Merge tag 'powerpc-3.19-1' of git://git.kernel.org/pub/scm/linux/kernel/git/mpe/linux

Pull powerpc updates from Michael Ellerman:
"Some nice cleanups like removing bootmem, and removal of
__get_cpu_var().

There is one patch to mm/gup.c. This is the generic GUP
implementation, but is only used by us and arm(64). We have an ack
from Steve Capper, and although we didn't get an ack from Andrew he
told us to take the patch through the powerpc tree.

There's one cxl patch. This is in drivers/misc, but Greg said he was
happy for us to manage fixes for it.

There is an infrastructure patch to support an IPMI driver for OPAL.

There is also an RTC driver for OPAL. We weren't able to get any
response from the RTC maintainer, Alessandro Zummo, so in the end we
just merged the driver.

The usual batch of Freescale updates from Scott"

* tag 'powerpc-3.19-1' of git://git.kernel.org/pub/scm/linux/kernel/git/mpe/linux: (101 commits)
powerpc/powernv: Return to cpu offline loop when finished in KVM guest
powerpc/book3s: Fix partial invalidation of TLBs in MCE code.
powerpc/mm: don't do tlbie for updatepp request with NO HPTE fault
powerpc/xmon: Cleanup the breakpoint flags
powerpc/xmon: Enable HW instruction breakpoint on POWER8
powerpc/mm/thp: Use tlbiel if possible
powerpc/mm/thp: Remove code duplication
powerpc/mm/hugetlb: Sanity check gigantic hugepage count
powerpc/oprofile: Disable pagefaults during user stack read
powerpc/mm: Check for matching hpte without taking hpte lock
powerpc: Drop useless warning in eeh_init()
powerpc/powernv: Cleanup unused MCE definitions/declarations.
powerpc/eeh: Dump PHB diag-data early
powerpc/eeh: Recover EEH error on ownership change for BCM5719
powerpc/eeh: Set EEH_PE_RESET on PE reset
powerpc/eeh: Refactor eeh_reset_pe()
powerpc: Remove more traces of bootmem
powerpc/pseries: Initialise nvram_pstore_info's buf_lock
cxl: Name interrupts in /proc/interrupt
cxl: Return error to PSL if IRQ demultiplexing fails & print clearer warning
...

Documentation/devicetree/bindings/clock/qoriq-clock.txt

···
 		It takes parent's clock-frequency as its clock.
 	* "fsl,qoriq-sysclk-2.0": for input system clock (v2.0).
 		It takes parent's clock-frequency as its clock.
+	* "fsl,qoriq-platform-pll-1.0" for the platform PLL clock (v1.0)
+	* "fsl,qoriq-platform-pll-2.0" for the platform PLL clock (v2.0)
 - #clock-cells: From common clock binding. The number of cells in a
 	clock-specifier. Should be <0> for "fsl,qoriq-sysclk-[1,2].0"
 	clocks, or <1> for "fsl,qoriq-core-pll-[1,2].0" clocks.
···
 			clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2";
 			clock-output-names = "cmux1";
 		};
+
+		platform-pll: platform-pll@c00 {
+			#clock-cells = <1>;
+			reg = <0xc00 0x4>;
+			compatible = "fsl,qoriq-platform-pll-1.0";
+			clocks = <&sysclk>;
+			clock-output-names = "platform-pll", "platform-pll-div2";
+		};
 	};
-  }
+};
 
 Example for clock consumer:
 
···
 		clocks = <&mux0>;
 		...
 	};
-  }
+};

Documentation/devicetree/bindings/powerpc/fsl/fman.txt

···
+=============================================================================
+Freescale Frame Manager Device Bindings
+
+CONTENTS
+  - FMan Node
+  - FMan Port Node
+  - FMan MURAM Node
+  - FMan dTSEC/XGEC/mEMAC Node
+  - FMan IEEE 1588 Node
+  - Example
+
+=============================================================================
+FMan Node
+
+DESCRIPTION
+
+Due to the fact that the FMan is an aggregation of sub-engines (ports, MACs,
+etc.) the FMan node will have child nodes for each of them.
+
+PROPERTIES
+
+- compatible
+		Usage: required
+		Value type: <stringlist>
+		Definition: Must include "fsl,fman"
+		FMan version can be determined via FM_IP_REV_1 register in the
+		FMan block. The offset is 0xc4 from the beginning of the
+		Frame Processing Manager memory map (0xc3000 from the
+		beginning of the FMan node).
+
+- cell-index
+		Usage: required
+		Value type: <u32>
+		Definition: Specifies the index of the FMan unit.
+
+		The cell-index value may be used by the SoC, to identify the
+		FMan unit in the SoC memory map. In the table bellow,
+		there's a description of the cell-index use in each SoC:
+
+		- P1023:
+		register[bit]			FMan unit	cell-index
+		============================================================
+		DEVDISR[1]			1		0
+
+		- P2041, P3041, P4080 P5020, P5040:
+		register[bit]			FMan unit	cell-index
+		============================================================
+		DCFG_DEVDISR2[6]		1		0
+		DCFG_DEVDISR2[14]		2		1
+			(Second FM available only in P4080 and P5040)
+
+		- B4860, T1040, T2080, T4240:
+		register[bit]			FMan unit	cell-index
+		============================================================
+		DCFG_CCSR_DEVDISR2[24]		1		0
+		DCFG_CCSR_DEVDISR2[25]		2		1
+			(Second FM available only in T4240)
+
+		DEVDISR, DCFG_DEVDISR2 and DCFG_CCSR_DEVDISR2 are located in
+		the specific SoC "Device Configuration/Pin Control" Memory
+		Map.
+
+- reg
+		Usage: required
+		Value type: <prop-encoded-array>
+		Definition: A standard property. Specifies the offset of the
+		following configuration registers:
+		- BMI configuration registers.
+		- QMI configuration registers.
+		- DMA configuration registers.
+		- FPM configuration registers.
+		- FMan controller configuration registers.
+
+- ranges
+		Usage: required
+		Value type: <prop-encoded-array>
+		Definition: A standard property.
+
+- clocks
+		Usage: required
+		Value type: <prop-encoded-array>
+		Definition: phandle for the fman input clock.
+
+- clock-names
+		usage: required
+		Value type: <stringlist>
+		Definition: "fmanclk" for the fman input clock.
+
+- interrupts
+		Usage: required
+		Value type: <prop-encoded-array>
+		Definition: A pair of IRQs are specified in this property.
+		The first element is associated with the event interrupts and
+		the second element is associated with the error interrupts.
+
+- fsl,qman-channel-range
+		Usage: required
+		Value type: <prop-encoded-array>
+		Definition: Specifies the range of the available dedicated
+		channels in the FMan. The first cell specifies the beginning
+		of the range and the second cell specifies the number of
+		channels.
+		Further information available at:
+		"Work Queue (WQ) Channel Assignments in the QMan" section
+		in DPAA Reference Manual.
+
+- fsl,qman
+- fsl,bman
+		Usage: required
+		Definition: See soc/fsl/qman.txt and soc/fsl/bman.txt
+
+=============================================================================
+FMan MURAM Node
+
+DESCRIPTION
+
+FMan Internal memory - shared between all the FMan modules.
+It contains data structures that are common and written to or read by
+the modules.
+FMan internal memory is split into the following parts:
+	Packet buffering (Tx/Rx FIFOs)
+	Frames internal context
+
+PROPERTIES
+
+- compatible
+		Usage: required
+		Value type: <stringlist>
+		Definition: Must include "fsl,fman-muram"
+
+- ranges
+		Usage: required
+		Value type: <prop-encoded-array>
+		Definition: A standard property.
+		Specifies the multi-user memory offset and the size within
+		the FMan.
+
+EXAMPLE
+
+muram@0 {
+	compatible = "fsl,fman-muram";
+	ranges = <0 0x000000 0x28000>;
+};
+
+=============================================================================
+FMan Port Node
+
+DESCRIPTION
+
+The Frame Manager (FMan) supports several types of hardware ports:
+	Ethernet receiver (RX)
+	Ethernet transmitter (TX)
+	Offline/Host command (O/H)
+
+PROPERTIES
+
+- compatible
+		Usage: required
+		Value type: <stringlist>
+		Definition: A standard property.
+		Must include one of the following:
+			- "fsl,fman-v2-port-oh" for FManV2 OH ports
+			- "fsl,fman-v2-port-rx" for FManV2 RX ports
+			- "fsl,fman-v2-port-tx" for FManV2 TX ports
+			- "fsl,fman-v3-port-oh" for FManV3 OH ports
+			- "fsl,fman-v3-port-rx" for FManV3 RX ports
+			- "fsl,fman-v3-port-tx" for FManV3 TX ports
+
+- cell-index
+		Usage: required
+		Value type: <u32>
+		Definition: Specifies the hardware port id.
+		Each hardware port on the FMan has its own hardware PortID.
+		Super set of all hardware Port IDs available at FMan Reference
+		Manual under "FMan Hardware Ports in Freescale Devices" table.
+
+		Each hardware port is assigned a 4KB, port-specific page in
+		the FMan hardware port memory region (which is part of the
+		FMan memory map). The first 4 KB in the FMan hardware ports
+		memory region is used for what are called common registers.
+		The subsequent 63 4KB pages are allocated to the hardware
+		ports.
+		The page of a specific port is determined by the cell-index.
+
+- reg
+		Usage: required
+		Value type: <prop-encoded-array>
+		Definition: There is one reg region describing the port
+		configuration registers.
+
+EXAMPLE
+
+port@a8000 {
+	cell-index = <0x28>;
+	compatible = "fsl,fman-v2-port-tx";
+	reg = <0xa8000 0x1000>;
+};
+
+port@88000 {
+	cell-index = <0x8>;
+	compatible = "fsl,fman-v2-port-rx";
+	reg = <0x88000 0x1000>;
+};
+
+port@81000 {
+	cell-index = <0x1>;
+	compatible = "fsl,fman-v2-port-oh";
+	reg = <0x81000 0x1000>;
+};
+
+=============================================================================
+FMan dTSEC/XGEC/mEMAC Node
+
+DESCRIPTION
+
+mEMAC/dTSEC/XGEC are the Ethernet network interfaces
+
+PROPERTIES
+
+- compatible
+		Usage: required
+		Value type: <stringlist>
+		Definition: A standard property.
+		Must include one of the following:
+		- "fsl,fman-dtsec" for dTSEC MAC
+		- "fsl,fman-xgec" for XGEC MAC
+		- "fsl,fman-memac for mEMAC MAC
+
+- cell-index
+		Usage: required
+		Value type: <u32>
+		Definition: Specifies the MAC id.
+
+		The cell-index value may be used by the FMan or the SoC, to
+		identify the MAC unit in the FMan (or SoC) memory map.
+		In the tables bellow there's a description of the cell-index
+		use, there are two tables, one describes the use of cell-index
+		by the FMan, the second describes the use by the SoC:
+
+		1. FMan Registers
+
+		FManV2:
+		register[bit]		MAC		cell-index
+		============================================================
+		FM_EPI[16]		XGEC		8
+		FM_EPI[16+n]		dTSECn		n-1
+		FM_NPI[11+n]		dTSECn		n-1
+			n = 1,..,5
+
+		FManV3:
+		register[bit]		MAC		cell-index
+		============================================================
+		FM_EPI[16+n]		mEMACn		n-1
+		FM_EPI[25]		mEMAC10		9
+
+		FM_NPI[11+n]		mEMACn		n-1
+		FM_NPI[10]		mEMAC10		9
+		FM_NPI[11]		mEMAC9		8
+			n = 1,..8
+
+		FM_EPI and FM_NPI are located in the FMan memory map.
+
+		2. SoC registers:
+
+		- P2041, P3041, P4080 P5020, P5040:
+		register[bit]		FMan		MAC		cell
+					Unit				index
+		============================================================
+		DCFG_DEVDISR2[7]	1		XGEC		8
+		DCFG_DEVDISR2[7+n]	1		dTSECn		n-1
+		DCFG_DEVDISR2[15]	2		XGEC		8
+		DCFG_DEVDISR2[15+n]	2		dTSECn		n-1
+			n = 1,..5
+
+		- T1040, T2080, T4240, B4860:
+		register[bit]			FMan	MAC		cell
+						Unit			index
+		============================================================
+		DCFG_CCSR_DEVDISR2[n-1]		1	mEMACn		n-1
+		DCFG_CCSR_DEVDISR2[11+n]	2	mEMACn		n-1
+			n = 1,..6,9,10
+
+		EVDISR, DCFG_DEVDISR2 and DCFG_CCSR_DEVDISR2 are located in
+		the specific SoC "Device Configuration/Pin Control" Memory
+		Map.
+
+- reg
+		Usage: required
+		Value type: <prop-encoded-array>
+		Definition: A standard property.
+
+- fsl,fman-ports
+		Usage: required
+		Value type: <prop-encoded-array>
+		Definition: An array of two phandles - the first references is
+		the FMan RX port and the second is the TX port used by this
+		MAC.
+
+- ptp-timer
+		Usage required
+		Value type: <phandle>
+		Definition: A phandle for 1EEE1588 timer.
+
+EXAMPLE
+
+fman1_tx28: port@a8000 {
+	cell-index = <0x28>;
+	compatible = "fsl,fman-v2-port-tx";
+	reg = <0xa8000 0x1000>;
+};
+
+fman1_rx8: port@88000 {
+	cell-index = <0x8>;
+	compatible = "fsl,fman-v2-port-rx";
+	reg = <0x88000 0x1000>;
+};
+
+ptp-timer: ptp_timer@fe000 {
+	compatible = "fsl,fman-ptp-timer";
+	reg = <0xfe000 0x1000>;
+};
+
+ethernet@e0000 {
+	compatible = "fsl,fman-dtsec";
+	cell-index = <0>;
+	reg = <0xe0000 0x1000>;
+	fsl,fman-ports = <&fman1_rx8 &fman1_tx28>;
+	ptp-timer = <&ptp-timer>;
+};
+
+============================================================================
+FMan IEEE 1588 Node
+
+DESCRIPTION
+
+The FMan interface to support IEEE 1588
+
+
+PROPERTIES
+
+- compatible
+		Usage: required
+		Value type: <stringlist>
+		Definition: A standard property.
+		Must include "fsl,fman-ptp-timer".
+
+- reg
+		Usage: required
+		Value type: <prop-encoded-array>
+		Definition: A standard property.
+
+EXAMPLE
+
+ptp-timer@fe000 {
+	compatible = "fsl,fman-ptp-timer";
+	reg = <0xfe000 0x1000>;
+};
+
+=============================================================================
+Example
+
+fman@400000 {
+	#address-cells = <1>;
+	#size-cells = <1>;
+	cell-index = <1>;
+	compatible = "fsl,fman"
+	ranges = <0 0x400000 0x100000>;
+	reg = <0x400000 0x100000>;
+	clocks = <&fman_clk>;
+	clock-names = "fmanclk";
+	interrupts = <
+		96 2 0 0
+		16 2 1 1>;
+	fsl,qman-channel-range = <0x40 0xc>;
+
+	muram@0 {
+		compatible = "fsl,fman-muram";
+		reg = <0x0 0x28000>;
+	};
+
+	port@81000 {
+		cell-index = <1>;
+		compatible = "fsl,fman-v2-port-oh";
+		reg = <0x81000 0x1000>;
+	};
+
+	port@82000 {
+		cell-index = <2>;
+		compatible = "fsl,fman-v2-port-oh";
+		reg = <0x82000 0x1000>;
+	};
+
+	port@83000 {
+		cell-index = <3>;
+		compatible = "fsl,fman-v2-port-oh";
+		reg = <0x83000 0x1000>;
+	};
+
+	port@84000 {
+		cell-index = <4>;
+		compatible = "fsl,fman-v2-port-oh";
+		reg = <0x84000 0x1000>;
+	};
+
+	port@85000 {
+		cell-index = <5>;
+		compatible = "fsl,fman-v2-port-oh";
+		reg = <0x85000 0x1000>;
+	};
+
+	port@86000 {
+		cell-index = <6>;
+		compatible = "fsl,fman-v2-port-oh";
+		reg = <0x86000 0x1000>;
+	};
+
+	fman1_rx_0x8: port@88000 {
+		cell-index = <0x8>;
+		compatible = "fsl,fman-v2-port-rx";
+		reg = <0x88000 0x1000>;
+	};
+
+	fman1_rx_0x9: port@89000 {
+		cell-index = <0x9>;
+		compatible = "fsl,fman-v2-port-rx";
+		reg = <0x89000 0x1000>;
+	};
+
+	fman1_rx_0xa: port@8a000 {
+		cell-index = <0xa>;
+		compatible = "fsl,fman-v2-port-rx";
+		reg = <0x8a000 0x1000>;
+	};
+
+	fman1_rx_0xb: port@8b000 {
+		cell-index = <0xb>;
+		compatible = "fsl,fman-v2-port-rx";
+		reg = <0x8b000 0x1000>;
+	};
+
+	fman1_rx_0xc: port@8c000 {
+		cell-index = <0xc>;
+		compatible = "fsl,fman-v2-port-rx";
+		reg = <0x8c000 0x1000>;
+	};
+
+	fman1_rx_0x10: port@90000 {
+		cell-index = <0x10>;
+		compatible = "fsl,fman-v2-port-rx";
+		reg = <0x90000 0x1000>;
+	};
+
+	fman1_tx_0x28: port@a8000 {
+		cell-index = <0x28>;
+		compatible = "fsl,fman-v2-port-tx";
+		reg = <0xa8000 0x1000>;
+	};
+
+	fman1_tx_0x29: port@a9000 {
+		cell-index = <0x29>;
+		compatible = "fsl,fman-v2-port-tx";
+		reg = <0xa9000 0x1000>;
+	};
+
+	fman1_tx_0x2a: port@aa000 {
+		cell-index = <0x2a>;
+		compatible = "fsl,fman-v2-port-tx";
+		reg = <0xaa000 0x1000>;
+	};
+
+	fman1_tx_0x2b: port@ab000 {
+		cell-index = <0x2b>;
+		compatible = "fsl,fman-v2-port-tx";
+		reg = <0xab000 0x1000>;
+	};
+
+	fman1_tx_0x2c: port@ac0000 {
+		cell-index = <0x2c>;
+		compatible = "fsl,fman-v2-port-tx";
+		reg = <0xac000 0x1000>;
+	};
+
+	fman1_tx_0x30: port@b0000 {
+		cell-index = <0x30>;
+		compatible = "fsl,fman-v2-port-tx";
+		reg = <0xb0000 0x1000>;
+	};
+
+	ethernet@e0000 {
+		compatible = "fsl,fman-dtsec";
+		cell-index = <0>;
+		reg = <0xe0000 0x1000>;
+		fsl,fman-ports = <&fman1_rx_0x8 &fman1_tx_0x28>;
+	};
+
+	ethernet@e2000 {
+		compatible = "fsl,fman-dtsec";
+		cell-index = <1>;
+		reg = <0xe2000 0x1000>;
+		fsl,fman-ports = <&fman1_rx_0x9 &fman1_tx_0x29>;
+	};
+
+	ethernet@e4000 {
+		compatible = "fsl,fman-dtsec";
+		cell-index = <2>;
+		reg = <0xe4000 0x1000>;
+		fsl,fman-ports = <&fman1_rx_0xa &fman1_tx_0x2a>;
+	};
+
+	ethernet@e6000 {
+		compatible = "fsl,fman-dtsec";
+		cell-index = <3>;
+		reg = <0xe6000 0x1000>;
+		fsl,fman-ports = <&fman1_rx_0xb &fman1_tx_0x2b>;
+	};
+
+	ethernet@e8000 {
+		compatible = "fsl,fman-dtsec";
+		cell-index = <4>;
+		reg = <0xf0000 0x1000>;
+		fsl,fman-ports = <&fman1_rx_0xc &fman1_tx_0x2c>;
+
+	ethernet@f0000 {
+		cell-index = <8>;
+		compatible = "fsl,fman-xgec";
+		reg = <0xf0000 0x1000>;
+		fsl,fman-ports = <&fman1_rx_0x10 &fman1_tx_0x30>;
+	};
+
+	ptp-timer@fe000 {
+		compatible = "fsl,fman-ptp-timer";
+		reg = <0xfe000 0x1000>;
+	};
+};

Documentation/devicetree/bindings/rtc/rtc-opal.txt

···
+IBM OPAL real-time clock
+------------------------
+
+Required properties:
+- comapatible: Should be "ibm,opal-rtc"
+
+Optional properties:
+- has-tpo: Decides if the wakeup is supported or not.
+
+Example:
+	rtc {
+		compatible = "ibm,opal-rtc";
+		has-tpo;
+		phandle = <0x10000029>;
+		linux,phandle = <0x10000029>;
+	};

Documentation/devicetree/bindings/soc/fsl/bman-portals.txt

···
+QorIQ DPAA Buffer Manager Portals Device Tree Binding
+
+Copyright (C) 2008 - 2014 Freescale Semiconductor Inc.
+
+CONTENTS
+
+	- BMan Portal
+	- Example
+
+BMan Portal Node
+
+Portals are memory mapped interfaces to BMan that allow low-latency, lock-less
+interaction by software running on processor cores, accelerators and network
+interfaces with the BMan
+
+PROPERTIES
+
+- compatible
+	Usage:		Required
+	Value type:	<stringlist>
+	Definition:	Must include "fsl,bman-portal-<hardware revision>"
+			May include "fsl,<SoC>-bman-portal" or "fsl,bman-portal"
+
+- reg
+	Usage:		Required
+	Value type:	<prop-encoded-array>
+	Definition:	Two regions. The first is the cache-enabled region of
+			the portal. The second is the cache-inhibited region of
+			the portal
+
+- interrupts
+	Usage:		Required
+	Value type:	<prop-encoded-array>
+	Definition:	Standard property
+
+EXAMPLE
+
+The example below shows a (P4080) BMan portals container/bus node with two portals
+
+	bman-portals@ff4000000 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "simple-bus";
+		ranges = <0 0xf 0xf4000000 0x200000>;
+
+		bman-portal@0 {
+			compatible = "fsl,bman-portal-1.0.0", "fsl,bman-portal";
+			reg = <0x0 0x4000>, <0x100000 0x1000>;
+			interrupts = <105 2 0 0>;
+		};
+		bman-portal@4000 {
+			compatible = "fsl,bman-portal-1.0.0", "fsl,bman-portal";
+			reg = <0x4000 0x4000>, <0x101000 0x1000>;
+			interrupts = <107 2 0 0>;
+		};
+	};

Documentation/devicetree/bindings/soc/fsl/bman.txt

···
+QorIQ DPAA Buffer Manager Device Tree Bindings
+
+Copyright (C) 2008 - 2014 Freescale Semiconductor Inc.
+
+CONTENTS
+
+	- BMan Node
+	- BMan Private Memory Node
+	- Example
+
+BMan Node
+
+The Buffer Manager is part of the Data-Path Acceleration Architecture (DPAA).
+BMan supports hardware allocation and deallocation of buffers belonging to pools
+originally created by software with configurable depletion thresholds. This
+binding covers the CCSR space programming model
+
+PROPERTIES
+
+- compatible
+	Usage:		Required
+	Value type:	<stringlist>
+	Definition:	Must include "fsl,bman"
+			May include "fsl,<SoC>-bman"
+
+- reg
+	Usage:		Required
+	Value type:	<prop-encoded-array>
+	Definition:	Registers region within the CCSR address space
+
+The BMan revision information is located in the BMAN_IP_REV_1/2 registers which
+are located at offsets 0xbf8 and 0xbfc
+
+- interrupts
+	Usage:		Required
+	Value type:	<prop-encoded-array>
+	Definition:	Standard property. The error interrupt
+
+- fsl,liodn
+	Usage:		See pamu.txt
+	Value type:	<prop-encoded-array>
+	Definition:	PAMU property used for static LIODN assignment
+
+- fsl,iommu-parent
+	Usage:		See pamu.txt
+	Value type:	<phandle>
+	Definition:	PAMU property used for dynamic LIODN assignment
+
+	For additional details about the PAMU/LIODN binding(s) see pamu.txt
+
+Devices connected to a BMan instance via Direct Connect Portals (DCP) must link
+to the respective BMan instance
+
+- fsl,bman
+	Usage:		Required
+	Value type:	<prop-encoded-array>
+	Description:	List of phandle and DCP index pairs, to the BMan instance
+			to which this device is connected via the DCP
+
+BMan Private Memory Node
+
+BMan requires a contiguous range of physical memory used for the backing store
+for BMan Free Buffer Proxy Records (FBPR). This memory is reserved/allocated as a
+node under the /reserved-memory node
+
+The BMan FBPR memory node must be named "bman-fbpr"
+
+PROPERTIES
+
+- compatible
+	Usage:		required
+	Value type:	<stringlist>
+	Definition:	Must inclide "fsl,bman-fbpr"
+
+The following constraints are relevant to the FBPR private memory:
+	- The size must be 2^(size + 1), with size = 11..33. That is 4 KiB to
+	  16 GiB
+	- The alignment must be a muliptle of the memory size
+
+The size of the FBPR must be chosen by observing the hardware features configured
+via the Reset Configuration Word (RCW) and that are relevant to a specific board
+(e.g. number of MAC(s) pinned-out, number of offline/host command FMan ports,
+etc.). The size configured in the DT must reflect the hardware capabilities and
+not the specific needs of an application
+
+For additional details about reserved memory regions see reserved-memory.txt
+
+EXAMPLE
+
+The example below shows a BMan FBPR dynamic allocation memory node
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		bman_fbpr: bman-fbpr {
+			compatible = "fsl,bman-fbpr";
+			alloc-ranges = <0 0 0xf 0xffffffff>;
+			size = <0 0x1000000>;
+			alignment = <0 0x1000000>;
+		};
+	};
+
+The example below shows a (P4080) BMan CCSR-space node
+
+	crypto@300000 {
+		...
+		fsl,bman = <&bman, 2>;
+		...
+	};
+
+	bman: bman@31a000 {
+		compatible = "fsl,bman";
+		reg = <0x31a000 0x1000>;
+		interrupts = <16 2 1 2>;
+		fsl,liodn = <0x17>;
+		memory-region = <&bman_fbpr>;
+	};
+
+	fman@400000 {
+		...
+		fsl,bman = <&bman, 0>;
+		...
+	};

Documentation/devicetree/bindings/soc/fsl/qman-portals.txt

···
+QorIQ DPAA Queue Manager Portals Device Tree Binding
+
+Copyright (C) 2008 - 2014 Freescale Semiconductor Inc.
+
+CONTENTS
+
+	- QMan Portal
+	- QMan Pool Channel
+	- Example
+
+QMan Portal Node
+
+Portals are memory mapped interfaces to QMan that allow low-latency, lock-less
+interaction by software running on processor cores, accelerators and network
+interfaces with the QMan
+
+PROPERTIES
+
+- compatible
+	Usage:		Required
+	Value type:	<stringlist>
+	Definition:	Must include "fsl,qman-portal-<hardware revision>"
+			May include "fsl,<SoC>-qman-portal" or "fsl,qman-portal"
+
+- reg
+	Usage:		Required
+	Value type:	<prop-encoded-array>
+	Definition:	Two regions. The first is the cache-enabled region of
+			the portal. The second is the cache-inhibited region of
+			the portal
+
+- interrupts
+	Usage:		Required
+	Value type:	<prop-encoded-array>
+	Definition:	Standard property
+
+- fsl,liodn
+	Usage:		See pamu.txt
+	Value type:	<prop-encoded-array>
+	Definition:	Two LIODN(s). DQRR LIODN (DLIODN) and Frame LIODN
+			(FLIODN)
+
+- fsl,iommu-parent
+	Usage:		See pamu.txt
+	Value type:	<phandle>
+	Definition:	PAMU property used for dynamic LIODN assignment
+
+	For additional details about the PAMU/LIODN binding(s) see pamu.txt
+
+- fsl,qman-channel-id
+	Usage:		Required
+	Value type:	<u32>
+	Definition:	The hardware index of the channel. This can also be
+			determined by dividing any of the channel's 8 work queue
+			IDs by 8
+
+In addition to these properties the qman-portals should have sub-nodes to
+represent the HW devices/portals that are connected to the software portal
+described here
+
+The currently supported sub-nodes are:
+	* fman0
+	* fman1
+	* pme
+	* crypto
+
+These subnodes should have the following properties:
+
+- fsl,liodn
+	Usage:		See pamu.txt
+	Value type:	<prop-encoded-array>
+	Definition:	PAMU property used for static LIODN assignment
+
+- fsl,iommu-parent
+	Usage:		See pamu.txt
+	Value type:	<phandle>
+	Definition:	PAMU property used for dynamic LIODN assignment
+
+- dev-handle
+	Usage:		Required
+	Value type:	<phandle>
+	Definition:	The phandle to the particular hardware device that this
+			portal is connected to.
+
+DPAA QMan Pool Channel Nodes
+
+Pool Channels are defined with the following properties.
+
+PROPERTIES
+
+- compatible
+	Usage:		Required
+	Value type:	<stringlist>
+	Definition:	Must include "fsl,qman-pool-channel"
+			May include "fsl,<SoC>-qman-pool-channel"
+
+- fsl,qman-channel-id
+	Usage:		Required
+	Value type:	<u32>
+	Definition:	The hardware index of the channel. This can also be
+			determined by dividing any of the channel's 8 work queue
+			IDs by 8
+
+EXAMPLE
+
+The example below shows a (P4080) QMan portals container/bus node with two portals
+
+	qman-portals@ff4200000 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "simple-bus";
+		ranges = <0 0xf 0xf4200000 0x200000>;
+
+		qman-portal@0 {
+			compatible = "fsl,qman-portal-1.2.0", "fsl,qman-portal";
+			reg = <0 0x4000>, <0x100000 0x1000>;
+			interrupts = <104 2 0 0>;
+			fsl,liodn = <1 2>;
+			fsl,qman-channel-id = <0>;
+
+			fman0 {
+				fsl,liodn = <0x21>;
+				dev-handle = <&fman0>;
+			};
+			fman1 {
+				fsl,liodn = <0xa1>;
+				dev-handle = <&fman1>;
+			};
+			crypto {
+				fsl,liodn = <0x41 0x66>;
+				dev-handle = <&crypto>;
+			};
+		};
+		qman-portal@4000 {
+			compatible = "fsl,qman-portal-1.2.0", "fsl,qman-portal";
+			reg = <0x4000 0x4000>, <0x101000 0x1000>;
+			interrupts = <106 2 0 0>;
+			fsl,liodn = <3 4>;
+			fsl,qman-channel-id = <1>;
+
+			fman0 {
+				fsl,liodn = <0x22>;
+				dev-handle = <&fman0>;
+			};
+			fman1 {
+				fsl,liodn = <0xa2>;
+				dev-handle = <&fman1>;
+			};
+			crypto {
+				fsl,liodn = <0x42 0x67>;
+				dev-handle = <&crypto>;
+			};
+		};
+	};

Documentation/devicetree/bindings/soc/fsl/qman.txt

···
+QorIQ DPAA Queue Manager Device Tree Binding
+
+Copyright (C) 2008 - 2014 Freescale Semiconductor Inc.
+
+CONTENTS
+
+	- QMan Node
+	- QMan Private Memory Nodes
+	- Example
+
+QMan Node
+
+The Queue Manager is part of the Data-Path Acceleration Architecture (DPAA). QMan
+supports queuing and QoS scheduling of frames to CPUs, network interfaces and
+DPAA logic modules, maintains packet ordering within flows. Besides providing
+flow-level queuing, is also responsible for congestion management functions such
+as RED/WRED, congestion notifications and tail discards. This binding covers the
+CCSR space programming model
+
+PROPERTIES
+
+- compatible
+	Usage:		Required
+	Value type:	<stringlist>
+	Definition:	Must include "fsl,qman"
+			May include "fsl,<SoC>-qman"
+
+- reg
+	Usage:		Required
+	Value type:	<prop-encoded-array>
+	Definition:	Registers region within the CCSR address space
+
+The QMan revision information is located in the QMAN_IP_REV_1/2 registers which
+are located at offsets 0xbf8 and 0xbfc
+
+- interrupts
+	Usage:		Required
+	Value type:	<prop-encoded-array>
+	Definition:	Standard property. The error interrupt
+
+- fsl,liodn
+	Usage:		See pamu.txt
+	Value type:	<prop-encoded-array>
+	Definition:	PAMU property used for static LIODN assignment
+
+- fsl,iommu-parent
+	Usage:		See pamu.txt
+	Value type:	<phandle>
+	Definition:	PAMU property used for dynamic LIODN assignment
+
+	For additional details about the PAMU/LIODN binding(s) see pamu.txt
+
+- clocks
+	Usage:		See clock-bindings.txt and qoriq-clock.txt
+	Value type:	<prop-encoded-array>
+	Definition:	Reference input clock. Its frequency is half of the
+			platform clock
+
+Devices connected to a QMan instance via Direct Connect Portals (DCP) must link
+to the respective QMan instance
+
+- fsl,qman
+	Usage:		Required
+	Value type:	<prop-encoded-array>
+	Description:	List of phandle and DCP index pairs, to the QMan instance
+			to which this device is connected via the DCP
+
+QMan Private Memory Nodes
+
+QMan requires two contiguous range of physical memory used for the backing store
+for QMan Frame Queue Descriptor (FQD) and Packed Frame Descriptor Record (PFDR).
+This memory is reserved/allocated as a nodes under the /reserved-memory node
+
+The QMan FQD memory node must be named "qman-fqd"
+
+PROPERTIES
+
+- compatible
+	Usage:		required
+	Value type:	<stringlist>
+	Definition:	Must inclide "fsl,qman-fqd"
+
+The QMan PFDR memory node must be named "qman-pfdr"
+
+PROPERTIES
+
+- compatible
+	Usage:		required
+	Value type:	<stringlist>
+	Definition:	Must inclide "fsl,qman-pfdr"
+
+The following constraints are relevant to the FQD and PFDR private memory:
+	- The size must be 2^(size + 1), with size = 11..29. That is 4 KiB to
+	  1 GiB
+	- The alignment must be a muliptle of the memory size
+
+The size of the FQD and PFDP must be chosen by observing the hardware features
+configured via the Reset Configuration Word (RCW) and that are relevant to a
+specific board (e.g. number of MAC(s) pinned-out, number of offline/host command
+FMan ports, etc.). The size configured in the DT must reflect the hardware
+capabilities and not the specific needs of an application
+
+For additional details about reserved memory regions see reserved-memory.txt
+
+EXAMPLE
+
+The example below shows a QMan FQD and a PFDR dynamic allocation memory nodes
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		qman_fqd: qman-fqd {
+			compatible = "fsl,qman-fqd";
+			alloc-ranges = <0 0 0xf 0xffffffff>;
+			size = <0 0x400000>;
+			alignment = <0 0x400000>;
+		};
+		qman_pfdr: qman-pfdr {
+			compatible = "fsl,qman-pfdr";
+			alloc-ranges = <0 0 0xf 0xffffffff>;
+			size = <0 0x2000000>;
+			alignment = <0 0x2000000>;
+		};
+	};
+
+The example below shows a (P4080) QMan CCSR-space node
+
+	clockgen: global-utilities@e1000 {
+		...
+		sysclk: sysclk {
+			...
+		};
+		...
+		platform_pll: platform-pll@c00 {
+			#clock-cells = <1>;
+			reg = <0xc00 0x4>;
+			compatible = "fsl,qoriq-platform-pll-1.0";
+			clocks = <&sysclk>;
+			clock-output-names = "platform-pll", "platform-pll-div2";
+		};
+		...
+	};
+
+	crypto@300000 {
+		...
+		fsl,qman = <&qman, 2>;
+		...
+	};
+
+	qman: qman@318000 {
+		compatible = "fsl,qman";
+		reg = <0x318000 0x1000>;
+		interrupts = <16 2 1 3>
+		fsl,liodn = <0x16>;
+		memory-region = <&qman_fqd &qman_pfdr>;
+		clocks = <&platform_pll 1>;
+	};
+
+	fman@400000 {
+		...
+		fsl,qman = <&qman, 0>;
+		...
+	};

arch/powerpc/Kconfig

···
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select BINFMT_ELF
+	select ARCH_BINFMT_ELF_RANDOMIZE_PIE
 	select OF
 	select OF_EARLY_FLATTREE
 	select OF_RESERVED_MEM
···
 	select HAVE_ARCH_AUDITSYSCALL
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select DCACHE_WORD_ACCESS if PPC64 && CPU_LITTLE_ENDIAN
+	select NO_BOOTMEM
+	select HAVE_GENERIC_RCU_GUP
 
 config GENERIC_CSUM
 	def_bool CPU_LITTLE_ENDIAN
···
 	bool "4k page size"
 
 config PPC_16K_PAGES
-	bool "16k page size" if 44x
+	bool "16k page size" if 44x || PPC_8xx
 
 config PPC_64K_PAGES
 	bool "64k page size" if 44x || PPC_STD_MMU_64 || PPC_BOOK3E_64

arch/powerpc/boot/dts/b4860emu.dts

···
 		fsl,liodn-bits = <12>;
 	};
 
-	clockgen: global-utilities@e1000 {
+/include/ "fsl/qoriq-clockgen2.dtsi"
+	global-utilities@e1000 {
 		compatible = "fsl,b4-clockgen", "fsl,qoriq-clockgen-2.0";
-		reg = <0xe1000 0x1000>;
 	};
 
 /include/ "fsl/qoriq-dma-0.dtsi"

arch/powerpc/boot/dts/b4qds.dtsi

···
 						reg = <0x68>;
 					};
 				};
+
+				i2c@2 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <0x2>;
+
+					ina220@40 {
+						compatible = "ti,ina220";
+						reg = <0x40>;
+						shunt-resistor = <1000>;
+					};
+				};
+
+				i2c@3 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <0x3>;
+
+					adt7461@4c {
+						compatible = "adi,adt7461";
+						reg = <0x4c>;
+					};
+				};
 			};
 		};
 

arch/powerpc/boot/dts/bsc9131rdb.dtsi

···
 		compatible = "fsl,ifc-nand";
 		reg = <0x0 0x0 0x4000>;
 
-		partition@0 {
-			/* This location must not be altered  */
-			/* 3MB for u-boot Bootloader Image */
-			reg = <0x0 0x00300000>;
-			label = "NAND U-Boot Image";
-			read-only;
-		};
-
-		partition@300000 {
-			/* 1MB for DTB Image */
-			reg = <0x00300000 0x00100000>;
-			label = "NAND DTB Image";
-		};
-
-		partition@400000 {
-			/* 8MB for Linux Kernel Image */
-			reg = <0x00400000 0x00800000>;
-			label = "NAND Linux Kernel Image";
-		};
-
-		partition@c00000 {
-			/* Rest space for Root file System Image */
-			reg = <0x00c00000 0x07400000>;
-			label = "NAND RFS Image";
-		};
 	};
 };
 
···
 			compatible = "spansion,s25sl12801";
 			reg = <0>;
 			spi-max-frequency = <50000000>;
-
-			/* 512KB for u-boot Bootloader Image */
-			partition@0 {
-				reg = <0x0 0x00080000>;
-				label = "SPI Flash U-Boot Image";
-				read-only;
-			};
-
-			/* 512KB for DTB Image */
-			partition@80000 {
-				reg = <0x00080000 0x00080000>;
-				label = "SPI Flash DTB Image";
-			};
-
-			/* 4MB for Linux Kernel Image */
-			partition@100000 {
-				reg = <0x00100000 0x00400000>;
-				label = "SPI Flash Kernel Image";
-			};
-
-			/*11MB for RFS Image */
-			partition@500000 {
-				reg = <0x00500000 0x00B00000>;
-				label = "SPI Flash RFS Image";
-			};
 
 		};
 	};

arch/powerpc/boot/dts/fsl/b4420si-post.dtsi

···
 		compatible = "fsl,b4420-device-config", "fsl,qoriq-device-config-2.0";
 	};
 
-	clockgen: global-utilities@e1000 {
+/include/ "qoriq-clockgen2.dtsi"
+	global-utilities@e1000 {
 		compatible = "fsl,b4420-clockgen", "fsl,qoriq-clockgen-2.0";
-		ranges = <0x0 0xe1000 0x1000>;
-		#address-cells = <1>;
-		#size-cells = <1>;
-
-		sysclk: sysclk {
-			#clock-cells = <0>;
-			compatible = "fsl,qoriq-sysclk-2.0";
-			clock-output-names = "sysclk";
-		};
-
-		pll0: pll0@800 {
-			#clock-cells = <1>;
-			reg = <0x800 0x4>;
-			compatible = "fsl,qoriq-core-pll-2.0";
-			clocks = <&sysclk>;
-			clock-output-names = "pll0", "pll0-div2", "pll0-div4";
-		};
-
-		pll1: pll1@820 {
-			#clock-cells = <1>;
-			reg = <0x820 0x4>;
-			compatible = "fsl,qoriq-core-pll-2.0";
-			clocks = <&sysclk>;
-			clock-output-names = "pll1", "pll1-div2", "pll1-div4";
-		};
 
 		mux0: mux0@0 {
 			#clock-cells = <0>;

arch/powerpc/boot/dts/fsl/b4860si-post.dtsi

···
 		compatible = "fsl,b4860-device-config", "fsl,qoriq-device-config-2.0";
 	};
 
-	clockgen: global-utilities@e1000 {
+/include/ "qoriq-clockgen2.dtsi"
+	global-utilities@e1000 {
 		compatible = "fsl,b4860-clockgen", "fsl,qoriq-clockgen-2.0";
-		ranges = <0x0 0xe1000 0x1000>;
-		#address-cells = <1>;
-		#size-cells = <1>;
-
-		sysclk: sysclk {
-			#clock-cells = <0>;
-			compatible = "fsl,qoriq-sysclk-2.0";
-			clock-output-names = "sysclk";
-		};
-
-		pll0: pll0@800 {
-			#clock-cells = <1>;
-			reg = <0x800 0x4>;
-			compatible = "fsl,qoriq-core-pll-2.0";
-			clocks = <&sysclk>;
-			clock-output-names = "pll0", "pll0-div2", "pll0-div4";
-		};
-
-		pll1: pll1@820 {
-			#clock-cells = <1>;
-			reg = <0x820 0x4>;
-			compatible = "fsl,qoriq-core-pll-2.0";
-			clocks = <&sysclk>;
-			clock-output-names = "pll1", "pll1-div2", "pll1-div4";
-		};
 
 		mux0: mux0@0 {
 			#clock-cells = <0>;

arch/powerpc/boot/dts/fsl/p2041si-post.dtsi

···
 		#sleep-cells = <2>;
 	};
 
-	clockgen: global-utilities@e1000 {
+/include/ "qoriq-clockgen1.dtsi"
+	global-utilities@e1000 {
 		compatible = "fsl,p2041-clockgen", "fsl,qoriq-clockgen-1.0";
-		ranges = <0x0 0xe1000 0x1000>;
-		reg = <0xe1000 0x1000>;
-		clock-frequency = <0>;
-		#address-cells = <1>;
-		#size-cells = <1>;
-
-		sysclk: sysclk {
-			#clock-cells = <0>;
-			compatible = "fsl,qoriq-sysclk-1.0";
-			clock-output-names = "sysclk";
-		};
-
-		pll0: pll0@800 {
-			#clock-cells = <1>;
-			reg = <0x800 0x4>;
-			compatible = "fsl,qoriq-core-pll-1.0";
-			clocks = <&sysclk>;
-			clock-output-names = "pll0", "pll0-div2";
-		};
-
-		pll1: pll1@820 {
-			#clock-cells = <1>;
-			reg = <0x820 0x4>;
-			compatible = "fsl,qoriq-core-pll-1.0";
-			clocks = <&sysclk>;
-			clock-output-names = "pll1", "pll1-div2";
-		};
-
-		mux0: mux0@0 {
-			#clock-cells = <0>;
-			reg = <0x0 0x4>;
-			compatible = "fsl,qoriq-core-mux-1.0";
-			clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>;
-			clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2";
-			clock-output-names = "cmux0";
-		};
-
-		mux1: mux1@20 {
-			#clock-cells = <0>;
-			reg = <0x20 0x4>;
-			compatible = "fsl,qoriq-core-mux-1.0";
-			clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>;
-			clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2";
-			clock-output-names = "cmux1";
-		};
 
 		mux2: mux2@40 {
 			#clock-cells = <0>;

arch/powerpc/boot/dts/fsl/p3041si-post.dtsi

···
 		#sleep-cells = <2>;
 	};
 
-	clockgen: global-utilities@e1000 {
+/include/ "qoriq-clockgen1.dtsi"
+	global-utilities@e1000 {
 		compatible = "fsl,p3041-clockgen", "fsl,qoriq-clockgen-1.0";
-		ranges = <0x0 0xe1000 0x1000>;
-		reg = <0xe1000 0x1000>;
-		clock-frequency = <0>;
-		#address-cells = <1>;
-		#size-cells = <1>;
-
-		sysclk: sysclk {
-			#clock-cells = <0>;
-			compatible = "fsl,qoriq-sysclk-1.0";
-			clock-output-names = "sysclk";
-		};
-
-		pll0: pll0@800 {
-			#clock-cells = <1>;
-			reg = <0x800 0x4>;
-			compatible = "fsl,qoriq-core-pll-1.0";
-			clocks = <&sysclk>;
-			clock-output-names = "pll0", "pll0-div2";
-		};
-
-		pll1: pll1@820 {
-			#clock-cells = <1>;
-			reg = <0x820 0x4>;
-			compatible = "fsl,qoriq-core-pll-1.0";
-			clocks = <&sysclk>;
-			clock-output-names = "pll1", "pll1-div2";
-		};
-
-		mux0: mux0@0 {
-			#clock-cells = <0>;
-			reg = <0x0 0x4>;
-			compatible = "fsl,qoriq-core-mux-1.0";
-			clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>;
-			clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2";
-			clock-output-names = "cmux0";
-		};
-
-		mux1: mux1@20 {
-			#clock-cells = <0>;
-			reg = <0x20 0x4>;
-			compatible = "fsl,qoriq-core-mux-1.0";
-			clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>;
-			clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2";
-			clock-output-names = "cmux1";
-		};
 
 		mux2: mux2@40 {
 			#clock-cells = <0>;

arch/powerpc/boot/dts/fsl/p4080si-post.dtsi

···
 		#sleep-cells = <2>;
 	};
 
-	clockgen: global-utilities@e1000 {
+/include/ "qoriq-clockgen1.dtsi"
+	global-utilities@e1000 {
 		compatible = "fsl,p4080-clockgen", "fsl,qoriq-clockgen-1.0";
-		ranges = <0x0 0xe1000 0x1000>;
-		reg = <0xe1000 0x1000>;
-		clock-frequency = <0>;
-		#address-cells = <1>;
-		#size-cells = <1>;
-
-		sysclk: sysclk {
-			#clock-cells = <0>;
-			compatible = "fsl,qoriq-sysclk-1.0";
-			clock-output-names = "sysclk";
-		};
-
-		pll0: pll0@800 {
-			#clock-cells = <1>;
-			reg = <0x800 0x4>;
-			compatible = "fsl,qoriq-core-pll-1.0";
-			clocks = <&sysclk>;
-			clock-output-names = "pll0", "pll0-div2";
-		};
-
-		pll1: pll1@820 {
-			#clock-cells = <1>;
-			reg = <0x820 0x4>;
-			compatible = "fsl,qoriq-core-pll-1.0";
-			clocks = <&sysclk>;
-			clock-output-names = "pll1", "pll1-div2";
-		};
 
 		pll2: pll2@840 {
 			#clock-cells = <1>;
···
 			compatible = "fsl,qoriq-core-pll-1.0";
 			clocks = <&sysclk>;
 			clock-output-names = "pll3", "pll3-div2";
-		};
-
-		mux0: mux0@0 {
-			#clock-cells = <0>;
-			reg = <0x0 0x4>;
-			compatible = "fsl,qoriq-core-mux-1.0";
-			clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>;
-			clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2";
-			clock-output-names = "cmux0";
-		};
-
-		mux1: mux1@20 {
-			#clock-cells = <0>;
-			reg = <0x20 0x4>;
-			compatible = "fsl,qoriq-core-mux-1.0";
-			clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>;
-			clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2";
-			clock-output-names = "cmux1";
 		};
 
 		mux2: mux2@40 {

arch/powerpc/boot/dts/fsl/p5020si-post.dtsi

···
 		#sleep-cells = <2>;
 	};
 
-	clockgen: global-utilities@e1000 {
+/include/ "qoriq-clockgen1.dtsi"
+	global-utilities@e1000 {
 		compatible = "fsl,p5020-clockgen", "fsl,qoriq-clockgen-1.0";
-		ranges = <0x0 0xe1000 0x1000>;
-		reg = <0xe1000 0x1000>;
-		clock-frequency = <0>;
-		#address-cells = <1>;
-		#size-cells = <1>;
-
-		sysclk: sysclk {
-			#clock-cells = <0>;
-			compatible = "fsl,qoriq-sysclk-1.0";
-			clock-output-names = "sysclk";
-		};
-
-		pll0: pll0@800 {
-			#clock-cells = <1>;
-			reg = <0x800 0x4>;
-			compatible = "fsl,qoriq-core-pll-1.0";
-			clocks = <&sysclk>;
-			clock-output-names = "pll0", "pll0-div2";
-		};
-
-		pll1: pll1@820 {
-			#clock-cells = <1>;
-			reg = <0x820 0x4>;
-			compatible = "fsl,qoriq-core-pll-1.0";
-			clocks = <&sysclk>;
-			clock-output-names = "pll1", "pll1-div2";
-		};
-
-		mux0: mux0@0 {
-			#clock-cells = <0>;
-			reg = <0x0 0x4>;
-			compatible = "fsl,qoriq-core-mux-1.0";
-			clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>;
-			clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2";
-			clock-output-names = "cmux0";
-		};
-
-		mux1: mux1@20 {
-			#clock-cells = <0>;
-			reg = <0x20 0x4>;
-			compatible = "fsl,qoriq-core-mux-1.0";
-			clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>;
-			clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2";
-			clock-output-names = "cmux1";
-		};
 	};
 
 	rcpm: global-utilities@e2000 {

arch/powerpc/boot/dts/fsl/p5040si-post.dtsi

···
 		#sleep-cells = <2>;
 	};
 
-	clockgen: global-utilities@e1000 {
+/include/ "qoriq-clockgen1.dtsi"
+	global-utilities@e1000 {
 		compatible = "fsl,p5040-clockgen", "fsl,qoriq-clockgen-1.0";
-		ranges = <0x0 0xe1000 0x1000>;
-		reg = <0xe1000 0x1000>;
-		clock-frequency = <0>;
-		#address-cells = <1>;
-		#size-cells = <1>;
-
-		sysclk: sysclk {
-			#clock-cells = <0>;
-			compatible = "fsl,qoriq-sysclk-1.0";
-			clock-output-names = "sysclk";
-		};
-
-		pll0: pll0@800 {
-			#clock-cells = <1>;
-			reg = <0x800 0x4>;
-			compatible = "fsl,qoriq-core-pll-1.0";
-			clocks = <&sysclk>;
-			clock-output-names = "pll0", "pll0-div2";
-		};
-
-		pll1: pll1@820 {
-			#clock-cells = <1>;
-			reg = <0x820 0x4>;
-			compatible = "fsl,qoriq-core-pll-1.0";
-			clocks = <&sysclk>;
-			clock-output-names = "pll1", "pll1-div2";
-		};
-
-		mux0: mux0@0 {
-			#clock-cells = <0>;
-			reg = <0x0 0x4>;
-			compatible = "fsl,qoriq-core-mux-1.0";
-			clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>;
-			clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2";
-			clock-output-names = "cmux0";
-		};
-
-		mux1: mux1@20 {
-			#clock-cells = <0>;
-			reg = <0x20 0x4>;
-			compatible = "fsl,qoriq-core-mux-1.0";
-			clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>;
-			clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2";
-			clock-output-names = "cmux1";
-		};
 
 		mux2: mux2@40 {
 			#clock-cells = <0>;

arch/powerpc/boot/dts/fsl/qoriq-clockgen1.dtsi

···
+/*
+ * QorIQ clock control device tree stub [ controller @ offset 0xe1000 ]
+ *
+ * Copyright 2014 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.
+ */
+
+global-utilities@e1000 {
+	compatible = "fsl,qoriq-clockgen-1.0";
+	ranges = <0x0 0xe1000 0x1000>;
+	reg = <0xe1000 0x1000>;
+	clock-frequency = <0>;
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	sysclk: sysclk {
+		#clock-cells = <0>;
+		compatible = "fsl,qoriq-sysclk-1.0", "fixed-clock";
+		clock-output-names = "sysclk";
+	};
+	pll0: pll0@800 {
+		#clock-cells = <1>;
+		reg = <0x800 0x4>;
+		compatible = "fsl,qoriq-core-pll-1.0";
+		clocks = <&sysclk>;
+		clock-output-names = "pll0", "pll0-div2";
+	};
+	pll1: pll1@820 {
+		#clock-cells = <1>;
+		reg = <0x820 0x4>;
+		compatible = "fsl,qoriq-core-pll-1.0";
+		clocks = <&sysclk>;
+		clock-output-names = "pll1", "pll1-div2";
+	};
+	mux0: mux0@0 {
+		#clock-cells = <0>;
+		reg = <0x0 0x4>;
+		compatible = "fsl,qoriq-core-mux-1.0";
+		clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>;
+		clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2";
+		clock-output-names = "cmux0";
+	};
+	mux1: mux1@20 {
+		#clock-cells = <0>;
+		reg = <0x20 0x4>;
+		compatible = "fsl,qoriq-core-mux-1.0";
+		clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>;
+		clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2";
+		clock-output-names = "cmux1";
+	};
+	platform_pll: platform-pll@c00 {
+		#clock-cells = <1>;
+		reg = <0xc00 0x4>;
+		compatible = "fsl,qoriq-platform-pll-1.0";
+		clocks = <&sysclk>;
+		clock-output-names = "platform-pll", "platform-pll-div2";
+	};
+};

arch/powerpc/boot/dts/fsl/qoriq-clockgen2.dtsi

···
+/*
+ * QorIQ clock control device tree stub [ controller @ offset 0xe1000 ]
+ *
+ * Copyright 2014 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.
+ */
+
+global-utilities@e1000 {
+	compatible = "fsl,qoriq-clockgen-2.0";
+	ranges = <0x0 0xe1000 0x1000>;
+	reg = <0xe1000 0x1000>;
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	sysclk: sysclk {
+		#clock-cells = <0>;
+		compatible = "fsl,qoriq-sysclk-2.0", "fixed-clock";
+		clock-output-names = "sysclk";
+	};
+	pll0: pll0@800 {
+		#clock-cells = <1>;
+		reg = <0x800 0x4>;
+		compatible = "fsl,qoriq-core-pll-2.0";
+		clocks = <&sysclk>;
+		clock-output-names = "pll0", "pll0-div2", "pll0-div4";
+	};
+	pll1: pll1@820 {
+		#clock-cells = <1>;
+		reg = <0x820 0x4>;
+		compatible = "fsl,qoriq-core-pll-2.0";
+		clocks = <&sysclk>;
+		clock-output-names = "pll1", "pll1-div2", "pll1-div4";
+	};
+	platform_pll: platform-pll@c00 {
+		#clock-cells = <1>;
+		reg = <0xc00 0x4>;
+		compatible = "fsl,qoriq-platform-pll-2.0";
+		clocks = <&sysclk>;
+		clock-output-names = "platform-pll", "platform-pll-div2";
+	};
+};

arch/powerpc/boot/dts/fsl/t1040si-post.dtsi

···
 		fsl,liodn-bits = <12>;
 	};
 
-	clockgen: global-utilities@e1000 {
+/include/ "qoriq-clockgen2.dtsi"
+	global-utilities@e1000 {
 		compatible = "fsl,t1040-clockgen", "fsl,qoriq-clockgen-2.0";
-		ranges = <0x0 0xe1000 0x1000>;
-		reg = <0xe1000 0x1000>;
-		#address-cells = <1>;
-		#size-cells = <1>;
-
-		sysclk: sysclk {
-			#clock-cells = <0>;
-			compatible = "fsl,qoriq-sysclk-2.0";
-			clock-output-names = "sysclk", "fixed-clock";
-		};
-
-
-		pll0: pll0@800 {
-			#clock-cells = <1>;
-			reg = <0x800 4>;
-			compatible = "fsl,qoriq-core-pll-2.0";
-			clocks = <&sysclk>;
-			clock-output-names = "pll0", "pll0-div2", "pll0-div4";
-		};
-
-		pll1: pll1@820 {
-			#clock-cells = <1>;
-			reg = <0x820 4>;
-			compatible = "fsl,qoriq-core-pll-2.0";
-			clocks = <&sysclk>;
-			clock-output-names = "pll1", "pll1-div2", "pll1-div4";
-		};
 
 		mux0: mux0@0 {
 			#clock-cells = <0>;

arch/powerpc/boot/dts/fsl/t2081si-post.dtsi

···
 		fsl,liodn-bits = <12>;
 	};
 
-	clockgen: global-utilities@e1000 {
+/include/ "qoriq-clockgen2.dtsi"
+	global-utilities@e1000 {
 		compatible = "fsl,t2080-clockgen", "fsl,qoriq-clockgen-2.0";
-		ranges = <0x0 0xe1000 0x1000>;
-		reg = <0xe1000 0x1000>;
-		#address-cells = <1>;
-		#size-cells = <1>;
-
-		sysclk: sysclk {
-			#clock-cells = <0>;
-			compatible = "fsl,qoriq-sysclk-2.0";
-			clock-output-names = "sysclk", "fixed-clock";
-		};
-
-		pll0: pll0@800 {
-			#clock-cells = <1>;
-			reg = <0x800 4>;
-			compatible = "fsl,qoriq-core-pll-2.0";
-			clocks = <&sysclk>;
-			clock-output-names = "pll0", "pll0-div2", "pll0-div4";
-		};
-
-		pll1: pll1@820 {
-			#clock-cells = <1>;
-			reg = <0x820 4>;
-			compatible = "fsl,qoriq-core-pll-2.0";
-			clocks = <&sysclk>;
-			clock-output-names = "pll1", "pll1-div2", "pll1-div4";
-		};
 
 		mux0: mux0@0 {
 			#clock-cells = <0>;

arch/powerpc/boot/dts/fsl/t4240si-post.dtsi

···
 		fsl,liodn-bits = <12>;
 	};
 
-	clockgen: global-utilities@e1000 {
+/include/ "qoriq-clockgen2.dtsi"
+	global-utilities@e1000 {
 		compatible = "fsl,t4240-clockgen", "fsl,qoriq-clockgen-2.0";
-		ranges = <0x0 0xe1000 0x1000>;
-		reg = <0xe1000 0x1000>;
-		#address-cells = <1>;
-		#size-cells = <1>;
-
-		sysclk: sysclk {
-			#clock-cells = <0>;
-			compatible = "fsl,qoriq-sysclk-2.0";
-			clock-output-names = "sysclk";
-		};
-
-		pll0: pll0@800 {
-			#clock-cells = <1>;
-			reg = <0x800 0x4>;
-			compatible = "fsl,qoriq-core-pll-2.0";
-			clocks = <&sysclk>;
-			clock-output-names = "pll0", "pll0-div2", "pll0-div4";
-		};
-
-		pll1: pll1@820 {
-			#clock-cells = <1>;
-			reg = <0x820 0x4>;
-			compatible = "fsl,qoriq-core-pll-2.0";
-			clocks = <&sysclk>;
-			clock-output-names = "pll1", "pll1-div2", "pll1-div4";
-		};
 
 		pll2: pll2@840 {
 			#clock-cells = <1>;

arch/powerpc/boot/dts/p3041ds.dts

···
 				reg = <0x68>;
 				interrupts = <0x1 0x1 0 0>;
 			};
+			ina220@40 {
+				compatible = "ti,ina220";
+				reg = <0x40>;
+				shunt-resistor = <1000>;
+			};
+			ina220@41 {
+				compatible = "ti,ina220";
+				reg = <0x41>;
+				shunt-resistor = <1000>;
+			};
+			ina220@44 {
+				compatible = "ti,ina220";
+				reg = <0x44>;
+				shunt-resistor = <1000>;
+			};
+			ina220@45 {
+				compatible = "ti,ina220";
+				reg = <0x45>;
+				shunt-resistor = <1000>;
+			};
 			adt7461@4c {
 				compatible = "adi,adt7461";
 				reg = <0x4c>;

arch/powerpc/boot/dts/p5020ds.dts

···
 				reg = <0x68>;
 				interrupts = <0x1 0x1 0 0>;
 			};
+			ina220@40 {
+				compatible = "ti,ina220";
+				reg = <0x40>;
+				shunt-resistor = <1000>;
+			};
+			ina220@41 {
+				compatible = "ti,ina220";
+				reg = <0x41>;
+				shunt-resistor = <1000>;
+			};
+			ina220@44 {
+				compatible = "ti,ina220";
+				reg = <0x44>;
+				shunt-resistor = <1000>;
+			};
+			ina220@45 {
+				compatible = "ti,ina220";
+				reg = <0x45>;
+				shunt-resistor = <1000>;
+			};
 			adt7461@4c {
 				compatible = "adi,adt7461";
 				reg = <0x4c>;

arch/powerpc/boot/dts/p5040ds.dts

···
 				reg = <0x68>;
 				interrupts = <0x1 0x1 0 0>;
 			};
+			ina220@40 {
+				compatible = "ti,ina220";
+				reg = <0x40>;
+				shunt-resistor = <1000>;
+			};
+			ina220@41 {
+				compatible = "ti,ina220";
+				reg = <0x41>;
+				shunt-resistor = <1000>;
+			};
+			ina220@44 {
+				compatible = "ti,ina220";
+				reg = <0x44>;
+				shunt-resistor = <1000>;
+			};
+			ina220@45 {
+				compatible = "ti,ina220";
+				reg = <0x45>;
+				shunt-resistor = <1000>;
+			};
 			adt7461@4c {
 				compatible = "adi,adt7461";
 				reg = <0x4c>;

arch/powerpc/boot/dts/t104xrdb.dtsi

···
 			};
 		};
 
+		i2c@118000 {
+			adt7461@4c {
+				compatible = "adi,adt7461";
+				reg = <0x4c>;
+			};
+		};
+
 		i2c@118100 {
 			pca9546@77 {
 				compatible = "nxp,pca9546";

arch/powerpc/boot/dts/t208xqds.dtsi

···
 						shunt-resistor = <1000>;
 					};
 				};
+
+				i2c@3 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <0x3>;
+
+					adt7461@4c {
+						compatible = "adi,adt7461";
+						reg = <0x4c>;
+					};
+				};
 			};
 		};
 

arch/powerpc/boot/dts/t4240emu.dts

···
 		fsl,liodn-bits = <12>;
 	};
 
-	clockgen: global-utilities@e1000 {
+/include/ "fsl/qoriq-clockgen2.dtsi"
+	global-utilities@e1000 {
 		compatible = "fsl,t4240-clockgen", "fsl,qoriq-clockgen-2.0";
-		reg = <0xe1000 0x1000>;
 	};
 
 /include/ "fsl/qoriq-dma-0.dtsi"

arch/powerpc/boot/main.c

···
 
 static void prep_cmdline(void *chosen)
 {
+	unsigned int getline_timeout = 5000;
+	int v;
+	int n;
+
+	/* Wait-for-input time */
+	n = getprop(chosen, "linux,cmdline-timeout", &v, sizeof(v));
+	if (n == sizeof(v))
+		getline_timeout = v;
+
 	if (cmdline[0] == '\0')
 		getprop(chosen, "bootargs", cmdline, BOOT_COMMAND_LINE_SIZE-1);
 
 	printf("\n\rLinux/PowerPC load: %s", cmdline);
+
 	/* If possible, edit the command line */
-	if (console_ops.edit_cmdline)
-		console_ops.edit_cmdline(cmdline, BOOT_COMMAND_LINE_SIZE);
+	if (console_ops.edit_cmdline && getline_timeout)
+		console_ops.edit_cmdline(cmdline, BOOT_COMMAND_LINE_SIZE, getline_timeout);
+
 	printf("\n\r");
 
 	/* Put the command line back into the devtree for the kernel */

arch/powerpc/boot/ops.h

···
 struct console_ops {
 	int	(*open)(void);
 	void	(*write)(const char *buf, int len);
-	void	(*edit_cmdline)(char *buf, int len);
+	void	(*edit_cmdline)(char *buf, int len, unsigned int getline_timeout);
 	void	(*close)(void);
 	void	*data;
 };

arch/powerpc/boot/serial.c

···
 		scdp->putc(*buf++);
 }
 
-static void serial_edit_cmdline(char *buf, int len)
+static void serial_edit_cmdline(char *buf, int len, unsigned int timeout)
 {
 	int timer = 0, count;
 	char ch, *cp;
···
 	cp = &buf[count];
 	count++;
 
-	while (timer++ < 5*1000) {
+	do {
 		if (scdp->tstc()) {
 			while (((ch = scdp->getc()) != '\n') && (ch != '\r')) {
 				/* Test for backspace/delete */
···
 			break;  /* Exit 'timer' loop */
 		}
 		udelay(1000);  /* 1 msec */
-	}
+	} while (timer++ < timeout);
 	*cp = 0;
 }
 

arch/powerpc/configs/corenet32_smp_defconfig

···
 CONFIG_RTC_DRV_DS3232=y
 CONFIG_UIO=y
 CONFIG_STAGING=y
+CONFIG_MEMORY=y
 CONFIG_VIRT_DRIVERS=y
 CONFIG_FSL_HV_MANAGER=y
 CONFIG_EXT2_FS=y

arch/powerpc/configs/corenet64_smp_defconfig

···
 CONFIG_VIRT_DRIVERS=y
 CONFIG_FSL_HV_MANAGER=y
 CONFIG_FSL_CORENET_CF=y
+CONFIG_MEMORY=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
 CONFIG_ISO9660_FS=m

arch/powerpc/configs/mpc85xx_defconfig

···
 CONFIG_RTC_DRV_CMOS=y
 CONFIG_DMADEVICES=y
 CONFIG_FSL_DMA=y
+CONFIG_MEMORY=y
 # CONFIG_NET_DMA is not set
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y

arch/powerpc/configs/mpc85xx_smp_defconfig

···
 CONFIG_RTC_DRV_CMOS=y
 CONFIG_DMADEVICES=y
 CONFIG_FSL_DMA=y
+CONFIG_MEMORY=y
 # CONFIG_NET_DMA is not set
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y

arch/powerpc/include/asm/bitops.h

···
  *
  * The bitop functions are defined to work on unsigned longs, so for a
  * ppc64 system the bits end up numbered:
- *   |63..............0|127............64|191...........128|255...........196|
+ *   |63..............0|127............64|191...........128|255...........192|
  * and on ppc32:
- *   |31.....0|63....31|95....64|127...96|159..128|191..160|223..192|255..224|
+ *   |31.....0|63....32|95....64|127...96|159..128|191..160|223..192|255..224|
  *
  * There are a few little-endian macros used mostly for filesystem
  * bitmaps, these work on similar bit arrays layouts, but
···
 	return __ilog2(x & -x);
 }
 
-static __inline__ int __ffs(unsigned long x)
+static __inline__ unsigned long __ffs(unsigned long x)
 {
 	return __ilog2(x & -x);
 }

arch/powerpc/include/asm/cputable.h

···
 	    CPU_FTR_PURR | CPU_FTR_REAL_LE | CPU_FTR_DABRX)
 #define CPU_FTRS_COMPATIBLE	(CPU_FTR_USE_TB | CPU_FTR_PPCAS_ARCH_V2)
 
-#define CPU_FTRS_A2 (CPU_FTR_USE_TB | CPU_FTR_SMT | CPU_FTR_DBELL | \
-		     CPU_FTR_NOEXECUTE | CPU_FTR_NODSISRALIGN | \
-		     CPU_FTR_ICSWX | CPU_FTR_DABRX )
-
 #ifdef __powerpc64__
 #ifdef CONFIG_PPC_BOOK3E
-#define CPU_FTRS_POSSIBLE	(CPU_FTRS_E6500 | CPU_FTRS_E5500 | CPU_FTRS_A2)
+#define CPU_FTRS_POSSIBLE	(CPU_FTRS_E6500 | CPU_FTRS_E5500)
 #else
 #define CPU_FTRS_POSSIBLE	\
 	    (CPU_FTRS_POWER4 | CPU_FTRS_PPC970 | CPU_FTRS_POWER5 | \
···
 
 #ifdef __powerpc64__
 #ifdef CONFIG_PPC_BOOK3E
-#define CPU_FTRS_ALWAYS		(CPU_FTRS_E6500 & CPU_FTRS_E5500 & CPU_FTRS_A2)
+#define CPU_FTRS_ALWAYS		(CPU_FTRS_E6500 & CPU_FTRS_E5500)
 #else
 #define CPU_FTRS_ALWAYS		\
 	    (CPU_FTRS_POWER4 & CPU_FTRS_PPC970 & CPU_FTRS_POWER5 & \
 	     CPU_FTRS_POWER6 & CPU_FTRS_POWER7 & CPU_FTRS_CELL & \
 	     CPU_FTRS_PA6T & CPU_FTRS_POWER8 & CPU_FTRS_POWER8E & \
-	     CPU_FTRS_POWER8_DD1 & CPU_FTRS_POSSIBLE)
+	     CPU_FTRS_POWER8_DD1 & ~CPU_FTR_HVMODE & CPU_FTRS_POSSIBLE)
 #endif
 #else
 enum {

arch/powerpc/include/asm/eeh.h

···
 #define EEH_PROBE_MODE_DEV	0x04	/* From PCI device	*/
 #define EEH_PROBE_MODE_DEVTREE	0x08	/* From device tree	*/
 #define EEH_ENABLE_IO_FOR_LOG	0x10	/* Enable IO for log	*/
+#define EEH_EARLY_DUMP_LOG	0x20	/* Dump log immediately	*/
 
 /*
  * Delay for PE reset, all in ms
···
 #define EEH_PE_ISOLATED		(1 << 0)	/* Isolated PE		*/
 #define EEH_PE_RECOVERING	(1 << 1)	/* Recovering PE	*/
 #define EEH_PE_CFG_BLOCKED	(1 << 2)	/* Block config access	*/
+#define EEH_PE_RESET		(1 << 3)	/* PE reset in progress */
 
 #define EEH_PE_KEEP		(1 << 8)	/* Keep PE on hotplug	*/
 #define EEH_PE_CFG_RESTRICTED	(1 << 9)	/* Block config on error */

arch/powerpc/include/asm/elf.h

···
    the loader.  We need to make sure that it is out of the way of the program
    that it will "exec", and that there is sufficient room for the brk.  */
 
-extern unsigned long randomize_et_dyn(unsigned long base);
-#define ELF_ET_DYN_BASE		(randomize_et_dyn(0x20000000))
+#define ELF_ET_DYN_BASE	0x20000000
 
 #define ELF_CORE_EFLAGS (is_elf2_task() ? 2 : 0)
 

arch/powerpc/include/asm/fsl_guts.h

···
 	u8	res0b4[0xc0 - 0xb4];
 	__be32  iovselsr;	/* 0x.00c0 - I/O voltage select status register
 					     Called 'elbcvselcr' on 86xx SOCs */
-	u8	res0c4[0x224 - 0xc4];
+	u8	res0c4[0x100 - 0xc4];
+	__be32	rcwsr[16];	/* 0x.0100 - Reset Control Word Status registers
+					     There are 16 registers */
+	u8	res140[0x224 - 0x140];
 	__be32  iodelay1;	/* 0x.0224 - IO delay control register 1 */
 	__be32  iodelay2;	/* 0x.0228 - IO delay control register 2 */
 	u8	res22c[0x604 - 0x22c];

arch/powerpc/include/asm/hardirq.h

···
 
 #define __ARCH_IRQ_STAT
 
-#define local_softirq_pending()	__get_cpu_var(irq_stat).__softirq_pending
+#define local_softirq_pending()	__this_cpu_read(irq_stat.__softirq_pending)
+
+#define __ARCH_SET_SOFTIRQ_PENDING
+
+#define set_softirq_pending(x) __this_cpu_write(irq_stat.__softirq_pending, (x))
+#define or_softirq_pending(x) __this_cpu_or(irq_stat.__softirq_pending, (x))
 
 static inline void ack_bad_irq(unsigned int irq)
 {

arch/powerpc/include/asm/hugetlb.h

···
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
 
-static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr,
+static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr,
 				    unsigned pdshift)
 {
 	/*
···
 	 */
 	unsigned long idx = 0;
 
-	pte_t *dir = hugepd_page(*hpdp);
+	pte_t *dir = hugepd_page(hpd);
 #ifndef CONFIG_PPC_FSL_BOOK3E
-	idx = (addr & ((1UL << pdshift) - 1)) >> hugepd_shift(*hpdp);
+	idx = (addr & ((1UL << pdshift) - 1)) >> hugepd_shift(hpd);
 #endif
 
 	return dir + idx;
···
 }
 
 #define hugepd_shift(x) 0
-static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr,
+static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr,
 				    unsigned pdshift)
 {
 	return 0;

arch/powerpc/include/asm/io.h

···
 
 #define clrsetbits_8(addr, clear, set) clrsetbits(8, addr, clear, set)
 
-void __iomem *devm_ioremap_prot(struct device *dev, resource_size_t offset,
-				size_t size, unsigned long flags);
-
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_POWERPC_IO_H */

arch/powerpc/include/asm/machdep.h

···
 					 unsigned long newpp, 
 					 unsigned long vpn,
 					 int bpsize, int apsize,
-					 int ssize, int local);
+					 int ssize, unsigned long flags);
 	void            (*hpte_updateboltedpp)(unsigned long newpp, 
 					       unsigned long ea,
 					       int psize, int ssize);
···
 	void		(*hugepage_invalidate)(unsigned long vsid,
 					       unsigned long addr,
 					       unsigned char *hpte_slot_array,
-					       int psize, int ssize);
+					       int psize, int ssize, int local);
 	/* special for kexec, to be called in real mode, linear mapping is
 	 * destroyed as well */
 	void		(*hpte_clear_all)(void);
···
 #endif
 
 	void		(*restart)(char *cmd);
-	void		(*power_off)(void);
 	void		(*halt)(void);
 	void		(*panic)(char *str);
 	void		(*cpu_die)(void);
···
 #ifdef CONFIG_ARCH_RANDOM
 	int (*get_random_long)(unsigned long *v);
 #endif
-
-#ifdef CONFIG_MEMORY_HOTREMOVE
-	int (*remove_memory)(u64, u64);
-#endif
 };
 
 extern void e500_idle(void);
···
 extern sys_ctrler_t sys_ctrler;
 
 #endif /* CONFIG_PPC_PMAC */
-
-
-/* Functions to produce codes on the leds.
- * The SRC code should be unique for the message category and should
- * be limited to the lower 24 bits (the upper 8 are set by these funcs),
- * and (for boot & dump) should be sorted numerically in the order
- * the events occur.
- */
-/* Print a boot progress message. */
-void ppc64_boot_msg(unsigned int src, const char *msg);
 
 static inline void log_error(char *buf, unsigned int err_type, int fatal)
 {

arch/powerpc/include/asm/mmu-8xx.h

···
  * additional information from the MI_EPN, and MI_TWC registers.
  */
 #define SPRN_MI_RPN	790
+#define MI_SPS16K	0x00000008	/* Small page size (0 = 4k, 1 = 16k) */
 
 /* Define an RPN value for mapping kernel memory to large virtual
  * pages for boot initialization.  This has real page number of 0,
···
  * additional information from the MD_EPN, and MD_TWC registers.
  */
 #define SPRN_MD_RPN	798
+#define MD_SPS16K	0x00000008	/* Small page size (0 = 4k, 1 = 16k) */
 
 /* This is a temporary storage register that could be used to save
  * a processor working register during a tablewalk.

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

···
 	return hash & 0x7fffffffffUL;
 }
 
+#define HPTE_LOCAL_UPDATE	0x1
+#define HPTE_NOHPTE_UPDATE	0x2
+
 extern int __hash_page_4K(unsigned long ea, unsigned long access,
 			  unsigned long vsid, pte_t *ptep, unsigned long trap,
-			  unsigned int local, int ssize, int subpage_prot);
+			  unsigned long flags, int ssize, int subpage_prot);
 extern int __hash_page_64K(unsigned long ea, unsigned long access,
 			   unsigned long vsid, pte_t *ptep, unsigned long trap,
-			   unsigned int local, int ssize);
+			   unsigned long flags, int ssize);
 struct mm_struct;
 unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap);
-extern int hash_page_mm(struct mm_struct *mm, unsigned long ea, unsigned long access, unsigned long trap);
-extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap);
+extern int hash_page_mm(struct mm_struct *mm, unsigned long ea,
+			unsigned long access, unsigned long trap,
+			unsigned long flags);
+extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap,
+		     unsigned long dsisr);
 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);
+		     pte_t *ptep, unsigned long trap, unsigned long flags,
+		     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);
+			   unsigned long flags, 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,
+				  unsigned long trap, unsigned long flags,
 				  int ssize, unsigned int psize)
 {
 	BUG();

arch/powerpc/include/asm/opal.h

···
 #define OPAL_HANDLE_HMI				98
 #define OPAL_REGISTER_DUMP_REGION		101
 #define OPAL_UNREGISTER_DUMP_REGION		102
+#define OPAL_WRITE_TPO				103
+#define OPAL_READ_TPO				104
+#define OPAL_IPMI_SEND				107
+#define OPAL_IPMI_RECV				108
 
 #ifndef __ASSEMBLY__
 
···
 	OPAL_MSG_TYPE_MAX,
 };
 
-/* Machine check related definitions */
-enum OpalMCE_Version {
-	OpalMCE_V1 = 1,
-};
-
-enum OpalMCE_Severity {
-	OpalMCE_SEV_NO_ERROR = 0,
-	OpalMCE_SEV_WARNING = 1,
-	OpalMCE_SEV_ERROR_SYNC = 2,
-	OpalMCE_SEV_FATAL = 3,
-};
-
-enum OpalMCE_Disposition {
-	OpalMCE_DISPOSITION_RECOVERED = 0,
-	OpalMCE_DISPOSITION_NOT_RECOVERED = 1,
-};
-
-enum OpalMCE_Initiator {
-	OpalMCE_INITIATOR_UNKNOWN = 0,
-	OpalMCE_INITIATOR_CPU = 1,
-};
-
-enum OpalMCE_ErrorType {
-	OpalMCE_ERROR_TYPE_UNKNOWN = 0,
-	OpalMCE_ERROR_TYPE_UE = 1,
-	OpalMCE_ERROR_TYPE_SLB = 2,
-	OpalMCE_ERROR_TYPE_ERAT = 3,
-	OpalMCE_ERROR_TYPE_TLB = 4,
-};
-
-enum OpalMCE_UeErrorType {
-	OpalMCE_UE_ERROR_INDETERMINATE = 0,
-	OpalMCE_UE_ERROR_IFETCH = 1,
-	OpalMCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH = 2,
-	OpalMCE_UE_ERROR_LOAD_STORE = 3,
-	OpalMCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE = 4,
-};
-
-enum OpalMCE_SlbErrorType {
-	OpalMCE_SLB_ERROR_INDETERMINATE = 0,
-	OpalMCE_SLB_ERROR_PARITY = 1,
-	OpalMCE_SLB_ERROR_MULTIHIT = 2,
-};
-
-enum OpalMCE_EratErrorType {
-	OpalMCE_ERAT_ERROR_INDETERMINATE = 0,
-	OpalMCE_ERAT_ERROR_PARITY = 1,
-	OpalMCE_ERAT_ERROR_MULTIHIT = 2,
-};
-
-enum OpalMCE_TlbErrorType {
-	OpalMCE_TLB_ERROR_INDETERMINATE = 0,
-	OpalMCE_TLB_ERROR_PARITY = 1,
-	OpalMCE_TLB_ERROR_MULTIHIT = 2,
-};
-
 enum OpalThreadStatus {
 	OPAL_THREAD_INACTIVE = 0x0,
 	OPAL_THREAD_STARTED = 0x1,
···
 	__be64 params[8];
 };
 
-struct opal_machine_check_event {
-	enum OpalMCE_Version	version:8;	/* 0x00 */
-	uint8_t			in_use;		/* 0x01 */
-	enum OpalMCE_Severity	severity:8;	/* 0x02 */
-	enum OpalMCE_Initiator	initiator:8;	/* 0x03 */
-	enum OpalMCE_ErrorType	error_type:8;	/* 0x04 */
-	enum OpalMCE_Disposition disposition:8; /* 0x05 */
-	uint8_t			reserved_1[2];	/* 0x06 */
-	uint64_t		gpr3;		/* 0x08 */
-	uint64_t		srr0;		/* 0x10 */
-	uint64_t		srr1;		/* 0x18 */
-	union {					/* 0x20 */
-		struct {
-			enum OpalMCE_UeErrorType ue_error_type:8;
-			uint8_t		effective_address_provided;
-			uint8_t		physical_address_provided;
-			uint8_t		reserved_1[5];
-			uint64_t	effective_address;
-			uint64_t	physical_address;
-			uint8_t		reserved_2[8];
-		} ue_error;
+enum {
+	OPAL_IPMI_MSG_FORMAT_VERSION_1 = 1,
+};
 
-		struct {
-			enum OpalMCE_SlbErrorType slb_error_type:8;
-			uint8_t		effective_address_provided;
-			uint8_t		reserved_1[6];
-			uint64_t	effective_address;
-			uint8_t		reserved_2[16];
-		} slb_error;
-
-		struct {
-			enum OpalMCE_EratErrorType erat_error_type:8;
-			uint8_t		effective_address_provided;
-			uint8_t		reserved_1[6];
-			uint64_t	effective_address;
-			uint8_t		reserved_2[16];
-		} erat_error;
-
-		struct {
-			enum OpalMCE_TlbErrorType tlb_error_type:8;
-			uint8_t		effective_address_provided;
-			uint8_t		reserved_1[6];
-			uint64_t	effective_address;
-			uint8_t		reserved_2[16];
-		} tlb_error;
-	} u;
+struct opal_ipmi_msg {
+	uint8_t		version;
+	uint8_t		netfn;
+	uint8_t		cmd;
+	uint8_t		data[];
 };
 
 /* FSP memory errors handling */
···
 		      __be64 *hour_minute_second_millisecond);
 int64_t opal_rtc_write(uint32_t year_month_day,
 		       uint64_t hour_minute_second_millisecond);
+int64_t opal_tpo_read(uint64_t token, __be32 *year_mon_day, __be32 *hour_min);
+int64_t opal_tpo_write(uint64_t token, uint32_t year_mon_day,
+		       uint32_t hour_min);
 int64_t opal_cec_power_down(uint64_t request);
 int64_t opal_cec_reboot(void);
 int64_t opal_read_nvram(uint64_t buffer, uint64_t size, uint64_t offset);
···
 int64_t opal_register_dump_region(uint32_t id, uint64_t start, uint64_t end);
 int64_t opal_unregister_dump_region(uint32_t id);
 int64_t opal_pci_set_phb_cxl_mode(uint64_t phb_id, uint64_t mode, uint64_t pe_number);
+int64_t opal_ipmi_send(uint64_t interface, struct opal_ipmi_msg *msg,
+		uint64_t msg_len);
+int64_t opal_ipmi_recv(uint64_t interface, struct opal_ipmi_msg *msg,
+		uint64_t *msg_len);
 
 /* Internal functions */
 extern int early_init_dt_scan_opal(unsigned long node, const char *uname,
···
 extern int opal_get_sensor_data(u32 sensor_hndl, u32 *sensor_data);
 
 struct rtc_time;
-extern int opal_set_rtc_time(struct rtc_time *tm);
-extern void opal_get_rtc_time(struct rtc_time *tm);
 extern unsigned long opal_get_boot_time(void);
 extern void opal_nvram_init(void);
 extern void opal_flash_init(void);

arch/powerpc/include/asm/paca.h

···
 #define get_slb_shadow()	(get_paca()->slb_shadow_ptr)
 
 struct task_struct;
-struct opal_machine_check_event;
 
 /*
  * Defines the layout of the paca.
···
 	u64 tm_scratch;                 /* TM scratch area for reclaim */
 #endif
 
-#ifdef CONFIG_PPC_POWERNV
-	/* Pointer to OPAL machine check event structure set by the
-	 * early exception handler for use by high level C handler
-	 */
-	struct opal_machine_check_event *opal_mc_evt;
-#endif
 #ifdef CONFIG_PPC_BOOK3S_64
 	/* Exclusive emergency stack pointer for machine check exception. */
 	void *mc_emergency_sp;

arch/powerpc/include/asm/page.h

···
 }
 #endif
 
-#define is_hugepd(pdep)               (hugepd_ok(*((hugepd_t *)(pdep))))
+#define is_hugepd(hpd)               (hugepd_ok(hpd))
+#define pgd_huge pgd_huge
 int pgd_huge(pgd_t pgd);
 #else /* CONFIG_HUGETLB_PAGE */
 #define is_hugepd(pdep)			0
 #define pgd_huge(pgd)			0
 #endif /* CONFIG_HUGETLB_PAGE */
+#define __hugepd(x) ((hugepd_t) { (x) })
 
 struct page;
 extern void clear_user_page(void *page, unsigned long vaddr, struct page *pg);

arch/powerpc/include/asm/pgtable-ppc32.h

···
 #ifdef PTE_ATOMIC_UPDATES
 	unsigned long old, tmp;
 
+#ifdef CONFIG_PPC_8xx
+	unsigned long tmp2;
+
+	__asm__ __volatile__("\
+1:	lwarx	%0,0,%4\n\
+	andc	%1,%0,%5\n\
+	or	%1,%1,%6\n\
+	/* 0x200 == Extended encoding, bit 22 */ \
+	/* Bit 22 has to be 1 if neither _PAGE_USER nor _PAGE_RW are set */ \
+	rlwimi	%1,%1,32-2,0x200\n /* get _PAGE_USER */ \
+	rlwinm	%3,%1,32-1,0x200\n /* get _PAGE_RW */ \
+	or	%1,%3,%1\n\
+	xori	%1,%1,0x200\n"
+"	stwcx.	%1,0,%4\n\
+	bne-	1b"
+	: "=&r" (old), "=&r" (tmp), "=m" (*p), "=&r" (tmp2)
+	: "r" (p), "r" (clr), "r" (set), "m" (*p)
+	: "cc" );
+#else /* CONFIG_PPC_8xx */
 	__asm__ __volatile__("\
 1:	lwarx	%0,0,%3\n\
 	andc	%1,%0,%4\n\
···
 	: "=&r" (old), "=&r" (tmp), "=m" (*p)
 	: "r" (p), "r" (clr), "r" (set), "m" (*p)
 	: "cc" );
+#endif /* CONFIG_PPC_8xx */
 #else /* PTE_ATOMIC_UPDATES */
 	unsigned long old = pte_val(*p);
 	*p = __pte((old & ~clr) | set);

arch/powerpc/include/asm/pgtable-ppc64-4k.h

···
 #define pgd_present(pgd)	(pgd_val(pgd) != 0)
 #define pgd_clear(pgdp)		(pgd_val(*(pgdp)) = 0)
 #define pgd_page_vaddr(pgd)	(pgd_val(pgd) & ~PGD_MASKED_BITS)
-#define pgd_page(pgd)		virt_to_page(pgd_page_vaddr(pgd))
+
+#ifndef __ASSEMBLY__
+
+static inline pte_t pgd_pte(pgd_t pgd)
+{
+	return __pte(pgd_val(pgd));
+}
+
+static inline pgd_t pte_pgd(pte_t pte)
+{
+	return __pgd(pte_val(pte));
+}
+extern struct page *pgd_page(pgd_t pgd);
+
+#endif /* !__ASSEMBLY__ */
 
 #define pud_offset(pgdp, addr)	\
   (((pud_t *) pgd_page_vaddr(*(pgdp))) + \

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

···
 /* Bits to mask out from a PGD/PUD to get to the PMD page */
 #define PUD_MASKED_BITS		0x1ff
 
+#define pgd_pte(pgd)	(pud_pte(((pud_t){ pgd })))
+#define pte_pgd(pte)	((pgd_t)pte_pud(pte))
+
 #endif /* _ASM_POWERPC_PGTABLE_PPC64_64K_H */

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

···
 #define pmd_none(pmd)		(!pmd_val(pmd))
 #define	pmd_bad(pmd)		(!is_kernel_addr(pmd_val(pmd)) \
 				 || (pmd_val(pmd) & PMD_BAD_BITS))
-#define	pmd_present(pmd)	(pmd_val(pmd) != 0)
+#define	pmd_present(pmd)	(!pmd_none(pmd))
 #define	pmd_clear(pmdp)		(pmd_val(*(pmdp)) = 0)
 #define pmd_page_vaddr(pmd)	(pmd_val(pmd) & ~PMD_MASKED_BITS)
 extern struct page *pmd_page(pmd_t pmd);
···
 #define pud_present(pud)	(pud_val(pud) != 0)
 #define pud_clear(pudp)		(pud_val(*(pudp)) = 0)
 #define pud_page_vaddr(pud)	(pud_val(pud) & ~PUD_MASKED_BITS)
-#define pud_page(pud)		virt_to_page(pud_page_vaddr(pud))
 
+extern struct page *pud_page(pud_t pud);
+
+static inline pte_t pud_pte(pud_t pud)
+{
+	return __pte(pud_val(pud));
+}
+
+static inline pud_t pte_pud(pte_t pte)
+{
+	return __pud(pte_val(pte));
+}
+#define pud_write(pud)		pte_write(pud_pte(pud))
 #define pgd_set(pgdp, pudp)	({pgd_val(*(pgdp)) = (unsigned long)(pudp);})
+#define pgd_write(pgd)		pte_write(pgd_pte(pgd))
 
 /*
  * Find an entry in a page-table-directory.  We combine the address region
···
 		       pmd_t *pmdp, pmd_t pmd);
 extern void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
 				 pmd_t *pmd);
-
+/*
+ *
+ * For core kernel code by design pmd_trans_huge is never run on any hugetlbfs
+ * page. The hugetlbfs page table walking and mangling paths are totally
+ * separated form the core VM paths and they're differentiated by
+ *  VM_HUGETLB being set on vm_flags well before any pmd_trans_huge could run.
+ *
+ * pmd_trans_huge() is defined as false at build time if
+ * CONFIG_TRANSPARENT_HUGEPAGE=n to optimize away code blocks at build
+ * time in such case.
+ *
+ * For ppc64 we need to differntiate from explicit hugepages from THP, because
+ * for THP we also track the subpage details at the pmd level. We don't do
+ * that for explicit huge pages.
+ *
+ */
 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)
···
 
 extern int has_transparent_hugepage(void);
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+static inline int pmd_large(pmd_t pmd)
+{
+	/*
+	 * leaf pte for huge page, bottom two bits != 00
+	 */
+	return ((pmd_val(pmd) & 0x3) != 0x0);
+}
 
 static inline pte_t pmd_pte(pmd_t pmd)
 {
···
 	 */
 	return true;
 }
-
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_POWERPC_PGTABLE_PPC64_H_ */

arch/powerpc/include/asm/pgtable.h

···
  */
 extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t *);
 
-extern int gup_hugepd(hugepd_t *hugepd, unsigned pdshift, unsigned long addr,
-		      unsigned long end, int write, struct page **pages, int *nr);
-
 extern int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
-		       unsigned long end, int write, struct page **pages, int *nr);
+		       unsigned long end, int write,
+		       struct page **pages, int *nr);
 #ifndef CONFIG_TRANSPARENT_HUGEPAGE
 #define pmd_large(pmd)		0
 #define has_transparent_hugepage() 0

arch/powerpc/include/asm/processor.h

···
 enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF};
 
 extern int powersave_nap;	/* set if nap mode can be used in idle loop */
-extern void power7_nap(int check_irq);
+extern unsigned long power7_nap(int check_irq);
 extern void power7_sleep(void);
 extern void flush_instruction_cache(void);
 extern void hard_reset_now(void);

arch/powerpc/include/asm/pte-8xx.h

···
  */
 #define _PAGE_RW	0x0400	/* lsb PP bits, inverted in HW */
 #define _PAGE_USER	0x0800	/* msb PP bits */
+/* set when neither _PAGE_USER nor _PAGE_RW are set */
+#define _PAGE_KNLRO	0x0200
 
 #define _PMD_PRESENT	0x0001
 #define _PMD_BAD	0x0ff0
 #define _PMD_PAGE_MASK	0x000c
 #define _PMD_PAGE_8M	0x000c
 
-#define _PTE_NONE_MASK _PAGE_ACCESSED
+#define _PTE_NONE_MASK _PAGE_KNLRO
 
 /* Until my rework is finished, 8xx still needs atomic PTE updates */
 #define PTE_ATOMIC_UPDATES	1
 
 /* We need to add _PAGE_SHARED to kernel pages */
-#define _PAGE_KERNEL_RO	(_PAGE_SHARED)
+#define _PAGE_KERNEL_RO	(_PAGE_SHARED | _PAGE_KNLRO)
+#define _PAGE_KERNEL_ROX	(_PAGE_EXEC | _PAGE_KNLRO)
 #define _PAGE_KERNEL_RW	(_PAGE_DIRTY | _PAGE_RW | _PAGE_HWWRITE)
 
 #endif /* __KERNEL__ */

arch/powerpc/include/asm/setup.h

···
 
 extern unsigned int rtas_data;
 extern int mem_init_done;	/* set on boot once kmalloc can be called */
-extern int init_bootmem_done;	/* set once bootmem is available */
 extern unsigned long long memory_limit;
 extern unsigned long klimit;
 extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask);
···
 #define PTRRELOC(x)	((typeof(x)) add_reloc_offset((unsigned long)(x)))
 
 void check_for_initrd(void);
-void do_init_bootmem(void);
+void initmem_init(void);
 void setup_panic(void);
 #define ARCH_PANIC_TIMEOUT 180
 

arch/powerpc/include/asm/thread_info.h

···
 #define THREAD_SIZE_ORDER	(THREAD_SHIFT - PAGE_SHIFT)
 
 /* how to get the thread information struct from C */
+register unsigned long __current_r1 asm("r1");
 static inline struct thread_info *current_thread_info(void)
 {
-	register unsigned long sp asm("r1");
-
 	/* gcc4, at least, is smart enough to turn this into a single
 	 * rlwinm for ppc32 and clrrdi for ppc64 */
-	return (struct thread_info *)(sp & ~(THREAD_SIZE-1));
+	return (struct thread_info *)(__current_r1 & ~(THREAD_SIZE-1));
 }
 
 #endif /* __ASSEMBLY__ */

arch/powerpc/include/asm/tlbflush.h

···
 
 static inline void arch_enter_lazy_mmu_mode(void)
 {
-	struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch);
+	struct ppc64_tlb_batch *batch = this_cpu_ptr(&ppc64_tlb_batch);
 
 	batch->active = 1;
 }
 
 static inline void arch_leave_lazy_mmu_mode(void)
 {
-	struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch);
+	struct ppc64_tlb_batch *batch = this_cpu_ptr(&ppc64_tlb_batch);
 
 	if (batch->index)
 		__flush_tlb_pending(batch);
···
 
 
 extern void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize,
-			    int ssize, int local);
+			    int ssize, unsigned long flags);
 extern void flush_hash_range(unsigned long number, int local);
-
+extern void flush_hash_hugepage(unsigned long vsid, unsigned long addr,
+				pmd_t *pmdp, unsigned int psize, int ssize,
+				unsigned long flags);
 
 static inline void local_flush_tlb_mm(struct mm_struct *mm)
 {

arch/powerpc/include/asm/vga.h

···
 
 #endif /* !CONFIG_VGA_CONSOLE && !CONFIG_MDA_CONSOLE */
 
-extern unsigned long vgacon_remap_base;
-
 #ifdef __powerpc64__
 #define VGA_MAP_MEM(x,s) ((unsigned long) ioremap((x), s))
 #else
-#define VGA_MAP_MEM(x,s) (x + vgacon_remap_base)
+#define VGA_MAP_MEM(x,s) (x)
 #endif
 
 #define vga_readb(x) (*(x))

arch/powerpc/include/asm/xics.h

···
 
 static inline void xics_push_cppr(unsigned int vec)
 {
-	struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr);
+	struct xics_cppr *os_cppr = this_cpu_ptr(&xics_cppr);
 
 	if (WARN_ON(os_cppr->index >= MAX_NUM_PRIORITIES - 1))
 		return;
···
 
 static inline unsigned char xics_pop_cppr(void)
 {
-	struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr);
+	struct xics_cppr *os_cppr = this_cpu_ptr(&xics_cppr);
 
 	if (WARN_ON(os_cppr->index < 1))
 		return LOWEST_PRIORITY;
···
 
 static inline void xics_set_base_cppr(unsigned char cppr)
 {
-	struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr);
+	struct xics_cppr *os_cppr = this_cpu_ptr(&xics_cppr);
 
 	/* we only really want to set the priority when there's
 	 * just one cppr value on the stack
···
 
 static inline unsigned char xics_cppr_top(void)
 {
-	struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr);
+	struct xics_cppr *os_cppr = this_cpu_ptr(&xics_cppr);
 	
 	return os_cppr->stack[os_cppr->index];
 }

arch/powerpc/kernel/align.c

···
 		flush_fp_to_thread(current);
 	}
 
-	if ((nb == 16)) {
+	if (nb == 16) {
 		if (flags & F) {
 			/* Special case for 16-byte FP loads and stores */
 			PPC_WARN_ALIGNMENT(fp_pair, regs);

arch/powerpc/kernel/asm-offsets.c

···
 					arch.timing_last_enter.tv32.tbl));
 #endif
 
-#ifdef CONFIG_PPC_POWERNV
-	DEFINE(OPAL_MC_GPR3, offsetof(struct opal_machine_check_event, gpr3));
-	DEFINE(OPAL_MC_SRR0, offsetof(struct opal_machine_check_event, srr0));
-	DEFINE(OPAL_MC_SRR1, offsetof(struct opal_machine_check_event, srr1));
-	DEFINE(PACA_OPAL_MC_EVT, offsetof(struct paca_struct, opal_mc_evt));
-#endif
-
 	return 0;
 }

arch/powerpc/kernel/crash_dump.c

···
 #undef DEBUG
 
 #include <linux/crash_dump.h>
-#include <linux/bootmem.h>
 #include <linux/io.h>
 #include <linux/memblock.h>
 #include <asm/code-patching.h>

arch/powerpc/kernel/dbell.c

···
 
 	may_hard_irq_enable();
 
-	__get_cpu_var(irq_stat).doorbell_irqs++;
+	__this_cpu_inc(irq_stat.doorbell_irqs);
 
 	smp_ipi_demux();
 

arch/powerpc/kernel/eeh.c

···
 {
 	if (!strcmp(str, "off"))
 		eeh_add_flag(EEH_FORCE_DISABLED);
+	else if (!strcmp(str, "early_log"))
+		eeh_add_flag(EEH_EARLY_DUMP_LOG);
 
 	return 1;
 }
···
 int eeh_reset_pe(struct eeh_pe *pe)
 {
 	int flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
-	int i, rc;
+	int i, state, ret;
+
+	/* Mark as reset and block config space */
+	eeh_pe_state_mark(pe, EEH_PE_RESET | EEH_PE_CFG_BLOCKED);
 
 	/* Take three shots at resetting the bus */
-	for (i=0; i<3; i++) {
+	for (i = 0; i < 3; i++) {
 		eeh_reset_pe_once(pe);
 
 		/*
 		 * EEH_PE_ISOLATED is expected to be removed after
 		 * BAR restore.
 		 */
-		rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
-		if ((rc & flags) == flags)
-			return 0;
-
-		if (rc < 0) {
-			pr_err("%s: Unrecoverable slot failure on PHB#%d-PE#%x",
-				__func__, pe->phb->global_number, pe->addr);
-			return -1;
+		state = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
+		if ((state & flags) == flags) {
+			ret = 0;
+			goto out;
 		}
-		pr_err("EEH: bus reset %d failed on PHB#%d-PE#%x, rc=%d\n",
-			i+1, pe->phb->global_number, pe->addr, rc);
+
+		if (state < 0) {
+			pr_warn("%s: Unrecoverable slot failure on PHB#%d-PE#%x",
+				__func__, pe->phb->global_number, pe->addr);
+			ret = -ENOTRECOVERABLE;
+			goto out;
+		}
+
+		/* We might run out of credits */
+		ret = -EIO;
+		pr_warn("%s: Failure %d resetting PHB#%x-PE#%x\n (%d)\n",
+			__func__, state, pe->phb->global_number, pe->addr, (i + 1));
 	}
 
-	return -1;
+out:
+	eeh_pe_state_clear(pe, EEH_PE_RESET | EEH_PE_CFG_BLOCKED);
+	return ret;
 }
 
 /**
···
 		pr_warn("%s: Platform EEH operation not found\n",
 			__func__);
 		return -EEXIST;
-	} else if ((ret = eeh_ops->init())) {
-		pr_warn("%s: Failed to call platform init function (%d)\n",
-			__func__, ret);
+	} else if ((ret = eeh_ops->init()))
 		return ret;
-	}
 
 	/* Initialize EEH event */
 	ret = eeh_event_init();
···
 static struct pci_device_id eeh_reset_ids[] = {
 	{ PCI_DEVICE(0x19a2, 0x0710) },	/* Emulex, BE     */
 	{ PCI_DEVICE(0x10df, 0xe220) },	/* Emulex, Lancer */
+	{ PCI_DEVICE(0x14e4, 0x1657) }, /* Broadcom BCM5719 */
 	{ 0 }
 };
 

arch/powerpc/kernel/eeh_driver.c

···
 	eeh_pe_dev_traverse(pe, eeh_report_error, &result);
 
 	/* Issue reset */
-	eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
 	ret = eeh_reset_pe(pe);
 	if (ret) {
-		eeh_pe_state_clear(pe, EEH_PE_RECOVERING | EEH_PE_CFG_BLOCKED);
+		eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
 		return ret;
 	}
-	eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED);
 
 	/* Unfreeze the PE */
 	ret = eeh_clear_pe_frozen_state(pe, true);
···
 	 * config accesses. So we prefer to block them. However, controlled
 	 * PCI config accesses initiated from EEH itself are allowed.
 	 */
-	eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
 	rc = eeh_reset_pe(pe);
-	if (rc) {
-		eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED);
+	if (rc)
 		return rc;
-	}
 
 	pci_lock_rescan_remove();
 
 	/* Restore PE */
 	eeh_ops->configure_bridge(pe);
 	eeh_pe_restore_bars(pe);
-	eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED);
 
 	/* Clear frozen state */
 	rc = eeh_clear_pe_frozen_state(pe, false);

arch/powerpc/kernel/entry_32.S

···
 	lwz	r4, 44(r1)
 	subi	r4, r4, MCOUNT_INSN_SIZE
 
-	/* get the parent address */
-	addi	r3, r1, 52
+	/* Grab the LR out of the caller stack frame */
+	lwz	r3,52(r1)
 
 	bl	prepare_ftrace_return
 	nop
+
+        /*
+         * prepare_ftrace_return gives us the address we divert to.
+         * Change the LR in the callers stack frame to this.
+         */
+	stw	r3,52(r1)
 
 	MCOUNT_RESTORE_FRAME
 	/* old link register ends up in ctr reg */
···
 	blr
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
-#endif /* CONFIG_MCOUNT */
+#endif /* CONFIG_FUNCTION_TRACER */

arch/powerpc/kernel/entry_64.S

···
 	ld	r4, 128(r1)
 	subi	r4, r4, MCOUNT_INSN_SIZE
 
-	/* get the parent address */
+	/* Grab the LR out of the caller stack frame */
 	ld	r11, 112(r1)
-	addi	r3, r11, 16
+	ld	r3, 16(r11)
 
 	bl	prepare_ftrace_return
 	nop
+
+	/*
+	 * prepare_ftrace_return gives us the address we divert to.
+	 * Change the LR in the callers stack frame to this.
+	 */
+	ld	r11, 112(r1)
+	std	r3, 16(r11)
 
 	ld	r0, 128(r1)
 	mtlr	r0
···
 	blr
 
 _GLOBAL(return_to_handler)
-	/* need to save return values */
-	std	r4,  -24(r1)
-	std	r3,  -16(r1)
-	std	r31, -8(r1)
-	mr	r31, r1
-	stdu	r1, -112(r1)
-
-	bl	ftrace_return_to_handler
-	nop
-
-	/* return value has real return address */
-	mtlr	r3
-
-	ld	r1, 0(r1)
-	ld	r4,  -24(r1)
-	ld	r3,  -16(r1)
-	ld	r31, -8(r1)
-
-	/* Jump back to real return address */
-	blr
-
-_GLOBAL(mod_return_to_handler)
 	/* need to save return values */
 	std	r4,  -32(r1)
 	std	r3,  -24(r1)
···
 	stdu	r1, -112(r1)
 
 	/*
-	 * We are in a module using the module's TOC.
+	 * We might be called from a module.
 	 * Switch to our TOC to run inside the core kernel.
 	 */
 	ld	r2, PACATOC(r13)

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

···
 1:
 #endif
 
+	/* Return SRR1 from power7_nap() */
+	mfspr	r3,SPRN_SRR1
 	beq	cr1,2f
 	b	power7_wakeup_noloss
 2:	b	power7_wakeup_loss
···
 	. = 0xc00
 	.globl	system_call_pSeries
 system_call_pSeries:
-	HMT_MEDIUM
+	 /*
+	  * If CONFIG_KVM_BOOK3S_64_HANDLER is set, save the PPR (on systems
+	  * that support it) before changing to HMT_MEDIUM. That allows the KVM
+	  * code to save that value into the guest state (it is the guest's PPR
+	  * value). Otherwise just change to HMT_MEDIUM as userspace has
+	  * already saved the PPR.
+	  */
 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
 	SET_SCRATCH0(r13)
 	GET_PACA(r13)
 	std	r9,PACA_EXGEN+EX_R9(r13)
+	OPT_GET_SPR(r9, SPRN_PPR, CPU_FTR_HAS_PPR);
+	HMT_MEDIUM;
 	std	r10,PACA_EXGEN+EX_R10(r13)
+	OPT_SAVE_REG_TO_PACA(PACA_EXGEN+EX_PPR, r9, CPU_FTR_HAS_PPR);
 	mfcr	r9
 	KVMTEST(0xc00)
 	GET_SCRATCH0(r13)
+#else
+	HMT_MEDIUM;
 #endif
 	SYSCALL_PSERIES_1
 	SYSCALL_PSERIES_2_RFID
···
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	hmi_exception_hv
 
-#ifdef CONFIG_PPC_POWERNV
-_GLOBAL(opal_mc_secondary_handler)
-	HMT_MEDIUM_PPR_DISCARD
-	SET_SCRATCH0(r13)
-	GET_PACA(r13)
-	clrldi	r3,r3,2
-	tovirt(r3,r3)
-	std	r3,PACA_OPAL_MC_EVT(r13)
-	ld	r13,OPAL_MC_SRR0(r3)
-	mtspr	SPRN_SRR0,r13
-	ld	r13,OPAL_MC_SRR1(r3)
-	mtspr	SPRN_SRR1,r13
-	ld	r3,OPAL_MC_GPR3(r3)
-	GET_SCRATCH0(r13)
-	b	machine_check_pSeries
-#endif /* CONFIG_PPC_POWERNV */
-
 
 #define MACHINE_CHECK_HANDLER_WINDUP			\
 	/* Clear MSR_RI before setting SRR0 and SRR1. */\
···
 	 * r3 contains the faulting address
 	 * r4 contains the required access permissions
 	 * r5 contains the trap number
+	 * r6 contains dsisr
 	 *
 	 * at return r3 = 0 for success, 1 for page fault, negative for error
 	 */
+	ld      r6,_DSISR(r1)
 	bl	hash_page		/* build HPTE if possible */
 	cmpdi	r3,0			/* see if hash_page succeeded */
 

arch/powerpc/kernel/ftrace.c

···
 }
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
-#ifdef CONFIG_PPC64
-extern void mod_return_to_handler(void);
-#endif
-
 /*
  * Hook the return address and push it in the stack of return addrs
- * in current thread info.
+ * in current thread info. Return the address we want to divert to.
  */
-void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
+unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip)
 {
-	unsigned long old;
-	int faulted;
 	struct ftrace_graph_ent trace;
-	unsigned long return_hooker = (unsigned long)&return_to_handler;
+	unsigned long return_hooker;
 
 	if (unlikely(ftrace_graph_is_dead()))
-		return;
+		goto out;
 
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
-		return;
+		goto out;
 
-#ifdef CONFIG_PPC64
-	/* non core kernel code needs to save and restore the TOC */
-	if (REGION_ID(self_addr) != KERNEL_REGION_ID)
-		return_hooker = (unsigned long)&mod_return_to_handler;
-#endif
+	return_hooker = ppc_function_entry(return_to_handler);
 
-	return_hooker = ppc_function_entry((void *)return_hooker);
-
-	/*
-	 * Protect against fault, even if it shouldn't
-	 * happen. This tool is too much intrusive to
-	 * ignore such a protection.
-	 */
-	asm volatile(
-		"1: " PPC_LL "%[old], 0(%[parent])\n"
-		"2: " PPC_STL "%[return_hooker], 0(%[parent])\n"
-		"   li %[faulted], 0\n"
-		"3:\n"
-
-		".section .fixup, \"ax\"\n"
-		"4: li %[faulted], 1\n"
-		"   b 3b\n"
-		".previous\n"
-
-		".section __ex_table,\"a\"\n"
-			PPC_LONG_ALIGN "\n"
-			PPC_LONG "1b,4b\n"
-			PPC_LONG "2b,4b\n"
-		".previous"
-
-		: [old] "=&r" (old), [faulted] "=r" (faulted)
-		: [parent] "r" (parent), [return_hooker] "r" (return_hooker)
-		: "memory"
-	);
-
-	if (unlikely(faulted)) {
-		ftrace_graph_stop();
-		WARN_ON(1);
-		return;
-	}
-
-	trace.func = self_addr;
+	trace.func = ip;
 	trace.depth = current->curr_ret_stack + 1;
 
 	/* Only trace if the calling function expects to */
-	if (!ftrace_graph_entry(&trace)) {
-		*parent = old;
-		return;
-	}
+	if (!ftrace_graph_entry(&trace))
+		goto out;
 
-	if (ftrace_push_return_trace(old, self_addr, &trace.depth, 0) == -EBUSY)
-		*parent = old;
+	if (ftrace_push_return_trace(parent, ip, &trace.depth, 0) == -EBUSY)
+		goto out;
+
+	parent = return_hooker;
+out:
+	return parent;
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 

arch/powerpc/kernel/head_8xx.S

···
 
 /* Macro to make the code more readable. */
 #ifdef CONFIG_8xx_CPU6
-#define DO_8xx_CPU6(val, reg)	\
-	li	reg, val;	\
-	stw	reg, 12(r0);	\
-	lwz	reg, 12(r0);
+#define SPRN_MI_TWC_ADDR	0x2b80
+#define SPRN_MI_RPN_ADDR	0x2d80
+#define SPRN_MD_TWC_ADDR	0x3b80
+#define SPRN_MD_RPN_ADDR	0x3d80
+
+#define MTSPR_CPU6(spr, reg, treg)	\
+	li	treg, spr##_ADDR;	\
+	stw	treg, 12(r0);		\
+	lwz	treg, 12(r0);		\
+	mtspr	spr, reg
 #else
-#define DO_8xx_CPU6(val, reg)
+#define MTSPR_CPU6(spr, reg, treg)	\
+	mtspr	spr, reg
 #endif
+
+/*
+ * Value for the bits that have fixed value in RPN entries.
+ * Also used for tagging DAR for DTLBerror.
+ */
+#ifdef CONFIG_PPC_16K_PAGES
+#define RPN_PATTERN	(0x00f0 | MD_SPS16K)
+#else
+#define RPN_PATTERN	0x00f0
+#endif
+
 	__HEAD
 _ENTRY(_stext);
 _ENTRY(_start);
···
  * entry into each of the instruction and data TLBs to map the first
  * 8M 1:1.  I also mapped an additional I/O space 1:1 so we can get to
  * the "internal" processor registers before MMU_init is called.
- *
- * The TLB code currently contains a major hack.  Since I use the condition
- * code register, I have to save and restore it.  I am out of registers, so
- * I just store it in memory location 0 (the TLB handlers are not reentrant).
- * To avoid making any decisions, I need to use the "segment" valid bit
- * in the first level table, but that would require many changes to the
- * Linux page directory/table functions that I don't want to do right now.
  *
  *	-- Dan
  */
···
 	EXCEPTION_PROLOG
 	mfspr r4,SPRN_DAR
 	stw r4,_DAR(r11)
-	li r5,0x00f0
+	li r5,RPN_PATTERN
 	mtspr SPRN_DAR,r5	/* Tag DAR, to be used in DTLB Error */
 	mfspr r5,SPRN_DSISR
 	stw r5,_DSISR(r11)
···
 	EXC_XFER_STD(0x200, machine_check_exception)
 
 /* Data access exception.
- * This is "never generated" by the MPC8xx.  We jump to it for other
- * translation errors.
+ * This is "never generated" by the MPC8xx.
  */
 	. = 0x300
 DataAccess:
-	EXCEPTION_PROLOG
-	mfspr	r10,SPRN_DSISR
-	stw	r10,_DSISR(r11)
-	mr	r5,r10
-	mfspr	r4,SPRN_DAR
-	li	r10,0x00f0
-	mtspr	SPRN_DAR,r10	/* Tag DAR, to be used in DTLB Error */
-	EXC_XFER_LITE(0x300, handle_page_fault)
 
 /* Instruction access exception.
- * This is "never generated" by the MPC8xx.  We jump to it for other
- * translation errors.
+ * This is "never generated" by the MPC8xx.
  */
 	. = 0x400
 InstructionAccess:
-	EXCEPTION_PROLOG
-	mr	r4,r12
-	mr	r5,r9
-	EXC_XFER_LITE(0x400, handle_page_fault)
 
 /* External interrupt */
 	EXCEPTION(0x500, HardwareInterrupt, do_IRQ, EXC_XFER_LITE)
···
 	EXCEPTION_PROLOG
 	mfspr	r4,SPRN_DAR
 	stw	r4,_DAR(r11)
-	li	r5,0x00f0
+	li	r5,RPN_PATTERN
 	mtspr	SPRN_DAR,r5	/* Tag DAR, to be used in DTLB Error */
 	mfspr	r5,SPRN_DSISR
 	stw	r5,_DSISR(r11)
···
 	. = 0x1100
 /*
  * For the MPC8xx, this is a software tablewalk to load the instruction
- * TLB.  It is modelled after the example in the Motorola manual.  The task
- * switch loads the M_TWB register with the pointer to the first level table.
+ * TLB.  The task switch loads the M_TW register with the pointer to the first
+ * level table.
  * If we discover there is no second level table (value is zero) or if there
  * is an invalid pte, we load that into the TLB, which causes another fault
  * into the TLB Error interrupt where we can handle such problems.
···
  */
 InstructionTLBMiss:
 #ifdef CONFIG_8xx_CPU6
-	stw	r3, 8(r0)
+	mtspr	SPRN_DAR, r3
 #endif
 	EXCEPTION_PROLOG_0
 	mtspr	SPRN_SPRG_SCRATCH2, r10
 	mfspr	r10, SPRN_SRR0	/* Get effective address of fault */
 #ifdef CONFIG_8xx_CPU15
-	addi	r11, r10, 0x1000
+	addi	r11, r10, PAGE_SIZE
 	tlbie	r11
-	addi	r11, r10, -0x1000
+	addi	r11, r10, -PAGE_SIZE
 	tlbie	r11
 #endif
-	DO_8xx_CPU6(0x3780, r3)
-	mtspr	SPRN_MD_EPN, r10	/* Have to use MD_EPN for walk, MI_EPN can't */
-	mfspr	r10, SPRN_M_TWB	/* Get level 1 table entry address */
 
 	/* If we are faulting a kernel address, we have to use the
 	 * kernel page tables.
···
 #ifdef CONFIG_MODULES
 	/* Only modules will cause ITLB Misses as we always
 	 * pin the first 8MB of kernel memory */
-	andi.	r11, r10, 0x0800	/* Address >= 0x80000000 */
+	andis.	r11, r10, 0x8000	/* Address >= 0x80000000 */
+#endif
+	mfspr	r11, SPRN_M_TW	/* Get level 1 table base address */
+#ifdef CONFIG_MODULES
 	beq	3f
-	lis	r11, swapper_pg_dir@h
-	ori	r11, r11, swapper_pg_dir@l
-	rlwimi	r10, r11, 0, 2, 19
+	lis	r11, (swapper_pg_dir-PAGE_OFFSET)@h
+	ori	r11, r11, (swapper_pg_dir-PAGE_OFFSET)@l
 3:
 #endif
-	lwz	r11, 0(r10)	/* Get the level 1 entry */
+	/* Extract level 1 index */
+	rlwinm	r10, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29
+	lwzx	r11, r10, r11	/* Get the level 1 entry */
 	rlwinm.	r10, r11,0,0,19	/* Extract page descriptor page address */
 	beq	2f		/* If zero, don't try to find a pte */
 
 	/* We have a pte table, so load the MI_TWC with the attributes
 	 * for this "segment."
 	 */
-	ori	r11,r11,1		/* Set valid bit */
-	DO_8xx_CPU6(0x2b80, r3)
-	mtspr	SPRN_MI_TWC, r11	/* Set segment attributes */
-	DO_8xx_CPU6(0x3b80, r3)
-	mtspr	SPRN_MD_TWC, r11	/* Load pte table base address */
-	mfspr	r11, SPRN_MD_TWC	/* ....and get the pte address */
-	lwz	r10, 0(r11)	/* Get the pte */
+	MTSPR_CPU6(SPRN_MI_TWC, r11, r3)	/* Set segment attributes */
+	mfspr	r11, SPRN_SRR0	/* Get effective address of fault */
+	/* Extract level 2 index */
+	rlwinm	r11, r11, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29
+	lwzx	r10, r10, r11	/* Get the pte */
 
 #ifdef CONFIG_SWAP
 	andi.	r11, r10, _PAGE_ACCESSED | _PAGE_PRESENT
 	cmpwi	cr0, r11, _PAGE_ACCESSED | _PAGE_PRESENT
+	li	r11, RPN_PATTERN
 	bne-	cr0, 2f
+#else
+	li	r11, RPN_PATTERN
 #endif
 	/* The Linux PTE won't go exactly into the MMU TLB.
 	 * Software indicator bits 21 and 28 must be clear.
···
 	 * set.  All other Linux PTE bits control the behavior
 	 * of the MMU.
 	 */
-	li	r11, 0x00f0
 	rlwimi	r10, r11, 0, 0x07f8	/* Set 24-27, clear 21-23,28 */
-	DO_8xx_CPU6(0x2d80, r3)
-	mtspr	SPRN_MI_RPN, r10	/* Update TLB entry */
+	MTSPR_CPU6(SPRN_MI_RPN, r10, r3)	/* Update TLB entry */
 
 	/* Restore registers */
 #ifdef CONFIG_8xx_CPU6
-	lwz	r3, 8(r0)
+	mfspr	r3, SPRN_DAR
+	mtspr	SPRN_DAR, r11	/* Tag DAR */
 #endif
 	mfspr	r10, SPRN_SPRG_SCRATCH2
 	EXCEPTION_EPILOG_0
 	rfi
 2:
-	mfspr	r11, SPRN_SRR1
+	mfspr	r10, SPRN_SRR1
 	/* clear all error bits as TLB Miss
 	 * sets a few unconditionally
 	*/
-	rlwinm	r11, r11, 0, 0xffff
-	mtspr	SPRN_SRR1, r11
+	rlwinm	r10, r10, 0, 0xffff
+	mtspr	SPRN_SRR1, r10
 
 	/* Restore registers */
 #ifdef CONFIG_8xx_CPU6
-	lwz	r3, 8(r0)
+	mfspr	r3, SPRN_DAR
+	mtspr	SPRN_DAR, r11	/* Tag DAR */
 #endif
 	mfspr	r10, SPRN_SPRG_SCRATCH2
-	EXCEPTION_EPILOG_0
-	b	InstructionAccess
+	b	InstructionTLBError1
 
 	. = 0x1200
 DataStoreTLBMiss:
 #ifdef CONFIG_8xx_CPU6
-	stw	r3, 8(r0)
+	mtspr	SPRN_DAR, r3
 #endif
 	EXCEPTION_PROLOG_0
 	mtspr	SPRN_SPRG_SCRATCH2, r10
-	mfspr	r10, SPRN_M_TWB	/* Get level 1 table entry address */
+	mfspr	r10, SPRN_MD_EPN
 
 	/* If we are faulting a kernel address, we have to use the
 	 * kernel page tables.
 	 */
-	andi.	r11, r10, 0x0800
+	andis.	r11, r10, 0x8000
+	mfspr	r11, SPRN_M_TW	/* Get level 1 table base address */
 	beq	3f
-	lis	r11, swapper_pg_dir@h
-	ori	r11, r11, swapper_pg_dir@l
-	rlwimi	r10, r11, 0, 2, 19
+	lis	r11, (swapper_pg_dir-PAGE_OFFSET)@h
+	ori	r11, r11, (swapper_pg_dir-PAGE_OFFSET)@l
 3:
-	lwz	r11, 0(r10)	/* Get the level 1 entry */
+	/* Extract level 1 index */
+	rlwinm	r10, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29
+	lwzx	r11, r10, r11	/* Get the level 1 entry */
 	rlwinm.	r10, r11,0,0,19	/* Extract page descriptor page address */
 	beq	2f		/* If zero, don't try to find a pte */
 
 	/* We have a pte table, so load fetch the pte from the table.
 	 */
-	ori	r11, r11, 1	/* Set valid bit in physical L2 page */
-	DO_8xx_CPU6(0x3b80, r3)
-	mtspr	SPRN_MD_TWC, r11	/* Load pte table base address */
-	mfspr	r10, SPRN_MD_TWC	/* ....and get the pte address */
+	mfspr	r10, SPRN_MD_EPN	/* Get address of fault */
+	/* Extract level 2 index */
+	rlwinm	r10, r10, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29
+	rlwimi	r10, r11, 0, 0, 32 - PAGE_SHIFT - 1	/* Add level 2 base */
 	lwz	r10, 0(r10)	/* Get the pte */
 
 	/* Insert the Guarded flag into the TWC from the Linux PTE.
···
 	 * It is bit 25 in the Linux PTE and bit 30 in the TWC
 	 */
 	rlwimi	r11, r10, 32-5, 30, 30
-	DO_8xx_CPU6(0x3b80, r3)
-	mtspr	SPRN_MD_TWC, r11
+	MTSPR_CPU6(SPRN_MD_TWC, r11, r3)
 
 	/* Both _PAGE_ACCESSED and _PAGE_PRESENT has to be set.
 	 * We also need to know if the insn is a load/store, so:
···
 	and	r11, r11, r10
 	rlwimi	r10, r11, 0, _PAGE_PRESENT
 #endif
-	/* Honour kernel RO, User NA */
-	/* 0x200 == Extended encoding, bit 22 */
-	rlwimi	r10, r10, 32-2, 0x200 /* Copy USER to bit 22, 0x200 */
-	/* r11 =  (r10 & _PAGE_RW) >> 1 */
-	rlwinm	r11, r10, 32-1, 0x200
-	or	r10, r11, r10
-	/* invert RW and 0x200 bits */
-	xori	r10, r10, _PAGE_RW | 0x200
+	/* invert RW */
+	xori	r10, r10, _PAGE_RW
 
 	/* The Linux PTE won't go exactly into the MMU TLB.
 	 * Software indicator bits 22 and 28 must be clear.
···
 	 * set.  All other Linux PTE bits control the behavior
 	 * of the MMU.
 	 */
-2:	li	r11, 0x00f0
+2:	li	r11, RPN_PATTERN
 	rlwimi	r10, r11, 0, 24, 28	/* Set 24-27, clear 28 */
-	DO_8xx_CPU6(0x3d80, r3)
-	mtspr	SPRN_MD_RPN, r10	/* Update TLB entry */
+	MTSPR_CPU6(SPRN_MD_RPN, r10, r3)	/* Update TLB entry */
 
 	/* Restore registers */
 #ifdef CONFIG_8xx_CPU6
-	lwz	r3, 8(r0)
+	mfspr	r3, SPRN_DAR
 #endif
 	mtspr	SPRN_DAR, r11	/* Tag DAR */
 	mfspr	r10, SPRN_SPRG_SCRATCH2
···
  */
 	. = 0x1300
 InstructionTLBError:
-	b	InstructionAccess
+	EXCEPTION_PROLOG_0
+InstructionTLBError1:
+	EXCEPTION_PROLOG_1
+	EXCEPTION_PROLOG_2
+	mr	r4,r12
+	mr	r5,r9
+	andis.	r10,r5,0x4000
+	beq+	1f
+	tlbie	r4
+	/* 0x400 is InstructionAccess exception, needed by bad_page_fault() */
+1:	EXC_XFER_LITE(0x400, handle_page_fault)
 
 /* This is the data TLB error on the MPC8xx.  This could be due to
  * many reasons, including a dirty update to a pte.  We bail out to
···
 	EXCEPTION_PROLOG_0
 
 	mfspr	r11, SPRN_DAR
-	cmpwi	cr0, r11, 0x00f0
+	cmpwi	cr0, r11, RPN_PATTERN
 	beq-	FixupDAR	/* must be a buggy dcbX, icbi insn. */
 DARFixed:/* Return from dcbx instruction bug workaround */
-	EXCEPTION_EPILOG_0
-	b	DataAccess
+	EXCEPTION_PROLOG_1
+	EXCEPTION_PROLOG_2
+	mfspr	r5,SPRN_DSISR
+	stw	r5,_DSISR(r11)
+	mfspr	r4,SPRN_DAR
+	andis.	r10,r5,0x4000
+	beq+	1f
+	tlbie	r4
+1:	li	r10,RPN_PATTERN
+	mtspr	SPRN_DAR,r10	/* Tag DAR, to be used in DTLB Error */
+	/* 0x300 is DataAccess exception, needed by bad_page_fault() */
+	EXC_XFER_LITE(0x300, handle_page_fault)
 
 	EXCEPTION(0x1500, Trap_15, unknown_exception, EXC_XFER_EE)
 	EXCEPTION(0x1600, Trap_16, unknown_exception, EXC_XFER_EE)
···
 #define NO_SELF_MODIFYING_CODE
 FixupDAR:/* Entry point for dcbx workaround. */
 #ifdef CONFIG_8xx_CPU6
-	stw	r3, 8(r0)
+	mtspr	SPRN_DAR, r3
 #endif
 	mtspr	SPRN_SPRG_SCRATCH2, r10
 	/* fetch instruction from memory. */
 	mfspr	r10, SPRN_SRR0
 	andis.	r11, r10, 0x8000	/* Address >= 0x80000000 */
-	DO_8xx_CPU6(0x3780, r3)
-	mtspr	SPRN_MD_EPN, r10
-	mfspr	r11, SPRN_M_TWB	/* Get level 1 table entry address */
+	mfspr	r11, SPRN_M_TW	/* Get level 1 table base address */
 	beq-	3f		/* Branch if user space */
 	lis	r11, (swapper_pg_dir-PAGE_OFFSET)@h
 	ori	r11, r11, (swapper_pg_dir-PAGE_OFFSET)@l
-	rlwimi	r11, r10, 32-20, 0xffc /* r11 = r11&~0xffc|(r10>>20)&0xffc */
-3:	lwz	r11, 0(r11)	/* Get the level 1 entry */
-	DO_8xx_CPU6(0x3b80, r3)
-	mtspr	SPRN_MD_TWC, r11	/* Load pte table base address */
-	mfspr	r11, SPRN_MD_TWC	/* ....and get the pte address */
-	lwz	r11, 0(r11)	/* Get the pte */
+	/* Extract level 1 index */
+3:	rlwinm	r10, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29
+	lwzx	r11, r10, r11	/* Get the level 1 entry */
+	rlwinm	r10, r11,0,0,19	/* Extract page descriptor page address */
+	mfspr	r11, SPRN_SRR0	/* Get effective address of fault */
+	/* Extract level 2 index */
+	rlwinm	r11, r11, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29
+	lwzx	r11, r10, r11	/* Get the pte */
 #ifdef CONFIG_8xx_CPU6
-	lwz	r3, 8(r0)	/* restore r3 from memory */
+	mfspr	r3, SPRN_DAR
 #endif
 	/* concat physical page address(r11) and page offset(r10) */
-	rlwimi	r11, r10, 0, 20, 31
+	mfspr	r10, SPRN_SRR0
+	rlwimi	r11, r10, 0, 32 - PAGE_SHIFT, 31
 	lwz	r11,0(r11)
 /* Check if it really is a dcbx instruction. */
 /* dcbt and dcbtst does not generate DTLB Misses/Errors,
···
 #ifdef CONFIG_8xx_CPU6
 	lis	r4, cpu6_errata_word@h
 	ori	r4, r4, cpu6_errata_word@l
-	li	r3, 0x3980
+	li	r3, 0x3f80
 	stw	r3, 12(r4)
 	lwz	r3, 12(r4)
 #endif
-	mtspr	SPRN_M_TWB, r6
+	mtspr	SPRN_M_TW, r6
 	lis	r4,2f@h
 	ori	r4,r4,2f@l
 	tophys(r4,r4)
···
 	lis	r6, cpu6_errata_word@h
 	ori	r6, r6, cpu6_errata_word@l
 	tophys	(r4, r4)
-	li	r7, 0x3980
+	li	r7, 0x3f80
 	stw	r7, 12(r6)
 	lwz	r7, 12(r6)
-        mtspr   SPRN_M_TWB, r4               /* Update MMU base address */
+        mtspr   SPRN_M_TW, r4               /* Update MMU base address */
 	li	r7, 0x3380
 	stw	r7, 12(r6)
 	lwz	r7, 12(r6)
···
 #else
         mtspr   SPRN_M_CASID,r3		/* Update context */
 	tophys	(r4, r4)
-	mtspr	SPRN_M_TWB, r4		/* and pgd */
+	mtspr	SPRN_M_TW, r4		/* and pgd */
 #endif
 	SYNC
 	blr
···
 	.globl	sdata
 sdata:
 	.globl	empty_zero_page
+	.align	PAGE_SHIFT
 empty_zero_page:
-	.space	4096
+	.space	PAGE_SIZE
 
 	.globl	swapper_pg_dir
 swapper_pg_dir:
-	.space	4096
+	.space	PGD_TABLE_SIZE
 
 /* Room for two PTE table poiners, usually the kernel and current user
  * pointer to their respective root page table (pgdir).

arch/powerpc/kernel/hw_breakpoint.c

···
 int arch_install_hw_breakpoint(struct perf_event *bp)
 {
 	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-	struct perf_event **slot = &__get_cpu_var(bp_per_reg);
+	struct perf_event **slot = this_cpu_ptr(&bp_per_reg);
 
 	*slot = bp;
 
···
  */
 void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 {
-	struct perf_event **slot = &__get_cpu_var(bp_per_reg);
+	struct perf_event **slot = this_cpu_ptr(&bp_per_reg);
 
 	if (*slot != bp) {
 		WARN_ONCE(1, "Can't find the breakpoint");
···
 	 */
 	rcu_read_lock();
 
-	bp = __get_cpu_var(bp_per_reg);
+	bp = __this_cpu_read(bp_per_reg);
 	if (!bp)
 		goto out;
 	info = counter_arch_bp(bp);

arch/powerpc/kernel/idle_power7.S

···
 	mtspr	SPRN_SRR0,r5
 	rfid
 
+/*
+ * R3 here contains the value that will be returned to the caller
+ * of power7_nap.
+ */
 _GLOBAL(power7_wakeup_loss)
 	ld	r1,PACAR1(r13)
 BEGIN_FTR_SECTION
···
 END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
 	REST_NVGPRS(r1)
 	REST_GPR(2, r1)
-	ld	r3,_CCR(r1)
+	ld	r6,_CCR(r1)
 	ld	r4,_MSR(r1)
 	ld	r5,_NIP(r1)
 	addi	r1,r1,INT_FRAME_SIZE
-	mtcr	r3
+	mtcr	r6
 	mtspr	SPRN_SRR1,r4
 	mtspr	SPRN_SRR0,r5
 	rfid
 
+/*
+ * R3 here contains the value that will be returned to the caller
+ * of power7_nap.
+ */
 _GLOBAL(power7_wakeup_noloss)
 	lbz	r0,PACA_NAPSTATELOST(r13)
 	cmpwi	r0,0

arch/powerpc/kernel/iommu.c

···
 	 * We don't need to disable preemption here because any CPU can
 	 * safely use any IOMMU pool.
 	 */
-	pool_nr = __raw_get_cpu_var(iommu_pool_hash) & (tbl->nr_pools - 1);
+	pool_nr = __this_cpu_read(iommu_pool_hash) & (tbl->nr_pools - 1);
 
 	if (largealloc)
 		pool = &(tbl->large_pool);

arch/powerpc/kernel/irq.c

···
 #include <linux/list.h>
 #include <linux/radix-tree.h>
 #include <linux/mutex.h>
-#include <linux/bootmem.h>
 #include <linux/pci.h>
 #include <linux/debugfs.h>
 #include <linux/of.h>
···
 static inline notrace int decrementer_check_overflow(void)
 {
  	u64 now = get_tb_or_rtc();
- 	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
+	u64 *next_tb = this_cpu_ptr(&decrementers_next_tb);
  
 	return now >= *next_tb;
 }
···
 
 	/* And finally process it */
 	if (unlikely(irq == NO_IRQ))
-		__get_cpu_var(irq_stat).spurious_irqs++;
+		__this_cpu_inc(irq_stat.spurious_irqs);
 	else
 		generic_handle_irq(irq);
 

arch/powerpc/kernel/kgdb.c

···
 {
 	struct thread_info *thread_info, *exception_thread_info;
 	struct thread_info *backup_current_thread_info =
-		&__get_cpu_var(kgdb_thread_info);
+		this_cpu_ptr(&kgdb_thread_info);
 
 	if (user_mode(regs))
 		return 0;

arch/powerpc/kernel/kprobes.c

···
 
 static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 {
-	__get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp;
+	__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
 	kcb->kprobe_status = kcb->prev_kprobe.status;
 	kcb->kprobe_saved_msr = kcb->prev_kprobe.saved_msr;
 }
···
 static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
 				struct kprobe_ctlblk *kcb)
 {
-	__get_cpu_var(current_kprobe) = p;
+	__this_cpu_write(current_kprobe, p);
 	kcb->kprobe_saved_msr = regs->msr;
 }
 
···
 				ret = 1;
 				goto no_kprobe;
 			}
-			p = __get_cpu_var(current_kprobe);
+			p = __this_cpu_read(current_kprobe);
 			if (p->break_handler && p->break_handler(p, regs)) {
 				goto ss_probe;
 			}

arch/powerpc/kernel/mce.c

···
 		    uint64_t nip, uint64_t addr)
 {
 	uint64_t srr1;
-	int index = __get_cpu_var(mce_nest_count)++;
-	struct machine_check_event *mce = &__get_cpu_var(mce_event[index]);
+	int index = __this_cpu_inc_return(mce_nest_count);
+	struct machine_check_event *mce = this_cpu_ptr(&mce_event[index]);
 
 	/*
 	 * Return if we don't have enough space to log mce event.
···
  */
 int get_mce_event(struct machine_check_event *mce, bool release)
 {
-	int index = __get_cpu_var(mce_nest_count) - 1;
+	int index = __this_cpu_read(mce_nest_count) - 1;
 	struct machine_check_event *mc_evt;
 	int ret = 0;
 
···
 
 	/* Check if we have MCE info to process. */
 	if (index < MAX_MC_EVT) {
-		mc_evt = &__get_cpu_var(mce_event[index]);
+		mc_evt = this_cpu_ptr(&mce_event[index]);
 		/* Copy the event structure and release the original */
 		if (mce)
 			*mce = *mc_evt;
···
 	}
 	/* Decrement the count to free the slot. */
 	if (release)
-		__get_cpu_var(mce_nest_count)--;
+		__this_cpu_dec(mce_nest_count);
 
 	return ret;
 }
···
 	if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
 		return;
 
-	index = __get_cpu_var(mce_queue_count)++;
+	index = __this_cpu_inc_return(mce_queue_count);
 	/* If queue is full, just return for now. */
 	if (index >= MAX_MC_EVT) {
-		__get_cpu_var(mce_queue_count)--;
+		__this_cpu_dec(mce_queue_count);
 		return;
 	}
-	__get_cpu_var(mce_event_queue[index]) = evt;
+	memcpy(this_cpu_ptr(&mce_event_queue[index]), &evt, sizeof(evt));
 
 	/* Queue irq work to process this event later. */
 	irq_work_queue(&mce_event_process_work);
···
 	 * For now just print it to console.
 	 * TODO: log this error event to FSP or nvram.
 	 */
-	while (__get_cpu_var(mce_queue_count) > 0) {
-		index = __get_cpu_var(mce_queue_count) - 1;
+	while (__this_cpu_read(mce_queue_count) > 0) {
+		index = __this_cpu_read(mce_queue_count) - 1;
 		machine_check_print_event_info(
-				&__get_cpu_var(mce_event_queue[index]));
-		__get_cpu_var(mce_queue_count)--;
+				this_cpu_ptr(&mce_event_queue[index]));
+		__this_cpu_dec(mce_queue_count);
 	}
 }
 

arch/powerpc/kernel/mce_power.c

···
 	}
 	if (dsisr & P7_DSISR_MC_TLB_MULTIHIT_MFTLB) {
 		if (cur_cpu_spec && cur_cpu_spec->flush_tlb)
-			cur_cpu_spec->flush_tlb(TLBIEL_INVAL_PAGE);
+			cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET);
 		/* reset error bits */
 		dsisr &= ~P7_DSISR_MC_TLB_MULTIHIT_MFTLB;
 	}
···
 		break;
 	case P7_SRR1_MC_IFETCH_TLB_MULTIHIT:
 		if (cur_cpu_spec && cur_cpu_spec->flush_tlb) {
-			cur_cpu_spec->flush_tlb(TLBIEL_INVAL_PAGE);
+			cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET);
 			handled = 1;
 		}
 		break;

arch/powerpc/kernel/pci-common.c

···
 #include <linux/pci.h>
 #include <linux/string.h>
 #include <linux/init.h>
-#include <linux/bootmem.h>
 #include <linux/delay.h>
 #include <linux/export.h>
 #include <linux/of_address.h>
···
 	res = &hose->io_resource;
 
 	if (!res->flags) {
-		printk(KERN_WARNING "PCI: I/O resource not set for host"
+		pr_info("PCI: I/O resource not set for host"
 		       " bridge %s (domain %d)\n",
 		       hose->dn->full_name, hose->global_number);
 	} else {

arch/powerpc/kernel/pci_32.c

···
 	struct property* of_prop;
 	struct device_node *dn;
 
-	of_prop = (struct property*) alloc_bootmem(sizeof(struct property) + 256);
-	if (!of_prop)
-		return;
+	of_prop = memblock_virt_alloc(sizeof(struct property) + 256, 0);
 	dn = of_find_node_by_path("/");
 	if (dn) {
 		memset(of_prop, -1, sizeof(struct property) + 256);

arch/powerpc/kernel/pci_64.c

···
 #include <linux/pci.h>
 #include <linux/string.h>
 #include <linux/init.h>
-#include <linux/bootmem.h>
 #include <linux/export.h>
 #include <linux/mm.h>
 #include <linux/list.h>

arch/powerpc/kernel/process.c

···
 #include <linux/personality.h>
 #include <linux/random.h>
 #include <linux/hw_breakpoint.h>
+#include <linux/uaccess.h>
 
 #include <asm/pgtable.h>
-#include <asm/uaccess.h>
 #include <asm/io.h>
 #include <asm/processor.h>
 #include <asm/mmu.h>
···
 
 void __set_breakpoint(struct arch_hw_breakpoint *brk)
 {
-	__get_cpu_var(current_brk) = *brk;
+	memcpy(this_cpu_ptr(&current_brk), brk, sizeof(*brk));
 
 	if (cpu_has_feature(CPU_FTR_DAWR))
 		set_dawr(brk);
···
  * schedule DABR
  */
 #ifndef CONFIG_HAVE_HW_BREAKPOINT
-	if (unlikely(!hw_brk_match(&__get_cpu_var(current_brk), &new->thread.hw_brk)))
+	if (unlikely(!hw_brk_match(this_cpu_ptr(&current_brk), &new->thread.hw_brk)))
 		__set_breakpoint(&new->thread.hw_brk);
 #endif /* CONFIG_HAVE_HW_BREAKPOINT */
 #endif
···
 	 * Collect processor utilization data per process
 	 */
 	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
-		struct cpu_usage *cu = &__get_cpu_var(cpu_usage_array);
+		struct cpu_usage *cu = this_cpu_ptr(&cpu_usage_array);
 		long unsigned start_tb, current_tb;
 		start_tb = old_thread->start_tb;
 		cu->current_tb = current_tb = mfspr(SPRN_PURR);
···
 #endif /* CONFIG_PPC64 */
 
 #ifdef CONFIG_PPC_BOOK3S_64
-	batch = &__get_cpu_var(ppc64_tlb_batch);
+	batch = this_cpu_ptr(&ppc64_tlb_batch);
 	if (batch->active) {
 		current_thread_info()->local_flags |= _TLF_LAZY_MMU;
 		if (batch->index)
···
 #ifdef CONFIG_PPC_BOOK3S_64
 	if (current_thread_info()->local_flags & _TLF_LAZY_MMU) {
 		current_thread_info()->local_flags &= ~_TLF_LAZY_MMU;
-		batch = &__get_cpu_var(ppc64_tlb_batch);
+		batch = this_cpu_ptr(&ppc64_tlb_batch);
 		batch->active = 1;
 	}
 #endif /* CONFIG_PPC_BOOK3S_64 */
···
 			pc = (unsigned long)phys_to_virt(pc);
 #endif
 
-		/* We use __get_user here *only* to avoid an OOPS on a
-		 * bad address because the pc *should* only be a
-		 * kernel address.
-		 */
 		if (!__kernel_text_address(pc) ||
-		     __get_user(instr, (unsigned int __user *)pc)) {
+		     probe_kernel_address((unsigned int __user *)pc, instr)) {
 			printk(KERN_CONT "XXXXXXXX ");
 		} else {
 			if (regs->nip == pc)
···
 	int curr_frame = current->curr_ret_stack;
 	extern void return_to_handler(void);
 	unsigned long rth = (unsigned long)return_to_handler;
-	unsigned long mrth = -1;
-#ifdef CONFIG_PPC64
-	extern void mod_return_to_handler(void);
-	rth = *(unsigned long *)rth;
-	mrth = (unsigned long)mod_return_to_handler;
-	mrth = *(unsigned long *)mrth;
-#endif
 #endif
 
 	sp = (unsigned long) stack;
···
 		if (!firstframe || ip != lr) {
 			printk("["REG"] ["REG"] %pS", sp, ip, (void *)ip);
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-			if ((ip == rth || ip == mrth) && curr_frame >= 0) {
+			if ((ip == rth) && curr_frame >= 0) {
 				printk(" (%pS)",
 				       (void *)current->ret_stack[curr_frame].ret);
 				curr_frame--;
···
 	return ret;
 }
 
-unsigned long randomize_et_dyn(unsigned long base)
-{
-	unsigned long ret = PAGE_ALIGN(base + brk_rnd());
-
-	if (ret < base)
-		return base;
-
-	return ret;
-}

arch/powerpc/kernel/prom.c

···
 	{CPU_FTR_NODSISRALIGN, 0, 0,	1, 1, 1},
 	{0, MMU_FTR_CI_LARGE_PAGE, 0,	1, 2, 0},
 	{CPU_FTR_REAL_LE, PPC_FEATURE_TRUE_LE, 5, 0, 0},
+	/*
+	 * If the kernel doesn't support TM (ie. CONFIG_PPC_TRANSACTIONAL_MEM=n),
+	 * we don't want to turn on CPU_FTR_TM here, so we use CPU_FTR_TM_COMP
+	 * which is 0 if the kernel doesn't support TM.
+	 */
+	{CPU_FTR_TM_COMP, 0, 0,		22, 0, 0},
 };
 
 static void __init scan_features(unsigned long node, const unsigned char *ftrs,
···
 		reserve_crashkernel();
 	early_reserve_mem();
 
-	/*
-	 * Ensure that total memory size is page-aligned, because otherwise
-	 * mark_bootmem() gets upset.
-	 */
+	/* Ensure that total memory size is page-aligned. */
 	limit = ALIGN(memory_limit ?: memblock_phys_mem_size(), PAGE_SIZE);
 	memblock_enforce_memory_limit(limit);
 

arch/powerpc/kernel/rtas-proc.c

···
 #define SENSOR_PREFIX		"ibm,sensor-"
 #define cel_to_fahr(x)		((x*9/5)+32)
 
-
-/* Globals */
-static struct rtas_sensors sensors;
-static struct device_node *rtas_node = NULL;
-static unsigned long power_on_time = 0; /* Save the time the user set */
-static char progress_led[MAX_LINELENGTH];
-
-static unsigned long rtas_tone_frequency = 1000;
-static unsigned long rtas_tone_volume = 0;
-
-/* ****************STRUCTS******************************************* */
 struct individual_sensor {
 	unsigned int token;
 	unsigned int quant;
···
         struct individual_sensor sensor[MAX_SENSORS];
 	unsigned int quant;
 };
+
+/* Globals */
+static struct rtas_sensors sensors;
+static struct device_node *rtas_node = NULL;
+static unsigned long power_on_time = 0; /* Save the time the user set */
+static char progress_led[MAX_LINELENGTH];
+
+static unsigned long rtas_tone_frequency = 1000;
+static unsigned long rtas_tone_volume = 0;
 
 /* ****************************************************************** */
 /* Declarations */

arch/powerpc/kernel/rtas.c

···
 }
 
 /*
- * Call early during boot, before mem init or bootmem, to retrieve the RTAS
- * informations from the device-tree and allocate the RMO buffer for userland
+ * Call early during boot, before mem init, to retrieve the RTAS
+ * information from the device-tree and allocate the RMO buffer for userland
  * accesses.
  */
 void __init rtas_initialize(void)

arch/powerpc/kernel/rtas_pci.c

···
 #include <linux/pci.h>
 #include <linux/string.h>
 #include <linux/init.h>
-#include <linux/bootmem.h>
 
 #include <asm/io.h>
 #include <asm/pgtable.h>

arch/powerpc/kernel/setup-common.c

···
 void machine_power_off(void)
 {
 	machine_shutdown();
-	if (ppc_md.power_off)
-		ppc_md.power_off();
+	if (pm_power_off)
+		pm_power_off();
 #ifdef CONFIG_SMP
 	smp_send_stop();
 #endif
···
 /* Used by the G5 thermal driver */
 EXPORT_SYMBOL_GPL(machine_power_off);
 
-void (*pm_power_off)(void) = machine_power_off;
+void (*pm_power_off)(void);
 EXPORT_SYMBOL_GPL(pm_power_off);
 
 void machine_halt(void)

arch/powerpc/kernel/setup_32.c

···
 #include <linux/delay.h>
 #include <linux/initrd.h>
 #include <linux/tty.h>
-#include <linux/bootmem.h>
 #include <linux/seq_file.h>
 #include <linux/root_dev.h>
 #include <linux/cpu.h>
···
 unsigned long ISA_DMA_THRESHOLD;
 unsigned int DMA_MODE_READ;
 unsigned int DMA_MODE_WRITE;
-
-#ifdef CONFIG_VGA_CONSOLE
-unsigned long vgacon_remap_base;
-EXPORT_SYMBOL(vgacon_remap_base);
-#endif
 
 /*
  * These are used in binfmt_elf.c to put aux entries on the stack
···
 
 	irqstack_early_init();
 
-	/* set up the bootmem stuff with available memory */
-	do_init_bootmem();
-	if ( ppc_md.progress ) ppc_md.progress("setup_arch: bootmem", 0x3eab);
+	initmem_init();
+	if ( ppc_md.progress ) ppc_md.progress("setup_arch: initmem", 0x3eab);
 
 #ifdef CONFIG_DUMMY_CONSOLE
 	conswitchp = &dummy_con;

arch/powerpc/kernel/setup_64.c

···
 }
 
 /*
- * Called into from start_kernel this initializes bootmem, which is used
+ * Called into from start_kernel this initializes memblock, which is used
  * to manage page allocation until mem_init is called.
  */
 void __init setup_arch(char **cmdline_p)
 {
-	ppc64_boot_msg(0x12, "Setup Arch");
-
 	*cmdline_p = boot_command_line;
 
 	/*
···
 	exc_lvl_early_init();
 	emergency_stack_init();
 
-	/* set up the bootmem stuff with available memory */
-	do_init_bootmem();
-	sparse_init();
+	initmem_init();
 
 #ifdef CONFIG_DUMMY_CONSOLE
 	conswitchp = &dummy_con;
···
 	if ((unsigned long)_stext & 0xffff)
 		panic("Kernelbase not 64K-aligned (0x%lx)!\n",
 		      (unsigned long)_stext);
-
-	ppc64_boot_msg(0x15, "Setup Done");
-}
-
-
-/* ToDo: do something useful if ppc_md is not yet setup. */
-#define PPC64_LINUX_FUNCTION 0x0f000000
-#define PPC64_IPL_MESSAGE 0xc0000000
-#define PPC64_TERM_MESSAGE 0xb0000000
-
-static void ppc64_do_msg(unsigned int src, const char *msg)
-{
-	if (ppc_md.progress) {
-		char buf[128];
-
-		sprintf(buf, "%08X\n", src);
-		ppc_md.progress(buf, 0);
-		snprintf(buf, 128, "%s", msg);
-		ppc_md.progress(buf, 0);
-	}
-}
-
-/* Print a boot progress message. */
-void ppc64_boot_msg(unsigned int src, const char *msg)
-{
-	ppc64_do_msg(PPC64_LINUX_FUNCTION|PPC64_IPL_MESSAGE|src, msg);
-	printk("[boot]%04x %s\n", src, msg);
 }
 
 #ifdef CONFIG_SMP

arch/powerpc/kernel/smp.c

···
 
 irqreturn_t smp_ipi_demux(void)
 {
-	struct cpu_messages *info = &__get_cpu_var(ipi_message);
+	struct cpu_messages *info = this_cpu_ptr(&ipi_message);
 	unsigned int all;
 
 	mb();	/* order any irq clear */
···
 	idle_task_exit();
 	cpu = smp_processor_id();
 	printk(KERN_DEBUG "CPU%d offline\n", cpu);
-	__get_cpu_var(cpu_state) = CPU_DEAD;
+	__this_cpu_write(cpu_state, CPU_DEAD);
 	smp_wmb();
-	while (__get_cpu_var(cpu_state) != CPU_UP_PREPARE)
+	while (__this_cpu_read(cpu_state) != CPU_UP_PREPARE)
 		cpu_relax();
 }
 

arch/powerpc/kernel/sysfs.c

···
 	ppc_set_pmu_inuse(1);
 
 	/* Only need to enable them once */
-	if (__get_cpu_var(pmcs_enabled))
+	if (__this_cpu_read(pmcs_enabled))
 		return;
 
-	__get_cpu_var(pmcs_enabled) = 1;
+	__this_cpu_write(pmcs_enabled, 1);
 
 	if (ppc_md.enable_pmcs)
 		ppc_md.enable_pmcs();

arch/powerpc/kernel/time.c

···
 
 DEFINE_PER_CPU(u8, irq_work_pending);
 
-#define set_irq_work_pending_flag()	__get_cpu_var(irq_work_pending) = 1
-#define test_irq_work_pending()		__get_cpu_var(irq_work_pending)
-#define clear_irq_work_pending()	__get_cpu_var(irq_work_pending) = 0
+#define set_irq_work_pending_flag()	__this_cpu_write(irq_work_pending, 1)
+#define test_irq_work_pending()		__this_cpu_read(irq_work_pending)
+#define clear_irq_work_pending()	__this_cpu_write(irq_work_pending, 0)
 
 #endif /* 32 vs 64 bit */
 
···
 static void __timer_interrupt(void)
 {
 	struct pt_regs *regs = get_irq_regs();
-	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
-	struct clock_event_device *evt = &__get_cpu_var(decrementers);
+	u64 *next_tb = this_cpu_ptr(&decrementers_next_tb);
+	struct clock_event_device *evt = this_cpu_ptr(&decrementers);
 	u64 now;
 
 	trace_timer_interrupt_entry(regs);
···
 		*next_tb = ~(u64)0;
 		if (evt->event_handler)
 			evt->event_handler(evt);
-		__get_cpu_var(irq_stat).timer_irqs_event++;
+		__this_cpu_inc(irq_stat.timer_irqs_event);
 	} else {
 		now = *next_tb - now;
 		if (now <= DECREMENTER_MAX)
···
 		/* We may have raced with new irq work */
 		if (test_irq_work_pending())
 			set_dec(1);
-		__get_cpu_var(irq_stat).timer_irqs_others++;
+		__this_cpu_inc(irq_stat.timer_irqs_others);
 	}
 
 #ifdef CONFIG_PPC64
 	/* collect purr register values often, for accurate calculations */
 	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
-		struct cpu_usage *cu = &__get_cpu_var(cpu_usage_array);
+		struct cpu_usage *cu = this_cpu_ptr(&cpu_usage_array);
 		cu->current_tb = mfspr(SPRN_PURR);
 	}
 #endif
···
 void timer_interrupt(struct pt_regs * regs)
 {
 	struct pt_regs *old_regs;
-	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
+	u64 *next_tb = this_cpu_ptr(&decrementers_next_tb);
 
 	/* Ensure a positive value is written to the decrementer, or else
 	 * some CPUs will continue to take decrementer exceptions.
···
 static int decrementer_set_next_event(unsigned long evt,
 				      struct clock_event_device *dev)
 {
-	__get_cpu_var(decrementers_next_tb) = get_tb_or_rtc() + evt;
+	__this_cpu_write(decrementers_next_tb, get_tb_or_rtc() + evt);
 	set_dec(evt);
 
 	/* We may have raced with new irq work */
···
 /* Interrupt handler for the timer broadcast IPI */
 void tick_broadcast_ipi_handler(void)
 {
-	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
+	u64 *next_tb = this_cpu_ptr(&decrementers_next_tb);
 
 	*next_tb = get_tb_or_rtc();
 	__timer_interrupt();
···
 
 	tm->tm_wday = day % 7;
 }
+EXPORT_SYMBOL_GPL(GregorianDay);
 
 void to_tm(int tim, struct rtc_time * tm)
 {

arch/powerpc/kernel/traps.c

···
 {
 	long handled = 0;
 
-	__get_cpu_var(irq_stat).mce_exceptions++;
+	__this_cpu_inc(irq_stat.mce_exceptions);
 
 	if (cur_cpu_spec && cur_cpu_spec->machine_check_early)
 		handled = cur_cpu_spec->machine_check_early(regs);
···
 
 long hmi_exception_realmode(struct pt_regs *regs)
 {
-	__get_cpu_var(irq_stat).hmi_exceptions++;
+	__this_cpu_inc(irq_stat.hmi_exceptions);
 
 	if (ppc_md.hmi_exception_early)
 		ppc_md.hmi_exception_early(regs);
···
 	enum ctx_state prev_state = exception_enter();
 	int recover = 0;
 
-	__get_cpu_var(irq_stat).mce_exceptions++;
+	__this_cpu_inc(irq_stat.mce_exceptions);
 
 	/* See if any machine dependent calls. In theory, we would want
 	 * to call the CPU first, and call the ppc_md. one if the CPU
···
 
 void performance_monitor_exception(struct pt_regs *regs)
 {
-	__get_cpu_var(irq_stat).pmu_irqs++;
+	__this_cpu_inc(irq_stat.pmu_irqs);
 
 	perf_irq(regs);
 }

arch/powerpc/kernel/udbg_16550.c

···
 
 static int udbg_uart_getc_poll(void)
 {
-	if (!udbg_uart_in || !(udbg_uart_in(UART_LSR) & LSR_DR))
+	if (!udbg_uart_in)
+		return -1;
+
+	if (!(udbg_uart_in(UART_LSR) & LSR_DR))
 		return udbg_uart_in(UART_RBR);
+
 	return -1;
 }
 

arch/powerpc/kernel/vdso.c

···
 #include <linux/user.h>
 #include <linux/elf.h>
 #include <linux/security.h>
-#include <linux/bootmem.h>
 #include <linux/memblock.h>
 
 #include <asm/pgtable.h>

arch/powerpc/kvm/book3s_hv_builtin.c

···
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/spinlock.h>
-#include <linux/bootmem.h>
 #include <linux/init.h>
 #include <linux/memblock.h>
 #include <linux/sizes.h>
···
  * kvm_cma_reserve() - reserve area for kvm hash pagetable
  *
  * This function reserves memory from early allocator. It should be
- * called by arch specific code once the early allocator (memblock or bootmem)
+ * called by arch specific code once the memblock allocator
  * has been activated and all other subsystems have already allocated/reserved
  * memory.
  */

arch/powerpc/kvm/book3s_hv_rmhandlers.S

···
 	bge	kvm_novcpu_exit	/* another thread already exiting */
 	li	r3, NAPPING_NOVCPU
 	stb	r3, HSTATE_NAPPING(r13)
-	li	r3, 1
-	stb	r3, HSTATE_HWTHREAD_REQ(r13)
 
 	b	kvm_do_nap
 
···
 	/* if we have no vcpu to run, go back to sleep */
 	beq	kvm_no_guest
 
+kvm_secondary_got_guest:
+
 	/* Set HSTATE_DSCR(r13) to something sensible */
 	ld	r6, PACA_DSCR(r13)
 	std	r6, HSTATE_DSCR(r13)
···
 	stwcx.	r3, 0, r4
 	bne	51b
 
+/*
+ * At this point we have finished executing in the guest.
+ * We need to wait for hwthread_req to become zero, since
+ * we may not turn on the MMU while hwthread_req is non-zero.
+ * While waiting we also need to check if we get given a vcpu to run.
+ */
 kvm_no_guest:
-	li	r0, KVM_HWTHREAD_IN_NAP
+	lbz	r3, HSTATE_HWTHREAD_REQ(r13)
+	cmpwi	r3, 0
+	bne	53f
+	HMT_MEDIUM
+	li	r0, KVM_HWTHREAD_IN_KERNEL
 	stb	r0, HSTATE_HWTHREAD_STATE(r13)
-kvm_do_nap:
-	/* Clear the runlatch bit before napping */
-	mfspr	r2, SPRN_CTRLF
-	clrrdi	r2, r2, 1
-	mtspr	SPRN_CTRLT, r2
-
+	/* need to recheck hwthread_req after a barrier, to avoid race */
+	sync
+	lbz	r3, HSTATE_HWTHREAD_REQ(r13)
+	cmpwi	r3, 0
+	bne	54f
+/*
+ * We jump to power7_wakeup_loss, which will return to the caller
+ * of power7_nap in the powernv cpu offline loop.  The value we
+ * put in r3 becomes the return value for power7_nap.
+ */
 	li	r3, LPCR_PECE0
 	mfspr	r4, SPRN_LPCR
 	rlwimi	r4, r3, 0, LPCR_PECE0 | LPCR_PECE1
 	mtspr	SPRN_LPCR, r4
-	isync
-	std	r0, HSTATE_SCRATCH0(r13)
-	ptesync
-	ld	r0, HSTATE_SCRATCH0(r13)
-1:	cmpd	r0, r0
-	bne	1b
-	nap
-	b	.
+	li	r3, 0
+	b	power7_wakeup_loss
+
+53:	HMT_LOW
+	ld	r4, HSTATE_KVM_VCPU(r13)
+	cmpdi	r4, 0
+	beq	kvm_no_guest
+	HMT_MEDIUM
+	b	kvm_secondary_got_guest
+
+54:	li	r0, KVM_HWTHREAD_IN_KVM
+	stb	r0, HSTATE_HWTHREAD_STATE(r13)
+	b	kvm_no_guest
 
 /******************************************************************************
  *                                                                            *
···
 	 * occurs, with PECE1, PECE0 and PECEDP set in LPCR. Also clear the
 	 * runlatch bit before napping.
 	 */
+kvm_do_nap:
 	mfspr	r2, SPRN_CTRLF
 	clrrdi	r2, r2, 1
 	mtspr	SPRN_CTRLT, r2

arch/powerpc/kvm/e500.c

···
 	unsigned long sid;
 	int ret = -1;
 
-	sid = ++(__get_cpu_var(pcpu_last_used_sid));
+	sid = __this_cpu_inc_return(pcpu_last_used_sid);
 	if (sid < NUM_TIDS) {
-		__get_cpu_var(pcpu_sids).entry[sid] = entry;
+		__this_cpu_write(pcpu_sids)entry[sid], entry);
 		entry->val = sid;
-		entry->pentry = &__get_cpu_var(pcpu_sids).entry[sid];
+		entry->pentry = this_cpu_ptr(&pcpu_sids.entry[sid]);
 		ret = sid;
 	}
 
···
 static inline int local_sid_lookup(struct id *entry)
 {
 	if (entry && entry->val != 0 &&
-	    __get_cpu_var(pcpu_sids).entry[entry->val] == entry &&
-	    entry->pentry == &__get_cpu_var(pcpu_sids).entry[entry->val])
+	    __this_cpu_read(pcpu_sids.entry[entry->val]) == entry &&
+	    entry->pentry == this_cpu_ptr(&pcpu_sids.entry[entry->val]))
 		return entry->val;
 	return -1;
 }
···
 /* Invalidate all id mappings on local core -- call with preempt disabled */
 static inline void local_sid_destroy_all(void)
 {
-	__get_cpu_var(pcpu_last_used_sid) = 0;
-	memset(&__get_cpu_var(pcpu_sids), 0, sizeof(__get_cpu_var(pcpu_sids)));
+	__this_cpu_write(pcpu_last_used_sid, 0);
+	memset(this_cpu_ptr(&pcpu_sids), 0, sizeof(pcpu_sids));
 }
 
 static void *kvmppc_e500_id_table_alloc(struct kvmppc_vcpu_e500 *vcpu_e500)

arch/powerpc/kvm/e500mc.c

···
 	mtspr(SPRN_GESR, vcpu->arch.shared->esr);
 
 	if (vcpu->arch.oldpir != mfspr(SPRN_PIR) ||
-	    __get_cpu_var(last_vcpu_of_lpid)[get_lpid(vcpu)] != vcpu) {
+	    __this_cpu_read(last_vcpu_of_lpid[get_lpid(vcpu)]) != vcpu) {
 		kvmppc_e500_tlbil_all(vcpu_e500);
-		__get_cpu_var(last_vcpu_of_lpid)[get_lpid(vcpu)] = vcpu;
+		__this_cpu_write(last_vcpu_of_lpid[get_lpid(vcpu)], vcpu);
 	}
 }
 

arch/powerpc/lib/Makefile

···
 obj-y			:= string.o alloc.o \
 			   crtsavres.o ppc_ksyms.o
 obj-$(CONFIG_PPC32)	+= div64.o copy_32.o
-obj-$(CONFIG_HAS_IOMEM)	+= devres.o
 
 obj-$(CONFIG_PPC64)	+= copypage_64.o copyuser_64.o \
 			   usercopy_64.o mem_64.o string.o \

arch/powerpc/lib/alloc.c

···
 	if (mem_init_done)
 		p = kzalloc(size, mask);
 	else {
-		p = alloc_bootmem(size);
-		if (p)
-			memset(p, 0, size);
+		p = memblock_virt_alloc(size, 0);
 	}
 	return p;
 }

arch/powerpc/lib/devres.c

···
-/*
- * Copyright (C) 2008 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/device.h>	/* devres_*(), devm_ioremap_release() */
-#include <linux/gfp.h>
-#include <linux/io.h>		/* ioremap_prot() */
-#include <linux/export.h>	/* EXPORT_SYMBOL() */
-
-/**
- * devm_ioremap_prot - Managed ioremap_prot()
- * @dev: Generic device to remap IO address for
- * @offset: BUS offset to map
- * @size: Size of map
- * @flags: Page flags
- *
- * Managed ioremap_prot().  Map is automatically unmapped on driver
- * detach.
- */
-void __iomem *devm_ioremap_prot(struct device *dev, resource_size_t offset,
-				 size_t size, unsigned long flags)
-{
-	void __iomem **ptr, *addr;
-
-	ptr = devres_alloc(devm_ioremap_release, sizeof(*ptr), GFP_KERNEL);
-	if (!ptr)
-		return NULL;
-
-	addr = ioremap_prot(offset, size, flags);
-	if (addr) {
-		*ptr = addr;
-		devres_add(dev, ptr);
-	} else
-		devres_free(ptr);
-
-	return addr;
-}
-EXPORT_SYMBOL(devm_ioremap_prot);

arch/powerpc/lib/sstep.c

···
 		}
 		goto ldst_done;
 
+#ifdef CONFIG_PPC_FPU
 	case LOAD_FP:
 		if (regs->msr & MSR_LE)
 			return 0;
···
 		else
 			err = do_fp_load(op.reg, do_lfd, op.ea, size, regs);
 		goto ldst_done;
-
+#endif
 #ifdef CONFIG_ALTIVEC
 	case LOAD_VMX:
 		if (regs->msr & MSR_LE)
···
 		err = write_mem(op.val, op.ea, size, regs);
 		goto ldst_done;
 
+#ifdef CONFIG_PPC_FPU
 	case STORE_FP:
 		if (regs->msr & MSR_LE)
 			return 0;
···
 		else
 			err = do_fp_store(op.reg, do_stfd, op.ea, size, regs);
 		goto ldst_done;
-
+#endif
 #ifdef CONFIG_ALTIVEC
 	case STORE_VMX:
 		if (regs->msr & MSR_LE)

arch/powerpc/mm/Makefile

···
 
 ccflags-$(CONFIG_PPC64)	:= $(NO_MINIMAL_TOC)
 
-obj-y				:= fault.o mem.o pgtable.o gup.o mmap.o \
+obj-y				:= fault.o mem.o pgtable.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 \

arch/powerpc/mm/fault.c

···
 #include <asm/tlbflush.h>
 #include <asm/siginfo.h>
 #include <asm/debug.h>
-#include <mm/mmu_decl.h>
 
 #include "icswx.h"
 
···
 		goto bad_area;
 #endif /* CONFIG_6xx */
 #if defined(CONFIG_8xx)
-	/* 8xx sometimes need to load a invalid/non-present TLBs.
-	 * These must be invalidated separately as linux mm don't.
-	 */
-	if (error_code & 0x40000000) /* no translation? */
-		_tlbil_va(address, 0, 0, 0);
-
         /* The MPC8xx seems to always set 0x80000000, which is
          * "undefined".  Of those that can be set, this is the only
          * one which seems bad.

arch/powerpc/mm/gup.c

···
-/*
- * Lockless get_user_pages_fast for powerpc
- *
- * Copyright (C) 2008 Nick Piggin
- * Copyright (C) 2008 Novell Inc.
- */
-#undef DEBUG
-
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/hugetlb.h>
-#include <linux/vmstat.h>
-#include <linux/pagemap.h>
-#include <linux/rwsem.h>
-#include <asm/pgtable.h>
-
-#ifdef __HAVE_ARCH_PTE_SPECIAL
-
-/*
- * The performance critical leaf functions are made noinline otherwise gcc
- * inlines everything into a single function which results in too much
- * register pressure.
- */
-static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	unsigned long mask, result;
-	pte_t *ptep;
-
-	result = _PAGE_PRESENT|_PAGE_USER;
-	if (write)
-		result |= _PAGE_RW;
-	mask = result | _PAGE_SPECIAL;
-
-	ptep = pte_offset_kernel(&pmd, addr);
-	do {
-		pte_t pte = ACCESS_ONCE(*ptep);
-		struct page *page;
-		/*
-		 * Similar to the PMD case, NUMA hinting must take slow path
-		 */
-		if (pte_numa(pte))
-			return 0;
-
-		if ((pte_val(pte) & mask) != result)
-			return 0;
-		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
-		page = pte_page(pte);
-		if (!page_cache_get_speculative(page))
-			return 0;
-		if (unlikely(pte_val(pte) != pte_val(*ptep))) {
-			put_page(page);
-			return 0;
-		}
-		pages[*nr] = page;
-		(*nr)++;
-
-	} while (ptep++, addr += PAGE_SIZE, addr != end);
-
-	return 1;
-}
-
-static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
-		int write, struct page **pages, int *nr)
-{
-	unsigned long next;
-	pmd_t *pmdp;
-
-	pmdp = pmd_offset(&pud, addr);
-	do {
-		pmd_t pmd = ACCESS_ONCE(*pmdp);
-
-		next = pmd_addr_end(addr, end);
-		/*
-		 * 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) || pmd_large(pmd)) {
-			/*
-			 * NUMA hinting faults need to be handled in the GUP
-			 * slowpath for accounting purposes and so that they
-			 * can be serialised against THP migration.
-			 */
-			if (pmd_numa(pmd))
-				return 0;
-
-			if (!gup_hugepte((pte_t *)pmdp, PMD_SIZE, addr, next,
-					 write, pages, nr))
-				return 0;
-		} else if (is_hugepd(pmdp)) {
-			if (!gup_hugepd((hugepd_t *)pmdp, PMD_SHIFT,
-					addr, next, write, pages, nr))
-				return 0;
-		} else if (!gup_pte_range(pmd, addr, next, write, pages, nr))
-			return 0;
-	} while (pmdp++, addr = next, addr != end);
-
-	return 1;
-}
-
-static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
-		int write, struct page **pages, int *nr)
-{
-	unsigned long next;
-	pud_t *pudp;
-
-	pudp = pud_offset(&pgd, addr);
-	do {
-		pud_t pud = ACCESS_ONCE(*pudp);
-
-		next = pud_addr_end(addr, end);
-		if (pud_none(pud))
-			return 0;
-		if (pud_huge(pud)) {
-			if (!gup_hugepte((pte_t *)pudp, PUD_SIZE, addr, next,
-					 write, pages, nr))
-				return 0;
-		} else if (is_hugepd(pudp)) {
-			if (!gup_hugepd((hugepd_t *)pudp, PUD_SHIFT,
-					addr, next, write, pages, nr))
-				return 0;
-		} else if (!gup_pmd_range(pud, addr, next, write, pages, nr))
-			return 0;
-	} while (pudp++, addr = next, addr != end);
-
-	return 1;
-}
-
-int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
-			  struct page **pages)
-{
-	struct mm_struct *mm = current->mm;
-	unsigned long addr, len, end;
-	unsigned long next;
-	unsigned long flags;
-	pgd_t *pgdp;
-	int nr = 0;
-
-	pr_devel("%s(%lx,%x,%s)\n", __func__, start, nr_pages, write ? "write" : "read");
-
-	start &= PAGE_MASK;
-	addr = start;
-	len = (unsigned long) nr_pages << PAGE_SHIFT;
-	end = start + len;
-
-	if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ,
-					start, len)))
-		return 0;
-
-	pr_devel("  aligned: %lx .. %lx\n", start, end);
-
-	/*
-	 * XXX: batch / limit 'nr', to avoid large irq off latency
-	 * needs some instrumenting to determine the common sizes used by
-	 * important workloads (eg. DB2), and whether limiting the batch size
-	 * will decrease performance.
-	 *
-	 * It seems like we're in the clear for the moment. Direct-IO is
-	 * the main guy that batches up lots of get_user_pages, and even
-	 * they are limited to 64-at-a-time which is not so many.
-	 */
-	/*
-	 * This doesn't prevent pagetable teardown, but does prevent
-	 * the pagetables from being freed on powerpc.
-	 *
-	 * So long as we atomically load page table pointers versus teardown,
-	 * we can follow the address down to the the page and take a ref on it.
-	 */
-	local_irq_save(flags);
-
-	pgdp = pgd_offset(mm, addr);
-	do {
-		pgd_t pgd = ACCESS_ONCE(*pgdp);
-
-		pr_devel("  %016lx: normal pgd %p\n", addr,
-			 (void *)pgd_val(pgd));
-		next = pgd_addr_end(addr, end);
-		if (pgd_none(pgd))
-			break;
-		if (pgd_huge(pgd)) {
-			if (!gup_hugepte((pte_t *)pgdp, PGDIR_SIZE, addr, next,
-					 write, pages, &nr))
-				break;
-		} else if (is_hugepd(pgdp)) {
-			if (!gup_hugepd((hugepd_t *)pgdp, PGDIR_SHIFT,
-					addr, next, write, pages, &nr))
-				break;
-		} else if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
-			break;
-	} while (pgdp++, addr = next, addr != end);
-
-	local_irq_restore(flags);
-
-	return nr;
-}
-
-int get_user_pages_fast(unsigned long start, int nr_pages, int write,
-			struct page **pages)
-{
-	struct mm_struct *mm = current->mm;
-	int nr, ret;
-
-	start &= PAGE_MASK;
-	nr = __get_user_pages_fast(start, nr_pages, write, pages);
-	ret = nr;
-
-	if (nr < nr_pages) {
-		pr_devel("  slow path ! nr = %d\n", nr);
-
-		/* Try to get the remaining pages with get_user_pages */
-		start += nr << PAGE_SHIFT;
-		pages += nr;
-
-		down_read(&mm->mmap_sem);
-		ret = get_user_pages(current, mm, start,
-				     nr_pages - nr, write, 0, pages, NULL);
-		up_read(&mm->mmap_sem);
-
-		/* Have to be a bit careful with return values */
-		if (nr > 0) {
-			if (ret < 0)
-				ret = nr;
-			else
-				ret += nr;
-		}
-	}
-
-	return ret;
-}
-
-#endif /* __HAVE_ARCH_PTE_SPECIAL */

arch/powerpc/mm/hash_low_64.S

···
 
 /*
  * _hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
- *		 pte_t *ptep, unsigned long trap, int local, int ssize)
+ *		 pte_t *ptep, unsigned long trap, unsigned long flags,
+ *		 int ssize)
  *
  * Adds a 4K page to the hash table in a segment of 4K pages only
  */
···
 	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 */
+	ld	r9,STK_PARAM(R8)(r1)	/* get "flags" param */
 .globl htab_call_hpte_updatepp
 htab_call_hpte_updatepp:
 	bl	.			/* Patched by htab_finish_init() */
···
  *****************************************************************************/
 
 /* _hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
- *		 pte_t *ptep, unsigned long trap, int local, int ssize,
- *		 int subpg_prot)
+ *		 pte_t *ptep, unsigned long trap, unsigned local flags,
+ *		 int ssize, int subpg_prot)
  */
 
 /*
···
 	andis.	r0,r31,_PAGE_4K_PFN@h
 	srdi	r5,r31,PTE_RPN_SHIFT
 	bne-	htab_special_pfn
-	sldi	r5,r5,PAGE_SHIFT-HW_PAGE_SHIFT
+	sldi	r5,r5,PAGE_FACTOR
 	add	r5,r5,r25
 htab_special_pfn:
 	sldi	r5,r5,HW_PAGE_SHIFT
···
 	andis.	r0,r31,_PAGE_4K_PFN@h
 	srdi	r5,r31,PTE_RPN_SHIFT
 	bne-	3f
-	sldi	r5,r5,PAGE_SHIFT-HW_PAGE_SHIFT
+	sldi	r5,r5,PAGE_FACTOR
 	add	r5,r5,r25
 3:	sldi	r5,r5,HW_PAGE_SHIFT
 
···
 	li	r5,0			/* PTE.hidx */
 	li	r6,MMU_PAGE_64K		/* psize */
 	ld	r7,STK_PARAM(R9)(r1)	/* ssize */
-	ld	r8,STK_PARAM(R8)(r1)	/* local */
+	ld	r8,STK_PARAM(R8)(r1)	/* flags */
 	bl	flush_hash_page
 	/* Clear out _PAGE_HPTE_SUB bits in the new linux PTE */
 	lis	r0,_PAGE_HPTE_SUB@h
···
 	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 */
+	ld	r9,STK_PARAM(R8)(r1)	/* get "flags" param */
 .globl htab_call_hpte_updatepp
 htab_call_hpte_updatepp:
 	bl	.			/* patched by htab_finish_init() */
···
 	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 */
+	ld	r9,STK_PARAM(R8)(r1)	/* get "flags" param */
 .globl ht64_call_hpte_updatepp
 ht64_call_hpte_updatepp:
 	bl	.			/* patched by htab_finish_init() */

arch/powerpc/mm/hash_native_64.c

···
 
 static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 				 unsigned long vpn, int bpsize,
-				 int apsize, int ssize, int local)
+				 int apsize, int ssize, unsigned long flags)
 {
 	struct hash_pte *hptep = htab_address + slot;
 	unsigned long hpte_v, want_v;
-	int ret = 0;
+	int ret = 0, local = 0;
 
 	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 = be64_to_cpu(hptep->v);
 	/*
···
 		DBG_LOW(" -> miss\n");
 		ret = -1;
 	} else {
-		DBG_LOW(" -> hit\n");
-		/* Update the HPTE */
-		hptep->r = cpu_to_be64((be64_to_cpu(hptep->r) & ~(HPTE_R_PP | HPTE_R_N)) |
-			(newpp & (HPTE_R_PP | HPTE_R_N | HPTE_R_C)));
+		native_lock_hpte(hptep);
+		/* recheck with locks held */
+		hpte_v = be64_to_cpu(hptep->v);
+		if (unlikely(!HPTE_V_COMPARE(hpte_v, want_v) ||
+			     !(hpte_v & HPTE_V_VALID))) {
+			ret = -1;
+		} else {
+			DBG_LOW(" -> hit\n");
+			/* Update the HPTE */
+			hptep->r = cpu_to_be64((be64_to_cpu(hptep->r) &
+						~(HPTE_R_PP | HPTE_R_N)) |
+					       (newpp & (HPTE_R_PP | HPTE_R_N |
+							 HPTE_R_C)));
+		}
+		native_unlock_hpte(hptep);
 	}
-	native_unlock_hpte(hptep);
 
-	/* Ensure it is out of the tlb too. */
-	tlbie(vpn, bpsize, apsize, ssize, local);
+	if (flags & HPTE_LOCAL_UPDATE)
+		local = 1;
+	/*
+	 * Ensure it is out of the tlb too if it is not a nohpte fault
+	 */
+	if (!(flags & HPTE_NOHPTE_UPDATE))
+		tlbie(vpn, bpsize, apsize, ssize, local);
 
 	return ret;
 }
···
 static void native_hugepage_invalidate(unsigned long vsid,
 				       unsigned long addr,
 				       unsigned char *hpte_slot_array,
-				       int psize, int ssize)
+				       int psize, int ssize, int local)
 {
 	int i;
 	struct hash_pte *hptep;
···
 		 * instruction compares entry_VA in tlb with the VA specified
 		 * here
 		 */
-		tlbie(vpn, psize, actual_psize, ssize, 0);
+		tlbie(vpn, psize, actual_psize, ssize, local);
 	}
 	local_irq_restore(flags);
 }
···
 	unsigned long want_v;
 	unsigned long flags;
 	real_pte_t pte;
-	struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch);
+	struct ppc64_tlb_batch *batch = this_cpu_ptr(&ppc64_tlb_batch);
 	unsigned long psize = batch->psize;
 	int ssize = batch->ssize;
 	int i;

arch/powerpc/mm/hash_utils_64.c

···
  * -1 - critical hash insertion error
  * -2 - access not permitted by subpage protection mechanism
  */
-int hash_page_mm(struct mm_struct *mm, unsigned long ea, unsigned long access, unsigned long trap)
+int hash_page_mm(struct mm_struct *mm, unsigned long ea,
+		 unsigned long access, unsigned long trap,
+		 unsigned long flags)
 {
 	enum ctx_state prev_state = exception_enter();
 	pgd_t *pgdir;
···
 	pte_t *ptep;
 	unsigned hugeshift;
 	const struct cpumask *tmp;
-	int rc, user_region = 0, local = 0;
+	int rc, user_region = 0;
 	int psize, ssize;
 
 	DBG_LOW("hash_page(ea=%016lx, access=%lx, trap=%lx\n",
···
 	/* Check CPU locality */
 	tmp = cpumask_of(smp_processor_id());
 	if (user_region && cpumask_equal(mm_cpumask(mm), tmp))
-		local = 1;
+		flags |= HPTE_LOCAL_UPDATE;
 
 #ifndef CONFIG_PPC_64K_PAGES
 	/* If we use 4K pages and our psize is not 4K, then we might
···
 	if (hugeshift) {
 		if (pmd_trans_huge(*(pmd_t *)ptep))
 			rc = __hash_page_thp(ea, access, vsid, (pmd_t *)ptep,
-					     trap, local, ssize, psize);
+					     trap, flags, ssize, psize);
 #ifdef CONFIG_HUGETLB_PAGE
 		else
 			rc = __hash_page_huge(ea, access, vsid, ptep, trap,
-					      local, ssize, hugeshift, psize);
+					      flags, ssize, hugeshift, psize);
 #else
 		else {
 			/*
···
 
 #ifdef CONFIG_PPC_HAS_HASH_64K
 	if (psize == MMU_PAGE_64K)
-		rc = __hash_page_64K(ea, access, vsid, ptep, trap, local, ssize);
+		rc = __hash_page_64K(ea, access, vsid, ptep, trap,
+				     flags, ssize);
 	else
 #endif /* CONFIG_PPC_HAS_HASH_64K */
 	{
···
 			rc = -2;
 		else
 			rc = __hash_page_4K(ea, access, vsid, ptep, trap,
-					    local, ssize, spp);
+					    flags, ssize, spp);
 	}
 
 	/* Dump some info in case of hash insertion failure, they should
···
 }
 EXPORT_SYMBOL_GPL(hash_page_mm);
 
-int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
+int hash_page(unsigned long ea, unsigned long access, unsigned long trap,
+	      unsigned long dsisr)
 {
+	unsigned long flags = 0;
 	struct mm_struct *mm = current->mm;
 
 	if (REGION_ID(ea) == VMALLOC_REGION_ID)
 		mm = &init_mm;
 
-	return hash_page_mm(mm, ea, access, trap);
+	if (dsisr & DSISR_NOHPTE)
+		flags |= HPTE_NOHPTE_UPDATE;
+
+	return hash_page_mm(mm, ea, access, trap, flags);
 }
 EXPORT_SYMBOL_GPL(hash_page);
 
···
 	pgd_t *pgdir;
 	pte_t *ptep;
 	unsigned long flags;
-	int rc, ssize, local = 0;
+	int rc, ssize, update_flags = 0;
 
 	BUG_ON(REGION_ID(ea) != USER_REGION_ID);
 
···
 
 	/* Is that local to this CPU ? */
 	if (cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())))
-		local = 1;
+		update_flags |= HPTE_LOCAL_UPDATE;
 
 	/* Hash it in */
 #ifdef CONFIG_PPC_HAS_HASH_64K
 	if (mm->context.user_psize == MMU_PAGE_64K)
-		rc = __hash_page_64K(ea, access, vsid, ptep, trap, local, ssize);
+		rc = __hash_page_64K(ea, access, vsid, ptep, trap,
+				     update_flags, ssize);
 	else
 #endif /* CONFIG_PPC_HAS_HASH_64K */
-		rc = __hash_page_4K(ea, access, vsid, ptep, trap, local, ssize,
-				    subpage_protection(mm, ea));
+		rc = __hash_page_4K(ea, access, vsid, ptep, trap, update_flags,
+				    ssize, subpage_protection(mm, ea));
 
 	/* Dump some info in case of hash insertion failure, they should
 	 * never happen so it is really useful to know if/when they do
···
  *          do not forget to update the assembly call site !
  */
 void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize, int ssize,
-		     int local)
+		     unsigned long flags)
 {
 	unsigned long hash, index, shift, hidx, slot;
+	int local = flags & HPTE_LOCAL_UPDATE;
 
 	DBG_LOW("flush_hash_page(vpn=%016lx)\n", vpn);
 	pte_iterate_hashed_subpages(pte, psize, vpn, index, shift) {
···
 #endif
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+void flush_hash_hugepage(unsigned long vsid, unsigned long addr,
+			 pmd_t *pmdp, unsigned int psize, int ssize,
+			 unsigned long flags)
+{
+	int i, max_hpte_count, valid;
+	unsigned long s_addr;
+	unsigned char *hpte_slot_array;
+	unsigned long hidx, shift, vpn, hash, slot;
+	int local = flags & HPTE_LOCAL_UPDATE;
+
+	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;
+
+	if (ppc_md.hugepage_invalidate) {
+		ppc_md.hugepage_invalidate(vsid, s_addr, hpte_slot_array,
+					   psize, ssize, local);
+		goto tm_abort;
+	}
+	/*
+	 * 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));
+		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, local);
+	}
+tm_abort:
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	/* Transactions are not aborted by tlbiel, only tlbie.
+	 * Without, syncing a page back to a block device w/ PIO could pick up
+	 * transactional data (bad!) so we force an abort here.  Before the
+	 * sync the page will be made read-only, which will flush_hash_page.
+	 * BIG ISSUE here: if the kernel uses a page from userspace without
+	 * unmapping it first, it may see the speculated version.
+	 */
+	if (local && cpu_has_feature(CPU_FTR_TM) &&
+	    current->thread.regs &&
+	    MSR_TM_ACTIVE(current->thread.regs->msr)) {
+		tm_enable();
+		tm_abort(TM_CAUSE_TLBI);
+	}
+#endif
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
 void flush_hash_range(unsigned long number, int local)
 {
 	if (ppc_md.flush_hash_range)
···
 	else {
 		int i;
 		struct ppc64_tlb_batch *batch =
-			&__get_cpu_var(ppc64_tlb_batch);
+			this_cpu_ptr(&ppc64_tlb_batch);
 
 		for (i = 0; i < number; i++)
 			flush_hash_page(batch->vpn[i], batch->pte[i],

arch/powerpc/mm/hugepage-hash64.c

···
 #include <linux/mm.h>
 #include <asm/machdep.h>
 
-static void invalidate_old_hpte(unsigned long vsid, unsigned long addr,
-				pmd_t *pmdp, unsigned int psize, int ssize)
-{
-	int i, max_hpte_count, valid;
-	unsigned long s_addr;
-	unsigned char *hpte_slot_array;
-	unsigned long hidx, shift, vpn, hash, slot;
-
-	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;
-
-	if (ppc_md.hugepage_invalidate)
-		return ppc_md.hugepage_invalidate(vsid, s_addr, hpte_slot_array,
-						  psize, ssize);
-	/*
-	 * 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));
-		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);
-	}
-}
-
-
 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)
+		    pmd_t *pmdp, unsigned long trap, unsigned long flags,
+		    int ssize, unsigned int psize)
 {
 	unsigned int index, valid;
 	unsigned char *hpte_slot_array;
···
 		 * hash page table entries.
 		 */
 		if ((old_pmd & _PAGE_HASHPTE) && !(old_pmd & _PAGE_COMBO))
-			invalidate_old_hpte(vsid, ea, pmdp, MMU_PAGE_64K, ssize);
+			flush_hash_hugepage(vsid, ea, pmdp, MMU_PAGE_64K,
+					    ssize, flags);
 	}
 
 	valid = hpte_valid(hpte_slot_array, index);
···
 		slot += hidx & _PTEIDX_GROUP_IX;
 
 		ret = ppc_md.hpte_updatepp(slot, rflags, vpn,
-					   psize, lpsize, ssize, local);
+					   psize, lpsize, ssize, flags);
 		/*
 		 * We failed to update, try to insert a new entry.
 		 */

arch/powerpc/mm/hugetlbpage-book3e.c

···
 
 	ncams = mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY;
 
-	index = __get_cpu_var(next_tlbcam_idx);
+	index = this_cpu_read(next_tlbcam_idx);
 
 	/* Just round-robin the entries and wrap when we hit the end */
 	if (unlikely(index == ncams - 1))
-		__get_cpu_var(next_tlbcam_idx) = tlbcam_index;
+		__this_cpu_write(next_tlbcam_idx, tlbcam_index);
 	else
-		__get_cpu_var(next_tlbcam_idx)++;
+		__this_cpu_inc(next_tlbcam_idx);
 
 	return index;
 }

arch/powerpc/mm/hugetlbpage-hash64.c

···
 				  unsigned long vflags, int psize, int ssize);
 
 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)
+		     pte_t *ptep, unsigned long trap, unsigned long flags,
+		     int ssize, unsigned int shift, unsigned int mmu_psize)
 {
 	unsigned long vpn;
 	unsigned long old_pte, new_pte;
···
 		slot += (old_pte & _PAGE_F_GIX) >> 12;
 
 		if (ppc_md.hpte_updatepp(slot, rflags, vpn, mmu_psize,
-					 mmu_psize, ssize, local) == -1)
+					 mmu_psize, ssize, flags) == -1)
 			old_pte &= ~_PAGE_HPTEFLAGS;
 	}
 

arch/powerpc/mm/hugetlbpage.c

···
 /*
  * We have PGD_INDEX_SIZ = 12 and PTE_INDEX_SIZE = 8, so that we can have
  * 16GB hugepage pte in PGD and 16MB hugepage pte at PMD;
+ *
+ * Defined in such a way that we can optimize away code block at build time
+ * if CONFIG_HUGETLB_PAGE=n.
  */
 int pmd_huge(pmd_t pmd)
 {
···
 	if (hugepd_none(*hpdp) && __hugepte_alloc(mm, hpdp, addr, pdshift, pshift))
 		return NULL;
 
-	return hugepte_offset(hpdp, addr, pdshift);
+	return hugepte_offset(*hpdp, addr, pdshift);
 }
 
 #else
···
 	if (hugepd_none(*hpdp) && __hugepte_alloc(mm, hpdp, addr, pdshift, pshift))
 		return NULL;
 
-	return hugepte_offset(hpdp, addr, pdshift);
+	return hugepte_offset(*hpdp, addr, pdshift);
 }
 #endif
 
 #ifdef CONFIG_PPC_FSL_BOOK3E
 /* Build list of addresses of gigantic pages.  This function is used in early
- * boot before the buddy or bootmem allocator is setup.
+ * boot before the buddy allocator is setup.
  */
 void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages)
 {
···
 	 * If gpages can be in highmem we can't use the trick of storing the
 	 * data structure in the page; allocate space for this
 	 */
-	m = alloc_bootmem(sizeof(struct huge_bootmem_page));
+	m = memblock_virt_alloc(sizeof(struct huge_bootmem_page), 0);
 	m->phys = gpage_freearray[idx].gpage_list[--nr_gpages];
 #else
 	m = phys_to_virt(gpage_freearray[idx].gpage_list[--nr_gpages]);
···
 		if (size != 0) {
 			if (sscanf(val, "%lu", &npages) <= 0)
 				npages = 0;
+			if (npages > MAX_NUMBER_GPAGES) {
+				pr_warn("MMU: %lu pages requested for page "
+					"size %llu KB, limiting to "
+					__stringify(MAX_NUMBER_GPAGES) "\n",
+					npages, size / 1024);
+				npages = MAX_NUMBER_GPAGES;
+			}
 			gpage_npages[shift_to_mmu_psize(__ffs(size))] = npages;
 			size = 0;
 		}
···
 #else /* !PPC_FSL_BOOK3E */
 
 /* Build list of addresses of gigantic pages.  This function is used in early
- * boot before the buddy or bootmem allocator is setup.
+ * boot before the buddy allocator is setup.
  */
 void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages)
 {
···
 {
 	struct hugepd_freelist **batchp;
 
-	batchp = &get_cpu_var(hugepd_freelist_cur);
+	batchp = this_cpu_ptr(&hugepd_freelist_cur);
 
 	if (atomic_read(&tlb->mm->mm_users) < 2 ||
 	    cpumask_equal(mm_cpumask(tlb->mm),
···
 	do {
 		pmd = pmd_offset(pud, addr);
 		next = pmd_addr_end(addr, end);
-		if (!is_hugepd(pmd)) {
+		if (!is_hugepd(__hugepd(pmd_val(*pmd)))) {
 			/*
 			 * if it is not hugepd pointer, we should already find
 			 * it cleared.
···
 	do {
 		pud = pud_offset(pgd, addr);
 		next = pud_addr_end(addr, end);
-		if (!is_hugepd(pud)) {
+		if (!is_hugepd(__hugepd(pud_val(*pud)))) {
 			if (pud_none_or_clear_bad(pud))
 				continue;
 			hugetlb_free_pmd_range(tlb, pud, addr, next, floor,
···
 	do {
 		next = pgd_addr_end(addr, end);
 		pgd = pgd_offset(tlb->mm, addr);
-		if (!is_hugepd(pgd)) {
+		if (!is_hugepd(__hugepd(pgd_val(*pgd)))) {
 			if (pgd_none_or_clear_bad(pgd))
 				continue;
 			hugetlb_free_pud_range(tlb, pgd, addr, next, floor, ceiling);
···
 	return (__boundary - 1 < end - 1) ? __boundary : end;
 }
 
-int gup_hugepd(hugepd_t *hugepd, unsigned pdshift,
-	       unsigned long addr, unsigned long end,
-	       int write, struct page **pages, int *nr)
+int gup_huge_pd(hugepd_t hugepd, unsigned long addr, unsigned pdshift,
+		unsigned long end, int write, struct page **pages, int *nr)
 {
 	pte_t *ptep;
-	unsigned long sz = 1UL << hugepd_shift(*hugepd);
+	unsigned long sz = 1UL << hugepd_shift(hugepd);
 	unsigned long next;
 
 	ptep = hugepte_offset(hugepd, addr, pdshift);
···
 	else if (pgd_huge(pgd)) {
 		ret_pte = (pte_t *) pgdp;
 		goto out;
-	} else if (is_hugepd(&pgd))
+	} else if (is_hugepd(__hugepd(pgd_val(pgd))))
 		hpdp = (hugepd_t *)&pgd;
 	else {
 		/*
···
 		else if (pud_huge(pud)) {
 			ret_pte = (pte_t *) pudp;
 			goto out;
-		} else if (is_hugepd(&pud))
+		} else if (is_hugepd(__hugepd(pud_val(pud))))
 			hpdp = (hugepd_t *)&pud;
 		else {
 			pdshift = PMD_SHIFT;
···
 			if (pmd_huge(pmd) || pmd_large(pmd)) {
 				ret_pte = (pte_t *) pmdp;
 				goto out;
-			} else if (is_hugepd(&pmd))
+			} else if (is_hugepd(__hugepd(pmd_val(pmd))))
 				hpdp = (hugepd_t *)&pmd;
 			else
 				return pte_offset_kernel(&pmd, ea);
···
 	if (!hpdp)
 		return NULL;
 
-	ret_pte = hugepte_offset(hpdp, ea, pdshift);
+	ret_pte = hugepte_offset(*hpdp, ea, pdshift);
 	pdshift = hugepd_shift(*hpdp);
 out:
 	if (shift)
···
 
 	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)));

arch/powerpc/mm/init_32.c

···
 #include <linux/mm.h>
 #include <linux/stddef.h>
 #include <linux/init.h>
-#include <linux/bootmem.h>
 #include <linux/highmem.h>
 #include <linux/initrd.h>
 #include <linux/pagemap.h>
···
 
 	/* Shortly after that, the entire linear mapping will be available */
 	memblock_set_current_limit(lowmem_end_addr);
-}
-
-/* This is only called until mem_init is done. */
-void __init *early_get_page(void)
-{
-	if (init_bootmem_done)
-		return alloc_bootmem_pages(PAGE_SIZE);
-	else
-		return __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE));
 }
 
 #ifdef CONFIG_8xx /* No 8xx specific .c file to put that in ... */

arch/powerpc/mm/init_64.c

···
 #include <linux/vmalloc.h>
 #include <linux/init.h>
 #include <linux/delay.h>
-#include <linux/bootmem.h>
 #include <linux/highmem.h>
 #include <linux/idr.h>
 #include <linux/nodemask.h>

arch/powerpc/mm/mem.c

···
 #include <linux/memblock.h>
 #include <linux/hugetlb.h>
 #include <linux/slab.h>
+#include <linux/vmalloc.h>
 
 #include <asm/pgalloc.h>
 #include <asm/prom.h>
···
 #define CPU_FTR_NOEXECUTE	0
 #endif
 
-int init_bootmem_done;
 int mem_init_done;
 unsigned long long memory_limit;
 
···
 
 	zone = page_zone(pfn_to_page(start_pfn));
 	ret = __remove_pages(zone, start_pfn, nr_pages);
-	if (!ret && (ppc_md.remove_memory))
-		ret = ppc_md.remove_memory(start, size);
+	if (ret)
+		return ret;
+
+	/* Remove htab bolted mappings for this section of memory */
+	start = (unsigned long)__va(start);
+	ret = remove_section_mapping(start, start + size);
+
+	/* Ensure all vmalloc mappings are flushed in case they also
+	 * hit that section of memory
+	 */
+	vm_unmap_aliases();
 
 	return ret;
 }
···
 }
 EXPORT_SYMBOL_GPL(walk_system_ram_range);
 
-/*
- * Initialize the bootmem system and give it all the memory we
- * have available.  If we are using highmem, we only put the
- * lowmem into the bootmem system.
- */
 #ifndef CONFIG_NEED_MULTIPLE_NODES
-void __init do_init_bootmem(void)
+void __init initmem_init(void)
 {
-	unsigned long start, bootmap_pages;
-	unsigned long total_pages;
-	struct memblock_region *reg;
-	int boot_mapsize;
-
 	max_low_pfn = max_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT;
-	total_pages = (memblock_end_of_DRAM() - memstart_addr) >> PAGE_SHIFT;
+	min_low_pfn = MEMORY_START >> PAGE_SHIFT;
 #ifdef CONFIG_HIGHMEM
-	total_pages = total_lowmem >> PAGE_SHIFT;
 	max_low_pfn = lowmem_end_addr >> PAGE_SHIFT;
 #endif
-
-	/*
-	 * Find an area to use for the bootmem bitmap.  Calculate the size of
-	 * bitmap required as (Total Memory) / PAGE_SIZE / BITS_PER_BYTE.
-	 * Add 1 additional page in case the address isn't page-aligned.
-	 */
-	bootmap_pages = bootmem_bootmap_pages(total_pages);
-
-	start = memblock_alloc(bootmap_pages << PAGE_SHIFT, PAGE_SIZE);
-
-	min_low_pfn = MEMORY_START >> PAGE_SHIFT;
-	boot_mapsize = init_bootmem_node(NODE_DATA(0), start >> PAGE_SHIFT, min_low_pfn, max_low_pfn);
 
 	/* Place all memblock_regions in the same node and merge contiguous
 	 * memblock_regions
 	 */
 	memblock_set_node(0, (phys_addr_t)ULLONG_MAX, &memblock.memory, 0);
 
-	/* Add all physical memory to the bootmem map, mark each area
-	 * present.
-	 */
-#ifdef CONFIG_HIGHMEM
-	free_bootmem_with_active_regions(0, lowmem_end_addr >> PAGE_SHIFT);
-
-	/* reserve the sections we're already using */
-	for_each_memblock(reserved, reg) {
-		unsigned long top = reg->base + reg->size - 1;
-		if (top < lowmem_end_addr)
-			reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
-		else if (reg->base < lowmem_end_addr) {
-			unsigned long trunc_size = lowmem_end_addr - reg->base;
-			reserve_bootmem(reg->base, trunc_size, BOOTMEM_DEFAULT);
-		}
-	}
-#else
-	free_bootmem_with_active_regions(0, max_pfn);
-
-	/* reserve the sections we're already using */
-	for_each_memblock(reserved, reg)
-		reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
-#endif
 	/* XXX need to clip this if using highmem? */
 	sparse_memory_present_with_active_regions(0);
-
-	init_bootmem_done = 1;
+	sparse_init();
 }
 
 /* mark pages that don't exist as nosave */
···
 	mark_nonram_nosave();
 }
 
-static void __init register_page_bootmem_info(void)
-{
-	int i;
-
-	for_each_online_node(i)
-		register_page_bootmem_info_node(NODE_DATA(i));
-}
-
 void __init mem_init(void)
 {
 	/*
···
 	swiotlb_init(0);
 #endif
 
-	register_page_bootmem_info();
 	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
 	set_max_mapnr(max_pfn);
 	free_all_bootmem();

arch/powerpc/mm/mmu_context_nohash.c

···
 	/*
 	 * Allocate the maps used by context management
 	 */
-	context_map = alloc_bootmem(CTX_MAP_SIZE);
-	context_mm = alloc_bootmem(sizeof(void *) * (last_context + 1));
+	context_map = memblock_virt_alloc(CTX_MAP_SIZE, 0);
+	context_mm = memblock_virt_alloc(sizeof(void *) * (last_context + 1), 0);
 #ifndef CONFIG_SMP
-	stale_map[0] = alloc_bootmem(CTX_MAP_SIZE);
+	stale_map[0] = memblock_virt_alloc(CTX_MAP_SIZE, 0);
 #else
-	stale_map[boot_cpuid] = alloc_bootmem(CTX_MAP_SIZE);
+	stale_map[boot_cpuid] = memblock_virt_alloc(CTX_MAP_SIZE, 0);
 
 	register_cpu_notifier(&mmu_context_cpu_nb);
 #endif

arch/powerpc/mm/numa.c

···
 	return 0;
 }
 
-/*
- * get_node_active_region - Return active region containing pfn
- * Active range returned is empty if none found.
- * @pfn: The page to return the region for
- * @node_ar: Returned set to the active region containing @pfn
- */
-static void __init get_node_active_region(unsigned long pfn,
-					  struct node_active_region *node_ar)
-{
-	unsigned long start_pfn, end_pfn;
-	int i, nid;
-
-	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) {
-		if (pfn >= start_pfn && pfn < end_pfn) {
-			node_ar->nid = nid;
-			node_ar->start_pfn = start_pfn;
-			node_ar->end_pfn = end_pfn;
-			break;
-		}
-	}
-}
-
 static void reset_numa_cpu_lookup_table(void)
 {
 	unsigned int cpu;
···
 	}
 }
 
-/*
- * Allocate some memory, satisfying the memblock or bootmem allocator where
- * required. nid is the preferred node and end is the physical address of
- * the highest address in the node.
- *
- * Returns the virtual address of the memory.
- */
-static void __init *careful_zallocation(int nid, unsigned long size,
-				       unsigned long align,
-				       unsigned long end_pfn)
-{
-	void *ret;
-	int new_nid;
-	unsigned long ret_paddr;
-
-	ret_paddr = __memblock_alloc_base(size, align, end_pfn << PAGE_SHIFT);
-
-	/* retry over all memory */
-	if (!ret_paddr)
-		ret_paddr = __memblock_alloc_base(size, align, memblock_end_of_DRAM());
-
-	if (!ret_paddr)
-		panic("numa.c: cannot allocate %lu bytes for node %d",
-		      size, nid);
-
-	ret = __va(ret_paddr);
-
-	/*
-	 * We initialize the nodes in numeric order: 0, 1, 2...
-	 * and hand over control from the MEMBLOCK allocator to the
-	 * bootmem allocator.  If this function is called for
-	 * node 5, then we know that all nodes <5 are using the
-	 * bootmem allocator instead of the MEMBLOCK allocator.
-	 *
-	 * So, check the nid from which this allocation came
-	 * and double check to see if we need to use bootmem
-	 * instead of the MEMBLOCK.  We don't free the MEMBLOCK memory
-	 * since it would be useless.
-	 */
-	new_nid = early_pfn_to_nid(ret_paddr >> PAGE_SHIFT);
-	if (new_nid < nid) {
-		ret = __alloc_bootmem_node(NODE_DATA(new_nid),
-				size, align, 0);
-
-		dbg("alloc_bootmem %p %lx\n", ret, size);
-	}
-
-	memset(ret, 0, size);
-	return ret;
-}
-
 static struct notifier_block ppc64_numa_nb = {
 	.notifier_call = cpu_numa_callback,
 	.priority = 1 /* Must run before sched domains notifier. */
 };
 
-static void __init mark_reserved_regions_for_nid(int nid)
+/* Initialize NODE_DATA for a node on the local memory */
+static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
 {
-	struct pglist_data *node = NODE_DATA(nid);
-	struct memblock_region *reg;
+	u64 spanned_pages = end_pfn - start_pfn;
+	const size_t nd_size = roundup(sizeof(pg_data_t), SMP_CACHE_BYTES);
+	u64 nd_pa;
+	void *nd;
+	int tnid;
 
-	for_each_memblock(reserved, reg) {
-		unsigned long physbase = reg->base;
-		unsigned long size = reg->size;
-		unsigned long start_pfn = physbase >> PAGE_SHIFT;
-		unsigned long end_pfn = PFN_UP(physbase + size);
-		struct node_active_region node_ar;
-		unsigned long node_end_pfn = pgdat_end_pfn(node);
+	if (spanned_pages)
+		pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
+			nid, start_pfn << PAGE_SHIFT,
+			(end_pfn << PAGE_SHIFT) - 1);
+	else
+		pr_info("Initmem setup node %d\n", nid);
 
-		/*
-		 * Check to make sure that this memblock.reserved area is
-		 * within the bounds of the node that we care about.
-		 * Checking the nid of the start and end points is not
-		 * sufficient because the reserved area could span the
-		 * entire node.
-		 */
-		if (end_pfn <= node->node_start_pfn ||
-		    start_pfn >= node_end_pfn)
-			continue;
+	nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
+	nd = __va(nd_pa);
 
-		get_node_active_region(start_pfn, &node_ar);
-		while (start_pfn < end_pfn &&
-			node_ar.start_pfn < node_ar.end_pfn) {
-			unsigned long reserve_size = size;
-			/*
-			 * if reserved region extends past active region
-			 * then trim size to active region
-			 */
-			if (end_pfn > node_ar.end_pfn)
-				reserve_size = (node_ar.end_pfn << PAGE_SHIFT)
-					- physbase;
-			/*
-			 * Only worry about *this* node, others may not
-			 * yet have valid NODE_DATA().
-			 */
-			if (node_ar.nid == nid) {
-				dbg("reserve_bootmem %lx %lx nid=%d\n",
-					physbase, reserve_size, node_ar.nid);
-				reserve_bootmem_node(NODE_DATA(node_ar.nid),
-						physbase, reserve_size,
-						BOOTMEM_DEFAULT);
-			}
-			/*
-			 * if reserved region is contained in the active region
-			 * then done.
-			 */
-			if (end_pfn <= node_ar.end_pfn)
-				break;
+	/* report and initialize */
+	pr_info("  NODE_DATA [mem %#010Lx-%#010Lx]\n",
+		nd_pa, nd_pa + nd_size - 1);
+	tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
+	if (tnid != nid)
+		pr_info("    NODE_DATA(%d) on node %d\n", nid, tnid);
 
-			/*
-			 * reserved region extends past the active region
-			 *   get next active region that contains this
-			 *   reserved region
-			 */
-			start_pfn = node_ar.end_pfn;
-			physbase = start_pfn << PAGE_SHIFT;
-			size = size - reserve_size;
-			get_node_active_region(start_pfn, &node_ar);
-		}
-	}
+	node_data[nid] = nd;
+	memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
+	NODE_DATA(nid)->node_id = nid;
+	NODE_DATA(nid)->node_start_pfn = start_pfn;
+	NODE_DATA(nid)->node_spanned_pages = spanned_pages;
 }
 
-
-void __init do_init_bootmem(void)
+void __init initmem_init(void)
 {
 	int nid, cpu;
 
-	min_low_pfn = 0;
 	max_low_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT;
 	max_pfn = max_low_pfn;
 
···
 	else
 		dump_numa_memory_topology();
 
+	memblock_dump_all();
+
 	for_each_online_node(nid) {
 		unsigned long start_pfn, end_pfn;
-		void *bootmem_vaddr;
-		unsigned long bootmap_pages;
 
 		get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
-
-		/*
-		 * Allocate the node structure node local if possible
-		 *
-		 * Be careful moving this around, as it relies on all
-		 * previous nodes' bootmem to be initialized and have
-		 * all reserved areas marked.
-		 */
-		NODE_DATA(nid) = careful_zallocation(nid,
-					sizeof(struct pglist_data),
-					SMP_CACHE_BYTES, end_pfn);
-
-  		dbg("node %d\n", nid);
-		dbg("NODE_DATA() = %p\n", NODE_DATA(nid));
-
-		NODE_DATA(nid)->bdata = &bootmem_node_data[nid];
-		NODE_DATA(nid)->node_start_pfn = start_pfn;
-		NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn;
-
-		if (NODE_DATA(nid)->node_spanned_pages == 0)
-  			continue;
-
-  		dbg("start_paddr = %lx\n", start_pfn << PAGE_SHIFT);
-  		dbg("end_paddr = %lx\n", end_pfn << PAGE_SHIFT);
-
-		bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn);
-		bootmem_vaddr = careful_zallocation(nid,
-					bootmap_pages << PAGE_SHIFT,
-					PAGE_SIZE, end_pfn);
-
-		dbg("bootmap_vaddr = %p\n", bootmem_vaddr);
-
-		init_bootmem_node(NODE_DATA(nid),
-				  __pa(bootmem_vaddr) >> PAGE_SHIFT,
-				  start_pfn, end_pfn);
-
-		free_bootmem_with_active_regions(nid, end_pfn);
-		/*
-		 * Be very careful about moving this around.  Future
-		 * calls to careful_zallocation() depend on this getting
-		 * done correctly.
-		 */
-		mark_reserved_regions_for_nid(nid);
+		setup_node_data(nid, start_pfn, end_pfn);
 		sparse_memory_present_with_active_regions(nid);
 	}
 
-	init_bootmem_done = 1;
+	sparse_init();
 
-	/*
-	 * Now bootmem is initialised we can create the node to cpumask
-	 * lookup tables and setup the cpu callback to populate them.
-	 */
 	setup_node_to_cpumask_map();
 
 	reset_numa_cpu_lookup_table();

arch/powerpc/mm/pgtable_32.c

···
 {
 	pte_t *pte;
 	extern int mem_init_done;
-	extern void *early_get_page(void);
 
 	if (mem_init_done) {
 		pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
 	} else {
-		pte = (pte_t *)early_get_page();
+		pte = __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE));
 		if (pte)
 			clear_page(pte);
 	}

arch/powerpc/mm/pgtable_64.c

···
 #include <linux/swap.h>
 #include <linux/stddef.h>
 #include <linux/vmalloc.h>
-#include <linux/bootmem.h>
 #include <linux/memblock.h>
 #include <linux/slab.h>
+#include <linux/hugetlb.h>
 
 #include <asm/pgalloc.h>
 #include <asm/page.h>
···
 #include <asm/cputable.h>
 #include <asm/sections.h>
 #include <asm/firmware.h>
+#include <asm/dma.h>
 
 #include "mmu_decl.h"
 
···
 {
 	void *pt;
 
-	if (init_bootmem_done)
-		pt = __alloc_bootmem(size, size, __pa(MAX_DMA_ADDRESS));
-	else
-		pt = __va(memblock_alloc_base(size, size,
-					 __pa(MAX_DMA_ADDRESS)));
+	pt = __va(memblock_alloc_base(size, size, __pa(MAX_DMA_ADDRESS)));
 	memset(pt, 0, size);
 
 	return pt;
···
 							  __pgprot(flags)));
 	} else {
 #ifdef CONFIG_PPC_MMU_NOHASH
-		/* Warning ! This will blow up if bootmem is not initialized
-		 * which our ppc64 code is keen to do that, we'll need to
-		 * fix it and/or be more careful
-		 */
 		pgdp = pgd_offset_k(ea);
 #ifdef PUD_TABLE_SIZE
 		if (pgd_none(*pgdp)) {
···
 EXPORT_SYMBOL(__iounmap);
 EXPORT_SYMBOL(__iounmap_at);
 
+#ifndef __PAGETABLE_PUD_FOLDED
+/* 4 level page table */
+struct page *pgd_page(pgd_t pgd)
+{
+	if (pgd_huge(pgd))
+		return pte_page(pgd_pte(pgd));
+	return virt_to_page(pgd_page_vaddr(pgd));
+}
+#endif
+
+struct page *pud_page(pud_t pud)
+{
+	if (pud_huge(pud))
+		return pte_page(pud_pte(pud));
+	return virt_to_page(pud_page_vaddr(pud));
+}
+
 /*
  * 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))
+	if (pmd_trans_huge(pmd) || pmd_huge(pmd))
 		return pfn_to_page(pmd_pfn(pmd));
-#endif
 	return virt_to_page(pmd_page_vaddr(pmd));
 }
 
···
 void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
 			    pmd_t *pmdp, unsigned long old_pmd)
 {
-	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;
+	int ssize;
+	unsigned int psize;
+	unsigned long vsid;
+	unsigned long flags = 0;
+	const struct cpumask *tmp;
 
 	/* get the base page size,vsid and segment size */
 #ifdef CONFIG_DEBUG_VM
-	psize = get_slice_psize(mm, s_addr);
+	psize = get_slice_psize(mm, addr);
 	BUG_ON(psize == MMU_PAGE_16M);
 #endif
 	if (old_pmd & _PAGE_COMBO)
···
 	else
 		psize = MMU_PAGE_64K;
 
-	if (!is_kernel_addr(s_addr)) {
-		ssize = user_segment_size(s_addr);
-		vsid = get_vsid(mm->context.id, s_addr, ssize);
+	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(s_addr, mmu_kernel_ssize);
+		vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
 		ssize = mmu_kernel_ssize;
 	}
 
-	if (ppc_md.hugepage_invalidate)
-		return ppc_md.hugepage_invalidate(vsid, s_addr,
-						  hpte_slot_array,
-						  psize, ssize);
-	/*
-	 * 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);
+	tmp = cpumask_of(smp_processor_id());
+	if (cpumask_equal(mm_cpumask(mm), tmp))
+		flags |= HPTE_LOCAL_UPDATE;
 
-		/* get the vpn */
-		addr = s_addr + (i * (1ul << shift));
-		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);
-	}
+	return flush_hash_hugepage(vsid, addr, pmdp, psize, ssize, flags);
 }
 
 static pmd_t pmd_set_protbits(pmd_t pmd, pgprot_t pgprot)

arch/powerpc/oprofile/backtrace.c

···
 #include <linux/oprofile.h>
 #include <linux/sched.h>
 #include <asm/processor.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/compat.h>
 #include <asm/oprofile_impl.h>
 
···
 			first_frame = 0;
 		}
 	} else {
+		pagefault_disable();
 #ifdef CONFIG_PPC64
 		if (!is_32bit_task()) {
 			while (depth--) {
···
 					break;
 				first_frame = 0;
 			}
-
+			pagefault_enable();
 			return;
 		}
 #endif
···
 				break;
 			first_frame = 0;
 		}
+		pagefault_enable();
 	}
 }

arch/powerpc/perf/core-book3s.c

···
 
 static void power_pmu_bhrb_enable(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	if (!ppmu->bhrb_nr)
 		return;
···
 
 static void power_pmu_bhrb_disable(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	if (!ppmu->bhrb_nr)
 		return;
···
 	if (!ppmu)
 		return;
 	local_irq_save(flags);
-	cpuhw = &__get_cpu_var(cpu_hw_events);
+	cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	if (!cpuhw->disabled) {
 		/*
···
 		return;
 	local_irq_save(flags);
 
-	cpuhw = &__get_cpu_var(cpu_hw_events);
+	cpuhw = this_cpu_ptr(&cpu_hw_events);
 	if (!cpuhw->disabled)
 		goto out;
 
···
 	 * Add the event to the list (if there is room)
 	 * and check whether the total set is still feasible.
 	 */
-	cpuhw = &__get_cpu_var(cpu_hw_events);
+	cpuhw = this_cpu_ptr(&cpu_hw_events);
 	n0 = cpuhw->n_events;
 	if (n0 >= ppmu->n_counter)
 		goto out;
···
 
 	power_pmu_read(event);
 
-	cpuhw = &__get_cpu_var(cpu_hw_events);
+	cpuhw = this_cpu_ptr(&cpu_hw_events);
 	for (i = 0; i < cpuhw->n_events; ++i) {
 		if (event == cpuhw->event[i]) {
 			while (++i < cpuhw->n_events) {
···
  */
 static void power_pmu_start_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	perf_pmu_disable(pmu);
 	cpuhw->group_flag |= PERF_EVENT_TXN;
···
  */
 static void power_pmu_cancel_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	cpuhw->group_flag &= ~PERF_EVENT_TXN;
 	perf_pmu_enable(pmu);
···
 
 	if (!ppmu)
 		return -EAGAIN;
-	cpuhw = &__get_cpu_var(cpu_hw_events);
+	cpuhw = this_cpu_ptr(&cpu_hw_events);
 	n = cpuhw->n_events;
 	if (check_excludes(cpuhw->event, cpuhw->flags, 0, n))
 		return -EAGAIN;
···
 
 		if (event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK) {
 			struct cpu_hw_events *cpuhw;
-			cpuhw = &__get_cpu_var(cpu_hw_events);
+			cpuhw = this_cpu_ptr(&cpu_hw_events);
 			power_pmu_bhrb_read(cpuhw);
 			data.br_stack = &cpuhw->bhrb_stack;
 		}
···
 static void perf_event_interrupt(struct pt_regs *regs)
 {
 	int i, j;
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 	struct perf_event *event;
 	unsigned long val[8];
 	int found, active;

arch/powerpc/perf/core-fsl-emb.c

···
 	unsigned long flags;
 
 	local_irq_save(flags);
-	cpuhw = &__get_cpu_var(cpu_hw_events);
+	cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	if (!cpuhw->disabled) {
 		cpuhw->disabled = 1;
···
 	unsigned long flags;
 
 	local_irq_save(flags);
-	cpuhw = &__get_cpu_var(cpu_hw_events);
+	cpuhw = this_cpu_ptr(&cpu_hw_events);
 	if (!cpuhw->disabled)
 		goto out;
 
···
 static void perf_event_interrupt(struct pt_regs *regs)
 {
 	int i;
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 	struct perf_event *event;
 	unsigned long val;
 	int found = 0;

arch/powerpc/platforms/44x/ppc476.c

···
 {
 	avr_i2c_client = client;
 	ppc_md.restart = avr_reset_system;
-	ppc_md.power_off = avr_power_off_system;
+	pm_power_off = avr_power_off_system;
 	return 0;
 }
 

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

···
 #include <linux/irq.h>
 #include <linux/of_platform.h>
 #include <linux/fsl-diu-fb.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <sysdev/fsl_soc.h>
 
 #include <asm/cacheflush.h>
···
 	 * and so negatively affect boot time. Instead we reserve the
 	 * already configured frame buffer area so that it won't be
 	 * destroyed. The starting address of the area to reserve and
-	 * also it's length is passed to reserve_bootmem(). It will be
+	 * also it's length is passed to memblock_reserve(). It will be
 	 * freed later on first open of fbdev, when splash image is not
 	 * needed any more.
 	 */
 	if (diu_shared_fb.in_use) {
-		ret = reserve_bootmem(diu_shared_fb.fb_phys,
-				      diu_shared_fb.fb_len,
-				      BOOTMEM_EXCLUSIVE);
+		ret = memblock_reserve(diu_shared_fb.fb_phys,
+				       diu_shared_fb.fb_len);
 		if (ret) {
 			pr_err("%s: reserve bootmem failed\n", __func__);
 			diu_shared_fb.in_use = false;

arch/powerpc/platforms/52xx/efika.c

···
 	DMA_MODE_READ = 0x44;
 	DMA_MODE_WRITE = 0x48;
 
+	pm_power_off = rtas_power_off;
+
 	return 1;
 }
 
···
 	.init_IRQ		= mpc52xx_init_irq,
 	.get_irq		= mpc52xx_get_irq,
 	.restart		= rtas_restart,
-	.power_off		= rtas_power_off,
 	.halt			= rtas_halt,
 	.set_rtc_time		= rtas_set_rtc_time,
 	.get_rtc_time		= rtas_get_rtc_time,

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

···
 	if (ret)
 		goto err;
 
-	/* XXX: this is potentially racy, but there is no lock for ppc_md */
-	if (!ppc_md.power_off) {
+	/* XXX: this is potentially racy, but there is no lock for pm_power_off */
+	if (!pm_power_off) {
 		glob_mcu = mcu;
-		ppc_md.power_off = mcu_power_off;
+		pm_power_off = mcu_power_off;
 		dev_info(&client->dev, "will provide power-off service\n");
 	}
 
···
 	device_remove_file(&client->dev, &dev_attr_status);
 
 	if (glob_mcu == mcu) {
-		ppc_md.power_off = NULL;
+		pm_power_off = NULL;
 		glob_mcu = NULL;
 	}
 

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

···
 
 			ppc_md.get_irq = ehv_pic_get_irq;
 			ppc_md.restart = fsl_hv_restart;
-			ppc_md.power_off = fsl_hv_halt;
+			pm_power_off = fsl_hv_halt;
 			ppc_md.halt = fsl_hv_halt;
 #ifdef CONFIG_SMP
 			/*

arch/powerpc/platforms/85xx/sgy_cts1000.c

···
 
 	/* Register our halt function */
 	ppc_md.halt = gpio_halt_cb;
-	ppc_md.power_off = gpio_halt_cb;
+	pm_power_off = gpio_halt_cb;
 
 	printk(KERN_INFO "gpio-halt: registered GPIO %d (%d trigger, %d"
 	       " irq).\n", gpio, trigger, irq);
···
 		free_irq(irq, halt_node);
 
 		ppc_md.halt = NULL;
-		ppc_md.power_off = NULL;
+		pm_power_off = NULL;
 
 		gpio_free(gpio);
 

arch/powerpc/platforms/8xx/Kconfig

···
-config FADS
-	bool
-
 config CPM1
 	bool
 	select CPM
···
 
 config MPC8XXFADS
 	bool "FADS"
-	select FADS
 
 config MPC86XADS
 	bool "MPC86XADS"

arch/powerpc/platforms/cell/beat_htab.c

···
 				    unsigned long newpp,
 				    unsigned long vpn,
 				    int psize, int apsize,
-				    int ssize, int local)
+				    int ssize, unsigned long flags)
 {
 	unsigned long lpar_rc;
 	u64 dummy0, dummy1;
···
 				       unsigned long newpp,
 				       unsigned long vpn,
 				       int psize, int apsize,
-				       int ssize, int local)
+				       int ssize, unsigned long flags)
 {
 	unsigned long lpar_rc;
 	unsigned long want_v;

arch/powerpc/platforms/cell/celleb_pci.c

···
 #include <linux/pci.h>
 #include <linux/string.h>
 #include <linux/init.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/pci_regs.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
···
 	} else {
 		if (config && *config) {
 			size = 256;
-			free_bootmem(__pa(*config), size);
+			memblock_free(__pa(*config), size);
 		}
 		if (res && *res) {
 			size = sizeof(struct celleb_pci_resource);
-			free_bootmem(__pa(*res), size);
+			memblock_free(__pa(*res), size);
 		}
 	}
 

arch/powerpc/platforms/cell/celleb_scc_epci.c

···
 #include <linux/pci.h>
 #include <linux/init.h>
 #include <linux/pci_regs.h>
-#include <linux/bootmem.h>
 
 #include <asm/io.h>
 #include <asm/irq.h>

arch/powerpc/platforms/cell/celleb_scc_pciex.c

···
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/init.h>
-#include <linux/bootmem.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 

arch/powerpc/platforms/cell/celleb_setup.c

···
 	powerpc_firmware_features |= FW_FEATURE_CELLEB_ALWAYS
 		| FW_FEATURE_BEAT | FW_FEATURE_LPAR;
 	hpte_init_beat_v3();
+	pm_power_off = beat_power_off;
 
 	return 1;
 }
···
 
 	powerpc_firmware_features |= FW_FEATURE_CELLEB_ALWAYS;
 	hpte_init_native();
+	pm_power_off = rtas_power_off;
 
 	return 1;
 }
···
 	.setup_arch		= celleb_setup_arch_beat,
 	.show_cpuinfo		= celleb_show_cpuinfo,
 	.restart		= beat_restart,
-	.power_off		= beat_power_off,
 	.halt			= beat_halt,
 	.get_rtc_time		= beat_get_rtc_time,
 	.set_rtc_time		= beat_set_rtc_time,
···
 	.setup_arch		= celleb_setup_arch_native,
 	.show_cpuinfo		= celleb_show_cpuinfo,
 	.restart		= rtas_restart,
-	.power_off		= rtas_power_off,
 	.halt			= rtas_halt,
 	.get_boot_time		= rtas_get_boot_time,
 	.get_rtc_time		= rtas_get_rtc_time,

arch/powerpc/platforms/cell/interrupt.c

···
 
 static void iic_eoi(struct irq_data *d)
 {
-	struct iic *iic = &__get_cpu_var(cpu_iic);
+	struct iic *iic = this_cpu_ptr(&cpu_iic);
 	out_be64(&iic->regs->prio, iic->eoi_stack[--iic->eoi_ptr]);
 	BUG_ON(iic->eoi_ptr < 0);
 }
···
 	struct iic *iic;
 	unsigned int virq;
 
-	iic = &__get_cpu_var(cpu_iic);
+	iic = this_cpu_ptr(&cpu_iic);
 	*(unsigned long *) &pending =
 		in_be64((u64 __iomem *) &iic->regs->pending_destr);
 	if (!(pending.flags & CBE_IIC_IRQ_VALID))
···
 
 void iic_setup_cpu(void)
 {
-	out_be64(&__get_cpu_var(cpu_iic).regs->prio, 0xff);
+	out_be64(this_cpu_ptr(&cpu_iic.regs->prio), 0xff);
 }
 
 u8 iic_get_target_id(int cpu)

arch/powerpc/platforms/cell/qpace_setup.c

···
 		return 0;
 
 	hpte_init_native();
+	pm_power_off = rtas_power_off;
 
 	return 1;
 }
···
 	.setup_arch		= qpace_setup_arch,
 	.show_cpuinfo		= qpace_show_cpuinfo,
 	.restart		= rtas_restart,
-	.power_off		= rtas_power_off,
 	.halt			= rtas_halt,
 	.get_boot_time		= rtas_get_boot_time,
 	.get_rtc_time		= rtas_get_rtc_time,

arch/powerpc/platforms/cell/setup.c

···
 		return 0;
 
 	hpte_init_native();
+	pm_power_off = rtas_power_off;
 
 	return 1;
 }
···
 	.setup_arch		= cell_setup_arch,
 	.show_cpuinfo		= cell_show_cpuinfo,
 	.restart		= rtas_restart,
-	.power_off		= rtas_power_off,
 	.halt			= rtas_halt,
 	.get_boot_time		= rtas_get_boot_time,
 	.get_rtc_time		= rtas_get_rtc_time,

arch/powerpc/platforms/cell/spu_base.c

···
 	return 0;
 }
 
-extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap); //XXX
+extern int hash_page(unsigned long ea, unsigned long access,
+		     unsigned long trap, unsigned long dsisr); //XXX
 static int __spu_trap_data_map(struct spu *spu, unsigned long ea, u64 dsisr)
 {
 	int ret;
···
 	    (REGION_ID(ea) != USER_REGION_ID)) {
 
 		spin_unlock(&spu->register_lock);
-		ret = hash_page(ea, _PAGE_PRESENT, 0x300);
+		ret = hash_page(ea, _PAGE_PRESENT, 0x300, dsisr);
 		spin_lock(&spu->register_lock);
 
 		if (!ret) {

arch/powerpc/platforms/cell/spufs/fault.c

···
 	access = (_PAGE_PRESENT | _PAGE_USER);
 	access |= (dsisr & MFC_DSISR_ACCESS_PUT) ? _PAGE_RW : 0UL;
 	local_irq_save(flags);
-	ret = hash_page(ea, access, 0x300);
+	ret = hash_page(ea, access, 0x300, dsisr);
 	local_irq_restore(flags);
 
 	/* hashing failed, so try the actual fault handler */

arch/powerpc/platforms/chrp/setup.c

···
 	DMA_MODE_READ = 0x44;
 	DMA_MODE_WRITE = 0x48;
 
+	pm_power_off = rtas_power_off;
+
 	return 1;
 }
 
···
 	.show_cpuinfo		= chrp_show_cpuinfo,
 	.init_IRQ		= chrp_init_IRQ,
 	.restart		= rtas_restart,
-	.power_off		= rtas_power_off,
 	.halt			= rtas_halt,
 	.time_init		= chrp_time_init,
 	.set_rtc_time		= chrp_set_rtc_time,

arch/powerpc/platforms/embedded6xx/gamecube.c

···
 	if (!of_flat_dt_is_compatible(dt_root, "nintendo,gamecube"))
 		return 0;
 
+	pm_power_off = gamecube_power_off;
+
 	return 1;
 }
 
···
 	.probe			= gamecube_probe,
 	.init_early		= gamecube_init_early,
 	.restart		= gamecube_restart,
-	.power_off		= gamecube_power_off,
 	.halt			= gamecube_halt,
 	.init_IRQ		= flipper_pic_probe,
 	.get_irq		= flipper_pic_get_irq,

arch/powerpc/platforms/embedded6xx/linkstation.c

···
 
 	if (!of_flat_dt_is_compatible(root, "linkstation"))
 		return 0;
+
+	pm_power_off = linkstation_power_off;
+
 	return 1;
 }
 
···
 	.show_cpuinfo 		= linkstation_show_cpuinfo,
 	.get_irq 		= mpic_get_irq,
 	.restart 		= linkstation_restart,
-	.power_off 		= linkstation_power_off,
 	.halt	 		= linkstation_halt,
 	.calibrate_decr 	= generic_calibrate_decr,
 };

arch/powerpc/platforms/embedded6xx/usbgecko_udbg.c

···
 	np = of_find_compatible_node(NULL, NULL, "nintendo,flipper-exi");
 	if (!np) {
 		udbg_printf("%s: EXI node not found\n", __func__);
-		goto done;
+		goto out;
 	}
 
 	exi_io_base = ug_udbg_setup_exi_io_base(np);
···
 	}
 
 done:
-	if (np)
-		of_node_put(np);
+	of_node_put(np);
+out:
 	return;
 }
 

arch/powerpc/platforms/embedded6xx/wii.c

···
 	if (!of_flat_dt_is_compatible(dt_root, "nintendo,wii"))
 		return 0;
 
+	pm_power_off = wii_power_off;
+
 	return 1;
 }
 
···
 	.init_early		= wii_init_early,
 	.setup_arch		= wii_setup_arch,
 	.restart		= wii_restart,
-	.power_off		= wii_power_off,
 	.halt			= wii_halt,
 	.init_IRQ		= wii_pic_probe,
 	.get_irq		= flipper_pic_get_irq,

arch/powerpc/platforms/maple/pci.c

···
 #include <linux/delay.h>
 #include <linux/string.h>
 #include <linux/init.h>
-#include <linux/bootmem.h>
 #include <linux/irq.h>
 
 #include <asm/sections.h>

arch/powerpc/platforms/maple/setup.c

···
 	if (rtas_service_present("system-reboot") &&
 	    rtas_service_present("power-off")) {
 		ppc_md.restart = rtas_restart;
-		ppc_md.power_off = rtas_power_off;
+		pm_power_off = rtas_power_off;
 		ppc_md.halt = rtas_halt;
 	}
 }
···
 	alloc_dart_table();
 
 	hpte_init_native();
+	pm_power_off = maple_power_off;
 
 	return 1;
 }
···
 	.pci_irq_fixup		= maple_pci_irq_fixup,
 	.pci_get_legacy_ide_irq	= maple_pci_get_legacy_ide_irq,
 	.restart		= maple_restart,
-	.power_off		= maple_power_off,
 	.halt			= maple_halt,
        	.get_boot_time		= maple_get_boot_time,
        	.set_rtc_time		= maple_set_rtc_time,

arch/powerpc/platforms/powermac/nvram.c

···
 		printk(KERN_ERR "nvram: no address\n");
 		return -EINVAL;
 	}
-	nvram_image = alloc_bootmem(NVRAM_SIZE);
-	if (nvram_image == NULL) {
-		printk(KERN_ERR "nvram: can't allocate ram image\n");
-		return -ENOMEM;
-	}
+	nvram_image = memblock_virt_alloc(NVRAM_SIZE, 0);
 	nvram_data = ioremap(addr, NVRAM_SIZE*2);
 	nvram_naddrs = 1; /* Make sure we get the correct case */
 

arch/powerpc/platforms/powermac/pci.c

···
 #include <linux/delay.h>
 #include <linux/string.h>
 #include <linux/init.h>
-#include <linux/bootmem.h>
 #include <linux/irq.h>
 #include <linux/of_pci.h>
 

arch/powerpc/platforms/powermac/setup.c

···
 	smu_cmdbuf_abs = memblock_alloc_base(4096, 4096, 0x80000000UL);
 #endif /* CONFIG_PMAC_SMU */
 
+	pm_power_off = pmac_power_off;
+
 	return 1;
 }
 
···
 	.get_irq		= NULL,	/* changed later */
 	.pci_irq_fixup		= pmac_pci_irq_fixup,
 	.restart		= pmac_restart,
-	.power_off		= pmac_power_off,
 	.halt			= pmac_halt,
 	.time_init		= pmac_time_init,
 	.get_boot_time		= pmac_get_boot_time,

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

···
  * (at your option) any later version.
  */
 
-#include <linux/bootmem.h>
 #include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/io.h>
···
 	} else if (!(pe->state & EEH_PE_ISOLATED)) {
 		eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
 		ioda_eeh_phb_diag(pe);
+
+		if (eeh_has_flag(EEH_EARLY_DUMP_LOG))
+			pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
 	}
 
 	return result;
···
 	 * moving forward, we have to return operational
 	 * state during PE reset.
 	 */
-	if (pe->state & EEH_PE_CFG_BLOCKED) {
+	if (pe->state & EEH_PE_RESET) {
 		result = (EEH_STATE_MMIO_ACTIVE  |
 			  EEH_STATE_DMA_ACTIVE   |
 			  EEH_STATE_MMIO_ENABLED |
···
 
 		eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
 		ioda_eeh_phb_diag(pe);
+
+		if (eeh_has_flag(EEH_EARLY_DUMP_LOG))
+			pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
 	}
 
 	return result;
···
 static int ioda_eeh_get_log(struct eeh_pe *pe, int severity,
 			    char *drv_log, unsigned long len)
 {
-	pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
+	if (!eeh_has_flag(EEH_EARLY_DUMP_LOG))
+		pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
 
 	return 0;
 }
···
 		    !((*pe)->state & EEH_PE_ISOLATED)) {
 			eeh_pe_state_mark(*pe, EEH_PE_ISOLATED);
 			ioda_eeh_phb_diag(*pe);
+
+			if (eeh_has_flag(EEH_EARLY_DUMP_LOG))
+				pnv_pci_dump_phb_diag_data((*pe)->phb,
+							   (*pe)->data);
 		}
 
 		/*

arch/powerpc/platforms/powernv/opal-async.c

···
 
 	return token;
 }
+EXPORT_SYMBOL_GPL(opal_async_get_token_interruptible);
 
 int __opal_async_release_token(int token)
 {
···
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(opal_async_release_token);
 
 int opal_async_wait_response(uint64_t token, struct opal_msg *msg)
 {
···
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(opal_async_wait_response);
 
 static int opal_async_comp_event(struct notifier_block *nb,
 		unsigned long msg_type, void *msg)

arch/powerpc/platforms/powernv/opal-rtc.c

···
 #include <linux/bcd.h>
 #include <linux/rtc.h>
 #include <linux/delay.h>
+#include <linux/platform_device.h>
+#include <linux/of_platform.h>
 
 #include <asm/opal.h>
 #include <asm/firmware.h>
···
 	long rc = OPAL_BUSY;
 
 	if (!opal_check_token(OPAL_RTC_READ))
-		goto out;
+		return 0;
 
 	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
 		rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms);
···
 			mdelay(10);
 	}
 	if (rc != OPAL_SUCCESS)
-		goto out;
+		return 0;
 
 	y_m_d = be32_to_cpu(__y_m_d);
 	h_m_s_ms = be64_to_cpu(__h_m_s_ms);
 	opal_to_tm(y_m_d, h_m_s_ms, &tm);
 	return mktime(tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday,
 		      tm.tm_hour, tm.tm_min, tm.tm_sec);
-out:
-	ppc_md.get_rtc_time = NULL;
-	ppc_md.set_rtc_time = NULL;
-	return 0;
 }
 
-void opal_get_rtc_time(struct rtc_time *tm)
+static __init int opal_time_init(void)
 {
-	long rc = OPAL_BUSY;
-	u32 y_m_d;
-	u64 h_m_s_ms;
-	__be32 __y_m_d;
-	__be64 __h_m_s_ms;
+	struct platform_device *pdev;
+	struct device_node *rtc;
 
-	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
-		rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms);
-		if (rc == OPAL_BUSY_EVENT)
-			opal_poll_events(NULL);
+	rtc = of_find_node_by_path("/ibm,opal/rtc");
+	if (rtc) {
+		pdev = of_platform_device_create(rtc, "opal-rtc", NULL);
+		of_node_put(rtc);
+	} else {
+		if (opal_check_token(OPAL_RTC_READ) ||
+		    opal_check_token(OPAL_READ_TPO))
+			pdev = platform_device_register_simple("opal-rtc", -1,
+							       NULL, 0);
 		else
-			mdelay(10);
+			return -ENODEV;
 	}
-	if (rc != OPAL_SUCCESS)
-		return;
-	y_m_d = be32_to_cpu(__y_m_d);
-	h_m_s_ms = be64_to_cpu(__h_m_s_ms);
-	opal_to_tm(y_m_d, h_m_s_ms, tm);
+
+	return PTR_ERR_OR_ZERO(pdev);
 }
-
-int opal_set_rtc_time(struct rtc_time *tm)
-{
-	long rc = OPAL_BUSY;
-	u32 y_m_d = 0;
-	u64 h_m_s_ms = 0;
-
-	y_m_d |= ((u32)bin2bcd((tm->tm_year + 1900) / 100)) << 24;
-	y_m_d |= ((u32)bin2bcd((tm->tm_year + 1900) % 100)) << 16;
-	y_m_d |= ((u32)bin2bcd((tm->tm_mon + 1))) << 8;
-	y_m_d |= ((u32)bin2bcd(tm->tm_mday));
-
-	h_m_s_ms |= ((u64)bin2bcd(tm->tm_hour)) << 56;
-	h_m_s_ms |= ((u64)bin2bcd(tm->tm_min)) << 48;
-	h_m_s_ms |= ((u64)bin2bcd(tm->tm_sec)) << 40;
-
-	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
-		rc = opal_rtc_write(y_m_d, h_m_s_ms);
-		if (rc == OPAL_BUSY_EVENT)
-			opal_poll_events(NULL);
-		else
-			mdelay(10);
-	}
-	return rc == OPAL_SUCCESS ? 0 : -EIO;
-}
+machine_subsys_initcall(powernv, opal_time_init);

arch/powerpc/platforms/powernv/opal-tracepoints.c

···
 
 	local_irq_save(flags);
 
-	depth = &__get_cpu_var(opal_trace_depth);
+	depth = this_cpu_ptr(&opal_trace_depth);
 
 	if (*depth)
 		goto out;
···
 
 	local_irq_save(flags);
 
-	depth = &__get_cpu_var(opal_trace_depth);
+	depth = this_cpu_ptr(&opal_trace_depth);
 
 	if (*depth)
 		goto out;

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

···
 	.section	".text"
 
 #ifdef CONFIG_TRACEPOINTS
-#ifdef CONFIG_JUMP_LABEL
+#ifdef HAVE_JUMP_LABEL
 #define OPAL_BRANCH(LABEL)					\
 	ARCH_STATIC_BRANCH(LABEL, opal_tracepoint_key)
 #else
···
 OPAL_CALL(opal_register_dump_region,		OPAL_REGISTER_DUMP_REGION);
 OPAL_CALL(opal_unregister_dump_region,		OPAL_UNREGISTER_DUMP_REGION);
 OPAL_CALL(opal_pci_set_phb_cxl_mode,		OPAL_PCI_SET_PHB_CXL_MODE);
+OPAL_CALL(opal_tpo_write,			OPAL_WRITE_TPO);
+OPAL_CALL(opal_tpo_read,			OPAL_READ_TPO);
+OPAL_CALL(opal_ipmi_send,			OPAL_IPMI_SEND);
+OPAL_CALL(opal_ipmi_recv,			OPAL_IPMI_RECV);

arch/powerpc/platforms/powernv/opal.c

···
 
 struct device_node *opal_node;
 static DEFINE_SPINLOCK(opal_write_lock);
-extern u64 opal_mc_secondary_handler[];
 static unsigned int *opal_irqs;
 static unsigned int opal_irq_count;
 static ATOMIC_NOTIFIER_HEAD(opal_notifier_head);
···
 		pr_warn("DUMP: Failed to register kernel log buffer. "
 			"rc = %d\n", rc);
 }
+
+static void opal_ipmi_init(struct device_node *opal_node)
+{
+	struct device_node *np;
+
+	for_each_child_of_node(opal_node, np)
+		if (of_device_is_compatible(np, "ibm,opal-ipmi"))
+			of_platform_device_create(np, NULL, NULL);
+}
+
 static int __init opal_init(void)
 {
 	struct device_node *np, *consoles;
···
 		opal_msglog_init();
 	}
 
+	opal_ipmi_init(opal_node);
+
 	return 0;
 }
 machine_subsys_initcall(powernv, opal_init);
···
 
 /* Export this so that test modules can use it */
 EXPORT_SYMBOL_GPL(opal_invalid_call);
+EXPORT_SYMBOL_GPL(opal_ipmi_send);
+EXPORT_SYMBOL_GPL(opal_ipmi_recv);
 
 /* Convert a region of vmalloc memory to an opal sg list */
 struct opal_sg_list *opal_vmalloc_to_sg_list(void *vmalloc_addr,
···
 			sg = NULL;
 	}
 }
+
+EXPORT_SYMBOL_GPL(opal_poll_events);
+EXPORT_SYMBOL_GPL(opal_rtc_read);
+EXPORT_SYMBOL_GPL(opal_rtc_write);
+EXPORT_SYMBOL_GPL(opal_tpo_read);
+EXPORT_SYMBOL_GPL(opal_tpo_write);

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

···
 		(IORESOURCE_MEM_64 | IORESOURCE_PREFETCH));
 }
 
+static void pnv_ioda_reserve_pe(struct pnv_phb *phb, int pe_no)
+{
+	if (!(pe_no >= 0 && pe_no < phb->ioda.total_pe)) {
+		pr_warn("%s: Invalid PE %d on PHB#%x\n",
+			__func__, pe_no, phb->hose->global_number);
+		return;
+	}
+
+	if (test_and_set_bit(pe_no, phb->ioda.pe_alloc)) {
+		pr_warn("%s: PE %d was assigned on PHB#%x\n",
+			__func__, pe_no, phb->hose->global_number);
+		return;
+	}
+
+	phb->ioda.pe_array[pe_no].phb = phb;
+	phb->ioda.pe_array[pe_no].pe_number = pe_no;
+}
+
 static int pnv_ioda_alloc_pe(struct pnv_phb *phb)
 {
 	unsigned long pe;
···
 	return -EIO;
 }
 
-static void pnv_ioda2_alloc_m64_pe(struct pnv_phb *phb)
+static void pnv_ioda2_reserve_m64_pe(struct pnv_phb *phb)
 {
 	resource_size_t sgsz = phb->ioda.m64_segsize;
 	struct pci_dev *pdev;
···
 	 * instead of root bus.
 	 */
 	list_for_each_entry(pdev, &phb->hose->bus->devices, bus_list) {
-		for (i = PCI_BRIDGE_RESOURCES;
-		     i <= PCI_BRIDGE_RESOURCE_END; i++) {
-			r = &pdev->resource[i];
+		for (i = 0; i < PCI_BRIDGE_RESOURCE_NUM; i++) {
+			r = &pdev->resource[PCI_BRIDGE_RESOURCES + i];
 			if (!r->parent ||
 			    !pnv_pci_is_mem_pref_64(r->flags))
 				continue;
 
 			base = (r->start - phb->ioda.m64_base) / sgsz;
 			for (step = 0; step < resource_size(r) / sgsz; step++)
-				set_bit(base + step, phb->ioda.pe_alloc);
+				pnv_ioda_reserve_pe(phb, base + step);
 		}
 	}
 }
···
 	while ((i = find_next_bit(pe_alloc, phb->ioda.total_pe, i + 1)) <
 		phb->ioda.total_pe) {
 		pe = &phb->ioda.pe_array[i];
-		pe->phb = phb;
-		pe->pe_number = i;
 
 		if (!master_pe) {
 			pe->flags |= PNV_IODA_PE_MASTER;
···
 	const u32 *r;
 	u64 pci_addr;
 
+	/* FIXME: Support M64 for P7IOC */
+	if (phb->type != PNV_PHB_IODA2) {
+		pr_info("  Not support M64 window\n");
+		return;
+	}
+
 	if (!firmware_has_feature(FW_FEATURE_OPALv3)) {
 		pr_info("  Firmware too old to support M64 window\n");
 		return;
···
 	if (!r) {
 		pr_info("  No <ibm,opal-m64-window> on %s\n",
 			dn->full_name);
-		return;
-	}
-
-	/* FIXME: Support M64 for P7IOC */
-	if (phb->type != PNV_PHB_IODA2) {
-		pr_info("  Not support M64 window\n");
 		return;
 	}
 
···
 	/* Use last M64 BAR to cover M64 window */
 	phb->ioda.m64_bar_idx = 15;
 	phb->init_m64 = pnv_ioda2_init_m64;
-	phb->alloc_m64_pe = pnv_ioda2_alloc_m64_pe;
+	phb->reserve_m64_pe = pnv_ioda2_reserve_m64_pe;
 	phb->pick_m64_pe = pnv_ioda2_pick_m64_pe;
 }
 
···
 	/* Fetch master PE */
 	if (pe->flags & PNV_IODA_PE_SLAVE) {
 		pe = pe->master;
-		WARN_ON(!pe || !(pe->flags & PNV_IODA_PE_MASTER));
+		if (WARN_ON(!pe || !(pe->flags & PNV_IODA_PE_MASTER)))
+			return;
+
 		pe_no = pe->pe_number;
 	}
 
···
 }
 #endif /* CONFIG_PCI_MSI */
 
+static int pnv_ioda_set_one_peltv(struct pnv_phb *phb,
+				  struct pnv_ioda_pe *parent,
+				  struct pnv_ioda_pe *child,
+				  bool is_add)
+{
+	const char *desc = is_add ? "adding" : "removing";
+	uint8_t op = is_add ? OPAL_ADD_PE_TO_DOMAIN :
+			      OPAL_REMOVE_PE_FROM_DOMAIN;
+	struct pnv_ioda_pe *slave;
+	long rc;
+
+	/* Parent PE affects child PE */
+	rc = opal_pci_set_peltv(phb->opal_id, parent->pe_number,
+				child->pe_number, op);
+	if (rc != OPAL_SUCCESS) {
+		pe_warn(child, "OPAL error %ld %s to parent PELTV\n",
+			rc, desc);
+		return -ENXIO;
+	}
+
+	if (!(child->flags & PNV_IODA_PE_MASTER))
+		return 0;
+
+	/* Compound case: parent PE affects slave PEs */
+	list_for_each_entry(slave, &child->slaves, list) {
+		rc = opal_pci_set_peltv(phb->opal_id, parent->pe_number,
+					slave->pe_number, op);
+		if (rc != OPAL_SUCCESS) {
+			pe_warn(slave, "OPAL error %ld %s to parent PELTV\n",
+				rc, desc);
+			return -ENXIO;
+		}
+	}
+
+	return 0;
+}
+
+static int pnv_ioda_set_peltv(struct pnv_phb *phb,
+			      struct pnv_ioda_pe *pe,
+			      bool is_add)
+{
+	struct pnv_ioda_pe *slave;
+	struct pci_dev *pdev;
+	int ret;
+
+	/*
+	 * Clear PE frozen state. If it's master PE, we need
+	 * clear slave PE frozen state as well.
+	 */
+	if (is_add) {
+		opal_pci_eeh_freeze_clear(phb->opal_id, pe->pe_number,
+					  OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
+		if (pe->flags & PNV_IODA_PE_MASTER) {
+			list_for_each_entry(slave, &pe->slaves, list)
+				opal_pci_eeh_freeze_clear(phb->opal_id,
+							  slave->pe_number,
+							  OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
+		}
+	}
+
+	/*
+	 * Associate PE in PELT. We need add the PE into the
+	 * corresponding PELT-V as well. Otherwise, the error
+	 * originated from the PE might contribute to other
+	 * PEs.
+	 */
+	ret = pnv_ioda_set_one_peltv(phb, pe, pe, is_add);
+	if (ret)
+		return ret;
+
+	/* For compound PEs, any one affects all of them */
+	if (pe->flags & PNV_IODA_PE_MASTER) {
+		list_for_each_entry(slave, &pe->slaves, list) {
+			ret = pnv_ioda_set_one_peltv(phb, slave, pe, is_add);
+			if (ret)
+				return ret;
+		}
+	}
+
+	if (pe->flags & (PNV_IODA_PE_BUS_ALL | PNV_IODA_PE_BUS))
+		pdev = pe->pbus->self;
+	else
+		pdev = pe->pdev->bus->self;
+	while (pdev) {
+		struct pci_dn *pdn = pci_get_pdn(pdev);
+		struct pnv_ioda_pe *parent;
+
+		if (pdn && pdn->pe_number != IODA_INVALID_PE) {
+			parent = &phb->ioda.pe_array[pdn->pe_number];
+			ret = pnv_ioda_set_one_peltv(phb, parent, pe, is_add);
+			if (ret)
+				return ret;
+		}
+
+		pdev = pdev->bus->self;
+	}
+
+	return 0;
+}
+
 static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 {
 	struct pci_dev *parent;
···
 		return -ENXIO;
 	}
 
-	rc = opal_pci_set_peltv(phb->opal_id, pe->pe_number,
-				pe->pe_number, OPAL_ADD_PE_TO_DOMAIN);
-	if (rc)
-		pe_warn(pe, "OPAL error %d adding self to PELTV\n", rc);
-	opal_pci_eeh_freeze_clear(phb->opal_id, pe->pe_number,
-				  OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
+	/* Configure PELTV */
+	pnv_ioda_set_peltv(phb, pe, true);
 
-	/* Add to all parents PELT-V */
-	while (parent) {
-		struct pci_dn *pdn = pci_get_pdn(parent);
-		if (pdn && pdn->pe_number != IODA_INVALID_PE) {
-			rc = opal_pci_set_peltv(phb->opal_id, pdn->pe_number,
-						pe->pe_number, OPAL_ADD_PE_TO_DOMAIN);
-			/* XXX What to do in case of error ? */
-		}
-		parent = parent->bus->self;
-	}
 	/* Setup reverse map */
 	for (rid = pe->rid; rid < rid_end; rid++)
 		phb->ioda.pe_rmap[rid] = pe->pe_number;
 
 	/* Setup one MVTs on IODA1 */
-	if (phb->type == PNV_PHB_IODA1) {
-		pe->mve_number = pe->pe_number;
-		rc = opal_pci_set_mve(phb->opal_id, pe->mve_number,
-				      pe->pe_number);
+	if (phb->type != PNV_PHB_IODA1) {
+		pe->mve_number = 0;
+		goto out;
+	}
+
+	pe->mve_number = pe->pe_number;
+	rc = opal_pci_set_mve(phb->opal_id, pe->mve_number, pe->pe_number);
+	if (rc != OPAL_SUCCESS) {
+		pe_err(pe, "OPAL error %ld setting up MVE %d\n",
+		       rc, pe->mve_number);
+		pe->mve_number = -1;
+	} else {
+		rc = opal_pci_set_mve_enable(phb->opal_id,
+					     pe->mve_number, OPAL_ENABLE_MVE);
 		if (rc) {
-			pe_err(pe, "OPAL error %ld setting up MVE %d\n",
+			pe_err(pe, "OPAL error %ld enabling MVE %d\n",
 			       rc, pe->mve_number);
 			pe->mve_number = -1;
-		} else {
-			rc = opal_pci_set_mve_enable(phb->opal_id,
-						     pe->mve_number, OPAL_ENABLE_MVE);
-			if (rc) {
-				pe_err(pe, "OPAL error %ld enabling MVE %d\n",
-				       rc, pe->mve_number);
-				pe->mve_number = -1;
-			}
 		}
-	} else if (phb->type == PNV_PHB_IODA2)
-		pe->mve_number = 0;
+	}
 
+out:
 	return 0;
 }
 
···
 		phb = hose->private_data;
 
 		/* M64 layout might affect PE allocation */
-		if (phb->alloc_m64_pe)
-			phb->alloc_m64_pe(phb);
+		if (phb->reserve_m64_pe)
+			phb->reserve_m64_pe(phb);
 
 		pnv_ioda_setup_PEs(hose->bus);
 	}
···
 	phb_id = be64_to_cpup(prop64);
 	pr_debug("  PHB-ID  : 0x%016llx\n", phb_id);
 
-	phb = alloc_bootmem(sizeof(struct pnv_phb));
-	if (!phb) {
-		pr_err("  Out of memory !\n");
-		return;
-	}
+	phb = memblock_virt_alloc(sizeof(struct pnv_phb), 0);
 
 	/* Allocate PCI controller */
-	memset(phb, 0, sizeof(struct pnv_phb));
 	phb->hose = hose = pcibios_alloc_controller(np);
 	if (!phb->hose) {
 		pr_err("  Can't allocate PCI controller for %s\n",
 		       np->full_name);
-		free_bootmem((unsigned long)phb, sizeof(struct pnv_phb));
+		memblock_free(__pa(phb), sizeof(struct pnv_phb));
 		return;
 	}
 
···
 	}
 	pemap_off = size;
 	size += phb->ioda.total_pe * sizeof(struct pnv_ioda_pe);
-	aux = alloc_bootmem(size);
-	memset(aux, 0, size);
+	aux = memblock_virt_alloc(size, 0);
 	phb->ioda.pe_alloc = aux;
 	phb->ioda.m32_segmap = aux + m32map_off;
 	if (phb->type == PNV_PHB_IODA1)
···
 		ioda_eeh_phb_reset(hose, EEH_RESET_DEACTIVATE);
 	}
 
-	/* Configure M64 window */
-	if (phb->init_m64 && phb->init_m64(phb))
+	/* Remove M64 resource if we can't configure it successfully */
+	if (!phb->init_m64 || phb->init_m64(phb))
 		hose->mem_resources[1].flags = 0;
 }
 

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

···
 		return;
 	}
 
-	phb = alloc_bootmem(sizeof(struct pnv_phb));
-	if (phb) {
-		memset(phb, 0, sizeof(struct pnv_phb));
-		phb->hose = pcibios_alloc_controller(np);
-	}
-	if (!phb || !phb->hose) {
+	phb = memblock_virt_alloc(sizeof(struct pnv_phb), 0);
+	phb->hose = pcibios_alloc_controller(np);
+	if (!phb->hose) {
 		pr_err("  Failed to allocate PCI controller\n");
 		return;
 	}
···
 	hub_id = be64_to_cpup(prop64);
 	pr_info(" HUB-ID : 0x%016llx\n", hub_id);
 
+	/* Count child PHBs and calculate TCE space per PHB */
+	for_each_child_of_node(np, phbn) {
+		if (of_device_is_compatible(phbn, "ibm,p5ioc2-pcix") ||
+		    of_device_is_compatible(phbn, "ibm,p5ioc2-pciex"))
+			phb_count++;
+	}
+
+	if (phb_count <= 0) {
+		pr_info(" No PHBs for Hub %s\n", np->full_name);
+		return;
+	}
+
+	tce_per_phb = __rounddown_pow_of_two(P5IOC2_TCE_MEMORY / phb_count);
+	pr_info(" Allocating %lld MB of TCE memory per PHB\n",
+		tce_per_phb >> 20);
+
 	/* Currently allocate 16M of TCE memory for every Hub
 	 *
 	 * XXX TODO: Make it chip local if possible
 	 */
-	tce_mem = __alloc_bootmem(P5IOC2_TCE_MEMORY, P5IOC2_TCE_MEMORY,
-				  __pa(MAX_DMA_ADDRESS));
-	if (!tce_mem) {
-		pr_err(" Failed to allocate TCE Memory !\n");
-		return;
-	}
+	tce_mem = memblock_virt_alloc(P5IOC2_TCE_MEMORY, P5IOC2_TCE_MEMORY);
 	pr_debug(" TCE    : 0x%016lx..0x%016lx\n",
 		__pa(tce_mem), __pa(tce_mem) + P5IOC2_TCE_MEMORY - 1);
 	rc = opal_pci_set_hub_tce_memory(hub_id, __pa(tce_mem),
···
 		pr_err(" Failed to allocate TCE memory, OPAL error %lld\n", rc);
 		return;
 	}
-
-	/* Count child PHBs */
-	for_each_child_of_node(np, phbn) {
-		if (of_device_is_compatible(phbn, "ibm,p5ioc2-pcix") ||
-		    of_device_is_compatible(phbn, "ibm,p5ioc2-pciex"))
-			phb_count++;
-	}
-
-	/* Calculate how much TCE space we can give per PHB */
-	tce_per_phb = __rounddown_pow_of_two(P5IOC2_TCE_MEMORY / phb_count);
-	pr_info(" Allocating %lld MB of TCE memory per PHB\n",
-		tce_per_phb >> 20);
 
 	/* Initialize PHBs */
 	for_each_child_of_node(np, phbn) {

arch/powerpc/platforms/powernv/pci.c

···
 #include <linux/delay.h>
 #include <linux/string.h>
 #include <linux/init.h>
-#include <linux/bootmem.h>
 #include <linux/irq.h>
 #include <linux/io.h>
 #include <linux/msi.h>

arch/powerpc/platforms/powernv/pci.h

···
 	u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn);
 	void (*shutdown)(struct pnv_phb *phb);
 	int (*init_m64)(struct pnv_phb *phb);
-	void (*alloc_m64_pe)(struct pnv_phb *phb);
+	void (*reserve_m64_pe)(struct pnv_phb *phb);
 	int (*pick_m64_pe)(struct pnv_phb *phb, struct pci_bus *bus, int all);
 	int (*get_pe_state)(struct pnv_phb *phb, int pe_no);
 	void (*freeze_pe)(struct pnv_phb *phb, int pe_no);

arch/powerpc/platforms/powernv/setup.c

···
 static void __init pnv_setup_machdep_opal(void)
 {
 	ppc_md.get_boot_time = opal_get_boot_time;
-	ppc_md.get_rtc_time = opal_get_rtc_time;
-	ppc_md.set_rtc_time = opal_set_rtc_time;
 	ppc_md.restart = pnv_restart;
-	ppc_md.power_off = pnv_power_off;
+	pm_power_off = pnv_power_off;
 	ppc_md.halt = pnv_halt;
 	ppc_md.machine_check_exception = opal_machine_check;
 	ppc_md.mce_check_early_recovery = opal_mce_check_early_recovery;
···
 		ppc_md.set_rtc_time = rtas_set_rtc_time;
 	}
 	ppc_md.restart = rtas_restart;
-	ppc_md.power_off = rtas_power_off;
+	pm_power_off = rtas_power_off;
 	ppc_md.halt = rtas_halt;
 }
 #endif /* CONFIG_PPC_POWERNV_RTAS */

arch/powerpc/platforms/powernv/smp.c

···
 static void pnv_smp_cpu_kill_self(void)
 {
 	unsigned int cpu;
+	unsigned long srr1;
 
 	/* Standard hot unplug procedure */
 	local_irq_disable();
···
 	mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1);
 	while (!generic_check_cpu_restart(cpu)) {
 		ppc64_runlatch_off();
-		power7_nap(1);
+		srr1 = power7_nap(1);
 		ppc64_runlatch_on();
 
-		/* Clear the IPI that woke us up */
-		icp_native_flush_interrupt();
-		local_paca->irq_happened &= PACA_IRQ_HARD_DIS;
-		mb();
+		/*
+		 * If the SRR1 value indicates that we woke up due to
+		 * an external interrupt, then clear the interrupt.
+		 * We clear the interrupt before checking for the
+		 * reason, so as to avoid a race where we wake up for
+		 * some other reason, find nothing and clear the interrupt
+		 * just as some other cpu is sending us an interrupt.
+		 * If we returned from power7_nap as a result of
+		 * having finished executing in a KVM guest, then srr1
+		 * contains 0.
+		 */
+		if ((srr1 & SRR1_WAKEMASK) == SRR1_WAKEEE) {
+			icp_native_flush_interrupt();
+			local_paca->irq_happened &= PACA_IRQ_HARD_DIS;
+			smp_mb();
+		}
 
 		if (cpu_core_split_required())
 			continue;

arch/powerpc/platforms/ps3/htab.c

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

arch/powerpc/platforms/ps3/interrupt.c

···
 
 static unsigned int ps3_get_irq(void)
 {
-	struct ps3_private *pd = &__get_cpu_var(ps3_private);
+	struct ps3_private *pd = this_cpu_ptr(&ps3_private);
 	u64 x = (pd->bmp.status & pd->bmp.mask);
 	unsigned int plug;
 

arch/powerpc/platforms/ps3/setup.c

···
 	if (!p->size)
 		return;
 
-	p->address = __alloc_bootmem(p->size, p->align, __pa(MAX_DMA_ADDRESS));
-	if (!p->address) {
-		printk(KERN_ERR "%s: Cannot allocate %s\n", __func__,
-		       p->name);
-		return;
-	}
+	p->address = memblock_virt_alloc(p->size, p->align);
 
 	printk(KERN_INFO "%s: %lu bytes at %p\n", p->name, p->size,
 	       p->address);
···
 	ps3_mm_init();
 	ps3_mm_vas_create(&htab_size);
 	ps3_hpte_init(htab_size);
+	pm_power_off = ps3_power_off;
 
 	DBG(" <- %s:%d\n", __func__, __LINE__);
 	return 1;
···
 	.calibrate_decr			= ps3_calibrate_decr,
 	.progress			= ps3_progress,
 	.restart			= ps3_restart,
-	.power_off			= ps3_power_off,
 	.halt				= ps3_halt,
 #if defined(CONFIG_KEXEC)
 	.kexec_cpu_down			= ps3_kexec_cpu_down,

arch/powerpc/platforms/pseries/dtl.c

···
  */
 static void consume_dtle(struct dtl_entry *dtle, u64 index)
 {
-	struct dtl_ring *dtlr = &__get_cpu_var(dtl_rings);
+	struct dtl_ring *dtlr = this_cpu_ptr(&dtl_rings);
 	struct dtl_entry *wp = dtlr->write_ptr;
 	struct lppaca *vpa = local_paca->lppaca_ptr;
 

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

···
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/memblock.h>
-#include <linux/vmalloc.h>
 #include <linux/memory.h>
 #include <linux/memory_hotplug.h>
 
···
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
-static int pseries_remove_memory(u64 start, u64 size)
-{
-	int ret;
-
-	/* Remove htab bolted mappings for this section of memory */
-	start = (unsigned long)__va(start);
-	ret = remove_section_mapping(start, start + size);
-
-	/* Ensure all vmalloc mappings are flushed in case they also
-	 * hit that section of memory
-	 */
-	vm_unmap_aliases();
-
-	return ret;
-}
-
 static int pseries_remove_memblock(unsigned long base, unsigned int memblock_size)
 {
 	unsigned long block_sz, start_pfn;
···
 {
 	if (firmware_has_feature(FW_FEATURE_LPAR))
 		of_reconfig_notifier_register(&pseries_mem_nb);
-
-#ifdef CONFIG_MEMORY_HOTREMOVE
-	ppc_md.remove_memory = pseries_remove_memory;
-#endif
 
 	return 0;
 }

arch/powerpc/platforms/pseries/hvCall.S

···
 	
 #ifdef CONFIG_TRACEPOINTS
 
-#ifndef CONFIG_JUMP_LABEL
+#ifndef HAVE_JUMP_LABEL
 	.section	".toc","aw"
 
 	.globl hcall_tracepoint_refcount
···
 	mr	r5,BUFREG;					\
 	__HCALL_INST_POSTCALL
 
-#ifdef CONFIG_JUMP_LABEL
+#ifdef HAVE_JUMP_LABEL
 #define HCALL_BRANCH(LABEL)					\
 	ARCH_STATIC_BRANCH(LABEL, hcall_tracepoint_key)
 #else

arch/powerpc/platforms/pseries/hvCall_inst.c

···
 	if (opcode > MAX_HCALL_OPCODE)
 		return;
 
-	h = &__get_cpu_var(hcall_stats)[opcode / 4];
+	h = this_cpu_ptr(&hcall_stats[opcode / 4]);
 	h->tb_start = mftb();
 	h->purr_start = mfspr(SPRN_PURR);
 }
···
 	if (opcode > MAX_HCALL_OPCODE)
 		return;
 
-	h = &__get_cpu_var(hcall_stats)[opcode / 4];
+	h = this_cpu_ptr(&hcall_stats[opcode / 4]);
 	h->num_calls++;
 	h->tb_total += mftb() - h->tb_start;
 	h->purr_total += mfspr(SPRN_PURR) - h->purr_start;

arch/powerpc/platforms/pseries/iommu.c

···
 
 	local_irq_save(flags);	/* to protect tcep and the page behind it */
 
-	tcep = __get_cpu_var(tce_page);
+	tcep = __this_cpu_read(tce_page);
 
 	/* This is safe to do since interrupts are off when we're called
 	 * from iommu_alloc{,_sg}()
···
 			return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr,
 					    direction, attrs);
 		}
-		__get_cpu_var(tce_page) = tcep;
+		__this_cpu_write(tce_page, tcep);
 	}
 
 	rpn = __pa(uaddr) >> TCE_SHIFT;
···
 	long l, limit;
 
 	local_irq_disable();	/* to protect tcep and the page behind it */
-	tcep = __get_cpu_var(tce_page);
+	tcep = __this_cpu_read(tce_page);
 
 	if (!tcep) {
 		tcep = (__be64 *)__get_free_page(GFP_ATOMIC);
···
 			local_irq_enable();
 			return -ENOMEM;
 		}
-		__get_cpu_var(tce_page) = tcep;
+		__this_cpu_write(tce_page, tcep);
 	}
 
 	proto_tce = TCE_PCI_READ | TCE_PCI_WRITE;
···
 	while (isa_dn && isa_dn != dn)
 		isa_dn = isa_dn->parent;
 
-	if (isa_dn_orig)
-		of_node_put(isa_dn_orig);
+	of_node_put(isa_dn_orig);
 
 	/* Count number of direct PCI children of the PHB. */
 	for (children = 0, tmp = dn->child; tmp; tmp = tmp->sibling)

arch/powerpc/platforms/pseries/lpar.c

···
 				       unsigned long newpp,
 				       unsigned long vpn,
 				       int psize, int apsize,
-				       int ssize, int local)
+				       int ssize, unsigned long inv_flags)
 {
 	unsigned long lpar_rc;
 	unsigned long flags = (newpp & 7) | H_AVPN;
···
 static void pSeries_lpar_hugepage_invalidate(unsigned long vsid,
 					     unsigned long addr,
 					     unsigned char *hpte_slot_array,
-					     int psize, int ssize)
+					     int psize, int ssize, int local)
 {
 	int i, index = 0;
 	unsigned long s_addr = addr;
···
 	unsigned long vpn;
 	unsigned long i, pix, rc;
 	unsigned long flags = 0;
-	struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch);
+	struct ppc64_tlb_batch *batch = this_cpu_ptr(&ppc64_tlb_batch);
 	int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
 	unsigned long param[9];
 	unsigned long hash, index, shift, hidx, slot;
···
 
 	local_irq_save(flags);
 
-	depth = &__get_cpu_var(hcall_trace_depth);
+	depth = this_cpu_ptr(&hcall_trace_depth);
 
 	if (*depth)
 		goto out;
···
 
 	local_irq_save(flags);
 
-	depth = &__get_cpu_var(hcall_trace_depth);
+	depth = this_cpu_ptr(&hcall_trace_depth);
 
 	if (*depth)
 		goto out;

arch/powerpc/platforms/pseries/nvram.c

···
 	nvram_pstore_info.buf = oops_data;
 	nvram_pstore_info.bufsize = oops_data_sz;
 
+	spin_lock_init(&nvram_pstore_info.buf_lock);
+
 	rc = pstore_register(&nvram_pstore_info);
 	if (rc != 0)
 		pr_err("nvram: pstore_register() failed, defaults to "

arch/powerpc/platforms/pseries/pci.c

···
 	of_node_put(pdn);
 
 	if (rc) {
-		pr_err("no ibm,pcie-link-speed-stats property\n");
+		pr_debug("no ibm,pcie-link-speed-stats property\n");
 		return 0;
 	}
 

arch/powerpc/platforms/pseries/ras.c

···
 	/* If it isn't an extended log we can use the per cpu 64bit buffer */
 	h = (struct rtas_error_log *)&savep[1];
 	if (!rtas_error_extended(h)) {
-		memcpy(&__get_cpu_var(mce_data_buf), h, sizeof(__u64));
-		errhdr = (struct rtas_error_log *)&__get_cpu_var(mce_data_buf);
+		memcpy(this_cpu_ptr(&mce_data_buf), h, sizeof(__u64));
+		errhdr = (struct rtas_error_log *)this_cpu_ptr(&mce_data_buf);
 	} else {
 		int len, error_log_length;
 

arch/powerpc/platforms/pseries/setup.c

···
 
 	if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
 		long rc;
-		if ((rc = pSeries_enable_reloc_on_exc()) != H_SUCCESS) {
+
+		rc = pSeries_enable_reloc_on_exc();
+		if (rc == H_P2) {
+			pr_info("Relocation on exceptions not supported\n");
+		} else if (rc != H_SUCCESS) {
 			pr_warn("Unable to enable relocation on exceptions: "
 				"%ld\n", rc);
 		}
···
 	pr_debug(" <- pSeries_init_early()\n");
 }
 
+/**
+ * pseries_power_off - tell firmware about how to power off the system.
+ *
+ * This function calls either the power-off rtas token in normal cases
+ * or the ibm,power-off-ups token (if present & requested) in case of
+ * a power failure. If power-off token is used, power on will only be
+ * possible with power button press. If ibm,power-off-ups token is used
+ * it will allow auto poweron after power is restored.
+ */
+static void pseries_power_off(void)
+{
+	int rc;
+	int rtas_poweroff_ups_token = rtas_token("ibm,power-off-ups");
+
+	if (rtas_flash_term_hook)
+		rtas_flash_term_hook(SYS_POWER_OFF);
+
+	if (rtas_poweron_auto == 0 ||
+		rtas_poweroff_ups_token == RTAS_UNKNOWN_SERVICE) {
+		rc = rtas_call(rtas_token("power-off"), 2, 1, NULL, -1, -1);
+		printk(KERN_INFO "RTAS power-off returned %d\n", rc);
+	} else {
+		rc = rtas_call(rtas_poweroff_ups_token, 0, 1, NULL);
+		printk(KERN_INFO "RTAS ibm,power-off-ups returned %d\n", rc);
+	}
+	for (;;);
+}
+
 /*
  * Called very early, MMU is off, device-tree isn't unflattened
  */
···
 	else
 		hpte_init_native();
 
+	pm_power_off = pseries_power_off;
+
 	pr_debug("Machine is%s LPAR !\n",
 	         (powerpc_firmware_features & FW_FEATURE_LPAR) ? "" : " not");
 
···
 	if (firmware_has_feature(FW_FEATURE_LPAR))
 		return PCI_PROBE_DEVTREE;
 	return PCI_PROBE_NORMAL;
-}
-
-/**
- * pSeries_power_off - tell firmware about how to power off the system.
- *
- * This function calls either the power-off rtas token in normal cases
- * or the ibm,power-off-ups token (if present & requested) in case of
- * a power failure. If power-off token is used, power on will only be
- * possible with power button press. If ibm,power-off-ups token is used
- * it will allow auto poweron after power is restored.
- */
-static void pSeries_power_off(void)
-{
-	int rc;
-	int rtas_poweroff_ups_token = rtas_token("ibm,power-off-ups");
-
-	if (rtas_flash_term_hook)
-		rtas_flash_term_hook(SYS_POWER_OFF);
-
-	if (rtas_poweron_auto == 0 ||
-		rtas_poweroff_ups_token == RTAS_UNKNOWN_SERVICE) {
-		rc = rtas_call(rtas_token("power-off"), 2, 1, NULL, -1, -1);
-		printk(KERN_INFO "RTAS power-off returned %d\n", rc);
-	} else {
-		rc = rtas_call(rtas_poweroff_ups_token, 0, 1, NULL);
-		printk(KERN_INFO "RTAS ibm,power-off-ups returned %d\n", rc);
-	}
-	for (;;);
 }
 
 #ifndef CONFIG_PCI
···
 	.pcibios_fixup		= pSeries_final_fixup,
 	.pci_probe_mode		= pSeries_pci_probe_mode,
 	.restart		= rtas_restart,
-	.power_off		= pSeries_power_off,
 	.halt			= rtas_halt,
 	.panic			= rtas_os_term,
 	.get_boot_time		= rtas_get_boot_time,

arch/powerpc/sysdev/fsl_msi.c

···
  *
  */
 #include <linux/irq.h>
-#include <linux/bootmem.h>
 #include <linux/msi.h>
 #include <linux/pci.h>
 #include <linux/slab.h>

arch/powerpc/sysdev/fsl_pci.c

···
 #include <linux/string.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
-#include <linux/bootmem.h>
 #include <linux/memblock.h>
 #include <linux/log2.h>
 #include <linux/slab.h>
···
 		flags |= 0x10000000; /* enable relaxed ordering */
 
 	for (i = 0; size > 0; i++) {
-		unsigned int bits = min(ilog2(size),
+		unsigned int bits = min_t(u32, ilog2(size),
 					__ffs(pci_addr | phys_addr));
 
 		if (index + i >= 5)

arch/powerpc/sysdev/fsl_rio.c

···
 #define RIO_ISR_AACR		0x10120
 #define RIO_ISR_AACR_AA		0x1	/* Accept All ID */
 
+#define RIWTAR_TRAD_VAL_SHIFT	12
+#define RIWTAR_TRAD_MASK	0x00FFFFFF
+#define RIWBAR_BADD_VAL_SHIFT	12
+#define RIWBAR_BADD_MASK	0x003FFFFF
+#define RIWAR_ENABLE		0x80000000
+#define RIWAR_TGINT_LOCAL	0x00F00000
+#define RIWAR_RDTYP_NO_SNOOP	0x00040000
+#define RIWAR_RDTYP_SNOOP	0x00050000
+#define RIWAR_WRTYP_NO_SNOOP	0x00004000
+#define RIWAR_WRTYP_SNOOP	0x00005000
+#define RIWAR_WRTYP_ALLOC	0x00006000
+#define RIWAR_SIZE_MASK		0x0000003F
+
 #define __fsl_read_rio_config(x, addr, err, op)		\
 	__asm__ __volatile__(				\
 		"1:	"op" %1,0(%2)\n"		\
···
 	return 0;
 }
 
+static void fsl_rio_inbound_mem_init(struct rio_priv *priv)
+{
+	int i;
+
+	/* close inbound windows */
+	for (i = 0; i < RIO_INB_ATMU_COUNT; i++)
+		out_be32(&priv->inb_atmu_regs[i].riwar, 0);
+}
+
+int fsl_map_inb_mem(struct rio_mport *mport, dma_addr_t lstart,
+	u64 rstart, u32 size, u32 flags)
+{
+	struct rio_priv *priv = mport->priv;
+	u32 base_size;
+	unsigned int base_size_log;
+	u64 win_start, win_end;
+	u32 riwar;
+	int i;
+
+	if ((size & (size - 1)) != 0)
+		return -EINVAL;
+
+	base_size_log = ilog2(size);
+	base_size = 1 << base_size_log;
+
+	/* check if addresses are aligned with the window size */
+	if (lstart & (base_size - 1))
+		return -EINVAL;
+	if (rstart & (base_size - 1))
+		return -EINVAL;
+
+	/* check for conflicting ranges */
+	for (i = 0; i < RIO_INB_ATMU_COUNT; i++) {
+		riwar = in_be32(&priv->inb_atmu_regs[i].riwar);
+		if ((riwar & RIWAR_ENABLE) == 0)
+			continue;
+		win_start = ((u64)(in_be32(&priv->inb_atmu_regs[i].riwbar) & RIWBAR_BADD_MASK))
+			<< RIWBAR_BADD_VAL_SHIFT;
+		win_end = win_start + ((1 << ((riwar & RIWAR_SIZE_MASK) + 1)) - 1);
+		if (rstart < win_end && (rstart + size) > win_start)
+			return -EINVAL;
+	}
+
+	/* find unused atmu */
+	for (i = 0; i < RIO_INB_ATMU_COUNT; i++) {
+		riwar = in_be32(&priv->inb_atmu_regs[i].riwar);
+		if ((riwar & RIWAR_ENABLE) == 0)
+			break;
+	}
+	if (i >= RIO_INB_ATMU_COUNT)
+		return -ENOMEM;
+
+	out_be32(&priv->inb_atmu_regs[i].riwtar, lstart >> RIWTAR_TRAD_VAL_SHIFT);
+	out_be32(&priv->inb_atmu_regs[i].riwbar, rstart >> RIWBAR_BADD_VAL_SHIFT);
+	out_be32(&priv->inb_atmu_regs[i].riwar, RIWAR_ENABLE | RIWAR_TGINT_LOCAL |
+		RIWAR_RDTYP_SNOOP | RIWAR_WRTYP_SNOOP | (base_size_log - 1));
+
+	return 0;
+}
+
+void fsl_unmap_inb_mem(struct rio_mport *mport, dma_addr_t lstart)
+{
+	u32 win_start_shift, base_start_shift;
+	struct rio_priv *priv = mport->priv;
+	u32 riwar, riwtar;
+	int i;
+
+	/* skip default window */
+	base_start_shift = lstart >> RIWTAR_TRAD_VAL_SHIFT;
+	for (i = 0; i < RIO_INB_ATMU_COUNT; i++) {
+		riwar = in_be32(&priv->inb_atmu_regs[i].riwar);
+		if ((riwar & RIWAR_ENABLE) == 0)
+			continue;
+
+		riwtar = in_be32(&priv->inb_atmu_regs[i].riwtar);
+		win_start_shift = riwtar & RIWTAR_TRAD_MASK;
+		if (win_start_shift == base_start_shift) {
+			out_be32(&priv->inb_atmu_regs[i].riwar, riwar & ~RIWAR_ENABLE);
+			return;
+		}
+	}
+}
+
 void fsl_rio_port_error_handler(int offset)
 {
 	/*XXX: Error recovery is not implemented, we just clear errors */
···
 	ops->add_outb_message = fsl_add_outb_message;
 	ops->add_inb_buffer = fsl_add_inb_buffer;
 	ops->get_inb_message = fsl_get_inb_message;
+	ops->map_inb = fsl_map_inb_mem;
+	ops->unmap_inb = fsl_unmap_inb_mem;
 
 	rmu_node = of_parse_phandle(dev->dev.of_node, "fsl,srio-rmu-handle", 0);
 	if (!rmu_node) {
···
 			RIO_ATMU_REGS_PORT2_OFFSET));
 
 		priv->maint_atmu_regs = priv->atmu_regs + 1;
+		priv->inb_atmu_regs = (struct rio_inb_atmu_regs __iomem *)
+			(priv->regs_win +
+			((i == 0) ? RIO_INB_ATMU_REGS_PORT1_OFFSET :
+			RIO_INB_ATMU_REGS_PORT2_OFFSET));
+
 
 		/* Set to receive any dist ID for serial RapidIO controller. */
 		if (port->phy_type == RIO_PHY_SERIAL)
···
 		rio_law_start = range_start;
 
 		fsl_rio_setup_rmu(port, rmu_np[i]);
+		fsl_rio_inbound_mem_init(priv);
 
 		dbell->mport[i] = port;
 

arch/powerpc/sysdev/fsl_rio.h

···
 #define RIO_S_DBELL_REGS_OFFSET	0x13400
 #define RIO_S_PW_REGS_OFFSET	0x134e0
 #define RIO_ATMU_REGS_DBELL_OFFSET	0x10C40
+#define RIO_INB_ATMU_REGS_PORT1_OFFSET 0x10d60
+#define RIO_INB_ATMU_REGS_PORT2_OFFSET 0x10f60
 
 #define MAX_MSG_UNIT_NUM	2
 #define MAX_PORT_NUM		4
+#define RIO_INB_ATMU_COUNT	4
 
 struct rio_atmu_regs {
 	 u32 rowtar;
···
 	 u32 pad1;
 	 u32 rowar;
 	 u32 pad2[3];
+};
+
+struct rio_inb_atmu_regs {
+	u32 riwtar;
+	u32 pad1;
+	u32 riwbar;
+	u32 pad2;
+	u32 riwar;
+	u32 pad3[3];
 };
 
 struct rio_dbell_ring {
···
 	void __iomem *regs_win;
 	struct rio_atmu_regs __iomem *atmu_regs;
 	struct rio_atmu_regs __iomem *maint_atmu_regs;
+	struct rio_inb_atmu_regs __iomem *inb_atmu_regs;
 	void __iomem *maint_win;
 	void *rmm_handle; /* RapidIO message manager(unit) Handle */
 };

arch/powerpc/sysdev/fsl_soc.c

···
 	if (!rstcr && ppc_md.restart == fsl_rstcr_restart)
 		printk(KERN_ERR "No RSTCR register, warm reboot won't work\n");
 
-	if (np)
-		of_node_put(np);
+	of_node_put(np);
 
 	return 0;
 }
···
 /*
  * Halt the current partition
  *
- * This function should be assigned to the ppc_md.power_off and ppc_md.halt
+ * This function should be assigned to the pm_power_off and ppc_md.halt
  * function pointers, to shut down the partition when we're running under
  * the Freescale hypervisor.
  */

arch/powerpc/sysdev/ipic.c

···
 #include <linux/signal.h>
 #include <linux/syscore_ops.h>
 #include <linux/device.h>
-#include <linux/bootmem.h>
 #include <linux/spinlock.h>
 #include <linux/fsl_devices.h>
 #include <asm/irq.h>

arch/powerpc/sysdev/mpc5xxx_clocks.c

···
 		of_node_put(node);
 		node = np;
 	}
-	if (node)
-		of_node_put(node);
+	of_node_put(node);
 
 	return p_bus_freq ? *p_bus_freq : 0;
 }

arch/powerpc/sysdev/mpic.c

···
 #include <linux/irq.h>
 #include <linux/smp.h>
 #include <linux/interrupt.h>
-#include <linux/bootmem.h>
 #include <linux/spinlock.h>
 #include <linux/pci.h>
 #include <linux/slab.h>

arch/powerpc/sysdev/mpic_pasemi_msi.c

···
 #undef DEBUG
 
 #include <linux/irq.h>
-#include <linux/bootmem.h>
 #include <linux/msi.h>
 #include <asm/mpic.h>
 #include <asm/prom.h>

arch/powerpc/sysdev/mpic_u3msi.c

···
  */
 
 #include <linux/irq.h>
-#include <linux/bootmem.h>
 #include <linux/msi.h>
 #include <asm/mpic.h>
 #include <asm/prom.h>

arch/powerpc/sysdev/ppc4xx_cpm.c

···
 		printk(KERN_ERR "cpm: could not parse dcr property for %s\n",
 		       np->full_name);
 		ret = -EINVAL;
-		goto out;
+		goto node_put;
 	}
 
 	cpm.dcr_host = dcr_map(np, dcr_base, dcr_len);
···
 		printk(KERN_ERR "cpm: failed to map dcr property for %s\n",
 		       np->full_name);
 		ret = -EINVAL;
-		goto out;
+		goto node_put;
 	}
 
 	/* All 4xx SoCs with a CPM controller have one of two
···
 
 	if (cpm.standby || cpm.suspend)
 		suspend_set_ops(&cpm_suspend_ops);
+node_put:
+	of_node_put(np);
 out:
-	if (np)
-		of_node_put(np);
 	return ret;
 }
 

arch/powerpc/sysdev/ppc4xx_msi.c

···
  */
 
 #include <linux/irq.h>
-#include <linux/bootmem.h>
 #include <linux/pci.h>
 #include <linux/msi.h>
 #include <linux/of_platform.h>

arch/powerpc/sysdev/ppc4xx_pci.c

···
 #include <linux/pci.h>
 #include <linux/init.h>
 #include <linux/of.h>
-#include <linux/bootmem.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
 

arch/powerpc/sysdev/qe_lib/qe.c

···
 #include <linux/spinlock.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
-#include <linux/bootmem.h>
 #include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/ioport.h>

arch/powerpc/sysdev/qe_lib/qe_ic.c

···
 #include <linux/sched.h>
 #include <linux/signal.h>
 #include <linux/device.h>
-#include <linux/bootmem.h>
 #include <linux/spinlock.h>
 #include <asm/irq.h>
 #include <asm/io.h>

arch/powerpc/sysdev/uic.c

···
 #include <linux/sched.h>
 #include <linux/signal.h>
 #include <linux/device.h>
-#include <linux/bootmem.h>
 #include <linux/spinlock.h>
 #include <linux/irq.h>
 #include <linux/interrupt.h>

arch/powerpc/sysdev/xics/xics-common.c

···
 
 void xics_teardown_cpu(void)
 {
-	struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr);
+	struct xics_cppr *os_cppr = this_cpu_ptr(&xics_cppr);
 
 	/*
 	 * we have to reset the cppr index to 0 because we're

arch/powerpc/xmon/xmon.c

···
 #include <asm/paca.h>
 #endif
 
+#if defined(CONFIG_PPC_SPLPAR)
+#include <asm/plpar_wrappers.h>
+#else
+static inline long plapr_set_ciabr(unsigned long ciabr) {return 0; };
+#endif
+
 #include "nonstdio.h"
 #include "dis-asm.h"
 
···
 };
 
 /* Bits in bpt.enabled */
-#define BP_IABR_TE	1		/* IABR translation enabled */
-#define BP_IABR		2
-#define BP_TRAP		8
-#define BP_DABR		0x10
+#define BP_CIABR	1
+#define BP_TRAP		2
+#define BP_DABR		4
 
 #define NBPTS	256
 static struct bpt bpts[NBPTS];
···
 static inline void cinval(void *p)
 {
 	asm volatile ("dcbi 0,%0; icbi 0,%0" : : "r" (p));
+}
+
+/**
+ * write_ciabr() - write the CIABR SPR
+ * @ciabr:	The value to write.
+ *
+ * This function writes a value to the CIARB register either directly
+ * through mtspr instruction if the kernel is in HV privilege mode or
+ * call a hypervisor function to achieve the same in case the kernel
+ * is in supervisor privilege mode.
+ */
+static void write_ciabr(unsigned long ciabr)
+{
+	if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+		return;
+
+	if (cpu_has_feature(CPU_FTR_HVMODE)) {
+		mtspr(SPRN_CIABR, ciabr);
+		return;
+	}
+	plapr_set_ciabr(ciabr);
+}
+
+/**
+ * set_ciabr() - set the CIABR
+ * @addr:	The value to set.
+ *
+ * This function sets the correct privilege value into the the HW
+ * breakpoint address before writing it up in the CIABR register.
+ */
+static void set_ciabr(unsigned long addr)
+{
+	addr &= ~CIABR_PRIV;
+
+	if (cpu_has_feature(CPU_FTR_HVMODE))
+		addr |= CIABR_PRIV_HYPER;
+	else
+		addr |= CIABR_PRIV_SUPER;
+	write_ciabr(addr);
 }
 
 /*
···
 
 	bp = bpts;
 	for (i = 0; i < NBPTS; ++i, ++bp) {
-		if ((bp->enabled & (BP_TRAP|BP_IABR)) == 0)
+		if ((bp->enabled & (BP_TRAP|BP_CIABR)) == 0)
 			continue;
 		if (mread(bp->address, &bp->instr[0], 4) != 4) {
 			printf("Couldn't read instruction at %lx, "
···
 			continue;
 		}
 		store_inst(&bp->instr[0]);
-		if (bp->enabled & BP_IABR)
+		if (bp->enabled & BP_CIABR)
 			continue;
 		if (mwrite(bp->address, &bpinstr, 4) != 4) {
 			printf("Couldn't write instruction at %lx, "
···
 		brk.len = 8;
 		__set_breakpoint(&brk);
 	}
-	if (iabr && cpu_has_feature(CPU_FTR_IABR))
-		mtspr(SPRN_IABR, iabr->address
-			 | (iabr->enabled & (BP_IABR|BP_IABR_TE)));
+
+	if (iabr)
+		set_ciabr(iabr->address);
 }
 
 static void remove_bpts(void)
···
 
 	bp = bpts;
 	for (i = 0; i < NBPTS; ++i, ++bp) {
-		if ((bp->enabled & (BP_TRAP|BP_IABR)) != BP_TRAP)
+		if ((bp->enabled & (BP_TRAP|BP_CIABR)) != BP_TRAP)
 			continue;
 		if (mread(bp->address, &instr, 4) == 4
 		    && instr == bpinstr
···
 static void remove_cpu_bpts(void)
 {
 	hw_breakpoint_disable();
-	if (cpu_has_feature(CPU_FTR_IABR))
-		mtspr(SPRN_IABR, 0);
+	write_ciabr(0);
 }
 
 /* Command interpreting routine */
···
 		case 'u':
 			dump_segments();
 			break;
-#elif defined(CONFIG_4xx)
+#elif defined(CONFIG_44x)
 		case 'u':
 			dump_tlb_44x();
 			break;
···
 	else if (cmd == 'h')
 		ppc_md.halt();
 	else if (cmd == 'p')
-		ppc_md.power_off();
+		if (pm_power_off)
+			pm_power_off();
 }
 
 static int cpu_cmd(void)
···
     "b <addr> [cnt]   set breakpoint at given instr addr\n"
     "bc               clear all breakpoints\n"
     "bc <n/addr>      clear breakpoint number n or at addr\n"
-    "bi <addr> [cnt]  set hardware instr breakpoint (POWER3/RS64 only)\n"
+    "bi <addr> [cnt]  set hardware instr breakpoint (POWER8 only)\n"
     "bd <addr> [cnt]  set hardware data breakpoint\n"
     "";
 
···
 		break;
 
 	case 'i':	/* bi - hardware instr breakpoint */
-		if (!cpu_has_feature(CPU_FTR_IABR)) {
+		if (!cpu_has_feature(CPU_FTR_ARCH_207S)) {
 			printf("Hardware instruction breakpoint "
 			       "not supported on this cpu\n");
 			break;
 		}
 		if (iabr) {
-			iabr->enabled &= ~(BP_IABR | BP_IABR_TE);
+			iabr->enabled &= ~BP_CIABR;
 			iabr = NULL;
 		}
 		if (!scanhex(&a))
···
 			break;
 		bp = new_breakpoint(a);
 		if (bp != NULL) {
-			bp->enabled |= BP_IABR | BP_IABR_TE;
+			bp->enabled |= BP_CIABR;
 			iabr = bp;
 		}
 		break;
···
 				if (!bp->enabled)
 					continue;
 				printf("%2x %s   ", BP_NUM(bp),
-				    (bp->enabled & BP_IABR)? "inst": "trap");
+				    (bp->enabled & BP_CIABR) ? "inst": "trap");
 				xmon_print_symbol(bp->address, "  ", "\n");
 			}
 			break;

drivers/misc/cxl/cxl.h

···
 struct cxl_afu {
 	irq_hw_number_t psl_hwirq;
 	irq_hw_number_t serr_hwirq;
+	char *err_irq_name;
+	char *psl_irq_name;
 	unsigned int serr_virq;
 	void __iomem *p1n_mmio;
 	void __iomem *p2n_mmio;
···
 	bool enabled;
 };
 
+
+struct cxl_irq_name {
+	struct list_head list;
+	char *name;
+};
+
 /*
  * This is a cxl context.  If the PSL is in dedicated mode, there will be one
  * of these per AFU.  If in AFU directed there can be lots of these.
···
 
 	unsigned long *irq_bitmap; /* Accessed from IRQ context */
 	struct cxl_irq_ranges irqs;
+	struct list_head irq_names;
 	u64 fault_addr;
 	u64 fault_dsisr;
 	u64 afu_err;
···
 	struct dentry *trace;
 	struct dentry *psl_err_chk;
 	struct dentry *debugfs;
+	char *irq_name;
 	struct bin_attribute cxl_attr;
 	int adapter_num;
 	int user_irqs;
···
 int cxl_afu_deactivate_mode(struct cxl_afu *afu);
 int cxl_afu_select_best_mode(struct cxl_afu *afu);
 
-unsigned int cxl_map_irq(struct cxl *adapter, irq_hw_number_t hwirq,
-		         irq_handler_t handler, void *cookie);
-void cxl_unmap_irq(unsigned int virq, void *cookie);
 int cxl_register_psl_irq(struct cxl_afu *afu);
 void cxl_release_psl_irq(struct cxl_afu *afu);
 int cxl_register_psl_err_irq(struct cxl *adapter);
···
 			    u64 amr);
 int cxl_detach_process(struct cxl_context *ctx);
 
-int cxl_get_irq(struct cxl_context *ctx, struct cxl_irq_info *info);
+int cxl_get_irq(struct cxl_afu *afu, struct cxl_irq_info *info);
 int cxl_ack_irq(struct cxl_context *ctx, u64 tfc, u64 psl_reset_mask);
 
 int cxl_check_error(struct cxl_afu *afu);

drivers/misc/cxl/fault.c

···
 {
 	unsigned flt = 0;
 	int result;
-	unsigned long access, flags;
+	unsigned long access, flags, inv_flags = 0;
 
 	if ((result = copro_handle_mm_fault(mm, dar, dsisr, &flt))) {
 		pr_devel("copro_handle_mm_fault failed: %#x\n", result);
···
 		access |= _PAGE_RW;
 	if ((!ctx->kernel) || ~(dar & (1ULL << 63)))
 		access |= _PAGE_USER;
+
+	if (dsisr & DSISR_NOHPTE)
+		inv_flags |= HPTE_NOHPTE_UPDATE;
+
 	local_irq_save(flags);
-	hash_page_mm(mm, dar, access, 0x300);
+	hash_page_mm(mm, dar, access, 0x300, inv_flags);
 	local_irq_restore(flags);
 
 	pr_devel("Page fault successfully handled for pe: %i!\n", ctx->pe);

drivers/misc/cxl/irq.c

···
 	return IRQ_HANDLED;
 }
 
-static irqreturn_t cxl_irq(int irq, void *data)
+static irqreturn_t cxl_irq(int irq, void *data, struct cxl_irq_info *irq_info)
 {
 	struct cxl_context *ctx = data;
-	struct cxl_irq_info irq_info;
 	u64 dsisr, dar;
-	int result;
 
-	if ((result = cxl_get_irq(ctx, &irq_info))) {
-		WARN(1, "Unable to get CXL IRQ Info: %i\n", result);
-		return IRQ_HANDLED;
-	}
-
-	dsisr = irq_info.dsisr;
-	dar = irq_info.dar;
+	dsisr = irq_info->dsisr;
+	dar = irq_info->dar;
 
 	pr_devel("CXL interrupt %i for afu pe: %i DSISR: %#llx DAR: %#llx\n", irq, ctx->pe, dsisr, dar);
 
···
 	if (dsisr & CXL_PSL_DSISR_An_UR)
 		pr_devel("CXL interrupt: AURP PTE not found\n");
 	if (dsisr & CXL_PSL_DSISR_An_PE)
-		return handle_psl_slice_error(ctx, dsisr, irq_info.errstat);
+		return handle_psl_slice_error(ctx, dsisr, irq_info->errstat);
 	if (dsisr & CXL_PSL_DSISR_An_AE) {
-		pr_devel("CXL interrupt: AFU Error %.llx\n", irq_info.afu_err);
+		pr_devel("CXL interrupt: AFU Error %.llx\n", irq_info->afu_err);
 
 		if (ctx->pending_afu_err) {
 			/*
···
 			 */
 			dev_err_ratelimited(&ctx->afu->dev, "CXL AFU Error "
 					    "undelivered to pe %i: %.llx\n",
-					    ctx->pe, irq_info.afu_err);
+					    ctx->pe, irq_info->afu_err);
 		} else {
 			spin_lock(&ctx->lock);
-			ctx->afu_err = irq_info.afu_err;
+			ctx->afu_err = irq_info->afu_err;
 			ctx->pending_afu_err = 1;
 			spin_unlock(&ctx->lock);
 
···
 	return IRQ_HANDLED;
 }
 
+static irqreturn_t fail_psl_irq(struct cxl_afu *afu, struct cxl_irq_info *irq_info)
+{
+	if (irq_info->dsisr & CXL_PSL_DSISR_TRANS)
+		cxl_p2n_write(afu, CXL_PSL_TFC_An, CXL_PSL_TFC_An_AE);
+	else
+		cxl_p2n_write(afu, CXL_PSL_TFC_An, CXL_PSL_TFC_An_A);
+
+	return IRQ_HANDLED;
+}
+
 static irqreturn_t cxl_irq_multiplexed(int irq, void *data)
 {
 	struct cxl_afu *afu = data;
 	struct cxl_context *ctx;
+	struct cxl_irq_info irq_info;
 	int ph = cxl_p2n_read(afu, CXL_PSL_PEHandle_An) & 0xffff;
 	int ret;
+
+	if ((ret = cxl_get_irq(afu, &irq_info))) {
+		WARN(1, "Unable to get CXL IRQ Info: %i\n", ret);
+		return fail_psl_irq(afu, &irq_info);
+	}
 
 	rcu_read_lock();
 	ctx = idr_find(&afu->contexts_idr, ph);
 	if (ctx) {
-		ret = cxl_irq(irq, ctx);
+		ret = cxl_irq(irq, ctx, &irq_info);
 		rcu_read_unlock();
 		return ret;
 	}
 	rcu_read_unlock();
 
-	WARN(1, "Unable to demultiplex CXL PSL IRQ\n");
-	return IRQ_HANDLED;
+	WARN(1, "Unable to demultiplex CXL PSL IRQ for PE %i DSISR %.16llx DAR"
+		" %.16llx\n(Possible AFU HW issue - was a term/remove acked"
+		" with outstanding transactions?)\n", ph, irq_info.dsisr,
+		irq_info.dar);
+	return fail_psl_irq(afu, &irq_info);
 }
 
 static irqreturn_t cxl_irq_afu(int irq, void *data)
···
 }
 
 unsigned int cxl_map_irq(struct cxl *adapter, irq_hw_number_t hwirq,
-			 irq_handler_t handler, void *cookie)
+			 irq_handler_t handler, void *cookie, const char *name)
 {
 	unsigned int virq;
 	int result;
···
 
 	pr_devel("hwirq %#lx mapped to virq %u\n", hwirq, virq);
 
-	result = request_irq(virq, handler, 0, "cxl", cookie);
+	result = request_irq(virq, handler, 0, name, cookie);
 	if (result) {
 		dev_warn(&adapter->dev, "cxl_map_irq: request_irq failed: %i\n", result);
 		return 0;
···
 				irq_handler_t handler,
 				void *cookie,
 				irq_hw_number_t *dest_hwirq,
-				unsigned int *dest_virq)
+				unsigned int *dest_virq,
+				const char *name)
 {
 	int hwirq, virq;
 
 	if ((hwirq = cxl_alloc_one_irq(adapter)) < 0)
 		return hwirq;
 
-	if (!(virq = cxl_map_irq(adapter, hwirq, handler, cookie)))
+	if (!(virq = cxl_map_irq(adapter, hwirq, handler, cookie, name)))
 		goto err;
 
 	*dest_hwirq = hwirq;
···
 {
 	int rc;
 
+	adapter->irq_name = kasprintf(GFP_KERNEL, "cxl-%s-err",
+				      dev_name(&adapter->dev));
+	if (!adapter->irq_name)
+		return -ENOMEM;
+
 	if ((rc = cxl_register_one_irq(adapter, cxl_irq_err, adapter,
 				       &adapter->err_hwirq,
-				       &adapter->err_virq)))
+				       &adapter->err_virq,
+				       adapter->irq_name))) {
+		kfree(adapter->irq_name);
+		adapter->irq_name = NULL;
 		return rc;
+	}
 
 	cxl_p1_write(adapter, CXL_PSL_ErrIVTE, adapter->err_hwirq & 0xffff);
 
···
 	cxl_p1_write(adapter, CXL_PSL_ErrIVTE, 0x0000000000000000);
 	cxl_unmap_irq(adapter->err_virq, adapter);
 	cxl_release_one_irq(adapter, adapter->err_hwirq);
+	kfree(adapter->irq_name);
 }
 
 int cxl_register_serr_irq(struct cxl_afu *afu)
···
 	u64 serr;
 	int rc;
 
+	afu->err_irq_name = kasprintf(GFP_KERNEL, "cxl-%s-err",
+				      dev_name(&afu->dev));
+	if (!afu->err_irq_name)
+		return -ENOMEM;
+
 	if ((rc = cxl_register_one_irq(afu->adapter, cxl_slice_irq_err, afu,
 				       &afu->serr_hwirq,
-				       &afu->serr_virq)))
+				       &afu->serr_virq, afu->err_irq_name))) {
+		kfree(afu->err_irq_name);
+		afu->err_irq_name = NULL;
 		return rc;
+	}
 
 	serr = cxl_p1n_read(afu, CXL_PSL_SERR_An);
 	serr = (serr & 0x00ffffffffff0000ULL) | (afu->serr_hwirq & 0xffff);
···
 	cxl_p1n_write(afu, CXL_PSL_SERR_An, 0x0000000000000000);
 	cxl_unmap_irq(afu->serr_virq, afu);
 	cxl_release_one_irq(afu->adapter, afu->serr_hwirq);
+	kfree(afu->err_irq_name);
 }
 
 int cxl_register_psl_irq(struct cxl_afu *afu)
 {
-	return cxl_register_one_irq(afu->adapter, cxl_irq_multiplexed, afu,
-			&afu->psl_hwirq, &afu->psl_virq);
+	int rc;
+
+	afu->psl_irq_name = kasprintf(GFP_KERNEL, "cxl-%s",
+				      dev_name(&afu->dev));
+	if (!afu->psl_irq_name)
+		return -ENOMEM;
+
+	if ((rc = cxl_register_one_irq(afu->adapter, cxl_irq_multiplexed, afu,
+				    &afu->psl_hwirq, &afu->psl_virq,
+				    afu->psl_irq_name))) {
+		kfree(afu->psl_irq_name);
+		afu->psl_irq_name = NULL;
+	}
+	return rc;
 }
 
 void cxl_release_psl_irq(struct cxl_afu *afu)
 {
 	cxl_unmap_irq(afu->psl_virq, afu);
 	cxl_release_one_irq(afu->adapter, afu->psl_hwirq);
+	kfree(afu->psl_irq_name);
+}
+
+void afu_irq_name_free(struct cxl_context *ctx)
+{
+	struct cxl_irq_name *irq_name, *tmp;
+
+	list_for_each_entry_safe(irq_name, tmp, &ctx->irq_names, list) {
+		kfree(irq_name->name);
+		list_del(&irq_name->list);
+		kfree(irq_name);
+	}
 }
 
 int afu_register_irqs(struct cxl_context *ctx, u32 count)
 {
 	irq_hw_number_t hwirq;
-	int rc, r, i;
+	int rc, r, i, j = 1;
+	struct cxl_irq_name *irq_name;
 
 	if ((rc = cxl_alloc_irq_ranges(&ctx->irqs, ctx->afu->adapter, count)))
 		return rc;
···
 				  sizeof(*ctx->irq_bitmap), GFP_KERNEL);
 	if (!ctx->irq_bitmap)
 		return -ENOMEM;
+
+	/*
+	 * Allocate names first.  If any fail, bail out before allocating
+	 * actual hardware IRQs.
+	 */
+	INIT_LIST_HEAD(&ctx->irq_names);
+	for (r = 1; r < CXL_IRQ_RANGES; r++) {
+		for (i = 0; i < ctx->irqs.range[r]; hwirq++, i++) {
+			irq_name = kmalloc(sizeof(struct cxl_irq_name),
+					   GFP_KERNEL);
+			if (!irq_name)
+				goto out;
+			irq_name->name = kasprintf(GFP_KERNEL, "cxl-%s-pe%i-%i",
+						   dev_name(&ctx->afu->dev),
+						   ctx->pe, j);
+			if (!irq_name->name) {
+				kfree(irq_name);
+				goto out;
+			}
+			/* Add to tail so next look get the correct order */
+			list_add_tail(&irq_name->list, &ctx->irq_names);
+			j++;
+		}
+	}
+
+	/* We've allocated all memory now, so let's do the irq allocations */
+	irq_name = list_first_entry(&ctx->irq_names, struct cxl_irq_name, list);
 	for (r = 1; r < CXL_IRQ_RANGES; r++) {
 		hwirq = ctx->irqs.offset[r];
 		for (i = 0; i < ctx->irqs.range[r]; hwirq++, i++) {
 			cxl_map_irq(ctx->afu->adapter, hwirq,
-				     cxl_irq_afu, ctx);
+				    cxl_irq_afu, ctx, irq_name->name);
+			irq_name = list_next_entry(irq_name, list);
 		}
 	}
 
 	return 0;
+
+out:
+	afu_irq_name_free(ctx);
+	return -ENOMEM;
 }
 
 void afu_release_irqs(struct cxl_context *ctx)
···
 		}
 	}
 
+	afu_irq_name_free(ctx);
 	cxl_release_irq_ranges(&ctx->irqs, ctx->afu->adapter);
 }

drivers/misc/cxl/native.c

···
 	return detach_process_native_afu_directed(ctx);
 }
 
-int cxl_get_irq(struct cxl_context *ctx, struct cxl_irq_info *info)
+int cxl_get_irq(struct cxl_afu *afu, struct cxl_irq_info *info)
 {
 	u64 pidtid;
 
-	info->dsisr = cxl_p2n_read(ctx->afu, CXL_PSL_DSISR_An);
-	info->dar = cxl_p2n_read(ctx->afu, CXL_PSL_DAR_An);
-	info->dsr = cxl_p2n_read(ctx->afu, CXL_PSL_DSR_An);
-	pidtid = cxl_p2n_read(ctx->afu, CXL_PSL_PID_TID_An);
+	info->dsisr = cxl_p2n_read(afu, CXL_PSL_DSISR_An);
+	info->dar = cxl_p2n_read(afu, CXL_PSL_DAR_An);
+	info->dsr = cxl_p2n_read(afu, CXL_PSL_DSR_An);
+	pidtid = cxl_p2n_read(afu, CXL_PSL_PID_TID_An);
 	info->pid = pidtid >> 32;
 	info->tid = pidtid & 0xffffffff;
-	info->afu_err = cxl_p2n_read(ctx->afu, CXL_AFU_ERR_An);
-	info->errstat = cxl_p2n_read(ctx->afu, CXL_PSL_ErrStat_An);
+	info->afu_err = cxl_p2n_read(afu, CXL_AFU_ERR_An);
+	info->errstat = cxl_p2n_read(afu, CXL_PSL_ErrStat_An);
 
 	return 0;
 }

drivers/rtc/Kconfig

···
 	  If you say yes here you get support for the RTC subsystem of the
 	  NUC910/NUC920 used in embedded systems.
 
+config RTC_DRV_OPAL
+	tristate "IBM OPAL RTC driver"
+	depends on PPC_POWERNV
+	default y
+	help
+	  If you say yes here you get support for the PowerNV platform RTC
+	  driver based on OPAL interfaces.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called rtc-opal.
+
 comment "on-CPU RTC drivers"
 
 config RTC_DRV_DAVINCI

drivers/rtc/Makefile

···
 obj-$(CONFIG_RTC_DRV_MPC5121)	+= rtc-mpc5121.o
 obj-$(CONFIG_RTC_DRV_MV)	+= rtc-mv.o
 obj-$(CONFIG_RTC_DRV_NUC900)	+= rtc-nuc900.o
+obj-$(CONFIG_RTC_DRV_OPAL)	+= rtc-opal.o
 obj-$(CONFIG_RTC_DRV_OMAP)	+= rtc-omap.o
 obj-$(CONFIG_RTC_DRV_PALMAS)	+= rtc-palmas.o
 obj-$(CONFIG_RTC_DRV_PCAP)	+= rtc-pcap.o

drivers/rtc/rtc-opal.c

···
+/*
+ * IBM OPAL RTC driver
+ * Copyright (C) 2014 IBM
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.
+ */
+
+#define DRVNAME		"rtc-opal"
+#define pr_fmt(fmt)	DRVNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/err.h>
+#include <linux/rtc.h>
+#include <linux/delay.h>
+#include <linux/bcd.h>
+#include <linux/platform_device.h>
+#include <linux/of.h>
+#include <asm/opal.h>
+#include <asm/firmware.h>
+
+static void opal_to_tm(u32 y_m_d, u64 h_m_s_ms, struct rtc_time *tm)
+{
+	tm->tm_year = ((bcd2bin(y_m_d >> 24) * 100) +
+		       bcd2bin((y_m_d >> 16) & 0xff)) - 1900;
+	tm->tm_mon  = bcd2bin((y_m_d >> 8) & 0xff) - 1;
+	tm->tm_mday = bcd2bin(y_m_d & 0xff);
+	tm->tm_hour = bcd2bin((h_m_s_ms >> 56) & 0xff);
+	tm->tm_min  = bcd2bin((h_m_s_ms >> 48) & 0xff);
+	tm->tm_sec  = bcd2bin((h_m_s_ms >> 40) & 0xff);
+
+	GregorianDay(tm);
+}
+
+static void tm_to_opal(struct rtc_time *tm, u32 *y_m_d, u64 *h_m_s_ms)
+{
+	*y_m_d |= ((u32)bin2bcd((tm->tm_year + 1900) / 100)) << 24;
+	*y_m_d |= ((u32)bin2bcd((tm->tm_year + 1900) % 100)) << 16;
+	*y_m_d |= ((u32)bin2bcd((tm->tm_mon + 1))) << 8;
+	*y_m_d |= ((u32)bin2bcd(tm->tm_mday));
+
+	*h_m_s_ms |= ((u64)bin2bcd(tm->tm_hour)) << 56;
+	*h_m_s_ms |= ((u64)bin2bcd(tm->tm_min)) << 48;
+	*h_m_s_ms |= ((u64)bin2bcd(tm->tm_sec)) << 40;
+}
+
+static int opal_get_rtc_time(struct device *dev, struct rtc_time *tm)
+{
+	long rc = OPAL_BUSY;
+	u32 y_m_d;
+	u64 h_m_s_ms;
+	__be32 __y_m_d;
+	__be64 __h_m_s_ms;
+
+	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+		rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms);
+		if (rc == OPAL_BUSY_EVENT)
+			opal_poll_events(NULL);
+		else
+			msleep(10);
+	}
+
+	if (rc != OPAL_SUCCESS)
+		return -EIO;
+
+	y_m_d = be32_to_cpu(__y_m_d);
+	h_m_s_ms = be64_to_cpu(__h_m_s_ms);
+	opal_to_tm(y_m_d, h_m_s_ms, tm);
+
+	return 0;
+}
+
+static int opal_set_rtc_time(struct device *dev, struct rtc_time *tm)
+{
+	long rc = OPAL_BUSY;
+	u32 y_m_d = 0;
+	u64 h_m_s_ms = 0;
+
+	tm_to_opal(tm, &y_m_d, &h_m_s_ms);
+	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+		rc = opal_rtc_write(y_m_d, h_m_s_ms);
+		if (rc == OPAL_BUSY_EVENT)
+			opal_poll_events(NULL);
+		else
+			msleep(10);
+	}
+
+	return rc == OPAL_SUCCESS ? 0 : -EIO;
+}
+
+/*
+ * TPO	Timed Power-On
+ *
+ * TPO get/set OPAL calls care about the hour and min and to make it consistent
+ * with the rtc utility time conversion functions, we use the 'u64' to store
+ * its value and perform bit shift by 32 before use..
+ */
+static int opal_get_tpo_time(struct device *dev, struct rtc_wkalrm *alarm)
+{
+	__be32 __y_m_d, __h_m;
+	struct opal_msg msg;
+	int rc, token;
+	u64 h_m_s_ms;
+	u32 y_m_d;
+
+	token = opal_async_get_token_interruptible();
+	if (token < 0) {
+		if (token != -ERESTARTSYS)
+			pr_err("Failed to get the async token\n");
+
+		return token;
+	}
+
+	rc = opal_tpo_read(token, &__y_m_d, &__h_m);
+	if (rc != OPAL_ASYNC_COMPLETION) {
+		rc = -EIO;
+		goto exit;
+	}
+
+	rc = opal_async_wait_response(token, &msg);
+	if (rc) {
+		rc = -EIO;
+		goto exit;
+	}
+
+	rc = be64_to_cpu(msg.params[1]);
+	if (rc != OPAL_SUCCESS) {
+		rc = -EIO;
+		goto exit;
+	}
+
+	y_m_d = be32_to_cpu(__y_m_d);
+	h_m_s_ms = ((u64)be32_to_cpu(__h_m) << 32);
+	opal_to_tm(y_m_d, h_m_s_ms, &alarm->time);
+
+exit:
+	opal_async_release_token(token);
+	return rc;
+}
+
+/* Set Timed Power-On */
+static int opal_set_tpo_time(struct device *dev, struct rtc_wkalrm *alarm)
+{
+	u64 h_m_s_ms = 0, token;
+	struct opal_msg msg;
+	u32 y_m_d = 0;
+	int rc;
+
+	tm_to_opal(&alarm->time, &y_m_d, &h_m_s_ms);
+
+	token = opal_async_get_token_interruptible();
+	if (token < 0) {
+		if (token != -ERESTARTSYS)
+			pr_err("Failed to get the async token\n");
+
+		return token;
+	}
+
+	/* TPO, we care about hour and minute */
+	rc = opal_tpo_write(token, y_m_d,
+			    (u32)((h_m_s_ms >> 32) & 0xffff0000));
+	if (rc != OPAL_ASYNC_COMPLETION) {
+		rc = -EIO;
+		goto exit;
+	}
+
+	rc = opal_async_wait_response(token, &msg);
+	if (rc) {
+		rc = -EIO;
+		goto exit;
+	}
+
+	rc = be64_to_cpu(msg.params[1]);
+	if (rc != OPAL_SUCCESS)
+		rc = -EIO;
+
+exit:
+	opal_async_release_token(token);
+	return rc;
+}
+
+static const struct rtc_class_ops opal_rtc_ops = {
+	.read_time	= opal_get_rtc_time,
+	.set_time	= opal_set_rtc_time,
+	.read_alarm	= opal_get_tpo_time,
+	.set_alarm	= opal_set_tpo_time,
+};
+
+static int opal_rtc_probe(struct platform_device *pdev)
+{
+	struct rtc_device *rtc;
+
+	if (pdev->dev.of_node && of_get_property(pdev->dev.of_node, "has-tpo",
+						 NULL))
+		device_set_wakeup_capable(&pdev->dev, true);
+
+	rtc = devm_rtc_device_register(&pdev->dev, DRVNAME, &opal_rtc_ops,
+				       THIS_MODULE);
+	if (IS_ERR(rtc))
+		return PTR_ERR(rtc);
+
+	rtc->uie_unsupported = 1;
+
+	return 0;
+}
+
+static const struct of_device_id opal_rtc_match[] = {
+	{
+		.compatible	= "ibm,opal-rtc",
+	},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, opal_rtc_match);
+
+static const struct platform_device_id opal_rtc_driver_ids[] = {
+	{
+		.name		= "opal-rtc",
+	},
+	{ }
+};
+MODULE_DEVICE_TABLE(platform, opal_rtc_driver_ids);
+
+static struct platform_driver opal_rtc_driver = {
+	.probe		= opal_rtc_probe,
+	.id_table	= opal_rtc_driver_ids,
+	.driver		= {
+		.name		= DRVNAME,
+		.owner		= THIS_MODULE,
+		.of_match_table	= opal_rtc_match,
+	},
+};
+
+static int __init opal_rtc_init(void)
+{
+	if (!firmware_has_feature(FW_FEATURE_OPAL))
+		return -ENODEV;
+
+	return platform_driver_register(&opal_rtc_driver);
+}
+
+static void __exit opal_rtc_exit(void)
+{
+	platform_driver_unregister(&opal_rtc_driver);
+}
+
+MODULE_AUTHOR("Neelesh Gupta <[e-mail]>");
+MODULE_DESCRIPTION("IBM OPAL RTC driver");
+MODULE_LICENSE("GPL");
+
+module_init(opal_rtc_init);
+module_exit(opal_rtc_exit);

include/linux/hugetlb.h

···
 }
 
 #endif /* !CONFIG_HUGETLB_PAGE */
+/*
+ * hugepages at page global directory. If arch support
+ * hugepages at pgd level, they need to define this.
+ */
+#ifndef pgd_huge
+#define pgd_huge(x)	0
+#endif
+
+#ifndef pgd_write
+static inline int pgd_write(pgd_t pgd)
+{
+	BUG();
+	return 0;
+}
+#endif
+
+#ifndef pud_write
+static inline int pud_write(pud_t pud)
+{
+	BUG();
+	return 0;
+}
+#endif
+
+#ifndef is_hugepd
+/*
+ * Some architectures requires a hugepage directory format that is
+ * required to support multiple hugepage sizes. For example
+ * a4fe3ce76 "powerpc/mm: Allow more flexible layouts for hugepage pagetables"
+ * introduced the same on powerpc. This allows for a more flexible hugepage
+ * pagetable layout.
+ */
+typedef struct { unsigned long pd; } hugepd_t;
+#define is_hugepd(hugepd) (0)
+#define __hugepd(x) ((hugepd_t) { (x) })
+static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
+			      unsigned pdshift, unsigned long end,
+			      int write, struct page **pages, int *nr)
+{
+	return 0;
+}
+#else
+extern int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
+		       unsigned pdshift, unsigned long end,
+		       int write, struct page **pages, int *nr);
+#endif
 
 #define HUGETLB_ANON_FILE "anon_hugepage"
 

mm/gup.c

···
 #include <linux/err.h>
 #include <linux/spinlock.h>
 
-#include <linux/hugetlb.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
 #include <linux/rmap.h>
···
 
 #include <linux/sched.h>
 #include <linux/rwsem.h>
+#include <linux/hugetlb.h>
 #include <asm/pgtable.h>
 
 #include "internal.h"
···
 	return 1;
 }
 
+static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
+			unsigned long end, int write,
+			struct page **pages, int *nr)
+{
+	int refs;
+	struct page *head, *page, *tail;
+
+	if (write && !pgd_write(orig))
+		return 0;
+
+	refs = 0;
+	head = pgd_page(orig);
+	page = head + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT);
+	tail = page;
+	do {
+		VM_BUG_ON_PAGE(compound_head(page) != head, page);
+		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(pgd_val(orig) != pgd_val(*pgdp))) {
+		*nr -= refs;
+		while (refs--)
+			put_page(head);
+		return 0;
+	}
+
+	while (refs--) {
+		if (PageTail(tail))
+			get_huge_page_tail(tail);
+		tail++;
+	}
+
+	return 1;
+}
+
 static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 		int write, struct page **pages, int *nr)
 {
···
 				pages, nr))
 				return 0;
 
+		} else if (unlikely(is_hugepd(__hugepd(pmd_val(pmd))))) {
+			/*
+			 * architecture have different format for hugetlbfs
+			 * pmd format and THP pmd format
+			 */
+			if (!gup_huge_pd(__hugepd(pmd_val(pmd)), addr,
+					 PMD_SHIFT, next, write, pages, nr))
+				return 0;
 		} else if (!gup_pte_range(pmd, addr, next, write, pages, nr))
 				return 0;
 	} while (pmdp++, addr = next, addr != end);
···
 	return 1;
 }
 
-static int gup_pud_range(pgd_t *pgdp, unsigned long addr, unsigned long end,
-		int write, struct page **pages, int *nr)
+static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
+			 int write, struct page **pages, int *nr)
 {
 	unsigned long next;
 	pud_t *pudp;
 
-	pudp = pud_offset(pgdp, addr);
+	pudp = pud_offset(&pgd, addr);
 	do {
 		pud_t pud = ACCESS_ONCE(*pudp);
 
 		next = pud_addr_end(addr, end);
 		if (pud_none(pud))
 			return 0;
-		if (pud_huge(pud)) {
+		if (unlikely(pud_huge(pud))) {
 			if (!gup_huge_pud(pud, pudp, addr, next, write,
-					pages, nr))
+					  pages, nr))
+				return 0;
+		} else if (unlikely(is_hugepd(__hugepd(pud_val(pud))))) {
+			if (!gup_huge_pd(__hugepd(pud_val(pud)), addr,
+					 PUD_SHIFT, next, write, pages, nr))
 				return 0;
 		} else if (!gup_pmd_range(pud, addr, next, write, pages, nr))
 			return 0;
···
 	local_irq_save(flags);
 	pgdp = pgd_offset(mm, addr);
 	do {
+		pgd_t pgd = ACCESS_ONCE(*pgdp);
+
 		next = pgd_addr_end(addr, end);
-		if (pgd_none(*pgdp))
+		if (pgd_none(pgd))
 			break;
-		else if (!gup_pud_range(pgdp, addr, next, write, pages, &nr))
+		if (unlikely(pgd_huge(pgd))) {
+			if (!gup_huge_pgd(pgd, pgdp, addr, next, write,
+					  pages, &nr))
+				break;
+		} else if (unlikely(is_hugepd(__hugepd(pgd_val(pgd))))) {
+			if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr,
+					 PGDIR_SHIFT, next, write, pages, &nr))
+				break;
+		} else if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
 			break;
 	} while (pgdp++, addr = next, addr != end);
 	local_irq_restore(flags);