Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux into sh-fixes-for-linus

Documentation/00-INDEX

@@ -272,6 +272,8 @@ printk-formats.txt
 	- 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

Documentation/PCI/MSI-HOWTO.txt

@@ -45,7 +45,7 @@ arrived in memory (this becomes more likely with devices behind PCI-PCI
 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 @@ device.
 
 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 @@ the device are in the range dev->irq to dev->irq + count - 1.
 
 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 number and frees the previously allocated message signaled
 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 @@ struct msix_entry {
 };
 
 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 @@ int pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec)
 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 @@ below.
 
 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 @@ static int foo_driver_enable_msix(struct foo_adapter *adapter, int nvec)
 
 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 @@ mask or unmask an interrupt, it should call disable_irq() / enable_irq().
 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 @@ the MSI-X facilities in preference to the MSI facilities.  As mentioned
 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 @@ disabled to enabled and back again.
 
 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 @@ The PCI stack provides three ways to disable MSIs:
 
 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 @@ Some bridges allow you to enable MSIs by changing some bits in their
 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 @@ where $bridge is the PCI address of the bridge you've enabled (eg
 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 @@ special handling.
 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 @@ for your machine.  You should also check your .config to be sure you
 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.
 

Documentation/SubmittingDrivers

@@ -130,7 +130,7 @@ Linux kernel master tree:
 	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

Documentation/SubmittingPatches

@@ -303,7 +303,7 @@ patches that are being emailed around.
 
 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

Documentation/block/cfq-iosched.txt

@@ -43,3 +43,74 @@ If one sets slice_idle=0 and if storage supports NCQ, CFQ internally switches
 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.

Documentation/email-clients.txt

@@ -199,18 +199,16 @@ to coerce it into behaving.
 
 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/

Documentation/filesystems/befs.txt

@@ -27,7 +27,7 @@ His original code can still be found at:
 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?
 ==================

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

Documentation/kernel-parameters.txt

@@ -40,6 +40,7 @@ parameter is applicable:
 	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 @@ parameter is applicable:
 	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 @@ parameter is applicable:
 			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 @@ parameter is applicable:
 	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 @@ parameter is applicable:
 	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 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	atkbd.softrepeat= [HW]
 			Use software keyboard repeat
 
-	autotest	[IA64]
+	autotest	[IA-64]
 
 	baycom_epp=	[HW,AX25]
 			Format: <io>,<mode>
@@ -681,8 +683,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 		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 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			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 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			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 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	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 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			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 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			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 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 		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 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	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 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			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 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	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 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			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 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	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 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	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.
 
@@ -2077,7 +2082,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			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
 
@@ -2635,6 +2640,16 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 					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 +2695,27 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	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;

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 @@ atm.txt
 	- 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 @@ cxacru.txt
 	- 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 @@ ipddp.txt
 	- 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

Documentation/networking/bonding.txt

@@ -238,6 +238,18 @@ ad_select
 
 	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 @@ miimon
 	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

Documentation/networking/ip-sysctl.txt

@@ -992,7 +992,7 @@ bindv6only - BOOLEAN
 		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:
 

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)

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/* .

Documentation/virtual/00-INDEX

@@ -8,3 +8,6 @@ lguest/
 	- 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

Documentation/virtual/lguest/lguest.c

@@ -1996,6 +1996,9 @@ int main(int argc, char *argv[])
 	/* 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;
 

MAINTAINERS

@@ -1883,7 +1883,7 @@ S:	Maintained
 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 +1932,7 @@ S:	Maintained
 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
@@ -3905,9 +3905,9 @@ F:	arch/powerpc/platforms/powermac/
 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/
@@ -4604,7 +4604,7 @@ F:	arch/arm/mach-omap2/clockdomain2xxx_3xxx.c
 F:	arch/arm/mach-omap2/clockdomain44xx.c
 
 OMAP AUDIO SUPPORT
-M:	Jarkko Nikula <jhnikula@gmail.com>
+M:	Jarkko Nikula <jarkko.nikula@bitmer.com>
 L:	alsa-devel@alsa-project.org (subscribers-only)
 L:	linux-omap@vger.kernel.org
 S:	Maintained
@@ -4971,7 +4971,7 @@ M:	Paul Mackerras <paulus@samba.org>
 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
@@ -7087,7 +7087,7 @@ S:	Supported
 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/
@@ -7357,7 +7357,7 @@ THE REST
 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:	*/

Makefile

@@ -1,8 +1,8 @@
 VERSION = 3
 PATCHLEVEL = 1
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
-NAME = Sneaky Weasel
+EXTRAVERSION = -rc3
+NAME = "Divemaster Edition"
 
 # *DOCUMENTATION*
 # To see a list of typical targets execute "make help"

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 */

arch/alpha/include/asm/thread_info.h

@@ -74,9 +74,9 @@ register struct thread_info *__current_thread_info __asm__("$8");
 #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 @@ register struct thread_info *__current_thread_info __asm__("$8");
 #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)
 

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 @@ SYSCALL_DEFINE5(osf_getsysinfo, unsigned long, op, void __user *, buffer,
  	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 @@ SYSCALL_DEFINE5(osf_setsysinfo, unsigned long, op, void __user *, buffer,
  			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;

arch/arm/Kconfig

@@ -195,8 +195,7 @@ config VECTORS_BASE
 	  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

arch/arm/kernel/iwmmxt.S

@@ -195,10 +195,10 @@ ENTRY(iwmmxt_task_disable)
 
 	@ 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 @@ ENTRY(iwmmxt_task_switch)
 	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)

arch/arm/kernel/module.c

@@ -323,7 +323,11 @@ int module_finalize(const Elf32_Ehdr *hdr, const Elf_Shdr *sechdrs,
 #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;
 }
 

arch/arm/mach-imx/clock-imx25.c

@@ -331,6 +331,9 @@ int __init mx25_clocks_init(void)
 	__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;

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 @@ static struct pca953x_platform_data visstrim_m10_pca9555_pdata = {
 	.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 @@ static struct i2c_board_info visstrim_m10_i2c_devices[] = {
 	},
 	{
 		I2C_BOARD_INFO("tlv320aic32x4", 0x18),
+		.platform_data = &visstrim_m10_aic32x4_pdata,
 	}
 };
 

arch/arm/mach-imx/mach-mx31ads.c

@@ -468,7 +468,7 @@ static struct i2c_board_info __initdata mx31ads_i2c1_devices[] = {
 #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 @@ static unsigned int ssi_pins[] = {
 	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");

arch/arm/mach-imx/mach-mx31lilly.c

@@ -192,7 +192,7 @@ static struct mxc_usbh_platform_data usbh2_pdata __initdata = {
 	.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);
 

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 @@ static unsigned long gplugd_pin_config[] __initdata = {
 	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 @@ static void __init select_disp_freq(void)
 				"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 @@ static void __init select_disp_freq(void)
 				"frequency\n");
 	} else {
 		gpio_direction_output(85, 0);
-		gpio_free(104);
+		gpio_free(85);
 	}
 }
 

arch/arm/mach-mmp/include/mach/mfp-gplugd.h

@@ -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 */

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 */

arch/arm/mach-mmp/time.c

@@ -51,12 +51,12 @@ static inline uint32_t timer_read(void)
 {
 	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 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id)
 {
 	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 struct clocksource cksrc = {
 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 = {

arch/arm/mach-mx5/board-cpuimx51.c

@@ -81,7 +81,7 @@ static struct plat_serial8250_port serial_platform_data[] = {
 		.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,

arch/arm/mach-mx5/board-mx51_babbage.c

@@ -369,7 +369,7 @@ static void __init mx51_babbage_init(void)
 					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();

arch/arm/mach-mx5/board-mx51_efikamx.c

@@ -108,9 +108,9 @@ static void __init mx51_efikamx_board_id(void)
 	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:

arch/arm/mach-mx5/board-mx51_efikasb.c

@@ -156,23 +156,24 @@ static struct gpio_keys_button mx51_efikasb_keys[] = {
 	{
 		.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 @@ static void __init mx51_efikasb_board_id(void)
 	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:

arch/arm/mach-mx5/clock-mx51-mx53.c

@@ -271,7 +271,11 @@ static int _clk_pll_enable(struct clk *clk)
 	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 */

arch/arm/mach-mx5/mx51_efika.c

@@ -186,7 +186,7 @@ static int initialize_usbh1_port(struct platform_device *pdev)
 
 	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 = {

arch/arm/mach-omap2/Kconfig

@@ -7,7 +7,6 @@ config ARCH_OMAP2PLUS_TYPICAL
 	default y
 	select AEABI
 	select REGULATOR
-	select PM
 	select PM_RUNTIME
 	select VFP
 	select NEON if ARCH_OMAP3 || ARCH_OMAP4

arch/arm/mach-omap2/board-am3517crane.c

@@ -45,8 +45,6 @@ static struct omap_board_config_kernel am3517_crane_config[] __initdata = {
 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)

arch/arm/mach-omap2/board-omap3beagle.c

@@ -491,23 +491,22 @@ static void __init beagle_opp_init(void)
 
 	/* 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 @@ static void __init beagle_opp_init(void)
 			 * 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;

arch/arm/mach-omap2/cminst44xx.h

@@ -18,13 +18,36 @@ extern void omap4_cminst_clkdm_force_sleep(u8 part, s16 inst, u16 cdoffs);
 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

arch/arm/mach-omap2/mux.c

@@ -821,11 +821,10 @@ static void __init omap_mux_set_cmdline_signals(void)
 	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 @@ static int __init omap_mux_copy_names(struct omap_mux *src,
 
 	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

arch/arm/mach-omap2/smartreflex.c

@@ -621,7 +621,7 @@ void sr_disable(struct voltagedomain *voltdm)
 			sr_v2_disable(sr);
 	}
 
-	pm_runtime_put_sync(&sr->pdev->dev);
+	pm_runtime_put_sync_suspend(&sr->pdev->dev);
 }
 
 /**
@@ -860,6 +860,7 @@ static int __init omap_sr_probe(struct platform_device *pdev)
 	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;

arch/arm/mach-omap2/timer.c

@@ -293,7 +293,8 @@ static void __init omap2_gp_clocksource_init(int gptimer_id,
 	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))

arch/arm/mach-omap2/twl-common.c

@@ -48,14 +48,7 @@ void __init omap_pmic_init(int bus, u32 clkrate,
 	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 @@ static struct regulator_init_data omap3_vpll2_idata = {
 	.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 @@ void __init omap4_pmic_get_config(struct twl4030_platform_data *pmic_data,
 	    !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 */

arch/arm/mach-s3c64xx/mach-crag6410.c

@@ -65,7 +65,7 @@
 #include <plat/iic.h>
 #include <plat/pm.h>
 
-#include <sound/wm8915.h>
+#include <sound/wm8996.h>
 #include <sound/wm8962.h>
 #include <sound/wm9081.h>
 
@@ -614,7 +614,7 @@ static struct wm831x_pdata glenfarclas_pmic_pdata __initdata = {
 	.disable_touch = true,
 };
 
-static struct wm8915_retune_mobile_config wm8915_retune[] = {
+static struct wm8996_retune_mobile_config wm8996_retune[] = {
 	{
 		.name = "Sub LPF",
 		.rate = 48000,
@@ -635,12 +635,12 @@ static struct wm8915_retune_mobile_config wm8915_retune[] = {
 	},
 };
 
-static struct wm8915_pdata wm8915_pdata __initdata = {
+static struct wm8996_pdata wm8996_pdata __initdata = {
 	.ldo_ena = S3C64XX_GPN(7),
 	.gpio_base = CODEC_GPIO_BASE,
 	.micdet_def = 1,
-	.inl_mode = WM8915_DIFFERRENTIAL_1,
-	.inr_mode = WM8915_DIFFERRENTIAL_1,
+	.inl_mode = WM8996_DIFFERRENTIAL_1,
+	.inr_mode = WM8996_DIFFERRENTIAL_1,
 
 	.irq_flags = IRQF_TRIGGER_RISING,
 
@@ -652,8 +652,8 @@ static struct wm8915_pdata wm8915_pdata __initdata = {
 		0x020e, /* GPIO5 == CLKOUT */
 	},
 
-	.retune_mobile_cfgs = wm8915_retune,
-	.num_retune_mobile_cfgs = ARRAY_SIZE(wm8915_retune),
+	.retune_mobile_cfgs = wm8996_retune,
+	.num_retune_mobile_cfgs = ARRAY_SIZE(wm8996_retune),
 };
 
 static struct wm8962_pdata wm8962_pdata __initdata = {
@@ -679,8 +679,8 @@ static struct i2c_board_info i2c_devs1[] __initdata = {
 	  .platform_data = &glenfarclas_pmic_pdata },
 
 	{ I2C_BOARD_INFO("wm1250-ev1", 0x27) },
-	{ I2C_BOARD_INFO("wm8915", 0x1a),
-	  .platform_data = &wm8915_pdata,
+	{ I2C_BOARD_INFO("wm8996", 0x1a),
+	  .platform_data = &wm8996_pdata,
 	  .irq = GLENFARCLAS_PMIC_IRQ_BASE + WM831X_IRQ_GPIO_2,
 	},
 	{ I2C_BOARD_INFO("wm9081", 0x6c),

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);
 

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 @@ static const char *usermode_action[] = {
 	"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 @@ static ssize_t alignment_proc_write(struct file *file, const char __user *buffer
 		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 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	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 @@ static int __init alignment_init(void)
 		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,

arch/arm/mm/init.c

@@ -441,7 +441,7 @@ static inline int free_area(unsigned long pfn, unsigned long end, char *s)
 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;
 }
 

arch/arm/mm/proc-arm946.S

@@ -410,6 +410,7 @@ __arm946_proc_info:
 	.long	0x41009460
 	.long	0xff00fff0
 	.long	0
+	.long	0
 	b	__arm946_setup
 	.long	cpu_arch_name
 	.long	cpu_elf_name
@@ -418,6 +419,6 @@ __arm946_proc_info:
 	.long	arm946_processor_functions
 	.long	0
 	.long	0
-	.long	arm940_cache_fns
+	.long	arm946_cache_fns
 	.size	__arm946_proc_info, . - __arm946_proc_info
 

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

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))

arch/arm/plat-omap/Kconfig

@@ -13,6 +13,7 @@ config ARCH_OMAP1
 	bool "TI OMAP1"
 	select CLKDEV_LOOKUP
 	select CLKSRC_MMIO
+	select GENERIC_IRQ_CHIP
 	help
 	  "Systems based on omap7xx, omap15xx or omap16xx"
 

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)

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

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

arch/arm/plat-omap/iovmm.c

@@ -423,9 +423,6 @@ static void sgtable_fill_kmalloc(struct sg_table *sgt, u32 pa, u32 da,
 {
 	unsigned int i;
 	struct scatterlist *sg;
-	void *va;
-
-	va = phys_to_virt(pa);
 
 	for_each_sg(sgt->sgl, sg, sgt->nents, i) {
 		unsigned bytes;

arch/arm/tools/mach-types

@@ -910,7 +910,7 @@ omapl138_case_a3	MACH_OMAPL138_CASE_A3	OMAPL138_CASE_A3	3280
 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

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 */

arch/ia64/Kconfig

@@ -162,7 +162,6 @@ config IA64_GENERIC
 	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

arch/ia64/configs/generic_defconfig

@@ -234,3 +234,4 @@ CONFIG_CRYPTO_MD5=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRC_T10DIF=y
 CONFIG_MISC_DEVICES=y
+CONFIG_DMAR=y

arch/m68k/include/asm/page_mm.h

@@ -162,7 +162,7 @@ static inline __attribute_const__ int __virt_to_node_shift(void)
 	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;		\

arch/powerpc/include/asm/jump_label.h

@@ -22,7 +22,6 @@ static __always_inline bool arch_static_branch(struct jump_label_key *key)
 	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 @@ struct jump_entry {
 	jump_label_t code;
 	jump_label_t target;
 	jump_label_t key;
-	jump_label_t pad;
 };
 
 #endif /* _ASM_POWERPC_JUMP_LABEL_H */

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.

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__

arch/powerpc/kernel/cputable.c

@@ -2051,7 +2051,8 @@ static struct cpu_spec __initdata cpu_specs[] = {
 
 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 @@ static void __init setup_cpu_spec(unsigned long offset, struct cpu_spec *s)
 		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 @@ struct cpu_spec * __init identify_cpu(unsigned long offset, unsigned int pvr)
 	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();

arch/powerpc/kernel/iomap.c

@@ -117,6 +117,7 @@ void ioport_unmap(void __iomem *addr)
 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 @@ void pci_iounmap(struct pci_dev *dev, void __iomem *addr)
 
 EXPORT_SYMBOL(pci_iomap);
 EXPORT_SYMBOL(pci_iounmap);
+#endif /* CONFIG_PCI */

arch/powerpc/kernel/machine_kexec.c

@@ -136,12 +136,16 @@ void __init reserve_crashkernel(void)
 	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);

arch/powerpc/kernel/perf_callchain.c

@@ -154,8 +154,12 @@ static int read_user_stack_64(unsigned long __user *ptr, unsigned long *ret)
 	    ((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 @@ static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret)
 	    ((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 inline int current_is_64bit(void)
  */
 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,

arch/powerpc/kernel/prom_init.c

@@ -1020,7 +1020,7 @@ static unsigned long __init alloc_up(unsigned long size, unsigned long align)
 	}
 	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 @@ static void __init *make_room(unsigned long *mem_start, unsigned long *mem_end,
 		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 @@ static void __init flatten_device_tree(void)
 
 	/*
 	 * 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 @@ static void __init flatten_device_tree(void)
 	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);

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -1251,7 +1251,7 @@ BEGIN_FTR_SECTION
 	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 @@ BEGIN_FTR_SECTION
 	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

arch/powerpc/platforms/Kconfig

@@ -24,7 +24,7 @@ source "arch/powerpc/platforms/wsp/Kconfig"
 
 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

arch/powerpc/platforms/pseries/dtl.c

@@ -181,7 +181,7 @@ static void dtl_stop(struct dtl *dtl)
 
 	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)

arch/powerpc/platforms/pseries/hotplug-cpu.c

@@ -135,7 +135,7 @@ static void pseries_mach_cpu_die(void)
 		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 @@ static void pseries_mach_cpu_die(void)
 	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... */

arch/powerpc/platforms/pseries/io_event_irq.c

@@ -212,17 +212,15 @@ static int __init ioei_init(void)
 	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;

arch/powerpc/platforms/pseries/kexec.c

@@ -25,20 +25,30 @@ static void pseries_kexec_cpu_down(int crash_shutdown, int secondary)
 {
 	/* 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);
 		}
 	}
 }

arch/powerpc/platforms/pseries/lpar.c

@@ -67,9 +67,8 @@ void vpa_init(int cpu)
 	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 @@ void vpa_init(int cpu)
 	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 @@ void vpa_init(int cpu)
 		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 @@ static void pSeries_lpar_hptab_clear(void)
 		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

arch/powerpc/platforms/pseries/plpar_wrappers.h

@@ -53,9 +53,9 @@ static inline long vpa_call(unsigned long flags, unsigned long cpu,
 	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 @@ static inline long register_vpa(unsigned long cpu, unsigned long vpa)
 	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 @@ static inline long register_slb_shadow(unsigned long cpu, unsigned long vpa)
 	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)

arch/powerpc/platforms/pseries/setup.c

@@ -324,8 +324,9 @@ static int alloc_dispatch_logs(void)
 	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;

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 @@ static void port_error_handler(struct rio_mport *port, int offset)
 
 	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);
 	}
 }

arch/powerpc/sysdev/ppc4xx_pci.c

@@ -655,8 +655,6 @@ struct ppc4xx_pciex_hwops
 
 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 @@ static int __init ppc4xx_pciex_port_reset_sdr(struct ppc4xx_pciex_port *port)
 	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 @@ static void __init ppc4xx_pciex_check_link_sdr(struct ppc4xx_pciex_port *port)
 		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)
 {

arch/sparc/Kconfig

@@ -55,6 +55,7 @@ config SPARC64
 	select PERF_USE_VMALLOC
 	select IRQ_PREFLOW_FASTEOI
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
+	select HAVE_C_RECORDMCOUNT
 
 config ARCH_DEFCONFIG
 	string

arch/sparc/include/asm/sigcontext.h

@@ -45,6 +45,19 @@ typedef struct {
 	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 @@ struct sigcontext {
 		unsigned long	ss_size;
 	}			sigc_stack;
 	unsigned long		sigc_mask;
+	__siginfo_rwin_t *	sigc_rwin_save;
 };
 
 #else

arch/sparc/include/asm/spinlock_32.h

@@ -131,6 +131,15 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 	*(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 @@ static inline int __arch_read_trylock(arch_rwlock_t *rw)
 	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)

arch/sparc/include/asm/spinlock_64.h

@@ -210,14 +210,8 @@ static int inline arch_write_trylock(arch_rwlock_t *lock)
 	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)

arch/sparc/kernel/Makefile

@@ -32,6 +32,7 @@ obj-$(CONFIG_SPARC32)   += sun4m_irq.o sun4c_irq.o sun4d_irq.o
 
 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

arch/sparc/kernel/ds.c

@@ -1256,13 +1256,14 @@ static int __init ds_init(void)
 {
 	unsigned long hv_ret, major, minor;
 
-	hv_ret = sun4v_get_version(HV_GRP_REBOOT_DATA, &major, &minor);
-	if (hv_ret == HV_EOK) {
-		pr_info("SUN4V: Reboot data supported (maj=%lu,min=%lu).\n",
-			major, minor);
-		reboot_data_supported = 1;
+	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);

arch/sparc/kernel/pcic.c

@@ -352,8 +352,8 @@ int __init pcic_probe(void)
 	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];

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 @@ typedef struct {
 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 @@ struct rt_signal_frame32 {
 	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 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
 	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 @@ void do_sigreturn32(struct pt_regs *regs)
 	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 @@ segv:
 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 @@ asmlinkage void do_rt_sigreturn32(struct pt_regs *regs)
 	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 @@ asmlinkage void do_rt_sigreturn32(struct pt_regs *regs)
 	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 @@ static void __user *get_sigframe(struct sigaction *sa, struct pt_regs *regs, uns
 	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 @@ static int setup_frame32(struct k_sigaction *ka, struct pt_regs *regs,
 			 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 @@ static int setup_frame32(struct k_sigaction *ka, struct pt_regs *regs,
 	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 @@ static int setup_frame32(struct k_sigaction *ka, struct pt_regs *regs,
 			  &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 @@ static int setup_frame32(struct k_sigaction *ka, struct pt_regs *regs,
 	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 @@ static int setup_frame32(struct k_sigaction *ka, struct pt_regs *regs,
 		err |= __put_user(0x91d02010, &sf->insns[1]); /*t 0x10*/
 		if (err)
 			goto sigsegv;
-
 		flush_signal_insns(address);
 	}
 	return 0;
@@ -632,18 +631,23 @@ static int setup_rt_frame32(struct k_sigaction *ka, struct pt_regs *regs,
 			    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 @@ static int setup_rt_frame32(struct k_sigaction *ka, struct pt_regs *regs,
 	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 @@ static int setup_rt_frame32(struct k_sigaction *ka, struct pt_regs *regs,
 			  &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 @@ static int setup_rt_frame32(struct k_sigaction *ka, struct pt_regs *regs,
 	}
 	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;
 	

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 @@ struct signal_frame {
 	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 @@ struct rt_signal_frame {
 	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 @@ asmlinkage int sys_sigsuspend(old_sigset_t set)
 	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 @@ asmlinkage void do_sigreturn(struct pt_regs *regs)
 	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 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs)
 	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 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs)
 	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 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs)
 	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 @@ static inline void __user *get_sigframe(struct sigaction *sa, struct pt_regs *re
 	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 @@ static int setup_frame(struct k_sigaction *ka, struct pt_regs *regs,
 	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 @@ static int setup_frame(struct k_sigaction *ka, struct pt_regs *regs,
 	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 @@ static int setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs,
 			  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 @@ static int setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs,
 	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 @@ static int setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs,
 	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);
 

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 @@ struct rt_signal_frame {
 	__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 @@ asmlinkage long sys_sigsuspend(old_sigset_t set)
 	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 @@ void do_rt_sigreturn(struct pt_regs *regs)
 	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 @@ void do_rt_sigreturn(struct pt_regs *regs)
 	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 @@ segv:
 }
 
 /* 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 @@ setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs,
 	       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 @@ setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs,
 
 	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 {

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 */

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;
+
+}

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;
+}

arch/x86/include/asm/desc.h

@@ -27,8 +27,8 @@ static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *in
 
 	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;
 }

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.

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 paravirt_callee_save {
 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;
 };

arch/x86/include/asm/ptrace.h

@@ -131,6 +131,9 @@ struct pt_regs {
 #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 @@ static inline int v8086_mode(struct pt_regs *regs)
 #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