Merge branch 'for-linus' of git://github.com/tiwai/sound

* 'for-linus' of git://github.com/tiwai/sound:
  ASoC: ssm2602: Re-enable oscillator after suspend
  ALSA: usb-audio: Check for possible chip NULL pointer before clearing probing flag
  ALSA: hda/realtek - Don't detect LO jack when identical with HP
  ALSA: hda/realtek - Avoid bogus HP-pin assignment
  ALSA: HDA: No power nids on 92HD93
  ASoC: omap-mcbsp: Do not attempt to change DAI sysclk if stream is active
diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX
index 1f89424..65bbd26 100644
--- a/Documentation/00-INDEX
+++ b/Documentation/00-INDEX
@@ -272,6 +272,8 @@
 	- how to get printk format specifiers right
 prio_tree.txt
 	- info on radix-priority-search-tree use for indexing vmas.
+ramoops.txt
+	- documentation of the ramoops oops/panic logging module.
 rbtree.txt
 	- info on what red-black trees are and what they are for.
 robust-futex-ABI.txt
diff --git a/Documentation/ABI/testing/sysfs-class-scsi_host b/Documentation/ABI/testing/sysfs-class-scsi_host
new file mode 100644
index 0000000..29a4f89
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-scsi_host
@@ -0,0 +1,13 @@
+What:		/sys/class/scsi_host/hostX/isci_id
+Date:		June 2011
+Contact:	Dave Jiang <dave.jiang@intel.com>
+Description:
+		This file contains the enumerated host ID for the Intel
+		SCU controller. The Intel(R) C600 Series Chipset SATA/SAS
+		Storage Control Unit embeds up to two 4-port controllers in
+		a single PCI device.  The controllers are enumerated in order
+		which usually means the lowest number scsi_host corresponds
+		with the first controller, but this association is not
+		guaranteed.  The 'isci_id' attribute unambiguously identifies
+		the controller index: '0' for the first controller,
+		'1' for the second.
diff --git a/Documentation/DocBook/media/v4l/controls.xml b/Documentation/DocBook/media/v4l/controls.xml
index 8516401..23fdf79 100644
--- a/Documentation/DocBook/media/v4l/controls.xml
+++ b/Documentation/DocBook/media/v4l/controls.xml
@@ -1455,7 +1455,7 @@
 	      </row>
 
 	      <row><entry></entry></row>
-	      <row>
+	      <row id="v4l2-mpeg-video-h264-vui-sar-idc">
 		<entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_H264_VUI_SAR_IDC</constant>&nbsp;</entry>
 		<entry>enum&nbsp;v4l2_mpeg_video_h264_vui_sar_idc</entry>
 	      </row>
@@ -1561,7 +1561,7 @@
 	      </row>
 
 	      <row><entry></entry></row>
-	      <row>
+	      <row id="v4l2-mpeg-video-h264-level">
 		<entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_H264_LEVEL</constant>&nbsp;</entry>
 		<entry>enum&nbsp;v4l2_mpeg_video_h264_level</entry>
 	      </row>
@@ -1641,7 +1641,7 @@
 	      </row>
 
 	      <row><entry></entry></row>
-	      <row>
+	      <row id="v4l2-mpeg-video-mpeg4-level">
 		<entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_MPEG4_LEVEL</constant>&nbsp;</entry>
 		<entry>enum&nbsp;v4l2_mpeg_video_mpeg4_level</entry>
 	      </row>
@@ -1689,9 +1689,9 @@
 	      </row>
 
 	      <row><entry></entry></row>
-	      <row>
+	      <row id="v4l2-mpeg-video-h264-profile">
 		<entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_H264_PROFILE</constant>&nbsp;</entry>
-		<entry>enum&nbsp;v4l2_mpeg_h264_profile</entry>
+		<entry>enum&nbsp;v4l2_mpeg_video_h264_profile</entry>
 	      </row>
 	      <row><entry spanname="descr">The profile information for H264.
 Applicable to the H264 encoder.
@@ -1774,9 +1774,9 @@
 	      </row>
 
 	      <row><entry></entry></row>
-	      <row>
+	      <row id="v4l2-mpeg-video-mpeg4-profile">
 		<entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_MPEG4_PROFILE</constant>&nbsp;</entry>
-		<entry>enum&nbsp;v4l2_mpeg_mpeg4_profile</entry>
+		<entry>enum&nbsp;v4l2_mpeg_video_mpeg4_profile</entry>
 	      </row>
 	      <row><entry spanname="descr">The profile information for MPEG4.
 Applicable to the MPEG4 encoder.
@@ -1820,9 +1820,9 @@
 	      </row>
 
 	      <row><entry></entry></row>
-	      <row>
+	      <row id="v4l2-mpeg-video-multi-slice-mode">
 		<entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_MULTI_SLICE_MODE</constant>&nbsp;</entry>
-		<entry>enum&nbsp;v4l2_mpeg_multi_slice_mode</entry>
+		<entry>enum&nbsp;v4l2_mpeg_video_multi_slice_mode</entry>
 	      </row>
 	      <row><entry spanname="descr">Determines how the encoder should handle division of frame into slices.
 Applicable to the encoder.
@@ -1868,9 +1868,9 @@
 	      </row>
 
 	      <row><entry></entry></row>
-	      <row>
+	      <row id="v4l2-mpeg-video-h264-loop-filter-mode">
 		<entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_H264_LOOP_FILTER_MODE</constant>&nbsp;</entry>
-		<entry>enum&nbsp;v4l2_mpeg_h264_loop_filter_mode</entry>
+		<entry>enum&nbsp;v4l2_mpeg_video_h264_loop_filter_mode</entry>
 	      </row>
 	      <row><entry spanname="descr">Loop filter mode for H264 encoder.
 Possible values are:</entry>
@@ -1913,9 +1913,9 @@
 	      </row>
 
 	      <row><entry></entry></row>
-	      <row>
+	      <row id="v4l2-mpeg-video-h264-entropy-mode">
 		<entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_H264_ENTROPY_MODE</constant>&nbsp;</entry>
-		<entry>enum&nbsp;v4l2_mpeg_h264_symbol_mode</entry>
+		<entry>enum&nbsp;v4l2_mpeg_video_h264_entropy_mode</entry>
 	      </row>
 	      <row><entry spanname="descr">Entropy coding mode for H264 - CABAC/CAVALC.
 Applicable to the H264 encoder.
@@ -2140,9 +2140,9 @@
 	      </row>
 
 	      <row><entry></entry></row>
-	      <row>
+	      <row id="v4l2-mpeg-video-header-mode">
 		<entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_HEADER_MODE</constant>&nbsp;</entry>
-		<entry>enum&nbsp;v4l2_mpeg_header_mode</entry>
+		<entry>enum&nbsp;v4l2_mpeg_video_header_mode</entry>
 	      </row>
 	      <row><entry spanname="descr">Determines whether the header is returned as the first buffer or is
 it returned together with the first frame. Applicable to encoders.
@@ -2320,9 +2320,9 @@
 Applicable to the H264 encoder.</entry>
 	      </row>
 	      <row><entry></entry></row>
-	      <row>
+	      <row id="v4l2-mpeg-mfc51-video-frame-skip-mode">
 		<entry spanname="id"><constant>V4L2_CID_MPEG_MFC51_VIDEO_FRAME_SKIP_MODE</constant>&nbsp;</entry>
-		<entry>enum&nbsp;v4l2_mpeg_mfc51_frame_skip_mode</entry>
+		<entry>enum&nbsp;v4l2_mpeg_mfc51_video_frame_skip_mode</entry>
 	      </row>
 	      <row><entry spanname="descr">
 Indicates in what conditions the encoder should skip frames. If encoding a frame would cause the encoded stream to be larger then
@@ -2361,9 +2361,9 @@
 </entry>
 	      </row>
 	      <row><entry></entry></row>
-	      <row>
+	      <row id="v4l2-mpeg-mfc51-video-force-frame-type">
 		<entry spanname="id"><constant>V4L2_CID_MPEG_MFC51_VIDEO_FORCE_FRAME_TYPE</constant>&nbsp;</entry>
-		<entry>enum&nbsp;v4l2_mpeg_mfc51_force_frame_type</entry>
+		<entry>enum&nbsp;v4l2_mpeg_mfc51_video_force_frame_type</entry>
 	      </row>
 	      <row><entry spanname="descr">Force a frame type for the next queued buffer. Applicable to encoders.
 Possible values are:</entry>
diff --git a/Documentation/PCI/MSI-HOWTO.txt b/Documentation/PCI/MSI-HOWTO.txt
index 3f5e0b0..53e6fca 100644
--- a/Documentation/PCI/MSI-HOWTO.txt
+++ b/Documentation/PCI/MSI-HOWTO.txt
@@ -45,7 +45,7 @@
 bridges).  In order to ensure that all the data has arrived in memory,
 the interrupt handler must read a register on the device which raised
 the interrupt.  PCI transaction ordering rules require that all the data
-arrives in memory before the value can be returned from the register.
+arrive in memory before the value may be returned from the register.
 Using MSIs avoids this problem as the interrupt-generating write cannot
 pass the data writes, so by the time the interrupt is raised, the driver
 knows that all the data has arrived in memory.
@@ -86,13 +86,13 @@
 
 int pci_enable_msi(struct pci_dev *dev)
 
-A successful call will allocate ONE interrupt to the device, regardless
-of how many MSIs the device supports.  The device will be switched from
+A successful call allocates ONE interrupt to the device, regardless
+of how many MSIs the device supports.  The device is switched from
 pin-based interrupt mode to MSI mode.  The dev->irq number is changed
-to a new number which represents the message signaled interrupt.
-This function should be called before the driver calls request_irq()
-since enabling MSIs disables the pin-based IRQ and the driver will not
-receive interrupts on the old interrupt.
+to a new number which represents the message signaled interrupt;
+consequently, this function should be called before the driver calls
+request_irq(), because an MSI is delivered via a vector that is
+different from the vector of a pin-based interrupt.
 
 4.2.2 pci_enable_msi_block
 
@@ -111,20 +111,20 @@
 
 If this function returns a negative number, it indicates an error and
 the driver should not attempt to request any more MSI interrupts for
-this device.  If this function returns a positive number, it will be
-less than 'count' and indicate the number of interrupts that could have
-been allocated.  In neither case will the irq value have been
-updated, nor will the device have been switched into MSI mode.
+this device.  If this function returns a positive number, it is
+less than 'count' and indicates the number of interrupts that could have
+been allocated.  In neither case is the irq value updated or the device
+switched into MSI mode.
 
 The device driver must decide what action to take if
-pci_enable_msi_block() returns a value less than the number asked for.
-Some devices can make use of fewer interrupts than the maximum they
-request; in this case the driver should call pci_enable_msi_block()
+pci_enable_msi_block() returns a value less than the number requested.
+For instance, the driver could still make use of fewer interrupts;
+in this case the driver should call pci_enable_msi_block()
 again.  Note that it is not guaranteed to succeed, even when the
 'count' has been reduced to the value returned from a previous call to
 pci_enable_msi_block().  This is because there are multiple constraints
 on the number of vectors that can be allocated; pci_enable_msi_block()
-will return as soon as it finds any constraint that doesn't allow the
+returns as soon as it finds any constraint that doesn't allow the
 call to succeed.
 
 4.2.3 pci_disable_msi
@@ -137,10 +137,10 @@
 interrupt(s).  The interrupt may subsequently be assigned to another
 device, so drivers should not cache the value of dev->irq.
 
-A device driver must always call free_irq() on the interrupt(s)
-for which it has called request_irq() before calling this function.
-Failure to do so will result in a BUG_ON(), the device will be left with
-MSI enabled and will leak its vector.
+Before calling this function, a device driver must always call free_irq()
+on any interrupt for which it previously called request_irq().
+Failure to do so results in a BUG_ON(), leaving the device with
+MSI enabled and thus leaking its vector.
 
 4.3 Using MSI-X
 
@@ -155,10 +155,10 @@
 };
 
 This allows for the device to use these interrupts in a sparse fashion;
-for example it could use interrupts 3 and 1027 and allocate only a
+for example, it could use interrupts 3 and 1027 and yet allocate only a
 two-element array.  The driver is expected to fill in the 'entry' value
-in each element of the array to indicate which entries it wants the kernel
-to assign interrupts for.  It is invalid to fill in two entries with the
+in each element of the array to indicate for which entries the kernel
+should assign interrupts; it is invalid to fill in two entries with the
 same number.
 
 4.3.1 pci_enable_msix
@@ -168,10 +168,11 @@
 Calling this function asks the PCI subsystem to allocate 'nvec' MSIs.
 The 'entries' argument is a pointer to an array of msix_entry structs
 which should be at least 'nvec' entries in size.  On success, the
-function will return 0 and the device will have been switched into
-MSI-X interrupt mode.  The 'vector' elements in each entry will have
-been filled in with the interrupt number.  The driver should then call
-request_irq() for each 'vector' that it decides to use.
+device is switched into MSI-X mode and the function returns 0.
+The 'vector' member in each entry is populated with the interrupt number;
+the driver should then call request_irq() for each 'vector' that it
+decides to use.  The device driver is responsible for keeping track of the
+interrupts assigned to the MSI-X vectors so it can free them again later.
 
 If this function returns a negative number, it indicates an error and
 the driver should not attempt to allocate any more MSI-X interrupts for
@@ -181,16 +182,14 @@
 
 This function, in contrast with pci_enable_msi(), does not adjust
 dev->irq.  The device will not generate interrupts for this interrupt
-number once MSI-X is enabled.  The device driver is responsible for
-keeping track of the interrupts assigned to the MSI-X vectors so it can
-free them again later.
+number once MSI-X is enabled.
 
 Device drivers should normally call this function once per device
 during the initialization phase.
 
-It is ideal if drivers can cope with a variable number of MSI-X interrupts,
+It is ideal if drivers can cope with a variable number of MSI-X interrupts;
 there are many reasons why the platform may not be able to provide the
-exact number a driver asks for.
+exact number that a driver asks for.
 
 A request loop to achieve that might look like:
 
@@ -212,15 +211,15 @@
 
 void pci_disable_msix(struct pci_dev *dev)
 
-This API should be used to undo the effect of pci_enable_msix().  It frees
+This function should be used to undo the effect of pci_enable_msix().  It frees
 the previously allocated message signaled interrupts.  The interrupts may
 subsequently be assigned to another device, so drivers should not cache
 the value of the 'vector' elements over a call to pci_disable_msix().
 
-A device driver must always call free_irq() on the interrupt(s)
-for which it has called request_irq() before calling this function.
-Failure to do so will result in a BUG_ON(), the device will be left with
-MSI enabled and will leak its vector.
+Before calling this function, a device driver must always call free_irq()
+on any interrupt for which it previously called request_irq().
+Failure to do so results in a BUG_ON(), leaving the device with
+MSI-X enabled and thus leaking its vector.
 
 4.3.3 The MSI-X Table
 
@@ -232,10 +231,10 @@
 4.4 Handling devices implementing both MSI and MSI-X capabilities
 
 If a device implements both MSI and MSI-X capabilities, it can
-run in either MSI mode or MSI-X mode but not both simultaneously.
+run in either MSI mode or MSI-X mode, but not both simultaneously.
 This is a requirement of the PCI spec, and it is enforced by the
 PCI layer.  Calling pci_enable_msi() when MSI-X is already enabled or
-pci_enable_msix() when MSI is already enabled will result in an error.
+pci_enable_msix() when MSI is already enabled results in an error.
 If a device driver wishes to switch between MSI and MSI-X at runtime,
 it must first quiesce the device, then switch it back to pin-interrupt
 mode, before calling pci_enable_msi() or pci_enable_msix() and resuming
@@ -251,7 +250,7 @@
 above, MSI-X supports any number of interrupts between 1 and 2048.
 In constrast, MSI is restricted to a maximum of 32 interrupts (and
 must be a power of two).  In addition, the MSI interrupt vectors must
-be allocated consecutively, so the system may not be able to allocate
+be allocated consecutively, so the system might not be able to allocate
 as many vectors for MSI as it could for MSI-X.  On some platforms, MSI
 interrupts must all be targeted at the same set of CPUs whereas MSI-X
 interrupts can all be targeted at different CPUs.
@@ -281,7 +280,7 @@
 
 Using 'lspci -v' (as root) may show some devices with "MSI", "Message
 Signalled Interrupts" or "MSI-X" capabilities.  Each of these capabilities
-has an 'Enable' flag which will be followed with either "+" (enabled)
+has an 'Enable' flag which is followed with either "+" (enabled)
 or "-" (disabled).
 
 
@@ -298,7 +297,7 @@
 
 Some host chipsets simply don't support MSIs properly.  If we're
 lucky, the manufacturer knows this and has indicated it in the ACPI
-FADT table.  In this case, Linux will automatically disable MSIs.
+FADT table.  In this case, Linux automatically disables MSIs.
 Some boards don't include this information in the table and so we have
 to detect them ourselves.  The complete list of these is found near the
 quirk_disable_all_msi() function in drivers/pci/quirks.c.
@@ -317,7 +316,7 @@
 PCI configuration space (especially the Hypertransport chipsets such
 as the nVidia nForce and Serverworks HT2000).  As with host chipsets,
 Linux mostly knows about them and automatically enables MSIs if it can.
-If you have a bridge which Linux doesn't yet know about, you can enable
+If you have a bridge unknown to Linux, you can enable
 MSIs in configuration space using whatever method you know works, then
 enable MSIs on that bridge by doing:
 
@@ -327,7 +326,7 @@
 0000:00:0e.0).
 
 To disable MSIs, echo 0 instead of 1.  Changing this value should be
-done with caution as it can break interrupt handling for all devices
+done with caution as it could break interrupt handling for all devices
 below this bridge.
 
 Again, please notify linux-pci@vger.kernel.org of any bridges that need
@@ -336,7 +335,7 @@
 5.3. Disabling MSIs on a single device
 
 Some devices are known to have faulty MSI implementations.  Usually this
-is handled in the individual device driver but occasionally it's necessary
+is handled in the individual device driver, but occasionally it's necessary
 to handle this with a quirk.  Some drivers have an option to disable use
 of MSI.  While this is a convenient workaround for the driver author,
 it is not good practise, and should not be emulated.
@@ -350,7 +349,7 @@
 have enabled CONFIG_PCI_MSI.
 
 Then, 'lspci -t' gives the list of bridges above a device.  Reading
-/sys/bus/pci/devices/*/msi_bus will tell you whether MSI are enabled (1)
+/sys/bus/pci/devices/*/msi_bus will tell you whether MSIs are enabled (1)
 or disabled (0).  If 0 is found in any of the msi_bus files belonging
 to bridges between the PCI root and the device, MSIs are disabled.
 
diff --git a/Documentation/SubmittingDrivers b/Documentation/SubmittingDrivers
index 319baa8..36d16bb 100644
--- a/Documentation/SubmittingDrivers
+++ b/Documentation/SubmittingDrivers
@@ -130,7 +130,7 @@
 	ftp.??.kernel.org:/pub/linux/kernel/...
 	?? == your country code, such as "us", "uk", "fr", etc.
 
-	http://git.kernel.org/?p=linux/kernel/git/torvalds/linux-2.6.git
+	http://git.kernel.org/?p=linux/kernel/git/torvalds/linux.git
 
 Linux kernel mailing list:
 	linux-kernel@vger.kernel.org
diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches
index 569f353..4468ce2 100644
--- a/Documentation/SubmittingPatches
+++ b/Documentation/SubmittingPatches
@@ -303,7 +303,7 @@
 
 The sign-off is a simple line at the end of the explanation for the
 patch, which certifies that you wrote it or otherwise have the right to
-pass it on as a open-source patch.  The rules are pretty simple: if you
+pass it on as an open-source patch.  The rules are pretty simple: if you
 can certify the below:
 
         Developer's Certificate of Origin 1.1
diff --git a/Documentation/block/cfq-iosched.txt b/Documentation/block/cfq-iosched.txt
index e578fee..6d670f5 100644
--- a/Documentation/block/cfq-iosched.txt
+++ b/Documentation/block/cfq-iosched.txt
@@ -43,3 +43,74 @@
 to IOPS mode and starts providing fairness in terms of number of requests
 dispatched. Note that this mode switching takes effect only for group
 scheduling. For non-cgroup users nothing should change.
+
+CFQ IO scheduler Idling Theory
+===============================
+Idling on a queue is primarily about waiting for the next request to come
+on same queue after completion of a request. In this process CFQ will not
+dispatch requests from other cfq queues even if requests are pending there.
+
+The rationale behind idling is that it can cut down on number of seeks
+on rotational media. For example, if a process is doing dependent
+sequential reads (next read will come on only after completion of previous
+one), then not dispatching request from other queue should help as we
+did not move the disk head and kept on dispatching sequential IO from
+one queue.
+
+CFQ has following service trees and various queues are put on these trees.
+
+	sync-idle	sync-noidle	async
+
+All cfq queues doing synchronous sequential IO go on to sync-idle tree.
+On this tree we idle on each queue individually.
+
+All synchronous non-sequential queues go on sync-noidle tree. Also any
+request which are marked with REQ_NOIDLE go on this service tree. On this
+tree we do not idle on individual queues instead idle on the whole group
+of queues or the tree. So if there are 4 queues waiting for IO to dispatch
+we will idle only once last queue has dispatched the IO and there is
+no more IO on this service tree.
+
+All async writes go on async service tree. There is no idling on async
+queues.
+
+CFQ has some optimizations for SSDs and if it detects a non-rotational
+media which can support higher queue depth (multiple requests at in
+flight at a time), then it cuts down on idling of individual queues and
+all the queues move to sync-noidle tree and only tree idle remains. This
+tree idling provides isolation with buffered write queues on async tree.
+
+FAQ
+===
+Q1. Why to idle at all on queues marked with REQ_NOIDLE.
+
+A1. We only do tree idle (all queues on sync-noidle tree) on queues marked
+    with REQ_NOIDLE. This helps in providing isolation with all the sync-idle
+    queues. Otherwise in presence of many sequential readers, other
+    synchronous IO might not get fair share of disk.
+
+    For example, if there are 10 sequential readers doing IO and they get
+    100ms each. If a REQ_NOIDLE request comes in, it will be scheduled
+    roughly after 1 second. If after completion of REQ_NOIDLE request we
+    do not idle, and after a couple of milli seconds a another REQ_NOIDLE
+    request comes in, again it will be scheduled after 1second. Repeat it
+    and notice how a workload can lose its disk share and suffer due to
+    multiple sequential readers.
+
+    fsync can generate dependent IO where bunch of data is written in the
+    context of fsync, and later some journaling data is written. Journaling
+    data comes in only after fsync has finished its IO (atleast for ext4
+    that seemed to be the case). Now if one decides not to idle on fsync
+    thread due to REQ_NOIDLE, then next journaling write will not get
+    scheduled for another second. A process doing small fsync, will suffer
+    badly in presence of multiple sequential readers.
+
+    Hence doing tree idling on threads using REQ_NOIDLE flag on requests
+    provides isolation from multiple sequential readers and at the same
+    time we do not idle on individual threads.
+
+Q2. When to specify REQ_NOIDLE
+A2. I would think whenever one is doing synchronous write and not expecting
+    more writes to be dispatched from same context soon, should be able
+    to specify REQ_NOIDLE on writes and that probably should work well for
+    most of the cases.
diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index 6f3c598..06eb6d9 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -380,7 +380,7 @@
 
 5.2 stat file
 
-5.2.1 memory.stat file includes following statistics
+memory.stat file includes following statistics
 
 # per-memory cgroup local status
 cache		- # of bytes of page cache memory.
@@ -438,89 +438,6 @@
 	 file_mapped is accounted only when the memory cgroup is owner of page
 	 cache.)
 
-5.2.2 memory.vmscan_stat
-
-memory.vmscan_stat includes statistics information for memory scanning and
-freeing, reclaiming. The statistics shows memory scanning information since
-memory cgroup creation and can be reset to 0 by writing 0 as
-
- #echo 0 > ../memory.vmscan_stat
-
-This file contains following statistics.
-
-[param]_[file_or_anon]_pages_by_[reason]_[under_heararchy]
-[param]_elapsed_ns_by_[reason]_[under_hierarchy]
-
-For example,
-
-  scanned_file_pages_by_limit indicates the number of scanned
-  file pages at vmscan.
-
-Now, 3 parameters are supported
-
-  scanned - the number of pages scanned by vmscan
-  rotated - the number of pages activated at vmscan
-  freed   - the number of pages freed by vmscan
-
-If "rotated" is high against scanned/freed, the memcg seems busy.
-
-Now, 2 reason are supported
-
-  limit - the memory cgroup's limit
-  system - global memory pressure + softlimit
-           (global memory pressure not under softlimit is not handled now)
-
-When under_hierarchy is added in the tail, the number indicates the
-total memcg scan of its children and itself.
-
-elapsed_ns is a elapsed time in nanosecond. This may include sleep time
-and not indicates CPU usage. So, please take this as just showing
-latency.
-
-Here is an example.
-
-# cat /cgroup/memory/A/memory.vmscan_stat
-scanned_pages_by_limit 9471864
-scanned_anon_pages_by_limit 6640629
-scanned_file_pages_by_limit 2831235
-rotated_pages_by_limit 4243974
-rotated_anon_pages_by_limit 3971968
-rotated_file_pages_by_limit 272006
-freed_pages_by_limit 2318492
-freed_anon_pages_by_limit 962052
-freed_file_pages_by_limit 1356440
-elapsed_ns_by_limit 351386416101
-scanned_pages_by_system 0
-scanned_anon_pages_by_system 0
-scanned_file_pages_by_system 0
-rotated_pages_by_system 0
-rotated_anon_pages_by_system 0
-rotated_file_pages_by_system 0
-freed_pages_by_system 0
-freed_anon_pages_by_system 0
-freed_file_pages_by_system 0
-elapsed_ns_by_system 0
-scanned_pages_by_limit_under_hierarchy 9471864
-scanned_anon_pages_by_limit_under_hierarchy 6640629
-scanned_file_pages_by_limit_under_hierarchy 2831235
-rotated_pages_by_limit_under_hierarchy 4243974
-rotated_anon_pages_by_limit_under_hierarchy 3971968
-rotated_file_pages_by_limit_under_hierarchy 272006
-freed_pages_by_limit_under_hierarchy 2318492
-freed_anon_pages_by_limit_under_hierarchy 962052
-freed_file_pages_by_limit_under_hierarchy 1356440
-elapsed_ns_by_limit_under_hierarchy 351386416101
-scanned_pages_by_system_under_hierarchy 0
-scanned_anon_pages_by_system_under_hierarchy 0
-scanned_file_pages_by_system_under_hierarchy 0
-rotated_pages_by_system_under_hierarchy 0
-rotated_anon_pages_by_system_under_hierarchy 0
-rotated_file_pages_by_system_under_hierarchy 0
-freed_pages_by_system_under_hierarchy 0
-freed_anon_pages_by_system_under_hierarchy 0
-freed_file_pages_by_system_under_hierarchy 0
-elapsed_ns_by_system_under_hierarchy 0
-
 5.3 swappiness
 
 Similar to /proc/sys/vm/swappiness, but affecting a hierarchy of groups only.
diff --git a/Documentation/email-clients.txt b/Documentation/email-clients.txt
index a0b58e2..860c29a 100644
--- a/Documentation/email-clients.txt
+++ b/Documentation/email-clients.txt
@@ -199,18 +199,16 @@
 
 To beat some sense out of the internal editor, do this:
 
-- Under account settings, composition and addressing, uncheck "Compose
-  messages in HTML format".
-
 - Edit your Thunderbird config settings so that it won't use format=flowed.
   Go to "edit->preferences->advanced->config editor" to bring up the
   thunderbird's registry editor, and set "mailnews.send_plaintext_flowed" to
   "false".
 
-- Enable "preformat" mode: Shft-click on the Write icon to bring up the HTML
-  composer, select "Preformat" from the drop-down box just under the subject
-  line, then close the message without saving.  (This setting also applies to
-  the text composer, but the only control for it is in the HTML composer.)
+- Disable HTML Format: Set "mail.identity.id1.compose_html" to "false".
+
+- Enable "preformat" mode: Set "editor.quotesPreformatted" to "true".
+
+- Enable UTF8: Set "prefs.converted-to-utf8" to "true".
 
 - Install the "toggle wordwrap" extension.  Download the file from:
     https://addons.mozilla.org/thunderbird/addon/2351/
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index c4a6e14..4dc4654 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -592,3 +592,11 @@
 	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>
+
+----------------------------
+What:	The XFS nodelaylog mount option
+When:	3.3
+Why:	The delaylog mode that has been the default since 2.6.39 has proven
+	stable, and the old code is in the way of additional improvements in
+	the log code.
+Who:	Christoph Hellwig <hch@lst.de>
diff --git a/Documentation/filesystems/befs.txt b/Documentation/filesystems/befs.txt
index 6e49c36..da45e6c 100644
--- a/Documentation/filesystems/befs.txt
+++ b/Documentation/filesystems/befs.txt
@@ -27,7 +27,7 @@
 Does anyone know of a more current email address for Makoto? He doesn't
 respond to the address given above...
 
-Current maintainer: Sergey S. Kostyliov <rathamahata@php4.ru>
+This filesystem doesn't have a maintainer.
 
 WHAT IS THIS DRIVER?
 ==================
diff --git a/Documentation/hwmon/coretemp b/Documentation/hwmon/coretemp
index fa8776a..84d46c0 100644
--- a/Documentation/hwmon/coretemp
+++ b/Documentation/hwmon/coretemp
@@ -35,13 +35,6 @@
 All Sysfs entries are named with their core_id (represented here by 'X').
 tempX_input	 - Core temperature (in millidegrees Celsius).
 tempX_max	 - All cooling devices should be turned on (on Core2).
-		   Initialized with IA32_THERM_INTERRUPT. When the CPU
-		   temperature reaches this temperature, an interrupt is
-		   generated and tempX_max_alarm is set.
-tempX_max_hyst   - If the CPU temperature falls below than temperature,
-		   an interrupt is generated and tempX_max_alarm is reset.
-tempX_max_alarm  - Set if the temperature reaches or exceeds tempX_max.
-		   Reset if the temperature drops to or below tempX_max_hyst.
 tempX_crit	 - Maximum junction temperature (in millidegrees Celsius).
 tempX_crit_alarm - Set when Out-of-spec bit is set, never clears.
 		   Correct CPU operation is no longer guaranteed.
@@ -49,9 +42,10 @@
 		   number. For Package temp, this will be "Physical id Y",
 		   where Y is the package number.
 
-The TjMax temperature is set to 85 degrees C if undocumented model specific
-register (UMSR) 0xee has bit 30 set. If not the TjMax is 100 degrees C as
-(sometimes) documented in processor datasheet.
+On CPU models which support it, TjMax is read from a model-specific register.
+On other models, it is set to an arbitrary value based on weak heuristics.
+If these heuristics don't work for you, you can pass the correct TjMax value
+as a module parameter (tjmax).
 
 Appendix A. Known TjMax lists (TBD):
 Some information comes from ark.intel.com
diff --git a/Documentation/hwmon/max16065 b/Documentation/hwmon/max16065
index 44b4f61..c11f64a 100644
--- a/Documentation/hwmon/max16065
+++ b/Documentation/hwmon/max16065
@@ -62,6 +62,13 @@
 the devices explicitly. Please see Documentation/i2c/instantiating-devices for
 details.
 
+WARNING: Do not access chip registers using the i2cdump command, and do not use
+any of the i2ctools commands on a command register (0xa5 to 0xac). The chips
+supported by this driver interpret any access to a command register (including
+read commands) as request to execute the command in question. This may result in
+power loss, board resets, and/or Flash corruption. Worst case, your board may
+turn into a brick.
+
 
 Sysfs entries
 -------------
diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt
index 845a191..54078ed 100644
--- a/Documentation/ioctl/ioctl-number.txt
+++ b/Documentation/ioctl/ioctl-number.txt
@@ -319,4 +319,6 @@
 					<mailto:thomas@winischhofer.net>
 0xF4	00-1F	video/mbxfb.h		mbxfb
 					<mailto:raph@8d.com>
+0xF6	all	LTTng			Linux Trace Toolkit Next Generation
+					<mailto:mathieu.desnoyers@efficios.com>
 0xFD	all	linux/dm-ioctl.h
diff --git a/Documentation/kernel-docs.txt b/Documentation/kernel-docs.txt
index 9a86746..0e0734b 100644
--- a/Documentation/kernel-docs.txt
+++ b/Documentation/kernel-docs.txt
@@ -620,17 +620,6 @@
        (including this document itself) have been moved there, and might
        be more up to date than the web version.
 
-     * Name: "Linux Source Driver"
-       URL: http://lsd.linux.cz
-       Keywords: Browsing source code.
-       Description: "Linux Source Driver (LSD) is an application, which
-       can make browsing source codes of Linux kernel easier than you can
-       imagine. You can select between multiple versions of kernel (e.g.
-       0.01, 1.0.0, 2.0.33, 2.0.34pre13, 2.0.0, 2.1.101 etc.). With LSD
-       you can search Linux kernel (fulltext, macros, types, functions
-       and variables) and LSD can generate patches for you on the fly
-       (files, directories or kernel)".
-
      * Name: "Linux Kernel Source Reference"
        Author: Thomas Graichen.
        URL: http://marc.info/?l=linux-kernel&m=96446640102205&w=4
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index e279b72..854ed5ca 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -40,6 +40,7 @@
 	ALSA	ALSA sound support is enabled.
 	APIC	APIC support is enabled.
 	APM	Advanced Power Management support is enabled.
+	ARM	ARM architecture is enabled.
 	AVR32	AVR32 architecture is enabled.
 	AX25	Appropriate AX.25 support is enabled.
 	BLACKFIN Blackfin architecture is enabled.
@@ -49,6 +50,7 @@
 	EFI	EFI Partitioning (GPT) is enabled
 	EIDE	EIDE/ATAPI support is enabled.
 	FB	The frame buffer device is enabled.
+	FTRACE	Function tracing enabled.
 	GCOV	GCOV profiling is enabled.
 	HW	Appropriate hardware is enabled.
 	IA-64	IA-64 architecture is enabled.
@@ -69,6 +71,7 @@
 			Documentation/m68k/kernel-options.txt.
 	MCA	MCA bus support is enabled.
 	MDA	MDA console support is enabled.
+	MIPS	MIPS architecture is enabled.
 	MOUSE	Appropriate mouse support is enabled.
 	MSI	Message Signaled Interrupts (PCI).
 	MTD	MTD (Memory Technology Device) support is enabled.
@@ -100,7 +103,6 @@
 	SPARC	Sparc architecture is enabled.
 	SWSUSP	Software suspend (hibernation) is enabled.
 	SUSPEND	System suspend states are enabled.
-	FTRACE	Function tracing enabled.
 	TPM	TPM drivers are enabled.
 	TS	Appropriate touchscreen support is enabled.
 	UMS	USB Mass Storage support is enabled.
@@ -115,7 +117,7 @@
 	X86-64	X86-64 architecture is enabled.
 			More X86-64 boot options can be found in
 			Documentation/x86/x86_64/boot-options.txt .
-	X86	Either 32bit or 64bit x86 (same as X86-32+X86-64)
+	X86	Either 32-bit or 64-bit x86 (same as X86-32+X86-64)
 	XEN	Xen support is enabled
 
 In addition, the following text indicates that the option:
@@ -376,7 +378,7 @@
 	atkbd.softrepeat= [HW]
 			Use software keyboard repeat
 
-	autotest	[IA64]
+	autotest	[IA-64]
 
 	baycom_epp=	[HW,AX25]
 			Format: <io>,<mode>
@@ -681,8 +683,8 @@
 		uart[8250],mmio32,<addr>[,options]
 			Start an early, polled-mode console on the 8250/16550
 			UART at the specified I/O port or MMIO address.
-			MMIO inter-register address stride is either 8bit (mmio)
-                        or 32bit (mmio32).
+			MMIO inter-register address stride is either 8-bit
+			(mmio) or 32-bit (mmio32).
 			The options are the same as for ttyS, above.
 
 	earlyprintk=	[X86,SH,BLACKFIN]
@@ -725,7 +727,7 @@
 			See Documentation/block/as-iosched.txt and
 			Documentation/block/deadline-iosched.txt for details.
 
-	elfcorehdr=	[IA64,PPC,SH,X86]
+	elfcorehdr=	[IA-64,PPC,SH,X86]
 			Specifies physical address of start of kernel core
 			image elf header. Generally kexec loader will
 			pass this option to capture kernel.
@@ -791,7 +793,7 @@
 			tracer at boot up. function-list is a comma separated
 			list of functions. This list can be changed at run
 			time by the set_ftrace_filter file in the debugfs
-			tracing directory. 
+			tracing directory.
 
 	ftrace_notrace=[function-list]
 			[FTRACE] Do not trace the functions specified in
@@ -829,7 +831,7 @@
 
 	hashdist=	[KNL,NUMA] Large hashes allocated during boot
 			are distributed across NUMA nodes.  Defaults on
-			for 64bit NUMA, off otherwise.
+			for 64-bit NUMA, off otherwise.
 			Format: 0 | 1 (for off | on)
 
 	hcl=		[IA-64] SGI's Hardware Graph compatibility layer
@@ -998,10 +1000,10 @@
 			DMA.
 		forcedac [x86_64]
 			With this option iommu will not optimize to look
-			for io virtual address below 32 bit forcing dual
+			for io virtual address below 32-bit forcing dual
 			address cycle on pci bus for cards supporting greater
-			than 32 bit addressing. The default is to look
-			for translation below 32 bit and if not available
+			than 32-bit addressing. The default is to look
+			for translation below 32-bit and if not available
 			then look in the higher range.
 		strict [Default Off]
 			With this option on every unmap_single operation will
@@ -1017,7 +1019,7 @@
 			off	disable Interrupt Remapping
 			nosid	disable Source ID checking
 
-	inttest=	[IA64]
+	inttest=	[IA-64]
 
 	iomem=		Disable strict checking of access to MMIO memory
 		strict	regions from userspace.
@@ -1034,7 +1036,7 @@
 		nomerge
 		forcesac
 		soft
-		pt	[x86, IA64]
+		pt	[x86, IA-64]
 
 	io7=		[HW] IO7 for Marvel based alpha systems
 			See comment before marvel_specify_io7 in
@@ -1165,7 +1167,7 @@
 
 	kvm-amd.npt=	[KVM,AMD] Disable nested paging (virtualized MMU)
 			for all guests.
-			Default is 1 (enabled) if in 64bit or 32bit-PAE mode
+			Default is 1 (enabled) if in 64-bit or 32-bit PAE mode.
 
 	kvm-intel.ept=	[KVM,Intel] Disable extended page tables
 			(virtualized MMU) support on capable Intel chips.
@@ -1202,10 +1204,10 @@
 			libata.dma=0	  Disable all PATA and SATA DMA
 			libata.dma=1	  PATA and SATA Disk DMA only
 			libata.dma=2	  ATAPI (CDROM) DMA only
-			libata.dma=4	  Compact Flash DMA only 
+			libata.dma=4	  Compact Flash DMA only
 			Combinations also work, so libata.dma=3 enables DMA
 			for disks and CDROMs, but not CFs.
-	
+
 	libata.ignore_hpa=	[LIBATA] Ignore HPA limit
 			libata.ignore_hpa=0	  keep BIOS limits (default)
 			libata.ignore_hpa=1	  ignore limits, using full disk
@@ -1331,7 +1333,7 @@
 	ltpc=		[NET]
 			Format: <io>,<irq>,<dma>
 
-	machvec=	[IA64] Force the use of a particular machine-vector
+	machvec=	[IA-64] Force the use of a particular machine-vector
 			(machvec) in a generic kernel.
 			Example: machvec=hpzx1_swiotlb
 
@@ -1348,9 +1350,12 @@
 			it is equivalent to "nosmp", which also disables
 			the IO APIC.
 
-	max_loop=	[LOOP] Maximum number of loopback devices that can
-			be mounted
-			Format: <1-256>
+	max_loop=	[LOOP] The number of loop block devices that get
+	(loop.max_loop)	unconditionally pre-created at init time. The default
+			number is configured by BLK_DEV_LOOP_MIN_COUNT. Instead
+			of statically allocating a predefined number, loop
+			devices can be requested on-demand with the
+			/dev/loop-control interface.
 
 	mcatest=	[IA-64]
 
@@ -1734,7 +1739,7 @@
 
 	nointroute	[IA-64]
 
-	nojitter	[IA64] Disables jitter checking for ITC timers.
+	nojitter	[IA-64] Disables jitter checking for ITC timers.
 
 	no-kvmclock	[X86,KVM] Disable paravirtualized KVM clock driver
 
@@ -1800,7 +1805,7 @@
 
 	nox2apic	[X86-64,APIC] Do not enable x2APIC mode.
 
-	nptcg=		[IA64] Override max number of concurrent global TLB
+	nptcg=		[IA-64] Override max number of concurrent global TLB
 			purges which is reported from either PAL_VM_SUMMARY or
 			SAL PALO.
 
@@ -2077,13 +2082,16 @@
 			Format: { parport<nr> | timid | 0 }
 			See also Documentation/parport.txt.
 
-	pmtmr=		[X86] Manual setup of pmtmr I/O Port. 
+	pmtmr=		[X86] Manual setup of pmtmr I/O Port.
 			Override pmtimer IOPort with a hex value.
 			e.g. pmtmr=0x508
 
-	pnp.debug	[PNP]
-			Enable PNP debug messages.  This depends on the
-			CONFIG_PNP_DEBUG_MESSAGES option.
+	pnp.debug=1	[PNP]
+			Enable PNP debug messages (depends on the
+			CONFIG_PNP_DEBUG_MESSAGES option).  Change at run-time
+			via /sys/module/pnp/parameters/debug.  We always show
+			current resource usage; turning this on also shows
+			possible settings and some assignment information.
 
 	pnpacpi=	[ACPI]
 			{ off }
@@ -2635,6 +2643,16 @@
 					medium is write-protected).
 			Example: quirks=0419:aaf5:rl,0421:0433:rc
 
+	user_debug=	[KNL,ARM]
+			Format: <int>
+			See arch/arm/Kconfig.debug help text.
+				 1 - undefined instruction events
+				 2 - system calls
+				 4 - invalid data aborts
+				 8 - SIGSEGV faults
+				16 - SIGBUS faults
+			Example: user_debug=31
+
 	userpte=
 			[X86] Flags controlling user PTE allocations.
 
@@ -2680,6 +2698,27 @@
 	vmpoff=		[KNL,S390] Perform z/VM CP command after power off.
 			Format: <command>
 
+	vsyscall=	[X86-64]
+			Controls the behavior of vsyscalls (i.e. calls to
+			fixed addresses of 0xffffffffff600x00 from legacy
+			code).  Most statically-linked binaries and older
+			versions of glibc use these calls.  Because these
+			functions are at fixed addresses, they make nice
+			targets for exploits that can control RIP.
+
+			emulate     [default] Vsyscalls turn into traps and are
+			            emulated reasonably safely.
+
+			native      Vsyscalls are native syscall instructions.
+			            This is a little bit faster than trapping
+			            and makes a few dynamic recompilers work
+			            better than they would in emulation mode.
+			            It also makes exploits much easier to write.
+
+			none        Vsyscalls don't work at all.  This makes
+			            them quite hard to use for exploits but
+			            might break your system.
+
 	vt.cur_default=	[VT] Default cursor shape.
 			Format: 0xCCBBAA, where AA, BB, and CC are the same as
 			the parameters of the <Esc>[?A;B;Cc escape sequence;
diff --git a/Documentation/networking/00-INDEX b/Documentation/networking/00-INDEX
index 4edd78d..bbce121 100644
--- a/Documentation/networking/00-INDEX
+++ b/Documentation/networking/00-INDEX
@@ -1,13 +1,21 @@
 00-INDEX
 	- this file
+3c359.txt
+	- information on the 3Com TokenLink Velocity XL (3c5359) driver.
 3c505.txt
 	- information on the 3Com EtherLink Plus (3c505) driver.
+3c509.txt
+	- information on the 3Com Etherlink III Series Ethernet cards.
 6pack.txt
 	- info on the 6pack protocol, an alternative to KISS for AX.25
 DLINK.txt
 	- info on the D-Link DE-600/DE-620 parallel port pocket adapters
 PLIP.txt
 	- PLIP: The Parallel Line Internet Protocol device driver
+README.ipw2100
+	- README for the Intel PRO/Wireless 2100 driver.
+README.ipw2200
+	- README for the Intel PRO/Wireless 2915ABG and 2200BG driver.
 README.sb1000
 	- info on General Instrument/NextLevel SURFboard1000 cable modem.
 alias.txt
@@ -20,8 +28,12 @@
 	- info on where to get ATM programs and support for Linux.
 ax25.txt
 	- info on using AX.25 and NET/ROM code for Linux
+batman-adv.txt
+	- B.A.T.M.A.N routing protocol on top of layer 2 Ethernet Frames.
 baycom.txt
 	- info on the driver for Baycom style amateur radio modems
+bonding.txt
+	- Linux Ethernet Bonding Driver HOWTO: link aggregation in Linux.
 bridge.txt
 	- where to get user space programs for ethernet bridging with Linux.
 can.txt
@@ -34,32 +46,60 @@
 	- Conexant AccessRunner USB ADSL Modem
 cxacru-cf.py
 	- Conexant AccessRunner USB ADSL Modem configuration file parser
+cxgb.txt
+	- Release Notes for the Chelsio N210 Linux device driver.
+dccp.txt
+	- the Datagram Congestion Control Protocol (DCCP) (RFC 4340..42).
 de4x5.txt
 	- the Digital EtherWORKS DE4?? and DE5?? PCI Ethernet driver
 decnet.txt
 	- info on using the DECnet networking layer in Linux.
 depca.txt
 	- the Digital DEPCA/EtherWORKS DE1?? and DE2?? LANCE Ethernet driver
+dl2k.txt
+	- README for D-Link DL2000-based Gigabit Ethernet Adapters (dl2k.ko).
+dm9000.txt
+	- README for the Simtec DM9000 Network driver.
 dmfe.txt
 	- info on the Davicom DM9102(A)/DM9132/DM9801 fast ethernet driver.
+dns_resolver.txt
+	- The DNS resolver module allows kernel servies to make DNS queries.
+driver.txt
+	- Softnet driver issues.
 e100.txt
 	- info on Intel's EtherExpress PRO/100 line of 10/100 boards
 e1000.txt
 	- info on Intel's E1000 line of gigabit ethernet boards
+e1000e.txt
+	- README for the Intel Gigabit Ethernet Driver (e1000e).
 eql.txt
 	- serial IP load balancing
 ewrk3.txt
 	- the Digital EtherWORKS 3 DE203/4/5 Ethernet driver
+fib_trie.txt
+	- Level Compressed Trie (LC-trie) notes: a structure for routing.
 filter.txt
 	- Linux Socket Filtering
 fore200e.txt
 	- FORE Systems PCA-200E/SBA-200E ATM NIC driver info.
 framerelay.txt
 	- info on using Frame Relay/Data Link Connection Identifier (DLCI).
+gen_stats.txt
+	- Generic networking statistics for netlink users.
+generic_hdlc.txt
+	- The generic High Level Data Link Control (HDLC) layer.
 generic_netlink.txt
 	- info on Generic Netlink
+gianfar.txt
+	- Gianfar Ethernet Driver.
 ieee802154.txt
 	- Linux IEEE 802.15.4 implementation, API and drivers
+ifenslave.c
+	- Configure network interfaces for parallel routing (bonding).
+igb.txt
+	- README for the Intel Gigabit Ethernet Driver (igb).
+igbvf.txt
+	- README for the Intel Gigabit Ethernet Driver (igbvf).
 ip-sysctl.txt
 	- /proc/sys/net/ipv4/* variables
 ip_dynaddr.txt
@@ -68,41 +108,117 @@
 	- AppleTalk-IP Decapsulation and AppleTalk-IP Encapsulation
 iphase.txt
 	- Interphase PCI ATM (i)Chip IA Linux driver info.
+ipv6.txt
+	- Options to the ipv6 kernel module.
+ipvs-sysctl.txt
+	- Per-inode explanation of the /proc/sys/net/ipv4/vs interface.
 irda.txt
 	- where to get IrDA (infrared) utilities and info for Linux.
+ixgb.txt
+	- README for the Intel 10 Gigabit Ethernet Driver (ixgb).
+ixgbe.txt
+	- README for the Intel 10 Gigabit Ethernet Driver (ixgbe).
+ixgbevf.txt
+	- README for the Intel Virtual Function (VF) Driver (ixgbevf).
+l2tp.txt
+	- User guide to the L2TP tunnel protocol.
 lapb-module.txt
 	- programming information of the LAPB module.
 ltpc.txt
 	- the Apple or Farallon LocalTalk PC card driver
+mac80211-injection.txt
+	- HOWTO use packet injection with mac80211
 multicast.txt
 	- Behaviour of cards under Multicast
+multiqueue.txt
+	- HOWTO for multiqueue network device support.
+netconsole.txt
+	- The network console module netconsole.ko: configuration and notes.
+netdev-features.txt
+	- Network interface features API description.
 netdevices.txt
 	- info on network device driver functions exported to the kernel.
+netif-msg.txt
+	- Design of the network interface message level setting (NETIF_MSG_*).
+nfc.txt
+	- The Linux Near Field Communication (NFS) subsystem.
 olympic.txt
 	- IBM PCI Pit/Pit-Phy/Olympic Token Ring driver info.
+operstates.txt
+	- Overview of network interface operational states.
+packet_mmap.txt
+	- User guide to memory mapped packet socket rings (PACKET_[RT]X_RING).
+phonet.txt
+	- The Phonet packet protocol used in Nokia cellular modems.
+phy.txt
+	- The PHY abstraction layer.
+pktgen.txt
+	- User guide to the kernel packet generator (pktgen.ko).
 policy-routing.txt
 	- IP policy-based routing
+ppp_generic.txt
+	- Information about the generic PPP driver.
+proc_net_tcp.txt
+	- Per inode overview of the /proc/net/tcp and /proc/net/tcp6 interfaces.
+radiotap-headers.txt
+	- Background on radiotap headers.
 ray_cs.txt
 	- Raylink Wireless LAN card driver info.
+rds.txt
+	- Background on the reliable, ordered datagram delivery method RDS.
+regulatory.txt
+	- Overview of the Linux wireless regulatory infrastructure.
+rxrpc.txt
+	- Guide to the RxRPC protocol.
+s2io.txt
+	- Release notes for Neterion Xframe I/II 10GbE driver.
+scaling.txt
+	- Explanation of network scaling techniques: RSS, RPS, RFS, aRFS, XPS.
+sctp.txt
+	- Notes on the Linux kernel implementation of the SCTP protocol.
+secid.txt
+	- Explanation of the secid member in flow structures.
 skfp.txt
 	- SysKonnect FDDI (SK-5xxx, Compaq Netelligent) driver info.
 smc9.txt
 	- the driver for SMC's 9000 series of Ethernet cards
 smctr.txt
 	- SMC TokenCard TokenRing Linux driver info.
+spider-net.txt
+	- README for the Spidernet Driver (as found in PS3 / Cell BE).
+stmmac.txt
+	- README for the STMicro Synopsys Ethernet driver.
+tc-actions-env-rules.txt
+	- rules for traffic control (tc) actions.
+timestamping.txt
+	- overview of network packet timestamping variants.
 tcp.txt
 	- short blurb on how TCP output takes place.
+tcp-thin.txt
+	- kernel tuning options for low rate 'thin' TCP streams.
 tlan.txt
 	- ThunderLAN (Compaq Netelligent 10/100, Olicom OC-2xxx) driver info.
 tms380tr.txt
 	- SysKonnect Token Ring ISA/PCI adapter driver info.
+tproxy.txt
+	- Transparent proxy support user guide.
 tuntap.txt
 	- TUN/TAP device driver, allowing user space Rx/Tx of packets.
+udplite.txt
+	- UDP-Lite protocol (RFC 3828) introduction.
 vortex.txt
 	- info on using 3Com Vortex (3c590, 3c592, 3c595, 3c597) Ethernet cards.
+vxge.txt
+	- README for the Neterion X3100 PCIe Server Adapter.
 x25.txt
 	- general info on X.25 development.
 x25-iface.txt
 	- description of the X.25 Packet Layer to LAPB device interface.
+xfrm_proc.txt
+	- description of the statistics package for XFRM.
+xfrm_sync.txt
+	- sync patches for XFRM enable migration of an SA between hosts.
+xfrm_sysctl.txt
+	- description of the XFRM configuration options.
 z8530drv.txt
 	- info about Linux driver for Z8530 based HDLC cards for AX.25
diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt
index 5dd960d..91df678 100644
--- a/Documentation/networking/bonding.txt
+++ b/Documentation/networking/bonding.txt
@@ -238,6 +238,18 @@
 
 	This option was added in bonding version 3.4.0.
 
+all_slaves_active
+
+	Specifies that duplicate frames (received on inactive ports) should be
+	dropped (0) or delivered (1).
+
+	Normally, bonding will drop duplicate frames (received on inactive
+	ports), which is desirable for most users. But there are some times
+	it is nice to allow duplicate frames to be delivered.
+
+	The default value is 0 (drop duplicate frames received on inactive
+	ports).
+
 arp_interval
 
 	Specifies the ARP link monitoring frequency in milliseconds.
@@ -433,6 +445,23 @@
 	determined.  See the High Availability section for additional
 	information.  The default value is 0.
 
+min_links
+
+	Specifies the minimum number of links that must be active before
+	asserting carrier. It is similar to the Cisco EtherChannel min-links
+	feature. This allows setting the minimum number of member ports that
+	must be up (link-up state) before marking the bond device as up
+	(carrier on). This is useful for situations where higher level services
+	such as clustering want to ensure a minimum number of low bandwidth
+	links are active before switchover. This option only affect 802.3ad
+	mode.
+
+	The default value is 0. This will cause carrier to be asserted (for
+	802.3ad mode) whenever there is an active aggregator, regardless of the
+	number of available links in that aggregator. Note that, because an
+	aggregator cannot be active without at least one available link,
+	setting this option to 0 or to 1 has the exact same effect.
+
 mode
 
 	Specifies one of the bonding policies. The default is
diff --git a/Documentation/networking/dmfe.txt b/Documentation/networking/dmfe.txt
index 8006c22..25320bf 100644
--- a/Documentation/networking/dmfe.txt
+++ b/Documentation/networking/dmfe.txt
@@ -1,3 +1,5 @@
+Note: This driver doesn't have a maintainer.
+
 Davicom DM9102(A)/DM9132/DM9801 fast ethernet driver for Linux.
 
 This program is free software; you can redistribute it and/or
@@ -55,7 +57,6 @@
 Authors:
 
 Sten Wang <sten_wang@davicom.com.tw >   : Original Author
-Tobias Ringstrom <tori@unhappy.mine.nu> : Current Maintainer
 
 Contributors:
 
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index db2a406..8154699 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -992,7 +992,7 @@
 		TRUE: disable IPv4-mapped address feature
 		FALSE: enable IPv4-mapped address feature
 
-	Default: FALSE (as specified in RFC2553bis)
+	Default: FALSE (as specified in RFC3493)
 
 IPv6 Fragmentation:
 
diff --git a/Documentation/networking/scaling.txt b/Documentation/networking/scaling.txt
new file mode 100644
index 0000000..58fd741
--- /dev/null
+++ b/Documentation/networking/scaling.txt
@@ -0,0 +1,378 @@
+Scaling in the Linux Networking Stack
+
+
+Introduction
+============
+
+This document describes a set of complementary techniques in the Linux
+networking stack to increase parallelism and improve performance for
+multi-processor systems.
+
+The following technologies are described:
+
+  RSS: Receive Side Scaling
+  RPS: Receive Packet Steering
+  RFS: Receive Flow Steering
+  Accelerated Receive Flow Steering
+  XPS: Transmit Packet Steering
+
+
+RSS: Receive Side Scaling
+=========================
+
+Contemporary NICs support multiple receive and transmit descriptor queues
+(multi-queue). On reception, a NIC can send different packets to different
+queues to distribute processing among CPUs. The NIC distributes packets by
+applying a filter to each packet that assigns it to one of a small number
+of logical flows. Packets for each flow are steered to a separate receive
+queue, which in turn can be processed by separate CPUs. This mechanism is
+generally known as “Receive-side Scaling” (RSS). The goal of RSS and
+the other scaling techniques to increase performance uniformly.
+Multi-queue distribution can also be used for traffic prioritization, but
+that is not the focus of these techniques.
+
+The filter used in RSS is typically a hash function over the network
+and/or transport layer headers-- for example, a 4-tuple hash over
+IP addresses and TCP ports of a packet. The most common hardware
+implementation of RSS uses a 128-entry indirection table where each entry
+stores a queue number. The receive queue for a packet is determined
+by masking out the low order seven bits of the computed hash for the
+packet (usually a Toeplitz hash), taking this number as a key into the
+indirection table and reading the corresponding value.
+
+Some advanced NICs allow steering packets to queues based on
+programmable filters. For example, webserver bound TCP port 80 packets
+can be directed to their own receive queue. Such “n-tuple” filters can
+be configured from ethtool (--config-ntuple).
+
+==== RSS Configuration
+
+The driver for a multi-queue capable NIC typically provides a kernel
+module parameter for specifying the number of hardware queues to
+configure. In the bnx2x driver, for instance, this parameter is called
+num_queues. A typical RSS configuration would be to have one receive queue
+for each CPU if the device supports enough queues, or otherwise at least
+one for each memory domain, where a memory domain is a set of CPUs that
+share a particular memory level (L1, L2, NUMA node, etc.).
+
+The indirection table of an RSS device, which resolves a queue by masked
+hash, is usually programmed by the driver at initialization. The
+default mapping is to distribute the queues evenly in the table, but the
+indirection table can be retrieved and modified at runtime using ethtool
+commands (--show-rxfh-indir and --set-rxfh-indir). Modifying the
+indirection table could be done to give different queues different
+relative weights.
+
+== RSS IRQ Configuration
+
+Each receive queue has a separate IRQ associated with it. The NIC triggers
+this to notify a CPU when new packets arrive on the given queue. The
+signaling path for PCIe devices uses message signaled interrupts (MSI-X),
+that can route each interrupt to a particular CPU. The active mapping
+of queues to IRQs can be determined from /proc/interrupts. By default,
+an IRQ may be handled on any CPU. Because a non-negligible part of packet
+processing takes place in receive interrupt handling, it is advantageous
+to spread receive interrupts between CPUs. To manually adjust the IRQ
+affinity of each interrupt see Documentation/IRQ-affinity. Some systems
+will be running irqbalance, a daemon that dynamically optimizes IRQ
+assignments and as a result may override any manual settings.
+
+== Suggested Configuration
+
+RSS should be enabled when latency is a concern or whenever receive
+interrupt processing forms a bottleneck. Spreading load between CPUs
+decreases queue length. For low latency networking, the optimal setting
+is to allocate as many queues as there are CPUs in the system (or the
+NIC maximum, if lower). The most efficient high-rate configuration
+is likely the one with the smallest number of receive queues where no
+receive queue overflows due to a saturated CPU, because in default
+mode with interrupt coalescing enabled, the aggregate number of
+interrupts (and thus work) grows with each additional queue.
+
+Per-cpu load can be observed using the mpstat utility, but note that on
+processors with hyperthreading (HT), each hyperthread is represented as
+a separate CPU. For interrupt handling, HT has shown no benefit in
+initial tests, so limit the number of queues to the number of CPU cores
+in the system.
+
+
+RPS: Receive Packet Steering
+============================
+
+Receive Packet Steering (RPS) is logically a software implementation of
+RSS. Being in software, it is necessarily called later in the datapath.
+Whereas RSS selects the queue and hence CPU that will run the hardware
+interrupt handler, RPS selects the CPU to perform protocol processing
+above the interrupt handler. This is accomplished by placing the packet
+on the desired CPU’s backlog queue and waking up the CPU for processing.
+RPS has some advantages over RSS: 1) it can be used with any NIC,
+2) software filters can easily be added to hash over new protocols,
+3) it does not increase hardware device interrupt rate (although it does
+introduce inter-processor interrupts (IPIs)).
+
+RPS is called during bottom half of the receive interrupt handler, when
+a driver sends a packet up the network stack with netif_rx() or
+netif_receive_skb(). These call the get_rps_cpu() function, which
+selects the queue that should process a packet.
+
+The first step in determining the target CPU for RPS is to calculate a
+flow hash over the packet’s addresses or ports (2-tuple or 4-tuple hash
+depending on the protocol). This serves as a consistent hash of the
+associated flow of the packet. The hash is either provided by hardware
+or will be computed in the stack. Capable hardware can pass the hash in
+the receive descriptor for the packet; this would usually be the same
+hash used for RSS (e.g. computed Toeplitz hash). The hash is saved in
+skb->rx_hash and can be used elsewhere in the stack as a hash of the
+packet’s flow.
+
+Each receive hardware queue has an associated list of CPUs to which
+RPS may enqueue packets for processing. For each received packet,
+an index into the list is computed from the flow hash modulo the size
+of the list. The indexed CPU is the target for processing the packet,
+and the packet is queued to the tail of that CPU’s backlog queue. At
+the end of the bottom half routine, IPIs are sent to any CPUs for which
+packets have been queued to their backlog queue. The IPI wakes backlog
+processing on the remote CPU, and any queued packets are then processed
+up the networking stack.
+
+==== RPS Configuration
+
+RPS requires a kernel compiled with the CONFIG_RPS kconfig symbol (on
+by default for SMP). Even when compiled in, RPS remains disabled until
+explicitly configured. The list of CPUs to which RPS may forward traffic
+can be configured for each receive queue using a sysfs file entry:
+
+ /sys/class/net/<dev>/queues/rx-<n>/rps_cpus
+
+This file implements a bitmap of CPUs. RPS is disabled when it is zero
+(the default), in which case packets are processed on the interrupting
+CPU. Documentation/IRQ-affinity.txt explains how CPUs are assigned to
+the bitmap.
+
+== Suggested Configuration
+
+For a single queue device, a typical RPS configuration would be to set
+the rps_cpus to the CPUs in the same memory domain of the interrupting
+CPU. If NUMA locality is not an issue, this could also be all CPUs in
+the system. At high interrupt rate, it might be wise to exclude the
+interrupting CPU from the map since that already performs much work.
+
+For a multi-queue system, if RSS is configured so that a hardware
+receive queue is mapped to each CPU, then RPS is probably redundant
+and unnecessary. If there are fewer hardware queues than CPUs, then
+RPS might be beneficial if the rps_cpus for each queue are the ones that
+share the same memory domain as the interrupting CPU for that queue.
+
+
+RFS: Receive Flow Steering
+==========================
+
+While RPS steers packets solely based on hash, and thus generally
+provides good load distribution, it does not take into account
+application locality. This is accomplished by Receive Flow Steering
+(RFS). The goal of RFS is to increase datacache hitrate by steering
+kernel processing of packets to the CPU where the application thread
+consuming the packet is running. RFS relies on the same RPS mechanisms
+to enqueue packets onto the backlog of another CPU and to wake up that
+CPU.
+
+In RFS, packets are not forwarded directly by the value of their hash,
+but the hash is used as index into a flow lookup table. This table maps
+flows to the CPUs where those flows are being processed. The flow hash
+(see RPS section above) is used to calculate the index into this table.
+The CPU recorded in each entry is the one which last processed the flow.
+If an entry does not hold a valid CPU, then packets mapped to that entry
+are steered using plain RPS. Multiple table entries may point to the
+same CPU. Indeed, with many flows and few CPUs, it is very likely that
+a single application thread handles flows with many different flow hashes.
+
+rps_sock_table is a global flow table that contains the *desired* CPU for
+flows: the CPU that is currently processing the flow in userspace. Each
+table value is a CPU index that is updated during calls to recvmsg and
+sendmsg (specifically, inet_recvmsg(), inet_sendmsg(), inet_sendpage()
+and tcp_splice_read()).
+
+When the scheduler moves a thread to a new CPU while it has outstanding
+receive packets on the old CPU, packets may arrive out of order. To
+avoid this, RFS uses a second flow table to track outstanding packets
+for each flow: rps_dev_flow_table is a table specific to each hardware
+receive queue of each device. Each table value stores a CPU index and a
+counter. The CPU index represents the *current* CPU onto which packets
+for this flow are enqueued for further kernel processing. Ideally, kernel
+and userspace processing occur on the same CPU, and hence the CPU index
+in both tables is identical. This is likely false if the scheduler has
+recently migrated a userspace thread while the kernel still has packets
+enqueued for kernel processing on the old CPU.
+
+The counter in rps_dev_flow_table values records the length of the current
+CPU's backlog when a packet in this flow was last enqueued. Each backlog
+queue has a head counter that is incremented on dequeue. A tail counter
+is computed as head counter + queue length. In other words, the counter
+in rps_dev_flow_table[i] records the last element in flow i that has
+been enqueued onto the currently designated CPU for flow i (of course,
+entry i is actually selected by hash and multiple flows may hash to the
+same entry i).
+
+And now the trick for avoiding out of order packets: when selecting the
+CPU for packet processing (from get_rps_cpu()) the rps_sock_flow table
+and the rps_dev_flow table of the queue that the packet was received on
+are compared. If the desired CPU for the flow (found in the
+rps_sock_flow table) matches the current CPU (found in the rps_dev_flow
+table), the packet is enqueued onto that CPU’s backlog. If they differ,
+the current CPU is updated to match the desired CPU if one of the
+following is true:
+
+- The current CPU's queue head counter >= the recorded tail counter
+  value in rps_dev_flow[i]
+- The current CPU is unset (equal to NR_CPUS)
+- The current CPU is offline
+
+After this check, the packet is sent to the (possibly updated) current
+CPU. These rules aim to ensure that a flow only moves to a new CPU when
+there are no packets outstanding on the old CPU, as the outstanding
+packets could arrive later than those about to be processed on the new
+CPU.
+
+==== RFS Configuration
+
+RFS is only available if the kconfig symbol CONFIG_RFS is enabled (on
+by default for SMP). The functionality remains disabled until explicitly
+configured. The number of entries in the global flow table is set through:
+
+ /proc/sys/net/core/rps_sock_flow_entries
+
+The number of entries in the per-queue flow table are set through:
+
+ /sys/class/net/<dev>/queues/tx-<n>/rps_flow_cnt
+
+== Suggested Configuration
+
+Both of these need to be set before RFS is enabled for a receive queue.
+Values for both are rounded up to the nearest power of two. The
+suggested flow count depends on the expected number of active connections
+at any given time, which may be significantly less than the number of open
+connections. We have found that a value of 32768 for rps_sock_flow_entries
+works fairly well on a moderately loaded server.
+
+For a single queue device, the rps_flow_cnt value for the single queue
+would normally be configured to the same value as rps_sock_flow_entries.
+For a multi-queue device, the rps_flow_cnt for each queue might be
+configured as rps_sock_flow_entries / N, where N is the number of
+queues. So for instance, if rps_flow_entries is set to 32768 and there
+are 16 configured receive queues, rps_flow_cnt for each queue might be
+configured as 2048.
+
+
+Accelerated RFS
+===============
+
+Accelerated RFS is to RFS what RSS is to RPS: a hardware-accelerated load
+balancing mechanism that uses soft state to steer flows based on where
+the application thread consuming the packets of each flow is running.
+Accelerated RFS should perform better than RFS since packets are sent
+directly to a CPU local to the thread consuming the data. The target CPU
+will either be the same CPU where the application runs, or at least a CPU
+which is local to the application thread’s CPU in the cache hierarchy.
+
+To enable accelerated RFS, the networking stack calls the
+ndo_rx_flow_steer driver function to communicate the desired hardware
+queue for packets matching a particular flow. The network stack
+automatically calls this function every time a flow entry in
+rps_dev_flow_table is updated. The driver in turn uses a device specific
+method to program the NIC to steer the packets.
+
+The hardware queue for a flow is derived from the CPU recorded in
+rps_dev_flow_table. The stack consults a CPU to hardware queue map which
+is maintained by the NIC driver. This is an auto-generated reverse map of
+the IRQ affinity table shown by /proc/interrupts. Drivers can use
+functions in the cpu_rmap (“CPU affinity reverse map”) kernel library
+to populate the map. For each CPU, the corresponding queue in the map is
+set to be one whose processing CPU is closest in cache locality.
+
+==== Accelerated RFS Configuration
+
+Accelerated RFS is only available if the kernel is compiled with
+CONFIG_RFS_ACCEL and support is provided by the NIC device and driver.
+It also requires that ntuple filtering is enabled via ethtool. The map
+of CPU to queues is automatically deduced from the IRQ affinities
+configured for each receive queue by the driver, so no additional
+configuration should be necessary.
+
+== Suggested Configuration
+
+This technique should be enabled whenever one wants to use RFS and the
+NIC supports hardware acceleration.
+
+XPS: Transmit Packet Steering
+=============================
+
+Transmit Packet Steering is a mechanism for intelligently selecting
+which transmit queue to use when transmitting a packet on a multi-queue
+device. To accomplish this, a mapping from CPU to hardware queue(s) is
+recorded. The goal of this mapping is usually to assign queues
+exclusively to a subset of CPUs, where the transmit completions for
+these queues are processed on a CPU within this set. This choice
+provides two benefits. First, contention on the device queue lock is
+significantly reduced since fewer CPUs contend for the same queue
+(contention can be eliminated completely if each CPU has its own
+transmit queue). Secondly, cache miss rate on transmit completion is
+reduced, in particular for data cache lines that hold the sk_buff
+structures.
+
+XPS is configured per transmit queue by setting a bitmap of CPUs that
+may use that queue to transmit. The reverse mapping, from CPUs to
+transmit queues, is computed and maintained for each network device.
+When transmitting the first packet in a flow, the function
+get_xps_queue() is called to select a queue. This function uses the ID
+of the running CPU as a key into the CPU-to-queue lookup table. If the
+ID matches a single queue, that is used for transmission. If multiple
+queues match, one is selected by using the flow hash to compute an index
+into the set.
+
+The queue chosen for transmitting a particular flow is saved in the
+corresponding socket structure for the flow (e.g. a TCP connection).
+This transmit queue is used for subsequent packets sent on the flow to
+prevent out of order (ooo) packets. The choice also amortizes the cost
+of calling get_xps_queues() over all packets in the flow. To avoid
+ooo packets, the queue for a flow can subsequently only be changed if
+skb->ooo_okay is set for a packet in the flow. This flag indicates that
+there are no outstanding packets in the flow, so the transmit queue can
+change without the risk of generating out of order packets. The
+transport layer is responsible for setting ooo_okay appropriately. TCP,
+for instance, sets the flag when all data for a connection has been
+acknowledged.
+
+==== XPS Configuration
+
+XPS is only available if the kconfig symbol CONFIG_XPS is enabled (on by
+default for SMP). The functionality remains disabled until explicitly
+configured. To enable XPS, the bitmap of CPUs that may use a transmit
+queue is configured using the sysfs file entry:
+
+/sys/class/net/<dev>/queues/tx-<n>/xps_cpus
+
+== Suggested Configuration
+
+For a network device with a single transmission queue, XPS configuration
+has no effect, since there is no choice in this case. In a multi-queue
+system, XPS is preferably configured so that each CPU maps onto one queue.
+If there are as many queues as there are CPUs in the system, then each
+queue can also map onto one CPU, resulting in exclusive pairings that
+experience no contention. If there are fewer queues than CPUs, then the
+best CPUs to share a given queue are probably those that share the cache
+with the CPU that processes transmit completions for that queue
+(transmit interrupts).
+
+
+Further Information
+===================
+RPS and RFS were introduced in kernel 2.6.35. XPS was incorporated into
+2.6.38. Original patches were submitted by Tom Herbert
+(therbert@google.com)
+
+Accelerated RFS was introduced in 2.6.35. Original patches were
+submitted by Ben Hutchings (bhutchings@solarflare.com)
+
+Authors:
+Tom Herbert (therbert@google.com)
+Willem de Bruijn (willemb@google.com)
diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt
index 4ce5450..6066e3a 100644
--- a/Documentation/power/runtime_pm.txt
+++ b/Documentation/power/runtime_pm.txt
@@ -431,8 +431,7 @@
 
   void pm_runtime_irq_safe(struct device *dev);
     - set the power.irq_safe flag for the device, causing the runtime-PM
-      suspend and resume callbacks (but not the idle callback) to be invoked
-      with interrupts disabled
+      callbacks to be invoked with interrupts off
 
   void pm_runtime_mark_last_busy(struct device *dev);
     - set the power.last_busy field to the current time
diff --git a/Documentation/ramoops.txt b/Documentation/ramoops.txt
new file mode 100644
index 0000000..8fb1ba7
--- /dev/null
+++ b/Documentation/ramoops.txt
@@ -0,0 +1,76 @@
+Ramoops oops/panic logger
+=========================
+
+Sergiu Iordache <sergiu@chromium.org>
+
+Updated: 8 August 2011
+
+0. Introduction
+
+Ramoops is an oops/panic logger that writes its logs to RAM before the system
+crashes. It works by logging oopses and panics in a circular buffer. Ramoops
+needs a system with persistent RAM so that the content of that area can
+survive after a restart.
+
+1. Ramoops concepts
+
+Ramoops uses a predefined memory area to store the dump. The start and size of
+the memory area are set using two variables:
+  * "mem_address" for the start
+  * "mem_size" for the size. The memory size will be rounded down to a
+  power of two.
+
+The memory area is divided into "record_size" chunks (also rounded down to
+power of two) and each oops/panic writes a "record_size" chunk of
+information.
+
+Dumping both oopses and panics can be done by setting 1 in the "dump_oops"
+variable while setting 0 in that variable dumps only the panics.
+
+The module uses a counter to record multiple dumps but the counter gets reset
+on restart (i.e. new dumps after the restart will overwrite old ones).
+
+2. Setting the parameters
+
+Setting the ramoops parameters can be done in 2 different manners:
+ 1. Use the module parameters (which have the names of the variables described
+ as before).
+ 2. Use a platform device and set the platform data. The parameters can then
+ be set through that platform data. An example of doing that is:
+
+#include <linux/ramoops.h>
+[...]
+
+static struct ramoops_platform_data ramoops_data = {
+        .mem_size               = <...>,
+        .mem_address            = <...>,
+        .record_size            = <...>,
+        .dump_oops              = <...>,
+};
+
+static struct platform_device ramoops_dev = {
+        .name = "ramoops",
+        .dev = {
+                .platform_data = &ramoops_data,
+        },
+};
+
+[... inside a function ...]
+int ret;
+
+ret = platform_device_register(&ramoops_dev);
+if (ret) {
+	printk(KERN_ERR "unable to register platform device\n");
+	return ret;
+}
+
+3. Dump format
+
+The data dump begins with a header, currently defined as "====" followed by a
+timestamp and a new line. The dump then continues with the actual data.
+
+4. Reading the data
+
+The dump data can be read from memory (through /dev/mem or other means).
+Getting the module parameters, which are needed in order to parse the data, can
+be done through /sys/module/ramoops/parameters/* .
diff --git a/Documentation/virtual/00-INDEX b/Documentation/virtual/00-INDEX
index fe0251c..8e60199 100644
--- a/Documentation/virtual/00-INDEX
+++ b/Documentation/virtual/00-INDEX
@@ -8,3 +8,6 @@
 	- Extremely simple hypervisor for experimental/educational use.
 uml/
 	- User Mode Linux, builds/runs Linux kernel as a userspace program.
+virtio.txt
+	- Text version of draft virtio spec.
+          See http://ozlabs.org/~rusty/virtio-spec
diff --git a/Documentation/virtual/lguest/lguest.c b/Documentation/virtual/lguest/lguest.c
index 043bd7d..d928c13 100644
--- a/Documentation/virtual/lguest/lguest.c
+++ b/Documentation/virtual/lguest/lguest.c
@@ -1996,6 +1996,9 @@
 	/* We use a simple helper to copy the arguments separated by spaces. */
 	concat((char *)(boot + 1), argv+optind+2);
 
+	/* Set kernel alignment to 16M (CONFIG_PHYSICAL_ALIGN) */
+	boot->hdr.kernel_alignment = 0x1000000;
+
 	/* Boot protocol version: 2.07 supports the fields for lguest. */
 	boot->hdr.version = 0x207;
 
diff --git a/Documentation/virtual/virtio-spec.txt b/Documentation/virtual/virtio-spec.txt
new file mode 100644
index 0000000..a350ae1
--- /dev/null
+++ b/Documentation/virtual/virtio-spec.txt
@@ -0,0 +1,2200 @@
+[Generated file: see http://ozlabs.org/~rusty/virtio-spec/]
+Virtio PCI Card Specification
+v0.9.1 DRAFT
+-
+
+Rusty Russell <rusty@rustcorp.com.au>IBM Corporation (Editor)
+
+2011 August 1.
+
+Purpose and Description
+
+This document describes the specifications of the “virtio” family
+of PCI[LaTeX Command: nomenclature] devices. These are devices
+are found in virtual environments[LaTeX Command: nomenclature],
+yet by design they are not all that different from physical PCI
+devices, and this document treats them as such. This allows the
+guest to use standard PCI drivers and discovery mechanisms.
+
+The purpose of virtio and this specification is that virtual
+environments and guests should have a straightforward, efficient,
+standard and extensible mechanism for virtual devices, rather
+than boutique per-environment or per-OS mechanisms.
+
+  Straightforward: Virtio PCI devices use normal PCI mechanisms
+  of interrupts and DMA which should be familiar to any device
+  driver author. There is no exotic page-flipping or COW
+  mechanism: it's just a PCI device.[footnote:
+This lack of page-sharing implies that the implementation of the
+device (e.g. the hypervisor or host) needs full access to the
+guest memory. Communication with untrusted parties (i.e.
+inter-guest communication) requires copying.
+]
+
+  Efficient: Virtio PCI devices consist of rings of descriptors
+  for input and output, which are neatly separated to avoid cache
+  effects from both guest and device writing to the same cache
+  lines.
+
+  Standard: Virtio PCI makes no assumptions about the environment
+  in which it operates, beyond supporting PCI. In fact the virtio
+  devices specified in the appendices do not require PCI at all:
+  they have been implemented on non-PCI buses.[footnote:
+The Linux implementation further separates the PCI virtio code
+from the specific virtio drivers: these drivers are shared with
+the non-PCI implementations (currently lguest and S/390).
+]
+
+  Extensible: Virtio PCI devices contain feature bits which are
+  acknowledged by the guest operating system during device setup.
+  This allows forwards and backwards compatibility: the device
+  offers all the features it knows about, and the driver
+  acknowledges those it understands and wishes to use.
+
+  Virtqueues
+
+The mechanism for bulk data transport on virtio PCI devices is
+pretentiously called a virtqueue. Each device can have zero or
+more virtqueues: for example, the network device has one for
+transmit and one for receive.
+
+Each virtqueue occupies two or more physically-contiguous pages
+(defined, for the purposes of this specification, as 4096 bytes),
+and consists of three parts:
+
+
++-------------------+-----------------------------------+-----------+
+| Descriptor Table  |   Available Ring     (padding)    | Used Ring |
++-------------------+-----------------------------------+-----------+
+
+
+When the driver wants to send buffers to the device, it puts them
+in one or more slots in the descriptor table, and writes the
+descriptor indices into the available ring. It then notifies the
+device. When the device has finished with the buffers, it writes
+the descriptors into the used ring, and sends an interrupt.
+
+Specification
+
+  PCI Discovery
+
+Any PCI device with Vendor ID 0x1AF4, and Device ID 0x1000
+through 0x103F inclusive is a virtio device[footnote:
+The actual value within this range is ignored
+]. The device must also have a Revision ID of 0 to match this
+specification.
+
+The Subsystem Device ID indicates which virtio device is
+supported by the device. The Subsystem Vendor ID should reflect
+the PCI Vendor ID of the environment (it's currently only used
+for informational purposes by the guest).
+
+
++----------------------+--------------------+---------------+
+| Subsystem Device ID  |   Virtio Device    | Specification |
++----------------------+--------------------+---------------+
++----------------------+--------------------+---------------+
+|          1           |   network card     |  Appendix C   |
++----------------------+--------------------+---------------+
+|          2           |   block device     |  Appendix D   |
++----------------------+--------------------+---------------+
+|          3           |      console       |  Appendix E   |
++----------------------+--------------------+---------------+
+|          4           |  entropy source    |  Appendix F   |
++----------------------+--------------------+---------------+
+|          5           | memory ballooning  |  Appendix G   |
++----------------------+--------------------+---------------+
+|          6           |     ioMemory       |       -       |
++----------------------+--------------------+---------------+
+|          9           |   9P transport     |       -       |
++----------------------+--------------------+---------------+
+
+
+  Device Configuration
+
+To configure the device, we use the first I/O region of the PCI
+device. This contains a virtio header followed by a
+device-specific region.
+
+There may be different widths of accesses to the I/O region; the “
+natural” access method for each field in the virtio header must
+be used (i.e. 32-bit accesses for 32-bit fields, etc), but the
+device-specific region can be accessed using any width accesses,
+and should obtain the same results.
+
+Note that this is possible because while the virtio header is PCI
+(i.e. little) endian, the device-specific region is encoded in
+the native endian of the guest (where such distinction is
+applicable).
+
+  Device Initialization Sequence
+
+We start with an overview of device initialization, then expand
+on the details of the device and how each step is preformed.
+
+  Reset the device. This is not required on initial start up.
+
+  The ACKNOWLEDGE status bit is set: we have noticed the device.
+
+  The DRIVER status bit is set: we know how to drive the device.
+
+  Device-specific setup, including reading the Device Feature
+  Bits, discovery of virtqueues for the device, optional MSI-X
+  setup, and reading and possibly writing the virtio
+  configuration space.
+
+  The subset of Device Feature Bits understood by the driver is
+  written to the device.
+
+  The DRIVER_OK status bit is set.
+
+  The device can now be used (ie. buffers added to the
+  virtqueues)[footnote:
+Historically, drivers have used the device before steps 5 and 6.
+This is only allowed if the driver does not use any features
+which would alter this early use of the device.
+]
+
+If any of these steps go irrecoverably wrong, the guest should
+set the FAILED status bit to indicate that it has given up on the
+device (it can reset the device later to restart if desired).
+
+We now cover the fields required for general setup in detail.
+
+  Virtio Header
+
+The virtio header looks as follows:
+
+
++------------++---------------------+---------------------+----------+--------+---------+---------+---------+--------+
+| Bits       || 32                  | 32                  | 32       | 16     | 16      | 16      | 8       | 8      |
++------------++---------------------+---------------------+----------+--------+---------+---------+---------+--------+
+| Read/Write || R                   | R+W                 | R+W      | R      | R+W     | R+W     | R+W     | R      |
++------------++---------------------+---------------------+----------+--------+---------+---------+---------+--------+
+| Purpose    || Device              | Guest               | Queue    | Queue  | Queue   | Queue   | Device  | ISR    |
+|            || Features bits 0:31  | Features bits 0:31  | Address  | Size   | Select  | Notify  | Status  | Status |
++------------++---------------------+---------------------+----------+--------+---------+---------+---------+--------+
+
+
+If MSI-X is enabled for the device, two additional fields
+immediately follow this header:
+
+
++------------++----------------+--------+
+| Bits       || 16             | 16     |
+              +----------------+--------+
++------------++----------------+--------+
+| Read/Write || R+W            | R+W    |
++------------++----------------+--------+
+| Purpose    || Configuration  | Queue  |
+| (MSI-X)    || Vector         | Vector |
++------------++----------------+--------+
+
+
+Finally, if feature bits (VIRTIO_F_FEATURES_HI) this is
+immediately followed by two additional fields:
+
+
++------------++----------------------+----------------------
+| Bits       || 32                   | 32
++------------++----------------------+----------------------
+| Read/Write || R                    | R+W
++------------++----------------------+----------------------
+| Purpose    || Device               | Guest
+|            || Features bits 32:63  | Features bits 32:63
++------------++----------------------+----------------------
+
+
+Immediately following these general headers, there may be
+device-specific headers:
+
+
++------------++--------------------+
+| Bits       || Device Specific    |
+              +--------------------+
++------------++--------------------+
+| Read/Write || Device Specific    |
++------------++--------------------+
+| Purpose    || Device Specific... |
+|            ||                    |
++------------++--------------------+
+
+
+  Device Status
+
+The Device Status field is updated by the guest to indicate its
+progress. This provides a simple low-level diagnostic: it's most
+useful to imagine them hooked up to traffic lights on the console
+indicating the status of each device.
+
+The device can be reset by writing a 0 to this field, otherwise
+at least one bit should be set:
+
+  ACKNOWLEDGE (1) Indicates that the guest OS has found the
+  device and recognized it as a valid virtio device.
+
+  DRIVER (2) Indicates that the guest OS knows how to drive the
+  device. Under Linux, drivers can be loadable modules so there
+  may be a significant (or infinite) delay before setting this
+  bit.
+
+  DRIVER_OK (3) Indicates that the driver is set up and ready to
+  drive the device.
+
+  FAILED (8) Indicates that something went wrong in the guest,
+  and it has given up on the device. This could be an internal
+  error, or the driver didn't like the device for some reason, or
+  even a fatal error during device operation. The device must be
+  reset before attempting to re-initialize.
+
+  Feature Bits
+
+The least significant 31 bits of the first configuration field
+indicates the features that the device supports (the high bit is
+reserved, and will be used to indicate the presence of future
+feature bits elsewhere). If more than 31 feature bits are
+supported, the device indicates so by setting feature bit 31 (see
+[cha:Reserved-Feature-Bits]). The bits are allocated as follows:
+
+  0 to 23 Feature bits for the specific device type
+
+  24 to 40 Feature bits reserved for extensions to the queue and
+  feature negotiation mechanisms
+
+  41 to 63 Feature bits reserved for future extensions
+
+For example, feature bit 0 for a network device (i.e. Subsystem
+Device ID 1) indicates that the device supports checksumming of
+packets.
+
+The feature bits are negotiated: the device lists all the
+features it understands in the Device Features field, and the
+guest writes the subset that it understands into the Guest
+Features field. The only way to renegotiate is to reset the
+device.
+
+In particular, new fields in the device configuration header are
+indicated by offering a feature bit, so the guest can check
+before accessing that part of the configuration space.
+
+This allows for forwards and backwards compatibility: if the
+device is enhanced with a new feature bit, older guests will not
+write that feature bit back to the Guest Features field and it
+can go into backwards compatibility mode. Similarly, if a guest
+is enhanced with a feature that the device doesn't support, it
+will not see that feature bit in the Device Features field and
+can go into backwards compatibility mode (or, for poor
+implementations, set the FAILED Device Status bit).
+
+Access to feature bits 32 to 63 is enabled by Guest by setting
+feature bit 31. If this bit is unset, Device must assume that all
+feature bits > 31 are unset.
+
+  Configuration/Queue Vectors
+
+When MSI-X capability is present and enabled in the device
+(through standard PCI configuration space) 4 bytes at byte offset
+20 are used to map configuration change and queue interrupts to
+MSI-X vectors. In this case, the ISR Status field is unused, and
+device specific configuration starts at byte offset 24 in virtio
+header structure. When MSI-X capability is not enabled, device
+specific configuration starts at byte offset 20 in virtio header.
+
+Writing a valid MSI-X Table entry number, 0 to 0x7FF, to one of
+Configuration/Queue Vector registers, maps interrupts triggered
+by the configuration change/selected queue events respectively to
+the corresponding MSI-X vector. To disable interrupts for a
+specific event type, unmap it by writing a special NO_VECTOR
+value:
+
+/* Vector value used to disable MSI for queue */
+
+#define VIRTIO_MSI_NO_VECTOR            0xffff
+
+Reading these registers returns vector mapped to a given event,
+or NO_VECTOR if unmapped. All queue and configuration change
+events are unmapped by default.
+
+Note that mapping an event to vector might require allocating
+internal device resources, and might fail. Devices report such
+failures by returning the NO_VECTOR value when the relevant
+Vector field is read. After mapping an event to vector, the
+driver must verify success by reading the Vector field value: on
+success, the previously written value is returned, and on
+failure, NO_VECTOR is returned. If a mapping failure is detected,
+the driver can retry mapping with fewervectors, or disable MSI-X.
+
+  Virtqueue Configuration
+
+As a device can have zero or more virtqueues for bulk data
+transport (for example, the network driver has two), the driver
+needs to configure them as part of the device-specific
+configuration.
+
+This is done as follows, for each virtqueue a device has:
+
+  Write the virtqueue index (first queue is 0) to the Queue
+  Select field.
+
+  Read the virtqueue size from the Queue Size field, which is
+  always a power of 2. This controls how big the virtqueue is
+  (see below). If this field is 0, the virtqueue does not exist.
+
+  Allocate and zero virtqueue in contiguous physical memory, on a
+  4096 byte alignment. Write the physical address, divided by
+  4096 to the Queue Address field.[footnote:
+The 4096 is based on the x86 page size, but it's also large
+enough to ensure that the separate parts of the virtqueue are on
+separate cache lines.
+]
+
+  Optionally, if MSI-X capability is present and enabled on the
+  device, select a vector to use to request interrupts triggered
+  by virtqueue events. Write the MSI-X Table entry number
+  corresponding to this vector in Queue Vector field. Read the
+  Queue Vector field: on success, previously written value is
+  returned; on failure, NO_VECTOR value is returned.
+
+The Queue Size field controls the total number of bytes required
+for the virtqueue according to the following formula:
+
+#define ALIGN(x) (((x) + 4095) & ~4095)
+
+static inline unsigned vring_size(unsigned int qsz)
+
+{
+
+     return ALIGN(sizeof(struct vring_desc)*qsz + sizeof(u16)*(2
++ qsz))
+
+          + ALIGN(sizeof(struct vring_used_elem)*qsz);
+
+}
+
+This currently wastes some space with padding, but also allows
+future extensions. The virtqueue layout structure looks like this
+(qsz is the Queue Size field, which is a variable, so this code
+won't compile):
+
+struct vring {
+
+    /* The actual descriptors (16 bytes each) */
+
+    struct vring_desc desc[qsz];
+
+
+
+    /* A ring of available descriptor heads with free-running
+index. */
+
+    struct vring_avail avail;
+
+
+
+    // Padding to the next 4096 boundary.
+
+    char pad[];
+
+
+
+    // A ring of used descriptor heads with free-running index.
+
+    struct vring_used used;
+
+};
+
+  A Note on Virtqueue Endianness
+
+Note that the endian of these fields and everything else in the
+virtqueue is the native endian of the guest, not little-endian as
+PCI normally is. This makes for simpler guest code, and it is
+assumed that the host already has to be deeply aware of the guest
+endian so such an “endian-aware” device is not a significant
+issue.
+
+  Descriptor Table
+
+The descriptor table refers to the buffers the guest is using for
+the device. The addresses are physical addresses, and the buffers
+can be chained via the next field. Each descriptor describes a
+buffer which is read-only or write-only, but a chain of
+descriptors can contain both read-only and write-only buffers.
+
+No descriptor chain may be more than 2^32 bytes long in total.struct vring_desc {
+
+    /* Address (guest-physical). */
+
+    u64 addr;
+
+    /* Length. */
+
+    u32 len;
+
+/* This marks a buffer as continuing via the next field. */
+
+#define VRING_DESC_F_NEXT   1
+
+/* This marks a buffer as write-only (otherwise read-only). */
+
+#define VRING_DESC_F_WRITE     2
+
+/* This means the buffer contains a list of buffer descriptors.
+*/
+
+#define VRING_DESC_F_INDIRECT   4
+
+    /* The flags as indicated above. */
+
+    u16 flags;
+
+    /* Next field if flags & NEXT */
+
+    u16 next;
+
+};
+
+The number of descriptors in the table is specified by the Queue
+Size field for this virtqueue.
+
+  <sub:Indirect-Descriptors>Indirect Descriptors
+
+Some devices benefit by concurrently dispatching a large number
+of large requests. The VIRTIO_RING_F_INDIRECT_DESC feature can be
+used to allow this (see [cha:Reserved-Feature-Bits]). To increase
+ring capacity it is possible to store a table of indirect
+descriptors anywhere in memory, and insert a descriptor in main
+virtqueue (with flags&INDIRECT on) that refers to memory buffer
+containing this indirect descriptor table; fields addr and len
+refer to the indirect table address and length in bytes,
+respectively. The indirect table layout structure looks like this
+(len is the length of the descriptor that refers to this table,
+which is a variable, so this code won't compile):
+
+struct indirect_descriptor_table {
+
+    /* The actual descriptors (16 bytes each) */
+
+    struct vring_desc desc[len / 16];
+
+};
+
+The first indirect descriptor is located at start of the indirect
+descriptor table (index 0), additional indirect descriptors are
+chained by next field. An indirect descriptor without next field
+(with flags&NEXT off) signals the end of the indirect descriptor
+table, and transfers control back to the main virtqueue. An
+indirect descriptor can not refer to another indirect descriptor
+table (flags&INDIRECT must be off). A single indirect descriptor
+table can include both read-only and write-only descriptors;
+write-only flag (flags&WRITE) in the descriptor that refers to it
+is ignored.
+
+  Available Ring
+
+The available ring refers to what descriptors we are offering the
+device: it refers to the head of a descriptor chain. The “flags”
+field is currently 0 or 1: 1 indicating that we do not need an
+interrupt when the device consumes a descriptor from the
+available ring. Alternatively, the guest can ask the device to
+delay interrupts until an entry with an index specified by the “
+used_event” field is written in the used ring (equivalently,
+until the idx field in the used ring will reach the value
+used_event + 1). The method employed by the device is controlled
+by the VIRTIO_RING_F_EVENT_IDX feature bit (see [cha:Reserved-Feature-Bits]
+). This interrupt suppression is merely an optimization; it may
+not suppress interrupts entirely.
+
+The “idx” field indicates where we would put the next descriptor
+entry (modulo the ring size). This starts at 0, and increases.
+
+struct vring_avail {
+
+#define VRING_AVAIL_F_NO_INTERRUPT      1
+
+   u16 flags;
+
+   u16 idx;
+
+   u16 ring[qsz]; /* qsz is the Queue Size field read from device
+*/
+
+   u16 used_event;
+
+};
+
+  Used Ring
+
+The used ring is where the device returns buffers once it is done
+with them. The flags field can be used by the device to hint that
+no notification is necessary when the guest adds to the available
+ring. Alternatively, the “avail_event” field can be used by the
+device to hint that no notification is necessary until an entry
+with an index specified by the “avail_event” is written in the
+available ring (equivalently, until the idx field in the
+available ring will reach the value avail_event + 1). The method
+employed by the device is controlled by the guest through the
+VIRTIO_RING_F_EVENT_IDX feature bit (see [cha:Reserved-Feature-Bits]
+). [footnote:
+These fields are kept here because this is the only part of the
+virtqueue written by the device
+].
+
+Each entry in the ring is a pair: the head entry of the
+descriptor chain describing the buffer (this matches an entry
+placed in the available ring by the guest earlier), and the total
+of bytes written into the buffer. The latter is extremely useful
+for guests using untrusted buffers: if you do not know exactly
+how much has been written by the device, you usually have to zero
+the buffer to ensure no data leakage occurs.
+
+/* u32 is used here for ids for padding reasons. */
+
+struct vring_used_elem {
+
+    /* Index of start of used descriptor chain. */
+
+    u32 id;
+
+    /* Total length of the descriptor chain which was used
+(written to) */
+
+    u32 len;
+
+};
+
+
+
+struct vring_used {
+
+#define VRING_USED_F_NO_NOTIFY  1
+
+    u16 flags;
+
+    u16 idx;
+
+    struct vring_used_elem ring[qsz];
+
+    u16 avail_event;
+
+};
+
+  Helpers for Managing Virtqueues
+
+The Linux Kernel Source code contains the definitions above and
+helper routines in a more usable form, in
+include/linux/virtio_ring.h. This was explicitly licensed by IBM
+and Red Hat under the (3-clause) BSD license so that it can be
+freely used by all other projects, and is reproduced (with slight
+variation to remove Linux assumptions) in Appendix A.
+
+  Device Operation
+
+There are two parts to device operation: supplying new buffers to
+the device, and processing used buffers from the device. As an
+example, the virtio network device has two virtqueues: the
+transmit virtqueue and the receive virtqueue. The driver adds
+outgoing (read-only) packets to the transmit virtqueue, and then
+frees them after they are used. Similarly, incoming (write-only)
+buffers are added to the receive virtqueue, and processed after
+they are used.
+
+  Supplying Buffers to The Device
+
+Actual transfer of buffers from the guest OS to the device
+operates as follows:
+
+  Place the buffer(s) into free descriptor(s).
+
+  If there are no free descriptors, the guest may choose to
+    notify the device even if notifications are suppressed (to
+    reduce latency).[footnote:
+The Linux drivers do this only for read-only buffers: for
+write-only buffers, it is assumed that the driver is merely
+trying to keep the receive buffer ring full, and no notification
+of this expected condition is necessary.
+]
+
+  Place the id of the buffer in the next ring entry of the
+  available ring.
+
+  The steps (1) and (2) may be performed repeatedly if batching
+  is possible.
+
+  A memory barrier should be executed to ensure the device sees
+  the updated descriptor table and available ring before the next
+  step.
+
+  The available “idx” field should be increased by the number of
+  entries added to the available ring.
+
+  A memory barrier should be executed to ensure that we update
+  the idx field before checking for notification suppression.
+
+  If notifications are not suppressed, the device should be
+  notified of the new buffers.
+
+Note that the above code does not take precautions against the
+available ring buffer wrapping around: this is not possible since
+the ring buffer is the same size as the descriptor table, so step
+(1) will prevent such a condition.
+
+In addition, the maximum queue size is 32768 (it must be a power
+of 2 which fits in 16 bits), so the 16-bit “idx” value can always
+distinguish between a full and empty buffer.
+
+Here is a description of each stage in more detail.
+
+  Placing Buffers Into The Descriptor Table
+
+A buffer consists of zero or more read-only physically-contiguous
+elements followed by zero or more physically-contiguous
+write-only elements (it must have at least one element). This
+algorithm maps it into the descriptor table:
+
+  for each buffer element, b:
+
+  Get the next free descriptor table entry, d
+
+  Set d.addr to the physical address of the start of b
+
+  Set d.len to the length of b.
+
+  If b is write-only, set d.flags to VRING_DESC_F_WRITE,
+    otherwise 0.
+
+  If there is a buffer element after this:
+
+    Set d.next to the index of the next free descriptor element.
+
+    Set the VRING_DESC_F_NEXT bit in d.flags.
+
+In practice, the d.next fields are usually used to chain free
+descriptors, and a separate count kept to check there are enough
+free descriptors before beginning the mappings.
+
+  Updating The Available Ring
+
+The head of the buffer we mapped is the first d in the algorithm
+above. A naive implementation would do the following:
+
+avail->ring[avail->idx % qsz] = head;
+
+However, in general we can add many descriptors before we update
+the “idx” field (at which point they become visible to the
+device), so we keep a counter of how many we've added:
+
+avail->ring[(avail->idx + added++) % qsz] = head;
+
+  Updating The Index Field
+
+Once the idx field of the virtqueue is updated, the device will
+be able to access the descriptor entries we've created and the
+memory they refer to. This is why a memory barrier is generally
+used before the idx update, to ensure it sees the most up-to-date
+copy.
+
+The idx field always increments, and we let it wrap naturally at
+65536:
+
+avail->idx += added;
+
+  <sub:Notifying-The-Device>Notifying The Device
+
+Device notification occurs by writing the 16-bit virtqueue index
+of this virtqueue to the Queue Notify field of the virtio header
+in the first I/O region of the PCI device. This can be expensive,
+however, so the device can suppress such notifications if it
+doesn't need them. We have to be careful to expose the new idx
+value before checking the suppression flag: it's OK to notify
+gratuitously, but not to omit a required notification. So again,
+we use a memory barrier here before reading the flags or the
+avail_event field.
+
+If the VIRTIO_F_RING_EVENT_IDX feature is not negotiated, and if
+the VRING_USED_F_NOTIFY flag is not set, we go ahead and write to
+the PCI configuration space.
+
+If the VIRTIO_F_RING_EVENT_IDX feature is negotiated, we read the
+avail_event field in the available ring structure. If the
+available index crossed_the avail_event field value since the
+last notification, we go ahead and write to the PCI configuration
+space. The avail_event field wraps naturally at 65536 as well:
+
+(u16)(new_idx - avail_event - 1) < (u16)(new_idx - old_idx)
+
+  <sub:Receiving-Used-Buffers>Receiving Used Buffers From The
+  Device
+
+Once the device has used a buffer (read from or written to it, or
+parts of both, depending on the nature of the virtqueue and the
+device), it sends an interrupt, following an algorithm very
+similar to the algorithm used for the driver to send the device a
+buffer:
+
+  Write the head descriptor number to the next field in the used
+  ring.
+
+  Update the used ring idx.
+
+  Determine whether an interrupt is necessary:
+
+  If the VIRTIO_F_RING_EVENT_IDX feature is not negotiated: check
+    if f the VRING_AVAIL_F_NO_INTERRUPT flag is not set in avail-
+    >flags
+
+  If the VIRTIO_F_RING_EVENT_IDX feature is negotiated: check
+    whether the used index crossed the used_event field value
+    since the last update. The used_event field wraps naturally
+    at 65536 as well:(u16)(new_idx - used_event - 1) < (u16)(new_idx - old_idx)
+
+  If an interrupt is necessary:
+
+  If MSI-X capability is disabled:
+
+    Set the lower bit of the ISR Status field for the device.
+
+    Send the appropriate PCI interrupt for the device.
+
+  If MSI-X capability is enabled:
+
+    Request the appropriate MSI-X interrupt message for the
+      device, Queue Vector field sets the MSI-X Table entry
+      number.
+
+    If Queue Vector field value is NO_VECTOR, no interrupt
+      message is requested for this event.
+
+The guest interrupt handler should:
+
+  If MSI-X capability is disabled: read the ISR Status field,
+  which will reset it to zero. If the lower bit is zero, the
+  interrupt was not for this device. Otherwise, the guest driver
+  should look through the used rings of each virtqueue for the
+  device, to see if any progress has been made by the device
+  which requires servicing.
+
+  If MSI-X capability is enabled: look through the used rings of
+  each virtqueue mapped to the specific MSI-X vector for the
+  device, to see if any progress has been made by the device
+  which requires servicing.
+
+For each ring, guest should then disable interrupts by writing
+VRING_AVAIL_F_NO_INTERRUPT flag in avail structure, if required.
+It can then process used ring entries finally enabling interrupts
+by clearing the VRING_AVAIL_F_NO_INTERRUPT flag or updating the
+EVENT_IDX field in the available structure, Guest should then
+execute a memory barrier, and then recheck the ring empty
+condition. This is necessary to handle the case where, after the
+last check and before enabling interrupts, an interrupt has been
+suppressed by the device:
+
+vring_disable_interrupts(vq);
+
+for (;;) {
+
+    if (vq->last_seen_used != vring->used.idx) {
+
+		vring_enable_interrupts(vq);
+
+		mb();
+
+		if (vq->last_seen_used != vring->used.idx)
+
+			break;
+
+    }
+
+    struct vring_used_elem *e =
+vring.used->ring[vq->last_seen_used%vsz];
+
+    process_buffer(e);
+
+    vq->last_seen_used++;
+
+}
+
+  Dealing With Configuration Changes
+
+Some virtio PCI devices can change the device configuration
+state, as reflected in the virtio header in the PCI configuration
+space. In this case:
+
+  If MSI-X capability is disabled: an interrupt is delivered and
+  the second highest bit is set in the ISR Status field to
+  indicate that the driver should re-examine the configuration
+  space.Note that a single interrupt can indicate both that one
+  or more virtqueue has been used and that the configuration
+  space has changed: even if the config bit is set, virtqueues
+  must be scanned.
+
+  If MSI-X capability is enabled: an interrupt message is
+  requested. The Configuration Vector field sets the MSI-X Table
+  entry number to use. If Configuration Vector field value is
+  NO_VECTOR, no interrupt message is requested for this event.
+
+Creating New Device Types
+
+Various considerations are necessary when creating a new device
+type:
+
+  How Many Virtqueues?
+
+It is possible that a very simple device will operate entirely
+through its configuration space, but most will need at least one
+virtqueue in which it will place requests. A device with both
+input and output (eg. console and network devices described here)
+need two queues: one which the driver fills with buffers to
+receive input, and one which the driver places buffers to
+transmit output.
+
+  What Configuration Space Layout?
+
+Configuration space is generally used for rarely-changing or
+initialization-time parameters. But it is a limited resource, so
+it might be better to use a virtqueue to update configuration
+information (the network device does this for filtering,
+otherwise the table in the config space could potentially be very
+large).
+
+Note that this space is generally the guest's native endian,
+rather than PCI's little-endian.
+
+  What Device Number?
+
+Currently device numbers are assigned quite freely: a simple
+request mail to the author of this document or the Linux
+virtualization mailing list[footnote:
+
+https://lists.linux-foundation.org/mailman/listinfo/virtualization
+] will be sufficient to secure a unique one.
+
+Meanwhile for experimental drivers, use 65535 and work backwards.
+
+  How many MSI-X vectors?
+
+Using the optional MSI-X capability devices can speed up
+interrupt processing by removing the need to read ISR Status
+register by guest driver (which might be an expensive operation),
+reducing interrupt sharing between devices and queues within the
+device, and handling interrupts from multiple CPUs. However, some
+systems impose a limit (which might be as low as 256) on the
+total number of MSI-X vectors that can be allocated to all
+devices. Devices and/or device drivers should take this into
+account, limiting the number of vectors used unless the device is
+expected to cause a high volume of interrupts. Devices can
+control the number of vectors used by limiting the MSI-X Table
+Size or not presenting MSI-X capability in PCI configuration
+space. Drivers can control this by mapping events to as small
+number of vectors as possible, or disabling MSI-X capability
+altogether.
+
+  Message Framing
+
+The descriptors used for a buffer should not effect the semantics
+of the message, except for the total length of the buffer. For
+example, a network buffer consists of a 10 byte header followed
+by the network packet. Whether this is presented in the ring
+descriptor chain as (say) a 10 byte buffer and a 1514 byte
+buffer, or a single 1524 byte buffer, or even three buffers,
+should have no effect.
+
+In particular, no implementation should use the descriptor
+boundaries to determine the size of any header in a request.[footnote:
+The current qemu device implementations mistakenly insist that
+the first descriptor cover the header in these cases exactly, so
+a cautious driver should arrange it so.
+]
+
+  Device Improvements
+
+Any change to configuration space, or new virtqueues, or
+behavioural changes, should be indicated by negotiation of a new
+feature bit. This establishes clarity[footnote:
+Even if it does mean documenting design or implementation
+mistakes!
+] and avoids future expansion problems.
+
+Clusters of functionality which are always implemented together
+can use a single bit, but if one feature makes sense without the
+others they should not be gratuitously grouped together to
+conserve feature bits. We can always extend the spec when the
+first person needs more than 24 feature bits for their device.
+
+[LaTeX Command: printnomenclature]
+
+Appendix A: virtio_ring.h
+
+#ifndef VIRTIO_RING_H
+
+#define VIRTIO_RING_H
+
+/* An interface for efficient virtio implementation.
+
+ *
+
+ * This header is BSD licensed so anyone can use the definitions
+
+ * to implement compatible drivers/servers.
+
+ *
+
+ * Copyright 2007, 2009, IBM Corporation
+
+ * Copyright 2011, Red Hat, Inc
+
+ * All rights reserved.
+
+ *
+
+ * Redistribution and use in source and binary forms, with or
+without
+
+ * modification, are permitted provided that the following
+conditions
+
+ * are met:
+
+ * 1. Redistributions of source code must retain the above
+copyright
+
+ *    notice, this list of conditions and the following
+disclaimer.
+
+ * 2. Redistributions in binary form must reproduce the above
+copyright
+
+ *    notice, this list of conditions and the following
+disclaimer in the
+
+ *    documentation and/or other materials provided with the
+distribution.
+
+ * 3. Neither the name of IBM nor the names of its contributors
+
+ *    may be used to endorse or promote products derived from
+this software
+
+ *    without specific prior written permission.
+
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
+CONTRIBUTORS ``AS IS'' AND
+
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+TO, THE
+
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+PARTICULAR PURPOSE
+
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE
+LIABLE
+
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL
+
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS
+
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION)
+
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT
+
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING
+IN ANY WAY
+
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF
+
+ * SUCH DAMAGE.
+
+ */
+
+
+
+/* This marks a buffer as continuing via the next field. */
+
+#define VRING_DESC_F_NEXT       1
+
+/* This marks a buffer as write-only (otherwise read-only). */
+
+#define VRING_DESC_F_WRITE      2
+
+
+
+/* The Host uses this in used->flags to advise the Guest: don't
+kick me
+
+ * when you add a buffer.  It's unreliable, so it's simply an
+
+ * optimization.  Guest will still kick if it's out of buffers.
+*/
+
+#define VRING_USED_F_NO_NOTIFY  1
+
+/* The Guest uses this in avail->flags to advise the Host: don't
+
+ * interrupt me when you consume a buffer.  It's unreliable, so
+it's
+
+ * simply an optimization.  */
+
+#define VRING_AVAIL_F_NO_INTERRUPT      1
+
+
+
+/* Virtio ring descriptors: 16 bytes.
+
+ * These can chain together via "next". */
+
+struct vring_desc {
+
+        /* Address (guest-physical). */
+
+        uint64_t addr;
+
+        /* Length. */
+
+        uint32_t len;
+
+        /* The flags as indicated above. */
+
+        uint16_t flags;
+
+        /* We chain unused descriptors via this, too */
+
+        uint16_t next;
+
+};
+
+
+
+struct vring_avail {
+
+        uint16_t flags;
+
+        uint16_t idx;
+
+        uint16_t ring[];
+
+        uint16_t used_event;
+
+};
+
+
+
+/* u32 is used here for ids for padding reasons. */
+
+struct vring_used_elem {
+
+        /* Index of start of used descriptor chain. */
+
+        uint32_t id;
+
+        /* Total length of the descriptor chain which was written
+to. */
+
+        uint32_t len;
+
+};
+
+
+
+struct vring_used {
+
+        uint16_t flags;
+
+        uint16_t idx;
+
+        struct vring_used_elem ring[];
+
+        uint16_t avail_event;
+
+};
+
+
+
+struct vring {
+
+        unsigned int num;
+
+
+
+        struct vring_desc *desc;
+
+        struct vring_avail *avail;
+
+        struct vring_used *used;
+
+};
+
+
+
+/* The standard layout for the ring is a continuous chunk of
+memory which
+
+ * looks like this.  We assume num is a power of 2.
+
+ *
+
+ * struct vring {
+
+ *      // The actual descriptors (16 bytes each)
+
+ *      struct vring_desc desc[num];
+
+ *
+
+ *      // A ring of available descriptor heads with free-running
+index.
+
+ *      __u16 avail_flags;
+
+ *      __u16 avail_idx;
+
+ *      __u16 available[num];
+
+ *
+
+ *      // Padding to the next align boundary.
+
+ *      char pad[];
+
+ *
+
+ *      // A ring of used descriptor heads with free-running
+index.
+
+ *      __u16 used_flags;
+
+ *      __u16 EVENT_IDX;
+
+ *      struct vring_used_elem used[num];
+
+ * };
+
+ * Note: for virtio PCI, align is 4096.
+
+ */
+
+static inline void vring_init(struct vring *vr, unsigned int num,
+void *p,
+
+                              unsigned long align)
+
+{
+
+        vr->num = num;
+
+        vr->desc = p;
+
+        vr->avail = p + num*sizeof(struct vring_desc);
+
+        vr->used = (void *)(((unsigned long)&vr->avail->ring[num]
+
+                              + align-1)
+
+                            & ~(align - 1));
+
+}
+
+
+
+static inline unsigned vring_size(unsigned int num, unsigned long
+align)
+
+{
+
+        return ((sizeof(struct vring_desc)*num +
+sizeof(uint16_t)*(2+num)
+
+                 + align - 1) & ~(align - 1))
+
+                + sizeof(uint16_t)*3 + sizeof(struct
+vring_used_elem)*num;
+
+}
+
+
+
+static inline int vring_need_event(uint16_t event_idx, uint16_t
+new_idx, uint16_t old_idx)
+
+{
+
+         return (uint16_t)(new_idx - event_idx - 1) <
+(uint16_t)(new_idx - old_idx);
+
+}
+
+#endif /* VIRTIO_RING_H */
+
+<cha:Reserved-Feature-Bits>Appendix B: Reserved Feature Bits
+
+Currently there are five device-independent feature bits defined:
+
+  VIRTIO_F_NOTIFY_ON_EMPTY (24) Negotiating this feature
+  indicates that the driver wants an interrupt if the device runs
+  out of available descriptors on a virtqueue, even though
+  interrupts are suppressed using the VRING_AVAIL_F_NO_INTERRUPT
+  flag or the used_event field. An example of this is the
+  networking driver: it doesn't need to know every time a packet
+  is transmitted, but it does need to free the transmitted
+  packets a finite time after they are transmitted. It can avoid
+  using a timer if the device interrupts it when all the packets
+  are transmitted.
+
+  VIRTIO_F_RING_INDIRECT_DESC (28) Negotiating this feature
+  indicates that the driver can use descriptors with the
+  VRING_DESC_F_INDIRECT flag set, as described in [sub:Indirect-Descriptors]
+  .
+
+  VIRTIO_F_RING_EVENT_IDX(29) This feature enables the used_event
+  and the avail_event fields. If set, it indicates that the
+  device should ignore the flags field in the available ring
+  structure. Instead, the used_event field in this structure is
+  used by guest to suppress device interrupts. Further, the
+  driver should ignore the flags field in the used ring
+  structure. Instead, the avail_event field in this structure is
+  used by the device to suppress notifications. If unset, the
+  driver should ignore the used_event field; the device should
+  ignore the avail_event field; the flags field is used
+
+  VIRTIO_F_BAD_FEATURE(30) This feature should never be
+  negotiated by the guest; doing so is an indication that the
+  guest is faulty[footnote:
+An experimental virtio PCI driver contained in Linux version
+2.6.25 had this problem, and this feature bit can be used to
+detect it.
+]
+
+  VIRTIO_F_FEATURES_HIGH(31) This feature indicates that the
+  device supports feature bits 32:63. If unset, feature bits
+  32:63 are unset.
+
+Appendix C: Network Device
+
+The virtio network device is a virtual ethernet card, and is the
+most complex of the devices supported so far by virtio. It has
+enhanced rapidly and demonstrates clearly how support for new
+features should be added to an existing device. Empty buffers are
+placed in one virtqueue for receiving packets, and outgoing
+packets are enqueued into another for transmission in that order.
+A third command queue is used to control advanced filtering
+features.
+
+  Configuration
+
+  Subsystem Device ID 1
+
+  Virtqueues 0:receiveq. 1:transmitq. 2:controlq[footnote:
+Only if VIRTIO_NET_F_CTRL_VQ set
+]
+
+  Feature bits
+
+  VIRTIO_NET_F_CSUM (0) Device handles packets with partial
+    checksum
+
+  VIRTIO_NET_F_GUEST_CSUM (1) Guest handles packets with partial
+    checksum
+
+  VIRTIO_NET_F_MAC (5) Device has given MAC address.
+
+  VIRTIO_NET_F_GSO (6) (Deprecated) device handles packets with
+    any GSO type.[footnote:
+It was supposed to indicate segmentation offload support, but
+upon further investigation it became clear that multiple bits
+were required.
+]
+
+  VIRTIO_NET_F_GUEST_TSO4 (7) Guest can receive TSOv4.
+
+  VIRTIO_NET_F_GUEST_TSO6 (8) Guest can receive TSOv6.
+
+  VIRTIO_NET_F_GUEST_ECN (9) Guest can receive TSO with ECN.
+
+  VIRTIO_NET_F_GUEST_UFO (10) Guest can receive UFO.
+
+  VIRTIO_NET_F_HOST_TSO4 (11) Device can receive TSOv4.
+
+  VIRTIO_NET_F_HOST_TSO6 (12) Device can receive TSOv6.
+
+  VIRTIO_NET_F_HOST_ECN (13) Device can receive TSO with ECN.
+
+  VIRTIO_NET_F_HOST_UFO (14) Device can receive UFO.
+
+  VIRTIO_NET_F_MRG_RXBUF (15) Guest can merge receive buffers.
+
+  VIRTIO_NET_F_STATUS (16) Configuration status field is
+    available.
+
+  VIRTIO_NET_F_CTRL_VQ (17) Control channel is available.
+
+  VIRTIO_NET_F_CTRL_RX (18) Control channel RX mode support.
+
+  VIRTIO_NET_F_CTRL_VLAN (19) Control channel VLAN filtering.
+
+  Device configuration layout Two configuration fields are
+  currently defined. The mac address field always exists (though
+  is only valid if VIRTIO_NET_F_MAC is set), and the status field
+  only exists if VIRTIO_NET_F_STATUS is set. Only one bit is
+  currently defined for the status field: VIRTIO_NET_S_LINK_UP. #define VIRTIO_NET_S_LINK_UP	1
+
+
+
+struct virtio_net_config {
+
+    u8 mac[6];
+
+    u16 status;
+
+};
+
+  Device Initialization
+
+  The initialization routine should identify the receive and
+  transmission virtqueues.
+
+  If the VIRTIO_NET_F_MAC feature bit is set, the configuration
+  space “mac” entry indicates the “physical” address of the the
+  network card, otherwise a private MAC address should be
+  assigned. All guests are expected to negotiate this feature if
+  it is set.
+
+  If the VIRTIO_NET_F_CTRL_VQ feature bit is negotiated, identify
+  the control virtqueue.
+
+  If the VIRTIO_NET_F_STATUS feature bit is negotiated, the link
+  status can be read from the bottom bit of the “status” config
+  field. Otherwise, the link should be assumed active.
+
+  The receive virtqueue should be filled with receive buffers.
+  This is described in detail below in “Setting Up Receive
+  Buffers”.
+
+  A driver can indicate that it will generate checksumless
+  packets by negotating the VIRTIO_NET_F_CSUM feature. This “
+  checksum offload” is a common feature on modern network cards.
+
+  If that feature is negotiated, a driver can use TCP or UDP
+  segmentation offload by negotiating the VIRTIO_NET_F_HOST_TSO4
+  (IPv4 TCP), VIRTIO_NET_F_HOST_TSO6 (IPv6 TCP) and
+  VIRTIO_NET_F_HOST_UFO (UDP fragmentation) features. It should
+  not send TCP packets requiring segmentation offload which have
+  the Explicit Congestion Notification bit set, unless the
+  VIRTIO_NET_F_HOST_ECN feature is negotiated.[footnote:
+This is a common restriction in real, older network cards.
+]
+
+  The converse features are also available: a driver can save the
+  virtual device some work by negotiating these features.[footnote:
+For example, a network packet transported between two guests on
+the same system may not require checksumming at all, nor
+segmentation, if both guests are amenable.
+] The VIRTIO_NET_F_GUEST_CSUM feature indicates that partially
+  checksummed packets can be received, and if it can do that then
+  the VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6,
+  VIRTIO_NET_F_GUEST_UFO and VIRTIO_NET_F_GUEST_ECN are the input
+  equivalents of the features described above. See “Receiving
+  Packets” below.
+
+  Device Operation
+
+Packets are transmitted by placing them in the transmitq, and
+buffers for incoming packets are placed in the receiveq. In each
+case, the packet itself is preceeded by a header:
+
+struct virtio_net_hdr {
+
+#define VIRTIO_NET_HDR_F_NEEDS_CSUM    1
+
+	u8 flags;
+
+#define VIRTIO_NET_HDR_GSO_NONE        0
+
+#define VIRTIO_NET_HDR_GSO_TCPV4       1
+
+#define VIRTIO_NET_HDR_GSO_UDP		 3
+
+#define VIRTIO_NET_HDR_GSO_TCPV6       4
+
+#define VIRTIO_NET_HDR_GSO_ECN      0x80
+
+	u8 gso_type;
+
+	u16 hdr_len;
+
+	u16 gso_size;
+
+	u16 csum_start;
+
+	u16 csum_offset;
+
+/* Only if VIRTIO_NET_F_MRG_RXBUF: */
+
+	u16 num_buffers
+
+};
+
+The controlq is used to control device features such as
+filtering.
+
+  Packet Transmission
+
+Transmitting a single packet is simple, but varies depending on
+the different features the driver negotiated.
+
+  If the driver negotiated VIRTIO_NET_F_CSUM, and the packet has
+  not been fully checksummed, then the virtio_net_hdr's fields
+  are set as follows. Otherwise, the packet must be fully
+  checksummed, and flags is zero.
+
+  flags has the VIRTIO_NET_HDR_F_NEEDS_CSUM set,
+
+  <ite:csum_start-is-set>csum_start is set to the offset within
+    the packet to begin checksumming, and
+
+  csum_offset indicates how many bytes after the csum_start the
+    new (16 bit ones' complement) checksum should be placed.[footnote:
+For example, consider a partially checksummed TCP (IPv4) packet.
+It will have a 14 byte ethernet header and 20 byte IP header
+followed by the TCP header (with the TCP checksum field 16 bytes
+into that header). csum_start will be 14+20 = 34 (the TCP
+checksum includes the header), and csum_offset will be 16. The
+value in the TCP checksum field will be the sum of the TCP pseudo
+header, so that replacing it by the ones' complement checksum of
+the TCP header and body will give the correct result.
+]
+
+  <enu:If-the-driver>If the driver negotiated
+  VIRTIO_NET_F_HOST_TSO4, TSO6 or UFO, and the packet requires
+  TCP segmentation or UDP fragmentation, then the “gso_type”
+  field is set to VIRTIO_NET_HDR_GSO_TCPV4, TCPV6 or UDP.
+  (Otherwise, it is set to VIRTIO_NET_HDR_GSO_NONE). In this
+  case, packets larger than 1514 bytes can be transmitted: the
+  metadata indicates how to replicate the packet header to cut it
+  into smaller packets. The other gso fields are set:
+
+  hdr_len is a hint to the device as to how much of the header
+    needs to be kept to copy into each packet, usually set to the
+    length of the headers, including the transport header.[footnote:
+Due to various bugs in implementations, this field is not useful
+as a guarantee of the transport header size.
+]
+
+  gso_size is the size of the packet beyond that header (ie.
+    MSS).
+
+  If the driver negotiated the VIRTIO_NET_F_HOST_ECN feature, the
+    VIRTIO_NET_HDR_GSO_ECN bit may be set in “gso_type” as well,
+    indicating that the TCP packet has the ECN bit set.[footnote:
+This case is not handled by some older hardware, so is called out
+specifically in the protocol.
+]
+
+  If the driver negotiated the VIRTIO_NET_F_MRG_RXBUF feature,
+  the num_buffers field is set to zero.
+
+  The header and packet are added as one output buffer to the
+  transmitq, and the device is notified of the new entry (see [sub:Notifying-The-Device]
+  ).[footnote:
+Note that the header will be two bytes longer for the
+VIRTIO_NET_F_MRG_RXBUF case.
+]
+
+  Packet Transmission Interrupt
+
+Often a driver will suppress transmission interrupts using the
+VRING_AVAIL_F_NO_INTERRUPT flag (see [sub:Receiving-Used-Buffers]
+) and check for used packets in the transmit path of following
+packets. However, it will still receive interrupts if the
+VIRTIO_F_NOTIFY_ON_EMPTY feature is negotiated, indicating that
+the transmission queue is completely emptied.
+
+The normal behavior in this interrupt handler is to retrieve and
+new descriptors from the used ring and free the corresponding
+headers and packets.
+
+  Setting Up Receive Buffers
+
+It is generally a good idea to keep the receive virtqueue as
+fully populated as possible: if it runs out, network performance
+will suffer.
+
+If the VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6 or
+VIRTIO_NET_F_GUEST_UFO features are used, the Guest will need to
+accept packets of up to 65550 bytes long (the maximum size of a
+TCP or UDP packet, plus the 14 byte ethernet header), otherwise
+1514 bytes. So unless VIRTIO_NET_F_MRG_RXBUF is negotiated, every
+buffer in the receive queue needs to be at least this length [footnote:
+Obviously each one can be split across multiple descriptor
+elements.
+].
+
+If VIRTIO_NET_F_MRG_RXBUF is negotiated, each buffer must be at
+least the size of the struct virtio_net_hdr.
+
+  Packet Receive Interrupt
+
+When a packet is copied into a buffer in the receiveq, the
+optimal path is to disable further interrupts for the receiveq
+(see [sub:Receiving-Used-Buffers]) and process packets until no
+more are found, then re-enable them.
+
+Processing packet involves:
+
+  If the driver negotiated the VIRTIO_NET_F_MRG_RXBUF feature,
+  then the “num_buffers” field indicates how many descriptors
+  this packet is spread over (including this one). This allows
+  receipt of large packets without having to allocate large
+  buffers. In this case, there will be at least “num_buffers” in
+  the used ring, and they should be chained together to form a
+  single packet. The other buffers will not begin with a struct
+  virtio_net_hdr.
+
+  If the VIRTIO_NET_F_MRG_RXBUF feature was not negotiated, or
+  the “num_buffers” field is one, then the entire packet will be
+  contained within this buffer, immediately following the struct
+  virtio_net_hdr.
+
+  If the VIRTIO_NET_F_GUEST_CSUM feature was negotiated, the
+  VIRTIO_NET_HDR_F_NEEDS_CSUM bit in the “flags” field may be
+  set: if so, the checksum on the packet is incomplete and the “
+  csum_start” and “csum_offset” fields indicate how to calculate
+  it (see [ite:csum_start-is-set]).
+
+  If the VIRTIO_NET_F_GUEST_TSO4, TSO6 or UFO options were
+  negotiated, then the “gso_type” may be something other than
+  VIRTIO_NET_HDR_GSO_NONE, and the “gso_size” field indicates the
+  desired MSS (see [enu:If-the-driver]).Control Virtqueue
+
+The driver uses the control virtqueue (if VIRTIO_NET_F_VTRL_VQ is
+negotiated) to send commands to manipulate various features of
+the device which would not easily map into the configuration
+space.
+
+All commands are of the following form:
+
+struct virtio_net_ctrl {
+
+	u8 class;
+
+	u8 command;
+
+	u8 command-specific-data[];
+
+	u8 ack;
+
+};
+
+
+
+/* ack values */
+
+#define VIRTIO_NET_OK     0
+
+#define VIRTIO_NET_ERR    1
+
+The class, command and command-specific-data are set by the
+driver, and the device sets the ack byte. There is little it can
+do except issue a diagnostic if the ack byte is not
+VIRTIO_NET_OK.
+
+  Packet Receive Filtering
+
+If the VIRTIO_NET_F_CTRL_RX feature is negotiated, the driver can
+send control commands for promiscuous mode, multicast receiving,
+and filtering of MAC addresses.
+
+Note that in general, these commands are best-effort: unwanted
+packets may still arrive.
+
+  Setting Promiscuous Mode
+
+#define VIRTIO_NET_CTRL_RX    0
+
+ #define VIRTIO_NET_CTRL_RX_PROMISC      0
+
+ #define VIRTIO_NET_CTRL_RX_ALLMULTI     1
+
+The class VIRTIO_NET_CTRL_RX has two commands:
+VIRTIO_NET_CTRL_RX_PROMISC turns promiscuous mode on and off, and
+VIRTIO_NET_CTRL_RX_ALLMULTI turns all-multicast receive on and
+off. The command-specific-data is one byte containing 0 (off) or
+1 (on).
+
+  Setting MAC Address Filtering
+
+struct virtio_net_ctrl_mac {
+
+	u32 entries;
+
+	u8 macs[entries][ETH_ALEN];
+
+};
+
+
+
+#define VIRTIO_NET_CTRL_MAC    1
+
+ #define VIRTIO_NET_CTRL_MAC_TABLE_SET        0
+
+The device can filter incoming packets by any number of
+destination MAC addresses.[footnote:
+Since there are no guarentees, it can use a hash filter
+orsilently switch to allmulti or promiscuous mode if it is given
+too many addresses.
+] This table is set using the class VIRTIO_NET_CTRL_MAC and the
+command VIRTIO_NET_CTRL_MAC_TABLE_SET. The command-specific-data
+is two variable length tables of 6-byte MAC addresses. The first
+table contains unicast addresses, and the second contains
+multicast addresses.
+
+  VLAN Filtering
+
+If the driver negotiates the VIRTION_NET_F_CTRL_VLAN feature, it
+can control a VLAN filter table in the device.
+
+#define VIRTIO_NET_CTRL_VLAN       2
+
+ #define VIRTIO_NET_CTRL_VLAN_ADD             0
+
+ #define VIRTIO_NET_CTRL_VLAN_DEL             1
+
+Both the VIRTIO_NET_CTRL_VLAN_ADD and VIRTIO_NET_CTRL_VLAN_DEL
+command take a 16-bit VLAN id as the command-specific-data.
+
+Appendix D: Block Device
+
+The virtio block device is a simple virtual block device (ie.
+disk). Read and write requests (and other exotic requests) are
+placed in the queue, and serviced (probably out of order) by the
+device except where noted.
+
+  Configuration
+
+  Subsystem Device ID 2
+
+  Virtqueues 0:requestq.
+
+  Feature bits
+
+  VIRTIO_BLK_F_BARRIER (0) Host supports request barriers.
+
+  VIRTIO_BLK_F_SIZE_MAX (1) Maximum size of any single segment is
+    in “size_max”.
+
+  VIRTIO_BLK_F_SEG_MAX (2) Maximum number of segments in a
+    request is in “seg_max”.
+
+  VIRTIO_BLK_F_GEOMETRY (4) Disk-style geometry specified in “
+    geometry”.
+
+  VIRTIO_BLK_F_RO (5) Device is read-only.
+
+  VIRTIO_BLK_F_BLK_SIZE (6) Block size of disk is in “blk_size”.
+
+  VIRTIO_BLK_F_SCSI (7) Device supports scsi packet commands.
+
+  VIRTIO_BLK_F_FLUSH (9) Cache flush command support.
+
+
+
+  Device configuration layout The capacity of the device
+  (expressed in 512-byte sectors) is always present. The
+  availability of the others all depend on various feature bits
+  as indicated above. struct virtio_blk_config {
+
+	u64 capacity;
+
+	u32 size_max;
+
+	u32 seg_max;
+
+	struct virtio_blk_geometry {
+
+		u16 cylinders;
+
+		u8 heads;
+
+		u8 sectors;
+
+	} geometry;
+
+	u32 blk_size;
+
+
+
+};
+
+  Device Initialization
+
+  The device size should be read from the “capacity”
+  configuration field. No requests should be submitted which goes
+  beyond this limit.
+
+  If the VIRTIO_BLK_F_BLK_SIZE feature is negotiated, the
+  blk_size field can be read to determine the optimal sector size
+  for the driver to use. This does not effect the units used in
+  the protocol (always 512 bytes), but awareness of the correct
+  value can effect performance.
+
+  If the VIRTIO_BLK_F_RO feature is set by the device, any write
+  requests will fail.
+
+
+
+  Device Operation
+
+The driver queues requests to the virtqueue, and they are used by
+the device (not necessarily in order). Each request is of form:
+
+struct virtio_blk_req {
+
+
+
+	u32 type;
+
+	u32 ioprio;
+
+	u64 sector;
+
+	char data[][512];
+
+	u8 status;
+
+};
+
+If the device has VIRTIO_BLK_F_SCSI feature, it can also support
+scsi packet command requests, each of these requests is of form:struct virtio_scsi_pc_req {
+
+	u32 type;
+
+	u32 ioprio;
+
+	u64 sector;
+
+    char cmd[];
+
+	char data[][512];
+
+#define SCSI_SENSE_BUFFERSIZE   96
+
+    u8 sense[SCSI_SENSE_BUFFERSIZE];
+
+    u32 errors;
+
+    u32 data_len;
+
+    u32 sense_len;
+
+    u32 residual;
+
+	u8 status;
+
+};
+
+The type of the request is either a read (VIRTIO_BLK_T_IN), a
+write (VIRTIO_BLK_T_OUT), a scsi packet command
+(VIRTIO_BLK_T_SCSI_CMD or VIRTIO_BLK_T_SCSI_CMD_OUT[footnote:
+the SCSI_CMD and SCSI_CMD_OUT types are equivalent, the device
+does not distinguish between them
+]) or a flush (VIRTIO_BLK_T_FLUSH or VIRTIO_BLK_T_FLUSH_OUT[footnote:
+the FLUSH and FLUSH_OUT types are equivalent, the device does not
+distinguish between them
+]). If the device has VIRTIO_BLK_F_BARRIER feature the high bit
+(VIRTIO_BLK_T_BARRIER) indicates that this request acts as a
+barrier and that all preceeding requests must be complete before
+this one, and all following requests must not be started until
+this is complete. Note that a barrier does not flush caches in
+the underlying backend device in host, and thus does not serve as
+data consistency guarantee. Driver must use FLUSH request to
+flush the host cache.
+
+#define VIRTIO_BLK_T_IN           0
+
+#define VIRTIO_BLK_T_OUT          1
+
+#define VIRTIO_BLK_T_SCSI_CMD     2
+
+#define VIRTIO_BLK_T_SCSI_CMD_OUT 3
+
+#define VIRTIO_BLK_T_FLUSH        4
+
+#define VIRTIO_BLK_T_FLUSH_OUT    5
+
+#define VIRTIO_BLK_T_BARRIER	 0x80000000
+
+The ioprio field is a hint about the relative priorities of
+requests to the device: higher numbers indicate more important
+requests.
+
+The sector number indicates the offset (multiplied by 512) where
+the read or write is to occur. This field is unused and set to 0
+for scsi packet commands and for flush commands.
+
+The cmd field is only present for scsi packet command requests,
+and indicates the command to perform. This field must reside in a
+single, separate read-only buffer; command length can be derived
+from the length of this buffer.
+
+Note that these first three (four for scsi packet commands)
+fields are always read-only: the data field is either read-only
+or write-only, depending on the request. The size of the read or
+write can be derived from the total size of the request buffers.
+
+The sense field is only present for scsi packet command requests,
+and indicates the buffer for scsi sense data.
+
+The data_len field is only present for scsi packet command
+requests, this field is deprecated, and should be ignored by the
+driver. Historically, devices copied data length there.
+
+The sense_len field is only present for scsi packet command
+requests and indicates the number of bytes actually written to
+the sense buffer.
+
+The residual field is only present for scsi packet command
+requests and indicates the residual size, calculated as data
+length - number of bytes actually transferred.
+
+The final status byte is written by the device: either
+VIRTIO_BLK_S_OK for success, VIRTIO_BLK_S_IOERR for host or guest
+error or VIRTIO_BLK_S_UNSUPP for a request unsupported by host:#define VIRTIO_BLK_S_OK        0
+
+#define VIRTIO_BLK_S_IOERR     1
+
+#define VIRTIO_BLK_S_UNSUPP    2
+
+Historically, devices assumed that the fields type, ioprio and
+sector reside in a single, separate read-only buffer; the fields
+errors, data_len, sense_len and residual reside in a single,
+separate write-only buffer; the sense field in a separate
+write-only buffer of size 96 bytes, by itself; the fields errors,
+data_len, sense_len and residual in a single write-only buffer;
+and the status field is a separate read-only buffer of size 1
+byte, by itself.
+
+Appendix E: Console Device
+
+The virtio console device is a simple device for data input and
+output. A device may have one or more ports. Each port has a pair
+of input and output virtqueues. Moreover, a device has a pair of
+control IO virtqueues. The control virtqueues are used to
+communicate information between the device and the driver about
+ports being opened and closed on either side of the connection,
+indication from the host about whether a particular port is a
+console port, adding new ports, port hot-plug/unplug, etc., and
+indication from the guest about whether a port or a device was
+successfully added, port open/close, etc.. For data IO, one or
+more empty buffers are placed in the receive queue for incoming
+data and outgoing characters are placed in the transmit queue.
+
+  Configuration
+
+  Subsystem Device ID 3
+
+  Virtqueues 0:receiveq(port0). 1:transmitq(port0), 2:control
+  receiveq[footnote:
+Ports 2 onwards only if VIRTIO_CONSOLE_F_MULTIPORT is set
+], 3:control transmitq, 4:receiveq(port1), 5:transmitq(port1),
+  ...
+
+  Feature bits
+
+  VIRTIO_CONSOLE_F_SIZE (0) Configuration cols and rows fields
+    are valid.
+
+  VIRTIO_CONSOLE_F_MULTIPORT(1) Device has support for multiple
+    ports; configuration fields nr_ports and max_nr_ports are
+    valid and control virtqueues will be used.
+
+  Device configuration layout The size of the console is supplied
+  in the configuration space if the VIRTIO_CONSOLE_F_SIZE feature
+  is set. Furthermore, if the VIRTIO_CONSOLE_F_MULTIPORT feature
+  is set, the maximum number of ports supported by the device can
+  be fetched.struct virtio_console_config {
+
+	u16 cols;
+
+	u16 rows;
+
+
+
+	u32 max_nr_ports;
+
+};
+
+  Device Initialization
+
+  If the VIRTIO_CONSOLE_F_SIZE feature is negotiated, the driver
+  can read the console dimensions from the configuration fields.
+
+  If the VIRTIO_CONSOLE_F_MULTIPORT feature is negotiated, the
+  driver can spawn multiple ports, not all of which may be
+  attached to a console. Some could be generic ports. In this
+  case, the control virtqueues are enabled and according to the
+  max_nr_ports configuration-space value, the appropriate number
+  of virtqueues are created. A control message indicating the
+  driver is ready is sent to the host. The host can then send
+  control messages for adding new ports to the device. After
+  creating and initializing each port, a
+  VIRTIO_CONSOLE_PORT_READY control message is sent to the host
+  for that port so the host can let us know of any additional
+  configuration options set for that port.
+
+  The receiveq for each port is populated with one or more
+  receive buffers.
+
+  Device Operation
+
+  For output, a buffer containing the characters is placed in the
+  port's transmitq.[footnote:
+Because this is high importance and low bandwidth, the current
+Linux implementation polls for the buffer to be used, rather than
+waiting for an interrupt, simplifying the implementation
+significantly. However, for generic serial ports with the
+O_NONBLOCK flag set, the polling limitation is relaxed and the
+consumed buffers are freed upon the next write or poll call or
+when a port is closed or hot-unplugged.
+]
+
+  When a buffer is used in the receiveq (signalled by an
+  interrupt), the contents is the input to the port associated
+  with the virtqueue for which the notification was received.
+
+  If the driver negotiated the VIRTIO_CONSOLE_F_SIZE feature, a
+  configuration change interrupt may occur. The updated size can
+  be read from the configuration fields.
+
+  If the driver negotiated the VIRTIO_CONSOLE_F_MULTIPORT
+  feature, active ports are announced by the host using the
+  VIRTIO_CONSOLE_PORT_ADD control message. The same message is
+  used for port hot-plug as well.
+
+  If the host specified a port `name', a sysfs attribute is
+  created with the name filled in, so that udev rules can be
+  written that can create a symlink from the port's name to the
+  char device for port discovery by applications in the guest.
+
+  Changes to ports' state are effected by control messages.
+  Appropriate action is taken on the port indicated in the
+  control message. The layout of the structure of the control
+  buffer and the events associated are:struct virtio_console_control {
+
+	uint32_t id;    /* Port number */
+
+	uint16_t event; /* The kind of control event */
+
+	uint16_t value; /* Extra information for the event */
+
+};
+
+
+
+/* Some events for the internal messages (control packets) */
+
+
+
+#define VIRTIO_CONSOLE_DEVICE_READY     0
+
+#define VIRTIO_CONSOLE_PORT_ADD         1
+
+#define VIRTIO_CONSOLE_PORT_REMOVE      2
+
+#define VIRTIO_CONSOLE_PORT_READY       3
+
+#define VIRTIO_CONSOLE_CONSOLE_PORT     4
+
+#define VIRTIO_CONSOLE_RESIZE           5
+
+#define VIRTIO_CONSOLE_PORT_OPEN        6
+
+#define VIRTIO_CONSOLE_PORT_NAME        7
+
+Appendix F: Entropy Device
+
+The virtio entropy device supplies high-quality randomness for
+guest use.
+
+  Configuration
+
+  Subsystem Device ID 4
+
+  Virtqueues 0:requestq.
+
+  Feature bits None currently defined
+
+  Device configuration layout None currently defined.
+
+  Device Initialization
+
+  The virtqueue is initialized
+
+  Device Operation
+
+When the driver requires random bytes, it places the descriptor
+of one or more buffers in the queue. It will be completely filled
+by random data by the device.
+
+Appendix G: Memory Balloon Device
+
+The virtio memory balloon device is a primitive device for
+managing guest memory: the device asks for a certain amount of
+memory, and the guest supplies it (or withdraws it, if the device
+has more than it asks for). This allows the guest to adapt to
+changes in allowance of underlying physical memory. If the
+feature is negotiated, the device can also be used to communicate
+guest memory statistics to the host.
+
+  Configuration
+
+  Subsystem Device ID 5
+
+  Virtqueues 0:inflateq. 1:deflateq. 2:statsq.[footnote:
+Only if VIRTIO_BALLON_F_STATS_VQ set
+]
+
+  Feature bits
+
+  VIRTIO_BALLOON_F_MUST_TELL_HOST (0) Host must be told before
+    pages from the balloon are used.
+
+  VIRTIO_BALLOON_F_STATS_VQ (1) A virtqueue for reporting guest
+    memory statistics is present.
+
+  Device configuration layout Both fields of this configuration
+  are always available. Note that they are little endian, despite
+  convention that device fields are guest endian:struct virtio_balloon_config {
+
+	u32 num_pages;
+
+	u32 actual;
+
+};
+
+  Device Initialization
+
+  The inflate and deflate virtqueues are identified.
+
+  If the VIRTIO_BALLOON_F_STATS_VQ feature bit is negotiated:
+
+  Identify the stats virtqueue.
+
+  Add one empty buffer to the stats virtqueue and notify the
+    host.
+
+Device operation begins immediately.
+
+  Device Operation
+
+  Memory Ballooning The device is driven by the receipt of a
+  configuration change interrupt.
+
+  The “num_pages” configuration field is examined. If this is
+  greater than the “actual” number of pages, memory must be given
+  to the balloon. If it is less than the “actual” number of
+  pages, memory may be taken back from the balloon for general
+  use.
+
+  To supply memory to the balloon (aka. inflate):
+
+  The driver constructs an array of addresses of unused memory
+    pages. These addresses are divided by 4096[footnote:
+This is historical, and independent of the guest page size
+] and the descriptor describing the resulting 32-bit array is
+    added to the inflateq.
+
+  To remove memory from the balloon (aka. deflate):
+
+  The driver constructs an array of addresses of memory pages it
+    has previously given to the balloon, as described above. This
+    descriptor is added to the deflateq.
+
+  If the VIRTIO_BALLOON_F_MUST_TELL_HOST feature is set, the
+    guest may not use these requested pages until that descriptor
+    in the deflateq has been used by the device.
+
+  Otherwise, the guest may begin to re-use pages previously given
+    to the balloon before the device has acknowledged their
+    withdrawl. [footnote:
+In this case, deflation advice is merely a courtesy
+]
+
+  In either case, once the device has completed the inflation or
+  deflation, the “actual” field of the configuration should be
+  updated to reflect the new number of pages in the balloon.[footnote:
+As updates to configuration space are not atomic, this field
+isn't particularly reliable, but can be used to diagnose buggy
+guests.
+]
+
+  Memory Statistics
+
+The stats virtqueue is atypical because communication is driven
+by the device (not the driver). The channel becomes active at
+driver initialization time when the driver adds an empty buffer
+and notifies the device. A request for memory statistics proceeds
+as follows:
+
+  The device pushes the buffer onto the used ring and sends an
+  interrupt.
+
+  The driver pops the used buffer and discards it.
+
+  The driver collects memory statistics and writes them into a
+  new buffer.
+
+  The driver adds the buffer to the virtqueue and notifies the
+  device.
+
+  The device pops the buffer (retaining it to initiate a
+  subsequent request) and consumes the statistics.
+
+  Memory Statistics Format Each statistic consists of a 16 bit
+  tag and a 64 bit value. Both quantities are represented in the
+  native endian of the guest. All statistics are optional and the
+  driver may choose which ones to supply. To guarantee backwards
+  compatibility, unsupported statistics should be omitted.
+
+  struct virtio_balloon_stat {
+
+#define VIRTIO_BALLOON_S_SWAP_IN  0
+
+#define VIRTIO_BALLOON_S_SWAP_OUT 1
+
+#define VIRTIO_BALLOON_S_MAJFLT   2
+
+#define VIRTIO_BALLOON_S_MINFLT   3
+
+#define VIRTIO_BALLOON_S_MEMFREE  4
+
+#define VIRTIO_BALLOON_S_MEMTOT   5
+
+	u16 tag;
+
+	u64 val;
+
+} __attribute__((packed));
+
+  Tags
+
+  VIRTIO_BALLOON_S_SWAP_IN The amount of memory that has been
+  swapped in (in bytes).
+
+  VIRTIO_BALLOON_S_SWAP_OUT The amount of memory that has been
+  swapped out to disk (in bytes).
+
+  VIRTIO_BALLOON_S_MAJFLT The number of major page faults that
+  have occurred.
+
+  VIRTIO_BALLOON_S_MINFLT The number of minor page faults that
+  have occurred.
+
+  VIRTIO_BALLOON_S_MEMFREE The amount of memory not being used
+  for any purpose (in bytes).
+
+  VIRTIO_BALLOON_S_MEMTOT The total amount of memory available
+  (in bytes).
+
diff --git a/Documentation/vm/transhuge.txt b/Documentation/vm/transhuge.txt
index 0924aac..29bdf62 100644
--- a/Documentation/vm/transhuge.txt
+++ b/Documentation/vm/transhuge.txt
@@ -123,10 +123,11 @@
 khugepaged runs usually at low frequency so while one may not want to
 invoke defrag algorithms synchronously during the page faults, it
 should be worth invoking defrag at least in khugepaged. However it's
-also possible to disable defrag in khugepaged:
+also possible to disable defrag in khugepaged by writing 0 or enable
+defrag in khugepaged by writing 1:
 
-echo yes >/sys/kernel/mm/transparent_hugepage/khugepaged/defrag
-echo no >/sys/kernel/mm/transparent_hugepage/khugepaged/defrag
+echo 0 >/sys/kernel/mm/transparent_hugepage/khugepaged/defrag
+echo 1 >/sys/kernel/mm/transparent_hugepage/khugepaged/defrag
 
 You can also control how many pages khugepaged should scan at each
 pass:
diff --git a/MAINTAINERS b/MAINTAINERS
index 0b4ccdd..ae8820e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1278,7 +1278,6 @@
 ATLX ETHERNET DRIVERS
 M:	Jay Cliburn <jcliburn@gmail.com>
 M:	Chris Snook <chris.snook@gmail.com>
-M:	Jie Yang <jie.yang@atheros.com>
 L:	netdev@vger.kernel.org
 W:	http://sourceforge.net/projects/atl1
 W:	http://atl1.sourceforge.net
@@ -1574,7 +1573,6 @@
 
 BROCADE BNA 10 GIGABIT ETHERNET DRIVER
 M:	Rasesh Mody <rmody@brocade.com>
-M:	Debashis Dutt <ddutt@brocade.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/bna/
@@ -1758,7 +1756,6 @@
 
 CISCO VIC ETHERNET NIC DRIVER
 M:	Christian Benvenuti <benve@cisco.com>
-M:	Vasanthy Kolluri <vkolluri@cisco.com>
 M:	Roopa Prabhu <roprabhu@cisco.com>
 M:	David Wang <dwang2@cisco.com>
 S:	Supported
@@ -1883,7 +1880,7 @@
 F:	drivers/connector/
 
 CONTROL GROUPS (CGROUPS)
-M:	Paul Menage <menage@google.com>
+M:	Paul Menage <paul@paulmenage.org>
 M:	Li Zefan <lizf@cn.fujitsu.com>
 L:	containers@lists.linux-foundation.org
 S:	Maintained
@@ -1932,7 +1929,7 @@
 F:	tools/power/cpupower
 
 CPUSETS
-M:	Paul Menage <menage@google.com>
+M:	Paul Menage <paul@paulmenage.org>
 W:	http://www.bullopensource.org/cpuset/
 W:	http://oss.sgi.com/projects/cpusets/
 S:	Supported
@@ -2649,11 +2646,11 @@
 F:	drivers/net/wan/sdla.c
 
 FRAMEBUFFER LAYER
-M:	Paul Mundt <lethal@linux-sh.org>
+M:	Florian Tobias Schandinat <FlorianSchandinat@gmx.de>
 L:	linux-fbdev@vger.kernel.org
 W:	http://linux-fbdev.sourceforge.net/
 Q:	http://patchwork.kernel.org/project/linux-fbdev/list/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/lethal/fbdev-2.6.git
+T:	git git://github.com/schandinat/linux-2.6.git fbdev-next
 S:	Maintained
 F:	Documentation/fb/
 F:	Documentation/devicetree/bindings/fb/
@@ -3262,6 +3259,17 @@
 F:	drivers/input/input-mt.c
 K:	\b(ABS|SYN)_MT_
 
+INTEL C600 SERIES SAS CONTROLLER DRIVER
+M:	Intel SCU Linux support <intel-linux-scu@intel.com>
+M:	Dan Williams <dan.j.williams@intel.com>
+M:	Dave Jiang <dave.jiang@intel.com>
+M:	Ed Nadolski <edmund.nadolski@intel.com>
+L:	linux-scsi@vger.kernel.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/djbw/isci.git
+S:	Maintained
+F:	drivers/scsi/isci/
+F:	firmware/isci/
+
 INTEL IDLE DRIVER
 M:	Len Brown <lenb@kernel.org>
 L:	linux-pm@lists.linux-foundation.org
@@ -3905,9 +3913,9 @@
 F:	drivers/macintosh/
 
 LINUX FOR POWERPC EMBEDDED MPC5XXX
-M:	Grant Likely <grant.likely@secretlab.ca>
+M:	Anatolij Gustschin <agust@denx.de>
 L:	linuxppc-dev@lists.ozlabs.org
-T:	git git://git.secretlab.ca/git/linux-2.6.git
+T:	git git://git.denx.de/linux-2.6-agust.git
 S:	Maintained
 F:	arch/powerpc/platforms/512x/
 F:	arch/powerpc/platforms/52xx/
@@ -4404,7 +4412,8 @@
 L:	coreteam@netfilter.org
 W:	http://www.netfilter.org/
 W:	http://www.iptables.org/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kaber/nf-2.6.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf-2.6.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf-next-2.6.git
 S:	Supported
 F:	include/linux/netfilter*
 F:	include/linux/netfilter/
@@ -4450,8 +4459,8 @@
 L:	netdev@vger.kernel.org
 W:	http://www.linuxfoundation.org/en/Net
 W:	http://patchwork.ozlabs.org/project/netdev/list/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6.git
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git
 S:	Maintained
 F:	net/
 F:	include/net/
@@ -4774,7 +4783,7 @@
 
 OSD LIBRARY and FILESYSTEM
 M:	Boaz Harrosh <bharrosh@panasas.com>
-M:	Benny Halevy <bhalevy@panasas.com>
+M:	Benny Halevy <bhalevy@tonian.com>
 L:	osd-dev@open-osd.org
 W:	http://open-osd.org
 T:	git git://git.open-osd.org/open-osd.git
@@ -4971,7 +4980,7 @@
 M:	Ingo Molnar <mingo@elte.hu>
 M:	Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
 S:	Supported
-F:	kernel/perf_event*.c
+F:	kernel/events/*
 F:	include/linux/perf_event.h
 F:	arch/*/kernel/perf_event*.c
 F:	arch/*/kernel/*/perf_event*.c
@@ -7088,7 +7097,7 @@
 F:	drivers/mmc/host/vub300.c
 
 W1 DALLAS'S 1-WIRE BUS
-M:	Evgeniy Polyakov <johnpol@2ka.mipt.ru>
+M:	Evgeniy Polyakov <zbr@ioremap.net>
 S:	Maintained
 F:	Documentation/w1/
 F:	drivers/w1/
@@ -7362,7 +7371,7 @@
 M:	Linus Torvalds <torvalds@linux-foundation.org>
 L:	linux-kernel@vger.kernel.org
 Q:	http://patchwork.kernel.org/project/LKML/list/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
 S:	Buried alive in reporters
 F:	*
 F:	*/
diff --git a/Makefile b/Makefile
index b4ca4e1..733dcba 100644
--- a/Makefile
+++ b/Makefile
@@ -1,8 +1,8 @@
 VERSION = 3
 PATCHLEVEL = 1
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
-NAME = Sneaky Weasel
+EXTRAVERSION = -rc7
+NAME = "Divemaster Edition"
 
 # *DOCUMENTATION*
 # To see a list of typical targets execute "make help"
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index 60cde53..8bb9362 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -51,7 +51,7 @@
         def_bool y
 
 config GENERIC_GPIO
-	def_bool y
+	bool
 
 config ZONE_DMA
 	bool
diff --git a/arch/alpha/include/asm/sysinfo.h b/arch/alpha/include/asm/sysinfo.h
index 086aba2..e77d77c 100644
--- a/arch/alpha/include/asm/sysinfo.h
+++ b/arch/alpha/include/asm/sysinfo.h
@@ -27,13 +27,4 @@
 #define UAC_NOFIX			2
 #define UAC_SIGBUS			4
 
-
-#ifdef __KERNEL__
-
-/* This is the shift that is applied to the UAC bits as stored in the
-   per-thread flags.  See thread_info.h.  */
-#define UAC_SHIFT			6
-
-#endif
-
 #endif /* __ASM_ALPHA_SYSINFO_H */
diff --git a/arch/alpha/include/asm/thread_info.h b/arch/alpha/include/asm/thread_info.h
index 6f32f9c..ff73db0 100644
--- a/arch/alpha/include/asm/thread_info.h
+++ b/arch/alpha/include/asm/thread_info.h
@@ -74,9 +74,9 @@
 #define TIF_NEED_RESCHED	3	/* rescheduling necessary */
 #define TIF_POLLING_NRFLAG	8	/* poll_idle is polling NEED_RESCHED */
 #define TIF_DIE_IF_KERNEL	9	/* dik recursion lock */
-#define TIF_UAC_NOPRINT		10	/* see sysinfo.h */
-#define TIF_UAC_NOFIX		11
-#define TIF_UAC_SIGBUS		12
+#define TIF_UAC_NOPRINT		10	/* ! Preserve sequence of following */
+#define TIF_UAC_NOFIX		11	/* ! flags as they match            */
+#define TIF_UAC_SIGBUS		12	/* ! userspace part of 'osf_sysinfo' */
 #define TIF_MEMDIE		13	/* is terminating due to OOM killer */
 #define TIF_RESTORE_SIGMASK	14	/* restore signal mask in do_signal */
 #define TIF_FREEZE		16	/* is freezing for suspend */
@@ -97,7 +97,7 @@
 #define _TIF_ALLWORK_MASK	(_TIF_WORK_MASK		\
 				 | _TIF_SYSCALL_TRACE)
 
-#define ALPHA_UAC_SHIFT		10
+#define ALPHA_UAC_SHIFT		TIF_UAC_NOPRINT
 #define ALPHA_UAC_MASK		(1 << TIF_UAC_NOPRINT | 1 << TIF_UAC_NOFIX | \
 				 1 << TIF_UAC_SIGBUS)
 
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 326f0a2..01e8715 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -42,6 +42,7 @@
 #include <asm/uaccess.h>
 #include <asm/system.h>
 #include <asm/sysinfo.h>
+#include <asm/thread_info.h>
 #include <asm/hwrpb.h>
 #include <asm/processor.h>
 
@@ -633,9 +634,10 @@
  	case GSI_UACPROC:
 		if (nbytes < sizeof(unsigned int))
 			return -EINVAL;
- 		w = (current_thread_info()->flags >> UAC_SHIFT) & UAC_BITMASK;
- 		if (put_user(w, (unsigned int __user *)buffer))
- 			return -EFAULT;
+		w = (current_thread_info()->flags >> ALPHA_UAC_SHIFT) &
+			UAC_BITMASK;
+		if (put_user(w, (unsigned int __user *)buffer))
+			return -EFAULT;
  		return 1;
 
 	case GSI_PROC_TYPE:
@@ -756,8 +758,8 @@
  			case SSIN_UACPROC:
 			again:
 				old = current_thread_info()->flags;
-				new = old & ~(UAC_BITMASK << UAC_SHIFT);
-				new = new | (w & UAC_BITMASK) << UAC_SHIFT;
+				new = old & ~(UAC_BITMASK << ALPHA_UAC_SHIFT);
+				new = new | (w & UAC_BITMASK) << ALPHA_UAC_SHIFT;
 				if (cmpxchg(&current_thread_info()->flags,
 					    old, new) != old)
 					goto again;
diff --git a/arch/alpha/kernel/systbls.S b/arch/alpha/kernel/systbls.S
index b9c28f3..6acea1f 100644
--- a/arch/alpha/kernel/systbls.S
+++ b/arch/alpha/kernel/systbls.S
@@ -360,7 +360,7 @@
 	.quad sys_newuname
 	.quad sys_nanosleep			/* 340 */
 	.quad sys_mremap
-	.quad sys_nfsservctl
+	.quad sys_ni_syscall			/* old nfsservctl */
 	.quad sys_setresuid
 	.quad sys_getresuid
 	.quad sys_pciconfig_read		/* 345 */
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 2c71a8f..3146ed3 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -195,8 +195,7 @@
 	  The base address of exception vectors.
 
 config ARM_PATCH_PHYS_VIRT
-	bool "Patch physical to virtual translations at runtime (EXPERIMENTAL)"
-	depends on EXPERIMENTAL
+	bool "Patch physical to virtual translations at runtime"
 	depends on !XIP_KERNEL && MMU
 	depends on !ARCH_REALVIEW || !SPARSEMEM
 	help
@@ -1272,6 +1271,32 @@
 	  This workaround defines cpu_relax() as smp_mb(), preventing correctly
 	  written polling loops from denying visibility of updates to memory.
 
+config ARM_ERRATA_364296
+	bool "ARM errata: Possible cache data corruption with hit-under-miss enabled"
+	depends on CPU_V6 && !SMP
+	help
+	  This options enables the workaround for the 364296 ARM1136
+	  r0p2 erratum (possible cache data corruption with
+	  hit-under-miss enabled). It sets the undocumented bit 31 in
+	  the auxiliary control register and the FI bit in the control
+	  register, thus disabling hit-under-miss without putting the
+	  processor into full low interrupt latency mode. ARM11MPCore
+	  is not affected.
+
+config ARM_ERRATA_764369
+	bool "ARM errata: Data cache line maintenance operation by MVA may not succeed"
+	depends on CPU_V7 && SMP
+	help
+	  This option enables the workaround for erratum 764369
+	  affecting Cortex-A9 MPCore with two or more processors (all
+	  current revisions). Under certain timing circumstances, a data
+	  cache line maintenance operation by MVA targeting an Inner
+	  Shareable memory region may fail to proceed up to either the
+	  Point of Coherency or to the Point of Unification of the
+	  system. This workaround adds a DSB instruction before the
+	  relevant cache maintenance functions and sets a specific bit
+	  in the diagnostic control register of the SCU.
+
 endmenu
 
 source "arch/arm/common/Kconfig"
diff --git a/arch/arm/boot/compressed/mmcif-sh7372.c b/arch/arm/boot/compressed/mmcif-sh7372.c
index b6f61d9..672ae95 100644
--- a/arch/arm/boot/compressed/mmcif-sh7372.c
+++ b/arch/arm/boot/compressed/mmcif-sh7372.c
@@ -82,7 +82,7 @@
 
 
 	/* Disable clock to MMC hardware block */
-	__raw_writel(__raw_readl(SMSTPCR3) & (1 << 12), SMSTPCR3);
+	__raw_writel(__raw_readl(SMSTPCR3) | (1 << 12), SMSTPCR3);
 
 	mmc_update_progress(MMC_PROGRESS_DONE);
 }
diff --git a/arch/arm/boot/compressed/sdhi-sh7372.c b/arch/arm/boot/compressed/sdhi-sh7372.c
index d403a8b..d279294 100644
--- a/arch/arm/boot/compressed/sdhi-sh7372.c
+++ b/arch/arm/boot/compressed/sdhi-sh7372.c
@@ -85,7 +85,7 @@
 		goto err;
 
         /* Disable clock to SDHI1 hardware block */
-        __raw_writel(__raw_readl(SMSTPCR3) & (1 << 13), SMSTPCR3);
+        __raw_writel(__raw_readl(SMSTPCR3) | (1 << 13), SMSTPCR3);
 
 	mmc_update_progress(MMC_PROGRESS_DONE);
 
diff --git a/arch/arm/boot/dts/tegra-harmony.dts b/arch/arm/boot/dts/tegra-harmony.dts
index 4c05334..e581866 100644
--- a/arch/arm/boot/dts/tegra-harmony.dts
+++ b/arch/arm/boot/dts/tegra-harmony.dts
@@ -57,14 +57,14 @@
 	};
 
 	sdhci@c8000200 {
-		gpios = <&gpio 69 0>, /* cd, gpio PI5 */
-			<&gpio 57 0>, /* wp, gpio PH1 */
-			<&gpio 155 0>; /* power, gpio PT3 */
+		cd-gpios = <&gpio 69 0>; /* gpio PI5 */
+		wp-gpios = <&gpio 57 0>; /* gpio PH1 */
+		power-gpios = <&gpio 155 0>; /* gpio PT3 */
 	};
 
 	sdhci@c8000600 {
-		gpios = <&gpio 58 0>, /* cd, gpio PH2 */
-			<&gpio 59 0>, /* wp, gpio PH3 */
-			<&gpio 70 0>; /* power, gpio PI6 */
+		cd-gpios = <&gpio 58 0>; /* gpio PH2 */
+		wp-gpios = <&gpio 59 0>; /* gpio PH3 */
+		power-gpios = <&gpio 70 0>; /* gpio PI6 */
 	};
 };
diff --git a/arch/arm/boot/dts/tegra-seaboard.dts b/arch/arm/boot/dts/tegra-seaboard.dts
index 1940cae..64cedca 100644
--- a/arch/arm/boot/dts/tegra-seaboard.dts
+++ b/arch/arm/boot/dts/tegra-seaboard.dts
@@ -21,8 +21,8 @@
 	};
 
 	sdhci@c8000400 {
-		gpios = <&gpio 69 0>, /* cd, gpio PI5 */
-			<&gpio 57 0>, /* wp, gpio PH1 */
-			<&gpio 70 0>; /* power, gpio PI6 */
+		cd-gpios = <&gpio 69 0>; /* gpio PI5 */
+		wp-gpios = <&gpio 57 0>; /* gpio PH1 */
+		power-gpios = <&gpio 70 0>; /* gpio PI6 */
 	};
 };
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index 8c73900..253cc86 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -25,17 +25,17 @@
 
 #ifdef CONFIG_SMP
 
-#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)	\
+#define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg)	\
 	smp_mb();						\
 	__asm__ __volatile__(					\
-	"1:	ldrex	%1, [%2]\n"				\
+	"1:	ldrex	%1, [%3]\n"				\
 	"	" insn "\n"					\
-	"2:	strex	%1, %0, [%2]\n"				\
-	"	teq	%1, #0\n"				\
+	"2:	strex	%2, %0, [%3]\n"				\
+	"	teq	%2, #0\n"				\
 	"	bne	1b\n"					\
 	"	mov	%0, #0\n"				\
-	__futex_atomic_ex_table("%4")				\
-	: "=&r" (ret), "=&r" (oldval)				\
+	__futex_atomic_ex_table("%5")				\
+	: "=&r" (ret), "=&r" (oldval), "=&r" (tmp)		\
 	: "r" (uaddr), "r" (oparg), "Ir" (-EFAULT)		\
 	: "cc", "memory")
 
@@ -73,14 +73,14 @@
 #include <linux/preempt.h>
 #include <asm/domain.h>
 
-#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)	\
+#define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg)	\
 	__asm__ __volatile__(					\
-	"1:	" T(ldr) "	%1, [%2]\n"			\
+	"1:	" T(ldr) "	%1, [%3]\n"			\
 	"	" insn "\n"					\
-	"2:	" T(str) "	%0, [%2]\n"			\
+	"2:	" T(str) "	%0, [%3]\n"			\
 	"	mov	%0, #0\n"				\
-	__futex_atomic_ex_table("%4")				\
-	: "=&r" (ret), "=&r" (oldval)				\
+	__futex_atomic_ex_table("%5")				\
+	: "=&r" (ret), "=&r" (oldval), "=&r" (tmp)		\
 	: "r" (uaddr), "r" (oparg), "Ir" (-EFAULT)		\
 	: "cc", "memory")
 
@@ -117,7 +117,7 @@
 	int cmp = (encoded_op >> 24) & 15;
 	int oparg = (encoded_op << 8) >> 20;
 	int cmparg = (encoded_op << 20) >> 20;
-	int oldval = 0, ret;
+	int oldval = 0, ret, tmp;
 
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
@@ -129,19 +129,19 @@
 
 	switch (op) {
 	case FUTEX_OP_SET:
-		__futex_atomic_op("mov	%0, %3", ret, oldval, uaddr, oparg);
+		__futex_atomic_op("mov	%0, %4", ret, oldval, tmp, uaddr, oparg);
 		break;
 	case FUTEX_OP_ADD:
-		__futex_atomic_op("add	%0, %1, %3", ret, oldval, uaddr, oparg);
+		__futex_atomic_op("add	%0, %1, %4", ret, oldval, tmp, uaddr, oparg);
 		break;
 	case FUTEX_OP_OR:
-		__futex_atomic_op("orr	%0, %1, %3", ret, oldval, uaddr, oparg);
+		__futex_atomic_op("orr	%0, %1, %4", ret, oldval, tmp, uaddr, oparg);
 		break;
 	case FUTEX_OP_ANDN:
-		__futex_atomic_op("and	%0, %1, %3", ret, oldval, uaddr, ~oparg);
+		__futex_atomic_op("and	%0, %1, %4", ret, oldval, tmp, uaddr, ~oparg);
 		break;
 	case FUTEX_OP_XOR:
-		__futex_atomic_op("eor	%0, %1, %3", ret, oldval, uaddr, oparg);
+		__futex_atomic_op("eor	%0, %1, %4", ret, oldval, tmp, uaddr, oparg);
 		break;
 	default:
 		ret = -ENOSYS;
diff --git a/arch/arm/include/asm/hardware/cache-l2x0.h b/arch/arm/include/asm/hardware/cache-l2x0.h
index 16bd480..99a6ed7 100644
--- a/arch/arm/include/asm/hardware/cache-l2x0.h
+++ b/arch/arm/include/asm/hardware/cache-l2x0.h
@@ -45,8 +45,13 @@
 #define L2X0_CLEAN_INV_LINE_PA		0x7F0
 #define L2X0_CLEAN_INV_LINE_IDX		0x7F8
 #define L2X0_CLEAN_INV_WAY		0x7FC
-#define L2X0_LOCKDOWN_WAY_D		0x900
-#define L2X0_LOCKDOWN_WAY_I		0x904
+/*
+ * The lockdown registers repeat 8 times for L310, the L210 has only one
+ * D and one I lockdown register at 0x0900 and 0x0904.
+ */
+#define L2X0_LOCKDOWN_WAY_D_BASE	0x900
+#define L2X0_LOCKDOWN_WAY_I_BASE	0x904
+#define L2X0_LOCKDOWN_STRIDE		0x08
 #define L2X0_TEST_OPERATION		0xF00
 #define L2X0_LINE_DATA			0xF10
 #define L2X0_LINE_TAG			0xF30
@@ -64,7 +69,7 @@
 #define L2X0_AUX_CTRL_MASK			0xc0000fff
 #define L2X0_AUX_CTRL_ASSOCIATIVITY_SHIFT	16
 #define L2X0_AUX_CTRL_WAY_SIZE_SHIFT		17
-#define L2X0_AUX_CTRL_WAY_SIZE_MASK		(0x3 << 17)
+#define L2X0_AUX_CTRL_WAY_SIZE_MASK		(0x7 << 17)
 #define L2X0_AUX_CTRL_SHARE_OVERRIDE_SHIFT	22
 #define L2X0_AUX_CTRL_NS_LOCKDOWN_SHIFT		26
 #define L2X0_AUX_CTRL_NS_INT_CTRL_SHIFT		27
diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h
index 67c70a3..b7e82c4 100644
--- a/arch/arm/include/asm/pmu.h
+++ b/arch/arm/include/asm/pmu.h
@@ -41,7 +41,7 @@
  * encoded error on failure.
  */
 extern struct platform_device *
-reserve_pmu(enum arm_pmu_type device);
+reserve_pmu(enum arm_pmu_type type);
 
 /**
  * release_pmu() - Relinquish control of the performance counters
@@ -62,26 +62,26 @@
  * the actual hardware initialisation.
  */
 extern int
-init_pmu(enum arm_pmu_type device);
+init_pmu(enum arm_pmu_type type);
 
 #else /* CONFIG_CPU_HAS_PMU */
 
 #include <linux/err.h>
 
 static inline struct platform_device *
-reserve_pmu(enum arm_pmu_type device)
+reserve_pmu(enum arm_pmu_type type)
 {
 	return ERR_PTR(-ENODEV);
 }
 
 static inline int
-release_pmu(struct platform_device *pdev)
+release_pmu(enum arm_pmu_type type)
 {
 	return -ENODEV;
 }
 
 static inline int
-init_pmu(enum arm_pmu_type device)
+init_pmu(enum arm_pmu_type type)
 {
 	return -ENODEV;
 }
diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h
index 2c04ed5..c60a294 100644
--- a/arch/arm/include/asm/unistd.h
+++ b/arch/arm/include/asm/unistd.h
@@ -478,8 +478,8 @@
 /*
  * Unimplemented (or alternatively implemented) syscalls
  */
-#define __IGNORE_fadvise64_64		1
-#define __IGNORE_migrate_pages		1
+#define __IGNORE_fadvise64_64
+#define __IGNORE_migrate_pages
 
 #endif /* __KERNEL__ */
 #endif /* __ASM_ARM_UNISTD_H */
diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S
index 80f7896..9943e9e 100644
--- a/arch/arm/kernel/calls.S
+++ b/arch/arm/kernel/calls.S
@@ -178,7 +178,7 @@
 		CALL(sys_ni_syscall)		/* vm86 */
 		CALL(sys_ni_syscall)		/* was sys_query_module */
 		CALL(sys_poll)
-		CALL(sys_nfsservctl)
+		CALL(sys_ni_syscall)		/* was nfsservctl */
 /* 170 */	CALL(sys_setresgid16)
 		CALL(sys_getresgid16)
 		CALL(sys_prctl)
diff --git a/arch/arm/kernel/iwmmxt.S b/arch/arm/kernel/iwmmxt.S
index 7fa3bb0..a087838 100644
--- a/arch/arm/kernel/iwmmxt.S
+++ b/arch/arm/kernel/iwmmxt.S
@@ -195,10 +195,10 @@
 
 	@ enable access to CP0 and CP1
 	XSC(mrc	p15, 0, r4, c15, c1, 0)
-	XSC(orr	r4, r4, #0xf)
+	XSC(orr	r4, r4, #0x3)
 	XSC(mcr	p15, 0, r4, c15, c1, 0)
 	PJ4(mrc p15, 0, r4, c1, c0, 2)
-	PJ4(orr	r4, r4, #0x3)
+	PJ4(orr	r4, r4, #0xf)
 	PJ4(mcr	p15, 0, r4, c1, c0, 2)
 
 	mov	r0, #0				@ nothing to load
@@ -313,7 +313,7 @@
 	teq	r2, r3				@ next task owns it?
 	movne	pc, lr				@ no: leave Concan disabled
 
-1:	@ flip Conan access
+1:	@ flip Concan access
 	XSC(eor	r1, r1, #0x3)
 	XSC(mcr	p15, 0, r1, c15, c1, 0)
 	PJ4(eor r1, r1, #0xf)
diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index 05b3776..cc2020c 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -323,7 +323,11 @@
 #endif
 	s = find_mod_section(hdr, sechdrs, ".alt.smp.init");
 	if (s && !is_smp())
+#ifdef CONFIG_SMP_ON_UP
 		fixup_smp((void *)s->sh_addr, s->sh_size);
+#else
+		return -EINVAL;
+#endif
 	return 0;
 }
 
diff --git a/arch/arm/kernel/pmu.c b/arch/arm/kernel/pmu.c
index 2b70709..c53474f 100644
--- a/arch/arm/kernel/pmu.c
+++ b/arch/arm/kernel/pmu.c
@@ -31,7 +31,7 @@
 {
 	if (type < 0 || type >= ARM_NUM_PMU_DEVICES) {
 		pr_warning("received registration request for unknown "
-				"device %d\n", type);
+				"PMU device type %d\n", type);
 		return -EINVAL;
 	}
 
@@ -112,17 +112,17 @@
 device_initcall(register_pmu_driver);
 
 struct platform_device *
-reserve_pmu(enum arm_pmu_type device)
+reserve_pmu(enum arm_pmu_type type)
 {
 	struct platform_device *pdev;
 
-	if (test_and_set_bit_lock(device, &pmu_lock)) {
+	if (test_and_set_bit_lock(type, &pmu_lock)) {
 		pdev = ERR_PTR(-EBUSY);
-	} else if (pmu_devices[device] == NULL) {
-		clear_bit_unlock(device, &pmu_lock);
+	} else if (pmu_devices[type] == NULL) {
+		clear_bit_unlock(type, &pmu_lock);
 		pdev = ERR_PTR(-ENODEV);
 	} else {
-		pdev = pmu_devices[device];
+		pdev = pmu_devices[type];
 	}
 
 	return pdev;
@@ -130,11 +130,11 @@
 EXPORT_SYMBOL_GPL(reserve_pmu);
 
 int
-release_pmu(enum arm_pmu_type device)
+release_pmu(enum arm_pmu_type type)
 {
-	if (WARN_ON(!pmu_devices[device]))
+	if (WARN_ON(!pmu_devices[type]))
 		return -EINVAL;
-	clear_bit_unlock(device, &pmu_lock);
+	clear_bit_unlock(type, &pmu_lock);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(release_pmu);
@@ -182,17 +182,17 @@
 }
 
 int
-init_pmu(enum arm_pmu_type device)
+init_pmu(enum arm_pmu_type type)
 {
 	int err = 0;
 
-	switch (device) {
+	switch (type) {
 	case ARM_PMU_DEVICE_CPU:
 		err = init_cpu_pmu();
 		break;
 	default:
-		pr_warning("attempt to initialise unknown device %d\n",
-				device);
+		pr_warning("attempt to initialise PMU of unknown "
+			   "type %d\n", type);
 		err = -EINVAL;
 	}
 
diff --git a/arch/arm/kernel/relocate_kernel.S b/arch/arm/kernel/relocate_kernel.S
index 9cf4cbf..d0cdedf 100644
--- a/arch/arm/kernel/relocate_kernel.S
+++ b/arch/arm/kernel/relocate_kernel.S
@@ -57,7 +57,8 @@
 	mov r0,#0
 	ldr r1,kexec_mach_type
 	ldr r2,kexec_boot_atags
-	mov pc,lr
+ ARM(	mov pc, lr	)
+ THUMB(	bx lr		)
 
 	.align
 
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 70bca64..e514c76 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -280,18 +280,19 @@
 	if (arch >= CPU_ARCH_ARMv6) {
 		if ((cachetype & (7 << 29)) == 4 << 29) {
 			/* ARMv7 register format */
+			arch = CPU_ARCH_ARMv7;
 			cacheid = CACHEID_VIPT_NONALIASING;
 			if ((cachetype & (3 << 14)) == 1 << 14)
 				cacheid |= CACHEID_ASID_TAGGED;
-			else if (cpu_has_aliasing_icache(CPU_ARCH_ARMv7))
-				cacheid |= CACHEID_VIPT_I_ALIASING;
-		} else if (cachetype & (1 << 23)) {
-			cacheid = CACHEID_VIPT_ALIASING;
 		} else {
-			cacheid = CACHEID_VIPT_NONALIASING;
-			if (cpu_has_aliasing_icache(CPU_ARCH_ARMv6))
-				cacheid |= CACHEID_VIPT_I_ALIASING;
+			arch = CPU_ARCH_ARMv6;
+			if (cachetype & (1 << 23))
+				cacheid = CACHEID_VIPT_ALIASING;
+			else
+				cacheid = CACHEID_VIPT_NONALIASING;
 		}
+		if (cpu_has_aliasing_icache(arch))
+			cacheid |= CACHEID_VIPT_I_ALIASING;
 	} else {
 		cacheid = CACHEID_VIVT;
 	}
diff --git a/arch/arm/kernel/smp_scu.c b/arch/arm/kernel/smp_scu.c
index 79ed5e7..7fcddb7 100644
--- a/arch/arm/kernel/smp_scu.c
+++ b/arch/arm/kernel/smp_scu.c
@@ -13,6 +13,7 @@
 
 #include <asm/smp_scu.h>
 #include <asm/cacheflush.h>
+#include <asm/cputype.h>
 
 #define SCU_CTRL		0x00
 #define SCU_CONFIG		0x04
@@ -37,6 +38,15 @@
 {
 	u32 scu_ctrl;
 
+#ifdef CONFIG_ARM_ERRATA_764369
+	/* Cortex-A9 only */
+	if ((read_cpuid(CPUID_ID) & 0xff0ffff0) == 0x410fc090) {
+		scu_ctrl = __raw_readl(scu_base + 0x30);
+		if (!(scu_ctrl & 1))
+			__raw_writel(scu_ctrl | 0x1, scu_base + 0x30);
+	}
+#endif
+
 	scu_ctrl = __raw_readl(scu_base + SCU_CTRL);
 	/* already enabled? */
 	if (scu_ctrl & 1)
diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
index 2c277d4..01c1862 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -137,8 +137,8 @@
 	clk->max_delta_ns = clockevent_delta2ns(0xffffffff, clk);
 	clk->min_delta_ns = clockevent_delta2ns(0xf, clk);
 
+	clockevents_register_device(clk);
+
 	/* Make sure our local interrupt controller has this enabled */
 	gic_enable_ppi(clk->irq);
-
-	clockevents_register_device(clk);
 }
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index bf977f8..4e66f62 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -23,8 +23,10 @@
 
 #if defined(CONFIG_SMP_ON_UP) && !defined(CONFIG_DEBUG_SPINLOCK)
 #define ARM_EXIT_KEEP(x)	x
+#define ARM_EXIT_DISCARD(x)
 #else
 #define ARM_EXIT_KEEP(x)
+#define ARM_EXIT_DISCARD(x)	x
 #endif
 
 OUTPUT_ARCH(arm)
@@ -39,6 +41,11 @@
 SECTIONS
 {
 	/*
+	 * XXX: The linker does not define how output sections are
+	 * assigned to input sections when there are multiple statements
+	 * matching the same input section name.  There is no documented
+	 * order of matching.
+	 *
 	 * unwind exit sections must be discarded before the rest of the
 	 * unwind sections get included.
 	 */
@@ -47,6 +54,9 @@
 		*(.ARM.extab.exit.text)
 		ARM_CPU_DISCARD(*(.ARM.exidx.cpuexit.text))
 		ARM_CPU_DISCARD(*(.ARM.extab.cpuexit.text))
+		ARM_EXIT_DISCARD(EXIT_TEXT)
+		ARM_EXIT_DISCARD(EXIT_DATA)
+		EXIT_CALL
 #ifndef CONFIG_HOTPLUG
 		*(.ARM.exidx.devexit.text)
 		*(.ARM.extab.devexit.text)
@@ -58,6 +68,8 @@
 #ifndef CONFIG_SMP_ON_UP
 		*(.alt.smp.init)
 #endif
+		*(.discard)
+		*(.discard.*)
 	}
 
 #ifdef CONFIG_XIP_KERNEL
@@ -279,9 +291,6 @@
 
 	STABS_DEBUG
 	.comment 0 : { *(.comment) }
-
-	/* Default discards */
-	DISCARDS
 }
 
 /*
diff --git a/arch/arm/mach-at91/at91sam9261.c b/arch/arm/mach-at91/at91sam9261.c
index d522b47..6c8e3b5 100644
--- a/arch/arm/mach-at91/at91sam9261.c
+++ b/arch/arm/mach-at91/at91sam9261.c
@@ -157,7 +157,7 @@
 	CLKDEV_CON_DEV_ID("spi_clk", "atmel_spi.1", &spi1_clk),
 	CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.0", &tc0_clk),
 	CLKDEV_CON_DEV_ID("t1_clk", "atmel_tcb.0", &tc1_clk),
-	CLKDEV_CON_DEV_ID("t2_clk", "atmel_tcb.0", &tc1_clk),
+	CLKDEV_CON_DEV_ID("t2_clk", "atmel_tcb.0", &tc2_clk),
 	CLKDEV_CON_DEV_ID("pclk", "ssc.0", &ssc0_clk),
 	CLKDEV_CON_DEV_ID("pclk", "ssc.1", &ssc1_clk),
 	CLKDEV_CON_DEV_ID("pclk", "ssc.2", &ssc2_clk),
diff --git a/arch/arm/mach-cns3xxx/include/mach/entry-macro.S b/arch/arm/mach-cns3xxx/include/mach/entry-macro.S
index 6bd83ed..d87bfc3 100644
--- a/arch/arm/mach-cns3xxx/include/mach/entry-macro.S
+++ b/arch/arm/mach-cns3xxx/include/mach/entry-macro.S
@@ -8,7 +8,6 @@
  * published by the Free Software Foundation.
  */
 
-#include <mach/hardware.h>
 #include <asm/hardware/entry-macro-gic.S>
 
 		.macro	disable_fiq
diff --git a/arch/arm/mach-cns3xxx/include/mach/system.h b/arch/arm/mach-cns3xxx/include/mach/system.h
index 58bb03a..4f16c9b 100644
--- a/arch/arm/mach-cns3xxx/include/mach/system.h
+++ b/arch/arm/mach-cns3xxx/include/mach/system.h
@@ -13,7 +13,6 @@
 
 #include <linux/io.h>
 #include <asm/proc-fns.h>
-#include <mach/hardware.h>
 
 static inline void arch_idle(void)
 {
diff --git a/arch/arm/mach-cns3xxx/include/mach/uncompress.h b/arch/arm/mach-cns3xxx/include/mach/uncompress.h
index de8ead9..a91b605 100644
--- a/arch/arm/mach-cns3xxx/include/mach/uncompress.h
+++ b/arch/arm/mach-cns3xxx/include/mach/uncompress.h
@@ -8,7 +8,6 @@
  */
 
 #include <asm/mach-types.h>
-#include <mach/hardware.h>
 #include <mach/cns3xxx.h>
 
 #define AMBA_UART_DR(base)	(*(volatile unsigned char *)((base) + 0x00))
diff --git a/arch/arm/mach-cns3xxx/pcie.c b/arch/arm/mach-cns3xxx/pcie.c
index 06fd25d..0f8fca4 100644
--- a/arch/arm/mach-cns3xxx/pcie.c
+++ b/arch/arm/mach-cns3xxx/pcie.c
@@ -49,7 +49,7 @@
 	return &cns3xxx_pcie[root->domain];
 }
 
-static struct cns3xxx_pcie *pdev_to_cnspci(struct pci_dev *dev)
+static struct cns3xxx_pcie *pdev_to_cnspci(const struct pci_dev *dev)
 {
 	return sysdata_to_cnspci(dev->sysdata);
 }
diff --git a/arch/arm/mach-davinci/board-da850-evm.c b/arch/arm/mach-davinci/board-da850-evm.c
index bd53945..008d514 100644
--- a/arch/arm/mach-davinci/board-da850-evm.c
+++ b/arch/arm/mach-davinci/board-da850-evm.c
@@ -115,6 +115,32 @@
 	},
 };
 
+#ifdef CONFIG_MTD
+static void da850_evm_m25p80_notify_add(struct mtd_info *mtd)
+{
+	char *mac_addr = davinci_soc_info.emac_pdata->mac_addr;
+	size_t retlen;
+
+	if (!strcmp(mtd->name, "MAC-Address")) {
+		mtd->read(mtd, 0, ETH_ALEN, &retlen, mac_addr);
+		if (retlen == ETH_ALEN)
+			pr_info("Read MAC addr from SPI Flash: %pM\n",
+				mac_addr);
+	}
+}
+
+static struct mtd_notifier da850evm_spi_notifier = {
+	.add	= da850_evm_m25p80_notify_add,
+};
+
+static void da850_evm_setup_mac_addr(void)
+{
+	register_mtd_user(&da850evm_spi_notifier);
+}
+#else
+static void da850_evm_setup_mac_addr(void) { }
+#endif
+
 static struct mtd_partition da850_evm_norflash_partition[] = {
 	{
 		.name           = "bootloaders + env",
@@ -1244,6 +1270,8 @@
 	if (ret)
 		pr_warning("da850_evm_init: sata registration failed: %d\n",
 				ret);
+
+	da850_evm_setup_mac_addr();
 }
 
 #ifdef CONFIG_SERIAL_8250_CONSOLE
diff --git a/arch/arm/mach-davinci/include/mach/psc.h b/arch/arm/mach-davinci/include/mach/psc.h
index 47fd0bc..fa59c09 100644
--- a/arch/arm/mach-davinci/include/mach/psc.h
+++ b/arch/arm/mach-davinci/include/mach/psc.h
@@ -243,7 +243,7 @@
 #define PSC_STATE_DISABLE	2
 #define PSC_STATE_ENABLE	3
 
-#define MDSTAT_STATE_MASK	0x1f
+#define MDSTAT_STATE_MASK	0x3f
 #define MDCTL_FORCE		BIT(31)
 
 #ifndef __ASSEMBLER__
diff --git a/arch/arm/mach-davinci/sleep.S b/arch/arm/mach-davinci/sleep.S
index fb5e72b..5f1e045 100644
--- a/arch/arm/mach-davinci/sleep.S
+++ b/arch/arm/mach-davinci/sleep.S
@@ -217,7 +217,11 @@
 ENDPROC(davinci_ddr_psc_config)
 
 CACHE_FLUSH:
-	.word	arm926_flush_kern_cache_all
+#ifdef CONFIG_CPU_V6
+	.word	v6_flush_kern_cache_all
+#else
+	.word   arm926_flush_kern_cache_all
+#endif
 
 ENTRY(davinci_cpu_suspend_sz)
 	.word	. - davinci_cpu_suspend
diff --git a/arch/arm/mach-dove/common.c b/arch/arm/mach-dove/common.c
index 83dce85..a9e0dae 100644
--- a/arch/arm/mach-dove/common.c
+++ b/arch/arm/mach-dove/common.c
@@ -158,7 +158,7 @@
 
 void __init dove_spi1_init(void)
 {
-	orion_spi_init(DOVE_SPI1_PHYS_BASE, get_tclk());
+	orion_spi_1_init(DOVE_SPI1_PHYS_BASE, get_tclk());
 }
 
 /*****************************************************************************
diff --git a/arch/arm/mach-ep93xx/include/mach/ts72xx.h b/arch/arm/mach-ep93xx/include/mach/ts72xx.h
index 0eabec6..f1397a1 100644
--- a/arch/arm/mach-ep93xx/include/mach/ts72xx.h
+++ b/arch/arm/mach-ep93xx/include/mach/ts72xx.h
@@ -6,7 +6,7 @@
  * TS72xx memory map:
  *
  * virt		phys		size
- * febff000	22000000	4K	model number register
+ * febff000	22000000	4K	model number register (bits 0-2)
  * febfe000	22400000	4K	options register
  * febfd000	22800000	4K	options register #2
  * febf9000	10800000	4K	TS-5620 RTC index register
@@ -20,6 +20,9 @@
 #define TS72XX_MODEL_TS7200		0x00
 #define TS72XX_MODEL_TS7250		0x01
 #define TS72XX_MODEL_TS7260		0x02
+#define TS72XX_MODEL_TS7300		0x03
+#define TS72XX_MODEL_TS7400		0x04
+#define TS72XX_MODEL_MASK		0x07
 
 
 #define TS72XX_OPTIONS_PHYS_BASE	0x22400000
@@ -51,19 +54,34 @@
 
 #ifndef __ASSEMBLY__
 
+static inline int ts72xx_model(void)
+{
+	return __raw_readb(TS72XX_MODEL_VIRT_BASE) & TS72XX_MODEL_MASK;
+}
+
 static inline int board_is_ts7200(void)
 {
-	return __raw_readb(TS72XX_MODEL_VIRT_BASE) == TS72XX_MODEL_TS7200;
+	return ts72xx_model() == TS72XX_MODEL_TS7200;
 }
 
 static inline int board_is_ts7250(void)
 {
-	return __raw_readb(TS72XX_MODEL_VIRT_BASE) == TS72XX_MODEL_TS7250;
+	return ts72xx_model() == TS72XX_MODEL_TS7250;
 }
 
 static inline int board_is_ts7260(void)
 {
-	return __raw_readb(TS72XX_MODEL_VIRT_BASE) == TS72XX_MODEL_TS7260;
+	return ts72xx_model() == TS72XX_MODEL_TS7260;
+}
+
+static inline int board_is_ts7300(void)
+{
+	return ts72xx_model()  == TS72XX_MODEL_TS7300;
+}
+
+static inline int board_is_ts7400(void)
+{
+	return ts72xx_model() == TS72XX_MODEL_TS7400;
 }
 
 static inline int is_max197_installed(void)
diff --git a/arch/arm/mach-exynos4/clock.c b/arch/arm/mach-exynos4/clock.c
index 851dea0..86964d2 100644
--- a/arch/arm/mach-exynos4/clock.c
+++ b/arch/arm/mach-exynos4/clock.c
@@ -520,7 +520,7 @@
 		.ctrlbit	= (1 << 21),
 	}, {
 		.name		= "ac97",
-		.id		= -1,
+		.devname	= "samsung-ac97",
 		.enable		= exynos4_clk_ip_peril_ctrl,
 		.ctrlbit	= (1 << 27),
 	}, {
@@ -899,8 +899,7 @@
 		.reg_div = { .reg = S5P_CLKDIV_CAM, .shift = 28, .size = 4 },
 	}, {
 		.clk		= {
-			.name		= "sclk_cam",
-			.devname	= "exynos4-fimc.0",
+			.name		= "sclk_cam0",
 			.enable		= exynos4_clksrc_mask_cam_ctrl,
 			.ctrlbit	= (1 << 16),
 		},
@@ -909,8 +908,7 @@
 		.reg_div = { .reg = S5P_CLKDIV_CAM, .shift = 16, .size = 4 },
 	}, {
 		.clk		= {
-			.name		= "sclk_cam",
-			.devname	= "exynos4-fimc.1",
+			.name		= "sclk_cam1",
 			.enable		= exynos4_clksrc_mask_cam_ctrl,
 			.ctrlbit	= (1 << 20),
 		},
@@ -1160,7 +1158,7 @@
 
 	vpllsrc = clk_get_rate(&clk_vpllsrc.clk);
 	vpll = s5p_get_pll46xx(vpllsrc, __raw_readl(S5P_VPLL_CON0),
-				__raw_readl(S5P_VPLL_CON1), pll_4650);
+				__raw_readl(S5P_VPLL_CON1), pll_4650c);
 
 	clk_fout_apll.ops = &exynos4_fout_apll_ops;
 	clk_fout_mpll.rate = mpll;
diff --git a/arch/arm/mach-exynos4/cpu.c b/arch/arm/mach-exynos4/cpu.c
index 2d8a40c..746d6fc 100644
--- a/arch/arm/mach-exynos4/cpu.c
+++ b/arch/arm/mach-exynos4/cpu.c
@@ -24,12 +24,13 @@
 #include <plat/exynos4.h>
 #include <plat/adc-core.h>
 #include <plat/sdhci.h>
-#include <plat/devs.h>
 #include <plat/fb-core.h>
 #include <plat/fimc-core.h>
 #include <plat/iic-core.h>
+#include <plat/reset.h>
 
 #include <mach/regs-irq.h>
+#include <mach/regs-pmu.h>
 
 extern int combiner_init(unsigned int combiner_nr, void __iomem *base,
 			 unsigned int irq_start);
@@ -128,6 +129,11 @@
 	local_irq_enable();
 }
 
+static void exynos4_sw_reset(void)
+{
+	__raw_writel(0x1, S5P_SWRESET);
+}
+
 /*
  * exynos4_map_io
  *
@@ -241,5 +247,8 @@
 	/* set idle function */
 	pm_idle = exynos4_idle;
 
+	/* set sw_reset function */
+	s5p_reset_hook = exynos4_sw_reset;
+
 	return sysdev_register(&exynos4_sysdev);
 }
diff --git a/arch/arm/mach-exynos4/include/mach/irqs.h b/arch/arm/mach-exynos4/include/mach/irqs.h
index 934d2a4..f8952f8 100644
--- a/arch/arm/mach-exynos4/include/mach/irqs.h
+++ b/arch/arm/mach-exynos4/include/mach/irqs.h
@@ -80,9 +80,8 @@
 #define IRQ_HSMMC3		IRQ_SPI(76)
 #define IRQ_DWMCI		IRQ_SPI(77)
 
-#define IRQ_MIPICSI0		IRQ_SPI(78)
-
-#define IRQ_MIPICSI1		IRQ_SPI(80)
+#define IRQ_MIPI_CSIS0		IRQ_SPI(78)
+#define IRQ_MIPI_CSIS1		IRQ_SPI(80)
 
 #define IRQ_ONENAND_AUDI	IRQ_SPI(82)
 #define IRQ_ROTATOR		IRQ_SPI(83)
diff --git a/arch/arm/mach-exynos4/include/mach/regs-pmu.h b/arch/arm/mach-exynos4/include/mach/regs-pmu.h
index fa49bbb..cdf9b47 100644
--- a/arch/arm/mach-exynos4/include/mach/regs-pmu.h
+++ b/arch/arm/mach-exynos4/include/mach/regs-pmu.h
@@ -29,6 +29,8 @@
 #define S5P_USE_STANDBY_WFE1			(1 << 25)
 #define S5P_USE_MASK				((0x3 << 16) | (0x3 << 24))
 
+#define S5P_SWRESET				S5P_PMUREG(0x0400)
+
 #define S5P_WAKEUP_STAT				S5P_PMUREG(0x0600)
 #define S5P_EINT_WAKEUP_MASK			S5P_PMUREG(0x0604)
 #define S5P_WAKEUP_MASK				S5P_PMUREG(0x0608)
diff --git a/arch/arm/mach-exynos4/irq-eint.c b/arch/arm/mach-exynos4/irq-eint.c
index 9d87d2a..badb8c6 100644
--- a/arch/arm/mach-exynos4/irq-eint.c
+++ b/arch/arm/mach-exynos4/irq-eint.c
@@ -23,6 +23,8 @@
 
 #include <mach/regs-gpio.h>
 
+#include <asm/mach/irq.h>
+
 static DEFINE_SPINLOCK(eint_lock);
 
 static unsigned int eint0_15_data[16];
@@ -184,8 +186,11 @@
 
 static void exynos4_irq_demux_eint16_31(unsigned int irq, struct irq_desc *desc)
 {
+	struct irq_chip *chip = irq_get_chip(irq);
+	chained_irq_enter(chip, desc);
 	exynos4_irq_demux_eint(IRQ_EINT(16));
 	exynos4_irq_demux_eint(IRQ_EINT(24));
+	chained_irq_exit(chip, desc);
 }
 
 static void exynos4_irq_eint0_15(unsigned int irq, struct irq_desc *desc)
@@ -193,6 +198,7 @@
 	u32 *irq_data = irq_get_handler_data(irq);
 	struct irq_chip *chip = irq_get_chip(irq);
 
+	chained_irq_enter(chip, desc);
 	chip->irq_mask(&desc->irq_data);
 
 	if (chip->irq_ack)
@@ -201,6 +207,7 @@
 	generic_handle_irq(*irq_data);
 
 	chip->irq_unmask(&desc->irq_data);
+	chained_irq_exit(chip, desc);
 }
 
 int __init exynos4_init_irq_eint(void)
diff --git a/arch/arm/mach-exynos4/mach-universal_c210.c b/arch/arm/mach-exynos4/mach-universal_c210.c
index 0e280d1..b3b5d89 100644
--- a/arch/arm/mach-exynos4/mach-universal_c210.c
+++ b/arch/arm/mach-exynos4/mach-universal_c210.c
@@ -79,7 +79,7 @@
 };
 
 static struct regulator_consumer_supply max8952_consumer =
-	REGULATOR_SUPPLY("vddarm", NULL);
+	REGULATOR_SUPPLY("vdd_arm", NULL);
 
 static struct max8952_platform_data universal_max8952_pdata __initdata = {
 	.gpio_vid0	= EXYNOS4_GPX0(3),
@@ -105,7 +105,7 @@
 };
 
 static struct regulator_consumer_supply lp3974_buck1_consumer =
-	REGULATOR_SUPPLY("vddint", NULL);
+	REGULATOR_SUPPLY("vdd_int", NULL);
 
 static struct regulator_consumer_supply lp3974_buck2_consumer =
 	REGULATOR_SUPPLY("vddg3d", NULL);
diff --git a/arch/arm/mach-exynos4/mct.c b/arch/arm/mach-exynos4/mct.c
index 1ae059b..ddd8686 100644
--- a/arch/arm/mach-exynos4/mct.c
+++ b/arch/arm/mach-exynos4/mct.c
@@ -132,12 +132,18 @@
 	return ((cycle_t)hi << 32) | lo;
 }
 
+static void exynos4_frc_resume(struct clocksource *cs)
+{
+	exynos4_mct_frc_start(0, 0);
+}
+
 struct clocksource mct_frc = {
 	.name		= "mct-frc",
 	.rating		= 400,
 	.read		= exynos4_frc_read,
 	.mask		= CLOCKSOURCE_MASK(64),
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
+	.resume		= exynos4_frc_resume,
 };
 
 static void __init exynos4_clocksource_init(void)
@@ -389,9 +395,11 @@
 }
 
 /* Setup the local clock events for a CPU */
-void __cpuinit local_timer_setup(struct clock_event_device *evt)
+int __cpuinit local_timer_setup(struct clock_event_device *evt)
 {
 	exynos4_mct_tick_init(evt);
+
+	return 0;
 }
 
 int local_timer_ack(void)
diff --git a/arch/arm/mach-exynos4/platsmp.c b/arch/arm/mach-exynos4/platsmp.c
index 7c2282c..df6ef1b 100644
--- a/arch/arm/mach-exynos4/platsmp.c
+++ b/arch/arm/mach-exynos4/platsmp.c
@@ -106,6 +106,8 @@
 	 */
 	spin_lock(&boot_lock);
 	spin_unlock(&boot_lock);
+
+	set_cpu_online(cpu, true);
 }
 
 int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
diff --git a/arch/arm/mach-exynos4/setup-keypad.c b/arch/arm/mach-exynos4/setup-keypad.c
index 1ee0ebf..7862bfb 100644
--- a/arch/arm/mach-exynos4/setup-keypad.c
+++ b/arch/arm/mach-exynos4/setup-keypad.c
@@ -19,15 +19,16 @@
 
 	if (rows > 8) {
 		/* Set all the necessary GPX2 pins: KP_ROW[0~7] */
-		s3c_gpio_cfgrange_nopull(EXYNOS4_GPX2(0), 8, S3C_GPIO_SFN(3));
+		s3c_gpio_cfgall_range(EXYNOS4_GPX2(0), 8, S3C_GPIO_SFN(3),
+					S3C_GPIO_PULL_UP);
 
 		/* Set all the necessary GPX3 pins: KP_ROW[8~] */
-		s3c_gpio_cfgrange_nopull(EXYNOS4_GPX3(0), (rows - 8),
-					 S3C_GPIO_SFN(3));
+		s3c_gpio_cfgall_range(EXYNOS4_GPX3(0), (rows - 8),
+					 S3C_GPIO_SFN(3), S3C_GPIO_PULL_UP);
 	} else {
 		/* Set all the necessary GPX2 pins: KP_ROW[x] */
-		s3c_gpio_cfgrange_nopull(EXYNOS4_GPX2(0), rows,
-					 S3C_GPIO_SFN(3));
+		s3c_gpio_cfgall_range(EXYNOS4_GPX2(0), rows, S3C_GPIO_SFN(3),
+					S3C_GPIO_PULL_UP);
 	}
 
 	/* Set all the necessary GPX1 pins to special-function 3: KP_COL[x] */
diff --git a/arch/arm/mach-exynos4/setup-usb-phy.c b/arch/arm/mach-exynos4/setup-usb-phy.c
index 0883c1b..39aca04 100644
--- a/arch/arm/mach-exynos4/setup-usb-phy.c
+++ b/arch/arm/mach-exynos4/setup-usb-phy.c
@@ -82,7 +82,7 @@
 
 	rstcon &= ~(HOST_LINK_PORT_SWRST_MASK | PHY1_SWRST_MASK);
 	writel(rstcon, EXYNOS4_RSTCON);
-	udelay(50);
+	udelay(80);
 
 	clk_disable(otg_clk);
 	clk_put(otg_clk);
diff --git a/arch/arm/mach-footbridge/Kconfig b/arch/arm/mach-footbridge/Kconfig
index dc26fff..c8e7afc 100644
--- a/arch/arm/mach-footbridge/Kconfig
+++ b/arch/arm/mach-footbridge/Kconfig
@@ -62,6 +62,7 @@
 config ARCH_NETWINDER
 	bool "NetWinder"
 	select CLKSRC_I8253
+	select CLKEVT_I8253
 	select FOOTBRIDGE_HOST
 	select ISA
 	select ISA_DMA
diff --git a/arch/arm/mach-footbridge/dc21285.c b/arch/arm/mach-footbridge/dc21285.c
index 1331fff..18c32a5 100644
--- a/arch/arm/mach-footbridge/dc21285.c
+++ b/arch/arm/mach-footbridge/dc21285.c
@@ -18,6 +18,7 @@
 #include <linux/irq.h>
 #include <linux/io.h>
 #include <linux/spinlock.h>
+#include <video/vga.h>
 
 #include <asm/irq.h>
 #include <asm/system.h>
diff --git a/arch/arm/mach-imx/clock-imx25.c b/arch/arm/mach-imx/clock-imx25.c
index 0fc7ba5..e63e235 100644
--- a/arch/arm/mach-imx/clock-imx25.c
+++ b/arch/arm/mach-imx/clock-imx25.c
@@ -331,6 +331,9 @@
 	__raw_writel(__raw_readl(CRM_BASE+0x64) | (1 << 7) | (1 << 0),
 			CRM_BASE + 0x64);
 
+	/* Clock source for gpt is ahb_div */
+	__raw_writel(__raw_readl(CRM_BASE+0x64) & ~(1 << 5), CRM_BASE + 0x64);
+
 	mxc_timer_init(&gpt_clk, MX25_IO_ADDRESS(MX25_GPT1_BASE_ADDR), 54);
 
 	return 0;
diff --git a/arch/arm/mach-imx/mach-cpuimx27.c b/arch/arm/mach-imx/mach-cpuimx27.c
index 87887ac..f851fe9 100644
--- a/arch/arm/mach-imx/mach-cpuimx27.c
+++ b/arch/arm/mach-imx/mach-cpuimx27.c
@@ -310,7 +310,7 @@
 	.init = eukrea_cpuimx27_timer_init,
 };
 
-MACHINE_START(CPUIMX27, "EUKREA CPUIMX27")
+MACHINE_START(EUKREA_CPUIMX27, "EUKREA CPUIMX27")
 	.boot_params = MX27_PHYS_OFFSET + 0x100,
 	.map_io = mx27_map_io,
 	.init_early = imx27_init_early,
diff --git a/arch/arm/mach-imx/mach-cpuimx35.c b/arch/arm/mach-imx/mach-cpuimx35.c
index f39a478b..4bd083b 100644
--- a/arch/arm/mach-imx/mach-cpuimx35.c
+++ b/arch/arm/mach-imx/mach-cpuimx35.c
@@ -192,7 +192,7 @@
 	.init	= eukrea_cpuimx35_timer_init,
 };
 
-MACHINE_START(EUKREA_CPUIMX35, "Eukrea CPUIMX35")
+MACHINE_START(EUKREA_CPUIMX35SD, "Eukrea CPUIMX35")
 	/* Maintainer: Eukrea Electromatique */
 	.boot_params = MX3x_PHYS_OFFSET + 0x100,
 	.map_io = mx35_map_io,
diff --git a/arch/arm/mach-imx/mach-eukrea_cpuimx25.c b/arch/arm/mach-imx/mach-eukrea_cpuimx25.c
index da36da5..2442d5d 100644
--- a/arch/arm/mach-imx/mach-eukrea_cpuimx25.c
+++ b/arch/arm/mach-imx/mach-eukrea_cpuimx25.c
@@ -161,7 +161,7 @@
 	.init   = eukrea_cpuimx25_timer_init,
 };
 
-MACHINE_START(EUKREA_CPUIMX25, "Eukrea CPUIMX25")
+MACHINE_START(EUKREA_CPUIMX25SD, "Eukrea CPUIMX25")
 	/* Maintainer: Eukrea Electromatique */
 	.boot_params = MX25_PHYS_OFFSET + 0x100,
 	.map_io = mx25_map_io,
diff --git a/arch/arm/mach-imx/mach-imx27_visstrim_m10.c b/arch/arm/mach-imx/mach-imx27_visstrim_m10.c
index 6707de0a..6778f81 100644
--- a/arch/arm/mach-imx/mach-imx27_visstrim_m10.c
+++ b/arch/arm/mach-imx/mach-imx27_visstrim_m10.c
@@ -30,6 +30,7 @@
 #include <linux/input.h>
 #include <linux/gpio.h>
 #include <linux/delay.h>
+#include <sound/tlv320aic32x4.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/time.h>
@@ -196,6 +197,17 @@
 	.invert = 0,
 };
 
+static struct aic32x4_pdata visstrim_m10_aic32x4_pdata = {
+	.power_cfg = AIC32X4_PWR_MICBIAS_2075_LDOIN |
+		     AIC32X4_PWR_AVDD_DVDD_WEAK_DISABLE |
+		     AIC32X4_PWR_AIC32X4_LDO_ENABLE |
+		     AIC32X4_PWR_CMMODE_LDOIN_RANGE_18_36 |
+		     AIC32X4_PWR_CMMODE_HP_LDOIN_POWERED,
+	.micpga_routing = AIC32X4_MICPGA_ROUTE_LMIC_IN2R_10K |
+			 AIC32X4_MICPGA_ROUTE_RMIC_IN1L_10K,
+	.swapdacs = false,
+};
+
 static struct i2c_board_info visstrim_m10_i2c_devices[] = {
 	{
 		I2C_BOARD_INFO("pca9555", 0x20),
@@ -203,6 +215,7 @@
 	},
 	{
 		I2C_BOARD_INFO("tlv320aic32x4", 0x18),
+		.platform_data = &visstrim_m10_aic32x4_pdata,
 	}
 };
 
diff --git a/arch/arm/mach-imx/mach-mx31ads.c b/arch/arm/mach-imx/mach-mx31ads.c
index 0ce4947..29ca890 100644
--- a/arch/arm/mach-imx/mach-mx31ads.c
+++ b/arch/arm/mach-imx/mach-mx31ads.c
@@ -468,7 +468,7 @@
 #endif
 };
 
-static void mxc_init_i2c(void)
+static void __init mxc_init_i2c(void)
 {
 	i2c_register_board_info(1, mx31ads_i2c1_devices,
 				ARRAY_SIZE(mx31ads_i2c1_devices));
@@ -486,7 +486,7 @@
 	MX31_PIN_STXD5__STXD5,
 };
 
-static void mxc_init_audio(void)
+static void __init mxc_init_audio(void)
 {
 	imx31_add_imx_ssi(0, NULL);
 	mxc_iomux_setup_multiple_pins(ssi_pins, ARRAY_SIZE(ssi_pins), "ssi");
diff --git a/arch/arm/mach-imx/mach-mx31lilly.c b/arch/arm/mach-imx/mach-mx31lilly.c
index 750368d..126913a 100644
--- a/arch/arm/mach-imx/mach-mx31lilly.c
+++ b/arch/arm/mach-imx/mach-mx31lilly.c
@@ -192,7 +192,7 @@
 	.portsc	= MXC_EHCI_MODE_ULPI | MXC_EHCI_UTMI_8BIT,
 };
 
-static void lilly1131_usb_init(void)
+static void __init lilly1131_usb_init(void)
 {
 	imx31_add_mxc_ehci_hs(1, &usbh1_pdata);
 
diff --git a/arch/arm/mach-integrator/integrator_ap.c b/arch/arm/mach-integrator/integrator_ap.c
index 2fbbdd5..8cdc730 100644
--- a/arch/arm/mach-integrator/integrator_ap.c
+++ b/arch/arm/mach-integrator/integrator_ap.c
@@ -32,6 +32,7 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/mtd/physmap.h>
+#include <video/vga.h>
 
 #include <mach/hardware.h>
 #include <mach/platform.h>
@@ -154,6 +155,7 @@
 static void __init ap_map_io(void)
 {
 	iotable_init(ap_io_desc, ARRAY_SIZE(ap_io_desc));
+	vga_base = PCI_MEMORY_VADDR;
 }
 
 #define INTEGRATOR_SC_VALID_INT	0x003fffff
@@ -337,15 +339,15 @@
 static void integrator_clocksource_init(u32 khz)
 {
 	void __iomem *base = (void __iomem *)TIMER2_VA_BASE;
-	u32 ctrl = TIMER_CTRL_ENABLE;
+	u32 ctrl = TIMER_CTRL_ENABLE | TIMER_CTRL_PERIODIC;
 
 	if (khz >= 1500) {
 		khz /= 16;
-		ctrl = TIMER_CTRL_DIV16;
+		ctrl |= TIMER_CTRL_DIV16;
 	}
 
-	writel(ctrl, base + TIMER_CTRL);
 	writel(0xffff, base + TIMER_LOAD);
+	writel(ctrl, base + TIMER_CTRL);
 
 	clocksource_mmio_init(base + TIMER_VALUE, "timer2",
 		khz * 1000, 200, 16, clocksource_mmio_readl_down);
diff --git a/arch/arm/mach-integrator/pci_v3.c b/arch/arm/mach-integrator/pci_v3.c
index dd56bfb..11b86e5 100644
--- a/arch/arm/mach-integrator/pci_v3.c
+++ b/arch/arm/mach-integrator/pci_v3.c
@@ -27,7 +27,6 @@
 #include <linux/spinlock.h>
 #include <linux/init.h>
 #include <linux/io.h>
-#include <video/vga.h>
 
 #include <mach/hardware.h>
 #include <mach/platform.h>
@@ -505,7 +504,6 @@
 
 	pcibios_min_io = 0x6000;
 	pcibios_min_mem = 0x00100000;
-	vga_base = PCI_MEMORY_VADDR;
 
 	/*
 	 * Hook in our fault handler for PCI errors
diff --git a/arch/arm/mach-mmp/gplugd.c b/arch/arm/mach-mmp/gplugd.c
index c070c24..98e25d9 100644
--- a/arch/arm/mach-mmp/gplugd.c
+++ b/arch/arm/mach-mmp/gplugd.c
@@ -16,16 +16,18 @@
 #include <mach/gpio.h>
 #include <mach/pxa168.h>
 #include <mach/mfp-pxa168.h>
-#include <mach/mfp-gplugd.h>
 
 #include "common.h"
 
 static unsigned long gplugd_pin_config[] __initdata = {
 	/* UART3 */
-	GPIO8_UART3_SOUT,
-	GPIO9_UART3_SIN,
-	GPI1O_UART3_CTS,
-	GPI11_UART3_RTS,
+	GPIO8_UART3_TXD,
+	GPIO9_UART3_RXD,
+	GPIO1O_UART3_CTS,
+	GPIO11_UART3_RTS,
+
+	/* USB OTG PEN */
+	GPIO18_GPIO,
 
 	/* MMC2 */
 	GPIO28_MMC2_CMD,
@@ -109,6 +111,12 @@
 	GPIO105_CI2C_SDA,
 	GPIO106_CI2C_SCL,
 
+	/* SPI NOR Flash on SSP2 */
+	GPIO107_SSP2_RXD,
+	GPIO108_SSP2_TXD,
+	GPIO110_GPIO,     /* SPI_CSn */
+	GPIO111_SSP2_CLK,
+
 	/* Select JTAG */
 	GPIO109_GPIO,
 
@@ -154,7 +162,7 @@
 				"frequency\n");
 	} else {
 		gpio_direction_output(35, 1);
-		gpio_free(104);
+		gpio_free(35);
 	}
 
 	if (unlikely(gpio_request(85, "DISP_FREQ_SEL_2"))) {
@@ -162,7 +170,7 @@
 				"frequency\n");
 	} else {
 		gpio_direction_output(85, 0);
-		gpio_free(104);
+		gpio_free(85);
 	}
 }
 
diff --git a/arch/arm/mach-mmp/include/mach/mfp-gplugd.h b/arch/arm/mach-mmp/include/mach/mfp-gplugd.h
deleted file mode 100644
index b8cf38d..0000000
--- a/arch/arm/mach-mmp/include/mach/mfp-gplugd.h
+++ /dev/null
@@ -1,52 +0,0 @@
-/*
- * linux/arch/arm/mach-mmp/include/mach/mfp-gplugd.h
- *
- *   MFP definitions used in gplugD
- *
- * 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.
- */
-
-#ifndef __MACH_MFP_GPLUGD_H
-#define __MACH_MFP_GPLUGD_H
-
-#include <plat/mfp.h>
-#include <mach/mfp.h>
-
-/* UART3 */
-#define GPIO8_UART3_SOUT       MFP_CFG(GPIO8, AF2)
-#define GPIO9_UART3_SIN        MFP_CFG(GPIO9, AF2)
-#define GPI1O_UART3_CTS        MFP_CFG(GPIO10, AF2)
-#define GPI11_UART3_RTS        MFP_CFG(GPIO11, AF2)
-
-/* MMC2 */
-#define	GPIO28_MMC2_CMD		MFP_CFG_DRV(GPIO28, AF6, FAST)
-#define	GPIO29_MMC2_CLK		MFP_CFG_DRV(GPIO29, AF6, FAST)
-#define	GPIO30_MMC2_DAT0	MFP_CFG_DRV(GPIO30, AF6, FAST)
-#define	GPIO31_MMC2_DAT1	MFP_CFG_DRV(GPIO31, AF6, FAST)
-#define	GPIO32_MMC2_DAT2	MFP_CFG_DRV(GPIO32, AF6, FAST)
-#define	GPIO33_MMC2_DAT3	MFP_CFG_DRV(GPIO33, AF6, FAST)
-
-/* I2S */
-#undef GPIO114_I2S_FRM
-#undef GPIO115_I2S_BCLK
-
-#define GPIO114_I2S_FRM	        MFP_CFG_DRV(GPIO114, AF1, FAST)
-#define GPIO115_I2S_BCLK        MFP_CFG_DRV(GPIO115, AF1, FAST)
-#define GPIO116_I2S_TXD         MFP_CFG_DRV(GPIO116, AF1, FAST)
-
-/* MMC4 */
-#define GPIO125_MMC4_DAT3       MFP_CFG_DRV(GPIO125, AF7, FAST)
-#define GPIO126_MMC4_DAT2       MFP_CFG_DRV(GPIO126, AF7, FAST)
-#define GPIO127_MMC4_DAT1       MFP_CFG_DRV(GPIO127, AF7, FAST)
-#define GPIO0_2_MMC4_DAT0       MFP_CFG_DRV(GPIO0_2, AF7, FAST)
-#define GPIO1_2_MMC4_CMD        MFP_CFG_DRV(GPIO1_2, AF7, FAST)
-#define GPIO2_2_MMC4_CLK        MFP_CFG_DRV(GPIO2_2, AF7, FAST)
-
-/* OTG GPIO */
-#define GPIO_USB_OTG_PEN        18
-#define GPIO_USB_OIDIR          20
-
-/* Other GPIOs are 35, 84, 85 */
-#endif /* __MACH_MFP_GPLUGD_H */
diff --git a/arch/arm/mach-mmp/include/mach/mfp-pxa168.h b/arch/arm/mach-mmp/include/mach/mfp-pxa168.h
index 8c78232..92aaa3c 100644
--- a/arch/arm/mach-mmp/include/mach/mfp-pxa168.h
+++ b/arch/arm/mach-mmp/include/mach/mfp-pxa168.h
@@ -203,6 +203,10 @@
 #define GPIO33_CF_nCD2		MFP_CFG(GPIO33, AF3)
 
 /* UART */
+#define GPIO8_UART3_TXD		MFP_CFG(GPIO8, AF2)
+#define GPIO9_UART3_RXD		MFP_CFG(GPIO9, AF2)
+#define GPIO1O_UART3_CTS	MFP_CFG(GPIO10, AF2)
+#define GPIO11_UART3_RTS	MFP_CFG(GPIO11, AF2)
 #define GPIO88_UART2_TXD	MFP_CFG(GPIO88, AF2)
 #define GPIO89_UART2_RXD	MFP_CFG(GPIO89, AF2)
 #define GPIO107_UART1_TXD	MFP_CFG_DRV(GPIO107, AF1, FAST)
@@ -232,6 +236,22 @@
 #define GPIO53_MMC1_CD		MFP_CFG(GPIO53, AF1)
 #define GPIO46_MMC1_WP		MFP_CFG(GPIO46, AF1)
 
+/* MMC2 */
+#define	GPIO28_MMC2_CMD		MFP_CFG_DRV(GPIO28, AF6, FAST)
+#define	GPIO29_MMC2_CLK		MFP_CFG_DRV(GPIO29, AF6, FAST)
+#define	GPIO30_MMC2_DAT0	MFP_CFG_DRV(GPIO30, AF6, FAST)
+#define	GPIO31_MMC2_DAT1	MFP_CFG_DRV(GPIO31, AF6, FAST)
+#define	GPIO32_MMC2_DAT2	MFP_CFG_DRV(GPIO32, AF6, FAST)
+#define	GPIO33_MMC2_DAT3	MFP_CFG_DRV(GPIO33, AF6, FAST)
+
+/* MMC4 */
+#define GPIO125_MMC4_DAT3       MFP_CFG_DRV(GPIO125, AF7, FAST)
+#define GPIO126_MMC4_DAT2       MFP_CFG_DRV(GPIO126, AF7, FAST)
+#define GPIO127_MMC4_DAT1       MFP_CFG_DRV(GPIO127, AF7, FAST)
+#define GPIO0_2_MMC4_DAT0       MFP_CFG_DRV(GPIO0_2, AF7, FAST)
+#define GPIO1_2_MMC4_CMD        MFP_CFG_DRV(GPIO1_2, AF7, FAST)
+#define GPIO2_2_MMC4_CLK        MFP_CFG_DRV(GPIO2_2, AF7, FAST)
+
 /* LCD */
 #define GPIO84_LCD_CS		MFP_CFG(GPIO84, AF1)
 #define GPIO60_LCD_DD0		MFP_CFG(GPIO60, AF1)
@@ -269,11 +289,12 @@
 #define GPIO106_CI2C_SCL	MFP_CFG(GPIO106, AF1)
 
 /* I2S */
-#define GPIO113_I2S_MCLK	MFP_CFG(GPIO113,AF6)
-#define GPIO114_I2S_FRM		MFP_CFG(GPIO114,AF1)
-#define GPIO115_I2S_BCLK	MFP_CFG(GPIO115,AF1)
-#define GPIO116_I2S_RXD		MFP_CFG(GPIO116,AF2)
-#define GPIO117_I2S_TXD		MFP_CFG(GPIO117,AF2)
+#define GPIO113_I2S_MCLK	MFP_CFG(GPIO113, AF6)
+#define GPIO114_I2S_FRM		MFP_CFG(GPIO114, AF1)
+#define GPIO115_I2S_BCLK	MFP_CFG(GPIO115, AF1)
+#define GPIO116_I2S_RXD		MFP_CFG(GPIO116, AF2)
+#define GPIO116_I2S_TXD         MFP_CFG(GPIO116, AF1)
+#define GPIO117_I2S_TXD		MFP_CFG(GPIO117, AF2)
 
 /* PWM */
 #define GPIO96_PWM3_OUT		MFP_CFG(GPIO96, AF1)
@@ -324,4 +345,10 @@
 #define GPIO101_MII_MDIO	MFP_CFG(GPIO101, AF5)
 #define GPIO103_RX_DV		MFP_CFG(GPIO103, AF5)
 
+/* SSP2 */
+#define GPIO107_SSP2_RXD	MFP_CFG(GPIO107, AF4)
+#define GPIO108_SSP2_TXD	MFP_CFG(GPIO108, AF4)
+#define GPIO111_SSP2_CLK	MFP_CFG(GPIO111, AF4)
+#define GPIO112_SSP2_FRM	MFP_CFG(GPIO112, AF4)
+
 #endif /* __ASM_MACH_MFP_PXA168_H */
diff --git a/arch/arm/mach-mmp/time.c b/arch/arm/mach-mmp/time.c
index 99833b9..4e91ee6 100644
--- a/arch/arm/mach-mmp/time.c
+++ b/arch/arm/mach-mmp/time.c
@@ -51,12 +51,12 @@
 {
 	int delay = 100;
 
-	__raw_writel(1, TIMERS_VIRT_BASE + TMR_CVWR(0));
+	__raw_writel(1, TIMERS_VIRT_BASE + TMR_CVWR(1));
 
 	while (delay--)
 		cpu_relax();
 
-	return __raw_readl(TIMERS_VIRT_BASE + TMR_CVWR(0));
+	return __raw_readl(TIMERS_VIRT_BASE + TMR_CVWR(1));
 }
 
 unsigned long long notrace sched_clock(void)
@@ -75,28 +75,51 @@
 {
 	struct clock_event_device *c = dev_id;
 
-	/* disable and clear pending interrupt status */
-	__raw_writel(0x0, TIMERS_VIRT_BASE + TMR_IER(0));
-	__raw_writel(0x1, TIMERS_VIRT_BASE + TMR_ICR(0));
+	/*
+	 * Clear pending interrupt status.
+	 */
+	__raw_writel(0x01, TIMERS_VIRT_BASE + TMR_ICR(0));
+
+	/*
+	 * Disable timer 0.
+	 */
+	__raw_writel(0x02, TIMERS_VIRT_BASE + TMR_CER);
+
 	c->event_handler(c);
+
 	return IRQ_HANDLED;
 }
 
 static int timer_set_next_event(unsigned long delta,
 				struct clock_event_device *dev)
 {
-	unsigned long flags, next;
+	unsigned long flags;
 
 	local_irq_save(flags);
 
-	/* clear pending interrupt status and enable */
+	/*
+	 * Disable timer 0.
+	 */
+	__raw_writel(0x02, TIMERS_VIRT_BASE + TMR_CER);
+
+	/*
+	 * Clear and enable timer match 0 interrupt.
+	 */
 	__raw_writel(0x01, TIMERS_VIRT_BASE + TMR_ICR(0));
 	__raw_writel(0x01, TIMERS_VIRT_BASE + TMR_IER(0));
 
-	next = timer_read() + delta;
-	__raw_writel(next, TIMERS_VIRT_BASE + TMR_TN_MM(0, 0));
+	/*
+	 * Setup new clockevent timer value.
+	 */
+	__raw_writel(delta - 1, TIMERS_VIRT_BASE + TMR_TN_MM(0, 0));
+
+	/*
+	 * Enable timer 0.
+	 */
+	__raw_writel(0x03, TIMERS_VIRT_BASE + TMR_CER);
 
 	local_irq_restore(flags);
+
 	return 0;
 }
 
@@ -145,23 +168,26 @@
 static void __init timer_config(void)
 {
 	uint32_t ccr = __raw_readl(TIMERS_VIRT_BASE + TMR_CCR);
-	uint32_t cer = __raw_readl(TIMERS_VIRT_BASE + TMR_CER);
-	uint32_t cmr = __raw_readl(TIMERS_VIRT_BASE + TMR_CMR);
 
-	__raw_writel(cer & ~0x1, TIMERS_VIRT_BASE + TMR_CER); /* disable */
+	__raw_writel(0x0, TIMERS_VIRT_BASE + TMR_CER); /* disable */
 
-	ccr &= (cpu_is_mmp2()) ? TMR_CCR_CS_0(0) : TMR_CCR_CS_0(3);
+	ccr &= (cpu_is_mmp2()) ? (TMR_CCR_CS_0(0) | TMR_CCR_CS_1(0)) :
+		(TMR_CCR_CS_0(3) | TMR_CCR_CS_1(3));
 	__raw_writel(ccr, TIMERS_VIRT_BASE + TMR_CCR);
 
-	/* free-running mode */
-	__raw_writel(cmr | 0x01, TIMERS_VIRT_BASE + TMR_CMR);
+	/* set timer 0 to periodic mode, and timer 1 to free-running mode */
+	__raw_writel(0x2, TIMERS_VIRT_BASE + TMR_CMR);
 
-	__raw_writel(0x0, TIMERS_VIRT_BASE + TMR_PLCR(0)); /* free-running */
+	__raw_writel(0x1, TIMERS_VIRT_BASE + TMR_PLCR(0)); /* periodic */
 	__raw_writel(0x7, TIMERS_VIRT_BASE + TMR_ICR(0));  /* clear status */
 	__raw_writel(0x0, TIMERS_VIRT_BASE + TMR_IER(0));
 
-	/* enable timer counter */
-	__raw_writel(cer | 0x01, TIMERS_VIRT_BASE + TMR_CER);
+	__raw_writel(0x0, TIMERS_VIRT_BASE + TMR_PLCR(1)); /* free-running */
+	__raw_writel(0x7, TIMERS_VIRT_BASE + TMR_ICR(1));  /* clear status */
+	__raw_writel(0x0, TIMERS_VIRT_BASE + TMR_IER(1));
+
+	/* enable timer 1 counter */
+	__raw_writel(0x2, TIMERS_VIRT_BASE + TMR_CER);
 }
 
 static struct irqaction timer_irq = {
diff --git a/arch/arm/mach-mx5/board-cpuimx51.c b/arch/arm/mach-mx5/board-cpuimx51.c
index 7c893fa..68934ea 100644
--- a/arch/arm/mach-mx5/board-cpuimx51.c
+++ b/arch/arm/mach-mx5/board-cpuimx51.c
@@ -81,7 +81,7 @@
 		.flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST | UPF_IOREMAP,
 	}, {
 		.mapbase = (unsigned long)(MX51_CS1_BASE_ADDR + 0x2000000),
-		.irq = irq_to_gpio(CPUIMX51_QUARTD_GPIO),
+		.irq = gpio_to_irq(CPUIMX51_QUARTD_GPIO),
 		.irqflags = IRQF_TRIGGER_HIGH,
 		.uartclk = CPUIMX51_QUART_XTAL,
 		.regshift = CPUIMX51_QUART_REGSHIFT,
diff --git a/arch/arm/mach-mx5/board-mx51_babbage.c b/arch/arm/mach-mx5/board-mx51_babbage.c
index e400b09..11b0ff6 100644
--- a/arch/arm/mach-mx5/board-mx51_babbage.c
+++ b/arch/arm/mach-mx5/board-mx51_babbage.c
@@ -369,7 +369,7 @@
 					ARRAY_SIZE(mx51babbage_pads));
 
 	imx51_add_imx_uart(0, &uart_pdata);
-	imx51_add_imx_uart(1, &uart_pdata);
+	imx51_add_imx_uart(1, NULL);
 	imx51_add_imx_uart(2, &uart_pdata);
 
 	babbage_fec_reset();
diff --git a/arch/arm/mach-mx5/board-mx51_efikamx.c b/arch/arm/mach-mx5/board-mx51_efikamx.c
index f70700d..551daf8 100644
--- a/arch/arm/mach-mx5/board-mx51_efikamx.c
+++ b/arch/arm/mach-mx5/board-mx51_efikamx.c
@@ -108,9 +108,9 @@
 	gpio_request(EFIKAMX_PCBID2, "pcbid2");
 	gpio_direction_input(EFIKAMX_PCBID2);
 
-	id = gpio_get_value(EFIKAMX_PCBID0);
-	id |= gpio_get_value(EFIKAMX_PCBID1) << 1;
-	id |= gpio_get_value(EFIKAMX_PCBID2) << 2;
+	id = gpio_get_value(EFIKAMX_PCBID0) ? 1 : 0;
+	id |= (gpio_get_value(EFIKAMX_PCBID1) ? 1 : 0) << 1;
+	id |= (gpio_get_value(EFIKAMX_PCBID2) ? 1 : 0) << 2;
 
 	switch (id) {
 	case 7:
diff --git a/arch/arm/mach-mx5/board-mx51_efikasb.c b/arch/arm/mach-mx5/board-mx51_efikasb.c
index 2e4d9d3..8a9bca2 100644
--- a/arch/arm/mach-mx5/board-mx51_efikasb.c
+++ b/arch/arm/mach-mx5/board-mx51_efikasb.c
@@ -156,23 +156,24 @@
 	{
 		.code = KEY_POWER,
 		.gpio = EFIKASB_PWRKEY,
-		.type = EV_PWR,
+		.type = EV_KEY,
 		.desc = "Power Button",
 		.wakeup = 1,
-		.debounce_interval = 10, /* ms */
+		.active_low = 1,
 	},
 	{
 		.code = SW_LID,
 		.gpio = EFIKASB_LID,
 		.type = EV_SW,
 		.desc = "Lid Switch",
+		.active_low = 1,
 	},
 	{
-		/* SW_RFKILLALL vs KEY_RFKILL ? */
-		.code = SW_RFKILL_ALL,
+		.code = KEY_RFKILL,
 		.gpio = EFIKASB_RFKILL,
-		.type = EV_SW,
+		.type = EV_KEY,
 		.desc = "rfkill",
+		.active_low = 1,
 	},
 };
 
@@ -224,8 +225,8 @@
 	gpio_request(EFIKASB_PCBID1, "pcb id1");
 	gpio_direction_input(EFIKASB_PCBID1);
 
-	id = gpio_get_value(EFIKASB_PCBID0);
-	id |= gpio_get_value(EFIKASB_PCBID1) << 1;
+	id = gpio_get_value(EFIKASB_PCBID0) ? 1 : 0;
+	id |= (gpio_get_value(EFIKASB_PCBID1) ? 1 : 0) << 1;
 
 	switch (id) {
 	default:
diff --git a/arch/arm/mach-mx5/clock-mx51-mx53.c b/arch/arm/mach-mx5/clock-mx51-mx53.c
index 7f20308..f7bf996 100644
--- a/arch/arm/mach-mx5/clock-mx51-mx53.c
+++ b/arch/arm/mach-mx5/clock-mx51-mx53.c
@@ -271,7 +271,11 @@
 	int i = 0;
 
 	pllbase = _get_pll_base(clk);
-	reg = __raw_readl(pllbase + MXC_PLL_DP_CTL) | MXC_PLL_DP_CTL_UPEN;
+	reg = __raw_readl(pllbase + MXC_PLL_DP_CTL);
+	if (reg & MXC_PLL_DP_CTL_UPEN)
+		return 0;
+
+	reg |= MXC_PLL_DP_CTL_UPEN;
 	__raw_writel(reg, pllbase + MXC_PLL_DP_CTL);
 
 	/* Wait for lock */
diff --git a/arch/arm/mach-mx5/mx51_efika.c b/arch/arm/mach-mx5/mx51_efika.c
index 4435e03..c920945 100644
--- a/arch/arm/mach-mx5/mx51_efika.c
+++ b/arch/arm/mach-mx5/mx51_efika.c
@@ -186,7 +186,7 @@
 
 	mdelay(10);
 
-	return mx51_initialize_usb_hw(0, MXC_EHCI_ITC_NO_THRESHOLD);
+	return mx51_initialize_usb_hw(pdev->id, MXC_EHCI_ITC_NO_THRESHOLD);
 }
 
 static struct mxc_usbh_platform_data usbh1_config = {
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index 4ae6257..57b66d5 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -7,7 +7,6 @@
 	default y
 	select AEABI
 	select REGULATOR
-	select PM
 	select PM_RUNTIME
 	select VFP
 	select NEON if ARCH_OMAP3 || ARCH_OMAP4
diff --git a/arch/arm/mach-omap2/board-am3517crane.c b/arch/arm/mach-omap2/board-am3517crane.c
index 5f2b55f..933e935 100644
--- a/arch/arm/mach-omap2/board-am3517crane.c
+++ b/arch/arm/mach-omap2/board-am3517crane.c
@@ -45,8 +45,6 @@
 static struct omap_board_mux board_mux[] __initdata = {
 	{ .reg_offset = OMAP_MUX_TERMINATOR },
 };
-#else
-#define board_mux	NULL
 #endif
 
 static void __init am3517_crane_init_early(void)
diff --git a/arch/arm/mach-omap2/board-omap3beagle.c b/arch/arm/mach-omap2/board-omap3beagle.c
index 32f5f89..3ae16b4 100644
--- a/arch/arm/mach-omap2/board-omap3beagle.c
+++ b/arch/arm/mach-omap2/board-omap3beagle.c
@@ -491,23 +491,22 @@
 
 	/* Custom OPP enabled for all xM versions */
 	if (cpu_is_omap3630()) {
-		struct omap_hwmod *mh = omap_hwmod_lookup("mpu");
-		struct omap_hwmod *dh = omap_hwmod_lookup("iva");
-		struct device *dev;
+		struct device *mpu_dev, *iva_dev;
 
-		if (!mh || !dh) {
+		mpu_dev = omap2_get_mpuss_device();
+		iva_dev = omap2_get_iva_device();
+
+		if (!mpu_dev || !iva_dev) {
 			pr_err("%s: Aiee.. no mpu/dsp devices? %p %p\n",
-				__func__, mh, dh);
+				__func__, mpu_dev, iva_dev);
 			return;
 		}
 		/* Enable MPU 1GHz and lower opps */
-		dev = &mh->od->pdev.dev;
-		r = opp_enable(dev, 800000000);
+		r = opp_enable(mpu_dev, 800000000);
 		/* TODO: MPU 1GHz needs SR and ABB */
 
 		/* Enable IVA 800MHz and lower opps */
-		dev = &dh->od->pdev.dev;
-		r |= opp_enable(dev, 660000000);
+		r |= opp_enable(iva_dev, 660000000);
 		/* TODO: DSP 800MHz needs SR and ABB */
 		if (r) {
 			pr_err("%s: failed to enable higher opp %d\n",
@@ -516,10 +515,8 @@
 			 * Cleanup - disable the higher freqs - we dont care
 			 * about the results
 			 */
-			dev = &mh->od->pdev.dev;
-			opp_disable(dev, 800000000);
-			dev = &dh->od->pdev.dev;
-			opp_disable(dev, 660000000);
+			opp_disable(mpu_dev, 800000000);
+			opp_disable(iva_dev, 660000000);
 		}
 	}
 	return;
diff --git a/arch/arm/mach-omap2/clock3xxx_data.c b/arch/arm/mach-omap2/clock3xxx_data.c
index ffd55b1..b9b8446 100644
--- a/arch/arm/mach-omap2/clock3xxx_data.c
+++ b/arch/arm/mach-omap2/clock3xxx_data.c
@@ -3078,6 +3078,7 @@
 	.name		= "gpt12_fck",
 	.ops		= &clkops_null,
 	.parent		= &secure_32k_fck,
+	.clkdm_name	= "wkup_clkdm",
 	.recalc		= &followparent_recalc,
 };
 
@@ -3085,6 +3086,7 @@
 	.name		= "wdt1_fck",
 	.ops		= &clkops_null,
 	.parent		= &secure_32k_fck,
+	.clkdm_name	= "wkup_clkdm",
 	.recalc		= &followparent_recalc,
 };
 
diff --git a/arch/arm/mach-omap2/clock44xx_data.c b/arch/arm/mach-omap2/clock44xx_data.c
index 2af0e3f0..c0b6fbd 100644
--- a/arch/arm/mach-omap2/clock44xx_data.c
+++ b/arch/arm/mach-omap2/clock44xx_data.c
@@ -3376,10 +3376,18 @@
 	} else if (cpu_is_omap446x()) {
 		cpu_mask = RATE_IN_4460;
 		cpu_clkflg = CK_446X;
+	} else {
+		return 0;
 	}
 
 	clk_init(&omap2_clk_functions);
-	omap2_clk_disable_clkdm_control();
+
+	/*
+	 * Must stay commented until all OMAP SoC drivers are
+	 * converted to runtime PM, or drivers may start crashing
+	 *
+	 * omap2_clk_disable_clkdm_control();
+	 */
 
 	for (c = omap44xx_clks; c < omap44xx_clks + ARRAY_SIZE(omap44xx_clks);
 									  c++)
diff --git a/arch/arm/mach-omap2/clockdomain.c b/arch/arm/mach-omap2/clockdomain.c
index ab7db08..8f08906 100644
--- a/arch/arm/mach-omap2/clockdomain.c
+++ b/arch/arm/mach-omap2/clockdomain.c
@@ -747,6 +747,7 @@
 	spin_lock_irqsave(&clkdm->lock, flags);
 	clkdm->_flags &= ~_CLKDM_FLAG_HWSUP_ENABLED;
 	ret = arch_clkdm->clkdm_wakeup(clkdm);
+	ret |= pwrdm_state_switch(clkdm->pwrdm.ptr);
 	spin_unlock_irqrestore(&clkdm->lock, flags);
 	return ret;
 }
@@ -818,6 +819,7 @@
 	spin_lock_irqsave(&clkdm->lock, flags);
 	clkdm->_flags &= ~_CLKDM_FLAG_HWSUP_ENABLED;
 	arch_clkdm->clkdm_deny_idle(clkdm);
+	pwrdm_state_switch(clkdm->pwrdm.ptr);
 	spin_unlock_irqrestore(&clkdm->lock, flags);
 }
 
diff --git a/arch/arm/mach-omap2/cminst44xx.h b/arch/arm/mach-omap2/cminst44xx.h
index f2ea645..a018a73 100644
--- a/arch/arm/mach-omap2/cminst44xx.h
+++ b/arch/arm/mach-omap2/cminst44xx.h
@@ -18,13 +18,36 @@
 extern void omap4_cminst_clkdm_force_wakeup(u8 part, s16 inst, u16 cdoffs);
 
 extern int omap4_cminst_wait_module_ready(u8 part, u16 inst, s16 cdoffs, u16 clkctrl_offs);
-extern int omap4_cminst_wait_module_idle(u8 part, u16 inst, s16 cdoffs, u16 clkctrl_offs);
+
+# ifdef CONFIG_ARCH_OMAP4
+extern int omap4_cminst_wait_module_idle(u8 part, u16 inst, s16 cdoffs,
+					 u16 clkctrl_offs);
 
 extern void omap4_cminst_module_enable(u8 mode, u8 part, u16 inst, s16 cdoffs,
 				       u16 clkctrl_offs);
 extern void omap4_cminst_module_disable(u8 part, u16 inst, s16 cdoffs,
 					u16 clkctrl_offs);
 
+# else
+
+static inline int omap4_cminst_wait_module_idle(u8 part, u16 inst, s16 cdoffs,
+					u16 clkctrl_offs)
+{
+	return 0;
+}
+
+static inline void omap4_cminst_module_enable(u8 mode, u8 part, u16 inst,
+				s16 cdoffs, u16 clkctrl_offs)
+{
+}
+
+static inline void omap4_cminst_module_disable(u8 part, u16 inst, s16 cdoffs,
+				 u16 clkctrl_offs)
+{
+}
+
+# endif
+
 /*
  * In an ideal world, we would not export these low-level functions,
  * but this will probably take some time to fix properly
diff --git a/arch/arm/mach-omap2/mux.c b/arch/arm/mach-omap2/mux.c
index c7fb22a..655e948 100644
--- a/arch/arm/mach-omap2/mux.c
+++ b/arch/arm/mach-omap2/mux.c
@@ -821,11 +821,10 @@
 	if (!omap_mux_options)
 		return;
 
-	options = kmalloc(strlen(omap_mux_options) + 1, GFP_KERNEL);
+	options = kstrdup(omap_mux_options, GFP_KERNEL);
 	if (!options)
 		return;
 
-	strcpy(options, omap_mux_options);
 	next_opt = options;
 
 	while ((token = strsep(&next_opt, ",")) != NULL) {
@@ -855,24 +854,19 @@
 
 	for (i = 0; i < OMAP_MUX_NR_MODES; i++) {
 		if (src->muxnames[i]) {
-			dst->muxnames[i] =
-				kmalloc(strlen(src->muxnames[i]) + 1,
-					GFP_KERNEL);
+			dst->muxnames[i] = kstrdup(src->muxnames[i],
+						   GFP_KERNEL);
 			if (!dst->muxnames[i])
 				goto free;
-			strcpy(dst->muxnames[i], src->muxnames[i]);
 		}
 	}
 
 #ifdef CONFIG_DEBUG_FS
 	for (i = 0; i < OMAP_MUX_NR_SIDES; i++) {
 		if (src->balls[i]) {
-			dst->balls[i] =
-				kmalloc(strlen(src->balls[i]) + 1,
-					GFP_KERNEL);
+			dst->balls[i] = kstrdup(src->balls[i], GFP_KERNEL);
 			if (!dst->balls[i])
 				goto free;
-			strcpy(dst->balls[i], src->balls[i]);
 		}
 	}
 #endif
diff --git a/arch/arm/mach-omap2/omap_hwmod_2430_data.c b/arch/arm/mach-omap2/omap_hwmod_2430_data.c
index 16743c7..408193d 100644
--- a/arch/arm/mach-omap2/omap_hwmod_2430_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_2430_data.c
@@ -192,6 +192,7 @@
 		.pa_end		= OMAP243X_HS_BASE + SZ_4K - 1,
 		.flags		= ADDR_TYPE_RT
 	},
+	{ }
 };
 
 /*  l4_core ->usbhsotg  interface */
diff --git a/arch/arm/mach-omap2/pm.c b/arch/arm/mach-omap2/pm.c
index 3feb359..472bf22 100644
--- a/arch/arm/mach-omap2/pm.c
+++ b/arch/arm/mach-omap2/pm.c
@@ -130,7 +130,6 @@
 		} else {
 			hwsup = clkdm_in_hwsup(pwrdm->pwrdm_clkdms[0]);
 			clkdm_wakeup(pwrdm->pwrdm_clkdms[0]);
-			pwrdm_wait_transition(pwrdm);
 			sleep_switch = FORCEWAKEUP_SWITCH;
 		}
 	}
@@ -156,7 +155,6 @@
 		return ret;
 	}
 
-	pwrdm_wait_transition(pwrdm);
 	pwrdm_state_switch(pwrdm);
 err:
 	return ret;
diff --git a/arch/arm/mach-omap2/powerdomain.c b/arch/arm/mach-omap2/powerdomain.c
index 9af0847..ef71fdd 100644
--- a/arch/arm/mach-omap2/powerdomain.c
+++ b/arch/arm/mach-omap2/powerdomain.c
@@ -195,28 +195,35 @@
 
 /**
  * pwrdm_init - set up the powerdomain layer
- * @pwrdm_list: array of struct powerdomain pointers to register
+ * @pwrdms: array of struct powerdomain pointers to register
  * @custom_funcs: func pointers for arch specific implementations
  *
- * Loop through the array of powerdomains @pwrdm_list, registering all
- * that are available on the current CPU. If pwrdm_list is supplied
- * and not null, all of the referenced powerdomains will be
- * registered.  No return value.  XXX pwrdm_list is not really a
- * "list"; it is an array.  Rename appropriately.
+ * Loop through the array of powerdomains @pwrdms, registering all
+ * that are available on the current CPU.  Also, program all
+ * powerdomain target state as ON; this is to prevent domains from
+ * hitting low power states (if bootloader has target states set to
+ * something other than ON) and potentially even losing context while
+ * PM is not fully initialized.  The PM late init code can then program
+ * the desired target state for all the power domains.  No return
+ * value.
  */
-void pwrdm_init(struct powerdomain **pwrdm_list, struct pwrdm_ops *custom_funcs)
+void pwrdm_init(struct powerdomain **pwrdms, struct pwrdm_ops *custom_funcs)
 {
 	struct powerdomain **p = NULL;
+	struct powerdomain *temp_p;
 
 	if (!custom_funcs)
 		WARN(1, "powerdomain: No custom pwrdm functions registered\n");
 	else
 		arch_pwrdm = custom_funcs;
 
-	if (pwrdm_list) {
-		for (p = pwrdm_list; *p; p++)
+	if (pwrdms) {
+		for (p = pwrdms; *p; p++)
 			_pwrdm_register(*p);
 	}
+
+	list_for_each_entry(temp_p, &pwrdm_list, node)
+		pwrdm_set_next_pwrst(temp_p, PWRDM_POWER_ON);
 }
 
 /**
diff --git a/arch/arm/mach-omap2/smartreflex.c b/arch/arm/mach-omap2/smartreflex.c
index 2ce2fb7..34c01a7 100644
--- a/arch/arm/mach-omap2/smartreflex.c
+++ b/arch/arm/mach-omap2/smartreflex.c
@@ -621,7 +621,7 @@
 			sr_v2_disable(sr);
 	}
 
-	pm_runtime_put_sync(&sr->pdev->dev);
+	pm_runtime_put_sync_suspend(&sr->pdev->dev);
 }
 
 /**
@@ -860,6 +860,7 @@
 	irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
 
 	pm_runtime_enable(&pdev->dev);
+	pm_runtime_irq_safe(&pdev->dev);
 
 	sr_info->pdev = pdev;
 	sr_info->srid = pdev->id;
diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c
index e964072..cf1de7d 100644
--- a/arch/arm/mach-omap2/timer.c
+++ b/arch/arm/mach-omap2/timer.c
@@ -293,7 +293,8 @@
 	pr_info("OMAP clocksource: GPTIMER%d at %lu Hz\n",
 		gptimer_id, clksrc.rate);
 
-	__omap_dm_timer_load_start(clksrc.io_base, OMAP_TIMER_CTRL_ST, 0, 1);
+	__omap_dm_timer_load_start(clksrc.io_base,
+			OMAP_TIMER_CTRL_ST | OMAP_TIMER_CTRL_AR, 0, 1);
 	init_sched_clock(&cd, dmtimer_update_sched_clock, 32, clksrc.rate);
 
 	if (clocksource_register_hz(&clocksource_gpt, clksrc.rate))
diff --git a/arch/arm/mach-omap2/twl-common.c b/arch/arm/mach-omap2/twl-common.c
index 2543342..daa056e 100644
--- a/arch/arm/mach-omap2/twl-common.c
+++ b/arch/arm/mach-omap2/twl-common.c
@@ -48,14 +48,7 @@
 	omap_register_i2c_bus(bus, clkrate, &pmic_i2c_board_info, 1);
 }
 
-static struct twl4030_usb_data omap4_usb_pdata = {
-	.phy_init	= omap4430_phy_init,
-	.phy_exit	= omap4430_phy_exit,
-	.phy_power	= omap4430_phy_power,
-	.phy_set_clock	= omap4430_phy_set_clk,
-	.phy_suspend	= omap4430_phy_suspend,
-};
-
+#if defined(CONFIG_ARCH_OMAP3)
 static struct twl4030_usb_data omap3_usb_pdata = {
 	.usb_mode	= T2_USB_MODE_ULPI,
 };
@@ -122,6 +115,45 @@
 	.consumer_supplies		= omap3_vpll2_supplies,
 };
 
+void __init omap3_pmic_get_config(struct twl4030_platform_data *pmic_data,
+				  u32 pdata_flags, u32 regulators_flags)
+{
+	if (!pmic_data->irq_base)
+		pmic_data->irq_base = TWL4030_IRQ_BASE;
+	if (!pmic_data->irq_end)
+		pmic_data->irq_end = TWL4030_IRQ_END;
+
+	/* Common platform data configurations */
+	if (pdata_flags & TWL_COMMON_PDATA_USB && !pmic_data->usb)
+		pmic_data->usb = &omap3_usb_pdata;
+
+	if (pdata_flags & TWL_COMMON_PDATA_BCI && !pmic_data->bci)
+		pmic_data->bci = &omap3_bci_pdata;
+
+	if (pdata_flags & TWL_COMMON_PDATA_MADC && !pmic_data->madc)
+		pmic_data->madc = &omap3_madc_pdata;
+
+	if (pdata_flags & TWL_COMMON_PDATA_AUDIO && !pmic_data->audio)
+		pmic_data->audio = &omap3_audio_pdata;
+
+	/* Common regulator configurations */
+	if (regulators_flags & TWL_COMMON_REGULATOR_VDAC && !pmic_data->vdac)
+		pmic_data->vdac = &omap3_vdac_idata;
+
+	if (regulators_flags & TWL_COMMON_REGULATOR_VPLL2 && !pmic_data->vpll2)
+		pmic_data->vpll2 = &omap3_vpll2_idata;
+}
+#endif /* CONFIG_ARCH_OMAP3 */
+
+#if defined(CONFIG_ARCH_OMAP4)
+static struct twl4030_usb_data omap4_usb_pdata = {
+	.phy_init	= omap4430_phy_init,
+	.phy_exit	= omap4430_phy_exit,
+	.phy_power	= omap4430_phy_power,
+	.phy_set_clock	= omap4430_phy_set_clk,
+	.phy_suspend	= omap4430_phy_suspend,
+};
+
 static struct regulator_init_data omap4_vdac_idata = {
 	.constraints = {
 		.min_uV			= 1800000,
@@ -273,32 +305,4 @@
 	    !pmic_data->clk32kg)
 		pmic_data->clk32kg = &omap4_clk32kg_idata;
 }
-
-void __init omap3_pmic_get_config(struct twl4030_platform_data *pmic_data,
-				  u32 pdata_flags, u32 regulators_flags)
-{
-	if (!pmic_data->irq_base)
-		pmic_data->irq_base = TWL4030_IRQ_BASE;
-	if (!pmic_data->irq_end)
-		pmic_data->irq_end = TWL4030_IRQ_END;
-
-	/* Common platform data configurations */
-	if (pdata_flags & TWL_COMMON_PDATA_USB && !pmic_data->usb)
-		pmic_data->usb = &omap3_usb_pdata;
-
-	if (pdata_flags & TWL_COMMON_PDATA_BCI && !pmic_data->bci)
-		pmic_data->bci = &omap3_bci_pdata;
-
-	if (pdata_flags & TWL_COMMON_PDATA_MADC && !pmic_data->madc)
-		pmic_data->madc = &omap3_madc_pdata;
-
-	if (pdata_flags & TWL_COMMON_PDATA_AUDIO && !pmic_data->audio)
-		pmic_data->audio = &omap3_audio_pdata;
-
-	/* Common regulator configurations */
-	if (regulators_flags & TWL_COMMON_REGULATOR_VDAC && !pmic_data->vdac)
-		pmic_data->vdac = &omap3_vdac_idata;
-
-	if (regulators_flags & TWL_COMMON_REGULATOR_VPLL2 && !pmic_data->vpll2)
-		pmic_data->vpll2 = &omap3_vpll2_idata;
-}
+#endif /* CONFIG_ARCH_OMAP4 */
diff --git a/arch/arm/mach-orion5x/dns323-setup.c b/arch/arm/mach-orion5x/dns323-setup.c
index a6eddae..c105556 100644
--- a/arch/arm/mach-orion5x/dns323-setup.c
+++ b/arch/arm/mach-orion5x/dns323-setup.c
@@ -77,7 +77,7 @@
 	/*
 	 * Check for devices with hard-wired IRQs.
 	 */
-	irq = orion5x_pci_map_irq(const dev, slot, pin);
+	irq = orion5x_pci_map_irq(dev, slot, pin);
 	if (irq != -1)
 		return irq;
 
diff --git a/arch/arm/mach-orion5x/pci.c b/arch/arm/mach-orion5x/pci.c
index 28b8760..bc4a920 100644
--- a/arch/arm/mach-orion5x/pci.c
+++ b/arch/arm/mach-orion5x/pci.c
@@ -14,6 +14,7 @@
 #include <linux/pci.h>
 #include <linux/slab.h>
 #include <linux/mbus.h>
+#include <video/vga.h>
 #include <asm/irq.h>
 #include <asm/mach/pci.h>
 #include <plat/pcie.h>
diff --git a/arch/arm/mach-prima2/clock.c b/arch/arm/mach-prima2/clock.c
index f9a2aaf..615a4e7 100644
--- a/arch/arm/mach-prima2/clock.c
+++ b/arch/arm/mach-prima2/clock.c
@@ -481,6 +481,7 @@
 
 static struct of_device_id clkc_ids[] = {
 	{ .compatible = "sirf,prima2-clkc" },
+	{},
 };
 
 void __init sirfsoc_of_clk_init(void)
diff --git a/arch/arm/mach-prima2/irq.c b/arch/arm/mach-prima2/irq.c
index c3404cb..7af254d 100644
--- a/arch/arm/mach-prima2/irq.c
+++ b/arch/arm/mach-prima2/irq.c
@@ -51,6 +51,7 @@
 
 static struct of_device_id intc_ids[]  = {
 	{ .compatible = "sirf,prima2-intc" },
+	{},
 };
 
 void __init sirfsoc_of_irq_init(void)
diff --git a/arch/arm/mach-prima2/rstc.c b/arch/arm/mach-prima2/rstc.c
index d074786..492cfa8 100644
--- a/arch/arm/mach-prima2/rstc.c
+++ b/arch/arm/mach-prima2/rstc.c
@@ -19,6 +19,7 @@
 
 static struct of_device_id rstc_ids[]  = {
 	{ .compatible = "sirf,prima2-rstc" },
+	{},
 };
 
 static int __init sirfsoc_of_rstc_init(void)
diff --git a/arch/arm/mach-prima2/timer.c b/arch/arm/mach-prima2/timer.c
index 44027f3..ed7ec48 100644
--- a/arch/arm/mach-prima2/timer.c
+++ b/arch/arm/mach-prima2/timer.c
@@ -190,6 +190,7 @@
 
 static struct of_device_id timer_ids[] = {
 	{ .compatible = "sirf,prima2-tick" },
+	{},
 };
 
 static void __init sirfsoc_of_timer_map(void)
diff --git a/arch/arm/mach-realview/include/mach/system.h b/arch/arm/mach-realview/include/mach/system.h
index a30f2e3..6657ff23 100644
--- a/arch/arm/mach-realview/include/mach/system.h
+++ b/arch/arm/mach-realview/include/mach/system.h
@@ -44,6 +44,7 @@
 	 */
 	if (realview_reset)
 		realview_reset(mode);
+	dsb();
 }
 
 #endif
diff --git a/arch/arm/mach-s3c2443/clock.c b/arch/arm/mach-s3c2443/clock.c
index a1a7176..38058af 100644
--- a/arch/arm/mach-s3c2443/clock.c
+++ b/arch/arm/mach-s3c2443/clock.c
@@ -128,7 +128,7 @@
 		unsigned long clkcon0;
 
 		clkcon0 = __raw_readl(S3C2443_CLKDIV0);
-		clkcon0 &= S3C2443_CLKDIV0_ARMDIV_MASK;
+		clkcon0 &= ~S3C2443_CLKDIV0_ARMDIV_MASK;
 		clkcon0 |= val << S3C2443_CLKDIV0_ARMDIV_SHIFT;
 		__raw_writel(clkcon0, S3C2443_CLKDIV0);
 	}
diff --git a/arch/arm/mach-s3c64xx/mach-smdk6410.c b/arch/arm/mach-s3c64xx/mach-smdk6410.c
index ecbea92..a9f3183 100644
--- a/arch/arm/mach-s3c64xx/mach-smdk6410.c
+++ b/arch/arm/mach-s3c64xx/mach-smdk6410.c
@@ -262,45 +262,6 @@
 	.cols		= 8,
 };
 
-static int smdk6410_backlight_init(struct device *dev)
-{
-	int ret;
-
-	ret = gpio_request(S3C64XX_GPF(15), "Backlight");
-	if (ret) {
-		printk(KERN_ERR "failed to request GPF for PWM-OUT1\n");
-		return ret;
-	}
-
-	/* Configure GPIO pin with S3C64XX_GPF15_PWM_TOUT1 */
-	s3c_gpio_cfgpin(S3C64XX_GPF(15), S3C_GPIO_SFN(2));
-
-	return 0;
-}
-
-static void smdk6410_backlight_exit(struct device *dev)
-{
-	s3c_gpio_cfgpin(S3C64XX_GPF(15), S3C_GPIO_OUTPUT);
-	gpio_free(S3C64XX_GPF(15));
-}
-
-static struct platform_pwm_backlight_data smdk6410_backlight_data = {
-	.pwm_id		= 1,
-	.max_brightness	= 255,
-	.dft_brightness	= 255,
-	.pwm_period_ns	= 78770,
-	.init		= smdk6410_backlight_init,
-	.exit		= smdk6410_backlight_exit,
-};
-
-static struct platform_device smdk6410_backlight_device = {
-	.name		= "pwm-backlight",
-	.dev		= {
-		.parent		= &s3c_device_timer[1].dev,
-		.platform_data	= &smdk6410_backlight_data,
-	},
-};
-
 static struct map_desc smdk6410_iodesc[] = {};
 
 static struct platform_device *smdk6410_devices[] __initdata = {
diff --git a/arch/arm/mach-s3c64xx/pm.c b/arch/arm/mach-s3c64xx/pm.c
index 8bad643..055e285 100644
--- a/arch/arm/mach-s3c64xx/pm.c
+++ b/arch/arm/mach-s3c64xx/pm.c
@@ -16,6 +16,7 @@
 #include <linux/suspend.h>
 #include <linux/serial_core.h>
 #include <linux/io.h>
+#include <linux/gpio.h>
 
 #include <mach/map.h>
 #include <mach/irqs.h>
diff --git a/arch/arm/mach-s5p64x0/irq-eint.c b/arch/arm/mach-s5p64x0/irq-eint.c
index 69ed454..fe7380f 100644
--- a/arch/arm/mach-s5p64x0/irq-eint.c
+++ b/arch/arm/mach-s5p64x0/irq-eint.c
@@ -129,7 +129,7 @@
 	}
 
 	ct = gc->chip_types;
-	ct->chip.irq_ack = irq_gc_ack;
+	ct->chip.irq_ack = irq_gc_ack_set_bit;
 	ct->chip.irq_mask = irq_gc_mask_set_bit;
 	ct->chip.irq_unmask = irq_gc_mask_clr_bit;
 	ct->chip.irq_set_type = s5p64x0_irq_eint_set_type;
diff --git a/arch/arm/mach-s5pv210/clock.c b/arch/arm/mach-s5pv210/clock.c
index 52a8e60..f5f8fa8 100644
--- a/arch/arm/mach-s5pv210/clock.c
+++ b/arch/arm/mach-s5pv210/clock.c
@@ -815,8 +815,7 @@
 		.reg_div = { .reg = S5P_CLK_DIV3, .shift = 20, .size = 4 },
 	}, {
 		.clk		= {
-			.name		= "sclk_cam",
-			.devname	= "s5pv210-fimc.0",
+			.name		= "sclk_cam0",
 			.enable		= s5pv210_clk_mask0_ctrl,
 			.ctrlbit	= (1 << 3),
 		},
@@ -825,8 +824,7 @@
 		.reg_div = { .reg = S5P_CLK_DIV1, .shift = 12, .size = 4 },
 	}, {
 		.clk		= {
-			.name		= "sclk_cam",
-			.devname	= "s5pv210-fimc.1",
+			.name		= "sclk_cam1",
 			.enable		= s5pv210_clk_mask0_ctrl,
 			.ctrlbit	= (1 << 4),
 		},
diff --git a/arch/arm/mach-s5pv210/pm.c b/arch/arm/mach-s5pv210/pm.c
index 309e388..f149d27 100644
--- a/arch/arm/mach-s5pv210/pm.c
+++ b/arch/arm/mach-s5pv210/pm.c
@@ -88,7 +88,7 @@
 	SAVE_ITEM(S3C2410_TCNTO(0)),
 };
 
-void s5pv210_cpu_suspend(unsigned long arg)
+static int s5pv210_cpu_suspend(unsigned long arg)
 {
 	unsigned long tmp;
 
diff --git a/arch/arm/mach-sa1100/pci-nanoengine.c b/arch/arm/mach-sa1100/pci-nanoengine.c
index 964c6c3..dd39fee 100644
--- a/arch/arm/mach-sa1100/pci-nanoengine.c
+++ b/arch/arm/mach-sa1100/pci-nanoengine.c
@@ -28,6 +28,7 @@
 #include <asm/mach-types.h>
 
 #include <mach/nanoengine.h>
+#include <mach/hardware.h>
 
 static DEFINE_SPINLOCK(nano_lock);
 
diff --git a/arch/arm/mach-shmobile/board-ag5evm.c b/arch/arm/mach-shmobile/board-ag5evm.c
index ce5c251..cdfdd62 100644
--- a/arch/arm/mach-shmobile/board-ag5evm.c
+++ b/arch/arm/mach-shmobile/board-ag5evm.c
@@ -341,6 +341,7 @@
 static struct sh_mobile_sdhi_info sdhi0_info = {
 	.dma_slave_tx	= SHDMA_SLAVE_SDHI0_TX,
 	.dma_slave_rx	= SHDMA_SLAVE_SDHI0_RX,
+	.tmio_flags	= TMIO_MMC_HAS_IDLE_WAIT,
 	.tmio_caps	= MMC_CAP_SD_HIGHSPEED,
 	.tmio_ocr_mask	= MMC_VDD_27_28 | MMC_VDD_28_29,
 };
@@ -382,7 +383,7 @@
 }
 
 static struct sh_mobile_sdhi_info sh_sdhi1_info = {
-	.tmio_flags	= TMIO_MMC_WRPROTECT_DISABLE,
+	.tmio_flags	= TMIO_MMC_WRPROTECT_DISABLE | TMIO_MMC_HAS_IDLE_WAIT,
 	.tmio_caps	= MMC_CAP_NONREMOVABLE | MMC_CAP_SDIO_IRQ,
 	.tmio_ocr_mask	= MMC_VDD_32_33 | MMC_VDD_33_34,
 	.set_pwr	= ag5evm_sdhi1_set_pwr,
diff --git a/arch/arm/mach-shmobile/board-ap4evb.c b/arch/arm/mach-shmobile/board-ap4evb.c
index 9e0856b..523f608 100644
--- a/arch/arm/mach-shmobile/board-ap4evb.c
+++ b/arch/arm/mach-shmobile/board-ap4evb.c
@@ -1412,6 +1412,7 @@
 	fsi_init_pm_clock();
 	sh7372_pm_init();
 	pm_clk_add(&fsi_device.dev, "spu2");
+	pm_clk_add(&lcdc1_device.dev, "hdmi");
 }
 
 static void __init ap4evb_timer_init(void)
diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c
index d41c01f..17c19dc 100644
--- a/arch/arm/mach-shmobile/board-mackerel.c
+++ b/arch/arm/mach-shmobile/board-mackerel.c
@@ -641,6 +641,8 @@
 		},
 		.driver_param = {
 			.buswait_bwait	= 4,
+			.d0_tx_id	= SHDMA_SLAVE_USB0_TX,
+			.d1_rx_id	= SHDMA_SLAVE_USB0_RX,
 		},
 	},
 };
@@ -810,6 +812,8 @@
 			.buswait_bwait	= 4,
 			.pipe_type	= usbhs1_pipe_cfg,
 			.pipe_size	= ARRAY_SIZE(usbhs1_pipe_cfg),
+			.d0_tx_id	= SHDMA_SLAVE_USB1_TX,
+			.d1_rx_id	= SHDMA_SLAVE_USB1_RX,
 		},
 	},
 };
@@ -1588,6 +1592,7 @@
 	hdmi_init_pm_clock();
 	sh7372_pm_init();
 	pm_clk_add(&fsi_device.dev, "spu2");
+	pm_clk_add(&hdmi_lcdc_device.dev, "hdmi");
 }
 
 static void __init mackerel_timer_init(void)
diff --git a/arch/arm/mach-shmobile/clock-sh7372.c b/arch/arm/mach-shmobile/clock-sh7372.c
index 6b1619a..6697592 100644
--- a/arch/arm/mach-shmobile/clock-sh7372.c
+++ b/arch/arm/mach-shmobile/clock-sh7372.c
@@ -503,16 +503,17 @@
 	&sh7372_fsidivb_clk,
 };
 
-enum { MSTP001,
+enum { MSTP001, MSTP000,
        MSTP131, MSTP130,
        MSTP129, MSTP128, MSTP127, MSTP126, MSTP125,
        MSTP118, MSTP117, MSTP116, MSTP113,
        MSTP106, MSTP101, MSTP100,
        MSTP223,
-       MSTP218, MSTP217, MSTP216,
-       MSTP207, MSTP206, MSTP204, MSTP203, MSTP202, MSTP201, MSTP200,
-       MSTP329, MSTP328, MSTP323, MSTP322, MSTP314, MSTP313, MSTP312,
-       MSTP423, MSTP415, MSTP413, MSTP411, MSTP410, MSTP406, MSTP403,
+       MSTP218, MSTP217, MSTP216, MSTP214, MSTP208, MSTP207,
+       MSTP206, MSTP205, MSTP204, MSTP203, MSTP202, MSTP201, MSTP200,
+       MSTP328, MSTP323, MSTP322, MSTP314, MSTP313, MSTP312,
+       MSTP423, MSTP415, MSTP413, MSTP411, MSTP410, MSTP407, MSTP406,
+       MSTP405, MSTP404, MSTP403, MSTP400,
        MSTP_NR };
 
 #define MSTP(_parent, _reg, _bit, _flags) \
@@ -520,6 +521,7 @@
 
 static struct clk mstp_clks[MSTP_NR] = {
 	[MSTP001] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR0, 1, 0), /* IIC2 */
+	[MSTP000] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR0, 0, 0), /* MSIOF0 */
 	[MSTP131] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 31, 0), /* VEU3 */
 	[MSTP130] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 30, 0), /* VEU2 */
 	[MSTP129] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 29, 0), /* VEU1 */
@@ -538,14 +540,16 @@
 	[MSTP218] = MSTP(&div4_clks[DIV4_HP], SMSTPCR2, 18, 0), /* DMAC1 */
 	[MSTP217] = MSTP(&div4_clks[DIV4_HP], SMSTPCR2, 17, 0), /* DMAC2 */
 	[MSTP216] = MSTP(&div4_clks[DIV4_HP], SMSTPCR2, 16, 0), /* DMAC3 */
+	[MSTP214] = MSTP(&div4_clks[DIV4_HP], SMSTPCR2, 14, 0), /* USBDMAC */
+	[MSTP208] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 8, 0), /* MSIOF1 */
 	[MSTP207] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 7, 0), /* SCIFA5 */
 	[MSTP206] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 6, 0), /* SCIFB */
+	[MSTP205] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 5, 0), /* MSIOF2 */
 	[MSTP204] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 4, 0), /* SCIFA0 */
 	[MSTP203] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 3, 0), /* SCIFA1 */
 	[MSTP202] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 2, 0), /* SCIFA2 */
 	[MSTP201] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 1, 0), /* SCIFA3 */
 	[MSTP200] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 0, 0), /* SCIFA4 */
-	[MSTP329] = MSTP(&r_clk, SMSTPCR3, 29, 0), /* CMT10 */
 	[MSTP328] = MSTP(&div6_clks[DIV6_SPU], SMSTPCR3, 28, 0), /* FSI2 */
 	[MSTP323] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR3, 23, 0), /* IIC1 */
 	[MSTP322] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR3, 22, 0), /* USB0 */
@@ -557,8 +561,12 @@
 	[MSTP413] = MSTP(&pllc1_div2_clk, SMSTPCR4, 13, 0), /* HDMI */
 	[MSTP411] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR4, 11, 0), /* IIC3 */
 	[MSTP410] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR4, 10, 0), /* IIC4 */
+	[MSTP407] = MSTP(&div4_clks[DIV4_HP], SMSTPCR4, 7, 0), /* USB-DMAC1 */
 	[MSTP406] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR4, 6, 0), /* USB1 */
+	[MSTP405] = MSTP(&r_clk, SMSTPCR4, 5, 0), /* CMT4 */
+	[MSTP404] = MSTP(&r_clk, SMSTPCR4, 4, 0), /* CMT3 */
 	[MSTP403] = MSTP(&r_clk, SMSTPCR4, 3, 0), /* KEYSC */
+	[MSTP400] = MSTP(&r_clk, SMSTPCR4, 0, 0), /* CMT2 */
 };
 
 static struct clk_lookup lookups[] = {
@@ -609,6 +617,7 @@
 
 	/* MSTP32 clocks */
 	CLKDEV_DEV_ID("i2c-sh_mobile.2", &mstp_clks[MSTP001]), /* IIC2 */
+	CLKDEV_DEV_ID("spi_sh_msiof.0", &mstp_clks[MSTP000]), /* MSIOF0 */
 	CLKDEV_DEV_ID("uio_pdrv_genirq.4", &mstp_clks[MSTP131]), /* VEU3 */
 	CLKDEV_DEV_ID("uio_pdrv_genirq.3", &mstp_clks[MSTP130]), /* VEU2 */
 	CLKDEV_DEV_ID("uio_pdrv_genirq.2", &mstp_clks[MSTP129]), /* VEU1 */
@@ -629,14 +638,16 @@
 	CLKDEV_DEV_ID("sh-dma-engine.0", &mstp_clks[MSTP218]), /* DMAC1 */
 	CLKDEV_DEV_ID("sh-dma-engine.1", &mstp_clks[MSTP217]), /* DMAC2 */
 	CLKDEV_DEV_ID("sh-dma-engine.2", &mstp_clks[MSTP216]), /* DMAC3 */
+	CLKDEV_DEV_ID("sh-dma-engine.3", &mstp_clks[MSTP214]), /* USB-DMAC0 */
+	CLKDEV_DEV_ID("spi_sh_msiof.1", &mstp_clks[MSTP208]), /* MSIOF1 */
 	CLKDEV_DEV_ID("sh-sci.5", &mstp_clks[MSTP207]), /* SCIFA5 */
 	CLKDEV_DEV_ID("sh-sci.6", &mstp_clks[MSTP206]), /* SCIFB */
+	CLKDEV_DEV_ID("spi_sh_msiof.2", &mstp_clks[MSTP205]), /* MSIOF2 */
 	CLKDEV_DEV_ID("sh-sci.0", &mstp_clks[MSTP204]), /* SCIFA0 */
 	CLKDEV_DEV_ID("sh-sci.1", &mstp_clks[MSTP203]), /* SCIFA1 */
 	CLKDEV_DEV_ID("sh-sci.2", &mstp_clks[MSTP202]), /* SCIFA2 */
 	CLKDEV_DEV_ID("sh-sci.3", &mstp_clks[MSTP201]), /* SCIFA3 */
 	CLKDEV_DEV_ID("sh-sci.4", &mstp_clks[MSTP200]), /* SCIFA4 */
-	CLKDEV_DEV_ID("sh_cmt.10", &mstp_clks[MSTP329]), /* CMT10 */
 	CLKDEV_DEV_ID("sh_fsi2", &mstp_clks[MSTP328]), /* FSI2 */
 	CLKDEV_DEV_ID("i2c-sh_mobile.1", &mstp_clks[MSTP323]), /* IIC1 */
 	CLKDEV_DEV_ID("r8a66597_hcd.0", &mstp_clks[MSTP322]), /* USB0 */
@@ -650,11 +661,17 @@
 	CLKDEV_DEV_ID("sh-mobile-hdmi", &mstp_clks[MSTP413]), /* HDMI */
 	CLKDEV_DEV_ID("i2c-sh_mobile.3", &mstp_clks[MSTP411]), /* IIC3 */
 	CLKDEV_DEV_ID("i2c-sh_mobile.4", &mstp_clks[MSTP410]), /* IIC4 */
+	CLKDEV_DEV_ID("sh-dma-engine.4", &mstp_clks[MSTP407]), /* USB-DMAC1 */
 	CLKDEV_DEV_ID("r8a66597_hcd.1", &mstp_clks[MSTP406]), /* USB1 */
 	CLKDEV_DEV_ID("r8a66597_udc.1", &mstp_clks[MSTP406]), /* USB1 */
 	CLKDEV_DEV_ID("renesas_usbhs.1", &mstp_clks[MSTP406]), /* USB1 */
+	CLKDEV_DEV_ID("sh_cmt.4", &mstp_clks[MSTP405]), /* CMT4 */
+	CLKDEV_DEV_ID("sh_cmt.3", &mstp_clks[MSTP404]), /* CMT3 */
 	CLKDEV_DEV_ID("sh_keysc.0", &mstp_clks[MSTP403]), /* KEYSC */
+	CLKDEV_DEV_ID("sh_cmt.2", &mstp_clks[MSTP400]), /* CMT2 */
 
+	CLKDEV_ICK_ID("hdmi", "sh_mobile_lcdc_fb.1",
+		      &div6_reparent_clks[DIV6_HDMI]),
 	CLKDEV_ICK_ID("ick", "sh-mobile-hdmi", &div6_reparent_clks[DIV6_HDMI]),
 	CLKDEV_ICK_ID("icka", "sh_fsi2", &div6_reparent_clks[DIV6_FSIA]),
 	CLKDEV_ICK_ID("ickb", "sh_fsi2", &div6_reparent_clks[DIV6_FSIB]),
diff --git a/arch/arm/mach-shmobile/clock-sh73a0.c b/arch/arm/mach-shmobile/clock-sh73a0.c
index 6db2cca..61a846b 100644
--- a/arch/arm/mach-shmobile/clock-sh73a0.c
+++ b/arch/arm/mach-shmobile/clock-sh73a0.c
@@ -365,7 +365,7 @@
 	__raw_writel(0x108, SD2CKCR);
 
 	/* detect main clock parent */
-	switch ((__raw_readl(CKSCR) >> 24) & 0x03) {
+	switch ((__raw_readl(CKSCR) >> 28) & 0x03) {
 	case 0:
 		main_clk.parent = &sh73a0_extal1_clk;
 		break;
diff --git a/arch/arm/mach-shmobile/include/mach/sh7372.h b/arch/arm/mach-shmobile/include/mach/sh7372.h
index ce595ce..24e63a8 100644
--- a/arch/arm/mach-shmobile/include/mach/sh7372.h
+++ b/arch/arm/mach-shmobile/include/mach/sh7372.h
@@ -459,6 +459,10 @@
 	SHDMA_SLAVE_SDHI2_TX,
 	SHDMA_SLAVE_MMCIF_RX,
 	SHDMA_SLAVE_MMCIF_TX,
+	SHDMA_SLAVE_USB0_TX,
+	SHDMA_SLAVE_USB0_RX,
+	SHDMA_SLAVE_USB1_TX,
+	SHDMA_SLAVE_USB1_RX,
 };
 
 extern struct clk sh7372_extal1_clk;
diff --git a/arch/arm/mach-shmobile/intc-sh7372.c b/arch/arm/mach-shmobile/intc-sh7372.c
index 3b28743..739315e3 100644
--- a/arch/arm/mach-shmobile/intc-sh7372.c
+++ b/arch/arm/mach-shmobile/intc-sh7372.c
@@ -379,7 +379,7 @@
 	/* BBIF2 */
 	VPU,
 	TSIF1,
-	_3DG_SGX530,
+	/* 3DG */
 	_2DDMAC,
 	IIC2_ALI2, IIC2_TACKI2, IIC2_WAITI2, IIC2_DTEI2,
 	IPMMU_IPMMUR, IPMMU_IPMMUR2,
@@ -436,7 +436,7 @@
 	/* BBIF2 */
 	INTCS_VECT(VPU, 0x980),
 	INTCS_VECT(TSIF1, 0x9a0),
-	INTCS_VECT(_3DG_SGX530, 0x9e0),
+	/* 3DG */
 	INTCS_VECT(_2DDMAC, 0xa00),
 	INTCS_VECT(IIC2_ALI2, 0xa80), INTCS_VECT(IIC2_TACKI2, 0xaa0),
 	INTCS_VECT(IIC2_WAITI2, 0xac0), INTCS_VECT(IIC2_DTEI2, 0xae0),
@@ -521,7 +521,7 @@
 	    RTDMAC_1_DEI3, RTDMAC_1_DEI2, RTDMAC_1_DEI1, RTDMAC_1_DEI0 } },
 	{ 0xffd20198, 0xffd201d8, 8, /* IMR6SA / IMCR6SA */
 	  { 0, 0, MSIOF, 0,
-	    _3DG_SGX530, 0, 0, 0 } },
+	    0, 0, 0, 0 } },
 	{ 0xffd2019c, 0xffd201dc, 8, /* IMR7SA / IMCR7SA */
 	  { 0, TMU_TUNI2, TMU_TUNI1, TMU_TUNI0,
 	    0, 0, 0, 0 } },
@@ -561,7 +561,6 @@
 					      TMU_TUNI2, TSIF1 } },
 	{ 0xffd2001c, 0, 16, 4, /* IPRHS */ { 0, 0, VEU, BEU } },
 	{ 0xffd20020, 0, 16, 4, /* IPRIS */ { 0, MSIOF, TSIF0, IIC0 } },
-	{ 0xffd20024, 0, 16, 4, /* IPRJS */ { 0, _3DG_SGX530, 0, 0 } },
 	{ 0xffd20028, 0, 16, 4, /* IPRKS */ { 0, 0, LMB, 0 } },
 	{ 0xffd2002c, 0, 16, 4, /* IPRLS */ { IPMMU, 0, 0, 0 } },
 	{ 0xffd20030, 0, 16, 4, /* IPRMS */ { IIC2, 0, 0, 0 } },
diff --git a/arch/arm/mach-shmobile/setup-sh7372.c b/arch/arm/mach-shmobile/setup-sh7372.c
index 79f0413..2d9b1b1 100644
--- a/arch/arm/mach-shmobile/setup-sh7372.c
+++ b/arch/arm/mach-shmobile/setup-sh7372.c
@@ -169,35 +169,35 @@
 };
 
 /* CMT */
-static struct sh_timer_config cmt10_platform_data = {
-	.name = "CMT10",
-	.channel_offset = 0x10,
-	.timer_bit = 0,
+static struct sh_timer_config cmt2_platform_data = {
+	.name = "CMT2",
+	.channel_offset = 0x40,
+	.timer_bit = 5,
 	.clockevent_rating = 125,
 	.clocksource_rating = 125,
 };
 
-static struct resource cmt10_resources[] = {
+static struct resource cmt2_resources[] = {
 	[0] = {
-		.name	= "CMT10",
-		.start	= 0xe6138010,
-		.end	= 0xe613801b,
+		.name	= "CMT2",
+		.start	= 0xe6130040,
+		.end	= 0xe613004b,
 		.flags	= IORESOURCE_MEM,
 	},
 	[1] = {
-		.start	= evt2irq(0x0b00), /* CMT1_CMT10 */
+		.start	= evt2irq(0x0b80), /* CMT2 */
 		.flags	= IORESOURCE_IRQ,
 	},
 };
 
-static struct platform_device cmt10_device = {
+static struct platform_device cmt2_device = {
 	.name		= "sh_cmt",
-	.id		= 10,
+	.id		= 2,
 	.dev = {
-		.platform_data	= &cmt10_platform_data,
+		.platform_data	= &cmt2_platform_data,
 	},
-	.resource	= cmt10_resources,
-	.num_resources	= ARRAY_SIZE(cmt10_resources),
+	.resource	= cmt2_resources,
+	.num_resources	= ARRAY_SIZE(cmt2_resources),
 };
 
 /* TMU */
@@ -602,6 +602,150 @@
 	},
 };
 
+/*
+ * USB-DMAC
+ */
+
+unsigned int usbts_shift[] = {3, 4, 5};
+
+enum {
+	XMIT_SZ_8BYTE		= 0,
+	XMIT_SZ_16BYTE		= 1,
+	XMIT_SZ_32BYTE		= 2,
+};
+
+#define USBTS_INDEX2VAL(i) (((i) & 3) << 6)
+
+static const struct sh_dmae_channel sh7372_usb_dmae_channels[] = {
+	{
+		.offset = 0,
+	}, {
+		.offset = 0x20,
+	},
+};
+
+/* USB DMAC0 */
+static const struct sh_dmae_slave_config sh7372_usb_dmae0_slaves[] = {
+	{
+		.slave_id	= SHDMA_SLAVE_USB0_TX,
+		.chcr		= USBTS_INDEX2VAL(XMIT_SZ_8BYTE),
+	}, {
+		.slave_id	= SHDMA_SLAVE_USB0_RX,
+		.chcr		= USBTS_INDEX2VAL(XMIT_SZ_8BYTE),
+	},
+};
+
+static struct sh_dmae_pdata usb_dma0_platform_data = {
+	.slave		= sh7372_usb_dmae0_slaves,
+	.slave_num	= ARRAY_SIZE(sh7372_usb_dmae0_slaves),
+	.channel	= sh7372_usb_dmae_channels,
+	.channel_num	= ARRAY_SIZE(sh7372_usb_dmae_channels),
+	.ts_low_shift	= 6,
+	.ts_low_mask	= 0xc0,
+	.ts_high_shift	= 0,
+	.ts_high_mask	= 0,
+	.ts_shift	= usbts_shift,
+	.ts_shift_num	= ARRAY_SIZE(usbts_shift),
+	.dmaor_init	= DMAOR_DME,
+	.chcr_offset	= 0x14,
+	.chcr_ie_bit	= 1 << 5,
+	.dmaor_is_32bit	= 1,
+	.needs_tend_set	= 1,
+	.no_dmars	= 1,
+};
+
+static struct resource sh7372_usb_dmae0_resources[] = {
+	{
+		/* Channel registers and DMAOR */
+		.start	= 0xe68a0020,
+		.end	= 0xe68a0064 - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	{
+		/* VCR/SWR/DMICR */
+		.start	= 0xe68a0000,
+		.end	= 0xe68a0014 - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	{
+		/* IRQ for channels */
+		.start	= evt2irq(0x0a00),
+		.end	= evt2irq(0x0a00),
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device usb_dma0_device = {
+	.name		= "sh-dma-engine",
+	.id		= 3,
+	.resource	= sh7372_usb_dmae0_resources,
+	.num_resources	= ARRAY_SIZE(sh7372_usb_dmae0_resources),
+	.dev		= {
+		.platform_data	= &usb_dma0_platform_data,
+	},
+};
+
+/* USB DMAC1 */
+static const struct sh_dmae_slave_config sh7372_usb_dmae1_slaves[] = {
+	{
+		.slave_id	= SHDMA_SLAVE_USB1_TX,
+		.chcr		= USBTS_INDEX2VAL(XMIT_SZ_8BYTE),
+	}, {
+		.slave_id	= SHDMA_SLAVE_USB1_RX,
+		.chcr		= USBTS_INDEX2VAL(XMIT_SZ_8BYTE),
+	},
+};
+
+static struct sh_dmae_pdata usb_dma1_platform_data = {
+	.slave		= sh7372_usb_dmae1_slaves,
+	.slave_num	= ARRAY_SIZE(sh7372_usb_dmae1_slaves),
+	.channel	= sh7372_usb_dmae_channels,
+	.channel_num	= ARRAY_SIZE(sh7372_usb_dmae_channels),
+	.ts_low_shift	= 6,
+	.ts_low_mask	= 0xc0,
+	.ts_high_shift	= 0,
+	.ts_high_mask	= 0,
+	.ts_shift	= usbts_shift,
+	.ts_shift_num	= ARRAY_SIZE(usbts_shift),
+	.dmaor_init	= DMAOR_DME,
+	.chcr_offset	= 0x14,
+	.chcr_ie_bit	= 1 << 5,
+	.dmaor_is_32bit	= 1,
+	.needs_tend_set	= 1,
+	.no_dmars	= 1,
+};
+
+static struct resource sh7372_usb_dmae1_resources[] = {
+	{
+		/* Channel registers and DMAOR */
+		.start	= 0xe68c0020,
+		.end	= 0xe68c0064 - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	{
+		/* VCR/SWR/DMICR */
+		.start	= 0xe68c0000,
+		.end	= 0xe68c0014 - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	{
+		/* IRQ for channels */
+		.start	= evt2irq(0x1d00),
+		.end	= evt2irq(0x1d00),
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device usb_dma1_device = {
+	.name		= "sh-dma-engine",
+	.id		= 4,
+	.resource	= sh7372_usb_dmae1_resources,
+	.num_resources	= ARRAY_SIZE(sh7372_usb_dmae1_resources),
+	.dev		= {
+		.platform_data	= &usb_dma1_platform_data,
+	},
+};
+
 /* VPU */
 static struct uio_info vpu_platform_data = {
 	.name = "VPU5HG",
@@ -818,7 +962,7 @@
 	&scif4_device,
 	&scif5_device,
 	&scif6_device,
-	&cmt10_device,
+	&cmt2_device,
 	&tmu00_device,
 	&tmu01_device,
 };
@@ -829,6 +973,8 @@
 	&dma0_device,
 	&dma1_device,
 	&dma2_device,
+	&usb_dma0_device,
+	&usb_dma1_device,
 	&vpu_device,
 	&veu0_device,
 	&veu1_device,
diff --git a/arch/arm/mach-vexpress/v2m.c b/arch/arm/mach-vexpress/v2m.c
index 9e6b93b..d0d267a 100644
--- a/arch/arm/mach-vexpress/v2m.c
+++ b/arch/arm/mach-vexpress/v2m.c
@@ -318,6 +318,10 @@
 	.rate	= 1000000,
 };
 
+static struct clk v2m_ref_clk = {
+	.rate   = 32768,
+};
+
 static struct clk dummy_apb_pclk;
 
 static struct clk_lookup v2m_lookups[] = {
@@ -348,6 +352,9 @@
 	}, {	/* CLCD */
 		.dev_id		= "mb:clcd",
 		.clk		= &osc1_clk,
+	}, {	/* SP805 WDT */
+		.dev_id		= "mb:wdt",
+		.clk		= &v2m_ref_clk,
 	}, {	/* SP804 timers */
 		.dev_id		= "sp804",
 		.con_id		= "v2m-timer0",
diff --git a/arch/arm/mm/abort-macro.S b/arch/arm/mm/abort-macro.S
index 52162d5..2cbf68e 100644
--- a/arch/arm/mm/abort-macro.S
+++ b/arch/arm/mm/abort-macro.S
@@ -17,7 +17,7 @@
 	cmp	\tmp, # 0x5600			@ Is it ldrsb?
 	orreq	\tmp, \tmp, #1 << 11		@ Set L-bit if yes
 	tst	\tmp, #1 << 11			@ L = 0 -> write
-	orreq	\psr, \psr, #1 << 11		@ yes.
+	orreq	\fsr, \fsr, #1 << 11		@ yes.
 	b	do_DataAbort
 not_thumb:
 	.endm
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index be7c638..cfbcf8b 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -22,6 +22,7 @@
 #include <linux/sched.h>
 #include <linux/uaccess.h>
 
+#include <asm/system.h>
 #include <asm/unaligned.h>
 
 #include "fault.h"
@@ -95,6 +96,33 @@
 	"signal+warn"
 };
 
+/* Return true if and only if the ARMv6 unaligned access model is in use. */
+static bool cpu_is_v6_unaligned(void)
+{
+	return cpu_architecture() >= CPU_ARCH_ARMv6 && (cr_alignment & CR_U);
+}
+
+static int safe_usermode(int new_usermode, bool warn)
+{
+	/*
+	 * ARMv6 and later CPUs can perform unaligned accesses for
+	 * most single load and store instructions up to word size.
+	 * LDM, STM, LDRD and STRD still need to be handled.
+	 *
+	 * Ignoring the alignment fault is not an option on these
+	 * CPUs since we spin re-faulting the instruction without
+	 * making any progress.
+	 */
+	if (cpu_is_v6_unaligned() && !(new_usermode & (UM_FIXUP | UM_SIGNAL))) {
+		new_usermode |= UM_FIXUP;
+
+		if (warn)
+			printk(KERN_WARNING "alignment: ignoring faults is unsafe on this CPU.  Defaulting to fixup mode.\n");
+	}
+
+	return new_usermode;
+}
+
 static int alignment_proc_show(struct seq_file *m, void *v)
 {
 	seq_printf(m, "User:\t\t%lu\n", ai_user);
@@ -125,7 +153,7 @@
 		if (get_user(mode, buffer))
 			return -EFAULT;
 		if (mode >= '0' && mode <= '5')
-			ai_usermode = mode - '0';
+			ai_usermode = safe_usermode(mode - '0', true);
 	}
 	return count;
 }
@@ -886,9 +914,16 @@
 	if (ai_usermode & UM_FIXUP)
 		goto fixup;
 
-	if (ai_usermode & UM_SIGNAL)
-		force_sig(SIGBUS, current);
-	else {
+	if (ai_usermode & UM_SIGNAL) {
+		siginfo_t si;
+
+		si.si_signo = SIGBUS;
+		si.si_errno = 0;
+		si.si_code = BUS_ADRALN;
+		si.si_addr = (void __user *)addr;
+
+		force_sig_info(si.si_signo, &si, current);
+	} else {
 		/*
 		 * We're about to disable the alignment trap and return to
 		 * user space.  But if an interrupt occurs before actually
@@ -926,20 +961,11 @@
 		return -ENOMEM;
 #endif
 
-	/*
-	 * ARMv6 and later CPUs can perform unaligned accesses for
-	 * most single load and store instructions up to word size.
-	 * LDM, STM, LDRD and STRD still need to be handled.
-	 *
-	 * Ignoring the alignment fault is not an option on these
-	 * CPUs since we spin re-faulting the instruction without
-	 * making any progress.
-	 */
-	if (cpu_architecture() >= CPU_ARCH_ARMv6 && (cr_alignment & CR_U)) {
+	if (cpu_is_v6_unaligned()) {
 		cr_alignment &= ~CR_A;
 		cr_no_alignment &= ~CR_A;
 		set_cr(cr_alignment);
-		ai_usermode = UM_FIXUP;
+		ai_usermode = safe_usermode(ai_usermode, false);
 	}
 
 	hook_fault_code(1, do_alignment, SIGBUS, BUS_ADRALN,
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index 44c0867..9ecfdb5 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -277,6 +277,25 @@
 	spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 
+static void __init l2x0_unlock(__u32 cache_id)
+{
+	int lockregs;
+	int i;
+
+	if (cache_id == L2X0_CACHE_ID_PART_L310)
+		lockregs = 8;
+	else
+		/* L210 and unknown types */
+		lockregs = 1;
+
+	for (i = 0; i < lockregs; i++) {
+		writel_relaxed(0x0, l2x0_base + L2X0_LOCKDOWN_WAY_D_BASE +
+			       i * L2X0_LOCKDOWN_STRIDE);
+		writel_relaxed(0x0, l2x0_base + L2X0_LOCKDOWN_WAY_I_BASE +
+			       i * L2X0_LOCKDOWN_STRIDE);
+	}
+}
+
 void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask)
 {
 	__u32 aux;
@@ -328,6 +347,8 @@
 	 * accessing the below registers will fault.
 	 */
 	if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) {
+		/* Make sure that I&D is not locked down when starting */
+		l2x0_unlock(cache_id);
 
 		/* l2x0 controller is disabled */
 		writel_relaxed(aux, l2x0_base + L2X0_AUX_CTRL);
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 3b24bfa..07c4bc8 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -174,6 +174,10 @@
 	dcache_line_size r2, r3
 	sub	r3, r2, #1
 	bic	r12, r0, r3
+#ifdef CONFIG_ARM_ERRATA_764369
+	ALT_SMP(W(dsb))
+	ALT_UP(W(nop))
+#endif
 1:
  USER(	mcr	p15, 0, r12, c7, c11, 1	)	@ clean D line to the point of unification
 	add	r12, r12, r2
@@ -223,6 +227,10 @@
 	add	r1, r0, r1
 	sub	r3, r2, #1
 	bic	r0, r0, r3
+#ifdef CONFIG_ARM_ERRATA_764369
+	ALT_SMP(W(dsb))
+	ALT_UP(W(nop))
+#endif
 1:
 	mcr	p15, 0, r0, c7, c14, 1		@ clean & invalidate D line / unified line
 	add	r0, r0, r2
@@ -247,6 +255,10 @@
 	sub	r3, r2, #1
 	tst	r0, r3
 	bic	r0, r0, r3
+#ifdef CONFIG_ARM_ERRATA_764369
+	ALT_SMP(W(dsb))
+	ALT_UP(W(nop))
+#endif
 	mcrne	p15, 0, r0, c7, c14, 1		@ clean & invalidate D / U line
 
 	tst	r1, r3
@@ -270,6 +282,10 @@
 	dcache_line_size r2, r3
 	sub	r3, r2, #1
 	bic	r0, r0, r3
+#ifdef CONFIG_ARM_ERRATA_764369
+	ALT_SMP(W(dsb))
+	ALT_UP(W(nop))
+#endif
 1:
 	mcr	p15, 0, r0, c7, c10, 1		@ clean D / U line
 	add	r0, r0, r2
@@ -288,6 +304,10 @@
 	dcache_line_size r2, r3
 	sub	r3, r2, #1
 	bic	r0, r0, r3
+#ifdef CONFIG_ARM_ERRATA_764369
+	ALT_SMP(W(dsb))
+	ALT_UP(W(nop))
+#endif
 1:
 	mcr	p15, 0, r0, c7, c14, 1		@ clean & invalidate D / U line
 	add	r0, r0, r2
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 0a0a1e7..c3ff82f 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -324,6 +324,8 @@
 
 	if (addr)
 		*handle = pfn_to_dma(dev, page_to_pfn(page));
+	else
+		__dma_free_buffer(page, size);
 
 	return addr;
 }
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 2fee782..cc7e2d8 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -298,7 +298,7 @@
 #ifdef CONFIG_HAVE_ARCH_PFN_VALID
 int pfn_valid(unsigned long pfn)
 {
-	return memblock_is_memory(pfn << PAGE_SHIFT);
+	return memblock_is_memory(__pfn_to_phys(pfn));
 }
 EXPORT_SYMBOL(pfn_valid);
 #endif
@@ -441,7 +441,7 @@
 static inline void poison_init_mem(void *s, size_t count)
 {
 	u32 *p = (u32 *)s;
-	while ((count = count - 4))
+	for (; count != 0; count -= 4)
 		*p++ = 0xe7fddef0;
 }
 
diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S
index 92bd102..2e6849b 100644
--- a/arch/arm/mm/proc-arm920.S
+++ b/arch/arm/mm/proc-arm920.S
@@ -379,7 +379,7 @@
 
 /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */
 .globl	cpu_arm920_suspend_size
-.equ	cpu_arm920_suspend_size, 4 * 3
+.equ	cpu_arm920_suspend_size, 4 * 4
 #ifdef CONFIG_PM_SLEEP
 ENTRY(cpu_arm920_do_suspend)
 	stmfd	sp!, {r4 - r7, lr}
diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S
index 2bbcf05..cd8f79c 100644
--- a/arch/arm/mm/proc-arm926.S
+++ b/arch/arm/mm/proc-arm926.S
@@ -394,7 +394,7 @@
 
 /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */
 .globl	cpu_arm926_suspend_size
-.equ	cpu_arm926_suspend_size, 4 * 3
+.equ	cpu_arm926_suspend_size, 4 * 4
 #ifdef CONFIG_PM_SLEEP
 ENTRY(cpu_arm926_do_suspend)
 	stmfd	sp!, {r4 - r7, lr}
diff --git a/arch/arm/mm/proc-arm946.S b/arch/arm/mm/proc-arm946.S
index f8f7ea3..683af3a 100644
--- a/arch/arm/mm/proc-arm946.S
+++ b/arch/arm/mm/proc-arm946.S
@@ -410,6 +410,7 @@
 	.long	0x41009460
 	.long	0xff00fff0
 	.long	0
+	.long	0
 	b	__arm946_setup
 	.long	cpu_arch_name
 	.long	cpu_elf_name
@@ -418,6 +419,6 @@
 	.long	arm946_processor_functions
 	.long	0
 	.long	0
-	.long	arm940_cache_fns
+	.long	arm946_cache_fns
 	.size	__arm946_proc_info, . - __arm946_proc_info
 
diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S
index 07219c2..69e7f2e 100644
--- a/arch/arm/mm/proc-sa1100.S
+++ b/arch/arm/mm/proc-sa1100.S
@@ -182,11 +182,11 @@
 
 ENTRY(cpu_sa1100_do_resume)
 	ldmia	r0, {r4 - r7}			@ load cp regs
-	mov	r1, #0
-	mcr	p15, 0, r1, c8, c7, 0		@ flush I+D TLBs
-	mcr	p15, 0, r1, c7, c7, 0		@ flush I&D cache
-	mcr	p15, 0, r1, c9, c0, 0		@ invalidate RB
-	mcr	p15, 0, r1, c9, c0, 5		@ allow user space to use RB
+	mov	ip, #0
+	mcr	p15, 0, ip, c8, c7, 0		@ flush I+D TLBs
+	mcr	p15, 0, ip, c7, c7, 0		@ flush I&D cache
+	mcr	p15, 0, ip, c9, c0, 0		@ invalidate RB
+	mcr	p15, 0, ip, c9, c0, 5		@ allow user space to use RB
 
 	mcr	p15, 0, r4, c3, c0, 0		@ domain ID
 	mcr	p15, 0, r5, c2, c0, 0		@ translation table base addr
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index 219138d..a923aa0 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -223,6 +223,22 @@
 	mrc	p15, 0, r0, c1, c0, 0		@ read control register
 	bic	r0, r0, r5			@ clear bits them
 	orr	r0, r0, r6			@ set them
+#ifdef CONFIG_ARM_ERRATA_364296
+	/*
+	 * Workaround for the 364296 ARM1136 r0p2 erratum (possible cache data
+	 * corruption with hit-under-miss enabled). The conditional code below
+	 * (setting the undocumented bit 31 in the auxiliary control register
+	 * and the FI bit in the control register) disables hit-under-miss
+	 * without putting the processor into full low interrupt latency mode.
+	 */
+	ldr	r6, =0x4107b362			@ id for ARM1136 r0p2
+	mrc	p15, 0, r5, c0, c0, 0		@ get processor id
+	teq	r5, r6				@ check for the faulty core
+	mrceq	p15, 0, r5, c1, c0, 1		@ load aux control reg
+	orreq	r5, r5, #(1 << 31)		@ set the undocumented bit 31
+	mcreq	p15, 0, r5, c1, c0, 1		@ write aux control reg
+	orreq	r0, r0, #(1 << 21)		@ low interrupt latency configuration
+#endif
 	mov	pc, lr				@ return to head.S:__ret
 
 	/*
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index a30e785..9049c0764 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -66,6 +66,7 @@
 ENTRY(cpu_v7_reset)
 	mrc	p15, 0, r1, c1, c0, 0		@ ctrl register
 	bic	r1, r1, #0x1			@ ...............m
+ THUMB(	bic	r1, r1, #1 << 30 )		@ SCTLR.TE (Thumb exceptions)
 	mcr	p15, 0, r1, c1, c0, 0		@ disable MMU
 	isb
 	mov	pc, r0
@@ -247,13 +248,16 @@
 	mcr	p15, 0, r7, c2, c0, 0	@ TTB 0
 	mcr	p15, 0, r8, c2, c0, 1	@ TTB 1
 	mcr	p15, 0, ip, c2, c0, 2	@ TTB control register
-	mcr	p15, 0, r10, c1, c0, 1	@ Auxiliary control register
+	mrc	p15, 0, r4, c1, c0, 1	@ Read Auxiliary control register
+	teq	r4, r10			@ Is it already set?
+	mcrne	p15, 0, r10, c1, c0, 1	@ No, so write it
 	mcr	p15, 0, r11, c1, c0, 2	@ Co-processor access control
 	ldr	r4, =PRRR		@ PRRR
 	ldr	r5, =NMRR		@ NMRR
 	mcr	p15, 0, r4, c10, c2, 0	@ write PRRR
 	mcr	p15, 0, r5, c10, c2, 1	@ write NMRR
 	isb
+	dsb
 	mov	r0, r9			@ control register
 	mov	r2, r7, lsr #14		@ get TTB0 base
 	mov	r2, r2, lsl #14
diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S
index 28c72a2..755e1bf 100644
--- a/arch/arm/mm/proc-xsc3.S
+++ b/arch/arm/mm/proc-xsc3.S
@@ -406,7 +406,7 @@
 	.align
 
 .globl	cpu_xsc3_suspend_size
-.equ	cpu_xsc3_suspend_size, 4 * 8
+.equ	cpu_xsc3_suspend_size, 4 * 7
 #ifdef CONFIG_PM_SLEEP
 ENTRY(cpu_xsc3_do_suspend)
 	stmfd	sp!, {r4 - r10, lr}
@@ -418,12 +418,12 @@
 	mrc	p15, 0, r9, c1, c0, 1	@ auxiliary control reg
 	mrc 	p15, 0, r10, c1, c0, 0	@ control reg
 	bic	r4, r4, #2		@ clear frequency change bit
-	stmia	r0, {r1, r4 - r10}	@ store v:p offset + cp regs
+	stmia	r0, {r4 - r10}		@ store cp regs
 	ldmia	sp!, {r4 - r10, pc}
 ENDPROC(cpu_xsc3_do_suspend)
 
 ENTRY(cpu_xsc3_do_resume)
-	ldmia	r0, {r1, r4 - r10}	@ load v:p offset + cp regs
+	ldmia	r0, {r4 - r10}		@ load cp regs
 	mov	ip, #0
 	mcr	p15, 0, ip, c7, c7, 0	@ invalidate I & D caches, BTB
 	mcr	p15, 0, ip, c7, c10, 4	@ drain write (&fill) buffer
diff --git a/arch/arm/plat-mxc/include/mach/debug-macro.S b/arch/arm/plat-mxc/include/mach/debug-macro.S
index 91fc7cd..e4dde91 100644
--- a/arch/arm/plat-mxc/include/mach/debug-macro.S
+++ b/arch/arm/plat-mxc/include/mach/debug-macro.S
@@ -44,6 +44,14 @@
 #define UART_PADDR	MX51_UART1_BASE_ADDR
 #endif
 
+/* iMX50/53 have same addresses, but not iMX51 */
+#if defined(CONFIG_SOC_IMX50) || defined(CONFIG_SOC_IMX53)
+#ifdef UART_PADDR
+#error "CONFIG_DEBUG_LL is incompatible with multiple archs"
+#endif
+#define UART_PADDR	MX53_UART1_BASE_ADDR
+#endif
+
 #define UART_VADDR	IMX_IO_ADDRESS(UART_PADDR)
 
 		.macro	addruart, rp, rv
diff --git a/arch/arm/plat-mxc/include/mach/iomux-mx53.h b/arch/arm/plat-mxc/include/mach/iomux-mx53.h
index 9440b9e..5408fd1 100644
--- a/arch/arm/plat-mxc/include/mach/iomux-mx53.h
+++ b/arch/arm/plat-mxc/include/mach/iomux-mx53.h
@@ -30,6 +30,9 @@
 #define MX53_SDHC_PAD_CTRL 	(PAD_CTL_HYS | PAD_CTL_PKE | PAD_CTL_PUE | \
 				PAD_CTL_PUS_47K_UP | PAD_CTL_DSE_HIGH | \
 				PAD_CTL_SRE_FAST)
+#define PAD_CTRL_I2C	(PAD_CTL_SRE_FAST | PAD_CTL_ODE | PAD_CTL_PKE | \
+			PAD_CTL_PUE | PAD_CTL_DSE_HIGH | PAD_CTL_PUS_100K_UP \
+			| PAD_CTL_HYS)
 
 #define _MX53_PAD_GPIO_19__KPP_COL_5		IOMUX_PAD(0x348, 0x20, 0, 0x840, 0, 0)
 #define _MX53_PAD_GPIO_19__GPIO4_5		IOMUX_PAD(0x348, 0x20, 1, 0x0, 0, 0)
@@ -1256,7 +1259,7 @@
 #define MX53_PAD_KEY_COL3__GPIO4_12		(_MX53_PAD_KEY_COL3__GPIO4_12 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_KEY_COL3__USBOH3_H2_DP		(_MX53_PAD_KEY_COL3__USBOH3_H2_DP | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_KEY_COL3__SPDIF_IN1		(_MX53_PAD_KEY_COL3__SPDIF_IN1 | MUX_PAD_CTRL(NO_PAD_CTRL))
-#define MX53_PAD_KEY_COL3__I2C2_SCL		(_MX53_PAD_KEY_COL3__I2C2_SCL | MUX_PAD_CTRL(NO_PAD_CTRL))
+#define MX53_PAD_KEY_COL3__I2C2_SCL		(_MX53_PAD_KEY_COL3__I2C2_SCL | MUX_PAD_CTRL(PAD_CTRL_I2C))
 #define MX53_PAD_KEY_COL3__ECSPI1_SS3		(_MX53_PAD_KEY_COL3__ECSPI1_SS3 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_KEY_COL3__FEC_CRS		(_MX53_PAD_KEY_COL3__FEC_CRS | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_KEY_COL3__USBPHY1_SIECLOCK		(_MX53_PAD_KEY_COL3__USBPHY1_SIECLOCK | MUX_PAD_CTRL(NO_PAD_CTRL))
@@ -1264,7 +1267,7 @@
 #define MX53_PAD_KEY_ROW3__GPIO4_13		(_MX53_PAD_KEY_ROW3__GPIO4_13 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_KEY_ROW3__USBOH3_H2_DM		(_MX53_PAD_KEY_ROW3__USBOH3_H2_DM | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_KEY_ROW3__CCM_ASRC_EXT_CLK		(_MX53_PAD_KEY_ROW3__CCM_ASRC_EXT_CLK | MUX_PAD_CTRL(NO_PAD_CTRL))
-#define MX53_PAD_KEY_ROW3__I2C2_SDA		(_MX53_PAD_KEY_ROW3__I2C2_SDA | MUX_PAD_CTRL(NO_PAD_CTRL))
+#define MX53_PAD_KEY_ROW3__I2C2_SDA		(_MX53_PAD_KEY_ROW3__I2C2_SDA | MUX_PAD_CTRL(PAD_CTRL_I2C))
 #define MX53_PAD_KEY_ROW3__OSC32K_32K_OUT		(_MX53_PAD_KEY_ROW3__OSC32K_32K_OUT | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_KEY_ROW3__CCM_PLL4_BYP		(_MX53_PAD_KEY_ROW3__CCM_PLL4_BYP | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_KEY_ROW3__USBPHY1_LINESTATE_0		(_MX53_PAD_KEY_ROW3__USBPHY1_LINESTATE_0 | MUX_PAD_CTRL(NO_PAD_CTRL))
@@ -1536,7 +1539,7 @@
 #define MX53_PAD_CSI0_DAT8__KPP_COL_7		(_MX53_PAD_CSI0_DAT8__KPP_COL_7 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_CSI0_DAT8__ECSPI2_SCLK		(_MX53_PAD_CSI0_DAT8__ECSPI2_SCLK | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_CSI0_DAT8__USBOH3_USBH3_OC		(_MX53_PAD_CSI0_DAT8__USBOH3_USBH3_OC | MUX_PAD_CTRL(NO_PAD_CTRL))
-#define MX53_PAD_CSI0_DAT8__I2C1_SDA		(_MX53_PAD_CSI0_DAT8__I2C1_SDA | MUX_PAD_CTRL(NO_PAD_CTRL))
+#define MX53_PAD_CSI0_DAT8__I2C1_SDA		(_MX53_PAD_CSI0_DAT8__I2C1_SDA | MUX_PAD_CTRL(PAD_CTRL_I2C))
 #define MX53_PAD_CSI0_DAT8__EMI_EMI_DEBUG_37		(_MX53_PAD_CSI0_DAT8__EMI_EMI_DEBUG_37 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_CSI0_DAT8__TPIU_TRACE_5		(_MX53_PAD_CSI0_DAT8__TPIU_TRACE_5 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_CSI0_DAT9__IPU_CSI0_D_9		(_MX53_PAD_CSI0_DAT9__IPU_CSI0_D_9 | MUX_PAD_CTRL(NO_PAD_CTRL))
@@ -1544,7 +1547,7 @@
 #define MX53_PAD_CSI0_DAT9__KPP_ROW_7		(_MX53_PAD_CSI0_DAT9__KPP_ROW_7 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_CSI0_DAT9__ECSPI2_MOSI		(_MX53_PAD_CSI0_DAT9__ECSPI2_MOSI | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_CSI0_DAT9__USBOH3_USBH3_PWR		(_MX53_PAD_CSI0_DAT9__USBOH3_USBH3_PWR | MUX_PAD_CTRL(NO_PAD_CTRL))
-#define MX53_PAD_CSI0_DAT9__I2C1_SCL		(_MX53_PAD_CSI0_DAT9__I2C1_SCL | MUX_PAD_CTRL(NO_PAD_CTRL))
+#define MX53_PAD_CSI0_DAT9__I2C1_SCL		(_MX53_PAD_CSI0_DAT9__I2C1_SCL | MUX_PAD_CTRL(PAD_CTRL_I2C))
 #define MX53_PAD_CSI0_DAT9__EMI_EMI_DEBUG_38		(_MX53_PAD_CSI0_DAT9__EMI_EMI_DEBUG_38 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_CSI0_DAT9__TPIU_TRACE_6		(_MX53_PAD_CSI0_DAT9__TPIU_TRACE_6 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_CSI0_DAT10__IPU_CSI0_D_10		(_MX53_PAD_CSI0_DAT10__IPU_CSI0_D_10 | MUX_PAD_CTRL(NO_PAD_CTRL))
@@ -1631,25 +1634,25 @@
 #define MX53_PAD_EIM_EB2__CCM_DI1_EXT_CLK		(_MX53_PAD_EIM_EB2__CCM_DI1_EXT_CLK | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_EB2__IPU_SER_DISP1_CS		(_MX53_PAD_EIM_EB2__IPU_SER_DISP1_CS | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_EB2__ECSPI1_SS0		(_MX53_PAD_EIM_EB2__ECSPI1_SS0 | MUX_PAD_CTRL(NO_PAD_CTRL))
-#define MX53_PAD_EIM_EB2__I2C2_SCL		(_MX53_PAD_EIM_EB2__I2C2_SCL | MUX_PAD_CTRL(NO_PAD_CTRL))
+#define MX53_PAD_EIM_EB2__I2C2_SCL		(_MX53_PAD_EIM_EB2__I2C2_SCL | MUX_PAD_CTRL(PAD_CTRL_I2C))
 #define MX53_PAD_EIM_D16__EMI_WEIM_D_16		(_MX53_PAD_EIM_D16__EMI_WEIM_D_16 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D16__GPIO3_16		(_MX53_PAD_EIM_D16__GPIO3_16 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D16__IPU_DI0_PIN5		(_MX53_PAD_EIM_D16__IPU_DI0_PIN5 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D16__IPU_DISPB1_SER_CLK		(_MX53_PAD_EIM_D16__IPU_DISPB1_SER_CLK | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D16__ECSPI1_SCLK		(_MX53_PAD_EIM_D16__ECSPI1_SCLK | MUX_PAD_CTRL(NO_PAD_CTRL))
-#define MX53_PAD_EIM_D16__I2C2_SDA		(_MX53_PAD_EIM_D16__I2C2_SDA | MUX_PAD_CTRL(NO_PAD_CTRL))
+#define MX53_PAD_EIM_D16__I2C2_SDA		(_MX53_PAD_EIM_D16__I2C2_SDA | MUX_PAD_CTRL(PAD_CTRL_I2C))
 #define MX53_PAD_EIM_D17__EMI_WEIM_D_17		(_MX53_PAD_EIM_D17__EMI_WEIM_D_17 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D17__GPIO3_17		(_MX53_PAD_EIM_D17__GPIO3_17 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D17__IPU_DI0_PIN6		(_MX53_PAD_EIM_D17__IPU_DI0_PIN6 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D17__IPU_DISPB1_SER_DIN		(_MX53_PAD_EIM_D17__IPU_DISPB1_SER_DIN | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D17__ECSPI1_MISO		(_MX53_PAD_EIM_D17__ECSPI1_MISO | MUX_PAD_CTRL(NO_PAD_CTRL))
-#define MX53_PAD_EIM_D17__I2C3_SCL		(_MX53_PAD_EIM_D17__I2C3_SCL | MUX_PAD_CTRL(NO_PAD_CTRL))
+#define MX53_PAD_EIM_D17__I2C3_SCL		(_MX53_PAD_EIM_D17__I2C3_SCL | MUX_PAD_CTRL(PAD_CTRL_I2C))
 #define MX53_PAD_EIM_D18__EMI_WEIM_D_18		(_MX53_PAD_EIM_D18__EMI_WEIM_D_18 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D18__GPIO3_18		(_MX53_PAD_EIM_D18__GPIO3_18 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D18__IPU_DI0_PIN7		(_MX53_PAD_EIM_D18__IPU_DI0_PIN7 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D18__IPU_DISPB1_SER_DIO		(_MX53_PAD_EIM_D18__IPU_DISPB1_SER_DIO | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D18__ECSPI1_MOSI		(_MX53_PAD_EIM_D18__ECSPI1_MOSI | MUX_PAD_CTRL(NO_PAD_CTRL))
-#define MX53_PAD_EIM_D18__I2C3_SDA		(_MX53_PAD_EIM_D18__I2C3_SDA | MUX_PAD_CTRL(NO_PAD_CTRL))
+#define MX53_PAD_EIM_D18__I2C3_SDA		(_MX53_PAD_EIM_D18__I2C3_SDA | MUX_PAD_CTRL(PAD_CTRL_I2C))
 #define MX53_PAD_EIM_D18__IPU_DI1_D0_CS		(_MX53_PAD_EIM_D18__IPU_DI1_D0_CS | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D19__EMI_WEIM_D_19		(_MX53_PAD_EIM_D19__EMI_WEIM_D_19 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D19__GPIO3_19		(_MX53_PAD_EIM_D19__GPIO3_19 | MUX_PAD_CTRL(NO_PAD_CTRL))
@@ -1672,7 +1675,7 @@
 #define MX53_PAD_EIM_D21__IPU_DI0_PIN17		(_MX53_PAD_EIM_D21__IPU_DI0_PIN17 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D21__IPU_DISPB0_SER_CLK		(_MX53_PAD_EIM_D21__IPU_DISPB0_SER_CLK | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D21__CSPI_SCLK		(_MX53_PAD_EIM_D21__CSPI_SCLK | MUX_PAD_CTRL(NO_PAD_CTRL))
-#define MX53_PAD_EIM_D21__I2C1_SCL		(_MX53_PAD_EIM_D21__I2C1_SCL | MUX_PAD_CTRL(NO_PAD_CTRL))
+#define MX53_PAD_EIM_D21__I2C1_SCL		(_MX53_PAD_EIM_D21__I2C1_SCL | MUX_PAD_CTRL(PAD_CTRL_I2C))
 #define MX53_PAD_EIM_D21__USBOH3_USBOTG_OC		(_MX53_PAD_EIM_D21__USBOH3_USBOTG_OC | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D22__EMI_WEIM_D_22		(_MX53_PAD_EIM_D22__EMI_WEIM_D_22 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D22__GPIO3_22		(_MX53_PAD_EIM_D22__GPIO3_22 | MUX_PAD_CTRL(NO_PAD_CTRL))
@@ -1732,7 +1735,7 @@
 #define MX53_PAD_EIM_D28__UART2_CTS		(_MX53_PAD_EIM_D28__UART2_CTS | MUX_PAD_CTRL(MX53_UART_PAD_CTRL))
 #define MX53_PAD_EIM_D28__IPU_DISPB0_SER_DIO		(_MX53_PAD_EIM_D28__IPU_DISPB0_SER_DIO | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D28__CSPI_MOSI		(_MX53_PAD_EIM_D28__CSPI_MOSI | MUX_PAD_CTRL(NO_PAD_CTRL))
-#define MX53_PAD_EIM_D28__I2C1_SDA		(_MX53_PAD_EIM_D28__I2C1_SDA | MUX_PAD_CTRL(NO_PAD_CTRL))
+#define MX53_PAD_EIM_D28__I2C1_SDA		(_MX53_PAD_EIM_D28__I2C1_SDA | MUX_PAD_CTRL(PAD_CTRL_I2C))
 #define MX53_PAD_EIM_D28__IPU_EXT_TRIG		(_MX53_PAD_EIM_D28__IPU_EXT_TRIG | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D28__IPU_DI0_PIN13		(_MX53_PAD_EIM_D28__IPU_DI0_PIN13 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D29__EMI_WEIM_D_29		(_MX53_PAD_EIM_D29__EMI_WEIM_D_29 | MUX_PAD_CTRL(NO_PAD_CTRL))
@@ -2297,7 +2300,7 @@
 #define MX53_PAD_GPIO_9__SCC_FAIL_STATE		(_MX53_PAD_GPIO_9__SCC_FAIL_STATE | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_3__ESAI1_HCKR		(_MX53_PAD_GPIO_3__ESAI1_HCKR | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_3__GPIO1_3		(_MX53_PAD_GPIO_3__GPIO1_3 | MUX_PAD_CTRL(NO_PAD_CTRL))
-#define MX53_PAD_GPIO_3__I2C3_SCL		(_MX53_PAD_GPIO_3__I2C3_SCL | MUX_PAD_CTRL(NO_PAD_CTRL))
+#define MX53_PAD_GPIO_3__I2C3_SCL		(_MX53_PAD_GPIO_3__I2C3_SCL | MUX_PAD_CTRL(PAD_CTRL_I2C))
 #define MX53_PAD_GPIO_3__DPLLIP1_TOG_EN		(_MX53_PAD_GPIO_3__DPLLIP1_TOG_EN | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_3__CCM_CLKO2		(_MX53_PAD_GPIO_3__CCM_CLKO2 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_3__OBSERVE_MUX_OBSRV_INT_OUT0		(_MX53_PAD_GPIO_3__OBSERVE_MUX_OBSRV_INT_OUT0 | MUX_PAD_CTRL(NO_PAD_CTRL))
@@ -2305,7 +2308,7 @@
 #define MX53_PAD_GPIO_3__MLB_MLBCLK		(_MX53_PAD_GPIO_3__MLB_MLBCLK | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_6__ESAI1_SCKT		(_MX53_PAD_GPIO_6__ESAI1_SCKT | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_6__GPIO1_6		(_MX53_PAD_GPIO_6__GPIO1_6 | MUX_PAD_CTRL(NO_PAD_CTRL))
-#define MX53_PAD_GPIO_6__I2C3_SDA		(_MX53_PAD_GPIO_6__I2C3_SDA | MUX_PAD_CTRL(NO_PAD_CTRL))
+#define MX53_PAD_GPIO_6__I2C3_SDA		(_MX53_PAD_GPIO_6__I2C3_SDA | MUX_PAD_CTRL(PAD_CTRL_I2C))
 #define MX53_PAD_GPIO_6__CCM_CCM_OUT_0		(_MX53_PAD_GPIO_6__CCM_CCM_OUT_0 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_6__CSU_CSU_INT_DEB		(_MX53_PAD_GPIO_6__CSU_CSU_INT_DEB | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_6__OBSERVE_MUX_OBSRV_INT_OUT1		(_MX53_PAD_GPIO_6__OBSERVE_MUX_OBSRV_INT_OUT1 | MUX_PAD_CTRL(NO_PAD_CTRL))
@@ -2333,7 +2336,7 @@
 #define MX53_PAD_GPIO_5__CCM_CLKO		(_MX53_PAD_GPIO_5__CCM_CLKO | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_5__CSU_CSU_ALARM_AUT_2		(_MX53_PAD_GPIO_5__CSU_CSU_ALARM_AUT_2 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_5__OBSERVE_MUX_OBSRV_INT_OUT4		(_MX53_PAD_GPIO_5__OBSERVE_MUX_OBSRV_INT_OUT4 | MUX_PAD_CTRL(NO_PAD_CTRL))
-#define MX53_PAD_GPIO_5__I2C3_SCL		(_MX53_PAD_GPIO_5__I2C3_SCL | MUX_PAD_CTRL(NO_PAD_CTRL))
+#define MX53_PAD_GPIO_5__I2C3_SCL		(_MX53_PAD_GPIO_5__I2C3_SCL | MUX_PAD_CTRL(PAD_CTRL_I2C))
 #define MX53_PAD_GPIO_5__CCM_PLL1_BYP		(_MX53_PAD_GPIO_5__CCM_PLL1_BYP | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_7__ESAI1_TX4_RX1		(_MX53_PAD_GPIO_7__ESAI1_TX4_RX1 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_7__GPIO1_7		(_MX53_PAD_GPIO_7__GPIO1_7 | MUX_PAD_CTRL(NO_PAD_CTRL))
@@ -2356,7 +2359,7 @@
 #define MX53_PAD_GPIO_16__TZIC_PWRFAIL_INT		(_MX53_PAD_GPIO_16__TZIC_PWRFAIL_INT | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_16__RTC_CE_RTC_EXT_TRIG1		(_MX53_PAD_GPIO_16__RTC_CE_RTC_EXT_TRIG1 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_16__SPDIF_IN1		(_MX53_PAD_GPIO_16__SPDIF_IN1 | MUX_PAD_CTRL(NO_PAD_CTRL))
-#define MX53_PAD_GPIO_16__I2C3_SDA		(_MX53_PAD_GPIO_16__I2C3_SDA | MUX_PAD_CTRL(NO_PAD_CTRL))
+#define MX53_PAD_GPIO_16__I2C3_SDA		(_MX53_PAD_GPIO_16__I2C3_SDA | MUX_PAD_CTRL(PAD_CTRL_I2C))
 #define MX53_PAD_GPIO_16__SJC_DE_B		(_MX53_PAD_GPIO_16__SJC_DE_B | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_17__ESAI1_TX0		(_MX53_PAD_GPIO_17__ESAI1_TX0 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_17__GPIO7_12		(_MX53_PAD_GPIO_17__GPIO7_12 | MUX_PAD_CTRL(NO_PAD_CTRL))
diff --git a/arch/arm/plat-omap/Kconfig b/arch/arm/plat-omap/Kconfig
index 6e6735f..bb8f4a6 100644
--- a/arch/arm/plat-omap/Kconfig
+++ b/arch/arm/plat-omap/Kconfig
@@ -13,6 +13,7 @@
 	bool "TI OMAP1"
 	select CLKDEV_LOOKUP
 	select CLKSRC_MMIO
+	select GENERIC_IRQ_CHIP
 	help
 	  "Systems based on omap7xx, omap15xx or omap16xx"
 
diff --git a/arch/arm/plat-omap/include/plat/dma.h b/arch/arm/plat-omap/include/plat/dma.h
index d1c916f..dc562a5 100644
--- a/arch/arm/plat-omap/include/plat/dma.h
+++ b/arch/arm/plat-omap/include/plat/dma.h
@@ -195,6 +195,11 @@
 
 #define OMAP36XX_DMA_UART4_TX		81	/* S_DMA_80 */
 #define OMAP36XX_DMA_UART4_RX		82	/* S_DMA_81 */
+
+/* Only for AM35xx */
+#define AM35XX_DMA_UART4_TX		54
+#define AM35XX_DMA_UART4_RX		55
+
 /*----------------------------------------------------------------------------*/
 
 #define OMAP1_DMA_TOUT_IRQ		(1 << 0)
diff --git a/arch/arm/plat-omap/include/plat/irqs.h b/arch/arm/plat-omap/include/plat/irqs.h
index 926d25c..30e1071 100644
--- a/arch/arm/plat-omap/include/plat/irqs.h
+++ b/arch/arm/plat-omap/include/plat/irqs.h
@@ -357,6 +357,7 @@
 #define INT_35XX_EMAC_C0_TX_PULSE_IRQ	69
 #define INT_35XX_EMAC_C0_MISC_PULSE_IRQ	70
 #define INT_35XX_USBOTG_IRQ		71
+#define INT_35XX_UART4			84
 #define INT_35XX_CCDC_VD0_IRQ		88
 #define INT_35XX_CCDC_VD1_IRQ		92
 #define INT_35XX_CCDC_VD2_IRQ		93
diff --git a/arch/arm/plat-omap/include/plat/serial.h b/arch/arm/plat-omap/include/plat/serial.h
index 2723f91..de3b10c 100644
--- a/arch/arm/plat-omap/include/plat/serial.h
+++ b/arch/arm/plat-omap/include/plat/serial.h
@@ -56,6 +56,9 @@
 #define TI816X_UART2_BASE	0x48022000
 #define TI816X_UART3_BASE	0x48024000
 
+/* AM3505/3517 UART4 */
+#define AM35XX_UART4_BASE	0x4809E000	/* Only on AM3505/3517 */
+
 /* External port on Zoom2/3 */
 #define ZOOM_UART_BASE		0x10000000
 #define ZOOM_UART_VIRT		0xfa400000
diff --git a/arch/arm/plat-omap/iovmm.c b/arch/arm/plat-omap/iovmm.c
index c60737c..79e7fed 100644
--- a/arch/arm/plat-omap/iovmm.c
+++ b/arch/arm/plat-omap/iovmm.c
@@ -423,9 +423,6 @@
 {
 	unsigned int i;
 	struct scatterlist *sg;
-	void *va;
-
-	va = phys_to_virt(pa);
 
 	for_each_sg(sgt->sgl, sg, sgt->nents, i) {
 		unsigned bytes;
diff --git a/arch/arm/plat-omap/omap_device.c b/arch/arm/plat-omap/omap_device.c
index b6b4097..02609ee 100644
--- a/arch/arm/plat-omap/omap_device.c
+++ b/arch/arm/plat-omap/omap_device.c
@@ -615,6 +615,9 @@
 
 	return pm_generic_resume_noirq(dev);
 }
+#else
+#define _od_suspend_noirq NULL
+#define _od_resume_noirq NULL
 #endif
 
 static struct dev_pm_domain omap_device_pm_domain = {
@@ -622,7 +625,8 @@
 		SET_RUNTIME_PM_OPS(_od_runtime_suspend, _od_runtime_resume,
 				   _od_runtime_idle)
 		USE_PLATFORM_PM_SLEEP_OPS
-		SET_SYSTEM_SLEEP_PM_OPS(_od_suspend_noirq, _od_resume_noirq)
+		.suspend_noirq = _od_suspend_noirq,
+		.resume_noirq = _od_resume_noirq,
 	}
 };
 
diff --git a/arch/arm/plat-s5p/clock.c b/arch/arm/plat-s5p/clock.c
index 02af235..5f84a3f 100644
--- a/arch/arm/plat-s5p/clock.c
+++ b/arch/arm/plat-s5p/clock.c
@@ -192,7 +192,7 @@
 	if (IS_ERR(pclk))
 		return -EINVAL;
 
-	rate = pclk->ops->get_rate(clk);
+	rate = pclk->ops->get_rate(pclk);
 	clk_put(pclk);
 
 	return rate;
diff --git a/arch/arm/plat-s5p/irq-gpioint.c b/arch/arm/plat-s5p/irq-gpioint.c
index 327ab9f..f88216d 100644
--- a/arch/arm/plat-s5p/irq-gpioint.c
+++ b/arch/arm/plat-s5p/irq-gpioint.c
@@ -23,6 +23,8 @@
 #include <plat/gpio-core.h>
 #include <plat/gpio-cfg.h>
 
+#include <asm/mach/irq.h>
+
 #define GPIO_BASE(chip)		(((unsigned long)(chip)->base) & 0xFFFFF000u)
 
 #define CON_OFFSET		0x700
@@ -81,6 +83,9 @@
 	int group, pend_offset, mask_offset;
 	unsigned int pend, mask;
 
+	struct irq_chip *chip = irq_get_chip(irq);
+	chained_irq_enter(chip, desc);
+
 	for (group = 0; group < bank->nr_groups; group++) {
 		struct s3c_gpio_chip *chip = bank->chips[group];
 		if (!chip)
@@ -102,23 +107,25 @@
 			pend &= ~BIT(offset);
 		}
 	}
+	chained_irq_exit(chip, desc);
 }
 
 static __init int s5p_gpioint_add(struct s3c_gpio_chip *chip)
 {
 	static int used_gpioint_groups = 0;
 	int group = chip->group;
-	struct s5p_gpioint_bank *bank = NULL;
+	struct s5p_gpioint_bank *b, *bank = NULL;
 	struct irq_chip_generic *gc;
 	struct irq_chip_type *ct;
 
 	if (used_gpioint_groups >= S5P_GPIOINT_GROUP_COUNT)
 		return -ENOMEM;
 
-	list_for_each_entry(bank, &banks, list) {
-		if (group >= bank->start &&
-		    group < bank->start + bank->nr_groups)
+	list_for_each_entry(b, &banks, list) {
+		if (group >= b->start && group < b->start + b->nr_groups) {
+			bank = b;
 			break;
+		}
 	}
 	if (!bank)
 		return -EINVAL;
diff --git a/arch/arm/plat-samsung/clock.c b/arch/arm/plat-samsung/clock.c
index 302c426..3b44519 100644
--- a/arch/arm/plat-samsung/clock.c
+++ b/arch/arm/plat-samsung/clock.c
@@ -64,6 +64,17 @@
  */
 DEFINE_SPINLOCK(clocks_lock);
 
+/* Global watchdog clock used by arch_wtd_reset() callback */
+struct clk *s3c2410_wdtclk;
+static int __init s3c_wdt_reset_init(void)
+{
+	s3c2410_wdtclk = clk_get(NULL, "watchdog");
+	if (IS_ERR(s3c2410_wdtclk))
+		printk(KERN_WARNING "%s: warning: cannot get watchdog clock\n", __func__);
+	return 0;
+}
+arch_initcall(s3c_wdt_reset_init);
+
 /* enable and disable calls for use with the clk struct */
 
 static int clk_null_enable(struct clk *clk, int enable)
diff --git a/arch/arm/plat-samsung/include/plat/backlight.h b/arch/arm/plat-samsung/include/plat/backlight.h
index 51d8da8..ad530c7 100644
--- a/arch/arm/plat-samsung/include/plat/backlight.h
+++ b/arch/arm/plat-samsung/include/plat/backlight.h
@@ -20,7 +20,7 @@
 	int func;
 };
 
-extern void samsung_bl_set(struct samsung_bl_gpio_info *gpio_info,
+extern void __init samsung_bl_set(struct samsung_bl_gpio_info *gpio_info,
 	struct platform_pwm_backlight_data *bl_data);
 
 #endif /* __ASM_PLAT_BACKLIGHT_H */
diff --git a/arch/arm/plat-samsung/include/plat/clock.h b/arch/arm/plat-samsung/include/plat/clock.h
index 87d5b38..73c66d4 100644
--- a/arch/arm/plat-samsung/include/plat/clock.h
+++ b/arch/arm/plat-samsung/include/plat/clock.h
@@ -9,6 +9,9 @@
  * published by the Free Software Foundation.
 */
 
+#ifndef __ASM_PLAT_CLOCK_H
+#define __ASM_PLAT_CLOCK_H __FILE__
+
 #include <linux/spinlock.h>
 #include <linux/clkdev.h>
 
@@ -121,3 +124,8 @@
 
 extern void s3c_pwmclk_init(void);
 
+/* Global watchdog clock used by arch_wtd_reset() callback */
+
+extern struct clk *s3c2410_wdtclk;
+
+#endif /* __ASM_PLAT_CLOCK_H */
diff --git a/arch/arm/plat-samsung/include/plat/watchdog-reset.h b/arch/arm/plat-samsung/include/plat/watchdog-reset.h
index 54b762a..40dbb2b 100644
--- a/arch/arm/plat-samsung/include/plat/watchdog-reset.h
+++ b/arch/arm/plat-samsung/include/plat/watchdog-reset.h
@@ -10,6 +10,7 @@
  * published by the Free Software Foundation.
 */
 
+#include <plat/clock.h>
 #include <plat/regs-watchdog.h>
 #include <mach/map.h>
 
@@ -19,17 +20,12 @@
 
 static inline void arch_wdt_reset(void)
 {
-	struct clk *wdtclk;
-
 	printk("arch_reset: attempting watchdog reset\n");
 
 	__raw_writel(0, S3C2410_WTCON);	  /* disable watchdog, to be safe  */
 
-	wdtclk = clk_get(NULL, "watchdog");
-	if (!IS_ERR(wdtclk)) {
-		clk_enable(wdtclk);
-	} else
-		printk(KERN_WARNING "%s: warning: cannot get watchdog clock\n", __func__);
+	if (s3c2410_wdtclk)
+		clk_enable(s3c2410_wdtclk);
 
 	/* put initial values into count and data */
 	__raw_writel(0x80, S3C2410_WTCNT);
diff --git a/arch/arm/plat-samsung/irq-vic-timer.c b/arch/arm/plat-samsung/irq-vic-timer.c
index f714d06..51583cd 100644
--- a/arch/arm/plat-samsung/irq-vic-timer.c
+++ b/arch/arm/plat-samsung/irq-vic-timer.c
@@ -22,9 +22,14 @@
 #include <plat/irq-vic-timer.h>
 #include <plat/regs-timer.h>
 
+#include <asm/mach/irq.h>
+
 static void s3c_irq_demux_vic_timer(unsigned int irq, struct irq_desc *desc)
 {
+	struct irq_chip *chip = irq_get_chip(irq);
+	chained_irq_enter(chip, desc);
 	generic_handle_irq((int)desc->irq_data.handler_data);
+	chained_irq_exit(chip, desc);
 }
 
 /* We assume the IRQ_TIMER0..IRQ_TIMER4 range is continuous. */
diff --git a/arch/arm/tools/mach-types b/arch/arm/tools/mach-types
index 3b3776d..62cc8f9 100644
--- a/arch/arm/tools/mach-types
+++ b/arch/arm/tools/mach-types
@@ -351,7 +351,7 @@
 nokia_rx51		MACH_NOKIA_RX51		NOKIA_RX51		1955
 omap_zoom2		MACH_OMAP_ZOOM2		OMAP_ZOOM2		1967
 cpuat9260		MACH_CPUAT9260		CPUAT9260		1973
-eukrea_cpuimx27		MACH_CPUIMX27		CPUIMX27		1975
+eukrea_cpuimx27		MACH_EUKREA_CPUIMX27	EUKREA_CPUIMX27		1975
 acs5k			MACH_ACS5K		ACS5K			1982
 snapper_9260		MACH_SNAPPER_9260	SNAPPER_9260		1987
 dsm320			MACH_DSM320		DSM320			1988
@@ -476,8 +476,8 @@
 omap4_panda		MACH_OMAP4_PANDA	OMAP4_PANDA		2791
 ti8168evm		MACH_TI8168EVM		TI8168EVM		2800
 teton_bga		MACH_TETON_BGA		TETON_BGA		2816
-eukrea_cpuimx25sd	MACH_EUKREA_CPUIMX25	EUKREA_CPUIMX25		2820
-eukrea_cpuimx35sd	MACH_EUKREA_CPUIMX35	EUKREA_CPUIMX35		2821
+eukrea_cpuimx25sd	MACH_EUKREA_CPUIMX25SD	EUKREA_CPUIMX25SD	2820
+eukrea_cpuimx35sd	MACH_EUKREA_CPUIMX35SD	EUKREA_CPUIMX35SD	2821
 eukrea_cpuimx51sd	MACH_EUKREA_CPUIMX51SD	EUKREA_CPUIMX51SD	2822
 eukrea_cpuimx51		MACH_EUKREA_CPUIMX51	EUKREA_CPUIMX51		2823
 smdkc210		MACH_SMDKC210		SMDKC210		2838
@@ -910,7 +910,7 @@
 uemd			MACH_UEMD		UEMD			3281
 ccwmx51mut		MACH_CCWMX51MUT		CCWMX51MUT		3282
 rockhopper		MACH_ROCKHOPPER		ROCKHOPPER		3283
-nookcolor		MACH_NOOKCOLOR		NOOKCOLOR		3284
+encore			MACH_ENCORE		ENCORE			3284
 hkdkc100		MACH_HKDKC100		HKDKC100		3285
 ts42xx			MACH_TS42XX		TS42XX			3286
 aebl			MACH_AEBL		AEBL			3287
diff --git a/arch/avr32/kernel/syscall_table.S b/arch/avr32/kernel/syscall_table.S
index c7fd394..6eba535 100644
--- a/arch/avr32/kernel/syscall_table.S
+++ b/arch/avr32/kernel/syscall_table.S
@@ -158,7 +158,7 @@
 	.long	sys_sched_rr_get_interval
 	.long	sys_nanosleep
 	.long	sys_poll
-	.long	sys_nfsservctl		/* 145 */
+	.long	sys_ni_syscall		/* 145 was nfsservctl */
 	.long	sys_setresgid
 	.long	sys_getresgid
 	.long	sys_prctl
diff --git a/arch/blackfin/mach-common/entry.S b/arch/blackfin/mach-common/entry.S
index 225d311..e413729 100644
--- a/arch/blackfin/mach-common/entry.S
+++ b/arch/blackfin/mach-common/entry.S
@@ -1543,7 +1543,7 @@
 	.long _sys_ni_syscall	/* for vm86 */
 	.long _sys_ni_syscall	/* old "query_module" */
 	.long _sys_ni_syscall	/* sys_poll */
-	.long _sys_nfsservctl
+	.long _sys_ni_syscall   /* old nfsservctl */
 	.long _sys_setresgid	/* setresgid16 */	/* 170 */
 	.long _sys_getresgid	/* getresgid16 */
 	.long _sys_prctl
diff --git a/arch/cris/arch-v10/kernel/entry.S b/arch/cris/arch-v10/kernel/entry.S
index 1161883..592fbe9 100644
--- a/arch/cris/arch-v10/kernel/entry.S
+++ b/arch/cris/arch-v10/kernel/entry.S
@@ -771,7 +771,7 @@
 	.long sys_ni_syscall	/* sys_vm86 */
 	.long sys_ni_syscall	/* Old sys_query_module */
 	.long sys_poll
-	.long sys_nfsservctl
+	.long sys_ni_syscall    /* old nfsservctl */
 	.long sys_setresgid16	/* 170 */
 	.long sys_getresgid16
 	.long sys_prctl
diff --git a/arch/cris/arch-v32/kernel/entry.S b/arch/cris/arch-v32/kernel/entry.S
index 84fed7e..c3ea4694 100644
--- a/arch/cris/arch-v32/kernel/entry.S
+++ b/arch/cris/arch-v32/kernel/entry.S
@@ -714,7 +714,7 @@
 	.long sys_ni_syscall	/* sys_vm86 */
 	.long sys_ni_syscall	/* Old sys_query_module */
 	.long sys_poll
-	.long sys_nfsservctl
+	.long sys_ni_syscall	/* Old nfsservctl */
 	.long sys_setresgid16	/* 170 */
 	.long sys_getresgid16
 	.long sys_prctl
diff --git a/arch/cris/include/asm/serial.h b/arch/cris/include/asm/serial.h
new file mode 100644
index 0000000..af7535a
--- /dev/null
+++ b/arch/cris/include/asm/serial.h
@@ -0,0 +1,9 @@
+#ifndef _ASM_SERIAL_H
+#define _ASM_SERIAL_H
+
+/*
+ * This assumes you have a 1.8432 MHz clock for your UART.
+ */
+#define BASE_BAUD (1843200 / 16)
+
+#endif /* _ASM_SERIAL_H */
diff --git a/arch/frv/kernel/entry.S b/arch/frv/kernel/entry.S
index 017d6d7..5ba23f7 100644
--- a/arch/frv/kernel/entry.S
+++ b/arch/frv/kernel/entry.S
@@ -1358,7 +1358,7 @@
 	.long sys_ni_syscall	/* for vm86 */
 	.long sys_ni_syscall	/* Old sys_query_module */
 	.long sys_poll
-	.long sys_nfsservctl
+	.long sys_ni_syscall	/* Old nfsservctl */
 	.long sys_setresgid16	/* 170 */
 	.long sys_getresgid16
 	.long sys_prctl
diff --git a/arch/h8300/kernel/syscalls.S b/arch/h8300/kernel/syscalls.S
index f4b2e67..4be2ea2 100644
--- a/arch/h8300/kernel/syscalls.S
+++ b/arch/h8300/kernel/syscalls.S
@@ -183,7 +183,7 @@
 	.long SYMBOL_NAME(sys_ni_syscall)	/* for vm86 */
 	.long SYMBOL_NAME(sys_ni_syscall)	/* sys_query_module */
 	.long SYMBOL_NAME(sys_poll)
-	.long SYMBOL_NAME(sys_nfsservctl)
+	.long SYMBOL_NAME(sys_ni_syscall)	/* old nfsservctl */
 	.long SYMBOL_NAME(sys_setresgid16)	/* 170 */
 	.long SYMBOL_NAME(sys_getresgid16)
 	.long SYMBOL_NAME(sys_prctl)
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 1248547..3ff7785 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -162,7 +162,6 @@
 	select ACPI_NUMA
 	select SWIOTLB
 	select PCI_MSI
-	select DMAR
 	help
 	  This selects the system type of your hardware.  A "generic" kernel
 	  will run on any supported IA-64 system.  However, if you configure
diff --git a/arch/ia64/configs/generic_defconfig b/arch/ia64/configs/generic_defconfig
index 1d7bca0..0e5cd14 100644
--- a/arch/ia64/configs/generic_defconfig
+++ b/arch/ia64/configs/generic_defconfig
@@ -234,3 +234,4 @@
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRC_T10DIF=y
 CONFIG_MISC_DEVICES=y
+CONFIG_DMAR=y
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index 97dd2ab..198c753 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -1614,7 +1614,7 @@
 	data8 sys_sched_get_priority_min
 	data8 sys_sched_rr_get_interval
 	data8 sys_nanosleep
-	data8 sys_nfsservctl
+	data8 sys_ni_syscall			// old nfsservctl
 	data8 sys_prctl				// 1170
 	data8 sys_getpagesize
 	data8 sys_mmap2
diff --git a/arch/m32r/kernel/syscall_table.S b/arch/m32r/kernel/syscall_table.S
index 528f2e6..f365c19 100644
--- a/arch/m32r/kernel/syscall_table.S
+++ b/arch/m32r/kernel/syscall_table.S
@@ -168,7 +168,7 @@
 	.long sys_tas			/* vm86 syscall holder */
 	.long sys_ni_syscall		/* query_module syscall holder */
 	.long sys_poll
-	.long sys_nfsservctl
+	.long sys_ni_syscall		/* was nfsservctl */
 	.long sys_setresgid		/* 170 */
 	.long sys_getresgid
 	.long sys_prctl
diff --git a/arch/m68k/include/asm/page_mm.h b/arch/m68k/include/asm/page_mm.h
index 31d5570..89f2014 100644
--- a/arch/m68k/include/asm/page_mm.h
+++ b/arch/m68k/include/asm/page_mm.h
@@ -162,7 +162,7 @@
 	pgdat->node_mem_map + (__pfn - pgdat->node_start_pfn);		\
 })
 #define page_to_pfn(_page) ({						\
-	struct page *__p = (_page);					\
+	const struct page *__p = (_page);				\
 	struct pglist_data *pgdat;					\
 	pgdat = &pg_data_map[page_to_nid(__p)];				\
 	((__p) - pgdat->node_mem_map) + pgdat->node_start_pfn;		\
diff --git a/arch/m68k/kernel/syscalltable.S b/arch/m68k/kernel/syscalltable.S
index 00d1452..c468f2e 100644
--- a/arch/m68k/kernel/syscalltable.S
+++ b/arch/m68k/kernel/syscalltable.S
@@ -189,7 +189,7 @@
 	.long sys_getpagesize
 	.long sys_ni_syscall		/* old "query_module" */
 	.long sys_poll
-	.long sys_nfsservctl
+	.long sys_ni_syscall		/* old nfsservctl */
 	.long sys_setresgid16		/* 170 */
 	.long sys_getresgid16
 	.long sys_prctl
diff --git a/arch/microblaze/kernel/syscall_table.S b/arch/microblaze/kernel/syscall_table.S
index d915a12..8789daa 100644
--- a/arch/microblaze/kernel/syscall_table.S
+++ b/arch/microblaze/kernel/syscall_table.S
@@ -173,7 +173,7 @@
 	.long sys_ni_syscall		/* sys_vm86 */
 	.long sys_ni_syscall		/* Old sys_query_module */
 	.long sys_poll
-	.long sys_nfsservctl
+	.long sys_ni_syscall		/* old nfsservctl */
 	.long sys_setresgid		/* 170 */
 	.long sys_getresgid
 	.long sys_prctl
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index e521420..865bc7a 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -424,7 +424,7 @@
 	sys	sys_getresuid		3
 	sys	sys_ni_syscall		0	/* was sys_query_module */
 	sys	sys_poll		3
-	sys	sys_nfsservctl		3
+	sys	sys_ni_syscall		0	/* was nfsservctl */
 	sys	sys_setresgid		3	/* 4190 */
 	sys	sys_getresgid		3
 	sys	sys_prctl		5
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index 85874d6..fb7334b 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -299,7 +299,7 @@
 	PTR	sys_ni_syscall			/* 5170, was get_kernel_syms */
 	PTR	sys_ni_syscall			/* was query_module */
 	PTR	sys_quotactl
-	PTR	sys_nfsservctl
+	PTR	sys_ni_syscall			/* was nfsservctl */
 	PTR	sys_ni_syscall			/* res. for getpmsg */
 	PTR	sys_ni_syscall			/* 5175  for putpmsg */
 	PTR	sys_ni_syscall			/* res. for afs_syscall */
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index b85842f..f9296e8 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -294,7 +294,7 @@
 	PTR	sys_ni_syscall			/* 6170, was get_kernel_syms */
 	PTR	sys_ni_syscall			/* was query_module */
 	PTR	sys_quotactl
-	PTR	compat_sys_nfsservctl
+	PTR	sys_ni_syscall			/* was nfsservctl */
 	PTR	sys_ni_syscall			/* res. for getpmsg */
 	PTR	sys_ni_syscall			/* 6175  for putpmsg */
 	PTR	sys_ni_syscall			/* res. for afs_syscall */
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index 46c4763..4d7c982 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -392,7 +392,7 @@
 	PTR	sys_getresuid
 	PTR	sys_ni_syscall			/* was query_module */
 	PTR	sys_poll
-	PTR	compat_sys_nfsservctl
+	PTR	sys_ni_syscall			/* was nfsservctl */
 	PTR	sys_setresgid			/* 4190 */
 	PTR	sys_getresgid
 	PTR	sys_prctl
diff --git a/arch/mn10300/kernel/entry.S b/arch/mn10300/kernel/entry.S
index ae435e1..3e3620d 100644
--- a/arch/mn10300/kernel/entry.S
+++ b/arch/mn10300/kernel/entry.S
@@ -589,7 +589,7 @@
 	.long sys_ni_syscall	/* vm86 */
 	.long sys_ni_syscall	/* Old sys_query_module */
 	.long sys_poll
-	.long sys_nfsservctl
+	.long sys_ni_syscall	/* was nfsservctl */
 	.long sys_setresgid16	/* 170 */
 	.long sys_getresgid16
 	.long sys_prctl
diff --git a/arch/openrisc/include/asm/dma-mapping.h b/arch/openrisc/include/asm/dma-mapping.h
index 052f877..60b4722 100644
--- a/arch/openrisc/include/asm/dma-mapping.h
+++ b/arch/openrisc/include/asm/dma-mapping.h
@@ -31,7 +31,6 @@
 
 #define DMA_ERROR_CODE		(~(dma_addr_t)0x0)
 
-int dma_mapping_error(struct device *dev, dma_addr_t dma_addr);
 
 #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
 #define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
@@ -47,6 +46,12 @@
 void or1k_unmap_page(struct device *dev, dma_addr_t dma_handle,
 		     size_t size, enum dma_data_direction dir,
 		     struct dma_attrs *attrs);
+int or1k_map_sg(struct device *dev, struct scatterlist *sg,
+		int nents, enum dma_data_direction dir,
+		struct dma_attrs *attrs);
+void or1k_unmap_sg(struct device *dev, struct scatterlist *sg,
+		   int nents, enum dma_data_direction dir,
+		   struct dma_attrs *attrs);
 void or1k_sync_single_for_cpu(struct device *dev,
 			      dma_addr_t dma_handle, size_t size,
 			      enum dma_data_direction dir);
@@ -98,6 +103,51 @@
 	debug_dma_unmap_page(dev, addr, size, dir, true);
 }
 
+static inline int dma_map_sg(struct device *dev, struct scatterlist *sg,
+				   int nents, enum dma_data_direction dir)
+{
+	int i, ents;
+	struct scatterlist *s;
+
+	for_each_sg(sg, s, nents, i)
+		kmemcheck_mark_initialized(sg_virt(s), s->length);
+	BUG_ON(!valid_dma_direction(dir));
+	ents = or1k_map_sg(dev, sg, nents, dir, NULL);
+	debug_dma_map_sg(dev, sg, nents, ents, dir);
+
+	return ents;
+}
+
+static inline void dma_unmap_sg(struct device *dev, struct scatterlist *sg,
+				      int nents, enum dma_data_direction dir)
+{
+	BUG_ON(!valid_dma_direction(dir));
+	debug_dma_unmap_sg(dev, sg, nents, dir);
+	or1k_unmap_sg(dev, sg, nents, dir, NULL);
+}
+
+static inline dma_addr_t dma_map_page(struct device *dev, struct page *page,
+				      size_t offset, size_t size,
+				      enum dma_data_direction dir)
+{
+	dma_addr_t addr;
+
+	kmemcheck_mark_initialized(page_address(page) + offset, size);
+	BUG_ON(!valid_dma_direction(dir));
+	addr = or1k_map_page(dev, page, offset, size, dir, NULL);
+	debug_dma_map_page(dev, page, offset, size, dir, addr, false);
+
+	return addr;
+}
+
+static inline void dma_unmap_page(struct device *dev, dma_addr_t addr,
+				  size_t size, enum dma_data_direction dir)
+{
+	BUG_ON(!valid_dma_direction(dir));
+	or1k_unmap_page(dev, addr, size, dir, NULL);
+	debug_dma_unmap_page(dev, addr, size, dir, true);
+}
+
 static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
 					   size_t size,
 					   enum dma_data_direction dir)
@@ -119,7 +169,12 @@
 static inline int dma_supported(struct device *dev, u64 dma_mask)
 {
 	/* Support 32 bit DMA mask exclusively */
-	return dma_mask == 0xffffffffULL;
+	return dma_mask == DMA_BIT_MASK(32);
+}
+
+static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	return 0;
 }
 
 static inline int dma_set_mask(struct device *dev, u64 dma_mask)
diff --git a/arch/openrisc/include/asm/sigcontext.h b/arch/openrisc/include/asm/sigcontext.h
index 54a5c50..b79c2b1 100644
--- a/arch/openrisc/include/asm/sigcontext.h
+++ b/arch/openrisc/include/asm/sigcontext.h
@@ -23,16 +23,11 @@
 
 /* This struct is saved by setup_frame in signal.c, to keep the current
    context while a signal handler is executed. It's restored by sys_sigreturn.
-
-   To keep things simple, we use pt_regs here even though normally you just
-   specify the list of regs to save. Then we can use copy_from_user on the
-   entire regs instead of a bunch of get_user's as well...
 */
 
 struct sigcontext {
-	struct pt_regs regs;  /* needs to be first */
+	struct user_regs_struct regs;  /* needs to be first */
 	unsigned long oldmask;
-	unsigned long usp;    /* usp before stacking this gunk on it */
 };
 
 #endif /* __ASM_OPENRISC_SIGCONTEXT_H */
diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c
index 968d3ee..f1c8ee2 100644
--- a/arch/openrisc/kernel/dma.c
+++ b/arch/openrisc/kernel/dma.c
@@ -154,6 +154,33 @@
 	/* Nothing special to do here... */
 }
 
+int or1k_map_sg(struct device *dev, struct scatterlist *sg,
+		int nents, enum dma_data_direction dir,
+		struct dma_attrs *attrs)
+{
+	struct scatterlist *s;
+	int i;
+
+	for_each_sg(sg, s, nents, i) {
+		s->dma_address = or1k_map_page(dev, sg_page(s), s->offset,
+					       s->length, dir, NULL);
+	}
+
+	return nents;
+}
+
+void or1k_unmap_sg(struct device *dev, struct scatterlist *sg,
+		   int nents, enum dma_data_direction dir,
+		   struct dma_attrs *attrs)
+{
+	struct scatterlist *s;
+	int i;
+
+	for_each_sg(sg, s, nents, i) {
+		or1k_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir, NULL);
+	}
+}
+
 void or1k_sync_single_for_cpu(struct device *dev,
 			      dma_addr_t dma_handle, size_t size,
 			      enum dma_data_direction dir)
@@ -187,5 +214,4 @@
 
 	return 0;
 }
-
 fs_initcall(dma_init);
diff --git a/arch/openrisc/kernel/signal.c b/arch/openrisc/kernel/signal.c
index 5f759c7..95207ab 100644
--- a/arch/openrisc/kernel/signal.c
+++ b/arch/openrisc/kernel/signal.c
@@ -52,31 +52,25 @@
 static int restore_sigcontext(struct pt_regs *regs, struct sigcontext *sc)
 {
 	unsigned int err = 0;
-	unsigned long old_usp;
 
 	/* Alwys make any pending restarted system call return -EINTR */
 	current_thread_info()->restart_block.fn = do_no_restart_syscall;
 
-	/* restore the regs from &sc->regs (same as sc, since regs is first)
+	/*
+	 * Restore the regs from &sc->regs.
 	 * (sc is already checked for VERIFY_READ since the sigframe was
 	 *  checked in sys_sigreturn previously)
 	 */
-
-	if (__copy_from_user(regs, sc, sizeof(struct pt_regs)))
+	if (__copy_from_user(regs, sc->regs.gpr, 32 * sizeof(unsigned long)))
+		goto badframe;
+	if (__copy_from_user(&regs->pc, &sc->regs.pc, sizeof(unsigned long)))
+		goto badframe;
+	if (__copy_from_user(&regs->sr, &sc->regs.sr, sizeof(unsigned long)))
 		goto badframe;
 
 	/* make sure the SM-bit is cleared so user-mode cannot fool us */
 	regs->sr &= ~SPR_SR_SM;
 
-	/* restore the old USP as it was before we stacked the sc etc.
-	 * (we cannot just pop the sigcontext since we aligned the sp and
-	 *  stuff after pushing it)
-	 */
-
-	err |= __get_user(old_usp, &sc->usp);
-
-	regs->sp = old_usp;
-
 	/* TODO: the other ports use regs->orig_XX to disable syscall checks
 	 * after this completes, but we don't use that mechanism. maybe we can
 	 * use it now ?
@@ -137,18 +131,17 @@
 			    unsigned long mask)
 {
 	int err = 0;
-	unsigned long usp = regs->sp;
 
-	/* copy the regs. they are first in sc so we can use sc directly */
+	/* copy the regs */
 
-	err |= __copy_to_user(sc, regs, sizeof(struct pt_regs));
+	err |= __copy_to_user(sc->regs.gpr, regs, 32 * sizeof(unsigned long));
+	err |= __copy_to_user(&sc->regs.pc, &regs->pc, sizeof(unsigned long));
+	err |= __copy_to_user(&sc->regs.sr, &regs->sr, sizeof(unsigned long));
 
 	/* then some other stuff */
 
 	err |= __put_user(mask, &sc->oldmask);
 
-	err |= __put_user(usp, &sc->usp);
-
 	return err;
 }
 
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index e66366f..3735abd 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -259,7 +259,7 @@
 	ENTRY_SAME(ni_syscall)		/* query_module */
 	ENTRY_SAME(poll)
 	/* structs contain pointers and an in_addr... */
-	ENTRY_COMP(nfsservctl)
+	ENTRY_SAME(ni_syscall)		/* was nfsservctl */
 	ENTRY_SAME(setresgid)		/* 170 */
 	ENTRY_SAME(getresgid)
 	ENTRY_SAME(prctl)
diff --git a/arch/powerpc/boot/dts/p1023rds.dts b/arch/powerpc/boot/dts/p1023rds.dts
index bfa96aa..d9b7767 100644
--- a/arch/powerpc/boot/dts/p1023rds.dts
+++ b/arch/powerpc/boot/dts/p1023rds.dts
@@ -387,7 +387,7 @@
 			#size-cells = <1>;
 			compatible = "cfi-flash";
 			reg = <0x0 0x0 0x02000000>;
-			bank-width = <1>;
+			bank-width = <2>;
 			device-width = <1>;
 			partition@0 {
 				label = "ramdisk";
diff --git a/arch/powerpc/configs/85xx/p1023rds_defconfig b/arch/powerpc/configs/85xx/p1023rds_defconfig
index 980ff8f..3ff5a81 100644
--- a/arch/powerpc/configs/85xx/p1023rds_defconfig
+++ b/arch/powerpc/configs/85xx/p1023rds_defconfig
@@ -171,3 +171,4 @@
 CONFIG_CRYPTO_SHA512=y
 CONFIG_CRYPTO_AES=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
+CONFIG_CRYPTO_DEV_FSL_CAAM=y
diff --git a/arch/powerpc/configs/corenet32_smp_defconfig b/arch/powerpc/configs/corenet32_smp_defconfig
index 10562a5..4311d02 100644
--- a/arch/powerpc/configs/corenet32_smp_defconfig
+++ b/arch/powerpc/configs/corenet32_smp_defconfig
@@ -185,3 +185,4 @@
 CONFIG_CRYPTO_SHA512=y
 CONFIG_CRYPTO_AES=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
+CONFIG_CRYPTO_DEV_FSL_CAAM=y
diff --git a/arch/powerpc/configs/corenet64_smp_defconfig b/arch/powerpc/configs/corenet64_smp_defconfig
index d322835..c92c204 100644
--- a/arch/powerpc/configs/corenet64_smp_defconfig
+++ b/arch/powerpc/configs/corenet64_smp_defconfig
@@ -100,5 +100,8 @@
 CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_VIRQ_DEBUG=y
 CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_SHA256=y
+CONFIG_CRYPTO_SHA512=y
+CONFIG_CRYPTO_AES=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRYPTO_DEV_TALITOS=y
+CONFIG_CRYPTO_DEV_FSL_CAAM=y
diff --git a/arch/powerpc/configs/mpc85xx_defconfig b/arch/powerpc/configs/mpc85xx_defconfig
index fcd85d2..a3467bf 100644
--- a/arch/powerpc/configs/mpc85xx_defconfig
+++ b/arch/powerpc/configs/mpc85xx_defconfig
@@ -139,6 +139,7 @@
 CONFIG_SND_INTEL8X0=y
 # CONFIG_SND_PPC is not set
 # CONFIG_SND_USB is not set
+CONFIG_SND_SOC=y
 CONFIG_HID_A4TECH=y
 CONFIG_HID_APPLE=y
 CONFIG_HID_BELKIN=y
diff --git a/arch/powerpc/configs/mpc85xx_smp_defconfig b/arch/powerpc/configs/mpc85xx_smp_defconfig
index 908c941..9693f6e 100644
--- a/arch/powerpc/configs/mpc85xx_smp_defconfig
+++ b/arch/powerpc/configs/mpc85xx_smp_defconfig
@@ -140,6 +140,7 @@
 CONFIG_SND_INTEL8X0=y
 # CONFIG_SND_PPC is not set
 # CONFIG_SND_USB is not set
+CONFIG_SND_SOC=y
 CONFIG_HID_A4TECH=y
 CONFIG_HID_APPLE=y
 CONFIG_HID_BELKIN=y
diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h
index 1f780b9..938986e 100644
--- a/arch/powerpc/include/asm/jump_label.h
+++ b/arch/powerpc/include/asm/jump_label.h
@@ -22,7 +22,6 @@
 	asm goto("1:\n\t"
 		 "nop\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
-		 ".align 4\n\t"
 		 JUMP_ENTRY_TYPE "1b, %l[l_yes], %c0\n\t"
 		 ".popsection \n\t"
 		 : :  "i" (key) : : l_yes);
@@ -41,7 +40,6 @@
 	jump_label_t code;
 	jump_label_t target;
 	jump_label_t key;
-	jump_label_t pad;
 };
 
 #endif /* _ASM_POWERPC_JUMP_LABEL_H */
diff --git a/arch/powerpc/include/asm/kdump.h b/arch/powerpc/include/asm/kdump.h
index 6857af5..bffd062 100644
--- a/arch/powerpc/include/asm/kdump.h
+++ b/arch/powerpc/include/asm/kdump.h
@@ -3,17 +3,7 @@
 
 #include <asm/page.h>
 
-/*
- * If CONFIG_RELOCATABLE is enabled we can place the kdump kernel anywhere.
- * To keep enough space in the RMO for the first stage kernel on 64bit, we
- * place it at 64MB. If CONFIG_RELOCATABLE is not enabled we must place
- * the second stage at 32MB.
- */
-#if defined(CONFIG_RELOCATABLE) && defined(CONFIG_PPC64)
-#define KDUMP_KERNELBASE	0x4000000
-#else
 #define KDUMP_KERNELBASE	0x2000000
-#endif
 
 /* How many bytes to reserve at zero for kdump. The reserve limit should
  * be greater or equal to the trampoline's end address.
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index e8aaf6f..559da19 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -1003,7 +1003,6 @@
 #define PV_970		0x0039
 #define PV_POWER5	0x003A
 #define PV_POWER5p	0x003B
-#define PV_POWER7	0x003F
 #define PV_970FX	0x003C
 #define PV_POWER6	0x003E
 #define PV_POWER7	0x003F
@@ -1024,13 +1023,16 @@
 #define mtmsrd(v)	__mtmsrd((v), 0)
 #define mtmsr(v)	mtmsrd(v)
 #else
-#define mtmsr(v)	asm volatile("mtmsr %0" : : "r" (v) : "memory")
+#define mtmsr(v)	asm volatile("mtmsr %0" : \
+				     : "r" ((unsigned long)(v)) \
+				     : "memory")
 #endif
 
 #define mfspr(rn)	({unsigned long rval; \
 			asm volatile("mfspr %0," __stringify(rn) \
 				: "=r" (rval)); rval;})
-#define mtspr(rn, v)	asm volatile("mtspr " __stringify(rn) ",%0" : : "r" (v)\
+#define mtspr(rn, v)	asm volatile("mtspr " __stringify(rn) ",%0" : \
+				     : "r" ((unsigned long)(v)) \
 				     : "memory")
 
 #ifdef __powerpc64__
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index f6736b7..fa0d27a 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -171,7 +171,7 @@
 SYSCALL_SPU(getresuid)
 SYSCALL(ni_syscall)
 SYSCALL_SPU(poll)
-COMPAT_SYS(nfsservctl)
+SYSCALL(ni_syscall)
 SYSCALL_SPU(setresgid)
 SYSCALL_SPU(getresgid)
 COMPAT_SYS_SPU(prctl)
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 9fb9332..fa44ff5 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -2051,7 +2051,8 @@
 
 static struct cpu_spec the_cpu_spec;
 
-static void __init setup_cpu_spec(unsigned long offset, struct cpu_spec *s)
+static struct cpu_spec * __init setup_cpu_spec(unsigned long offset,
+					       struct cpu_spec *s)
 {
 	struct cpu_spec *t = &the_cpu_spec;
 	struct cpu_spec old;
@@ -2114,6 +2115,8 @@
 		t->cpu_setup(offset, t);
 	}
 #endif /* CONFIG_PPC64 || CONFIG_BOOKE */
+
+	return t;
 }
 
 struct cpu_spec * __init identify_cpu(unsigned long offset, unsigned int pvr)
@@ -2124,10 +2127,8 @@
 	s = PTRRELOC(s);
 
 	for (i = 0; i < ARRAY_SIZE(cpu_specs); i++,s++) {
-		if ((pvr & s->pvr_mask) == s->pvr_value) {
-			setup_cpu_spec(offset, s);
-			return s;
-		}
+		if ((pvr & s->pvr_mask) == s->pvr_value)
+			return setup_cpu_spec(offset, s);
 	}
 
 	BUG();
diff --git a/arch/powerpc/kernel/iomap.c b/arch/powerpc/kernel/iomap.c
index 1577434..b25f632 100644
--- a/arch/powerpc/kernel/iomap.c
+++ b/arch/powerpc/kernel/iomap.c
@@ -117,6 +117,7 @@
 EXPORT_SYMBOL(ioport_map);
 EXPORT_SYMBOL(ioport_unmap);
 
+#ifdef CONFIG_PCI
 void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max)
 {
 	resource_size_t start = pci_resource_start(dev, bar);
@@ -146,3 +147,4 @@
 
 EXPORT_SYMBOL(pci_iomap);
 EXPORT_SYMBOL(pci_iounmap);
+#endif /* CONFIG_PCI */
diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c
index 6658a15..9ce1672 100644
--- a/arch/powerpc/kernel/machine_kexec.c
+++ b/arch/powerpc/kernel/machine_kexec.c
@@ -136,12 +136,16 @@
 	crashk_res.start = KDUMP_KERNELBASE;
 #else
 	if (!crashk_res.start) {
+#ifdef CONFIG_PPC64
 		/*
-		 * unspecified address, choose a region of specified size
-		 * can overlap with initrd (ignoring corruption when retained)
-		 * ppc64 requires kernel and some stacks to be in first segemnt
+		 * On 64bit we split the RMO in half but cap it at half of
+		 * a small SLB (128MB) since the crash kernel needs to place
+		 * itself and some stacks to be in the first segment.
 		 */
+		crashk_res.start = min(0x80000000ULL, (ppc64_rma_size / 2));
+#else
 		crashk_res.start = KDUMP_KERNELBASE;
+#endif
 	}
 
 	crash_base = PAGE_ALIGN(crashk_res.start);
diff --git a/arch/powerpc/kernel/perf_callchain.c b/arch/powerpc/kernel/perf_callchain.c
index d05ae42..564c1d8 100644
--- a/arch/powerpc/kernel/perf_callchain.c
+++ b/arch/powerpc/kernel/perf_callchain.c
@@ -154,8 +154,12 @@
 	    ((unsigned long)ptr & 7))
 		return -EFAULT;
 
-	if (!__get_user_inatomic(*ret, ptr))
+	pagefault_disable();
+	if (!__get_user_inatomic(*ret, ptr)) {
+		pagefault_enable();
 		return 0;
+	}
+	pagefault_enable();
 
 	return read_user_stack_slow(ptr, ret, 8);
 }
@@ -166,8 +170,12 @@
 	    ((unsigned long)ptr & 3))
 		return -EFAULT;
 
-	if (!__get_user_inatomic(*ret, ptr))
+	pagefault_disable();
+	if (!__get_user_inatomic(*ret, ptr)) {
+		pagefault_enable();
 		return 0;
+	}
+	pagefault_enable();
 
 	return read_user_stack_slow(ptr, ret, 4);
 }
@@ -294,11 +302,17 @@
  */
 static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret)
 {
+	int rc;
+
 	if ((unsigned long)ptr > TASK_SIZE - sizeof(unsigned int) ||
 	    ((unsigned long)ptr & 3))
 		return -EFAULT;
 
-	return __get_user_inatomic(*ret, ptr);
+	pagefault_disable();
+	rc = __get_user_inatomic(*ret, ptr);
+	pagefault_enable();
+
+	return rc;
 }
 
 static inline void perf_callchain_user_64(struct perf_callchain_entry *entry,
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index c016033..a909f4e 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -1020,7 +1020,7 @@
 	}
 	if (addr == 0)
 		return 0;
-	RELOC(alloc_bottom) = addr;
+	RELOC(alloc_bottom) = addr + size;
 
 	prom_debug(" -> %x\n", addr);
 	prom_debug("  alloc_bottom : %x\n", RELOC(alloc_bottom));
@@ -1830,11 +1830,13 @@
 		if (room > DEVTREE_CHUNK_SIZE)
 			room = DEVTREE_CHUNK_SIZE;
 		if (room < PAGE_SIZE)
-			prom_panic("No memory for flatten_device_tree (no room)");
+			prom_panic("No memory for flatten_device_tree "
+				   "(no room)\n");
 		chunk = alloc_up(room, 0);
 		if (chunk == 0)
-			prom_panic("No memory for flatten_device_tree (claim failed)");
-		*mem_end = RELOC(alloc_top);
+			prom_panic("No memory for flatten_device_tree "
+				   "(claim failed)\n");
+		*mem_end = chunk + room;
 	}
 
 	ret = (void *)*mem_start;
@@ -2042,7 +2044,7 @@
 
 	/*
 	 * Check how much room we have between alloc top & bottom (+/- a
-	 * few pages), crop to 4Mb, as this is our "chuck" size
+	 * few pages), crop to 1MB, as this is our "chunk" size
 	 */
 	room = RELOC(alloc_top) - RELOC(alloc_bottom) - 0x4000;
 	if (room > DEVTREE_CHUNK_SIZE)
@@ -2053,7 +2055,7 @@
 	mem_start = (unsigned long)alloc_up(room, PAGE_SIZE);
 	if (mem_start == 0)
 		prom_panic("Can't allocate initial device-tree chunk\n");
-	mem_end = RELOC(alloc_top);
+	mem_end = mem_start + room;
 
 	/* Get root of tree */
 	root = call_prom("peer", 1, 1, (phandle)0);
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 6dd3358..de29501 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1251,7 +1251,7 @@
 	reg = 0
 	.rept	32
 	li	r6,reg*16+VCPU_VSRS
-	stxvd2x	reg,r6,r3
+	STXVD2X(reg,r6,r3)
 	reg = reg + 1
 	.endr
 FTR_SECTION_ELSE
@@ -1313,7 +1313,7 @@
 	reg = 0
 	.rept	32
 	li	r7,reg*16+VCPU_VSRS
-	lxvd2x	reg,r7,r4
+	LXVD2X(reg,r7,r4)
 	reg = reg + 1
 	.endr
 FTR_SECTION_ELSE
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index d0af7fb..b9ba861 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -24,7 +24,7 @@
 
 config KVM_GUEST
 	bool "KVM Guest support"
-	default y
+	default n
 	---help---
 	  This option enables various optimizations for running under the KVM
 	  hypervisor. Overhead for the kernel when not running inside KVM should
diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c
index e919007..0e86563 100644
--- a/arch/powerpc/platforms/pseries/dtl.c
+++ b/arch/powerpc/platforms/pseries/dtl.c
@@ -181,7 +181,7 @@
 
 	lppaca_of(dtl->cpu).dtl_enable_mask = 0x0;
 
-	unregister_dtl(hwcpu, __pa(dtl->buf));
+	unregister_dtl(hwcpu);
 }
 
 static u64 dtl_current_index(struct dtl *dtl)
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index bc02885..83a3ca2 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -135,7 +135,7 @@
 		get_lppaca()->idle = 0;
 
 		if (get_preferred_offline_state(cpu) == CPU_STATE_ONLINE) {
-			unregister_slb_shadow(hwcpu, __pa(get_slb_shadow()));
+			unregister_slb_shadow(hwcpu);
 
 			/*
 			 * Call to start_secondary_resume() will not return.
@@ -150,7 +150,7 @@
 	WARN_ON(get_preferred_offline_state(cpu) != CPU_STATE_OFFLINE);
 
 	set_cpu_current_state(cpu, CPU_STATE_OFFLINE);
-	unregister_slb_shadow(hwcpu, __pa(get_slb_shadow()));
+	unregister_slb_shadow(hwcpu);
 	rtas_stop_self();
 
 	/* Should never get here... */
diff --git a/arch/powerpc/platforms/pseries/io_event_irq.c b/arch/powerpc/platforms/pseries/io_event_irq.c
index c829e60..2c4dd1f 100644
--- a/arch/powerpc/platforms/pseries/io_event_irq.c
+++ b/arch/powerpc/platforms/pseries/io_event_irq.c
@@ -212,17 +212,15 @@
 	struct device_node *np;
 
 	ioei_check_exception_token = rtas_token("check-exception");
-	if (ioei_check_exception_token == RTAS_UNKNOWN_SERVICE) {
-		pr_warning("IO Event IRQ not supported on this system !\n");
+	if (ioei_check_exception_token == RTAS_UNKNOWN_SERVICE)
 		return -ENODEV;
-	}
+
 	np = of_find_node_by_path("/event-sources/ibm,io-events");
 	if (np) {
 		request_event_sources_irqs(np, ioei_interrupt, "IO_EVENT");
+		pr_info("IBM I/O event interrupts enabled\n");
 		of_node_put(np);
 	} else {
-		pr_err("io_event_irq: No ibm,io-events on system! "
-		       "IO Event interrupt disabled.\n");
 		return -ENODEV;
 	}
 	return 0;
diff --git a/arch/powerpc/platforms/pseries/kexec.c b/arch/powerpc/platforms/pseries/kexec.c
index 54cf3a4..7d94bdc 100644
--- a/arch/powerpc/platforms/pseries/kexec.c
+++ b/arch/powerpc/platforms/pseries/kexec.c
@@ -25,20 +25,30 @@
 {
 	/* Don't risk a hypervisor call if we're crashing */
 	if (firmware_has_feature(FW_FEATURE_SPLPAR) && !crash_shutdown) {
-		unsigned long addr;
+		int ret;
+		int cpu = smp_processor_id();
+		int hwcpu = hard_smp_processor_id();
 
-		addr = __pa(get_slb_shadow());
-		if (unregister_slb_shadow(hard_smp_processor_id(), addr))
-			printk("SLB shadow buffer deregistration of "
-			       "cpu %u (hw_cpu_id %d) failed\n",
-			       smp_processor_id(),
-			       hard_smp_processor_id());
+		if (get_lppaca()->dtl_enable_mask) {
+			ret = unregister_dtl(hwcpu);
+			if (ret) {
+				pr_err("WARNING: DTL deregistration for cpu "
+				       "%d (hw %d) failed with %d\n",
+				       cpu, hwcpu, ret);
+			}
+		}
 
-		addr = __pa(get_lppaca());
-		if (unregister_vpa(hard_smp_processor_id(), addr)) {
-			printk("VPA deregistration of cpu %u (hw_cpu_id %d) "
-					"failed\n", smp_processor_id(),
-					hard_smp_processor_id());
+		ret = unregister_slb_shadow(hwcpu);
+		if (ret) {
+			pr_err("WARNING: SLB shadow buffer deregistration "
+			       "for cpu %d (hw %d) failed with %d\n",
+			       cpu, hwcpu, ret);
+		}
+
+		ret = unregister_vpa(hwcpu);
+		if (ret) {
+			pr_err("WARNING: VPA deregistration for cpu %d "
+			       "(hw %d) failed with %d\n", cpu, hwcpu, ret);
 		}
 	}
 }
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index f7205d3..c9a29da 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -67,9 +67,8 @@
 	ret = register_vpa(hwcpu, addr);
 
 	if (ret) {
-		printk(KERN_ERR "WARNING: vpa_init: VPA registration for "
-				"cpu %d (hw %d) of area %lx returns %ld\n",
-				cpu, hwcpu, addr, ret);
+		pr_err("WARNING: VPA registration for cpu %d (hw %d) of area "
+		       "%lx failed with %ld\n", cpu, hwcpu, addr, ret);
 		return;
 	}
 	/*
@@ -80,10 +79,9 @@
 	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
 		ret = register_slb_shadow(hwcpu, addr);
 		if (ret)
-			printk(KERN_ERR
-			       "WARNING: vpa_init: SLB shadow buffer "
-			       "registration for cpu %d (hw %d) of area %lx "
-			       "returns %ld\n", cpu, hwcpu, addr, ret);
+			pr_err("WARNING: SLB shadow buffer registration for "
+			       "cpu %d (hw %d) of area %lx failed with %ld\n",
+			       cpu, hwcpu, addr, ret);
 	}
 
 	/*
@@ -100,8 +98,9 @@
 		dtl->enqueue_to_dispatch_time = DISPATCH_LOG_BYTES;
 		ret = register_dtl(hwcpu, __pa(dtl));
 		if (ret)
-			pr_warn("DTL registration failed for cpu %d (%ld)\n",
-				cpu, ret);
+			pr_err("WARNING: DTL registration of cpu %d (hw %d) "
+			       "failed with %ld\n", smp_processor_id(),
+			       hwcpu, ret);
 		lppaca_of(cpu).dtl_enable_mask = 2;
 	}
 }
@@ -204,7 +203,7 @@
 		unsigned long ptel;
 	} ptes[4];
 	long lpar_rc;
-	int i, j;
+	unsigned long i, j;
 
 	/* Read in batches of 4,
 	 * invalidate only valid entries not in the VRMA
diff --git a/arch/powerpc/platforms/pseries/plpar_wrappers.h b/arch/powerpc/platforms/pseries/plpar_wrappers.h
index 4bf2120..41c24c1 100644
--- a/arch/powerpc/platforms/pseries/plpar_wrappers.h
+++ b/arch/powerpc/platforms/pseries/plpar_wrappers.h
@@ -53,9 +53,9 @@
 	return plpar_hcall_norets(H_REGISTER_VPA, flags, cpu, vpa);
 }
 
-static inline long unregister_vpa(unsigned long cpu, unsigned long vpa)
+static inline long unregister_vpa(unsigned long cpu)
 {
-	return vpa_call(0x5, cpu, vpa);
+	return vpa_call(0x5, cpu, 0);
 }
 
 static inline long register_vpa(unsigned long cpu, unsigned long vpa)
@@ -63,9 +63,9 @@
 	return vpa_call(0x1, cpu, vpa);
 }
 
-static inline long unregister_slb_shadow(unsigned long cpu, unsigned long vpa)
+static inline long unregister_slb_shadow(unsigned long cpu)
 {
-	return vpa_call(0x7, cpu, vpa);
+	return vpa_call(0x7, cpu, 0);
 }
 
 static inline long register_slb_shadow(unsigned long cpu, unsigned long vpa)
@@ -73,9 +73,9 @@
 	return vpa_call(0x3, cpu, vpa);
 }
 
-static inline long unregister_dtl(unsigned long cpu, unsigned long vpa)
+static inline long unregister_dtl(unsigned long cpu)
 {
-	return vpa_call(0x6, cpu, vpa);
+	return vpa_call(0x6, cpu, 0);
 }
 
 static inline long register_dtl(unsigned long cpu, unsigned long vpa)
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index d00e529..0969fd9 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -324,8 +324,9 @@
 	dtl->enqueue_to_dispatch_time = DISPATCH_LOG_BYTES;
 	ret = register_dtl(hard_smp_processor_id(), __pa(dtl));
 	if (ret)
-		pr_warn("DTL registration failed for boot cpu %d (%d)\n",
-			smp_processor_id(), ret);
+		pr_err("WARNING: DTL registration of cpu %d (hw %d) failed "
+		       "with %d\n", smp_processor_id(),
+		       hard_smp_processor_id(), ret);
 	get_paca()->lppaca_ptr->dtl_enable_mask = 2;
 
 	return 0;
diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c
index 2de8551..c65f75a 100644
--- a/arch/powerpc/sysdev/fsl_rio.c
+++ b/arch/powerpc/sysdev/fsl_rio.c
@@ -54,6 +54,7 @@
 #define ODSR_CLEAR		0x1c00
 #define LTLEECSR_ENABLE_ALL	0xFFC000FC
 #define ESCSR_CLEAR		0x07120204
+#define IECSR_CLEAR		0x80000000
 
 #define RIO_PORT1_EDCSR		0x0640
 #define RIO_PORT2_EDCSR		0x0680
@@ -1089,11 +1090,11 @@
 
 	if (offset == 0) {
 		out_be32((u32 *)(rio_regs_win + RIO_PORT1_EDCSR), 0);
-		out_be32((u32 *)(rio_regs_win + RIO_PORT1_IECSR), 0);
+		out_be32((u32 *)(rio_regs_win + RIO_PORT1_IECSR), IECSR_CLEAR);
 		out_be32((u32 *)(rio_regs_win + RIO_ESCSR), ESCSR_CLEAR);
 	} else {
 		out_be32((u32 *)(rio_regs_win + RIO_PORT2_EDCSR), 0);
-		out_be32((u32 *)(rio_regs_win + RIO_PORT2_IECSR), 0);
+		out_be32((u32 *)(rio_regs_win + RIO_PORT2_IECSR), IECSR_CLEAR);
 		out_be32((u32 *)(rio_regs_win + RIO_PORT2_ESCSR), ESCSR_CLEAR);
 	}
 }
diff --git a/arch/powerpc/sysdev/ppc4xx_pci.c b/arch/powerpc/sysdev/ppc4xx_pci.c
index a59ba96..dbfe96b 100644
--- a/arch/powerpc/sysdev/ppc4xx_pci.c
+++ b/arch/powerpc/sysdev/ppc4xx_pci.c
@@ -655,8 +655,6 @@
 
 static struct ppc4xx_pciex_hwops *ppc4xx_pciex_hwops;
 
-#ifdef CONFIG_44x
-
 static int __init ppc4xx_pciex_wait_on_sdr(struct ppc4xx_pciex_port *port,
 					   unsigned int sdr_offset,
 					   unsigned int mask,
@@ -688,6 +686,7 @@
 	return 0;
 }
 
+
 static void __init ppc4xx_pciex_check_link_sdr(struct ppc4xx_pciex_port *port)
 {
 	printk(KERN_INFO "PCIE%d: Checking link...\n", port->index);
@@ -718,6 +717,8 @@
 		printk(KERN_INFO "PCIE%d: No device detected.\n", port->index);
 }
 
+#ifdef CONFIG_44x
+
 /* Check various reset bits of the 440SPe PCIe core */
 static int __init ppc440spe_pciex_check_reset(struct device_node *np)
 {
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 519eb5f..c0cb794 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -658,12 +658,14 @@
  * struct gmap_struct - guest address space
  * @mm: pointer to the parent mm_struct
  * @table: pointer to the page directory
+ * @asce: address space control element for gmap page table
  * @crst_list: list of all crst tables used in the guest address space
  */
 struct gmap {
 	struct list_head list;
 	struct mm_struct *mm;
 	unsigned long *table;
+	unsigned long asce;
 	struct list_head crst_list;
 };
 
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index 532fd43..2b45591 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -10,6 +10,7 @@
 #include <linux/sched.h>
 #include <asm/vdso.h>
 #include <asm/sigp.h>
+#include <asm/pgtable.h>
 
 /*
  * Make sure that the compiler is new enough. We want a compiler that
@@ -126,6 +127,7 @@
 	DEFINE(__LC_KERNEL_STACK, offsetof(struct _lowcore, kernel_stack));
 	DEFINE(__LC_ASYNC_STACK, offsetof(struct _lowcore, async_stack));
 	DEFINE(__LC_PANIC_STACK, offsetof(struct _lowcore, panic_stack));
+	DEFINE(__LC_USER_ASCE, offsetof(struct _lowcore, user_asce));
 	DEFINE(__LC_INT_CLOCK, offsetof(struct _lowcore, int_clock));
 	DEFINE(__LC_MCCK_CLOCK, offsetof(struct _lowcore, mcck_clock));
 	DEFINE(__LC_MACHINE_FLAGS, offsetof(struct _lowcore, machine_flags));
@@ -151,6 +153,7 @@
 	DEFINE(__LC_VDSO_PER_CPU, offsetof(struct _lowcore, vdso_per_cpu_data));
 	DEFINE(__LC_GMAP, offsetof(struct _lowcore, gmap));
 	DEFINE(__LC_CMF_HPP, offsetof(struct _lowcore, cmf_hpp));
+	DEFINE(__GMAP_ASCE, offsetof(struct gmap, asce));
 #endif /* CONFIG_32BIT */
 	return 0;
 }
diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S
index 08ab9aa..7526db6 100644
--- a/arch/s390/kernel/compat_wrapper.S
+++ b/arch/s390/kernel/compat_wrapper.S
@@ -665,12 +665,6 @@
 	lgfr	%r4,%r4			# long
 	jg	sys_poll		# branch to system call
 
-ENTRY(compat_sys_nfsservctl_wrapper)
-	lgfr	%r2,%r2			# int
-	llgtr	%r3,%r3			# struct compat_nfsctl_arg*
-	llgtr	%r4,%r4			# union compat_nfsctl_res*
-	jg	compat_sys_nfsservctl	# branch to system call
-
 ENTRY(sys32_setresgid16_wrapper)
 	llgfr	%r2,%r2			# __kernel_old_gid_emu31_t
 	llgfr	%r3,%r3			# __kernel_old_gid_emu31_t
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 068f846..f297456 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -396,17 +396,19 @@
 static __init void rescue_initrd(void)
 {
 #ifdef CONFIG_BLK_DEV_INITRD
+	unsigned long min_initrd_addr = (unsigned long) _end + (4UL << 20);
 	/*
-	 * Move the initrd right behind the bss section in case it starts
-	 * within the bss section. So we don't overwrite it when the bss
-	 * section gets cleared.
+	 * Just like in case of IPL from VM reader we make sure there is a
+	 * gap of 4MB between end of kernel and start of initrd.
+	 * That way we can also be sure that saving an NSS will succeed,
+	 * which however only requires different segments.
 	 */
 	if (!INITRD_START || !INITRD_SIZE)
 		return;
-	if (INITRD_START >= (unsigned long) __bss_stop)
+	if (INITRD_START >= min_initrd_addr)
 		return;
-	memmove(__bss_stop, (void *) INITRD_START, INITRD_SIZE);
-	INITRD_START = (unsigned long) __bss_stop;
+	memmove((void *) min_initrd_addr, (void *) INITRD_START, INITRD_SIZE);
+	INITRD_START = min_initrd_addr;
 #endif
 }
 
diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S
index 5f729d6..713da07 100644
--- a/arch/s390/kernel/entry64.S
+++ b/arch/s390/kernel/entry64.S
@@ -1076,6 +1076,11 @@
 	lg	%r14,__LC_THREAD_INFO		# pointer thread_info struct
 	tm	__TI_flags+7(%r14),_TIF_EXIT_SIE
 	jnz	sie_exit
+	lg	%r14,__LC_GMAP			# get gmap pointer
+	ltgr	%r14,%r14
+	jz	sie_gmap
+	lctlg	%c1,%c1,__GMAP_ASCE(%r14)	# load primary asce
+sie_gmap:
 	lg	%r14,__SF_EMPTY(%r15)		# get control block pointer
 	SPP	__SF_EMPTY(%r15)		# set guest id
 	sie	0(%r14)
@@ -1083,6 +1088,7 @@
 	SPP	__LC_CMF_HPP			# set host id
 	lg	%r14,__LC_THREAD_INFO		# pointer thread_info struct
 sie_exit:
+	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
 	ni	__TI_flags+6(%r14),255-(_TIF_SIE>>8)
 	lg	%r14,__SF_EMPTY+8(%r15)		# load guest register save area
 	stmg	%r0,%r13,0(%r14)		# save guest gprs 0-13
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index 04361d5..48c7102 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -1220,7 +1220,7 @@
 	/* sysfs: create fcp kset for mixing attr group and bin attrs */
 	reipl_fcp_kset = kset_create_and_add(IPL_FCP_STR, NULL,
 					     &reipl_kset->kobj);
-	if (!reipl_kset) {
+	if (!reipl_fcp_kset) {
 		free_page((unsigned long) reipl_block_fcp);
 		return -ENOMEM;
 	}
@@ -1618,7 +1618,8 @@
 
 static void stop_run(struct shutdown_trigger *trigger)
 {
-	if (strcmp(trigger->name, ON_PANIC_STR) == 0)
+	if (strcmp(trigger->name, ON_PANIC_STR) == 0 ||
+	    strcmp(trigger->name, ON_RESTART_STR) == 0)
 		disabled_wait((unsigned long) __builtin_return_address(0));
 	while (sigp(smp_processor_id(), sigp_stop) == sigp_busy)
 		cpu_relax();
@@ -1717,7 +1718,7 @@
 /* on restart */
 
 static struct shutdown_trigger on_restart_trigger = {ON_RESTART_STR,
-	&reipl_action};
+	&stop_action};
 
 static ssize_t on_restart_show(struct kobject *kobj,
 			       struct kobj_attribute *attr, char *page)
diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S
index 6ee39ef..73eb08c 100644
--- a/arch/s390/kernel/syscalls.S
+++ b/arch/s390/kernel/syscalls.S
@@ -177,7 +177,7 @@
 NI_SYSCALL							/* for vm86 */
 NI_SYSCALL							/* old sys_query_module */
 SYSCALL(sys_poll,sys_poll,sys32_poll_wrapper)
-SYSCALL(sys_nfsservctl,sys_nfsservctl,compat_sys_nfsservctl_wrapper)
+NI_SYSCALL							/* old nfsservctl */
 SYSCALL(sys_setresgid16,sys_ni_syscall,sys32_setresgid16_wrapper)	/* 170 old setresgid16 syscall */
 SYSCALL(sys_getresgid16,sys_ni_syscall,sys32_getresgid16_wrapper)	/* old getresgid16 syscall */
 SYSCALL(sys_prctl,sys_prctl,sys32_prctl_wrapper)
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index f17296e..dc2b580 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -123,6 +123,7 @@
 
 	switch (ext) {
 	case KVM_CAP_S390_PSW:
+	case KVM_CAP_S390_GMAP:
 		r = 1;
 		break;
 	default:
@@ -263,10 +264,12 @@
 	vcpu->arch.guest_fpregs.fpc &= FPC_VALID_MASK;
 	restore_fp_regs(&vcpu->arch.guest_fpregs);
 	restore_access_regs(vcpu->arch.guest_acrs);
+	gmap_enable(vcpu->arch.gmap);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
+	gmap_disable(vcpu->arch.gmap);
 	save_fp_regs(&vcpu->arch.guest_fpregs);
 	save_access_regs(vcpu->arch.guest_acrs);
 	restore_fp_regs(&vcpu->arch.host_fpregs);
@@ -461,7 +464,6 @@
 	local_irq_disable();
 	kvm_guest_enter();
 	local_irq_enable();
-	gmap_enable(vcpu->arch.gmap);
 	VCPU_EVENT(vcpu, 6, "entering sie flags %x",
 		   atomic_read(&vcpu->arch.sie_block->cpuflags));
 	if (sie64a(vcpu->arch.sie_block, vcpu->arch.guest_gprs)) {
@@ -470,7 +472,6 @@
 	}
 	VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
 		   vcpu->arch.sie_block->icptcode);
-	gmap_disable(vcpu->arch.gmap);
 	local_irq_disable();
 	kvm_guest_exit();
 	local_irq_enable();
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 4d1f2bc..f69ff3c 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -160,6 +160,8 @@
 	table = (unsigned long *) page_to_phys(page);
 	crst_table_init(table, _REGION1_ENTRY_EMPTY);
 	gmap->table = table;
+	gmap->asce = _ASCE_TYPE_REGION1 | _ASCE_TABLE_LENGTH |
+		     _ASCE_USER_BITS | __pa(table);
 	list_add(&gmap->list, &mm->context.gmap_list);
 	return gmap;
 
@@ -240,10 +242,6 @@
  */
 void gmap_enable(struct gmap *gmap)
 {
-	/* Load primary space page table origin. */
-	S390_lowcore.user_asce = _ASCE_TYPE_REGION1 | _ASCE_TABLE_LENGTH |
-				 _ASCE_USER_BITS | __pa(gmap->table);
-	asm volatile("lctlg 1,1,%0\n" : : "m" (S390_lowcore.user_asce) );
 	S390_lowcore.gmap = (unsigned long) gmap;
 }
 EXPORT_SYMBOL_GPL(gmap_enable);
@@ -254,10 +252,6 @@
  */
 void gmap_disable(struct gmap *gmap)
 {
-	/* Load primary space page table origin. */
-	S390_lowcore.user_asce =
-		gmap->mm->context.asce_bits | __pa(gmap->mm->pgd);
-	asm volatile("lctlg 1,1,%0\n" : : "m" (S390_lowcore.user_asce) );
 	S390_lowcore.gmap = 0UL;
 }
 EXPORT_SYMBOL_GPL(gmap_disable);
diff --git a/arch/sh/include/asm/ptrace.h b/arch/sh/include/asm/ptrace.h
index b97baf8..2d3679b 100644
--- a/arch/sh/include/asm/ptrace.h
+++ b/arch/sh/include/asm/ptrace.h
@@ -123,7 +123,7 @@
 struct perf_event;
 struct perf_sample_data;
 
-extern void ptrace_triggered(struct perf_event *bp, int nmi,
+extern void ptrace_triggered(struct perf_event *bp,
 		      struct perf_sample_data *data, struct pt_regs *regs);
 
 #define task_pt_regs(task) \
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7757.c b/arch/sh/kernel/cpu/sh4a/setup-sh7757.c
index e915dea..0555929 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-sh7757.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7757.c
@@ -15,6 +15,7 @@
 #include <linux/serial_sci.h>
 #include <linux/io.h>
 #include <linux/mm.h>
+#include <linux/dma-mapping.h>
 #include <linux/sh_timer.h>
 #include <linux/sh_dma.h>
 
diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c
index 32114e0..db4ecd7 100644
--- a/arch/sh/kernel/idle.c
+++ b/arch/sh/kernel/idle.c
@@ -22,7 +22,7 @@
 #include <linux/atomic.h>
 #include <asm/smp.h>
 
-static void (*pm_idle)(void);
+void (*pm_idle)(void);
 
 static int hlt_counter;
 
diff --git a/arch/sh/kernel/syscalls_32.S b/arch/sh/kernel/syscalls_32.S
index 39b051d..293e39c 100644
--- a/arch/sh/kernel/syscalls_32.S
+++ b/arch/sh/kernel/syscalls_32.S
@@ -185,7 +185,7 @@
 	.long sys_ni_syscall	/* vm86 */
 	.long sys_ni_syscall	/* old "query_module" */
 	.long sys_poll
-	.long sys_nfsservctl
+	.long sys_ni_syscall	/* was nfsservctl */
 	.long sys_setresgid16	/* 170 */
 	.long sys_getresgid16
 	.long sys_prctl
diff --git a/arch/sh/kernel/syscalls_64.S b/arch/sh/kernel/syscalls_64.S
index 089c4d8..ceb34b9 100644
--- a/arch/sh/kernel/syscalls_64.S
+++ b/arch/sh/kernel/syscalls_64.S
@@ -189,7 +189,7 @@
 	.long sys_ni_syscall	/* vm86 */
 	.long sys_ni_syscall	/* old "query_module" */
 	.long sys_poll
-	.long sys_nfsservctl
+	.long sys_ni_syscall	/* was nfsservctl */
 	.long sys_setresgid16		/* 170 */
 	.long sys_getresgid16
 	.long sys_prctl
diff --git a/arch/sh/kernel/traps_32.c b/arch/sh/kernel/traps_32.c
index d9006f8..7bbef95 100644
--- a/arch/sh/kernel/traps_32.c
+++ b/arch/sh/kernel/traps_32.c
@@ -316,6 +316,35 @@
 			break;
 		}
 		break;
+
+	case 9: /* mov.w @(disp,PC),Rn */
+		srcu = (unsigned char __user *)regs->pc;
+		srcu += 4;
+		srcu += (instruction & 0x00FF) << 1;
+		dst = (unsigned char *)rn;
+		*(unsigned long *)dst = 0;
+
+#if !defined(__LITTLE_ENDIAN__)
+		dst += 2;
+#endif
+
+		if (ma->from(dst, srcu, 2))
+			goto fetch_fault;
+		sign_extend(2, dst);
+		ret = 0;
+		break;
+
+	case 0xd: /* mov.l @(disp,PC),Rn */
+		srcu = (unsigned char __user *)(regs->pc & ~0x3);
+		srcu += 4;
+		srcu += (instruction & 0x00FF) << 2;
+		dst = (unsigned char *)rn;
+		*(unsigned long *)dst = 0;
+
+		if (ma->from(dst, srcu, 4))
+			goto fetch_fault;
+		ret = 0;
+		break;
 	}
 	return ret;
 
@@ -466,6 +495,7 @@
 		case 0x0500: /* mov.w @(disp,Rm),R0 */
 			goto simple;
 		case 0x0B00: /* bf   lab - no delayslot*/
+			ret = 0;
 			break;
 		case 0x0F00: /* bf/s lab */
 			ret = handle_delayslot(regs, instruction, ma);
@@ -479,6 +509,7 @@
 			}
 			break;
 		case 0x0900: /* bt   lab - no delayslot */
+			ret = 0;
 			break;
 		case 0x0D00: /* bt/s lab */
 			ret = handle_delayslot(regs, instruction, ma);
@@ -494,6 +525,9 @@
 		}
 		break;
 
+	case 0x9000: /* mov.w @(disp,Rm),Rn */
+		goto simple;
+
 	case 0xA000: /* bra label */
 		ret = handle_delayslot(regs, instruction, ma);
 		if (ret==0)
@@ -507,6 +541,9 @@
 			regs->pc += SH_PC_12BIT_OFFSET(instruction);
 		}
 		break;
+
+	case 0xD000: /* mov.l @(disp,Rm),Rn */
+		goto simple;
 	}
 	return ret;
 
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 42c67be..1a6f20d 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -55,6 +55,7 @@
 	select PERF_USE_VMALLOC
 	select IRQ_PREFLOW_FASTEOI
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
+	select HAVE_C_RECORDMCOUNT
 
 config ARCH_DEFCONFIG
 	string
diff --git a/arch/sparc/include/asm/sigcontext.h b/arch/sparc/include/asm/sigcontext.h
index a1607d18..69914d7 100644
--- a/arch/sparc/include/asm/sigcontext.h
+++ b/arch/sparc/include/asm/sigcontext.h
@@ -45,6 +45,19 @@
 	int			si_mask;
 } __siginfo32_t;
 
+#define __SIGC_MAXWIN	7
+
+typedef struct {
+	unsigned long locals[8];
+	unsigned long ins[8];
+} __siginfo_reg_window;
+
+typedef struct {
+	int			wsaved;
+	__siginfo_reg_window	reg_window[__SIGC_MAXWIN];
+	unsigned long		rwbuf_stkptrs[__SIGC_MAXWIN];
+} __siginfo_rwin_t;
+
 #ifdef CONFIG_SPARC64
 typedef struct {
 	unsigned   int si_float_regs [64];
@@ -73,6 +86,7 @@
 		unsigned long	ss_size;
 	}			sigc_stack;
 	unsigned long		sigc_mask;
+	__siginfo_rwin_t *	sigc_rwin_save;
 };
 
 #else
diff --git a/arch/sparc/include/asm/spinlock_32.h b/arch/sparc/include/asm/spinlock_32.h
index 5f5b8bf..bcc98fc 100644
--- a/arch/sparc/include/asm/spinlock_32.h
+++ b/arch/sparc/include/asm/spinlock_32.h
@@ -131,6 +131,15 @@
 	*(volatile __u32 *)&lp->lock = ~0U;
 }
 
+static void inline arch_write_unlock(arch_rwlock_t *lock)
+{
+	__asm__ __volatile__(
+"	st		%%g0, [%0]"
+	: /* no outputs */
+	: "r" (lock)
+	: "memory");
+}
+
 static inline int arch_write_trylock(arch_rwlock_t *rw)
 {
 	unsigned int val;
@@ -175,8 +184,6 @@
 	res; \
 })
 
-#define arch_write_unlock(rw)	do { (rw)->lock = 0; } while(0)
-
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
 #define arch_read_lock_flags(rw, flags)   arch_read_lock(rw)
 #define arch_write_lock_flags(rw, flags)  arch_write_lock(rw)
diff --git a/arch/sparc/include/asm/spinlock_64.h b/arch/sparc/include/asm/spinlock_64.h
index 073936a..9689176 100644
--- a/arch/sparc/include/asm/spinlock_64.h
+++ b/arch/sparc/include/asm/spinlock_64.h
@@ -210,14 +210,8 @@
 	return result;
 }
 
-#define arch_read_lock(p)	arch_read_lock(p)
 #define arch_read_lock_flags(p, f) arch_read_lock(p)
-#define arch_read_trylock(p)	arch_read_trylock(p)
-#define arch_read_unlock(p)	arch_read_unlock(p)
-#define arch_write_lock(p)	arch_write_lock(p)
 #define arch_write_lock_flags(p, f) arch_write_lock(p)
-#define arch_write_unlock(p)	arch_write_unlock(p)
-#define arch_write_trylock(p)	arch_write_trylock(p)
 
 #define arch_read_can_lock(rw)		(!((rw)->lock & 0x80000000UL))
 #define arch_write_can_lock(rw)	(!(rw)->lock)
diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile
index b90b4a1..cb85458 100644
--- a/arch/sparc/kernel/Makefile
+++ b/arch/sparc/kernel/Makefile
@@ -32,6 +32,7 @@
 
 obj-y                   += process_$(BITS).o
 obj-y                   += signal_$(BITS).o
+obj-y                   += sigutil_$(BITS).o
 obj-$(CONFIG_SPARC32)   += ioport.o
 obj-y                   += setup_$(BITS).o
 obj-y                   += idprom.o
diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c
index 490e541..7429b47 100644
--- a/arch/sparc/kernel/ds.c
+++ b/arch/sparc/kernel/ds.c
@@ -1256,13 +1256,14 @@
 {
 	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;
+	if (tlb_type == hypervisor) {
+		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);
diff --git a/arch/sparc/kernel/irq.h b/arch/sparc/kernel/irq.h
index 100b9c2..4285112 100644
--- a/arch/sparc/kernel/irq.h
+++ b/arch/sparc/kernel/irq.h
@@ -88,7 +88,7 @@
 #define set_irq_udt(cpu) BTFIXUP_CALL(set_irq_udt)(cpu)
 
 /* All SUN4D IPIs are sent on this IRQ, may be shared with hard IRQs */
-#define SUN4D_IPI_IRQ 14
+#define SUN4D_IPI_IRQ 13
 
 extern void sun4d_ipi_interrupt(void);
 
diff --git a/arch/sparc/kernel/pcic.c b/arch/sparc/kernel/pcic.c
index a19f041..1aaf8c1 100644
--- a/arch/sparc/kernel/pcic.c
+++ b/arch/sparc/kernel/pcic.c
@@ -352,8 +352,8 @@
 	strcpy(pbm->prom_name, namebuf);
 
 	{
-		extern volatile int t_nmi[1];
-		extern int pcic_nmi_trap_patch[1];
+		extern volatile int t_nmi[4];
+		extern int pcic_nmi_trap_patch[4];
 
 		t_nmi[0] = pcic_nmi_trap_patch[0];
 		t_nmi[1] = pcic_nmi_trap_patch[1];
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index 3e9daea..3c5bb78 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -440,8 +440,14 @@
 			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 == cheetah_plus) {
+			unsigned long impl, ver;
+
+			__asm__ __volatile__("rdpr %%ver, %0" : "=r" (ver));
+			impl = ((ver >> 32) & 0xffff);
+			if (impl == PANTHER_IMPL)
+				cap |= AV_SPARC_POPC;
+		}
 		if (tlb_type == hypervisor) {
 			if (sun4v_chip_type == SUN4V_CHIP_NIAGARA1)
 				cap |= AV_SPARC_ASI_BLK_INIT;
diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c
index 75fad42..1ba95af 100644
--- a/arch/sparc/kernel/signal32.c
+++ b/arch/sparc/kernel/signal32.c
@@ -29,6 +29,8 @@
 #include <asm/visasm.h>
 #include <asm/compat_signal.h>
 
+#include "sigutil.h"
+
 #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
 
 /* This magic should be in g_upper[0] for all upper parts
@@ -44,14 +46,14 @@
 struct signal_frame32 {
 	struct sparc_stackf32	ss;
 	__siginfo32_t		info;
-	/* __siginfo_fpu32_t * */ u32 fpu_save;
+	/* __siginfo_fpu_t * */ u32 fpu_save;
 	unsigned int		insns[2];
 	unsigned int		extramask[_COMPAT_NSIG_WORDS - 1];
 	unsigned int		extra_size; /* Should be sizeof(siginfo_extra_v8plus_t) */
 	/* Only valid if (info.si_regs.psr & (PSR_VERS|PSR_IMPL)) == PSR_V8PLUS */
 	siginfo_extra_v8plus_t	v8plus;
-	__siginfo_fpu_t		fpu_state;
-};
+	/* __siginfo_rwin_t * */u32 rwin_save;
+} __attribute__((aligned(8)));
 
 typedef struct compat_siginfo{
 	int si_signo;
@@ -110,18 +112,14 @@
 	compat_siginfo_t	info;
 	struct pt_regs32	regs;
 	compat_sigset_t		mask;
-	/* __siginfo_fpu32_t * */ u32 fpu_save;
+	/* __siginfo_fpu_t * */ u32 fpu_save;
 	unsigned int		insns[2];
 	stack_t32		stack;
 	unsigned int		extra_size; /* Should be sizeof(siginfo_extra_v8plus_t) */
 	/* Only valid if (regs.psr & (PSR_VERS|PSR_IMPL)) == PSR_V8PLUS */
 	siginfo_extra_v8plus_t	v8plus;
-	__siginfo_fpu_t		fpu_state;
-};
-
-/* Align macros */
-#define SF_ALIGNEDSZ  (((sizeof(struct signal_frame32) + 15) & (~15)))
-#define RT_ALIGNEDSZ  (((sizeof(struct rt_signal_frame32) + 15) & (~15)))
+	/* __siginfo_rwin_t * */u32 rwin_save;
+} __attribute__((aligned(8)));
 
 int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
 {
@@ -192,30 +190,13 @@
 	return 0;
 }
 
-static int restore_fpu_state32(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
-{
-	unsigned long *fpregs = current_thread_info()->fpregs;
-	unsigned long fprs;
-	int err;
-	
-	err = __get_user(fprs, &fpu->si_fprs);
-	fprs_write(0);
-	regs->tstate &= ~TSTATE_PEF;
-	if (fprs & FPRS_DL)
-		err |= copy_from_user(fpregs, &fpu->si_float_regs[0], (sizeof(unsigned int) * 32));
-	if (fprs & FPRS_DU)
-		err |= copy_from_user(fpregs+16, &fpu->si_float_regs[32], (sizeof(unsigned int) * 32));
-	err |= __get_user(current_thread_info()->xfsr[0], &fpu->si_fsr);
-	err |= __get_user(current_thread_info()->gsr[0], &fpu->si_gsr);
-	current_thread_info()->fpsaved[0] |= fprs;
-	return err;
-}
-
 void do_sigreturn32(struct pt_regs *regs)
 {
 	struct signal_frame32 __user *sf;
+	compat_uptr_t fpu_save;
+	compat_uptr_t rwin_save;
 	unsigned int psr;
-	unsigned pc, npc, fpu_save;
+	unsigned pc, npc;
 	sigset_t set;
 	unsigned seta[_COMPAT_NSIG_WORDS];
 	int err, i;
@@ -273,8 +254,13 @@
 	pt_regs_clear_syscall(regs);
 
 	err |= __get_user(fpu_save, &sf->fpu_save);
-	if (fpu_save)
-		err |= restore_fpu_state32(regs, &sf->fpu_state);
+	if (!err && fpu_save)
+		err |= restore_fpu_state(regs, compat_ptr(fpu_save));
+	err |= __get_user(rwin_save, &sf->rwin_save);
+	if (!err && rwin_save) {
+		if (restore_rwin_state(compat_ptr(rwin_save)))
+			goto segv;
+	}
 	err |= __get_user(seta[0], &sf->info.si_mask);
 	err |= copy_from_user(seta+1, &sf->extramask,
 			      (_COMPAT_NSIG_WORDS - 1) * sizeof(unsigned int));
@@ -300,7 +286,9 @@
 asmlinkage void do_rt_sigreturn32(struct pt_regs *regs)
 {
 	struct rt_signal_frame32 __user *sf;
-	unsigned int psr, pc, npc, fpu_save, u_ss_sp;
+	unsigned int psr, pc, npc, u_ss_sp;
+	compat_uptr_t fpu_save;
+	compat_uptr_t rwin_save;
 	mm_segment_t old_fs;
 	sigset_t set;
 	compat_sigset_t seta;
@@ -359,8 +347,8 @@
 	pt_regs_clear_syscall(regs);
 
 	err |= __get_user(fpu_save, &sf->fpu_save);
-	if (fpu_save)
-		err |= restore_fpu_state32(regs, &sf->fpu_state);
+	if (!err && fpu_save)
+		err |= restore_fpu_state(regs, compat_ptr(fpu_save));
 	err |= copy_from_user(&seta, &sf->mask, sizeof(compat_sigset_t));
 	err |= __get_user(u_ss_sp, &sf->stack.ss_sp);
 	st.ss_sp = compat_ptr(u_ss_sp);
@@ -376,6 +364,12 @@
 	do_sigaltstack((stack_t __user *) &st, NULL, (unsigned long)sf);
 	set_fs(old_fs);
 	
+	err |= __get_user(rwin_save, &sf->rwin_save);
+	if (!err && rwin_save) {
+		if (restore_rwin_state(compat_ptr(rwin_save)))
+			goto segv;
+	}
+
 	switch (_NSIG_WORDS) {
 		case 4: set.sig[3] = seta.sig[6] + (((long)seta.sig[7]) << 32);
 		case 3: set.sig[2] = seta.sig[4] + (((long)seta.sig[5]) << 32);
@@ -433,26 +427,6 @@
 	return (void __user *) sp;
 }
 
-static int save_fpu_state32(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
-{
-	unsigned long *fpregs = current_thread_info()->fpregs;
-	unsigned long fprs;
-	int err = 0;
-	
-	fprs = current_thread_info()->fpsaved[0];
-	if (fprs & FPRS_DL)
-		err |= copy_to_user(&fpu->si_float_regs[0], fpregs,
-				    (sizeof(unsigned int) * 32));
-	if (fprs & FPRS_DU)
-		err |= copy_to_user(&fpu->si_float_regs[32], fpregs+16,
-				    (sizeof(unsigned int) * 32));
-	err |= __put_user(current_thread_info()->xfsr[0], &fpu->si_fsr);
-	err |= __put_user(current_thread_info()->gsr[0], &fpu->si_gsr);
-	err |= __put_user(fprs, &fpu->si_fprs);
-
-	return err;
-}
-
 /* The I-cache flush instruction only works in the primary ASI, which
  * right now is the nucleus, aka. kernel space.
  *
@@ -515,18 +489,23 @@
 			 int signo, sigset_t *oldset)
 {
 	struct signal_frame32 __user *sf;
+	int i, err, wsaved;
+	void __user *tail;
 	int sigframe_size;
 	u32 psr;
-	int i, err;
 	unsigned int seta[_COMPAT_NSIG_WORDS];
 
 	/* 1. Make sure everything is clean */
 	synchronize_user_stack();
 	save_and_clear_fpu();
 	
-	sigframe_size = SF_ALIGNEDSZ;
-	if (!(current_thread_info()->fpsaved[0] & FPRS_FEF))
-		sigframe_size -= sizeof(__siginfo_fpu_t);
+	wsaved = get_thread_wsaved();
+
+	sigframe_size = sizeof(*sf);
+	if (current_thread_info()->fpsaved[0] & FPRS_FEF)
+		sigframe_size += sizeof(__siginfo_fpu_t);
+	if (wsaved)
+		sigframe_size += sizeof(__siginfo_rwin_t);
 
 	sf = (struct signal_frame32 __user *)
 		get_sigframe(&ka->sa, regs, sigframe_size);
@@ -534,8 +513,7 @@
 	if (invalid_frame_pointer(sf, sigframe_size))
 		goto sigill;
 
-	if (get_thread_wsaved() != 0)
-		goto sigill;
+	tail = (sf + 1);
 
 	/* 2. Save the current process state */
 	if (test_thread_flag(TIF_32BIT)) {
@@ -560,11 +538,22 @@
 			  &sf->v8plus.asi);
 
 	if (psr & PSR_EF) {
-		err |= save_fpu_state32(regs, &sf->fpu_state);
-		err |= __put_user((u64)&sf->fpu_state, &sf->fpu_save);
+		__siginfo_fpu_t __user *fp = tail;
+		tail += sizeof(*fp);
+		err |= save_fpu_state(regs, fp);
+		err |= __put_user((u64)fp, &sf->fpu_save);
 	} else {
 		err |= __put_user(0, &sf->fpu_save);
 	}
+	if (wsaved) {
+		__siginfo_rwin_t __user *rwp = tail;
+		tail += sizeof(*rwp);
+		err |= save_rwin_state(wsaved, rwp);
+		err |= __put_user((u64)rwp, &sf->rwin_save);
+		set_thread_wsaved(0);
+	} else {
+		err |= __put_user(0, &sf->rwin_save);
+	}
 
 	switch (_NSIG_WORDS) {
 	case 4: seta[7] = (oldset->sig[3] >> 32);
@@ -580,10 +569,21 @@
 	err |= __copy_to_user(sf->extramask, seta + 1,
 			      (_COMPAT_NSIG_WORDS - 1) * sizeof(unsigned int));
 
-	err |= copy_in_user((u32 __user *)sf,
-			    (u32 __user *)(regs->u_regs[UREG_FP]),
-			    sizeof(struct reg_window32));
-	
+	if (!wsaved) {
+		err |= copy_in_user((u32 __user *)sf,
+				    (u32 __user *)(regs->u_regs[UREG_FP]),
+				    sizeof(struct reg_window32));
+	} else {
+		struct reg_window *rp;
+
+		rp = &current_thread_info()->reg_window[wsaved - 1];
+		for (i = 0; i < 8; i++)
+			err |= __put_user(rp->locals[i], &sf->ss.locals[i]);
+		for (i = 0; i < 6; i++)
+			err |= __put_user(rp->ins[i], &sf->ss.ins[i]);
+		err |= __put_user(rp->ins[6], &sf->ss.fp);
+		err |= __put_user(rp->ins[7], &sf->ss.callers_pc);
+	}	
 	if (err)
 		goto sigsegv;
 
@@ -613,7 +613,6 @@
 		err |= __put_user(0x91d02010, &sf->insns[1]); /*t 0x10*/
 		if (err)
 			goto sigsegv;
-
 		flush_signal_insns(address);
 	}
 	return 0;
@@ -632,18 +631,23 @@
 			    siginfo_t *info)
 {
 	struct rt_signal_frame32 __user *sf;
+	int i, err, wsaved;
+	void __user *tail;
 	int sigframe_size;
 	u32 psr;
-	int i, err;
 	compat_sigset_t seta;
 
 	/* 1. Make sure everything is clean */
 	synchronize_user_stack();
 	save_and_clear_fpu();
 	
-	sigframe_size = RT_ALIGNEDSZ;
-	if (!(current_thread_info()->fpsaved[0] & FPRS_FEF))
-		sigframe_size -= sizeof(__siginfo_fpu_t);
+	wsaved = get_thread_wsaved();
+
+	sigframe_size = sizeof(*sf);
+	if (current_thread_info()->fpsaved[0] & FPRS_FEF)
+		sigframe_size += sizeof(__siginfo_fpu_t);
+	if (wsaved)
+		sigframe_size += sizeof(__siginfo_rwin_t);
 
 	sf = (struct rt_signal_frame32 __user *)
 		get_sigframe(&ka->sa, regs, sigframe_size);
@@ -651,8 +655,7 @@
 	if (invalid_frame_pointer(sf, sigframe_size))
 		goto sigill;
 
-	if (get_thread_wsaved() != 0)
-		goto sigill;
+	tail = (sf + 1);
 
 	/* 2. Save the current process state */
 	if (test_thread_flag(TIF_32BIT)) {
@@ -677,11 +680,22 @@
 			  &sf->v8plus.asi);
 
 	if (psr & PSR_EF) {
-		err |= save_fpu_state32(regs, &sf->fpu_state);
-		err |= __put_user((u64)&sf->fpu_state, &sf->fpu_save);
+		__siginfo_fpu_t __user *fp = tail;
+		tail += sizeof(*fp);
+		err |= save_fpu_state(regs, fp);
+		err |= __put_user((u64)fp, &sf->fpu_save);
 	} else {
 		err |= __put_user(0, &sf->fpu_save);
 	}
+	if (wsaved) {
+		__siginfo_rwin_t __user *rwp = tail;
+		tail += sizeof(*rwp);
+		err |= save_rwin_state(wsaved, rwp);
+		err |= __put_user((u64)rwp, &sf->rwin_save);
+		set_thread_wsaved(0);
+	} else {
+		err |= __put_user(0, &sf->rwin_save);
+	}
 
 	/* Update the siginfo structure.  */
 	err |= copy_siginfo_to_user32(&sf->info, info);
@@ -703,9 +717,21 @@
 	}
 	err |= __copy_to_user(&sf->mask, &seta, sizeof(compat_sigset_t));
 
-	err |= copy_in_user((u32 __user *)sf,
-			    (u32 __user *)(regs->u_regs[UREG_FP]),
-			    sizeof(struct reg_window32));
+	if (!wsaved) {
+		err |= copy_in_user((u32 __user *)sf,
+				    (u32 __user *)(regs->u_regs[UREG_FP]),
+				    sizeof(struct reg_window32));
+	} else {
+		struct reg_window *rp;
+
+		rp = &current_thread_info()->reg_window[wsaved - 1];
+		for (i = 0; i < 8; i++)
+			err |= __put_user(rp->locals[i], &sf->ss.locals[i]);
+		for (i = 0; i < 6; i++)
+			err |= __put_user(rp->ins[i], &sf->ss.ins[i]);
+		err |= __put_user(rp->ins[6], &sf->ss.fp);
+		err |= __put_user(rp->ins[7], &sf->ss.callers_pc);
+	}
 	if (err)
 		goto sigsegv;
 	
diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c
index 5e5c5fd..04ede8f 100644
--- a/arch/sparc/kernel/signal_32.c
+++ b/arch/sparc/kernel/signal_32.c
@@ -26,6 +26,8 @@
 #include <asm/pgtable.h>
 #include <asm/cacheflush.h>	/* flush_sig_insns */
 
+#include "sigutil.h"
+
 #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
 
 extern void fpsave(unsigned long *fpregs, unsigned long *fsr,
@@ -39,8 +41,8 @@
 	unsigned long		insns[2] __attribute__ ((aligned (8)));
 	unsigned int		extramask[_NSIG_WORDS - 1];
 	unsigned int		extra_size; /* Should be 0 */
-	__siginfo_fpu_t		fpu_state;
-};
+	__siginfo_rwin_t __user	*rwin_save;
+} __attribute__((aligned(8)));
 
 struct rt_signal_frame {
 	struct sparc_stackf	ss;
@@ -51,8 +53,8 @@
 	unsigned int		insns[2];
 	stack_t			stack;
 	unsigned int		extra_size; /* Should be 0 */
-	__siginfo_fpu_t		fpu_state;
-};
+	__siginfo_rwin_t __user	*rwin_save;
+} __attribute__((aligned(8)));
 
 /* Align macros */
 #define SF_ALIGNEDSZ  (((sizeof(struct signal_frame) + 7) & (~7)))
@@ -79,43 +81,13 @@
 	return _sigpause_common(set);
 }
 
-static inline int
-restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
-{
-	int err;
-#ifdef CONFIG_SMP
-	if (test_tsk_thread_flag(current, TIF_USEDFPU))
-		regs->psr &= ~PSR_EF;
-#else
-	if (current == last_task_used_math) {
-		last_task_used_math = NULL;
-		regs->psr &= ~PSR_EF;
-	}
-#endif
-	set_used_math();
-	clear_tsk_thread_flag(current, TIF_USEDFPU);
-
-	if (!access_ok(VERIFY_READ, fpu, sizeof(*fpu)))
-		return -EFAULT;
-
-	err = __copy_from_user(&current->thread.float_regs[0], &fpu->si_float_regs[0],
-			       (sizeof(unsigned long) * 32));
-	err |= __get_user(current->thread.fsr, &fpu->si_fsr);
-	err |= __get_user(current->thread.fpqdepth, &fpu->si_fpqdepth);
-	if (current->thread.fpqdepth != 0)
-		err |= __copy_from_user(&current->thread.fpqueue[0],
-					&fpu->si_fpqueue[0],
-					((sizeof(unsigned long) +
-					(sizeof(unsigned long *)))*16));
-	return err;
-}
-
 asmlinkage void do_sigreturn(struct pt_regs *regs)
 {
 	struct signal_frame __user *sf;
 	unsigned long up_psr, pc, npc;
 	sigset_t set;
 	__siginfo_fpu_t __user *fpu_save;
+	__siginfo_rwin_t __user *rwin_save;
 	int err;
 
 	/* Always make any pending restarted system calls return -EINTR */
@@ -150,9 +122,11 @@
 	pt_regs_clear_syscall(regs);
 
 	err |= __get_user(fpu_save, &sf->fpu_save);
-
 	if (fpu_save)
 		err |= restore_fpu_state(regs, fpu_save);
+	err |= __get_user(rwin_save, &sf->rwin_save);
+	if (rwin_save)
+		err |= restore_rwin_state(rwin_save);
 
 	/* This is pretty much atomic, no amount locking would prevent
 	 * the races which exist anyways.
@@ -180,6 +154,7 @@
 	struct rt_signal_frame __user *sf;
 	unsigned int psr, pc, npc;
 	__siginfo_fpu_t __user *fpu_save;
+	__siginfo_rwin_t __user *rwin_save;
 	mm_segment_t old_fs;
 	sigset_t set;
 	stack_t st;
@@ -207,8 +182,7 @@
 	pt_regs_clear_syscall(regs);
 
 	err |= __get_user(fpu_save, &sf->fpu_save);
-
-	if (fpu_save)
+	if (!err && fpu_save)
 		err |= restore_fpu_state(regs, fpu_save);
 	err |= __copy_from_user(&set, &sf->mask, sizeof(sigset_t));
 	
@@ -228,6 +202,12 @@
 	do_sigaltstack((const stack_t __user *) &st, NULL, (unsigned long)sf);
 	set_fs(old_fs);
 
+	err |= __get_user(rwin_save, &sf->rwin_save);
+	if (!err && rwin_save) {
+		if (restore_rwin_state(rwin_save))
+			goto segv;
+	}
+
 	sigdelsetmask(&set, ~_BLOCKABLE);
 	spin_lock_irq(&current->sighand->siglock);
 	current->blocked = set;
@@ -280,53 +260,23 @@
 	return (void __user *) sp;
 }
 
-static inline int
-save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
-{
-	int err = 0;
-#ifdef CONFIG_SMP
-	if (test_tsk_thread_flag(current, TIF_USEDFPU)) {
-		put_psr(get_psr() | PSR_EF);
-		fpsave(&current->thread.float_regs[0], &current->thread.fsr,
-		       &current->thread.fpqueue[0], &current->thread.fpqdepth);
-		regs->psr &= ~(PSR_EF);
-		clear_tsk_thread_flag(current, TIF_USEDFPU);
-	}
-#else
-	if (current == last_task_used_math) {
-		put_psr(get_psr() | PSR_EF);
-		fpsave(&current->thread.float_regs[0], &current->thread.fsr,
-		       &current->thread.fpqueue[0], &current->thread.fpqdepth);
-		last_task_used_math = NULL;
-		regs->psr &= ~(PSR_EF);
-	}
-#endif
-	err |= __copy_to_user(&fpu->si_float_regs[0],
-			      &current->thread.float_regs[0],
-			      (sizeof(unsigned long) * 32));
-	err |= __put_user(current->thread.fsr, &fpu->si_fsr);
-	err |= __put_user(current->thread.fpqdepth, &fpu->si_fpqdepth);
-	if (current->thread.fpqdepth != 0)
-		err |= __copy_to_user(&fpu->si_fpqueue[0],
-				      &current->thread.fpqueue[0],
-				      ((sizeof(unsigned long) +
-				      (sizeof(unsigned long *)))*16));
-	clear_used_math();
-	return err;
-}
-
 static int setup_frame(struct k_sigaction *ka, struct pt_regs *regs,
 		       int signo, sigset_t *oldset)
 {
 	struct signal_frame __user *sf;
-	int sigframe_size, err;
+	int sigframe_size, err, wsaved;
+	void __user *tail;
 
 	/* 1. Make sure everything is clean */
 	synchronize_user_stack();
 
-	sigframe_size = SF_ALIGNEDSZ;
-	if (!used_math())
-		sigframe_size -= sizeof(__siginfo_fpu_t);
+	wsaved = current_thread_info()->w_saved;
+
+	sigframe_size = sizeof(*sf);
+	if (used_math())
+		sigframe_size += sizeof(__siginfo_fpu_t);
+	if (wsaved)
+		sigframe_size += sizeof(__siginfo_rwin_t);
 
 	sf = (struct signal_frame __user *)
 		get_sigframe(&ka->sa, regs, sigframe_size);
@@ -334,8 +284,7 @@
 	if (invalid_frame_pointer(sf, sigframe_size))
 		goto sigill_and_return;
 
-	if (current_thread_info()->w_saved != 0)
-		goto sigill_and_return;
+	tail = sf + 1;
 
 	/* 2. Save the current process state */
 	err = __copy_to_user(&sf->info.si_regs, regs, sizeof(struct pt_regs));
@@ -343,17 +292,34 @@
 	err |= __put_user(0, &sf->extra_size);
 
 	if (used_math()) {
-		err |= save_fpu_state(regs, &sf->fpu_state);
-		err |= __put_user(&sf->fpu_state, &sf->fpu_save);
+		__siginfo_fpu_t __user *fp = tail;
+		tail += sizeof(*fp);
+		err |= save_fpu_state(regs, fp);
+		err |= __put_user(fp, &sf->fpu_save);
 	} else {
 		err |= __put_user(0, &sf->fpu_save);
 	}
+	if (wsaved) {
+		__siginfo_rwin_t __user *rwp = tail;
+		tail += sizeof(*rwp);
+		err |= save_rwin_state(wsaved, rwp);
+		err |= __put_user(rwp, &sf->rwin_save);
+	} else {
+		err |= __put_user(0, &sf->rwin_save);
+	}
 
 	err |= __put_user(oldset->sig[0], &sf->info.si_mask);
 	err |= __copy_to_user(sf->extramask, &oldset->sig[1],
 			      (_NSIG_WORDS - 1) * sizeof(unsigned int));
-	err |= __copy_to_user(sf, (char *) regs->u_regs[UREG_FP],
-			      sizeof(struct reg_window32));
+	if (!wsaved) {
+		err |= __copy_to_user(sf, (char *) regs->u_regs[UREG_FP],
+				      sizeof(struct reg_window32));
+	} else {
+		struct reg_window32 *rp;
+
+		rp = &current_thread_info()->reg_window[wsaved - 1];
+		err |= __copy_to_user(sf, rp, sizeof(struct reg_window32));
+	}
 	if (err)
 		goto sigsegv;
 	
@@ -399,21 +365,24 @@
 			  int signo, sigset_t *oldset, siginfo_t *info)
 {
 	struct rt_signal_frame __user *sf;
-	int sigframe_size;
+	int sigframe_size, wsaved;
+	void __user *tail;
 	unsigned int psr;
 	int err;
 
 	synchronize_user_stack();
-	sigframe_size = RT_ALIGNEDSZ;
-	if (!used_math())
-		sigframe_size -= sizeof(__siginfo_fpu_t);
+	wsaved = current_thread_info()->w_saved;
+	sigframe_size = sizeof(*sf);
+	if (used_math())
+		sigframe_size += sizeof(__siginfo_fpu_t);
+	if (wsaved)
+		sigframe_size += sizeof(__siginfo_rwin_t);
 	sf = (struct rt_signal_frame __user *)
 		get_sigframe(&ka->sa, regs, sigframe_size);
 	if (invalid_frame_pointer(sf, sigframe_size))
 		goto sigill;
-	if (current_thread_info()->w_saved != 0)
-		goto sigill;
 
+	tail = sf + 1;
 	err  = __put_user(regs->pc, &sf->regs.pc);
 	err |= __put_user(regs->npc, &sf->regs.npc);
 	err |= __put_user(regs->y, &sf->regs.y);
@@ -425,11 +394,21 @@
 	err |= __put_user(0, &sf->extra_size);
 
 	if (psr & PSR_EF) {
-		err |= save_fpu_state(regs, &sf->fpu_state);
-		err |= __put_user(&sf->fpu_state, &sf->fpu_save);
+		__siginfo_fpu_t *fp = tail;
+		tail += sizeof(*fp);
+		err |= save_fpu_state(regs, fp);
+		err |= __put_user(fp, &sf->fpu_save);
 	} else {
 		err |= __put_user(0, &sf->fpu_save);
 	}
+	if (wsaved) {
+		__siginfo_rwin_t *rwp = tail;
+		tail += sizeof(*rwp);
+		err |= save_rwin_state(wsaved, rwp);
+		err |= __put_user(rwp, &sf->rwin_save);
+	} else {
+		err |= __put_user(0, &sf->rwin_save);
+	}
 	err |= __copy_to_user(&sf->mask, &oldset->sig[0], sizeof(sigset_t));
 	
 	/* Setup sigaltstack */
@@ -437,8 +416,15 @@
 	err |= __put_user(sas_ss_flags(regs->u_regs[UREG_FP]), &sf->stack.ss_flags);
 	err |= __put_user(current->sas_ss_size, &sf->stack.ss_size);
 	
-	err |= __copy_to_user(sf, (char *) regs->u_regs[UREG_FP],
-			      sizeof(struct reg_window32));
+	if (!wsaved) {
+		err |= __copy_to_user(sf, (char *) regs->u_regs[UREG_FP],
+				      sizeof(struct reg_window32));
+	} else {
+		struct reg_window32 *rp;
+
+		rp = &current_thread_info()->reg_window[wsaved - 1];
+		err |= __copy_to_user(sf, rp, sizeof(struct reg_window32));
+	}
 
 	err |= copy_siginfo_to_user(&sf->info, info);
 
diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c
index 006fe45..47509df 100644
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@@ -34,6 +34,7 @@
 
 #include "entry.h"
 #include "systbls.h"
+#include "sigutil.h"
 
 #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
 
@@ -236,7 +237,7 @@
 	__siginfo_fpu_t __user	*fpu_save;
 	stack_t			stack;
 	sigset_t		mask;
-	__siginfo_fpu_t		fpu_state;
+	__siginfo_rwin_t	*rwin_save;
 };
 
 static long _sigpause_common(old_sigset_t set)
@@ -266,33 +267,12 @@
 	return _sigpause_common(set);
 }
 
-static inline int
-restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
-{
-	unsigned long *fpregs = current_thread_info()->fpregs;
-	unsigned long fprs;
-	int err;
-
-	err = __get_user(fprs, &fpu->si_fprs);
-	fprs_write(0);
-	regs->tstate &= ~TSTATE_PEF;
-	if (fprs & FPRS_DL)
-		err |= copy_from_user(fpregs, &fpu->si_float_regs[0],
-		       	       (sizeof(unsigned int) * 32));
-	if (fprs & FPRS_DU)
-		err |= copy_from_user(fpregs+16, &fpu->si_float_regs[32],
-		       	       (sizeof(unsigned int) * 32));
-	err |= __get_user(current_thread_info()->xfsr[0], &fpu->si_fsr);
-	err |= __get_user(current_thread_info()->gsr[0], &fpu->si_gsr);
-	current_thread_info()->fpsaved[0] |= fprs;
-	return err;
-}
-
 void do_rt_sigreturn(struct pt_regs *regs)
 {
 	struct rt_signal_frame __user *sf;
 	unsigned long tpc, tnpc, tstate;
 	__siginfo_fpu_t __user *fpu_save;
+	__siginfo_rwin_t __user *rwin_save;
 	sigset_t set;
 	int err;
 
@@ -325,8 +305,8 @@
 	regs->tstate |= (tstate & (TSTATE_ASI | TSTATE_ICC | TSTATE_XCC));
 
 	err |= __get_user(fpu_save, &sf->fpu_save);
-	if (fpu_save)
-		err |= restore_fpu_state(regs, &sf->fpu_state);
+	if (!err && fpu_save)
+		err |= restore_fpu_state(regs, fpu_save);
 
 	err |= __copy_from_user(&set, &sf->mask, sizeof(sigset_t));
 	err |= do_sigaltstack(&sf->stack, NULL, (unsigned long)sf);
@@ -334,6 +314,12 @@
 	if (err)
 		goto segv;
 
+	err |= __get_user(rwin_save, &sf->rwin_save);
+	if (!err && rwin_save) {
+		if (restore_rwin_state(rwin_save))
+			goto segv;
+	}
+
 	regs->tpc = tpc;
 	regs->tnpc = tnpc;
 
@@ -351,34 +337,13 @@
 }
 
 /* Checks if the fp is valid */
-static int invalid_frame_pointer(void __user *fp, int fplen)
+static int invalid_frame_pointer(void __user *fp)
 {
 	if (((unsigned long) fp) & 15)
 		return 1;
 	return 0;
 }
 
-static inline int
-save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
-{
-	unsigned long *fpregs = current_thread_info()->fpregs;
-	unsigned long fprs;
-	int err = 0;
-	
-	fprs = current_thread_info()->fpsaved[0];
-	if (fprs & FPRS_DL)
-		err |= copy_to_user(&fpu->si_float_regs[0], fpregs,
-				    (sizeof(unsigned int) * 32));
-	if (fprs & FPRS_DU)
-		err |= copy_to_user(&fpu->si_float_regs[32], fpregs+16,
-				    (sizeof(unsigned int) * 32));
-	err |= __put_user(current_thread_info()->xfsr[0], &fpu->si_fsr);
-	err |= __put_user(current_thread_info()->gsr[0], &fpu->si_gsr);
-	err |= __put_user(fprs, &fpu->si_fprs);
-
-	return err;
-}
-
 static inline void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, unsigned long framesize)
 {
 	unsigned long sp = regs->u_regs[UREG_FP] + STACK_BIAS;
@@ -414,34 +379,48 @@
 	       int signo, sigset_t *oldset, siginfo_t *info)
 {
 	struct rt_signal_frame __user *sf;
-	int sigframe_size, err;
+	int wsaved, err, sf_size;
+	void __user *tail;
 
 	/* 1. Make sure everything is clean */
 	synchronize_user_stack();
 	save_and_clear_fpu();
 	
-	sigframe_size = sizeof(struct rt_signal_frame);
-	if (!(current_thread_info()->fpsaved[0] & FPRS_FEF))
-		sigframe_size -= sizeof(__siginfo_fpu_t);
+	wsaved = get_thread_wsaved();
 
+	sf_size = sizeof(struct rt_signal_frame);
+	if (current_thread_info()->fpsaved[0] & FPRS_FEF)
+		sf_size += sizeof(__siginfo_fpu_t);
+	if (wsaved)
+		sf_size += sizeof(__siginfo_rwin_t);
 	sf = (struct rt_signal_frame __user *)
-		get_sigframe(ka, regs, sigframe_size);
-	
-	if (invalid_frame_pointer (sf, sigframe_size))
+		get_sigframe(ka, regs, sf_size);
+
+	if (invalid_frame_pointer (sf))
 		goto sigill;
 
-	if (get_thread_wsaved() != 0)
-		goto sigill;
+	tail = (sf + 1);
 
 	/* 2. Save the current process state */
 	err = copy_to_user(&sf->regs, regs, sizeof (*regs));
 
 	if (current_thread_info()->fpsaved[0] & FPRS_FEF) {
-		err |= save_fpu_state(regs, &sf->fpu_state);
-		err |= __put_user((u64)&sf->fpu_state, &sf->fpu_save);
+		__siginfo_fpu_t __user *fpu_save = tail;
+		tail += sizeof(__siginfo_fpu_t);
+		err |= save_fpu_state(regs, fpu_save);
+		err |= __put_user((u64)fpu_save, &sf->fpu_save);
 	} else {
 		err |= __put_user(0, &sf->fpu_save);
 	}
+	if (wsaved) {
+		__siginfo_rwin_t __user *rwin_save = tail;
+		tail += sizeof(__siginfo_rwin_t);
+		err |= save_rwin_state(wsaved, rwin_save);
+		err |= __put_user((u64)rwin_save, &sf->rwin_save);
+		set_thread_wsaved(0);
+	} else {
+		err |= __put_user(0, &sf->rwin_save);
+	}
 	
 	/* Setup sigaltstack */
 	err |= __put_user(current->sas_ss_sp, &sf->stack.ss_sp);
@@ -450,10 +429,17 @@
 
 	err |= copy_to_user(&sf->mask, oldset, sizeof(sigset_t));
 
-	err |= copy_in_user((u64 __user *)sf,
-			    (u64 __user *)(regs->u_regs[UREG_FP]+STACK_BIAS),
-			    sizeof(struct reg_window));
+	if (!wsaved) {
+		err |= copy_in_user((u64 __user *)sf,
+				    (u64 __user *)(regs->u_regs[UREG_FP] +
+						   STACK_BIAS),
+				    sizeof(struct reg_window));
+	} else {
+		struct reg_window *rp;
 
+		rp = &current_thread_info()->reg_window[wsaved - 1];
+		err |= copy_to_user(sf, rp, sizeof(struct reg_window));
+	}
 	if (info)
 		err |= copy_siginfo_to_user(&sf->info, info);
 	else {
diff --git a/arch/sparc/kernel/sigutil.h b/arch/sparc/kernel/sigutil.h
new file mode 100644
index 0000000..d223aa4
--- /dev/null
+++ b/arch/sparc/kernel/sigutil.h
@@ -0,0 +1,9 @@
+#ifndef _SIGUTIL_H
+#define _SIGUTIL_H
+
+int save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu);
+int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu);
+int save_rwin_state(int wsaved, __siginfo_rwin_t __user *rwin);
+int restore_rwin_state(__siginfo_rwin_t __user *rp);
+
+#endif /* _SIGUTIL_H */
diff --git a/arch/sparc/kernel/sigutil_32.c b/arch/sparc/kernel/sigutil_32.c
new file mode 100644
index 0000000..35c7897
--- /dev/null
+++ b/arch/sparc/kernel/sigutil_32.c
@@ -0,0 +1,120 @@
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/thread_info.h>
+#include <linux/uaccess.h>
+#include <linux/sched.h>
+
+#include <asm/sigcontext.h>
+#include <asm/fpumacro.h>
+#include <asm/ptrace.h>
+
+#include "sigutil.h"
+
+int save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
+{
+	int err = 0;
+#ifdef CONFIG_SMP
+	if (test_tsk_thread_flag(current, TIF_USEDFPU)) {
+		put_psr(get_psr() | PSR_EF);
+		fpsave(&current->thread.float_regs[0], &current->thread.fsr,
+		       &current->thread.fpqueue[0], &current->thread.fpqdepth);
+		regs->psr &= ~(PSR_EF);
+		clear_tsk_thread_flag(current, TIF_USEDFPU);
+	}
+#else
+	if (current == last_task_used_math) {
+		put_psr(get_psr() | PSR_EF);
+		fpsave(&current->thread.float_regs[0], &current->thread.fsr,
+		       &current->thread.fpqueue[0], &current->thread.fpqdepth);
+		last_task_used_math = NULL;
+		regs->psr &= ~(PSR_EF);
+	}
+#endif
+	err |= __copy_to_user(&fpu->si_float_regs[0],
+			      &current->thread.float_regs[0],
+			      (sizeof(unsigned long) * 32));
+	err |= __put_user(current->thread.fsr, &fpu->si_fsr);
+	err |= __put_user(current->thread.fpqdepth, &fpu->si_fpqdepth);
+	if (current->thread.fpqdepth != 0)
+		err |= __copy_to_user(&fpu->si_fpqueue[0],
+				      &current->thread.fpqueue[0],
+				      ((sizeof(unsigned long) +
+				      (sizeof(unsigned long *)))*16));
+	clear_used_math();
+	return err;
+}
+
+int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
+{
+	int err;
+#ifdef CONFIG_SMP
+	if (test_tsk_thread_flag(current, TIF_USEDFPU))
+		regs->psr &= ~PSR_EF;
+#else
+	if (current == last_task_used_math) {
+		last_task_used_math = NULL;
+		regs->psr &= ~PSR_EF;
+	}
+#endif
+	set_used_math();
+	clear_tsk_thread_flag(current, TIF_USEDFPU);
+
+	if (!access_ok(VERIFY_READ, fpu, sizeof(*fpu)))
+		return -EFAULT;
+
+	err = __copy_from_user(&current->thread.float_regs[0], &fpu->si_float_regs[0],
+			       (sizeof(unsigned long) * 32));
+	err |= __get_user(current->thread.fsr, &fpu->si_fsr);
+	err |= __get_user(current->thread.fpqdepth, &fpu->si_fpqdepth);
+	if (current->thread.fpqdepth != 0)
+		err |= __copy_from_user(&current->thread.fpqueue[0],
+					&fpu->si_fpqueue[0],
+					((sizeof(unsigned long) +
+					(sizeof(unsigned long *)))*16));
+	return err;
+}
+
+int save_rwin_state(int wsaved, __siginfo_rwin_t __user *rwin)
+{
+	int i, err = __put_user(wsaved, &rwin->wsaved);
+
+	for (i = 0; i < wsaved; i++) {
+		struct reg_window32 *rp;
+		unsigned long fp;
+
+		rp = &current_thread_info()->reg_window[i];
+		fp = current_thread_info()->rwbuf_stkptrs[i];
+		err |= copy_to_user(&rwin->reg_window[i], rp,
+				    sizeof(struct reg_window32));
+		err |= __put_user(fp, &rwin->rwbuf_stkptrs[i]);
+	}
+	return err;
+}
+
+int restore_rwin_state(__siginfo_rwin_t __user *rp)
+{
+	struct thread_info *t = current_thread_info();
+	int i, wsaved, err;
+
+	__get_user(wsaved, &rp->wsaved);
+	if (wsaved > NSWINS)
+		return -EFAULT;
+
+	err = 0;
+	for (i = 0; i < wsaved; i++) {
+		err |= copy_from_user(&t->reg_window[i],
+				      &rp->reg_window[i],
+				      sizeof(struct reg_window32));
+		err |= __get_user(t->rwbuf_stkptrs[i],
+				  &rp->rwbuf_stkptrs[i]);
+	}
+	if (err)
+		return err;
+
+	t->w_saved = wsaved;
+	synchronize_user_stack();
+	if (t->w_saved)
+		return -EFAULT;
+	return 0;
+
+}
diff --git a/arch/sparc/kernel/sigutil_64.c b/arch/sparc/kernel/sigutil_64.c
new file mode 100644
index 0000000..e7dc508
--- /dev/null
+++ b/arch/sparc/kernel/sigutil_64.c
@@ -0,0 +1,93 @@
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/thread_info.h>
+#include <linux/uaccess.h>
+
+#include <asm/sigcontext.h>
+#include <asm/fpumacro.h>
+#include <asm/ptrace.h>
+
+#include "sigutil.h"
+
+int save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
+{
+	unsigned long *fpregs = current_thread_info()->fpregs;
+	unsigned long fprs;
+	int err = 0;
+	
+	fprs = current_thread_info()->fpsaved[0];
+	if (fprs & FPRS_DL)
+		err |= copy_to_user(&fpu->si_float_regs[0], fpregs,
+				    (sizeof(unsigned int) * 32));
+	if (fprs & FPRS_DU)
+		err |= copy_to_user(&fpu->si_float_regs[32], fpregs+16,
+				    (sizeof(unsigned int) * 32));
+	err |= __put_user(current_thread_info()->xfsr[0], &fpu->si_fsr);
+	err |= __put_user(current_thread_info()->gsr[0], &fpu->si_gsr);
+	err |= __put_user(fprs, &fpu->si_fprs);
+
+	return err;
+}
+
+int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
+{
+	unsigned long *fpregs = current_thread_info()->fpregs;
+	unsigned long fprs;
+	int err;
+
+	err = __get_user(fprs, &fpu->si_fprs);
+	fprs_write(0);
+	regs->tstate &= ~TSTATE_PEF;
+	if (fprs & FPRS_DL)
+		err |= copy_from_user(fpregs, &fpu->si_float_regs[0],
+		       	       (sizeof(unsigned int) * 32));
+	if (fprs & FPRS_DU)
+		err |= copy_from_user(fpregs+16, &fpu->si_float_regs[32],
+		       	       (sizeof(unsigned int) * 32));
+	err |= __get_user(current_thread_info()->xfsr[0], &fpu->si_fsr);
+	err |= __get_user(current_thread_info()->gsr[0], &fpu->si_gsr);
+	current_thread_info()->fpsaved[0] |= fprs;
+	return err;
+}
+
+int save_rwin_state(int wsaved, __siginfo_rwin_t __user *rwin)
+{
+	int i, err = __put_user(wsaved, &rwin->wsaved);
+
+	for (i = 0; i < wsaved; i++) {
+		struct reg_window *rp = &current_thread_info()->reg_window[i];
+		unsigned long fp = current_thread_info()->rwbuf_stkptrs[i];
+
+		err |= copy_to_user(&rwin->reg_window[i], rp,
+				    sizeof(struct reg_window));
+		err |= __put_user(fp, &rwin->rwbuf_stkptrs[i]);
+	}
+	return err;
+}
+
+int restore_rwin_state(__siginfo_rwin_t __user *rp)
+{
+	struct thread_info *t = current_thread_info();
+	int i, wsaved, err;
+
+	__get_user(wsaved, &rp->wsaved);
+	if (wsaved > NSWINS)
+		return -EFAULT;
+
+	err = 0;
+	for (i = 0; i < wsaved; i++) {
+		err |= copy_from_user(&t->reg_window[i],
+				      &rp->reg_window[i],
+				      sizeof(struct reg_window));
+		err |= __get_user(t->rwbuf_stkptrs[i],
+				  &rp->rwbuf_stkptrs[i]);
+	}
+	if (err)
+		return err;
+
+	set_thread_wsaved(wsaved);
+	synchronize_user_stack();
+	if (get_thread_wsaved())
+		return -EFAULT;
+	return 0;
+}
diff --git a/arch/sparc/kernel/sys32.S b/arch/sparc/kernel/sys32.S
index 44e5faf..d97f3eb 100644
--- a/arch/sparc/kernel/sys32.S
+++ b/arch/sparc/kernel/sys32.S
@@ -81,7 +81,6 @@
 SIGN2(sys32_fadvise64_64, compat_sys_fadvise64_64, %o0, %o5)
 SIGN2(sys32_bdflush, sys_bdflush, %o0, %o1)
 SIGN1(sys32_mlockall, sys_mlockall, %o0)
-SIGN1(sys32_nfsservctl, compat_sys_nfsservctl, %o0)
 SIGN1(sys32_clock_nanosleep, compat_sys_clock_nanosleep, %o1)
 SIGN1(sys32_timer_settime, compat_sys_timer_settime, %o1)
 SIGN1(sys32_io_submit, compat_sys_io_submit, %o1)
diff --git a/arch/sparc/kernel/systbls_32.S b/arch/sparc/kernel/systbls_32.S
index 6e492d5..09d8ec4 100644
--- a/arch/sparc/kernel/systbls_32.S
+++ b/arch/sparc/kernel/systbls_32.S
@@ -67,7 +67,7 @@
 /*235*/	.long sys_fstatfs64, sys_llseek, sys_mlock, sys_munlock, sys_mlockall
 /*240*/	.long sys_munlockall, sys_sched_setparam, sys_sched_getparam, sys_sched_setscheduler, sys_sched_getscheduler
 /*245*/	.long sys_sched_yield, sys_sched_get_priority_max, sys_sched_get_priority_min, sys_sched_rr_get_interval, sys_nanosleep
-/*250*/	.long sys_mremap, sys_sysctl, sys_getsid, sys_fdatasync, sys_nfsservctl
+/*250*/	.long sys_mremap, sys_sysctl, sys_getsid, sys_fdatasync, sys_ni_syscall
 /*255*/	.long sys_sync_file_range, sys_clock_settime, sys_clock_gettime, sys_clock_getres, sys_clock_nanosleep
 /*260*/	.long sys_sched_getaffinity, sys_sched_setaffinity, sys_timer_settime, sys_timer_gettime, sys_timer_getoverrun
 /*265*/	.long sys_timer_delete, sys_timer_create, sys_nis_syscall, sys_io_setup, sys_io_destroy
diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S
index f566518..edbec45 100644
--- a/arch/sparc/kernel/systbls_64.S
+++ b/arch/sparc/kernel/systbls_64.S
@@ -68,7 +68,7 @@
 	.word compat_sys_fstatfs64, sys_llseek, sys_mlock, sys_munlock, sys32_mlockall
 /*240*/	.word sys_munlockall, sys32_sched_setparam, sys32_sched_getparam, sys32_sched_setscheduler, sys32_sched_getscheduler
 	.word sys_sched_yield, sys32_sched_get_priority_max, sys32_sched_get_priority_min, sys32_sched_rr_get_interval, compat_sys_nanosleep
-/*250*/	.word sys_mremap, compat_sys_sysctl, sys32_getsid, sys_fdatasync, sys32_nfsservctl
+/*250*/	.word sys_mremap, compat_sys_sysctl, sys32_getsid, sys_fdatasync, sys_nis_syscall
 	.word sys32_sync_file_range, compat_sys_clock_settime, compat_sys_clock_gettime, compat_sys_clock_getres, sys32_clock_nanosleep
 /*260*/	.word compat_sys_sched_getaffinity, compat_sys_sched_setaffinity, sys32_timer_settime, compat_sys_timer_gettime, sys_timer_getoverrun
 	.word sys_timer_delete, compat_sys_timer_create, sys_ni_syscall, compat_sys_io_setup, sys_io_destroy
@@ -145,7 +145,7 @@
 	.word sys_fstatfs64, sys_llseek, sys_mlock, sys_munlock, sys_mlockall
 /*240*/	.word sys_munlockall, sys_sched_setparam, sys_sched_getparam, sys_sched_setscheduler, sys_sched_getscheduler
 	.word sys_sched_yield, sys_sched_get_priority_max, sys_sched_get_priority_min, sys_sched_rr_get_interval, sys_nanosleep
-/*250*/	.word sys_64_mremap, sys_sysctl, sys_getsid, sys_fdatasync, sys_nfsservctl
+/*250*/	.word sys_64_mremap, sys_sysctl, sys_getsid, sys_fdatasync, sys_nis_syscall
 	.word sys_sync_file_range, sys_clock_settime, sys_clock_gettime, sys_clock_getres, sys_clock_nanosleep
 /*260*/	.word sys_sched_getaffinity, sys_sched_setaffinity, sys_timer_settime, sys_timer_gettime, sys_timer_getoverrun
 	.word sys_timer_delete, sys_timer_create, sys_ni_syscall, sys_io_setup, sys_io_destroy
diff --git a/arch/um/Kconfig.x86 b/arch/um/Kconfig.x86
index d31ecf3..21bebe6 100644
--- a/arch/um/Kconfig.x86
+++ b/arch/um/Kconfig.x86
@@ -10,6 +10,10 @@
 	bool
 	default n
 
+config CMPXCHG_DOUBLE
+	bool
+	default n
+
 source "arch/x86/Kconfig.cpu"
 
 endmenu
diff --git a/arch/um/Makefile b/arch/um/Makefile
index fab8121..c0f712c 100644
--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -41,7 +41,7 @@
 KBUILD_CFLAGS += $(CFLAGS) $(CFLAGS-y) -D__arch_um__ -DSUBARCH=\"$(SUBARCH)\" \
 	$(ARCH_INCLUDE) $(MODE_INCLUDE) -Dvmap=kernel_vmap	\
 	-Din6addr_loopback=kernel_in6addr_loopback \
-	-Din6addr_any=kernel_in6addr_any
+	-Din6addr_any=kernel_in6addr_any -Dstrrchr=kernel_strrchr
 
 KBUILD_AFLAGS += $(ARCH_INCLUDE)
 
diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c
index d51c404..364c8a1 100644
--- a/arch/um/drivers/line.c
+++ b/arch/um/drivers/line.c
@@ -399,8 +399,8 @@
  * is done under a spinlock.  Checking whether the device is in use is
  * line->tty->count > 1, also under the spinlock.
  *
- * tty->count serves to decide whether the device should be enabled or
- * disabled on the host.  If it's equal to 1, then we are doing the
+ * line->count serves to decide whether the device should be enabled or
+ * disabled on the host.  If it's equal to 0, then we are doing the
  * first open or last close.  Otherwise, open and close just return.
  */
 
@@ -414,16 +414,16 @@
 		goto out_unlock;
 
 	err = 0;
-	if (tty->count > 1)
+	if (line->count++)
 		goto out_unlock;
 
-	spin_unlock(&line->count_lock);
-
+	BUG_ON(tty->driver_data);
 	tty->driver_data = line;
 	line->tty = tty;
 
+	spin_unlock(&line->count_lock);
 	err = enable_chan(line);
-	if (err)
+	if (err) /* line_close() will be called by our caller */
 		return err;
 
 	INIT_DELAYED_WORK(&line->task, line_timer_cb);
@@ -436,7 +436,7 @@
 	chan_window_size(&line->chan_list, &tty->winsize.ws_row,
 			 &tty->winsize.ws_col);
 
-	return err;
+	return 0;
 
 out_unlock:
 	spin_unlock(&line->count_lock);
@@ -460,17 +460,16 @@
 	flush_buffer(line);
 
 	spin_lock(&line->count_lock);
-	if (!line->valid)
-		goto out_unlock;
+	BUG_ON(!line->valid);
 
-	if (tty->count > 1)
+	if (--line->count)
 		goto out_unlock;
 
-	spin_unlock(&line->count_lock);
-
 	line->tty = NULL;
 	tty->driver_data = NULL;
 
+	spin_unlock(&line->count_lock);
+
 	if (line->sigio) {
 		unregister_winch(tty);
 		line->sigio = 0;
@@ -498,7 +497,7 @@
 
 	spin_lock(&line->count_lock);
 
-	if (line->tty != NULL) {
+	if (line->count) {
 		*error_out = "Device is already open";
 		goto out;
 	}
@@ -722,41 +721,53 @@
 	int pid;
 	struct tty_struct *tty;
 	unsigned long stack;
+	struct work_struct work;
 };
 
-static void free_winch(struct winch *winch, int free_irq_ok)
+static void __free_winch(struct work_struct *work)
 {
-	if (free_irq_ok)
-		free_irq(WINCH_IRQ, winch);
-
-	list_del(&winch->list);
+	struct winch *winch = container_of(work, struct winch, work);
+	free_irq(WINCH_IRQ, winch);
 
 	if (winch->pid != -1)
 		os_kill_process(winch->pid, 1);
-	if (winch->fd != -1)
-		os_close_file(winch->fd);
 	if (winch->stack != 0)
 		free_stack(winch->stack, 0);
 	kfree(winch);
 }
 
+static void free_winch(struct winch *winch)
+{
+	int fd = winch->fd;
+	winch->fd = -1;
+	if (fd != -1)
+		os_close_file(fd);
+	list_del(&winch->list);
+	__free_winch(&winch->work);
+}
+
 static irqreturn_t winch_interrupt(int irq, void *data)
 {
 	struct winch *winch = data;
 	struct tty_struct *tty;
 	struct line *line;
+	int fd = winch->fd;
 	int err;
 	char c;
 
-	if (winch->fd != -1) {
-		err = generic_read(winch->fd, &c, NULL);
+	if (fd != -1) {
+		err = generic_read(fd, &c, NULL);
 		if (err < 0) {
 			if (err != -EAGAIN) {
+				winch->fd = -1;
+				list_del(&winch->list);
+				os_close_file(fd);
 				printk(KERN_ERR "winch_interrupt : "
 				       "read failed, errno = %d\n", -err);
 				printk(KERN_ERR "fd %d is losing SIGWINCH "
 				       "support\n", winch->tty_fd);
-				free_winch(winch, 0);
+				INIT_WORK(&winch->work, __free_winch);
+				schedule_work(&winch->work);
 				return IRQ_HANDLED;
 			}
 			goto out;
@@ -828,7 +839,7 @@
 	list_for_each_safe(ele, next, &winch_handlers) {
 		winch = list_entry(ele, struct winch, list);
 		if (winch->tty == tty) {
-			free_winch(winch, 1);
+			free_winch(winch);
 			break;
 		}
 	}
@@ -844,7 +855,7 @@
 
 	list_for_each_safe(ele, next, &winch_handlers) {
 		winch = list_entry(ele, struct winch, list);
-		free_winch(winch, 1);
+		free_winch(winch);
 	}
 
 	spin_unlock(&winch_handler_lock);
diff --git a/arch/um/drivers/xterm.c b/arch/um/drivers/xterm.c
index 8ac7146..2e1de57 100644
--- a/arch/um/drivers/xterm.c
+++ b/arch/um/drivers/xterm.c
@@ -123,6 +123,7 @@
 		err = -errno;
 		printk(UM_KERN_ERR "xterm_open : unlink failed, errno = %d\n",
 		       errno);
+		close(fd);
 		return err;
 	}
 	close(fd);
diff --git a/arch/um/include/asm/ptrace-generic.h b/arch/um/include/asm/ptrace-generic.h
index ae084ad..1a7d275 100644
--- a/arch/um/include/asm/ptrace-generic.h
+++ b/arch/um/include/asm/ptrace-generic.h
@@ -42,10 +42,6 @@
 	unsigned long addr, unsigned long data);
 extern unsigned long getreg(struct task_struct *child, int regno);
 extern int putreg(struct task_struct *child, int regno, unsigned long value);
-extern int get_fpregs(struct user_i387_struct __user *buf,
-		      struct task_struct *child);
-extern int set_fpregs(struct user_i387_struct __user *buf,
-		      struct task_struct *child);
 
 extern int arch_copy_tls(struct task_struct *new);
 extern void clear_flushed_tls(struct task_struct *task);
diff --git a/arch/um/include/shared/line.h b/arch/um/include/shared/line.h
index 72f4f25..63df3ca 100644
--- a/arch/um/include/shared/line.h
+++ b/arch/um/include/shared/line.h
@@ -33,6 +33,7 @@
 struct line {
 	struct tty_struct *tty;
 	spinlock_t count_lock;
+	unsigned long count;
 	int valid;
 
 	char *init_str;
diff --git a/arch/um/include/shared/registers.h b/arch/um/include/shared/registers.h
index b0b4589..f1e0aa5 100644
--- a/arch/um/include/shared/registers.h
+++ b/arch/um/include/shared/registers.h
@@ -16,7 +16,7 @@
 extern int save_registers(int pid, struct uml_pt_regs *regs);
 extern int restore_registers(int pid, struct uml_pt_regs *regs);
 extern int init_registers(int pid);
-extern void get_safe_registers(unsigned long *regs);
+extern void get_safe_registers(unsigned long *regs, unsigned long *fp_regs);
 extern unsigned long get_thread_reg(int reg, jmp_buf *buf);
 extern int get_fp_registers(int pid, unsigned long *regs);
 extern int put_fp_registers(int pid, unsigned long *regs);
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index fab4371..21c1ae7 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -202,7 +202,7 @@
 		arch_copy_thread(&current->thread.arch, &p->thread.arch);
 	}
 	else {
-		get_safe_registers(p->thread.regs.regs.gp);
+		get_safe_registers(p->thread.regs.regs.gp, p->thread.regs.regs.fp);
 		p->thread.request.u.thread = current->thread.request.u.thread;
 		handler = new_thread_handler;
 	}
diff --git a/arch/um/kernel/ptrace.c b/arch/um/kernel/ptrace.c
index 701b672..c9da32b 100644
--- a/arch/um/kernel/ptrace.c
+++ b/arch/um/kernel/ptrace.c
@@ -50,23 +50,11 @@
 	void __user *vp = p;
 
 	switch (request) {
-	/* read word at location addr. */
-	case PTRACE_PEEKTEXT:
-	case PTRACE_PEEKDATA:
-		ret = generic_ptrace_peekdata(child, addr, data);
-		break;
-
 	/* read the word at location addr in the USER area. */
 	case PTRACE_PEEKUSR:
 		ret = peek_user(child, addr, data);
 		break;
 
-	/* write the word at location addr. */
-	case PTRACE_POKETEXT:
-	case PTRACE_POKEDATA:
-		ret = generic_ptrace_pokedata(child, addr, data);
-		break;
-
 	/* write the word at location addr in the USER area */
 	case PTRACE_POKEUSR:
 		ret = poke_user(child, addr, data);
@@ -107,16 +95,6 @@
 		break;
 	}
 #endif
-#ifdef PTRACE_GETFPREGS
-	case PTRACE_GETFPREGS: /* Get the child FPU state. */
-		ret = get_fpregs(vp, child);
-		break;
-#endif
-#ifdef PTRACE_SETFPREGS
-	case PTRACE_SETFPREGS: /* Set the child FPU state. */
-		ret = set_fpregs(vp, child);
-		break;
-#endif
 	case PTRACE_GET_THREAD_AREA:
 		ret = ptrace_get_thread_area(child, addr, vp);
 		break;
@@ -154,12 +132,6 @@
 		break;
 	}
 #endif
-#ifdef PTRACE_ARCH_PRCTL
-	case PTRACE_ARCH_PRCTL:
-		/* XXX Calls ptrace on the host - needs some SMP thinking */
-		ret = arch_prctl(child, data, (void __user *) addr);
-		break;
-#endif
 	default:
 		ret = ptrace_request(child, request, addr, data);
 		if (ret == -EIO)
diff --git a/arch/um/os-Linux/registers.c b/arch/um/os-Linux/registers.c
index 830fe6a..b866b9e 100644
--- a/arch/um/os-Linux/registers.c
+++ b/arch/um/os-Linux/registers.c
@@ -8,6 +8,8 @@
 #include <string.h>
 #include <sys/ptrace.h>
 #include "sysdep/ptrace.h"
+#include "sysdep/ptrace_user.h"
+#include "registers.h"
 
 int save_registers(int pid, struct uml_pt_regs *regs)
 {
@@ -32,6 +34,7 @@
 /* This is set once at boot time and not changed thereafter */
 
 static unsigned long exec_regs[MAX_REG_NR];
+static unsigned long exec_fp_regs[FP_SIZE];
 
 int init_registers(int pid)
 {
@@ -42,10 +45,14 @@
 		return -errno;
 
 	arch_init_registers(pid);
+	get_fp_registers(pid, exec_fp_regs);
 	return 0;
 }
 
-void get_safe_registers(unsigned long *regs)
+void get_safe_registers(unsigned long *regs, unsigned long *fp_regs)
 {
 	memcpy(regs, exec_regs, sizeof(exec_regs));
+
+	if (fp_regs)
+		memcpy(fp_regs, exec_fp_regs, sizeof(exec_fp_regs));
 }
diff --git a/arch/um/os-Linux/skas/mem.c b/arch/um/os-Linux/skas/mem.c
index d261f17..e771398 100644
--- a/arch/um/os-Linux/skas/mem.c
+++ b/arch/um/os-Linux/skas/mem.c
@@ -39,7 +39,7 @@
 
 static int __init init_syscall_regs(void)
 {
-	get_safe_registers(syscall_regs);
+	get_safe_registers(syscall_regs, NULL);
 	syscall_regs[REGS_IP_INDEX] = STUB_CODE +
 		((unsigned long) &batch_syscall_stub -
 		 (unsigned long) &__syscall_stub_start);
diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c
index d6e0a22..dee0e8c 100644
--- a/arch/um/os-Linux/skas/process.c
+++ b/arch/um/os-Linux/skas/process.c
@@ -373,6 +373,9 @@
 		if (ptrace(PTRACE_SETREGS, pid, 0, regs->gp))
 			fatal_sigsegv();
 
+		if (put_fp_registers(pid, regs->fp))
+			fatal_sigsegv();
+
 		/* Now we set local_using_sysemu to be used for one loop */
 		local_using_sysemu = get_using_sysemu();
 
@@ -399,6 +402,12 @@
 			fatal_sigsegv();
 		}
 
+		if (get_fp_registers(pid, regs->fp)) {
+			printk(UM_KERN_ERR "userspace -  get_fp_registers failed, "
+			       "errno = %d\n", errno);
+			fatal_sigsegv();
+		}
+
 		UPT_SYSCALL_NR(regs) = -1; /* Assume: It's not a syscall */
 
 		if (WIFSTOPPED(status)) {
@@ -457,10 +466,11 @@
 }
 
 static unsigned long thread_regs[MAX_REG_NR];
+static unsigned long thread_fp_regs[FP_SIZE];
 
 static int __init init_thread_regs(void)
 {
-	get_safe_registers(thread_regs);
+	get_safe_registers(thread_regs, thread_fp_regs);
 	/* Set parent's instruction pointer to start of clone-stub */
 	thread_regs[REGS_IP_INDEX] = STUB_CODE +
 				(unsigned long) stub_clone_handler -
@@ -503,6 +513,13 @@
 		return err;
 	}
 
+	err = put_fp_registers(pid, thread_fp_regs);
+	if (err < 0) {
+		printk(UM_KERN_ERR "copy_context_skas0 : put_fp_registers "
+		       "failed, pid = %d, err = %d\n", pid, err);
+		return err;
+	}
+
 	/* set a well known return code for detection of child write failure */
 	child_data->err = 12345678;
 
diff --git a/arch/um/sys-i386/asm/ptrace.h b/arch/um/sys-i386/asm/ptrace.h
index 0273e4d..5d2a591 100644
--- a/arch/um/sys-i386/asm/ptrace.h
+++ b/arch/um/sys-i386/asm/ptrace.h
@@ -42,11 +42,6 @@
  */
 struct user_desc;
 
-extern int get_fpxregs(struct user_fxsr_struct __user *buf,
-		       struct task_struct *child);
-extern int set_fpxregs(struct user_fxsr_struct __user *buf,
-		       struct task_struct *tsk);
-
 extern int ptrace_get_thread_area(struct task_struct *child, int idx,
                                   struct user_desc __user *user_desc);
 
diff --git a/arch/um/sys-i386/ptrace.c b/arch/um/sys-i386/ptrace.c
index d23b2d3..3375c27 100644
--- a/arch/um/sys-i386/ptrace.c
+++ b/arch/um/sys-i386/ptrace.c
@@ -145,7 +145,7 @@
 	return put_user(tmp, (unsigned long __user *) data);
 }
 
-int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child)
+static int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child)
 {
 	int err, n, cpu = ((struct thread_info *) child->stack)->cpu;
 	struct user_i387_struct fpregs;
@@ -161,7 +161,7 @@
 	return n;
 }
 
-int set_fpregs(struct user_i387_struct __user *buf, struct task_struct *child)
+static int set_fpregs(struct user_i387_struct __user *buf, struct task_struct *child)
 {
 	int n, cpu = ((struct thread_info *) child->stack)->cpu;
 	struct user_i387_struct fpregs;
@@ -174,7 +174,7 @@
 				    (unsigned long *) &fpregs);
 }
 
-int get_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *child)
+static int get_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *child)
 {
 	int err, n, cpu = ((struct thread_info *) child->stack)->cpu;
 	struct user_fxsr_struct fpregs;
@@ -190,7 +190,7 @@
 	return n;
 }
 
-int set_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *child)
+static int set_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *child)
 {
 	int n, cpu = ((struct thread_info *) child->stack)->cpu;
 	struct user_fxsr_struct fpregs;
@@ -206,5 +206,23 @@
 long subarch_ptrace(struct task_struct *child, long request,
 		    unsigned long addr, unsigned long data)
 {
-	return -EIO;
+	int ret = -EIO;
+	void __user *datap = (void __user *) data;
+	switch (request) {
+	case PTRACE_GETFPREGS: /* Get the child FPU state. */
+		ret = get_fpregs(datap, child);
+		break;
+	case PTRACE_SETFPREGS: /* Set the child FPU state. */
+		ret = set_fpregs(datap, child);
+		break;
+	case PTRACE_GETFPXREGS: /* Get the child FPU state. */
+		ret = get_fpxregs(datap, child);
+		break;
+	case PTRACE_SETFPXREGS: /* Set the child FPU state. */
+		ret = set_fpxregs(datap, child);
+		break;
+	default:
+		ret = -EIO;
+	}
+	return ret;
 }
diff --git a/arch/um/sys-i386/shared/sysdep/ptrace.h b/arch/um/sys-i386/shared/sysdep/ptrace.h
index d50e62e..c398a50 100644
--- a/arch/um/sys-i386/shared/sysdep/ptrace.h
+++ b/arch/um/sys-i386/shared/sysdep/ptrace.h
@@ -53,6 +53,7 @@
 
 struct uml_pt_regs {
 	unsigned long gp[MAX_REG_NR];
+	unsigned long fp[HOST_FPX_SIZE];
 	struct faultinfo faultinfo;
 	long syscall;
 	int is_user;
diff --git a/arch/um/sys-x86_64/ptrace.c b/arch/um/sys-x86_64/ptrace.c
index f436136..4005506 100644
--- a/arch/um/sys-x86_64/ptrace.c
+++ b/arch/um/sys-x86_64/ptrace.c
@@ -145,7 +145,7 @@
 	return instr == 0x050f;
 }
 
-int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child)
+static int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child)
 {
 	int err, n, cpu = ((struct thread_info *) child->stack)->cpu;
 	long fpregs[HOST_FP_SIZE];
@@ -162,7 +162,7 @@
 	return n;
 }
 
-int set_fpregs(struct user_i387_struct __user *buf, struct task_struct *child)
+static int set_fpregs(struct user_i387_struct __user *buf, struct task_struct *child)
 {
 	int n, cpu = ((struct thread_info *) child->stack)->cpu;
 	long fpregs[HOST_FP_SIZE];
@@ -182,12 +182,16 @@
 	void __user *datap = (void __user *) data;
 
 	switch (request) {
-	case PTRACE_GETFPXREGS: /* Get the child FPU state. */
+	case PTRACE_GETFPREGS: /* Get the child FPU state. */
 		ret = get_fpregs(datap, child);
 		break;
-	case PTRACE_SETFPXREGS: /* Set the child FPU state. */
+	case PTRACE_SETFPREGS: /* Set the child FPU state. */
 		ret = set_fpregs(datap, child);
 		break;
+	case PTRACE_ARCH_PRCTL:
+		/* XXX Calls ptrace on the host - needs some SMP thinking */
+		ret = arch_prctl(child, data, (void __user *) addr);
+		break;
 	}
 
 	return ret;
diff --git a/arch/um/sys-x86_64/shared/sysdep/ptrace.h b/arch/um/sys-x86_64/shared/sysdep/ptrace.h
index fdba545..8ee8f8e 100644
--- a/arch/um/sys-x86_64/shared/sysdep/ptrace.h
+++ b/arch/um/sys-x86_64/shared/sysdep/ptrace.h
@@ -85,6 +85,7 @@
 
 struct uml_pt_regs {
 	unsigned long gp[MAX_REG_NR];
+	unsigned long fp[HOST_FP_SIZE];
 	struct faultinfo faultinfo;
 	long syscall;
 	int is_user;
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index a0e866d..54edb207 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -672,7 +672,7 @@
 	.quad sys32_vm86_warning	/* vm86 */ 
 	.quad quiet_ni_syscall	/* query_module */
 	.quad sys_poll
-	.quad compat_sys_nfsservctl
+	.quad quiet_ni_syscall /* old nfsservctl */
 	.quad sys_setresgid16	/* 170 */
 	.quad sys_getresgid16
 	.quad sys_prctl
diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h
index 4554cc6..091508b 100644
--- a/arch/x86/include/asm/alternative-asm.h
+++ b/arch/x86/include/asm/alternative-asm.h
@@ -16,7 +16,6 @@
 #endif
 
 .macro altinstruction_entry orig alt feature orig_len alt_len
-	.align 8
 	.long \orig - .
 	.long \alt - .
 	.word \feature
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 23fb6d7..37ad100 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -48,9 +48,6 @@
 	u16 cpuid;		/* cpuid bit set for replacement */
 	u8  instrlen;		/* length of original instruction */
 	u8  replacementlen;	/* length of new instruction, <= instrlen */
-#ifdef CONFIG_X86_64
-	u32 pad2;
-#endif
 };
 
 extern void alternative_instructions(void);
@@ -83,7 +80,6 @@
 									\
       "661:\n\t" oldinstr "\n662:\n"					\
       ".section .altinstructions,\"a\"\n"				\
-      _ASM_ALIGN "\n"							\
       "	 .long 661b - .\n"			/* label           */	\
       "	 .long 663f - .\n"			/* new instruction */	\
       "	 .word " __stringify(feature) "\n"	/* feature bit     */	\
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 4258aac..88b23a4 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -332,7 +332,6 @@
 		asm goto("1: jmp %l[t_no]\n"
 			 "2:\n"
 			 ".section .altinstructions,\"a\"\n"
-			 _ASM_ALIGN "\n"
 			 " .long 1b - .\n"
 			 " .long 0\n"		/* no replacement */
 			 " .word %P0\n"		/* feature bit */
@@ -350,7 +349,6 @@
 		asm volatile("1: movb $0,%0\n"
 			     "2:\n"
 			     ".section .altinstructions,\"a\"\n"
-			     _ASM_ALIGN "\n"
 			     " .long 1b - .\n"
 			     " .long 3f - .\n"
 			     " .word %P1\n"		/* feature bit */
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 7b439d9..41935fa 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -27,8 +27,8 @@
 
 	desc->base2		= (info->base_addr & 0xff000000) >> 24;
 	/*
-	 * Don't allow setting of the lm bit. It is useless anyway
-	 * because 64bit system calls require __USER_CS:
+	 * Don't allow setting of the lm bit. It would confuse
+	 * user_64bit_mode and would get overridden by sysret anyway.
 	 */
 	desc->l			= 0;
 }
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index f9a3209..7e50f06 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -17,7 +17,6 @@
  *  Vectors   0 ...  31 : system traps and exceptions - hardcoded events
  *  Vectors  32 ... 127 : device interrupts
  *  Vector  128         : legacy int80 syscall interface
- *  Vector  204         : legacy x86_64 vsyscall emulation
  *  Vectors 129 ... INVALIDATE_TLB_VECTOR_START-1 except 204 : device interrupts
  *  Vectors INVALIDATE_TLB_VECTOR_START ... 255 : special interrupts
  *
@@ -51,9 +50,6 @@
 #ifdef CONFIG_X86_32
 # define SYSCALL_VECTOR			0x80
 #endif
-#ifdef CONFIG_X86_64
-# define VSYSCALL_EMU_VECTOR		0xcc
-#endif
 
 /*
  * Vectors 0x30-0x3f are used for ISA interrupts.
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 2c76521..8e8b9a4 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -41,6 +41,7 @@
 
 #include <asm/desc_defs.h>
 #include <asm/kmap_types.h>
+#include <asm/pgtable_types.h>
 
 struct page;
 struct thread_struct;
@@ -63,6 +64,11 @@
 struct pv_info {
 	unsigned int kernel_rpl;
 	int shared_kernel_pmd;
+
+#ifdef CONFIG_X86_64
+	u16 extra_user_64bit_cs;  /* __USER_CS if none */
+#endif
+
 	int paravirt_enabled;
 	const char *name;
 };
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 94e7618..3566454 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -131,6 +131,9 @@
 #ifdef __KERNEL__
 
 #include <linux/init.h>
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt_types.h>
+#endif
 
 struct cpuinfo_x86;
 struct task_struct;
@@ -187,6 +190,22 @@
 #endif
 }
 
+#ifdef CONFIG_X86_64
+static inline bool user_64bit_mode(struct pt_regs *regs)
+{
+#ifndef CONFIG_PARAVIRT
+	/*
+	 * On non-paravirt systems, this is the only long mode CPL 3
+	 * selector.  We do not allow long mode selectors in the LDT.
+	 */
+	return regs->cs == __USER_CS;
+#else
+	/* Headers are too twisted for this to go in paravirt.h. */
+	return regs->cs == __USER_CS || regs->cs == pv_info.extra_user_64bit_cs;
+#endif
+}
+#endif
+
 /*
  * X86_32 CPUs don't save ss and esp if the CPU is already in kernel mode
  * when it traps.  The previous stack will be directly underneath the saved
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index a518c0a..c59cc97 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -44,7 +44,7 @@
 		: "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) );
 #elif defined(__x86_64__)
 	__asm__ (
-		"mul %[mul_frac] ; shrd $32, %[hi], %[lo]"
+		"mulq %[mul_frac] ; shrd $32, %[hi], %[lo]"
 		: [lo]"=a"(product),
 		  [hi]"=d"(tmp)
 		: "0"(delta),
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 2bae0a5..0012d09 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -40,7 +40,6 @@
 asmlinkage void machine_check(void);
 #endif /* CONFIG_X86_MCE */
 asmlinkage void simd_coprocessor_error(void);
-asmlinkage void emulate_vsyscall(void);
 
 dotraplinkage void do_divide_error(struct pt_regs *, long);
 dotraplinkage void do_debug(struct pt_regs *, long);
@@ -67,7 +66,6 @@
 dotraplinkage void do_machine_check(struct pt_regs *, long);
 #endif
 dotraplinkage void do_simd_coprocessor_error(struct pt_regs *, long);
-dotraplinkage void do_emulate_vsyscall(struct pt_regs *, long);
 #ifdef CONFIG_X86_32
 dotraplinkage void do_iret_error(struct pt_regs *, long);
 #endif
diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h
index 705bf13..2010405 100644
--- a/arch/x86/include/asm/unistd_64.h
+++ b/arch/x86/include/asm/unistd_64.h
@@ -414,7 +414,7 @@
 __SYSCALL(__NR_quotactl, sys_quotactl)
 
 #define __NR_nfsservctl				180
-__SYSCALL(__NR_nfsservctl, sys_nfsservctl)
+__SYSCALL(__NR_nfsservctl, sys_ni_syscall)
 
 /* reserved for LiS/STREAMS */
 #define __NR_getpmsg				181
@@ -681,6 +681,8 @@
 __SYSCALL(__NR_sendmmsg, sys_sendmmsg)
 #define __NR_setns				308
 __SYSCALL(__NR_setns, sys_setns)
+#define __NR_getcpu				309
+__SYSCALL(__NR_getcpu, sys_getcpu)
 
 #ifndef __NO_STUBS
 #define __ARCH_WANT_OLD_READDIR
diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h
index 6010707..eaea1d3 100644
--- a/arch/x86/include/asm/vsyscall.h
+++ b/arch/x86/include/asm/vsyscall.h
@@ -27,6 +27,12 @@
 
 extern void map_vsyscall(void);
 
+/*
+ * Called on instruction fetch fault in vsyscall page.
+ * Returns true if handled.
+ */
+extern bool emulate_vsyscall(struct pt_regs *regs, unsigned long address);
+
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_X86_VSYSCALL_H */
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 64a619d..7ff4669 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -39,7 +39,7 @@
     ((unsigned long)((u64)CONFIG_XEN_MAX_DOMAIN_MEMORY * 1024 * 1024 * 1024 / PAGE_SIZE))
 
 extern unsigned long *machine_to_phys_mapping;
-extern unsigned int   machine_to_phys_order;
+extern unsigned long  machine_to_phys_nr;
 
 extern unsigned long get_phys_to_machine(unsigned long pfn);
 extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn);
@@ -87,7 +87,7 @@
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return mfn;
 
-	if (unlikely((mfn >> machine_to_phys_order) != 0)) {
+	if (unlikely(mfn >= machine_to_phys_nr)) {
 		pfn = ~0;
 		goto try_override;
 	}
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 0410557..82f2912 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -17,19 +17,6 @@
 CFLAGS_REMOVE_early_printk.o = -pg
 endif
 
-#
-# vsyscalls (which work on the user stack) should have
-# no stack-protector checks:
-#
-nostackp := $(call cc-option, -fno-stack-protector)
-CFLAGS_vsyscall_64.o	:= $(PROFILING) -g0 $(nostackp)
-CFLAGS_hpet.o		:= $(nostackp)
-CFLAGS_paravirt.o	:= $(nostackp)
-GCOV_PROFILE_vsyscall_64.o	:= n
-GCOV_PROFILE_hpet.o		:= n
-GCOV_PROFILE_tsc.o		:= n
-GCOV_PROFILE_paravirt.o		:= n
-
 obj-y			:= process_$(BITS).o signal.o entry_$(BITS).o
 obj-y			+= traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
 obj-y			+= time.o ioport.o ldt.o dumpstack.o
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index adc66c3..34b1859 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -207,7 +207,6 @@
 	    ((start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) |
 	    APIC_DM_INIT;
 	uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
-	mdelay(10);
 
 	val = (1UL << UVH_IPI_INT_SEND_SHFT) |
 	    (phys_apicid << UVH_IPI_INT_APIC_ID_SHFT) |
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 08119a3..6b96110 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -149,7 +149,6 @@
  */
 static int mtrr_rendezvous_handler(void *info)
 {
-#ifdef CONFIG_SMP
 	struct set_mtrr_data *data = info;
 
 	/*
@@ -171,7 +170,6 @@
 	} else if (mtrr_aps_delayed_init || !cpu_online(smp_processor_id())) {
 		mtrr_if->set_all();
 	}
-#endif
 	return 0;
 }
 
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 4ee3abf..cfa62ec 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1900,6 +1900,9 @@
 
 	perf_callchain_store(entry, regs->ip);
 
+	if (!current->mm)
+		return;
+
 	if (perf_callchain_user32(regs, entry))
 		return;
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 45fbb8f..f88af2c 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1590,6 +1590,7 @@
 		break;
 
 	case 42: /* SandyBridge */
+	case 45: /* SandyBridge, "Romely-EP" */
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 5c1a9197..f3f6f53 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -54,6 +54,7 @@
 #include <asm/ftrace.h>
 #include <asm/irq_vectors.h>
 #include <asm/cpufeature.h>
+#include <asm/alternative-asm.h>
 
 /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
 #include <linux/elf-em.h>
@@ -873,12 +874,7 @@
 661:	pushl_cfi $do_general_protection
 662:
 .section .altinstructions,"a"
-	.balign 4
-	.long 661b
-	.long 663f
-	.word X86_FEATURE_XMM
-	.byte 662b-661b
-	.byte 664f-663f
+	altinstruction_entry 661b, 663f, X86_FEATURE_XMM, 662b-661b, 664f-663f
 .previous
 .section .altinstr_replacement,"ax"
 663:	pushl $do_simd_coprocessor_error
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index e13329d..6419bb0 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1111,7 +1111,6 @@
 zeroentry coprocessor_error do_coprocessor_error
 errorentry alignment_check do_alignment_check
 zeroentry simd_coprocessor_error do_simd_coprocessor_error
-zeroentry emulate_vsyscall do_emulate_vsyscall
 
 
 	/* Reload gs selector with exception handling */
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 613a793..d90272e 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -307,6 +307,10 @@
 	.paravirt_enabled = 0,
 	.kernel_rpl = 0,
 	.shared_kernel_pmd = 1,	/* Only used when CONFIG_X86_PAE is set */
+
+#ifdef CONFIG_X86_64
+	.extra_user_64bit_cs = __USER_CS,
+#endif
 };
 
 struct pv_init_ops pv_init_ops = {
diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index 7977f0c..c346d11 100644
--- a/arch/x86/kernel/step.c
+++ b/arch/x86/kernel/step.c
@@ -74,7 +74,7 @@
 
 #ifdef CONFIG_X86_64
 		case 0x40 ... 0x4f:
-			if (regs->cs != __USER_CS)
+			if (!user_64bit_mode(regs))
 				/* 32-bit mode: register increment */
 				return 0;
 			/* 64-bit mode: REX prefix */
diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S
index fbb0a04..bc19be3 100644
--- a/arch/x86/kernel/syscall_table_32.S
+++ b/arch/x86/kernel/syscall_table_32.S
@@ -168,7 +168,7 @@
 	.long ptregs_vm86
 	.long sys_ni_syscall	/* Old sys_query_module */
 	.long sys_poll
-	.long sys_nfsservctl
+	.long sys_ni_syscall	/* Old nfsservctl */
 	.long sys_setresgid16	/* 170 */
 	.long sys_getresgid16
 	.long sys_prctl
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 9682ec5..6913369 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -872,12 +872,6 @@
 	set_bit(SYSCALL_VECTOR, used_vectors);
 #endif
 
-#ifdef CONFIG_X86_64
-	BUG_ON(test_bit(VSYSCALL_EMU_VECTOR, used_vectors));
-	set_system_intr_gate(VSYSCALL_EMU_VECTOR, &emulate_vsyscall);
-	set_bit(VSYSCALL_EMU_VECTOR, used_vectors);
-#endif
-
 	/*
 	 * Should be a barrier for any external CPU state:
 	 */
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 4aa9c54..0f703f1 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -71,7 +71,6 @@
 	text PT_LOAD FLAGS(5);          /* R_E */
 	data PT_LOAD FLAGS(6);          /* RW_ */
 #ifdef CONFIG_X86_64
-	user PT_LOAD FLAGS(5);          /* R_E */
 #ifdef CONFIG_SMP
 	percpu PT_LOAD FLAGS(6);        /* RW_ */
 #endif
@@ -154,44 +153,16 @@
 
 #ifdef CONFIG_X86_64
 
-#define VSYSCALL_ADDR (-10*1024*1024)
-
-#define VLOAD_OFFSET (VSYSCALL_ADDR - __vsyscall_0 + LOAD_OFFSET)
-#define VLOAD(x) (ADDR(x) - VLOAD_OFFSET)
-
-#define VVIRT_OFFSET (VSYSCALL_ADDR - __vsyscall_0)
-#define VVIRT(x) (ADDR(x) - VVIRT_OFFSET)
-
-	. = ALIGN(4096);
-	__vsyscall_0 = .;
-
-	. = VSYSCALL_ADDR;
-	.vsyscall : AT(VLOAD(.vsyscall)) {
-		*(.vsyscall_0)
-
-		. = 1024;
-		*(.vsyscall_1)
-
-		. = 2048;
-		*(.vsyscall_2)
-
-		. = 4096;  /* Pad the whole page. */
-	} :user =0xcc
-	. = ALIGN(__vsyscall_0 + PAGE_SIZE, PAGE_SIZE);
-
-#undef VSYSCALL_ADDR
-#undef VLOAD_OFFSET
-#undef VLOAD
-#undef VVIRT_OFFSET
-#undef VVIRT
-
+	. = ALIGN(PAGE_SIZE);
 	__vvar_page = .;
 
 	.vvar : AT(ADDR(.vvar) - LOAD_OFFSET) {
+		/* work around gold bug 13023 */
+		__vvar_beginning_hack = .;
 
-	      /* Place all vvars at the offsets in asm/vvar.h. */
-#define EMIT_VVAR(name, offset) 		\
-		. = offset;		\
+		/* Place all vvars at the offsets in asm/vvar.h. */
+#define EMIT_VVAR(name, offset) 			\
+		. = __vvar_beginning_hack + offset;	\
 		*(.vvar_ ## name)
 #define __VVAR_KERNEL_LDS
 #include <asm/vvar.h>
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index dda7dff..18ae83d 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -18,9 +18,6 @@
  *  use the vDSO.
  */
 
-/* Disable profiling for userspace code: */
-#define DISABLE_BRANCH_PROFILING
-
 #include <linux/time.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -50,12 +47,36 @@
 #include <asm/vgtod.h>
 #include <asm/traps.h>
 
+#define CREATE_TRACE_POINTS
+#include "vsyscall_trace.h"
+
 DEFINE_VVAR(int, vgetcpu_mode);
 DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data) =
 {
 	.lock = __SEQLOCK_UNLOCKED(__vsyscall_gtod_data.lock),
 };
 
+static enum { EMULATE, NATIVE, NONE } vsyscall_mode = EMULATE;
+
+static int __init vsyscall_setup(char *str)
+{
+	if (str) {
+		if (!strcmp("emulate", str))
+			vsyscall_mode = EMULATE;
+		else if (!strcmp("native", str))
+			vsyscall_mode = NATIVE;
+		else if (!strcmp("none", str))
+			vsyscall_mode = NONE;
+		else
+			return -EINVAL;
+
+		return 0;
+	}
+
+	return -EINVAL;
+}
+early_param("vsyscall", vsyscall_setup);
+
 void update_vsyscall_tz(void)
 {
 	unsigned long flags;
@@ -100,7 +121,7 @@
 
 	printk("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n",
 	       level, tsk->comm, task_pid_nr(tsk),
-	       message, regs->ip - 2, regs->cs,
+	       message, regs->ip, regs->cs,
 	       regs->sp, regs->ax, regs->si, regs->di);
 }
 
@@ -118,46 +139,39 @@
 	return nr;
 }
 
-void dotraplinkage do_emulate_vsyscall(struct pt_regs *regs, long error_code)
+bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
 {
 	struct task_struct *tsk;
 	unsigned long caller;
 	int vsyscall_nr;
 	long ret;
 
-	local_irq_enable();
-
 	/*
-	 * Real 64-bit user mode code has cs == __USER_CS.  Anything else
-	 * is bogus.
+	 * No point in checking CS -- the only way to get here is a user mode
+	 * trap to a high address, which means that we're in 64-bit user code.
 	 */
-	if (regs->cs != __USER_CS) {
-		/*
-		 * If we trapped from kernel mode, we might as well OOPS now
-		 * instead of returning to some random address and OOPSing
-		 * then.
-		 */
-		BUG_ON(!user_mode(regs));
 
-		/* Compat mode and non-compat 32-bit CS should both segfault. */
-		warn_bad_vsyscall(KERN_WARNING, regs,
-				  "illegal int 0xcc from 32-bit mode");
-		goto sigsegv;
+	WARN_ON_ONCE(address != regs->ip);
+
+	if (vsyscall_mode == NONE) {
+		warn_bad_vsyscall(KERN_INFO, regs,
+				  "vsyscall attempted with vsyscall=none");
+		return false;
 	}
 
-	/*
-	 * x86-ism here: regs->ip points to the instruction after the int 0xcc,
-	 * and int 0xcc is two bytes long.
-	 */
-	vsyscall_nr = addr_to_vsyscall_nr(regs->ip - 2);
+	vsyscall_nr = addr_to_vsyscall_nr(address);
+
+	trace_emulate_vsyscall(vsyscall_nr);
+
 	if (vsyscall_nr < 0) {
 		warn_bad_vsyscall(KERN_WARNING, regs,
-				  "illegal int 0xcc (exploit attempt?)");
+				  "misaligned vsyscall (exploit attempt or buggy program) -- look up the vsyscall kernel parameter if you need a workaround");
 		goto sigsegv;
 	}
 
 	if (get_user(caller, (unsigned long __user *)regs->sp) != 0) {
-		warn_bad_vsyscall(KERN_WARNING, regs, "int 0xcc with bad stack (exploit attempt?)");
+		warn_bad_vsyscall(KERN_WARNING, regs,
+				  "vsyscall with bad stack (exploit attempt?)");
 		goto sigsegv;
 	}
 
@@ -202,13 +216,11 @@
 	regs->ip = caller;
 	regs->sp += 8;
 
-	local_irq_disable();
-	return;
+	return true;
 
 sigsegv:
-	regs->ip -= 2;  /* The faulting instruction should be the int 0xcc. */
 	force_sig(SIGSEGV, current);
-	local_irq_disable();
+	return true;
 }
 
 /*
@@ -256,15 +268,21 @@
 
 void __init map_vsyscall(void)
 {
-	extern char __vsyscall_0;
-	unsigned long physaddr_page0 = __pa_symbol(&__vsyscall_0);
+	extern char __vsyscall_page;
+	unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page);
 	extern char __vvar_page;
 	unsigned long physaddr_vvar_page = __pa_symbol(&__vvar_page);
 
-	/* Note that VSYSCALL_MAPPED_PAGES must agree with the code below. */
-	__set_fixmap(VSYSCALL_FIRST_PAGE, physaddr_page0, PAGE_KERNEL_VSYSCALL);
+	__set_fixmap(VSYSCALL_FIRST_PAGE, physaddr_vsyscall,
+		     vsyscall_mode == NATIVE
+		     ? PAGE_KERNEL_VSYSCALL
+		     : PAGE_KERNEL_VVAR);
+	BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_FIRST_PAGE) !=
+		     (unsigned long)VSYSCALL_START);
+
 	__set_fixmap(VVAR_PAGE, physaddr_vvar_page, PAGE_KERNEL_VVAR);
-	BUILD_BUG_ON((unsigned long)__fix_to_virt(VVAR_PAGE) != (unsigned long)VVAR_ADDRESS);
+	BUILD_BUG_ON((unsigned long)__fix_to_virt(VVAR_PAGE) !=
+		     (unsigned long)VVAR_ADDRESS);
 }
 
 static int __init vsyscall_init(void)
diff --git a/arch/x86/kernel/vsyscall_emu_64.S b/arch/x86/kernel/vsyscall_emu_64.S
index ffa845e..c9596a9 100644
--- a/arch/x86/kernel/vsyscall_emu_64.S
+++ b/arch/x86/kernel/vsyscall_emu_64.S
@@ -7,21 +7,31 @@
  */
 
 #include <linux/linkage.h>
+
 #include <asm/irq_vectors.h>
+#include <asm/page_types.h>
+#include <asm/unistd_64.h>
 
-/* The unused parts of the page are filled with 0xcc by the linker script. */
+__PAGE_ALIGNED_DATA
+	.globl __vsyscall_page
+	.balign PAGE_SIZE, 0xcc
+	.type __vsyscall_page, @object
+__vsyscall_page:
 
-.section .vsyscall_0, "a"
-ENTRY(vsyscall_0)
-	int $VSYSCALL_EMU_VECTOR
-END(vsyscall_0)
+	mov $__NR_gettimeofday, %rax
+	syscall
+	ret
 
-.section .vsyscall_1, "a"
-ENTRY(vsyscall_1)
-	int $VSYSCALL_EMU_VECTOR
-END(vsyscall_1)
+	.balign 1024, 0xcc
+	mov $__NR_time, %rax
+	syscall
+	ret
 
-.section .vsyscall_2, "a"
-ENTRY(vsyscall_2)
-	int $VSYSCALL_EMU_VECTOR
-END(vsyscall_2)
+	.balign 1024, 0xcc
+	mov $__NR_getcpu, %rax
+	syscall
+	ret
+
+	.balign 4096, 0xcc
+
+	.size __vsyscall_page, 4096
diff --git a/arch/x86/kernel/vsyscall_trace.h b/arch/x86/kernel/vsyscall_trace.h
new file mode 100644
index 0000000..a8b2ede
--- /dev/null
+++ b/arch/x86/kernel/vsyscall_trace.h
@@ -0,0 +1,29 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM vsyscall
+
+#if !defined(__VSYSCALL_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define __VSYSCALL_TRACE_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(emulate_vsyscall,
+
+	    TP_PROTO(int nr),
+
+	    TP_ARGS(nr),
+
+	    TP_STRUCT__entry(__field(int, nr)),
+
+	    TP_fast_assign(
+			   __entry->nr = nr;
+			   ),
+
+	    TP_printk("nr = %d", __entry->nr)
+);
+
+#endif
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH ../../arch/x86/kernel
+#define TRACE_INCLUDE_FILE vsyscall_trace
+#include <trace/define_trace.h>
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 988724b..ff5790d 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -22,6 +22,8 @@
 	depends on HAVE_KVM
 	# for device assignment:
 	depends on PCI
+	# for TASKSTATS/TASK_DELAY_ACCT:
+	depends on NET
 	select PREEMPT_NOTIFIERS
 	select MMU_NOTIFIER
 	select ANON_INODES
@@ -31,6 +33,7 @@
 	select KVM_ASYNC_PF
 	select USER_RETURN_NOTIFIER
 	select KVM_MMIO
+	select TASKSTATS
 	select TASK_DELAY_ACCT
 	---help---
 	  Support hosting fully virtualized guest machines using hardware
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 6f08bc9..8b4cc5f 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -3603,7 +3603,7 @@
 		break;
 	case Src2CL:
 		ctxt->src2.bytes = 1;
-		ctxt->src2.val = ctxt->regs[VCPU_REGS_RCX] & 0x8;
+		ctxt->src2.val = ctxt->regs[VCPU_REGS_RCX] & 0xff;
 		break;
 	case Src2ImmByte:
 		rc = decode_imm(ctxt, &ctxt->src2, 1, true);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 1c5b693..8e8da79 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -400,7 +400,8 @@
 
 	/* xchg acts as a barrier before the setting of the high bits */
 	orig.spte_low = xchg(&ssptep->spte_low, sspte.spte_low);
-	orig.spte_high = ssptep->spte_high = sspte.spte_high;
+	orig.spte_high = ssptep->spte_high;
+	ssptep->spte_high = sspte.spte_high;
 	count_spte_clear(sptep, spte);
 
 	return orig.spte;
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 4d09df0..0d17c8c 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -17,6 +17,7 @@
 #include <asm/traps.h>			/* dotraplinkage, ...		*/
 #include <asm/pgalloc.h>		/* pgd_*(), ...			*/
 #include <asm/kmemcheck.h>		/* kmemcheck_*(), ...		*/
+#include <asm/vsyscall.h>
 
 /*
  * Page fault error code bits:
@@ -105,7 +106,7 @@
 		 * but for now it's good enough to assume that long
 		 * mode only uses well known segments or kernel.
 		 */
-		return (!user_mode(regs)) || (regs->cs == __USER_CS);
+		return (!user_mode(regs) || user_64bit_mode(regs));
 #endif
 	case 0x60:
 		/* 0x64 thru 0x67 are valid prefixes in all modes. */
@@ -720,6 +721,18 @@
 		if (is_errata100(regs, address))
 			return;
 
+#ifdef CONFIG_X86_64
+		/*
+		 * Instruction fetch faults in the vsyscall page might need
+		 * emulation.
+		 */
+		if (unlikely((error_code & PF_INSTR) &&
+			     ((address & ~0xfff) == VSYSCALL_START))) {
+			if (emulate_vsyscall(regs, address))
+				return;
+		}
+#endif
+
 		if (unlikely(show_unhandled_signals))
 			show_signal_msg(regs, error_code, address, tsk);
 
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index ae3cb23..039d913 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -360,6 +360,20 @@
 		}
 	}
 
+	/* After the PCI-E bus has been walked and all devices discovered,
+	 * configure any settings of the fabric that might be necessary.
+	 */
+	if (bus) {
+		struct pci_bus *child;
+		list_for_each_entry(child, &bus->children, node) {
+			struct pci_dev *self = child->self;
+			if (!self)
+				continue;
+
+			pcie_bus_configure_settings(child, self->pcie_mpss);
+		}
+	}
+
 	if (!bus)
 		kfree(sd);
 
diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c
index 7000e74b..58425ad 100644
--- a/arch/x86/platform/mrst/mrst.c
+++ b/arch/x86/platform/mrst/mrst.c
@@ -689,7 +689,9 @@
 			irq_attr.trigger = 1;
 			irq_attr.polarity = 1;
 			io_apic_set_pci_routing(NULL, pentry->irq, &irq_attr);
-		}
+		} else
+			pentry->irq = 0; /* No irq */
+
 		switch (pentry->type) {
 		case SFI_DEV_TYPE_IPC:
 			/* ID as IRQ is a hack that will go away */
diff --git a/arch/x86/platform/olpc/olpc.c b/arch/x86/platform/olpc/olpc.c
index 8b9940e..7cce722 100644
--- a/arch/x86/platform/olpc/olpc.c
+++ b/arch/x86/platform/olpc/olpc.c
@@ -161,13 +161,13 @@
 	if (inbuf && inlen) {
 		/* write data to EC */
 		for (i = 0; i < inlen; i++) {
+			pr_devel("olpc-ec:  sending cmd arg 0x%x\n", inbuf[i]);
+			outb(inbuf[i], 0x68);
 			if (wait_on_ibf(0x6c, 0)) {
 				printk(KERN_ERR "olpc-ec:  timeout waiting for"
 						" EC accept data!\n");
 				goto err;
 			}
-			pr_devel("olpc-ec:  sending cmd arg 0x%x\n", inbuf[i]);
-			outb(inbuf[i], 0x68);
 		}
 	}
 	if (outbuf && outlen) {
diff --git a/arch/x86/vdso/vdso.S b/arch/x86/vdso/vdso.S
index 1b979c1..01f5e3b 100644
--- a/arch/x86/vdso/vdso.S
+++ b/arch/x86/vdso/vdso.S
@@ -9,6 +9,7 @@
 vdso_start:
 	.incbin "arch/x86/vdso/vdso.so"
 vdso_end:
+	.align PAGE_SIZE /* extra data here leaks to userspace. */
 
 .previous
 
diff --git a/arch/x86/vdso/vdso32/sysenter.S b/arch/x86/vdso/vdso32/sysenter.S
index e2800af..e354bce 100644
--- a/arch/x86/vdso/vdso32/sysenter.S
+++ b/arch/x86/vdso/vdso32/sysenter.S
@@ -43,7 +43,7 @@
 	.space 7,0x90
 
 	/* 14: System call restart point is here! (SYSENTER_RETURN-2) */
-	jmp .Lenter_kernel
+	int $0x80
 	/* 16: System call normal return point is here! */
 VDSO32_SYSENTER_RETURN:	/* Symbol used by sysenter.c via vdso32-syms.h */
 	pop %ebp
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 3326204..add2c2d 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -15,7 +15,7 @@
 			grant-table.o suspend.o platform-pci-unplug.o \
 			p2m.o
 
-obj-$(CONFIG_FTRACE) += trace.o
+obj-$(CONFIG_EVENT_TRACING) += trace.o
 
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 974a528..2d69617 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -77,8 +77,8 @@
 
 unsigned long *machine_to_phys_mapping = (void *)MACH2PHYS_VIRT_START;
 EXPORT_SYMBOL(machine_to_phys_mapping);
-unsigned int   machine_to_phys_order;
-EXPORT_SYMBOL(machine_to_phys_order);
+unsigned long  machine_to_phys_nr;
+EXPORT_SYMBOL(machine_to_phys_nr);
 
 struct start_info *xen_start_info;
 EXPORT_SYMBOL_GPL(xen_start_info);
@@ -951,6 +951,10 @@
 	.paravirt_enabled = 1,
 	.shared_kernel_pmd = 0,
 
+#ifdef CONFIG_X86_64
+	.extra_user_64bit_cs = FLAT_USER_CS64,
+#endif
+
 	.name = "Xen",
 };
 
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index f987bde..3dd53f9 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1713,15 +1713,17 @@
 void __init xen_setup_machphys_mapping(void)
 {
 	struct xen_machphys_mapping mapping;
-	unsigned long machine_to_phys_nr_ents;
 
 	if (HYPERVISOR_memory_op(XENMEM_machphys_mapping, &mapping) == 0) {
 		machine_to_phys_mapping = (unsigned long *)mapping.v_start;
-		machine_to_phys_nr_ents = mapping.max_mfn + 1;
+		machine_to_phys_nr = mapping.max_mfn + 1;
 	} else {
-		machine_to_phys_nr_ents = MACH2PHYS_NR_ENTRIES;
+		machine_to_phys_nr = MACH2PHYS_NR_ENTRIES;
 	}
-	machine_to_phys_order = fls(machine_to_phys_nr_ents - 1);
+#ifdef CONFIG_X86_32
+	WARN_ON((machine_to_phys_mapping + (machine_to_phys_nr - 1))
+		< machine_to_phys_mapping);
+#endif
 }
 
 #ifdef CONFIG_X86_64
@@ -1916,6 +1918,7 @@
 # endif
 #else
 	case VSYSCALL_LAST_PAGE ... VSYSCALL_FIRST_PAGE:
+	case VVAR_PAGE:
 #endif
 	case FIX_TEXT_POKE0:
 	case FIX_TEXT_POKE1:
@@ -1956,7 +1959,8 @@
 #ifdef CONFIG_X86_64
 	/* Replicate changes to map the vsyscall page into the user
 	   pagetable vsyscall mapping. */
-	if (idx >= VSYSCALL_LAST_PAGE && idx <= VSYSCALL_FIRST_PAGE) {
+	if ((idx >= VSYSCALL_LAST_PAGE && idx <= VSYSCALL_FIRST_PAGE) ||
+	    idx == VVAR_PAGE) {
 		unsigned long vaddr = __fix_to_virt(idx);
 		set_pte_vaddr_pud(level3_user_vsyscall, vaddr, pte);
 	}
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index df118a8..46d6d21 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -184,6 +184,19 @@
 					PFN_UP(start_pci), PFN_DOWN(last));
 	return identity;
 }
+
+static unsigned long __init xen_get_max_pages(void)
+{
+	unsigned long max_pages = MAX_DOMAIN_PAGES;
+	domid_t domid = DOMID_SELF;
+	int ret;
+
+	ret = HYPERVISOR_memory_op(XENMEM_maximum_reservation, &domid);
+	if (ret > 0)
+		max_pages = ret;
+	return min(max_pages, MAX_DOMAIN_PAGES);
+}
+
 /**
  * machine_specific_memory_setup - Hook for machine specific memory setup.
  **/
@@ -292,6 +305,14 @@
 
 	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
 
+	extra_limit = xen_get_max_pages();
+	if (max_pfn + extra_pages > extra_limit) {
+		if (extra_limit > max_pfn)
+			extra_pages = extra_limit - max_pfn;
+		else
+			extra_pages = 0;
+	}
+
 	extra_pages += xen_return_unused_memory(xen_start_info->nr_pages, &e820);
 
 	/*
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index b4533a8..041d4fe 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -32,6 +32,7 @@
 #include <xen/page.h>
 #include <xen/events.h>
 
+#include <xen/hvc-console.h>
 #include "xen-ops.h"
 #include "mmu.h"
 
@@ -207,6 +208,15 @@
 	unsigned cpu;
 	unsigned int i;
 
+	if (skip_ioapic_setup) {
+		char *m = (max_cpus == 0) ?
+			"The nosmp parameter is incompatible with Xen; " \
+			"use Xen dom0_max_vcpus=1 parameter" :
+			"The noapic parameter is incompatible with Xen";
+
+		xen_raw_printk(m);
+		panic(m);
+	}
 	xen_init_lock_cpu(0);
 
 	smp_store_cpu_info(0);
@@ -521,10 +531,7 @@
 	native_smp_prepare_cpus(max_cpus);
 	WARN_ON(xen_smp_intr_init(0));
 
-	if (!xen_have_vector_callback)
-		return;
 	xen_init_lock_cpu(0);
-	xen_init_spinlocks();
 }
 
 static int __cpuinit xen_hvm_cpu_up(unsigned int cpu)
@@ -546,6 +553,8 @@
 
 void __init xen_hvm_smp_init(void)
 {
+	if (!xen_have_vector_callback)
+		return;
 	smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus;
 	smp_ops.smp_send_reschedule = xen_smp_send_reschedule;
 	smp_ops.cpu_up = xen_hvm_cpu_up;
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 5158c50..163b467 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -168,9 +168,10 @@
         struct pvclock_vcpu_time_info *src;
 	cycle_t ret;
 
-	src = &get_cpu_var(xen_vcpu)->time;
+	preempt_disable_notrace();
+	src = &__get_cpu_var(xen_vcpu)->time;
 	ret = pvclock_clocksource_read(src);
-	put_cpu_var(xen_vcpu);
+	preempt_enable_notrace();
 	return ret;
 }
 
diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S
index 22a2093..b040b0e 100644
--- a/arch/x86/xen/xen-asm_32.S
+++ b/arch/x86/xen/xen-asm_32.S
@@ -113,11 +113,13 @@
 
 	/*
 	 * If there's something pending, mask events again so we can
-	 * jump back into xen_hypervisor_callback
+	 * jump back into xen_hypervisor_callback. Otherwise do not
+	 * touch XEN_vcpu_info_mask.
 	 */
-	sete XEN_vcpu_info_mask(%eax)
+	jne 1f
+	movb $1, XEN_vcpu_info_mask(%eax)
 
-	popl %eax
+1:	popl %eax
 
 	/*
 	 * From this point on the registers are restored and the stack
diff --git a/arch/xtensa/include/asm/unistd.h b/arch/xtensa/include/asm/unistd.h
index a6f934f..798ee6d 100644
--- a/arch/xtensa/include/asm/unistd.h
+++ b/arch/xtensa/include/asm/unistd.h
@@ -455,7 +455,7 @@
 #define __NR_quotactl 				204
 __SYSCALL(204, sys_quotactl, 4)
 #define __NR_nfsservctl 			205
-__SYSCALL(205, sys_nfsservctl, 3)
+__SYSCALL(205, sys_ni_syscall, 0)
 #define __NR__sysctl 				206
 __SYSCALL(206, sys_sysctl, 1)
 #define __NR_bdflush 				207
diff --git a/block/Kconfig b/block/Kconfig
index 60be1e0..e97934e 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -65,6 +65,16 @@
 
 	  If unsure, say Y.
 
+config BLK_DEV_BSGLIB
+	bool "Block layer SG support v4 helper lib"
+	default n
+	select BLK_DEV_BSG
+	help
+	  Subsystems will normally enable this if needed. Users will not
+	  normally need to manually enable this.
+
+	  If unsure, say N.
+
 config BLK_DEV_INTEGRITY
 	bool "Block layer data integrity support"
 	---help---
diff --git a/block/Makefile b/block/Makefile
index 0fec4b3..514c6e4 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -8,6 +8,7 @@
 			blk-iopoll.o blk-lib.o ioctl.o genhd.o scsi_ioctl.o
 
 obj-$(CONFIG_BLK_DEV_BSG)	+= bsg.o
+obj-$(CONFIG_BLK_DEV_BSGLIB)	+= bsg-lib.o
 obj-$(CONFIG_BLK_CGROUP)	+= blk-cgroup.o
 obj-$(CONFIG_BLK_DEV_THROTTLING)	+= blk-throttle.o
 obj-$(CONFIG_IOSCHED_NOOP)	+= noop-iosched.o
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index bcaf16e..b596e54 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -785,10 +785,10 @@
 {
 	char *s[4], *p, *major_s = NULL, *minor_s = NULL;
 	int ret;
-	unsigned long major, minor, temp;
+	unsigned long major, minor;
 	int i = 0;
 	dev_t dev;
-	u64 bps, iops;
+	u64 temp;
 
 	memset(s, 0, sizeof(s));
 
@@ -826,20 +826,23 @@
 
 	dev = MKDEV(major, minor);
 
-	ret = blkio_check_dev_num(dev);
+	ret = strict_strtoull(s[1], 10, &temp);
 	if (ret)
-		return ret;
+		return -EINVAL;
+
+	/* For rule removal, do not check for device presence. */
+	if (temp) {
+		ret = blkio_check_dev_num(dev);
+		if (ret)
+			return ret;
+	}
 
 	newpn->dev = dev;
 
-	if (s[1] == NULL)
-		return -EINVAL;
-
 	switch (plid) {
 	case BLKIO_POLICY_PROP:
-		ret = strict_strtoul(s[1], 10, &temp);
-		if (ret || (temp < BLKIO_WEIGHT_MIN && temp > 0) ||
-			temp > BLKIO_WEIGHT_MAX)
+		if ((temp < BLKIO_WEIGHT_MIN && temp > 0) ||
+		     temp > BLKIO_WEIGHT_MAX)
 			return -EINVAL;
 
 		newpn->plid = plid;
@@ -850,26 +853,18 @@
 		switch(fileid) {
 		case BLKIO_THROTL_read_bps_device:
 		case BLKIO_THROTL_write_bps_device:
-			ret = strict_strtoull(s[1], 10, &bps);
-			if (ret)
-				return -EINVAL;
-
 			newpn->plid = plid;
 			newpn->fileid = fileid;
-			newpn->val.bps = bps;
+			newpn->val.bps = temp;
 			break;
 		case BLKIO_THROTL_read_iops_device:
 		case BLKIO_THROTL_write_iops_device:
-			ret = strict_strtoull(s[1], 10, &iops);
-			if (ret)
-				return -EINVAL;
-
-			if (iops > THROTL_IOPS_MAX)
+			if (temp > THROTL_IOPS_MAX)
 				return -EINVAL;
 
 			newpn->plid = plid;
 			newpn->fileid = fileid;
-			newpn->val.iops = (unsigned int)iops;
+			newpn->val.iops = (unsigned int)temp;
 			break;
 		}
 		break;
diff --git a/block/blk-core.c b/block/blk-core.c
index b627558..b2ed78a 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1167,7 +1167,7 @@
  * true if merge was successful, otherwise false.
  */
 static bool attempt_plug_merge(struct task_struct *tsk, struct request_queue *q,
-			       struct bio *bio)
+			       struct bio *bio, unsigned int *request_count)
 {
 	struct blk_plug *plug;
 	struct request *rq;
@@ -1176,10 +1176,13 @@
 	plug = tsk->plug;
 	if (!plug)
 		goto out;
+	*request_count = 0;
 
 	list_for_each_entry_reverse(rq, &plug->list, queuelist) {
 		int el_ret;
 
+		(*request_count)++;
+
 		if (rq->q != q)
 			continue;
 
@@ -1219,6 +1222,7 @@
 	struct blk_plug *plug;
 	int el_ret, rw_flags, where = ELEVATOR_INSERT_SORT;
 	struct request *req;
+	unsigned int request_count = 0;
 
 	/*
 	 * low level driver can indicate that it wants pages above a
@@ -1237,7 +1241,7 @@
 	 * Check if we can merge with the plugged list before grabbing
 	 * any locks.
 	 */
-	if (attempt_plug_merge(current, q, bio))
+	if (attempt_plug_merge(current, q, bio, &request_count))
 		goto out;
 
 	spin_lock_irq(q->queue_lock);
@@ -1302,11 +1306,10 @@
 			if (__rq->q != q)
 				plug->should_sort = 1;
 		}
-		list_add_tail(&req->queuelist, &plug->list);
-		plug->count++;
-		drive_stat_acct(req, 1);
-		if (plug->count >= BLK_MAX_REQUEST_COUNT)
+		if (request_count >= BLK_MAX_REQUEST_COUNT)
 			blk_flush_plug_list(plug, false);
+		list_add_tail(&req->queuelist, &plug->list);
+		drive_stat_acct(req, 1);
 	} else {
 		spin_lock_irq(q->queue_lock);
 		add_acct_request(q, req, where);
@@ -1702,6 +1705,7 @@
 int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 {
 	unsigned long flags;
+	int where = ELEVATOR_INSERT_BACK;
 
 	if (blk_rq_check_limits(q, rq))
 		return -EIO;
@@ -1718,7 +1722,10 @@
 	 */
 	BUG_ON(blk_queued_rq(rq));
 
-	add_acct_request(q, rq, ELEVATOR_INSERT_BACK);
+	if (rq->cmd_flags & (REQ_FLUSH|REQ_FUA))
+		where = ELEVATOR_INSERT_FLUSH;
+
+	add_acct_request(q, rq, where);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 
 	return 0;
@@ -2275,7 +2282,7 @@
  *     %false - we are done with this request
  *     %true  - still buffers pending for this request
  **/
-static bool __blk_end_bidi_request(struct request *rq, int error,
+bool __blk_end_bidi_request(struct request *rq, int error,
 				   unsigned int nr_bytes, unsigned int bidi_bytes)
 {
 	if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes))
@@ -2630,7 +2637,6 @@
 	INIT_LIST_HEAD(&plug->list);
 	INIT_LIST_HEAD(&plug->cb_list);
 	plug->should_sort = 0;
-	plug->count = 0;
 
 	/*
 	 * If this is a nested plug, don't actually assign it. It will be
@@ -2714,7 +2720,6 @@
 		return;
 
 	list_splice_init(&plug->list, &list);
-	plug->count = 0;
 
 	if (plug->should_sort) {
 		list_sort(NULL, &list, plug_rq_cmp);
diff --git a/block/blk-flush.c b/block/blk-flush.c
index bb21e4c..491eb30 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -95,11 +95,12 @@
 {
 	unsigned int policy = 0;
 
+	if (blk_rq_sectors(rq))
+		policy |= REQ_FSEQ_DATA;
+
 	if (fflags & REQ_FLUSH) {
 		if (rq->cmd_flags & REQ_FLUSH)
 			policy |= REQ_FSEQ_PREFLUSH;
-		if (blk_rq_sectors(rq))
-			policy |= REQ_FSEQ_DATA;
 		if (!(fflags & REQ_FUA) && (rq->cmd_flags & REQ_FUA))
 			policy |= REQ_FSEQ_POSTFLUSH;
 	}
@@ -122,7 +123,7 @@
 
 	/* make @rq a normal request */
 	rq->cmd_flags &= ~REQ_FLUSH_SEQ;
-	rq->end_io = NULL;
+	rq->end_io = rq->flush.saved_end_io;
 }
 
 /**
@@ -300,9 +301,6 @@
 	unsigned int fflags = q->flush_flags;	/* may change, cache */
 	unsigned int policy = blk_flush_policy(fflags, rq);
 
-	BUG_ON(rq->end_io);
-	BUG_ON(!rq->bio || rq->bio != rq->biotail);
-
 	/*
 	 * @policy now records what operations need to be done.  Adjust
 	 * REQ_FLUSH and FUA for the driver.
@@ -312,6 +310,19 @@
 		rq->cmd_flags &= ~REQ_FUA;
 
 	/*
+	 * An empty flush handed down from a stacking driver may
+	 * translate into nothing if the underlying device does not
+	 * advertise a write-back cache.  In this case, simply
+	 * complete the request.
+	 */
+	if (!policy) {
+		__blk_end_bidi_request(rq, 0, 0, 0);
+		return;
+	}
+
+	BUG_ON(!rq->bio || rq->bio != rq->biotail);
+
+	/*
 	 * If there's data but flush is not necessary, the request can be
 	 * processed directly without going through flush machinery.  Queue
 	 * for normal execution.
@@ -319,6 +330,7 @@
 	if ((policy & REQ_FSEQ_DATA) &&
 	    !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
 		list_add_tail(&rq->queuelist, &q->queue_head);
+		blk_run_queue_async(q);
 		return;
 	}
 
@@ -329,6 +341,7 @@
 	memset(&rq->flush, 0, sizeof(rq->flush));
 	INIT_LIST_HEAD(&rq->flush.list);
 	rq->cmd_flags |= REQ_FLUSH_SEQ;
+	rq->flush.saved_end_io = rq->end_io; /* Usually NULL */
 	rq->end_io = flush_data_end_io;
 
 	blk_flush_complete_seq(rq, REQ_FSEQ_ACTIONS & ~policy, 0);
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index 475fab8..1366a89 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -115,7 +115,7 @@
 	/*
 	 * Select completion CPU
 	 */
-	if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags) && req->cpu != -1) {
+	if (req->cpu != -1) {
 		ccpu = req->cpu;
 		if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags)) {
 			ccpu = blk_cpu_to_group(ccpu);
@@ -124,6 +124,14 @@
 	} else
 		ccpu = cpu;
 
+	/*
+	 * If current CPU and requested CPU are in the same group, running
+	 * softirq in current CPU. One might concern this is just like
+	 * QUEUE_FLAG_SAME_FORCE, but actually not. blk_complete_request() is
+	 * running in interrupt handler, and currently I/O controller doesn't
+	 * support multiple interrupts, so current CPU is unique actually. This
+	 * avoids IPI sending from current CPU to the first CPU of a group.
+	 */
 	if (ccpu == cpu || ccpu == group_cpu) {
 		struct list_head *list;
 do_local:
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 0ee17b5..e681805 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -258,11 +258,13 @@
 
 	ret = queue_var_store(&val, page, count);
 	spin_lock_irq(q->queue_lock);
-	if (val) {
+	if (val == 2) {
 		queue_flag_set(QUEUE_FLAG_SAME_COMP, q);
-		if (val == 2)
-			queue_flag_set(QUEUE_FLAG_SAME_FORCE, q);
-	} else {
+		queue_flag_set(QUEUE_FLAG_SAME_FORCE, q);
+	} else if (val == 1) {
+		queue_flag_set(QUEUE_FLAG_SAME_COMP, q);
+		queue_flag_clear(QUEUE_FLAG_SAME_FORCE, q);
+	} else if (val == 0) {
 		queue_flag_clear(QUEUE_FLAG_SAME_COMP, q);
 		queue_flag_clear(QUEUE_FLAG_SAME_FORCE, q);
 	}
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index f6a7941..a19f58c 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -746,7 +746,7 @@
 static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio)
 {
 	bool rw = bio_data_dir(bio);
-	bool sync = bio->bi_rw & REQ_SYNC;
+	bool sync = rw_is_sync(bio->bi_rw);
 
 	/* Charge the bio to the group */
 	tg->bytes_disp[rw] += bio->bi_size;
@@ -1150,7 +1150,7 @@
 
 		if (tg_no_rule_group(tg, rw)) {
 			blkiocg_update_dispatch_stats(&tg->blkg, bio->bi_size,
-					rw, bio->bi_rw & REQ_SYNC);
+					rw, rw_is_sync(bio->bi_rw));
 			rcu_read_unlock();
 			return 0;
 		}
diff --git a/block/blk.h b/block/blk.h
index d658628..20b900a 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -17,6 +17,8 @@
 		      struct bio *bio);
 void blk_dequeue_request(struct request *rq);
 void __blk_queue_free_tags(struct request_queue *q);
+bool __blk_end_bidi_request(struct request *rq, int error,
+			    unsigned int nr_bytes, unsigned int bidi_bytes);
 
 void blk_rq_timed_out_timer(unsigned long data);
 void blk_delete_timer(struct request *);
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
new file mode 100644
index 0000000..6690e6e
--- /dev/null
+++ b/block/bsg-lib.c
@@ -0,0 +1,298 @@
+/*
+ *  BSG helper library
+ *
+ *  Copyright (C) 2008   James Smart, Emulex Corporation
+ *  Copyright (C) 2011   Red Hat, Inc.  All rights reserved.
+ *  Copyright (C) 2011   Mike Christie
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ */
+#include <linux/slab.h>
+#include <linux/blkdev.h>
+#include <linux/delay.h>
+#include <linux/scatterlist.h>
+#include <linux/bsg-lib.h>
+#include <linux/module.h>
+#include <scsi/scsi_cmnd.h>
+
+/**
+ * bsg_destroy_job - routine to teardown/delete a bsg job
+ * @job: bsg_job that is to be torn down
+ */
+static void bsg_destroy_job(struct bsg_job *job)
+{
+	put_device(job->dev);	/* release reference for the request */
+
+	kfree(job->request_payload.sg_list);
+	kfree(job->reply_payload.sg_list);
+	kfree(job);
+}
+
+/**
+ * bsg_job_done - completion routine for bsg requests
+ * @job: bsg_job that is complete
+ * @result: job reply result
+ * @reply_payload_rcv_len: length of payload recvd
+ *
+ * The LLD should call this when the bsg job has completed.
+ */
+void bsg_job_done(struct bsg_job *job, int result,
+		  unsigned int reply_payload_rcv_len)
+{
+	struct request *req = job->req;
+	struct request *rsp = req->next_rq;
+	int err;
+
+	err = job->req->errors = result;
+	if (err < 0)
+		/* we're only returning the result field in the reply */
+		job->req->sense_len = sizeof(u32);
+	else
+		job->req->sense_len = job->reply_len;
+	/* we assume all request payload was transferred, residual == 0 */
+	req->resid_len = 0;
+
+	if (rsp) {
+		WARN_ON(reply_payload_rcv_len > rsp->resid_len);
+
+		/* set reply (bidi) residual */
+		rsp->resid_len -= min(reply_payload_rcv_len, rsp->resid_len);
+	}
+	blk_complete_request(req);
+}
+EXPORT_SYMBOL_GPL(bsg_job_done);
+
+/**
+ * bsg_softirq_done - softirq done routine for destroying the bsg requests
+ * @rq: BSG request that holds the job to be destroyed
+ */
+static void bsg_softirq_done(struct request *rq)
+{
+	struct bsg_job *job = rq->special;
+
+	blk_end_request_all(rq, rq->errors);
+	bsg_destroy_job(job);
+}
+
+static int bsg_map_buffer(struct bsg_buffer *buf, struct request *req)
+{
+	size_t sz = (sizeof(struct scatterlist) * req->nr_phys_segments);
+
+	BUG_ON(!req->nr_phys_segments);
+
+	buf->sg_list = kzalloc(sz, GFP_KERNEL);
+	if (!buf->sg_list)
+		return -ENOMEM;
+	sg_init_table(buf->sg_list, req->nr_phys_segments);
+	buf->sg_cnt = blk_rq_map_sg(req->q, req, buf->sg_list);
+	buf->payload_len = blk_rq_bytes(req);
+	return 0;
+}
+
+/**
+ * bsg_create_job - create the bsg_job structure for the bsg request
+ * @dev: device that is being sent the bsg request
+ * @req: BSG request that needs a job structure
+ */
+static int bsg_create_job(struct device *dev, struct request *req)
+{
+	struct request *rsp = req->next_rq;
+	struct request_queue *q = req->q;
+	struct bsg_job *job;
+	int ret;
+
+	BUG_ON(req->special);
+
+	job = kzalloc(sizeof(struct bsg_job) + q->bsg_job_size, GFP_KERNEL);
+	if (!job)
+		return -ENOMEM;
+
+	req->special = job;
+	job->req = req;
+	if (q->bsg_job_size)
+		job->dd_data = (void *)&job[1];
+	job->request = req->cmd;
+	job->request_len = req->cmd_len;
+	job->reply = req->sense;
+	job->reply_len = SCSI_SENSE_BUFFERSIZE;	/* Size of sense buffer
+						 * allocated */
+	if (req->bio) {
+		ret = bsg_map_buffer(&job->request_payload, req);
+		if (ret)
+			goto failjob_rls_job;
+	}
+	if (rsp && rsp->bio) {
+		ret = bsg_map_buffer(&job->reply_payload, rsp);
+		if (ret)
+			goto failjob_rls_rqst_payload;
+	}
+	job->dev = dev;
+	/* take a reference for the request */
+	get_device(job->dev);
+	return 0;
+
+failjob_rls_rqst_payload:
+	kfree(job->request_payload.sg_list);
+failjob_rls_job:
+	kfree(job);
+	return -ENOMEM;
+}
+
+/*
+ * bsg_goose_queue - restart queue in case it was stopped
+ * @q: request q to be restarted
+ */
+void bsg_goose_queue(struct request_queue *q)
+{
+	if (!q)
+		return;
+
+	blk_run_queue_async(q);
+}
+EXPORT_SYMBOL_GPL(bsg_goose_queue);
+
+/**
+ * bsg_request_fn - generic handler for bsg requests
+ * @q: request queue to manage
+ *
+ * On error the create_bsg_job function should return a -Exyz error value
+ * that will be set to the req->errors.
+ *
+ * Drivers/subsys should pass this to the queue init function.
+ */
+void bsg_request_fn(struct request_queue *q)
+{
+	struct device *dev = q->queuedata;
+	struct request *req;
+	struct bsg_job *job;
+	int ret;
+
+	if (!get_device(dev))
+		return;
+
+	while (1) {
+		req = blk_fetch_request(q);
+		if (!req)
+			break;
+		spin_unlock_irq(q->queue_lock);
+
+		ret = bsg_create_job(dev, req);
+		if (ret) {
+			req->errors = ret;
+			blk_end_request_all(req, ret);
+			spin_lock_irq(q->queue_lock);
+			continue;
+		}
+
+		job = req->special;
+		ret = q->bsg_job_fn(job);
+		spin_lock_irq(q->queue_lock);
+		if (ret)
+			break;
+	}
+
+	spin_unlock_irq(q->queue_lock);
+	put_device(dev);
+	spin_lock_irq(q->queue_lock);
+}
+EXPORT_SYMBOL_GPL(bsg_request_fn);
+
+/**
+ * bsg_setup_queue - Create and add the bsg hooks so we can receive requests
+ * @dev: device to attach bsg device to
+ * @q: request queue setup by caller
+ * @name: device to give bsg device
+ * @job_fn: bsg job handler
+ * @dd_job_size: size of LLD data needed for each job
+ *
+ * The caller should have setup the reuqest queue with bsg_request_fn
+ * as the request_fn.
+ */
+int bsg_setup_queue(struct device *dev, struct request_queue *q,
+		    char *name, bsg_job_fn *job_fn, int dd_job_size)
+{
+	int ret;
+
+	q->queuedata = dev;
+	q->bsg_job_size = dd_job_size;
+	q->bsg_job_fn = job_fn;
+	queue_flag_set_unlocked(QUEUE_FLAG_BIDI, q);
+	blk_queue_softirq_done(q, bsg_softirq_done);
+	blk_queue_rq_timeout(q, BLK_DEFAULT_SG_TIMEOUT);
+
+	ret = bsg_register_queue(q, dev, name, NULL);
+	if (ret) {
+		printk(KERN_ERR "%s: bsg interface failed to "
+		       "initialize - register queue\n", dev->kobj.name);
+		return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(bsg_setup_queue);
+
+/**
+ * bsg_remove_queue - Deletes the bsg dev from the q
+ * @q:	the request_queue that is to be torn down.
+ *
+ * Notes:
+ *   Before unregistering the queue empty any requests that are blocked
+ */
+void bsg_remove_queue(struct request_queue *q)
+{
+	struct request *req; /* block request */
+	int counts; /* totals for request_list count and starved */
+
+	if (!q)
+		return;
+
+	/* Stop taking in new requests */
+	spin_lock_irq(q->queue_lock);
+	blk_stop_queue(q);
+
+	/* drain all requests in the queue */
+	while (1) {
+		/* need the lock to fetch a request
+		 * this may fetch the same reqeust as the previous pass
+		 */
+		req = blk_fetch_request(q);
+		/* save requests in use and starved */
+		counts = q->rq.count[0] + q->rq.count[1] +
+			 q->rq.starved[0] + q->rq.starved[1];
+		spin_unlock_irq(q->queue_lock);
+		/* any requests still outstanding? */
+		if (counts == 0)
+			break;
+
+		/* This may be the same req as the previous iteration,
+		 * always send the blk_end_request_all after a prefetch.
+		 * It is not okay to not end the request because the
+		 * prefetch started the request.
+		 */
+		if (req) {
+			/* return -ENXIO to indicate that this queue is
+			 * going away
+			 */
+			req->errors = -ENXIO;
+			blk_end_request_all(req, -ENXIO);
+		}
+
+		msleep(200); /* allow bsg to possibly finish */
+		spin_lock_irq(q->queue_lock);
+	}
+	bsg_unregister_queue(q);
+}
+EXPORT_SYMBOL_GPL(bsg_remove_queue);
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 1f96ad6..16ace89 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -130,6 +130,8 @@
 	unsigned long slice_end;
 	long slice_resid;
 
+	/* pending priority requests */
+	int prio_pending;
 	/* number of requests that are on the dispatch list or inside driver */
 	int dispatched;
 
@@ -682,6 +684,9 @@
 	if (rq_is_sync(rq1) != rq_is_sync(rq2))
 		return rq_is_sync(rq1) ? rq1 : rq2;
 
+	if ((rq1->cmd_flags ^ rq2->cmd_flags) & REQ_PRIO)
+		return rq1->cmd_flags & REQ_PRIO ? rq1 : rq2;
+
 	s1 = blk_rq_pos(rq1);
 	s2 = blk_rq_pos(rq2);
 
@@ -1209,6 +1214,9 @@
 
 	hlist_del_init(&cfqg->cfqd_node);
 
+	BUG_ON(cfqd->nr_blkcg_linked_grps <= 0);
+	cfqd->nr_blkcg_linked_grps--;
+
 	/*
 	 * Put the reference taken at the time of creation so that when all
 	 * queues are gone, group can be destroyed.
@@ -1604,6 +1612,10 @@
 	cfqq->cfqd->rq_queued--;
 	cfq_blkiocg_update_io_remove_stats(&(RQ_CFQG(rq))->blkg,
 					rq_data_dir(rq), rq_is_sync(rq));
+	if (rq->cmd_flags & REQ_PRIO) {
+		WARN_ON(!cfqq->prio_pending);
+		cfqq->prio_pending--;
+	}
 }
 
 static int cfq_merge(struct request_queue *q, struct request **req,
@@ -3357,6 +3369,13 @@
 		return true;
 
 	/*
+	 * So both queues are sync. Let the new request get disk time if
+	 * it's a metadata request and the current queue is doing regular IO.
+	 */
+	if ((rq->cmd_flags & REQ_PRIO) && !cfqq->prio_pending)
+		return true;
+
+	/*
 	 * Allow an RT request to pre-empt an ongoing non-RT cfqq timeslice.
 	 */
 	if (cfq_class_rt(new_cfqq) && !cfq_class_rt(cfqq))
@@ -3420,6 +3439,8 @@
 	struct cfq_io_context *cic = RQ_CIC(rq);
 
 	cfqd->rq_queued++;
+	if (rq->cmd_flags & REQ_PRIO)
+		cfqq->prio_pending++;
 
 	cfq_update_io_thinktime(cfqd, cfqq, cic);
 	cfq_update_io_seektime(cfqd, cfqq, rq);
diff --git a/block/genhd.c b/block/genhd.c
index 5cb51c5..e2f6790 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1146,17 +1146,17 @@
 		cpu = part_stat_lock();
 		part_round_stats(cpu, hd);
 		part_stat_unlock();
-		seq_printf(seqf, "%4d %7d %s %lu %lu %llu "
-			   "%u %lu %lu %llu %u %u %u %u\n",
+		seq_printf(seqf, "%4d %7d %s %lu %lu %lu "
+			   "%u %lu %lu %lu %u %u %u %u\n",
 			   MAJOR(part_devt(hd)), MINOR(part_devt(hd)),
 			   disk_name(gp, hd->partno, buf),
 			   part_stat_read(hd, ios[READ]),
 			   part_stat_read(hd, merges[READ]),
-			   (unsigned long long)part_stat_read(hd, sectors[READ]),
+			   part_stat_read(hd, sectors[READ]),
 			   jiffies_to_msecs(part_stat_read(hd, ticks[READ])),
 			   part_stat_read(hd, ios[WRITE]),
 			   part_stat_read(hd, merges[WRITE]),
-			   (unsigned long long)part_stat_read(hd, sectors[WRITE]),
+			   part_stat_read(hd, sectors[WRITE]),
 			   jiffies_to_msecs(part_stat_read(hd, ticks[WRITE])),
 			   part_in_flight(hd),
 			   jiffies_to_msecs(part_stat_read(hd, io_ticks)),
diff --git a/drivers/acpi/acpica/acconfig.h b/drivers/acpi/acpica/acconfig.h
index bc533dd..f895a24 100644
--- a/drivers/acpi/acpica/acconfig.h
+++ b/drivers/acpi/acpica/acconfig.h
@@ -121,7 +121,7 @@
 
 /* Maximum sleep allowed via Sleep() operator */
 
-#define ACPI_MAX_SLEEP                  20000	/* Two seconds */
+#define ACPI_MAX_SLEEP                  2000	/* Two seconds */
 
 /******************************************************************************
  *
diff --git a/drivers/acpi/apei/Kconfig b/drivers/acpi/apei/Kconfig
index c34aa51..e3f4787 100644
--- a/drivers/acpi/apei/Kconfig
+++ b/drivers/acpi/apei/Kconfig
@@ -13,6 +13,7 @@
 	bool "APEI Generic Hardware Error Source"
 	depends on ACPI_APEI && X86
 	select ACPI_HED
+	select IRQ_WORK
 	select LLIST
 	select GENERIC_ALLOCATOR
 	help
diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c
index 8041248..6154036 100644
--- a/drivers/acpi/apei/apei-base.c
+++ b/drivers/acpi/apei/apei-base.c
@@ -618,7 +618,7 @@
 	};
 
 	capbuf[OSC_QUERY_TYPE] = OSC_QUERY_ENABLE;
-	capbuf[OSC_SUPPORT_TYPE] = 0;
+	capbuf[OSC_SUPPORT_TYPE] = 1;
 	capbuf[OSC_CONTROL_TYPE] = 0;
 
 	if (ACPI_FAILURE(acpi_get_handle(NULL, "\\_SB", &handle))
diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig
index ca3e6be..5987e0b 100644
--- a/drivers/ata/Kconfig
+++ b/drivers/ata/Kconfig
@@ -468,6 +468,15 @@
 	  interface card.  This is not required for ICS partition support.
 	  If you are unsure, say N to this.
 
+config PATA_IMX
+	tristate "PATA support for Freescale iMX"
+	depends on ARCH_MXC
+	help
+	  This option enables support for the PATA host available on Freescale
+          iMX SoCs.
+
+	  If unsure, say N.
+
 config PATA_IT8213
 	tristate "IT8213 PATA support (Experimental)"
 	depends on PCI && EXPERIMENTAL
diff --git a/drivers/ata/Makefile b/drivers/ata/Makefile
index 8ac64e1..9550d69 100644
--- a/drivers/ata/Makefile
+++ b/drivers/ata/Makefile
@@ -48,6 +48,7 @@
 obj-$(CONFIG_PATA_HPT3X2N)	+= pata_hpt3x2n.o
 obj-$(CONFIG_PATA_HPT3X3)	+= pata_hpt3x3.o
 obj-$(CONFIG_PATA_ICSIDE)	+= pata_icside.o
+obj-$(CONFIG_PATA_IMX)		+= pata_imx.o
 obj-$(CONFIG_PATA_IT8213)	+= pata_it8213.o
 obj-$(CONFIG_PATA_IT821X)	+= pata_it821x.o
 obj-$(CONFIG_PATA_JMICRON)	+= pata_jmicron.o
diff --git a/drivers/ata/pata_imx.c b/drivers/ata/pata_imx.c
new file mode 100644
index 0000000..ca9d9ca
--- /dev/null
+++ b/drivers/ata/pata_imx.c
@@ -0,0 +1,253 @@
+/*
+ * Freescale iMX PATA driver
+ *
+ * Copyright (C) 2011 Arnaud Patard <arnaud.patard@rtp-net.org>
+ *
+ * Based on pata_platform - Copyright (C) 2006 - 2007  Paul Mundt
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * TODO:
+ * - dmaengine support
+ * - check if timing stuff needed
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/blkdev.h>
+#include <scsi/scsi_host.h>
+#include <linux/ata.h>
+#include <linux/libata.h>
+#include <linux/platform_device.h>
+#include <linux/clk.h>
+
+#define DRV_NAME "pata_imx"
+
+#define PATA_IMX_ATA_CONTROL		0x24
+#define PATA_IMX_ATA_CTRL_FIFO_RST_B	(1<<7)
+#define PATA_IMX_ATA_CTRL_ATA_RST_B	(1<<6)
+#define PATA_IMX_ATA_CTRL_IORDY_EN	(1<<0)
+#define PATA_IMX_ATA_INT_EN		0x2C
+#define PATA_IMX_ATA_INTR_ATA_INTRQ2	(1<<3)
+#define PATA_IMX_DRIVE_DATA		0xA0
+#define PATA_IMX_DRIVE_CONTROL		0xD8
+
+struct pata_imx_priv {
+	struct clk *clk;
+	/* timings/interrupt/control regs */
+	u8 *host_regs;
+	u32 ata_ctl;
+};
+
+static int pata_imx_set_mode(struct ata_link *link, struct ata_device **unused)
+{
+	struct ata_device *dev;
+	struct ata_port *ap = link->ap;
+	struct pata_imx_priv *priv = ap->host->private_data;
+	u32 val;
+
+	ata_for_each_dev(dev, link, ENABLED) {
+		dev->pio_mode = dev->xfer_mode = XFER_PIO_0;
+		dev->xfer_shift = ATA_SHIFT_PIO;
+		dev->flags |= ATA_DFLAG_PIO;
+
+		val = __raw_readl(priv->host_regs + PATA_IMX_ATA_CONTROL);
+		if (ata_pio_need_iordy(dev))
+			val |= PATA_IMX_ATA_CTRL_IORDY_EN;
+		else
+			val &= ~PATA_IMX_ATA_CTRL_IORDY_EN;
+		__raw_writel(val, priv->host_regs + PATA_IMX_ATA_CONTROL);
+
+		ata_dev_printk(dev, KERN_INFO, "configured for PIO\n");
+	}
+	return 0;
+}
+
+static struct scsi_host_template pata_imx_sht = {
+	ATA_PIO_SHT(DRV_NAME),
+};
+
+static struct ata_port_operations pata_imx_port_ops = {
+	.inherits		= &ata_sff_port_ops,
+	.sff_data_xfer		= ata_sff_data_xfer_noirq,
+	.cable_detect		= ata_cable_unknown,
+	.set_mode		= pata_imx_set_mode,
+};
+
+static void pata_imx_setup_port(struct ata_ioports *ioaddr)
+{
+	/* Fixup the port shift for platforms that need it */
+	ioaddr->data_addr	= ioaddr->cmd_addr + (ATA_REG_DATA    << 2);
+	ioaddr->error_addr	= ioaddr->cmd_addr + (ATA_REG_ERR     << 2);
+	ioaddr->feature_addr	= ioaddr->cmd_addr + (ATA_REG_FEATURE << 2);
+	ioaddr->nsect_addr	= ioaddr->cmd_addr + (ATA_REG_NSECT   << 2);
+	ioaddr->lbal_addr	= ioaddr->cmd_addr + (ATA_REG_LBAL    << 2);
+	ioaddr->lbam_addr	= ioaddr->cmd_addr + (ATA_REG_LBAM    << 2);
+	ioaddr->lbah_addr	= ioaddr->cmd_addr + (ATA_REG_LBAH    << 2);
+	ioaddr->device_addr	= ioaddr->cmd_addr + (ATA_REG_DEVICE  << 2);
+	ioaddr->status_addr	= ioaddr->cmd_addr + (ATA_REG_STATUS  << 2);
+	ioaddr->command_addr	= ioaddr->cmd_addr + (ATA_REG_CMD     << 2);
+}
+
+static int __devinit pata_imx_probe(struct platform_device *pdev)
+{
+	struct ata_host *host;
+	struct ata_port *ap;
+	struct pata_imx_priv *priv;
+	int irq = 0;
+	struct resource *io_res;
+
+	io_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (io_res == NULL)
+		return -EINVAL;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq <= 0)
+		return -EINVAL;
+
+	priv = devm_kzalloc(&pdev->dev,
+				sizeof(struct pata_imx_priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->clk = clk_get(&pdev->dev, NULL);
+	if (IS_ERR(priv->clk)) {
+		dev_err(&pdev->dev, "Failed to get clock\n");
+		return PTR_ERR(priv->clk);
+	}
+
+	clk_enable(priv->clk);
+
+	host = ata_host_alloc(&pdev->dev, 1);
+	if (!host)
+		goto free_priv;
+
+	host->private_data = priv;
+	ap = host->ports[0];
+
+	ap->ops = &pata_imx_port_ops;
+	ap->pio_mask = ATA_PIO0;
+	ap->flags |= ATA_FLAG_SLAVE_POSS;
+
+	priv->host_regs = devm_ioremap(&pdev->dev, io_res->start,
+		resource_size(io_res));
+	if (!priv->host_regs) {
+		dev_err(&pdev->dev, "failed to map IO/CTL base\n");
+		goto free_priv;
+	}
+
+	ap->ioaddr.cmd_addr = priv->host_regs + PATA_IMX_DRIVE_DATA;
+	ap->ioaddr.ctl_addr = priv->host_regs + PATA_IMX_DRIVE_CONTROL;
+
+	ap->ioaddr.altstatus_addr = ap->ioaddr.ctl_addr;
+
+	pata_imx_setup_port(&ap->ioaddr);
+
+	ata_port_desc(ap, "cmd 0x%llx ctl 0x%llx",
+		(unsigned long long)io_res->start + PATA_IMX_DRIVE_DATA,
+		(unsigned long long)io_res->start + PATA_IMX_DRIVE_CONTROL);
+
+	/* deassert resets */
+	__raw_writel(PATA_IMX_ATA_CTRL_FIFO_RST_B |
+			PATA_IMX_ATA_CTRL_ATA_RST_B,
+			priv->host_regs + PATA_IMX_ATA_CONTROL);
+	/* enable interrupts */
+	__raw_writel(PATA_IMX_ATA_INTR_ATA_INTRQ2,
+			priv->host_regs + PATA_IMX_ATA_INT_EN);
+
+	/* activate */
+	return ata_host_activate(host, irq, ata_sff_interrupt, 0,
+				&pata_imx_sht);
+
+free_priv:
+	clk_disable(priv->clk);
+	clk_put(priv->clk);
+	return -ENOMEM;
+}
+
+static int __devexit pata_imx_remove(struct platform_device *pdev)
+{
+	struct ata_host *host = dev_get_drvdata(&pdev->dev);
+	struct pata_imx_priv *priv = host->private_data;
+
+	ata_host_detach(host);
+
+	__raw_writel(0, priv->host_regs + PATA_IMX_ATA_INT_EN);
+
+	clk_disable(priv->clk);
+	clk_put(priv->clk);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int pata_imx_suspend(struct device *dev)
+{
+	struct ata_host *host = dev_get_drvdata(dev);
+	struct pata_imx_priv *priv = host->private_data;
+	int ret;
+
+	ret = ata_host_suspend(host, PMSG_SUSPEND);
+	if (!ret) {
+		__raw_writel(0, priv->host_regs + PATA_IMX_ATA_INT_EN);
+		priv->ata_ctl =
+			__raw_readl(priv->host_regs + PATA_IMX_ATA_CONTROL);
+		clk_disable(priv->clk);
+	}
+
+	return ret;
+}
+
+static int pata_imx_resume(struct device *dev)
+{
+	struct ata_host *host = dev_get_drvdata(dev);
+	struct pata_imx_priv *priv = host->private_data;
+
+	clk_enable(priv->clk);
+
+	__raw_writel(priv->ata_ctl, priv->host_regs + PATA_IMX_ATA_CONTROL);
+
+	__raw_writel(PATA_IMX_ATA_INTR_ATA_INTRQ2,
+			priv->host_regs + PATA_IMX_ATA_INT_EN);
+
+	ata_host_resume(host);
+
+	return 0;
+}
+
+static const struct dev_pm_ops pata_imx_pm_ops = {
+	.suspend	= pata_imx_suspend,
+	.resume		= pata_imx_resume,
+};
+#endif
+
+static struct platform_driver pata_imx_driver = {
+	.probe		= pata_imx_probe,
+	.remove		= __devexit_p(pata_imx_remove),
+	.driver = {
+		.name		= DRV_NAME,
+		.owner		= THIS_MODULE,
+#ifdef CONFIG_PM
+		.pm		= &pata_imx_pm_ops,
+#endif
+	},
+};
+
+static int __init pata_imx_init(void)
+{
+	return platform_driver_register(&pata_imx_driver);
+}
+
+static void __exit pata_imx_exit(void)
+{
+	platform_driver_unregister(&pata_imx_driver);
+}
+module_init(pata_imx_init);
+module_exit(pata_imx_exit);
+
+MODULE_AUTHOR("Arnaud Patard <arnaud.patard@rtp-net.org>");
+MODULE_DESCRIPTION("low-level driver for iMX PATA");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:" DRV_NAME);
diff --git a/drivers/ata/pata_via.c b/drivers/ata/pata_via.c
index 65e4be6..8e9f504 100644
--- a/drivers/ata/pata_via.c
+++ b/drivers/ata/pata_via.c
@@ -124,6 +124,17 @@
 	{ NULL }
 };
 
+static const struct dmi_system_id no_atapi_dma_dmi_table[] = {
+	{
+		.ident = "AVERATEC 3200",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "AVERATEC"),
+			DMI_MATCH(DMI_BOARD_NAME, "3200"),
+		},
+	},
+	{ }
+};
+
 struct via_port {
 	u8 cached_device;
 };
@@ -355,6 +366,13 @@
 			mask &= ~ ATA_MASK_UDMA;
 		}
 	}
+
+	if (dev->class == ATA_DEV_ATAPI &&
+	    dmi_check_system(no_atapi_dma_dmi_table)) {
+		ata_dev_warn(dev, "controller locks up on ATAPI DMA, forcing PIO\n");
+		mask &= ATA_MASK_PIO;
+	}
+
 	return mask;
 }
 
diff --git a/drivers/ata/sata_dwc_460ex.c b/drivers/ata/sata_dwc_460ex.c
index 0a9a774..5c42374 100644
--- a/drivers/ata/sata_dwc_460ex.c
+++ b/drivers/ata/sata_dwc_460ex.c
@@ -1329,7 +1329,7 @@
 			dev_err(ap->dev, "%s: dma_alloc_coherent failed\n",
 				 __func__);
 			err = -ENOMEM;
-			goto CLEANUP;
+			goto CLEANUP_ALLOC;
 		}
 	}
 
@@ -1349,15 +1349,13 @@
 	/* Clear any error bits before libata starts issuing commands */
 	clear_serror();
 	ap->private_data = hsdevp;
+	dev_dbg(ap->dev, "%s: done\n", __func__);
+	return 0;
 
+CLEANUP_ALLOC:
+	kfree(hsdevp);
 CLEANUP:
-	if (err) {
-		sata_dwc_port_stop(ap);
-		dev_dbg(ap->dev, "%s: fail\n", __func__);
-	} else {
-		dev_dbg(ap->dev, "%s: done\n", __func__);
-	}
-
+	dev_dbg(ap->dev, "%s: fail. ap->id = %d\n", __func__, ap->print_id);
 	return err;
 }
 
diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c
index 98c1d78..9dfb40b 100644
--- a/drivers/ata/sata_sil.c
+++ b/drivers/ata/sata_sil.c
@@ -438,7 +438,7 @@
 	u8 status;
 
 	if (unlikely(bmdma2 & SIL_DMA_SATA_IRQ)) {
-		u32 serror;
+		u32 serror = 0xffffffff;
 
 		/* SIEN doesn't mask SATA IRQs on some 3112s.  Those
 		 * controllers continue to assert IRQ as long as
diff --git a/drivers/base/devres.c b/drivers/base/devres.c
index cf7a0c7..65cd748 100644
--- a/drivers/base/devres.c
+++ b/drivers/base/devres.c
@@ -397,6 +397,7 @@
 
 static int release_nodes(struct device *dev, struct list_head *first,
 			 struct list_head *end, unsigned long flags)
+	__releases(&dev->devres_lock)
 {
 	LIST_HEAD(todo);
 	int cnt;
diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c
index 33e1bed..a4760e0 100644
--- a/drivers/base/devtmpfs.c
+++ b/drivers/base/devtmpfs.c
@@ -376,7 +376,7 @@
 	return err;
 }
 
-static __initdata DECLARE_COMPLETION(setup_done);
+static DECLARE_COMPLETION(setup_done);
 
 static int handle(const char *name, mode_t mode, struct device *dev)
 {
diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c
index bbb03e6..06ed6b4 100644
--- a/drivers/base/firmware_class.c
+++ b/drivers/base/firmware_class.c
@@ -521,11 +521,6 @@
 	if (!firmware_p)
 		return -EINVAL;
 
-	if (WARN_ON(usermodehelper_is_disabled())) {
-		dev_err(device, "firmware: %s will not be loaded\n", name);
-		return -EBUSY;
-	}
-
 	*firmware_p = firmware = kzalloc(sizeof(*firmware), GFP_KERNEL);
 	if (!firmware) {
 		dev_err(device, "%s: kmalloc(struct firmware) failed\n",
@@ -539,6 +534,12 @@
 		return 0;
 	}
 
+	if (WARN_ON(usermodehelper_is_disabled())) {
+		dev_err(device, "firmware: %s will not be loaded\n", name);
+		retval = -EBUSY;
+		goto out;
+	}
+
 	if (uevent)
 		dev_dbg(device, "firmware: requesting %s\n", name);
 
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 0cad9c7..99a5272 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -33,7 +33,7 @@
 
 /**
  * arch_setup_pdev_archdata - Allow manipulation of archdata before its used
- * @dev: platform device
+ * @pdev: platform device
  *
  * This is called before platform_device_add() such that any pdev_archdata may
  * be setup before the platform_notifier is called.  So if a user needs to
diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c
index a846b2f..b97294e 100644
--- a/drivers/base/power/clock_ops.c
+++ b/drivers/base/power/clock_ops.c
@@ -19,7 +19,7 @@
 
 struct pm_clk_data {
 	struct list_head clock_list;
-	struct mutex lock;
+	spinlock_t lock;
 };
 
 enum pce_status {
@@ -42,6 +42,22 @@
 }
 
 /**
+ * pm_clk_acquire - Acquire a device clock.
+ * @dev: Device whose clock is to be acquired.
+ * @ce: PM clock entry corresponding to the clock.
+ */
+static void pm_clk_acquire(struct device *dev, struct pm_clock_entry *ce)
+{
+	ce->clk = clk_get(dev, ce->con_id);
+	if (IS_ERR(ce->clk)) {
+		ce->status = PCE_STATUS_ERROR;
+	} else {
+		ce->status = PCE_STATUS_ACQUIRED;
+		dev_dbg(dev, "Clock %s managed by runtime PM.\n", ce->con_id);
+	}
+}
+
+/**
  * pm_clk_add - Start using a device clock for power management.
  * @dev: Device whose clock is going to be used for power management.
  * @con_id: Connection ID of the clock.
@@ -73,26 +89,23 @@
 		}
 	}
 
-	mutex_lock(&pcd->lock);
+	pm_clk_acquire(dev, ce);
+
+	spin_lock_irq(&pcd->lock);
 	list_add_tail(&ce->node, &pcd->clock_list);
-	mutex_unlock(&pcd->lock);
+	spin_unlock_irq(&pcd->lock);
 	return 0;
 }
 
 /**
  * __pm_clk_remove - Destroy PM clock entry.
  * @ce: PM clock entry to destroy.
- *
- * This routine must be called under the mutex protecting the PM list of clocks
- * corresponding the the @ce's device.
  */
 static void __pm_clk_remove(struct pm_clock_entry *ce)
 {
 	if (!ce)
 		return;
 
-	list_del(&ce->node);
-
 	if (ce->status < PCE_STATUS_ERROR) {
 		if (ce->status == PCE_STATUS_ENABLED)
 			clk_disable(ce->clk);
@@ -123,21 +136,25 @@
 	if (!pcd)
 		return;
 
-	mutex_lock(&pcd->lock);
+	spin_lock_irq(&pcd->lock);
 
 	list_for_each_entry(ce, &pcd->clock_list, node) {
-		if (!con_id && !ce->con_id) {
-			__pm_clk_remove(ce);
-			break;
-		} else if (!con_id || !ce->con_id) {
+		if (!con_id && !ce->con_id)
+			goto remove;
+		else if (!con_id || !ce->con_id)
 			continue;
-		} else if (!strcmp(con_id, ce->con_id)) {
-			__pm_clk_remove(ce);
-			break;
-		}
+		else if (!strcmp(con_id, ce->con_id))
+			goto remove;
 	}
 
-	mutex_unlock(&pcd->lock);
+	spin_unlock_irq(&pcd->lock);
+	return;
+
+ remove:
+	list_del(&ce->node);
+	spin_unlock_irq(&pcd->lock);
+
+	__pm_clk_remove(ce);
 }
 
 /**
@@ -158,7 +175,7 @@
 	}
 
 	INIT_LIST_HEAD(&pcd->clock_list);
-	mutex_init(&pcd->lock);
+	spin_lock_init(&pcd->lock);
 	dev->power.subsys_data = pcd;
 	return 0;
 }
@@ -175,20 +192,27 @@
 {
 	struct pm_clk_data *pcd = __to_pcd(dev);
 	struct pm_clock_entry *ce, *c;
+	struct list_head list;
 
 	if (!pcd)
 		return;
 
 	dev->power.subsys_data = NULL;
+	INIT_LIST_HEAD(&list);
 
-	mutex_lock(&pcd->lock);
+	spin_lock_irq(&pcd->lock);
 
 	list_for_each_entry_safe_reverse(ce, c, &pcd->clock_list, node)
-		__pm_clk_remove(ce);
+		list_move(&ce->node, &list);
 
-	mutex_unlock(&pcd->lock);
+	spin_unlock_irq(&pcd->lock);
 
 	kfree(pcd);
+
+	list_for_each_entry_safe_reverse(ce, c, &list, node) {
+		list_del(&ce->node);
+		__pm_clk_remove(ce);
+	}
 }
 
 #endif /* CONFIG_PM */
@@ -196,23 +220,6 @@
 #ifdef CONFIG_PM_RUNTIME
 
 /**
- * pm_clk_acquire - Acquire a device clock.
- * @dev: Device whose clock is to be acquired.
- * @con_id: Connection ID of the clock.
- */
-static void pm_clk_acquire(struct device *dev,
-				    struct pm_clock_entry *ce)
-{
-	ce->clk = clk_get(dev, ce->con_id);
-	if (IS_ERR(ce->clk)) {
-		ce->status = PCE_STATUS_ERROR;
-	} else {
-		ce->status = PCE_STATUS_ACQUIRED;
-		dev_dbg(dev, "Clock %s managed by runtime PM.\n", ce->con_id);
-	}
-}
-
-/**
  * pm_clk_suspend - Disable clocks in a device's PM clock list.
  * @dev: Device to disable the clocks for.
  */
@@ -220,25 +227,23 @@
 {
 	struct pm_clk_data *pcd = __to_pcd(dev);
 	struct pm_clock_entry *ce;
+	unsigned long flags;
 
 	dev_dbg(dev, "%s()\n", __func__);
 
 	if (!pcd)
 		return 0;
 
-	mutex_lock(&pcd->lock);
+	spin_lock_irqsave(&pcd->lock, flags);
 
 	list_for_each_entry_reverse(ce, &pcd->clock_list, node) {
-		if (ce->status == PCE_STATUS_NONE)
-			pm_clk_acquire(dev, ce);
-
 		if (ce->status < PCE_STATUS_ERROR) {
 			clk_disable(ce->clk);
 			ce->status = PCE_STATUS_ACQUIRED;
 		}
 	}
 
-	mutex_unlock(&pcd->lock);
+	spin_unlock_irqrestore(&pcd->lock, flags);
 
 	return 0;
 }
@@ -251,25 +256,23 @@
 {
 	struct pm_clk_data *pcd = __to_pcd(dev);
 	struct pm_clock_entry *ce;
+	unsigned long flags;
 
 	dev_dbg(dev, "%s()\n", __func__);
 
 	if (!pcd)
 		return 0;
 
-	mutex_lock(&pcd->lock);
+	spin_lock_irqsave(&pcd->lock, flags);
 
 	list_for_each_entry(ce, &pcd->clock_list, node) {
-		if (ce->status == PCE_STATUS_NONE)
-			pm_clk_acquire(dev, ce);
-
 		if (ce->status < PCE_STATUS_ERROR) {
 			clk_enable(ce->clk);
 			ce->status = PCE_STATUS_ENABLED;
 		}
 	}
 
-	mutex_unlock(&pcd->lock);
+	spin_unlock_irqrestore(&pcd->lock, flags);
 
 	return 0;
 }
@@ -344,6 +347,7 @@
 {
 	struct pm_clk_data *pcd = __to_pcd(dev);
 	struct pm_clock_entry *ce;
+	unsigned long flags;
 
 	dev_dbg(dev, "%s()\n", __func__);
 
@@ -351,12 +355,12 @@
 	if (!pcd || !dev->driver)
 		return 0;
 
-	mutex_lock(&pcd->lock);
+	spin_lock_irqsave(&pcd->lock, flags);
 
 	list_for_each_entry_reverse(ce, &pcd->clock_list, node)
 		clk_disable(ce->clk);
 
-	mutex_unlock(&pcd->lock);
+	spin_unlock_irqrestore(&pcd->lock, flags);
 
 	return 0;
 }
@@ -369,6 +373,7 @@
 {
 	struct pm_clk_data *pcd = __to_pcd(dev);
 	struct pm_clock_entry *ce;
+	unsigned long flags;
 
 	dev_dbg(dev, "%s()\n", __func__);
 
@@ -376,12 +381,12 @@
 	if (!pcd || !dev->driver)
 		return 0;
 
-	mutex_lock(&pcd->lock);
+	spin_lock_irqsave(&pcd->lock, flags);
 
 	list_for_each_entry(ce, &pcd->clock_list, node)
 		clk_enable(ce->clk);
 
-	mutex_unlock(&pcd->lock);
+	spin_unlock_irqrestore(&pcd->lock, flags);
 
 	return 0;
 }
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index e18566a..1c37457 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -460,6 +460,21 @@
 	return 0;
 }
 
+/**
+ * pm_genpd_poweroff_unused - Power off all PM domains with no devices in use.
+ */
+void pm_genpd_poweroff_unused(void)
+{
+	struct generic_pm_domain *genpd;
+
+	mutex_lock(&gpd_list_lock);
+
+	list_for_each_entry(genpd, &gpd_list, gpd_list_node)
+		genpd_queue_power_off_work(genpd);
+
+	mutex_unlock(&gpd_list_lock);
+}
+
 #else
 
 static inline void genpd_power_off_work_fn(struct work_struct *work) {}
@@ -1255,18 +1270,3 @@
 	list_add(&genpd->gpd_list_node, &gpd_list);
 	mutex_unlock(&gpd_list_lock);
 }
-
-/**
- * pm_genpd_poweroff_unused - Power off all PM domains with no devices in use.
- */
-void pm_genpd_poweroff_unused(void)
-{
-	struct generic_pm_domain *genpd;
-
-	mutex_lock(&gpd_list_lock);
-
-	list_for_each_entry(genpd, &gpd_list, gpd_list_node)
-		genpd_queue_power_off_work(genpd);
-
-	mutex_unlock(&gpd_list_lock);
-}
diff --git a/drivers/base/regmap/regmap-i2c.c b/drivers/base/regmap/regmap-i2c.c
index c2231ff..c4f7a45 100644
--- a/drivers/base/regmap/regmap-i2c.c
+++ b/drivers/base/regmap/regmap-i2c.c
@@ -113,3 +113,4 @@
 }
 EXPORT_SYMBOL_GPL(regmap_init_i2c);
 
+MODULE_LICENSE("GPL");
diff --git a/drivers/base/regmap/regmap-spi.c b/drivers/base/regmap/regmap-spi.c
index 4deba06..f839694 100644
--- a/drivers/base/regmap/regmap-spi.c
+++ b/drivers/base/regmap/regmap-spi.c
@@ -13,6 +13,7 @@
 #include <linux/regmap.h>
 #include <linux/spi/spi.h>
 #include <linux/init.h>
+#include <linux/module.h>
 
 static int regmap_spi_write(struct device *dev, const void *data, size_t count)
 {
@@ -70,3 +71,5 @@
 	return regmap_init(&spi->dev, &regmap_spi, config);
 }
 EXPORT_SYMBOL_GPL(regmap_init_spi);
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index cf3565c..20663f8 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -168,13 +168,11 @@
 	map->work_buf = kmalloc(map->format.buf_size, GFP_KERNEL);
 	if (map->work_buf == NULL) {
 		ret = -ENOMEM;
-		goto err_bus;
+		goto err_map;
 	}
 
 	return map;
 
-err_bus:
-	module_put(map->bus->owner);
 err_map:
 	kfree(map);
 err:
@@ -188,7 +186,6 @@
 void regmap_exit(struct regmap *map)
 {
 	kfree(map->work_buf);
-	module_put(map->bus->owner);
 	kfree(map);
 }
 EXPORT_SYMBOL_GPL(regmap_exit);
@@ -317,7 +314,7 @@
 		u8[0] |= map->bus->read_flag_mask;
 
 	ret = map->bus->read(map->dev, map->work_buf, map->format.reg_bytes,
-			     val, map->format.val_bytes);
+			     val, val_len);
 	if (ret != 0)
 		return ret;
 
diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c
index 873e2e4..73b7b1a 100644
--- a/drivers/bcma/main.c
+++ b/drivers/bcma/main.c
@@ -15,6 +15,7 @@
 static int bcma_bus_match(struct device *dev, struct device_driver *drv);
 static int bcma_device_probe(struct device *dev);
 static int bcma_device_remove(struct device *dev);
+static int bcma_device_uevent(struct device *dev, struct kobj_uevent_env *env);
 
 static ssize_t manuf_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
@@ -49,6 +50,7 @@
 	.match		= bcma_bus_match,
 	.probe		= bcma_device_probe,
 	.remove		= bcma_device_remove,
+	.uevent		= bcma_device_uevent,
 	.dev_attrs	= bcma_device_attrs,
 };
 
@@ -227,6 +229,16 @@
 	return 0;
 }
 
+static int bcma_device_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+	struct bcma_device *core = container_of(dev, struct bcma_device, dev);
+
+	return add_uevent_var(env,
+			      "MODALIAS=bcma:m%04Xid%04Xrev%02Xcl%02X",
+			      core->id.manuf, core->id.id,
+			      core->id.rev, core->id.class);
+}
+
 static int __init bcma_modinit(void)
 {
 	int err;
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index 717d6e4..6f07ec1 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -256,6 +256,21 @@
 
 	  Most users will answer N here.
 
+config BLK_DEV_LOOP_MIN_COUNT
+	int "Number of loop devices to pre-create at init time"
+	depends on BLK_DEV_LOOP
+	default 8
+	help
+	  Static number of loop devices to be unconditionally pre-created
+	  at init time.
+
+	  This default value can be overwritten on the kernel command
+	  line or with module-parameter loop.max_loop.
+
+	  The historic default is 8. If a late 2011 version of losetup(8)
+	  is used, it can be set to 0, since needed loop devices can be
+	  dynamically allocated with the /dev/loop-control interface.
+
 config BLK_DEV_CRYPTOLOOP
 	tristate "Cryptoloop Support"
 	select CRYPTO
@@ -471,7 +486,7 @@
 	  in another domain which drives the actual block device.
 
 config XEN_BLKDEV_BACKEND
-	tristate "Block-device backend driver"
+	tristate "Xen block-device backend driver"
 	depends on XEN_BACKEND
 	help
 	  The block-device backend driver allows the kernel to export its
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 515bcd9..0feab26 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -1829,10 +1829,10 @@
 
 	/* silently ignore cpu mask on UP kernel */
 	if (nr_cpu_ids > 1 && sc.cpu_mask[0] != 0) {
-		err = __bitmap_parse(sc.cpu_mask, 32, 0,
+		err = bitmap_parse(sc.cpu_mask, 32,
 				cpumask_bits(new_cpu_mask), nr_cpu_ids);
 		if (err) {
-			dev_warn(DEV, "__bitmap_parse() failed with %d\n", err);
+			dev_warn(DEV, "bitmap_parse() failed with %d\n", err);
 			retcode = ERR_CPU_MASK_PARSE;
 			goto fail;
 		}
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 98de8f4..9955a53 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -4250,7 +4250,7 @@
 	use_virtual_dma = can_use_virtual_dma & 1;
 	fdc_state[0].address = FDC1;
 	if (fdc_state[0].address == -1) {
-		del_timer(&fd_timeout);
+		del_timer_sync(&fd_timeout);
 		err = -ENODEV;
 		goto out_unreg_region;
 	}
@@ -4261,7 +4261,7 @@
 	fdc = 0;		/* reset fdc in case of unexpected interrupt */
 	err = floppy_grab_irq_and_dma();
 	if (err) {
-		del_timer(&fd_timeout);
+		del_timer_sync(&fd_timeout);
 		err = -EBUSY;
 		goto out_unreg_region;
 	}
@@ -4318,7 +4318,7 @@
 		user_reset_fdc(-1, FD_RESET_ALWAYS, false);
 	}
 	fdc = 0;
-	del_timer(&fd_timeout);
+	del_timer_sync(&fd_timeout);
 	current_drive = 0;
 	initialized = true;
 	if (have_no_fdc) {
@@ -4368,7 +4368,7 @@
 	unregister_blkdev(FLOPPY_MAJOR, "fd");
 out_put_disk:
 	while (dr--) {
-		del_timer(&motor_off_timer[dr]);
+		del_timer_sync(&motor_off_timer[dr]);
 		if (disks[dr]->queue)
 			blk_cleanup_queue(disks[dr]->queue);
 		put_disk(disks[dr]);
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 76c8da7..4720c7a 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -75,11 +75,11 @@
 #include <linux/kthread.h>
 #include <linux/splice.h>
 #include <linux/sysfs.h>
-
+#include <linux/miscdevice.h>
 #include <asm/uaccess.h>
 
-static LIST_HEAD(loop_devices);
-static DEFINE_MUTEX(loop_devices_mutex);
+static DEFINE_IDR(loop_index_idr);
+static DEFINE_MUTEX(loop_index_mutex);
 
 static int max_part;
 static int part_shift;
@@ -722,17 +722,10 @@
 static ssize_t loop_attr_show(struct device *dev, char *page,
 			      ssize_t (*callback)(struct loop_device *, char *))
 {
-	struct loop_device *l, *lo = NULL;
+	struct gendisk *disk = dev_to_disk(dev);
+	struct loop_device *lo = disk->private_data;
 
-	mutex_lock(&loop_devices_mutex);
-	list_for_each_entry(l, &loop_devices, lo_list)
-		if (disk_to_dev(l->lo_disk) == dev) {
-			lo = l;
-			break;
-		}
-	mutex_unlock(&loop_devices_mutex);
-
-	return lo ? callback(lo, page) : -EIO;
+	return callback(lo, page);
 }
 
 #define LOOP_ATTR_RO(_name)						\
@@ -750,10 +743,10 @@
 	ssize_t ret;
 	char *p = NULL;
 
-	mutex_lock(&lo->lo_ctl_mutex);
+	spin_lock_irq(&lo->lo_lock);
 	if (lo->lo_backing_file)
 		p = d_path(&lo->lo_backing_file->f_path, buf, PAGE_SIZE - 1);
-	mutex_unlock(&lo->lo_ctl_mutex);
+	spin_unlock_irq(&lo->lo_lock);
 
 	if (IS_ERR_OR_NULL(p))
 		ret = PTR_ERR(p);
@@ -1007,7 +1000,9 @@
 
 	kthread_stop(lo->lo_thread);
 
+	spin_lock_irq(&lo->lo_lock);
 	lo->lo_backing_file = NULL;
+	spin_unlock_irq(&lo->lo_lock);
 
 	loop_release_xfer(lo);
 	lo->transfer = NULL;
@@ -1485,13 +1480,22 @@
 
 static int lo_open(struct block_device *bdev, fmode_t mode)
 {
-	struct loop_device *lo = bdev->bd_disk->private_data;
+	struct loop_device *lo;
+	int err = 0;
+
+	mutex_lock(&loop_index_mutex);
+	lo = bdev->bd_disk->private_data;
+	if (!lo) {
+		err = -ENXIO;
+		goto out;
+	}
 
 	mutex_lock(&lo->lo_ctl_mutex);
 	lo->lo_refcnt++;
 	mutex_unlock(&lo->lo_ctl_mutex);
-
-	return 0;
+out:
+	mutex_unlock(&loop_index_mutex);
+	return err;
 }
 
 static int lo_release(struct gendisk *disk, fmode_t mode)
@@ -1557,40 +1561,71 @@
 	return 0;
 }
 
+static int unregister_transfer_cb(int id, void *ptr, void *data)
+{
+	struct loop_device *lo = ptr;
+	struct loop_func_table *xfer = data;
+
+	mutex_lock(&lo->lo_ctl_mutex);
+	if (lo->lo_encryption == xfer)
+		loop_release_xfer(lo);
+	mutex_unlock(&lo->lo_ctl_mutex);
+	return 0;
+}
+
 int loop_unregister_transfer(int number)
 {
 	unsigned int n = number;
-	struct loop_device *lo;
 	struct loop_func_table *xfer;
 
 	if (n == 0 || n >= MAX_LO_CRYPT || (xfer = xfer_funcs[n]) == NULL)
 		return -EINVAL;
 
 	xfer_funcs[n] = NULL;
-
-	list_for_each_entry(lo, &loop_devices, lo_list) {
-		mutex_lock(&lo->lo_ctl_mutex);
-
-		if (lo->lo_encryption == xfer)
-			loop_release_xfer(lo);
-
-		mutex_unlock(&lo->lo_ctl_mutex);
-	}
-
+	idr_for_each(&loop_index_idr, &unregister_transfer_cb, xfer);
 	return 0;
 }
 
 EXPORT_SYMBOL(loop_register_transfer);
 EXPORT_SYMBOL(loop_unregister_transfer);
 
-static struct loop_device *loop_alloc(int i)
+static int loop_add(struct loop_device **l, int i)
 {
 	struct loop_device *lo;
 	struct gendisk *disk;
+	int err;
 
 	lo = kzalloc(sizeof(*lo), GFP_KERNEL);
-	if (!lo)
+	if (!lo) {
+		err = -ENOMEM;
 		goto out;
+	}
+
+	err = idr_pre_get(&loop_index_idr, GFP_KERNEL);
+	if (err < 0)
+		goto out_free_dev;
+
+	if (i >= 0) {
+		int m;
+
+		/* create specific i in the index */
+		err = idr_get_new_above(&loop_index_idr, lo, i, &m);
+		if (err >= 0 && i != m) {
+			idr_remove(&loop_index_idr, m);
+			err = -EEXIST;
+		}
+	} else if (i == -1) {
+		int m;
+
+		/* get next free nr */
+		err = idr_get_new(&loop_index_idr, lo, &m);
+		if (err >= 0)
+			i = m;
+	} else {
+		err = -EINVAL;
+	}
+	if (err < 0)
+		goto out_free_dev;
 
 	lo->lo_queue = blk_alloc_queue(GFP_KERNEL);
 	if (!lo->lo_queue)
@@ -1611,81 +1646,158 @@
 	disk->private_data	= lo;
 	disk->queue		= lo->lo_queue;
 	sprintf(disk->disk_name, "loop%d", i);
-	return lo;
+	add_disk(disk);
+	*l = lo;
+	return lo->lo_number;
 
 out_free_queue:
 	blk_cleanup_queue(lo->lo_queue);
 out_free_dev:
 	kfree(lo);
 out:
-	return NULL;
+	return err;
 }
 
-static void loop_free(struct loop_device *lo)
+static void loop_remove(struct loop_device *lo)
 {
+	del_gendisk(lo->lo_disk);
 	blk_cleanup_queue(lo->lo_queue);
 	put_disk(lo->lo_disk);
-	list_del(&lo->lo_list);
 	kfree(lo);
 }
 
-static struct loop_device *loop_init_one(int i)
+static int find_free_cb(int id, void *ptr, void *data)
 {
-	struct loop_device *lo;
+	struct loop_device *lo = ptr;
+	struct loop_device **l = data;
 
-	list_for_each_entry(lo, &loop_devices, lo_list) {
-		if (lo->lo_number == i)
-			return lo;
+	if (lo->lo_state == Lo_unbound) {<