Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

Pull powerpc updates from Ben Herrenschmidt:
"This is the powerpc changes for the 3.11 merge window. In addition to
the usual bug fixes and small updates, the main highlights are:

- Support for transparent huge pages by Aneesh Kumar for 64-bit
server processors. This allows the use of 16M pages as transparent
huge pages on kernels compiled with a 64K base page size.

- Base VFIO support for KVM on power by Alexey Kardashevskiy

- Wiring up of our nvram to the pstore infrastructure, including
putting compressed oopses in there by Aruna Balakrishnaiah

- Move, rework and improve our "EEH" (basically PCI error handling
and recovery) infrastructure. It is no longer specific to pseries
but is now usable by the new "powernv" platform as well (no
hypervisor) by Gavin Shan.

- I fixed some bugs in our math-emu instruction decoding and made it
usable to emulate some optional FP instructions on processors with
hard FP that lack them (such as fsqrt on Freescale embedded
processors).

- Support for Power8 "Event Based Branch" facility by Michael
Ellerman. This facility allows what is basically "userspace
interrupts" for performance monitor events.

- A bunch of Transactional Memory vs. Signals bug fixes and HW
breakpoint/watchpoint fixes by Michael Neuling.

And more ... I appologize in advance if I've failed to highlight
something that somebody deemed worth it."

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (156 commits)
pstore: Add hsize argument in write_buf call of pstore_ftrace_call
powerpc/fsl: add MPIC timer wakeup support
powerpc/mpic: create mpic subsystem object
powerpc/mpic: add global timer support
powerpc/mpic: add irq_set_wake support
powerpc/85xx: enable coreint for all the 64bit boards
powerpc/8xx: Erroneous double irq_eoi() on CPM IRQ in MPC8xx
powerpc/fsl: Enable CONFIG_E1000E in mpc85xx_smp_defconfig
powerpc/mpic: Add get_version API both for internal and external use
powerpc: Handle both new style and old style reserve maps
powerpc/hw_brk: Fix off by one error when validating DAWR region end
powerpc/pseries: Support compression of oops text via pstore
powerpc/pseries: Re-organise the oops compression code
pstore: Pass header size in the pstore write callback
powerpc/powernv: Fix iommu initialization again
powerpc/pseries: Inform the hypervisor we are using EBB regs
powerpc/perf: Add power8 EBB support
powerpc/perf: Core EBB support for 64-bit book3s
powerpc/perf: Drop MMCRA from thread_struct
powerpc/perf: Don't enable if we have zero events
...

Documentation/devicetree/bindings/powerpc/fsl/interlaken-lac.txt

···
+===============================================================================
+Freescale Interlaken Look-Aside Controller Device Bindings
+Copyright 2012 Freescale Semiconductor Inc.
+
+CONTENTS
+  - Interlaken Look-Aside Controller (LAC) Node
+  - Example LAC Node
+  - Interlaken Look-Aside Controller (LAC) Software Portal Node
+  - Interlaken Look-Aside Controller (LAC) Software Portal Child Nodes
+  - Example LAC SWP Node with Child Nodes
+
+==============================================================================
+Interlaken Look-Aside Controller (LAC) Node
+
+DESCRIPTION
+
+The Interlaken is a narrow, high speed channelized chip-to-chip interface. To
+facilitate interoperability between a data path device and a look-aside
+co-processor, the Interlaken Look-Aside protocol is defined for short
+transaction-related transfers. Although based on the Interlaken protocol,
+Interlaken Look-Aside is not directly compatible with Interlaken and can be
+considered a different operation mode.
+
+The Interlaken LA controller connects internal platform to Interlaken serial
+interface. It accepts LA command through software portals, which are system
+memory mapped 4KB spaces. The LA commands are then translated into the
+Interlaken control words and data words, which are sent on TX side to TCAM
+through SerDes lanes.
+
+There are two 4KiB spaces defined within the LAC global register memory map.
+There is a full register set at 0x0000-0x0FFF (also known as the "hypervisor"
+version), and a subset at 0x1000-0x1FFF.  The former is a superset of the
+latter, and includes certain registers that should not be accessible to
+partitioned software.  Separate nodes are used for each region, with a phandle
+linking the hypervisor node to the normal operating node.
+
+PROPERTIES
+
+  - compatible
+	Usage: required
+	Value type: <string>
+	Definition: Must include "fsl,interlaken-lac". This represents only
+		those LAC CCSR registers not protected in partitioned
+		software. The version of the device is determined by the LAC
+		IP Block Revision Register (IPBRR0) at offset 0x0BF8.
+
+		Table of correspondences between IPBRR0 values and example
+		chips:
+			Value		Device
+			-----------	-------
+			0x02000100	T4240
+
+		The Hypervisor node has a different compatible. It must include
+		"fsl,interlaken-lac-hv". This node represents the protected
+		LAC register space and is required except inside a partition
+		where access to the hypervisor node is to be denied.
+
+  - fsl,non-hv-node
+	Usage: required in "fsl,interlaken-lac-hv"
+	Value type: <phandle>
+	Definition: Points to the non-protected LAC CCSR mapped register space
+		node.
+
+  - reg
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: A standard property. The first resource represents the
+		Interlaken LAC configuration registers.
+
+  - interrupts:
+	Usage: required in non-hv node only
+	Value type: <prop-encoded-array>
+	Definition: Interrupt mapping for Interlaken LAC error IRQ.
+
+EXAMPLE
+	lac: lac@229000 {
+		compatible = "fsl,interlaken-lac"
+		reg = <0x229000 0x1000>;
+		interrupts = <16 2 1 18>;
+	};
+
+	lac-hv@228000 {
+		compatible = "fsl,interlaken-lac-hv"
+		reg = <0x228000 0x1000>;
+		fsl,non-hv-node = <&lac>;
+	};
+
+===============================================================================
+Interlaken Look-Aside Controller (LAC) Software Portal Container Node
+
+DESCRIPTION
+The Interlaken Look-Aside Controller (LAC) utilizes Software Portals to accept
+Interlaken Look-Aside (ILA) commands. The Interlaken LAC software portal
+memory map occupies 128KB of memory space. The software portal memory space is
+intended to be cache-enabled. WIMG for each software space is required to be
+0010 if stashing is enabled; otherwise, WIMG can be 0000 or 0010.
+
+PROPERTIES
+
+  - #address-cells
+	Usage: required
+	Value type: <u32>
+	Definition: A standard property. Must have a value of 1.
+
+  - #size-cells
+	Usage: required
+	Value type: <u32>
+	Definition: A standard property. Must have a value of 1.
+
+  - compatible
+	Usage: required
+	Value type: <string>
+	Definition: Must include "fsl,interlaken-lac-portals"
+
+  - ranges
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: A standard property. Specifies the address and length
+		of the LAC portal memory space.
+
+===============================================================================
+Interlaken Look-Aside Controller (LAC) Software Portals Child Nodes
+
+DESCRIPTION
+There are up to 24 available software portals with each software portal
+requiring 4KB of consecutive memory within the software portal memory mapped
+space.
+
+PROPERTIES
+
+  - compatible
+	Usage: required
+	Value type: <string>
+	Definition: Must include "fsl,interlaken-lac-portal-vX.Y" where X is
+		the Major version (IP_MJ) found in the LAC IP Block Revision
+		Register (IPBRR0), at offset 0x0BF8, and Y is the Minor version
+		(IP_MN).
+
+		Table of correspondences between version values and example chips:
+		    Value	Device
+		    ------	-------
+		      1.0	T4240
+
+  - reg
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: A standard property.  The first resource represents the
+		Interlaken LAC software portal registers.
+
+  - fsl,liodn
+	Value type: <u32>
+	Definition: The logical I/O device number (LIODN) for this device.  The
+		LIODN is a number expressed by this device and used to perform
+		look-ups in the IOMMU (PAMU) address table when performing
+		DMAs. This property is automatically added by u-boot.
+
+===============================================================================
+EXAMPLE
+
+lac-portals {
+	#address-cells = <0x1>;
+	#size-cells = <0x1>;
+	compatible = "fsl,interlaken-lac-portals";
+	ranges = <0x0 0xf 0xf4400000 0x20000>;
+
+	lportal0: lac-portal@0 {
+		compatible = "fsl,interlaken-lac-portal-v1.0";
+		fsl,liodn = <0x204>;
+		reg = <0x0 0x1000>;
+	};
+
+	lportal1: lac-portal@1000 {
+		compatible = "fsl,interlaken-lac-portal-v1.0";
+		fsl,liodn = <0x205>;
+		reg = <0x1000 0x1000>;
+	};
+
+	lportal2: lac-portal@2000 {
+		compatible = "fsl,interlaken-lac-portal-v1.0";
+		fsl,liodn = <0x206>;
+		reg = <0x2000 0x1000>;
+	};
+
+	lportal3: lac-portal@3000 {
+		compatible = "fsl,interlaken-lac-portal-v1.0";
+		fsl,liodn = <0x207>;
+		reg = <0x3000 0x1000>;
+	};
+
+	lportal4: lac-portal@4000 {
+		compatible = "fsl,interlaken-lac-portal-v1.0";
+		fsl,liodn = <0x208>;
+		reg = <0x4000 0x1000>;
+	};
+
+	lportal5: lac-portal@5000 {
+		compatible = "fsl,interlaken-lac-portal-v1.0";
+		fsl,liodn = <0x209>;
+		reg = <0x5000 0x1000>;
+	};
+
+	lportal6: lac-portal@6000 {
+		compatible = "fsl,interlaken-lac-portal-v1.0";
+		fsl,liodn = <0x20A>;
+		reg = <0x6000 0x1000>;
+	};
+
+	lportal7: lac-portal@7000 {
+		compatible = "fsl,interlaken-lac-portal-v1.0";
+		fsl,liodn = <0x20B>;
+		reg = <0x7000 0x1000>;
+	};
+
+	lportal8: lac-portal@8000 {
+		compatible = "fsl,interlaken-lac-portal-v1.0";
+		fsl,liodn = <0x20C>;
+		reg = <0x8000 0x1000>;
+	};
+
+	lportal9: lac-portal@9000 {
+		compatible = "fsl,interlaken-lac-portal-v1.0";
+		fsl,liodn = <0x20D>;
+		reg = <0x9000 0x1000>;
+	};
+
+	lportal10: lac-portal@A000 {
+		compatible = "fsl,interlaken-lac-portal-v1.0";
+		fsl,liodn = <0x20E>;
+		reg = <0xA000 0x1000>;
+	};
+
+	lportal11: lac-portal@B000 {
+		compatible = "fsl,interlaken-lac-portal-v1.0";
+		fsl,liodn = <0x20F>;
+		reg = <0xB000 0x1000>;
+	};
+
+	lportal12: lac-portal@C000 {
+		compatible = "fsl,interlaken-lac-portal-v1.0";
+		fsl,liodn = <0x210>;
+		reg = <0xC000 0x1000>;
+	};
+
+	lportal13: lac-portal@D000 {
+		compatible = "fsl,interlaken-lac-portal-v1.0";
+		fsl,liodn = <0x211>;
+		reg = <0xD000 0x1000>;
+	};
+
+	lportal14: lac-portal@E000 {
+		compatible = "fsl,interlaken-lac-portal-v1.0";
+		fsl,liodn = <0x212>;
+		reg = <0xE000 0x1000>;
+	};
+
+	lportal15: lac-portal@F000 {
+		compatible = "fsl,interlaken-lac-portal-v1.0";
+		fsl,liodn = <0x213>;
+		reg = <0xF000 0x1000>;
+	};
+
+	lportal16: lac-portal@10000 {
+		compatible = "fsl,interlaken-lac-portal-v1.0";
+		fsl,liodn = <0x214>;
+		reg = <0x10000 0x1000>;
+	};
+
+	lportal17: lac-portal@11000 {
+		compatible = "fsl,interlaken-lac-portal-v1.0";
+		fsl,liodn = <0x215>;
+		reg = <0x11000 0x1000>;
+	};
+
+	lportal8: lac-portal@1200 {
+		compatible = "fsl,interlaken-lac-portal-v1.0";
+		fsl,liodn = <0x216>;
+		reg = <0x12000 0x1000>;
+	};
+
+	lportal19: lac-portal@13000 {
+		compatible = "fsl,interlaken-lac-portal-v1.0";
+		fsl,liodn = <0x217>;
+		reg = <0x13000 0x1000>;
+	};
+
+	lportal20: lac-portal@14000 {
+		compatible = "fsl,interlaken-lac-portal-v1.0";
+		fsl,liodn = <0x218>;
+		reg = <0x14000 0x1000>;
+	};
+
+	lportal21: lac-portal@15000 {
+		compatible = "fsl,interlaken-lac-portal-v1.0";
+		fsl,liodn = <0x219>;
+		reg = <0x15000 0x1000>;
+	};
+
+	lportal22: lac-portal@16000 {
+		compatible = "fsl,interlaken-lac-portal-v1.0";
+		fsl,liodn = <0x21A>;
+		reg = <0x16000 0x1000>;
+	};
+
+	lportal23: lac-portal@17000 {
+		compatible = "fsl,interlaken-lac-portal-v1.0";
+		fsl,liodn = <0x21B>;
+		reg = <0x17000 0x1000>;
+	};
+};

Documentation/powerpc/00-INDEX

···
 	- IBM "Hypervisor Virtual Console Server" Installation Guide
 mpc52xx.txt
 	- Linux 2.6.x on MPC52xx family
+pmu-ebb.txt
+	- Description of the API for using the PMU with Event Based Branches.
 qe_firmware.txt
 	- describes the layout of firmware binaries for the Freescale QUICC
 	  Engine and the code that parses and uploads the microcode therein.

Documentation/powerpc/pmu-ebb.txt

···
+PMU Event Based Branches
+========================
+
+Event Based Branches (EBBs) are a feature which allows the hardware to
+branch directly to a specified user space address when certain events occur.
+
+The full specification is available in Power ISA v2.07:
+
+  https://www.power.org/documentation/power-isa-version-2-07/
+
+One type of event for which EBBs can be configured is PMU exceptions. This
+document describes the API for configuring the Power PMU to generate EBBs,
+using the Linux perf_events API.
+
+
+Terminology
+-----------
+
+Throughout this document we will refer to an "EBB event" or "EBB events". This
+just refers to a struct perf_event which has set the "EBB" flag in its
+attr.config. All events which can be configured on the hardware PMU are
+possible "EBB events".
+
+
+Background
+----------
+
+When a PMU EBB occurs it is delivered to the currently running process. As such
+EBBs can only sensibly be used by programs for self-monitoring.
+
+It is a feature of the perf_events API that events can be created on other
+processes, subject to standard permission checks. This is also true of EBB
+events, however unless the target process enables EBBs (via mtspr(BESCR)) no
+EBBs will ever be delivered.
+
+This makes it possible for a process to enable EBBs for itself, but not
+actually configure any events. At a later time another process can come along
+and attach an EBB event to the process, which will then cause EBBs to be
+delivered to the first process. It's not clear if this is actually useful.
+
+
+When the PMU is configured for EBBs, all PMU interrupts are delivered to the
+user process. This means once an EBB event is scheduled on the PMU, no non-EBB
+events can be configured. This means that EBB events can not be run
+concurrently with regular 'perf' commands, or any other perf events.
+
+It is however safe to run 'perf' commands on a process which is using EBBs. The
+kernel will in general schedule the EBB event, and perf will be notified that
+its events could not run.
+
+The exclusion between EBB events and regular events is implemented using the
+existing "pinned" and "exclusive" attributes of perf_events. This means EBB
+events will be given priority over other events, unless they are also pinned.
+If an EBB event and a regular event are both pinned, then whichever is enabled
+first will be scheduled and the other will be put in error state. See the
+section below titled "Enabling an EBB event" for more information.
+
+
+Creating an EBB event
+---------------------
+
+To request that an event is counted using EBB, the event code should have bit
+63 set.
+
+EBB events must be created with a particular, and restrictive, set of
+attributes - this is so that they interoperate correctly with the rest of the
+perf_events subsystem.
+
+An EBB event must be created with the "pinned" and "exclusive" attributes set.
+Note that if you are creating a group of EBB events, only the leader can have
+these attributes set.
+
+An EBB event must NOT set any of the "inherit", "sample_period", "freq" or
+"enable_on_exec" attributes.
+
+An EBB event must be attached to a task. This is specified to perf_event_open()
+by passing a pid value, typically 0 indicating the current task.
+
+All events in a group must agree on whether they want EBB. That is all events
+must request EBB, or none may request EBB.
+
+EBB events must specify the PMC they are to be counted on. This ensures
+userspace is able to reliably determine which PMC the event is scheduled on.
+
+
+Enabling an EBB event
+---------------------
+
+Once an EBB event has been successfully opened, it must be enabled with the
+perf_events API. This can be achieved either via the ioctl() interface, or the
+prctl() interface.
+
+However, due to the design of the perf_events API, enabling an event does not
+guarantee that it has been scheduled on the PMU. To ensure that the EBB event
+has been scheduled on the PMU, you must perform a read() on the event. If the
+read() returns EOF, then the event has not been scheduled and EBBs are not
+enabled.
+
+This behaviour occurs because the EBB event is pinned and exclusive. When the
+EBB event is enabled it will force all other non-pinned events off the PMU. In
+this case the enable will be successful. However if there is already an event
+pinned on the PMU then the enable will not be successful.
+
+
+Reading an EBB event
+--------------------
+
+It is possible to read() from an EBB event. However the results are
+meaningless. Because interrupts are being delivered to the user process the
+kernel is not able to count the event, and so will return a junk value.
+
+
+Closing an EBB event
+--------------------
+
+When an EBB event is finished with, you can close it using close() as for any
+regular event. If this is the last EBB event the PMU will be deconfigured and
+no further PMU EBBs will be delivered.
+
+
+EBB Handler
+-----------
+
+The EBB handler is just regular userspace code, however it must be written in
+the style of an interrupt handler. When the handler is entered all registers
+are live (possibly) and so must be saved somehow before the handler can invoke
+other code.
+
+It's up to the program how to handle this. For C programs a relatively simple
+option is to create an interrupt frame on the stack and save registers there.
+
+Fork
+----
+
+EBB events are not inherited across fork. If the child process wishes to use
+EBBs it should open a new event for itself. Similarly the EBB state in
+BESCR/EBBHR/EBBRR is cleared across fork().

Documentation/vfio.txt

···
 interfaces implement the device region access defined by the device's
 own VFIO_DEVICE_GET_REGION_INFO ioctl.
 
+
+PPC64 sPAPR implementation note
+-------------------------------------------------------------------------------
+
+This implementation has some specifics:
+
+1) Only one IOMMU group per container is supported as an IOMMU group
+represents the minimal entity which isolation can be guaranteed for and
+groups are allocated statically, one per a Partitionable Endpoint (PE)
+(PE is often a PCI domain but not always).
+
+2) The hardware supports so called DMA windows - the PCI address range
+within which DMA transfer is allowed, any attempt to access address space
+out of the window leads to the whole PE isolation.
+
+3) PPC64 guests are paravirtualized but not fully emulated. There is an API
+to map/unmap pages for DMA, and it normally maps 1..32 pages per call and
+currently there is no way to reduce the number of calls. In order to make things
+faster, the map/unmap handling has been implemented in real mode which provides
+an excellent performance which has limitations such as inability to do
+locked pages accounting in real time.
+
+So 3 additional ioctls have been added:
+
+	VFIO_IOMMU_SPAPR_TCE_GET_INFO - returns the size and the start
+		of the DMA window on the PCI bus.
+
+	VFIO_IOMMU_ENABLE - enables the container. The locked pages accounting
+		is done at this point. This lets user first to know what
+		the DMA window is and adjust rlimit before doing any real job.
+
+	VFIO_IOMMU_DISABLE - disables the container.
+
+
+The code flow from the example above should be slightly changed:
+
+	.....
+	/* Add the group to the container */
+	ioctl(group, VFIO_GROUP_SET_CONTAINER, &container);
+
+	/* Enable the IOMMU model we want */
+	ioctl(container, VFIO_SET_IOMMU, VFIO_SPAPR_TCE_IOMMU)
+
+	/* Get addition sPAPR IOMMU info */
+	vfio_iommu_spapr_tce_info spapr_iommu_info;
+	ioctl(container, VFIO_IOMMU_SPAPR_TCE_GET_INFO, &spapr_iommu_info);
+
+	if (ioctl(container, VFIO_IOMMU_ENABLE))
+		/* Cannot enable container, may be low rlimit */
+
+	/* Allocate some space and setup a DMA mapping */
+	dma_map.vaddr = mmap(0, 1024 * 1024, PROT_READ | PROT_WRITE,
+			     MAP_PRIVATE | MAP_ANONYMOUS, 0, 0);
+
+	dma_map.size = 1024 * 1024;
+	dma_map.iova = 0; /* 1MB starting at 0x0 from device view */
+	dma_map.flags = VFIO_DMA_MAP_FLAG_READ | VFIO_DMA_MAP_FLAG_WRITE;
+
+	/* Check here is .iova/.size are within DMA window from spapr_iommu_info */
+
+	ioctl(container, VFIO_IOMMU_MAP_DMA, &dma_map);
+	.....
+
 -------------------------------------------------------------------------------
 
 [1] VFIO was originally an acronym for "Virtual Function I/O" in its

MAINTAINERS

···
 S:	Maintained
 F:	drivers/media/rc/ene_ir.*
 
+ENHANCED ERROR HANDLING (EEH)
+M:	Gavin Shan <[e-mail]>
+L:	[e-mail]
+S:	Supported
+F:	Documentation/powerpc/eeh-pci-error-recovery.txt
+F:	arch/powerpc/kernel/eeh*.c
+
 EPSON S1D13XXX FRAMEBUFFER DRIVER
 M:	Kristoffer Ericson <[e-mail]>
 S:	Maintained
···
 L:	[e-mail]
 S:	Supported
 F:	Documentation/PCI/pci-error-recovery.txt
-F:	Documentation/powerpc/eeh-pci-error-recovery.txt
 
 PCI SUBSYSTEM
 M:	Bjorn Helgaas <[e-mail]>

arch/powerpc/Kconfig

···
 
 config MATH_EMULATION
 	bool "Math emulation"
-	depends on 4xx || 8xx || E200 || PPC_MPC832x || E500
+	depends on 4xx || 8xx || PPC_MPC832x || BOOKE
 	---help---
 	  Some PowerPC chips designed for embedded applications do not have
 	  a floating-point unit and therefore do not implement the
···
 	  unit, which will allow programs that use floating-point
 	  instructions to run.
 
+	  This is also useful to emulate missing (optional) instructions
+	  such as fsqrt on cores that do have an FPU but do not implement
+	  them (such as Freescale BookE).
+
 config PPC_TRANSACTIONAL_MEM
        bool "Transactional Memory support for POWERPC"
        depends on PPC_BOOK3S_64
···
        default n
        ---help---
          Support user-mode Transactional Memory on POWERPC.
-
-config 8XX_MINIMAL_FPEMU
-	bool "Minimal math emulation for 8xx"
-	depends on 8xx && !MATH_EMULATION
-	help
-	  Older arch/ppc kernels still emulated a few floating point
-	  instructions such as load and store, even when full math
-	  emulation is disabled.  Say "Y" here if you want to preserve
-	  this behavior.
-
-	  It is recommended that you build a soft-float userspace instead.
 
 config IOMMU_HELPER
 	def_bool PPC64

arch/powerpc/Kconfig.debug

···
 	  enable debugging for the wrong type of machine your kernel
 	  _will not boot_.
 
+config PPC_EARLY_DEBUG_BOOTX
+	bool "BootX or OpenFirmware"
+	depends on BOOTX_TEXT
+	help
+	  Select this to enable early debugging for a machine using BootX
+	  or OpenFirmware.
+
 config PPC_EARLY_DEBUG_LPAR
 	bool "LPAR HV Console"
 	depends on PPC_PSERIES

arch/powerpc/boot/dts/currituck.dts

···
 				interrupts = <34 2>;
 			};
 
+			FPGA0: fpga@50000000 {
+				compatible = "ibm,currituck-fpga";
+				reg = <0x50000000 0x4>;
+			};
+
 			IIC0: i2c@00000000 {
 				compatible = "ibm,iic-currituck", "ibm,iic";
 				reg = <0x0 0x00000014>;

arch/powerpc/boot/dts/fsl/interlaken-lac-portals.dtsi

···
+/* T4240 Interlaken LAC Portal device tree stub with 24 portals.
+ *
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#address-cells = <0x1>;
+#size-cells = <0x1>;
+compatible = "fsl,interlaken-lac-portals";
+
+lportal0: lac-portal@0 {
+	compatible = "fsl,interlaken-lac-portal-v1.0";
+	reg = <0x0 0x1000>;
+};
+
+lportal1: lac-portal@1000 {
+	compatible = "fsl,interlaken-lac-portal-v1.0";
+	reg = <0x1000 0x1000>;
+};
+
+lportal2: lac-portal@2000 {
+	compatible = "fsl,interlaken-lac-portal-v1.0";
+	reg = <0x2000 0x1000>;
+};
+
+lportal3: lac-portal@3000 {
+	compatible = "fsl,interlaken-lac-portal-v1.0";
+	reg = <0x3000 0x1000>;
+};
+
+lportal4: lac-portal@4000 {
+	compatible = "fsl,interlaken-lac-portal-v1.0";
+	reg = <0x4000 0x1000>;
+};
+
+lportal5: lac-portal@5000 {
+	compatible = "fsl,interlaken-lac-portal-v1.0";
+	reg = <0x5000 0x1000>;
+};
+
+lportal6: lac-portal@6000 {
+	compatible = "fsl,interlaken-lac-portal-v1.0";
+	reg = <0x6000 0x1000>;
+};
+
+lportal7: lac-portal@7000 {
+	compatible = "fsl,interlaken-lac-portal-v1.0";
+	reg = <0x7000 0x1000>;
+};
+
+lportal8: lac-portal@8000 {
+	compatible = "fsl,interlaken-lac-portal-v1.0";
+	reg = <0x8000 0x1000>;
+};
+
+lportal9: lac-portal@9000 {
+	compatible = "fsl,interlaken-lac-portal-v1.0";
+	reg = <0x9000 0x1000>;
+};
+
+lportal10: lac-portal@A000 {
+	compatible = "fsl,interlaken-lac-portal-v1.0";
+	reg = <0xA000 0x1000>;
+};
+
+lportal11: lac-portal@B000 {
+	compatible = "fsl,interlaken-lac-portal-v1.0";
+	reg = <0xB000 0x1000>;
+};
+
+lportal12: lac-portal@C000 {
+	compatible = "fsl,interlaken-lac-portal-v1.0";
+	reg = <0xC000 0x1000>;
+};
+
+lportal13: lac-portal@D000 {
+	compatible = "fsl,interlaken-lac-portal-v1.0";
+	reg = <0xD000 0x1000>;
+};
+
+lportal14: lac-portal@E000 {
+	compatible = "fsl,interlaken-lac-portal-v1.0";
+	reg = <0xE000 0x1000>;
+};
+
+lportal15: lac-portal@F000 {
+	compatible = "fsl,interlaken-lac-portal-v1.0";
+	reg = <0xF000 0x1000>;
+};
+
+lportal16: lac-portal@10000 {
+	compatible = "fsl,interlaken-lac-portal-v1.0";
+	reg = <0x10000 0x1000>;
+};
+
+lportal17: lac-portal@11000 {
+	compatible = "fsl,interlaken-lac-portal-v1.0";
+	reg = <0x11000 0x1000>;
+};
+
+lportal18: lac-portal@1200 {
+	compatible = "fsl,interlaken-lac-portal-v1.0";
+	reg = <0x12000 0x1000>;
+};
+
+lportal19: lac-portal@13000 {
+	compatible = "fsl,interlaken-lac-portal-v1.0";
+	reg = <0x13000 0x1000>;
+};
+
+lportal20: lac-portal@14000 {
+	compatible = "fsl,interlaken-lac-portal-v1.0";
+	reg = <0x14000 0x1000>;
+};
+
+lportal21: lac-portal@15000 {
+	compatible = "fsl,interlaken-lac-portal-v1.0";
+	reg = <0x15000 0x1000>;
+};
+
+lportal22: lac-portal@16000 {
+	compatible = "fsl,interlaken-lac-portal-v1.0";
+	reg = <0x16000 0x1000>;
+};
+
+lportal23: lac-portal@17000 {
+	compatible = "fsl,interlaken-lac-portal-v1.0";
+	reg = <0x17000 0x1000>;
+};

arch/powerpc/boot/dts/fsl/interlaken-lac.dtsi

···
+/*
+ * T4 Interlaken Look-aside Controller (LAC) device tree stub
+ *
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+lac: lac@229000 {
+	compatible = "fsl,interlaken-lac";
+	reg = <0x229000 0x1000>;
+	interrupts = <16 2 1 18>;
+};
+
+lac-hv@228000 {
+	compatible = "fsl,interlaken-lac-hv";
+	reg = <0x228000 0x1000>;
+	fsl,non-hv-node = <&lac>;
+};

arch/powerpc/configs/c2k_defconfig

···
 CONFIG_DEBUG_STACKOVERFLOW=y
 CONFIG_DEBUG_STACK_USAGE=y
 CONFIG_BOOTX_TEXT=y
+CONFIG_PPC_EARLY_DEBUG=y
+CONFIG_PPC_EARLY_DEBUG_BOOTX=y
 CONFIG_KEYS=y
 CONFIG_KEYS_DEBUG_PROC_KEYS=y
 CONFIG_SECURITY=y

arch/powerpc/configs/g5_defconfig

···
 CONFIG_LATENCYTOP=y
 CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_BOOTX_TEXT=y
+CONFIG_PPC_EARLY_DEBUG=y
+CONFIG_PPC_EARLY_DEBUG_BOOTX=y
 CONFIG_CRYPTO_NULL=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_ECB=m

arch/powerpc/configs/maple_defconfig

···
 CONFIG_XMON=y
 CONFIG_XMON_DEFAULT=y
 CONFIG_BOOTX_TEXT=y
+CONFIG_PPC_EARLY_DEBUG=y
+CONFIG_PPC_EARLY_DEBUG_BOOTX=y
 CONFIG_CRYPTO_ECB=m
 CONFIG_CRYPTO_PCBC=m
 # CONFIG_CRYPTO_ANSI_CPRNG is not set

arch/powerpc/configs/mpc512x_defconfig

···
-CONFIG_EXPERIMENTAL=y
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
-CONFIG_SPARSE_IRQ=y
+CONFIG_NO_HZ=y
 CONFIG_LOG_BUF_SHIFT=16
 CONFIG_BLK_DEV_INITRD=y
 # CONFIG_COMPAT_BRK is not set
···
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
+CONFIG_PARTITION_ADVANCED=y
 # CONFIG_IOSCHED_CFQ is not set
 # CONFIG_PPC_CHRP is not set
 CONFIG_PPC_MPC512x=y
···
 CONFIG_MPC512x_GENERIC=y
 CONFIG_PDM360NG=y
 # CONFIG_PPC_PMAC is not set
-CONFIG_NO_HZ=y
 CONFIG_HZ_1000=y
-# CONFIG_MIGRATION is not set
 # CONFIG_SECCOMP is not set
 # CONFIG_PCI is not set
 CONFIG_NET=y
···
 # CONFIG_INET_DIAG is not set
 # CONFIG_IPV6 is not set
 CONFIG_CAN=y
-CONFIG_CAN_RAW=y
-CONFIG_CAN_BCM=y
 CONFIG_CAN_VCAN=y
 CONFIG_CAN_MSCAN=y
 CONFIG_CAN_DEBUG_DEVICES=y
···
 # CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_CFI=y
 CONFIG_MTD_CFI_AMDSTD=y
···
 CONFIG_BLK_DEV_RAM_COUNT=1
 CONFIG_BLK_DEV_RAM_SIZE=8192
 CONFIG_BLK_DEV_XIP=y
-CONFIG_MISC_DEVICES=y
 CONFIG_EEPROM_AT24=y
 CONFIG_EEPROM_AT25=y
 CONFIG_SCSI=y
···
 CONFIG_BLK_DEV_SD=y
 CONFIG_CHR_DEV_SG=y
 CONFIG_NETDEVICES=y
+CONFIG_FS_ENET=y
 CONFIG_MARVELL_PHY=y
 CONFIG_DAVICOM_PHY=y
 CONFIG_QSEMI_PHY=y
···
 CONFIG_LSI_ET1011C_PHY=y
 CONFIG_FIXED_PHY=y
 CONFIG_MDIO_BITBANG=y
-CONFIG_NET_ETHERNET=y
-CONFIG_FS_ENET=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
 # CONFIG_WLAN is not set
 # CONFIG_INPUT_MOUSEDEV_PSAUX is not set
 CONFIG_INPUT_EVDEV=y
···
 CONFIG_GPIO_MPC8XXX=y
 # CONFIG_HWMON is not set
 CONFIG_MEDIA_SUPPORT=y
-CONFIG_VIDEO_DEV=y
 CONFIG_VIDEO_ADV_DEBUG=y
-# CONFIG_VIDEO_HELPER_CHIPS_AUTO is not set
-CONFIG_VIDEO_SAA711X=y
 CONFIG_FB=y
 CONFIG_FB_FSL_DIU=y
 # CONFIG_VGA_CONSOLE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_USB=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_EHCI_FSL=y
+# CONFIG_USB_EHCI_HCD_PPC_OF is not set
+CONFIG_USB_STORAGE=y
+CONFIG_USB_GADGET=y
+CONFIG_USB_FSL_USB2=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_M41T80=y
 CONFIG_RTC_DRV_MPC5121=y
···
 CONFIG_JFFS2_FS=y
 CONFIG_UBIFS_FS=y
 CONFIG_NFS_FS=y
-CONFIG_NFS_V3=y
 CONFIG_ROOT_NFS=y
-CONFIG_PARTITION_ADVANCED=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
 # CONFIG_ENABLE_WARN_DEPRECATED is not set

arch/powerpc/configs/mpc85xx_smp_defconfig

···
 CONFIG_FS_ENET=y
 CONFIG_UCC_GETH=y
 CONFIG_GIANFAR=y
+CONFIG_E1000E=y
 CONFIG_MARVELL_PHY=y
 CONFIG_DAVICOM_PHY=y
 CONFIG_CICADA_PHY=y

arch/powerpc/configs/pmac32_defconfig

···
 CONFIG_XMON=y
 CONFIG_XMON_DEFAULT=y
 CONFIG_BOOTX_TEXT=y
+CONFIG_PPC_EARLY_DEBUG=y
+CONFIG_PPC_EARLY_DEBUG_BOOTX=y
 CONFIG_CRYPTO_NULL=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_MD4=m

arch/powerpc/configs/ppc64_defconfig

···
 CONFIG_MSI_BITMAP_SELFTEST=y
 CONFIG_XMON=y
 CONFIG_BOOTX_TEXT=y
+CONFIG_PPC_EARLY_DEBUG=y
+CONFIG_PPC_EARLY_DEBUG_BOOTX=y
 CONFIG_CRYPTO_NULL=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_PCBC=m

arch/powerpc/configs/ppc6xx_defconfig

···
 CONFIG_DEBUG_STACK_USAGE=y
 CONFIG_XMON=y
 CONFIG_BOOTX_TEXT=y
+CONFIG_PPC_EARLY_DEBUG=y
+CONFIG_PPC_EARLY_DEBUG_BOOTX=y
 CONFIG_KEYS=y
 CONFIG_KEYS_DEBUG_PROC_KEYS=y
 CONFIG_SECURITY=y

arch/powerpc/configs/pseries_defconfig

···
 CONFIG_SQUASHFS_XATTR=y
 CONFIG_SQUASHFS_LZO=y
 CONFIG_SQUASHFS_XZ=y
+CONFIG_PSTORE=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3_ACL=y
 CONFIG_NFS_V4=y

arch/powerpc/include/asm/eeh.h

···
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/string.h>
+#include <linux/time.h>
 
 struct pci_dev;
 struct pci_bus;
···
 
 #define EEH_PE_ISOLATED		(1 << 0)	/* Isolated PE		*/
 #define EEH_PE_RECOVERING	(1 << 1)	/* Recovering PE	*/
+#define EEH_PE_PHB_DEAD		(1 << 2)	/* Dead PHB		*/
 
 struct eeh_pe {
 	int type;			/* PE type: PHB/Bus/Device	*/
···
 	int config_addr;		/* Traditional PCI address	*/
 	int addr;			/* PE configuration address	*/
 	struct pci_controller *phb;	/* Associated PHB		*/
+	struct pci_bus *bus;		/* Top PCI bus for bus PE	*/
 	int check_count;		/* Times of ignored error	*/
 	int freeze_count;		/* Times of froze up		*/
+	struct timeval tstamp;		/* Time on first-time freeze	*/
 	int false_positives;		/* Times of reported #ff's	*/
 	struct eeh_pe *parent;		/* Parent PE			*/
 	struct list_head child_list;	/* Link PE to the child list	*/
···
 
 static inline struct device_node *eeh_dev_to_of_node(struct eeh_dev *edev)
 {
-	return edev->dn;
+	return edev ? edev->dn : NULL;
 }
 
 static inline struct pci_dev *eeh_dev_to_pci_dev(struct eeh_dev *edev)
 {
-	return edev->pdev;
+	return edev ? edev->pdev : NULL;
 }
 
 /*
···
 struct eeh_ops {
 	char *name;
 	int (*init)(void);
+	int (*post_init)(void);
 	void* (*of_probe)(struct device_node *dn, void *flag);
-	void* (*dev_probe)(struct pci_dev *dev, void *flag);
+	int (*dev_probe)(struct pci_dev *dev, void *flag);
 	int (*set_option)(struct eeh_pe *pe, int option);
 	int (*get_pe_addr)(struct eeh_pe *pe);
 	int (*get_state)(struct eeh_pe *pe, int *state);
···
 	int (*configure_bridge)(struct eeh_pe *pe);
 	int (*read_config)(struct device_node *dn, int where, int size, u32 *val);
 	int (*write_config)(struct device_node *dn, int where, int size, u32 val);
+	int (*next_error)(struct eeh_pe **pe);
 };
 
 extern struct eeh_ops *eeh_ops;
 extern int eeh_subsystem_enabled;
-extern struct mutex eeh_mutex;
+extern raw_spinlock_t confirm_error_lock;
 extern int eeh_probe_mode;
 
 #define EEH_PROBE_MODE_DEV	(1<<0)	/* From PCI device	*/
···
 	return (eeh_probe_mode == EEH_PROBE_MODE_DEV);
 }
 
-static inline void eeh_lock(void)
+static inline void eeh_serialize_lock(unsigned long *flags)
 {
-	mutex_lock(&eeh_mutex);
+	raw_spin_lock_irqsave(&confirm_error_lock, *flags);
 }
 
-static inline void eeh_unlock(void)
+static inline void eeh_serialize_unlock(unsigned long flags)
 {
-	mutex_unlock(&eeh_mutex);
+	raw_spin_unlock_irqrestore(&confirm_error_lock, flags);
 }
 
 /*
···
 
 typedef void *(*eeh_traverse_func)(void *data, void *flag);
 int eeh_phb_pe_create(struct pci_controller *phb);
+struct eeh_pe *eeh_phb_pe_get(struct pci_controller *phb);
+struct eeh_pe *eeh_pe_get(struct eeh_dev *edev);
 int eeh_add_to_parent_pe(struct eeh_dev *edev);
 int eeh_rmv_from_parent_pe(struct eeh_dev *edev, int purge_pe);
+void eeh_pe_update_time_stamp(struct eeh_pe *pe);
 void *eeh_pe_dev_traverse(struct eeh_pe *root,
 		eeh_traverse_func fn, void *flag);
 void eeh_pe_restore_bars(struct eeh_pe *pe);
···
 
 void *eeh_dev_init(struct device_node *dn, void *data);
 void eeh_dev_phb_init_dynamic(struct pci_controller *phb);
+int eeh_init(void);
 int __init eeh_ops_register(struct eeh_ops *ops);
 int __exit eeh_ops_unregister(const char *name);
 unsigned long eeh_check_failure(const volatile void __iomem *token,
 				unsigned long val);
 int eeh_dev_check_failure(struct eeh_dev *edev);
-void __init eeh_addr_cache_build(void);
+void eeh_addr_cache_build(void);
 void eeh_add_device_tree_early(struct device_node *);
 void eeh_add_device_tree_late(struct pci_bus *);
 void eeh_add_sysfs_files(struct pci_bus *);
···
 #define EEH_IO_ERROR_VALUE(size)	(~0U >> ((4 - (size)) * 8))
 
 #else /* !CONFIG_EEH */
+
+static inline int eeh_init(void)
+{
+	return 0;
+}
 
 static inline void *eeh_dev_init(struct device_node *dn, void *data)
 {
···
 static inline void eeh_add_sysfs_files(struct pci_bus *bus) { }
 
 static inline void eeh_remove_bus_device(struct pci_dev *dev, int purge_pe) { }
-
-static inline void eeh_lock(void) { }
-static inline void eeh_unlock(void) { }
 
 #define EEH_POSSIBLE_ERROR(val, type) (0)
 #define EEH_IO_ERROR_VALUE(size) (-1UL)

arch/powerpc/include/asm/eeh_event.h

···
 	struct eeh_pe		*pe;	/* EEH PE		*/
 };
 
+int eeh_event_init(void);
 int eeh_send_failure_event(struct eeh_pe *pe);
+void eeh_remove_event(struct eeh_pe *pe);
 void eeh_handle_event(struct eeh_pe *pe);
 
 #endif /* __KERNEL__ */

arch/powerpc/include/asm/exception-64s.h

···
 	/* No guest interrupts come through here */	\
 	SET_SCRATCH0(r13);		/* save r13 */	\
 	EXCEPTION_RELON_PROLOG_PSERIES(PACA_EXGEN, label##_common, \
-				       EXC_STD, KVMTEST_PR, vec)
+				       EXC_STD, NOTEST, vec)
 
 #define STD_RELON_EXCEPTION_PSERIES_OOL(vec, label)		\
 	.globl label##_relon_pSeries;				\
 label##_relon_pSeries:						\
-	EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_PR, vec);	\
+	EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, vec);		\
 	EXCEPTION_RELON_PROLOG_PSERIES_1(label##_common, EXC_STD)
 
 #define STD_RELON_EXCEPTION_HV(loc, vec, label)		\
···
 	/* No guest interrupts come through here */	\
 	SET_SCRATCH0(r13);	/* save r13 */		\
 	EXCEPTION_RELON_PROLOG_PSERIES(PACA_EXGEN, label##_common, \
-				       EXC_HV, KVMTEST, vec)
+				       EXC_HV, NOTEST, vec)
 
 #define STD_RELON_EXCEPTION_HV_OOL(vec, label)			\
 	.globl label##_relon_hv;				\
 label##_relon_hv:						\
-	EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST, vec);		\
+	EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, vec);		\
 	EXCEPTION_RELON_PROLOG_PSERIES_1(label##_common, EXC_HV)
 
 /* This associate vector numbers with bits in paca->irq_happened */

arch/powerpc/include/asm/hugetlb.h

···
 				      unsigned long vmaddr)
 {
 }
-#endif /* CONFIG_HUGETLB_PAGE */
 
+#define hugepd_shift(x) 0
+static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr,
+				    unsigned pdshift)
+{
+	return 0;
+}
+#endif /* CONFIG_HUGETLB_PAGE */
 
 /*
  * FSL Book3E platforms require special gpage handling - the gpages

arch/powerpc/include/asm/iommu.h

···
 	struct iommu_pool large_pool;
 	struct iommu_pool pools[IOMMU_NR_POOLS];
 	unsigned long *it_map;       /* A simple allocation bitmap for now */
+#ifdef CONFIG_IOMMU_API
+	struct iommu_group *it_group;
+#endif
 };
 
 struct scatterlist;
···
  */
 extern struct iommu_table *iommu_init_table(struct iommu_table * tbl,
 					    int nid);
+extern void iommu_register_group(struct iommu_table *tbl,
+				 int pci_domain_number, unsigned long pe_num);
 
 extern int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 			struct scatterlist *sglist, int nelems,
···
 extern void iommu_init_early_dart(void);
 extern void iommu_init_early_pasemi(void);
 
-#ifdef CONFIG_PCI
-extern void pci_iommu_init(void);
-extern void pci_direct_iommu_init(void);
-#else
-static inline void pci_iommu_init(void) { }
-#endif
-
 extern void alloc_dart_table(void);
 #if defined(CONFIG_PPC64) && defined(CONFIG_PM)
 static inline void iommu_save(void)
···
 		ppc_md.iommu_restore();
 }
 #endif
+
+/* The API to support IOMMU operations for VFIO */
+extern int iommu_tce_clear_param_check(struct iommu_table *tbl,
+		unsigned long ioba, unsigned long tce_value,
+		unsigned long npages);
+extern int iommu_tce_put_param_check(struct iommu_table *tbl,
+		unsigned long ioba, unsigned long tce);
+extern int iommu_tce_build(struct iommu_table *tbl, unsigned long entry,
+		unsigned long hwaddr, enum dma_data_direction direction);
+extern unsigned long iommu_clear_tce(struct iommu_table *tbl,
+		unsigned long entry);
+extern int iommu_clear_tces_and_put_pages(struct iommu_table *tbl,
+		unsigned long entry, unsigned long pages);
+extern int iommu_put_tce_user_mode(struct iommu_table *tbl,
+		unsigned long entry, unsigned long tce);
+
+extern void iommu_flush_tce(struct iommu_table *tbl);
+extern int iommu_take_ownership(struct iommu_table *tbl);
+extern void iommu_release_ownership(struct iommu_table *tbl);
+
+extern enum dma_data_direction iommu_tce_direction(unsigned long tce);
 
 #endif /* __KERNEL__ */
 #endif /* _ASM_IOMMU_H */

arch/powerpc/include/asm/kvm_book3s_64.h

···
 }
 
 /*
- * Lock and read a linux PTE.  If it's present and writable, atomically
- * set dirty and referenced bits and return the PTE, otherwise return 0.
+ * If it's present and writable, atomically set dirty and referenced bits and
+ * return the PTE, otherwise return 0. If we find a transparent hugepage
+ * and if it is marked splitting we return 0;
  */
-static inline pte_t kvmppc_read_update_linux_pte(pte_t *p, int writing)
+static inline pte_t kvmppc_read_update_linux_pte(pte_t *ptep, int writing,
+						 unsigned int hugepage)
 {
-	pte_t pte, tmp;
+	pte_t old_pte, new_pte = __pte(0);
 
-	/* wait until _PAGE_BUSY is clear then set it atomically */
-	__asm__ __volatile__ (
-		"1:	ldarx	%0,0,%3\n"
-		"	andi.	%1,%0,%4\n"
-		"	bne-	1b\n"
-		"	ori	%1,%0,%4\n"
-		"	stdcx.	%1,0,%3\n"
-		"	bne-	1b"
-		: "=&r" (pte), "=&r" (tmp), "=m" (*p)
-		: "r" (p), "i" (_PAGE_BUSY)
-		: "cc");
+	while (1) {
+		old_pte = pte_val(*ptep);
+		/*
+		 * wait until _PAGE_BUSY is clear then set it atomically
+		 */
+		if (unlikely(old_pte & _PAGE_BUSY)) {
+			cpu_relax();
+			continue;
+		}
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+		/* If hugepage and is trans splitting return None */
+		if (unlikely(hugepage &&
+			     pmd_trans_splitting(pte_pmd(old_pte))))
+			return __pte(0);
+#endif
+		/* If pte is not present return None */
+		if (unlikely(!(old_pte & _PAGE_PRESENT)))
+			return __pte(0);
 
-	if (pte_present(pte)) {
-		pte = pte_mkyoung(pte);
-		if (writing && pte_write(pte))
-			pte = pte_mkdirty(pte);
+		new_pte = pte_mkyoung(old_pte);
+		if (writing && pte_write(old_pte))
+			new_pte = pte_mkdirty(new_pte);
+
+		if (old_pte == __cmpxchg_u64((unsigned long *)ptep, old_pte,
+					     new_pte))
+			break;
 	}
-
-	*p = pte;	/* clears _PAGE_BUSY */
-
-	return pte;
+	return new_pte;
 }
+
 
 /* Return HPTE cache control bits corresponding to Linux pte bits */
 static inline unsigned long hpte_cache_bits(unsigned long pte_val)

arch/powerpc/include/asm/lppaca.h

···
 
 	u8	reserved6[48];
 	u8	cede_latency_hint;
-	u8	reserved7[7];
+	u8	ebb_regs_in_use;
+	u8	reserved7[6];
 	u8	dtl_enable_mask;	/* Dispatch Trace Log mask */
 	u8	donate_dedicated_cpu;	/* Donate dedicated CPU cycles */
 	u8	fpregs_in_use;

arch/powerpc/include/asm/machdep.h

···
 #ifdef CONFIG_PPC64
 	void            (*hpte_invalidate)(unsigned long slot,
 					   unsigned long vpn,
-					   int psize, int ssize,
-					   int local);
+					   int bpsize, int apsize,
+					   int ssize, int local);
 	long		(*hpte_updatepp)(unsigned long slot, 
 					 unsigned long newpp, 
 					 unsigned long vpn,
-					 int psize, int ssize,
-					 int local);
+					 int bpsize, int apsize,
+					 int ssize, int local);
 	void            (*hpte_updateboltedpp)(unsigned long newpp, 
 					       unsigned long ea,
 					       int psize, int ssize);
···
 	void            (*hpte_removebolted)(unsigned long ea,
 					     int psize, int ssize);
 	void		(*flush_hash_range)(unsigned long number, int local);
+	void		(*hugepage_invalidate)(struct mm_struct *mm,
+					       unsigned char *hpte_slot_array,
+					       unsigned long addr, int psize);
 
 	/* special for kexec, to be called in real mode, linear mapping is
 	 * destroyed as well */

arch/powerpc/include/asm/mmu-hash64.h

···
 int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 		     pte_t *ptep, unsigned long trap, int local, int ssize,
 		     unsigned int shift, unsigned int mmu_psize);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+extern int __hash_page_thp(unsigned long ea, unsigned long access,
+			   unsigned long vsid, pmd_t *pmdp, unsigned long trap,
+			   int local, int ssize, unsigned int psize);
+#else
+static inline int __hash_page_thp(unsigned long ea, unsigned long access,
+				  unsigned long vsid, pmd_t *pmdp,
+				  unsigned long trap, int local,
+				  int ssize, unsigned int psize)
+{
+	BUG();
+	return -1;
+}
+#endif
 extern void hash_failure_debug(unsigned long ea, unsigned long access,
 			       unsigned long vsid, unsigned long trap,
 			       int ssize, int psize, int lpsize,

arch/powerpc/include/asm/mpc5121.h

···
 };
 
 int mpc512x_cs_config(unsigned int cs, u32 val);
-int __init mpc5121_clk_init(void);
 
 #endif /* __ASM_POWERPC_MPC5121_H__ */

arch/powerpc/include/asm/mpic.h

···
 #endif
 };
 
+extern struct bus_type mpic_subsys;
+
 /*
  * MPIC flags (passed to mpic_alloc)
  *
···
 
 #define	MPIC_REGSET_STANDARD		MPIC_REGSET(0)	/* Original MPIC */
 #define	MPIC_REGSET_TSI108		MPIC_REGSET(1)	/* Tsi108/109 PIC */
+
+/* Get the version of primary MPIC */
+extern u32 fsl_mpic_primary_get_version(void);
 
 /* Allocate the controller structure and setup the linux irq descs
  * for the range if interrupts passed in. No HW initialization is

arch/powerpc/include/asm/mpic_timer.h

···
+/*
+ * arch/powerpc/include/asm/mpic_timer.h
+ *
+ * Header file for Mpic Global Timer
+ *
+ * Copyright 2013 Freescale Semiconductor, Inc.
+ *
+ * Author: Wang Dongsheng <[e-mail]>
+ *	   Li Yang <[e-mail]>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#ifndef __MPIC_TIMER__
+#define __MPIC_TIMER__
+
+#include <linux/interrupt.h>
+#include <linux/time.h>
+
+struct mpic_timer {
+	void			*dev;
+	struct cascade_priv	*cascade_handle;
+	unsigned int		num;
+	unsigned int		irq;
+};
+
+#ifdef CONFIG_MPIC_TIMER
+struct mpic_timer *mpic_request_timer(irq_handler_t fn,  void *dev,
+		const struct timeval *time);
+void mpic_start_timer(struct mpic_timer *handle);
+void mpic_stop_timer(struct mpic_timer *handle);
+void mpic_get_remain_time(struct mpic_timer *handle, struct timeval *time);
+void mpic_free_timer(struct mpic_timer *handle);
+#else
+struct mpic_timer *mpic_request_timer(irq_handler_t fn,  void *dev,
+		const struct timeval *time) { return NULL; }
+void mpic_start_timer(struct mpic_timer *handle) { }
+void mpic_stop_timer(struct mpic_timer *handle) { }
+void mpic_get_remain_time(struct mpic_timer *handle, struct timeval *time) { }
+void mpic_free_timer(struct mpic_timer *handle) { }
+#endif
+
+#endif

arch/powerpc/include/asm/opal.h

···
 #define OPAL_SET_SLOT_LED_STATUS		55
 #define OPAL_GET_EPOW_STATUS			56
 #define OPAL_SET_SYSTEM_ATTENTION_LED		57
+#define OPAL_RESERVED1				58
+#define OPAL_RESERVED2				59
+#define OPAL_PCI_NEXT_ERROR			60
+#define OPAL_PCI_EEH_FREEZE_STATUS2		61
+#define OPAL_PCI_POLL				62
 #define OPAL_PCI_MSI_EOI			63
+#define OPAL_PCI_GET_PHB_DIAG_DATA2		64
 
 #ifndef __ASSEMBLY__
 
···
 enum OpalVendorApiTokens {
 	OPAL_START_VENDOR_API_RANGE = 1000, OPAL_END_VENDOR_API_RANGE = 1999
 };
+
 enum OpalFreezeState {
 	OPAL_EEH_STOPPED_NOT_FROZEN = 0,
 	OPAL_EEH_STOPPED_MMIO_FREEZE = 1,
···
 	OPAL_EEH_STOPPED_TEMP_UNAVAIL = 5,
 	OPAL_EEH_STOPPED_PERM_UNAVAIL = 6
 };
+
 enum OpalEehFreezeActionToken {
 	OPAL_EEH_ACTION_CLEAR_FREEZE_MMIO = 1,
 	OPAL_EEH_ACTION_CLEAR_FREEZE_DMA = 2,
 	OPAL_EEH_ACTION_CLEAR_FREEZE_ALL = 3
 };
+
 enum OpalPciStatusToken {
-	OPAL_EEH_PHB_NO_ERROR = 0,
-	OPAL_EEH_PHB_FATAL = 1,
-	OPAL_EEH_PHB_RECOVERABLE = 2,
-	OPAL_EEH_PHB_BUS_ERROR = 3,
-	OPAL_EEH_PCI_NO_DEVSEL = 4,
-	OPAL_EEH_PCI_TA = 5,
-	OPAL_EEH_PCIEX_UR = 6,
-	OPAL_EEH_PCIEX_CA = 7,
-	OPAL_EEH_PCI_MMIO_ERROR = 8,
-	OPAL_EEH_PCI_DMA_ERROR = 9
+	OPAL_EEH_NO_ERROR	= 0,
+	OPAL_EEH_IOC_ERROR	= 1,
+	OPAL_EEH_PHB_ERROR	= 2,
+	OPAL_EEH_PE_ERROR	= 3,
+	OPAL_EEH_PE_MMIO_ERROR	= 4,
+	OPAL_EEH_PE_DMA_ERROR	= 5
 };
+
+enum OpalPciErrorSeverity {
+	OPAL_EEH_SEV_NO_ERROR	= 0,
+	OPAL_EEH_SEV_IOC_DEAD	= 1,
+	OPAL_EEH_SEV_PHB_DEAD	= 2,
+	OPAL_EEH_SEV_PHB_FENCED	= 3,
+	OPAL_EEH_SEV_PE_ER	= 4,
+	OPAL_EEH_SEV_INF	= 5
+};
+
 enum OpalShpcAction {
 	OPAL_SHPC_GET_LINK_STATE = 0,
 	OPAL_SHPC_GET_SLOT_STATE = 1
 };
+
 enum OpalShpcLinkState {
 	OPAL_SHPC_LINK_DOWN = 0,
 	OPAL_SHPC_LINK_UP = 1
 };
+
 enum OpalMmioWindowType {
 	OPAL_M32_WINDOW_TYPE = 1,
 	OPAL_M64_WINDOW_TYPE = 2,
 	OPAL_IO_WINDOW_TYPE = 3
 };
+
 enum OpalShpcSlotState {
 	OPAL_SHPC_DEV_NOT_PRESENT = 0,
 	OPAL_SHPC_DEV_PRESENT = 1
 };
+
 enum OpalExceptionHandler {
 	OPAL_MACHINE_CHECK_HANDLER = 1,
 	OPAL_HYPERVISOR_MAINTENANCE_HANDLER = 2,
 	OPAL_SOFTPATCH_HANDLER = 3
 };
+
 enum OpalPendingState {
-	OPAL_EVENT_OPAL_INTERNAL = 0x1,
-	OPAL_EVENT_NVRAM = 0x2,
-	OPAL_EVENT_RTC = 0x4,
-	OPAL_EVENT_CONSOLE_OUTPUT = 0x8,
-	OPAL_EVENT_CONSOLE_INPUT = 0x10,
-	OPAL_EVENT_ERROR_LOG_AVAIL = 0x20,
-	OPAL_EVENT_ERROR_LOG = 0x40,
-	OPAL_EVENT_EPOW = 0x80,
-	OPAL_EVENT_LED_STATUS = 0x100
+	OPAL_EVENT_OPAL_INTERNAL	= 0x1,
+	OPAL_EVENT_NVRAM		= 0x2,
+	OPAL_EVENT_RTC			= 0x4,
+	OPAL_EVENT_CONSOLE_OUTPUT	= 0x8,
+	OPAL_EVENT_CONSOLE_INPUT	= 0x10,
+	OPAL_EVENT_ERROR_LOG_AVAIL	= 0x20,
+	OPAL_EVENT_ERROR_LOG		= 0x40,
+	OPAL_EVENT_EPOW			= 0x80,
+	OPAL_EVENT_LED_STATUS		= 0x100,
+	OPAL_EVENT_PCI_ERROR		= 0x200
 };
 
 /* Machine check related definitions */
···
 	} u;
 };
 
+enum {
+	OPAL_P7IOC_DIAG_TYPE_NONE	= 0,
+	OPAL_P7IOC_DIAG_TYPE_RGC	= 1,
+	OPAL_P7IOC_DIAG_TYPE_BI		= 2,
+	OPAL_P7IOC_DIAG_TYPE_CI		= 3,
+	OPAL_P7IOC_DIAG_TYPE_MISC	= 4,
+	OPAL_P7IOC_DIAG_TYPE_I2C	= 5,
+	OPAL_P7IOC_DIAG_TYPE_LAST	= 6
+};
+
+struct OpalIoP7IOCErrorData {
+	uint16_t type;
+
+	/* GEM */
+	uint64_t gemXfir;
+	uint64_t gemRfir;
+	uint64_t gemRirqfir;
+	uint64_t gemMask;
+	uint64_t gemRwof;
+
+	/* LEM */
+	uint64_t lemFir;
+	uint64_t lemErrMask;
+	uint64_t lemAction0;
+	uint64_t lemAction1;
+	uint64_t lemWof;
+
+	union {
+		struct OpalIoP7IOCRgcErrorData {
+			uint64_t rgcStatus;		/* 3E1C10 */
+			uint64_t rgcLdcp;		/* 3E1C18 */
+		}rgc;
+		struct OpalIoP7IOCBiErrorData {
+			uint64_t biLdcp0;		/* 3C0100, 3C0118 */
+			uint64_t biLdcp1;		/* 3C0108, 3C0120 */
+			uint64_t biLdcp2;		/* 3C0110, 3C0128 */
+			uint64_t biFenceStatus;		/* 3C0130, 3C0130 */
+
+			uint8_t  biDownbound;		/* BI Downbound or Upbound */
+		}bi;
+		struct OpalIoP7IOCCiErrorData {
+			uint64_t ciPortStatus;		/* 3Dn008 */
+			uint64_t ciPortLdcp;		/* 3Dn010 */
+
+			uint8_t	 ciPort;		/* Index of CI port: 0/1 */
+		}ci;
+	};
+};
+
 /**
  * This structure defines the overlay which will be used to store PHB error
  * data upon request.
  */
 enum {
+	OPAL_PHB_ERROR_DATA_VERSION_1 = 1,
+};
+
+enum {
+	OPAL_PHB_ERROR_DATA_TYPE_P7IOC = 1,
+};
+
+enum {
 	OPAL_P7IOC_NUM_PEST_REGS = 128,
 };
 
+struct OpalIoPhbErrorCommon {
+	uint32_t version;
+	uint32_t ioType;
+	uint32_t len;
+};
+
 struct OpalIoP7IOCPhbErrorData {
+	struct OpalIoPhbErrorCommon common;
+
 	uint32_t brdgCtl;
 
 	// P7IOC utl regs
···
 					uint64_t pci_mem_size);
 int64_t opal_pci_reset(uint64_t phb_id, uint8_t reset_scope, uint8_t assert_state);
 
-int64_t opal_pci_get_hub_diag_data(uint64_t hub_id, void *diag_buffer, uint64_t diag_buffer_len);
-int64_t opal_pci_get_phb_diag_data(uint64_t phb_id, void *diag_buffer, uint64_t diag_buffer_len);
+int64_t opal_pci_get_hub_diag_data(uint64_t hub_id, void *diag_buffer,
+				   uint64_t diag_buffer_len);
+int64_t opal_pci_get_phb_diag_data(uint64_t phb_id, void *diag_buffer,
+				   uint64_t diag_buffer_len);
+int64_t opal_pci_get_phb_diag_data2(uint64_t phb_id, void *diag_buffer,
+				    uint64_t diag_buffer_len);
 int64_t opal_pci_fence_phb(uint64_t phb_id);
 int64_t opal_pci_reinit(uint64_t phb_id, uint8_t reinit_scope);
 int64_t opal_pci_mask_pe_error(uint64_t phb_id, uint16_t pe_number, uint8_t error_type, uint8_t mask_action);
 int64_t opal_set_slot_led_status(uint64_t phb_id, uint64_t slot_id, uint8_t led_type, uint8_t led_action);
 int64_t opal_get_epow_status(uint64_t *status);
 int64_t opal_set_system_attention_led(uint8_t led_action);
+int64_t opal_pci_next_error(uint64_t phb_id, uint64_t *first_frozen_pe,
+			    uint16_t *pci_error_type, uint16_t *severity);
+int64_t opal_pci_poll(uint64_t phb_id);
 
 /* Internal functions */
 extern int early_init_dt_scan_opal(unsigned long node, const char *uname, int depth, void *data);
···
 /* Internal functions */
 extern int early_init_dt_scan_opal(unsigned long node, const char *uname,
 				   int depth, void *data);
+
+extern int opal_notifier_register(struct notifier_block *nb);
+extern void opal_notifier_enable(void);
+extern void opal_notifier_disable(void);
+extern void opal_notifier_update_evt(uint64_t evt_mask, uint64_t evt_val);
 
 extern int opal_get_chars(uint32_t vtermno, char *buf, int count);
 extern int opal_put_chars(uint32_t vtermno, const char *buf, int total_len);

arch/powerpc/include/asm/perf_event_server.h

···
 #define PPMU_HAS_SSLOT		0x00000020 /* Has sampled slot in MMCRA */
 #define PPMU_HAS_SIER		0x00000040 /* Has SIER */
 #define PPMU_BHRB		0x00000080 /* has BHRB feature enabled */
+#define PPMU_EBB		0x00000100 /* supports event based branch */
 
 /*
  * Values for flags to get_alternatives()
···
 #define PPMU_LIMITED_PMC_OK	1	/* can put this on a limited PMC */
 #define PPMU_LIMITED_PMC_REQD	2	/* have to put this on a limited PMC */
 #define PPMU_ONLY_COUNT_RUN	4	/* only counting in run state */
+
+/*
+ * We use the event config bit 63 as a flag to request EBB.
+ */
+#define EVENT_CONFIG_EBB_SHIFT	63
 
 extern int register_power_pmu(struct power_pmu *);
 

arch/powerpc/include/asm/pgalloc-64.h

···
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return kmem_cache_alloc(PGT_CACHE(PMD_INDEX_SIZE),
+	return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX),
 				GFP_KERNEL|__GFP_REPEAT);
 }
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 {
-	kmem_cache_free(PGT_CACHE(PMD_INDEX_SIZE), pmd);
+	kmem_cache_free(PGT_CACHE(PMD_CACHE_INDEX), pmd);
 }
 
 #define __pmd_free_tlb(tlb, pmd, addr)		      \
-	pgtable_free_tlb(tlb, pmd, PMD_INDEX_SIZE)
+	pgtable_free_tlb(tlb, pmd, PMD_CACHE_INDEX)
 #ifndef CONFIG_PPC_64K_PAGES
 #define __pud_free_tlb(tlb, pud, addr)		      \
 	pgtable_free_tlb(tlb, pud, PUD_INDEX_SIZE)

arch/powerpc/include/asm/pgtable-ppc64-64k.h

···
 #define PGDIR_MASK	(~(PGDIR_SIZE-1))
 
 /* Bits to mask out from a PMD to get to the PTE page */
-#define PMD_MASKED_BITS		0x1ff
+/* PMDs point to PTE table fragments which are 4K aligned.  */
+#define PMD_MASKED_BITS		0xfff
 /* Bits to mask out from a PGD/PUD to get to the PMD page */
 #define PUD_MASKED_BITS		0x1ff
 

arch/powerpc/include/asm/pgtable-ppc64.h

···
 #else
 #include <asm/pgtable-ppc64-4k.h>
 #endif
+#include <asm/barrier.h>
 
 #define FIRST_USER_ADDRESS	0
 
···
                 	    PUD_INDEX_SIZE + PGD_INDEX_SIZE + PAGE_SHIFT)
 #define PGTABLE_RANGE (ASM_CONST(1) << PGTABLE_EADDR_SIZE)
 
-
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define PMD_CACHE_INDEX	(PMD_INDEX_SIZE + 1)
+#else
+#define PMD_CACHE_INDEX	PMD_INDEX_SIZE
+#endif
 /*
  * Define the address range of the kernel non-linear virtual area
  */
···
 #define	pmd_present(pmd)	(pmd_val(pmd) != 0)
 #define	pmd_clear(pmdp)		(pmd_val(*(pmdp)) = 0)
 #define pmd_page_vaddr(pmd)	(pmd_val(pmd) & ~PMD_MASKED_BITS)
-#define pmd_page(pmd)		virt_to_page(pmd_page_vaddr(pmd))
+extern struct page *pmd_page(pmd_t pmd);
 
 #define pud_set(pudp, pudval)	(pud_val(*(pudp)) = (pudval))
 #define pud_none(pud)		(!pud_val(pud))
···
 
 void pgtable_cache_add(unsigned shift, void (*ctor)(void *));
 void pgtable_cache_init(void);
-
-/*
- * find_linux_pte returns the address of a linux pte for a given
- * effective address and directory.  If not found, it returns zero.
- */
-static inline pte_t *find_linux_pte(pgd_t *pgdir, unsigned long ea)
-{
-	pgd_t *pg;
-	pud_t *pu;
-	pmd_t *pm;
-	pte_t *pt = NULL;
-
-	pg = pgdir + pgd_index(ea);
-	if (!pgd_none(*pg)) {
-		pu = pud_offset(pg, ea);
-		if (!pud_none(*pu)) {
-			pm = pmd_offset(pu, ea);
-			if (pmd_present(*pm))
-				pt = pte_offset_kernel(pm, ea);
-		}
-	}
-	return pt;
-}
-
-#ifdef CONFIG_HUGETLB_PAGE
-pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
-				 unsigned *shift);
-#else
-static inline pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
-					       unsigned *shift)
-{
-	if (shift)
-		*shift = 0;
-	return find_linux_pte(pgdir, ea);
-}
-#endif /* !CONFIG_HUGETLB_PAGE */
-
 #endif /* __ASSEMBLY__ */
 
+/*
+ * THP pages can't be special. So use the _PAGE_SPECIAL
+ */
+#define _PAGE_SPLITTING _PAGE_SPECIAL
+
+/*
+ * We need to differentiate between explicit huge page and THP huge
+ * page, since THP huge page also need to track real subpage details
+ */
+#define _PAGE_THP_HUGE  _PAGE_4K_PFN
+
+/*
+ * set of bits not changed in pmd_modify.
+ */
+#define _HPAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS |		\
+			 _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_SPLITTING | \
+			 _PAGE_THP_HUGE)
+
+#ifndef __ASSEMBLY__
+/*
+ * The linux hugepage PMD now include the pmd entries followed by the address
+ * to the stashed pgtable_t. The stashed pgtable_t contains the hpte bits.
+ * [ 1 bit secondary | 3 bit hidx | 1 bit valid | 000]. We use one byte per
+ * each HPTE entry. With 16MB hugepage and 64K HPTE we need 256 entries and
+ * with 4K HPTE we need 4096 entries. Both will fit in a 4K pgtable_t.
+ *
+ * The last three bits are intentionally left to zero. This memory location
+ * are also used as normal page PTE pointers. So if we have any pointers
+ * left around while we collapse a hugepage, we need to make sure
+ * _PAGE_PRESENT and _PAGE_FILE bits of that are zero when we look at them
+ */
+static inline unsigned int hpte_valid(unsigned char *hpte_slot_array, int index)
+{
+	return (hpte_slot_array[index] >> 3) & 0x1;
+}
+
+static inline unsigned int hpte_hash_index(unsigned char *hpte_slot_array,
+					   int index)
+{
+	return hpte_slot_array[index] >> 4;
+}
+
+static inline void mark_hpte_slot_valid(unsigned char *hpte_slot_array,
+					unsigned int index, unsigned int hidx)
+{
+	hpte_slot_array[index] = hidx << 4 | 0x1 << 3;
+}
+
+static inline char *get_hpte_slot_array(pmd_t *pmdp)
+{
+	/*
+	 * The hpte hindex is stored in the pgtable whose address is in the
+	 * second half of the PMD
+	 *
+	 * Order this load with the test for pmd_trans_huge in the caller
+	 */
+	smp_rmb();
+	return *(char **)(pmdp + PTRS_PER_PMD);
+
+
+}
+
+extern void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
+				   pmd_t *pmdp);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+extern pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot);
+extern pmd_t mk_pmd(struct page *page, pgprot_t pgprot);
+extern pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot);
+extern void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+		       pmd_t *pmdp, pmd_t pmd);
+extern void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
+				 pmd_t *pmd);
+
+static inline int pmd_trans_huge(pmd_t pmd)
+{
+	/*
+	 * leaf pte for huge page, bottom two bits != 00
+	 */
+	return (pmd_val(pmd) & 0x3) && (pmd_val(pmd) & _PAGE_THP_HUGE);
+}
+
+static inline int pmd_large(pmd_t pmd)
+{
+	/*
+	 * leaf pte for huge page, bottom two bits != 00
+	 */
+	if (pmd_trans_huge(pmd))
+		return pmd_val(pmd) & _PAGE_PRESENT;
+	return 0;
+}
+
+static inline int pmd_trans_splitting(pmd_t pmd)
+{
+	if (pmd_trans_huge(pmd))
+		return pmd_val(pmd) & _PAGE_SPLITTING;
+	return 0;
+}
+
+extern int has_transparent_hugepage(void);
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+static inline pte_t pmd_pte(pmd_t pmd)
+{
+	return __pte(pmd_val(pmd));
+}
+
+static inline pmd_t pte_pmd(pte_t pte)
+{
+	return __pmd(pte_val(pte));
+}
+
+static inline pte_t *pmdp_ptep(pmd_t *pmd)
+{
+	return (pte_t *)pmd;
+}
+
+#define pmd_pfn(pmd)		pte_pfn(pmd_pte(pmd))
+#define pmd_young(pmd)		pte_young(pmd_pte(pmd))
+#define pmd_mkold(pmd)		pte_pmd(pte_mkold(pmd_pte(pmd)))
+#define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
+#define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
+#define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
+#define pmd_mkwrite(pmd)	pte_pmd(pte_mkwrite(pmd_pte(pmd)))
+
+#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write(pmd)		pte_write(pmd_pte(pmd))
+
+static inline pmd_t pmd_mkhuge(pmd_t pmd)
+{
+	/* Do nothing, mk_pmd() does this part.  */
+	return pmd;
+}
+
+static inline pmd_t pmd_mknotpresent(pmd_t pmd)
+{
+	pmd_val(pmd) &= ~_PAGE_PRESENT;
+	return pmd;
+}
+
+static inline pmd_t pmd_mksplitting(pmd_t pmd)
+{
+	pmd_val(pmd) |= _PAGE_SPLITTING;
+	return pmd;
+}
+
+#define __HAVE_ARCH_PMD_SAME
+static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
+{
+	return (((pmd_val(pmd_a) ^ pmd_val(pmd_b)) & ~_PAGE_HPTEFLAGS) == 0);
+}
+
+#define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
+extern int pmdp_set_access_flags(struct vm_area_struct *vma,
+				 unsigned long address, pmd_t *pmdp,
+				 pmd_t entry, int dirty);
+
+extern unsigned long pmd_hugepage_update(struct mm_struct *mm,
+					 unsigned long addr,
+					 pmd_t *pmdp, unsigned long clr);
+
+static inline int __pmdp_test_and_clear_young(struct mm_struct *mm,
+					      unsigned long addr, pmd_t *pmdp)
+{
+	unsigned long old;
+
+	if ((pmd_val(*pmdp) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0)
+		return 0;
+	old = pmd_hugepage_update(mm, addr, pmdp, _PAGE_ACCESSED);
+	return ((old & _PAGE_ACCESSED) != 0);
+}
+
+#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
+extern int pmdp_test_and_clear_young(struct vm_area_struct *vma,
+				     unsigned long address, pmd_t *pmdp);
+#define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
+extern int pmdp_clear_flush_young(struct vm_area_struct *vma,
+				  unsigned long address, pmd_t *pmdp);
+
+#define __HAVE_ARCH_PMDP_GET_AND_CLEAR
+extern pmd_t pmdp_get_and_clear(struct mm_struct *mm,
+				unsigned long addr, pmd_t *pmdp);
+
+#define __HAVE_ARCH_PMDP_CLEAR_FLUSH
+extern pmd_t pmdp_clear_flush(struct vm_area_struct *vma, unsigned long address,
+			      pmd_t *pmdp);
+
+#define __HAVE_ARCH_PMDP_SET_WRPROTECT
+static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr,
+				      pmd_t *pmdp)
+{
+
+	if ((pmd_val(*pmdp) & _PAGE_RW) == 0)
+		return;
+
+	pmd_hugepage_update(mm, addr, pmdp, _PAGE_RW);
+}
+
+#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH
+extern void pmdp_splitting_flush(struct vm_area_struct *vma,
+				 unsigned long address, pmd_t *pmdp);
+
+#define __HAVE_ARCH_PGTABLE_DEPOSIT
+extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+				       pgtable_t pgtable);
+#define __HAVE_ARCH_PGTABLE_WITHDRAW
+extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
+
+#define __HAVE_ARCH_PMDP_INVALIDATE
+extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
+			    pmd_t *pmdp);
+#endif /* __ASSEMBLY__ */
 #endif /* _ASM_POWERPC_PGTABLE_PPC64_H_ */

arch/powerpc/include/asm/pgtable.h

···
 
 extern int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
 		       unsigned long end, int write, struct page **pages, int *nr);
+#ifndef CONFIG_TRANSPARENT_HUGEPAGE
+#define pmd_large(pmd)		0
+#define has_transparent_hugepage() 0
+#endif
+pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
+				 unsigned *shift);
 #endif /* __ASSEMBLY__ */
 
 #endif /* __KERNEL__ */

arch/powerpc/include/asm/probes.h

···
 #define is_trap(instr)		(IS_TW(instr) || IS_TWI(instr))
 #endif /* CONFIG_PPC64 */
 
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+#define MSR_SINGLESTEP	(MSR_DE)
+#else
+#define MSR_SINGLESTEP	(MSR_SE)
+#endif
+
+/* Enable single stepping for the current task */
+static inline void enable_single_step(struct pt_regs *regs)
+{
+	regs->msr |= MSR_SINGLESTEP;
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+	/*
+	 * We turn off Critical Input Exception(CE) to ensure that the single
+	 * step will be for the instruction we have the probe on; if we don't,
+	 * it is possible we'd get the single step reported for CE.
+	 */
+	regs->msr &= ~MSR_CE;
+	mtspr(SPRN_DBCR0, mfspr(SPRN_DBCR0) | DBCR0_IC | DBCR0_IDM);
+#ifdef CONFIG_PPC_47x
+	isync();
+#endif
+#endif
+}
+
+
 #endif /* __KERNEL__ */
 #endif	/* _ASM_POWERPC_PROBES_H */

arch/powerpc/include/asm/processor.h

···
 	 * The following help to manage the use of Debug Control Registers
 	 * om the BookE platforms.
 	 */
-	unsigned long	dbcr0;
-	unsigned long	dbcr1;
+	uint32_t	dbcr0;
+	uint32_t	dbcr1;
 #ifdef CONFIG_BOOKE
-	unsigned long	dbcr2;
+	uint32_t	dbcr2;
 #endif
 	/*
 	 * The stored value of the DBSR register will be the value at the
···
 	 * user (will never be written to) and has value while helping to
 	 * describe the reason for the last debug trap.  Torez
 	 */
-	unsigned long	dbsr;
+	uint32_t	dbsr;
 	/*
 	 * The following will contain addresses used by debug applications
 	 * to help trace and trap on particular address locations.
···
 #endif
 #endif
 	/* FP and VSX 0-31 register set */
-	double		fpr[32][TS_FPRWIDTH];
+	double		fpr[32][TS_FPRWIDTH] __attribute__((aligned(16)));
 	struct {
 
 		unsigned int pad;
···
 	unsigned long	siar;
 	unsigned long	sdar;
 	unsigned long	sier;
-	unsigned long	mmcr0;
 	unsigned long	mmcr2;
-	unsigned long	mmcra;
+	unsigned 	mmcr0;
+	unsigned 	used_ebb;
 #endif
 };
 
···
 
 #define spin_lock_prefetch(x)	prefetchw(x)
 
-#ifdef CONFIG_PPC64
 #define HAVE_ARCH_PICK_MMAP_LAYOUT
-#endif
 
 #ifdef CONFIG_PPC64
 static inline unsigned long get_clean_sp(unsigned long sp, int is_32)

arch/powerpc/include/asm/reg.h

···
 #define   MMCR0_PMXE	0x04000000UL /* performance monitor exception enable */
 #define   MMCR0_FCECE	0x02000000UL /* freeze ctrs on enabled cond or event */
 #define   MMCR0_TBEE	0x00400000UL /* time base exception enable */
+#define   MMCR0_EBE	0x00100000UL /* Event based branch enable */
+#define   MMCR0_PMCC	0x000c0000UL /* PMC control */
+#define   MMCR0_PMCC_U6	0x00080000UL /* PMC1-6 are R/W by user (PR) */
 #define   MMCR0_PMC1CE	0x00008000UL /* PMC1 count enable*/
 #define   MMCR0_PMCjCE	0x00004000UL /* PMCj count enable*/
 #define   MMCR0_TRIGGER	0x00002000UL /* TRIGGER enable */
 #define   MMCR0_PMAO	0x00000080UL /* performance monitor alert has occurred, set to 0 after handling exception */
 #define   MMCR0_SHRFC	0x00000040UL /* SHRre freeze conditions between threads */
+#define   MMCR0_FC56	0x00000010UL /* freeze counters 5 and 6 */
 #define   MMCR0_FCTI	0x00000008UL /* freeze counters in tags inactive mode */
 #define   MMCR0_FCTA	0x00000004UL /* freeze counters in tags active mode */
 #define   MMCR0_FCWAIT	0x00000002UL /* freeze counter in WAIT state */
···
 #define   SIER_SIHV		0x1000000	/* Sampled MSR_HV */
 #define   SIER_SIAR_VALID	0x0400000	/* SIAR contents valid */
 #define   SIER_SDAR_VALID	0x0200000	/* SDAR contents valid */
+
+/* When EBB is enabled, some of MMCR0/MMCR2/SIER are user accessible */
+#define MMCR0_USER_MASK	(MMCR0_FC | MMCR0_PMXE | MMCR0_PMAO)
+#define MMCR2_USER_MASK	0x4020100804020000UL /* (FC1P|FC2P|FC3P|FC4P|FC5P|FC6P) */
+#define SIER_USER_MASK	0x7fffffUL
 
 #define SPRN_PA6T_MMCR0 795
 #define   PA6T_MMCR0_EN0	0x0000000000000001UL

arch/powerpc/include/asm/rtas.h

···
 			(devfn << 8) | (reg & 0xff);
 }
 
-extern void __cpuinit rtas_give_timebase(void);
-extern void __cpuinit rtas_take_timebase(void);
+extern void rtas_give_timebase(void);
+extern void rtas_take_timebase(void);
 
 #ifdef CONFIG_PPC_RTAS
 static inline int page_is_rtas_user_buf(unsigned long pfn)

arch/powerpc/include/asm/switch_to.h

···
 }
 #endif
 
+static inline void clear_task_ebb(struct task_struct *t)
+{
+#ifdef CONFIG_PPC_BOOK3S_64
+    /* EBB perf events are not inherited, so clear all EBB state. */
+    t->thread.bescr = 0;
+    t->thread.mmcr2 = 0;
+    t->thread.mmcr0 = 0;
+    t->thread.siar = 0;
+    t->thread.sdar = 0;
+    t->thread.sier = 0;
+    t->thread.used_ebb = 0;
+#endif
+}
+
 #endif /* _ASM_POWERPC_SWITCH_TO_H */

arch/powerpc/include/asm/tlbflush.h

···
 /* Private function for use by PCI IO mapping code */
 extern void __flush_hash_table_range(struct mm_struct *mm, unsigned long start,
 				     unsigned long end);
-
+extern void flush_tlb_pmd_range(struct mm_struct *mm, pmd_t *pmd,
+				unsigned long addr);
 #else
 #error Unsupported MMU type
 #endif

arch/powerpc/include/asm/vdso.h

···
 extern unsigned long vdso32_sigtramp;
 extern unsigned long vdso32_rt_sigtramp;
 
-int __cpuinit vdso_getcpu_init(void);
+int vdso_getcpu_init(void);
 
 #else /* __ASSEMBLY__ */
 

arch/powerpc/kernel/Makefile

···
 obj-$(CONFIG_LPARCFG)		+= lparcfg.o
 obj-$(CONFIG_IBMVIO)		+= vio.o
 obj-$(CONFIG_IBMEBUS)           += ibmebus.o
+obj-$(CONFIG_EEH)              += eeh.o eeh_pe.o eeh_dev.o eeh_cache.o \
+				  eeh_driver.o eeh_event.o eeh_sysfs.o
 obj-$(CONFIG_GENERIC_TBSYNC)	+= smp-tbsync.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 obj-$(CONFIG_FA_DUMP)		+= fadump.o
···
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 obj-$(CONFIG_SWIOTLB)		+= dma-swiotlb.o
 
-pci64-$(CONFIG_PPC64)		+= pci_dn.o isa-bridge.o
+pci64-$(CONFIG_PPC64)		+= pci_dn.o pci-hotplug.o isa-bridge.o
 obj-$(CONFIG_PCI)		+= pci_$(CONFIG_WORD_SIZE).o $(pci64-y) \
 				   pci-common.o pci_of_scan.o
 obj-$(CONFIG_PCI_MSI)		+= msi.o

arch/powerpc/kernel/asm-offsets.c

···
 	DEFINE(KSP_VSID, offsetof(struct thread_struct, ksp_vsid));
 #else /* CONFIG_PPC64 */
 	DEFINE(PGDIR, offsetof(struct thread_struct, pgdir));
-#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
-	DEFINE(THREAD_DBCR0, offsetof(struct thread_struct, dbcr0));
-#endif
 #ifdef CONFIG_SPE
 	DEFINE(THREAD_EVR0, offsetof(struct thread_struct, evr[0]));
 	DEFINE(THREAD_ACC, offsetof(struct thread_struct, acc));
···
 	DEFINE(THREAD_USED_SPE, offsetof(struct thread_struct, used_spe));
 #endif /* CONFIG_SPE */
 #endif /* CONFIG_PPC64 */
+#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
+	DEFINE(THREAD_DBCR0, offsetof(struct thread_struct, dbcr0));
+#endif
 #ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	DEFINE(THREAD_KVM_SVCPU, offsetof(struct thread_struct, kvm_shadow_vcpu));
 #endif
···
 	DEFINE(THREAD_SIER, offsetof(struct thread_struct, sier));
 	DEFINE(THREAD_MMCR0, offsetof(struct thread_struct, mmcr0));
 	DEFINE(THREAD_MMCR2, offsetof(struct thread_struct, mmcr2));
-	DEFINE(THREAD_MMCRA, offsetof(struct thread_struct, mmcra));
 #endif
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	DEFINE(PACATMSCRATCH, offsetof(struct paca_struct, tm_scratch));

arch/powerpc/kernel/cacheinfo.c

···
 	return cache_type_info[cache->type].name;
 }
 
-static void __cpuinit cache_init(struct cache *cache, int type, int level, struct device_node *ofnode)
+static void cache_init(struct cache *cache, int type, int level,
+		       struct device_node *ofnode)
 {
 	cache->type = type;
 	cache->level = level;
···
 	list_add(&cache->list, &cache_list);
 }
 
-static struct cache *__cpuinit new_cache(int type, int level, struct device_node *ofnode)
+static struct cache *new_cache(int type, int level, struct device_node *ofnode)
 {
 	struct cache *cache;
 
···
 	return of_get_property(np, "cache-unified", NULL);
 }
 
-static struct cache *__cpuinit cache_do_one_devnode_unified(struct device_node *node, int level)
+static struct cache *cache_do_one_devnode_unified(struct device_node *node,
+						  int level)
 {
 	struct cache *cache;
 
···
 	return cache;
 }
 
-static struct cache *__cpuinit cache_do_one_devnode_split(struct device_node *node, int level)
+static struct cache *cache_do_one_devnode_split(struct device_node *node,
+						int level)
 {
 	struct cache *dcache, *icache;
 
···
 	return NULL;
 }
 
-static struct cache *__cpuinit cache_do_one_devnode(struct device_node *node, int level)
+static struct cache *cache_do_one_devnode(struct device_node *node, int level)
 {
 	struct cache *cache;
 
···
 	return cache;
 }
 
-static struct cache *__cpuinit cache_lookup_or_instantiate(struct device_node *node, int level)
+static struct cache *cache_lookup_or_instantiate(struct device_node *node,
+						 int level)
 {
 	struct cache *cache;
 
···
 	return cache;
 }
 
-static void __cpuinit link_cache_lists(struct cache *smaller, struct cache *bigger)
+static void link_cache_lists(struct cache *smaller, struct cache *bigger)
 {
 	while (smaller->next_local) {
 		if (smaller->next_local == bigger)
···
 	smaller->next_local = bigger;
 }
 
-static void __cpuinit do_subsidiary_caches_debugcheck(struct cache *cache)
+static void do_subsidiary_caches_debugcheck(struct cache *cache)
 {
 	WARN_ON_ONCE(cache->level != 1);
 	WARN_ON_ONCE(strcmp(cache->ofnode->type, "cpu"));
 }
 
-static void __cpuinit do_subsidiary_caches(struct cache *cache)
+static void do_subsidiary_caches(struct cache *cache)
 {
 	struct device_node *subcache_node;
 	int level = cache->level;
···
 	}
 }
 
-static struct cache *__cpuinit cache_chain_instantiate(unsigned int cpu_id)
+static struct cache *cache_chain_instantiate(unsigned int cpu_id)
 {
 	struct device_node *cpu_node;
 	struct cache *cpu_cache = NULL;
···
 	return cpu_cache;
 }
 
-static struct cache_dir *__cpuinit cacheinfo_create_cache_dir(unsigned int cpu_id)
+static struct cache_dir *cacheinfo_create_cache_dir(unsigned int cpu_id)
 {
 	struct cache_dir *cache_dir;
 	struct device *dev;
···
 	.default_attrs = cache_index_default_attrs,
 };
 
-static void __cpuinit cacheinfo_create_index_opt_attrs(struct cache_index_dir *dir)
+static void cacheinfo_create_index_opt_attrs(struct cache_index_dir *dir)
 {
 	const char *cache_name;
 	const char *cache_type;
···
 	kfree(buf);
 }
 
-static void __cpuinit cacheinfo_create_index_dir(struct cache *cache, int index, struct cache_dir *cache_dir)
+static void cacheinfo_create_index_dir(struct cache *cache, int index,
+				       struct cache_dir *cache_dir)
 {
 	struct cache_index_dir *index_dir;
 	int rc;
···
 	kfree(index_dir);
 }
 
-static void __cpuinit cacheinfo_sysfs_populate(unsigned int cpu_id, struct cache *cache_list)
+static void cacheinfo_sysfs_populate(unsigned int cpu_id,
+				     struct cache *cache_list)
 {
 	struct cache_dir *cache_dir;
 	struct cache *cache;
···
 	}
 }
 
-void __cpuinit cacheinfo_cpu_online(unsigned int cpu_id)
+void cacheinfo_cpu_online(unsigned int cpu_id)
 {
 	struct cache *cache;
 

arch/powerpc/kernel/entry_64.S

···
 
 	CURRENT_THREAD_INFO(r9, r1)
 	ld	r3,_MSR(r1)
+#ifdef CONFIG_PPC_BOOK3E
+	ld	r10,PACACURRENT(r13)
+#endif /* CONFIG_PPC_BOOK3E */
 	ld	r4,TI_FLAGS(r9)
 	andi.	r3,r3,MSR_PR
 	beq	resume_kernel
+#ifdef CONFIG_PPC_BOOK3E
+	lwz	r3,(THREAD+THREAD_DBCR0)(r10)
+#endif /* CONFIG_PPC_BOOK3E */
 
 	/* Check current_thread_info()->flags */
 	andi.	r0,r4,_TIF_USER_WORK_MASK
+#ifdef CONFIG_PPC_BOOK3E
+	bne	1f
+	/*
+	 * Check to see if the dbcr0 register is set up to debug.
+	 * Use the internal debug mode bit to do this.
+	 */
+	andis.	r0,r3,DBCR0_IDM@h
 	beq	restore
-
-	andi.	r0,r4,_TIF_NEED_RESCHED
-	beq	1f
+	mfmsr	r0
+	rlwinm	r0,r0,0,~MSR_DE	/* Clear MSR.DE */
+	mtmsr	r0
+	mtspr	SPRN_DBCR0,r3
+	li	r10, -1
+	mtspr	SPRN_DBSR,r10
+	b	restore
+#else
+	beq	restore
+#endif
+1:	andi.	r0,r4,_TIF_NEED_RESCHED
+	beq	2f
 	bl	.restore_interrupts
 	SCHEDULE_USER
 	b	.ret_from_except_lite
 
-1:	bl	.save_nvgprs
+2:	bl	.save_nvgprs
 	bl	.restore_interrupts
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	.do_notify_resume

arch/powerpc/kernel/exceptions-64s.S

···
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	vsx_unavailable_pSeries
 
+facility_unavailable_trampoline:
 	. = 0xf60
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
-	b	tm_unavailable_pSeries
+	b	facility_unavailable_pSeries
+
+hv_facility_unavailable_trampoline:
+	. = 0xf80
+	SET_SCRATCH0(r13)
+	EXCEPTION_PROLOG_0(PACA_EXGEN)
+	b	facility_unavailable_hv
 
 #ifdef CONFIG_CBE_RAS
 	STD_EXCEPTION_HV(0x1200, 0x1202, cbe_system_error)
···
 	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf20)
 	STD_EXCEPTION_PSERIES_OOL(0xf40, vsx_unavailable)
 	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf40)
-	STD_EXCEPTION_PSERIES_OOL(0xf60, tm_unavailable)
+	STD_EXCEPTION_PSERIES_OOL(0xf60, facility_unavailable)
 	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf60)
+	STD_EXCEPTION_HV_OOL(0xf82, facility_unavailable)
+	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xf82)
 
 /*
  * An interrupt came in while soft-disabled. We set paca->irq_happened, then:
···
 	STD_RELON_EXCEPTION_PSERIES(0x4d00, 0xd00, single_step)
 
 	. = 0x4e00
-	SET_SCRATCH0(r13)
-	EXCEPTION_PROLOG_0(PACA_EXGEN)
-	b	h_data_storage_relon_hv
+	b	.	/* Can't happen, see v2.07 Book III-S section 6.5 */
 
 	. = 0x4e20
-	SET_SCRATCH0(r13)
-	EXCEPTION_PROLOG_0(PACA_EXGEN)
-	b	h_instr_storage_relon_hv
+	b	.	/* Can't happen, see v2.07 Book III-S section 6.5 */
 
 	. = 0x4e40
 	SET_SCRATCH0(r13)
···
 	b	emulation_assist_relon_hv
 
 	. = 0x4e60
-	SET_SCRATCH0(r13)
-	EXCEPTION_PROLOG_0(PACA_EXGEN)
-	b	hmi_exception_relon_hv
+	b	.	/* Can't happen, see v2.07 Book III-S section 6.5 */
 
 	. = 0x4e80
 	SET_SCRATCH0(r13)
···
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	vsx_unavailable_relon_pSeries
 
-tm_unavailable_relon_pSeries_1:
+facility_unavailable_relon_trampoline:
 	. = 0x4f60
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
-	b	tm_unavailable_relon_pSeries
+	b	facility_unavailable_relon_pSeries
+
+hv_facility_unavailable_relon_trampoline:
+	. = 0x4f80
+	SET_SCRATCH0(r13)
+	EXCEPTION_PROLOG_0(PACA_EXGEN)
+	b	facility_unavailable_relon_hv
 
 	STD_RELON_EXCEPTION_PSERIES(0x5300, 0x1300, instruction_breakpoint)
 #ifdef CONFIG_PPC_DENORMALISATION
···
 	bl	.vsx_unavailable_exception
 	b	.ret_from_except
 
-	.align	7
-	.globl tm_unavailable_common
-tm_unavailable_common:
-	EXCEPTION_PROLOG_COMMON(0xf60, PACA_EXGEN)
-	bl	.save_nvgprs
-	DISABLE_INTS
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.tm_unavailable_exception
-	b	.ret_from_except
+	STD_EXCEPTION_COMMON(0xf60, facility_unavailable, .facility_unavailable_exception)
 
 	.align	7
 	.globl	__end_handlers
 __end_handlers:
 
 	/* Equivalents to the above handlers for relocation-on interrupt vectors */
-	STD_RELON_EXCEPTION_HV_OOL(0xe00, h_data_storage)
-	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe00)
-	STD_RELON_EXCEPTION_HV_OOL(0xe20, h_instr_storage)
-	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe20)
 	STD_RELON_EXCEPTION_HV_OOL(0xe40, emulation_assist)
-	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe40)
-	STD_RELON_EXCEPTION_HV_OOL(0xe60, hmi_exception)
-	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe60)
 	MASKABLE_RELON_EXCEPTION_HV_OOL(0xe80, h_doorbell)
-	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe80)
 
 	STD_RELON_EXCEPTION_PSERIES_OOL(0xf00, performance_monitor)
 	STD_RELON_EXCEPTION_PSERIES_OOL(0xf20, altivec_unavailable)
 	STD_RELON_EXCEPTION_PSERIES_OOL(0xf40, vsx_unavailable)
-	STD_RELON_EXCEPTION_PSERIES_OOL(0xf60, tm_unavailable)
+	STD_RELON_EXCEPTION_PSERIES_OOL(0xf60, facility_unavailable)
+	STD_RELON_EXCEPTION_HV_OOL(0xf80, facility_unavailable)
 
 #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
 /*

arch/powerpc/kernel/hw_breakpoint.c

···
 		length_max = 512 ; /* 64 doublewords */
 		/* DAWR region can't cross 512 boundary */
 		if ((bp->attr.bp_addr >> 10) != 
-		    ((bp->attr.bp_addr + bp->attr.bp_len) >> 10))
+		    ((bp->attr.bp_addr + bp->attr.bp_len - 1) >> 10))
 			return -EINVAL;
 	}
 	if (info->len >
···
 	 * we still need to single-step the instruction, but we don't
 	 * generate an event.
 	 */
+	info->type &= ~HW_BRK_TYPE_EXTRANEOUS_IRQ;
 	if (!((bp->attr.bp_addr <= dar) &&
 	      (dar - bp->attr.bp_addr < bp->attr.bp_len)))
 		info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ;

arch/powerpc/kernel/idle.c

···
 /*
  * Register the sysctl to set/clear powersave_nap.
  */
-static ctl_table powersave_nap_ctl_table[]={
+static struct ctl_table powersave_nap_ctl_table[] = {
 	{
 		.procname	= "powersave-nap",
 		.data		= &powersave_nap,
···
 	},
 	{}
 };
-static ctl_table powersave_nap_sysctl_root[] = {
+static struct ctl_table powersave_nap_sysctl_root[] = {
 	{
 		.procname	= "kernel",
 		.mode		= 0555,

arch/powerpc/kernel/io-workarounds.c

···
 
 struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
 {
+	unsigned hugepage_shift;
 	struct iowa_bus *bus;
 	int token;
 
···
 		if (vaddr < PHB_IO_BASE || vaddr >= PHB_IO_END)
 			return NULL;
 
-		ptep = find_linux_pte(init_mm.pgd, vaddr);
+		ptep = find_linux_pte_or_hugepte(init_mm.pgd, vaddr,
+						 &hugepage_shift);
 		if (ptep == NULL)
 			paddr = 0;
-		else
+		else {
+			/*
+			 * we don't have hugepages backing iomem
+			 */
+			WARN_ON(hugepage_shift);
 			paddr = pte_pfn(*ptep) << PAGE_SHIFT;
+		}
 		bus = iowa_pci_find(vaddr, paddr);
 
 		if (bus == NULL)

arch/powerpc/kernel/iommu.c

···
 #include <linux/hash.h>
 #include <linux/fault-inject.h>
 #include <linux/pci.h>
+#include <linux/iommu.h>
+#include <linux/sched.h>
 #include <asm/io.h>
 #include <asm/prom.h>
 #include <asm/iommu.h>
···
 #include <asm/kdump.h>
 #include <asm/fadump.h>
 #include <asm/vio.h>
+#include <asm/tce.h>
 
 #define DBG(...)
 
···
 	if (tbl->it_offset == 0)
 		clear_bit(0, tbl->it_map);
 
+#ifdef CONFIG_IOMMU_API
+	if (tbl->it_group) {
+		iommu_group_put(tbl->it_group);
+		BUG_ON(tbl->it_group);
+	}
+#endif
+
 	/* verify that table contains no entries */
 	if (!bitmap_empty(tbl->it_map, tbl->it_size))
 		pr_warn("%s: Unexpected TCEs for %s\n", __func__, node_name);
···
 		free_pages((unsigned long)vaddr, get_order(size));
 	}
 }
+
+#ifdef CONFIG_IOMMU_API
+/*
+ * SPAPR TCE API
+ */
+static void group_release(void *iommu_data)
+{
+	struct iommu_table *tbl = iommu_data;
+	tbl->it_group = NULL;
+}
+
+void iommu_register_group(struct iommu_table *tbl,
+		int pci_domain_number, unsigned long pe_num)
+{
+	struct iommu_group *grp;
+	char *name;
+
+	grp = iommu_group_alloc();
+	if (IS_ERR(grp)) {
+		pr_warn("powerpc iommu api: cannot create new group, err=%ld\n",
+				PTR_ERR(grp));
+		return;
+	}
+	tbl->it_group = grp;
+	iommu_group_set_iommudata(grp, tbl, group_release);
+	name = kasprintf(GFP_KERNEL, "domain%d-pe%lx",
+			pci_domain_number, pe_num);
+	if (!name)
+		return;
+	iommu_group_set_name(grp, name);
+	kfree(name);
+}
+
+enum dma_data_direction iommu_tce_direction(unsigned long tce)
+{
+	if ((tce & TCE_PCI_READ) && (tce & TCE_PCI_WRITE))
+		return DMA_BIDIRECTIONAL;
+	else if (tce & TCE_PCI_READ)
+		return DMA_TO_DEVICE;
+	else if (tce & TCE_PCI_WRITE)
+		return DMA_FROM_DEVICE;
+	else
+		return DMA_NONE;
+}
+EXPORT_SYMBOL_GPL(iommu_tce_direction);
+
+void iommu_flush_tce(struct iommu_table *tbl)
+{
+	/* Flush/invalidate TLB caches if necessary */
+	if (ppc_md.tce_flush)
+		ppc_md.tce_flush(tbl);
+
+	/* Make sure updates are seen by hardware */
+	mb();
+}
+EXPORT_SYMBOL_GPL(iommu_flush_tce);
+
+int iommu_tce_clear_param_check(struct iommu_table *tbl,
+		unsigned long ioba, unsigned long tce_value,
+		unsigned long npages)
+{
+	/* ppc_md.tce_free() does not support any value but 0 */
+	if (tce_value)
+		return -EINVAL;
+
+	if (ioba & ~IOMMU_PAGE_MASK)
+		return -EINVAL;
+
+	ioba >>= IOMMU_PAGE_SHIFT;
+	if (ioba < tbl->it_offset)
+		return -EINVAL;
+
+	if ((ioba + npages) > (tbl->it_offset + tbl->it_size))
+		return -EINVAL;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iommu_tce_clear_param_check);
+
+int iommu_tce_put_param_check(struct iommu_table *tbl,
+		unsigned long ioba, unsigned long tce)
+{
+	if (!(tce & (TCE_PCI_WRITE | TCE_PCI_READ)))
+		return -EINVAL;
+
+	if (tce & ~(IOMMU_PAGE_MASK | TCE_PCI_WRITE | TCE_PCI_READ))
+		return -EINVAL;
+
+	if (ioba & ~IOMMU_PAGE_MASK)
+		return -EINVAL;
+
+	ioba >>= IOMMU_PAGE_SHIFT;
+	if (ioba < tbl->it_offset)
+		return -EINVAL;
+
+	if ((ioba + 1) > (tbl->it_offset + tbl->it_size))
+		return -EINVAL;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iommu_tce_put_param_check);
+
+unsigned long iommu_clear_tce(struct iommu_table *tbl, unsigned long entry)
+{
+	unsigned long oldtce;
+	struct iommu_pool *pool = get_pool(tbl, entry);
+
+	spin_lock(&(pool->lock));
+
+	oldtce = ppc_md.tce_get(tbl, entry);
+	if (oldtce & (TCE_PCI_WRITE | TCE_PCI_READ))
+		ppc_md.tce_free(tbl, entry, 1);
+	else
+		oldtce = 0;
+
+	spin_unlock(&(pool->lock));
+
+	return oldtce;
+}
+EXPORT_SYMBOL_GPL(iommu_clear_tce);
+
+int iommu_clear_tces_and_put_pages(struct iommu_table *tbl,
+		unsigned long entry, unsigned long pages)
+{
+	unsigned long oldtce;
+	struct page *page;
+
+	for ( ; pages; --pages, ++entry) {
+		oldtce = iommu_clear_tce(tbl, entry);
+		if (!oldtce)
+			continue;
+
+		page = pfn_to_page(oldtce >> PAGE_SHIFT);
+		WARN_ON(!page);
+		if (page) {
+			if (oldtce & TCE_PCI_WRITE)
+				SetPageDirty(page);
+			put_page(page);
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iommu_clear_tces_and_put_pages);
+
+/*
+ * hwaddr is a kernel virtual address here (0xc... bazillion),
+ * tce_build converts it to a physical address.
+ */
+int iommu_tce_build(struct iommu_table *tbl, unsigned long entry,
+		unsigned long hwaddr, enum dma_data_direction direction)
+{
+	int ret = -EBUSY;
+	unsigned long oldtce;
+	struct iommu_pool *pool = get_pool(tbl, entry);
+
+	spin_lock(&(pool->lock));
+
+	oldtce = ppc_md.tce_get(tbl, entry);
+	/* Add new entry if it is not busy */
+	if (!(oldtce & (TCE_PCI_WRITE | TCE_PCI_READ)))
+		ret = ppc_md.tce_build(tbl, entry, 1, hwaddr, direction, NULL);
+
+	spin_unlock(&(pool->lock));
+
+	/* if (unlikely(ret))
+		pr_err("iommu_tce: %s failed on hwaddr=%lx ioba=%lx kva=%lx ret=%d\n",
+				__func__, hwaddr, entry << IOMMU_PAGE_SHIFT,
+				hwaddr, ret); */
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_tce_build);
+
+int iommu_put_tce_user_mode(struct iommu_table *tbl, unsigned long entry,
+		unsigned long tce)
+{
+	int ret;
+	struct page *page = NULL;
+	unsigned long hwaddr, offset = tce & IOMMU_PAGE_MASK & ~PAGE_MASK;
+	enum dma_data_direction direction = iommu_tce_direction(tce);
+
+	ret = get_user_pages_fast(tce & PAGE_MASK, 1,
+			direction != DMA_TO_DEVICE, &page);
+	if (unlikely(ret != 1)) {
+		/* pr_err("iommu_tce: get_user_pages_fast failed tce=%lx ioba=%lx ret=%d\n",
+				tce, entry << IOMMU_PAGE_SHIFT, ret); */
+		return -EFAULT;
+	}
+	hwaddr = (unsigned long) page_address(page) + offset;
+
+	ret = iommu_tce_build(tbl, entry, hwaddr, direction);
+	if (ret)
+		put_page(page);
+
+	if (ret < 0)
+		pr_err("iommu_tce: %s failed ioba=%lx, tce=%lx, ret=%d\n",
+				__func__, entry << IOMMU_PAGE_SHIFT, tce, ret);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_put_tce_user_mode);
+
+int iommu_take_ownership(struct iommu_table *tbl)
+{
+	unsigned long sz = (tbl->it_size + 7) >> 3;
+
+	if (tbl->it_offset == 0)
+		clear_bit(0, tbl->it_map);
+
+	if (!bitmap_empty(tbl->it_map, tbl->it_size)) {
+		pr_err("iommu_tce: it_map is not empty");
+		return -EBUSY;
+	}
+
+	memset(tbl->it_map, 0xff, sz);
+	iommu_clear_tces_and_put_pages(tbl, tbl->it_offset, tbl->it_size);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iommu_take_ownership);
+
+void iommu_release_ownership(struct iommu_table *tbl)
+{
+	unsigned long sz = (tbl->it_size + 7) >> 3;
+
+	iommu_clear_tces_and_put_pages(tbl, tbl->it_offset, tbl->it_size);
+	memset(tbl->it_map, 0, sz);
+
+	/* Restore bit#0 set by iommu_init_table() */
+	if (tbl->it_offset == 0)
+		set_bit(0, tbl->it_map);
+}
+EXPORT_SYMBOL_GPL(iommu_release_ownership);
+
+static int iommu_add_device(struct device *dev)
+{
+	struct iommu_table *tbl;
+	int ret = 0;
+
+	if (WARN_ON(dev->iommu_group)) {
+		pr_warn("iommu_tce: device %s is already in iommu group %d, skipping\n",
+				dev_name(dev),
+				iommu_group_id(dev->iommu_group));
+		return -EBUSY;
+	}
+
+	tbl = get_iommu_table_base(dev);
+	if (!tbl || !tbl->it_group) {
+		pr_debug("iommu_tce: skipping device %s with no tbl\n",
+				dev_name(dev));
+		return 0;
+	}
+
+	pr_debug("iommu_tce: adding %s to iommu group %d\n",
+			dev_name(dev), iommu_group_id(tbl->it_group));
+
+	ret = iommu_group_add_device(tbl->it_group, dev);
+	if (ret < 0)
+		pr_err("iommu_tce: %s has not been added, ret=%d\n",
+				dev_name(dev), ret);
+
+	return ret;
+}
+
+static void iommu_del_device(struct device *dev)
+{
+	iommu_group_remove_device(dev);
+}
+
+static int iommu_bus_notifier(struct notifier_block *nb,
+			      unsigned long action, void *data)
+{
+	struct device *dev = data;
+
+	switch (action) {
+	case BUS_NOTIFY_ADD_DEVICE:
+		return iommu_add_device(dev);
+	case BUS_NOTIFY_DEL_DEVICE:
+		iommu_del_device(dev);
+		return 0;
+	default:
+		return 0;
+	}
+}
+
+static struct notifier_block tce_iommu_bus_nb = {
+	.notifier_call = iommu_bus_notifier,
+};
+
+static int __init tce_iommu_init(void)
+{
+	struct pci_dev *pdev = NULL;
+
+	BUILD_BUG_ON(PAGE_SIZE < IOMMU_PAGE_SIZE);
+
+	for_each_pci_dev(pdev)
+		iommu_add_device(&pdev->dev);
+
+	bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb);
+	return 0;
+}
+
+subsys_initcall_sync(tce_iommu_init);
+
+#else
+
+void iommu_register_group(struct iommu_table *tbl,
+		int pci_domain_number, unsigned long pe_num)
+{
+}
+
+#endif /* CONFIG_IOMMU_API */

arch/powerpc/kernel/irq.c

···
  	u64 now = get_tb_or_rtc();
  	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
  
-	if (now >= *next_tb)
-		set_dec(1);
 	return now >= *next_tb;
 }
 

arch/powerpc/kernel/kprobes.c

···
 #include <asm/sstep.h>
 #include <asm/uaccess.h>
 
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
-#define MSR_SINGLESTEP	(MSR_DE)
-#else
-#define MSR_SINGLESTEP	(MSR_SE)
-#endif
-
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
 DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
···
 
 static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
 {
-	/* We turn off async exceptions to ensure that the single step will
-	 * be for the instruction we have the kprobe on, if we dont its
-	 * possible we'd get the single step reported for an exception handler
-	 * like Decrementer or External Interrupt */
-	regs->msr &= ~MSR_EE;
-	regs->msr |= MSR_SINGLESTEP;
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
-	regs->msr &= ~MSR_CE;
-	mtspr(SPRN_DBCR0, mfspr(SPRN_DBCR0) | DBCR0_IC | DBCR0_IDM);
-#ifdef CONFIG_PPC_47x
-	isync();
-#endif
-#endif
+	enable_single_step(regs);
 
 	/*
 	 * On powerpc we should single step on the original

arch/powerpc/kernel/nvram_64.c

···
 	char *tmp = NULL;
 	ssize_t size;
 
-	ret = -ENODEV;
-	if (!ppc_md.nvram_size)
+	if (!ppc_md.nvram_size) {
+		ret = -ENODEV;
 		goto out;
+	}
 
-	ret = 0;
 	size = ppc_md.nvram_size();
-	if (*ppos >= size || size < 0)
+	if (size < 0) {
+		ret = size;
 		goto out;
+	}
+
+	if (*ppos >= size) {
+		ret = 0;
+		goto out;
+	}
 
 	count = min_t(size_t, count, size - *ppos);
 	count = min(count, PAGE_SIZE);
 
-	ret = -ENOMEM;
 	tmp = kmalloc(count, GFP_KERNEL);
-	if (!tmp)
+	if (!tmp) {
+		ret = -ENOMEM;
 		goto out;
+	}
 
 	ret = ppc_md.nvram_read(tmp, count, ppos);
 	if (ret <= 0)

arch/powerpc/kernel/pci-hotplug.c

···
+/*
+ * Derived from "arch/powerpc/platforms/pseries/pci_dlpar.c"
+ *
+ * Copyright (C) 2003 Linda Xie <[e-mail]>
+ * Copyright (C) 2005 International Business Machines
+ *
+ * Updates, 2005, John Rose <[e-mail]>
+ * Updates, 2005, Linas Vepstas <[e-mail]>
+ * Updates, 2013, Gavin Shan <[e-mail]>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/pci.h>
+#include <linux/export.h>
+#include <asm/pci-bridge.h>
+#include <asm/ppc-pci.h>
+#include <asm/firmware.h>
+#include <asm/eeh.h>
+
+/**
+ * __pcibios_remove_pci_devices - remove all devices under this bus
+ * @bus: the indicated PCI bus
+ * @purge_pe: destroy the PE on removal of PCI devices
+ *
+ * Remove all of the PCI devices under this bus both from the
+ * linux pci device tree, and from the powerpc EEH address cache.
+ * By default, the corresponding PE will be destroied during the
+ * normal PCI hotplug path. For PCI hotplug during EEH recovery,
+ * the corresponding PE won't be destroied and deallocated.
+ */
+void __pcibios_remove_pci_devices(struct pci_bus *bus, int purge_pe)
+{
+	struct pci_dev *dev, *tmp;
+	struct pci_bus *child_bus;
+
+	/* First go down child busses */
+	list_for_each_entry(child_bus, &bus->children, node)
+		__pcibios_remove_pci_devices(child_bus, purge_pe);
+
+	pr_debug("PCI: Removing devices on bus %04x:%02x\n",
+		 pci_domain_nr(bus),  bus->number);
+	list_for_each_entry_safe(dev, tmp, &bus->devices, bus_list) {
+		pr_debug("     * Removing %s...\n", pci_name(dev));
+		eeh_remove_bus_device(dev, purge_pe);
+		pci_stop_and_remove_bus_device(dev);
+	}
+}
+
+/**
+ * pcibios_remove_pci_devices - remove all devices under this bus
+ * @bus: the indicated PCI bus
+ *
+ * Remove all of the PCI devices under this bus both from the
+ * linux pci device tree, and from the powerpc EEH address cache.
+ */
+void pcibios_remove_pci_devices(struct pci_bus *bus)
+{
+	__pcibios_remove_pci_devices(bus, 1);
+}
+EXPORT_SYMBOL_GPL(pcibios_remove_pci_devices);
+
+/**
+ * pcibios_add_pci_devices - adds new pci devices to bus
+ * @bus: the indicated PCI bus
+ *
+ * This routine will find and fixup new pci devices under
+ * the indicated bus. This routine presumes that there
+ * might already be some devices under this bridge, so
+ * it carefully tries to add only new devices.  (And that
+ * is how this routine differs from other, similar pcibios
+ * routines.)
+ */
+void pcibios_add_pci_devices(struct pci_bus * bus)
+{
+	int slotno, num, mode, pass, max;
+	struct pci_dev *dev;
+	struct device_node *dn = pci_bus_to_OF_node(bus);
+
+	eeh_add_device_tree_early(dn);
+
+	mode = PCI_PROBE_NORMAL;
+	if (ppc_md.pci_probe_mode)
+		mode = ppc_md.pci_probe_mode(bus);
+
+	if (mode == PCI_PROBE_DEVTREE) {
+		/* use ofdt-based probe */
+		of_rescan_bus(dn, bus);
+	} else if (mode == PCI_PROBE_NORMAL) {
+		/* use legacy probe */
+		slotno = PCI_SLOT(PCI_DN(dn->child)->devfn);
+		num = pci_scan_slot(bus, PCI_DEVFN(slotno, 0));
+		if (!num)
+			return;
+		pcibios_setup_bus_devices(bus);
+		max = bus->busn_res.start;
+		for (pass = 0; pass < 2; pass++) {
+			list_for_each_entry(dev, &bus->devices, bus_list) {
+				if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE ||
+				    dev->hdr_type == PCI_HEADER_TYPE_CARDBUS)
+					max = pci_scan_bridge(bus, dev,
+							      max, pass);
+			}
+		}
+	}
+	pcibios_finish_adding_to_bus(bus);
+}
+EXPORT_SYMBOL_GPL(pcibios_add_pci_devices);

arch/powerpc/kernel/process.c

···
 	flush_altivec_to_thread(src);
 	flush_vsx_to_thread(src);
 	flush_spe_to_thread(src);
+
 	*dst = *src;
+
+	clear_task_ebb(dst);
+
 	return 0;
 }
 

arch/powerpc/kernel/prom.c

···
 }
 #endif
 
+static void __init early_reserve_mem_dt(void)
+{
+	unsigned long i, len, dt_root;
+	const __be32 *prop;
+
+	dt_root = of_get_flat_dt_root();
+
+	prop = of_get_flat_dt_prop(dt_root, "reserved-ranges", &len);
+
+	if (!prop)
+		return;
+
+	DBG("Found new-style reserved-ranges\n");
+
+	/* Each reserved range is an (address,size) pair, 2 cells each,
+	 * totalling 4 cells per range. */
+	for (i = 0; i < len / (sizeof(*prop) * 4); i++) {
+		u64 base, size;
+
+		base = of_read_number(prop + (i * 4) + 0, 2);
+		size = of_read_number(prop + (i * 4) + 2, 2);
+
+		if (size) {
+			DBG("reserving: %llx -> %llx\n", base, size);
+			memblock_reserve(base, size);
+		}
+	}
+}
+
 static void __init early_reserve_mem(void)
 {
 	u64 base, size;
···
 	self_size = initial_boot_params->totalsize;
 	memblock_reserve(self_base, self_size);
 
+	/* Look for the new "reserved-regions" property in the DT */
+	early_reserve_mem_dt();
+
 #ifdef CONFIG_BLK_DEV_INITRD
-	/* then reserve the initrd, if any */
-	if (initrd_start && (initrd_end > initrd_start))
+	/* Then reserve the initrd, if any */
+	if (initrd_start && (initrd_end > initrd_start)) {
 		memblock_reserve(_ALIGN_DOWN(__pa(initrd_start), PAGE_SIZE),
 			_ALIGN_UP(initrd_end, PAGE_SIZE) -
 			_ALIGN_DOWN(initrd_start, PAGE_SIZE));
+	}
 #endif /* CONFIG_BLK_DEV_INITRD */
 
 #ifdef CONFIG_PPC32
···
 	if (*reserve_map > 0xffffffffull) {
 		u32 base_32, size_32;
 		u32 *reserve_map_32 = (u32 *)reserve_map;
+
+		DBG("Found old 32-bit reserve map\n");
 
 		while (1) {
 			base_32 = *(reserve_map_32++);
···
 		return;
 	}
 #endif
+	DBG("Processing reserve map\n");
+
+	/* Handle the reserve map in the fdt blob if it exists */
 	while (1) {
 		base = *(reserve_map++);
 		size = *(reserve_map++);

arch/powerpc/kernel/ptrace.c

···
 	 */
 	if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE) {
 		len = bp_info->addr2 - bp_info->addr;
-	} else if (bp_info->addr_mode != PPC_BREAKPOINT_MODE_EXACT) {
+	} else if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_EXACT)
+		len = 1;
+	else {
 		ptrace_put_breakpoints(child);
 		return -EINVAL;
 	}

arch/powerpc/kernel/reloc_32.S

···
 	/* R_PPC_ADDR16_LO */
 lo16:
 	cmpwi	r4, R_PPC_ADDR16_LO
-	bne	nxtrela
+	bne	unknown_type
 	lwz	r4, 0(r9)	/* r_offset */
 	lwz	r0, 8(r9)	/* r_addend */
 	add	r0, r0, r3
···
 	dcbst	r4,r7
 	sync			/* Ensure the data is flushed before icbi */
 	icbi	r4,r7
+unknown_type:
 	cmpwi	r8, 0		/* relasz = 0 ? */
 	ble	done
 	add	r9, r9, r6	/* move to next entry in the .rela table */

arch/powerpc/kernel/rtas.c

···
 static arch_spinlock_t timebase_lock;
 static u64 timebase = 0;
 
-void __cpuinit rtas_give_timebase(void)
+void rtas_give_timebase(void)
 {
 	unsigned long flags;
 
···
 	local_irq_restore(flags);
 }
 
-void __cpuinit rtas_take_timebase(void)
+void rtas_take_timebase(void)
 {
 	while (!timebase)
 		barrier();

arch/powerpc/kernel/setup_64.c

···
 #endif
 
 int boot_cpuid = 0;
-int __initdata spinning_secondaries;
+int spinning_secondaries;
 u64 ppc64_pft_size;
 
 /* Pick defaults since we might want to patch instructions

arch/powerpc/kernel/signal_32.c

···
  * altivec/spe instructions at some point.
  */
 static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame,
-		int sigret, int ctx_has_vsx_region)
+			  struct mcontext __user *tm_frame, int sigret,
+			  int ctx_has_vsx_region)
 {
 	unsigned long msr = regs->msr;
 
···
 
 	if (__put_user(msr, &frame->mc_gregs[PT_MSR]))
 		return 1;
+	/* We need to write 0 the MSR top 32 bits in the tm frame so that we
+	 * can check it on the restore to see if TM is active
+	 */
+	if (tm_frame && __put_user(0, &tm_frame->mc_gregs[PT_MSR]))
+		return 1;
+
 	if (sigret) {
 		/* Set up the sigreturn trampoline: li r0,sigret; sc */
 		if (__put_user(0x38000000UL + sigret, &frame->tramp[0])
···
 				 struct mcontext __user *tm_sr)
 {
 	long err;
-	unsigned long msr;
+	unsigned long msr, msr_hi;
 #ifdef CONFIG_VSX
 	int i;
 #endif
···
 	tm_enable();
 	/* This loads the checkpointed FP/VEC state, if used */
 	tm_recheckpoint(&current->thread, msr);
-	/* The task has moved into TM state S, so ensure MSR reflects this */
-	regs->msr = (regs->msr & ~MSR_TS_MASK) | MSR_TS_S;
+	/* Get the top half of the MSR */
+	if (__get_user(msr_hi, &tm_sr->mc_gregs[PT_MSR]))
+		return 1;
+	/* Pull in MSR TM from user context */
+	regs->msr = (regs->msr & ~MSR_TS_MASK) | ((msr_hi<<32) & MSR_TS_MASK);
 
 	/* This loads the speculative FP/VEC state, if used */
 	if (msr & MSR_FP) {
···
 {
 	struct rt_sigframe __user *rt_sf;
 	struct mcontext __user *frame;
+	struct mcontext __user *tm_frame = NULL;
 	void __user *addr;
 	unsigned long newsp = 0;
 	int sigret;
···
 	}
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	tm_frame = &rt_sf->uc_transact.uc_mcontext;
 	if (MSR_TM_ACTIVE(regs->msr)) {
-		if (save_tm_user_regs(regs, &rt_sf->uc.uc_mcontext,
-				      &rt_sf->uc_transact.uc_mcontext, sigret))
+		if (save_tm_user_regs(regs, frame, tm_frame, sigret))
 			goto badframe;
 	}
 	else
 #endif
-		if (save_user_regs(regs, frame, sigret, 1))
+	{
+		if (save_user_regs(regs, frame, tm_frame, sigret, 1))
 			goto badframe;
+	}
 	regs->link = tramp;
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	if (MSR_TM_ACTIVE(regs->msr)) {
 		if (__put_user((unsigned long)&rt_sf->uc_transact,
 			       &rt_sf->uc.uc_link)
-		    || __put_user(to_user_ptr(&rt_sf->uc_transact.uc_mcontext),
-				  &rt_sf->uc_transact.uc_regs))
+		    || __put_user((unsigned long)tm_frame, &rt_sf->uc_transact.uc_regs))
 			goto badframe;
 	}
 	else
···
 		mctx = (struct mcontext __user *)
 			((unsigned long) &old_ctx->uc_mcontext & ~0xfUL);
 		if (!access_ok(VERIFY_WRITE, old_ctx, ctx_size)
-		    || save_user_regs(regs, mctx, 0, ctx_has_vsx_region)
+		    || save_user_regs(regs, mctx, NULL, 0, ctx_has_vsx_region)
 		    || put_sigset_t(&old_ctx->uc_sigmask, &current->blocked)
 		    || __put_user(to_user_ptr(mctx), &old_ctx->uc_regs))
 			return -EFAULT;
···
 		if (__get_user(msr_hi, &mcp->mc_gregs[PT_MSR]))
 			goto bad;
 
-		if (MSR_TM_SUSPENDED(msr_hi<<32)) {
+		if (MSR_TM_ACTIVE(msr_hi<<32)) {
 			/* We only recheckpoint on return if we're
 			 * transaction.
 			 */
···
 {
 	struct sigcontext __user *sc;
 	struct sigframe __user *frame;
+	struct mcontext __user *tm_mctx = NULL;
 	unsigned long newsp = 0;
 	int sigret;
 	unsigned long tramp;
···
 	}
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	tm_mctx = &frame->mctx_transact;
 	if (MSR_TM_ACTIVE(regs->msr)) {
 		if (save_tm_user_regs(regs, &frame->mctx, &frame->mctx_transact,
 				      sigret))
···
 	}
 	else
 #endif
-		if (save_user_regs(regs, &frame->mctx, sigret, 1))
+	{
+		if (save_user_regs(regs, &frame->mctx, tm_mctx, sigret, 1))
 			goto badframe;
+	}
 
 	regs->link = tramp;
 
···
 long sys_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8,
 		       struct pt_regs *regs)
 {
+	struct sigframe __user *sf;
 	struct sigcontext __user *sc;
 	struct sigcontext sigctx;
 	struct mcontext __user *sr;
 	void __user *addr;
 	sigset_t set;
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	struct mcontext __user *mcp, *tm_mcp;
+	unsigned long msr_hi;
+#endif
 
 	/* Always make any pending restarted system calls return -EINTR */
 	current_thread_info()->restart_block.fn = do_no_restart_syscall;
 
-	sc = (struct sigcontext __user *)(regs->gpr[1] + __SIGNAL_FRAMESIZE);
+	sf = (struct sigframe __user *)(regs->gpr[1] + __SIGNAL_FRAMESIZE);
+	sc = &sf->sctx;
 	addr = sc;
 	if (copy_from_user(&sigctx, sc, sizeof(sigctx)))
 		goto badframe;
···
 #endif
 	set_current_blocked(&set);
 
-	sr = (struct mcontext __user *)from_user_ptr(sigctx.regs);
-	addr = sr;
-	if (!access_ok(VERIFY_READ, sr, sizeof(*sr))
-	    || restore_user_regs(regs, sr, 1))
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	mcp = (struct mcontext __user *)&sf->mctx;
+	tm_mcp = (struct mcontext __user *)&sf->mctx_transact;
+	if (__get_user(msr_hi, &tm_mcp->mc_gregs[PT_MSR]))
 		goto badframe;
+	if (MSR_TM_ACTIVE(msr_hi<<32)) {
+		if (!cpu_has_feature(CPU_FTR_TM))
+			goto badframe;
+		if (restore_tm_user_regs(regs, mcp, tm_mcp))
+			goto badframe;
+	} else
+#endif
+	{
+		sr = (struct mcontext __user *)from_user_ptr(sigctx.regs);
+		addr = sr;
+		if (!access_ok(VERIFY_READ, sr, sizeof(*sr))
+		    || restore_user_regs(regs, sr, 1))
+			goto badframe;
+	}
 
 	set_thread_flag(TIF_RESTOREALL);
 	return 0;

arch/powerpc/kernel/signal_64.c

···
 
 	/* get MSR separately, transfer the LE bit if doing signal return */
 	err |= __get_user(msr, &sc->gp_regs[PT_MSR]);
+	/* pull in MSR TM from user context */
+	regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr & MSR_TS_MASK);
+
+	/* pull in MSR LE from user context */
 	regs->msr = (regs->msr & ~MSR_LE) | (msr & MSR_LE);
 
 	/* The following non-GPR non-FPR non-VR state is also checkpointed: */
···
 	tm_enable();
 	/* This loads the checkpointed FP/VEC state, if used */
 	tm_recheckpoint(&current->thread, msr);
-	/* The task has moved into TM state S, so ensure MSR reflects this: */
-	regs->msr = (regs->msr & ~MSR_TS_MASK) | __MASK(33);
 
 	/* This loads the speculative FP/VEC state, if used */
 	if (msr & MSR_FP) {
···
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	if (__get_user(msr, &uc->uc_mcontext.gp_regs[PT_MSR]))
 		goto badframe;
-	if (MSR_TM_SUSPENDED(msr)) {
+	if (MSR_TM_ACTIVE(msr)) {
 		/* We recheckpoint on return. */
 		struct ucontext __user *uc_transact;
 		if (__get_user(uc_transact, &uc->uc_link))

arch/powerpc/kernel/smp.c

···
 	secondary_ti = current_set[cpu] = ti;
 }
 
-int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *tidle)
+int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
 	int rc, c;
 
···
 }
 
 /* Activate a secondary processor. */
-__cpuinit void start_secondary(void *unused)
+void start_secondary(void *unused)
 {
 	unsigned int cpu = smp_processor_id();
 	struct device_node *l2_cache;
···
 
 	vdso_getcpu_init();
 #endif
-	notify_cpu_starting(cpu);
-	set_cpu_online(cpu, true);
 	/* Update sibling maps */
 	base = cpu_first_thread_sibling(cpu);
 	for (i = 0; i < threads_per_core; i++) {
-		if (cpu_is_offline(base + i))
+		if (cpu_is_offline(base + i) && (cpu != base + i))
 			continue;
 		cpumask_set_cpu(cpu, cpu_sibling_mask(base + i));
 		cpumask_set_cpu(base + i, cpu_sibling_mask(cpu));
···
 		of_node_put(np);
 	}
 	of_node_put(l2_cache);
+
+	smp_wmb();
+	notify_cpu_starting(cpu);
+	set_cpu_online(cpu, true);
 
 	local_irq_enable();
 

arch/powerpc/kernel/sysfs.c

···
 #endif /* HAS_PPC_PMC_PA6T */
 #endif /* HAS_PPC_PMC_CLASSIC */
 
-static void __cpuinit register_cpu_online(unsigned int cpu)
+static void register_cpu_online(unsigned int cpu)
 {
 	struct cpu *c = &per_cpu(cpu_devices, cpu);
 	struct device *s = &c->dev;
···
 
 #endif /* CONFIG_HOTPLUG_CPU */
 
-static int __cpuinit sysfs_cpu_notify(struct notifier_block *self,
+static int sysfs_cpu_notify(struct notifier_block *self,
 				      unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (unsigned int)(long)hcpu;
···
 	return NOTIFY_OK;
 }
 
-static struct notifier_block __cpuinitdata sysfs_cpu_nb = {
+static struct notifier_block sysfs_cpu_nb = {
 	.notifier_call	= sysfs_cpu_notify,
 };
 

arch/powerpc/kernel/time.c

···
 	return found;
 }
 
-/* should become __cpuinit when secondary_cpu_time_init also is */
 void start_cpu_decrementer(void)
 {
 #if defined(CONFIG_BOOKE) || defined(CONFIG_40x)

arch/powerpc/kernel/tm.S

···
 	std	r3, STACK_PARAM(0)(r1)
 	SAVE_NVGPRS(r1)
 
+	/* We need to setup MSR for VSX register save instructions.  Here we
+	 * also clear the MSR RI since when we do the treclaim, we won't have a
+	 * valid kernel pointer for a while.  We clear RI here as it avoids
+	 * adding another mtmsr closer to the treclaim.  This makes the region
+	 * maked as non-recoverable wider than it needs to be but it saves on
+	 * inserting another mtmsrd later.
+	 */
 	mfmsr	r14
 	mr	r15, r14
 	ori	r15, r15, MSR_FP
+	li	r16, MSR_RI
+	andc	r15, r15, r16
 	oris	r15, r15, MSR_VEC@h
 #ifdef CONFIG_VSX
 	BEGIN_FTR_SECTION
···
 	mtcr	r5
 	mtxer	r6
 
-	/* MSR and flags:  We don't change CRs, and we don't need to alter
-	 * MSR.
+	/* Clear the MSR RI since we are about to change R1.  EE is already off
 	 */
+	li	r4, 0
+	mtmsrd	r4, 1
 
 	REST_4GPRS(0, r7)			/* GPR0-3 */
 	REST_GPR(4, r7)				/* GPR4-6 */
···
 
 	GET_PACA(r13)
 	GET_SCRATCH0(r1)
+
+	/* R1 is restored, so we are recoverable again.  EE is still off */
+	li	r4, MSR_RI
+	mtmsrd	r4, 1
 
 	REST_NVGPRS(r1)
 

arch/powerpc/kernel/traps.c

···
 		u8 val;
 		u32 shift = 8 * (3 - (pos & 0x3));
 
+		/* if process is 32-bit, clear upper 32 bits of EA */
+		if ((regs->msr & MSR_64BIT) == 0)
+			EA &= 0xFFFFFFFF;
+
 		switch ((instword & PPC_INST_STRING_MASK)) {
 			case PPC_INST_LSWX:
 			case PPC_INST_LSWI:
···
 	 * ESR_DST (!?) or 0.  In the process of chasing this with the
 	 * hardware people - not sure if it can happen on any illegal
 	 * instruction or only on FP instructions, whether there is a
-	 * pattern to occurrences etc. -dgibson 31/Mar/2003 */
+	 * pattern to occurrences etc. -dgibson 31/Mar/2003
+	 */
+
+	/*
+	 * If we support a HW FPU, we need to ensure the FP state
+	 * if flushed into the thread_struct before attempting
+	 * emulation
+	 */
+#ifdef CONFIG_PPC_FPU
+	flush_fp_to_thread(current);
+#endif
 	switch (do_mathemu(regs)) {
 	case 0:
 		emulate_single_step(regs);
···
 	die("Unrecoverable VSX Unavailable Exception", regs, SIGABRT);
 }
 
-void tm_unavailable_exception(struct pt_regs *regs)
+void facility_unavailable_exception(struct pt_regs *regs)
 {
+	static char *facility_strings[] = {
+		"FPU",
+		"VMX/VSX",
+		"DSCR",
+		"PMU SPRs",
+		"BHRB",
+		"TM",
+		"AT",
+		"EBB",
+		"TAR",
+	};
+	char *facility, *prefix;
+	u64 value;
+
+	if (regs->trap == 0xf60) {
+		value = mfspr(SPRN_FSCR);
+		prefix = "";
+	} else {
+		value = mfspr(SPRN_HFSCR);
+		prefix = "Hypervisor ";
+	}
+
+	value = value >> 56;
+
 	/* We restore the interrupt state now */
 	if (!arch_irq_disabled_regs(regs))
 		local_irq_enable();
 
-	/* Currently we never expect a TMU exception.  Catch
-	 * this and kill the process!
-	 */
-	printk(KERN_EMERG "Unexpected TM unavailable exception at %lx "
-	       "(msr %lx)\n",
-	       regs->nip, regs->msr);
+	if (value < ARRAY_SIZE(facility_strings))
+		facility = facility_strings[value];
+	else
+		facility = "unknown";
+
+	pr_err("%sFacility '%s' unavailable, exception at 0x%lx, MSR=%lx\n",
+		prefix, facility, regs->nip, regs->msr);
 
 	if (user_mode(regs)) {
 		_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
 		return;
 	}
 
-	die("Unexpected TM unavailable exception", regs, SIGABRT);
+	die("Unexpected facility unavailable exception", regs, SIGABRT);
 }
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
···
 void SoftwareEmulation(struct pt_regs *regs)
 {
 	extern int do_mathemu(struct pt_regs *);
-	extern int Soft_emulate_8xx(struct pt_regs *);
-#if defined(CONFIG_MATH_EMULATION) || defined(CONFIG_8XX_MINIMAL_FPEMU)
+#if defined(CONFIG_MATH_EMULATION)
 	int errcode;
 #endif
 
···
 		return;
 	default:
 		_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
-		return;
-	}
-
-#elif defined(CONFIG_8XX_MINIMAL_FPEMU)
-	errcode = Soft_emulate_8xx(regs);
-	if (errcode >= 0)
-		PPC_WARN_EMULATED(8xx, regs);
-
-	switch (errcode) {
-	case 0:
-		emulate_single_step(regs);
-		return;
-	case 1:
-		_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
-		return;
-	case -EFAULT:
-		_exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
 		return;
 	}
 #else
···
 	WARN_EMULATED_SETUP(unaligned),
 #ifdef CONFIG_MATH_EMULATION
 	WARN_EMULATED_SETUP(math),
-#elif defined(CONFIG_8XX_MINIMAL_FPEMU)
-	WARN_EMULATED_SETUP(8xx),
 #endif
 #ifdef CONFIG_VSX
 	WARN_EMULATED_SETUP(vsx),

arch/powerpc/kernel/udbg.c

···
 	udbg_init_debug_beat();
 #elif defined(CONFIG_PPC_EARLY_DEBUG_PAS_REALMODE)
 	udbg_init_pas_realmode();
-#elif defined(CONFIG_BOOTX_TEXT)
+#elif defined(CONFIG_PPC_EARLY_DEBUG_BOOTX)
 	udbg_init_btext();
 #elif defined(CONFIG_PPC_EARLY_DEBUG_44x)
 	/* PPC44x debug */

arch/powerpc/kernel/vdso.c

···
 }
 
 #ifdef CONFIG_PPC64
-int __cpuinit vdso_getcpu_init(void)
+int vdso_getcpu_init(void)
 {
 	unsigned long cpu, node, val;
 

arch/powerpc/kvm/book3s_64_mmu_host.c

···
 void kvmppc_mmu_invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 {
 	ppc_md.hpte_invalidate(pte->slot, pte->host_vpn,
-			       MMU_PAGE_4K, MMU_SEGSIZE_256M,
+			       MMU_PAGE_4K, MMU_PAGE_4K, MMU_SEGSIZE_256M,
 			       false);
 }
 

arch/powerpc/kvm/book3s_64_mmu_hv.c

···
 		}
 		/* if the guest wants write access, see if that is OK */
 		if (!writing && hpte_is_writable(r)) {
+			unsigned int hugepage_shift;
 			pte_t *ptep, pte;
 
 			/*
···
 			 */
 			rcu_read_lock_sched();
 			ptep = find_linux_pte_or_hugepte(current->mm->pgd,
-							 hva, NULL);
-			if (ptep && pte_present(*ptep)) {
-				pte = kvmppc_read_update_linux_pte(ptep, 1);
+							 hva, &hugepage_shift);
+			if (ptep) {
+				pte = kvmppc_read_update_linux_pte(ptep, 1,
+							   hugepage_shift);
 				if (pte_write(pte))
 					write_ok = 1;
 			}

arch/powerpc/kvm/book3s_hv_rm_mmu.c

···
 	unsigned long addr = (unsigned long) x;
 	pte_t *p;
 
-	p = find_linux_pte(swapper_pg_dir, addr);
+	p = find_linux_pte_or_hugepte(swapper_pg_dir, addr, NULL);
 	if (!p || !pte_present(*p))
 		return NULL;
 	/* assume we don't have huge pages in vmalloc space... */
···
 {
 	pte_t *ptep;
 	unsigned long ps = *pte_sizep;
-	unsigned int shift;
+	unsigned int hugepage_shift;
 
-	ptep = find_linux_pte_or_hugepte(pgdir, hva, &shift);
+	ptep = find_linux_pte_or_hugepte(pgdir, hva, &hugepage_shift);
 	if (!ptep)
 		return __pte(0);
-	if (shift)
-		*pte_sizep = 1ul << shift;
+	if (hugepage_shift)
+		*pte_sizep = 1ul << hugepage_shift;
 	else
 		*pte_sizep = PAGE_SIZE;
 	if (ps > *pte_sizep)
 		return __pte(0);
-	if (!pte_present(*ptep))
-		return __pte(0);
-	return kvmppc_read_update_linux_pte(ptep, writing);
+	return kvmppc_read_update_linux_pte(ptep, writing, hugepage_shift);
 }
 
 static inline void unlock_hpte(unsigned long *hpte, unsigned long hpte_v)

arch/powerpc/lib/sstep.c

···
 		if (instr & 1)
 			regs->link = regs->nip;
 		if (branch_taken(instr, regs))
-			regs->nip = imm;
+			regs->nip = truncate_if_32bit(regs->msr, imm);
 		return 1;
 #ifdef CONFIG_PPC64
 	case 17:	/* sc */

arch/powerpc/math-emu/Makefile

···
 					fmadd.o fmadds.o fmsub.o fmsubs.o \
 					fmul.o fmuls.o fnabs.o fneg.o \
 					fnmadd.o fnmadds.o fnmsub.o fnmsubs.o \
-					fres.o frsp.o frsqrte.o fsel.o lfs.o \
+					fres.o fre.o frsp.o fsel.o lfs.o \
+					frsqrte.o frsqrtes.o \
 					fsqrt.o	fsqrts.o fsub.o fsubs.o \
 					mcrfs.o mffs.o mtfsb0.o mtfsb1.o \
 					mtfsf.o mtfsfi.o stfiwx.o stfs.o \

arch/powerpc/math-emu/fre.c

···
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <asm/uaccess.h>
+
+int fre(void *frD, void *frB)
+{
+#ifdef DEBUG
+	printk("%s: %p %p\n", __func__, frD, frB);
+#endif
+	return -ENOSYS;
+}

arch/powerpc/math-emu/frsqrtes.c

···
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <asm/uaccess.h>
+
+int frsqrtes(void *frD, void *frB)
+{
+#ifdef DEBUG
+	printk("%s: %p %p\n", __func__, frD, frB);
+#endif
+	return 0;
+}

arch/powerpc/math-emu/math.c

···
 FLOATFUNC(fneg);
 
 /* Optional */
+FLOATFUNC(fre);
 FLOATFUNC(fres);
 FLOATFUNC(frsqrte);
+FLOATFUNC(frsqrtes);
 FLOATFUNC(fsel);
 FLOATFUNC(fsqrt);
 FLOATFUNC(fsqrts);
···
 #define FSQRTS		0x016		/*   22 */
 #define FRES		0x018		/*   24 */
 #define FMULS		0x019		/*   25 */
+#define FRSQRTES	0x01a		/*   26 */
 #define FMSUBS		0x01c		/*   28 */
 #define FMADDS		0x01d		/*   29 */
 #define FNMSUBS		0x01e		/*   30 */
···
 #define FADD		0x015		/*   21 */
 #define FSQRT		0x016		/*   22 */
 #define FSEL		0x017		/*   23 */
+#define FRE		0x018		/*   24 */
 #define FMUL		0x019		/*   25 */
 #define FRSQRTE		0x01a		/*   26 */
 #define FMSUB		0x01c		/*   28 */
···
 		case FDIVS:	func = fdivs;	type = AB;	break;
 		case FSUBS:	func = fsubs;	type = AB;	break;
 		case FADDS:	func = fadds;	type = AB;	break;
-		case FSQRTS:	func = fsqrts;	type = AB;	break;
-		case FRES:	func = fres;	type = AB;	break;
+		case FSQRTS:	func = fsqrts;	type = XB;	break;
+		case FRES:	func = fres;	type = XB;	break;
 		case FMULS:	func = fmuls;	type = AC;	break;
+		case FRSQRTES:	func = frsqrtes;type = XB;	break;
 		case FMSUBS:	func = fmsubs;	type = ABC;	break;
 		case FMADDS:	func = fmadds;	type = ABC;	break;
 		case FNMSUBS:	func = fnmsubs;	type = ABC;	break;
···
 			case FDIV:	func = fdiv;	type = AB;	break;
 			case FSUB:	func = fsub;	type = AB;	break;
 			case FADD:	func = fadd;	type = AB;	break;
-			case FSQRT:	func = fsqrt;	type = AB;	break;
+			case FSQRT:	func = fsqrt;	type = XB;	break;
+			case FRE:	func = fre;	type = XB;	break;
 			case FSEL:	func = fsel;	type = ABC;	break;
 			case FMUL:	func = fmul;	type = AC;	break;
-			case FRSQRTE:	func = frsqrte;	type = AB;	break;
+			case FRSQRTE:	func = frsqrte;	type = XB;	break;
 			case FMSUB:	func = fmsub;	type = ABC;	break;
 			case FMADD:	func = fmadd;	type = ABC;	break;
 			case FNMSUB:	func = fnmsub;	type = ABC;	break;

arch/powerpc/mm/44x_mmu.c

···
 
 unsigned long tlb_47x_boltmap[1024/8];
 
-static void __cpuinit ppc44x_update_tlb_hwater(void)
+static void ppc44x_update_tlb_hwater(void)
 {
 	extern unsigned int tlb_44x_patch_hwater_D[];
 	extern unsigned int tlb_44x_patch_hwater_I[];
···
 /*
  * "Pins" a 256MB TLB entry in AS0 for kernel lowmem for 47x type MMU
  */
-static void __cpuinit ppc47x_pin_tlb(unsigned int virt, unsigned int phys)
+static void ppc47x_pin_tlb(unsigned int virt, unsigned int phys)
 {
 	unsigned int rA;
 	int bolted;
···
 }
 
 #ifdef CONFIG_SMP
-void __cpuinit mmu_init_secondary(int cpu)
+void mmu_init_secondary(int cpu)
 {
 	unsigned long addr;
 	unsigned long memstart = memstart_addr & ~(PPC_PIN_SIZE - 1);

arch/powerpc/mm/Makefile

···
 
 ccflags-$(CONFIG_PPC64)	:= $(NO_MINIMAL_TOC)
 
-obj-y				:= fault.o mem.o pgtable.o gup.o \
+obj-y				:= fault.o mem.o pgtable.o gup.o mmap.o \
 				   init_$(CONFIG_WORD_SIZE).o \
 				   pgtable_$(CONFIG_WORD_SIZE).o
 obj-$(CONFIG_PPC_MMU_NOHASH)	+= mmu_context_nohash.o tlb_nohash.o \
 				   tlb_nohash_low.o
 obj-$(CONFIG_PPC_BOOK3E)	+= tlb_low_$(CONFIG_WORD_SIZE)e.o
-obj-$(CONFIG_PPC64)		+= mmap_64.o
 hash64-$(CONFIG_PPC_NATIVE)	:= hash_native_64.o
 obj-$(CONFIG_PPC_STD_MMU_64)	+= hash_utils_64.o \
 				   slb_low.o slb.o stab.o \
-				   mmap_64.o $(hash64-y)
+				   $(hash64-y)
 obj-$(CONFIG_PPC_STD_MMU_32)	+= ppc_mmu_32.o
 obj-$(CONFIG_PPC_STD_MMU)	+= hash_low_$(CONFIG_WORD_SIZE).o \
 				   tlb_hash$(CONFIG_WORD_SIZE).o \
···
 obj-$(CONFIG_PPC_FSL_BOOK3E)	+= fsl_booke_mmu.o
 obj-$(CONFIG_NEED_MULTIPLE_NODES) += numa.o
 obj-$(CONFIG_PPC_MM_SLICES)	+= slice.o
-ifeq ($(CONFIG_HUGETLB_PAGE),y)
 obj-y				+= hugetlbpage.o
+ifeq ($(CONFIG_HUGETLB_PAGE),y)
 obj-$(CONFIG_PPC_STD_MMU_64)	+= hugetlbpage-hash64.o
 obj-$(CONFIG_PPC_BOOK3E_MMU)	+= hugetlbpage-book3e.o
 endif
+obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += hugepage-hash64.o
 obj-$(CONFIG_PPC_SUBPAGE_PROT)	+= subpage-prot.o
 obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o
 obj-$(CONFIG_HIGHMEM)		+= highmem.o

arch/powerpc/mm/gup.c

···
 
 	ptep = pte_offset_kernel(&pmd, addr);
 	do {
-		pte_t pte = *ptep;
+		pte_t pte = ACCESS_ONCE(*ptep);
 		struct page *page;
 
 		if ((pte_val(pte) & mask) != result)
···
 
 	pmdp = pmd_offset(&pud, addr);
 	do {
-		pmd_t pmd = *pmdp;
+		pmd_t pmd = ACCESS_ONCE(*pmdp);
 
 		next = pmd_addr_end(addr, end);
-		if (pmd_none(pmd))
+		/*
+		 * If we find a splitting transparent hugepage we
+		 * return zero. That will result in taking the slow
+		 * path which will call wait_split_huge_page()
+		 * if the pmd is still in splitting state
+		 */
+		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
 			return 0;
-		if (pmd_huge(pmd)) {
+		if (pmd_huge(pmd) || pmd_large(pmd)) {
 			if (!gup_hugepte((pte_t *)pmdp, PMD_SIZE, addr, next,
 					 write, pages, nr))
 				return 0;
···
 
 	pudp = pud_offset(&pgd, addr);
 	do {
-		pud_t pud = *pudp;
+		pud_t pud = ACCESS_ONCE(*pudp);
 
 		next = pud_addr_end(addr, end);
 		if (pud_none(pud))
···
 
 	pgdp = pgd_offset(mm, addr);
 	do {
-		pgd_t pgd = *pgdp;
+		pgd_t pgd = ACCESS_ONCE(*pgdp);
 
 		pr_devel("  %016lx: normal pgd %p\n", addr,
 			 (void *)pgd_val(pgd));

arch/powerpc/mm/hash_low_64.S

···
 
 	/* Call ppc_md.hpte_updatepp */
 	mr	r5,r29			/* vpn */
-	li	r6,MMU_PAGE_4K		/* page size */
-	ld	r7,STK_PARAM(R9)(r1)	/* segment size */
-	ld	r8,STK_PARAM(R8)(r1)	/* get "local" param */
+	li	r6,MMU_PAGE_4K		/* base page size */
+	li	r7,MMU_PAGE_4K		/* actual page size */
+	ld	r8,STK_PARAM(R9)(r1)	/* segment size */
+	ld	r9,STK_PARAM(R8)(r1)	/* get "local" param */
 _GLOBAL(htab_call_hpte_updatepp)
 	bl	.			/* Patched by htab_finish_init() */
 
···
 
 	/* Call ppc_md.hpte_updatepp */
 	mr	r5,r29			/* vpn */
-	li	r6,MMU_PAGE_4K		/* page size */
-	ld	r7,STK_PARAM(R9)(r1)	/* segment size */
-	ld	r8,STK_PARAM(R8)(r1)	/* get "local" param */
+	li	r6,MMU_PAGE_4K		/* base page size */
+	li	r7,MMU_PAGE_4K		/* actual page size */
+	ld	r8,STK_PARAM(R9)(r1)	/* segment size */
+	ld	r9,STK_PARAM(R8)(r1)	/* get "local" param */
 _GLOBAL(htab_call_hpte_updatepp)
 	bl	.			/* patched by htab_finish_init() */
 
···
 
 	/* Call ppc_md.hpte_updatepp */
 	mr	r5,r29			/* vpn */
-	li	r6,MMU_PAGE_64K
-	ld	r7,STK_PARAM(R9)(r1)	/* segment size */
-	ld	r8,STK_PARAM(R8)(r1)	/* get "local" param */
+	li	r6,MMU_PAGE_64K		/* base page size */
+	li	r7,MMU_PAGE_64K		/* actual page size */
+	ld	r8,STK_PARAM(R9)(r1)	/* segment size */
+	ld	r9,STK_PARAM(R8)(r1)	/* get "local" param */
 _GLOBAL(ht64_call_hpte_updatepp)
 	bl	.			/* patched by htab_finish_init() */
 

arch/powerpc/mm/hash_native_64.c

···
 	return i;
 }
 
-static inline int __hpte_actual_psize(unsigned int lp, int psize)
-{
-	int i, shift;
-	unsigned int mask;
-
-	/* start from 1 ignoring MMU_PAGE_4K */
-	for (i = 1; i < MMU_PAGE_COUNT; i++) {
-
-		/* invalid penc */
-		if (mmu_psize_defs[psize].penc[i] == -1)
-			continue;
-		/*
-		 * encoding bits per actual page size
-		 *        PTE LP     actual page size
-		 *    rrrr rrrz		>=8KB
-		 *    rrrr rrzz		>=16KB
-		 *    rrrr rzzz		>=32KB
-		 *    rrrr zzzz		>=64KB
-		 * .......
-		 */
-		shift = mmu_psize_defs[i].shift - LP_SHIFT;
-		if (shift > LP_BITS)
-			shift = LP_BITS;
-		mask = (1 << shift) - 1;
-		if ((lp & mask) == mmu_psize_defs[psize].penc[i])
-			return i;
-	}
-	return -1;
-}
-
-static inline int hpte_actual_psize(struct hash_pte *hptep, int psize)
-{
-	/* Look at the 8 bit LP value */
-	unsigned int lp = (hptep->r >> LP_SHIFT) & ((1 << LP_BITS) - 1);
-
-	if (!(hptep->v & HPTE_V_VALID))
-		return -1;
-
-	/* First check if it is large page */
-	if (!(hptep->v & HPTE_V_LARGE))
-		return MMU_PAGE_4K;
-
-	return __hpte_actual_psize(lp, psize);
-}
-
 static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
-				 unsigned long vpn, int psize, int ssize,
-				 int local)
+				 unsigned long vpn, int bpsize,
+				 int apsize, int ssize, int local)
 {
 	struct hash_pte *hptep = htab_address + slot;
 	unsigned long hpte_v, want_v;
 	int ret = 0;
-	int actual_psize;
 
-	want_v = hpte_encode_avpn(vpn, psize, ssize);
+	want_v = hpte_encode_avpn(vpn, bpsize, ssize);
 
 	DBG_LOW("    update(vpn=%016lx, avpnv=%016lx, group=%lx, newpp=%lx)",
 		vpn, want_v & HPTE_V_AVPN, slot, newpp);
···
 	native_lock_hpte(hptep);
 
 	hpte_v = hptep->v;
-	actual_psize = hpte_actual_psize(hptep, psize);
 	/*
 	 * We need to invalidate the TLB always because hpte_remove doesn't do
 	 * a tlb invalidate. If a hash bucket gets full, we "evict" a more/less
···
 	 * (hpte_remove) because we assume the old translation is still
 	 * technically "valid".
 	 */
-	if (actual_psize < 0) {
-		actual_psize = psize;
-		ret = -1;
-		goto err_out;
-	}
-	if (!HPTE_V_COMPARE(hpte_v, want_v)) {
+	if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID)) {
 		DBG_LOW(" -> miss\n");
 		ret = -1;
 	} else {
···
 		hptep->r = (hptep->r & ~(HPTE_R_PP | HPTE_R_N)) |
 			(newpp & (HPTE_R_PP | HPTE_R_N | HPTE_R_C));
 	}
-err_out:
 	native_unlock_hpte(hptep);
 
 	/* Ensure it is out of the tlb too. */
-	tlbie(vpn, psize, actual_psize, ssize, local);
+	tlbie(vpn, bpsize, apsize, ssize, local);
 
 	return ret;
 }
···
 static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
 				       int psize, int ssize)
 {
-	int actual_psize;
 	unsigned long vpn;
 	unsigned long vsid;
 	long slot;
···
 	if (slot == -1)
 		panic("could not find page to bolt\n");
 	hptep = htab_address + slot;
-	actual_psize = hpte_actual_psize(hptep, psize);
-	if (actual_psize < 0)
-		actual_psize = psize;
 
 	/* Update the HPTE */
 	hptep->r = (hptep->r & ~(HPTE_R_PP | HPTE_R_N)) |
 		(newpp & (HPTE_R_PP | HPTE_R_N));
-
-	/* Ensure it is out of the tlb too. */
-	tlbie(vpn, psize, actual_psize, ssize, 0);
+	/*
+	 * Ensure it is out of the tlb too. Bolted entries base and
+	 * actual page size will be same.
+	 */
+	tlbie(vpn, psize, psize, ssize, 0);
 }
 
 static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
-				   int psize, int ssize, int local)
+				   int bpsize, int apsize, int ssize, int local)
 {
 	struct hash_pte *hptep = htab_address + slot;
 	unsigned long hpte_v;
 	unsigned long want_v;
 	unsigned long flags;
-	int actual_psize;
 
 	local_irq_save(flags);
 
 	DBG_LOW("    invalidate(vpn=%016lx, hash: %lx)\n", vpn, slot);
 
-	want_v = hpte_encode_avpn(vpn, psize, ssize);
+	want_v = hpte_encode_avpn(vpn, bpsize, ssize);
 	native_lock_hpte(hptep);
 	hpte_v = hptep->v;
 
-	actual_psize = hpte_actual_psize(hptep, psize);
 	/*
 	 * We need to invalidate the TLB always because hpte_remove doesn't do
 	 * a tlb invalidate. If a hash bucket gets full, we "evict" a more/less
···
 	 * (hpte_remove) because we assume the old translation is still
 	 * technically "valid".
 	 */
-	if (actual_psize < 0) {
-		actual_psize = psize;
-		native_unlock_hpte(hptep);
-		goto err_out;
-	}
-	if (!HPTE_V_COMPARE(hpte_v, want_v))
+	if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID))
 		native_unlock_hpte(hptep);
 	else
 		/* Invalidate the hpte. NOTE: this also unlocks it */
 		hptep->v = 0;
 
-err_out:
 	/* Invalidate the TLB */
-	tlbie(vpn, psize, actual_psize, ssize, local);
+	tlbie(vpn, bpsize, apsize, ssize, local);
+
 	local_irq_restore(flags);
+}
+
+static void native_hugepage_invalidate(struct mm_struct *mm,
+				       unsigned char *hpte_slot_array,
+				       unsigned long addr, int psize)
+{
+	int ssize = 0, i;
+	int lock_tlbie;
+	struct hash_pte *hptep;
+	int actual_psize = MMU_PAGE_16M;
+	unsigned int max_hpte_count, valid;
+	unsigned long flags, s_addr = addr;
+	unsigned long hpte_v, want_v, shift;
+	unsigned long hidx, vpn = 0, vsid, hash, slot;
+
+	shift = mmu_psize_defs[psize].shift;
+	max_hpte_count = 1U << (PMD_SHIFT - shift);
+
+	local_irq_save(flags);
+	for (i = 0; i < max_hpte_count; i++) {
+		valid = hpte_valid(hpte_slot_array, i);
+		if (!valid)
+			continue;
+		hidx =  hpte_hash_index(hpte_slot_array, i);
+
+		/* get the vpn */
+		addr = s_addr + (i * (1ul << shift));
+		if (!is_kernel_addr(addr)) {
+			ssize = user_segment_size(addr);
+			vsid = get_vsid(mm->context.id, addr, ssize);
+			WARN_ON(vsid == 0);
+		} else {
+			vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
+			ssize = mmu_kernel_ssize;
+		}
+
+		vpn = hpt_vpn(addr, vsid, ssize);
+		hash = hpt_hash(vpn, shift, ssize);
+		if (hidx & _PTEIDX_SECONDARY)
+			hash = ~hash;
+
+		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
+		slot += hidx & _PTEIDX_GROUP_IX;
+
+		hptep = htab_address + slot;
+		want_v = hpte_encode_avpn(vpn, psize, ssize);
+		native_lock_hpte(hptep);
+		hpte_v = hptep->v;
+
+		/* Even if we miss, we need to invalidate the TLB */
+		if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID))
+			native_unlock_hpte(hptep);
+		else
+			/* Invalidate the hpte. NOTE: this also unlocks it */
+			hptep->v = 0;
+	}
+	/*
+	 * Since this is a hugepage, we just need a single tlbie.
+	 * use the last vpn.
+	 */
+	lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
+	if (lock_tlbie)
+		raw_spin_lock(&native_tlbie_lock);
+
+	asm volatile("ptesync":::"memory");
+	__tlbie(vpn, psize, actual_psize, ssize);
+	asm volatile("eieio; tlbsync; ptesync":::"memory");
+
+	if (lock_tlbie)
+		raw_spin_unlock(&native_tlbie_lock);
+
+	local_irq_restore(flags);
+}
+
+static inline int __hpte_actual_psize(unsigned int lp, int psize)
+{
+	int i, shift;
+	unsigned int mask;
+
+	/* start from 1 ignoring MMU_PAGE_4K */
+	for (i = 1; i < MMU_PAGE_COUNT; i++) {
+
+		/* invalid penc */
+		if (mmu_psize_defs[psize].penc[i] == -1)
+			continue;
+		/*
+		 * encoding bits per actual page size
+		 *        PTE LP     actual page size
+		 *    rrrr rrrz		>=8KB
+		 *    rrrr rrzz		>=16KB
+		 *    rrrr rzzz		>=32KB
+		 *    rrrr zzzz		>=64KB
+		 * .......
+		 */
+		shift = mmu_psize_defs[i].shift - LP_SHIFT;
+		if (shift > LP_BITS)
+			shift = LP_BITS;
+		mask = (1 << shift) - 1;
+		if ((lp & mask) == mmu_psize_defs[psize].penc[i])
+			return i;
+	}
+	return -1;
 }
 
 static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
···
 	ppc_md.hpte_remove	= native_hpte_remove;
 	ppc_md.hpte_clear_all	= native_hpte_clear;
 	ppc_md.flush_hash_range = native_flush_hash_range;
+	ppc_md.hugepage_invalidate   = native_hugepage_invalidate;
 }

arch/powerpc/mm/hash_utils_64.c

···
 }
 
 #ifdef CONFIG_SMP
-void __cpuinit early_init_mmu_secondary(void)
+void early_init_mmu_secondary(void)
 {
 	/* Initialize hash table for that CPU */
 	if (!firmware_has_feature(FW_FEATURE_LPAR))
···
 		goto bail;
 	}
 
-#ifdef CONFIG_HUGETLB_PAGE
 	if (hugeshift) {
-		rc = __hash_page_huge(ea, access, vsid, ptep, trap, local,
-					ssize, hugeshift, psize);
+		if (pmd_trans_huge(*(pmd_t *)ptep))
+			rc = __hash_page_thp(ea, access, vsid, (pmd_t *)ptep,
+					     trap, local, ssize, psize);
+#ifdef CONFIG_HUGETLB_PAGE
+		else
+			rc = __hash_page_huge(ea, access, vsid, ptep, trap,
+					      local, ssize, hugeshift, psize);
+#else
+		else {
+			/*
+			 * if we have hugeshift, and is not transhuge with
+			 * hugetlb disabled, something is really wrong.
+			 */
+			rc = 1;
+			WARN_ON(1);
+		}
+#endif
 		goto bail;
 	}
-#endif /* CONFIG_HUGETLB_PAGE */
 
 #ifndef CONFIG_PPC_64K_PAGES
 	DBG_LOW(" i-pte: %016lx\n", pte_val(*ptep));
···
 void hash_preload(struct mm_struct *mm, unsigned long ea,
 		  unsigned long access, unsigned long trap)
 {
+	int hugepage_shift;
 	unsigned long vsid;
 	pgd_t *pgdir;
 	pte_t *ptep;
···
 	pgdir = mm->pgd;
 	if (pgdir == NULL)
 		return;
-	ptep = find_linux_pte(pgdir, ea);
-	if (!ptep)
-		return;
 
+	/* Get VSID */
+	ssize = user_segment_size(ea);
+	vsid = get_vsid(mm->context.id, ea, ssize);
+	if (!vsid)
+		return;
+	/*
+	 * Hash doesn't like irqs. Walking linux page table with irq disabled
+	 * saves us from holding multiple locks.
+	 */
+	local_irq_save(flags);
+
+	/*
+	 * THP pages use update_mmu_cache_pmd. We don't do
+	 * hash preload there. Hence can ignore THP here
+	 */
+	ptep = find_linux_pte_or_hugepte(pgdir, ea, &hugepage_shift);
+	if (!ptep)
+		goto out_exit;
+
+	WARN_ON(hugepage_shift);
 #ifdef CONFIG_PPC_64K_PAGES
 	/* If either _PAGE_4K_PFN or _PAGE_NO_CACHE is set (and we are on
 	 * a 64K kernel), then we don't preload, hash_page() will take
···
 	 * page size demotion here
 	 */
 	if (pte_val(*ptep) & (_PAGE_4K_PFN | _PAGE_NO_CACHE))
-		return;
+		goto out_exit;
 #endif /* CONFIG_PPC_64K_PAGES */
-
-	/* Get VSID */
-	ssize = user_segment_size(ea);
-	vsid = get_vsid(mm->context.id, ea, ssize);
-	if (!vsid)
-		return;
-
-	/* Hash doesn't like irqs */
-	local_irq_save(flags);
 
 	/* Is that local to this CPU ? */
 	if (cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())))
···
 				   mm->context.user_psize,
 				   mm->context.user_psize,
 				   pte_val(*ptep));
-
+out_exit:
 	local_irq_restore(flags);
 }
 
···
 		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
 		slot += hidx & _PTEIDX_GROUP_IX;
 		DBG_LOW(" sub %ld: hash=%lx, hidx=%lx\n", index, slot, hidx);
-		ppc_md.hpte_invalidate(slot, vpn, psize, ssize, local);
+		/*
+		 * We use same base page size and actual psize, because we don't
+		 * use these functions for hugepage
+		 */
+		ppc_md.hpte_invalidate(slot, vpn, psize, psize, ssize, local);
 	} pte_iterate_hashed_end();
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
···
 		hash = ~hash;
 	slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
 	slot += hidx & _PTEIDX_GROUP_IX;
-	ppc_md.hpte_invalidate(slot, vpn, mmu_linear_psize, mmu_kernel_ssize, 0);
+	ppc_md.hpte_invalidate(slot, vpn, mmu_linear_psize, mmu_linear_psize,
+			       mmu_kernel_ssize, 0);
 }
 
 void kernel_map_pages(struct page *page, int numpages, int enable)

arch/powerpc/mm/hugepage-hash64.c

···
+/*
+ * Copyright IBM Corporation, 2013
+ * Author Aneesh Kumar K.V <[e-mail]>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+
+/*
+ * PPC64 THP Support for hash based MMUs
+ */
+#include <linux/mm.h>
+#include <asm/machdep.h>
+
+int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
+		    pmd_t *pmdp, unsigned long trap, int local, int ssize,
+		    unsigned int psize)
+{
+	unsigned int index, valid;
+	unsigned char *hpte_slot_array;
+	unsigned long rflags, pa, hidx;
+	unsigned long old_pmd, new_pmd;
+	int ret, lpsize = MMU_PAGE_16M;
+	unsigned long vpn, hash, shift, slot;
+
+	/*
+	 * atomically mark the linux large page PMD busy and dirty
+	 */
+	do {
+		old_pmd = pmd_val(*pmdp);
+		/* If PMD busy, retry the access */
+		if (unlikely(old_pmd & _PAGE_BUSY))
+			return 0;
+		/* If PMD is trans splitting retry the access */
+		if (unlikely(old_pmd & _PAGE_SPLITTING))
+			return 0;
+		/* If PMD permissions don't match, take page fault */
+		if (unlikely(access & ~old_pmd))
+			return 1;
+		/*
+		 * Try to lock the PTE, add ACCESSED and DIRTY if it was
+		 * a write access
+		 */
+		new_pmd = old_pmd | _PAGE_BUSY | _PAGE_ACCESSED;
+		if (access & _PAGE_RW)
+			new_pmd |= _PAGE_DIRTY;
+	} while (old_pmd != __cmpxchg_u64((unsigned long *)pmdp,
+					  old_pmd, new_pmd));
+	/*
+	 * PP bits. _PAGE_USER is already PP bit 0x2, so we only
+	 * need to add in 0x1 if it's a read-only user page
+	 */
+	rflags = new_pmd & _PAGE_USER;
+	if ((new_pmd & _PAGE_USER) && !((new_pmd & _PAGE_RW) &&
+					   (new_pmd & _PAGE_DIRTY)))
+		rflags |= 0x1;
+	/*
+	 * _PAGE_EXEC -> HW_NO_EXEC since it's inverted
+	 */
+	rflags |= ((new_pmd & _PAGE_EXEC) ? 0 : HPTE_R_N);
+
+#if 0
+	if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) {
+
+		/*
+		 * No CPU has hugepages but lacks no execute, so we
+		 * don't need to worry about that case
+		 */
+		rflags = hash_page_do_lazy_icache(rflags, __pte(old_pte), trap);
+	}
+#endif
+	/*
+	 * Find the slot index details for this ea, using base page size.
+	 */
+	shift = mmu_psize_defs[psize].shift;
+	index = (ea & ~HPAGE_PMD_MASK) >> shift;
+	BUG_ON(index >= 4096);
+
+	vpn = hpt_vpn(ea, vsid, ssize);
+	hash = hpt_hash(vpn, shift, ssize);
+	hpte_slot_array = get_hpte_slot_array(pmdp);
+
+	valid = hpte_valid(hpte_slot_array, index);
+	if (valid) {
+		/* update the hpte bits */
+		hidx =  hpte_hash_index(hpte_slot_array, index);
+		if (hidx & _PTEIDX_SECONDARY)
+			hash = ~hash;
+		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
+		slot += hidx & _PTEIDX_GROUP_IX;
+
+		ret = ppc_md.hpte_updatepp(slot, rflags, vpn,
+					   psize, lpsize, ssize, local);
+		/*
+		 * We failed to update, try to insert a new entry.
+		 */
+		if (ret == -1) {
+			/*
+			 * large pte is marked busy, so we can be sure
+			 * nobody is looking at hpte_slot_array. hence we can
+			 * safely update this here.
+			 */
+			valid = 0;
+			new_pmd &= ~_PAGE_HPTEFLAGS;
+			hpte_slot_array[index] = 0;
+		} else
+			/* clear the busy bits and set the hash pte bits */
+			new_pmd = (new_pmd & ~_PAGE_HPTEFLAGS) | _PAGE_HASHPTE;
+	}
+
+	if (!valid) {
+		unsigned long hpte_group;
+
+		/* insert new entry */
+		pa = pmd_pfn(__pmd(old_pmd)) << PAGE_SHIFT;
+repeat:
+		hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
+
+		/* clear the busy bits and set the hash pte bits */
+		new_pmd = (new_pmd & ~_PAGE_HPTEFLAGS) | _PAGE_HASHPTE;
+
+		/* Add in WIMG bits */
+		rflags |= (new_pmd & (_PAGE_WRITETHRU | _PAGE_NO_CACHE |
+				      _PAGE_COHERENT | _PAGE_GUARDED));
+
+		/* Insert into the hash table, primary slot */
+		slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, 0,
+					  psize, lpsize, ssize);
+		/*
+		 * Primary is full, try the secondary
+		 */
+		if (unlikely(slot == -1)) {
+			hpte_group = ((~hash & htab_hash_mask) *
+				      HPTES_PER_GROUP) & ~0x7UL;
+			slot = ppc_md.hpte_insert(hpte_group, vpn, pa,
+						  rflags, HPTE_V_SECONDARY,
+						  psize, lpsize, ssize);
+			if (slot == -1) {
+				if (mftb() & 0x1)
+					hpte_group = ((hash & htab_hash_mask) *
+						      HPTES_PER_GROUP) & ~0x7UL;
+
+				ppc_md.hpte_remove(hpte_group);
+				goto repeat;
+			}
+		}
+		/*
+		 * Hypervisor failure. Restore old pmd and return -1
+		 * similar to __hash_page_*
+		 */
+		if (unlikely(slot == -2)) {
+			*pmdp = __pmd(old_pmd);
+			hash_failure_debug(ea, access, vsid, trap, ssize,
+					   psize, lpsize, old_pmd);
+			return -1;
+		}
+		/*
+		 * large pte is marked busy, so we can be sure
+		 * nobody is looking at hpte_slot_array. hence we can
+		 * safely update this here.
+		 */
+		mark_hpte_slot_valid(hpte_slot_array, index, slot);
+	}
+	/*
+	 * No need to use ldarx/stdcx here
+	 */
+	*pmdp = __pmd(new_pmd & ~_PAGE_BUSY);
+	return 0;
+}

arch/powerpc/mm/hugetlbpage-hash64.c

···
 		slot += (old_pte & _PAGE_F_GIX) >> 12;
 
 		if (ppc_md.hpte_updatepp(slot, rflags, vpn, mmu_psize,
-					 ssize, local) == -1)
+					 mmu_psize, ssize, local) == -1)
 			old_pte &= ~_PAGE_HPTEFLAGS;
 	}
 

arch/powerpc/mm/hugetlbpage.c

···
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
 #include <asm/setup.h>
+#include <asm/hugetlb.h>
+
+#ifdef CONFIG_HUGETLB_PAGE
 
 #define PAGE_SHIFT_64K	16
 #define PAGE_SHIFT_16M	24
···
 }
 #endif
 
-/*
- * We have 4 cases for pgds and pmds:
- * (1) invalid (all zeroes)
- * (2) pointer to next table, as normal; bottom 6 bits == 0
- * (3) leaf pte for huge page, bottom two bits != 00
- * (4) hugepd pointer, bottom two bits == 00, next 4 bits indicate size of table
- */
-pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift)
-{
-	pgd_t *pg;
-	pud_t *pu;
-	pmd_t *pm;
-	pte_t *ret_pte;
-	hugepd_t *hpdp = NULL;
-	unsigned pdshift = PGDIR_SHIFT;
-
-	if (shift)
-		*shift = 0;
-
-	pg = pgdir + pgd_index(ea);
-
-	if (pgd_huge(*pg)) {
-		ret_pte = (pte_t *) pg;
-		goto out;
-	} else if (is_hugepd(pg))
-		hpdp = (hugepd_t *)pg;
-	else if (!pgd_none(*pg)) {
-		pdshift = PUD_SHIFT;
-		pu = pud_offset(pg, ea);
-
-		if (pud_huge(*pu)) {
-			ret_pte = (pte_t *) pu;
-			goto out;
-		} else if (is_hugepd(pu))
-			hpdp = (hugepd_t *)pu;
-		else if (!pud_none(*pu)) {
-			pdshift = PMD_SHIFT;
-			pm = pmd_offset(pu, ea);
-
-			if (pmd_huge(*pm)) {
-				ret_pte = (pte_t *) pm;
-				goto out;
-			} else if (is_hugepd(pm))
-				hpdp = (hugepd_t *)pm;
-			else if (!pmd_none(*pm))
-				return pte_offset_kernel(pm, ea);
-		}
-	}
-	if (!hpdp)
-		return NULL;
-
-	ret_pte = hugepte_offset(hpdp, ea, pdshift);
-	pdshift = hugepd_shift(*hpdp);
-out:
-	if (shift)
-		*shift = pdshift;
-	return ret_pte;
-}
-EXPORT_SYMBOL_GPL(find_linux_pte_or_hugepte);
-
 pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 {
+	/* Only called for hugetlbfs pages, hence can ignore THP */
 	return find_linux_pte_or_hugepte(mm->pgd, addr, NULL);
 }
 
···
 	struct page *page;
 	unsigned shift;
 	unsigned long mask;
-
+	/*
+	 * Transparent hugepages are handled by generic code. We can skip them
+	 * here.
+	 */
 	ptep = find_linux_pte_or_hugepte(mm->pgd, address, &shift);
 
 	/* Verify it is a huge page else bail. */
-	if (!ptep || !shift)
+	if (!ptep || !shift || pmd_trans_huge(*(pmd_t *)ptep))
 		return ERR_PTR(-EINVAL);
 
 	mask = (1UL << shift) - 1;
···
 {
 	BUG();
 	return NULL;
-}
-
-int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	unsigned long mask;
-	unsigned long pte_end;
-	struct page *head, *page, *tail;
-	pte_t pte;
-	int refs;
-
-	pte_end = (addr + sz) & ~(sz-1);
-	if (pte_end < end)
-		end = pte_end;
-
-	pte = *ptep;
-	mask = _PAGE_PRESENT | _PAGE_USER;
-	if (write)
-		mask |= _PAGE_RW;
-
-	if ((pte_val(pte) & mask) != mask)
-		return 0;
-
-	/* hugepages are never "special" */
-	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
-
-	refs = 0;
-	head = pte_page(pte);
-
-	page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
-	tail = page;
-	do {
-		VM_BUG_ON(compound_head(page) != head);
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
-
-	if (!page_cache_add_speculative(head, refs)) {
-		*nr -= refs;
-		return 0;
-	}
-
-	if (unlikely(pte_val(pte) != pte_val(*ptep))) {
-		/* Could be optimized better */
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
-		return 0;
-	}
-
-	/*
-	 * Any tail page need their mapcount reference taken before we
-	 * return.
-	 */
-	while (refs--) {
-		if (PageTail(tail))
-			get_huge_page_tail(tail);
-		tail++;
-	}
-
-	return 1;
 }
 
 static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
···
 			kunmap_atomic(start);
 		}
 	}
+}
+
+#endif /* CONFIG_HUGETLB_PAGE */
+
+/*
+ * We have 4 cases for pgds and pmds:
+ * (1) invalid (all zeroes)
+ * (2) pointer to next table, as normal; bottom 6 bits == 0
+ * (3) leaf pte for huge page, bottom two bits != 00
+ * (4) hugepd pointer, bottom two bits == 00, next 4 bits indicate size of table
+ *
+ * So long as we atomically load page table pointers we are safe against teardown,
+ * we can follow the address down to the the page and take a ref on it.
+ */
+
+pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift)
+{
+	pgd_t pgd, *pgdp;
+	pud_t pud, *pudp;
+	pmd_t pmd, *pmdp;
+	pte_t *ret_pte;
+	hugepd_t *hpdp = NULL;
+	unsigned pdshift = PGDIR_SHIFT;
+
+	if (shift)
+		*shift = 0;
+
+	pgdp = pgdir + pgd_index(ea);
+	pgd  = ACCESS_ONCE(*pgdp);
+	/*
+	 * Always operate on the local stack value. This make sure the
+	 * value don't get updated by a parallel THP split/collapse,
+	 * page fault or a page unmap. The return pte_t * is still not
+	 * stable. So should be checked there for above conditions.
+	 */
+	if (pgd_none(pgd))
+		return NULL;
+	else if (pgd_huge(pgd)) {
+		ret_pte = (pte_t *) pgdp;
+		goto out;
+	} else if (is_hugepd(&pgd))
+		hpdp = (hugepd_t *)&pgd;
+	else {
+		/*
+		 * Even if we end up with an unmap, the pgtable will not
+		 * be freed, because we do an rcu free and here we are
+		 * irq disabled
+		 */
+		pdshift = PUD_SHIFT;
+		pudp = pud_offset(&pgd, ea);
+		pud  = ACCESS_ONCE(*pudp);
+
+		if (pud_none(pud))
+			return NULL;
+		else if (pud_huge(pud)) {
+			ret_pte = (pte_t *) pudp;
+			goto out;
+		} else if (is_hugepd(&pud))
+			hpdp = (hugepd_t *)&pud;
+		else {
+			pdshift = PMD_SHIFT;
+			pmdp = pmd_offset(&pud, ea);
+			pmd  = ACCESS_ONCE(*pmdp);
+			/*
+			 * A hugepage collapse is captured by pmd_none, because
+			 * it mark the pmd none and do a hpte invalidate.
+			 *
+			 * A hugepage split is captured by pmd_trans_splitting
+			 * because we mark the pmd trans splitting and do a
+			 * hpte invalidate
+			 *
+			 */
+			if (pmd_none(pmd) || pmd_trans_splitting(pmd))
+				return NULL;
+
+			if (pmd_huge(pmd) || pmd_large(pmd)) {
+				ret_pte = (pte_t *) pmdp;
+				goto out;
+			} else if (is_hugepd(&pmd))
+				hpdp = (hugepd_t *)&pmd;
+			else
+				return pte_offset_kernel(&pmd, ea);
+		}
+	}
+	if (!hpdp)
+		return NULL;
+
+	ret_pte = hugepte_offset(hpdp, ea, pdshift);
+	pdshift = hugepd_shift(*hpdp);
+out:
+	if (shift)
+		*shift = pdshift;
+	return ret_pte;
+}
+EXPORT_SYMBOL_GPL(find_linux_pte_or_hugepte);
+
+int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
+		unsigned long end, int write, struct page **pages, int *nr)
+{
+	unsigned long mask;
+	unsigned long pte_end;
+	struct page *head, *page, *tail;
+	pte_t pte;
+	int refs;
+
+	pte_end = (addr + sz) & ~(sz-1);
+	if (pte_end < end)
+		end = pte_end;
+
+	pte = ACCESS_ONCE(*ptep);
+	mask = _PAGE_PRESENT | _PAGE_USER;
+	if (write)
+		mask |= _PAGE_RW;
+
+	if ((pte_val(pte) & mask) != mask)
+		return 0;
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	/*
+	 * check for splitting here
+	 */
+	if (pmd_trans_splitting(pte_pmd(pte)))
+		return 0;
+#endif
+
+	/* hugepages are never "special" */
+	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+
+	refs = 0;
+	head = pte_page(pte);
+
+	page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
+	tail = page;
+	do {
+		VM_BUG_ON(compound_head(page) != head);
+		pages[*nr] = page;
+		(*nr)++;
+		page++;
+		refs++;
+	} while (addr += PAGE_SIZE, addr != end);
+
+	if (!page_cache_add_speculative(head, refs)) {
+		*nr -= refs;
+		return 0;
+	}
+
+	if (unlikely(pte_val(pte) != pte_val(*ptep))) {
+		/* Could be optimized better */
+		*nr -= refs;
+		while (refs--)
+			put_page(head);
+		return 0;
+	}
+
+	/*
+	 * Any tail page need their mapcount reference taken before we
+	 * return.
+	 */
+	while (refs--) {
+		if (PageTail(tail))
+			get_huge_page_tail(tail);
+		tail++;
+	}
+
+	return 1;
 }

arch/powerpc/mm/init_64.c

···
 
 static void pmd_ctor(void *addr)
 {
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	memset(addr, 0, PMD_TABLE_SIZE * 2);
+#else
 	memset(addr, 0, PMD_TABLE_SIZE);
+#endif
 }
 
 struct kmem_cache *pgtable_cache[MAX_PGTABLE_INDEX_SIZE];
···
 void pgtable_cache_init(void)
 {
 	pgtable_cache_add(PGD_INDEX_SIZE, pgd_ctor);
-	pgtable_cache_add(PMD_INDEX_SIZE, pmd_ctor);
-	if (!PGT_CACHE(PGD_INDEX_SIZE) || !PGT_CACHE(PMD_INDEX_SIZE))
+	pgtable_cache_add(PMD_CACHE_INDEX, pmd_ctor);
+	if (!PGT_CACHE(PGD_INDEX_SIZE) || !PGT_CACHE(PMD_CACHE_INDEX))
 		panic("Couldn't allocate pgtable caches");
-
 	/* In all current configs, when the PUD index exists it's the
 	 * same size as either the pgd or pmd index.  Verify that the
 	 * initialization above has also created a PUD cache.  This

arch/powerpc/mm/mem.c

···
 		      pte_t *ptep)
 {
 #ifdef CONFIG_PPC_STD_MMU
+	/*
+	 * We don't need to worry about _PAGE_PRESENT here because we are
+	 * called with either mm->page_table_lock held or ptl lock held
+	 */
 	unsigned long access = 0, trap;
 
 	/* We only want HPTEs for linux PTEs that have _PAGE_ACCESSED set */

arch/powerpc/mm/mmu_context_nohash.c

···
 		 */
 		for_each_cpu(cpu, mm_cpumask(mm)) {
 			for (i = cpu_first_thread_sibling(cpu);
-			     i <= cpu_last_thread_sibling(cpu); i++)
-				__set_bit(id, stale_map[i]);
+			     i <= cpu_last_thread_sibling(cpu); i++) {
+				if (stale_map[i])
+					__set_bit(id, stale_map[i]);
+			}
 			cpu = i - 1;
 		}
 		return id;
···
 		/* XXX This clear should ultimately be part of local_flush_tlb_mm */
 		for (i = cpu_first_thread_sibling(cpu);
 		     i <= cpu_last_thread_sibling(cpu); i++) {
-			__clear_bit(id, stale_map[i]);
+			if (stale_map[i])
+				__clear_bit(id, stale_map[i]);
 		}
 	}
 
···
 
 #ifdef CONFIG_SMP
 
-static int __cpuinit mmu_context_cpu_notify(struct notifier_block *self,
-					    unsigned long action, void *hcpu)
+static int mmu_context_cpu_notify(struct notifier_block *self,
+				  unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (unsigned int)(long)hcpu;
 
···
 	return NOTIFY_OK;
 }
 
-static struct notifier_block __cpuinitdata mmu_context_cpu_nb = {
+static struct notifier_block mmu_context_cpu_nb = {
 	.notifier_call	= mmu_context_cpu_notify,
 };
 

arch/powerpc/mm/numa.c

···
  * Figure out to which domain a cpu belongs and stick it there.
  * Return the id of the domain used.
  */
-static int __cpuinit numa_setup_cpu(unsigned long lcpu)
+static int numa_setup_cpu(unsigned long lcpu)
 {
 	int nid = 0;
 	struct device_node *cpu = of_get_cpu_node(lcpu, NULL);
···
 	return nid;
 }
 
-static int __cpuinit cpu_numa_callback(struct notifier_block *nfb,
-			     unsigned long action,
+static int cpu_numa_callback(struct notifier_block *nfb, unsigned long action,
 			     void *hcpu)
 {
 	unsigned long lcpu = (unsigned long)hcpu;
···
 	return ret;
 }
 
-static struct notifier_block __cpuinitdata ppc64_numa_nb = {
+static struct notifier_block ppc64_numa_nb = {
 	.notifier_call = cpu_numa_callback,
 	.priority = 1 /* Must run before sched domains notifier. */
 };
···
 		if (cpu != update->cpu)
 			continue;
 
-		unregister_cpu_under_node(update->cpu, update->old_nid);
 		unmap_cpu_from_node(update->cpu);
 		map_cpu_to_node(update->cpu, update->new_nid);
 		vdso_getcpu_init();
-		register_cpu_under_node(update->cpu, update->new_nid);
 	}
 
 	return 0;
···
 	stop_machine(update_cpu_topology, &updates[0], &updated_cpus);
 
 	for (ud = &updates[0]; ud; ud = ud->next) {
+		unregister_cpu_under_node(ud->cpu, ud->old_nid);
+		register_cpu_under_node(ud->cpu, ud->new_nid);
+
 		dev = get_cpu_device(ud->cpu);
 		if (dev)
 			kobject_uevent(&dev->kobj, KOBJ_CHANGE);

arch/powerpc/mm/pgtable.c

···
 	pud = pud_offset(pgd, addr);
 	BUG_ON(pud_none(*pud));
 	pmd = pmd_offset(pud, addr);
+	/*
+	 * khugepaged to collapse normal pages to hugepage, first set
+	 * pmd to none to force page fault/gup to take mmap_sem. After
+	 * pmd is set to none, we do a pte_clear which does this assertion
+	 * so if we find pmd none, return.
+	 */
+	if (pmd_none(*pmd))
+		return;
 	BUG_ON(!pmd_present(*pmd));
 	assert_spin_locked(pte_lockptr(mm, pmd));
 }

arch/powerpc/mm/pgtable_64.c

···
 EXPORT_SYMBOL(__iounmap);
 EXPORT_SYMBOL(__iounmap_at);
 
+/*
+ * For hugepage we have pfn in the pmd, we use PTE_RPN_SHIFT bits for flags
+ * For PTE page, we have a PTE_FRAG_SIZE (4K) aligned virtual address.
+ */
+struct page *pmd_page(pmd_t pmd)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	if (pmd_trans_huge(pmd))
+		return pfn_to_page(pmd_pfn(pmd));
+#endif
+	return virt_to_page(pmd_page_vaddr(pmd));
+}
+
 #ifdef CONFIG_PPC_64K_PAGES
 static pte_t *get_from_cache(struct mm_struct *mm)
 {
···
 }
 #endif
 #endif /* CONFIG_PPC_64K_PAGES */
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+
+/*
+ * This is called when relaxing access to a hugepage. It's also called in the page
+ * fault path when we don't hit any of the major fault cases, ie, a minor
+ * update of _PAGE_ACCESSED, _PAGE_DIRTY, etc... The generic code will have
+ * handled those two for us, we additionally deal with missing execute
+ * permission here on some processors
+ */
+int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address,
+			  pmd_t *pmdp, pmd_t entry, int dirty)
+{
+	int changed;
+#ifdef CONFIG_DEBUG_VM
+	WARN_ON(!pmd_trans_huge(*pmdp));
+	assert_spin_locked(&vma->vm_mm->page_table_lock);
+#endif
+	changed = !pmd_same(*(pmdp), entry);
+	if (changed) {
+		__ptep_set_access_flags(pmdp_ptep(pmdp), pmd_pte(entry));
+		/*
+		 * Since we are not supporting SW TLB systems, we don't
+		 * have any thing similar to flush_tlb_page_nohash()
+		 */
+	}
+	return changed;
+}
+
+unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr,
+				  pmd_t *pmdp, unsigned long clr)
+{
+
+	unsigned long old, tmp;
+
+#ifdef CONFIG_DEBUG_VM
+	WARN_ON(!pmd_trans_huge(*pmdp));
+	assert_spin_locked(&mm->page_table_lock);
+#endif
+
+#ifdef PTE_ATOMIC_UPDATES
+	__asm__ __volatile__(
+	"1:	ldarx	%0,0,%3\n\
+		andi.	%1,%0,%6\n\
+		bne-	1b \n\
+		andc	%1,%0,%4 \n\
+		stdcx.	%1,0,%3 \n\
+		bne-	1b"
+	: "=&r" (old), "=&r" (tmp), "=m" (*pmdp)
+	: "r" (pmdp), "r" (clr), "m" (*pmdp), "i" (_PAGE_BUSY)
+	: "cc" );
+#else
+	old = pmd_val(*pmdp);
+	*pmdp = __pmd(old & ~clr);
+#endif
+	if (old & _PAGE_HASHPTE)
+		hpte_do_hugepage_flush(mm, addr, pmdp);
+	return old;
+}
+
+pmd_t pmdp_clear_flush(struct vm_area_struct *vma, unsigned long address,
+		       pmd_t *pmdp)
+{
+	pmd_t pmd;
+
+	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+	if (pmd_trans_huge(*pmdp)) {
+		pmd = pmdp_get_and_clear(vma->vm_mm, address, pmdp);
+	} else {
+		/*
+		 * khugepaged calls this for normal pmd
+		 */
+		pmd = *pmdp;
+		pmd_clear(pmdp);
+		/*
+		 * Wait for all pending hash_page to finish. This is needed
+		 * in case of subpage collapse. When we collapse normal pages
+		 * to hugepage, we first clear the pmd, then invalidate all
+		 * the PTE entries. The assumption here is that any low level
+		 * page fault will see a none pmd and take the slow path that
+		 * will wait on mmap_sem. But we could very well be in a
+		 * hash_page with local ptep pointer value. Such a hash page
+		 * can result in adding new HPTE entries for normal subpages.
+		 * That means we could be modifying the page content as we
+		 * copy them to a huge page. So wait for parallel hash_page
+		 * to finish before invalidating HPTE entries. We can do this
+		 * by sending an IPI to all the cpus and executing a dummy
+		 * function there.
+		 */
+		kick_all_cpus_sync();
+		/*
+		 * Now invalidate the hpte entries in the range
+		 * covered by pmd. This make sure we take a
+		 * fault and will find the pmd as none, which will
+		 * result in a major fault which takes mmap_sem and
+		 * hence wait for collapse to complete. Without this
+		 * the __collapse_huge_page_copy can result in copying
+		 * the old content.
+		 */
+		flush_tlb_pmd_range(vma->vm_mm, &pmd, address);
+	}
+	return pmd;
+}
+
+int pmdp_test_and_clear_young(struct vm_area_struct *vma,
+			      unsigned long address, pmd_t *pmdp)
+{
+	return __pmdp_test_and_clear_young(vma->vm_mm, address, pmdp);
+}
+
+/*
+ * We currently remove entries from the hashtable regardless of whether
+ * the entry was young or dirty. The generic routines only flush if the
+ * entry was young or dirty which is not good enough.
+ *
+ * We should be more intelligent about this but for the moment we override
+ * these functions and force a tlb flush unconditionally
+ */
+int pmdp_clear_flush_young(struct vm_area_struct *vma,
+				  unsigned long address, pmd_t *pmdp)
+{
+	return __pmdp_test_and_clear_young(vma->vm_mm, address, pmdp);
+}
+
+/*
+ * We mark the pmd splitting and invalidate all the hpte
+ * entries for this hugepage.
+ */
+void pmdp_splitting_flush(struct vm_area_struct *vma,
+			  unsigned long address, pmd_t *pmdp)
+{
+	unsigned long old, tmp;
+
+	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+
+#ifdef CONFIG_DEBUG_VM
+	WARN_ON(!pmd_trans_huge(*pmdp));
+	assert_spin_locked(&vma->vm_mm->page_table_lock);
+#endif
+
+#ifdef PTE_ATOMIC_UPDATES
+
+	__asm__ __volatile__(
+	"1:	ldarx	%0,0,%3\n\
+		andi.	%1,%0,%6\n\
+		bne-	1b \n\
+		ori	%1,%0,%4 \n\
+		stdcx.	%1,0,%3 \n\
+		bne-	1b"
+	: "=&r" (old), "=&r" (tmp), "=m" (*pmdp)
+	: "r" (pmdp), "i" (_PAGE_SPLITTING), "m" (*pmdp), "i" (_PAGE_BUSY)
+	: "cc" );
+#else
+	old = pmd_val(*pmdp);
+	*pmdp = __pmd(old | _PAGE_SPLITTING);
+#endif
+	/*
+	 * If we didn't had the splitting flag set, go and flush the
+	 * HPTE entries.
+	 */
+	if (!(old & _PAGE_SPLITTING)) {
+		/* We need to flush the hpte */
+		if (old & _PAGE_HASHPTE)
+			hpte_do_hugepage_flush(vma->vm_mm, address, pmdp);
+	}
+}
+
+/*
+ * We want to put the pgtable in pmd and use pgtable for tracking
+ * the base page size hptes
+ */
+void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+				pgtable_t pgtable)
+{
+	pgtable_t *pgtable_slot;
+	assert_spin_locked(&mm->page_table_lock);
+	/*
+	 * we store the pgtable in the second half of PMD
+	 */
+	pgtable_slot = (pgtable_t *)pmdp + PTRS_PER_PMD;
+	*pgtable_slot = pgtable;
+	/*
+	 * expose the deposited pgtable to other cpus.
+	 * before we set the hugepage PTE at pmd level
+	 * hash fault code looks at the deposted pgtable
+	 * to store hash index values.
+	 */
+	smp_wmb();
+}
+
+pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
+{
+	pgtable_t pgtable;
+	pgtable_t *pgtable_slot;
+
+	assert_spin_locked(&mm->page_table_lock);
+	pgtable_slot = (pgtable_t *)pmdp + PTRS_PER_PMD;
+	pgtable = *pgtable_slot;
+	/*
+	 * Once we withdraw, mark the entry NULL.
+	 */
+	*pgtable_slot = NULL;
+	/*
+	 * We store HPTE information in the deposited PTE fragment.
+	 * zero out the content on withdraw.
+	 */
+	memset(pgtable, 0, PTE_FRAG_SIZE);
+	return pgtable;
+}
+
+/*
+ * set a new huge pmd. We should not be called for updating
+ * an existing pmd entry. That should go via pmd_hugepage_update.
+ */
+void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+		pmd_t *pmdp, pmd_t pmd)
+{
+#ifdef CONFIG_DEBUG_VM
+	WARN_ON(!pmd_none(*pmdp));
+	assert_spin_locked(&mm->page_table_lock);
+	WARN_ON(!pmd_trans_huge(pmd));
+#endif
+	return set_pte_at(mm, addr, pmdp_ptep(pmdp), pmd_pte(pmd));
+}
+
+void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
+		     pmd_t *pmdp)
+{
+	pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT);
+}
+
+/*
+ * A linux hugepage PMD was changed and the corresponding hash table entries
+ * neesd to be flushed.
+ */
+void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
+			    pmd_t *pmdp)
+{
+	int ssize, i;
+	unsigned long s_addr;
+	int max_hpte_count;
+	unsigned int psize, valid;
+	unsigned char *hpte_slot_array;
+	unsigned long hidx, vpn, vsid, hash, shift, slot;
+
+	/*
+	 * Flush all the hptes mapping this hugepage
+	 */
+	s_addr = addr & HPAGE_PMD_MASK;
+	hpte_slot_array = get_hpte_slot_array(pmdp);
+	/*
+	 * IF we try to do a HUGE PTE update after a withdraw is done.
+	 * we will find the below NULL. This happens when we do
+	 * split_huge_page_pmd
+	 */
+	if (!hpte_slot_array)
+		return;
+
+	/* get the base page size */
+	psize = get_slice_psize(mm, s_addr);
+
+	if (ppc_md.hugepage_invalidate)
+		return ppc_md.hugepage_invalidate(mm, hpte_slot_array,
+						  s_addr, psize);
+	/*
+	 * No bluk hpte removal support, invalidate each entry
+	 */
+	shift = mmu_psize_defs[psize].shift;
+	max_hpte_count = HPAGE_PMD_SIZE >> shift;
+	for (i = 0; i < max_hpte_count; i++) {
+		/*
+		 * 8 bits per each hpte entries
+		 * 000| [ secondary group (one bit) | hidx (3 bits) | valid bit]
+		 */
+		valid = hpte_valid(hpte_slot_array, i);
+		if (!valid)
+			continue;
+		hidx =  hpte_hash_index(hpte_slot_array, i);
+
+		/* get the vpn */
+		addr = s_addr + (i * (1ul << shift));
+		if (!is_kernel_addr(addr)) {
+			ssize = user_segment_size(addr);
+			vsid = get_vsid(mm->context.id, addr, ssize);
+			WARN_ON(vsid == 0);
+		} else {
+			vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
+			ssize = mmu_kernel_ssize;
+		}
+
+		vpn = hpt_vpn(addr, vsid, ssize);
+		hash = hpt_hash(vpn, shift, ssize);
+		if (hidx & _PTEIDX_SECONDARY)
+			hash = ~hash;
+
+		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
+		slot += hidx & _PTEIDX_GROUP_IX;
+		ppc_md.hpte_invalidate(slot, vpn, psize,
+				       MMU_PAGE_16M, ssize, 0);
+	}
+}
+
+static pmd_t pmd_set_protbits(pmd_t pmd, pgprot_t pgprot)
+{
+	pmd_val(pmd) |= pgprot_val(pgprot);
+	return pmd;
+}
+
+pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot)
+{
+	pmd_t pmd;
+	/*
+	 * For a valid pte, we would have _PAGE_PRESENT or _PAGE_FILE always
+	 * set. We use this to check THP page at pmd level.
+	 * leaf pte for huge page, bottom two bits != 00
+	 */
+	pmd_val(pmd) = pfn << PTE_RPN_SHIFT;
+	pmd_val(pmd) |= _PAGE_THP_HUGE;
+	pmd = pmd_set_protbits(pmd, pgprot);
+	return pmd;
+}
+
+pmd_t mk_pmd(struct page *page, pgprot_t pgprot)
+{
+	return pfn_pmd(page_to_pfn(page), pgprot);
+}
+
+pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
+{
+
+	pmd_val(pmd) &= _HPAGE_CHG_MASK;
+	pmd = pmd_set_protbits(pmd, newprot);
+	return pmd;
+}
+
+/*
+ * This is called at the end of handling a user page fault, when the
+ * fault has been handled by updating a HUGE PMD entry in the linux page tables.
+ * We use it to preload an HPTE into the hash table corresponding to
+ * the updated linux HUGE PMD entry.
+ */
+void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
+			  pmd_t *pmd)
+{
+	return;
+}
+
+pmd_t pmdp_get_and_clear(struct mm_struct *mm,
+			 unsigned long addr, pmd_t *pmdp)
+{
+	pmd_t old_pmd;
+	pgtable_t pgtable;
+	unsigned long old;
+	pgtable_t *pgtable_slot;
+
+	old = pmd_hugepage_update(mm, addr, pmdp, ~0UL);
+	old_pmd = __pmd(old);
+	/*
+	 * We have pmd == none and we are holding page_table_lock.
+	 * So we can safely go and clear the pgtable hash
+	 * index info.
+	 */
+	pgtable_slot = (pgtable_t *)pmdp + PTRS_PER_PMD;
+	pgtable = *pgtable_slot;
+	/*
+	 * Let's zero out old valid and hash index details
+	 * hash fault look at them.
+	 */
+	memset(pgtable, 0, PTE_FRAG_SIZE);
+	return old_pmd;
+}
+
+int has_transparent_hugepage(void)
+{
+	if (!mmu_has_feature(MMU_FTR_16M_PAGE))
+		return 0;
+	/*
+	 * We support THP only if PMD_SIZE is 16MB.
+	 */
+	if (mmu_psize_defs[MMU_PAGE_16M].shift != PMD_SHIFT)
+		return 0;
+	/*
+	 * We need to make sure that we support 16MB hugepage in a segement
+	 * with base page size 64K or 4K. We only enable THP with a PAGE_SIZE
+	 * of 64K.
+	 */
+	/*
+	 * If we have 64K HPTE, we will be using that by default
+	 */
+	if (mmu_psize_defs[MMU_PAGE_64K].shift &&
+	    (mmu_psize_defs[MMU_PAGE_64K].penc[MMU_PAGE_16M] == -1))
+		return 0;
+	/*
+	 * Ok we only have 4K HPTE
+	 */
+	if (mmu_psize_defs[MMU_PAGE_4K].penc[MMU_PAGE_16M] == -1)
+		return 0;
+
+	return 1;
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

arch/powerpc/mm/subpage-prot.c

···
 	up_write(&mm->mmap_sem);
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static int subpage_walk_pmd_entry(pmd_t *pmd, unsigned long addr,
+				  unsigned long end, struct mm_walk *walk)
+{
+	struct vm_area_struct *vma = walk->private;
+	split_huge_page_pmd(vma, addr, pmd);
+	return 0;
+}
+
+static void subpage_mark_vma_nohuge(struct mm_struct *mm, unsigned long addr,
+				    unsigned long len)
+{
+	struct vm_area_struct *vma;
+	struct mm_walk subpage_proto_walk = {
+		.mm = mm,
+		.pmd_entry = subpage_walk_pmd_entry,
+	};
+
+	/*
+	 * We don't try too hard, we just mark all the vma in that range
+	 * VM_NOHUGEPAGE and split them.
+	 */
+	vma = find_vma(mm, addr);
+	/*
+	 * If the range is in unmapped range, just return
+	 */
+	if (vma && ((addr + len) <= vma->vm_start))
+		return;
+
+	while (vma) {
+		if (vma->vm_start >= (addr + len))
+			break;
+		vma->vm_flags |= VM_NOHUGEPAGE;
+		subpage_proto_walk.private = vma;
+		walk_page_range(vma->vm_start, vma->vm_end,
+				&subpage_proto_walk);
+		vma = vma->vm_next;
+	}
+}
+#else
+static void subpage_mark_vma_nohuge(struct mm_struct *mm, unsigned long addr,
+				    unsigned long len)
+{
+	return;
+}
+#endif
+
 /*
  * Copy in a subpage protection map for an address range.
  * The map has 2 bits per 4k subpage, so 32 bits per 64k page.
···
 		return -EFAULT;
 
 	down_write(&mm->mmap_sem);
+	subpage_mark_vma_nohuge(mm, addr, len);
 	for (limit = addr + len; addr < limit; addr = next) {
 		next = pmd_addr_end(addr, limit);
 		err = -ENOMEM;

arch/powerpc/mm/tlb_hash64.c

···
 void __flush_hash_table_range(struct mm_struct *mm, unsigned long start,
 			      unsigned long end)
 {
+	int hugepage_shift;
 	unsigned long flags;
 
 	start = _ALIGN_DOWN(start, PAGE_SIZE);
···
 	local_irq_save(flags);
 	arch_enter_lazy_mmu_mode();
 	for (; start < end; start += PAGE_SIZE) {
-		pte_t *ptep = find_linux_pte(mm->pgd, start);
+		pte_t *ptep = find_linux_pte_or_hugepte(mm->pgd, start,
+							&hugepage_shift);
 		unsigned long pte;
 
 		if (ptep == NULL)
···
 		pte = pte_val(*ptep);
 		if (!(pte & _PAGE_HASHPTE))
 			continue;
-		hpte_need_flush(mm, start, ptep, pte, 0);
+		if (unlikely(hugepage_shift && pmd_trans_huge(*(pmd_t *)pte)))
+			hpte_do_hugepage_flush(mm, start, (pmd_t *)pte);
+		else
+			hpte_need_flush(mm, start, ptep, pte, 0);
+	}
+	arch_leave_lazy_mmu_mode();
+	local_irq_restore(flags);
+}
+
+void flush_tlb_pmd_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr)
+{
+	pte_t *pte;
+	pte_t *start_pte;
+	unsigned long flags;
+
+	addr = _ALIGN_DOWN(addr, PMD_SIZE);
+	/* Note: Normally, we should only ever use a batch within a
+	 * PTE locked section. This violates the rule, but will work
+	 * since we don't actually modify the PTEs, we just flush the
+	 * hash while leaving the PTEs intact (including their reference
+	 * to being hashed). This is not the most performance oriented
+	 * way to do things but is fine for our needs here.
+	 */
+	local_irq_save(flags);
+	arch_enter_lazy_mmu_mode();
+	start_pte = pte_offset_map(pmd, addr);
+	for (pte = start_pte; pte < start_pte + PTRS_PER_PTE; pte++) {
+		unsigned long pteval = pte_val(*pte);
+		if (pteval & _PAGE_HASHPTE)
+			hpte_need_flush(mm, addr, pte, pteval, 0);
+		addr += PAGE_SIZE;
 	}
 	arch_leave_lazy_mmu_mode();
 	local_irq_restore(flags);

arch/powerpc/mm/tlb_nohash.c

···
 	__early_init_mmu(1);
 }
 
-void __cpuinit early_init_mmu_secondary(void)
+void early_init_mmu_secondary(void)
 {
 	__early_init_mmu(0);
 }

arch/powerpc/perf/core-book3s.c

···
 
 #define MMCR0_FCHV		0
 #define MMCR0_PMCjCE		MMCR0_PMCnCE
+#define MMCR0_FC56		0
+#define MMCR0_PMAO		0
+#define MMCR0_EBE		0
+#define MMCR0_PMCC		0
+#define MMCR0_PMCC_U6		0
 
 #define SPRN_MMCRA		SPRN_MMCR2
 #define MMCRA_SAMPLE_ENABLE	0
···
 static inline int siar_valid(struct pt_regs *regs)
 {
 	return 1;
+}
+
+static bool is_ebb_event(struct perf_event *event) { return false; }
+static int ebb_event_check(struct perf_event *event) { return 0; }
+static void ebb_event_add(struct perf_event *event) { }
+static void ebb_switch_out(unsigned long mmcr0) { }
+static unsigned long ebb_switch_in(bool ebb, unsigned long mmcr0)
+{
+	return mmcr0;
 }
 
 static inline void power_pmu_bhrb_enable(struct perf_event *event) {}
···
 	return;
 }
 
+static bool is_ebb_event(struct perf_event *event)
+{
+	/*
+	 * This could be a per-PMU callback, but we'd rather avoid the cost. We
+	 * check that the PMU supports EBB, meaning those that don't can still
+	 * use bit 63 of the event code for something else if they wish.
+	 */
+	return (ppmu->flags & PPMU_EBB) &&
+	       ((event->attr.config >> EVENT_CONFIG_EBB_SHIFT) & 1);
+}
+
+static int ebb_event_check(struct perf_event *event)
+{
+	struct perf_event *leader = event->group_leader;
+
+	/* Event and group leader must agree on EBB */
+	if (is_ebb_event(leader) != is_ebb_event(event))
+		return -EINVAL;
+
+	if (is_ebb_event(event)) {
+		if (!(event->attach_state & PERF_ATTACH_TASK))
+			return -EINVAL;
+
+		if (!leader->attr.pinned || !leader->attr.exclusive)
+			return -EINVAL;
+
+		if (event->attr.inherit || event->attr.sample_period ||
+		    event->attr.enable_on_exec || event->attr.freq)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void ebb_event_add(struct perf_event *event)
+{
+	if (!is_ebb_event(event) || current->thread.used_ebb)
+		return;
+
+	/*
+	 * IFF this is the first time we've added an EBB event, set
+	 * PMXE in the user MMCR0 so we can detect when it's cleared by
+	 * userspace. We need this so that we can context switch while
+	 * userspace is in the EBB handler (where PMXE is 0).
+	 */
+	current->thread.used_ebb = 1;
+	current->thread.mmcr0 |= MMCR0_PMXE;
+}
+
+static void ebb_switch_out(unsigned long mmcr0)
+{
+	if (!(mmcr0 & MMCR0_EBE))
+		return;
+
+	current->thread.siar  = mfspr(SPRN_SIAR);
+	current->thread.sier  = mfspr(SPRN_SIER);
+	current->thread.sdar  = mfspr(SPRN_SDAR);
+	current->thread.mmcr0 = mmcr0 & MMCR0_USER_MASK;
+	current->thread.mmcr2 = mfspr(SPRN_MMCR2) & MMCR2_USER_MASK;
+}
+
+static unsigned long ebb_switch_in(bool ebb, unsigned long mmcr0)
+{
+	if (!ebb)
+		goto out;
+
+	/* Enable EBB and read/write to all 6 PMCs for userspace */
+	mmcr0 |= MMCR0_EBE | MMCR0_PMCC_U6;
+
+	/* Add any bits from the user reg, FC or PMAO */
+	mmcr0 |= current->thread.mmcr0;
+
+	/* Be careful not to set PMXE if userspace had it cleared */
+	if (!(current->thread.mmcr0 & MMCR0_PMXE))
+		mmcr0 &= ~MMCR0_PMXE;
+
+	mtspr(SPRN_SIAR, current->thread.siar);
+	mtspr(SPRN_SIER, current->thread.sier);
+	mtspr(SPRN_SDAR, current->thread.sdar);
+	mtspr(SPRN_MMCR2, current->thread.mmcr2);
+out:
+	return mmcr0;
+}
 #endif /* CONFIG_PPC64 */
 
 static void perf_event_interrupt(struct pt_regs *regs);
···
 
 	if (!event->hw.idx)
 		return;
+
+	if (is_ebb_event(event)) {
+		val = read_pmc(event->hw.idx);
+		local64_set(&event->hw.prev_count, val);
+		return;
+	}
+
 	/*
 	 * Performance monitor interrupts come even when interrupts
 	 * are soft-disabled, as long as interrupts are hard-enabled.
···
 static void power_pmu_disable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw;
-	unsigned long flags;
+	unsigned long flags, mmcr0, val;
 
 	if (!ppmu)
 		return;
···
 	cpuhw = &__get_cpu_var(cpu_hw_events);
 
 	if (!cpuhw->disabled) {
-		cpuhw->disabled = 1;
-		cpuhw->n_added = 0;
-
 		/*
 		 * Check if we ever enabled the PMU on this cpu.
 		 */
···
 			ppc_enable_pmcs();
 			cpuhw->pmcs_enabled = 1;
 		}
+
+		/*
+		 * Set the 'freeze counters' bit, clear EBE/PMCC/PMAO/FC56.
+		 */
+		val  = mmcr0 = mfspr(SPRN_MMCR0);
+		val |= MMCR0_FC;
+		val &= ~(MMCR0_EBE | MMCR0_PMCC | MMCR0_PMAO | MMCR0_FC56);
+
+		/*
+		 * The barrier is to make sure the mtspr has been
+		 * executed and the PMU has frozen the events etc.
+		 * before we return.
+		 */
+		write_mmcr0(cpuhw, val);
+		mb();
 
 		/*
 		 * Disable instruction sampling if it was enabled
···
 			mb();
 		}
 
-		/*
-		 * Set the 'freeze counters' bit.
-		 * The barrier is to make sure the mtspr has been
-		 * executed and the PMU has frozen the events
-		 * before we return.
-		 */
-		write_mmcr0(cpuhw, mfspr(SPRN_MMCR0) | MMCR0_FC);
-		mb();
+		cpuhw->disabled = 1;
+		cpuhw->n_added = 0;
+
+		ebb_switch_out(mmcr0);
 	}
+
 	local_irq_restore(flags);
 }
 
···
 	struct cpu_hw_events *cpuhw;
 	unsigned long flags;
 	long i;
-	unsigned long val;
+	unsigned long val, mmcr0;
 	s64 left;
 	unsigned int hwc_index[MAX_HWEVENTS];
 	int n_lim;
 	int idx;
+	bool ebb;
 
 	if (!ppmu)
 		return;
 	local_irq_save(flags);
+
 	cpuhw = &__get_cpu_var(cpu_hw_events);
-	if (!cpuhw->disabled) {
-		local_irq_restore(flags);
-		return;
+	if (!cpuhw->disabled)
+		goto out;
+
+	if (cpuhw->n_events == 0) {
+		ppc_set_pmu_inuse(0);
+		goto out;
 	}
+
 	cpuhw->disabled = 0;
+
+	/*
+	 * EBB requires an exclusive group and all events must have the EBB
+	 * flag set, or not set, so we can just check a single event. Also we
+	 * know we have at least one event.
+	 */
+	ebb = is_ebb_event(cpuhw->event[0]);
 
 	/*
 	 * If we didn't change anything, or only removed events,
···
 	if (!cpuhw->n_added) {
 		mtspr(SPRN_MMCRA, cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE);
 		mtspr(SPRN_MMCR1, cpuhw->mmcr[1]);
-		if (cpuhw->n_events == 0)
-			ppc_set_pmu_inuse(0);
 		goto out_enable;
 	}
 
···
 			++n_lim;
 			continue;
 		}
-		val = 0;
-		if (event->hw.sample_period) {
-			left = local64_read(&event->hw.period_left);
-			if (left < 0x80000000L)
-				val = 0x80000000L - left;
+
+		if (ebb)
+			val = local64_read(&event->hw.prev_count);
+		else {
+			val = 0;
+			if (event->hw.sample_period) {
+				left = local64_read(&event->hw.period_left);
+				if (left < 0x80000000L)
+					val = 0x80000000L - left;
+			}
+			local64_set(&event->hw.prev_count, val);
 		}
-		local64_set(&event->hw.prev_count, val);
+
 		event->hw.idx = idx;
 		if (event->hw.state & PERF_HES_STOPPED)
 			val = 0;
 		write_pmc(idx, val);
+
 		perf_event_update_userpage(event);
 	}
 	cpuhw->n_limited = n_lim;
 	cpuhw->mmcr[0] |= MMCR0_PMXE | MMCR0_FCECE;
 
  out_enable:
+	mmcr0 = ebb_switch_in(ebb, cpuhw->mmcr[0]);
+
 	mb();
-	write_mmcr0(cpuhw, cpuhw->mmcr[0]);
+	write_mmcr0(cpuhw, mmcr0);
 
 	/*
 	 * Enable instruction sampling if necessary
···
 	event->hw.config = cpuhw->events[n0];
 
 nocheck:
+	ebb_event_add(event);
+
 	++cpuhw->n_events;
 	++cpuhw->n_added;
 
···
 		}
 	}
 
+	/* Extra checks for EBB */
+	err = ebb_event_check(event);
+	if (err)
+		return err;
+
 	/*
 	 * If this is in a group, check if it can go on with all the
 	 * other hardware events in the group.  We assume the event
···
 	event->hw.event_base = cflags[n];
 	event->hw.last_period = event->hw.sample_period;
 	local64_set(&event->hw.period_left, event->hw.last_period);
+
+	/*
+	 * For EBB events we just context switch the PMC value, we don't do any
+	 * of the sample_period logic. We use hw.prev_count for this.
+	 */
+	if (is_ebb_event(event))
+		local64_set(&event->hw.prev_count, 0);
 
 	/*
 	 * See if we need to reserve the PMU.
···
 	cpuhw->mmcr[0] = MMCR0_FC;
 }
 
-static int __cpuinit
+static int
 power_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (long)hcpu;
···
 	return NOTIFY_OK;
 }
 
-int __cpuinit register_power_pmu(struct power_pmu *pmu)
+int register_power_pmu(struct power_pmu *pmu)
 {
 	if (ppmu)
 		return -EBUSY;		/* something's already registered */

arch/powerpc/perf/power8-pmu.c

···
  *
  *        60        56        52        48        44        40        36        32
  * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
- *                                     [      thresh_cmp     ]   [  thresh_ctl   ]
- *                                                                       |
- *                                       thresh start/stop OR FAB match -*
+ *   |                                 [      thresh_cmp     ]   [  thresh_ctl   ]
+ *   |                                                                   |
+ *   *- EBB (Linux)                      thresh start/stop OR FAB match -*
  *
  *        28        24        20        16        12         8         4         0
  * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
···
  *
  */
 
+#define EVENT_EBB_MASK		1ull
 #define EVENT_THR_CMP_SHIFT	40	/* Threshold CMP value */
 #define EVENT_THR_CMP_MASK	0x3ff
 #define EVENT_THR_CTL_SHIFT	32	/* Threshold control value (start/stop) */
···
 #define EVENT_IS_MARKED		(EVENT_MARKED_MASK << EVENT_MARKED_SHIFT)
 #define EVENT_PSEL_MASK		0xff	/* PMCxSEL value */
 
+#define EVENT_VALID_MASK	\
+	((EVENT_THRESH_MASK    << EVENT_THRESH_SHIFT)		|	\
+	 (EVENT_SAMPLE_MASK    << EVENT_SAMPLE_SHIFT)		|	\
+	 (EVENT_CACHE_SEL_MASK << EVENT_CACHE_SEL_SHIFT)	|	\
+	 (EVENT_PMC_MASK       << EVENT_PMC_SHIFT)		|	\
+	 (EVENT_UNIT_MASK      << EVENT_UNIT_SHIFT)		|	\
+	 (EVENT_COMBINE_MASK   << EVENT_COMBINE_SHIFT)		|	\
+	 (EVENT_MARKED_MASK    << EVENT_MARKED_SHIFT)		|	\
+	 (EVENT_EBB_MASK       << EVENT_CONFIG_EBB_SHIFT)	|	\
+	  EVENT_PSEL_MASK)
+
 /* MMCRA IFM bits - POWER8 */
 #define	POWER8_MMCRA_IFM1		0x0000000040000000UL
 #define	POWER8_MMCRA_IFM2		0x0000000080000000UL
···
  *
  *        28        24        20        16        12         8         4         0
  * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
- *                       [ ]   [  sample ]   [     ]   [6] [5]   [4] [3]   [2] [1]
- *                        |                     |
- *      L1 I/D qualifier -*                     |      Count of events for each PMC.
- *                                              |        p1, p2, p3, p4, p5, p6.
+ *                   |   [ ]   [  sample ]   [     ]   [6] [5]   [4] [3]   [2] [1]
+ *              EBB -*    |                     |
+ *                        |                     |      Count of events for each PMC.
+ *      L1 I/D qualifier -*                     |        p1, p2, p3, p4, p5, p6.
  *                     nc - number of counters -*
  *
  * The PMC fields P1..P6, and NC, are adder fields. As we accumulate constraints
···
 /* We just throw all the threshold bits into the constraint */
 #define CNST_THRESH_VAL(v)	(((v) & EVENT_THRESH_MASK) << 32)
 #define CNST_THRESH_MASK	CNST_THRESH_VAL(EVENT_THRESH_MASK)
+
+#define CNST_EBB_VAL(v)		(((v) & EVENT_EBB_MASK) << 24)
+#define CNST_EBB_MASK		CNST_EBB_VAL(EVENT_EBB_MASK)
 
 #define CNST_L1_QUAL_VAL(v)	(((v) & 3) << 22)
 #define CNST_L1_QUAL_MASK	CNST_L1_QUAL_VAL(3)
···
 
 static int power8_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp)
 {
-	unsigned int unit, pmc, cache;
+	unsigned int unit, pmc, cache, ebb;
 	unsigned long mask, value;
 
 	mask = value = 0;
 
-	pmc   = (event >> EVENT_PMC_SHIFT)       & EVENT_PMC_MASK;
-	unit  = (event >> EVENT_UNIT_SHIFT)      & EVENT_UNIT_MASK;
-	cache = (event >> EVENT_CACHE_SEL_SHIFT) & EVENT_CACHE_SEL_MASK;
+	if (event & ~EVENT_VALID_MASK)
+		return -1;
+
+	pmc   = (event >> EVENT_PMC_SHIFT)        & EVENT_PMC_MASK;
+	unit  = (event >> EVENT_UNIT_SHIFT)       & EVENT_UNIT_MASK;
+	cache = (event >> EVENT_CACHE_SEL_SHIFT)  & EVENT_CACHE_SEL_MASK;
+	ebb   = (event >> EVENT_CONFIG_EBB_SHIFT) & EVENT_EBB_MASK;
+
+	/* Clear the EBB bit in the event, so event checks work below */
+	event &= ~(EVENT_EBB_MASK << EVENT_CONFIG_EBB_SHIFT);
 
 	if (pmc) {
 		if (pmc > 6)
···
 		mask  |= CNST_THRESH_MASK;
 		value |= CNST_THRESH_VAL(event >> EVENT_THRESH_SHIFT);
 	}
+
+	if (!pmc && ebb)
+		/* EBB events must specify the PMC */
+		return -1;
+
+	/*
+	 * All events must agree on EBB, either all request it or none.
+	 * EBB events are pinned & exclusive, so this should never actually
+	 * hit, but we leave it as a fallback in case.
+	 */
+	mask  |= CNST_EBB_VAL(ebb);
+	value |= CNST_EBB_MASK;
 
 	*maskp = mask;
 	*valp = value;
···
 
 	if (pmc_inuse & 0x7c)
 		mmcr[0] |= MMCR0_PMCjCE;
+
+	/* If we're not using PMC 5 or 6, freeze them */
+	if (!(pmc_inuse & 0x60))
+		mmcr[0] |= MMCR0_FC56;
 
 	mmcr[1] = mmcr1;
 	mmcr[2] = mmcra;
···
 	.get_constraint		= power8_get_constraint,
 	.get_alternatives	= power8_get_alternatives,
 	.disable_pmc		= power8_disable_pmc,
-	.flags			= PPMU_HAS_SSLOT | PPMU_HAS_SIER | PPMU_BHRB,
+	.flags			= PPMU_HAS_SSLOT | PPMU_HAS_SIER | PPMU_BHRB | PPMU_EBB,
 	.n_generic		= ARRAY_SIZE(power8_generic_events),
 	.generic_events		= power8_generic_events,
 	.attr_groups		= power8_pmu_attr_groups,

arch/powerpc/platforms/44x/currituck.c

···
 }
 
 #ifdef CONFIG_SMP
-static void __cpuinit smp_ppc47x_setup_cpu(int cpu)
+static void smp_ppc47x_setup_cpu(int cpu)
 {
 	mpic_setup_this_cpu();
 }
 
-static int __cpuinit smp_ppc47x_kick_cpu(int cpu)
+static int smp_ppc47x_kick_cpu(int cpu)
 {
 	struct device_node *cpunode = of_get_cpu_node(cpu, NULL);
 	const u64 *spin_table_addr_prop;
···
 	return 1;
 }
 
+static int board_rev = -1;
+static int __init ppc47x_get_board_rev(void)
+{
+	u8 fpga_reg0;
+	void *fpga;
+	struct device_node *np;
+
+	np = of_find_compatible_node(NULL, NULL, "ibm,currituck-fpga");
+	if (!np)
+		goto fail;
+
+	fpga = of_iomap(np, 0);
+	of_node_put(np);
+	if (!fpga)
+		goto fail;
+
+	fpga_reg0 = ioread8(fpga);
+	board_rev = fpga_reg0 & 0x03;
+	pr_info("%s: Found board revision %d\n", __func__, board_rev);
+	iounmap(fpga);
+	return 0;
+
+fail:
+	pr_info("%s: Unable to find board revision\n", __func__);
+	return 0;
+}
+machine_arch_initcall(ppc47x, ppc47x_get_board_rev);
+
 /* Use USB controller should have been hardware swizzled but it wasn't :( */
 static void ppc47x_pci_irq_fixup(struct pci_dev *dev)
 {
 	if (dev->vendor == 0x1033 && (dev->device == 0x0035 ||
 	                              dev->device == 0x00e0)) {
-		dev->irq = irq_create_mapping(NULL, 47);
-		pr_info("%s: Mapping irq 47 %d\n", __func__, dev->irq);
+		if (board_rev == 0) {
+			dev->irq = irq_create_mapping(NULL, 47);
+			pr_info("%s: Mapping irq %d\n", __func__, dev->irq);
+		} else if (board_rev == 2) {
+			dev->irq = irq_create_mapping(NULL, 49);
+			pr_info("%s: Mapping irq %d\n", __func__, dev->irq);
+		} else {
+			pr_alert("%s: Unknown board revision\n", __func__);
+		}
 	}
 }
 

arch/powerpc/platforms/44x/iss4xx.c

···
 }
 
 #ifdef CONFIG_SMP
-static void __cpuinit smp_iss4xx_setup_cpu(int cpu)
+static void smp_iss4xx_setup_cpu(int cpu)
 {
 	mpic_setup_this_cpu();
 }
 
-static int __cpuinit smp_iss4xx_kick_cpu(int cpu)
+static int smp_iss4xx_kick_cpu(int cpu)
 {
 	struct device_node *cpunode = of_get_cpu_node(cpu, NULL);
 	const u64 *spin_table_addr_prop;

arch/powerpc/platforms/512x/mpc5121_ads.c

···
 		mpc83xx_add_bridge(np);
 #endif
 
-#if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE)
-	mpc512x_setup_diu();
-#endif
+	mpc512x_setup_arch();
 }
 
 static void __init mpc5121_ads_init_IRQ(void)
···
 	.probe			= mpc5121_ads_probe,
 	.setup_arch		= mpc5121_ads_setup_arch,
 	.init			= mpc512x_init,
-	.init_early		= mpc512x_init_diu,
+	.init_early		= mpc512x_init_early,
 	.init_IRQ		= mpc5121_ads_init_IRQ,
 	.get_irq		= ipic_get_irq,
 	.calibrate_decr		= generic_calibrate_decr,

arch/powerpc/platforms/512x/mpc512x.h

···
 #ifndef __MPC512X_H__
 #define __MPC512X_H__
 extern void __init mpc512x_init_IRQ(void);
+extern void __init mpc512x_init_early(void);
 extern void __init mpc512x_init(void);
+extern void __init mpc512x_setup_arch(void);
 extern int __init mpc5121_clk_init(void);
-void __init mpc512x_declare_of_platform_devices(void);
 extern const char *mpc512x_select_psc_compat(void);
+extern const char *mpc512x_select_reset_compat(void);
 extern void mpc512x_restart(char *cmd);
-
-#if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE)
-void mpc512x_init_diu(void);
-void mpc512x_setup_diu(void);
-#else
-#define mpc512x_init_diu NULL
-#define mpc512x_setup_diu NULL
-#endif
 
 #endif				/* __MPC512X_H__ */

arch/powerpc/platforms/512x/mpc512x_generic.c

···
 	.name			= "MPC512x generic",
 	.probe			= mpc512x_generic_probe,
 	.init			= mpc512x_init,
-	.init_early		= mpc512x_init_diu,
-	.setup_arch		= mpc512x_setup_diu,
+	.init_early		= mpc512x_init_early,
+	.setup_arch		= mpc512x_setup_arch,
 	.init_IRQ		= mpc512x_init_IRQ,
 	.get_irq		= ipic_get_irq,
 	.calibrate_decr		= generic_calibrate_decr,

arch/powerpc/platforms/512x/mpc512x_shared.c

···
 static void __init mpc512x_restart_init(void)
 {
 	struct device_node *np;
+	const char *reset_compat;
 
-	np = of_find_compatible_node(NULL, NULL, "fsl,mpc5121-reset");
+	reset_compat = mpc512x_select_reset_compat();
+	np = of_find_compatible_node(NULL, NULL, reset_compat);
 	if (!np)
 		return;
 
···
 		;
 }
 
-#if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE)
+#if IS_ENABLED(CONFIG_FB_FSL_DIU)
 
 struct fsl_diu_shared_fb {
 	u8		gamma[0x300];	/* 32-bit aligned! */
···
 	return NULL;
 }
 
+const char *mpc512x_select_reset_compat(void)
+{
+	if (of_machine_is_compatible("fsl,mpc5121"))
+		return "fsl,mpc5121-reset";
+
+	if (of_machine_is_compatible("fsl,mpc5125"))
+		return "fsl,mpc5125-reset";
+
+	return NULL;
+}
+
 static unsigned int __init get_fifo_size(struct device_node *np,
 					 char *prop_name)
 {
···
 	}
 }
 
+void __init mpc512x_init_early(void)
+{
+	mpc512x_restart_init();
+	if (IS_ENABLED(CONFIG_FB_FSL_DIU))
+		mpc512x_init_diu();
+}
+
 void __init mpc512x_init(void)
 {
 	mpc5121_clk_init();
 	mpc512x_declare_of_platform_devices();
-	mpc512x_restart_init();
 	mpc512x_psc_fifo_init();
+}
+
+void __init mpc512x_setup_arch(void)
+{
+	if (IS_ENABLED(CONFIG_FB_FSL_DIU))
+		mpc512x_setup_diu();
 }
 
 /**

arch/powerpc/platforms/512x/pdm360ng.c

···
 define_machine(pdm360ng) {
 	.name			= "PDM360NG",
 	.probe			= pdm360ng_probe,
-	.setup_arch		= mpc512x_setup_diu,
+	.setup_arch		= mpc512x_setup_arch,
 	.init			= pdm360ng_init,
-	.init_early		= mpc512x_init_diu,
+	.init_early		= mpc512x_init_early,
 	.init_IRQ		= mpc512x_init_IRQ,
 	.get_irq		= ipic_get_irq,
 	.calibrate_decr		= generic_calibrate_decr,

arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c

···
 	.id_table = mcu_ids,
 };
 
-static int __init mcu_init(void)
-{
-	return i2c_add_driver(&mcu_driver);
-}
-module_init(mcu_init);
-
-static void __exit mcu_exit(void)
-{
-	i2c_del_driver(&mcu_driver);
-}
-module_exit(mcu_exit);
+module_i2c_driver(mcu_driver);
 
 MODULE_DESCRIPTION("Power Management and GPIO expander driver for "
 		   "MPC8349E-mITX-compatible MCU");

arch/powerpc/platforms/85xx/p5020_ds.c

···
 #ifdef CONFIG_PCI
 	.pcibios_fixup_bus	= fsl_pcibios_fixup_bus,
 #endif
-/* coreint doesn't play nice with lazy EE, use legacy mpic for now */
-#ifdef CONFIG_PPC64
-	.get_irq		= mpic_get_irq,
-#else
 	.get_irq		= mpic_get_coreint_irq,
-#endif
 	.restart		= fsl_rstcr_restart,
 	.calibrate_decr		= generic_calibrate_decr,
 	.progress		= udbg_progress,

arch/powerpc/platforms/85xx/p5040_ds.c

···
 #ifdef CONFIG_PCI
 	.pcibios_fixup_bus	= fsl_pcibios_fixup_bus,
 #endif
-/* coreint doesn't play nice with lazy EE, use legacy mpic for now */
-#ifdef CONFIG_PPC64
-	.get_irq		= mpic_get_irq,
-#else
 	.get_irq		= mpic_get_coreint_irq,
-#endif
 	.restart		= fsl_rstcr_restart,
 	.calibrate_decr		= generic_calibrate_decr,
 	.progress		= udbg_progress,

arch/powerpc/platforms/85xx/smp.c

···
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static void __cpuinit smp_85xx_mach_cpu_die(void)
+static void smp_85xx_mach_cpu_die(void)
 {
 	unsigned int cpu = smp_processor_id();
 	u32 tmp;
···
 	return in_be32(&((struct epapr_spin_table *)spin_table)->addr_l);
 }
 
-static int __cpuinit smp_85xx_kick_cpu(int nr)
+static int smp_85xx_kick_cpu(int nr)
 {
 	unsigned long flags;
 	const u64 *cpu_rel_addr;
···
 }
 #endif /* CONFIG_KEXEC */
 
-static void __cpuinit smp_85xx_setup_cpu(int cpu_nr)
+static void smp_85xx_setup_cpu(int cpu_nr)
 {
 	if (smp_85xx_ops.probe == smp_mpic_probe)
 		mpic_setup_this_cpu();

arch/powerpc/platforms/85xx/t4240_qds.c

···
 #ifdef CONFIG_PCI
 	.pcibios_fixup_bus	= fsl_pcibios_fixup_bus,
 #endif
-/* coreint doesn't play nice with lazy EE, use legacy mpic for now */
-#ifdef CONFIG_PPC64
-	.get_irq		= mpic_get_irq,
-#else
 	.get_irq		= mpic_get_coreint_irq,
-#endif
 	.restart		= fsl_rstcr_restart,
 	.calibrate_decr		= generic_calibrate_decr,
 	.progress		= udbg_progress,

arch/powerpc/platforms/8xx/m8xx_setup.c

···
 
 static struct irqaction tbint_irqaction = {
 	.handler = timebase_interrupt,
+	.flags = IRQF_NO_THREAD,
 	.name = "tbint",
 };
 
···
 
 static void cpm_cascade(unsigned int irq, struct irq_desc *desc)
 {
-	struct irq_chip *chip;
-	int cascade_irq;
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	int cascade_irq = cpm_get_irq();
 
-	if ((cascade_irq = cpm_get_irq()) >= 0) {
-		struct irq_desc *cdesc = irq_to_desc(cascade_irq);
-
+	if (cascade_irq >= 0)
 		generic_handle_irq(cascade_irq);
 
-		chip = irq_desc_get_chip(cdesc);
-		chip->irq_eoi(&cdesc->irq_data);
-	}
-
-	chip = irq_desc_get_chip(desc);
 	chip->irq_eoi(&desc->irq_data);
 }
 

arch/powerpc/platforms/Kconfig

···
 	bool
 	default n
 
+config MPIC_TIMER
+	bool "MPIC Global Timer"
+	depends on MPIC && FSL_SOC
+	default n
+	help
+	  The MPIC global timer is a hardware timer inside the
+	  Freescale PIC complying with OpenPIC standard. When the
+	  specified interval times out, the hardware timer generates
+	  an interrupt. The driver currently is only tested on fsl
+	  chip, but it can potentially support other global timers
+	  complying with the OpenPIC standard.
+
+config FSL_MPIC_TIMER_WAKEUP
+	tristate "Freescale MPIC global timer wakeup driver"
+	depends on FSL_SOC &&  MPIC_TIMER && PM
+	default n
+	help
+	  The driver provides a way to wake up the system by MPIC
+	  timer.
+	  e.g. "echo 5 > /sys/devices/system/mpic/timer_wakeup"
+
 config PPC_EPAPR_HV_PIC
 	bool
 	default n
···
 	bool "Support for GX bus based adapters"
 	help
 	  Bus device driver for GX bus based adapters.
+
+config EEH
+	bool
+	depends on (PPC_POWERNV || PPC_PSERIES) && PCI
+	default y
 
 config PPC_MPC106
 	bool

arch/powerpc/platforms/Kconfig.cputype

···
 	select PPC_FPU
 	select PPC_HAVE_PMU_SUPPORT
 	select SYS_SUPPORTS_HUGETLBFS
+	select HAVE_ARCH_TRANSPARENT_HUGEPAGE if PPC_64K_PAGES
 
 config PPC_BOOK3E_64
 	bool "Embedded processors"

arch/powerpc/platforms/cell/beat_htab.c

···
 static long beat_lpar_hpte_updatepp(unsigned long slot,
 				    unsigned long newpp,
 				    unsigned long vpn,
-				    int psize, int ssize, int local)
+				    int psize, int apsize,
+				    int ssize, int local)
 {
 	unsigned long lpar_rc;
 	u64 dummy0, dummy1;
···
 }
 
 static void beat_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn,
-					 int psize, int ssize, int local)
+				      int psize, int apsize,
+				      int ssize, int local)
 {
 	unsigned long want_v;
 	unsigned long lpar_rc;
···
  * already zero.  For now I am paranoid.
  */
 static long beat_lpar_hpte_updatepp_v3(unsigned long slot,
-				    unsigned long newpp,
-				    unsigned long vpn,
-				    int psize, int ssize, int local)
+				       unsigned long newpp,
+				       unsigned long vpn,
+				       int psize, int apsize,
+				       int ssize, int local)
 {
 	unsigned long lpar_rc;
 	unsigned long want_v;
···
 }
 
 static void beat_lpar_hpte_invalidate_v3(unsigned long slot, unsigned long vpn,
-					 int psize, int ssize, int local)
+					 int psize, int apsize,
+					 int ssize, int local)
 {
 	unsigned long want_v;
 	unsigned long lpar_rc;

arch/powerpc/platforms/cell/smp.c

···
 	 * during boot if the user requests it.  Odd-numbered
 	 * cpus are assumed to be secondary threads.
 	 */
-	if (system_state < SYSTEM_RUNNING &&
+	if (system_state == SYSTEM_BOOTING &&
 	    cpu_has_feature(CPU_FTR_SMT) &&
 	    !smt_enabled_at_boot && cpu_thread_in_core(nr) != 0)
 		return 0;

arch/powerpc/platforms/powermac/smp.c

···
 	return NOTIFY_OK;
 }
 
-static struct notifier_block __cpuinitdata smp_core99_cpu_nb = {
+static struct notifier_block smp_core99_cpu_nb = {
 	.notifier_call	= smp_core99_cpu_notify,
 };
 #endif /* CONFIG_HOTPLUG_CPU */

arch/powerpc/platforms/powernv/Makefile

···
 
 obj-$(CONFIG_SMP)	+= smp.o
 obj-$(CONFIG_PCI)	+= pci.o pci-p5ioc2.o pci-ioda.o
+obj-$(CONFIG_EEH)	+= eeh-ioda.o eeh-powernv.o

arch/powerpc/platforms/powernv/eeh-ioda.c

···
+/*
+ * The file intends to implement the functions needed by EEH, which is
+ * built on IODA compliant chip. Actually, lots of functions related
+ * to EEH would be built based on the OPAL APIs.
+ *
+ * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2013.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/bootmem.h>
+#include <linux/debugfs.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/msi.h>
+#include <linux/notifier.h>
+#include <linux/pci.h>
+#include <linux/string.h>
+
+#include <asm/eeh.h>
+#include <asm/eeh_event.h>
+#include <asm/io.h>
+#include <asm/iommu.h>
+#include <asm/msi_bitmap.h>
+#include <asm/opal.h>
+#include <asm/pci-bridge.h>
+#include <asm/ppc-pci.h>
+#include <asm/tce.h>
+
+#include "powernv.h"
+#include "pci.h"
+
+/* Debugging option */
+#ifdef IODA_EEH_DBG_ON
+#define IODA_EEH_DBG(args...)	pr_info(args)
+#else
+#define IODA_EEH_DBG(args...)
+#endif
+
+static char *hub_diag = NULL;
+static int ioda_eeh_nb_init = 0;
+
+static int ioda_eeh_event(struct notifier_block *nb,
+			  unsigned long events, void *change)
+{
+	uint64_t changed_evts = (uint64_t)change;
+
+	/* We simply send special EEH event */
+	if ((changed_evts & OPAL_EVENT_PCI_ERROR) &&
+	    (events & OPAL_EVENT_PCI_ERROR))
+		eeh_send_failure_event(NULL);
+
+	return 0;
+}
+
+static struct notifier_block ioda_eeh_nb = {
+	.notifier_call	= ioda_eeh_event,
+	.next		= NULL,
+	.priority	= 0
+};
+
+#ifdef CONFIG_DEBUG_FS
+static int ioda_eeh_dbgfs_set(void *data, u64 val)
+{
+	struct pci_controller *hose = data;
+	struct pnv_phb *phb = hose->private_data;
+
+	out_be64(phb->regs + 0xD10, val);
+	return 0;
+}
+
+static int ioda_eeh_dbgfs_get(void *data, u64 *val)
+{
+	struct pci_controller *hose = data;
+	struct pnv_phb *phb = hose->private_data;
+
+	*val = in_be64(phb->regs + 0xD10);
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(ioda_eeh_dbgfs_ops, ioda_eeh_dbgfs_get,
+			ioda_eeh_dbgfs_set, "0x%llx\n");
+#endif /* CONFIG_DEBUG_FS */
+
+/**
+ * ioda_eeh_post_init - Chip dependent post initialization
+ * @hose: PCI controller
+ *
+ * The function will be called after eeh PEs and devices
+ * have been built. That means the EEH is ready to supply
+ * service with I/O cache.
+ */
+static int ioda_eeh_post_init(struct pci_controller *hose)
+{
+	struct pnv_phb *phb = hose->private_data;
+	int ret;
+
+	/* Register OPAL event notifier */
+	if (!ioda_eeh_nb_init) {
+		ret = opal_notifier_register(&ioda_eeh_nb);
+		if (ret) {
+			pr_err("%s: Can't register OPAL event notifier (%d)\n",
+			       __func__, ret);
+			return ret;
+		}
+
+		ioda_eeh_nb_init = 1;
+	}
+
+	/* FIXME: Enable it for PHB3 later */
+	if (phb->type == PNV_PHB_IODA1) {
+		if (!hub_diag) {
+			hub_diag = (char *)__get_free_page(GFP_KERNEL |
+							   __GFP_ZERO);
+			if (!hub_diag) {
+				pr_err("%s: Out of memory !\n",
+				       __func__);
+				return -ENOMEM;
+			}
+		}
+
+#ifdef CONFIG_DEBUG_FS
+		if (phb->dbgfs)
+			debugfs_create_file("err_injct", 0600,
+					    phb->dbgfs, hose,
+					    &ioda_eeh_dbgfs_ops);
+#endif
+
+		phb->eeh_state |= PNV_EEH_STATE_ENABLED;
+	}
+
+	return 0;
+}
+
+/**
+ * ioda_eeh_set_option - Set EEH operation or I/O setting
+ * @pe: EEH PE
+ * @option: options
+ *
+ * Enable or disable EEH option for the indicated PE. The
+ * function also can be used to enable I/O or DMA for the
+ * PE.
+ */
+static int ioda_eeh_set_option(struct eeh_pe *pe, int option)
+{
+	s64 ret;
+	u32 pe_no;
+	struct pci_controller *hose = pe->phb;
+	struct pnv_phb *phb = hose->private_data;
+
+	/* Check on PE number */
+	if (pe->addr < 0 || pe->addr >= phb->ioda.total_pe) {
+		pr_err("%s: PE address %x out of range [0, %x] "
+		       "on PHB#%x\n",
+			__func__, pe->addr, phb->ioda.total_pe,
+			hose->global_number);
+		return -EINVAL;
+	}
+
+	pe_no = pe->addr;
+	switch (option) {
+	case EEH_OPT_DISABLE:
+		ret = -EEXIST;
+		break;
+	case EEH_OPT_ENABLE:
+		ret = 0;
+		break;
+	case EEH_OPT_THAW_MMIO:
+		ret = opal_pci_eeh_freeze_clear(phb->opal_id, pe_no,
+				OPAL_EEH_ACTION_CLEAR_FREEZE_MMIO);
+		if (ret) {
+			pr_warning("%s: Failed to enable MMIO for "
+				   "PHB#%x-PE#%x, err=%lld\n",
+				__func__, hose->global_number, pe_no, ret);
+			return -EIO;
+		}
+
+		break;
+	case EEH_OPT_THAW_DMA:
+		ret = opal_pci_eeh_freeze_clear(phb->opal_id, pe_no,
+				OPAL_EEH_ACTION_CLEAR_FREEZE_DMA);
+		if (ret) {
+			pr_warning("%s: Failed to enable DMA for "
+				   "PHB#%x-PE#%x, err=%lld\n",
+				__func__, hose->global_number, pe_no, ret);
+			return -EIO;
+		}
+
+		break;
+	default:
+		pr_warning("%s: Invalid option %d\n", __func__, option);
+		return -EINVAL;
+	}
+
+	return ret;
+}
+
+/**
+ * ioda_eeh_get_state - Retrieve the state of PE
+ * @pe: EEH PE
+ *
+ * The PE's state should be retrieved from the PEEV, PEST
+ * IODA tables. Since the OPAL has exported the function
+ * to do it, it'd better to use that.
+ */
+static int ioda_eeh_get_state(struct eeh_pe *pe)
+{
+	s64 ret = 0;
+	u8 fstate;
+	u16 pcierr;
+	u32 pe_no;
+	int result;
+	struct pci_controller *hose = pe->phb;
+	struct pnv_phb *phb = hose->private_data;
+
+	/*
+	 * Sanity check on PE address. The PHB PE address should
+	 * be zero.
+	 */
+	if (pe->addr < 0 || pe->addr >= phb->ioda.total_pe) {
+		pr_err("%s: PE address %x out of range [0, %x] "
+		       "on PHB#%x\n",
+		       __func__, pe->addr, phb->ioda.total_pe,
+		       hose->global_number);
+		return EEH_STATE_NOT_SUPPORT;
+	}
+
+	/* Retrieve PE status through OPAL */
+	pe_no = pe->addr;
+	ret = opal_pci_eeh_freeze_status(phb->opal_id, pe_no,
+			&fstate, &pcierr, NULL);
+	if (ret) {
+		pr_err("%s: Failed to get EEH status on "
+		       "PHB#%x-PE#%x\n, err=%lld\n",
+		       __func__, hose->global_number, pe_no, ret);
+		return EEH_STATE_NOT_SUPPORT;
+	}
+
+	/* Check PHB status */
+	if (pe->type & EEH_PE_PHB) {
+		result = 0;
+		result &= ~EEH_STATE_RESET_ACTIVE;
+
+		if (pcierr != OPAL_EEH_PHB_ERROR) {
+			result |= EEH_STATE_MMIO_ACTIVE;
+			result |= EEH_STATE_DMA_ACTIVE;
+			result |= EEH_STATE_MMIO_ENABLED;
+			result |= EEH_STATE_DMA_ENABLED;
+		}
+
+		return result;
+	}
+
+	/* Parse result out */
+	result = 0;
+	switch (fstate) {
+	case OPAL_EEH_STOPPED_NOT_FROZEN:
+		result &= ~EEH_STATE_RESET_ACTIVE;
+		result |= EEH_STATE_MMIO_ACTIVE;
+		result |= EEH_STATE_DMA_ACTIVE;
+		result |= EEH_STATE_MMIO_ENABLED;
+		result |= EEH_STATE_DMA_ENABLED;
+		break;
+	case OPAL_EEH_STOPPED_MMIO_FREEZE:
+		result &= ~EEH_STATE_RESET_ACTIVE;
+		result |= EEH_STATE_DMA_ACTIVE;
+		result |= EEH_STATE_DMA_ENABLED;
+		break;
+	case OPAL_EEH_STOPPED_DMA_FREEZE:
+		result &= ~EEH_STATE_RESET_ACTIVE;
+		result |= EEH_STATE_MMIO_ACTIVE;
+		result |= EEH_STATE_MMIO_ENABLED;
+		break;
+	case OPAL_EEH_STOPPED_MMIO_DMA_FREEZE:
+		result &= ~EEH_STATE_RESET_ACTIVE;
+		break;
+	case OPAL_EEH_STOPPED_RESET:
+		result |= EEH_STATE_RESET_ACTIVE;
+		break;
+	case OPAL_EEH_STOPPED_TEMP_UNAVAIL:
+		result |= EEH_STATE_UNAVAILABLE;
+		break;
+	case OPAL_EEH_STOPPED_PERM_UNAVAIL:
+		result |= EEH_STATE_NOT_SUPPORT;
+		break;
+	default:
+		pr_warning("%s: Unexpected EEH status 0x%x "
+			   "on PHB#%x-PE#%x\n",
+			   __func__, fstate, hose->global_number, pe_no);
+	}
+
+	return result;
+}
+
+static int ioda_eeh_pe_clear(struct eeh_pe *pe)
+{
+	struct pci_controller *hose;
+	struct pnv_phb *phb;
+	u32 pe_no;
+	u8 fstate;
+	u16 pcierr;
+	s64 ret;
+
+	pe_no = pe->addr;
+	hose = pe->phb;
+	phb = pe->phb->private_data;
+
+	/* Clear the EEH error on the PE */
+	ret = opal_pci_eeh_freeze_clear(phb->opal_id,
+			pe_no, OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
+	if (ret) {
+		pr_err("%s: Failed to clear EEH error for "
+		       "PHB#%x-PE#%x, err=%lld\n",
+		       __func__, hose->global_number, pe_no, ret);
+		return -EIO;
+	}
+
+	/*
+	 * Read the PE state back and verify that the frozen
+	 * state has been removed.
+	 */
+	ret = opal_pci_eeh_freeze_status(phb->opal_id, pe_no,
+			&fstate, &pcierr, NULL);
+	if (ret) {
+		pr_err("%s: Failed to get EEH status on "
+		       "PHB#%x-PE#%x\n, err=%lld\n",
+		       __func__, hose->global_number, pe_no, ret);
+		return -EIO;
+	}
+
+	if (fstate != OPAL_EEH_STOPPED_NOT_FROZEN) {
+		pr_err("%s: Frozen state not cleared on "
+		       "PHB#%x-PE#%x, sts=%x\n",
+		       __func__, hose->global_number, pe_no, fstate);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static s64 ioda_eeh_phb_poll(struct pnv_phb *phb)
+{
+	s64 rc = OPAL_HARDWARE;
+
+	while (1) {
+		rc = opal_pci_poll(phb->opal_id);
+		if (rc <= 0)
+			break;
+
+		msleep(rc);
+	}
+
+	return rc;
+}
+
+static int ioda_eeh_phb_reset(struct pci_controller *hose, int option)
+{
+	struct pnv_phb *phb = hose->private_data;
+	s64 rc = OPAL_HARDWARE;
+
+	pr_debug("%s: Reset PHB#%x, option=%d\n",
+		 __func__, hose->global_number, option);
+
+	/* Issue PHB complete reset request */
+	if (option == EEH_RESET_FUNDAMENTAL ||
+	    option == EEH_RESET_HOT)
+		rc = opal_pci_reset(phb->opal_id,
+				OPAL_PHB_COMPLETE,
+				OPAL_ASSERT_RESET);
+	else if (option == EEH_RESET_DEACTIVATE)
+		rc = opal_pci_reset(phb->opal_id,
+				OPAL_PHB_COMPLETE,
+				OPAL_DEASSERT_RESET);
+	if (rc < 0)
+		goto out;
+
+	/*
+	 * Poll state of the PHB until the request is done
+	 * successfully.
+	 */
+	rc = ioda_eeh_phb_poll(phb);
+out:
+	if (rc != OPAL_SUCCESS)
+		return -EIO;
+
+	return 0;
+}
+
+static int ioda_eeh_root_reset(struct pci_controller *hose, int option)
+{
+	struct pnv_phb *phb = hose->private_data;
+	s64 rc = OPAL_SUCCESS;
+
+	pr_debug("%s: Reset PHB#%x, option=%d\n",
+		 __func__, hose->global_number, option);
+
+	/*
+	 * During the reset deassert time, we needn't care
+	 * the reset scope because the firmware does nothing
+	 * for fundamental or hot reset during deassert phase.
+	 */
+	if (option == EEH_RESET_FUNDAMENTAL)
+		rc = opal_pci_reset(phb->opal_id,
+				OPAL_PCI_FUNDAMENTAL_RESET,
+				OPAL_ASSERT_RESET);
+	else if (option == EEH_RESET_HOT)
+		rc = opal_pci_reset(phb->opal_id,
+				OPAL_PCI_HOT_RESET,
+				OPAL_ASSERT_RESET);
+	else if (option == EEH_RESET_DEACTIVATE)
+		rc = opal_pci_reset(phb->opal_id,
+				OPAL_PCI_HOT_RESET,
+				OPAL_DEASSERT_RESET);
+	if (rc < 0)
+		goto out;
+
+	/* Poll state of the PHB until the request is done */
+	rc = ioda_eeh_phb_poll(phb);
+out:
+	if (rc != OPAL_SUCCESS)
+		return -EIO;
+
+	return 0;
+}
+
+static int ioda_eeh_bridge_reset(struct pci_controller *hose,
+		struct pci_dev *dev, int option)
+{
+	u16 ctrl;
+
+	pr_debug("%s: Reset device %04x:%02x:%02x.%01x with option %d\n",
+		 __func__, hose->global_number, dev->bus->number,
+		 PCI_SLOT(dev->devfn), PCI_FUNC(dev->devfn), option);
+
+	switch (option) {
+	case EEH_RESET_FUNDAMENTAL:
+	case EEH_RESET_HOT:
+		pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &ctrl);
+		ctrl |= PCI_BRIDGE_CTL_BUS_RESET;
+		pci_write_config_word(dev, PCI_BRIDGE_CONTROL, ctrl);
+		break;
+	case EEH_RESET_DEACTIVATE:
+		pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &ctrl);
+		ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET;
+		pci_write_config_word(dev, PCI_BRIDGE_CONTROL, ctrl);
+		break;
+	}
+
+	return 0;
+}
+
+/**
+ * ioda_eeh_reset - Reset the indicated PE
+ * @pe: EEH PE
+ * @option: reset option
+ *
+ * Do reset on the indicated PE. For PCI bus sensitive PE,
+ * we need to reset the parent p2p bridge. The PHB has to
+ * be reinitialized if the p2p bridge is root bridge. For
+ * PCI device sensitive PE, we will try to reset the device
+ * through FLR. For now, we don't have OPAL APIs to do HARD
+ * reset yet, so all reset would be SOFT (HOT) reset.
+ */
+static int ioda_eeh_reset(struct eeh_pe *pe, int option)
+{
+	struct pci_controller *hose = pe->phb;
+	struct eeh_dev *edev;
+	struct pci_dev *dev;
+	int ret;
+
+	/*
+	 * Anyway, we have to clear the problematic state for the
+	 * corresponding PE. However, we needn't do it if the PE
+	 * is PHB associated. That means the PHB is having fatal
+	 * errors and it needs reset. Further more, the AIB interface
+	 * isn't reliable any more.
+	 */
+	if (!(pe->type & EEH_PE_PHB) &&
+	    (option == EEH_RESET_HOT ||
+	    option == EEH_RESET_FUNDAMENTAL)) {
+		ret = ioda_eeh_pe_clear(pe);
+		if (ret)
+			return -EIO;
+	}
+
+	/*
+	 * The rules applied to reset, either fundamental or hot reset:
+	 *
+	 * We always reset the direct upstream bridge of the PE. If the
+	 * direct upstream bridge isn't root bridge, we always take hot
+	 * reset no matter what option (fundamental or hot) is. Otherwise,
+	 * we should do the reset according to the required option.
+	 */
+	if (pe->type & EEH_PE_PHB) {
+		ret = ioda_eeh_phb_reset(hose, option);
+	} else {
+		if (pe->type & EEH_PE_DEVICE) {
+			/*
+			 * If it's device PE, we didn't refer to the parent
+			 * PCI bus yet. So we have to figure it out indirectly.
+			 */
+			edev = list_first_entry(&pe->edevs,
+					struct eeh_dev, list);
+			dev = eeh_dev_to_pci_dev(edev);
+			dev = dev->bus->self;
+		} else {
+			/*
+			 * If it's bus PE, the parent PCI bus is already there
+			 * and just pick it up.
+			 */
+			dev = pe->bus->self;
+		}
+
+		/*
+		 * Do reset based on the fact that the direct upstream bridge
+		 * is root bridge (port) or not.
+		 */
+		if (dev->bus->number == 0)
+			ret = ioda_eeh_root_reset(hose, option);
+		else
+			ret = ioda_eeh_bridge_reset(hose, dev, option);
+	}
+
+	return ret;
+}
+
+/**
+ * ioda_eeh_get_log - Retrieve error log
+ * @pe: EEH PE
+ * @severity: Severity level of the log
+ * @drv_log: buffer to store the log
+ * @len: space of the log buffer
+ *
+ * The function is used to retrieve error log from P7IOC.
+ */
+static int ioda_eeh_get_log(struct eeh_pe *pe, int severity,
+			    char *drv_log, unsigned long len)
+{
+	s64 ret;
+	unsigned long flags;
+	struct pci_controller *hose = pe->phb;
+	struct pnv_phb *phb = hose->private_data;
+
+	spin_lock_irqsave(&phb->lock, flags);
+
+	ret = opal_pci_get_phb_diag_data2(phb->opal_id,
+			phb->diag.blob, PNV_PCI_DIAG_BUF_SIZE);
+	if (ret) {
+		spin_unlock_irqrestore(&phb->lock, flags);
+		pr_warning("%s: Failed to get log for PHB#%x-PE#%x\n",
+			   __func__, hose->global_number, pe->addr);
+		return -EIO;
+	}
+
+	/*
+	 * FIXME: We probably need log the error in somewhere.
+	 * Lets make it up in future.
+	 */
+	/* pr_info("%s", phb->diag.blob); */
+
+	spin_unlock_irqrestore(&phb->lock, flags);
+
+	return 0;
+}
+
+/**
+ * ioda_eeh_configure_bridge - Configure the PCI bridges for the indicated PE
+ * @pe: EEH PE
+ *
+ * For particular PE, it might have included PCI bridges. In order
+ * to make the PE work properly, those PCI bridges should be configured
+ * correctly. However, we need do nothing on P7IOC since the reset
+ * function will do everything that should be covered by the function.
+ */
+static int ioda_eeh_configure_bridge(struct eeh_pe *pe)
+{
+	return 0;
+}
+
+static void ioda_eeh_hub_diag_common(struct OpalIoP7IOCErrorData *data)
+{
+	/* GEM */
+	pr_info("  GEM XFIR:        %016llx\n", data->gemXfir);
+	pr_info("  GEM RFIR:        %016llx\n", data->gemRfir);
+	pr_info("  GEM RIRQFIR:     %016llx\n", data->gemRirqfir);
+	pr_info("  GEM Mask:        %016llx\n", data->gemMask);
+	pr_info("  GEM RWOF:        %016llx\n", data->gemRwof);
+
+	/* LEM */
+	pr_info("  LEM FIR:         %016llx\n", data->lemFir);
+	pr_info("  LEM Error Mask:  %016llx\n", data->lemErrMask);
+	pr_info("  LEM Action 0:    %016llx\n", data->lemAction0);
+	pr_info("  LEM Action 1:    %016llx\n", data->lemAction1);
+	pr_info("  LEM WOF:         %016llx\n", data->lemWof);
+}
+
+static void ioda_eeh_hub_diag(struct pci_controller *hose)
+{
+	struct pnv_phb *phb = hose->private_data;
+	struct OpalIoP7IOCErrorData *data;
+	long rc;
+
+	data = (struct OpalIoP7IOCErrorData *)ioda_eeh_hub_diag;
+	rc = opal_pci_get_hub_diag_data(phb->hub_id, data, PAGE_SIZE);
+	if (rc != OPAL_SUCCESS) {
+		pr_warning("%s: Failed to get HUB#%llx diag-data (%ld)\n",
+			   __func__, phb->hub_id, rc);
+		return;
+	}
+
+	switch (data->type) {
+	case OPAL_P7IOC_DIAG_TYPE_RGC:
+		pr_info("P7IOC diag-data for RGC\n\n");
+		ioda_eeh_hub_diag_common(data);
+		pr_info("  RGC Status:      %016llx\n", data->rgc.rgcStatus);
+		pr_info("  RGC LDCP:        %016llx\n", data->rgc.rgcLdcp);
+		break;
+	case OPAL_P7IOC_DIAG_TYPE_BI:
+		pr_info("P7IOC diag-data for BI %s\n\n",
+			data->bi.biDownbound ? "Downbound" : "Upbound");
+		ioda_eeh_hub_diag_common(data);
+		pr_info("  BI LDCP 0:       %016llx\n", data->bi.biLdcp0);
+		pr_info("  BI LDCP 1:       %016llx\n", data->bi.biLdcp1);
+		pr_info("  BI LDCP 2:       %016llx\n", data->bi.biLdcp2);
+		pr_info("  BI Fence Status: %016llx\n", data->bi.biFenceStatus);
+		break;
+	case OPAL_P7IOC_DIAG_TYPE_CI:
+		pr_info("P7IOC diag-data for CI Port %d\\nn",
+			data->ci.ciPort);
+		ioda_eeh_hub_diag_common(data);
+		pr_info("  CI Port Status:  %016llx\n", data->ci.ciPortStatus);
+		pr_info("  CI Port LDCP:    %016llx\n", data->ci.ciPortLdcp);
+		break;
+	case OPAL_P7IOC_DIAG_TYPE_MISC:
+		pr_info("P7IOC diag-data for MISC\n\n");
+		ioda_eeh_hub_diag_common(data);
+		break;
+	case OPAL_P7IOC_DIAG_TYPE_I2C:
+		pr_info("P7IOC diag-data for I2C\n\n");
+		ioda_eeh_hub_diag_common(data);
+		break;
+	default:
+		pr_warning("%s: Invalid type of HUB#%llx diag-data (%d)\n",
+			   __func__, phb->hub_id, data->type);
+	}
+}
+
+static void ioda_eeh_p7ioc_phb_diag(struct pci_controller *hose,
+				    struct OpalIoPhbErrorCommon *common)
+{
+	struct OpalIoP7IOCPhbErrorData *data;
+	int i;
+
+	data = (struct OpalIoP7IOCPhbErrorData *)common;
+
+	pr_info("P7IOC PHB#%x Diag-data (Version: %d)\n\n",
+		hose->global_number, common->version);
+
+	pr_info("  brdgCtl:              %08x\n", data->brdgCtl);
+
+	pr_info("  portStatusReg:        %08x\n", data->portStatusReg);
+	pr_info("  rootCmplxStatus:      %08x\n", data->rootCmplxStatus);
+	pr_info("  busAgentStatus:       %08x\n", data->busAgentStatus);
+
+	pr_info("  deviceStatus:         %08x\n", data->deviceStatus);
+	pr_info("  slotStatus:           %08x\n", data->slotStatus);
+	pr_info("  linkStatus:           %08x\n", data->linkStatus);
+	pr_info("  devCmdStatus:         %08x\n", data->devCmdStatus);
+	pr_info("  devSecStatus:         %08x\n", data->devSecStatus);
+
+	pr_info("  rootErrorStatus:      %08x\n", data->rootErrorStatus);
+	pr_info("  uncorrErrorStatus:    %08x\n", data->uncorrErrorStatus);
+	pr_info("  corrErrorStatus:      %08x\n", data->corrErrorStatus);
+	pr_info("  tlpHdr1:              %08x\n", data->tlpHdr1);
+	pr_info("  tlpHdr2:              %08x\n", data->tlpHdr2);
+	pr_info("  tlpHdr3:              %08x\n", data->tlpHdr3);
+	pr_info("  tlpHdr4:              %08x\n", data->tlpHdr4);
+	pr_info("  sourceId:             %08x\n", data->sourceId);
+
+	pr_info("  errorClass:           %016llx\n", data->errorClass);
+	pr_info("  correlator:           %016llx\n", data->correlator);
+	pr_info("  p7iocPlssr:           %016llx\n", data->p7iocPlssr);
+	pr_info("  p7iocCsr:             %016llx\n", data->p7iocCsr);
+	pr_info("  lemFir:               %016llx\n", data->lemFir);
+	pr_info("  lemErrorMask:         %016llx\n", data->lemErrorMask);
+	pr_info("  lemWOF:               %016llx\n", data->lemWOF);
+	pr_info("  phbErrorStatus:       %016llx\n", data->phbErrorStatus);
+	pr_info("  phbFirstErrorStatus:  %016llx\n", data->phbFirstErrorStatus);
+	pr_info("  phbErrorLog0:         %016llx\n", data->phbErrorLog0);
+	pr_info("  phbErrorLog1:         %016llx\n", data->phbErrorLog1);
+	pr_info("  mmioErrorStatus:      %016llx\n", data->mmioErrorStatus);
+	pr_info("  mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus);
+	pr_info("  mmioErrorLog0:        %016llx\n", data->mmioErrorLog0);
+	pr_info("  mmioErrorLog1:        %016llx\n", data->mmioErrorLog1);
+	pr_info("  dma0ErrorStatus:      %016llx\n", data->dma0ErrorStatus);
+	pr_info("  dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus);
+	pr_info("  dma0ErrorLog0:        %016llx\n", data->dma0ErrorLog0);
+	pr_info("  dma0ErrorLog1:        %016llx\n", data->dma0ErrorLog1);
+	pr_info("  dma1ErrorStatus:      %016llx\n", data->dma1ErrorStatus);
+	pr_info("  dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus);
+	pr_info("  dma1ErrorLog0:        %016llx\n", data->dma1ErrorLog0);
+	pr_info("  dma1ErrorLog1:        %016llx\n", data->dma1ErrorLog1);
+
+	for (i = 0; i < OPAL_P7IOC_NUM_PEST_REGS; i++) {
+		if ((data->pestA[i] >> 63) == 0 &&
+		    (data->pestB[i] >> 63) == 0)
+			continue;
+
+		pr_info("  PE[%3d] PESTA:        %016llx\n", i, data->pestA[i]);
+		pr_info("          PESTB:        %016llx\n", data->pestB[i]);
+	}
+}
+
+static void ioda_eeh_phb_diag(struct pci_controller *hose)
+{
+	struct pnv_phb *phb = hose->private_data;
+	struct OpalIoPhbErrorCommon *common;
+	long rc;
+
+	common = (struct OpalIoPhbErrorCommon *)phb->diag.blob;
+	rc = opal_pci_get_phb_diag_data2(phb->opal_id, common, PAGE_SIZE);
+	if (rc != OPAL_SUCCESS) {
+		pr_warning("%s: Failed to get diag-data for PHB#%x (%ld)\n",
+			    __func__, hose->global_number, rc);
+		return;
+	}
+
+	switch (common->ioType) {
+	case OPAL_PHB_ERROR_DATA_TYPE_P7IOC:
+		ioda_eeh_p7ioc_phb_diag(hose, common);
+		break;
+	default:
+		pr_warning("%s: Unrecognized I/O chip %d\n",
+			   __func__, common->ioType);
+	}
+}
+
+static int ioda_eeh_get_phb_pe(struct pci_controller *hose,
+			       struct eeh_pe **pe)
+{
+	struct eeh_pe *phb_pe;
+
+	phb_pe = eeh_phb_pe_get(hose);
+	if (!phb_pe) {
+		pr_warning("%s Can't find PE for PHB#%d\n",
+			   __func__, hose->global_number);
+		return -EEXIST;
+	}
+
+	*pe = phb_pe;
+	return 0;
+}
+
+static int ioda_eeh_get_pe(struct pci_controller *hose,
+			   u16 pe_no, struct eeh_pe **pe)
+{
+	struct eeh_pe *phb_pe, *dev_pe;
+	struct eeh_dev dev;
+
+	/* Find the PHB PE */
+	if (ioda_eeh_get_phb_pe(hose, &phb_pe))
+		return -EEXIST;
+
+	/* Find the PE according to PE# */
+	memset(&dev, 0, sizeof(struct eeh_dev));
+	dev.phb = hose;
+	dev.pe_config_addr = pe_no;
+	dev_pe = eeh_pe_get(&dev);
+	if (!dev_pe) {
+		pr_warning("%s: Can't find PE for PHB#%x - PE#%x\n",
+			   __func__, hose->global_number, pe_no);
+		return -EEXIST;
+	}
+
+	*pe = dev_pe;
+	return 0;
+}
+
+/**
+ * ioda_eeh_next_error - Retrieve next error for EEH core to handle
+ * @pe: The affected PE
+ *
+ * The function is expected to be called by EEH core while it gets
+ * special EEH event (without binding PE). The function calls to
+ * OPAL APIs for next error to handle. The informational error is
+ * handled internally by platform. However, the dead IOC, dead PHB,
+ * fenced PHB and frozen PE should be handled by EEH core eventually.
+ */
+static int ioda_eeh_next_error(struct eeh_pe **pe)
+{
+	struct pci_controller *hose, *tmp;
+	struct pnv_phb *phb;
+	u64 frozen_pe_no;
+	u16 err_type, severity;
+	long rc;
+	int ret = 1;
+
+	/*
+	 * While running here, it's safe to purge the event queue.
+	 * And we should keep the cached OPAL notifier event sychronized
+	 * between the kernel and firmware.
+	 */
+	eeh_remove_event(NULL);
+	opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul);
+
+	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
+		/*
+		 * If the subordinate PCI buses of the PHB has been
+		 * removed, we needn't take care of it any more.
+		 */
+		phb = hose->private_data;
+		if (phb->eeh_state & PNV_EEH_STATE_REMOVED)
+			continue;
+
+		rc = opal_pci_next_error(phb->opal_id,
+				&frozen_pe_no, &err_type, &severity);
+
+		/* If OPAL API returns error, we needn't proceed */
+		if (rc != OPAL_SUCCESS) {
+			IODA_EEH_DBG("%s: Invalid return value on "
+				     "PHB#%x (0x%lx) from opal_pci_next_error",
+				     __func__, hose->global_number, rc);
+			continue;
+		}
+
+		/* If the PHB doesn't have error, stop processing */
+		if (err_type == OPAL_EEH_NO_ERROR ||
+		    severity == OPAL_EEH_SEV_NO_ERROR) {
+			IODA_EEH_DBG("%s: No error found on PHB#%x\n",
+				     __func__, hose->global_number);
+			continue;
+		}
+
+		/*
+		 * Processing the error. We're expecting the error with
+		 * highest priority reported upon multiple errors on the
+		 * specific PHB.
+		 */
+		IODA_EEH_DBG("%s: Error (%d, %d, %d) on PHB#%x\n",
+			err_type, severity, pe_no, hose->global_number);
+		switch (err_type) {
+		case OPAL_EEH_IOC_ERROR:
+			if (severity == OPAL_EEH_SEV_IOC_DEAD) {
+				list_for_each_entry_safe(hose, tmp,
+						&hose_list, list_node) {
+					phb = hose->private_data;
+					phb->eeh_state |= PNV_EEH_STATE_REMOVED;
+				}
+
+				pr_err("EEH: dead IOC detected\n");
+				ret = 4;
+				goto out;
+			} else if (severity == OPAL_EEH_SEV_INF) {
+				pr_info("EEH: IOC informative error "
+					"detected\n");
+				ioda_eeh_hub_diag(hose);
+			}
+
+			break;
+		case OPAL_EEH_PHB_ERROR:
+			if (severity == OPAL_EEH_SEV_PHB_DEAD) {
+				if (ioda_eeh_get_phb_pe(hose, pe))
+					break;
+
+				pr_err("EEH: dead PHB#%x detected\n",
+					hose->global_number);
+				phb->eeh_state |= PNV_EEH_STATE_REMOVED;
+				ret = 3;
+				goto out;
+			} else if (severity == OPAL_EEH_SEV_PHB_FENCED) {
+				if (ioda_eeh_get_phb_pe(hose, pe))
+					break;
+
+				pr_err("EEH: fenced PHB#%x detected\n",
+					hose->global_number);
+				ret = 2;
+				goto out;
+			} else if (severity == OPAL_EEH_SEV_INF) {
+				pr_info("EEH: PHB#%x informative error "
+					"detected\n",
+					hose->global_number);
+				ioda_eeh_phb_diag(hose);
+			}
+
+			break;
+		case OPAL_EEH_PE_ERROR:
+			if (ioda_eeh_get_pe(hose, frozen_pe_no, pe))
+				break;
+
+			pr_err("EEH: Frozen PE#%x on PHB#%x detected\n",
+				(*pe)->addr, (*pe)->phb->global_number);
+			ret = 1;
+			goto out;
+		}
+	}
+
+	ret = 0;
+out:
+	return ret;
+}
+
+struct pnv_eeh_ops ioda_eeh_ops = {
+	.post_init		= ioda_eeh_post_init,
+	.set_option		= ioda_eeh_set_option,
+	.get_state		= ioda_eeh_get_state,
+	.reset			= ioda_eeh_reset,
+	.get_log		= ioda_eeh_get_log,
+	.configure_bridge	= ioda_eeh_configure_bridge,
+	.next_error		= ioda_eeh_next_error
+};

arch/powerpc/platforms/powernv/eeh-powernv.c

···
+/*
+ * The file intends to implement the platform dependent EEH operations on
+ * powernv platform. Actually, the powernv was created in order to fully
+ * hypervisor support.
+ *
+ * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2013.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/atomic.h>
+#include <linux/delay.h>
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/msi.h>
+#include <linux/of.h>
+#include <linux/pci.h>
+#include <linux/proc_fs.h>
+#include <linux/rbtree.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/spinlock.h>
+
+#include <asm/eeh.h>
+#include <asm/eeh_event.h>
+#include <asm/firmware.h>
+#include <asm/io.h>
+#include <asm/iommu.h>
+#include <asm/machdep.h>
+#include <asm/msi_bitmap.h>
+#include <asm/opal.h>
+#include <asm/ppc-pci.h>
+
+#include "powernv.h"
+#include "pci.h"
+
+/**
+ * powernv_eeh_init - EEH platform dependent initialization
+ *
+ * EEH platform dependent initialization on powernv
+ */
+static int powernv_eeh_init(void)
+{
+	/* We require OPALv3 */
+	if (!firmware_has_feature(FW_FEATURE_OPALv3)) {
+		pr_warning("%s: OPALv3 is required !\n", __func__);
+		return -EINVAL;
+	}
+
+	/* Set EEH probe mode */
+	eeh_probe_mode_set(EEH_PROBE_MODE_DEV);
+
+	return 0;
+}
+
+/**
+ * powernv_eeh_post_init - EEH platform dependent post initialization
+ *
+ * EEH platform dependent post initialization on powernv. When
+ * the function is called, the EEH PEs and devices should have
+ * been built. If the I/O cache staff has been built, EEH is
+ * ready to supply service.
+ */
+static int powernv_eeh_post_init(void)
+{
+	struct pci_controller *hose;
+	struct pnv_phb *phb;
+	int ret = 0;
+
+	list_for_each_entry(hose, &hose_list, list_node) {
+		phb = hose->private_data;
+
+		if (phb->eeh_ops && phb->eeh_ops->post_init) {
+			ret = phb->eeh_ops->post_init(hose);
+			if (ret)
+				break;
+		}
+	}
+
+	return ret;
+}
+
+/**
+ * powernv_eeh_dev_probe - Do probe on PCI device
+ * @dev: PCI device
+ * @flag: unused
+ *
+ * When EEH module is installed during system boot, all PCI devices
+ * are checked one by one to see if it supports EEH. The function
+ * is introduced for the purpose. By default, EEH has been enabled
+ * on all PCI devices. That's to say, we only need do necessary
+ * initialization on the corresponding eeh device and create PE
+ * accordingly.
+ *
+ * It's notable that's unsafe to retrieve the EEH device through
+ * the corresponding PCI device. During the PCI device hotplug, which
+ * was possiblly triggered by EEH core, the binding between EEH device
+ * and the PCI device isn't built yet.
+ */
+static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	struct device_node *dn = pci_device_to_OF_node(dev);
+	struct eeh_dev *edev = of_node_to_eeh_dev(dn);
+
+	/*
+	 * When probing the root bridge, which doesn't have any
+	 * subordinate PCI devices. We don't have OF node for
+	 * the root bridge. So it's not reasonable to continue
+	 * the probing.
+	 */
+	if (!dn || !edev)
+		return 0;
+
+	/* Skip for PCI-ISA bridge */
+	if ((dev->class >> 8) == PCI_CLASS_BRIDGE_ISA)
+		return 0;
+
+	/* Initialize eeh device */
+	edev->class_code	= dev->class;
+	edev->mode		= 0;
+	edev->config_addr	= ((dev->bus->number << 8) | dev->devfn);
+	edev->pe_config_addr	= phb->bdfn_to_pe(phb, dev->bus, dev->devfn & 0xff);
+
+	/* Create PE */
+	eeh_add_to_parent_pe(edev);
+
+	/*
+	 * Enable EEH explicitly so that we will do EEH check
+	 * while accessing I/O stuff
+	 *
+	 * FIXME: Enable that for PHB3 later
+	 */
+	if (phb->type == PNV_PHB_IODA1)
+		eeh_subsystem_enabled = 1;
+
+	/* Save memory bars */
+	eeh_save_bars(edev);
+
+	return 0;
+}
+
+/**
+ * powernv_eeh_set_option - Initialize EEH or MMIO/DMA reenable
+ * @pe: EEH PE
+ * @option: operation to be issued
+ *
+ * The function is used to control the EEH functionality globally.
+ * Currently, following options are support according to PAPR:
+ * Enable EEH, Disable EEH, Enable MMIO and Enable DMA
+ */
+static int powernv_eeh_set_option(struct eeh_pe *pe, int option)
+{
+	struct pci_controller *hose = pe->phb;
+	struct pnv_phb *phb = hose->private_data;
+	int ret = -EEXIST;
+
+	/*
+	 * What we need do is pass it down for hardware
+	 * implementation to handle it.
+	 */
+	if (phb->eeh_ops && phb->eeh_ops->set_option)
+		ret = phb->eeh_ops->set_option(pe, option);
+
+	return ret;
+}
+
+/**
+ * powernv_eeh_get_pe_addr - Retrieve PE address
+ * @pe: EEH PE
+ *
+ * Retrieve the PE address according to the given tranditional
+ * PCI BDF (Bus/Device/Function) address.
+ */
+static int powernv_eeh_get_pe_addr(struct eeh_pe *pe)
+{
+	return pe->addr;
+}
+
+/**
+ * powernv_eeh_get_state - Retrieve PE state
+ * @pe: EEH PE
+ * @delay: delay while PE state is temporarily unavailable
+ *
+ * Retrieve the state of the specified PE. For IODA-compitable
+ * platform, it should be retrieved from IODA table. Therefore,
+ * we prefer passing down to hardware implementation to handle
+ * it.
+ */
+static int powernv_eeh_get_state(struct eeh_pe *pe, int *delay)
+{
+	struct pci_controller *hose = pe->phb;
+	struct pnv_phb *phb = hose->private_data;
+	int ret = EEH_STATE_NOT_SUPPORT;
+
+	if (phb->eeh_ops && phb->eeh_ops->get_state) {
+		ret = phb->eeh_ops->get_state(pe);
+
+		/*
+		 * If the PE state is temporarily unavailable,
+		 * to inform the EEH core delay for default
+		 * period (1 second)
+		 */
+		if (delay) {
+			*delay = 0;
+			if (ret & EEH_STATE_UNAVAILABLE)
+				*delay = 1000;
+		}
+	}
+
+	return ret;
+}
+
+/**
+ * powernv_eeh_reset - Reset the specified PE
+ * @pe: EEH PE
+ * @option: reset option
+ *
+ * Reset the specified PE
+ */
+static int powernv_eeh_reset(struct eeh_pe *pe, int option)
+{
+	struct pci_controller *hose = pe->phb;
+	struct pnv_phb *phb = hose->private_data;
+	int ret = -EEXIST;
+
+	if (phb->eeh_ops && phb->eeh_ops->reset)
+		ret = phb->eeh_ops->reset(pe, option);
+
+	return ret;
+}
+
+/**
+ * powernv_eeh_wait_state - Wait for PE state
+ * @pe: EEH PE
+ * @max_wait: maximal period in microsecond
+ *
+ * Wait for the state of associated PE. It might take some time
+ * to retrieve the PE's state.
+ */
+static int powernv_eeh_wait_state(struct eeh_pe *pe, int max_wait)
+{
+	int ret;
+	int mwait;
+
+	while (1) {
+		ret = powernv_eeh_get_state(pe, &mwait);
+
+		/*
+		 * If the PE's state is temporarily unavailable,
+		 * we have to wait for the specified time. Otherwise,
+		 * the PE's state will be returned immediately.
+		 */
+		if (ret != EEH_STATE_UNAVAILABLE)
+			return ret;
+
+		max_wait -= mwait;
+		if (max_wait <= 0) {
+			pr_warning("%s: Timeout getting PE#%x's state (%d)\n",
+				   __func__, pe->addr, max_wait);
+			return EEH_STATE_NOT_SUPPORT;
+		}
+
+		msleep(mwait);
+	}
+
+	return EEH_STATE_NOT_SUPPORT;
+}
+
+/**
+ * powernv_eeh_get_log - Retrieve error log
+ * @pe: EEH PE
+ * @severity: temporary or permanent error log
+ * @drv_log: driver log to be combined with retrieved error log
+ * @len: length of driver log
+ *
+ * Retrieve the temporary or permanent error from the PE.
+ */
+static int powernv_eeh_get_log(struct eeh_pe *pe, int severity,
+			char *drv_log, unsigned long len)
+{
+	struct pci_controller *hose = pe->phb;
+	struct pnv_phb *phb = hose->private_data;
+	int ret = -EEXIST;
+
+	if (phb->eeh_ops && phb->eeh_ops->get_log)
+		ret = phb->eeh_ops->get_log(pe, severity, drv_log, len);
+
+	return ret;
+}
+
+/**
+ * powernv_eeh_configure_bridge - Configure PCI bridges in the indicated PE
+ * @pe: EEH PE
+ *
+ * The function will be called to reconfigure the bridges included
+ * in the specified PE so that the mulfunctional PE would be recovered
+ * again.
+ */
+static int powernv_eeh_configure_bridge(struct eeh_pe *pe)
+{
+	struct pci_controller *hose = pe->phb;
+	struct pnv_phb *phb = hose->private_data;
+	int ret = 0;
+
+	if (phb->eeh_ops && phb->eeh_ops->configure_bridge)
+		ret = phb->eeh_ops->configure_bridge(pe);
+
+	return ret;
+}
+
+/**
+ * powernv_eeh_next_error - Retrieve next EEH error to handle
+ * @pe: Affected PE
+ *
+ * Using OPAL API, to retrieve next EEH error for EEH core to handle
+ */
+static int powernv_eeh_next_error(struct eeh_pe **pe)
+{
+	struct pci_controller *hose;
+	struct pnv_phb *phb = NULL;
+
+	list_for_each_entry(hose, &hose_list, list_node) {
+		phb = hose->private_data;
+		break;
+	}
+
+	if (phb && phb->eeh_ops->next_error)
+		return phb->eeh_ops->next_error(pe);
+
+	return -EEXIST;
+}
+
+static struct eeh_ops powernv_eeh_ops = {
+	.name                   = "powernv",
+	.init                   = powernv_eeh_init,
+	.post_init              = powernv_eeh_post_init,
+	.of_probe               = NULL,
+	.dev_probe              = powernv_eeh_dev_probe,
+	.set_option             = powernv_eeh_set_option,
+	.get_pe_addr            = powernv_eeh_get_pe_addr,
+	.get_state              = powernv_eeh_get_state,
+	.reset                  = powernv_eeh_reset,
+	.wait_state             = powernv_eeh_wait_state,
+	.get_log                = powernv_eeh_get_log,
+	.configure_bridge       = powernv_eeh_configure_bridge,
+	.read_config            = pnv_pci_cfg_read,
+	.write_config           = pnv_pci_cfg_write,
+	.next_error		= powernv_eeh_next_error
+};
+
+/**
+ * eeh_powernv_init - Register platform dependent EEH operations
+ *
+ * EEH initialization on powernv platform. This function should be
+ * called before any EEH related functions.
+ */
+static int __init eeh_powernv_init(void)
+{
+	int ret = -EINVAL;
+
+	if (!machine_is(powernv))
+		return ret;
+
+	ret = eeh_ops_register(&powernv_eeh_ops);
+	if (!ret)
+		pr_info("EEH: PowerNV platform initialized\n");
+	else
+		pr_info("EEH: Failed to initialize PowerNV platform (%d)\n", ret);
+
+	return ret;
+}
+
+early_initcall(eeh_powernv_init);

arch/powerpc/platforms/powernv/opal-wrappers.S

···
 OPAL_CALL(opal_set_slot_led_status,		OPAL_SET_SLOT_LED_STATUS);
 OPAL_CALL(opal_get_epow_status,			OPAL_GET_EPOW_STATUS);
 OPAL_CALL(opal_set_system_attention_led,	OPAL_SET_SYSTEM_ATTENTION_LED);
+OPAL_CALL(opal_pci_next_error,			OPAL_PCI_NEXT_ERROR);
+OPAL_CALL(opal_pci_poll,			OPAL_PCI_POLL);
 OPAL_CALL(opal_pci_msi_eoi,			OPAL_PCI_MSI_EOI);
+OPAL_CALL(opal_pci_get_phb_diag_data2,		OPAL_PCI_GET_PHB_DIAG_DATA2);

arch/powerpc/platforms/powernv/opal.c

···
 #include <linux/of.h>
 #include <linux/of_platform.h>
 #include <linux/interrupt.h>
+#include <linux/notifier.h>
 #include <linux/slab.h>
 #include <asm/opal.h>
 #include <asm/firmware.h>
···
 extern u64 opal_mc_secondary_handler[];
 static unsigned int *opal_irqs;
 static unsigned int opal_irq_count;
+static ATOMIC_NOTIFIER_HEAD(opal_notifier_head);
+static DEFINE_SPINLOCK(opal_notifier_lock);
+static uint64_t last_notified_mask = 0x0ul;
+static atomic_t opal_notifier_hold = ATOMIC_INIT(0);
 
 int __init early_init_dt_scan_opal(unsigned long node,
 				   const char *uname, int depth, void *data)
···
 }
 
 early_initcall(opal_register_exception_handlers);
+
+int opal_notifier_register(struct notifier_block *nb)
+{
+	if (!nb) {
+		pr_warning("%s: Invalid argument (%p)\n",
+			   __func__, nb);
+		return -EINVAL;
+	}
+
+	atomic_notifier_chain_register(&opal_notifier_head, nb);
+	return 0;
+}
+
+static void opal_do_notifier(uint64_t events)
+{
+	unsigned long flags;
+	uint64_t changed_mask;
+
+	if (atomic_read(&opal_notifier_hold))
+		return;
+
+	spin_lock_irqsave(&opal_notifier_lock, flags);
+	changed_mask = last_notified_mask ^ events;
+	last_notified_mask = events;
+	spin_unlock_irqrestore(&opal_notifier_lock, flags);
+
+	/*
+	 * We feed with the event bits and changed bits for
+	 * enough information to the callback.
+	 */
+	atomic_notifier_call_chain(&opal_notifier_head,
+				   events, (void *)changed_mask);
+}
+
+void opal_notifier_update_evt(uint64_t evt_mask,
+			      uint64_t evt_val)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&opal_notifier_lock, flags);
+	last_notified_mask &= ~evt_mask;
+	last_notified_mask |= evt_val;
+	spin_unlock_irqrestore(&opal_notifier_lock, flags);
+}
+
+void opal_notifier_enable(void)
+{
+	int64_t rc;
+	uint64_t evt = 0;
+
+	atomic_set(&opal_notifier_hold, 0);
+
+	/* Process pending events */
+	rc = opal_poll_events(&evt);
+	if (rc == OPAL_SUCCESS && evt)
+		opal_do_notifier(evt);
+}
+
+void opal_notifier_disable(void)
+{
+	atomic_set(&opal_notifier_hold, 1);
+}
 
 int opal_get_chars(uint32_t vtermno, char *buf, int count)
 {
···
 
 	opal_handle_interrupt(virq_to_hw(irq), &events);
 
-	/* XXX TODO: Do something with the events */
+	opal_do_notifier(events);
 
 	return IRQ_HANDLED;
 }

arch/powerpc/platforms/powernv/pci-ioda.c

···
 
 #include <linux/kernel.h>
 #include <linux/pci.h>
+#include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/string.h>
 #include <linux/init.h>
···
 #include <asm/iommu.h>
 #include <asm/tce.h>
 #include <asm/xics.h>
+#include <asm/debug.h>
 
 #include "powernv.h"
 #include "pci.h"
···
 	set_iommu_table_base(&pdev->dev, &pe->tce32_table);
 }
 
+static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		set_iommu_table_base(&dev->dev, &pe->tce32_table);
+		if (dev->subordinate)
+			pnv_ioda_setup_bus_dma(pe, dev->subordinate);
+	}
+}
+
 static void pnv_pci_ioda1_tce_invalidate(struct iommu_table *tbl,
 					 u64 *startp, u64 *endp)
 {
···
 			       TCE_PCI_SWINV_PAIR;
 	}
 	iommu_init_table(tbl, phb->hose->node);
+	iommu_register_group(tbl, pci_domain_nr(pe->pbus), pe->pe_number);
+
+	if (pe->pdev)
+		set_iommu_table_base(&pe->pdev->dev, tbl);
+	else
+		pnv_ioda_setup_bus_dma(pe, pe->pbus);
 
 	return;
  fail:
···
 		tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE;
 	}
 	iommu_init_table(tbl, phb->hose->node);
+
+	if (pe->pdev)
+		set_iommu_table_base(&pe->pdev->dev, tbl);
+	else
+		pnv_ioda_setup_bus_dma(pe, pe->pbus);
 
 	return;
 fail:
···
 	}
 }
 
+static void pnv_pci_ioda_create_dbgfs(void)
+{
+#ifdef CONFIG_DEBUG_FS
+	struct pci_controller *hose, *tmp;
+	struct pnv_phb *phb;
+	char name[16];
+
+	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
+		phb = hose->private_data;
+
+		sprintf(name, "PCI%04x", hose->global_number);
+		phb->dbgfs = debugfs_create_dir(name, powerpc_debugfs_root);
+		if (!phb->dbgfs)
+			pr_warning("%s: Error on creating debugfs on PHB#%x\n",
+				__func__, hose->global_number);
+	}
+#endif /* CONFIG_DEBUG_FS */
+}
+
 static void pnv_pci_ioda_fixup(void)
 {
 	pnv_pci_ioda_setup_PEs();
 	pnv_pci_ioda_setup_seg();
 	pnv_pci_ioda_setup_DMA();
+
+	pnv_pci_ioda_create_dbgfs();
+
+#ifdef CONFIG_EEH
+	eeh_probe_mode_set(EEH_PROBE_MODE_DEV);
+	eeh_addr_cache_build();
+	eeh_init();
+#endif
 }
 
 /*
···
 		       OPAL_ASSERT_RESET);
 }
 
-void __init pnv_pci_init_ioda_phb(struct device_node *np, int ioda_type)
+void __init pnv_pci_init_ioda_phb(struct device_node *np,
+				  u64 hub_id, int ioda_type)
 {
 	struct pci_controller *hose;
 	static int primary = 1;
···
 	hose->first_busno = 0;
 	hose->last_busno = 0xff;
 	hose->private_data = phb;
+	phb->hub_id = hub_id;
 	phb->opal_id = phb_id;
 	phb->type = ioda_type;
 
···
 		phb->ioda.io_size, phb->ioda.io_segsize);
 
 	phb->hose->ops = &pnv_pci_ops;
+#ifdef CONFIG_EEH
+	phb->eeh_ops = &ioda_eeh_ops;
+#endif
 
 	/* Setup RID -> PE mapping function */
 	phb->bdfn_to_pe = pnv_ioda_bdfn_to_pe;
···
 
 void pnv_pci_init_ioda2_phb(struct device_node *np)
 {
-	pnv_pci_init_ioda_phb(np, PNV_PHB_IODA2);
+	pnv_pci_init_ioda_phb(np, 0, PNV_PHB_IODA2);
 }
 
 void __init pnv_pci_init_ioda_hub(struct device_node *np)
···
 	for_each_child_of_node(np, phbn) {
 		/* Look for IODA1 PHBs */
 		if (of_device_is_compatible(phbn, "ibm,ioda-phb"))
-			pnv_pci_init_ioda_phb(phbn, PNV_PHB_IODA1);
+			pnv_pci_init_ioda_phb(phbn, hub_id, PNV_PHB_IODA1);
 	}
 }

arch/powerpc/platforms/powernv/pci-p5ioc2.c

···
 static void pnv_pci_p5ioc2_dma_dev_setup(struct pnv_phb *phb,
 					 struct pci_dev *pdev)
 {
-	if (phb->p5ioc2.iommu_table.it_map == NULL)
+	if (phb->p5ioc2.iommu_table.it_map == NULL) {
 		iommu_init_table(&phb->p5ioc2.iommu_table, phb->hose->node);
+		iommu_register_group(&phb->p5ioc2.iommu_table,
+				pci_domain_nr(phb->hose->bus), phb->opal_id);
+	}
 
 	set_iommu_table_base(&pdev->dev, &phb->p5ioc2.iommu_table);
 }
 
-static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np,
+static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, u64 hub_id,
 					   void *tce_mem, u64 tce_size)
 {
 	struct pnv_phb *phb;
···
 	phb->hose->first_busno = 0;
 	phb->hose->last_busno = 0xff;
 	phb->hose->private_data = phb;
+	phb->hub_id = hub_id;
 	phb->opal_id = phb_id;
 	phb->type = PNV_PHB_P5IOC2;
 	phb->model = PNV_PHB_MODEL_P5IOC2;
···
 	for_each_child_of_node(np, phbn) {
 		if (of_device_is_compatible(phbn, "ibm,p5ioc2-pcix") ||
 		    of_device_is_compatible(phbn, "ibm,p5ioc2-pciex")) {
-			pnv_pci_init_p5ioc2_phb(phbn, tce_mem, tce_per_phb);
+			pnv_pci_init_p5ioc2_phb(phbn, hub_id,
+					tce_mem, tce_per_phb);
 			tce_mem += tce_per_phb;
 		}
 	}

arch/powerpc/platforms/powernv/pci.c

···
 #include <linux/irq.h>
 #include <linux/io.h>
 #include <linux/msi.h>
+#include <linux/iommu.h>
 
 #include <asm/sections.h>
 #include <asm/io.h>
···
 #include <asm/iommu.h>
 #include <asm/tce.h>
 #include <asm/firmware.h>
+#include <asm/eeh_event.h>
+#include <asm/eeh.h>
 
 #include "powernv.h"
 #include "pci.h"
···
 
 	spin_lock_irqsave(&phb->lock, flags);
 
-	rc = opal_pci_get_phb_diag_data(phb->opal_id, phb->diag.blob, PNV_PCI_DIAG_BUF_SIZE);
+	rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob,
+					 PNV_PCI_DIAG_BUF_SIZE);
 	has_diag = (rc == OPAL_SUCCESS);
 
 	rc = opal_pci_eeh_freeze_clear(phb->opal_id, pe_no,
···
 	spin_unlock_irqrestore(&phb->lock, flags);
 }
 
-static void pnv_pci_config_check_eeh(struct pnv_phb *phb, struct pci_bus *bus,
-				     u32 bdfn)
+static void pnv_pci_config_check_eeh(struct pnv_phb *phb,
+				     struct device_node *dn)
 {
 	s64	rc;
 	u8	fstate;
 	u16	pcierr;
 	u32	pe_no;
 
-	/* Get PE# if we support IODA */
-	pe_no = phb->bdfn_to_pe ? phb->bdfn_to_pe(phb, bus, bdfn & 0xff) : 0;
+	/*
+	 * Get the PE#. During the PCI probe stage, we might not
+	 * setup that yet. So all ER errors should be mapped to
+	 * PE#0
+	 */
+	pe_no = PCI_DN(dn)->pe_number;
+	if (pe_no == IODA_INVALID_PE)
+		pe_no = 0;
 
 	/* Read freeze status */
 	rc = opal_pci_eeh_freeze_status(phb->opal_id, pe_no, &fstate, &pcierr,
 					NULL);
 	if (rc) {
-		pr_warning("PCI %d: Failed to read EEH status for PE#%d,"
-			   " err %lld\n", phb->hose->global_number, pe_no, rc);
+		pr_warning("%s: Can't read EEH status (PE#%d) for "
+			   "%s, err %lld\n",
+			   __func__, pe_no, dn->full_name, rc);
 		return;
 	}
-	cfg_dbg(" -> EEH check, bdfn=%04x PE%d fstate=%x\n",
-		bdfn, pe_no, fstate);
+	cfg_dbg(" -> EEH check, bdfn=%04x PE#%d fstate=%x\n",
+		(PCI_DN(dn)->busno << 8) | (PCI_DN(dn)->devfn),
+		pe_no, fstate);
 	if (fstate != 0)
 		pnv_pci_handle_eeh_config(phb, pe_no);
 }
 
-static int pnv_pci_read_config(struct pci_bus *bus,
-			       unsigned int devfn,
-			       int where, int size, u32 *val)
+int pnv_pci_cfg_read(struct device_node *dn,
+		     int where, int size, u32 *val)
 {
-	struct pci_controller *hose = pci_bus_to_host(bus);
-	struct pnv_phb *phb = hose->private_data;
-	u32 bdfn = (((uint64_t)bus->number) << 8) | devfn;
+	struct pci_dn *pdn = PCI_DN(dn);
+	struct pnv_phb *phb = pdn->phb->private_data;
+	u32 bdfn = (pdn->busno << 8) | pdn->devfn;
+#ifdef CONFIG_EEH
+	struct eeh_pe *phb_pe = NULL;
+#endif
 	s64 rc;
-
-	if (hose == NULL)
-		return PCIBIOS_DEVICE_NOT_FOUND;
 
 	switch (size) {
 	case 1: {
···
 	default:
 		return PCIBIOS_FUNC_NOT_SUPPORTED;
 	}
-	cfg_dbg("pnv_pci_read_config bus: %x devfn: %x +%x/%x -> %08x\n",
-		bus->number, devfn, where, size, *val);
+	cfg_dbg("%s: bus: %x devfn: %x +%x/%x -> %08x\n",
+		__func__, pdn->busno, pdn->devfn, where, size, *val);
 
-	/* Check if the PHB got frozen due to an error (no response) */
-	pnv_pci_config_check_eeh(phb, bus, bdfn);
+	/*
+	 * Check if the specified PE has been put into frozen
+	 * state. On the other hand, we needn't do that while
+	 * the PHB has been put into frozen state because of
+	 * PHB-fatal errors.
+	 */
+#ifdef CONFIG_EEH
+	phb_pe = eeh_phb_pe_get(pdn->phb);
+	if (phb_pe && (phb_pe->state & EEH_PE_ISOLATED))
+		return PCIBIOS_SUCCESSFUL;
+
+	if (phb->eeh_state & PNV_EEH_STATE_ENABLED) {
+		if (*val == EEH_IO_ERROR_VALUE(size) &&
+		    eeh_dev_check_failure(of_node_to_eeh_dev(dn)))
+			return PCIBIOS_DEVICE_NOT_FOUND;
+	} else {
+		pnv_pci_config_check_eeh(phb, dn);
+	}
+#else
+	pnv_pci_config_check_eeh(phb, dn);
+#endif
 
 	return PCIBIOS_SUCCESSFUL;
 }
 
-static int pnv_pci_write_config(struct pci_bus *bus,
-				unsigned int devfn,
-				int where, int size, u32 val)
+int pnv_pci_cfg_write(struct device_node *dn,
+		      int where, int size, u32 val)
 {
-	struct pci_controller *hose = pci_bus_to_host(bus);
-	struct pnv_phb *phb = hose->private_data;
-	u32 bdfn = (((uint64_t)bus->number) << 8) | devfn;
+	struct pci_dn *pdn = PCI_DN(dn);
+	struct pnv_phb *phb = pdn->phb->private_data;
+	u32 bdfn = (pdn->busno << 8) | pdn->devfn;
 
-	if (hose == NULL)
-		return PCIBIOS_DEVICE_NOT_FOUND;
-
-	cfg_dbg("pnv_pci_write_config bus: %x devfn: %x +%x/%x -> %08x\n",
-		bus->number, devfn, where, size, val);
+	cfg_dbg("%s: bus: %x devfn: %x +%x/%x -> %08x\n",
+		pdn->busno, pdn->devfn, where, size, val);
 	switch (size) {
 	case 1:
 		opal_pci_config_write_byte(phb->opal_id, bdfn, where, val);
···
 	default:
 		return PCIBIOS_FUNC_NOT_SUPPORTED;
 	}
+
 	/* Check if the PHB got frozen due to an error (no response) */
-	pnv_pci_config_check_eeh(phb, bus, bdfn);
+#ifdef CONFIG_EEH
+	if (!(phb->eeh_state & PNV_EEH_STATE_ENABLED))
+		pnv_pci_config_check_eeh(phb, dn);
+#else
+	pnv_pci_config_check_eeh(phb, dn);
+#endif
 
 	return PCIBIOS_SUCCESSFUL;
 }
 
+static int pnv_pci_read_config(struct pci_bus *bus,
+			       unsigned int devfn,
+			       int where, int size, u32 *val)
+{
+	struct device_node *dn, *busdn = pci_bus_to_OF_node(bus);
+	struct pci_dn *pdn;
+
+	for (dn = busdn->child; dn; dn = dn->sibling) {
+		pdn = PCI_DN(dn);
+		if (pdn && pdn->devfn == devfn)
+			return pnv_pci_cfg_read(dn, where, size, val);
+	}
+
+	*val = 0xFFFFFFFF;
+	return PCIBIOS_DEVICE_NOT_FOUND;
+
+}
+
+static int pnv_pci_write_config(struct pci_bus *bus,
+				unsigned int devfn,
+				int where, int size, u32 val)
+{
+	struct device_node *dn, *busdn = pci_bus_to_OF_node(bus);
+	struct pci_dn *pdn;
+
+	for (dn = busdn->child; dn; dn = dn->sibling) {
+		pdn = PCI_DN(dn);
+		if (pdn && pdn->devfn == devfn)
+			return pnv_pci_cfg_write(dn, where, size, val);
+	}
+
+	return PCIBIOS_DEVICE_NOT_FOUND;
+}
+
 struct pci_ops pnv_pci_ops = {
-	.read = pnv_pci_read_config,
+	.read  = pnv_pci_read_config,
 	.write = pnv_pci_write_config,
 };
 
···
 	pnv_pci_setup_iommu_table(tbl, __va(be64_to_cpup(basep)),
 				  be32_to_cpup(sizep), 0);
 	iommu_init_table(tbl, hose->node);
+	iommu_register_group(tbl, pci_domain_nr(hose->bus), 0);
 
 	/* Deal with SW invalidated TCEs when needed (BML way) */
 	swinvp = of_get_property(hose->dn, "linux,tce-sw-invalidate-info",

arch/powerpc/platforms/powernv/pci.h

···
 	struct list_head	list;
 };
 
+/* IOC dependent EEH operations */
+#ifdef CONFIG_EEH
+struct pnv_eeh_ops {
+	int (*post_init)(struct pci_controller *hose);
+	int (*set_option)(struct eeh_pe *pe, int option);
+	int (*get_state)(struct eeh_pe *pe);
+	int (*reset)(struct eeh_pe *pe, int option);
+	int (*get_log)(struct eeh_pe *pe, int severity,
+		       char *drv_log, unsigned long len);
+	int (*configure_bridge)(struct eeh_pe *pe);
+	int (*next_error)(struct eeh_pe **pe);
+};
+
+#define PNV_EEH_STATE_ENABLED	(1 << 0)	/* EEH enabled	*/
+#define PNV_EEH_STATE_REMOVED	(1 << 1)	/* PHB removed	*/
+
+#endif /* CONFIG_EEH */
+
 struct pnv_phb {
 	struct pci_controller	*hose;
 	enum pnv_phb_type	type;
 	enum pnv_phb_model	model;
+	u64			hub_id;
 	u64			opal_id;
 	void __iomem		*regs;
 	int			initialized;
 	spinlock_t		lock;
+
+#ifdef CONFIG_EEH
+	struct pnv_eeh_ops	*eeh_ops;
+	int			eeh_state;
+#endif
+
+#ifdef CONFIG_DEBUG_FS
+	struct dentry		*dbgfs;
+#endif
 
 #ifdef CONFIG_PCI_MSI
 	unsigned int		msi_base;
···
 };
 
 extern struct pci_ops pnv_pci_ops;
+#ifdef CONFIG_EEH
+extern struct pnv_eeh_ops ioda_eeh_ops;
+#endif
 
+int pnv_pci_cfg_read(struct device_node *dn,
+		     int where, int size, u32 *val);
+int pnv_pci_cfg_write(struct device_node *dn,
+		      int where, int size, u32 val);
 extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
 				      void *tce_mem, u64 tce_size,
 				      u64 dma_offset);

arch/powerpc/platforms/powernv/setup.c

···
 {
 	long rc = OPAL_BUSY;
 
+	opal_notifier_disable();
+
 	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
 		rc = opal_cec_reboot();
 		if (rc == OPAL_BUSY_EVENT)
···
 static void __noreturn pnv_power_off(void)
 {
 	long rc = OPAL_BUSY;
+
+	opal_notifier_disable();
 
 	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
 		rc = opal_cec_power_down(0);

arch/powerpc/platforms/powernv/smp.c

···
 #define DBG(fmt...)
 #endif
 
-static void __cpuinit pnv_smp_setup_cpu(int cpu)
+static void pnv_smp_setup_cpu(int cpu)
 {
 	if (cpu != boot_cpuid)
 		xics_setup_cpu();
···
 	/* Special case - we inhibit secondary thread startup
 	 * during boot if the user requests it.
 	 */
-	if (system_state < SYSTEM_RUNNING && cpu_has_feature(CPU_FTR_SMT)) {
+	if (system_state == SYSTEM_BOOTING && cpu_has_feature(CPU_FTR_SMT)) {
 		if (!smt_enabled_at_boot && cpu_thread_in_core(nr) != 0)
 			return 0;
 		if (smt_enabled_at_boot

arch/powerpc/platforms/ps3/htab.c

···
 }
 
 static long ps3_hpte_updatepp(unsigned long slot, unsigned long newpp,
-	unsigned long vpn, int psize, int ssize, int local)
+			      unsigned long vpn, int psize, int apsize,
+			      int ssize, int local)
 {
 	int result;
 	u64 hpte_v, want_v, hpte_rs;
···
 }
 
 static void ps3_hpte_invalidate(unsigned long slot, unsigned long vpn,
-	int psize, int ssize, int local)
+				int psize, int apsize, int ssize, int local)
 {
 	unsigned long flags;
 	int result;

arch/powerpc/platforms/pseries/Kconfig

···
 	  processors, that is, which share physical processors between
 	  two or more partitions.
 
-config EEH
-	bool
-	depends on PPC_PSERIES && PCI
-	default y
-
 config PSERIES_MSI
        bool
        depends on PCI_MSI && EEH

arch/powerpc/platforms/pseries/Makefile

···
 			   firmware.o power.o dlpar.o mobility.o
 obj-$(CONFIG_SMP)	+= smp.o
 obj-$(CONFIG_SCANLOG)	+= scanlog.o
-obj-$(CONFIG_EEH)	+= eeh.o eeh_pe.o eeh_dev.o eeh_cache.o \
-			   eeh_driver.o eeh_event.o eeh_sysfs.o \
-			   eeh_pseries.o
+obj-$(CONFIG_EEH)	+= eeh_pseries.o
 obj-$(CONFIG_KEXEC)	+= kexec.o
 obj-$(CONFIG_PCI)	+= pci.o pci_dlpar.o
 obj-$(CONFIG_PSERIES_MSI)	+= msi.o

arch/powerpc/platforms/pseries/eeh.c arch/powerpc/kernel/eeh.c

···
  */
 int eeh_probe_mode;
 
-/* Global EEH mutex */
-DEFINE_MUTEX(eeh_mutex);
-
 /* Lock to avoid races due to multiple reports of an error */
-static DEFINE_RAW_SPINLOCK(confirm_error_lock);
+DEFINE_RAW_SPINLOCK(confirm_error_lock);
 
 /* Buffer for reporting pci register dumps. Its here in BSS, and
  * not dynamically alloced, so that it ends up in RMO where RTAS
···
 {
 	size_t loglen = 0;
 	struct eeh_dev *edev;
+	bool valid_cfg_log = true;
 
-	eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
-	eeh_ops->configure_bridge(pe);
-	eeh_pe_restore_bars(pe);
+	/*
+	 * When the PHB is fenced or dead, it's pointless to collect
+	 * the data from PCI config space because it should return
+	 * 0xFF's. For ER, we still retrieve the data from the PCI
+	 * config space.
+	 */
+	if (eeh_probe_mode_dev() &&
+	    (pe->type & EEH_PE_PHB) &&
+	    (pe->state & (EEH_PE_ISOLATED | EEH_PE_PHB_DEAD)))
+		valid_cfg_log = false;
 
-	pci_regs_buf[0] = 0;
-	eeh_pe_for_each_dev(pe, edev) {
-		loglen += eeh_gather_pci_data(edev, pci_regs_buf,
-				EEH_PCI_REGS_LOG_LEN);
-        }
+	if (valid_cfg_log) {
+		eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
+		eeh_ops->configure_bridge(pe);
+		eeh_pe_restore_bars(pe);
+
+		pci_regs_buf[0] = 0;
+		eeh_pe_for_each_dev(pe, edev) {
+			loglen += eeh_gather_pci_data(edev, pci_regs_buf + loglen,
+						      EEH_PCI_REGS_LOG_LEN - loglen);
+		}
+	}
 
 	eeh_ops->get_log(pe, severity, pci_regs_buf, loglen);
 }
···
 {
 	pte_t *ptep;
 	unsigned long pa;
+	int hugepage_shift;
 
-	ptep = find_linux_pte(init_mm.pgd, token);
+	/*
+	 * We won't find hugepages here, iomem
+	 */
+	ptep = find_linux_pte_or_hugepte(init_mm.pgd, token, &hugepage_shift);
 	if (!ptep)
 		return token;
+	WARN_ON(hugepage_shift);
 	pa = pte_pfn(*ptep) << PAGE_SHIFT;
 
 	return pa | (token & (PAGE_SIZE-1));
+}
+
+/*
+ * On PowerNV platform, we might already have fenced PHB there.
+ * For that case, it's meaningless to recover frozen PE. Intead,
+ * We have to handle fenced PHB firstly.
+ */
+static int eeh_phb_check_failure(struct eeh_pe *pe)
+{
+	struct eeh_pe *phb_pe;
+	unsigned long flags;
+	int ret;
+
+	if (!eeh_probe_mode_dev())
+		return -EPERM;
+
+	/* Find the PHB PE */
+	phb_pe = eeh_phb_pe_get(pe->phb);
+	if (!phb_pe) {
+		pr_warning("%s Can't find PE for PHB#%d\n",
+			   __func__, pe->phb->global_number);
+		return -EEXIST;
+	}
+
+	/* If the PHB has been in problematic state */
+	eeh_serialize_lock(&flags);
+	if (phb_pe->state & (EEH_PE_ISOLATED | EEH_PE_PHB_DEAD)) {
+		ret = 0;
+		goto out;
+	}
+
+	/* Check PHB state */
+	ret = eeh_ops->get_state(phb_pe, NULL);
+	if ((ret < 0) ||
+	    (ret == EEH_STATE_NOT_SUPPORT) ||
+	    (ret & (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) ==
+	    (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) {
+		ret = 0;
+		goto out;
+	}
+
+	/* Isolate the PHB and send event */
+	eeh_pe_state_mark(phb_pe, EEH_PE_ISOLATED);
+	eeh_serialize_unlock(flags);
+	eeh_send_failure_event(phb_pe);
+
+	pr_err("EEH: PHB#%x failure detected\n",
+		phb_pe->phb->global_number);
+	dump_stack();
+
+	return 1;
+out:
+	eeh_serialize_unlock(flags);
+	return ret;
 }
 
 /**
···
 		return 0;
 	}
 
+	/*
+	 * On PowerNV platform, we might already have fenced PHB
+	 * there and we need take care of that firstly.
+	 */
+	ret = eeh_phb_check_failure(pe);
+	if (ret > 0)
+		return ret;
+
 	/* If we already have a pending isolation event for this
 	 * slot, we know it's bad already, we don't need to check.
 	 * Do this checking under a lock; as multiple PCI devices
 	 * in one slot might report errors simultaneously, and we
 	 * only want one error recovery routine running.
 	 */
-	raw_spin_lock_irqsave(&confirm_error_lock, flags);
+	eeh_serialize_lock(&flags);
 	rc = 1;
 	if (pe->state & EEH_PE_ISOLATED) {
 		pe->check_count++;
···
 	}
 
 	eeh_stats.slot_resets++;
- 
+
 	/* Avoid repeated reports of this failure, including problems
 	 * with other functions on this device, and functions under
 	 * bridges.
 	 */
 	eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
-	raw_spin_unlock_irqrestore(&confirm_error_lock, flags);
+	eeh_serialize_unlock(flags);
 
 	eeh_send_failure_event(pe);
 
···
 	 * a stack trace will help the device-driver authors figure
 	 * out what happened.  So print that out.
 	 */
-	WARN(1, "EEH: failure detected\n");
+	pr_err("EEH: Frozen PE#%x detected on PHB#%x\n",
+		pe->addr, pe->phb->global_number);
+	dump_stack();
+
 	return 1;
 
 dn_unlock:
-	raw_spin_unlock_irqrestore(&confirm_error_lock, flags);
+	eeh_serialize_unlock(flags);
 	return rc;
 }
 
···
 	 * or a fundamental reset (3).
 	 * A fundamental reset required by any device under
 	 * Partitionable Endpoint trumps hot-reset.
-  	 */
+	 */
 	eeh_pe_dev_traverse(pe, eeh_set_dev_freset, &freset);
 
 	if (freset)
···
 	 */
 #define PCI_BUS_RST_HOLD_TIME_MSEC 250
 	msleep(PCI_BUS_RST_HOLD_TIME_MSEC);
-	
-	/* We might get hit with another EEH freeze as soon as the 
+
+	/* We might get hit with another EEH freeze as soon as the
 	 * pci slot reset line is dropped. Make sure we don't miss
 	 * these, and clear the flag now.
 	 */
···
  */
 int eeh_reset_pe(struct eeh_pe *pe)
 {
+	int flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
 	int i, rc;
 
 	/* Take three shots at resetting the bus */
···
 		eeh_reset_pe_once(pe);
 
 		rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
-		if (rc == (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE))
+		if ((rc & flags) == flags)
 			return 0;
 
 		if (rc < 0) {
···
 	if (!edev)
 		return;
 	dn = eeh_dev_to_of_node(edev);
-	
+
 	for (i = 0; i < 16; i++)
 		eeh_ops->read_config(dn, i * 4, 4, &edev->config_space[i]);
 }
···
  * Even if force-off is set, the EEH hardware is still enabled, so that
  * newer systems can boot.
  */
-static int __init eeh_init(void)
+int eeh_init(void)
 {
 	struct pci_controller *hose, *tmp;
 	struct device_node *phb;
-	int ret;
+	static int cnt = 0;
+	int ret = 0;
+
+	/*
+	 * We have to delay the initialization on PowerNV after
+	 * the PCI hierarchy tree has been built because the PEs
+	 * are figured out based on PCI devices instead of device
+	 * tree nodes
+	 */
+	if (machine_is(powernv) && cnt++ <= 0)
+		return ret;
 
 	/* call platform initialization function */
 	if (!eeh_ops) {
···
 		return ret;
 	}
 
-	raw_spin_lock_init(&confirm_error_lock);
+	/* Initialize EEH event */
+	ret = eeh_event_init();
+	if (ret)
+		return ret;
 
 	/* Enable EEH for all adapters */
 	if (eeh_probe_mode_devtree()) {
···
 			phb = hose->dn;
 			traverse_pci_devices(phb, eeh_ops->of_probe, NULL);
 		}
+	} else if (eeh_probe_mode_dev()) {
+		list_for_each_entry_safe(hose, tmp,
+			&hose_list, list_node)
+			pci_walk_bus(hose->bus, eeh_ops->dev_probe, NULL);
+	} else {
+		pr_warning("%s: Invalid probe mode %d\n",
+			   __func__, eeh_probe_mode);
+		return -EINVAL;
+	}
+
+	/*
+	 * Call platform post-initialization. Actually, It's good chance
+	 * to inform platform that EEH is ready to supply service if the
+	 * I/O cache stuff has been built up.
+	 */
+	if (eeh_ops->post_init) {
+		ret = eeh_ops->post_init();
+		if (ret)
+			return ret;
 	}
 
 	if (eeh_subsystem_enabled)
···
 {
 	struct pci_controller *phb;
 
+	/*
+	 * If we're doing EEH probe based on PCI device, we
+	 * would delay the probe until late stage because
+	 * the PCI device isn't available this moment.
+	 */
+	if (!eeh_probe_mode_devtree())
+		return;
+
 	if (!of_node_to_eeh_dev(dn))
 		return;
 	phb = of_node_to_eeh_dev(dn)->phb;
···
 	if (NULL == phb || 0 == phb->buid)
 		return;
 
-	/* FIXME: hotplug support on POWERNV */
 	eeh_ops->of_probe(dn, NULL);
 }
 
···
 	edev->pdev = dev;
 	dev->dev.archdata.edev = edev;
 
+	/*
+	 * We have to do the EEH probe here because the PCI device
+	 * hasn't been created yet in the early stage.
+	 */
+	if (eeh_probe_mode_dev())
+		eeh_ops->dev_probe(dev, NULL);
+
 	eeh_addr_cache_insert_dev(dev);
 }
 
···
 	struct pci_dev *dev;
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
- 		eeh_add_device_late(dev);
- 		if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
- 			struct pci_bus *subbus = dev->subordinate;
- 			if (subbus)
- 				eeh_add_device_tree_late(subbus);
- 		}
+		eeh_add_device_late(dev);
+		if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
+			struct pci_bus *subbus = dev->subordinate;
+			if (subbus)
+				eeh_add_device_tree_late(subbus);
+		}
 	}
 }
 EXPORT_SYMBOL_GPL(eeh_add_device_tree_late);

arch/powerpc/platforms/pseries/eeh_cache.c arch/powerpc/kernel/eeh_cache.c

···
 	}
 
 	/* Skip any devices for which EEH is not enabled. */
-	if (!edev->pe) {
+	if (!eeh_probe_mode_dev() && !edev->pe) {
 #ifdef DEBUG
 		pr_info("PCI: skip building address cache for=%s - %s\n",
 			pci_name(dev), dn->full_name);
···
  * Must be run late in boot process, after the pci controllers
  * have been scanned for devices (after all device resources are known).
  */
-void __init eeh_addr_cache_build(void)
+void eeh_addr_cache_build(void)
 {
 	struct device_node *dn;
 	struct eeh_dev *edev;
···
 	eeh_addr_cache_print(&pci_io_addr_cache_root);
 #endif
 }
-

arch/powerpc/platforms/pseries/eeh_driver.c arch/powerpc/kernel/eeh_driver.c

···
  * eeh_report_error - Report pci error to each device driver
  * @data: eeh device
  * @userdata: return value
- * 
- * Report an EEH error to each device driver, collect up and 
- * merge the device driver responses. Cumulative response 
+ *
+ * Report an EEH error to each device driver, collect up and
+ * merge the device driver responses. Cumulative response
  * passed back in "userdata".
  */
 static void *eeh_report_error(void *data, void *userdata)
···
  */
 static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 {
+	struct timeval tstamp;
 	int cnt, rc;
 
 	/* pcibios will clear the counter; save the value */
 	cnt = pe->freeze_count;
+	tstamp = pe->tstamp;
 
 	/*
 	 * We don't remove the corresponding PE instances because
···
 	eeh_pe_restore_bars(pe);
 
 	/* Give the system 5 seconds to finish running the user-space
-	 * hotplug shutdown scripts, e.g. ifdown for ethernet.  Yes, 
-	 * this is a hack, but if we don't do this, and try to bring 
-	 * the device up before the scripts have taken it down, 
+	 * hotplug shutdown scripts, e.g. ifdown for ethernet.  Yes,
+	 * this is a hack, but if we don't do this, and try to bring
+	 * the device up before the scripts have taken it down,
 	 * potentially weird things happen.
 	 */
 	if (bus) {
 		ssleep(5);
 		pcibios_add_pci_devices(bus);
 	}
+
+	pe->tstamp = tstamp;
 	pe->freeze_count = cnt;
 
 	return 0;
···
  */
 #define MAX_WAIT_FOR_RECOVERY 150
 
-/**
- * eeh_handle_event - Reset a PCI device after hard lockup.
- * @pe: EEH PE
- *
- * While PHB detects address or data parity errors on particular PCI
- * slot, the associated PE will be frozen. Besides, DMA's occurring
- * to wild addresses (which usually happen due to bugs in device
- * drivers or in PCI adapter firmware) can cause EEH error. #SERR,
- * #PERR or other misc PCI-related errors also can trigger EEH errors.
- *
- * Recovery process consists of unplugging the device driver (which
- * generated hotplug events to userspace), then issuing a PCI #RST to
- * the device, then reconfiguring the PCI config space for all bridges
- * & devices under this slot, and then finally restarting the device
- * drivers (which cause a second set of hotplug events to go out to
- * userspace).
- */
-void eeh_handle_event(struct eeh_pe *pe)
+static void eeh_handle_normal_event(struct eeh_pe *pe)
 {
 	struct pci_bus *frozen_bus;
 	int rc = 0;
···
 		return;
 	}
 
+	eeh_pe_update_time_stamp(pe);
 	pe->freeze_count++;
 	if (pe->freeze_count > EEH_MAX_ALLOWED_FREEZES)
 		goto excess_failures;
···
 	 * status ... if any child can't handle the reset, then the entire
 	 * slot is dlpar removed and added.
 	 */
+	pr_info("EEH: Notify device drivers to shutdown\n");
 	eeh_pe_dev_traverse(pe, eeh_report_error, &result);
 
 	/* Get the current PCI slot state. This can take a long time,
···
 	 */
 	rc = eeh_ops->wait_state(pe, MAX_WAIT_FOR_RECOVERY*1000);
 	if (rc < 0 || rc == EEH_STATE_NOT_SUPPORT) {
-		printk(KERN_WARNING "EEH: Permanent failure\n");
+		pr_warning("EEH: Permanent failure\n");
 		goto hard_fail;
 	}
 
···
 	 * don't post the error log until after all dev drivers
 	 * have been informed.
 	 */
+	pr_info("EEH: Collect temporary log\n");
 	eeh_slot_error_detail(pe, EEH_LOG_TEMP);
 
 	/* If all device drivers were EEH-unaware, then shut
···
 	 * go down willingly, without panicing the system.
 	 */
 	if (result == PCI_ERS_RESULT_NONE) {
+		pr_info("EEH: Reset with hotplug activity\n");
 		rc = eeh_reset_device(pe, frozen_bus);
 		if (rc) {
-			printk(KERN_WARNING "EEH: Unable to reset, rc=%d\n", rc);
+			pr_warning("%s: Unable to reset, err=%d\n",
+				   __func__, rc);
 			goto hard_fail;
 		}
 	}
 
 	/* If all devices reported they can proceed, then re-enable MMIO */
 	if (result == PCI_ERS_RESULT_CAN_RECOVER) {
+		pr_info("EEH: Enable I/O for affected devices\n");
 		rc = eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
 
 		if (rc < 0)
···
 		if (rc) {
 			result = PCI_ERS_RESULT_NEED_RESET;
 		} else {
+			pr_info("EEH: Notify device drivers to resume I/O\n");
 			result = PCI_ERS_RESULT_NONE;
 			eeh_pe_dev_traverse(pe, eeh_report_mmio_enabled, &result);
 		}
···
 
 	/* If all devices reported they can proceed, then re-enable DMA */
 	if (result == PCI_ERS_RESULT_CAN_RECOVER) {
+		pr_info("EEH: Enabled DMA for affected devices\n");
 		rc = eeh_pci_enable(pe, EEH_OPT_THAW_DMA);
 
 		if (rc < 0)
···
 
 	/* If any device has a hard failure, then shut off everything. */
 	if (result == PCI_ERS_RESULT_DISCONNECT) {
-		printk(KERN_WARNING "EEH: Device driver gave up\n");
+		pr_warning("EEH: Device driver gave up\n");
 		goto hard_fail;
 	}
 
 	/* If any device called out for a reset, then reset the slot */
 	if (result == PCI_ERS_RESULT_NEED_RESET) {
+		pr_info("EEH: Reset without hotplug activity\n");
 		rc = eeh_reset_device(pe, NULL);
 		if (rc) {
-			printk(KERN_WARNING "EEH: Cannot reset, rc=%d\n", rc);
+			pr_warning("%s: Cannot reset, err=%d\n",
+				   __func__, rc);
 			goto hard_fail;
 		}
+
+		pr_info("EEH: Notify device drivers "
+			"the completion of reset\n");
 		result = PCI_ERS_RESULT_NONE;
 		eeh_pe_dev_traverse(pe, eeh_report_reset, &result);
 	}
···
 	/* All devices should claim they have recovered by now. */
 	if ((result != PCI_ERS_RESULT_RECOVERED) &&
 	    (result != PCI_ERS_RESULT_NONE)) {
-		printk(KERN_WARNING "EEH: Not recovered\n");
+		pr_warning("EEH: Not recovered\n");
 		goto hard_fail;
 	}
 
 	/* Tell all device drivers that they can resume operations */
+	pr_info("EEH: Notify device driver to resume\n");
 	eeh_pe_dev_traverse(pe, eeh_report_resume, NULL);
 
 	return;
-	
+
 excess_failures:
 	/*
 	 * About 90% of all real-life EEH failures in the field
···
 		pcibios_remove_pci_devices(frozen_bus);
 }
 
+static void eeh_handle_special_event(void)
+{
+	struct eeh_pe *pe, *phb_pe;
+	struct pci_bus *bus;
+	struct pci_controller *hose, *tmp;
+	unsigned long flags;
+	int rc = 0;
+
+	/*
+	 * The return value from next_error() has been classified as follows.
+	 * It might be good to enumerate them. However, next_error() is only
+	 * supported by PowerNV platform for now. So it would be fine to use
+	 * integer directly:
+	 *
+	 * 4 - Dead IOC           3 - Dead PHB
+	 * 2 - Fenced PHB         1 - Frozen PE
+	 * 0 - No error found
+	 *
+	 */
+	rc = eeh_ops->next_error(&pe);
+	if (rc <= 0)
+		return;
+
+	switch (rc) {
+	case 4:
+		/* Mark all PHBs in dead state */
+		eeh_serialize_lock(&flags);
+		list_for_each_entry_safe(hose, tmp,
+				&hose_list, list_node) {
+			phb_pe = eeh_phb_pe_get(hose);
+			if (!phb_pe) continue;
+
+			eeh_pe_state_mark(phb_pe,
+				EEH_PE_ISOLATED | EEH_PE_PHB_DEAD);
+		}
+		eeh_serialize_unlock(flags);
+
+		/* Purge all events */
+		eeh_remove_event(NULL);
+		break;
+	case 3:
+	case 2:
+	case 1:
+		/* Mark the PE in fenced state */
+		eeh_serialize_lock(&flags);
+		if (rc == 3)
+			eeh_pe_state_mark(pe,
+				EEH_PE_ISOLATED | EEH_PE_PHB_DEAD);
+		else
+			eeh_pe_state_mark(pe,
+				EEH_PE_ISOLATED | EEH_PE_RECOVERING);
+		eeh_serialize_unlock(flags);
+
+		/* Purge all events of the PHB */
+		eeh_remove_event(pe);
+		break;
+	default:
+		pr_err("%s: Invalid value %d from next_error()\n",
+		       __func__, rc);
+		return;
+	}
+
+	/*
+	 * For fenced PHB and frozen PE, it's handled as normal
+	 * event. We have to remove the affected PHBs for dead
+	 * PHB and IOC
+	 */
+	if (rc == 2 || rc == 1)
+		eeh_handle_normal_event(pe);
+	else {
+		list_for_each_entry_safe(hose, tmp,
+			&hose_list, list_node) {
+			phb_pe = eeh_phb_pe_get(hose);
+			if (!phb_pe || !(phb_pe->state & EEH_PE_PHB_DEAD))
+				continue;
+
+			bus = eeh_pe_bus_get(phb_pe);
+			/* Notify all devices that they're about to go down. */
+			eeh_pe_dev_traverse(pe, eeh_report_failure, NULL);
+			pcibios_remove_pci_devices(bus);
+		}
+	}
+}
+
+/**
+ * eeh_handle_event - Reset a PCI device after hard lockup.
+ * @pe: EEH PE
+ *
+ * While PHB detects address or data parity errors on particular PCI
+ * slot, the associated PE will be frozen. Besides, DMA's occurring
+ * to wild addresses (which usually happen due to bugs in device
+ * drivers or in PCI adapter firmware) can cause EEH error. #SERR,
+ * #PERR or other misc PCI-related errors also can trigger EEH errors.
+ *
+ * Recovery process consists of unplugging the device driver (which
+ * generated hotplug events to userspace), then issuing a PCI #RST to
+ * the device, then reconfiguring the PCI config space for all bridges
+ * & devices under this slot, and then finally restarting the device
+ * drivers (which cause a second set of hotplug events to go out to
+ * userspace).
+ */
+void eeh_handle_event(struct eeh_pe *pe)
+{
+	if (pe)
+		eeh_handle_normal_event(pe);
+	else
+		eeh_handle_special_event();
+}

arch/powerpc/platforms/pseries/eeh_event.c arch/powerpc/kernel/eeh_event.c

···
 
 #include <linux/delay.h>
 #include <linux/list.h>
-#include <linux/mutex.h>
 #include <linux/sched.h>
+#include <linux/semaphore.h>
 #include <linux/pci.h>
 #include <linux/slab.h>
-#include <linux/workqueue.h>
 #include <linux/kthread.h>
 #include <asm/eeh_event.h>
 #include <asm/ppc-pci.h>
···
  *  work-queue, where a worker thread can drive recovery.
  */
 
-/* EEH event workqueue setup. */
 static DEFINE_SPINLOCK(eeh_eventlist_lock);
+static struct semaphore eeh_eventlist_sem;
 LIST_HEAD(eeh_eventlist);
-static void eeh_thread_launcher(struct work_struct *);
-DECLARE_WORK(eeh_event_wq, eeh_thread_launcher);
-
-/* Serialize reset sequences for a given pci device */
-DEFINE_MUTEX(eeh_event_mutex);
 
 /**
  * eeh_event_handler - Dispatch EEH events.
···
 	struct eeh_event *event;
 	struct eeh_pe *pe;
 
-	spin_lock_irqsave(&eeh_eventlist_lock, flags);
-	event = NULL;
+	while (!kthread_should_stop()) {
+		if (down_interruptible(&eeh_eventlist_sem))
+			break;
 
-	/* Unqueue the event, get ready to process. */
-	if (!list_empty(&eeh_eventlist)) {
-		event = list_entry(eeh_eventlist.next, struct eeh_event, list);
-		list_del(&event->list);
-	}
-	spin_unlock_irqrestore(&eeh_eventlist_lock, flags);
+		/* Fetch EEH event from the queue */
+		spin_lock_irqsave(&eeh_eventlist_lock, flags);
+		event = NULL;
+		if (!list_empty(&eeh_eventlist)) {
+			event = list_entry(eeh_eventlist.next,
+					   struct eeh_event, list);
+			list_del(&event->list);
+		}
+		spin_unlock_irqrestore(&eeh_eventlist_lock, flags);
+		if (!event)
+			continue;
 
-	if (event == NULL)
-		return 0;
+		/* We might have event without binding PE */
+		pe = event->pe;
+		if (pe) {
+			eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
+			pr_info("EEH: Detected PCI bus error on PHB#%d-PE#%x\n",
+				 pe->phb->global_number, pe->addr);
+			eeh_handle_event(pe);
+			eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
+		} else {
+			eeh_handle_event(NULL);
+		}
 
-	/* Serialize processing of EEH events */
-	mutex_lock(&eeh_event_mutex);
-	pe = event->pe;
-	eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
-	pr_info("EEH: Detected PCI bus error on PHB#%d-PE#%x\n",
-		pe->phb->global_number, pe->addr);
-
-	set_current_state(TASK_INTERRUPTIBLE);	/* Don't add to load average */
-	eeh_handle_event(pe);
-	eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
-
-	kfree(event);
-	mutex_unlock(&eeh_event_mutex);
-
-	/* If there are no new errors after an hour, clear the counter. */
-	if (pe && pe->freeze_count > 0) {
-		msleep_interruptible(3600*1000);
-		if (pe->freeze_count > 0)
-			pe->freeze_count--;
-
+		kfree(event);
 	}
 
 	return 0;
 }
 
 /**
- * eeh_thread_launcher - Start kernel thread to handle EEH events
- * @dummy - unused
+ * eeh_event_init - Start kernel thread to handle EEH events
  *
  * This routine is called to start the kernel thread for processing
  * EEH event.
  */
-static void eeh_thread_launcher(struct work_struct *dummy)
+int eeh_event_init(void)
 {
-	if (IS_ERR(kthread_run(eeh_event_handler, NULL, "eehd")))
-		printk(KERN_ERR "Failed to start EEH daemon\n");
+	struct task_struct *t;
+	int ret = 0;
+
+	/* Initialize semaphore */
+	sema_init(&eeh_eventlist_sem, 0);
+
+	t = kthread_run(eeh_event_handler, NULL, "eehd");
+	if (IS_ERR(t)) {
+		ret = PTR_ERR(t);
+		pr_err("%s: Failed to start EEH daemon (%d)\n",
+			__func__, ret);
+		return ret;
+	}
+
+	return 0;
 }
 
 /**
···
 	list_add(&event->list, &eeh_eventlist);
 	spin_unlock_irqrestore(&eeh_eventlist_lock, flags);
 
-	schedule_work(&eeh_event_wq);
+	/* For EEH deamon to knick in */
+	up(&eeh_eventlist_sem);
 
 	return 0;
+}
+
+/**
+ * eeh_remove_event - Remove EEH event from the queue
+ * @pe: Event binding to the PE
+ *
+ * On PowerNV platform, we might have subsequent coming events
+ * is part of the former one. For that case, those subsequent
+ * coming events are totally duplicated and unnecessary, thus
+ * they should be removed.
+ */
+void eeh_remove_event(struct eeh_pe *pe)
+{
+	unsigned long flags;
+	struct eeh_event *event, *tmp;
+
+	spin_lock_irqsave(&eeh_eventlist_lock, flags);
+	list_for_each_entry_safe(event, tmp, &eeh_eventlist, list) {
+		/*
+		 * If we don't have valid PE passed in, that means
+		 * we already have event corresponding to dead IOC
+		 * and all events should be purged.
+		 */
+		if (!pe) {
+			list_del(&event->list);
+			kfree(event);
+		} else if (pe->type & EEH_PE_PHB) {
+			if (event->pe && event->pe->phb == pe->phb) {
+				list_del(&event->list);
+				kfree(event);
+			}
+		} else if (event->pe == pe) {
+			list_del(&event->list);
+			kfree(event);
+		}
+	}
+	spin_unlock_irqrestore(&eeh_eventlist_lock, flags);
 }

arch/powerpc/platforms/pseries/eeh_pe.c arch/powerpc/kernel/eeh_pe.c

···
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
+#include <linux/delay.h>
 #include <linux/export.h>
 #include <linux/gfp.h>
 #include <linux/init.h>
···
 	}
 
 	/* Put it into the list */
-	eeh_lock();
 	list_add_tail(&pe->child, &eeh_phb_pe);
-	eeh_unlock();
 
 	pr_debug("EEH: Add PE for PHB#%d\n", phb->global_number);
 
···
  * hierarchy tree is composed of PHB PEs. The function is used
  * to retrieve the corresponding PHB PE according to the given PHB.
  */
-static struct eeh_pe *eeh_phb_pe_get(struct pci_controller *phb)
+struct eeh_pe *eeh_phb_pe_get(struct pci_controller *phb)
 {
 	struct eeh_pe *pe;
 
···
 		return NULL;
 	}
 
-	eeh_lock();
-
 	/* Traverse root PE */
 	for (pe = root; pe; pe = eeh_pe_next(pe, root)) {
 		eeh_pe_for_each_dev(pe, edev) {
 			ret = fn(edev, flag);
-			if (ret) {
-				eeh_unlock();
+			if (ret)
 				return ret;
-			}
 		}
 	}
-
-	eeh_unlock();
 
 	return NULL;
 }
···
 		return pe;
 
 	/* Try BDF address */
-	if (edev->pe_config_addr &&
+	if (edev->config_addr &&
 	   (edev->config_addr == pe->config_addr))
 		return pe;
 
···
  * which is composed of PCI bus/device/function number, or unified
  * PE address.
  */
-static struct eeh_pe *eeh_pe_get(struct eeh_dev *edev)
+struct eeh_pe *eeh_pe_get(struct eeh_dev *edev)
 {
 	struct eeh_pe *root = eeh_phb_pe_get(edev->phb);
 	struct eeh_pe *pe;
···
 {
 	struct eeh_pe *pe, *parent;
 
-	eeh_lock();
-
 	/*
 	 * Search the PE has been existing or not according
 	 * to the PE address. If that has been existing, the
···
 	pe = eeh_pe_get(edev);
 	if (pe && !(pe->type & EEH_PE_INVALID)) {
 		if (!edev->pe_config_addr) {
-			eeh_unlock();
 			pr_err("%s: PE with addr 0x%x already exists\n",
 				__func__, edev->config_addr);
 			return -EEXIST;
···
 
 		/* Put the edev to PE */
 		list_add_tail(&edev->list, &pe->edevs);
-		eeh_unlock();
 		pr_debug("EEH: Add %s to Bus PE#%x\n",
 			edev->dn->full_name, pe->addr);
 
···
 			parent->type &= ~EEH_PE_INVALID;
 			parent = parent->parent;
 		}
-		eeh_unlock();
 		pr_debug("EEH: Add %s to Device PE#%x, Parent PE#%x\n",
 			edev->dn->full_name, pe->addr, pe->parent->addr);
 
···
 	/* Create a new EEH PE */
 	pe = eeh_pe_alloc(edev->phb, EEH_PE_DEVICE);
 	if (!pe) {
-		eeh_unlock();
 		pr_err("%s: out of memory!\n", __func__);
 		return -ENOMEM;
 	}
 	pe->addr	= edev->pe_config_addr;
 	pe->config_addr	= edev->config_addr;
+
+	/*
+	 * While doing PE reset, we probably hot-reset the
+	 * upstream bridge. However, the PCI devices including
+	 * the associated EEH devices might be removed when EEH
+	 * core is doing recovery. So that won't safe to retrieve
+	 * the bridge through downstream EEH device. We have to
+	 * trace the parent PCI bus, then the upstream bridge.
+	 */
+	if (eeh_probe_mode_dev())
+		pe->bus = eeh_dev_to_pci_dev(edev)->bus;
 
 	/*
 	 * Put the new EEH PE into hierarchy tree. If the parent
···
 	if (!parent) {
 		parent = eeh_phb_pe_get(edev->phb);
 		if (!parent) {
-			eeh_unlock();
 			pr_err("%s: No PHB PE is found (PHB Domain=%d)\n",
 				__func__, edev->phb->global_number);
 			edev->pe = NULL;
···
 	list_add_tail(&pe->child, &parent->child_list);
 	list_add_tail(&edev->list, &pe->edevs);
 	edev->pe = pe;
-	eeh_unlock();
 	pr_debug("EEH: Add %s to Device PE#%x, Parent PE#%x\n",
 		edev->dn->full_name, pe->addr, pe->parent->addr);
 
···
 			__func__, edev->dn->full_name);
 		return -EEXIST;
 	}
-
-	eeh_lock();
 
 	/* Remove the EEH device */
 	pe = edev->pe;
···
 		pe = parent;
 	}
 
-	eeh_unlock();
-
 	return 0;
+}
+
+/**
+ * eeh_pe_update_time_stamp - Update PE's frozen time stamp
+ * @pe: EEH PE
+ *
+ * We have time stamp for each PE to trace its time of getting
+ * frozen in last hour. The function should be called to update
+ * the time stamp on first error of the specific PE. On the other
+ * handle, we needn't account for errors happened in last hour.
+ */
+void eeh_pe_update_time_stamp(struct eeh_pe *pe)
+{
+	struct timeval tstamp;
+
+	if (!pe) return;
+
+	if (pe->freeze_count <= 0) {
+		pe->freeze_count = 0;
+		do_gettimeofday(&pe->tstamp);
+	} else {
+		do_gettimeofday(&tstamp);
+		if (tstamp.tv_sec - pe->tstamp.tv_sec > 3600) {
+			pe->tstamp = tstamp;
+			pe->freeze_count = 0;
+		}
+	}
 }
 
 /**
···
  */
 void eeh_pe_state_mark(struct eeh_pe *pe, int state)
 {
-	eeh_lock();
 	eeh_pe_traverse(pe, __eeh_pe_state_mark, &state);
-	eeh_unlock();
 }
 
 /**
···
  */
 void eeh_pe_state_clear(struct eeh_pe *pe, int state)
 {
-	eeh_lock();
 	eeh_pe_traverse(pe, __eeh_pe_state_clear, &state);
-	eeh_unlock();
 }
 
-/**
- * eeh_restore_one_device_bars - Restore the Base Address Registers for one device
- * @data: EEH device
- * @flag: Unused
+/*
+ * Some PCI bridges (e.g. PLX bridges) have primary/secondary
+ * buses assigned explicitly by firmware, and we probably have
+ * lost that after reset. So we have to delay the check until
+ * the PCI-CFG registers have been restored for the parent
+ * bridge.
  *
- * Loads the PCI configuration space base address registers,
- * the expansion ROM base address, the latency timer, and etc.
- * from the saved values in the device node.
+ * Don't use normal PCI-CFG accessors, which probably has been
+ * blocked on normal path during the stage. So we need utilize
+ * eeh operations, which is always permitted.
  */
-static void *eeh_restore_one_device_bars(void *data, void *flag)
+static void eeh_bridge_check_link(struct pci_dev *pdev,
+				  struct device_node *dn)
+{
+	int cap;
+	uint32_t val;
+	int timeout = 0;
+
+	/*
+	 * We only check root port and downstream ports of
+	 * PCIe switches
+	 */
+	if (!pci_is_pcie(pdev) ||
+	    (pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT &&
+	     pci_pcie_type(pdev) != PCI_EXP_TYPE_DOWNSTREAM))
+		return;
+
+	pr_debug("%s: Check PCIe link for %s ...\n",
+		 __func__, pci_name(pdev));
+
+	/* Check slot status */
+	cap = pdev->pcie_cap;
+	eeh_ops->read_config(dn, cap + PCI_EXP_SLTSTA, 2, &val);
+	if (!(val & PCI_EXP_SLTSTA_PDS)) {
+		pr_debug("  No card in the slot (0x%04x) !\n", val);
+		return;
+	}
+
+	/* Check power status if we have the capability */
+	eeh_ops->read_config(dn, cap + PCI_EXP_SLTCAP, 2, &val);
+	if (val & PCI_EXP_SLTCAP_PCP) {
+		eeh_ops->read_config(dn, cap + PCI_EXP_SLTCTL, 2, &val);
+		if (val & PCI_EXP_SLTCTL_PCC) {
+			pr_debug("  In power-off state, power it on ...\n");
+			val &= ~(PCI_EXP_SLTCTL_PCC | PCI_EXP_SLTCTL_PIC);
+			val |= (0x0100 & PCI_EXP_SLTCTL_PIC);
+			eeh_ops->write_config(dn, cap + PCI_EXP_SLTCTL, 2, val);
+			msleep(2 * 1000);
+		}
+	}
+
+	/* Enable link */
+	eeh_ops->read_config(dn, cap + PCI_EXP_LNKCTL, 2, &val);
+	val &= ~PCI_EXP_LNKCTL_LD;
+	eeh_ops->write_config(dn, cap + PCI_EXP_LNKCTL, 2, val);
+
+	/* Check link */
+	eeh_ops->read_config(dn, cap + PCI_EXP_LNKCAP, 4, &val);
+	if (!(val & PCI_EXP_LNKCAP_DLLLARC)) {
+		pr_debug("  No link reporting capability (0x%08x) \n", val);
+		msleep(1000);
+		return;
+	}
+
+	/* Wait the link is up until timeout (5s) */
+	timeout = 0;
+	while (timeout < 5000) {
+		msleep(20);
+		timeout += 20;
+
+		eeh_ops->read_config(dn, cap + PCI_EXP_LNKSTA, 2, &val);
+		if (val & PCI_EXP_LNKSTA_DLLLA)
+			break;
+	}
+
+	if (val & PCI_EXP_LNKSTA_DLLLA)
+		pr_debug("  Link up (%s)\n",
+			 (val & PCI_EXP_LNKSTA_CLS_2_5GB) ? "2.5GB" : "5GB");
+	else
+		pr_debug("  Link not ready (0x%04x)\n", val);
+}
+
+#define BYTE_SWAP(OFF)	(8*((OFF)/4)+3-(OFF))
+#define SAVED_BYTE(OFF)	(((u8 *)(edev->config_space))[BYTE_SWAP(OFF)])
+
+static void eeh_restore_bridge_bars(struct pci_dev *pdev,
+				    struct eeh_dev *edev,
+				    struct device_node *dn)
+{
+	int i;
+
+	/*
+	 * Device BARs: 0x10 - 0x18
+	 * Bus numbers and windows: 0x18 - 0x30
+	 */
+	for (i = 4; i < 13; i++)
+		eeh_ops->write_config(dn, i*4, 4, edev->config_space[i]);
+	/* Rom: 0x38 */
+	eeh_ops->write_config(dn, 14*4, 4, edev->config_space[14]);
+
+	/* Cache line & Latency timer: 0xC 0xD */
+	eeh_ops->write_config(dn, PCI_CACHE_LINE_SIZE, 1,
+                SAVED_BYTE(PCI_CACHE_LINE_SIZE));
+        eeh_ops->write_config(dn, PCI_LATENCY_TIMER, 1,
+                SAVED_BYTE(PCI_LATENCY_TIMER));
+	/* Max latency, min grant, interrupt ping and line: 0x3C */
+	eeh_ops->write_config(dn, 15*4, 4, edev->config_space[15]);
+
+	/* PCI Command: 0x4 */
+	eeh_ops->write_config(dn, PCI_COMMAND, 4, edev->config_space[1]);
+
+	/* Check the PCIe link is ready */
+	eeh_bridge_check_link(pdev, dn);
+}
+
+static void eeh_restore_device_bars(struct eeh_dev *edev,
+				    struct device_node *dn)
 {
 	int i;
 	u32 cmd;
-	struct eeh_dev *edev = (struct eeh_dev *)data;
-	struct device_node *dn = eeh_dev_to_of_node(edev);
 
 	for (i = 4; i < 10; i++)
 		eeh_ops->write_config(dn, i*4, 4, edev->config_space[i]);
 	/* 12 == Expansion ROM Address */
 	eeh_ops->write_config(dn, 12*4, 4, edev->config_space[12]);
-
-#define BYTE_SWAP(OFF) (8*((OFF)/4)+3-(OFF))
-#define SAVED_BYTE(OFF) (((u8 *)(edev->config_space))[BYTE_SWAP(OFF)])
 
 	eeh_ops->write_config(dn, PCI_CACHE_LINE_SIZE, 1,
 		SAVED_BYTE(PCI_CACHE_LINE_SIZE));
···
 	else
 		cmd &= ~PCI_COMMAND_SERR;
 	eeh_ops->write_config(dn, PCI_COMMAND, 4, cmd);
+}
+
+/**
+ * eeh_restore_one_device_bars - Restore the Base Address Registers for one device
+ * @data: EEH device
+ * @flag: Unused
+ *
+ * Loads the PCI configuration space base address registers,
+ * the expansion ROM base address, the latency timer, and etc.
+ * from the saved values in the device node.
+ */
+static void *eeh_restore_one_device_bars(void *data, void *flag)
+{
+	struct pci_dev *pdev = NULL;
+	struct eeh_dev *edev = (struct eeh_dev *)data;
+	struct device_node *dn = eeh_dev_to_of_node(edev);
+
+	/* Trace the PCI bridge */
+	if (eeh_probe_mode_dev()) {
+		pdev = eeh_dev_to_pci_dev(edev);
+		if (pdev->hdr_type != PCI_HEADER_TYPE_BRIDGE)
+                        pdev = NULL;
+        }
+
+	if (pdev)
+		eeh_restore_bridge_bars(pdev, edev, dn);
+	else
+		eeh_restore_device_bars(edev, dn);
 
 	return NULL;
 }
···
 	struct eeh_dev *edev;
 	struct pci_dev *pdev;
 
-	eeh_lock();
-
 	if (pe->type & EEH_PE_PHB) {
 		bus = pe->phb->bus;
 	} else if (pe->type & EEH_PE_BUS ||
 		   pe->type & EEH_PE_DEVICE) {
+		if (pe->bus) {
+			bus = pe->bus;
+			goto out;
+		}
+
 		edev = list_first_entry(&pe->edevs, struct eeh_dev, list);
 		pdev = eeh_dev_to_pci_dev(edev);
 		if (pdev)
 			bus = pdev->bus;
 	}
 
-	eeh_unlock();
-
+out:
 	return bus;
 }

arch/powerpc/platforms/pseries/eeh_sysfs.c arch/powerpc/kernel/eeh_sysfs.c

···
 	device_remove_file(&pdev->dev, &dev_attr_eeh_config_addr);
 	device_remove_file(&pdev->dev, &dev_attr_eeh_pe_config_addr);
 }
-

arch/powerpc/platforms/pseries/io_event_irq.c

···
  *   by scope or event type alone. For example, Torrent ISR route change
  *   event is reported with scope 0x00 (Not Applicatable) rather than
  *   0x3B (Torrent-hub). It is better to let the clients to identify
- *   who owns the the event.
+ *   who owns the event.
  */
 
 static irqreturn_t ioei_interrupt(int irq, void *dev_id)

arch/powerpc/platforms/pseries/iommu.c

···
 
 	iommu_table_setparms(pci->phb, dn, tbl);
 	pci->iommu_table = iommu_init_table(tbl, pci->phb->node);
+	iommu_register_group(tbl, pci_domain_nr(bus), 0);
 
 	/* Divide the rest (1.75GB) among the children */
 	pci->phb->dma_window_size = 0x80000000ul;
···
 				   ppci->phb->node);
 		iommu_table_setparms_lpar(ppci->phb, pdn, tbl, dma_window);
 		ppci->iommu_table = iommu_init_table(tbl, ppci->phb->node);
+		iommu_register_group(tbl, pci_domain_nr(bus), 0);
 		pr_debug("  created table: %p\n", ppci->iommu_table);
 	}
 }
···
 				   phb->node);
 		iommu_table_setparms(phb, dn, tbl);
 		PCI_DN(dn)->iommu_table = iommu_init_table(tbl, phb->node);
+		iommu_register_group(tbl, pci_domain_nr(phb->bus), 0);
 		set_iommu_table_base(&dev->dev, PCI_DN(dn)->iommu_table);
 		return;
 	}
···
 				   pci->phb->node);
 		iommu_table_setparms_lpar(pci->phb, pdn, tbl, dma_window);
 		pci->iommu_table = iommu_init_table(tbl, pci->phb->node);
+		iommu_register_group(tbl, pci_domain_nr(pci->phb->bus), 0);
 		pr_debug("  created table: %p\n", pci->iommu_table);
 	} else {
 		pr_debug("  found DMA window, table: %p\n", pci->iommu_table);

arch/powerpc/platforms/pseries/lpar.c

···
 #include "plpar_wrappers.h"
 #include "pseries.h"
 
+/* Flag bits for H_BULK_REMOVE */
+#define HBR_REQUEST	0x4000000000000000UL
+#define HBR_RESPONSE	0x8000000000000000UL
+#define HBR_END		0xc000000000000000UL
+#define HBR_AVPN	0x0200000000000000UL
+#define HBR_ANDCOND	0x0100000000000000UL
+
 
 /* in hvCall.S */
 EXPORT_SYMBOL(plpar_hcall);
···
 
 	if (cpu_has_feature(CPU_FTR_ALTIVEC))
 		lppaca_of(cpu).vmxregs_in_use = 1;
+
+	if (cpu_has_feature(CPU_FTR_ARCH_207S))
+		lppaca_of(cpu).ebb_regs_in_use = 1;
 
 	addr = __pa(&lppaca_of(cpu));
 	ret = register_vpa(hwcpu, addr);
···
 static long pSeries_lpar_hpte_updatepp(unsigned long slot,
 				       unsigned long newpp,
 				       unsigned long vpn,
-				       int psize, int ssize, int local)
+				       int psize, int apsize,
+				       int ssize, int local)
 {
 	unsigned long lpar_rc;
 	unsigned long flags = (newpp & 7) | H_AVPN;
···
 }
 
 static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn,
-					 int psize, int ssize, int local)
+					 int psize, int apsize,
+					 int ssize, int local)
 {
 	unsigned long want_v;
 	unsigned long lpar_rc;
···
 	BUG_ON(lpar_rc != H_SUCCESS);
 }
 
+/*
+ * Limit iterations holding pSeries_lpar_tlbie_lock to 3. We also need
+ * to make sure that we avoid bouncing the hypervisor tlbie lock.
+ */
+#define PPC64_HUGE_HPTE_BATCH 12
+
+static void __pSeries_lpar_hugepage_invalidate(unsigned long *slot,
+					     unsigned long *vpn, int count,
+					     int psize, int ssize)
+{
+	unsigned long param[8];
+	int i = 0, pix = 0, rc;
+	unsigned long flags = 0;
+	int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
+
+	if (lock_tlbie)
+		spin_lock_irqsave(&pSeries_lpar_tlbie_lock, flags);
+
+	for (i = 0; i < count; i++) {
+
+		if (!firmware_has_feature(FW_FEATURE_BULK_REMOVE)) {
+			pSeries_lpar_hpte_invalidate(slot[i], vpn[i], psize, 0,
+						     ssize, 0);
+		} else {
+			param[pix] = HBR_REQUEST | HBR_AVPN | slot[i];
+			param[pix+1] = hpte_encode_avpn(vpn[i], psize, ssize);
+			pix += 2;
+			if (pix == 8) {
+				rc = plpar_hcall9(H_BULK_REMOVE, param,
+						  param[0], param[1], param[2],
+						  param[3], param[4], param[5],
+						  param[6], param[7]);
+				BUG_ON(rc != H_SUCCESS);
+				pix = 0;
+			}
+		}
+	}
+	if (pix) {
+		param[pix] = HBR_END;
+		rc = plpar_hcall9(H_BULK_REMOVE, param, param[0], param[1],
+				  param[2], param[3], param[4], param[5],
+				  param[6], param[7]);
+		BUG_ON(rc != H_SUCCESS);
+	}
+
+	if (lock_tlbie)
+		spin_unlock_irqrestore(&pSeries_lpar_tlbie_lock, flags);
+}
+
+static void pSeries_lpar_hugepage_invalidate(struct mm_struct *mm,
+				       unsigned char *hpte_slot_array,
+				       unsigned long addr, int psize)
+{
+	int ssize = 0, i, index = 0;
+	unsigned long s_addr = addr;
+	unsigned int max_hpte_count, valid;
+	unsigned long vpn_array[PPC64_HUGE_HPTE_BATCH];
+	unsigned long slot_array[PPC64_HUGE_HPTE_BATCH];
+	unsigned long shift, hidx, vpn = 0, vsid, hash, slot;
+
+	shift = mmu_psize_defs[psize].shift;
+	max_hpte_count = 1U << (PMD_SHIFT - shift);
+
+	for (i = 0; i < max_hpte_count; i++) {
+		valid = hpte_valid(hpte_slot_array, i);
+		if (!valid)
+			continue;
+		hidx =  hpte_hash_index(hpte_slot_array, i);
+
+		/* get the vpn */
+		addr = s_addr + (i * (1ul << shift));
+		if (!is_kernel_addr(addr)) {
+			ssize = user_segment_size(addr);
+			vsid = get_vsid(mm->context.id, addr, ssize);
+			WARN_ON(vsid == 0);
+		} else {
+			vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
+			ssize = mmu_kernel_ssize;
+		}
+
+		vpn = hpt_vpn(addr, vsid, ssize);
+		hash = hpt_hash(vpn, shift, ssize);
+		if (hidx & _PTEIDX_SECONDARY)
+			hash = ~hash;
+
+		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
+		slot += hidx & _PTEIDX_GROUP_IX;
+
+		slot_array[index] = slot;
+		vpn_array[index] = vpn;
+		if (index == PPC64_HUGE_HPTE_BATCH - 1) {
+			/*
+			 * Now do a bluk invalidate
+			 */
+			__pSeries_lpar_hugepage_invalidate(slot_array,
+							   vpn_array,
+							   PPC64_HUGE_HPTE_BATCH,
+							   psize, ssize);
+			index = 0;
+		} else
+			index++;
+	}
+	if (index)
+		__pSeries_lpar_hugepage_invalidate(slot_array, vpn_array,
+						   index, psize, ssize);
+}
+
 static void pSeries_lpar_hpte_removebolted(unsigned long ea,
 					   int psize, int ssize)
 {
···
 
 	slot = pSeries_lpar_hpte_find(vpn, psize, ssize);
 	BUG_ON(slot == -1);
-
-	pSeries_lpar_hpte_invalidate(slot, vpn, psize, ssize, 0);
+	/*
+	 * lpar doesn't use the passed actual page size
+	 */
+	pSeries_lpar_hpte_invalidate(slot, vpn, psize, 0, ssize, 0);
 }
-
-/* Flag bits for H_BULK_REMOVE */
-#define HBR_REQUEST	0x4000000000000000UL
-#define HBR_RESPONSE	0x8000000000000000UL
-#define HBR_END		0xc000000000000000UL
-#define HBR_AVPN	0x0200000000000000UL
-#define HBR_ANDCOND	0x0100000000000000UL
 
 /*
  * Take a spinlock around flushes to avoid bouncing the hypervisor tlbie
···
 			slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
 			slot += hidx & _PTEIDX_GROUP_IX;
 			if (!firmware_has_feature(FW_FEATURE_BULK_REMOVE)) {
+				/*
+				 * lpar doesn't use the passed actual page size
+				 */
 				pSeries_lpar_hpte_invalidate(slot, vpn, psize,
-							     ssize, local);
+							     0, ssize, local);
 			} else {
 				param[pix] = HBR_REQUEST | HBR_AVPN | slot;
 				param[pix+1] = hpte_encode_avpn(vpn, psize,
···
 	ppc_md.hpte_removebolted = pSeries_lpar_hpte_removebolted;
 	ppc_md.flush_hash_range	= pSeries_lpar_flush_hash_range;
 	ppc_md.hpte_clear_all   = pSeries_lpar_hptab_clear;
+	ppc_md.hugepage_invalidate = pSeries_lpar_hugepage_invalidate;
 }
 
 #ifdef CONFIG_PPC_SMLPAR

arch/powerpc/platforms/pseries/nvram.c

···
 #include <linux/spinlock.h>
 #include <linux/slab.h>
 #include <linux/kmsg_dump.h>
+#include <linux/pstore.h>
 #include <linux/ctype.h>
 #include <linux/zlib.h>
 #include <asm/uaccess.h>
···
 
 /* Max bytes to read/write in one go */
 #define NVRW_CNT 0x20
+
+/*
+ * Set oops header version to distingush between old and new format header.
+ * lnx,oops-log partition max size is 4000, header version > 4000 will
+ * help in identifying new header.
+ */
+#define OOPS_HDR_VERSION 5000
 
 static unsigned int nvram_size;
 static int nvram_fetch, nvram_store;
···
 	int min_size;	/* minimum acceptable size (0 means req_size) */
 	long size;	/* size of data portion (excluding err_log_info) */
 	long index;	/* offset of data portion of partition */
+	bool os_partition; /* partition initialized by OS, not FW */
 };
 
 static struct nvram_os_partition rtas_log_partition = {
 	.name = "ibm,rtas-log",
 	.req_size = 2079,
 	.min_size = 1055,
-	.index = -1
+	.index = -1,
+	.os_partition = true
 };
 
 static struct nvram_os_partition oops_log_partition = {
 	.name = "lnx,oops-log",
 	.req_size = 4000,
 	.min_size = 2000,
-	.index = -1
+	.index = -1,
+	.os_partition = true
 };
 
 static const char *pseries_nvram_os_partitions[] = {
···
 	"lnx,oops-log",
 	NULL
 };
+
+struct oops_log_info {
+	u16 version;
+	u16 report_length;
+	u64 timestamp;
+} __attribute__((packed));
 
 static void oops_to_nvram(struct kmsg_dumper *dumper,
 			  enum kmsg_dump_reason reason);
···
 
  * big_oops_buf[] holds the uncompressed text we're capturing.
  *
- * oops_buf[] holds the compressed text, preceded by a prefix.
- * The prefix is just a u16 holding the length of the compressed* text.
- * (*Or uncompressed, if compression fails.)  oops_buf[] gets written
- * to NVRAM.
+ * oops_buf[] holds the compressed text, preceded by a oops header.
+ * oops header has u16 holding the version of oops header (to differentiate
+ * between old and new format header) followed by u16 holding the length of
+ * the compressed* text (*Or uncompressed, if compression fails.) and u64
+ * holding the timestamp. oops_buf[] gets written to NVRAM.
  *
- * oops_len points to the prefix.  oops_data points to the compressed text.
+ * oops_log_info points to the header. oops_data points to the compressed text.
  *
  * +- oops_buf
- * |		+- oops_data
- * v		v
- * +------------+-----------------------------------------------+
- * | length	| text                                          |
- * | (2 bytes)	| (oops_data_sz bytes)                          |
- * +------------+-----------------------------------------------+
+ * |                                   +- oops_data
+ * v                                   v
+ * +-----------+-----------+-----------+------------------------+
+ * | version   | length    | timestamp | text                   |
+ * | (2 bytes) | (2 bytes) | (8 bytes) | (oops_data_sz bytes)   |
+ * +-----------+-----------+-----------+------------------------+
  * ^
- * +- oops_len
+ * +- oops_log_info
  *
  * We preallocate these buffers during init to avoid kmalloc during oops/panic.
  */
 static size_t big_oops_buf_sz;
 static char *big_oops_buf, *oops_buf;
-static u16 *oops_len;
 static char *oops_data;
 static size_t oops_data_sz;
 
···
 #define WINDOW_BITS 12
 #define MEM_LEVEL 4
 static struct z_stream_s stream;
+
+#ifdef CONFIG_PSTORE
+static struct nvram_os_partition of_config_partition = {
+	.name = "of-config",
+	.index = -1,
+	.os_partition = false
+};
+
+static struct nvram_os_partition common_partition = {
+	.name = "common",
+	.index = -1,
+	.os_partition = false
+};
+
+static enum pstore_type_id nvram_type_ids[] = {
+	PSTORE_TYPE_DMESG,
+	PSTORE_TYPE_PPC_RTAS,
+	PSTORE_TYPE_PPC_OF,
+	PSTORE_TYPE_PPC_COMMON,
+	-1
+};
+static int read_type;
+static unsigned long last_rtas_event;
+#endif
 
 static ssize_t pSeries_nvram_read(char *buf, size_t count, loff_t *index)
 {
···
 {
 	int rc = nvram_write_os_partition(&rtas_log_partition, buff, length,
 						err_type, error_log_cnt);
-	if (!rc)
+	if (!rc) {
 		last_unread_rtas_event = get_seconds();
+#ifdef CONFIG_PSTORE
+		last_rtas_event = get_seconds();
+#endif
+	}
+
 	return rc;
+}
+
+/* nvram_read_partition
+ *
+ * Reads nvram partition for at most 'length'
+ */
+int nvram_read_partition(struct nvram_os_partition *part, char *buff,
+			int length, unsigned int *err_type,
+			unsigned int *error_log_cnt)
+{
+	int rc;
+	loff_t tmp_index;
+	struct err_log_info info;
+	
+	if (part->index == -1)
+		return -1;
+
+	if (length > part->size)
+		length = part->size;
+
+	tmp_index = part->index;
+
+	if (part->os_partition) {
+		rc = ppc_md.nvram_read((char *)&info,
+					sizeof(struct err_log_info),
+					&tmp_index);
+		if (rc <= 0) {
+			pr_err("%s: Failed nvram_read (%d)\n", __FUNCTION__,
+									rc);
+			return rc;
+		}
+	}
+
+	rc = ppc_md.nvram_read(buff, length, &tmp_index);
+	if (rc <= 0) {
+		pr_err("%s: Failed nvram_read (%d)\n", __FUNCTION__, rc);
+		return rc;
+	}
+
+	if (part->os_partition) {
+		*error_log_cnt = info.seq_num;
+		*err_type = info.error_type;
+	}
+
+	return 0;
 }
 
 /* nvram_read_error_log
  *
  * Reads nvram for error log for at most 'length'
  */
-int nvram_read_error_log(char * buff, int length,
-                         unsigned int * err_type, unsigned int * error_log_cnt)
+int nvram_read_error_log(char *buff, int length,
+			unsigned int *err_type, unsigned int *error_log_cnt)
 {
-	int rc;
-	loff_t tmp_index;
-	struct err_log_info info;
-	
-	if (rtas_log_partition.index == -1)
-		return -1;
-
-	if (length > rtas_log_partition.size)
-		length = rtas_log_partition.size;
-
-	tmp_index = rtas_log_partition.index;
-
-	rc = ppc_md.nvram_read((char *)&info, sizeof(struct err_log_info), &tmp_index);
-	if (rc <= 0) {
-		printk(KERN_ERR "nvram_read_error_log: Failed nvram_read (%d)\n", rc);
-		return rc;
-	}
-
-	rc = ppc_md.nvram_read(buff, length, &tmp_index);
-	if (rc <= 0) {
-		printk(KERN_ERR "nvram_read_error_log: Failed nvram_read (%d)\n", rc);
-		return rc;
-	}
-
-	*error_log_cnt = info.seq_num;
-	*err_type = info.error_type;
-
-	return 0;
+	return nvram_read_partition(&rtas_log_partition, buff, length,
+						err_type, error_log_cnt);
 }
 
 /* This doesn't actually zero anything, but it sets the event_logged
···
 	return 0;
 }
 
-static void __init nvram_init_oops_partition(int rtas_partition_exists)
-{
-	int rc;
-
-	rc = pseries_nvram_init_os_partition(&oops_log_partition);
-	if (rc != 0) {
-		if (!rtas_partition_exists)
-			return;
-		pr_notice("nvram: Using %s partition to log both"
-			" RTAS errors and oops/panic reports\n",
-			rtas_log_partition.name);
-		memcpy(&oops_log_partition, &rtas_log_partition,
-						sizeof(rtas_log_partition));
-	}
-	oops_buf = kmalloc(oops_log_partition.size, GFP_KERNEL);
-	if (!oops_buf) {
-		pr_err("nvram: No memory for %s partition\n",
-						oops_log_partition.name);
-		return;
-	}
-	oops_len = (u16*) oops_buf;
-	oops_data = oops_buf + sizeof(u16);
-	oops_data_sz = oops_log_partition.size - sizeof(u16);
-
-	/*
-	 * Figure compression (preceded by elimination of each line's <n>
-	 * severity prefix) will reduce the oops/panic report to at most
-	 * 45% of its original size.
-	 */
-	big_oops_buf_sz = (oops_data_sz * 100) / 45;
-	big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL);
-	if (big_oops_buf) {
-		stream.workspace = kmalloc(zlib_deflate_workspacesize(
-				WINDOW_BITS, MEM_LEVEL), GFP_KERNEL);
-		if (!stream.workspace) {
-			pr_err("nvram: No memory for compression workspace; "
-				"skipping compression of %s partition data\n",
-				oops_log_partition.name);
-			kfree(big_oops_buf);
-			big_oops_buf = NULL;
-		}
-	} else {
-		pr_err("No memory for uncompressed %s data; "
-			"skipping compression\n", oops_log_partition.name);
-		stream.workspace = NULL;
-	}
-
-	rc = kmsg_dump_register(&nvram_kmsg_dumper);
-	if (rc != 0) {
-		pr_err("nvram: kmsg_dump_register() failed; returned %d\n", rc);
-		kfree(oops_buf);
-		kfree(big_oops_buf);
-		kfree(stream.workspace);
-	}
-}
-
-static int __init pseries_nvram_init_log_partitions(void)
-{
-	int rc;
-
-	rc = pseries_nvram_init_os_partition(&rtas_log_partition);
-	nvram_init_oops_partition(rc == 0);
-	return 0;
-}
-machine_arch_initcall(pseries, pseries_nvram_init_log_partitions);
-
-int __init pSeries_nvram_init(void)
-{
-	struct device_node *nvram;
-	const unsigned int *nbytes_p;
-	unsigned int proplen;
-
-	nvram = of_find_node_by_type(NULL, "nvram");
-	if (nvram == NULL)
-		return -ENODEV;
-
-	nbytes_p = of_get_property(nvram, "#bytes", &proplen);
-	if (nbytes_p == NULL || proplen != sizeof(unsigned int)) {
-		of_node_put(nvram);
-		return -EIO;
-	}
-
-	nvram_size = *nbytes_p;
-
-	nvram_fetch = rtas_token("nvram-fetch");
-	nvram_store = rtas_token("nvram-store");
-	printk(KERN_INFO "PPC64 nvram contains %d bytes\n", nvram_size);
-	of_node_put(nvram);
-
-	ppc_md.nvram_read	= pSeries_nvram_read;
-	ppc_md.nvram_write	= pSeries_nvram_write;
-	ppc_md.nvram_size	= pSeries_nvram_get_size;
-
-	return 0;
-}
-
 /*
  * Are we using the ibm,rtas-log for oops/panic reports?  And if so,
  * would logging this oops/panic overwrite an RTAS event that rtas_errd
···
 /* Compress the text from big_oops_buf into oops_buf. */
 static int zip_oops(size_t text_len)
 {
+	struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf;
 	int zipped_len = nvram_compress(big_oops_buf, oops_data, text_len,
 								oops_data_sz);
 	if (zipped_len < 0) {
···
 		pr_err("nvram: logging uncompressed oops/panic report\n");
 		return -1;
 	}
-	*oops_len = (u16) zipped_len;
+	oops_hdr->version = OOPS_HDR_VERSION;
+	oops_hdr->report_length = (u16) zipped_len;
+	oops_hdr->timestamp = get_seconds();
 	return 0;
 }
+
+#ifdef CONFIG_PSTORE
+/* Derived from logfs_uncompress */
+int nvram_decompress(void *in, void *out, size_t inlen, size_t outlen)
+{
+	int err, ret;
+
+	ret = -EIO;
+	err = zlib_inflateInit(&stream);
+	if (err != Z_OK)
+		goto error;
+
+	stream.next_in = in;
+	stream.avail_in = inlen;
+	stream.total_in = 0;
+	stream.next_out = out;
+	stream.avail_out = outlen;
+	stream.total_out = 0;
+
+	err = zlib_inflate(&stream, Z_FINISH);
+	if (err != Z_STREAM_END)
+		goto error;
+
+	err = zlib_inflateEnd(&stream);
+	if (err != Z_OK)
+		goto error;
+
+	ret = stream.total_out;
+error:
+	return ret;
+}
+
+static int unzip_oops(char *oops_buf, char *big_buf)
+{
+	struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf;
+	u64 timestamp = oops_hdr->timestamp;
+	char *big_oops_data = NULL;
+	char *oops_data_buf = NULL;
+	size_t big_oops_data_sz;
+	int unzipped_len;
+
+	big_oops_data = big_buf + sizeof(struct oops_log_info);
+	big_oops_data_sz = big_oops_buf_sz - sizeof(struct oops_log_info);
+	oops_data_buf = oops_buf + sizeof(struct oops_log_info);
+
+	unzipped_len = nvram_decompress(oops_data_buf, big_oops_data,
+					oops_hdr->report_length,
+					big_oops_data_sz);
+
+	if (unzipped_len < 0) {
+		pr_err("nvram: decompression failed; returned %d\n",
+								unzipped_len);
+		return -1;
+	}
+	oops_hdr = (struct oops_log_info *)big_buf;
+	oops_hdr->version = OOPS_HDR_VERSION;
+	oops_hdr->report_length = (u16) unzipped_len;
+	oops_hdr->timestamp = timestamp;
+	return 0;
+}
+
+static int nvram_pstore_open(struct pstore_info *psi)
+{
+	/* Reset the iterator to start reading partitions again */
+	read_type = -1;
+	return 0;
+}
+
+/**
+ * nvram_pstore_write - pstore write callback for nvram
+ * @type:               Type of message logged
+ * @reason:             reason behind dump (oops/panic)
+ * @id:                 identifier to indicate the write performed
+ * @part:               pstore writes data to registered buffer in parts,
+ *                      part number will indicate the same.
+ * @count:              Indicates oops count
+ * @hsize:              Size of header added by pstore
+ * @size:               number of bytes written to the registered buffer
+ * @psi:                registered pstore_info structure
+ *
+ * Called by pstore_dump() when an oops or panic report is logged in the
+ * printk buffer.
+ * Returns 0 on successful write.
+ */
+static int nvram_pstore_write(enum pstore_type_id type,
+				enum kmsg_dump_reason reason,
+				u64 *id, unsigned int part, int count,
+				size_t hsize, size_t size,
+				struct pstore_info *psi)
+{
+	int rc;
+	unsigned int err_type = ERR_TYPE_KERNEL_PANIC;
+	struct oops_log_info *oops_hdr = (struct oops_log_info *) oops_buf;
+
+	/* part 1 has the recent messages from printk buffer */
+	if (part > 1 || type != PSTORE_TYPE_DMESG ||
+				clobbering_unread_rtas_event())
+		return -1;
+
+	oops_hdr->version = OOPS_HDR_VERSION;
+	oops_hdr->report_length = (u16) size;
+	oops_hdr->timestamp = get_seconds();
+
+	if (big_oops_buf) {
+		rc = zip_oops(size);
+		/*
+		 * If compression fails copy recent log messages from
+		 * big_oops_buf to oops_data.
+		 */
+		if (rc != 0) {
+			size_t diff = size - oops_data_sz + hsize;
+
+			if (size > oops_data_sz) {
+				memcpy(oops_data, big_oops_buf, hsize);
+				memcpy(oops_data + hsize, big_oops_buf + diff,
+					oops_data_sz - hsize);
+
+				oops_hdr->report_length = (u16) oops_data_sz;
+			} else
+				memcpy(oops_data, big_oops_buf, size);
+		} else
+			err_type = ERR_TYPE_KERNEL_PANIC_GZ;
+	}
+
+	rc = nvram_write_os_partition(&oops_log_partition, oops_buf,
+		(int) (sizeof(*oops_hdr) + oops_hdr->report_length), err_type,
+		count);
+
+	if (rc != 0)
+		return rc;
+
+	*id = part;
+	return 0;
+}
+
+/*
+ * Reads the oops/panic report, rtas, of-config and common partition.
+ * Returns the length of the data we read from each partition.
+ * Returns 0 if we've been called before.
+ */
+static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
+				int *count, struct timespec *time, char **buf,
+				struct pstore_info *psi)
+{
+	struct oops_log_info *oops_hdr;
+	unsigned int err_type, id_no, size = 0;
+	struct nvram_os_partition *part = NULL;
+	char *buff = NULL, *big_buff = NULL;
+	int rc, sig = 0;
+	loff_t p;
+
+read_partition:
+	read_type++;
+
+	switch (nvram_type_ids[read_type]) {
+	case PSTORE_TYPE_DMESG:
+		part = &oops_log_partition;
+		*type = PSTORE_TYPE_DMESG;
+		break;
+	case PSTORE_TYPE_PPC_RTAS:
+		part = &rtas_log_partition;
+		*type = PSTORE_TYPE_PPC_RTAS;
+		time->tv_sec = last_rtas_event;
+		time->tv_nsec = 0;
+		break;
+	case PSTORE_TYPE_PPC_OF:
+		sig = NVRAM_SIG_OF;
+		part = &of_config_partition;
+		*type = PSTORE_TYPE_PPC_OF;
+		*id = PSTORE_TYPE_PPC_OF;
+		time->tv_sec = 0;
+		time->tv_nsec = 0;
+		break;
+	case PSTORE_TYPE_PPC_COMMON:
+		sig = NVRAM_SIG_SYS;
+		part = &common_partition;
+		*type = PSTORE_TYPE_PPC_COMMON;
+		*id = PSTORE_TYPE_PPC_COMMON;
+		time->tv_sec = 0;
+		time->tv_nsec = 0;
+		break;
+	default:
+		return 0;
+	}
+
+	if (!part->os_partition) {
+		p = nvram_find_partition(part->name, sig, &size);
+		if (p <= 0) {
+			pr_err("nvram: Failed to find partition %s, "
+				"err %d\n", part->name, (int)p);
+			return 0;
+		}
+		part->index = p;
+		part->size = size;
+	}
+
+	buff = kmalloc(part->size, GFP_KERNEL);
+
+	if (!buff)
+		return -ENOMEM;
+
+	if (nvram_read_partition(part, buff, part->size, &err_type, &id_no)) {
+		kfree(buff);
+		return 0;
+	}
+
+	*count = 0;
+
+	if (part->os_partition)
+		*id = id_no;
+
+	if (nvram_type_ids[read_type] == PSTORE_TYPE_DMESG) {
+		oops_hdr = (struct oops_log_info *)buff;
+		*buf = buff + sizeof(*oops_hdr);
+
+		if (err_type == ERR_TYPE_KERNEL_PANIC_GZ) {
+			big_buff = kmalloc(big_oops_buf_sz, GFP_KERNEL);
+			if (!big_buff)
+				return -ENOMEM;
+
+			rc = unzip_oops(buff, big_buff);
+
+			if (rc != 0) {
+				kfree(buff);
+				kfree(big_buff);
+				goto read_partition;
+			}
+
+			oops_hdr = (struct oops_log_info *)big_buff;
+			*buf = big_buff + sizeof(*oops_hdr);
+			kfree(buff);
+		}
+
+		time->tv_sec = oops_hdr->timestamp;
+		time->tv_nsec = 0;
+		return oops_hdr->report_length;
+	}
+
+	*buf = buff;
+	return part->size;
+}
+
+static struct pstore_info nvram_pstore_info = {
+	.owner = THIS_MODULE,
+	.name = "nvram",
+	.open = nvram_pstore_open,
+	.read = nvram_pstore_read,
+	.write = nvram_pstore_write,
+};
+
+static int nvram_pstore_init(void)
+{
+	int rc = 0;
+
+	if (big_oops_buf) {
+		nvram_pstore_info.buf = big_oops_buf;
+		nvram_pstore_info.bufsize = big_oops_buf_sz;
+	} else {
+		nvram_pstore_info.buf = oops_data;
+		nvram_pstore_info.bufsize = oops_data_sz;
+	}
+
+	rc = pstore_register(&nvram_pstore_info);
+	if (rc != 0)
+		pr_err("nvram: pstore_register() failed, defaults to "
+				"kmsg_dump; returned %d\n", rc);
+
+	return rc;
+}
+#else
+static int nvram_pstore_init(void)
+{
+	return -1;
+}
+#endif
+
+static void __init nvram_init_oops_partition(int rtas_partition_exists)
+{
+	int rc;
+
+	rc = pseries_nvram_init_os_partition(&oops_log_partition);
+	if (rc != 0) {
+		if (!rtas_partition_exists)
+			return;
+		pr_notice("nvram: Using %s partition to log both"
+			" RTAS errors and oops/panic reports\n",
+			rtas_log_partition.name);
+		memcpy(&oops_log_partition, &rtas_log_partition,
+						sizeof(rtas_log_partition));
+	}
+	oops_buf = kmalloc(oops_log_partition.size, GFP_KERNEL);
+	if (!oops_buf) {
+		pr_err("nvram: No memory for %s partition\n",
+						oops_log_partition.name);
+		return;
+	}
+	oops_data = oops_buf + sizeof(struct oops_log_info);
+	oops_data_sz = oops_log_partition.size - sizeof(struct oops_log_info);
+
+	/*
+	 * Figure compression (preceded by elimination of each line's <n>
+	 * severity prefix) will reduce the oops/panic report to at most
+	 * 45% of its original size.
+	 */
+	big_oops_buf_sz = (oops_data_sz * 100) / 45;
+	big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL);
+	if (big_oops_buf) {
+		stream.workspace = kmalloc(zlib_deflate_workspacesize(
+				WINDOW_BITS, MEM_LEVEL), GFP_KERNEL);
+		if (!stream.workspace) {
+			pr_err("nvram: No memory for compression workspace; "
+				"skipping compression of %s partition data\n",
+				oops_log_partition.name);
+			kfree(big_oops_buf);
+			big_oops_buf = NULL;
+		}
+	} else {
+		pr_err("No memory for uncompressed %s data; "
+			"skipping compression\n", oops_log_partition.name);
+		stream.workspace = NULL;
+	}
+
+	rc = nvram_pstore_init();
+
+	if (!rc)
+		return;
+
+	rc = kmsg_dump_register(&nvram_kmsg_dumper);
+	if (rc != 0) {
+		pr_err("nvram: kmsg_dump_register() failed; returned %d\n", rc);
+		kfree(oops_buf);
+		kfree(big_oops_buf);
+		kfree(stream.workspace);
+	}
+}
+
+static int __init pseries_nvram_init_log_partitions(void)
+{
+	int rc;
+
+	rc = pseries_nvram_init_os_partition(&rtas_log_partition);
+	nvram_init_oops_partition(rc == 0);
+	return 0;
+}
+machine_arch_initcall(pseries, pseries_nvram_init_log_partitions);
+
+int __init pSeries_nvram_init(void)
+{
+	struct device_node *nvram;
+	const unsigned int *nbytes_p;
+	unsigned int proplen;
+
+	nvram = of_find_node_by_type(NULL, "nvram");
+	if (nvram == NULL)
+		return -ENODEV;
+
+	nbytes_p = of_get_property(nvram, "#bytes", &proplen);
+	if (nbytes_p == NULL || proplen != sizeof(unsigned int)) {
+		of_node_put(nvram);
+		return -EIO;
+	}
+
+	nvram_size = *nbytes_p;
+
+	nvram_fetch = rtas_token("nvram-fetch");
+	nvram_store = rtas_token("nvram-store");
+	printk(KERN_INFO "PPC64 nvram contains %d bytes\n", nvram_size);
+	of_node_put(nvram);
+
+	ppc_md.nvram_read	= pSeries_nvram_read;
+	ppc_md.nvram_write	= pSeries_nvram_write;
+	ppc_md.nvram_size	= pSeries_nvram_get_size;
+
+	return 0;
+}
+
 
 /*
  * This is our kmsg_dump callback, called after an oops or panic report
···
 static void oops_to_nvram(struct kmsg_dumper *dumper,
 			  enum kmsg_dump_reason reason)
 {
+	struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf;
 	static unsigned int oops_count = 0;
 	static bool panicking = false;
 	static DEFINE_SPINLOCK(lock);
···
 	}
 	if (rc != 0) {
 		kmsg_dump_rewind(dumper);
-		kmsg_dump_get_buffer(dumper, true,
+		kmsg_dump_get_buffer(dumper, false,
 				     oops_data, oops_data_sz, &text_len);
 		err_type = ERR_TYPE_KERNEL_PANIC;
-		*oops_len = (u16) text_len;
+		oops_hdr->version = OOPS_HDR_VERSION;
+		oops_hdr->report_length = (u16) text_len;
+		oops_hdr->timestamp = get_seconds();
 	}
 
 	(void) nvram_write_os_partition(&oops_log_partition, oops_buf,
-		(int) (sizeof(*oops_len) + *oops_len), err_type, ++oops_count);
+		(int) (sizeof(*oops_hdr) + oops_hdr->report_length), err_type,
+		++oops_count);
 
 	spin_unlock_irqrestore(&lock, flags);
 }

arch/powerpc/platforms/pseries/pci_dlpar.c

···
 }
 EXPORT_SYMBOL_GPL(pcibios_find_pci_bus);
 
-/**
- * __pcibios_remove_pci_devices - remove all devices under this bus
- * @bus: the indicated PCI bus
- * @purge_pe: destroy the PE on removal of PCI devices
- *
- * Remove all of the PCI devices under this bus both from the
- * linux pci device tree, and from the powerpc EEH address cache.
- * By default, the corresponding PE will be destroied during the
- * normal PCI hotplug path. For PCI hotplug during EEH recovery,
- * the corresponding PE won't be destroied and deallocated.
- */
-void __pcibios_remove_pci_devices(struct pci_bus *bus, int purge_pe)
-{
-	struct pci_dev *dev, *tmp;
-	struct pci_bus *child_bus;
-
-	/* First go down child busses */
-	list_for_each_entry(child_bus, &bus->children, node)
-		__pcibios_remove_pci_devices(child_bus, purge_pe);
-
-	pr_debug("PCI: Removing devices on bus %04x:%02x\n",
-		pci_domain_nr(bus),  bus->number);
-	list_for_each_entry_safe(dev, tmp, &bus->devices, bus_list) {
-		pr_debug("     * Removing %s...\n", pci_name(dev));
-		eeh_remove_bus_device(dev, purge_pe);
-		pci_stop_and_remove_bus_device(dev);
-	}
-}
-
-/**
- * pcibios_remove_pci_devices - remove all devices under this bus
- *
- * Remove all of the PCI devices under this bus both from the
- * linux pci device tree, and from the powerpc EEH address cache.
- */
-void pcibios_remove_pci_devices(struct pci_bus *bus)
-{
-	__pcibios_remove_pci_devices(bus, 1);
-}
-EXPORT_SYMBOL_GPL(pcibios_remove_pci_devices);
-
-/**
- * pcibios_add_pci_devices - adds new pci devices to bus
- *
- * This routine will find and fixup new pci devices under
- * the indicated bus. This routine presumes that there
- * might already be some devices under this bridge, so
- * it carefully tries to add only new devices.  (And that
- * is how this routine differs from other, similar pcibios
- * routines.)
- */
-void pcibios_add_pci_devices(struct pci_bus * bus)
-{
-	int slotno, num, mode, pass, max;
-	struct pci_dev *dev;
-	struct device_node *dn = pci_bus_to_OF_node(bus);
-
-	eeh_add_device_tree_early(dn);
-
-	mode = PCI_PROBE_NORMAL;
-	if (ppc_md.pci_probe_mode)
-		mode = ppc_md.pci_probe_mode(bus);
-
-	if (mode == PCI_PROBE_DEVTREE) {
-		/* use ofdt-based probe */
-		of_rescan_bus(dn, bus);
-	} else if (mode == PCI_PROBE_NORMAL) {
-		/* use legacy probe */
-		slotno = PCI_SLOT(PCI_DN(dn->child)->devfn);
-		num = pci_scan_slot(bus, PCI_DEVFN(slotno, 0));
-		if (!num)
-			return;
-		pcibios_setup_bus_devices(bus);
-		max = bus->busn_res.start;
-		for (pass=0; pass < 2; pass++)
-			list_for_each_entry(dev, &bus->devices, bus_list) {
-			if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE ||
-			    dev->hdr_type == PCI_HEADER_TYPE_CARDBUS)
-				max = pci_scan_bridge(bus, dev, max, pass);
-		}
-	}
-	pcibios_finish_adding_to_bus(bus);
-}
-EXPORT_SYMBOL_GPL(pcibios_add_pci_devices);
-
 struct pci_controller *init_phb_dynamic(struct device_node *dn)
 {
 	struct pci_controller *phb;

arch/powerpc/platforms/pseries/ras.c

···
 	switch (event_modifier) {
 	case EPOW_SHUTDOWN_NORMAL:
 		pr_emerg("Firmware initiated power off");
-		orderly_poweroff(1);
+		orderly_poweroff(true);
 		break;
 
 	case EPOW_SHUTDOWN_ON_UPS:
···
 		pr_emerg("Loss of system critical functions reported by "
 			"firmware");
 		pr_emerg("Check RTAS error log for details");
-		orderly_poweroff(1);
+		orderly_poweroff(true);
 		break;
 
 	case EPOW_SHUTDOWN_AMBIENT_TEMPERATURE_TOO_HIGH:
 		pr_emerg("Ambient temperature too high reported by firmware");
 		pr_emerg("Check RTAS error log for details");
-		orderly_poweroff(1);
+		orderly_poweroff(true);
 		break;
 
 	default:
···
 
 	case EPOW_SYSTEM_HALT:
 		pr_emerg("Firmware initiated power off");
-		orderly_poweroff(1);
+		orderly_poweroff(true);
 		break;
 
 	case EPOW_MAIN_ENCLOSURE:

arch/powerpc/platforms/pseries/smp.c

···
 	/* Special case - we inhibit secondary thread startup
 	 * during boot if the user requests it.
 	 */
-	if (system_state < SYSTEM_RUNNING && cpu_has_feature(CPU_FTR_SMT)) {
+	if (system_state == SYSTEM_BOOTING && cpu_has_feature(CPU_FTR_SMT)) {
 		if (!smt_enabled_at_boot && cpu_thread_in_core(nr) != 0)
 			return 0;
 		if (smt_enabled_at_boot

arch/powerpc/sysdev/Makefile

···
 
 mpic-msi-obj-$(CONFIG_PCI_MSI)	+= mpic_msi.o mpic_u3msi.o mpic_pasemi_msi.o
 obj-$(CONFIG_MPIC)		+= mpic.o $(mpic-msi-obj-y)
+obj-$(CONFIG_MPIC_TIMER)        += mpic_timer.o
+obj-$(CONFIG_FSL_MPIC_TIMER_WAKEUP)	+= fsl_mpic_timer_wakeup.o
 mpic-msgr-obj-$(CONFIG_MPIC_MSGR)	+= mpic_msgr.o
 obj-$(CONFIG_MPIC)		+= mpic.o $(mpic-msi-obj-y) $(mpic-msgr-obj-y)
 obj-$(CONFIG_PPC_EPAPR_HV_PIC)	+= ehv_pic.o

arch/powerpc/sysdev/cpm1.c

···
 
 static struct irqaction cpm_error_irqaction = {
 	.handler = cpm_error_interrupt,
+	.flags = IRQF_NO_THREAD,
 	.name = "error",
 };
 

arch/powerpc/sysdev/fsl_mpic_timer_wakeup.c

···
+/*
+ * MPIC timer wakeup driver
+ *
+ * Copyright 2013 Freescale Semiconductor, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/device.h>
+
+#include <asm/mpic_timer.h>
+#include <asm/mpic.h>
+
+struct fsl_mpic_timer_wakeup {
+	struct mpic_timer *timer;
+	struct work_struct free_work;
+};
+
+static struct fsl_mpic_timer_wakeup *fsl_wakeup;
+static DEFINE_MUTEX(sysfs_lock);
+
+static void fsl_free_resource(struct work_struct *ws)
+{
+	struct fsl_mpic_timer_wakeup *wakeup =
+		container_of(ws, struct fsl_mpic_timer_wakeup, free_work);
+
+	mutex_lock(&sysfs_lock);
+
+	if (wakeup->timer) {
+		disable_irq_wake(wakeup->timer->irq);
+		mpic_free_timer(wakeup->timer);
+	}
+
+	wakeup->timer = NULL;
+	mutex_unlock(&sysfs_lock);
+}
+
+static irqreturn_t fsl_mpic_timer_irq(int irq, void *dev_id)
+{
+	struct fsl_mpic_timer_wakeup *wakeup = dev_id;
+
+	schedule_work(&wakeup->free_work);
+
+	return wakeup->timer ? IRQ_HANDLED : IRQ_NONE;
+}
+
+static ssize_t fsl_timer_wakeup_show(struct device *dev,
+				struct device_attribute *attr,
+				char *buf)
+{
+	struct timeval interval;
+	int val = 0;
+
+	mutex_lock(&sysfs_lock);
+	if (fsl_wakeup->timer) {
+		mpic_get_remain_time(fsl_wakeup->timer, &interval);
+		val = interval.tv_sec + 1;
+	}
+	mutex_unlock(&sysfs_lock);
+
+	return sprintf(buf, "%d\n", val);
+}
+
+static ssize_t fsl_timer_wakeup_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf,
+				size_t count)
+{
+	struct timeval interval;
+	int ret;
+
+	interval.tv_usec = 0;
+	if (kstrtol(buf, 0, &interval.tv_sec))
+		return -EINVAL;
+
+	mutex_lock(&sysfs_lock);
+
+	if (fsl_wakeup->timer) {
+		disable_irq_wake(fsl_wakeup->timer->irq);
+		mpic_free_timer(fsl_wakeup->timer);
+		fsl_wakeup->timer = NULL;
+	}
+
+	if (!interval.tv_sec) {
+		mutex_unlock(&sysfs_lock);
+		return count;
+	}
+
+	fsl_wakeup->timer = mpic_request_timer(fsl_mpic_timer_irq,
+						fsl_wakeup, &interval);
+	if (!fsl_wakeup->timer) {
+		mutex_unlock(&sysfs_lock);
+		return -EINVAL;
+	}
+
+	ret = enable_irq_wake(fsl_wakeup->timer->irq);
+	if (ret) {
+		mpic_free_timer(fsl_wakeup->timer);
+		fsl_wakeup->timer = NULL;
+		mutex_unlock(&sysfs_lock);
+
+		return ret;
+	}
+
+	mpic_start_timer(fsl_wakeup->timer);
+
+	mutex_unlock(&sysfs_lock);
+
+	return count;
+}
+
+static struct device_attribute mpic_attributes = __ATTR(timer_wakeup, 0644,
+			fsl_timer_wakeup_show, fsl_timer_wakeup_store);
+
+static int __init fsl_wakeup_sys_init(void)
+{
+	int ret;
+
+	fsl_wakeup = kzalloc(sizeof(struct fsl_mpic_timer_wakeup), GFP_KERNEL);
+	if (!fsl_wakeup)
+		return -ENOMEM;
+
+	INIT_WORK(&fsl_wakeup->free_work, fsl_free_resource);
+
+	ret = device_create_file(mpic_subsys.dev_root, &mpic_attributes);
+	if (ret)
+		kfree(fsl_wakeup);
+
+	return ret;
+}
+
+static void __exit fsl_wakeup_sys_exit(void)
+{
+	device_remove_file(mpic_subsys.dev_root, &mpic_attributes);
+
+	mutex_lock(&sysfs_lock);
+
+	if (fsl_wakeup->timer) {
+		disable_irq_wake(fsl_wakeup->timer->irq);
+		mpic_free_timer(fsl_wakeup->timer);
+	}
+
+	kfree(fsl_wakeup);
+
+	mutex_unlock(&sysfs_lock);
+}
+
+module_init(fsl_wakeup_sys_init);
+module_exit(fsl_wakeup_sys_exit);
+
+MODULE_DESCRIPTION("Freescale MPIC global timer wakeup driver");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Wang Dongsheng <[e-mail]>");

arch/powerpc/sysdev/mpic.c

···
 #define DBG(fmt...)
 #endif
 
+struct bus_type mpic_subsys = {
+	.name = "mpic",
+	.dev_name = "mpic",
+};
+EXPORT_SYMBOL_GPL(mpic_subsys);
+
 static struct mpic *mpics;
 static struct mpic *mpic_primary;
 static DEFINE_RAW_SPINLOCK(mpic_lock);
···
 	return IRQ_SET_MASK_OK_NOCOPY;
 }
 
+static int mpic_irq_set_wake(struct irq_data *d, unsigned int on)
+{
+	struct irq_desc *desc = container_of(d, struct irq_desc, irq_data);
+	struct mpic *mpic = mpic_from_irq_data(d);
+
+	if (!(mpic->flags & MPIC_FSL))
+		return -ENXIO;
+
+	if (on)
+		desc->action->flags |= IRQF_NO_SUSPEND;
+	else
+		desc->action->flags &= ~IRQF_NO_SUSPEND;
+
+	return 0;
+}
+
 void mpic_set_vector(unsigned int virq, unsigned int vector)
 {
 	struct mpic *mpic = mpic_from_irq(virq);
···
 	.irq_unmask	= mpic_unmask_irq,
 	.irq_eoi	= mpic_end_irq,
 	.irq_set_type	= mpic_set_irq_type,
+	.irq_set_wake	= mpic_irq_set_wake,
 };
 
 #ifdef CONFIG_SMP
···
 	.irq_mask	= mpic_mask_tm,
 	.irq_unmask	= mpic_unmask_tm,
 	.irq_eoi	= mpic_end_irq,
+	.irq_set_wake	= mpic_irq_set_wake,
 };
 
 #ifdef CONFIG_MPIC_U3_HT_IRQS
···
 	.xlate = mpic_host_xlate,
 };
 
+static u32 fsl_mpic_get_version(struct mpic *mpic)
+{
+	u32 brr1;
+
+	if (!(mpic->flags & MPIC_FSL))
+		return 0;
+
+	brr1 = _mpic_read(mpic->reg_type, &mpic->thiscpuregs,
+			MPIC_FSL_BRR1);
+
+	return brr1 & MPIC_FSL_BRR1_VER;
+}
+
 /*
  * Exported functions
  */
+
+u32 fsl_mpic_primary_get_version(void)
+{
+	struct mpic *mpic = mpic_primary;
+
+	if (mpic)
+		return fsl_mpic_get_version(mpic);
+
+	return 0;
+}
 
 struct mpic * __init mpic_alloc(struct device_node *node,
 				phys_addr_t phys_addr,
···
 	mpic_map(mpic, mpic->paddr, &mpic->tmregs, MPIC_INFO(TIMER_BASE), 0x1000);
 
 	if (mpic->flags & MPIC_FSL) {
-		u32 brr1;
 		int ret;
 
 		/*
···
 		mpic_map(mpic, mpic->paddr, &mpic->thiscpuregs,
 			 MPIC_CPU_THISBASE, 0x1000);
 
-		brr1 = _mpic_read(mpic->reg_type, &mpic->thiscpuregs,
-				MPIC_FSL_BRR1);
-		fsl_version = brr1 & MPIC_FSL_BRR1_VER;
+		fsl_version = fsl_mpic_get_version(mpic);
 
 		/* Error interrupt mask register (EIMR) is required for
 		 * handling individual device error interrupts. EIMR
···
 	mpic_cpu_write(MPIC_INFO(CPU_CURRENT_TASK_PRI), 0xf);
 
 	if (mpic->flags & MPIC_FSL) {
-		u32 brr1 = _mpic_read(mpic->reg_type, &mpic->thiscpuregs,
-				      MPIC_FSL_BRR1);
-		u32 version = brr1 & MPIC_FSL_BRR1_VER;
+		u32 version = fsl_mpic_get_version(mpic);
 
 		/*
 		 * Timer group B is present at the latest in MPIC 3.1 (e.g.
···
 static int mpic_init_sys(void)
 {
 	register_syscore_ops(&mpic_syscore_ops);
+	subsys_system_register(&mpic_subsys, NULL);
+
 	return 0;
 }
 

arch/powerpc/sysdev/mpic_timer.c

···
+/*
+ * MPIC timer driver
+ *
+ * Copyright 2013 Freescale Semiconductor, Inc.
+ * Author: Dongsheng Wang <[e-mail]>
+ *	   Li Yang <[e-mail]>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/mm.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/syscore_ops.h>
+#include <sysdev/fsl_soc.h>
+#include <asm/io.h>
+
+#include <asm/mpic_timer.h>
+
+#define FSL_GLOBAL_TIMER		0x1
+
+/* Clock Ratio
+ * Divide by 64 0x00000300
+ * Divide by 32 0x00000200
+ * Divide by 16 0x00000100
+ * Divide by  8 0x00000000 (Hardware default div)
+ */
+#define MPIC_TIMER_TCR_CLKDIV		0x00000300
+
+#define MPIC_TIMER_TCR_ROVR_OFFSET	24
+
+#define TIMER_STOP			0x80000000
+#define TIMERS_PER_GROUP		4
+#define MAX_TICKS			(~0U >> 1)
+#define MAX_TICKS_CASCADE		(~0U)
+#define TIMER_OFFSET(num)		(1 << (TIMERS_PER_GROUP - 1 - num))
+
+/* tv_usec should be less than ONE_SECOND, otherwise use tv_sec */
+#define ONE_SECOND			1000000
+
+struct timer_regs {
+	u32	gtccr;
+	u32	res0[3];
+	u32	gtbcr;
+	u32	res1[3];
+	u32	gtvpr;
+	u32	res2[3];
+	u32	gtdr;
+	u32	res3[3];
+};
+
+struct cascade_priv {
+	u32 tcr_value;			/* TCR register: CASC & ROVR value */
+	unsigned int cascade_map;	/* cascade map */
+	unsigned int timer_num;		/* cascade control timer */
+};
+
+struct timer_group_priv {
+	struct timer_regs __iomem	*regs;
+	struct mpic_timer		timer[TIMERS_PER_GROUP];
+	struct list_head		node;
+	unsigned int			timerfreq;
+	unsigned int			idle;
+	unsigned int			flags;
+	spinlock_t			lock;
+	void __iomem			*group_tcr;
+};
+
+static struct cascade_priv cascade_timer[] = {
+	/* cascade timer 0 and 1 */
+	{0x1, 0xc, 0x1},
+	/* cascade timer 1 and 2 */
+	{0x2, 0x6, 0x2},
+	/* cascade timer 2 and 3 */
+	{0x4, 0x3, 0x3}
+};
+
+static LIST_HEAD(timer_group_list);
+
+static void convert_ticks_to_time(struct timer_group_priv *priv,
+		const u64 ticks, struct timeval *time)
+{
+	u64 tmp_sec;
+
+	time->tv_sec = (__kernel_time_t)div_u64(ticks, priv->timerfreq);
+	tmp_sec = (u64)time->tv_sec * (u64)priv->timerfreq;
+
+	time->tv_usec = (__kernel_suseconds_t)
+		div_u64((ticks - tmp_sec) * 1000000, priv->timerfreq);
+
+	return;
+}
+
+/* the time set by the user is converted to "ticks" */
+static int convert_time_to_ticks(struct timer_group_priv *priv,
+		const struct timeval *time, u64 *ticks)
+{
+	u64 max_value;		/* prevent u64 overflow */
+	u64 tmp = 0;
+
+	u64 tmp_sec;
+	u64 tmp_ms;
+	u64 tmp_us;
+
+	max_value = div_u64(ULLONG_MAX, priv->timerfreq);
+
+	if (time->tv_sec > max_value ||
+			(time->tv_sec == max_value && time->tv_usec > 0))
+		return -EINVAL;
+
+	tmp_sec = (u64)time->tv_sec * (u64)priv->timerfreq;
+	tmp += tmp_sec;
+
+	tmp_ms = time->tv_usec / 1000;
+	tmp_ms = div_u64((u64)tmp_ms * (u64)priv->timerfreq, 1000);
+	tmp += tmp_ms;
+
+	tmp_us = time->tv_usec % 1000;
+	tmp_us = div_u64((u64)tmp_us * (u64)priv->timerfreq, 1000000);
+	tmp += tmp_us;
+
+	*ticks = tmp;
+
+	return 0;
+}
+
+/* detect whether there is a cascade timer available */
+static struct mpic_timer *detect_idle_cascade_timer(
+					struct timer_group_priv *priv)
+{
+	struct cascade_priv *casc_priv;
+	unsigned int map;
+	unsigned int array_size = ARRAY_SIZE(cascade_timer);
+	unsigned int num;
+	unsigned int i;
+	unsigned long flags;
+
+	casc_priv = cascade_timer;
+	for (i = 0; i < array_size; i++) {
+		spin_lock_irqsave(&priv->lock, flags);
+		map = casc_priv->cascade_map & priv->idle;
+		if (map == casc_priv->cascade_map) {
+			num = casc_priv->timer_num;
+			priv->timer[num].cascade_handle = casc_priv;
+
+			/* set timer busy */
+			priv->idle &= ~casc_priv->cascade_map;
+			spin_unlock_irqrestore(&priv->lock, flags);
+			return &priv->timer[num];
+		}
+		spin_unlock_irqrestore(&priv->lock, flags);
+		casc_priv++;
+	}
+
+	return NULL;
+}
+
+static int set_cascade_timer(struct timer_group_priv *priv, u64 ticks,
+		unsigned int num)
+{
+	struct cascade_priv *casc_priv;
+	u32 tcr;
+	u32 tmp_ticks;
+	u32 rem_ticks;
+
+	/* set group tcr reg for cascade */
+	casc_priv = priv->timer[num].cascade_handle;
+	if (!casc_priv)
+		return -EINVAL;
+
+	tcr = casc_priv->tcr_value |
+		(casc_priv->tcr_value << MPIC_TIMER_TCR_ROVR_OFFSET);
+	setbits32(priv->group_tcr, tcr);
+
+	tmp_ticks = div_u64_rem(ticks, MAX_TICKS_CASCADE, &rem_ticks);
+
+	out_be32(&priv->regs[num].gtccr, 0);
+	out_be32(&priv->regs[num].gtbcr, tmp_ticks | TIMER_STOP);
+
+	out_be32(&priv->regs[num - 1].gtccr, 0);
+	out_be32(&priv->regs[num - 1].gtbcr, rem_ticks);
+
+	return 0;
+}
+
+static struct mpic_timer *get_cascade_timer(struct timer_group_priv *priv,
+					u64 ticks)
+{
+	struct mpic_timer *allocated_timer;
+
+	/* Two cascade timers: Support the maximum time */
+	const u64 max_ticks = (u64)MAX_TICKS * (u64)MAX_TICKS_CASCADE;
+	int ret;
+
+	if (ticks > max_ticks)
+		return NULL;
+
+	/* detect idle timer */
+	allocated_timer = detect_idle_cascade_timer(priv);
+	if (!allocated_timer)
+		return NULL;
+
+	/* set ticks to timer */
+	ret = set_cascade_timer(priv, ticks, allocated_timer->num);
+	if (ret < 0)
+		return NULL;
+
+	return allocated_timer;
+}
+
+static struct mpic_timer *get_timer(const struct timeval *time)
+{
+	struct timer_group_priv *priv;
+	struct mpic_timer *timer;
+
+	u64 ticks;
+	unsigned int num;
+	unsigned int i;
+	unsigned long flags;
+	int ret;
+
+	list_for_each_entry(priv, &timer_group_list, node) {
+		ret = convert_time_to_ticks(priv, time, &ticks);
+		if (ret < 0)
+			return NULL;
+
+		if (ticks > MAX_TICKS) {
+			if (!(priv->flags & FSL_GLOBAL_TIMER))
+				return NULL;
+
+			timer = get_cascade_timer(priv, ticks);
+			if (!timer)
+				continue;
+
+			return timer;
+		}
+
+		for (i = 0; i < TIMERS_PER_GROUP; i++) {
+			/* one timer: Reverse allocation */
+			num = TIMERS_PER_GROUP - 1 - i;
+			spin_lock_irqsave(&priv->lock, flags);
+			if (priv->idle & (1 << i)) {
+				/* set timer busy */
+				priv->idle &= ~(1 << i);
+				/* set ticks & stop timer */
+				out_be32(&priv->regs[num].gtbcr,
+					ticks | TIMER_STOP);
+				out_be32(&priv->regs[num].gtccr, 0);
+				priv->timer[num].cascade_handle = NULL;
+				spin_unlock_irqrestore(&priv->lock, flags);
+				return &priv->timer[num];
+			}
+			spin_unlock_irqrestore(&priv->lock, flags);
+		}
+	}
+
+	return NULL;
+}
+
+/**
+ * mpic_start_timer - start hardware timer
+ * @handle: the timer to be started.
+ *
+ * It will do ->fn(->dev) callback from the hardware interrupt at
+ * the ->timeval point in the future.
+ */
+void mpic_start_timer(struct mpic_timer *handle)
+{
+	struct timer_group_priv *priv = container_of(handle,
+			struct timer_group_priv, timer[handle->num]);
+
+	clrbits32(&priv->regs[handle->num].gtbcr, TIMER_STOP);
+}
+EXPORT_SYMBOL(mpic_start_timer);
+
+/**
+ * mpic_stop_timer - stop hardware timer
+ * @handle: the timer to be stoped
+ *
+ * The timer periodically generates an interrupt. Unless user stops the timer.
+ */
+void mpic_stop_timer(struct mpic_timer *handle)
+{
+	struct timer_group_priv *priv = container_of(handle,
+			struct timer_group_priv, timer[handle->num]);
+	struct cascade_priv *casc_priv;
+
+	setbits32(&priv->regs[handle->num].gtbcr, TIMER_STOP);
+
+	casc_priv = priv->timer[handle->num].cascade_handle;
+	if (casc_priv) {
+		out_be32(&priv->regs[handle->num].gtccr, 0);
+		out_be32(&priv->regs[handle->num - 1].gtccr, 0);
+	} else {
+		out_be32(&priv->regs[handle->num].gtccr, 0);
+	}
+}
+EXPORT_SYMBOL(mpic_stop_timer);
+
+/**
+ * mpic_get_remain_time - get timer time
+ * @handle: the timer to be selected.
+ * @time: time for timer
+ *
+ * Query timer remaining time.
+ */
+void mpic_get_remain_time(struct mpic_timer *handle, struct timeval *time)
+{
+	struct timer_group_priv *priv = container_of(handle,
+			struct timer_group_priv, timer[handle->num]);
+	struct cascade_priv *casc_priv;
+
+	u64 ticks;
+	u32 tmp_ticks;
+
+	casc_priv = priv->timer[handle->num].cascade_handle;
+	if (casc_priv) {
+		tmp_ticks = in_be32(&priv->regs[handle->num].gtccr);
+		ticks = ((u64)tmp_ticks & UINT_MAX) * (u64)MAX_TICKS_CASCADE;
+		tmp_ticks = in_be32(&priv->regs[handle->num - 1].gtccr);
+		ticks += tmp_ticks;
+	} else {
+		ticks = in_be32(&priv->regs[handle->num].gtccr);
+	}
+
+	convert_ticks_to_time(priv, ticks, time);
+}
+EXPORT_SYMBOL(mpic_get_remain_time);
+
+/**
+ * mpic_free_timer - free hardware timer
+ * @handle: the timer to be removed.
+ *
+ * Free the timer.
+ *
+ * Note: can not be used in interrupt context.
+ */
+void mpic_free_timer(struct mpic_timer *handle)
+{
+	struct timer_group_priv *priv = container_of(handle,
+			struct timer_group_priv, timer[handle->num]);
+
+	struct cascade_priv *casc_priv;
+	unsigned long flags;
+
+	mpic_stop_timer(handle);
+
+	casc_priv = priv->timer[handle->num].cascade_handle;
+
+	free_irq(priv->timer[handle->num].irq, priv->timer[handle->num].dev);
+
+	spin_lock_irqsave(&priv->lock, flags);
+	if (casc_priv) {
+		u32 tcr;
+		tcr = casc_priv->tcr_value | (casc_priv->tcr_value <<
+					MPIC_TIMER_TCR_ROVR_OFFSET);
+		clrbits32(priv->group_tcr, tcr);
+		priv->idle |= casc_priv->cascade_map;
+		priv->timer[handle->num].cascade_handle = NULL;
+	} else {
+		priv->idle |= TIMER_OFFSET(handle->num);
+	}
+	spin_unlock_irqrestore(&priv->lock, flags);
+}
+EXPORT_SYMBOL(mpic_free_timer);
+
+/**
+ * mpic_request_timer - get a hardware timer
+ * @fn: interrupt handler function
+ * @dev: callback function of the data
+ * @time: time for timer
+ *
+ * This executes the "request_irq", returning NULL
+ * else "handle" on success.
+ */
+struct mpic_timer *mpic_request_timer(irq_handler_t fn, void *dev,
+					const struct timeval *time)
+{
+	struct mpic_timer *allocated_timer;
+	int ret;
+
+	if (list_empty(&timer_group_list))
+		return NULL;
+
+	if (!(time->tv_sec + time->tv_usec) ||
+			time->tv_sec < 0 || time->tv_usec < 0)
+		return NULL;
+
+	if (time->tv_usec > ONE_SECOND)
+		return NULL;
+
+	allocated_timer = get_timer(time);
+	if (!allocated_timer)
+		return NULL;
+
+	ret = request_irq(allocated_timer->irq, fn,
+			IRQF_TRIGGER_LOW, "global-timer", dev);
+	if (ret) {
+		mpic_free_timer(allocated_timer);
+		return NULL;
+	}
+
+	allocated_timer->dev = dev;
+
+	return allocated_timer;
+}
+EXPORT_SYMBOL(mpic_request_timer);
+
+static int timer_group_get_freq(struct device_node *np,
+			struct timer_group_priv *priv)
+{
+	u32 div;
+
+	if (priv->flags & FSL_GLOBAL_TIMER) {
+		struct device_node *dn;
+
+		dn = of_find_compatible_node(NULL, NULL, "fsl,mpic");
+		if (dn) {
+			of_property_read_u32(dn, "clock-frequency",
+					&priv->timerfreq);
+			of_node_put(dn);
+		}
+	}
+
+	if (priv->timerfreq <= 0)
+		return -EINVAL;
+
+	if (priv->flags & FSL_GLOBAL_TIMER) {
+		div = (1 << (MPIC_TIMER_TCR_CLKDIV >> 8)) * 8;
+		priv->timerfreq /= div;
+	}
+
+	return 0;
+}
+
+static int timer_group_get_irq(struct device_node *np,
+		struct timer_group_priv *priv)
+{
+	const u32 all_timer[] = { 0, TIMERS_PER_GROUP };
+	const u32 *p;
+	u32 offset;
+	u32 count;
+
+	unsigned int i;
+	unsigned int j;
+	unsigned int irq_index = 0;
+	unsigned int irq;
+	int len;
+
+	p = of_get_property(np, "fsl,available-ranges", &len);
+	if (p && len % (2 * sizeof(u32)) != 0) {
+		pr_err("%s: malformed available-ranges property.\n",
+				np->full_name);
+		return -EINVAL;
+	}
+
+	if (!p) {
+		p = all_timer;
+		len = sizeof(all_timer);
+	}
+
+	len /= 2 * sizeof(u32);
+
+	for (i = 0; i < len; i++) {
+		offset = p[i * 2];
+		count = p[i * 2 + 1];
+		for (j = 0; j < count; j++) {
+			irq = irq_of_parse_and_map(np, irq_index);
+			if (!irq) {
+				pr_err("%s: irq parse and map failed.\n",
+						np->full_name);
+				return -EINVAL;
+			}
+
+			/* Set timer idle */
+			priv->idle |= TIMER_OFFSET((offset + j));
+			priv->timer[offset + j].irq = irq;
+			priv->timer[offset + j].num = offset + j;
+			irq_index++;
+		}
+	}
+
+	return 0;
+}
+
+static void timer_group_init(struct device_node *np)
+{
+	struct timer_group_priv *priv;
+	unsigned int i = 0;
+	int ret;
+
+	priv = kzalloc(sizeof(struct timer_group_priv), GFP_KERNEL);
+	if (!priv) {
+		pr_err("%s: cannot allocate memory for group.\n",
+				np->full_name);
+		return;
+	}
+
+	if (of_device_is_compatible(np, "fsl,mpic-global-timer"))
+		priv->flags |= FSL_GLOBAL_TIMER;
+
+	priv->regs = of_iomap(np, i++);
+	if (!priv->regs) {
+		pr_err("%s: cannot ioremap timer register address.\n",
+				np->full_name);
+		goto out;
+	}
+
+	if (priv->flags & FSL_GLOBAL_TIMER) {
+		priv->group_tcr = of_iomap(np, i++);
+		if (!priv->group_tcr) {
+			pr_err("%s: cannot ioremap tcr address.\n",
+					np->full_name);
+			goto out;
+		}
+	}
+
+	ret = timer_group_get_freq(np, priv);
+	if (ret < 0) {
+		pr_err("%s: cannot get timer frequency.\n", np->full_name);
+		goto out;
+	}
+
+	ret = timer_group_get_irq(np, priv);
+	if (ret < 0) {
+		pr_err("%s: cannot get timer irqs.\n", np->full_name);
+		goto out;
+	}
+
+	spin_lock_init(&priv->lock);
+
+	/* Init FSL timer hardware */
+	if (priv->flags & FSL_GLOBAL_TIMER)
+		setbits32(priv->group_tcr, MPIC_TIMER_TCR_CLKDIV);
+
+	list_add_tail(&priv->node, &timer_group_list);
+
+	return;
+
+out:
+	if (priv->regs)
+		iounmap(priv->regs);
+
+	if (priv->group_tcr)
+		iounmap(priv->group_tcr);
+
+	kfree(priv);
+}
+
+static void mpic_timer_resume(void)
+{
+	struct timer_group_priv *priv;
+
+	list_for_each_entry(priv, &timer_group_list, node) {
+		/* Init FSL timer hardware */
+		if (priv->flags & FSL_GLOBAL_TIMER)
+			setbits32(priv->group_tcr, MPIC_TIMER_TCR_CLKDIV);
+	}
+}
+
+static const struct of_device_id mpic_timer_ids[] = {
+	{ .compatible = "fsl,mpic-global-timer", },
+	{},
+};
+
+static struct syscore_ops mpic_timer_syscore_ops = {
+	.resume = mpic_timer_resume,
+};
+
+static int __init mpic_timer_init(void)
+{
+	struct device_node *np = NULL;
+
+	for_each_matching_node(np, mpic_timer_ids)
+		timer_group_init(np);
+
+	register_syscore_ops(&mpic_timer_syscore_ops);
+
+	if (list_empty(&timer_group_list))
+		return -ENODEV;
+
+	return 0;
+}
+subsys_initcall(mpic_timer_init);

arch/s390/include/asm/pgtable.h

···
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 
 #define __HAVE_ARCH_PGTABLE_DEPOSIT
-extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable);
+extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+				       pgtable_t pgtable);
 
 #define __HAVE_ARCH_PGTABLE_WITHDRAW
-extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm);
+extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
 
 static inline int pmd_trans_splitting(pmd_t pmd)
 {

arch/s390/mm/pgtable.c

···
 	}
 }
 
-void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable)
+void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+				pgtable_t pgtable)
 {
 	struct list_head *lh = (struct list_head *) pgtable;
 
···
 	mm->pmd_huge_pte = pgtable;
 }
 
-pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm)
+pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
 {
 	struct list_head *lh;
 	pgtable_t pgtable;

arch/sparc/include/asm/pgtable_64.h

···
 				 pmd_t *pmd);
 
 #define __HAVE_ARCH_PGTABLE_DEPOSIT
-extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable);
+extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+				       pgtable_t pgtable);
 
 #define __HAVE_ARCH_PGTABLE_WITHDRAW
-extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm);
+extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
 #endif
 
 /* Encode and de-code a swap entry */

arch/sparc/mm/tlb.c

···
 	}
 }
 
-void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable)
+void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+				pgtable_t pgtable)
 {
 	struct list_head *lh = (struct list_head *) pgtable;
 
···
 	mm->pmd_huge_pte = pgtable;
 }
 
-pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm)
+pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
 {
 	struct list_head *lh;
 	pgtable_t pgtable;

drivers/acpi/apei/erst.c

···
 			   struct timespec *time, char **buf,
 			   struct pstore_info *psi);
 static int erst_writer(enum pstore_type_id type, enum kmsg_dump_reason reason,
-		       u64 *id, unsigned int part, int count,
+		       u64 *id, unsigned int part, int count, size_t hsize,
 		       size_t size, struct pstore_info *psi);
 static int erst_clearer(enum pstore_type_id type, u64 id, int count,
 			struct timespec time, struct pstore_info *psi);
···
 }
 
 static int erst_writer(enum pstore_type_id type, enum kmsg_dump_reason reason,
-		       u64 *id, unsigned int part, int count,
+		       u64 *id, unsigned int part, int count, size_t hsize,
 		       size_t size, struct pstore_info *psi)
 {
 	struct cper_pstore_record *rcd = (struct cper_pstore_record *)

drivers/firmware/efi/efi-pstore.c

···
 
 static int efi_pstore_write(enum pstore_type_id type,
 		enum kmsg_dump_reason reason, u64 *id,
-		unsigned int part, int count, size_t size,
+		unsigned int part, int count, size_t hsize, size_t size,
 		struct pstore_info *psi)
 {
 	char name[DUMP_NAME_LEN];

drivers/i2c/busses/i2c-cpm.c

···
 	tptr = 0;
 	rptr = 0;
 
+	/*
+	 * If there was a collision in the last i2c transaction,
+	 * Set I2COM_MASTER as it was cleared during collision.
+	 */
+	if (in_be16(&tbdf->cbd_sc) & BD_SC_CL) {
+		out_8(&cpm->i2c_reg->i2com, I2COM_MASTER);
+	}
+
 	while (tptr < num) {
 		pmsg = &msgs[tptr];
 		dev_dbg(&adap->dev, "R: %d T: %d\n", rptr, tptr);

drivers/iommu/Kconfig

···
 	default 256 if SHMOBILE_IOMMU_ADDRSIZE_64MB
 	default 128 if SHMOBILE_IOMMU_ADDRSIZE_32MB
 
+config SPAPR_TCE_IOMMU
+	bool "sPAPR TCE IOMMU Support"
+	depends on PPC_POWERNV || PPC_PSERIES
+	select IOMMU_API
+	help
+	  Enables bits of IOMMU API required by VFIO. The iommu_ops
+	  is not implemented as it is not necessary for VFIO.
+
 endif # IOMMU_SUPPORT

drivers/macintosh/adb.c

···
 	int ret = 0;
 	struct adbdev_state *state = file->private_data;
 	struct adb_request *req;
-	wait_queue_t wait = __WAITQUEUE_INITIALIZER(wait,current);
+	DECLARE_WAITQUEUE(wait,current);
 	unsigned long flags;
 
 	if (count < 2)

drivers/macintosh/mac_hid.c

···
 	mac_hid_destroy_emumouse();
 }
 
-static int mac_hid_toggle_emumouse(ctl_table *table, int write,
+static int mac_hid_toggle_emumouse(struct ctl_table *table, int write,
 				   void __user *buffer, size_t *lenp,
 				   loff_t *ppos)
 {
···
 }
 
 /* file(s) in /proc/sys/dev/mac_hid */
-static ctl_table mac_hid_files[] = {
+static struct ctl_table mac_hid_files[] = {
 	{
 		.procname	= "mouse_button_emulation",
 		.data		= &mouse_emulate_buttons,
···
 };
 
 /* dir in /proc/sys/dev */
-static ctl_table mac_hid_dir[] = {
+static struct ctl_table mac_hid_dir[] = {
 	{
 		.procname	= "mac_hid",
 		.maxlen		= 0,
···
 };
 
 /* /proc/sys/dev itself, in case that is not there yet */
-static ctl_table mac_hid_root_dir[] = {
+static struct ctl_table mac_hid_root_dir[] = {
 	{
 		.procname	= "dev",
 		.maxlen		= 0,

drivers/macintosh/via-cuda.c

···
     } while (0)
 
 static int
-cuda_init_via(void)
+__init cuda_init_via(void)
 {
     out_8(&via[DIRB], (in_8(&via[DIRB]) | TACK | TIP) & ~TREQ);	/* TACK & TIP out */
     out_8(&via[B], in_8(&via[B]) | TACK | TIP);			/* negate them */

drivers/macintosh/windfarm_pm121.c

···
 
 static unsigned int pm121_failure_state;
 static int pm121_readjust, pm121_skipping;
+static bool pm121_overtemp;
 static s32 average_power;
 
 struct pm121_correction {
···
 	if (new_failure & FAILURE_OVERTEMP) {
 		wf_set_overtemp();
 		pm121_skipping = 2;
+		pm121_overtemp = true;
 	}
 
 	/* We only clear the overtemp condition if overtemp is cleared
···
 	 * the control loop levels, but we don't want to keep it clear
 	 * here in this case
 	 */
-	if (new_failure == 0 && last_failure & FAILURE_OVERTEMP)
+	if (!pm121_failure_state && pm121_overtemp) {
 		wf_clear_overtemp();
+		pm121_overtemp = false;
+	}
 }
 
 

drivers/macintosh/windfarm_pm81.c

···
 
 static unsigned int wf_smu_failure_state;
 static int wf_smu_readjust, wf_smu_skipping;
+static bool wf_smu_overtemp;
 
 /*
  * ****** System Fans Control Loop ******
···
 	if (new_failure & FAILURE_OVERTEMP) {
 		wf_set_overtemp();
 		wf_smu_skipping = 2;
+		wf_smu_overtemp = true;
 	}
 
 	/* We only clear the overtemp condition if overtemp is cleared
···
 	 * the control loop levels, but we don't want to keep it clear
 	 * here in this case
 	 */
-	if (new_failure == 0 && last_failure & FAILURE_OVERTEMP)
+	if (!wf_smu_failure_state && wf_smu_overtemp) {
 		wf_clear_overtemp();
+		wf_smu_overtemp = false;
+	}
 }
 
 static void wf_smu_new_control(struct wf_control *ct)

drivers/macintosh/windfarm_pm91.c

···
 
 /* Set to kick the control loop into life */
 static int wf_smu_all_controls_ok, wf_smu_all_sensors_ok, wf_smu_started;
+static bool wf_smu_overtemp;
 
 /* Failure handling.. could be nicer */
 #define FAILURE_FAN		0x01
···
 	if (new_failure & FAILURE_OVERTEMP) {
 		wf_set_overtemp();
 		wf_smu_skipping = 2;
+		wf_smu_overtemp = true;
 	}
 
 	/* We only clear the overtemp condition if overtemp is cleared
···
 	 * the control loop levels, but we don't want to keep it clear
 	 * here in this case
 	 */
-	if (new_failure == 0 && last_failure & FAILURE_OVERTEMP)
+	if (!wf_smu_failure_state && wf_smu_overtemp) {
 		wf_clear_overtemp();
+		wf_smu_overtemp = false;
+	}
 }
 
 

drivers/macintosh/windfarm_smu_sat.c

···
 		wf_unregister_sensor(&sens->sens);
 	}
 	sat->i2c = NULL;
-	i2c_set_clientdata(client, NULL);
 	kref_put(&sat->ref, wf_sat_release);
 
 	return 0;

drivers/vfio/Kconfig

···
 	depends on VFIO
 	default n
 
+config VFIO_IOMMU_SPAPR_TCE
+	tristate
+	depends on VFIO && SPAPR_TCE_IOMMU
+	default n
+
 menuconfig VFIO
 	tristate "VFIO Non-Privileged userspace driver framework"
 	depends on IOMMU_API
 	select VFIO_IOMMU_TYPE1 if X86
+	select VFIO_IOMMU_SPAPR_TCE if (PPC_POWERNV || PPC_PSERIES)
 	help
 	  VFIO provides a framework for secure userspace device drivers.
 	  See Documentation/vfio.txt for more details.

drivers/vfio/Makefile

···
 obj-$(CONFIG_VFIO) += vfio.o
 obj-$(CONFIG_VFIO_IOMMU_TYPE1) += vfio_iommu_type1.o
+obj-$(CONFIG_VFIO_IOMMU_SPAPR_TCE) += vfio_iommu_spapr_tce.o
 obj-$(CONFIG_VFIO_PCI) += pci/

drivers/vfio/vfio.c

···
 	 * drivers.
 	 */
 	request_module_nowait("vfio_iommu_type1");
+	request_module_nowait("vfio_iommu_spapr_tce");
 
 	return 0;
 

drivers/vfio/vfio_iommu_spapr_tce.c

···
+/*
+ * VFIO: IOMMU DMA mapping support for TCE on POWER
+ *
+ * Copyright (C) 2013 IBM Corp.  All rights reserved.
+ *     Author: Alexey Kardashevskiy <[e-mail]>
+ *
+ * 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.
+ *
+ * Derived from original vfio_iommu_type1.c:
+ * Copyright (C) 2012 Red Hat, Inc.  All rights reserved.
+ *     Author: Alex Williamson <[e-mail]>
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/err.h>
+#include <linux/vfio.h>
+#include <asm/iommu.h>
+#include <asm/tce.h>
+
+#define DRIVER_VERSION  "0.1"
+#define DRIVER_AUTHOR   "[e-mail]"
+#define DRIVER_DESC     "VFIO IOMMU SPAPR TCE"
+
+static void tce_iommu_detach_group(void *iommu_data,
+		struct iommu_group *iommu_group);
+
+/*
+ * VFIO IOMMU fd for SPAPR_TCE IOMMU implementation
+ *
+ * This code handles mapping and unmapping of user data buffers
+ * into DMA'ble space using the IOMMU
+ */
+
+/*
+ * The container descriptor supports only a single group per container.
+ * Required by the API as the container is not supplied with the IOMMU group
+ * at the moment of initialization.
+ */
+struct tce_container {
+	struct mutex lock;
+	struct iommu_table *tbl;
+	bool enabled;
+};
+
+static int tce_iommu_enable(struct tce_container *container)
+{
+	int ret = 0;
+	unsigned long locked, lock_limit, npages;
+	struct iommu_table *tbl = container->tbl;
+
+	if (!container->tbl)
+		return -ENXIO;
+
+	if (!current->mm)
+		return -ESRCH; /* process exited */
+
+	if (container->enabled)
+		return -EBUSY;
+
+	/*
+	 * When userspace pages are mapped into the IOMMU, they are effectively
+	 * locked memory, so, theoretically, we need to update the accounting
+	 * of locked pages on each map and unmap.  For powerpc, the map unmap
+	 * paths can be very hot, though, and the accounting would kill
+	 * performance, especially since it would be difficult to impossible
+	 * to handle the accounting in real mode only.
+	 *
+	 * To address that, rather than precisely accounting every page, we
+	 * instead account for a worst case on locked memory when the iommu is
+	 * enabled and disabled.  The worst case upper bound on locked memory
+	 * is the size of the whole iommu window, which is usually relatively
+	 * small (compared to total memory sizes) on POWER hardware.
+	 *
+	 * Also we don't have a nice way to fail on H_PUT_TCE due to ulimits,
+	 * that would effectively kill the guest at random points, much better
+	 * enforcing the limit based on the max that the guest can map.
+	 */
+	down_write(&current->mm->mmap_sem);
+	npages = (tbl->it_size << IOMMU_PAGE_SHIFT) >> PAGE_SHIFT;
+	locked = current->mm->locked_vm + npages;
+	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+	if (locked > lock_limit && !capable(CAP_IPC_LOCK)) {
+		pr_warn("RLIMIT_MEMLOCK (%ld) exceeded\n",
+				rlimit(RLIMIT_MEMLOCK));
+		ret = -ENOMEM;
+	} else {
+
+		current->mm->locked_vm += npages;
+		container->enabled = true;
+	}
+	up_write(&current->mm->mmap_sem);
+
+	return ret;
+}
+
+static void tce_iommu_disable(struct tce_container *container)
+{
+	if (!container->enabled)
+		return;
+
+	container->enabled = false;
+
+	if (!container->tbl || !current->mm)
+		return;
+
+	down_write(&current->mm->mmap_sem);
+	current->mm->locked_vm -= (container->tbl->it_size <<
+			IOMMU_PAGE_SHIFT) >> PAGE_SHIFT;
+	up_write(&current->mm->mmap_sem);
+}
+
+static void *tce_iommu_open(unsigned long arg)
+{
+	struct tce_container *container;
+
+	if (arg != VFIO_SPAPR_TCE_IOMMU) {
+		pr_err("tce_vfio: Wrong IOMMU type\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	container = kzalloc(sizeof(*container), GFP_KERNEL);
+	if (!container)
+		return ERR_PTR(-ENOMEM);
+
+	mutex_init(&container->lock);
+
+	return container;
+}
+
+static void tce_iommu_release(void *iommu_data)
+{
+	struct tce_container *container = iommu_data;
+
+	WARN_ON(container->tbl && !container->tbl->it_group);
+	tce_iommu_disable(container);
+
+	if (container->tbl && container->tbl->it_group)
+		tce_iommu_detach_group(iommu_data, container->tbl->it_group);
+
+	mutex_destroy(&container->lock);
+
+	kfree(container);
+}
+
+static long tce_iommu_ioctl(void *iommu_data,
+				 unsigned int cmd, unsigned long arg)
+{
+	struct tce_container *container = iommu_data;
+	unsigned long minsz;
+	long ret;
+
+	switch (cmd) {
+	case VFIO_CHECK_EXTENSION:
+		return (arg == VFIO_SPAPR_TCE_IOMMU) ? 1 : 0;
+
+	case VFIO_IOMMU_SPAPR_TCE_GET_INFO: {
+		struct vfio_iommu_spapr_tce_info info;
+		struct iommu_table *tbl = container->tbl;
+
+		if (WARN_ON(!tbl))
+			return -ENXIO;
+
+		minsz = offsetofend(struct vfio_iommu_spapr_tce_info,
+				dma32_window_size);
+
+		if (copy_from_user(&info, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (info.argsz < minsz)
+			return -EINVAL;
+
+		info.dma32_window_start = tbl->it_offset << IOMMU_PAGE_SHIFT;
+		info.dma32_window_size = tbl->it_size << IOMMU_PAGE_SHIFT;
+		info.flags = 0;
+
+		if (copy_to_user((void __user *)arg, &info, minsz))
+			return -EFAULT;
+
+		return 0;
+	}
+	case VFIO_IOMMU_MAP_DMA: {
+		struct vfio_iommu_type1_dma_map param;
+		struct iommu_table *tbl = container->tbl;
+		unsigned long tce, i;
+
+		if (!tbl)
+			return -ENXIO;
+
+		BUG_ON(!tbl->it_group);
+
+		minsz = offsetofend(struct vfio_iommu_type1_dma_map, size);
+
+		if (copy_from_user(&param, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (param.argsz < minsz)
+			return -EINVAL;
+
+		if (param.flags & ~(VFIO_DMA_MAP_FLAG_READ |
+				VFIO_DMA_MAP_FLAG_WRITE))
+			return -EINVAL;
+
+		if ((param.size & ~IOMMU_PAGE_MASK) ||
+				(param.vaddr & ~IOMMU_PAGE_MASK))
+			return -EINVAL;
+
+		/* iova is checked by the IOMMU API */
+		tce = param.vaddr;
+		if (param.flags & VFIO_DMA_MAP_FLAG_READ)
+			tce |= TCE_PCI_READ;
+		if (param.flags & VFIO_DMA_MAP_FLAG_WRITE)
+			tce |= TCE_PCI_WRITE;
+
+		ret = iommu_tce_put_param_check(tbl, param.iova, tce);
+		if (ret)
+			return ret;
+
+		for (i = 0; i < (param.size >> IOMMU_PAGE_SHIFT); ++i) {
+			ret = iommu_put_tce_user_mode(tbl,
+					(param.iova >> IOMMU_PAGE_SHIFT) + i,
+					tce);
+			if (ret)
+				break;
+			tce += IOMMU_PAGE_SIZE;
+		}
+		if (ret)
+			iommu_clear_tces_and_put_pages(tbl,
+					param.iova >> IOMMU_PAGE_SHIFT,	i);
+
+		iommu_flush_tce(tbl);
+
+		return ret;
+	}
+	case VFIO_IOMMU_UNMAP_DMA: {
+		struct vfio_iommu_type1_dma_unmap param;
+		struct iommu_table *tbl = container->tbl;
+
+		if (WARN_ON(!tbl))
+			return -ENXIO;
+
+		minsz = offsetofend(struct vfio_iommu_type1_dma_unmap,
+				size);
+
+		if (copy_from_user(&param, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (param.argsz < minsz)
+			return -EINVAL;
+
+		/* No flag is supported now */
+		if (param.flags)
+			return -EINVAL;
+
+		if (param.size & ~IOMMU_PAGE_MASK)
+			return -EINVAL;
+
+		ret = iommu_tce_clear_param_check(tbl, param.iova, 0,
+				param.size >> IOMMU_PAGE_SHIFT);
+		if (ret)
+			return ret;
+
+		ret = iommu_clear_tces_and_put_pages(tbl,
+				param.iova >> IOMMU_PAGE_SHIFT,
+				param.size >> IOMMU_PAGE_SHIFT);
+		iommu_flush_tce(tbl);
+
+		return ret;
+	}
+	case VFIO_IOMMU_ENABLE:
+		mutex_lock(&container->lock);
+		ret = tce_iommu_enable(container);
+		mutex_unlock(&container->lock);
+		return ret;
+
+
+	case VFIO_IOMMU_DISABLE:
+		mutex_lock(&container->lock);
+		tce_iommu_disable(container);
+		mutex_unlock(&container->lock);
+		return 0;
+	}
+
+	return -ENOTTY;
+}
+
+static int tce_iommu_attach_group(void *iommu_data,
+		struct iommu_group *iommu_group)
+{
+	int ret;
+	struct tce_container *container = iommu_data;
+	struct iommu_table *tbl = iommu_group_get_iommudata(iommu_group);
+
+	BUG_ON(!tbl);
+	mutex_lock(&container->lock);
+
+	/* pr_debug("tce_vfio: Attaching group #%u to iommu %p\n",
+			iommu_group_id(iommu_group), iommu_group); */
+	if (container->tbl) {
+		pr_warn("tce_vfio: Only one group per IOMMU container is allowed, existing id=%d, attaching id=%d\n",
+				iommu_group_id(container->tbl->it_group),
+				iommu_group_id(iommu_group));
+		ret = -EBUSY;
+	} else if (container->enabled) {
+		pr_err("tce_vfio: attaching group #%u to enabled container\n",
+				iommu_group_id(iommu_group));
+		ret = -EBUSY;
+	} else {
+		ret = iommu_take_ownership(tbl);
+		if (!ret)
+			container->tbl = tbl;
+	}
+
+	mutex_unlock(&container->lock);
+
+	return ret;
+}
+
+static void tce_iommu_detach_group(void *iommu_data,
+		struct iommu_group *iommu_group)
+{
+	struct tce_container *container = iommu_data;
+	struct iommu_table *tbl = iommu_group_get_iommudata(iommu_group);
+
+	BUG_ON(!tbl);
+	mutex_lock(&container->lock);
+	if (tbl != container->tbl) {
+		pr_warn("tce_vfio: detaching group #%u, expected group is #%u\n",
+				iommu_group_id(iommu_group),
+				iommu_group_id(tbl->it_group));
+	} else {
+		if (container->enabled) {
+			pr_warn("tce_vfio: detaching group #%u from enabled container, forcing disable\n",
+					iommu_group_id(tbl->it_group));
+			tce_iommu_disable(container);
+		}
+
+		/* pr_debug("tce_vfio: detaching group #%u from iommu %p\n",
+				iommu_group_id(iommu_group), iommu_group); */
+		container->tbl = NULL;
+		iommu_release_ownership(tbl);
+	}
+	mutex_unlock(&container->lock);
+}
+
+const struct vfio_iommu_driver_ops tce_iommu_driver_ops = {
+	.name		= "iommu-vfio-powerpc",
+	.owner		= THIS_MODULE,
+	.open		= tce_iommu_open,
+	.release	= tce_iommu_release,
+	.ioctl		= tce_iommu_ioctl,
+	.attach_group	= tce_iommu_attach_group,
+	.detach_group	= tce_iommu_detach_group,
+};
+
+static int __init tce_iommu_init(void)
+{
+	return vfio_register_iommu_driver(&tce_iommu_driver_ops);
+}
+
+static void __exit tce_iommu_cleanup(void)
+{
+	vfio_unregister_iommu_driver(&tce_iommu_driver_ops);
+}
+
+module_init(tce_iommu_init);
+module_exit(tce_iommu_cleanup);
+
+MODULE_VERSION(DRIVER_VERSION);
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
+

drivers/watchdog/booke_wdt.c

···
 	val &= ~WDTP_MASK;
 	val |= (TCR_WIE|TCR_WRC(WRC_CHIP)|WDTP(booke_wdt_period));
 
+#ifdef CONFIG_PPC_BOOK3E_64
+	/*
+	 * Crit ints are currently broken on PPC64 Book-E, so
+	 * just disable them for now.
+	 */
+	val &= ~TCR_WIE;
+#endif
+
 	mtspr(SPRN_TCR, val);
 }
 

fs/pstore/ftrace.c

···
 	rec.parent_ip = parent_ip;
 	pstore_ftrace_encode_cpu(&rec, raw_smp_processor_id());
 	psinfo->write_buf(PSTORE_TYPE_FTRACE, 0, NULL, 0, (void *)&rec,
-			  sizeof(rec), psinfo);
+			  0, sizeof(rec), psinfo);
 
 	local_irq_restore(flags);
 }

fs/pstore/inode.c

···
 	case PSTORE_TYPE_MCE:
 		sprintf(name, "mce-%s-%lld", psname, id);
 		break;
+	case PSTORE_TYPE_PPC_RTAS:
+		sprintf(name, "rtas-%s-%lld", psname, id);
+		break;
+	case PSTORE_TYPE_PPC_OF:
+		sprintf(name, "powerpc-ofw-%s-%lld", psname, id);
+		break;
+	case PSTORE_TYPE_PPC_COMMON:
+		sprintf(name, "powerpc-common-%s-%lld", psname, id);
+		break;
 	case PSTORE_TYPE_UNKNOWN:
 		sprintf(name, "unknown-%s-%lld", psname, id);
 		break;

fs/pstore/platform.c

···
 			break;
 
 		ret = psinfo->write(PSTORE_TYPE_DMESG, reason, &id, part,
-				    oopscount, hsize + len, psinfo);
+				    oopscount, hsize, hsize + len, psinfo);
 		if (ret == 0 && reason == KMSG_DUMP_OOPS && pstore_is_mounted())
 			pstore_new_entry = 1;
 
···
 			spin_lock_irqsave(&psinfo->buf_lock, flags);
 		}
 		memcpy(psinfo->buf, s, c);
-		psinfo->write(PSTORE_TYPE_CONSOLE, 0, &id, 0, 0, c, psinfo);
+		psinfo->write(PSTORE_TYPE_CONSOLE, 0, &id, 0, 0, 0, c, psinfo);
 		spin_unlock_irqrestore(&psinfo->buf_lock, flags);
 		s += c;
 		c = e - s;
···
 static int pstore_write_compat(enum pstore_type_id type,
 			       enum kmsg_dump_reason reason,
 			       u64 *id, unsigned int part, int count,
-			       size_t size, struct pstore_info *psi)
+			       size_t hsize, size_t size,
+			       struct pstore_info *psi)
 {
-	return psi->write_buf(type, reason, id, part, psinfo->buf, size, psi);
+	return psi->write_buf(type, reason, id, part, psinfo->buf, hsize,
+			     size, psi);
 }
 
 /*

fs/pstore/ram.c

···
 static int notrace ramoops_pstore_write_buf(enum pstore_type_id type,
 					    enum kmsg_dump_reason reason,
 					    u64 *id, unsigned int part,
-					    const char *buf, size_t size,
+					    const char *buf,
+					    size_t hsize, size_t size,
 					    struct pstore_info *psi)
 {
 	struct ramoops_context *cxt = psi->data;

include/asm-generic/pgtable.h

···
 #endif
 
 #ifndef __HAVE_ARCH_PGTABLE_DEPOSIT
-extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable);
+extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+				       pgtable_t pgtable);
 #endif
 
 #ifndef __HAVE_ARCH_PGTABLE_WITHDRAW
-extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm);
+extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
 #endif
 
 #ifndef __HAVE_ARCH_PMDP_INVALIDATE

include/linux/huge_mm.h

···
 #define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-#define HPAGE_PMD_SHIFT HPAGE_SHIFT
-#define HPAGE_PMD_MASK HPAGE_MASK
-#define HPAGE_PMD_SIZE HPAGE_SIZE
+#define HPAGE_PMD_SHIFT PMD_SHIFT
+#define HPAGE_PMD_SIZE	((1UL) << HPAGE_PMD_SHIFT)
+#define HPAGE_PMD_MASK	(~(HPAGE_PMD_SIZE - 1))
 
 extern bool is_vma_temporary_stack(struct vm_area_struct *vma);
 

include/linux/pstore.h

···
 	PSTORE_TYPE_MCE		= 1,
 	PSTORE_TYPE_CONSOLE	= 2,
 	PSTORE_TYPE_FTRACE	= 3,
+	/* PPC64 partition types */
+	PSTORE_TYPE_PPC_RTAS	= 4,
+	PSTORE_TYPE_PPC_OF	= 5,
+	PSTORE_TYPE_PPC_COMMON	= 6,
 	PSTORE_TYPE_UNKNOWN	= 255
 };
 
···
 			struct pstore_info *psi);
 	int		(*write)(enum pstore_type_id type,
 			enum kmsg_dump_reason reason, u64 *id,
-			unsigned int part, int count, size_t size,
-			struct pstore_info *psi);
+			unsigned int part, int count, size_t hsize,
+			size_t size, struct pstore_info *psi);
 	int		(*write_buf)(enum pstore_type_id type,
 			enum kmsg_dump_reason reason, u64 *id,
-			unsigned int part, const char *buf, size_t size,
-			struct pstore_info *psi);
+			unsigned int part, const char *buf, size_t hsize,
+			size_t size, struct pstore_info *psi);
 	int		(*erase)(enum pstore_type_id type, u64 id,
 			int count, struct timespec time,
 			struct pstore_info *psi);

include/uapi/linux/vfio.h

···
 /* Extensions */
 
 #define VFIO_TYPE1_IOMMU		1
+#define VFIO_SPAPR_TCE_IOMMU		2
 
 /*
  * The IOCTL interface is designed for extensibility by embedding the
···
 };
 
 #define VFIO_IOMMU_UNMAP_DMA _IO(VFIO_TYPE, VFIO_BASE + 14)
+
+/*
+ * IOCTLs to enable/disable IOMMU container usage.
+ * No parameters are supported.
+ */
+#define VFIO_IOMMU_ENABLE	_IO(VFIO_TYPE, VFIO_BASE + 15)
+#define VFIO_IOMMU_DISABLE	_IO(VFIO_TYPE, VFIO_BASE + 16)
+
+/* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */
+
+/*
+ * The SPAPR TCE info struct provides the information about the PCI bus
+ * address ranges available for DMA, these values are programmed into
+ * the hardware so the guest has to know that information.
+ *
+ * The DMA 32 bit window start is an absolute PCI bus address.
+ * The IOVA address passed via map/unmap ioctls are absolute PCI bus
+ * addresses too so the window works as a filter rather than an offset
+ * for IOVA addresses.
+ *
+ * A flag will need to be added if other page sizes are supported,
+ * so as defined here, it is always 4k.
+ */
+struct vfio_iommu_spapr_tce_info {
+	__u32 argsz;
+	__u32 flags;			/* reserved for future use */
+	__u32 dma32_window_start;	/* 32 bit window start (bytes) */
+	__u32 dma32_window_size;	/* 32 bit window size (bytes) */
+};
+
+#define VFIO_IOMMU_SPAPR_TCE_GET_INFO	_IO(VFIO_TYPE, VFIO_BASE + 12)
+
+/* ***************************************************************** */
 
 #endif /* _UAPIVFIO_H */

mm/huge_memory.c

···
 		pmd_t entry;
 		entry = mk_huge_pmd(page, vma);
 		page_add_new_anon_rmap(page, vma, haddr);
+		pgtable_trans_huge_deposit(mm, pmd, pgtable);
 		set_pmd_at(mm, haddr, pmd, entry);
-		pgtable_trans_huge_deposit(mm, pgtable);
 		add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);
 		mm->nr_ptes++;
 		spin_unlock(&mm->page_table_lock);
···
 	entry = mk_pmd(zero_page, vma->vm_page_prot);
 	entry = pmd_wrprotect(entry);
 	entry = pmd_mkhuge(entry);
+	pgtable_trans_huge_deposit(mm, pmd, pgtable);
 	set_pmd_at(mm, haddr, pmd, entry);
-	pgtable_trans_huge_deposit(mm, pgtable);
 	mm->nr_ptes++;
 	return true;
 }
···
 
 	pmdp_set_wrprotect(src_mm, addr, src_pmd);
 	pmd = pmd_mkold(pmd_wrprotect(pmd));
+	pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);
 	set_pmd_at(dst_mm, addr, dst_pmd, pmd);
-	pgtable_trans_huge_deposit(dst_mm, pgtable);
 	dst_mm->nr_ptes++;
 
 	ret = 0;
···
 	pmdp_clear_flush(vma, haddr, pmd);
 	/* leave pmd empty until pte is filled */
 
-	pgtable = pgtable_trans_huge_withdraw(mm);
+	pgtable = pgtable_trans_huge_withdraw(mm, pmd);
 	pmd_populate(mm, &_pmd, pgtable);
 
 	for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
···
 	pmdp_clear_flush(vma, haddr, pmd);
 	/* leave pmd empty until pte is filled */
 
-	pgtable = pgtable_trans_huge_withdraw(mm);
+	pgtable = pgtable_trans_huge_withdraw(mm, pmd);
 	pmd_populate(mm, &_pmd, pgtable);
 
 	for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
···
 		 * young bit, instead of the current set_pmd_at.
 		 */
 		_pmd = pmd_mkyoung(pmd_mkdirty(*pmd));
-		set_pmd_at(mm, addr & HPAGE_PMD_MASK, pmd, _pmd);
+		if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK,
+					  pmd, _pmd,  1))
+			update_mmu_cache_pmd(vma, addr, pmd);
 	}
 	if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
 		if (page->mapping && trylock_page(page)) {
···
 		struct page *page;
 		pgtable_t pgtable;
 		pmd_t orig_pmd;
-		pgtable = pgtable_trans_huge_withdraw(tlb->mm);
+		/*
+		 * For architectures like ppc64 we look at deposited pgtable
+		 * when calling pmdp_get_and_clear. So do the
+		 * pgtable_trans_huge_withdraw after finishing pmdp related
+		 * operations.
+		 */
 		orig_pmd = pmdp_get_and_clear(tlb->mm, addr, pmd);
 		tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
+		pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd);
 		if (is_huge_zero_pmd(orig_pmd)) {
 			tlb->mm->nr_ptes--;
 			spin_unlock(&tlb->mm->page_table_lock);
···
 	pmd = page_check_address_pmd(page, mm, address,
 				     PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG);
 	if (pmd) {
-		pgtable = pgtable_trans_huge_withdraw(mm);
+		pgtable = pgtable_trans_huge_withdraw(mm, pmd);
 		pmd_populate(mm, &_pmd, pgtable);
 
 		haddr = address;
···
 	spin_lock(&mm->page_table_lock);
 	BUG_ON(!pmd_none(*pmd));
 	page_add_new_anon_rmap(new_page, vma, address);
+	pgtable_trans_huge_deposit(mm, pmd, pgtable);
 	set_pmd_at(mm, address, pmd, _pmd);
 	update_mmu_cache_pmd(vma, address, pmd);
-	pgtable_trans_huge_deposit(mm, pgtable);
 	spin_unlock(&mm->page_table_lock);
 
 	*hpage = NULL;
···
 	pmdp_clear_flush(vma, haddr, pmd);
 	/* leave pmd empty until pte is filled */
 
-	pgtable = pgtable_trans_huge_withdraw(mm);
+	pgtable = pgtable_trans_huge_withdraw(mm, pmd);
 	pmd_populate(mm, &_pmd, pgtable);
 
 	for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {

mm/pgtable-generic.c

···
 
 #ifndef __HAVE_ARCH_PGTABLE_DEPOSIT
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable)
+void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+				pgtable_t pgtable)
 {
 	assert_spin_locked(&mm->page_table_lock);
 
···
 #ifndef __HAVE_ARCH_PGTABLE_WITHDRAW
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 /* no "address" argument so destroys page coloring of some arch */
-pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm)
+pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
 {
 	pgtable_t pgtable;