cmdline_p)
 {
 	/* Initialize PROM console and command line. */
@ -337,6 +522,7 @@ void __init setup_arch(char **cmdline_p)
 	init_cur_cpu_trap(current_thread_info());

 	paging_init();
+	init_sparc64_elf_hwcap();
 }

 extern int stop_a_enabled;
--- a/arch/sparc/kernel/sparc_ksyms_64.c
+++ b/arch/sparc/kernel/sparc_ksyms_64.c
@ -8,6 +8,7 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/init.h>
+#include <linux/bitops.h>

 #include <asm/system.h>
 #include <asm/cpudata.h>
@ -38,5 +39,15 @@ EXPORT_SYMBOL(sun4v_niagara_setperf);
 EXPORT_SYMBOL(sun4v_niagara2_getperf);
 EXPORT_SYMBOL(sun4v_niagara2_setperf);

+/* from hweight.S */
+EXPORT_SYMBOL(__arch_hweight8);
+EXPORT_SYMBOL(__arch_hweight16);
+EXPORT_SYMBOL(__arch_hweight32);
+EXPORT_SYMBOL(__arch_hweight64);
+
+/* from ffs_ffz.S */
+EXPORT_SYMBOL(ffs);
+EXPORT_SYMBOL(__ffs);
+
 /* Exporting a symbol from /init/main.c */
 EXPORT_SYMBOL(saved_command_line);
--- a/arch/sparc/kernel/sstate.c
+++ b/arch/sparc/kernel/sstate.c
@ -14,15 +14,10 @@
 #include <asm/head.h>
 #include <asm/io.h>

+#include "kernel.h"
+
 static int hv_supports_soft_state;

-static unsigned long kimage_addr_to_ra(const char *p)
-{
-	unsigned long val = (unsigned long) p;
-
-	return kern_base + (val - KERNBASE);
-}
-
 static void do_set_sstate(unsigned long state, const char *msg)
 {
 	unsigned long err;
--- a/arch/sparc/kernel/unaligned_64.c
+++ b/arch/sparc/kernel/unaligned_64.c
@ -22,6 +22,7 @@
 #include <linux/bitops.h>
 #include <linux/perf_event.h>
 #include <linux/ratelimit.h>
+#include <linux/bitops.h>
 #include <asm/fpumacro.h>

 enum direction {
@ -373,16 +374,11 @@ asmlinkage void kernel_unaligned_trap(struct pt_regs *regs, unsigned int insn)
 	}
 }

-static char popc_helper[] = {
-0, 1, 1, 2, 1, 2, 2, 3,
-1, 2, 2, 3, 2, 3, 3, 4, 
-};
-
 int handle_popc(u32 insn, struct pt_regs *regs)
 {
-	u64 value;
-	int ret, i, rd = ((insn >> 25) & 0x1f);
 	int from_kernel = (regs->tstate & TSTATE_PRIV) != 0;
+	int ret, rd = ((insn >> 25) & 0x1f);
+	u64 value;
 	                        
 	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, 0);
 	if (insn & 0x2000) {
@ -392,10 +388,7 @@ int handle_popc(u32 insn, struct pt_regs *regs)
 		maybe_flush_windows(0, insn & 0x1f, rd, from_kernel);
 		value = fetch_reg(insn & 0x1f, regs);
 	}
-	for (ret = 0, i = 0; i < 16; i++) {
-		ret += popc_helper[value & 0xf];
-		value >>= 4;
-	}
+	ret = hweight64(value);
 	if (rd < 16) {
 		if (rd)
 			regs->u_regs[rd] = ret;
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@ -107,7 +107,26 @@ SECTIONS
 		*(.sun4v_2insn_patch)
 		__sun4v_2insn_patch_end = .;
 	}
-
+	.swapper_tsb_phys_patch : {
+		__swapper_tsb_phys_patch = .;
+		*(.swapper_tsb_phys_patch)
+		__swapper_tsb_phys_patch_end = .;
+	}
+	.swapper_4m_tsb_phys_patch : {
+		__swapper_4m_tsb_phys_patch = .;
+		*(.swapper_4m_tsb_phys_patch)
+		__swapper_4m_tsb_phys_patch_end = .;
+	}
+	.popc_3insn_patch : {
+		__popc_3insn_patch = .;
+		*(.popc_3insn_patch)
+		__popc_3insn_patch_end = .;
+	}
+	.popc_6insn_patch : {
+		__popc_6insn_patch = .;
+		*(.popc_6insn_patch)
+		__popc_6insn_patch_end = .;
+	}
 	PERCPU_SECTION(SMP_CACHE_BYTES)

 	. = ALIGN(PAGE_SIZE);
--- a/arch/sparc/lib/Makefile
+++ b/arch/sparc/lib/Makefile
@ -31,13 +31,13 @@ lib-$(CONFIG_SPARC64) += NGmemcpy.o NGcopy_from_user.o NGcopy_to_user.o
 lib-$(CONFIG_SPARC64) += NGpatch.o NGpage.o NGbzero.o

 lib-$(CONFIG_SPARC64) += NG2memcpy.o NG2copy_from_user.o NG2copy_to_user.o
-lib-$(CONFIG_SPARC64) +=  NG2patch.o NG2page.o
+lib-$(CONFIG_SPARC64) +=  NG2patch.o

 lib-$(CONFIG_SPARC64) += GENmemcpy.o GENcopy_from_user.o GENcopy_to_user.o
 lib-$(CONFIG_SPARC64) += GENpatch.o GENpage.o GENbzero.o

 lib-$(CONFIG_SPARC64) += copy_in_user.o user_fixup.o memmove.o
-lib-$(CONFIG_SPARC64) += mcount.o ipcsum.o xor.o
+lib-$(CONFIG_SPARC64) += mcount.o ipcsum.o xor.o hweight.o ffs.o

 obj-y                 += iomap.o
 obj-$(CONFIG_SPARC32) += atomic32.o
--- a/arch/sparc/lib/NG2page.S
+++ b/arch/sparc/lib/NG2page.S
@ -1,61 +0,0 @@
-/* NG2page.S: Niagara-2 optimized clear and copy page.
- *
- * Copyright (C) 2007 (davem@davemloft.net)
- */
-
-#include <asm/asi.h>
-#include <asm/page.h>
-#include <asm/visasm.h>
-
-	.text
-	.align	32
-
-	/* This is heavily simplified from the sun4u variants
-	 * because Niagara-2 does not have any D-cache aliasing issues.
-	 */
-NG2copy_user_page:	/* %o0=dest, %o1=src, %o2=vaddr */
-	prefetch	[%o1 + 0x00], #one_read
-	prefetch	[%o1 + 0x40], #one_read
-	VISEntryHalf
-	set		PAGE_SIZE, %g7
-	sub		%o0, %o1, %g3
-1:	stxa		%g0, [%o1 + %g3] ASI_BLK_INIT_QUAD_LDD_P
-	subcc		%g7, 64, %g7
-	ldda		[%o1] ASI_BLK_P, %f0
-	stda		%f0, [%o1 + %g3] ASI_BLK_P
-	add		%o1, 64, %o1
-	bne,pt		%xcc, 1b
-	 prefetch	[%o1 + 0x40], #one_read
-	membar		#Sync
-	VISExitHalf
-	retl
-	 nop
-
-#define BRANCH_ALWAYS	0x10680000
-#define NOP		0x01000000
-#define NG_DO_PATCH(OLD, NEW)	\
-	sethi	%hi(NEW), %g1; \
-	or	%g1, %lo(NEW), %g1; \
-	sethi	%hi(OLD), %g2; \
-	or	%g2, %lo(OLD), %g2; \
-	sub	%g1, %g2, %g1; \
-	sethi	%hi(BRANCH_ALWAYS), %g3; \
-	sll	%g1, 11, %g1; \
-	srl	%g1, 11 + 2, %g1; \
-	or	%g3, %lo(BRANCH_ALWAYS), %g3; \
-	or	%g3, %g1, %g3; \
-	stw	%g3, [%g2]; \
-	sethi	%hi(NOP), %g3; \
-	or	%g3, %lo(NOP), %g3; \
-	stw	%g3, [%g2 + 0x4]; \
-	flush	%g2;
-
-	.globl	niagara2_patch_pageops
-	.type	niagara2_patch_pageops,#function
-niagara2_patch_pageops:
-	NG_DO_PATCH(copy_user_page, NG2copy_user_page)
-	NG_DO_PATCH(_clear_page, NGclear_page)
-	NG_DO_PATCH(clear_user_page, NGclear_user_page)
-	retl
-	 nop
-	.size	niagara2_patch_pageops,.-niagara2_patch_pageops
--- a/arch/sparc/lib/NGpage.S
+++ b/arch/sparc/lib/NGpage.S
@ -16,55 +16,91 @@
 	 */

 NGcopy_user_page:	/* %o0=dest, %o1=src, %o2=vaddr */
-	prefetch	[%o1 + 0x00], #one_read
-	mov		8, %g1
-	mov		16, %g2
-	mov		24, %g3
+	save		%sp, -192, %sp
+	rd		%asi, %g3
+	wr		%g0, ASI_BLK_INIT_QUAD_LDD_P, %asi
 	set		PAGE_SIZE, %g7
+	prefetch	[%i1 + 0x00], #one_read
+	prefetch	[%i1 + 0x40], #one_read

-1:	ldda		[%o1 + %g0] ASI_BLK_INIT_QUAD_LDD_P, %o2
-	ldda		[%o1 + %g2] ASI_BLK_INIT_QUAD_LDD_P, %o4
-	prefetch	[%o1 + 0x40], #one_read
-	add		%o1, 32, %o1
-	stxa		%o2, [%o0 + %g0] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%o3, [%o0 + %g1] ASI_BLK_INIT_QUAD_LDD_P
-	ldda		[%o1 + %g0] ASI_BLK_INIT_QUAD_LDD_P, %o2
-	stxa		%o4, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%o5, [%o0 + %g3] ASI_BLK_INIT_QUAD_LDD_P
-	ldda		[%o1 + %g2] ASI_BLK_INIT_QUAD_LDD_P, %o4
-	add		%o1, 32, %o1
-	add		%o0, 32, %o0
-	stxa		%o2, [%o0 + %g0] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%o3, [%o0 + %g1] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%o4, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%o5, [%o0 + %g3] ASI_BLK_INIT_QUAD_LDD_P
-	subcc		%g7, 64, %g7
+1:	prefetch	[%i1 + 0x80], #one_read
+	prefetch	[%i1 + 0xc0], #one_read
+	ldda		[%i1 + 0x00] %asi, %o2
+	ldda		[%i1 + 0x10] %asi, %o4
+	ldda		[%i1 + 0x20] %asi, %l2
+	ldda		[%i1 + 0x30] %asi, %l4
+	stxa		%o2, [%i0 + 0x00] %asi
+	stxa		%o3, [%i0 + 0x08] %asi
+	stxa		%o4, [%i0 + 0x10] %asi
+	stxa		%o5, [%i0 + 0x18] %asi
+	stxa		%l2, [%i0 + 0x20] %asi
+	stxa		%l3, [%i0 + 0x28] %asi
+	stxa		%l4, [%i0 + 0x30] %asi
+	stxa		%l5, [%i0 + 0x38] %asi
+	ldda		[%i1 + 0x40] %asi, %o2
+	ldda		[%i1 + 0x50] %asi, %o4
+	ldda		[%i1 + 0x60] %asi, %l2
+	ldda		[%i1 + 0x70] %asi, %l4
+	stxa		%o2, [%i0 + 0x40] %asi
+	stxa		%o3, [%i0 + 0x48] %asi
+	stxa		%o4, [%i0 + 0x50] %asi
+	stxa		%o5, [%i0 + 0x58] %asi
+	stxa		%l2, [%i0 + 0x60] %asi
+	stxa		%l3, [%i0 + 0x68] %asi
+	stxa		%l4, [%i0 + 0x70] %asi
+	stxa		%l5, [%i0 + 0x78] %asi
+	add		%i1, 128, %i1
+	subcc		%g7, 128, %g7
 	bne,pt		%xcc, 1b
-	 add		%o0, 32, %o0
+	 add		%i0, 128, %i0
+	wr		%g3, 0x0, %asi
 	membar		#Sync
-	retl
-	 nop
+	ret
+	 restore

-	.globl		NGclear_page, NGclear_user_page
+	.align		32
 NGclear_page:		/* %o0=dest */
 NGclear_user_page:	/* %o0=dest, %o1=vaddr */
-	mov		8, %g1
-	mov		16, %g2
-	mov		24, %g3
+	rd		%asi, %g3
+	wr		%g0, ASI_BLK_INIT_QUAD_LDD_P, %asi
 	set		PAGE_SIZE, %g7

-1:	stxa		%g0, [%o0 + %g0] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%g0, [%o0 + %g1] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%g0, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%g0, [%o0 + %g3] ASI_BLK_INIT_QUAD_LDD_P
-	add		%o0, 32, %o0
-	stxa		%g0, [%o0 + %g0] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%g0, [%o0 + %g1] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%g0, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P
-	stxa		%g0, [%o0 + %g3] ASI_BLK_INIT_QUAD_LDD_P
-	subcc		%g7, 64, %g7
+1:	stxa		%g0, [%o0 + 0x00] %asi
+	stxa		%g0, [%o0 + 0x08] %asi
+	stxa		%g0, [%o0 + 0x10] %asi
+	stxa		%g0, [%o0 + 0x18] %asi
+	stxa		%g0, [%o0 + 0x20] %asi
+	stxa		%g0, [%o0 + 0x28] %asi
+	stxa		%g0, [%o0 + 0x30] %asi
+	stxa		%g0, [%o0 + 0x38] %asi
+	stxa		%g0, [%o0 + 0x40] %asi
+	stxa		%g0, [%o0 + 0x48] %asi
+	stxa		%g0, [%o0 + 0x50] %asi
+	stxa		%g0, [%o0 + 0x58] %asi
+	stxa		%g0, [%o0 + 0x60] %asi
+	stxa		%g0, [%o0 + 0x68] %asi
+	stxa		%g0, [%o0 + 0x70] %asi
+	stxa		%g0, [%o0 + 0x78] %asi
+	stxa		%g0, [%o0 + 0x80] %asi
+	stxa		%g0, [%o0 + 0x88] %asi
+	stxa		%g0, [%o0 + 0x90] %asi
+	stxa		%g0, [%o0 + 0x98] %asi
+	stxa		%g0, [%o0 + 0xa0] %asi
+	stxa		%g0, [%o0 + 0xa8] %asi
+	stxa		%g0, [%o0 + 0xb0] %asi
+	stxa		%g0, [%o0 + 0xb8] %asi
+	stxa		%g0, [%o0 + 0xc0] %asi
+	stxa		%g0, [%o0 + 0xc8] %asi
+	stxa		%g0, [%o0 + 0xd0] %asi
+	stxa		%g0, [%o0 + 0xd8] %asi
+	stxa		%g0, [%o0 + 0xe0] %asi
+	stxa		%g0, [%o0 + 0xe8] %asi
+	stxa		%g0, [%o0 + 0xf0] %asi
+	stxa		%g0, [%o0 + 0xf8] %asi
+	subcc		%g7, 256, %g7
 	bne,pt		%xcc, 1b
-	 add		%o0, 32, %o0
+	 add		%o0, 256, %o0
+	wr		%g3, 0x0, %asi
 	membar		#Sync
 	retl
 	 nop
--- a/arch/sparc/lib/atomic32.c
+++ b/arch/sparc/lib/atomic32.c
@ -65,7 +65,7 @@ int __atomic_add_unless(atomic_t *v, int a, int u)
 	if (ret != u)
 		v->counter += a;
 	spin_unlock_irqrestore(ATOMIC_HASH(v), flags);
-	return ret != u;
+	return ret;
 }
 EXPORT_SYMBOL(__atomic_add_unless);

--- a/arch/sparc/lib/ffs.S
+++ b/arch/sparc/lib/ffs.S
@ -0,0 +1,84 @@
+#include <linux/linkage.h>
+
+	.register	%g2,#scratch
+
+	.text
+	.align	32
+
+ENTRY(ffs)
+	brnz,pt	%o0, 1f
+	 mov	1, %o1
+	retl
+	 clr	%o0
+	nop
+	nop
+ENTRY(__ffs)
+	sllx	%o0, 32, %g1		/* 1  */
+	srlx	%o0, 32, %g2
+
+	clr	%o1			/* 2  */
+	movrz	%g1, %g2, %o0
+
+	movrz	%g1, 32, %o1		/* 3  */
+1:	clr	%o2
+
+	sllx	%o0, (64 - 16), %g1	/* 4  */
+	srlx	%o0, 16, %g2
+
+	movrz	%g1, %g2, %o0		/* 5  */
+	clr	%o3
+
+	movrz	%g1, 16, %o2		/* 6  */
+	clr	%o4
+
+	and	%o0, 0xff, %g1		/* 7  */
+	srlx	%o0, 8, %g2
+
+	movrz	%g1, %g2, %o0		/* 8  */
+	clr	%o5
+
+	movrz	%g1, 8, %o3		/* 9  */
+	add	%o2, %o1, %o2
+
+	and	%o0, 0xf, %g1		/* 10 */
+	srlx	%o0, 4, %g2
+
+	movrz	%g1, %g2, %o0		/* 11 */
+	add	%o2, %o3, %o2
+
+	movrz	%g1, 4, %o4		/* 12 */
+
+	and	%o0, 0x3, %g1		/* 13 */
+	srlx	%o0, 2, %g2
+
+	movrz	%g1, %g2, %o0		/* 14 */
+	add	%o2, %o4, %o2
+
+	movrz	%g1, 2, %o5		/* 15 */
+
+	and	%o0, 0x1, %g1		/* 16 */
+
+	add	%o2, %o5, %o2		/* 17 */
+	xor	%g1, 0x1, %g1
+
+	retl				/* 18 */
+	 add	%o2, %g1, %o0
+ENDPROC(ffs)
+ENDPROC(__ffs)
+
+	.section	.popc_6insn_patch, "ax"
+	.word		ffs
+	brz,pn	%o0, 98f
+	 neg	%o0, %g1
+	xnor	%o0, %g1, %o1
+	popc	%o1, %o0
+98:	retl
+	 nop
+	.word		__ffs
+	neg	%o0, %g1
+	xnor	%o0, %g1, %o1
+	popc	%o1, %o0
+	retl
+	 sub	%o0, 1, %o0
+	nop
+	.previous
--- a/arch/sparc/lib/hweight.S
+++ b/arch/sparc/lib/hweight.S
@ -0,0 +1,51 @@
+#include <linux/linkage.h>
+
+	.text
+	.align	32
+ENTRY(__arch_hweight8)
+	ba,pt	%xcc, __sw_hweight8
+	 nop
+	nop
+ENDPROC(__arch_hweight8)
+	.section	.popc_3insn_patch, "ax"
+	.word		__arch_hweight8
+	sllx		%o0, 64-8, %g1
+	retl
+	 popc		%g1, %o0
+	.previous
+
+ENTRY(__arch_hweight16)
+	ba,pt	%xcc, __sw_hweight16
+	 nop
+	nop
+ENDPROC(__arch_hweight16)
+	.section	.popc_3insn_patch, "ax"
+	.word		__arch_hweight16
+	sllx		%o0, 64-16, %g1
+	retl
+	 popc		%g1, %o0
+	.previous
+
+ENTRY(__arch_hweight32)
+	ba,pt	%xcc, __sw_hweight32
+	 nop
+	nop
+ENDPROC(__arch_hweight32)
+	.section	.popc_3insn_patch, "ax"
+	.word		__arch_hweight32
+	sllx		%o0, 64-32, %g1
+	retl
+	 popc		%g1, %o0
+	.previous
+
+ENTRY(__arch_hweight64)
+	ba,pt	%xcc, __sw_hweight64
+	 nop
+	nop
+ENDPROC(__arch_hweight64)
+	.section	.popc_3insn_patch, "ax"
+	.word		__arch_hweight64
+	retl
+	 popc		%o0, %o0
+	nop
+	.previous
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@ -1597,6 +1597,44 @@ static void __init tsb_phys_patch(void)
 static struct hv_tsb_descr ktsb_descr[NUM_KTSB_DESCR];
 extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES];

+static void patch_one_ktsb_phys(unsigned int *start, unsigned int *end, unsigned long pa)
+{
+	pa >>= KTSB_PHYS_SHIFT;
+
+	while (start < end) {
+		unsigned int *ia = (unsigned int *)(unsigned long)*start;
+
+		ia[0] = (ia[0] & ~0x3fffff) | (pa >> 10);
+		__asm__ __volatile__("flush	%0" : : "r" (ia));
+
+		ia[1] = (ia[1] & ~0x3ff) | (pa & 0x3ff);
+		__asm__ __volatile__("flush	%0" : : "r" (ia + 1));
+
+		start++;
+	}
+}
+
+static void ktsb_phys_patch(void)
+{
+	extern unsigned int __swapper_tsb_phys_patch;
+	extern unsigned int __swapper_tsb_phys_patch_end;
+	unsigned long ktsb_pa;
+
+	ktsb_pa = kern_base + ((unsigned long)&swapper_tsb[0] - KERNBASE);
+	patch_one_ktsb_phys(&__swapper_tsb_phys_patch,
+			    &__swapper_tsb_phys_patch_end, ktsb_pa);
+#ifndef CONFIG_DEBUG_PAGEALLOC
+	{
+	extern unsigned int __swapper_4m_tsb_phys_patch;
+	extern unsigned int __swapper_4m_tsb_phys_patch_end;
+	ktsb_pa = (kern_base +
+		   ((unsigned long)&swapper_4m_tsb[0] - KERNBASE));
+	patch_one_ktsb_phys(&__swapper_4m_tsb_phys_patch,
+			    &__swapper_4m_tsb_phys_patch_end, ktsb_pa);
+	}
+#endif
+}
+
 static void __init sun4v_ktsb_init(void)
 {
 	unsigned long ktsb_pa;
@ -1716,8 +1754,10 @@ void __init paging_init(void)
 		sun4u_pgprot_init();

 	if (tlb_type == cheetah_plus ||
-	    tlb_type == hypervisor)
+	    tlb_type == hypervisor) {
 		tsb_phys_patch();
+		ktsb_phys_patch();
+	}

 	if (tlb_type == hypervisor) {
 		sun4v_patch_tlb_handlers();
--- a/arch/tile/Kconfig
+++ b/arch/tile/Kconfig
@ -12,6 +12,7 @@ config TILE
 	select GENERIC_PENDING_IRQ if SMP
 	select GENERIC_IRQ_SHOW
 	select SYS_HYPERVISOR
+	select ARCH_HAVE_NMI_SAFE_CMPXCHG if !M386

 # FIXME: investigate whether we need/want these options.
 #	select HAVE_IOREMAP_PROT
--- a/arch/tile/include/asm/Kbuild
+++ b/arch/tile/include/asm/Kbuild
@ -2,3 +2,41 @@ include include/asm-generic/Kbuild.asm

 header-y += ucontext.h
 header-y += hardwall.h
+
+generic-y += bug.h
+generic-y += bugs.h
+generic-y += cputime.h
+generic-y += device.h
+generic-y += div64.h
+generic-y += emergency-restart.h
+generic-y += errno.h
+generic-y += fb.h
+generic-y += fcntl.h
+generic-y += ioctl.h
+generic-y += ioctls.h
+generic-y += ipc.h
+generic-y += ipcbuf.h
+generic-y += irq_regs.h
+generic-y += kdebug.h
+generic-y += local.h
+generic-y += module.h
+generic-y += msgbuf.h
+generic-y += mutex.h
+generic-y += param.h
+generic-y += parport.h
+generic-y += poll.h
+generic-y += posix_types.h
+generic-y += resource.h
+generic-y += scatterlist.h
+generic-y += sembuf.h
+generic-y += serial.h
+generic-y += shmbuf.h
+generic-y += shmparam.h
+generic-y += socket.h
+generic-y += sockios.h
+generic-y += statfs.h
+generic-y += termbits.h
+generic-y += termios.h
+generic-y += types.h
+generic-y += ucontext.h
+generic-y += xor.h
--- a/arch/tile/include/asm/bug.h
+++ b/arch/tile/include/asm/bug.h
@ -1 +0,0 @@
-#include <asm-generic/bug.h>
--- a/arch/tile/include/asm/bugs.h
+++ b/arch/tile/include/asm/bugs.h
@ -1 +0,0 @@
-#include <asm-generic/bugs.h>
--- a/arch/tile/include/asm/cputime.h
+++ b/arch/tile/include/asm/cputime.h
@ -1 +0,0 @@
-#include <asm-generic/cputime.h>
--- a/arch/tile/include/asm/device.h
+++ b/arch/tile/include/asm/device.h
@ -1 +0,0 @@
-#include <asm-generic/device.h>
--- a/arch/tile/include/asm/div64.h
+++ b/arch/tile/include/asm/div64.h
@ -1 +0,0 @@
-#include <asm-generic/div64.h>
--- a/arch/tile/include/asm/emergency-restart.h
+++ b/arch/tile/include/asm/emergency-restart.h
@ -1 +0,0 @@
-#include <asm-generic/emergency-restart.h>
--- a/arch/tile/include/asm/errno.h
+++ b/arch/tile/include/asm/errno.h
@ -1 +0,0 @@
-#include <asm-generic/errno.h>
--- a/Show More
+++ b/Show More