Merge tag 'powerpc-4.5-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Core:
   - Ground work for the new Power9 MMU from Aneesh Kumar K.V
   - Optimise FP/VMX/VSX context switching from Anton Blanchard

  Misc:
   - Various cleanups from Krzysztof Kozlowski, John Ogness, Rashmica
     Gupta, Russell Currey, Gavin Shan, Daniel Axtens, Michael Neuling,
     Andrew Donnellan
   - Allow wrapper to work on non-english system from Laurent Vivier
   - Add rN aliases to the pt_regs_offset table from Rashmica Gupta
   - Fix module autoload for rackmeter & axonram drivers from Luis de
     Bethencourt
   - Include KVM guest test in all interrupt vectors from Paul Mackerras
   - Fix DSCR inheritance over fork() from Anton Blanchard
   - Make value-returning atomics & {cmp}xchg* & their atomic_ versions
     fully ordered from Boqun Feng
   - Print MSR TM bits in oops messages from Michael Neuling
   - Add TM signal return & invalid stack selftests from Michael Neuling
   - Limit EPOW reset event warnings from Vipin K Parashar
   - Remove the Cell QPACE code from Rashmica Gupta
   - Append linux_banner to exception information in xmon from Rashmica
     Gupta
   - Add selftest to check if VSRs are corrupted from Rashmica Gupta
   - Remove broken GregorianDay() from Daniel Axtens
   - Import Anton's context_switch2 benchmark into selftests from
     Michael Ellerman
   - Add selftest script to test HMI functionality from Daniel Axtens
   - Remove obsolete OPAL v2 support from Stewart Smith
   - Make enter_rtas() private from Michael Ellerman
   - PPR exception cleanups from Michael Ellerman
   - Add page soft dirty tracking from Laurent Dufour
   - Add support for Nvlink NPUs from Alistair Popple
   - Add support for kexec on 476fpe from Alistair Popple
   - Enable kernel CPU dlpar from sysfs from Nathan Fontenot
   - Copy only required pieces of the mm_context_t to the paca from
     Michael Neuling
   - Add a kmsg_dumper that flushes OPAL console output on panic from
     Russell Currey
   - Implement save_stack_trace_regs() to enable kprobe stack tracing
     from Steven Rostedt
   - Add HWCAP bits for Power9 from Michael Ellerman
   - Fix _PAGE_PTE breaking swapoff from Aneesh Kumar K.V
   - Fix _PAGE_SWP_SOFT_DIRTY breaking swapoff from Hugh Dickins
   - scripts/recordmcount.pl: support data in text section on powerpc
     from Ulrich Weigand
   - Handle R_PPC64_ENTRY relocations in modules from Ulrich Weigand

  cxl:
   - cxl: Fix possible idr warning when contexts are released from
     Vaibhav Jain
   - cxl: use correct operator when writing pcie config space values
     from Andrew Donnellan
   - cxl: Fix DSI misses when the context owning task exits from Vaibhav
     Jain
   - cxl: fix build for GCC 4.6.x from Brian Norris
   - cxl: use -Werror only with CONFIG_PPC_WERROR from Brian Norris
   - cxl: Enable PCI device ID for future IBM CXL adapter from Uma
     Krishnan

  Freescale:
   - Freescale updates from Scott: Highlights include moving QE code out
     of arch/powerpc (to be shared with arm), device tree updates, and
     minor fixes"

* tag 'powerpc-4.5-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (149 commits)
  powerpc/module: Handle R_PPC64_ENTRY relocations
  scripts/recordmcount.pl: support data in text section on powerpc
  powerpc/powernv: Fix OPAL_CONSOLE_FLUSH prototype and usages
  powerpc/mm: fix _PAGE_SWP_SOFT_DIRTY breaking swapoff
  powerpc/mm: Fix _PAGE_PTE breaking swapoff
  cxl: Enable PCI device ID for future IBM CXL adapter
  cxl: use -Werror only with CONFIG_PPC_WERROR
  cxl: fix build for GCC 4.6.x
  powerpc: Add HWCAP bits for Power9
  powerpc/powernv: Reserve PE#0 on NPU
  powerpc/powernv: Change NPU PE# assignment
  powerpc/powernv: Fix update of NVLink DMA mask
  powerpc/powernv: Remove misleading comment in pci.c
  powerpc: Implement save_stack_trace_regs() to enable kprobe stack tracing
  powerpc: Fix build break due to paca mm_context_t changes
  cxl: Fix DSI misses when the context owning task exits
  MAINTAINERS: Update Scott Wood's e-mail address
  powerpc/powernv: Fix minor off-by-one error in opal_mce_check_early_recovery()
  powerpc: Fix style of self-test config prompts
  powerpc/powernv: Only delay opal_rtc_read() retry when necessary
  ...

Documentation/devicetree/bindings/serial/8250.txt

@@ -14,7 +14,6 @@ Required properties:
 	  tegra132, or tegra210.
 	- "nxp,lpc3220-uart"
 	- "ralink,rt2880-uart"
-	- "ibm,qpace-nwp-serial"
 	- "altr,16550-FIFO32"
 	- "altr,16550-FIFO64"
 	- "altr,16550-FIFO128"

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

@@ -0,0 +1,63 @@
+* Thermal Monitoring Unit (TMU) on Freescale QorIQ SoCs
+
+Required properties:
+- compatible : Must include "fsl,qoriq-tmu". The version of the device is
+	determined by the TMU IP Block Revision Register (IPBRR0) at
+	offset 0x0BF8.
+	Table of correspondences between IPBRR0 values and example  chips:
+		Value           Device
+		----------      -----
+		0x01900102      T1040
+- reg : Address range of TMU registers.
+- interrupts : Contains the interrupt for TMU.
+- fsl,tmu-range : The values to be programmed into TTRnCR, as specified by
+	the SoC reference manual. The first cell is TTR0CR, the second is
+	TTR1CR, etc.
+- fsl,tmu-calibration : A list of cell pairs containing temperature
+	calibration data, as specified by the SoC reference manual.
+	The first cell of each pair is the value to be written to TTCFGR,
+	and the second is the value to be written to TSCFGR.
+
+Example:
+
+tmu@f0000 {
+	compatible = "fsl,qoriq-tmu";
+	reg = <0xf0000 0x1000>;
+	interrupts = <18 2 0 0>;
+	fsl,tmu-range = <0x000a0000 0x00090026 0x0008004a 0x0001006a>;
+	fsl,tmu-calibration = <0x00000000 0x00000025
+			       0x00000001 0x00000028
+			       0x00000002 0x0000002d
+			       0x00000003 0x00000031
+			       0x00000004 0x00000036
+			       0x00000005 0x0000003a
+			       0x00000006 0x00000040
+			       0x00000007 0x00000044
+			       0x00000008 0x0000004a
+			       0x00000009 0x0000004f
+			       0x0000000a 0x00000054
+
+			       0x00010000 0x0000000d
+			       0x00010001 0x00000013
+			       0x00010002 0x00000019
+			       0x00010003 0x0000001f
+			       0x00010004 0x00000025
+			       0x00010005 0x0000002d
+			       0x00010006 0x00000033
+			       0x00010007 0x00000043
+			       0x00010008 0x0000004b
+			       0x00010009 0x00000053
+
+			       0x00020000 0x00000010
+			       0x00020001 0x00000017
+			       0x00020002 0x0000001f
+			       0x00020003 0x00000029
+			       0x00020004 0x00000031
+			       0x00020005 0x0000003c
+			       0x00020006 0x00000042
+			       0x00020007 0x0000004d
+			       0x00020008 0x00000056
+
+			       0x00030000 0x00000012
+			       0x00030001 0x0000001d>;
+};

Documentation/kernel-parameters.txt

@@ -2993,6 +2993,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			may be specified.
 			Format: <port>,<port>....
 
+	ppc_strict_facility_enable
+			[PPC] This option catches any kernel floating point,
+			Altivec, VSX and SPE outside of regions specifically
+			allowed (eg kernel_enable_fpu()/kernel_disable_fpu()).
+			There is some performance impact when enabling this.
+
 	print-fatal-signals=
 			[KNL] debug: print fatal signals
 

MAINTAINERS

@@ -4490,8 +4490,9 @@ F:	include/linux/fs_enet_pd.h
 FREESCALE QUICC ENGINE LIBRARY
 L:	linuxppc-dev@lists.ozlabs.org
 S:	Orphan
-F:	arch/powerpc/sysdev/qe_lib/
-F:	arch/powerpc/include/asm/*qe.h
+F:	drivers/soc/fsl/qe/
+F:	include/soc/fsl/*qe*.h
+F:	include/soc/fsl/*ucc*.h
 
 FREESCALE USB PERIPHERAL DRIVERS
 M:	Li Yang <leoli@freescale.com>
@@ -6444,7 +6445,7 @@ S:	Maintained
 F:	arch/powerpc/platforms/8xx/
 
 LINUX FOR POWERPC EMBEDDED PPC83XX AND PPC85XX
-M:	Scott Wood <scottwood@freescale.com>
+M:	Scott Wood <oss@buserror.net>
 M:	Kumar Gala <galak@kernel.crashing.org>
 W:	http://www.penguinppc.org/
 L:	linuxppc-dev@lists.ozlabs.org

arch/powerpc/Kconfig

@@ -560,6 +560,7 @@ choice
 
 config PPC_4K_PAGES
 	bool "4k page size"
+	select HAVE_ARCH_SOFT_DIRTY if CHECKPOINT_RESTORE && PPC_BOOK3S
 
 config PPC_16K_PAGES
 	bool "16k page size"
@@ -568,6 +569,7 @@ config PPC_16K_PAGES
 config PPC_64K_PAGES
 	bool "64k page size"
 	depends on !PPC_FSL_BOOK3E && (44x || PPC_STD_MMU_64 || PPC_BOOK3E_64)
+	select HAVE_ARCH_SOFT_DIRTY if CHECKPOINT_RESTORE && PPC_BOOK3S
 
 config PPC_256K_PAGES
 	bool "256k page size"
@@ -1075,8 +1077,6 @@ source "drivers/Kconfig"
 
 source "fs/Kconfig"
 
-source "arch/powerpc/sysdev/qe_lib/Kconfig"
-
 source "lib/Kconfig"
 
 source "arch/powerpc/Kconfig.debug"

arch/powerpc/Kconfig.debug

@@ -64,17 +64,17 @@ config PPC_EMULATED_STATS
 	  emulated.
 
 config CODE_PATCHING_SELFTEST
-	bool "Run self-tests of the code-patching code."
+	bool "Run self-tests of the code-patching code"
 	depends on DEBUG_KERNEL
 	default n
 
 config FTR_FIXUP_SELFTEST
-	bool "Run self-tests of the feature-fixup code."
+	bool "Run self-tests of the feature-fixup code"
 	depends on DEBUG_KERNEL
 	default n
 
 config MSI_BITMAP_SELFTEST
-	bool "Run self-tests of the MSI bitmap code."
+	bool "Run self-tests of the MSI bitmap code"
 	depends on DEBUG_KERNEL
 	default n
 

arch/powerpc/boot/Makefile

@@ -113,7 +113,6 @@ src-plat-$(CONFIG_EPAPR_BOOT) += epapr.c epapr-wrapper.c
 src-plat-$(CONFIG_PPC_PSERIES) += pseries-head.S
 src-plat-$(CONFIG_PPC_POWERNV) += pseries-head.S
 src-plat-$(CONFIG_PPC_IBM_CELL_BLADE) += pseries-head.S
-src-plat-$(CONFIG_PPC_CELL_QPACE) += pseries-head.S
 
 src-wlib := $(sort $(src-wlib-y))
 src-plat := $(sort $(src-plat-y))
@@ -217,7 +216,6 @@ image-$(CONFIG_PPC_POWERNV)		+= zImage.pseries
 image-$(CONFIG_PPC_MAPLE)		+= zImage.maple
 image-$(CONFIG_PPC_IBM_CELL_BLADE)	+= zImage.pseries
 image-$(CONFIG_PPC_PS3)			+= dtbImage.ps3
-image-$(CONFIG_PPC_CELL_QPACE)		+= zImage.pseries
 image-$(CONFIG_PPC_CHRP)		+= zImage.chrp
 image-$(CONFIG_PPC_EFIKA)		+= zImage.chrp
 image-$(CONFIG_PPC_PMAC)		+= zImage.pmac

arch/powerpc/boot/dts/fsl/b4si-post.dtsi

@@ -474,6 +474,11 @@
 	fman@400000 {
 		interrupts = <96 2 0 0>, <16 2 1 30>;
 
+		muram@0 {
+			compatible = "fsl,fman-muram";
+			reg = <0x0 0x80000>;
+		};
+
 		enet0: ethernet@e0000 {
 		};
 

arch/powerpc/boot/dts/fsl/bsc9132qds.dts

@@ -29,6 +29,21 @@
 	soc: soc@ff700000 {
 		ranges = <0x0 0x0 0xff700000 0x100000>;
 	};
+
+	pci0: pcie@ff70a000 {
+		reg = <0 0xff70a000 0 0x1000>;
+		ranges = <0x2000000 0x0 0x90000000 0 0x90000000 0x0 0x20000000
+			  0x1000000 0x0 0x00000000 0 0xc0010000 0x0 0x10000>;
+		pcie@0 {
+			ranges = <0x2000000 0x0 0x90000000
+				  0x2000000 0x0 0x90000000
+				  0x0 0x20000000
+
+				  0x1000000 0x0 0x0
+				  0x1000000 0x0 0x0
+				  0x0 0x100000>;
+		};
+	};
 };
 
 /include/ "bsc9132qds.dtsi"

arch/powerpc/boot/dts/fsl/bsc9132si-post.dtsi

@@ -40,6 +40,34 @@
 	interrupts = <16 2 0 0 20 2 0 0>;
 };
 
+/* controller at 0xa000 */
+&pci0 {
+	compatible = "fsl,bsc9132-pcie", "fsl,qoriq-pcie-v2.2";
+	device_type = "pci";
+	#size-cells = <2>;
+	#address-cells = <3>;
+	bus-range = <0 255>;
+	interrupts = <16 2 0 0>;
+
+	pcie@0 {
+		reg = <0 0 0 0 0>;
+		#interrupt-cells = <1>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		device_type = "pci";
+		interrupts = <16 2 0 0>;
+		interrupt-map-mask = <0xf800 0 0 7>;
+
+		interrupt-map = <
+			/* IDSEL 0x0 */
+			0000 0x0 0x0 0x1 &mpic 0x0 0x2 0x0 0x0
+			0000 0x0 0x0 0x2 &mpic 0x1 0x2 0x0 0x0
+			0000 0x0 0x0 0x3 &mpic 0x2 0x2 0x0 0x0
+			0000 0x0 0x0 0x4 &mpic 0x3 0x2 0x0 0x0
+			>;
+	};
+};
+
 &soc {
 	#address-cells = <1>;
 	#size-cells = <1>;

arch/powerpc/boot/dts/fsl/bsc9132si-pre.dtsi

@@ -45,6 +45,7 @@
 		serial0 = &serial0;
 		ethernet0 = &enet0;
 		ethernet1 = &enet1;
+		pci0 = &pci0;
 	};
 
 	cpus {

arch/powerpc/boot/dts/fsl/p1010rdb.dtsi

@@ -215,3 +215,19 @@
 		phy-connection-type = "sgmii";
 	};
 };
+
+&pci0 {
+	pcie@0 {
+		interrupt-map = <
+			/* IDSEL 0x0 */
+			/*
+			 *irq[4:5] are active-high
+			 *irq[6:7] are active-low
+			 */
+			0000 0x0 0x0 0x1 &mpic 0x4 0x2 0x0 0x0
+			0000 0x0 0x0 0x2 &mpic 0x5 0x2 0x0 0x0
+			0000 0x0 0x0 0x3 &mpic 0x6 0x1 0x0 0x0
+			0000 0x0 0x0 0x4 &mpic 0x7 0x1 0x0 0x0
+			>;
+	};
+};

arch/powerpc/boot/dts/fsl/t1023rdb.dts

@@ -159,4 +159,4 @@
 	};
 };
 
-/include/ "t1023si-post.dtsi"
+#include "t1023si-post.dtsi"

arch/powerpc/boot/dts/fsl/t1023si-post.dtsi

@@ -32,6 +32,8 @@
  * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 
+#include <dt-bindings/thermal/thermal.h>
+
 &ifc {
 	#address-cells = <2>;
 	#size-cells = <1>;
@@ -275,6 +277,90 @@
 		reg = <0xea000 0x4000>;
 	};
 
+	tmu: tmu@f0000 {
+		compatible = "fsl,qoriq-tmu";
+		reg = <0xf0000 0x1000>;
+		interrupts = <18 2 0 0>;
+		fsl,tmu-range = <0xb0000 0xa0026 0x80048 0x30061>;
+		fsl,tmu-calibration = <0x00000000 0x0000000f
+				       0x00000001 0x00000017
+				       0x00000002 0x0000001e
+				       0x00000003 0x00000026
+				       0x00000004 0x0000002e
+				       0x00000005 0x00000035
+				       0x00000006 0x0000003d
+				       0x00000007 0x00000044
+				       0x00000008 0x0000004c
+				       0x00000009 0x00000053
+				       0x0000000a 0x0000005b
+				       0x0000000b 0x00000064
+
+				       0x00010000 0x00000011
+				       0x00010001 0x0000001c
+				       0x00010002 0x00000024
+				       0x00010003 0x0000002b
+				       0x00010004 0x00000034
+				       0x00010005 0x00000039
+				       0x00010006 0x00000042
+				       0x00010007 0x0000004c
+				       0x00010008 0x00000051
+				       0x00010009 0x0000005a
+				       0x0001000a 0x00000063
+
+				       0x00020000 0x00000013
+				       0x00020001 0x00000019
+				       0x00020002 0x00000024
+				       0x00020003 0x0000002c
+				       0x00020004 0x00000035
+				       0x00020005 0x0000003d
+				       0x00020006 0x00000046
+				       0x00020007 0x00000050
+				       0x00020008 0x00000059
+
+				       0x00030000 0x00000002
+				       0x00030001 0x0000000d
+				       0x00030002 0x00000019
+				       0x00030003 0x00000024>;
+		#thermal-sensor-cells = <0>;
+	};
+
+	thermal-zones {
+		cpu_thermal: cpu-thermal {
+			polling-delay-passive = <1000>;
+			polling-delay = <5000>;
+
+			thermal-sensors = <&tmu>;
+
+			trips {
+				cpu_alert: cpu-alert {
+					temperature = <85000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+				cpu_crit: cpu-crit {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				map0 {
+					trip = <&cpu_alert>;
+					cooling-device =
+						<&cpu0 THERMAL_NO_LIMIT
+							THERMAL_NO_LIMIT>;
+				};
+				map1 {
+					trip = <&cpu_alert>;
+					cooling-device =
+						<&cpu1 THERMAL_NO_LIMIT
+							THERMAL_NO_LIMIT>;
+				};
+			};
+		};
+	};
+
 	scfg: global-utilities@fc000 {
 		compatible = "fsl,t1023-scfg";
 		reg = <0xfc000 0x1000>;

arch/powerpc/boot/dts/fsl/t1024qds.dts

@@ -248,4 +248,4 @@
 	};
 };
 
-/include/ "t1024si-post.dtsi"
+#include "t1024si-post.dtsi"

arch/powerpc/boot/dts/fsl/t1024rdb.dts

@@ -188,4 +188,4 @@
 	};
 };
 
-/include/ "t1024si-post.dtsi"
+#include "t1024si-post.dtsi"

arch/powerpc/boot/dts/fsl/t1024si-post.dtsi

@@ -32,7 +32,7 @@
  * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 
-/include/ "t1023si-post.dtsi"
+#include "t1023si-post.dtsi"
 
 / {
 	aliases {

arch/powerpc/boot/dts/fsl/t102xsi-pre.dtsi

@@ -76,6 +76,7 @@
 			reg = <0>;
 			clocks = <&mux0>;
 			next-level-cache = <&L2_1>;
+			#cooling-cells = <2>;
 			L2_1: l2-cache {
 				next-level-cache = <&cpc>;
 			};
@@ -85,6 +86,7 @@
 			reg = <1>;
 			clocks = <&mux1>;
 			next-level-cache = <&L2_2>;
+			#cooling-cells = <2>;
 			L2_2: l2-cache {
 				next-level-cache = <&cpc>;
 			};

arch/powerpc/boot/dts/fsl/t1040d4rdb.dts

@@ -43,4 +43,4 @@
 	interrupt-parent = <&mpic>;
 };
 
-/include/ "t1040si-post.dtsi"
+#include "t1040si-post.dtsi"

arch/powerpc/boot/dts/fsl/t1040qds.dts

@@ -43,4 +43,4 @@
 	interrupt-parent = <&mpic>;
 };
 
-/include/ "t1040si-post.dtsi"
+#include "t1040si-post.dtsi"

arch/powerpc/boot/dts/fsl/t1040rdb.dts

@@ -45,4 +45,4 @@
 	};
 };
 
-/include/ "t1040si-post.dtsi"
+#include "t1040si-post.dtsi"

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

@@ -32,6 +32,8 @@
  * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 
+#include <dt-bindings/thermal/thermal.h>
+
 &bman_fbpr {
 	compatible = "fsl,bman-fbpr";
 	alloc-ranges = <0 0 0x10000 0>;
@@ -484,6 +486,98 @@
 		reg	   = <0xea000 0x4000>;
 	};
 
+	tmu: tmu@f0000 {
+		compatible = "fsl,qoriq-tmu";
+		reg = <0xf0000 0x1000>;
+		interrupts = <18 2 0 0>;
+		fsl,tmu-range = <0xa0000 0x90026 0x8004a 0x1006a>;
+		fsl,tmu-calibration = <0x00000000 0x00000025
+				       0x00000001 0x00000028
+				       0x00000002 0x0000002d
+				       0x00000003 0x00000031
+				       0x00000004 0x00000036
+				       0x00000005 0x0000003a
+				       0x00000006 0x00000040
+				       0x00000007 0x00000044
+				       0x00000008 0x0000004a
+				       0x00000009 0x0000004f
+				       0x0000000a 0x00000054
+
+				       0x00010000 0x0000000d
+				       0x00010001 0x00000013
+				       0x00010002 0x00000019
+				       0x00010003 0x0000001f
+				       0x00010004 0x00000025
+				       0x00010005 0x0000002d
+				       0x00010006 0x00000033
+				       0x00010007 0x00000043
+				       0x00010008 0x0000004b
+				       0x00010009 0x00000053
+
+				       0x00020000 0x00000010
+				       0x00020001 0x00000017
+				       0x00020002 0x0000001f
+				       0x00020003 0x00000029
+				       0x00020004 0x00000031
+				       0x00020005 0x0000003c
+				       0x00020006 0x00000042
+				       0x00020007 0x0000004d
+				       0x00020008 0x00000056
+
+				       0x00030000 0x00000012
+				       0x00030001 0x0000001d>;
+		#thermal-sensor-cells = <0>;
+	};
+
+	thermal-zones {
+		cpu_thermal: cpu-thermal {
+			polling-delay-passive = <1000>;
+			polling-delay = <5000>;
+
+			thermal-sensors = <&tmu>;
+
+			trips {
+				cpu_alert: cpu-alert {
+					temperature = <85000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+				cpu_crit: cpu-crit {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				map0 {
+					trip = <&cpu_alert>;
+					cooling-device =
+						<&cpu0 THERMAL_NO_LIMIT
+							THERMAL_NO_LIMIT>;
+				};
+				map1 {
+					trip = <&cpu_alert>;
+					cooling-device =
+						<&cpu1 THERMAL_NO_LIMIT
+							THERMAL_NO_LIMIT>;
+				};
+				map2 {
+					trip = <&cpu_alert>;
+					cooling-device =
+						<&cpu2 THERMAL_NO_LIMIT
+							THERMAL_NO_LIMIT>;
+				};
+				map3 {
+					trip = <&cpu_alert>;
+					cooling-device =
+						<&cpu3 THERMAL_NO_LIMIT
+							THERMAL_NO_LIMIT>;
+				};
+			};
+		};
+	};
+
 	scfg: global-utilities@fc000 {
 		compatible = "fsl,t1040-scfg";
 		reg = <0xfc000 0x1000>;

arch/powerpc/boot/dts/fsl/t1042d4rdb.dts

@@ -50,4 +50,4 @@
 	};
 };
 
-/include/ "t1040si-post.dtsi"
+#include "t1042si-post.dtsi"

arch/powerpc/boot/dts/fsl/t1042qds.dts

@@ -43,4 +43,4 @@
 	interrupt-parent = <&mpic>;
 };
 
-/include/ "t1042si-post.dtsi"
+#include "t1042si-post.dtsi"

arch/powerpc/boot/dts/fsl/t1042rdb.dts

@@ -45,4 +45,4 @@
 	};
 };
 
-/include/ "t1042si-post.dtsi"
+#include "t1042si-post.dtsi"

arch/powerpc/boot/dts/fsl/t1042rdb_pi.dts

@@ -54,4 +54,4 @@
 	};
 };
 
-/include/ "t1042si-post.dtsi"
+#include "t1042si-post.dtsi"

arch/powerpc/boot/dts/fsl/t1042si-post.dtsi

@@ -32,6 +32,6 @@
  * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 
-/include/ "t1040si-post.dtsi"
+#include "t1040si-post.dtsi"
 
 /* Place holder for ethernet related device tree nodes */

arch/powerpc/boot/dts/fsl/t104xsi-pre.dtsi

@@ -76,6 +76,7 @@
 			reg = <0>;
 			clocks = <&mux0>;
 			next-level-cache = <&L2_1>;
+			#cooling-cells = <2>;
 			L2_1: l2-cache {
 				next-level-cache = <&cpc>;
 			};
@@ -85,6 +86,7 @@
 			reg = <1>;
 			clocks = <&mux1>;
 			next-level-cache = <&L2_2>;
+			#cooling-cells = <2>;
 			L2_2: l2-cache {
 				next-level-cache = <&cpc>;
 			};
@@ -94,6 +96,7 @@
 			reg = <2>;
 			clocks = <&mux2>;
 			next-level-cache = <&L2_3>;
+			#cooling-cells = <2>;
 			L2_3: l2-cache {
 				next-level-cache = <&cpc>;
 			};
@@ -103,6 +106,7 @@
 			reg = <3>;
 			clocks = <&mux3>;
 			next-level-cache = <&L2_4>;
+			#cooling-cells = <2>;
 			L2_4: l2-cache {
 				next-level-cache = <&cpc>;
 			};

arch/powerpc/boot/wrapper

@@ -154,7 +154,7 @@ if [ -z "$kernel" ]; then
     kernel=vmlinux
 fi
 
-elfformat="`${CROSS}objdump -p "$kernel" | grep 'file format' | awk '{print $4}'`"
+LANG=C elfformat="`${CROSS}objdump -p "$kernel" | grep 'file format' | awk '{print $4}'`"
 case "$elfformat" in
     elf64-powerpcle)	format=elf64lppc	;;
     elf64-powerpc)	format=elf32ppc	;;

arch/powerpc/configs/mpc85xx_basic_defconfig

@@ -12,6 +12,7 @@ CONFIG_P1010_RDB=y
 CONFIG_P1022_DS=y
 CONFIG_P1022_RDK=y
 CONFIG_P1023_RDB=y
+CONFIG_TWR_P102x=y
 CONFIG_SBC8548=y
 CONFIG_SOCRATES=y
 CONFIG_STX_GP3=y

arch/powerpc/configs/ppc64_defconfig

@@ -36,7 +36,6 @@ CONFIG_PS3_ROM=m
 CONFIG_PS3_FLASH=m
 CONFIG_PS3_LPM=m
 CONFIG_PPC_IBM_CELL_BLADE=y
-CONFIG_PPC_CELL_QPACE=y
 CONFIG_RTAS_FLASH=m
 CONFIG_IBMEBUS=y
 CONFIG_CPU_FREQ_PMAC64=y

arch/powerpc/crypto/aes-spe-glue.c

@@ -85,6 +85,7 @@ static void spe_begin(void)
 
 static void spe_end(void)
 {
+	disable_kernel_spe();
 	/* reenable preemption */
 	preempt_enable();
 }

arch/powerpc/crypto/sha1-spe-glue.c

@@ -46,6 +46,7 @@ static void spe_begin(void)
 
 static void spe_end(void)
 {
+	disable_kernel_spe();
 	/* reenable preemption */
 	preempt_enable();
 }

arch/powerpc/crypto/sha256-spe-glue.c

@@ -47,6 +47,7 @@ static void spe_begin(void)
 
 static void spe_end(void)
 {
+	disable_kernel_spe();
 	/* reenable preemption */
 	preempt_enable();
 }

arch/powerpc/include/asm/pte-hash32.h → arch/powerpc/include/asm/book3s/32/hash.h

@@ -1,5 +1,5 @@
-#ifndef _ASM_POWERPC_PTE_HASH32_H
-#define _ASM_POWERPC_PTE_HASH32_H
+#ifndef _ASM_POWERPC_BOOK3S_32_HASH_H
+#define _ASM_POWERPC_BOOK3S_32_HASH_H
 #ifdef __KERNEL__
 
 /*
@@ -43,4 +43,4 @@
 #define PTE_ATOMIC_UPDATES	1
 
 #endif /* __KERNEL__ */
-#endif /*  _ASM_POWERPC_PTE_HASH32_H */
+#endif /* _ASM_POWERPC_BOOK3S_32_HASH_H */

arch/powerpc/include/asm/book3s/32/pgtable.h

@@ -0,0 +1,482 @@
+#ifndef _ASM_POWERPC_BOOK3S_32_PGTABLE_H
+#define _ASM_POWERPC_BOOK3S_32_PGTABLE_H
+
+#include <asm-generic/pgtable-nopmd.h>
+
+#include <asm/book3s/32/hash.h>
+
+/* And here we include common definitions */
+#include <asm/pte-common.h>
+
+/*
+ * The normal case is that PTEs are 32-bits and we have a 1-page
+ * 1024-entry pgdir pointing to 1-page 1024-entry PTE pages.  -- paulus
+ *
+ * For any >32-bit physical address platform, we can use the following
+ * two level page table layout where the pgdir is 8KB and the MS 13 bits
+ * are an index to the second level table.  The combined pgdir/pmd first
+ * level has 2048 entries and the second level has 512 64-bit PTE entries.
+ * -Matt
+ */
+/* PGDIR_SHIFT determines what a top-level page table entry can map */
+#define PGDIR_SHIFT	(PAGE_SHIFT + PTE_SHIFT)
+#define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
+#define PGDIR_MASK	(~(PGDIR_SIZE-1))
+
+#define PTRS_PER_PTE	(1 << PTE_SHIFT)
+#define PTRS_PER_PMD	1
+#define PTRS_PER_PGD	(1 << (32 - PGDIR_SHIFT))
+
+#define USER_PTRS_PER_PGD	(TASK_SIZE / PGDIR_SIZE)
+/*
+ * This is the bottom of the PKMAP area with HIGHMEM or an arbitrary
+ * value (for now) on others, from where we can start layout kernel
+ * virtual space that goes below PKMAP and FIXMAP
+ */
+#ifdef CONFIG_HIGHMEM
+#define KVIRT_TOP	PKMAP_BASE
+#else
+#define KVIRT_TOP	(0xfe000000UL)	/* for now, could be FIXMAP_BASE ? */
+#endif
+
+/*
+ * ioremap_bot starts at that address. Early ioremaps move down from there,
+ * until mem_init() at which point this becomes the top of the vmalloc
+ * and ioremap space
+ */
+#ifdef CONFIG_NOT_COHERENT_CACHE
+#define IOREMAP_TOP	((KVIRT_TOP - CONFIG_CONSISTENT_SIZE) & PAGE_MASK)
+#else
+#define IOREMAP_TOP	KVIRT_TOP
+#endif
+
+/*
+ * Just any arbitrary offset to the start of the vmalloc VM area: the
+ * current 16MB value just means that there will be a 64MB "hole" after the
+ * physical memory until the kernel virtual memory starts.  That means that
+ * any out-of-bounds memory accesses will hopefully be caught.
+ * The vmalloc() routines leaves a hole of 4kB between each vmalloced
+ * area for the same reason. ;)
+ *
+ * We no longer map larger than phys RAM with the BATs so we don't have
+ * to worry about the VMALLOC_OFFSET causing problems.  We do have to worry
+ * about clashes between our early calls to ioremap() that start growing down
+ * from ioremap_base being run into the VM area allocations (growing upwards
+ * from VMALLOC_START).  For this reason we have ioremap_bot to check when
+ * we actually run into our mappings setup in the early boot with the VM
+ * system.  This really does become a problem for machines with good amounts
+ * of RAM.  -- Cort
+ */
+#define VMALLOC_OFFSET (0x1000000) /* 16M */
+#ifdef PPC_PIN_SIZE
+#define VMALLOC_START (((_ALIGN((long)high_memory, PPC_PIN_SIZE) + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1)))
+#else
+#define VMALLOC_START ((((long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1)))
+#endif
+#define VMALLOC_END	ioremap_bot
+
+#ifndef __ASSEMBLY__
+#include <linux/sched.h>
+#include <linux/threads.h>
+#include <asm/io.h>			/* For sub-arch specific PPC_PIN_SIZE */
+
+extern unsigned long ioremap_bot;
+
+/*
+ * entries per page directory level: our page-table tree is two-level, so
+ * we don't really have any PMD directory.
+ */
+#define PTE_TABLE_SIZE	(sizeof(pte_t) << PTE_SHIFT)
+#define PGD_TABLE_SIZE	(sizeof(pgd_t) << (32 - PGDIR_SHIFT))
+
+#define pte_ERROR(e) \
+	pr_err("%s:%d: bad pte %llx.\n", __FILE__, __LINE__, \
+		(unsigned long long)pte_val(e))
+#define pgd_ERROR(e) \
+	pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
+/*
+ * Bits in a linux-style PTE.  These match the bits in the
+ * (hardware-defined) PowerPC PTE as closely as possible.
+ */
+
+#define pte_clear(mm, addr, ptep) \
+	do { pte_update(ptep, ~_PAGE_HASHPTE, 0); } while (0)
+
+#define pmd_none(pmd)		(!pmd_val(pmd))
+#define	pmd_bad(pmd)		(pmd_val(pmd) & _PMD_BAD)
+#define	pmd_present(pmd)	(pmd_val(pmd) & _PMD_PRESENT_MASK)
+static inline void pmd_clear(pmd_t *pmdp)
+{
+	*pmdp = __pmd(0);
+}
+
+
+/*
+ * When flushing the tlb entry for a page, we also need to flush the hash
+ * table entry.  flush_hash_pages is assembler (for speed) in hashtable.S.
+ */
+extern int flush_hash_pages(unsigned context, unsigned long va,
+			    unsigned long pmdval, int count);
+
+/* Add an HPTE to the hash table */
+extern void add_hash_page(unsigned context, unsigned long va,
+			  unsigned long pmdval);
+
+/* Flush an entry from the TLB/hash table */
+extern void flush_hash_entry(struct mm_struct *mm, pte_t *ptep,
+			     unsigned long address);
+
+/*
+ * PTE updates. This function is called whenever an existing
+ * valid PTE is updated. This does -not- include set_pte_at()
+ * which nowadays only sets a new PTE.
+ *
+ * Depending on the type of MMU, we may need to use atomic updates
+ * and the PTE may be either 32 or 64 bit wide. In the later case,
+ * when using atomic updates, only the low part of the PTE is
+ * accessed atomically.
+ *
+ * In addition, on 44x, we also maintain a global flag indicating
+ * that an executable user mapping was modified, which is needed
+ * to properly flush the virtually tagged instruction cache of
+ * those implementations.
+ */
+#ifndef CONFIG_PTE_64BIT
+static inline unsigned long pte_update(pte_t *p,
+				       unsigned long clr,
+				       unsigned long set)
+{
+	unsigned long old, tmp;
+
+	__asm__ __volatile__("\
+1:	lwarx	%0,0,%3\n\
+	andc	%1,%0,%4\n\
+	or	%1,%1,%5\n"
+	PPC405_ERR77(0,%3)
+"	stwcx.	%1,0,%3\n\
+	bne-	1b"
+	: "=&r" (old), "=&r" (tmp), "=m" (*p)
+	: "r" (p), "r" (clr), "r" (set), "m" (*p)
+	: "cc" );
+
+	return old;
+}
+#else /* CONFIG_PTE_64BIT */
+static inline unsigned long long pte_update(pte_t *p,
+					    unsigned long clr,
+					    unsigned long set)
+{
+	unsigned long long old;
+	unsigned long tmp;
+
+	__asm__ __volatile__("\
+1:	lwarx	%L0,0,%4\n\
+	lwzx	%0,0,%3\n\
+	andc	%1,%L0,%5\n\
+	or	%1,%1,%6\n"
+	PPC405_ERR77(0,%3)
+"	stwcx.	%1,0,%4\n\
+	bne-	1b"
+	: "=&r" (old), "=&r" (tmp), "=m" (*p)
+	: "r" (p), "r" ((unsigned long)(p) + 4), "r" (clr), "r" (set), "m" (*p)
+	: "cc" );
+
+	return old;
+}
+#endif /* CONFIG_PTE_64BIT */
+
+/*
+ * 2.6 calls this without flushing the TLB entry; this is wrong
+ * for our hash-based implementation, we fix that up here.
+ */
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+static inline int __ptep_test_and_clear_young(unsigned int context, unsigned long addr, pte_t *ptep)
+{
+	unsigned long old;
+	old = pte_update(ptep, _PAGE_ACCESSED, 0);
+	if (old & _PAGE_HASHPTE) {
+		unsigned long ptephys = __pa(ptep) & PAGE_MASK;
+		flush_hash_pages(context, addr, ptephys, 1);
+	}
+	return (old & _PAGE_ACCESSED) != 0;
+}
+#define ptep_test_and_clear_young(__vma, __addr, __ptep) \
+	__ptep_test_and_clear_young((__vma)->vm_mm->context.id, __addr, __ptep)
+
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+				       pte_t *ptep)
+{
+	return __pte(pte_update(ptep, ~_PAGE_HASHPTE, 0));
+}
+
+#define __HAVE_ARCH_PTEP_SET_WRPROTECT
+static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
+				      pte_t *ptep)
+{
+	pte_update(ptep, (_PAGE_RW | _PAGE_HWWRITE), _PAGE_RO);
+}
+static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
+					   unsigned long addr, pte_t *ptep)
+{
+	ptep_set_wrprotect(mm, addr, ptep);
+}
+
+
+static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry)
+{
+	unsigned long set = pte_val(entry) &
+		(_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC);
+	unsigned long clr = ~pte_val(entry) & _PAGE_RO;
+
+	pte_update(ptep, clr, set);
+}
+
+#define __HAVE_ARCH_PTE_SAME
+#define pte_same(A,B)	(((pte_val(A) ^ pte_val(B)) & ~_PAGE_HASHPTE) == 0)
+
+/*
+ * Note that on Book E processors, the pmd contains the kernel virtual
+ * (lowmem) address of the pte page.  The physical address is less useful
+ * because everything runs with translation enabled (even the TLB miss
+ * handler).  On everything else the pmd contains the physical address
+ * of the pte page.  -- paulus
+ */
+#ifndef CONFIG_BOOKE
+#define pmd_page_vaddr(pmd)	\
+	((unsigned long) __va(pmd_val(pmd) & PAGE_MASK))
+#define pmd_page(pmd)		\
+	pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT)
+#else
+#define pmd_page_vaddr(pmd)	\
+	((unsigned long) (pmd_val(pmd) & PAGE_MASK))
+#define pmd_page(pmd)		\
+	pfn_to_page((__pa(pmd_val(pmd)) >> PAGE_SHIFT))
+#endif
+
+/* to find an entry in a kernel page-table-directory */
+#define pgd_offset_k(address) pgd_offset(&init_mm, address)
+
+/* to find an entry in a page-table-directory */
+#define pgd_index(address)	 ((address) >> PGDIR_SHIFT)
+#define pgd_offset(mm, address)	 ((mm)->pgd + pgd_index(address))
+
+/* Find an entry in the third-level page table.. */
+#define pte_index(address)		\
+	(((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+#define pte_offset_kernel(dir, addr)	\
+	((pte_t *) pmd_page_vaddr(*(dir)) + pte_index(addr))
+#define pte_offset_map(dir, addr)		\
+	((pte_t *) kmap_atomic(pmd_page(*(dir))) + pte_index(addr))
+#define pte_unmap(pte)		kunmap_atomic(pte)
+
+/*
+ * Encode and decode a swap entry.
+ * Note that the bits we use in a PTE for representing a swap entry
+ * must not include the _PAGE_PRESENT bit or the _PAGE_HASHPTE bit (if used).
+ *   -- paulus
+ */
+#define __swp_type(entry)		((entry).val & 0x1f)
+#define __swp_offset(entry)		((entry).val >> 5)
+#define __swp_entry(type, offset)	((swp_entry_t) { (type) | ((offset) << 5) })
+#define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) >> 3 })
+#define __swp_entry_to_pte(x)		((pte_t) { (x).val << 3 })
+
+#ifndef CONFIG_PPC_4K_PAGES
+void pgtable_cache_init(void);
+#else
+/*
+ * No page table caches to initialise
+ */
+#define pgtable_cache_init()	do { } while (0)
+#endif
+
+extern int get_pteptr(struct mm_struct *mm, unsigned long addr, pte_t **ptep,
+		      pmd_t **pmdp);
+
+/* Generic accessors to PTE bits */
+static inline int pte_write(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_RW);}
+static inline int pte_dirty(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_DIRTY); }
+static inline int pte_young(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_ACCESSED); }
+static inline int pte_special(pte_t pte)	{ return !!(pte_val(pte) & _PAGE_SPECIAL); }
+static inline int pte_none(pte_t pte)		{ return (pte_val(pte) & ~_PTE_NONE_MASK) == 0; }
+static inline pgprot_t pte_pgprot(pte_t pte)	{ return __pgprot(pte_val(pte) & PAGE_PROT_BITS); }
+
+static inline int pte_present(pte_t pte)
+{
+	return pte_val(pte) & _PAGE_PRESENT;
+}
+
+/* Conversion functions: convert a page and protection to a page entry,
+ * and a page entry and page directory to the page they refer to.
+ *
+ * Even if PTEs can be unsigned long long, a PFN is always an unsigned
+ * long for now.
+ */
+static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot)
+{
+	return __pte(((pte_basic_t)(pfn) << PTE_RPN_SHIFT) |
+		     pgprot_val(pgprot));
+}
+
+static inline unsigned long pte_pfn(pte_t pte)
+{
+	return pte_val(pte) >> PTE_RPN_SHIFT;
+}
+
+/* Generic modifiers for PTE bits */
+static inline pte_t pte_wrprotect(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_RW);
+}
+
+static inline pte_t pte_mkclean(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_DIRTY);
+}
+
+static inline pte_t pte_mkold(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_ACCESSED);
+}
+
+static inline pte_t pte_mkwrite(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_RW);
+}
+
+static inline pte_t pte_mkdirty(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_DIRTY);
+}
+
+static inline pte_t pte_mkyoung(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_ACCESSED);
+}
+
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_SPECIAL);
+}
+
+static inline pte_t pte_mkhuge(pte_t pte)
+{
+	return pte;
+}
+
+static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+{
+	return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot));
+}
+
+
+
+/* This low level function performs the actual PTE insertion
+ * Setting the PTE depends on the MMU type and other factors. It's
+ * an horrible mess that I'm not going to try to clean up now but
+ * I'm keeping it in one place rather than spread around
+ */
+static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
+				pte_t *ptep, pte_t pte, int percpu)
+{
+#if defined(CONFIG_PPC_STD_MMU_32) && defined(CONFIG_SMP) && !defined(CONFIG_PTE_64BIT)
+	/* First case is 32-bit Hash MMU in SMP mode with 32-bit PTEs. We use the
+	 * helper pte_update() which does an atomic update. We need to do that
+	 * because a concurrent invalidation can clear _PAGE_HASHPTE. If it's a
+	 * per-CPU PTE such as a kmap_atomic, we do a simple update preserving
+	 * the hash bits instead (ie, same as the non-SMP case)
+	 */
+	if (percpu)
+		*ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE)
+			      | (pte_val(pte) & ~_PAGE_HASHPTE));
+	else
+		pte_update(ptep, ~_PAGE_HASHPTE, pte_val(pte));
+
+#elif defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT)
+	/* Second case is 32-bit with 64-bit PTE.  In this case, we
+	 * can just store as long as we do the two halves in the right order
+	 * with a barrier in between. This is possible because we take care,
+	 * in the hash code, to pre-invalidate if the PTE was already hashed,
+	 * which synchronizes us with any concurrent invalidation.
+	 * In the percpu case, we also fallback to the simple update preserving
+	 * the hash bits
+	 */
+	if (percpu) {
+		*ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE)
+			      | (pte_val(pte) & ~_PAGE_HASHPTE));
+		return;
+	}
+	if (pte_val(*ptep) & _PAGE_HASHPTE)
+		flush_hash_entry(mm, ptep, addr);
+	__asm__ __volatile__("\
+		stw%U0%X0 %2,%0\n\
+		eieio\n\
+		stw%U0%X0 %L2,%1"
+	: "=m" (*ptep), "=m" (*((unsigned char *)ptep+4))
+	: "r" (pte) : "memory");
+
+#elif defined(CONFIG_PPC_STD_MMU_32)
+	/* Third case is 32-bit hash table in UP mode, we need to preserve
+	 * the _PAGE_HASHPTE bit since we may not have invalidated the previous
+	 * translation in the hash yet (done in a subsequent flush_tlb_xxx())
+	 * and see we need to keep track that this PTE needs invalidating
+	 */
+	*ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE)
+		      | (pte_val(pte) & ~_PAGE_HASHPTE));
+
+#else
+#error "Not supported "
+#endif
+}
+
+/*
+ * Macro to mark a page protection value as "uncacheable".
+ */
+
+#define _PAGE_CACHE_CTL	(_PAGE_COHERENT | _PAGE_GUARDED | _PAGE_NO_CACHE | \
+			 _PAGE_WRITETHRU)
+
+#define pgprot_noncached pgprot_noncached
+static inline pgprot_t pgprot_noncached(pgprot_t prot)
+{
+	return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) |
+			_PAGE_NO_CACHE | _PAGE_GUARDED);
+}
+
+#define pgprot_noncached_wc pgprot_noncached_wc
+static inline pgprot_t pgprot_noncached_wc(pgprot_t prot)
+{
+	return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) |
+			_PAGE_NO_CACHE);
+}
+
+#define pgprot_cached pgprot_cached
+static inline pgprot_t pgprot_cached(pgprot_t prot)
+{
+	return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) |
+			_PAGE_COHERENT);
+}
+
+#define pgprot_cached_wthru pgprot_cached_wthru
+static inline pgprot_t pgprot_cached_wthru(pgprot_t prot)
+{
+	return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) |
+			_PAGE_COHERENT | _PAGE_WRITETHRU);
+}
+
+#define pgprot_cached_noncoherent pgprot_cached_noncoherent
+static inline pgprot_t pgprot_cached_noncoherent(pgprot_t prot)
+{
+	return __pgprot(pgprot_val(prot) & ~_PAGE_CACHE_CTL);
+}
+
+#define pgprot_writecombine pgprot_writecombine
+static inline pgprot_t pgprot_writecombine(pgprot_t prot)
+{
+	return pgprot_noncached_wc(prot);
+}
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /*  _ASM_POWERPC_BOOK3S_32_PGTABLE_H */

arch/powerpc/include/asm/book3s/64/hash-4k.h

@@ -0,0 +1,132 @@
+#ifndef _ASM_POWERPC_BOOK3S_64_HASH_4K_H
+#define _ASM_POWERPC_BOOK3S_64_HASH_4K_H
+/*
+ * Entries per page directory level.  The PTE level must use a 64b record
+ * for each page table entry.  The PMD and PGD level use a 32b record for
+ * each entry by assuming that each entry is page aligned.
+ */
+#define PTE_INDEX_SIZE  9
+#define PMD_INDEX_SIZE  7
+#define PUD_INDEX_SIZE  9
+#define PGD_INDEX_SIZE  9
+
+#ifndef __ASSEMBLY__
+#define PTE_TABLE_SIZE	(sizeof(pte_t) << PTE_INDEX_SIZE)
+#define PMD_TABLE_SIZE	(sizeof(pmd_t) << PMD_INDEX_SIZE)
+#define PUD_TABLE_SIZE	(sizeof(pud_t) << PUD_INDEX_SIZE)
+#define PGD_TABLE_SIZE	(sizeof(pgd_t) << PGD_INDEX_SIZE)
+#endif	/* __ASSEMBLY__ */
+
+#define PTRS_PER_PTE	(1 << PTE_INDEX_SIZE)
+#define PTRS_PER_PMD	(1 << PMD_INDEX_SIZE)
+#define PTRS_PER_PUD	(1 << PUD_INDEX_SIZE)
+#define PTRS_PER_PGD	(1 << PGD_INDEX_SIZE)
+
+/* PMD_SHIFT determines what a second-level page table entry can map */
+#define PMD_SHIFT	(PAGE_SHIFT + PTE_INDEX_SIZE)
+#define PMD_SIZE	(1UL << PMD_SHIFT)
+#define PMD_MASK	(~(PMD_SIZE-1))
+
+/* With 4k base page size, hugepage PTEs go at the PMD level */
+#define MIN_HUGEPTE_SHIFT	PMD_SHIFT
+
+/* PUD_SHIFT determines what a third-level page table entry can map */
+#define PUD_SHIFT	(PMD_SHIFT + PMD_INDEX_SIZE)
+#define PUD_SIZE	(1UL << PUD_SHIFT)
+#define PUD_MASK	(~(PUD_SIZE-1))
+
+/* PGDIR_SHIFT determines what a fourth-level page table entry can map */
+#define PGDIR_SHIFT	(PUD_SHIFT + PUD_INDEX_SIZE)
+#define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
+#define PGDIR_MASK	(~(PGDIR_SIZE-1))
+
+/* Bits to mask out from a PMD to get to the PTE page */
+#define PMD_MASKED_BITS		0
+/* Bits to mask out from a PUD to get to the PMD page */
+#define PUD_MASKED_BITS		0
+/* Bits to mask out from a PGD to get to the PUD page */
+#define PGD_MASKED_BITS		0
+
+/* PTE flags to conserve for HPTE identification */
+#define _PAGE_HPTEFLAGS (_PAGE_BUSY | _PAGE_HASHPTE | \
+			 _PAGE_F_SECOND | _PAGE_F_GIX)
+
+/* shift to put page number into pte */
+#define PTE_RPN_SHIFT	(18)
+
+#define _PAGE_4K_PFN		0
+#ifndef __ASSEMBLY__
+/*
+ * 4-level page tables related bits
+ */
+
+#define pgd_none(pgd)		(!pgd_val(pgd))
+#define pgd_bad(pgd)		(pgd_val(pgd) == 0)
+#define pgd_present(pgd)	(pgd_val(pgd) != 0)
+#define pgd_page_vaddr(pgd)	(pgd_val(pgd) & ~PGD_MASKED_BITS)
+
+static inline void pgd_clear(pgd_t *pgdp)
+{
+	*pgdp = __pgd(0);
+}
+
+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);
+
+#define pud_offset(pgdp, addr)	\
+  (((pud_t *) pgd_page_vaddr(*(pgdp))) + \
+    (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)))
+
+#define pud_ERROR(e) \
+	pr_err("%s:%d: bad pud %08lx.\n", __FILE__, __LINE__, pud_val(e))
+
+/*
+ * On all 4K setups, remap_4k_pfn() equates to remap_pfn_range() */
+#define remap_4k_pfn(vma, addr, pfn, prot)	\
+	remap_pfn_range((vma), (addr), (pfn), PAGE_SIZE, (prot))
+
+#ifdef CONFIG_HUGETLB_PAGE
+/*
+ * For 4k page size, we support explicit hugepage via hugepd
+ */
+static inline int pmd_huge(pmd_t pmd)
+{
+	return 0;
+}
+
+static inline int pud_huge(pud_t pud)
+{
+	return 0;
+}
+
+static inline int pgd_huge(pgd_t pgd)
+{
+	return 0;
+}
+#define pgd_huge pgd_huge
+
+static inline int hugepd_ok(hugepd_t hpd)
+{
+	/*
+	 * if it is not a pte and have hugepd shift mask
+	 * set, then it is a hugepd directory pointer
+	 */
+	if (!(hpd.pd & _PAGE_PTE) &&
+	    ((hpd.pd & HUGEPD_SHIFT_MASK) != 0))
+		return true;
+	return false;
+}
+#define is_hugepd(hpd)		(hugepd_ok(hpd))
+#endif
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* _ASM_POWERPC_BOOK3S_64_HASH_4K_H */

arch/powerpc/include/asm/book3s/64/hash-64k.h

@@ -0,0 +1,312 @@
+#ifndef _ASM_POWERPC_BOOK3S_64_HASH_64K_H
+#define _ASM_POWERPC_BOOK3S_64_HASH_64K_H
+
+#include <asm-generic/pgtable-nopud.h>
+
+#define PTE_INDEX_SIZE  8
+#define PMD_INDEX_SIZE  10
+#define PUD_INDEX_SIZE	0
+#define PGD_INDEX_SIZE  12
+
+#define PTRS_PER_PTE	(1 << PTE_INDEX_SIZE)
+#define PTRS_PER_PMD	(1 << PMD_INDEX_SIZE)
+#define PTRS_PER_PGD	(1 << PGD_INDEX_SIZE)
+
+/* With 4k base page size, hugepage PTEs go at the PMD level */
+#define MIN_HUGEPTE_SHIFT	PAGE_SHIFT
+
+/* PMD_SHIFT determines what a second-level page table entry can map */
+#define PMD_SHIFT	(PAGE_SHIFT + PTE_INDEX_SIZE)
+#define PMD_SIZE	(1UL << PMD_SHIFT)
+#define PMD_MASK	(~(PMD_SIZE-1))
+
+/* PGDIR_SHIFT determines what a third-level page table entry can map */
+#define PGDIR_SHIFT	(PMD_SHIFT + PMD_INDEX_SIZE)
+#define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
+#define PGDIR_MASK	(~(PGDIR_SIZE-1))
+
+#define _PAGE_COMBO	0x00040000 /* this is a combo 4k page */
+#define _PAGE_4K_PFN	0x00080000 /* PFN is for a single 4k page */
+/*
+ * Used to track subpage group valid if _PAGE_COMBO is set
+ * This overloads _PAGE_F_GIX and _PAGE_F_SECOND
+ */
+#define _PAGE_COMBO_VALID	(_PAGE_F_GIX | _PAGE_F_SECOND)
+
+/* PTE flags to conserve for HPTE identification */
+#define _PAGE_HPTEFLAGS (_PAGE_BUSY | _PAGE_F_SECOND | \
+			 _PAGE_F_GIX | _PAGE_HASHPTE | _PAGE_COMBO)
+
+/* Shift to put page number into pte.
+ *
+ * That gives us a max RPN of 34 bits, which means a max of 50 bits
+ * of addressable physical space, or 46 bits for the special 4k PFNs.
+ */
+#define PTE_RPN_SHIFT	(30)
+/*
+ * we support 16 fragments per PTE page of 64K size.
+ */
+#define PTE_FRAG_NR	16
+/*
+ * We use a 2K PTE page fragment and another 2K for storing
+ * real_pte_t hash index
+ */
+#define PTE_FRAG_SIZE_SHIFT  12
+#define PTE_FRAG_SIZE (1UL << PTE_FRAG_SIZE_SHIFT)
+
+/*
+ * Bits to mask out from a PMD to get to the PTE page
+ * PMDs point to PTE table fragments which are PTE_FRAG_SIZE aligned.
+ */
+#define PMD_MASKED_BITS		(PTE_FRAG_SIZE - 1)
+/* Bits to mask out from a PGD/PUD to get to the PMD page */
+#define PUD_MASKED_BITS		0x1ff
+
+#ifndef __ASSEMBLY__
+
+/*
+ * With 64K pages on hash table, we have a special PTE format that
+ * uses a second "half" of the page table to encode sub-page information
+ * in order to deal with 64K made of 4K HW pages. Thus we override the
+ * generic accessors and iterators here
+ */
+#define __real_pte __real_pte
+static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep)
+{
+	real_pte_t rpte;
+	unsigned long *hidxp;
+
+	rpte.pte = pte;
+	rpte.hidx = 0;
+	if (pte_val(pte) & _PAGE_COMBO) {
+		/*
+		 * Make sure we order the hidx load against the _PAGE_COMBO
+		 * check. The store side ordering is done in __hash_page_4K
+		 */
+		smp_rmb();
+		hidxp = (unsigned long *)(ptep + PTRS_PER_PTE);
+		rpte.hidx = *hidxp;
+	}
+	return rpte;
+}
+
+static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index)
+{
+	if ((pte_val(rpte.pte) & _PAGE_COMBO))
+		return (rpte.hidx >> (index<<2)) & 0xf;
+	return (pte_val(rpte.pte) >> _PAGE_F_GIX_SHIFT) & 0xf;
+}
+
+#define __rpte_to_pte(r)	((r).pte)
+extern bool __rpte_sub_valid(real_pte_t rpte, unsigned long index);
+/*
+ * Trick: we set __end to va + 64k, which happens works for
+ * a 16M page as well as we want only one iteration
+ */
+#define pte_iterate_hashed_subpages(rpte, psize, vpn, index, shift)	\
+	do {								\
+		unsigned long __end = vpn + (1UL << (PAGE_SHIFT - VPN_SHIFT));	\
+		unsigned __split = (psize == MMU_PAGE_4K ||		\
+				    psize == MMU_PAGE_64K_AP);		\
+		shift = mmu_psize_defs[psize].shift;			\
+		for (index = 0; vpn < __end; index++,			\
+			     vpn += (1L << (shift - VPN_SHIFT))) {	\
+			if (!__split || __rpte_sub_valid(rpte, index))	\
+				do {
+
+#define pte_iterate_hashed_end() } while(0); } } while(0)
+
+#define pte_pagesize_index(mm, addr, pte)	\
+	(((pte) & _PAGE_COMBO)? MMU_PAGE_4K: MMU_PAGE_64K)
+
+#define remap_4k_pfn(vma, addr, pfn, prot)				\
+	(WARN_ON(((pfn) >= (1UL << (64 - PTE_RPN_SHIFT)))) ? -EINVAL :	\
+		remap_pfn_range((vma), (addr), (pfn), PAGE_SIZE,	\
+			__pgprot(pgprot_val((prot)) | _PAGE_4K_PFN)))
+
+#define PTE_TABLE_SIZE	PTE_FRAG_SIZE
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define PMD_TABLE_SIZE	((sizeof(pmd_t) << PMD_INDEX_SIZE) + (sizeof(unsigned long) << PMD_INDEX_SIZE))
+#else
+#define PMD_TABLE_SIZE	(sizeof(pmd_t) << PMD_INDEX_SIZE)
+#endif
+#define PGD_TABLE_SIZE	(sizeof(pgd_t) << PGD_INDEX_SIZE)
+
+#define pgd_pte(pgd)	(pud_pte(((pud_t){ pgd })))
+#define pte_pgd(pte)	((pgd_t)pte_pud(pte))
+
+#ifdef CONFIG_HUGETLB_PAGE
+/*
+ * 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.
+ */
+static inline int pmd_huge(pmd_t pmd)
+{
+	/*
+	 * leaf pte for huge page
+	 */
+	return !!(pmd_val(pmd) & _PAGE_PTE);
+}
+
+static inline int pud_huge(pud_t pud)
+{
+	/*
+	 * leaf pte for huge page
+	 */
+	return !!(pud_val(pud) & _PAGE_PTE);
+}
+
+static inline int pgd_huge(pgd_t pgd)
+{
+	/*
+	 * leaf pte for huge page
+	 */
+	return !!(pgd_val(pgd) & _PAGE_PTE);
+}
+#define pgd_huge pgd_huge
+
+#ifdef CONFIG_DEBUG_VM
+extern int hugepd_ok(hugepd_t hpd);
+#define is_hugepd(hpd)               (hugepd_ok(hpd))
+#else
+/*
+ * With 64k page size, we have hugepage ptes in the pgd and pmd entries. We don't
+ * need to setup hugepage directory for them. Our pte and page directory format
+ * enable us to have this enabled.
+ */
+static inline int hugepd_ok(hugepd_t hpd)
+{
+	return 0;
+}
+#define is_hugepd(pdep)			0
+#endif /* CONFIG_DEBUG_VM */
+
+#endif /* CONFIG_HUGETLB_PAGE */
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+extern unsigned long pmd_hugepage_update(struct mm_struct *mm,
+					 unsigned long addr,
+					 pmd_t *pmdp,
+					 unsigned long clr,
+					 unsigned long set);
+static inline char *get_hpte_slot_array(pmd_t *pmdp)
+{
+	/*
+	 * The hpte hindex is stored in the pgtable whose address is in the
+	 * second half of the PMD
+	 *
+	 * Order this load with the test for pmd_trans_huge in the caller
+	 */
+	smp_rmb();
+	return *(char **)(pmdp + PTRS_PER_PMD);
+
+
+}
+/*
+ * The linux hugepage PMD now include the pmd entries followed by the address
+ * to the stashed pgtable_t. The stashed pgtable_t contains the hpte bits.
+ * [ 1 bit secondary | 3 bit hidx | 1 bit valid | 000]. We use one byte per
+ * each HPTE entry. With 16MB hugepage and 64K HPTE we need 256 entries and
+ * with 4K HPTE we need 4096 entries. Both will fit in a 4K pgtable_t.
+ *
+ * The last three bits are intentionally left to zero. This memory location
+ * are also used as normal page PTE pointers. So if we have any pointers
+ * left around while we collapse a hugepage, we need to make sure
+ * _PAGE_PRESENT bit of that is zero when we look at them
+ */
+static inline unsigned int hpte_valid(unsigned char *hpte_slot_array, int index)
+{
+	return (hpte_slot_array[index] >> 3) & 0x1;
+}
+
+static inline unsigned int hpte_hash_index(unsigned char *hpte_slot_array,
+					   int index)
+{
+	return hpte_slot_array[index] >> 4;
+}
+
+static inline void mark_hpte_slot_valid(unsigned char *hpte_slot_array,
+					unsigned int index, unsigned int hidx)
+{
+	hpte_slot_array[index] = hidx << 4 | 0x1 << 3;
+}
+
+/*
+ *
+ * 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)
+{
+	return !!((pmd_val(pmd) & (_PAGE_PTE | _PAGE_THP_HUGE)) ==
+		  (_PAGE_PTE | _PAGE_THP_HUGE));
+}
+
+static inline int pmd_trans_splitting(pmd_t pmd)
+{
+	if (pmd_trans_huge(pmd))
+		return pmd_val(pmd) & _PAGE_SPLITTING;
+	return 0;
+}
+
+static inline int pmd_large(pmd_t pmd)
+{
+	return !!(pmd_val(pmd) & _PAGE_PTE);
+}
+
+static inline pmd_t pmd_mknotpresent(pmd_t pmd)
+{
+	return __pmd(pmd_val(pmd) & ~_PAGE_PRESENT);
+}
+
+static inline pmd_t pmd_mksplitting(pmd_t pmd)
+{
+	return __pmd(pmd_val(pmd) | _PAGE_SPLITTING);
+}
+
+#define __HAVE_ARCH_PMD_SAME
+static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
+{
+	return (((pmd_val(pmd_a) ^ pmd_val(pmd_b)) & ~_PAGE_HPTEFLAGS) == 0);
+}
+
+static inline int __pmdp_test_and_clear_young(struct mm_struct *mm,
+					      unsigned long addr, pmd_t *pmdp)
+{
+	unsigned long old;
+
+	if ((pmd_val(*pmdp) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0)
+		return 0;
+	old = pmd_hugepage_update(mm, addr, pmdp, _PAGE_ACCESSED, 0);
+	return ((old & _PAGE_ACCESSED) != 0);
+}
+
+#define __HAVE_ARCH_PMDP_SET_WRPROTECT
+static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr,
+				      pmd_t *pmdp)
+{
+
+	if ((pmd_val(*pmdp) & _PAGE_RW) == 0)
+		return;
+
+	pmd_hugepage_update(mm, addr, pmdp, _PAGE_RW, 0);
+}
+
+#endif /*  CONFIG_TRANSPARENT_HUGEPAGE */
+#endif	/* __ASSEMBLY__ */
+
+#endif /* _ASM_POWERPC_BOOK3S_64_HASH_64K_H */

arch/powerpc/include/asm/book3s/64/hash.h

@@ -0,0 +1,551 @@
+#ifndef _ASM_POWERPC_BOOK3S_64_HASH_H
+#define _ASM_POWERPC_BOOK3S_64_HASH_H
+#ifdef __KERNEL__
+
+/*
+ * Common bits between 4K and 64K pages in a linux-style PTE.
+ * These match the bits in the (hardware-defined) PowerPC PTE as closely
+ * as possible. Additional bits may be defined in pgtable-hash64-*.h
+ *
+ * Note: We only support user read/write permissions. Supervisor always
+ * have full read/write to pages above PAGE_OFFSET (pages below that
+ * always use the user access permissions).
+ *
+ * We could create separate kernel read-only if we used the 3 PP bits
+ * combinations that newer processors provide but we currently don't.
+ */
+#define _PAGE_PTE		0x00001
+#define _PAGE_PRESENT		0x00002 /* software: pte contains a translation */
+#define _PAGE_BIT_SWAP_TYPE	2
+#define _PAGE_USER		0x00004 /* matches one of the PP bits */
+#define _PAGE_EXEC		0x00008 /* No execute on POWER4 and newer (we invert) */
+#define _PAGE_GUARDED		0x00010
+/* We can derive Memory coherence from _PAGE_NO_CACHE */
+#define _PAGE_COHERENT		0x0
+#define _PAGE_NO_CACHE		0x00020 /* I: cache inhibit */
+#define _PAGE_WRITETHRU		0x00040 /* W: cache write-through */
+#define _PAGE_DIRTY		0x00080 /* C: page changed */
+#define _PAGE_ACCESSED		0x00100 /* R: page referenced */
+#define _PAGE_RW		0x00200 /* software: user write access allowed */
+#define _PAGE_HASHPTE		0x00400 /* software: pte has an associated HPTE */
+#define _PAGE_BUSY		0x00800 /* software: PTE & hash are busy */
+#define _PAGE_F_GIX		0x07000 /* full page: hidx bits */
+#define _PAGE_F_GIX_SHIFT	12
+#define _PAGE_F_SECOND		0x08000 /* Whether to use secondary hash or not */
+#define _PAGE_SPECIAL		0x10000 /* software: special page */
+
+#ifdef CONFIG_MEM_SOFT_DIRTY
+#define _PAGE_SOFT_DIRTY	0x20000 /* software: software dirty tracking */
+#else
+#define _PAGE_SOFT_DIRTY	0x00000
+#endif
+
+/*
+ * THP pages can't be special. So use the _PAGE_SPECIAL
+ */
+#define _PAGE_SPLITTING _PAGE_SPECIAL
+
+/*
+ * We need to differentiate between explicit huge page and THP huge
+ * page, since THP huge page also need to track real subpage details
+ */
+#define _PAGE_THP_HUGE  _PAGE_4K_PFN
+
+/*
+ * set of bits not changed in pmd_modify.
+ */
+#define _HPAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS |		\
+			 _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_SPLITTING | \
+			 _PAGE_THP_HUGE | _PAGE_PTE | _PAGE_SOFT_DIRTY)
+
+#ifdef CONFIG_PPC_64K_PAGES
+#include <asm/book3s/64/hash-64k.h>
+#else
+#include <asm/book3s/64/hash-4k.h>
+#endif
+
+/*
+ * Size of EA range mapped by our pagetables.
+ */
+#define PGTABLE_EADDR_SIZE	(PTE_INDEX_SIZE + PMD_INDEX_SIZE + \
+				 PUD_INDEX_SIZE + PGD_INDEX_SIZE + PAGE_SHIFT)
+#define PGTABLE_RANGE		(ASM_CONST(1) << PGTABLE_EADDR_SIZE)
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define PMD_CACHE_INDEX	(PMD_INDEX_SIZE + 1)
+#else
+#define PMD_CACHE_INDEX	PMD_INDEX_SIZE
+#endif
+/*
+ * Define the address range of the kernel non-linear virtual area
+ */
+#define KERN_VIRT_START ASM_CONST(0xD000000000000000)
+#define KERN_VIRT_SIZE	ASM_CONST(0x0000100000000000)
+
+/*
+ * The vmalloc space starts at the beginning of that region, and
+ * occupies half of it on hash CPUs and a quarter of it on Book3E
+ * (we keep a quarter for the virtual memmap)
+ */
+#define VMALLOC_START	KERN_VIRT_START
+#define VMALLOC_SIZE	(KERN_VIRT_SIZE >> 1)
+#define VMALLOC_END	(VMALLOC_START + VMALLOC_SIZE)
+
+/*
+ * Region IDs
+ */
+#define REGION_SHIFT		60UL
+#define REGION_MASK		(0xfUL << REGION_SHIFT)
+#define REGION_ID(ea)		(((unsigned long)(ea)) >> REGION_SHIFT)
+
+#define VMALLOC_REGION_ID	(REGION_ID(VMALLOC_START))
+#define KERNEL_REGION_ID	(REGION_ID(PAGE_OFFSET))
+#define VMEMMAP_REGION_ID	(0xfUL)	/* Server only */
+#define USER_REGION_ID		(0UL)
+
+/*
+ * Defines the address of the vmemap area, in its own region on
+ * hash table CPUs.
+ */
+#define VMEMMAP_BASE		(VMEMMAP_REGION_ID << REGION_SHIFT)
+
+#ifdef CONFIG_PPC_MM_SLICES
+#define HAVE_ARCH_UNMAPPED_AREA
+#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
+#endif /* CONFIG_PPC_MM_SLICES */
+
+/* No separate kernel read-only */
+#define _PAGE_KERNEL_RW		(_PAGE_RW | _PAGE_DIRTY) /* user access blocked by key */
+#define _PAGE_KERNEL_RO		 _PAGE_KERNEL_RW
+#define _PAGE_KERNEL_RWX	(_PAGE_DIRTY | _PAGE_RW | _PAGE_EXEC)
+
+/* Strong Access Ordering */
+#define _PAGE_SAO		(_PAGE_WRITETHRU | _PAGE_NO_CACHE | _PAGE_COHERENT)
+
+/* No page size encoding in the linux PTE */
+#define _PAGE_PSIZE		0
+
+/* PTEIDX nibble */
+#define _PTEIDX_SECONDARY	0x8
+#define _PTEIDX_GROUP_IX	0x7
+
+/* Hash table based platforms need atomic updates of the linux PTE */
+#define PTE_ATOMIC_UPDATES	1
+#define _PTE_NONE_MASK	_PAGE_HPTEFLAGS
+/*
+ * The mask convered by the RPN must be a ULL on 32-bit platforms with
+ * 64-bit PTEs
+ */
+#define PTE_RPN_MASK	(~((1UL << PTE_RPN_SHIFT) - 1))
+/*
+ * _PAGE_CHG_MASK masks of bits that are to be preserved across
+ * pgprot changes
+ */
+#define _PAGE_CHG_MASK	(PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \
+			 _PAGE_ACCESSED | _PAGE_SPECIAL | _PAGE_PTE | \
+			 _PAGE_SOFT_DIRTY)
+/*
+ * Mask of bits returned by pte_pgprot()
+ */
+#define PAGE_PROT_BITS	(_PAGE_GUARDED | _PAGE_COHERENT | _PAGE_NO_CACHE | \
+			 _PAGE_WRITETHRU | _PAGE_4K_PFN | \
+			 _PAGE_USER | _PAGE_ACCESSED |  \
+			 _PAGE_RW |  _PAGE_DIRTY | _PAGE_EXEC | \
+			 _PAGE_SOFT_DIRTY)
+/*
+ * We define 2 sets of base prot bits, one for basic pages (ie,
+ * cacheable kernel and user pages) and one for non cacheable
+ * pages. We always set _PAGE_COHERENT when SMP is enabled or
+ * the processor might need it for DMA coherency.
+ */
+#define _PAGE_BASE_NC	(_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_PSIZE)
+#define _PAGE_BASE	(_PAGE_BASE_NC | _PAGE_COHERENT)
+
+/* Permission masks used to generate the __P and __S table,
+ *
+ * Note:__pgprot is defined in arch/powerpc/include/asm/page.h
+ *
+ * Write permissions imply read permissions for now (we could make write-only
+ * pages on BookE but we don't bother for now). Execute permission control is
+ * possible on platforms that define _PAGE_EXEC
+ *
+ * Note due to the way vm flags are laid out, the bits are XWR
+ */
+#define PAGE_NONE	__pgprot(_PAGE_BASE)
+#define PAGE_SHARED	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW)
+#define PAGE_SHARED_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | \
+				 _PAGE_EXEC)
+#define PAGE_COPY	__pgprot(_PAGE_BASE | _PAGE_USER )
+#define PAGE_COPY_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC)
+#define PAGE_READONLY	__pgprot(_PAGE_BASE | _PAGE_USER )
+#define PAGE_READONLY_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC)
+
+#define __P000	PAGE_NONE
+#define __P001	PAGE_READONLY
+#define __P010	PAGE_COPY
+#define __P011	PAGE_COPY
+#define __P100	PAGE_READONLY_X
+#define __P101	PAGE_READONLY_X
+#define __P110	PAGE_COPY_X
+#define __P111	PAGE_COPY_X
+
+#define __S000	PAGE_NONE
+#define __S001	PAGE_READONLY
+#define __S010	PAGE_SHARED
+#define __S011	PAGE_SHARED
+#define __S100	PAGE_READONLY_X
+#define __S101	PAGE_READONLY_X
+#define __S110	PAGE_SHARED_X
+#define __S111	PAGE_SHARED_X
+
+/* Permission masks used for kernel mappings */
+#define PAGE_KERNEL	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RW)
+#define PAGE_KERNEL_NC	__pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | \
+				 _PAGE_NO_CACHE)
+#define PAGE_KERNEL_NCG	__pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | \
+				 _PAGE_NO_CACHE | _PAGE_GUARDED)
+#define PAGE_KERNEL_X	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RWX)
+#define PAGE_KERNEL_RO	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RO)
+#define PAGE_KERNEL_ROX	__pgprot(_PAGE_BASE | _PAGE_KERNEL_ROX)
+
+/* Protection used for kernel text. We want the debuggers to be able to
+ * set breakpoints anywhere, so don't write protect the kernel text
+ * on platforms where such control is possible.
+ */
+#if defined(CONFIG_KGDB) || defined(CONFIG_XMON) || defined(CONFIG_BDI_SWITCH) ||\
+	defined(CONFIG_KPROBES) || defined(CONFIG_DYNAMIC_FTRACE)
+#define PAGE_KERNEL_TEXT	PAGE_KERNEL_X
+#else
+#define PAGE_KERNEL_TEXT	PAGE_KERNEL_ROX
+#endif
+
+/* Make modules code happy. We don't set RO yet */
+#define PAGE_KERNEL_EXEC	PAGE_KERNEL_X
+#define PAGE_AGP		(PAGE_KERNEL_NC)
+
+#define PMD_BAD_BITS		(PTE_TABLE_SIZE-1)
+#define PUD_BAD_BITS		(PMD_TABLE_SIZE-1)
+
+#ifndef __ASSEMBLY__
+#define	pmd_bad(pmd)		(!is_kernel_addr(pmd_val(pmd)) \
+				 || (pmd_val(pmd) & PMD_BAD_BITS))
+#define pmd_page_vaddr(pmd)	(pmd_val(pmd) & ~PMD_MASKED_BITS)
+
+#define	pud_bad(pud)		(!is_kernel_addr(pud_val(pud)) \
+				 || (pud_val(pud) & PUD_BAD_BITS))
+#define pud_page_vaddr(pud)	(pud_val(pud) & ~PUD_MASKED_BITS)
+
+#define pgd_index(address) (((address) >> (PGDIR_SHIFT)) & (PTRS_PER_PGD - 1))
+#define pmd_index(address) (((address) >> (PMD_SHIFT)) & (PTRS_PER_PMD - 1))
+#define pte_index(address) (((address) >> (PAGE_SHIFT)) & (PTRS_PER_PTE - 1))
+
+extern void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
+			    pte_t *ptep, unsigned long pte, int huge);
+extern unsigned long htab_convert_pte_flags(unsigned long pteflags);
+/* Atomic PTE updates */
+static inline unsigned long pte_update(struct mm_struct *mm,
+				       unsigned long addr,
+				       pte_t *ptep, unsigned long clr,
+				       unsigned long set,
+				       int huge)
+{
+	unsigned long old, tmp;
+
+	__asm__ __volatile__(
+	"1:	ldarx	%0,0,%3		# pte_update\n\
+	andi.	%1,%0,%6\n\
+	bne-	1b \n\
+	andc	%1,%0,%4 \n\
+	or	%1,%1,%7\n\
+	stdcx.	%1,0,%3 \n\
+	bne-	1b"
+	: "=&r" (old), "=&r" (tmp), "=m" (*ptep)
+	: "r" (ptep), "r" (clr), "m" (*ptep), "i" (_PAGE_BUSY), "r" (set)
+	: "cc" );
+	/* huge pages use the old page table lock */
+	if (!huge)
+		assert_pte_locked(mm, addr);
+
+	if (old & _PAGE_HASHPTE)
+		hpte_need_flush(mm, addr, ptep, old, huge);
+
+	return old;
+}
+
+static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
+					      unsigned long addr, pte_t *ptep)
+{
+	unsigned long old;
+
+	if ((pte_val(*ptep) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0)
+		return 0;
+	old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0);
+	return (old & _PAGE_ACCESSED) != 0;
+}
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+#define ptep_test_and_clear_young(__vma, __addr, __ptep)		   \
+({									   \
+	int __r;							   \
+	__r = __ptep_test_and_clear_young((__vma)->vm_mm, __addr, __ptep); \
+	__r;								   \
+})
+
+#define __HAVE_ARCH_PTEP_SET_WRPROTECT
+static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
+				      pte_t *ptep)
+{
+
+	if ((pte_val(*ptep) & _PAGE_RW) == 0)
+		return;
+
+	pte_update(mm, addr, ptep, _PAGE_RW, 0, 0);
+}
+
+static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
+					   unsigned long addr, pte_t *ptep)
+{
+	if ((pte_val(*ptep) & _PAGE_RW) == 0)
+		return;
+
+	pte_update(mm, addr, ptep, _PAGE_RW, 0, 1);
+}
+
+/*
+ * We currently remove entries from the hashtable regardless of whether
+ * the entry was young or dirty. The generic routines only flush if the
+ * entry was young or dirty which is not good enough.
+ *
+ * We should be more intelligent about this but for the moment we override
+ * these functions and force a tlb flush unconditionally
+ */
+#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
+#define ptep_clear_flush_young(__vma, __address, __ptep)		\
+({									\
+	int __young = __ptep_test_and_clear_young((__vma)->vm_mm, __address, \
+						  __ptep);		\
+	__young;							\
+})
+
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
+				       unsigned long addr, pte_t *ptep)
+{
+	unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0, 0);
+	return __pte(old);
+}
+
+static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
+			     pte_t * ptep)
+{
+	pte_update(mm, addr, ptep, ~0UL, 0, 0);
+}
+
+
+/* Set the dirty and/or accessed bits atomically in a linux PTE, this
+ * function doesn't need to flush the hash entry
+ */
+static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry)
+{
+	unsigned long bits = pte_val(entry) &
+		(_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC |
+		 _PAGE_SOFT_DIRTY);
+
+	unsigned long old, tmp;
+
+	__asm__ __volatile__(
+	"1:	ldarx	%0,0,%4\n\
+		andi.	%1,%0,%6\n\
+		bne-	1b \n\
+		or	%0,%3,%0\n\
+		stdcx.	%0,0,%4\n\
+		bne-	1b"
+	:"=&r" (old), "=&r" (tmp), "=m" (*ptep)
+	:"r" (bits), "r" (ptep), "m" (*ptep), "i" (_PAGE_BUSY)
+	:"cc");
+}
+
+#define __HAVE_ARCH_PTE_SAME
+#define pte_same(A,B)	(((pte_val(A) ^ pte_val(B)) & ~_PAGE_HPTEFLAGS) == 0)
+
+/* Generic accessors to PTE bits */
+static inline int pte_write(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_RW);}
+static inline int pte_dirty(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_DIRTY); }
+static inline int pte_young(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_ACCESSED); }
+static inline int pte_special(pte_t pte)	{ return !!(pte_val(pte) & _PAGE_SPECIAL); }
+static inline int pte_none(pte_t pte)		{ return (pte_val(pte) & ~_PTE_NONE_MASK) == 0; }
+static inline pgprot_t pte_pgprot(pte_t pte)	{ return __pgprot(pte_val(pte) & PAGE_PROT_BITS); }
+
+#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
+static inline bool pte_soft_dirty(pte_t pte)
+{
+	return !!(pte_val(pte) & _PAGE_SOFT_DIRTY);
+}
+static inline pte_t pte_mksoft_dirty(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_SOFT_DIRTY);
+}
+
+static inline pte_t pte_clear_soft_dirty(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_SOFT_DIRTY);
+}
+#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */
+
+#ifdef CONFIG_NUMA_BALANCING
+/*
+ * These work without NUMA balancing but the kernel does not care. See the
+ * comment in include/asm-generic/pgtable.h . On powerpc, this will only
+ * work for user pages and always return true for kernel pages.
+ */
+static inline int pte_protnone(pte_t pte)
+{
+	return (pte_val(pte) &
+		(_PAGE_PRESENT | _PAGE_USER)) == _PAGE_PRESENT;
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
+static inline int pte_present(pte_t pte)
+{
+	return pte_val(pte) & _PAGE_PRESENT;
+}
+
+/* Conversion functions: convert a page and protection to a page entry,
+ * and a page entry and page directory to the page they refer to.
+ *
+ * Even if PTEs can be unsigned long long, a PFN is always an unsigned
+ * long for now.
+ */
+static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot)
+{
+	return __pte(((pte_basic_t)(pfn) << PTE_RPN_SHIFT) |
+		     pgprot_val(pgprot));
+}
+
+static inline unsigned long pte_pfn(pte_t pte)
+{
+	return pte_val(pte) >> PTE_RPN_SHIFT;
+}
+
+/* Generic modifiers for PTE bits */
+static inline pte_t pte_wrprotect(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_RW);
+}
+
+static inline pte_t pte_mkclean(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_DIRTY);
+}
+
+static inline pte_t pte_mkold(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_ACCESSED);
+}
+
+static inline pte_t pte_mkwrite(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_RW);
+}
+
+static inline pte_t pte_mkdirty(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_DIRTY | _PAGE_SOFT_DIRTY);
+}
+
+static inline pte_t pte_mkyoung(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_ACCESSED);
+}
+
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_SPECIAL);
+}
+
+static inline pte_t pte_mkhuge(pte_t pte)
+{
+	return pte;
+}
+
+static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+{
+	return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot));
+}
+
+/* This low level function performs the actual PTE insertion
+ * Setting the PTE depends on the MMU type and other factors. It's
+ * an horrible mess that I'm not going to try to clean up now but
+ * I'm keeping it in one place rather than spread around
+ */
+static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
+				pte_t *ptep, pte_t pte, int percpu)
+{
+	/*
+	 * Anything else just stores the PTE normally. That covers all 64-bit
+	 * cases, and 32-bit non-hash with 32-bit PTEs.
+	 */
+	*ptep = pte;
+}
+
+/*
+ * Macro to mark a page protection value as "uncacheable".
+ */
+
+#define _PAGE_CACHE_CTL	(_PAGE_COHERENT | _PAGE_GUARDED | _PAGE_NO_CACHE | \
+			 _PAGE_WRITETHRU)
+
+#define pgprot_noncached pgprot_noncached
+static inline pgprot_t pgprot_noncached(pgprot_t prot)
+{
+	return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) |
+			_PAGE_NO_CACHE | _PAGE_GUARDED);
+}
+
+#define pgprot_noncached_wc pgprot_noncached_wc
+static inline pgprot_t pgprot_noncached_wc(pgprot_t prot)
+{
+	return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) |
+			_PAGE_NO_CACHE);
+}
+
+#define pgprot_cached pgprot_cached
+static inline pgprot_t pgprot_cached(pgprot_t prot)
+{
+	return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) |
+			_PAGE_COHERENT);
+}
+
+#define pgprot_cached_wthru pgprot_cached_wthru
+static inline pgprot_t pgprot_cached_wthru(pgprot_t prot)
+{
+	return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) |
+			_PAGE_COHERENT | _PAGE_WRITETHRU);
+}
+
+#define pgprot_cached_noncoherent pgprot_cached_noncoherent
+static inline pgprot_t pgprot_cached_noncoherent(pgprot_t prot)
+{
+	return __pgprot(pgprot_val(prot) & ~_PAGE_CACHE_CTL);
+}
+
+#define pgprot_writecombine pgprot_writecombine
+static inline pgprot_t pgprot_writecombine(pgprot_t prot)
+{
+	return pgprot_noncached_wc(prot);
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+extern void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
+				   pmd_t *pmdp, unsigned long old_pmd);
+#else
+static inline void hpte_do_hugepage_flush(struct mm_struct *mm,
+					  unsigned long addr, pmd_t *pmdp,
+					  unsigned long old_pmd)
+{
+	WARN(1, "%s called with THP disabled\n", __func__);
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+#endif /* !__ASSEMBLY__ */
+#endif /* __KERNEL__ */
+#endif /* _ASM_POWERPC_BOOK3S_64_HASH_H */

arch/powerpc/include/asm/book3s/64/pgtable.h

@@ -0,0 +1,300 @@
+#ifndef _ASM_POWERPC_BOOK3S_64_PGTABLE_H_
+#define _ASM_POWERPC_BOOK3S_64_PGTABLE_H_
+/*
+ * This file contains the functions and defines necessary to modify and use
+ * the ppc64 hashed page table.
+ */
+
+#include <asm/book3s/64/hash.h>
+#include <asm/barrier.h>
+
+/*
+ * The second half of the kernel virtual space is used for IO mappings,
+ * it's itself carved into the PIO region (ISA and PHB IO space) and
+ * the ioremap space
+ *
+ *  ISA_IO_BASE = KERN_IO_START, 64K reserved area
+ *  PHB_IO_BASE = ISA_IO_BASE + 64K to ISA_IO_BASE + 2G, PHB IO spaces
+ * IOREMAP_BASE = ISA_IO_BASE + 2G to VMALLOC_START + PGTABLE_RANGE
+ */
+#define KERN_IO_START	(KERN_VIRT_START + (KERN_VIRT_SIZE >> 1))
+#define FULL_IO_SIZE	0x80000000ul
+#define  ISA_IO_BASE	(KERN_IO_START)
+#define  ISA_IO_END	(KERN_IO_START + 0x10000ul)
+#define  PHB_IO_BASE	(ISA_IO_END)
+#define  PHB_IO_END	(KERN_IO_START + FULL_IO_SIZE)
+#define IOREMAP_BASE	(PHB_IO_END)
+#define IOREMAP_END	(KERN_VIRT_START + KERN_VIRT_SIZE)
+
+#define vmemmap			((struct page *)VMEMMAP_BASE)
+
+/* Advertise special mapping type for AGP */
+#define HAVE_PAGE_AGP
+
+/* Advertise support for _PAGE_SPECIAL */
+#define __HAVE_ARCH_PTE_SPECIAL
+
+#ifndef __ASSEMBLY__
+
+/*
+ * This is the default implementation of various PTE accessors, it's
+ * used in all cases except Book3S with 64K pages where we have a
+ * concept of sub-pages
+ */
+#ifndef __real_pte
+
+#ifdef CONFIG_STRICT_MM_TYPECHECKS
+#define __real_pte(e,p)		((real_pte_t){(e)})
+#define __rpte_to_pte(r)	((r).pte)
+#else
+#define __real_pte(e,p)		(e)
+#define __rpte_to_pte(r)	(__pte(r))
+#endif
+#define __rpte_to_hidx(r,index)	(pte_val(__rpte_to_pte(r)) >>_PAGE_F_GIX_SHIFT)
+
+#define pte_iterate_hashed_subpages(rpte, psize, va, index, shift)       \
+	do {							         \
+		index = 0;					         \
+		shift = mmu_psize_defs[psize].shift;		         \
+
+#define pte_iterate_hashed_end() } while(0)
+
+/*
+ * We expect this to be called only for user addresses or kernel virtual
+ * addresses other than the linear mapping.
+ */
+#define pte_pagesize_index(mm, addr, pte)	MMU_PAGE_4K
+
+#endif /* __real_pte */
+
+static inline void pmd_set(pmd_t *pmdp, unsigned long val)
+{
+	*pmdp = __pmd(val);
+}
+
+static inline void pmd_clear(pmd_t *pmdp)
+{
+	*pmdp = __pmd(0);
+}
+
+#define pmd_none(pmd)		(!pmd_val(pmd))
+#define	pmd_present(pmd)	(!pmd_none(pmd))
+
+static inline void pud_set(pud_t *pudp, unsigned long val)
+{
+	*pudp = __pud(val);
+}
+
+static inline void pud_clear(pud_t *pudp)
+{
+	*pudp = __pud(0);
+}
+
+#define pud_none(pud)		(!pud_val(pud))
+#define pud_present(pud)	(pud_val(pud) != 0)
+
+extern struct page *pud_page(pud_t pud);
+extern struct page *pmd_page(pmd_t pmd);
+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_write(pgd)		pte_write(pgd_pte(pgd))
+static inline void pgd_set(pgd_t *pgdp, unsigned long val)
+{
+	*pgdp = __pgd(val);
+}
+
+/*
+ * Find an entry in a page-table-directory.  We combine the address region
+ * (the high order N bits) and the pgd portion of the address.
+ */
+
+#define pgd_offset(mm, address)	 ((mm)->pgd + pgd_index(address))
+
+#define pmd_offset(pudp,addr) \
+	(((pmd_t *) pud_page_vaddr(*(pudp))) + pmd_index(addr))
+
+#define pte_offset_kernel(dir,addr) \
+	(((pte_t *) pmd_page_vaddr(*(dir))) + pte_index(addr))
+
+#define pte_offset_map(dir,addr)	pte_offset_kernel((dir), (addr))
+#define pte_unmap(pte)			do { } while(0)
+
+/* to find an entry in a kernel page-table-directory */
+/* This now only contains the vmalloc pages */
+#define pgd_offset_k(address) pgd_offset(&init_mm, address)
+
+#define pte_ERROR(e) \
+	pr_err("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e))
+#define pmd_ERROR(e) \
+	pr_err("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e))
+#define pgd_ERROR(e) \
+	pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
+
+/* Encode and de-code a swap entry */
+#define MAX_SWAPFILES_CHECK() do { \
+	BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS); \
+	/*							\
+	 * Don't have overlapping bits with _PAGE_HPTEFLAGS	\
+	 * We filter HPTEFLAGS on set_pte.			\
+	 */							\
+	BUILD_BUG_ON(_PAGE_HPTEFLAGS & (0x1f << _PAGE_BIT_SWAP_TYPE)); \
+	BUILD_BUG_ON(_PAGE_HPTEFLAGS & _PAGE_SWP_SOFT_DIRTY);	\
+	} while (0)
+/*
+ * on pte we don't need handle RADIX_TREE_EXCEPTIONAL_SHIFT;
+ */
+#define SWP_TYPE_BITS 5
+#define __swp_type(x)		(((x).val >> _PAGE_BIT_SWAP_TYPE) \
+				& ((1UL << SWP_TYPE_BITS) - 1))
+#define __swp_offset(x)		((x).val >> PTE_RPN_SHIFT)
+#define __swp_entry(type, offset)	((swp_entry_t) { \
+					((type) << _PAGE_BIT_SWAP_TYPE) \
+					| ((offset) << PTE_RPN_SHIFT) })
+/*
+ * swp_entry_t must be independent of pte bits. We build a swp_entry_t from
+ * swap type and offset we get from swap and convert that to pte to find a
+ * matching pte in linux page table.
+ * Clear bits not found in swap entries here.
+ */
+#define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val((pte)) & ~_PAGE_PTE })
+#define __swp_entry_to_pte(x)	__pte((x).val | _PAGE_PTE)
+
+#ifdef CONFIG_MEM_SOFT_DIRTY
+#define _PAGE_SWP_SOFT_DIRTY   (1UL << (SWP_TYPE_BITS + _PAGE_BIT_SWAP_TYPE))
+#else
+#define _PAGE_SWP_SOFT_DIRTY	0UL
+#endif /* CONFIG_MEM_SOFT_DIRTY */
+
+#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
+static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_SWP_SOFT_DIRTY);
+}
+static inline bool pte_swp_soft_dirty(pte_t pte)
+{
+	return !!(pte_val(pte) & _PAGE_SWP_SOFT_DIRTY);
+}
+static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_SWP_SOFT_DIRTY);
+}
+#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */
+
+void pgtable_cache_add(unsigned shift, void (*ctor)(void *));
+void pgtable_cache_init(void);
+
+struct page *realmode_pfn_to_page(unsigned long pfn);
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+extern pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot);
+extern pmd_t mk_pmd(struct page *page, pgprot_t pgprot);
+extern pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot);
+extern void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+		       pmd_t *pmdp, pmd_t pmd);
+extern void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
+				 pmd_t *pmd);
+extern int has_transparent_hugepage(void);
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+
+static inline pte_t pmd_pte(pmd_t pmd)
+{
+	return __pte(pmd_val(pmd));
+}
+
+static inline pmd_t pte_pmd(pte_t pte)
+{
+	return __pmd(pte_val(pte));
+}
+
+static inline pte_t *pmdp_ptep(pmd_t *pmd)
+{
+	return (pte_t *)pmd;
+}
+
+#define pmd_pfn(pmd)		pte_pfn(pmd_pte(pmd))
+#define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
+#define pmd_young(pmd)		pte_young(pmd_pte(pmd))
+#define pmd_mkold(pmd)		pte_pmd(pte_mkold(pmd_pte(pmd)))
+#define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
+#define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
+#define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
+#define pmd_mkwrite(pmd)	pte_pmd(pte_mkwrite(pmd_pte(pmd)))
+
+#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
+#define pmd_soft_dirty(pmd)    pte_soft_dirty(pmd_pte(pmd))
+#define pmd_mksoft_dirty(pmd)  pte_pmd(pte_mksoft_dirty(pmd_pte(pmd)))
+#define pmd_clear_soft_dirty(pmd) pte_pmd(pte_clear_soft_dirty(pmd_pte(pmd)))
+#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */
+
+#ifdef CONFIG_NUMA_BALANCING
+static inline int pmd_protnone(pmd_t pmd)
+{
+	return pte_protnone(pmd_pte(pmd));
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
+#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write(pmd)		pte_write(pmd_pte(pmd))
+
+static inline pmd_t pmd_mkhuge(pmd_t pmd)
+{
+	return __pmd(pmd_val(pmd) | (_PAGE_PTE | _PAGE_THP_HUGE));
+}
+
+#define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
+extern int pmdp_set_access_flags(struct vm_area_struct *vma,
+				 unsigned long address, pmd_t *pmdp,
+				 pmd_t entry, int dirty);
+
+#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
+extern int pmdp_test_and_clear_young(struct vm_area_struct *vma,
+				     unsigned long address, pmd_t *pmdp);
+#define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
+extern int pmdp_clear_flush_young(struct vm_area_struct *vma,
+				  unsigned long address, pmd_t *pmdp);
+
+#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
+extern pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
+				     unsigned long addr, pmd_t *pmdp);
+
+#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH
+extern void pmdp_splitting_flush(struct vm_area_struct *vma,
+				 unsigned long address, pmd_t *pmdp);
+
+extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
+				 unsigned long address, pmd_t *pmdp);
+#define pmdp_collapse_flush pmdp_collapse_flush
+
+#define __HAVE_ARCH_PGTABLE_DEPOSIT
+extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+				       pgtable_t pgtable);
+#define __HAVE_ARCH_PGTABLE_WITHDRAW
+extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
+
+#define __HAVE_ARCH_PMDP_INVALIDATE
+extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
+			    pmd_t *pmdp);
+
+#define pmd_move_must_withdraw pmd_move_must_withdraw
+struct spinlock;
+static inline int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl,
+					 struct spinlock *old_pmd_ptl)
+{
+	/*
+	 * Archs like ppc64 use pgtable to store per pmd
+	 * specific information. So when we switch the pmd,
+	 * we should also withdraw and deposit the pgtable
+	 */
+	return true;
+}
+#endif /* __ASSEMBLY__ */
+#endif /* _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ */

arch/powerpc/include/asm/book3s/pgtable.h

@@ -0,0 +1,29 @@
+#ifndef _ASM_POWERPC_BOOK3S_PGTABLE_H
+#define _ASM_POWERPC_BOOK3S_PGTABLE_H
+
+#ifdef CONFIG_PPC64
+#include <asm/book3s/64/pgtable.h>
+#else
+#include <asm/book3s/32/pgtable.h>
+#endif
+
+#define FIRST_USER_ADDRESS	0UL
+#ifndef __ASSEMBLY__
+/* Insert a PTE, top-level function is out of line. It uses an inline
+ * low level function in the respective pgtable-* files
+ */
+extern void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+		       pte_t pte);
+
+
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address,
+				 pte_t *ptep, pte_t entry, int dirty);
+
+struct file;
+extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+				     unsigned long size, pgprot_t vma_prot);
+#define __HAVE_PHYS_MEM_ACCESS_PROT
+
+#endif /* __ASSEMBLY__ */
+#endif

arch/powerpc/include/asm/cmpxchg.h

@@ -18,12 +18,12 @@ __xchg_u32(volatile void *p, unsigned long val)
 	unsigned long prev;
 
 	__asm__ __volatile__(
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	lwarx	%0,0,%2 \n"
 	PPC405_ERR77(0,%2)
 "	stwcx.	%3,0,%2 \n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	: "=&r" (prev), "+m" (*(volatile unsigned int *)p)
 	: "r" (p), "r" (val)
 	: "cc", "memory");
@@ -61,12 +61,12 @@ __xchg_u64(volatile void *p, unsigned long val)
 	unsigned long prev;
 
 	__asm__ __volatile__(
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	ldarx	%0,0,%2 \n"
 	PPC405_ERR77(0,%2)
 "	stdcx.	%3,0,%2 \n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	: "=&r" (prev), "+m" (*(volatile unsigned long *)p)
 	: "r" (p), "r" (val)
 	: "cc", "memory");
@@ -151,14 +151,14 @@ __cmpxchg_u32(volatile unsigned int *p, unsigned long old, unsigned long new)
 	unsigned int prev;
 
 	__asm__ __volatile__ (
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	lwarx	%0,0,%2		# __cmpxchg_u32\n\
 	cmpw	0,%0,%3\n\
 	bne-	2f\n"
 	PPC405_ERR77(0,%2)
 "	stwcx.	%4,0,%2\n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	"\n\
 2:"
 	: "=&r" (prev), "+m" (*p)
@@ -197,13 +197,13 @@ __cmpxchg_u64(volatile unsigned long *p, unsigned long old, unsigned long new)
 	unsigned long prev;
 
 	__asm__ __volatile__ (
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	ldarx	%0,0,%2		# __cmpxchg_u64\n\
 	cmpd	0,%0,%3\n\
 	bne-	2f\n\
 	stdcx.	%4,0,%2\n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	"\n\
 2:"
 	: "=&r" (prev), "+m" (*p)

arch/powerpc/include/asm/cpm.h

@@ -5,6 +5,7 @@
 #include <linux/types.h>
 #include <linux/errno.h>
 #include <linux/of.h>
+#include <soc/fsl/qe/qe.h>
 
 /*
  * SPI Parameter RAM common to QE and CPM.
@@ -155,49 +156,6 @@ typedef struct cpm_buf_desc {
  */
 #define BD_I2C_START		(0x0400)
 
-int cpm_muram_init(void);
-
-#if defined(CONFIG_CPM) || defined(CONFIG_QUICC_ENGINE)
-unsigned long cpm_muram_alloc(unsigned long size, unsigned long align);
-int cpm_muram_free(unsigned long offset);
-unsigned long cpm_muram_alloc_fixed(unsigned long offset, unsigned long size);
-void __iomem *cpm_muram_addr(unsigned long offset);
-unsigned long cpm_muram_offset(void __iomem *addr);
-dma_addr_t cpm_muram_dma(void __iomem *addr);
-#else
-static inline unsigned long cpm_muram_alloc(unsigned long size,
-					    unsigned long align)
-{
-	return -ENOSYS;
-}
-
-static inline int cpm_muram_free(unsigned long offset)
-{
-	return -ENOSYS;
-}
-
-static inline unsigned long cpm_muram_alloc_fixed(unsigned long offset,
-						  unsigned long size)
-{
-	return -ENOSYS;
-}
-
-static inline void __iomem *cpm_muram_addr(unsigned long offset)
-{
-	return NULL;
-}
-
-static inline unsigned long cpm_muram_offset(void __iomem *addr)
-{
-	return -ENOSYS;
-}
-
-static inline dma_addr_t cpm_muram_dma(void __iomem *addr)
-{
-	return 0;
-}
-#endif /* defined(CONFIG_CPM) || defined(CONFIG_QUICC_ENGINE) */
-
 #ifdef CONFIG_CPM
 int cpm_command(u32 command, u8 opcode);
 #else

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

@@ -129,15 +129,6 @@ BEGIN_FTR_SECTION_NESTED(941)						\
 	mtspr	SPRN_PPR,ra;						\
 END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,941)
 
-/*
- * Increase the priority on systems where PPR save/restore is not
- * implemented/ supported.
- */
-#define HMT_MEDIUM_PPR_DISCARD						\
-BEGIN_FTR_SECTION_NESTED(942)						\
-	HMT_MEDIUM;							\
-END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,0,942)  /*non P7*/		
-
 /*
  * Get an SPR into a register if the CPU has the given feature
  */
@@ -263,17 +254,6 @@ do_kvm_##n:								\
 #define KVM_HANDLER_SKIP(area, h, n)
 #endif
 
-#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
-#define KVMTEST_PR(n)			__KVMTEST(n)
-#define KVM_HANDLER_PR(area, h, n)	__KVM_HANDLER(area, h, n)
-#define KVM_HANDLER_PR_SKIP(area, h, n)	__KVM_HANDLER_SKIP(area, h, n)
-
-#else
-#define KVMTEST_PR(n)
-#define KVM_HANDLER_PR(area, h, n)
-#define KVM_HANDLER_PR_SKIP(area, h, n)
-#endif
-
 #define NOTEST(n)
 
 /*
@@ -353,27 +333,25 @@ do_kvm_##n:								\
 /*
  * Exception vectors.
  */
-#define STD_EXCEPTION_PSERIES(loc, vec, label)		\
-	. = loc;					\
+#define STD_EXCEPTION_PSERIES(vec, label)		\
+	. = vec;					\
 	.globl label##_pSeries;				\
 label##_pSeries:					\
-	HMT_MEDIUM_PPR_DISCARD;				\
 	SET_SCRATCH0(r13);		/* save r13 */		\
 	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common,	\
-				 EXC_STD, KVMTEST_PR, vec)
+				 EXC_STD, KVMTEST, vec)
 
 /* Version of above for when we have to branch out-of-line */
 #define STD_EXCEPTION_PSERIES_OOL(vec, label)			\
 	.globl label##_pSeries;					\
 label##_pSeries:						\
-	EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_PR, vec);	\
+	EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST, vec);	\
 	EXCEPTION_PROLOG_PSERIES_1(label##_common, EXC_STD)
 
 #define STD_EXCEPTION_HV(loc, vec, label)		\
 	. = loc;					\
 	.globl label##_hv;				\
 label##_hv:						\
-	HMT_MEDIUM_PPR_DISCARD;				\
 	SET_SCRATCH0(r13);	/* save r13 */			\
 	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common,	\
 				 EXC_HV, KVMTEST, vec)
@@ -389,7 +367,6 @@ label##_hv:						\
 	. = loc;					\
 	.globl label##_relon_pSeries;			\
 label##_relon_pSeries:					\
-	HMT_MEDIUM_PPR_DISCARD;				\
 	/* No guest interrupts come through here */	\
 	SET_SCRATCH0(r13);		/* save r13 */	\
 	EXCEPTION_RELON_PROLOG_PSERIES(PACA_EXGEN, label##_common, \
@@ -405,7 +382,6 @@ label##_relon_pSeries:						\
 	. = loc;					\
 	.globl label##_relon_hv;			\
 label##_relon_hv:					\
-	HMT_MEDIUM_PPR_DISCARD;				\
 	/* No guest interrupts come through here */	\
 	SET_SCRATCH0(r13);	/* save r13 */		\
 	EXCEPTION_RELON_PROLOG_PSERIES(PACA_EXGEN, label##_common, \
@@ -436,17 +412,13 @@ label##_relon_hv:						\
 #define _SOFTEN_TEST(h, vec)	__SOFTEN_TEST(h, vec)
 
 #define SOFTEN_TEST_PR(vec)						\
-	KVMTEST_PR(vec);						\
+	KVMTEST(vec);							\
 	_SOFTEN_TEST(EXC_STD, vec)
 
 #define SOFTEN_TEST_HV(vec)						\
 	KVMTEST(vec);							\
 	_SOFTEN_TEST(EXC_HV, vec)
 
-#define SOFTEN_TEST_HV_201(vec)						\
-	KVMTEST(vec);							\
-	_SOFTEN_TEST(EXC_STD, vec)
-
 #define SOFTEN_NOTEST_PR(vec)		_SOFTEN_TEST(EXC_STD, vec)
 #define SOFTEN_NOTEST_HV(vec)		_SOFTEN_TEST(EXC_HV, vec)
 
@@ -463,7 +435,6 @@ label##_relon_hv:						\
 	. = loc;							\
 	.globl label##_pSeries;						\
 label##_pSeries:							\
-	HMT_MEDIUM_PPR_DISCARD;						\
 	_MASKABLE_EXCEPTION_PSERIES(vec, label,				\
 				    EXC_STD, SOFTEN_TEST_PR)
 
@@ -481,7 +452,6 @@ label##_hv:								\
 	EXCEPTION_PROLOG_PSERIES_1(label##_common, EXC_HV);
 
 #define __MASKABLE_RELON_EXCEPTION_PSERIES(vec, label, h, extra)	\
-	HMT_MEDIUM_PPR_DISCARD;						\
 	SET_SCRATCH0(r13);    /* save r13 */				\
 	EXCEPTION_PROLOG_0(PACA_EXGEN);					\
 	__EXCEPTION_PROLOG_1(PACA_EXGEN, extra, vec);		\

arch/powerpc/include/asm/firmware.h

@@ -47,12 +47,10 @@
 #define FW_FEATURE_VPHN		ASM_CONST(0x0000000004000000)
 #define FW_FEATURE_XCMO		ASM_CONST(0x0000000008000000)
 #define FW_FEATURE_OPAL		ASM_CONST(0x0000000010000000)
-#define FW_FEATURE_OPALv2	ASM_CONST(0x0000000020000000)
 #define FW_FEATURE_SET_MODE	ASM_CONST(0x0000000040000000)
 #define FW_FEATURE_BEST_ENERGY	ASM_CONST(0x0000000080000000)
 #define FW_FEATURE_TYPE1_AFFINITY ASM_CONST(0x0000000100000000)
 #define FW_FEATURE_PRRN		ASM_CONST(0x0000000200000000)
-#define FW_FEATURE_OPALv3	ASM_CONST(0x0000000400000000)
 
 #ifndef __ASSEMBLY__
 
@@ -70,8 +68,7 @@ enum {
 		FW_FEATURE_SET_MODE | FW_FEATURE_BEST_ENERGY |
 		FW_FEATURE_TYPE1_AFFINITY | FW_FEATURE_PRRN,
 	FW_FEATURE_PSERIES_ALWAYS = 0,
-	FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL | FW_FEATURE_OPALv2 |
-		FW_FEATURE_OPALv3,
+	FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL,
 	FW_FEATURE_POWERNV_ALWAYS = 0,
 	FW_FEATURE_PS3_POSSIBLE = FW_FEATURE_LPAR | FW_FEATURE_PS3_LV1,
 	FW_FEATURE_PS3_ALWAYS = FW_FEATURE_LPAR | FW_FEATURE_PS3_LV1,

arch/powerpc/include/asm/io.h

@@ -385,6 +385,17 @@ static inline void __raw_writeq(unsigned long v, volatile void __iomem *addr)
 {
 	*(volatile unsigned long __force *)PCI_FIX_ADDR(addr) = v;
 }
+
+/*
+ * Real mode version of the above. stdcix is only supposed to be used
+ * in hypervisor real mode as per the architecture spec.
+ */
+static inline void __raw_rm_writeq(u64 val, volatile void __iomem *paddr)
+{
+	__asm__ __volatile__("stdcix %0,0,%1"
+		: : "r" (val), "r" (paddr) : "memory");
+}
+
 #endif /* __powerpc64__ */
 
 /*

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

@@ -21,7 +21,7 @@
  * need for various slices related matters. Note that this isn't the
  * complete pgtable.h but only a portion of it.
  */
-#include <asm/pgtable-ppc64.h>
+#include <asm/book3s/64/pgtable.h>
 #include <asm/bug.h>
 #include <asm/processor.h>
 

arch/powerpc/include/asm/pgtable-ppc32.h → arch/powerpc/include/asm/nohash/32/pgtable.h

@@ -1,5 +1,5 @@
-#ifndef _ASM_POWERPC_PGTABLE_PPC32_H
-#define _ASM_POWERPC_PGTABLE_PPC32_H
+#ifndef _ASM_POWERPC_NOHASH_32_PGTABLE_H
+#define _ASM_POWERPC_NOHASH_32_PGTABLE_H
 
 #include <asm-generic/pgtable-nopmd.h>
 
@@ -106,17 +106,15 @@ extern int icache_44x_need_flush;
  */
 
 #if defined(CONFIG_40x)
-#include <asm/pte-40x.h>
+#include <asm/nohash/32/pte-40x.h>
 #elif defined(CONFIG_44x)
-#include <asm/pte-44x.h>
+#include <asm/nohash/32/pte-44x.h>
 #elif defined(CONFIG_FSL_BOOKE) && defined(CONFIG_PTE_64BIT)
-#include <asm/pte-book3e.h>
+#include <asm/nohash/pte-book3e.h>
 #elif defined(CONFIG_FSL_BOOKE)
-#include <asm/pte-fsl-booke.h>
+#include <asm/nohash/32/pte-fsl-booke.h>
 #elif defined(CONFIG_8xx)
-#include <asm/pte-8xx.h>
-#else /* CONFIG_6xx */
-#include <asm/pte-hash32.h>
+#include <asm/nohash/32/pte-8xx.h>
 #endif
 
 /* And here we include common definitions */
@@ -130,7 +128,12 @@ extern int icache_44x_need_flush;
 #define pmd_none(pmd)		(!pmd_val(pmd))
 #define	pmd_bad(pmd)		(pmd_val(pmd) & _PMD_BAD)
 #define	pmd_present(pmd)	(pmd_val(pmd) & _PMD_PRESENT_MASK)
-#define	pmd_clear(pmdp)		do { pmd_val(*(pmdp)) = 0; } while (0)
+static inline void pmd_clear(pmd_t *pmdp)
+{
+	*pmdp = __pmd(0);
+}
+
+
 
 /*
  * When flushing the tlb entry for a page, we also need to flush the hash
@@ -337,4 +340,4 @@ extern int get_pteptr(struct mm_struct *mm, unsigned long addr, pte_t **ptep,
 
 #endif /* !__ASSEMBLY__ */
 
-#endif /* _ASM_POWERPC_PGTABLE_PPC32_H */
+#endif /* __ASM_POWERPC_NOHASH_32_PGTABLE_H */

arch/powerpc/include/asm/pte-40x.h → arch/powerpc/include/asm/nohash/32/pte-40x.h

@@ -1,5 +1,5 @@
-#ifndef _ASM_POWERPC_PTE_40x_H
-#define _ASM_POWERPC_PTE_40x_H
+#ifndef _ASM_POWERPC_NOHASH_32_PTE_40x_H
+#define _ASM_POWERPC_NOHASH_32_PTE_40x_H
 #ifdef __KERNEL__
 
 /*
@@ -61,4 +61,4 @@
 #define PTE_ATOMIC_UPDATES	1
 
 #endif /* __KERNEL__ */
-#endif /*  _ASM_POWERPC_PTE_40x_H */
+#endif /*  _ASM_POWERPC_NOHASH_32_PTE_40x_H */

arch/powerpc/include/asm/pte-44x.h → arch/powerpc/include/asm/nohash/32/pte-44x.h

@@ -1,5 +1,5 @@
-#ifndef _ASM_POWERPC_PTE_44x_H
-#define _ASM_POWERPC_PTE_44x_H
+#ifndef _ASM_POWERPC_NOHASH_32_PTE_44x_H
+#define _ASM_POWERPC_NOHASH_32_PTE_44x_H
 #ifdef __KERNEL__
 
 /*
@@ -94,4 +94,4 @@
 
 
 #endif /* __KERNEL__ */
-#endif /*  _ASM_POWERPC_PTE_44x_H */
+#endif /*  _ASM_POWERPC_NOHASH_32_PTE_44x_H */

arch/powerpc/include/asm/pte-8xx.h → arch/powerpc/include/asm/nohash/32/pte-8xx.h

@@ -1,5 +1,5 @@
-#ifndef _ASM_POWERPC_PTE_8xx_H
-#define _ASM_POWERPC_PTE_8xx_H
+#ifndef _ASM_POWERPC_NOHASH_32_PTE_8xx_H
+#define _ASM_POWERPC_NOHASH_32_PTE_8xx_H
 #ifdef __KERNEL__
 
 /*
@@ -62,4 +62,4 @@
 				 _PAGE_HWWRITE | _PAGE_EXEC)
 
 #endif /* __KERNEL__ */
-#endif /*  _ASM_POWERPC_PTE_8xx_H */
+#endif /*  _ASM_POWERPC_NOHASH_32_PTE_8xx_H */

arch/powerpc/include/asm/pte-fsl-booke.h → arch/powerpc/include/asm/nohash/32/pte-fsl-booke.h

@@ -1,5 +1,5 @@
-#ifndef _ASM_POWERPC_PTE_FSL_BOOKE_H
-#define _ASM_POWERPC_PTE_FSL_BOOKE_H
+#ifndef _ASM_POWERPC_NOHASH_32_PTE_FSL_BOOKE_H
+#define _ASM_POWERPC_NOHASH_32_PTE_FSL_BOOKE_H
 #ifdef __KERNEL__
 
 /* PTE bit definitions for Freescale BookE SW loaded TLB MMU based
@@ -37,4 +37,4 @@
 #define PTE_WIMGE_SHIFT (6)
 
 #endif /* __KERNEL__ */
-#endif /*  _ASM_POWERPC_PTE_FSL_BOOKE_H */
+#endif /*  _ASM_POWERPC_NOHASH_32_PTE_FSL_BOOKE_H */

arch/powerpc/include/asm/pgtable-ppc64-4k.h → arch/powerpc/include/asm/nohash/64/pgtable-4k.h

@@ -1,5 +1,5 @@
-#ifndef _ASM_POWERPC_PGTABLE_PPC64_4K_H
-#define _ASM_POWERPC_PGTABLE_PPC64_4K_H
+#ifndef _ASM_POWERPC_NOHASH_64_PGTABLE_4K_H
+#define _ASM_POWERPC_NOHASH_64_PGTABLE_4K_H
 /*
  * Entries per page directory level.  The PTE level must use a 64b record
  * for each page table entry.  The PMD and PGD level use a 32b record for
@@ -55,11 +55,15 @@
 #define pgd_none(pgd)		(!pgd_val(pgd))
 #define pgd_bad(pgd)		(pgd_val(pgd) == 0)
 #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)
 
 #ifndef __ASSEMBLY__
 
+static inline void pgd_clear(pgd_t *pgdp)
+{
+	*pgdp = __pgd(0);
+}
+
 static inline pte_t pgd_pte(pgd_t pgd)
 {
 	return __pte(pgd_val(pgd));
@@ -85,4 +89,4 @@ extern struct page *pgd_page(pgd_t pgd);
 #define remap_4k_pfn(vma, addr, pfn, prot)	\
 	remap_pfn_range((vma), (addr), (pfn), PAGE_SIZE, (prot))
 
-#endif /* _ASM_POWERPC_PGTABLE_PPC64_4K_H */
+#endif /* _ _ASM_POWERPC_NOHASH_64_PGTABLE_4K_H */

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

@@ -1,5 +1,5 @@
-#ifndef _ASM_POWERPC_PGTABLE_PPC64_64K_H
-#define _ASM_POWERPC_PGTABLE_PPC64_64K_H
+#ifndef _ASM_POWERPC_NOHASH_64_PGTABLE_64K_H
+#define _ASM_POWERPC_NOHASH_64_PGTABLE_64K_H
 
 #include <asm-generic/pgtable-nopud.h>
 
@@ -9,8 +9,19 @@
 #define PUD_INDEX_SIZE	0
 #define PGD_INDEX_SIZE  12
 
+/*
+ * we support 32 fragments per PTE page of 64K size
+ */
+#define PTE_FRAG_NR	32
+/*
+ * We use a 2K PTE page fragment and another 2K for storing
+ * real_pte_t hash index
+ */
+#define PTE_FRAG_SIZE_SHIFT  11
+#define PTE_FRAG_SIZE (1UL << PTE_FRAG_SIZE_SHIFT)
+
 #ifndef __ASSEMBLY__
-#define PTE_TABLE_SIZE	(sizeof(real_pte_t) << PTE_INDEX_SIZE)
+#define PTE_TABLE_SIZE	PTE_FRAG_SIZE
 #define PMD_TABLE_SIZE	(sizeof(pmd_t) << PMD_INDEX_SIZE)
 #define PGD_TABLE_SIZE	(sizeof(pgd_t) << PGD_INDEX_SIZE)
 #endif	/* __ASSEMBLY__ */
@@ -32,13 +43,15 @@
 #define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
 #define PGDIR_MASK	(~(PGDIR_SIZE-1))
 
-/* Bits to mask out from a PMD to get to the PTE page */
-/* PMDs point to PTE table fragments which are 4K aligned.  */
-#define PMD_MASKED_BITS		0xfff
+/*
+ * Bits to mask out from a PMD to get to the PTE page
+ * PMDs point to PTE table fragments which are PTE_FRAG_SIZE aligned.
+ */
+#define PMD_MASKED_BITS		(PTE_FRAG_SIZE - 1)
 /* 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 */
+#endif /* _ASM_POWERPC_NOHASH_64_PGTABLE_64K_H */

arch/powerpc/include/asm/pgtable-ppc64.h → arch/powerpc/include/asm/nohash/64/pgtable.h

@@ -1,14 +1,14 @@
-#ifndef _ASM_POWERPC_PGTABLE_PPC64_H_
-#define _ASM_POWERPC_PGTABLE_PPC64_H_
+#ifndef _ASM_POWERPC_NOHASH_64_PGTABLE_H
+#define _ASM_POWERPC_NOHASH_64_PGTABLE_H
 /*
  * This file contains the functions and defines necessary to modify and use
  * the ppc64 hashed page table.
  */
 
 #ifdef CONFIG_PPC_64K_PAGES
-#include <asm/pgtable-ppc64-64k.h>
+#include <asm/nohash/64/pgtable-64k.h>
 #else
-#include <asm/pgtable-ppc64-4k.h>
+#include <asm/nohash/64/pgtable-4k.h>
 #endif
 #include <asm/barrier.h>
 
@@ -18,7 +18,7 @@
  * Size of EA range mapped by our pagetables.
  */
 #define PGTABLE_EADDR_SIZE (PTE_INDEX_SIZE + PMD_INDEX_SIZE + \
-                	    PUD_INDEX_SIZE + PGD_INDEX_SIZE + PAGE_SHIFT)
+			    PUD_INDEX_SIZE + PGD_INDEX_SIZE + PAGE_SHIFT)
 #define PGTABLE_RANGE (ASM_CONST(1) << PGTABLE_EADDR_SIZE)
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -97,11 +97,7 @@
 /*
  * Include the PTE bits definitions
  */
-#ifdef CONFIG_PPC_BOOK3S
-#include <asm/pte-hash64.h>
-#else
-#include <asm/pte-book3e.h>
-#endif
+#include <asm/nohash/pte-book3e.h>
 #include <asm/pte-common.h>
 
 #ifdef CONFIG_PPC_MM_SLICES
@@ -110,59 +106,47 @@
 #endif /* CONFIG_PPC_MM_SLICES */
 
 #ifndef __ASSEMBLY__
-
-/*
- * This is the default implementation of various PTE accessors, it's
- * used in all cases except Book3S with 64K pages where we have a
- * concept of sub-pages
- */
-#ifndef __real_pte
-
-#ifdef CONFIG_STRICT_MM_TYPECHECKS
-#define __real_pte(e,p)		((real_pte_t){(e)})
-#define __rpte_to_pte(r)	((r).pte)
-#else
-#define __real_pte(e,p)		(e)
-#define __rpte_to_pte(r)	(__pte(r))
-#endif
-#define __rpte_to_hidx(r,index)	(pte_val(__rpte_to_pte(r)) >> 12)
-
-#define pte_iterate_hashed_subpages(rpte, psize, va, index, shift)       \
-	do {							         \
-		index = 0;					         \
-		shift = mmu_psize_defs[psize].shift;		         \
-
-#define pte_iterate_hashed_end() } while(0)
-
-/*
- * We expect this to be called only for user addresses or kernel virtual
- * addresses other than the linear mapping.
- */
-#define pte_pagesize_index(mm, addr, pte)	MMU_PAGE_4K
-
-#endif /* __real_pte */
-
-
 /* pte_clear moved to later in this file */
 
 #define PMD_BAD_BITS		(PTE_TABLE_SIZE-1)
 #define PUD_BAD_BITS		(PMD_TABLE_SIZE-1)
 
-#define pmd_set(pmdp, pmdval) 	(pmd_val(*(pmdp)) = (pmdval))
+static inline void pmd_set(pmd_t *pmdp, unsigned long val)
+{
+	*pmdp = __pmd(val);
+}
+
+static inline void pmd_clear(pmd_t *pmdp)
+{
+	*pmdp = __pmd(0);
+}
+
+static inline pte_t pmd_pte(pmd_t pmd)
+{
+	return __pte(pmd_val(pmd));
+}
+
 #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_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_set(pudp, pudval)	(pud_val(*(pudp)) = (pudval))
+static inline void pud_set(pud_t *pudp, unsigned long val)
+{
+	*pudp = __pud(val);
+}
+
+static inline void pud_clear(pud_t *pudp)
+{
+	*pudp = __pud(0);
+}
+
 #define pud_none(pud)		(!pud_val(pud))
 #define	pud_bad(pud)		(!is_kernel_addr(pud_val(pud)) \
 				 || (pud_val(pud) & PUD_BAD_BITS))
 #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)
 
 extern struct page *pud_page(pud_t pud);
@@ -177,9 +161,13 @@ 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))
 
+static inline void pgd_set(pgd_t *pgdp, unsigned long val)
+{
+	*pgdp = __pgd(val);
+}
+
 /*
  * Find an entry in a page-table-directory.  We combine the address region
  * (the high order N bits) and the pgd portion of the address.
@@ -373,254 +361,4 @@ void pgtable_cache_add(unsigned shift, void (*ctor)(void *));
 void pgtable_cache_init(void);
 #endif /* __ASSEMBLY__ */
 
-/*
- * THP pages can't be special. So use the _PAGE_SPECIAL
- */
-#define _PAGE_SPLITTING _PAGE_SPECIAL
-
-/*
- * We need to differentiate between explicit huge page and THP huge
- * page, since THP huge page also need to track real subpage details
- */
-#define _PAGE_THP_HUGE  _PAGE_4K_PFN
-
-/*
- * set of bits not changed in pmd_modify.
- */
-#define _HPAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS |		\
-			 _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_SPLITTING | \
-			 _PAGE_THP_HUGE)
-
-#ifndef __ASSEMBLY__
-/*
- * The linux hugepage PMD now include the pmd entries followed by the address
- * to the stashed pgtable_t. The stashed pgtable_t contains the hpte bits.
- * [ 1 bit secondary | 3 bit hidx | 1 bit valid | 000]. We use one byte per
- * each HPTE entry. With 16MB hugepage and 64K HPTE we need 256 entries and
- * with 4K HPTE we need 4096 entries. Both will fit in a 4K pgtable_t.
- *
- * The last three bits are intentionally left to zero. This memory location
- * are also used as normal page PTE pointers. So if we have any pointers
- * left around while we collapse a hugepage, we need to make sure
- * _PAGE_PRESENT bit of that is zero when we look at them
- */
-static inline unsigned int hpte_valid(unsigned char *hpte_slot_array, int index)
-{
-	return (hpte_slot_array[index] >> 3) & 0x1;
-}
-
-static inline unsigned int hpte_hash_index(unsigned char *hpte_slot_array,
-					   int index)
-{
-	return hpte_slot_array[index] >> 4;
-}
-
-static inline void mark_hpte_slot_valid(unsigned char *hpte_slot_array,
-					unsigned int index, unsigned int hidx)
-{
-	hpte_slot_array[index] = hidx << 4 | 0x1 << 3;
-}
-
-struct page *realmode_pfn_to_page(unsigned long pfn);
-
-static inline char *get_hpte_slot_array(pmd_t *pmdp)
-{
-	/*
-	 * The hpte hindex is stored in the pgtable whose address is in the
-	 * second half of the PMD
-	 *
-	 * Order this load with the test for pmd_trans_huge in the caller
-	 */
-	smp_rmb();
-	return *(char **)(pmdp + PTRS_PER_PMD);
-
-
-}
-
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-extern void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
-				   pmd_t *pmdp, unsigned long old_pmd);
-extern pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot);
-extern pmd_t mk_pmd(struct page *page, pgprot_t pgprot);
-extern pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot);
-extern void set_pmd_at(struct mm_struct *mm, unsigned long addr,
-		       pmd_t *pmdp, pmd_t pmd);
-extern void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
-				 pmd_t *pmd);
-/*
- *
- * 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_trans_splitting(pmd_t pmd)
-{
-	if (pmd_trans_huge(pmd))
-		return pmd_val(pmd) & _PAGE_SPLITTING;
-	return 0;
-}
-
-extern int has_transparent_hugepage(void);
-#else
-static inline void hpte_do_hugepage_flush(struct mm_struct *mm,
-					  unsigned long addr, pmd_t *pmdp,
-					  unsigned long old_pmd)
-{
-
-	WARN(1, "%s called with THP disabled\n", __func__);
-}
-#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 __pte(pmd_val(pmd));
-}
-
-static inline pmd_t pte_pmd(pte_t pte)
-{
-	return __pmd(pte_val(pte));
-}
-
-static inline pte_t *pmdp_ptep(pmd_t *pmd)
-{
-	return (pte_t *)pmd;
-}
-
-#define pmd_pfn(pmd)		pte_pfn(pmd_pte(pmd))
-#define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
-#define pmd_young(pmd)		pte_young(pmd_pte(pmd))
-#define pmd_mkold(pmd)		pte_pmd(pte_mkold(pmd_pte(pmd)))
-#define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
-#define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
-#define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
-#define pmd_mkwrite(pmd)	pte_pmd(pte_mkwrite(pmd_pte(pmd)))
-
-#define __HAVE_ARCH_PMD_WRITE
-#define pmd_write(pmd)		pte_write(pmd_pte(pmd))
-
-static inline pmd_t pmd_mkhuge(pmd_t pmd)
-{
-	/* Do nothing, mk_pmd() does this part.  */
-	return pmd;
-}
-
-static inline pmd_t pmd_mknotpresent(pmd_t pmd)
-{
-	pmd_val(pmd) &= ~_PAGE_PRESENT;
-	return pmd;
-}
-
-static inline pmd_t pmd_mksplitting(pmd_t pmd)
-{
-	pmd_val(pmd) |= _PAGE_SPLITTING;
-	return pmd;
-}
-
-#define __HAVE_ARCH_PMD_SAME
-static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
-{
-	return (((pmd_val(pmd_a) ^ pmd_val(pmd_b)) & ~_PAGE_HPTEFLAGS) == 0);
-}
-
-#define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
-extern int pmdp_set_access_flags(struct vm_area_struct *vma,
-				 unsigned long address, pmd_t *pmdp,
-				 pmd_t entry, int dirty);
-
-extern unsigned long pmd_hugepage_update(struct mm_struct *mm,
-					 unsigned long addr,
-					 pmd_t *pmdp,
-					 unsigned long clr,
-					 unsigned long set);
-
-static inline int __pmdp_test_and_clear_young(struct mm_struct *mm,
-					      unsigned long addr, pmd_t *pmdp)
-{
-	unsigned long old;
-
-	if ((pmd_val(*pmdp) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0)
-		return 0;
-	old = pmd_hugepage_update(mm, addr, pmdp, _PAGE_ACCESSED, 0);
-	return ((old & _PAGE_ACCESSED) != 0);
-}
-
-#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
-extern int pmdp_test_and_clear_young(struct vm_area_struct *vma,
-				     unsigned long address, pmd_t *pmdp);
-#define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
-extern int pmdp_clear_flush_young(struct vm_area_struct *vma,
-				  unsigned long address, pmd_t *pmdp);
-
-#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
-extern pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
-				     unsigned long addr, pmd_t *pmdp);
-
-#define __HAVE_ARCH_PMDP_SET_WRPROTECT
-static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr,
-				      pmd_t *pmdp)
-{
-
-	if ((pmd_val(*pmdp) & _PAGE_RW) == 0)
-		return;
-
-	pmd_hugepage_update(mm, addr, pmdp, _PAGE_RW, 0);
-}
-
-#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH
-extern void pmdp_splitting_flush(struct vm_area_struct *vma,
-				 unsigned long address, pmd_t *pmdp);
-
-extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
-				 unsigned long address, pmd_t *pmdp);
-#define pmdp_collapse_flush pmdp_collapse_flush
-
-#define __HAVE_ARCH_PGTABLE_DEPOSIT
-extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
-				       pgtable_t pgtable);
-#define __HAVE_ARCH_PGTABLE_WITHDRAW
-extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
-
-#define __HAVE_ARCH_PMDP_INVALIDATE
-extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
-			    pmd_t *pmdp);
-
-#define pmd_move_must_withdraw pmd_move_must_withdraw
-struct spinlock;
-static inline int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl,
-					 struct spinlock *old_pmd_ptl)
-{
-	/*
-	 * Archs like ppc64 use pgtable to store per pmd
-	 * specific information. So when we switch the pmd,
-	 * we should also withdraw and deposit the pgtable
-	 */
-	return true;
-}
-#endif /* __ASSEMBLY__ */
-#endif /* _ASM_POWERPC_PGTABLE_PPC64_H_ */
+#endif /* _ASM_POWERPC_NOHASH_64_PGTABLE_H */

arch/powerpc/include/asm/nohash/pgtable.h

@@ -0,0 +1,252 @@
+#ifndef _ASM_POWERPC_NOHASH_PGTABLE_H
+#define _ASM_POWERPC_NOHASH_PGTABLE_H
+
+#if defined(CONFIG_PPC64)
+#include <asm/nohash/64/pgtable.h>
+#else
+#include <asm/nohash/32/pgtable.h>
+#endif
+
+#ifndef __ASSEMBLY__
+
+/* Generic accessors to PTE bits */
+static inline int pte_write(pte_t pte)
+{
+	return (pte_val(pte) & (_PAGE_RW | _PAGE_RO)) != _PAGE_RO;
+}
+static inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & _PAGE_DIRTY; }
+static inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED; }
+static inline int pte_special(pte_t pte)	{ return pte_val(pte) & _PAGE_SPECIAL; }
+static inline int pte_none(pte_t pte)		{ return (pte_val(pte) & ~_PTE_NONE_MASK) == 0; }
+static inline pgprot_t pte_pgprot(pte_t pte)	{ return __pgprot(pte_val(pte) & PAGE_PROT_BITS); }
+
+#ifdef CONFIG_NUMA_BALANCING
+/*
+ * These work without NUMA balancing but the kernel does not care. See the
+ * comment in include/asm-generic/pgtable.h . On powerpc, this will only
+ * work for user pages and always return true for kernel pages.
+ */
+static inline int pte_protnone(pte_t pte)
+{
+	return (pte_val(pte) &
+		(_PAGE_PRESENT | _PAGE_USER)) == _PAGE_PRESENT;
+}
+
+static inline int pmd_protnone(pmd_t pmd)
+{
+	return pte_protnone(pmd_pte(pmd));
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
+static inline int pte_present(pte_t pte)
+{
+	return pte_val(pte) & _PAGE_PRESENT;
+}
+
+/* Conversion functions: convert a page and protection to a page entry,
+ * and a page entry and page directory to the page they refer to.
+ *
+ * Even if PTEs can be unsigned long long, a PFN is always an unsigned
+ * long for now.
+ */
+static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot) {
+	return __pte(((pte_basic_t)(pfn) << PTE_RPN_SHIFT) |
+		     pgprot_val(pgprot)); }
+static inline unsigned long pte_pfn(pte_t pte)	{
+	return pte_val(pte) >> PTE_RPN_SHIFT; }
+
+/* Generic modifiers for PTE bits */
+static inline pte_t pte_wrprotect(pte_t pte)
+{
+	pte_basic_t ptev;
+
+	ptev = pte_val(pte) & ~(_PAGE_RW | _PAGE_HWWRITE);
+	ptev |= _PAGE_RO;
+	return __pte(ptev);
+}
+
+static inline pte_t pte_mkclean(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~(_PAGE_DIRTY | _PAGE_HWWRITE));
+}
+
+static inline pte_t pte_mkold(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_ACCESSED);
+}
+
+static inline pte_t pte_mkwrite(pte_t pte)
+{
+	pte_basic_t ptev;
+
+	ptev = pte_val(pte) & ~_PAGE_RO;
+	ptev |= _PAGE_RW;
+	return __pte(ptev);
+}
+
+static inline pte_t pte_mkdirty(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_DIRTY);
+}
+
+static inline pte_t pte_mkyoung(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_ACCESSED);
+}
+
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_SPECIAL);
+}
+
+static inline pte_t pte_mkhuge(pte_t pte)
+{
+	return pte;
+}
+
+static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+{
+	return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot));
+}
+
+/* Insert a PTE, top-level function is out of line. It uses an inline
+ * low level function in the respective pgtable-* files
+ */
+extern void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+		       pte_t pte);
+
+/* This low level function performs the actual PTE insertion
+ * Setting the PTE depends on the MMU type and other factors. It's
+ * an horrible mess that I'm not going to try to clean up now but
+ * I'm keeping it in one place rather than spread around
+ */
+static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
+				pte_t *ptep, pte_t pte, int percpu)
+{
+#if defined(CONFIG_PPC_STD_MMU_32) && defined(CONFIG_SMP) && !defined(CONFIG_PTE_64BIT)
+	/* First case is 32-bit Hash MMU in SMP mode with 32-bit PTEs. We use the
+	 * helper pte_update() which does an atomic update. We need to do that
+	 * because a concurrent invalidation can clear _PAGE_HASHPTE. If it's a
+	 * per-CPU PTE such as a kmap_atomic, we do a simple update preserving
+	 * the hash bits instead (ie, same as the non-SMP case)
+	 */
+	if (percpu)
+		*ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE)
+			      | (pte_val(pte) & ~_PAGE_HASHPTE));
+	else
+		pte_update(ptep, ~_PAGE_HASHPTE, pte_val(pte));
+
+#elif defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT)
+	/* Second case is 32-bit with 64-bit PTE.  In this case, we
+	 * can just store as long as we do the two halves in the right order
+	 * with a barrier in between. This is possible because we take care,
+	 * in the hash code, to pre-invalidate if the PTE was already hashed,
+	 * which synchronizes us with any concurrent invalidation.
+	 * In the percpu case, we also fallback to the simple update preserving
+	 * the hash bits
+	 */
+	if (percpu) {
+		*ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE)
+			      | (pte_val(pte) & ~_PAGE_HASHPTE));
+		return;
+	}
+#if _PAGE_HASHPTE != 0
+	if (pte_val(*ptep) & _PAGE_HASHPTE)
+		flush_hash_entry(mm, ptep, addr);
+#endif
+	__asm__ __volatile__("\
+		stw%U0%X0 %2,%0\n\
+		eieio\n\
+		stw%U0%X0 %L2,%1"
+	: "=m" (*ptep), "=m" (*((unsigned char *)ptep+4))
+	: "r" (pte) : "memory");
+
+#elif defined(CONFIG_PPC_STD_MMU_32)
+	/* Third case is 32-bit hash table in UP mode, we need to preserve
+	 * the _PAGE_HASHPTE bit since we may not have invalidated the previous
+	 * translation in the hash yet (done in a subsequent flush_tlb_xxx())
+	 * and see we need to keep track that this PTE needs invalidating
+	 */
+	*ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE)
+		      | (pte_val(pte) & ~_PAGE_HASHPTE));
+
+#else
+	/* Anything else just stores the PTE normally. That covers all 64-bit
+	 * cases, and 32-bit non-hash with 32-bit PTEs.
+	 */
+	*ptep = pte;
+
+#ifdef CONFIG_PPC_BOOK3E_64
+	/*
+	 * With hardware tablewalk, a sync is needed to ensure that
+	 * subsequent accesses see the PTE we just wrote.  Unlike userspace
+	 * mappings, we can't tolerate spurious faults, so make sure
+	 * the new PTE will be seen the first time.
+	 */
+	if (is_kernel_addr(addr))
+		mb();
+#endif
+#endif
+}
+
+
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address,
+				 pte_t *ptep, pte_t entry, int dirty);
+
+/*
+ * Macro to mark a page protection value as "uncacheable".
+ */
+
+#define _PAGE_CACHE_CTL	(_PAGE_COHERENT | _PAGE_GUARDED | _PAGE_NO_CACHE | \
+			 _PAGE_WRITETHRU)
+
+#define pgprot_noncached(prot)	  (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \
+				            _PAGE_NO_CACHE | _PAGE_GUARDED))
+
+#define pgprot_noncached_wc(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \
+				            _PAGE_NO_CACHE))
+
+#define pgprot_cached(prot)       (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \
+				            _PAGE_COHERENT))
+
+#define pgprot_cached_wthru(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \
+				            _PAGE_COHERENT | _PAGE_WRITETHRU))
+
+#define pgprot_cached_noncoherent(prot) \
+		(__pgprot(pgprot_val(prot) & ~_PAGE_CACHE_CTL))
+
+#define pgprot_writecombine pgprot_noncached_wc
+
+struct file;
+extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+				     unsigned long size, pgprot_t vma_prot);
+#define __HAVE_PHYS_MEM_ACCESS_PROT
+
+#ifdef CONFIG_HUGETLB_PAGE
+static inline int hugepd_ok(hugepd_t hpd)
+{
+	return (hpd.pd > 0);
+}
+
+static inline int pmd_huge(pmd_t pmd)
+{
+	return 0;
+}
+
+static inline int pud_huge(pud_t pud)
+{
+	return 0;
+}
+
+static inline int pgd_huge(pgd_t pgd)
+{
+	return 0;
+}
+#define pgd_huge		pgd_huge
+
+#define is_hugepd(hpd)		(hugepd_ok(hpd))
+#endif
+
+#endif /* __ASSEMBLY__ */
+#endif

arch/powerpc/include/asm/pte-book3e.h → arch/powerpc/include/asm/nohash/pte-book3e.h

@@ -1,5 +1,5 @@
-#ifndef _ASM_POWERPC_PTE_BOOK3E_H
-#define _ASM_POWERPC_PTE_BOOK3E_H
+#ifndef _ASM_POWERPC_NOHASH_PTE_BOOK3E_H
+#define _ASM_POWERPC_NOHASH_PTE_BOOK3E_H
 #ifdef __KERNEL__
 
 /* PTE bit definitions for processors compliant to the Book3E
@@ -84,4 +84,4 @@
 #endif
 
 #endif /* __KERNEL__ */
-#endif /*  _ASM_POWERPC_PTE_FSL_BOOKE_H */
+#endif /*  _ASM_POWERPC_NOHASH_PTE_BOOK3E_H */

arch/powerpc/include/asm/opal-api.h

@@ -157,7 +157,8 @@
 #define OPAL_LEDS_GET_INDICATOR			114
 #define OPAL_LEDS_SET_INDICATOR			115
 #define OPAL_CEC_REBOOT2			116
-#define OPAL_LAST				116
+#define OPAL_CONSOLE_FLUSH			117
+#define OPAL_LAST				117
 
 /* Device tree flags */
 

arch/powerpc/include/asm/opal.h

@@ -35,6 +35,7 @@ int64_t opal_console_read(int64_t term_number, __be64 *length,
 			  uint8_t *buffer);
 int64_t opal_console_write_buffer_space(int64_t term_number,
 					__be64 *length);
+int64_t opal_console_flush(int64_t term_number);
 int64_t opal_rtc_read(__be32 *year_month_day,
 		      __be64 *hour_minute_second_millisecond);
 int64_t opal_rtc_write(uint32_t year_month_day,
@@ -262,6 +263,8 @@ extern int opal_resync_timebase(void);
 
 extern void opal_lpc_init(void);
 
+extern void opal_kmsg_init(void);
+
 extern int opal_event_request(unsigned int opal_event_nr);
 
 struct opal_sg_list *opal_vmalloc_to_sg_list(void *vmalloc_addr,

arch/powerpc/include/asm/paca.h

@@ -16,6 +16,7 @@
 
 #ifdef CONFIG_PPC64
 
+#include <linux/string.h>
 #include <asm/types.h>
 #include <asm/lppaca.h>
 #include <asm/mmu.h>
@@ -131,7 +132,16 @@ struct paca_struct {
 	struct tlb_core_data tcd;
 #endif /* CONFIG_PPC_BOOK3E */
 
-	mm_context_t context;
+#ifdef CONFIG_PPC_BOOK3S
+	mm_context_id_t mm_ctx_id;
+#ifdef CONFIG_PPC_MM_SLICES
+	u64 mm_ctx_low_slices_psize;
+	unsigned char mm_ctx_high_slices_psize[SLICE_ARRAY_SIZE];
+#else
+	u16 mm_ctx_user_psize;
+	u16 mm_ctx_sllp;
+#endif
+#endif
 
 	/*
 	 * then miscellaneous read-write fields
@@ -194,6 +204,23 @@ struct paca_struct {
 #endif
 };
 
+#ifdef CONFIG_PPC_BOOK3S
+static inline void copy_mm_to_paca(mm_context_t *context)
+{
+	get_paca()->mm_ctx_id = context->id;
+#ifdef CONFIG_PPC_MM_SLICES
+	get_paca()->mm_ctx_low_slices_psize = context->low_slices_psize;
+	memcpy(&get_paca()->mm_ctx_high_slices_psize,
+	       &context->high_slices_psize, SLICE_ARRAY_SIZE);
+#else
+	get_paca()->mm_ctx_user_psize = context->user_psize;
+	get_paca()->mm_ctx_sllp = context->sllp;
+#endif
+}
+#else
+static inline void copy_mm_to_paca(mm_context_t *context){}
+#endif
+
 extern struct paca_struct *paca;
 extern void initialise_paca(struct paca_struct *new_paca, int cpu);
 extern void setup_paca(struct paca_struct *new_paca);

arch/powerpc/include/asm/page.h

@@ -286,8 +286,11 @@ extern long long virt_phys_offset;
 
 /* PTE level */
 typedef struct { pte_basic_t pte; } pte_t;
-#define pte_val(x)	((x).pte)
 #define __pte(x)	((pte_t) { (x) })
+static inline pte_basic_t pte_val(pte_t x)
+{
+	return x.pte;
+}
 
 /* 64k pages additionally define a bigger "real PTE" type that gathers
  * the "second half" part of the PTE for pseudo 64k pages
@@ -301,21 +304,30 @@ typedef struct { pte_t pte; } real_pte_t;
 /* PMD level */
 #ifdef CONFIG_PPC64
 typedef struct { unsigned long pmd; } pmd_t;
-#define pmd_val(x)	((x).pmd)
 #define __pmd(x)	((pmd_t) { (x) })
+static inline unsigned long pmd_val(pmd_t x)
+{
+	return x.pmd;
+}
 
 /* PUD level exusts only on 4k pages */
 #ifndef CONFIG_PPC_64K_PAGES
 typedef struct { unsigned long pud; } pud_t;
-#define pud_val(x)	((x).pud)
 #define __pud(x)	((pud_t) { (x) })
+static inline unsigned long pud_val(pud_t x)
+{
+	return x.pud;
+}
 #endif /* !CONFIG_PPC_64K_PAGES */
 #endif /* CONFIG_PPC64 */
 
 /* PGD level */
 typedef struct { unsigned long pgd; } pgd_t;
-#define pgd_val(x)	((x).pgd)
 #define __pgd(x)	((pgd_t) { (x) })
+static inline unsigned long pgd_val(pgd_t x)
+{
+	return x.pgd;
+}
 
 /* Page protection bits */
 typedef struct { unsigned long pgprot; } pgprot_t;
@@ -329,8 +341,11 @@ typedef struct { unsigned long pgprot; } pgprot_t;
  */
 
 typedef pte_basic_t pte_t;
-#define pte_val(x)	(x)
 #define __pte(x)	(x)
+static inline pte_basic_t pte_val(pte_t pte)
+{
+	return pte;
+}
 
 #if defined(CONFIG_PPC_64K_PAGES) && defined(CONFIG_PPC_STD_MMU_64)
 typedef struct { pte_t pte; unsigned long hidx; } real_pte_t;
@@ -341,67 +356,42 @@ typedef pte_t real_pte_t;
 
 #ifdef CONFIG_PPC64
 typedef unsigned long pmd_t;
-#define pmd_val(x)	(x)
 #define __pmd(x)	(x)
+static inline unsigned long pmd_val(pmd_t pmd)
+{
+	return pmd;
+}
 
 #ifndef CONFIG_PPC_64K_PAGES
 typedef unsigned long pud_t;
-#define pud_val(x)	(x)
 #define __pud(x)	(x)
+static inline unsigned long pud_val(pud_t pud)
+{
+	return pud;
+}
 #endif /* !CONFIG_PPC_64K_PAGES */
 #endif /* CONFIG_PPC64 */
 
 typedef unsigned long pgd_t;
-#define pgd_val(x)	(x)
-#define pgprot_val(x)	(x)
+#define __pgd(x)	(x)
+static inline unsigned long pgd_val(pgd_t pgd)
+{
+	return pgd;
+}
 
 typedef unsigned long pgprot_t;
-#define __pgd(x)	(x)
+#define pgprot_val(x)	(x)
 #define __pgprot(x)	(x)
 
 #endif
 
 typedef struct { signed long pd; } hugepd_t;
 
-#ifdef CONFIG_HUGETLB_PAGE
-#ifdef CONFIG_PPC_BOOK3S_64
-#ifdef CONFIG_PPC_64K_PAGES
-/*
- * With 64k page size, we have hugepage ptes in the pgd and pmd entries. We don't
- * need to setup hugepage directory for them. Our pte and page directory format
- * enable us to have this enabled. But to avoid errors when implementing new
- * features disable hugepd for 64K. We enable a debug version here, So we catch
- * wrong usage.
- */
-#ifdef CONFIG_DEBUG_VM
-extern int hugepd_ok(hugepd_t hpd);
-#else
-#define hugepd_ok(x)	(0)
-#endif
-#else
-static inline int hugepd_ok(hugepd_t hpd)
-{
-	/*
-	 * hugepd pointer, bottom two bits == 00 and next 4 bits
-	 * indicate size of table
-	 */
-	return (((hpd.pd & 0x3) == 0x0) && ((hpd.pd & HUGEPD_SHIFT_MASK) != 0));
-}
-#endif
-#else
-static inline int hugepd_ok(hugepd_t hpd)
-{
-	return (hpd.pd > 0);
-}
-#endif
-
-#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
+#ifndef 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;

arch/powerpc/include/asm/pci-bridge.h

@@ -205,6 +205,7 @@ struct pci_dn {
 
 	int	pci_ext_config_space;	/* for pci devices */
 
+	struct	pci_dev *pcidev;	/* back-pointer to the pci device */
 #ifdef CONFIG_EEH
 	struct eeh_dev *edev;		/* eeh device */
 #endif

arch/powerpc/include/asm/pci.h

@@ -149,4 +149,8 @@ extern void pcibios_setup_phb_io_space(struct pci_controller *hose);
 extern void pcibios_scan_phb(struct pci_controller *hose);
 
 #endif	/* __KERNEL__ */
+
+extern struct pci_dev *pnv_pci_get_gpu_dev(struct pci_dev *npdev);
+extern struct pci_dev *pnv_pci_get_npu_dev(struct pci_dev *gpdev, int index);
+
 #endif /* __ASM_POWERPC_PCI_H */

arch/powerpc/include/asm/pgalloc-32.h

@@ -21,16 +21,34 @@ extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
 /* #define pgd_populate(mm, pmd, pte)      BUG() */
 
 #ifndef CONFIG_BOOKE
-#define pmd_populate_kernel(mm, pmd, pte)	\
-		(pmd_val(*(pmd)) = __pa(pte) | _PMD_PRESENT)
-#define pmd_populate(mm, pmd, pte)	\
-		(pmd_val(*(pmd)) = (page_to_pfn(pte) << PAGE_SHIFT) | _PMD_PRESENT)
+
+static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp,
+				       pte_t *pte)
+{
+	*pmdp = __pmd(__pa(pte) | _PMD_PRESENT);
+}
+
+static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp,
+				pgtable_t pte_page)
+{
+	*pmdp = __pmd((page_to_pfn(pte_page) << PAGE_SHIFT) | _PMD_PRESENT);
+}
+
 #define pmd_pgtable(pmd) pmd_page(pmd)
 #else
-#define pmd_populate_kernel(mm, pmd, pte)	\
-		(pmd_val(*(pmd)) = (unsigned long)pte | _PMD_PRESENT)
-#define pmd_populate(mm, pmd, pte)	\
-		(pmd_val(*(pmd)) = (unsigned long)lowmem_page_address(pte) | _PMD_PRESENT)
+
+static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp,
+				       pte_t *pte)
+{
+	*pmdp = __pmd((unsigned long)pte | _PMD_PRESENT);
+}
+
+static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp,
+				pgtable_t pte_page)
+{
+	*pmdp = __pmd((unsigned long)lowmem_page_address(pte_page) | _PMD_PRESENT);
+}
+
 #define pmd_pgtable(pmd) pmd_page(pmd)
 #endif
 

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

@@ -53,7 +53,7 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 
 #ifndef CONFIG_PPC_64K_PAGES
 
-#define pgd_populate(MM, PGD, PUD)	pgd_set(PGD, PUD)
+#define pgd_populate(MM, PGD, PUD)	pgd_set(PGD, (unsigned long)PUD)
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
@@ -71,9 +71,18 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 	pud_set(pud, (unsigned long)pmd);
 }
 
-#define pmd_populate(mm, pmd, pte_page) \
-	pmd_populate_kernel(mm, pmd, page_address(pte_page))
-#define pmd_populate_kernel(mm, pmd, pte) pmd_set(pmd, (unsigned long)(pte))
+static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
+				       pte_t *pte)
+{
+	pmd_set(pmd, (unsigned long)pte);
+}
+
+static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
+				pgtable_t pte_page)
+{
+	pmd_set(pmd, (unsigned long)page_address(pte_page));
+}
+
 #define pmd_pgtable(pmd) pmd_page(pmd)
 
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
@@ -154,16 +163,6 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
 }
 
 #else /* if CONFIG_PPC_64K_PAGES */
-/*
- * we support 16 fragments per PTE page.
- */
-#define PTE_FRAG_NR	16
-/*
- * We use a 2K PTE page fragment and another 2K for storing
- * real_pte_t hash index
- */
-#define PTE_FRAG_SIZE_SHIFT  12
-#define PTE_FRAG_SIZE (2 * PTRS_PER_PTE * sizeof(pte_t))
 
 extern pte_t *page_table_alloc(struct mm_struct *, unsigned long, int);
 extern void page_table_free(struct mm_struct *, unsigned long *, int);

arch/powerpc/include/asm/pgtable.h

@@ -1,6 +1,5 @@
 #ifndef _ASM_POWERPC_PGTABLE_H
 #define _ASM_POWERPC_PGTABLE_H
-#ifdef __KERNEL__
 
 #ifndef __ASSEMBLY__
 #include <linux/mmdebug.h>
@@ -13,210 +12,20 @@ struct mm_struct;
 
 #endif /* !__ASSEMBLY__ */
 
-#if defined(CONFIG_PPC64)
-#  include <asm/pgtable-ppc64.h>
+#ifdef CONFIG_PPC_BOOK3S
+#include <asm/book3s/pgtable.h>
 #else
-#  include <asm/pgtable-ppc32.h>
-#endif
-
-/*
- * We save the slot number & secondary bit in the second half of the
- * PTE page. We use the 8 bytes per each pte entry.
- */
-#define PTE_PAGE_HIDX_OFFSET (PTRS_PER_PTE * 8)
+#include <asm/nohash/pgtable.h>
+#endif /* !CONFIG_PPC_BOOK3S */
 
 #ifndef __ASSEMBLY__
 
 #include <asm/tlbflush.h>
 
-/* Generic accessors to PTE bits */
-static inline int pte_write(pte_t pte)
-{	return (pte_val(pte) & (_PAGE_RW | _PAGE_RO)) != _PAGE_RO; }
-static inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & _PAGE_DIRTY; }
-static inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED; }
-static inline int pte_special(pte_t pte)	{ return pte_val(pte) & _PAGE_SPECIAL; }
-static inline int pte_none(pte_t pte)		{ return (pte_val(pte) & ~_PTE_NONE_MASK) == 0; }
-static inline pgprot_t pte_pgprot(pte_t pte)	{ return __pgprot(pte_val(pte) & PAGE_PROT_BITS); }
-
-#ifdef CONFIG_NUMA_BALANCING
-/*
- * These work without NUMA balancing but the kernel does not care. See the
- * comment in include/asm-generic/pgtable.h . On powerpc, this will only
- * work for user pages and always return true for kernel pages.
- */
-static inline int pte_protnone(pte_t pte)
-{
-	return (pte_val(pte) &
-		(_PAGE_PRESENT | _PAGE_USER)) == _PAGE_PRESENT;
-}
-
-static inline int pmd_protnone(pmd_t pmd)
-{
-	return pte_protnone(pmd_pte(pmd));
-}
-#endif /* CONFIG_NUMA_BALANCING */
-
-static inline int pte_present(pte_t pte)
-{
-	return pte_val(pte) & _PAGE_PRESENT;
-}
-
-/* Conversion functions: convert a page and protection to a page entry,
- * and a page entry and page directory to the page they refer to.
- *
- * Even if PTEs can be unsigned long long, a PFN is always an unsigned
- * long for now.
- */
-static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot) {
-	return __pte(((pte_basic_t)(pfn) << PTE_RPN_SHIFT) |
-		     pgprot_val(pgprot)); }
-static inline unsigned long pte_pfn(pte_t pte)	{
-	return pte_val(pte) >> PTE_RPN_SHIFT; }
-
 /* Keep these as a macros to avoid include dependency mess */
 #define pte_page(x)		pfn_to_page(pte_pfn(x))
 #define mk_pte(page, pgprot)	pfn_pte(page_to_pfn(page), (pgprot))
 
-/* Generic modifiers for PTE bits */
-static inline pte_t pte_wrprotect(pte_t pte) {
-	pte_val(pte) &= ~(_PAGE_RW | _PAGE_HWWRITE);
-	pte_val(pte) |= _PAGE_RO; return pte; }
-static inline pte_t pte_mkclean(pte_t pte) {
-	pte_val(pte) &= ~(_PAGE_DIRTY | _PAGE_HWWRITE); return pte; }
-static inline pte_t pte_mkold(pte_t pte) {
-	pte_val(pte) &= ~_PAGE_ACCESSED; return pte; }
-static inline pte_t pte_mkwrite(pte_t pte) {
-	pte_val(pte) &= ~_PAGE_RO;
-	pte_val(pte) |= _PAGE_RW; return pte; }
-static inline pte_t pte_mkdirty(pte_t pte) {
-	pte_val(pte) |= _PAGE_DIRTY; return pte; }
-static inline pte_t pte_mkyoung(pte_t pte) {
-	pte_val(pte) |= _PAGE_ACCESSED; return pte; }
-static inline pte_t pte_mkspecial(pte_t pte) {
-	pte_val(pte) |= _PAGE_SPECIAL; return pte; }
-static inline pte_t pte_mkhuge(pte_t pte) {
-	return pte; }
-static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
-{
-	pte_val(pte) = (pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot);
-	return pte;
-}
-
-
-/* Insert a PTE, top-level function is out of line. It uses an inline
- * low level function in the respective pgtable-* files
- */
-extern void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
-		       pte_t pte);
-
-/* This low level function performs the actual PTE insertion
- * Setting the PTE depends on the MMU type and other factors. It's
- * an horrible mess that I'm not going to try to clean up now but
- * I'm keeping it in one place rather than spread around
- */
-static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
-				pte_t *ptep, pte_t pte, int percpu)
-{
-#if defined(CONFIG_PPC_STD_MMU_32) && defined(CONFIG_SMP) && !defined(CONFIG_PTE_64BIT)
-	/* First case is 32-bit Hash MMU in SMP mode with 32-bit PTEs. We use the
-	 * helper pte_update() which does an atomic update. We need to do that
-	 * because a concurrent invalidation can clear _PAGE_HASHPTE. If it's a
-	 * per-CPU PTE such as a kmap_atomic, we do a simple update preserving
-	 * the hash bits instead (ie, same as the non-SMP case)
-	 */
-	if (percpu)
-		*ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE)
-			      | (pte_val(pte) & ~_PAGE_HASHPTE));
-	else
-		pte_update(ptep, ~_PAGE_HASHPTE, pte_val(pte));
-
-#elif defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT)
-	/* Second case is 32-bit with 64-bit PTE.  In this case, we
-	 * can just store as long as we do the two halves in the right order
-	 * with a barrier in between. This is possible because we take care,
-	 * in the hash code, to pre-invalidate if the PTE was already hashed,
-	 * which synchronizes us with any concurrent invalidation.
-	 * In the percpu case, we also fallback to the simple update preserving
-	 * the hash bits
-	 */
-	if (percpu) {
-		*ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE)
-			      | (pte_val(pte) & ~_PAGE_HASHPTE));
-		return;
-	}
-#if _PAGE_HASHPTE != 0
-	if (pte_val(*ptep) & _PAGE_HASHPTE)
-		flush_hash_entry(mm, ptep, addr);
-#endif
-	__asm__ __volatile__("\
-		stw%U0%X0 %2,%0\n\
-		eieio\n\
-		stw%U0%X0 %L2,%1"
-	: "=m" (*ptep), "=m" (*((unsigned char *)ptep+4))
-	: "r" (pte) : "memory");
-
-#elif defined(CONFIG_PPC_STD_MMU_32)
-	/* Third case is 32-bit hash table in UP mode, we need to preserve
-	 * the _PAGE_HASHPTE bit since we may not have invalidated the previous
-	 * translation in the hash yet (done in a subsequent flush_tlb_xxx())
-	 * and see we need to keep track that this PTE needs invalidating
-	 */
-	*ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE)
-		      | (pte_val(pte) & ~_PAGE_HASHPTE));
-
-#else
-	/* Anything else just stores the PTE normally. That covers all 64-bit
-	 * cases, and 32-bit non-hash with 32-bit PTEs.
-	 */
-	*ptep = pte;
-
-#ifdef CONFIG_PPC_BOOK3E_64
-	/*
-	 * With hardware tablewalk, a sync is needed to ensure that
-	 * subsequent accesses see the PTE we just wrote.  Unlike userspace
-	 * mappings, we can't tolerate spurious faults, so make sure
-	 * the new PTE will be seen the first time.
-	 */
-	if (is_kernel_addr(addr))
-		mb();
-#endif
-#endif
-}
-
-
-#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
-extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address,
-				 pte_t *ptep, pte_t entry, int dirty);
-
-/*
- * Macro to mark a page protection value as "uncacheable".
- */
-
-#define _PAGE_CACHE_CTL	(_PAGE_COHERENT | _PAGE_GUARDED | _PAGE_NO_CACHE | \
-			 _PAGE_WRITETHRU)
-
-#define pgprot_noncached(prot)	  (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \
-				            _PAGE_NO_CACHE | _PAGE_GUARDED))
-
-#define pgprot_noncached_wc(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \
-				            _PAGE_NO_CACHE))
-
-#define pgprot_cached(prot)       (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \
-				            _PAGE_COHERENT))
-
-#define pgprot_cached_wthru(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \
-				            _PAGE_COHERENT | _PAGE_WRITETHRU))
-
-#define pgprot_cached_noncoherent(prot) \
-		(__pgprot(pgprot_val(prot) & ~_PAGE_CACHE_CTL))
-
-#define pgprot_writecombine pgprot_noncached_wc
-
-struct file;
-extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
-				     unsigned long size, pgprot_t vma_prot);
-#define __HAVE_PHYS_MEM_ACCESS_PROT
-
 /*
  * ZERO_PAGE is a global shared page that is always zero: used
  * for zero-mapped memory areas etc..
@@ -271,5 +80,4 @@ static inline pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
 }
 #endif /* __ASSEMBLY__ */
 
-#endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_PGTABLE_H */

arch/powerpc/include/asm/plpar_wrappers.h

@@ -201,6 +201,23 @@ static inline long plpar_pte_read_raw(unsigned long flags, unsigned long ptex,
 	return rc;
 }
 
+/*
+ * ptes must be 8*sizeof(unsigned long)
+ */
+static inline long plpar_pte_read_4(unsigned long flags, unsigned long ptex,
+				    unsigned long *ptes)
+
+{
+	long rc;
+	unsigned long retbuf[PLPAR_HCALL9_BUFSIZE];
+
+	rc = plpar_hcall9(H_READ, retbuf, flags | H_READ_4, ptex);
+
+	memcpy(ptes, retbuf, 8*sizeof(unsigned long));
+
+	return rc;
+}
+
 /*
  * plpar_pte_read_4_raw can be called in real mode.
  * ptes must be 8*sizeof(unsigned long)

arch/powerpc/include/asm/ppc_asm.h

@@ -413,24 +413,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601)
 	FTR_SECTION_ELSE_NESTED(848);	\
 	mtocrf (FXM), RS;		\
 	ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_NOEXECUTE, 848)
-
-/*
- * PPR restore macros used in entry_64.S
- * Used for P7 or later processors
- */
-#define HMT_MEDIUM_LOW_HAS_PPR						\
-BEGIN_FTR_SECTION_NESTED(944)						\
-	HMT_MEDIUM_LOW;							\
-END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,944)
-
-#define SET_DEFAULT_THREAD_PPR(ra, rb)					\
-BEGIN_FTR_SECTION_NESTED(945)						\
-	lis	ra,INIT_PPR@highest;	/* default ppr=3 */		\
-	ld	rb,PACACURRENT(r13);					\
-	sldi	ra,ra,32;	/* 11- 13 bits are used for ppr */	\
-	std	ra,TASKTHREADPPR(rb);					\
-END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,945)
-
 #endif
 
 /*

arch/powerpc/include/asm/processor.h

@@ -88,12 +88,6 @@ struct task_struct;
 void start_thread(struct pt_regs *regs, unsigned long fdptr, unsigned long sp);
 void release_thread(struct task_struct *);
 
-/* Lazy FPU handling on uni-processor */
-extern struct task_struct *last_task_used_math;
-extern struct task_struct *last_task_used_altivec;
-extern struct task_struct *last_task_used_vsx;
-extern struct task_struct *last_task_used_spe;
-
 #ifdef CONFIG_PPC32
 
 #if CONFIG_TASK_SIZE > CONFIG_KERNEL_START
@@ -294,6 +288,7 @@ struct thread_struct {
 #endif
 #ifdef CONFIG_PPC64
 	unsigned long	dscr;
+	unsigned long	fscr;
 	/*
 	 * This member element dscr_inherit indicates that the process
 	 * has explicitly attempted and changed the DSCR register value
@@ -385,8 +380,6 @@ extern int set_endian(struct task_struct *tsk, unsigned int val);
 extern int get_unalign_ctl(struct task_struct *tsk, unsigned long adr);
 extern int set_unalign_ctl(struct task_struct *tsk, unsigned int val);
 
-extern void fp_enable(void);
-extern void vec_enable(void);
 extern void load_fp_state(struct thread_fp_state *fp);
 extern void store_fp_state(struct thread_fp_state *fp);
 extern void load_vr_state(struct thread_vr_state *vr);

arch/powerpc/include/asm/pte-common.h

@@ -40,6 +40,11 @@
 #else
 #define _PAGE_RW 0
 #endif
+
+#ifndef _PAGE_PTE
+#define _PAGE_PTE 0
+#endif
+
 #ifndef _PMD_PRESENT_MASK
 #define _PMD_PRESENT_MASK	_PMD_PRESENT
 #endif

arch/powerpc/include/asm/pte-hash64-4k.h

@@ -1,17 +0,0 @@
-/* To be include by pgtable-hash64.h only */
-
-/* PTE bits */
-#define _PAGE_HASHPTE	0x0400 /* software: pte has an associated HPTE */
-#define _PAGE_SECONDARY 0x8000 /* software: HPTE is in secondary group */
-#define _PAGE_GROUP_IX  0x7000 /* software: HPTE index within group */
-#define _PAGE_F_SECOND  _PAGE_SECONDARY
-#define _PAGE_F_GIX     _PAGE_GROUP_IX
-#define _PAGE_SPECIAL	0x10000 /* software: special page */
-
-/* PTE flags to conserve for HPTE identification */
-#define _PAGE_HPTEFLAGS (_PAGE_BUSY | _PAGE_HASHPTE | \
-			 _PAGE_SECONDARY | _PAGE_GROUP_IX)
-
-/* shift to put page number into pte */
-#define PTE_RPN_SHIFT	(17)
-

arch/powerpc/include/asm/pte-hash64-64k.h

@@ -1,102 +0,0 @@
-/* To be include by pgtable-hash64.h only */
-
-/* Additional PTE bits (don't change without checking asm in hash_low.S) */
-#define _PAGE_SPECIAL	0x00000400 /* software: special page */
-#define _PAGE_HPTE_SUB	0x0ffff000 /* combo only: sub pages HPTE bits */
-#define _PAGE_HPTE_SUB0	0x08000000 /* combo only: first sub page */
-#define _PAGE_COMBO	0x10000000 /* this is a combo 4k page */
-#define _PAGE_4K_PFN	0x20000000 /* PFN is for a single 4k page */
-
-/* For 64K page, we don't have a separate _PAGE_HASHPTE bit. Instead,
- * we set that to be the whole sub-bits mask. The C code will only
- * test this, so a multi-bit mask will work. For combo pages, this
- * is equivalent as effectively, the old _PAGE_HASHPTE was an OR of
- * all the sub bits. For real 64k pages, we now have the assembly set
- * _PAGE_HPTE_SUB0 in addition to setting the HIDX bits which overlap
- * that mask. This is fine as long as the HIDX bits are never set on
- * a PTE that isn't hashed, which is the case today.
- *
- * A little nit is for the huge page C code, which does the hashing
- * in C, we need to provide which bit to use.
- */
-#define _PAGE_HASHPTE	_PAGE_HPTE_SUB
-
-/* Note the full page bits must be in the same location as for normal
- * 4k pages as the same assembly will be used to insert 64K pages
- * whether the kernel has CONFIG_PPC_64K_PAGES or not
- */
-#define _PAGE_F_SECOND  0x00008000 /* full page: hidx bits */
-#define _PAGE_F_GIX     0x00007000 /* full page: hidx bits */
-
-/* PTE flags to conserve for HPTE identification */
-#define _PAGE_HPTEFLAGS (_PAGE_BUSY | _PAGE_HASHPTE | _PAGE_COMBO)
-
-/* Shift to put page number into pte.
- *
- * That gives us a max RPN of 34 bits, which means a max of 50 bits
- * of addressable physical space, or 46 bits for the special 4k PFNs.
- */
-#define PTE_RPN_SHIFT	(30)
-
-#ifndef __ASSEMBLY__
-
-/*
- * With 64K pages on hash table, we have a special PTE format that
- * uses a second "half" of the page table to encode sub-page information
- * in order to deal with 64K made of 4K HW pages. Thus we override the
- * generic accessors and iterators here
- */
-#define __real_pte __real_pte
-static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep)
-{
-	real_pte_t rpte;
-
-	rpte.pte = pte;
-	rpte.hidx = 0;
-	if (pte_val(pte) & _PAGE_COMBO) {
-		/*
-		 * Make sure we order the hidx load against the _PAGE_COMBO
-		 * check. The store side ordering is done in __hash_page_4K
-		 */
-		smp_rmb();
-		rpte.hidx = pte_val(*((ptep) + PTRS_PER_PTE));
-	}
-	return rpte;
-}
-
-static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index)
-{
-	if ((pte_val(rpte.pte) & _PAGE_COMBO))
-		return (rpte.hidx >> (index<<2)) & 0xf;
-	return (pte_val(rpte.pte) >> 12) & 0xf;
-}
-
-#define __rpte_to_pte(r)	((r).pte)
-#define __rpte_sub_valid(rpte, index) \
-	(pte_val(rpte.pte) & (_PAGE_HPTE_SUB0 >> (index)))
-
-/* Trick: we set __end to va + 64k, which happens works for
- * a 16M page as well as we want only one iteration
- */
-#define pte_iterate_hashed_subpages(rpte, psize, vpn, index, shift)	\
-	do {								\
-		unsigned long __end = vpn + (1UL << (PAGE_SHIFT - VPN_SHIFT));	\
-		unsigned __split = (psize == MMU_PAGE_4K ||		\
-				    psize == MMU_PAGE_64K_AP);		\
-		shift = mmu_psize_defs[psize].shift;			\
-		for (index = 0; vpn < __end; index++,			\
-			     vpn += (1L << (shift - VPN_SHIFT))) {	\
-			if (!__split || __rpte_sub_valid(rpte, index))	\
-				do {
-
-#define pte_iterate_hashed_end() } while(0); } } while(0)
-
-#define pte_pagesize_index(mm, addr, pte)	\
-	(((pte) & _PAGE_COMBO)? MMU_PAGE_4K: MMU_PAGE_64K)
-
-#define remap_4k_pfn(vma, addr, pfn, prot)				\
-	(WARN_ON(((pfn) >= (1UL << (64 - PTE_RPN_SHIFT)))) ? -EINVAL :	\
-		remap_pfn_range((vma), (addr), (pfn), PAGE_SIZE,	\
-			__pgprot(pgprot_val((prot)) | _PAGE_4K_PFN)))
-
-#endif	/* __ASSEMBLY__ */

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

@@ -1,54 +0,0 @@
-#ifndef _ASM_POWERPC_PTE_HASH64_H
-#define _ASM_POWERPC_PTE_HASH64_H
-#ifdef __KERNEL__
-
-/*
- * Common bits between 4K and 64K pages in a linux-style PTE.
- * These match the bits in the (hardware-defined) PowerPC PTE as closely
- * as possible. Additional bits may be defined in pgtable-hash64-*.h
- *
- * Note: We only support user read/write permissions. Supervisor always
- * have full read/write to pages above PAGE_OFFSET (pages below that
- * always use the user access permissions).
- *
- * We could create separate kernel read-only if we used the 3 PP bits
- * combinations that newer processors provide but we currently don't.
- */
-#define _PAGE_PRESENT		0x0001 /* software: pte contains a translation */
-#define _PAGE_USER		0x0002 /* matches one of the PP bits */
-#define _PAGE_BIT_SWAP_TYPE	2
-#define _PAGE_EXEC		0x0004 /* No execute on POWER4 and newer (we invert) */
-#define _PAGE_GUARDED		0x0008
-/* We can derive Memory coherence from _PAGE_NO_CACHE */
-#define _PAGE_NO_CACHE		0x0020 /* I: cache inhibit */
-#define _PAGE_WRITETHRU		0x0040 /* W: cache write-through */
-#define _PAGE_DIRTY		0x0080 /* C: page changed */
-#define _PAGE_ACCESSED		0x0100 /* R: page referenced */
-#define _PAGE_RW		0x0200 /* software: user write access allowed */
-#define _PAGE_BUSY		0x0800 /* software: PTE & hash are busy */
-
-/* No separate kernel read-only */
-#define _PAGE_KERNEL_RW		(_PAGE_RW | _PAGE_DIRTY) /* user access blocked by key */
-#define _PAGE_KERNEL_RO		 _PAGE_KERNEL_RW
-
-/* Strong Access Ordering */
-#define _PAGE_SAO		(_PAGE_WRITETHRU | _PAGE_NO_CACHE | _PAGE_COHERENT)
-
-/* No page size encoding in the linux PTE */
-#define _PAGE_PSIZE		0
-
-/* PTEIDX nibble */
-#define _PTEIDX_SECONDARY	0x8
-#define _PTEIDX_GROUP_IX	0x7
-
-/* Hash table based platforms need atomic updates of the linux PTE */
-#define PTE_ATOMIC_UPDATES	1
-
-#ifdef CONFIG_PPC_64K_PAGES
-#include <asm/pte-hash64-64k.h>
-#else
-#include <asm/pte-hash64-4k.h>
-#endif
-
-#endif /* __KERNEL__ */
-#endif /*  _ASM_POWERPC_PTE_HASH64_H */

arch/powerpc/include/asm/reg.h

@@ -1194,12 +1194,20 @@
 #define __mtmsrd(v, l)	asm volatile("mtmsrd %0," __stringify(l) \
 				     : : "r" (v) : "memory")
 #define mtmsr(v)	__mtmsrd((v), 0)
+#define __MTMSR		"mtmsrd"
 #else
 #define mtmsr(v)	asm volatile("mtmsr %0" : \
 				     : "r" ((unsigned long)(v)) \
 				     : "memory")
+#define __MTMSR		"mtmsr"
 #endif
 
+static inline void mtmsr_isync(unsigned long val)
+{
+	asm volatile(__MTMSR " %0; " ASM_FTR_IFCLR("isync", "nop", %1) : :
+			"r" (val), "i" (CPU_FTR_ARCH_206) : "memory");
+}
+
 #define mfspr(rn)	({unsigned long rval; \
 			asm volatile("mfspr %0," __stringify(rn) \
 				: "=r" (rval)); rval;})
@@ -1207,6 +1215,15 @@
 				     : "r" ((unsigned long)(v)) \
 				     : "memory")
 
+extern void msr_check_and_set(unsigned long bits);
+extern bool strict_msr_control;
+extern void __msr_check_and_clear(unsigned long bits);
+static inline void msr_check_and_clear(unsigned long bits)
+{
+	if (strict_msr_control)
+		__msr_check_and_clear(bits);
+}
+
 static inline unsigned long mfvtb (void)
 {
 #ifdef CONFIG_PPC_BOOK3S_64

arch/powerpc/include/asm/rtas.h

@@ -334,10 +334,11 @@ extern void (*rtas_flash_term_hook)(int);
 
 extern struct rtas_t rtas;
 
-extern void enter_rtas(unsigned long);
 extern int rtas_token(const char *service);
 extern int rtas_service_present(const char *service);
 extern int rtas_call(int token, int, int, int *, ...);
+void rtas_call_unlocked(struct rtas_args *args, int token, int nargs,
+			int nret, ...);
 extern void rtas_restart(char *cmd);
 extern void rtas_power_off(void);
 extern void rtas_halt(void);

arch/powerpc/include/asm/switch_to.h

@@ -4,6 +4,8 @@
 #ifndef _ASM_POWERPC_SWITCH_TO_H
 #define _ASM_POWERPC_SWITCH_TO_H
 
+#include <asm/reg.h>
+
 struct thread_struct;
 struct task_struct;
 struct pt_regs;
@@ -12,74 +14,59 @@ extern struct task_struct *__switch_to(struct task_struct *,
 	struct task_struct *);
 #define switch_to(prev, next, last)	((last) = __switch_to((prev), (next)))
 
-struct thread_struct;
 extern struct task_struct *_switch(struct thread_struct *prev,
 				   struct thread_struct *next);
-#ifdef CONFIG_PPC_BOOK3S_64
-static inline void save_early_sprs(struct thread_struct *prev)
-{
-	if (cpu_has_feature(CPU_FTR_ARCH_207S))
-		prev->tar = mfspr(SPRN_TAR);
-	if (cpu_has_feature(CPU_FTR_DSCR))
-		prev->dscr = mfspr(SPRN_DSCR);
-}
-#else
-static inline void save_early_sprs(struct thread_struct *prev) {}
-#endif
 
-extern void enable_kernel_fp(void);
-extern void enable_kernel_altivec(void);
-extern void enable_kernel_vsx(void);
-extern int emulate_altivec(struct pt_regs *);
-extern void __giveup_vsx(struct task_struct *);
-extern void giveup_vsx(struct task_struct *);
-extern void enable_kernel_spe(void);
-extern void giveup_spe(struct task_struct *);
-extern void load_up_spe(struct task_struct *);
 extern void switch_booke_debug_regs(struct debug_reg *new_debug);
 
-#ifndef CONFIG_SMP
-extern void discard_lazy_cpu_state(void);
-#else
-static inline void discard_lazy_cpu_state(void)
-{
-}
-#endif
+extern int emulate_altivec(struct pt_regs *);
+
+extern void flush_all_to_thread(struct task_struct *);
+extern void giveup_all(struct task_struct *);
 
 #ifdef CONFIG_PPC_FPU
+extern void enable_kernel_fp(void);
 extern void flush_fp_to_thread(struct task_struct *);
 extern void giveup_fpu(struct task_struct *);
+extern void __giveup_fpu(struct task_struct *);
+static inline void disable_kernel_fp(void)
+{
+	msr_check_and_clear(MSR_FP);
+}
 #else
 static inline void flush_fp_to_thread(struct task_struct *t) { }
-static inline void giveup_fpu(struct task_struct *t) { }
 #endif
 
 #ifdef CONFIG_ALTIVEC
+extern void enable_kernel_altivec(void);
 extern void flush_altivec_to_thread(struct task_struct *);
 extern void giveup_altivec(struct task_struct *);
-extern void giveup_altivec_notask(void);
-#else
-static inline void flush_altivec_to_thread(struct task_struct *t)
-{
-}
-static inline void giveup_altivec(struct task_struct *t)
+extern void __giveup_altivec(struct task_struct *);
+static inline void disable_kernel_altivec(void)
 {
+	msr_check_and_clear(MSR_VEC);
 }
 #endif
 
 #ifdef CONFIG_VSX
+extern void enable_kernel_vsx(void);
 extern void flush_vsx_to_thread(struct task_struct *);
-#else
-static inline void flush_vsx_to_thread(struct task_struct *t)
+extern void giveup_vsx(struct task_struct *);
+extern void __giveup_vsx(struct task_struct *);
+static inline void disable_kernel_vsx(void)
 {
+	msr_check_and_clear(MSR_FP|MSR_VEC|MSR_VSX);
 }
 #endif
 
 #ifdef CONFIG_SPE
+extern void enable_kernel_spe(void);
 extern void flush_spe_to_thread(struct task_struct *);
-#else
-static inline void flush_spe_to_thread(struct task_struct *t)
+extern void giveup_spe(struct task_struct *);
+extern void __giveup_spe(struct task_struct *);
+static inline void disable_kernel_spe(void)
 {
+	msr_check_and_clear(MSR_SPE);
 }
 #endif
 

arch/powerpc/include/asm/synch.h

@@ -44,7 +44,7 @@ static inline void isync(void)
 	MAKE_LWSYNC_SECTION_ENTRY(97, __lwsync_fixup);
 #define PPC_ACQUIRE_BARRIER	 "\n" stringify_in_c(__PPC_ACQUIRE_BARRIER)
 #define PPC_RELEASE_BARRIER	 stringify_in_c(LWSYNC) "\n"
-#define PPC_ATOMIC_ENTRY_BARRIER "\n" stringify_in_c(LWSYNC) "\n"
+#define PPC_ATOMIC_ENTRY_BARRIER "\n" stringify_in_c(sync) "\n"
 #define PPC_ATOMIC_EXIT_BARRIER	 "\n" stringify_in_c(sync) "\n"
 #else
 #define PPC_ACQUIRE_BARRIER

arch/powerpc/include/asm/time.h

@@ -27,7 +27,6 @@ extern struct clock_event_device decrementer_clockevent;
 
 struct rtc_time;
 extern void to_tm(int tim, struct rtc_time * tm);
-extern void GregorianDay(struct rtc_time *tm);
 extern void tick_broadcast_ipi_handler(void);
 
 extern void generic_calibrate_decr(void);

arch/powerpc/include/asm/unistd.h

@@ -12,10 +12,9 @@
 #include <uapi/asm/unistd.h>
 
 
-#define __NR_syscalls		379
+#define NR_syscalls		379
 
 #define __NR__exit __NR_exit
-#define NR_syscalls	__NR_syscalls
 
 #ifndef __ASSEMBLY__
 

arch/powerpc/include/asm/vdso_datapage.h

@@ -41,7 +41,7 @@
 #include <linux/unistd.h>
 #include <linux/time.h>
 
-#define SYSCALL_MAP_SIZE      ((__NR_syscalls + 31) / 32)
+#define SYSCALL_MAP_SIZE      ((NR_syscalls + 31) / 32)
 
 /*
  * So here is the ppc64 backward compatible version

arch/powerpc/include/uapi/asm/cputable.h

@@ -43,5 +43,7 @@
 #define PPC_FEATURE2_TAR		0x04000000
 #define PPC_FEATURE2_VEC_CRYPTO		0x02000000
 #define PPC_FEATURE2_HTM_NOSC		0x01000000
+#define PPC_FEATURE2_ARCH_3_00		0x00800000 /* ISA 3.00 */
+#define PPC_FEATURE2_HAS_IEEE128	0x00400000 /* VSX IEEE Binary Float 128-bit */
 
 #endif /* _UAPI__ASM_POWERPC_CPUTABLE_H */

arch/powerpc/include/uapi/asm/elf.h

@@ -295,6 +295,8 @@ do {									\
 #define R_PPC64_TLSLD		108
 #define R_PPC64_TOCSAVE		109
 
+#define R_PPC64_ENTRY		118
+
 #define R_PPC64_REL16		249
 #define R_PPC64_REL16_LO	250
 #define R_PPC64_REL16_HI	251

arch/powerpc/kernel/align.c

@@ -960,6 +960,7 @@ int fix_alignment(struct pt_regs *regs)
 			preempt_disable();
 			enable_kernel_fp();
 			cvt_df(&data.dd, (float *)&data.x32.low32);
+			disable_kernel_fp();
 			preempt_enable();
 #else
 			return 0;
@@ -1000,6 +1001,7 @@ int fix_alignment(struct pt_regs *regs)
 		preempt_disable();
 		enable_kernel_fp();
 		cvt_fd((float *)&data.x32.low32, &data.dd);
+		disable_kernel_fp();
 		preempt_enable();
 #else
 		return 0;

arch/powerpc/kernel/asm-offsets.c

@@ -185,14 +185,16 @@ int main(void)
 	DEFINE(PACAKMSR, offsetof(struct paca_struct, kernel_msr));
 	DEFINE(PACASOFTIRQEN, offsetof(struct paca_struct, soft_enabled));
 	DEFINE(PACAIRQHAPPENED, offsetof(struct paca_struct, irq_happened));
-	DEFINE(PACACONTEXTID, offsetof(struct paca_struct, context.id));
+#ifdef CONFIG_PPC_BOOK3S
+	DEFINE(PACACONTEXTID, offsetof(struct paca_struct, mm_ctx_id));
 #ifdef CONFIG_PPC_MM_SLICES
 	DEFINE(PACALOWSLICESPSIZE, offsetof(struct paca_struct,
-					    context.low_slices_psize));
+					    mm_ctx_low_slices_psize));
 	DEFINE(PACAHIGHSLICEPSIZE, offsetof(struct paca_struct,
-					    context.high_slices_psize));
+					    mm_ctx_high_slices_psize));
 	DEFINE(MMUPSIZEDEFSIZE, sizeof(struct mmu_psize_def));
 #endif /* CONFIG_PPC_MM_SLICES */
+#endif
 
 #ifdef CONFIG_PPC_BOOK3E
 	DEFINE(PACAPGD, offsetof(struct paca_struct, pgd));
@@ -222,7 +224,7 @@ int main(void)
 #ifdef CONFIG_PPC_MM_SLICES
 	DEFINE(MMUPSIZESLLP, offsetof(struct mmu_psize_def, sllp));
 #else
-	DEFINE(PACACONTEXTSLLP, offsetof(struct paca_struct, context.sllp));
+	DEFINE(PACACONTEXTSLLP, offsetof(struct paca_struct, mm_ctx_sllp));
 #endif /* CONFIG_PPC_MM_SLICES */
 	DEFINE(PACA_EXGEN, offsetof(struct paca_struct, exgen));
 	DEFINE(PACA_EXMC, offsetof(struct paca_struct, exmc));

arch/powerpc/kernel/entry_64.S

@@ -223,7 +223,11 @@ END_FTR_SECTION_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 
 	beq-	1f
 	ACCOUNT_CPU_USER_EXIT(r11, r12)
-	HMT_MEDIUM_LOW_HAS_PPR
+
+BEGIN_FTR_SECTION
+	HMT_MEDIUM_LOW
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+
 	ld	r13,GPR13(r1)	/* only restore r13 if returning to usermode */
 1:	ld	r2,GPR2(r1)
 	ld	r1,GPR1(r1)
@@ -312,7 +316,13 @@ syscall_exit_work:
 	subi	r12,r12,TI_FLAGS
 
 4:	/* Anything else left to do? */
-	SET_DEFAULT_THREAD_PPR(r3, r10)		/* Set thread.ppr = 3 */
+BEGIN_FTR_SECTION
+	lis	r3,INIT_PPR@highest	/* Set thread.ppr = 3 */
+	ld	r10,PACACURRENT(r13)
+	sldi	r3,r3,32	/* bits 11-13 are used for ppr */
+	std	r3,TASKTHREADPPR(r10)
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+
 	andi.	r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP)
 	beq	ret_from_except_lite
 
@@ -452,43 +462,11 @@ _GLOBAL(_switch)
 	/* r3-r13 are caller saved -- Cort */
 	SAVE_8GPRS(14, r1)
 	SAVE_10GPRS(22, r1)
-	mflr	r20		/* Return to switch caller */
-	mfmsr	r22
-	li	r0, MSR_FP
-#ifdef CONFIG_VSX
-BEGIN_FTR_SECTION
-	oris	r0,r0,MSR_VSX@h	/* Disable VSX */
-END_FTR_SECTION_IFSET(CPU_FTR_VSX)
-#endif /* CONFIG_VSX */
-#ifdef CONFIG_ALTIVEC
-BEGIN_FTR_SECTION
-	oris	r0,r0,MSR_VEC@h	/* Disable altivec */
-	mfspr	r24,SPRN_VRSAVE	/* save vrsave register value */
-	std	r24,THREAD_VRSAVE(r3)
-END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
-#endif /* CONFIG_ALTIVEC */
-	and.	r0,r0,r22
-	beq+	1f
-	andc	r22,r22,r0
-	MTMSRD(r22)
-	isync
-1:	std	r20,_NIP(r1)
+	std	r0,_NIP(r1)	/* Return to switch caller */
 	mfcr	r23
 	std	r23,_CCR(r1)
 	std	r1,KSP(r3)	/* Set old stack pointer */
 
-#ifdef CONFIG_PPC_BOOK3S_64
-BEGIN_FTR_SECTION
-	/* Event based branch registers */
-	mfspr	r0, SPRN_BESCR
-	std	r0, THREAD_BESCR(r3)
-	mfspr	r0, SPRN_EBBHR
-	std	r0, THREAD_EBBHR(r3)
-	mfspr	r0, SPRN_EBBRR
-	std	r0, THREAD_EBBRR(r3)
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
-#endif
-
 #ifdef CONFIG_SMP
 	/* We need a sync somewhere here to make sure that if the
 	 * previous task gets rescheduled on another CPU, it sees all
@@ -576,47 +554,6 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 	mr	r1,r8		/* start using new stack pointer */
 	std	r7,PACAKSAVE(r13)
 
-#ifdef CONFIG_PPC_BOOK3S_64
-BEGIN_FTR_SECTION
-	/* Event based branch registers */
-	ld	r0, THREAD_BESCR(r4)
-	mtspr	SPRN_BESCR, r0
-	ld	r0, THREAD_EBBHR(r4)
-	mtspr	SPRN_EBBHR, r0
-	ld	r0, THREAD_EBBRR(r4)
-	mtspr	SPRN_EBBRR, r0
-
-	ld	r0,THREAD_TAR(r4)
-	mtspr	SPRN_TAR,r0
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
-#endif
-
-#ifdef CONFIG_ALTIVEC
-BEGIN_FTR_SECTION
-	ld	r0,THREAD_VRSAVE(r4)
-	mtspr	SPRN_VRSAVE,r0		/* if G4, restore VRSAVE reg */
-END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
-#endif /* CONFIG_ALTIVEC */
-#ifdef CONFIG_PPC64
-BEGIN_FTR_SECTION
-	lwz	r6,THREAD_DSCR_INHERIT(r4)
-	ld	r0,THREAD_DSCR(r4)
-	cmpwi	r6,0
-	bne	1f
-	ld	r0,PACA_DSCR_DEFAULT(r13)
-1:
-BEGIN_FTR_SECTION_NESTED(70)
-	mfspr	r8, SPRN_FSCR
-	rldimi	r8, r6, FSCR_DSCR_LG, (63 - FSCR_DSCR_LG)
-	mtspr	SPRN_FSCR, r8
-END_FTR_SECTION_NESTED(CPU_FTR_ARCH_207S, CPU_FTR_ARCH_207S, 70)
-	cmpd	r0,r25
-	beq	2f
-	mtspr	SPRN_DSCR,r0
-2:
-END_FTR_SECTION_IFSET(CPU_FTR_DSCR)
-#endif
-
 	ld	r6,_CCR(r1)
 	mtcrf	0xFF,r6
 

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

@@ -96,7 +96,6 @@ __start_interrupts:
 
 	.globl system_reset_pSeries;
 system_reset_pSeries:
-	HMT_MEDIUM_PPR_DISCARD
 	SET_SCRATCH0(r13)
 #ifdef CONFIG_PPC_P7_NAP
 BEGIN_FTR_SECTION
@@ -164,7 +163,6 @@ machine_check_pSeries_1:
 	 * some code path might still want to branch into the original
 	 * vector
 	 */
-	HMT_MEDIUM_PPR_DISCARD
 	SET_SCRATCH0(r13)		/* save r13 */
 #ifdef CONFIG_PPC_P7_NAP
 BEGIN_FTR_SECTION
@@ -199,7 +197,6 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
 	. = 0x300
 	.globl data_access_pSeries
 data_access_pSeries:
-	HMT_MEDIUM_PPR_DISCARD
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common, EXC_STD,
 				 KVMTEST, 0x300)
@@ -207,7 +204,6 @@ data_access_pSeries:
 	. = 0x380
 	.globl data_access_slb_pSeries
 data_access_slb_pSeries:
-	HMT_MEDIUM_PPR_DISCARD
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXSLB)
 	EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST, 0x380)
@@ -234,15 +230,14 @@ data_access_slb_pSeries:
 	bctr
 #endif
 
-	STD_EXCEPTION_PSERIES(0x400, 0x400, instruction_access)
+	STD_EXCEPTION_PSERIES(0x400, instruction_access)
 
 	. = 0x480
 	.globl instruction_access_slb_pSeries
 instruction_access_slb_pSeries:
-	HMT_MEDIUM_PPR_DISCARD
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXSLB)
-	EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x480)
+	EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST, 0x480)
 	std	r3,PACA_EXSLB+EX_R3(r13)
 	mfspr	r3,SPRN_SRR0		/* SRR0 is faulting address */
 #ifdef __DISABLED__
@@ -269,25 +264,24 @@ instruction_access_slb_pSeries:
 	.globl hardware_interrupt_hv;
 hardware_interrupt_pSeries:
 hardware_interrupt_hv:
-	HMT_MEDIUM_PPR_DISCARD
 	BEGIN_FTR_SECTION
 		_MASKABLE_EXCEPTION_PSERIES(0x502, hardware_interrupt,
 					    EXC_HV, SOFTEN_TEST_HV)
 		KVM_HANDLER(PACA_EXGEN, EXC_HV, 0x502)
 	FTR_SECTION_ELSE
 		_MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt,
-					    EXC_STD, SOFTEN_TEST_HV_201)
+					    EXC_STD, SOFTEN_TEST_PR)
 		KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x500)
 	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
 
-	STD_EXCEPTION_PSERIES(0x600, 0x600, alignment)
-	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x600)
+	STD_EXCEPTION_PSERIES(0x600, alignment)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x600)
 
-	STD_EXCEPTION_PSERIES(0x700, 0x700, program_check)
-	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x700)
+	STD_EXCEPTION_PSERIES(0x700, program_check)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x700)
 
-	STD_EXCEPTION_PSERIES(0x800, 0x800, fp_unavailable)
-	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x800)
+	STD_EXCEPTION_PSERIES(0x800, fp_unavailable)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x800)
 
 	. = 0x900
 	.globl decrementer_pSeries
@@ -297,10 +291,10 @@ decrementer_pSeries:
 	STD_EXCEPTION_HV(0x980, 0x982, hdecrementer)
 
 	MASKABLE_EXCEPTION_PSERIES(0xa00, 0xa00, doorbell_super)
-	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xa00)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xa00)
 
-	STD_EXCEPTION_PSERIES(0xb00, 0xb00, trap_0b)
-	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xb00)
+	STD_EXCEPTION_PSERIES(0xb00, trap_0b)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xb00)
 
 	. = 0xc00
 	.globl	system_call_pSeries
@@ -331,8 +325,8 @@ system_call_pSeries:
 	SYSCALL_PSERIES_3
 	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xc00)
 
-	STD_EXCEPTION_PSERIES(0xd00, 0xd00, single_step)
-	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xd00)
+	STD_EXCEPTION_PSERIES(0xd00, single_step)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xd00)
 
 	/* At 0xe??? we have a bunch of hypervisor exceptions, we branch
 	 * out of line to handle them
@@ -407,13 +401,12 @@ hv_facility_unavailable_trampoline:
 	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1202)
 #endif /* CONFIG_CBE_RAS */
 
-	STD_EXCEPTION_PSERIES(0x1300, 0x1300, instruction_breakpoint)
-	KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_STD, 0x1300)
+	STD_EXCEPTION_PSERIES(0x1300, instruction_breakpoint)
+	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x1300)
 
 	. = 0x1500
 	.global denorm_exception_hv
 denorm_exception_hv:
-	HMT_MEDIUM_PPR_DISCARD
 	mtspr	SPRN_SPRG_HSCRATCH0,r13
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, 0x1500)
@@ -435,8 +428,8 @@ denorm_exception_hv:
 	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1602)
 #endif /* CONFIG_CBE_RAS */
 
-	STD_EXCEPTION_PSERIES(0x1700, 0x1700, altivec_assist)
-	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x1700)
+	STD_EXCEPTION_PSERIES(0x1700, altivec_assist)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x1700)
 
 #ifdef CONFIG_CBE_RAS
 	STD_EXCEPTION_HV(0x1800, 0x1802, cbe_thermal)
@@ -527,7 +520,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
 machine_check_pSeries:
 	.globl machine_check_fwnmi
 machine_check_fwnmi:
-	HMT_MEDIUM_PPR_DISCARD
 	SET_SCRATCH0(r13)		/* save r13 */
 	EXCEPTION_PROLOG_0(PACA_EXMC)
 machine_check_pSeries_0:
@@ -536,9 +528,9 @@ machine_check_pSeries_0:
 	KVM_HANDLER_SKIP(PACA_EXMC, EXC_STD, 0x200)
 	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x300)
 	KVM_HANDLER_SKIP(PACA_EXSLB, EXC_STD, 0x380)
-	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x400)
-	KVM_HANDLER_PR(PACA_EXSLB, EXC_STD, 0x480)
-	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x900)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x400)
+	KVM_HANDLER(PACA_EXSLB, EXC_STD, 0x480)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x900)
 	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0x982)
 
 #ifdef CONFIG_PPC_DENORMALISATION
@@ -621,13 +613,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 
 	/* moved from 0xf00 */
 	STD_EXCEPTION_PSERIES_OOL(0xf00, performance_monitor)
-	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf00)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf00)
 	STD_EXCEPTION_PSERIES_OOL(0xf20, altivec_unavailable)
-	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf20)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf20)
 	STD_EXCEPTION_PSERIES_OOL(0xf40, vsx_unavailable)
-	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf40)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf40)
 	STD_EXCEPTION_PSERIES_OOL(0xf60, facility_unavailable)
-	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf60)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf60)
 	STD_EXCEPTION_HV_OOL(0xf82, facility_unavailable)
 	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xf82)
 
@@ -711,7 +703,6 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
 	.globl system_reset_fwnmi
       .align 7
 system_reset_fwnmi:
-	HMT_MEDIUM_PPR_DISCARD
 	SET_SCRATCH0(r13)		/* save r13 */
 	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD,
 				 NOTEST, 0x100)
@@ -1556,29 +1547,19 @@ do_hash_page:
 	lwz	r0,TI_PREEMPT(r11)	/* If we're in an "NMI" */
 	andis.	r0,r0,NMI_MASK@h	/* (i.e. an irq when soft-disabled) */
 	bne	77f			/* then don't call hash_page now */
-	/*
-	 * We need to set the _PAGE_USER bit if MSR_PR is set or if we are
-	 * accessing a userspace segment (even from the kernel). We assume
-	 * kernel addresses always have the high bit set.
-	 */
-	rlwinm	r4,r4,32-25+9,31-9,31-9	/* DSISR_STORE -> _PAGE_RW */
-	rotldi	r0,r3,15		/* Move high bit into MSR_PR posn */
-	orc	r0,r12,r0		/* MSR_PR | ~high_bit */
-	rlwimi	r4,r0,32-13,30,30	/* becomes _PAGE_USER access bit */
-	ori	r4,r4,1			/* add _PAGE_PRESENT */
-	rlwimi	r4,r5,22+2,31-2,31-2	/* Set _PAGE_EXEC if trap is 0x400 */
 
 	/*
 	 * r3 contains the faulting address
-	 * r4 contains the required access permissions
+	 * r4 msr
 	 * r5 contains the trap number
 	 * r6 contains dsisr
 	 *
 	 * at return r3 = 0 for success, 1 for page fault, negative for error
 	 */
+        mr 	r4,r12
 	ld      r6,_DSISR(r1)
-	bl	hash_page		/* build HPTE if possible */
-	cmpdi	r3,0			/* see if hash_page succeeded */
+	bl	__hash_page		/* build HPTE if possible */
+        cmpdi	r3,0			/* see if __hash_page succeeded */
 
 	/* Success */
 	beq	fast_exc_return_irq	/* Return from exception on success */

arch/powerpc/kernel/fpu.S

@@ -73,29 +73,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 	MTFSF_L(fr0)
 	REST_32FPVSRS(0, R4, R7)
 
-	/* FP/VSX off again */
-	MTMSRD(r6)
-	SYNC
-
 	blr
 #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
 
-/*
- * Enable use of the FPU, and VSX if possible, for the caller.
- */
-_GLOBAL(fp_enable)
-	mfmsr	r3
-	ori	r3,r3,MSR_FP
-#ifdef CONFIG_VSX
-BEGIN_FTR_SECTION
-	oris	r3,r3,MSR_VSX@h
-END_FTR_SECTION_IFSET(CPU_FTR_VSX)
-#endif
-	SYNC
-	MTMSRD(r3)
-	isync			/* (not necessary for arch 2.02 and later) */
-	blr
-
 /*
  * Load state from memory into FP registers including FPSCR.
  * Assumes the caller has enabled FP in the MSR.
@@ -136,31 +116,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 	SYNC
 	MTMSRD(r5)			/* enable use of fpu now */
 	isync
-/*
- * For SMP, we don't do lazy FPU switching because it just gets too
- * horrendously complex, especially when a task switches from one CPU
- * to another.  Instead we call giveup_fpu in switch_to.
- */
-#ifndef CONFIG_SMP
-	LOAD_REG_ADDRBASE(r3, last_task_used_math)
-	toreal(r3)
-	PPC_LL	r4,ADDROFF(last_task_used_math)(r3)
-	PPC_LCMPI	0,r4,0
-	beq	1f
-	toreal(r4)
-	addi	r4,r4,THREAD		/* want last_task_used_math->thread */
-	addi	r10,r4,THREAD_FPSTATE
-	SAVE_32FPVSRS(0, R5, R10)
-	mffs	fr0
-	stfd	fr0,FPSTATE_FPSCR(r10)
-	PPC_LL	r5,PT_REGS(r4)
-	toreal(r5)
-	PPC_LL	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
-	li	r10,MSR_FP|MSR_FE0|MSR_FE1
-	andc	r4,r4,r10		/* disable FP for previous task */
-	PPC_STL	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
-1:
-#endif /* CONFIG_SMP */
 	/* enable use of FP after return */
 #ifdef CONFIG_PPC32
 	mfspr	r5,SPRN_SPRG_THREAD	/* current task's THREAD (phys) */
@@ -179,36 +134,17 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 	lfd	fr0,FPSTATE_FPSCR(r10)
 	MTFSF_L(fr0)
 	REST_32FPVSRS(0, R4, R10)
-#ifndef CONFIG_SMP
-	subi	r4,r5,THREAD
-	fromreal(r4)
-	PPC_STL	r4,ADDROFF(last_task_used_math)(r3)
-#endif /* CONFIG_SMP */
 	/* restore registers and return */
 	/* we haven't used ctr or xer or lr */
 	blr
 
 /*
- * giveup_fpu(tsk)
+ * __giveup_fpu(tsk)
  * Disable FP for the task given as the argument,
  * and save the floating-point registers in its thread_struct.
  * Enables the FPU for use in the kernel on return.
  */
-_GLOBAL(giveup_fpu)
-	mfmsr	r5
-	ori	r5,r5,MSR_FP
-#ifdef CONFIG_VSX
-BEGIN_FTR_SECTION
-	oris	r5,r5,MSR_VSX@h
-END_FTR_SECTION_IFSET(CPU_FTR_VSX)
-#endif
-	SYNC_601
-	ISYNC_601
-	MTMSRD(r5)			/* enable use of fpu now */
-	SYNC_601
-	isync
-	PPC_LCMPI	0,r3,0
-	beqlr-				/* if no previous owner, done */
+_GLOBAL(__giveup_fpu)
 	addi	r3,r3,THREAD	        /* want THREAD of task */
 	PPC_LL	r6,THREAD_FPSAVEAREA(r3)
 	PPC_LL	r5,PT_REGS(r3)
@@ -230,11 +166,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 	andc	r4,r4,r3		/* disable FP for previous task */
 	PPC_STL	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
 1:
-#ifndef CONFIG_SMP
-	li	r5,0
-	LOAD_REG_ADDRBASE(r4,last_task_used_math)
-	PPC_STL	r5,ADDROFF(last_task_used_math)(r4)
-#endif /* CONFIG_SMP */
 	blr
 
 /*

arch/powerpc/kernel/head_fsl_booke.S

@@ -857,29 +857,6 @@ _GLOBAL(load_up_spe)
 	oris	r5,r5,MSR_SPE@h
 	mtmsr	r5			/* enable use of SPE now */
 	isync
-/*
- * For SMP, we don't do lazy SPE switching because it just gets too
- * horrendously complex, especially when a task switches from one CPU
- * to another.  Instead we call giveup_spe in switch_to.
- */
-#ifndef CONFIG_SMP
-	lis	r3,last_task_used_spe@ha
-	lwz	r4,last_task_used_spe@l(r3)
-	cmpi	0,r4,0
-	beq	1f
-	addi	r4,r4,THREAD	/* want THREAD of last_task_used_spe */
-	SAVE_32EVRS(0,r10,r4,THREAD_EVR0)
-	evxor	evr10, evr10, evr10	/* clear out evr10 */
-	evmwumiaa evr10, evr10, evr10	/* evr10 <- ACC = 0 * 0 + ACC */
-	li	r5,THREAD_ACC
-	evstddx	evr10, r4, r5		/* save off accumulator */
-	lwz	r5,PT_REGS(r4)
-	lwz	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
-	lis	r10,MSR_SPE@h
-	andc	r4,r4,r10	/* disable SPE for previous task */
-	stw	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
-1:
-#endif /* !CONFIG_SMP */
 	/* enable use of SPE after return */
 	oris	r9,r9,MSR_SPE@h
 	mfspr	r5,SPRN_SPRG_THREAD	/* current task's THREAD (phys) */
@@ -889,10 +866,6 @@ _GLOBAL(load_up_spe)
 	evlddx	evr4,r10,r5
 	evmra	evr4,evr4
 	REST_32EVRS(0,r10,r5,THREAD_EVR0)
-#ifndef CONFIG_SMP
-	subi	r4,r5,THREAD
-	stw	r4,last_task_used_spe@l(r3)
-#endif /* !CONFIG_SMP */
 	blr
 
 /*
@@ -1011,16 +984,10 @@ _GLOBAL(__setup_ehv_ivors)
 
 #ifdef CONFIG_SPE
 /*
- * extern void giveup_spe(struct task_struct *prev)
+ * extern void __giveup_spe(struct task_struct *prev)
  *
  */
-_GLOBAL(giveup_spe)
-	mfmsr	r5
-	oris	r5,r5,MSR_SPE@h
-	mtmsr	r5			/* enable use of SPE now */
-	isync
-	cmpi	0,r3,0
-	beqlr-				/* if no previous owner, done */
+_GLOBAL(__giveup_spe)
 	addi	r3,r3,THREAD		/* want THREAD of task */
 	lwz	r5,PT_REGS(r3)
 	cmpi	0,r5,0
@@ -1035,11 +1002,6 @@ _GLOBAL(giveup_spe)
 	andc	r4,r4,r3		/* disable SPE for previous task */
 	stw	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
 1:
-#ifndef CONFIG_SMP
-	li	r5,0
-	lis	r4,last_task_used_spe@ha
-	stw	r5,last_task_used_spe@l(r4)
-#endif /* !CONFIG_SMP */
 	blr
 #endif /* CONFIG_SPE */
 

arch/powerpc/kernel/idle_power7.S

@@ -89,13 +89,6 @@ _GLOBAL(power7_powersave_common)
 	std	r0,_LINK(r1)
 	std	r0,_NIP(r1)
 
-#ifndef CONFIG_SMP
-	/* Make sure FPU, VSX etc... are flushed as we may lose
-	 * state when going to nap mode
-	 */
-	bl	discard_lazy_cpu_state
-#endif /* CONFIG_SMP */
-
 	/* Hard disable interrupts */
 	mfmsr	r9
 	rldicl	r9,r9,48,1

arch/powerpc/kernel/misc_32.S

@@ -743,6 +743,8 @@ relocate_new_kernel:
 	/* Check for 47x cores */
 	mfspr	r3,SPRN_PVR
 	srwi	r3,r3,16
+	cmplwi	cr0,r3,PVR_476FPE@h
+	beq	setup_map_47x
 	cmplwi	cr0,r3,PVR_476@h
 	beq	setup_map_47x
 	cmplwi	cr0,r3,PVR_476_ISS@h

arch/powerpc/kernel/module_64.c

@@ -635,6 +635,33 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 			 */
 			break;
 
+		case R_PPC64_ENTRY:
+			/*
+			 * Optimize ELFv2 large code model entry point if
+			 * the TOC is within 2GB range of current location.
+			 */
+			value = my_r2(sechdrs, me) - (unsigned long)location;
+			if (value + 0x80008000 > 0xffffffff)
+				break;
+			/*
+			 * Check for the large code model prolog sequence:
+		         *	ld r2, ...(r12)
+			 *	add r2, r2, r12
+			 */
+			if ((((uint32_t *)location)[0] & ~0xfffc)
+			    != 0xe84c0000)
+				break;
+			if (((uint32_t *)location)[1] != 0x7c426214)
+				break;
+			/*
+			 * If found, replace it with:
+			 *	addis r2, r12, (.TOC.-func)@ha
+			 *	addi r2, r12, (.TOC.-func)@l
+			 */
+			((uint32_t *)location)[0] = 0x3c4c0000 + PPC_HA(value);
+			((uint32_t *)location)[1] = 0x38420000 + PPC_LO(value);
+			break;
+
 		case R_PPC64_REL16_HA:
 			/* Subtract location pointer */
 			value -= (unsigned long)location;

arch/powerpc/kernel/ppc_ksyms.c

@@ -19,13 +19,11 @@ EXPORT_SYMBOL(_mcount);
 #endif
 
 #ifdef CONFIG_PPC_FPU
-EXPORT_SYMBOL(giveup_fpu);
 EXPORT_SYMBOL(load_fp_state);
 EXPORT_SYMBOL(store_fp_state);
 #endif
 
 #ifdef CONFIG_ALTIVEC
-EXPORT_SYMBOL(giveup_altivec);
 EXPORT_SYMBOL(load_vr_state);
 EXPORT_SYMBOL(store_vr_state);
 #endif
@@ -34,10 +32,6 @@ EXPORT_SYMBOL(store_vr_state);
 EXPORT_SYMBOL_GPL(__giveup_vsx);
 #endif
 
-#ifdef CONFIG_SPE
-EXPORT_SYMBOL(giveup_spe);
-#endif
-
 #ifdef CONFIG_EPAPR_PARAVIRT
 EXPORT_SYMBOL(epapr_hypercall_start);
 #endif

arch/powerpc/kernel/process.c

@@ -67,15 +67,8 @@
 
 extern unsigned long _get_SP(void);
 
-#ifndef CONFIG_SMP
-struct task_struct *last_task_used_math = NULL;
-struct task_struct *last_task_used_altivec = NULL;
-struct task_struct *last_task_used_vsx = NULL;
-struct task_struct *last_task_used_spe = NULL;
-#endif
-
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-void giveup_fpu_maybe_transactional(struct task_struct *tsk)
+static void check_if_tm_restore_required(struct task_struct *tsk)
 {
 	/*
 	 * If we are saving the current thread's registers, and the
@@ -89,34 +82,67 @@ void giveup_fpu_maybe_transactional(struct task_struct *tsk)
 		tsk->thread.ckpt_regs.msr = tsk->thread.regs->msr;
 		set_thread_flag(TIF_RESTORE_TM);
 	}
+}
+#else
+static inline void check_if_tm_restore_required(struct task_struct *tsk) { }
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+
+bool strict_msr_control;
+EXPORT_SYMBOL(strict_msr_control);
+
+static int __init enable_strict_msr_control(char *str)
+{
+	strict_msr_control = true;
+	pr_info("Enabling strict facility control\n");
 
-	giveup_fpu(tsk);
+	return 0;
 }
+early_param("ppc_strict_facility_enable", enable_strict_msr_control);
 
-void giveup_altivec_maybe_transactional(struct task_struct *tsk)
+void msr_check_and_set(unsigned long bits)
 {
-	/*
-	 * If we are saving the current thread's registers, and the
-	 * thread is in a transactional state, set the TIF_RESTORE_TM
-	 * bit so that we know to restore the registers before
-	 * returning to userspace.
-	 */
-	if (tsk == current && tsk->thread.regs &&
-	    MSR_TM_ACTIVE(tsk->thread.regs->msr) &&
-	    !test_thread_flag(TIF_RESTORE_TM)) {
-		tsk->thread.ckpt_regs.msr = tsk->thread.regs->msr;
-		set_thread_flag(TIF_RESTORE_TM);
-	}
+	unsigned long oldmsr = mfmsr();
+	unsigned long newmsr;
 
-	giveup_altivec(tsk);
+	newmsr = oldmsr | bits;
+
+#ifdef CONFIG_VSX
+	if (cpu_has_feature(CPU_FTR_VSX) && (bits & MSR_FP))
+		newmsr |= MSR_VSX;
+#endif
+
+	if (oldmsr != newmsr)
+		mtmsr_isync(newmsr);
 }
 
-#else
-#define giveup_fpu_maybe_transactional(tsk)	giveup_fpu(tsk)
-#define giveup_altivec_maybe_transactional(tsk)	giveup_altivec(tsk)
-#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+void __msr_check_and_clear(unsigned long bits)
+{
+	unsigned long oldmsr = mfmsr();
+	unsigned long newmsr;
+
+	newmsr = oldmsr & ~bits;
+
+#ifdef CONFIG_VSX
+	if (cpu_has_feature(CPU_FTR_VSX) && (bits & MSR_FP))
+		newmsr &= ~MSR_VSX;
+#endif
+
+	if (oldmsr != newmsr)
+		mtmsr_isync(newmsr);
+}
+EXPORT_SYMBOL(__msr_check_and_clear);
 
 #ifdef CONFIG_PPC_FPU
+void giveup_fpu(struct task_struct *tsk)
+{
+	check_if_tm_restore_required(tsk);
+
+	msr_check_and_set(MSR_FP);
+	__giveup_fpu(tsk);
+	msr_check_and_clear(MSR_FP);
+}
+EXPORT_SYMBOL(giveup_fpu);
+
 /*
  * Make sure the floating-point register state in the
  * the thread_struct is up to date for task tsk.
@@ -134,52 +160,56 @@ void flush_fp_to_thread(struct task_struct *tsk)
 		 */
 		preempt_disable();
 		if (tsk->thread.regs->msr & MSR_FP) {
-#ifdef CONFIG_SMP
 			/*
 			 * This should only ever be called for current or
 			 * for a stopped child process.  Since we save away
-			 * the FP register state on context switch on SMP,
+			 * the FP register state on context switch,
 			 * there is something wrong if a stopped child appears
 			 * to still have its FP state in the CPU registers.
 			 */
 			BUG_ON(tsk != current);
-#endif
-			giveup_fpu_maybe_transactional(tsk);
+			giveup_fpu(tsk);
 		}
 		preempt_enable();
 	}
 }
 EXPORT_SYMBOL_GPL(flush_fp_to_thread);
-#endif /* CONFIG_PPC_FPU */
 
 void enable_kernel_fp(void)
 {
 	WARN_ON(preemptible());
 
-#ifdef CONFIG_SMP
-	if (current->thread.regs && (current->thread.regs->msr & MSR_FP))
-		giveup_fpu_maybe_transactional(current);
-	else
-		giveup_fpu(NULL);	/* just enables FP for kernel */
-#else
-	giveup_fpu_maybe_transactional(last_task_used_math);
-#endif /* CONFIG_SMP */
+	msr_check_and_set(MSR_FP);
+
+	if (current->thread.regs && (current->thread.regs->msr & MSR_FP)) {
+		check_if_tm_restore_required(current);
+		__giveup_fpu(current);
+	}
 }
 EXPORT_SYMBOL(enable_kernel_fp);
+#endif /* CONFIG_PPC_FPU */
 
 #ifdef CONFIG_ALTIVEC
+void giveup_altivec(struct task_struct *tsk)
+{
+	check_if_tm_restore_required(tsk);
+
+	msr_check_and_set(MSR_VEC);
+	__giveup_altivec(tsk);
+	msr_check_and_clear(MSR_VEC);
+}
+EXPORT_SYMBOL(giveup_altivec);
+
 void enable_kernel_altivec(void)
 {
 	WARN_ON(preemptible());
 
-#ifdef CONFIG_SMP
-	if (current->thread.regs && (current->thread.regs->msr & MSR_VEC))
-		giveup_altivec_maybe_transactional(current);
-	else
-		giveup_altivec_notask();
-#else
-	giveup_altivec_maybe_transactional(last_task_used_altivec);
-#endif /* CONFIG_SMP */
+	msr_check_and_set(MSR_VEC);
+
+	if (current->thread.regs && (current->thread.regs->msr & MSR_VEC)) {
+		check_if_tm_restore_required(current);
+		__giveup_altivec(current);
+	}
 }
 EXPORT_SYMBOL(enable_kernel_altivec);
 
@@ -192,10 +222,8 @@ void flush_altivec_to_thread(struct task_struct *tsk)
 	if (tsk->thread.regs) {
 		preempt_disable();
 		if (tsk->thread.regs->msr & MSR_VEC) {
-#ifdef CONFIG_SMP
 			BUG_ON(tsk != current);
-#endif
-			giveup_altivec_maybe_transactional(tsk);
+			giveup_altivec(tsk);
 		}
 		preempt_enable();
 	}
@@ -204,37 +232,43 @@ EXPORT_SYMBOL_GPL(flush_altivec_to_thread);
 #endif /* CONFIG_ALTIVEC */
 
 #ifdef CONFIG_VSX
-void enable_kernel_vsx(void)
+void giveup_vsx(struct task_struct *tsk)
 {
-	WARN_ON(preemptible());
+	check_if_tm_restore_required(tsk);
 
-#ifdef CONFIG_SMP
-	if (current->thread.regs && (current->thread.regs->msr & MSR_VSX))
-		giveup_vsx(current);
-	else
-		giveup_vsx(NULL);	/* just enable vsx for kernel - force */
-#else
-	giveup_vsx(last_task_used_vsx);
-#endif /* CONFIG_SMP */
+	msr_check_and_set(MSR_FP|MSR_VEC|MSR_VSX);
+	if (tsk->thread.regs->msr & MSR_FP)
+		__giveup_fpu(tsk);
+	if (tsk->thread.regs->msr & MSR_VEC)
+		__giveup_altivec(tsk);
+	__giveup_vsx(tsk);
+	msr_check_and_clear(MSR_FP|MSR_VEC|MSR_VSX);
 }
-EXPORT_SYMBOL(enable_kernel_vsx);
+EXPORT_SYMBOL(giveup_vsx);
 
-void giveup_vsx(struct task_struct *tsk)
+void enable_kernel_vsx(void)
 {
-	giveup_fpu_maybe_transactional(tsk);
-	giveup_altivec_maybe_transactional(tsk);
-	__giveup_vsx(tsk);
+	WARN_ON(preemptible());
+
+	msr_check_and_set(MSR_FP|MSR_VEC|MSR_VSX);
+
+	if (current->thread.regs && (current->thread.regs->msr & MSR_VSX)) {
+		check_if_tm_restore_required(current);
+		if (current->thread.regs->msr & MSR_FP)
+			__giveup_fpu(current);
+		if (current->thread.regs->msr & MSR_VEC)
+			__giveup_altivec(current);
+		__giveup_vsx(current);
+	}
 }
-EXPORT_SYMBOL(giveup_vsx);
+EXPORT_SYMBOL(enable_kernel_vsx);
 
 void flush_vsx_to_thread(struct task_struct *tsk)
 {
 	if (tsk->thread.regs) {
 		preempt_disable();
 		if (tsk->thread.regs->msr & MSR_VSX) {
-#ifdef CONFIG_SMP
 			BUG_ON(tsk != current);
-#endif
 			giveup_vsx(tsk);
 		}
 		preempt_enable();
@@ -244,19 +278,26 @@ EXPORT_SYMBOL_GPL(flush_vsx_to_thread);
 #endif /* CONFIG_VSX */
 
 #ifdef CONFIG_SPE
+void giveup_spe(struct task_struct *tsk)
+{
+	check_if_tm_restore_required(tsk);
+
+	msr_check_and_set(MSR_SPE);
+	__giveup_spe(tsk);
+	msr_check_and_clear(MSR_SPE);
+}
+EXPORT_SYMBOL(giveup_spe);
 
 void enable_kernel_spe(void)
 {
 	WARN_ON(preemptible());
 
-#ifdef CONFIG_SMP
-	if (current->thread.regs && (current->thread.regs->msr & MSR_SPE))
-		giveup_spe(current);
-	else
-		giveup_spe(NULL);	/* just enable SPE for kernel - force */
-#else
-	giveup_spe(last_task_used_spe);
-#endif /* __SMP __ */
+	msr_check_and_set(MSR_SPE);
+
+	if (current->thread.regs && (current->thread.regs->msr & MSR_SPE)) {
+		check_if_tm_restore_required(current);
+		__giveup_spe(current);
+	}
 }
 EXPORT_SYMBOL(enable_kernel_spe);
 
@@ -265,9 +306,7 @@ void flush_spe_to_thread(struct task_struct *tsk)
 	if (tsk->thread.regs) {
 		preempt_disable();
 		if (tsk->thread.regs->msr & MSR_SPE) {
-#ifdef CONFIG_SMP
 			BUG_ON(tsk != current);
-#endif
 			tsk->thread.spefscr = mfspr(SPRN_SPEFSCR);
 			giveup_spe(tsk);
 		}
@@ -276,31 +315,81 @@ void flush_spe_to_thread(struct task_struct *tsk)
 }
 #endif /* CONFIG_SPE */
 
-#ifndef CONFIG_SMP
-/*
- * If we are doing lazy switching of CPU state (FP, altivec or SPE),
- * and the current task has some state, discard it.
- */
-void discard_lazy_cpu_state(void)
+static unsigned long msr_all_available;
+
+static int __init init_msr_all_available(void)
 {
-	preempt_disable();
-	if (last_task_used_math == current)
-		last_task_used_math = NULL;
+#ifdef CONFIG_PPC_FPU
+	msr_all_available |= MSR_FP;
+#endif
 #ifdef CONFIG_ALTIVEC
-	if (last_task_used_altivec == current)
-		last_task_used_altivec = NULL;
-#endif /* CONFIG_ALTIVEC */
+	if (cpu_has_feature(CPU_FTR_ALTIVEC))
+		msr_all_available |= MSR_VEC;
+#endif
 #ifdef CONFIG_VSX
-	if (last_task_used_vsx == current)
-		last_task_used_vsx = NULL;
-#endif /* CONFIG_VSX */
+	if (cpu_has_feature(CPU_FTR_VSX))
+		msr_all_available |= MSR_VSX;
+#endif
 #ifdef CONFIG_SPE
-	if (last_task_used_spe == current)
-		last_task_used_spe = NULL;
+	if (cpu_has_feature(CPU_FTR_SPE))
+		msr_all_available |= MSR_SPE;
 #endif
-	preempt_enable();
+
+	return 0;
+}
+early_initcall(init_msr_all_available);
+
+void giveup_all(struct task_struct *tsk)
+{
+	unsigned long usermsr;
+
+	if (!tsk->thread.regs)
+		return;
+
+	usermsr = tsk->thread.regs->msr;
+
+	if ((usermsr & msr_all_available) == 0)
+		return;
+
+	msr_check_and_set(msr_all_available);
+
+#ifdef CONFIG_PPC_FPU
+	if (usermsr & MSR_FP)
+		__giveup_fpu(tsk);
+#endif
+#ifdef CONFIG_ALTIVEC
+	if (usermsr & MSR_VEC)
+		__giveup_altivec(tsk);
+#endif
+#ifdef CONFIG_VSX
+	if (usermsr & MSR_VSX)
+		__giveup_vsx(tsk);
+#endif
+#ifdef CONFIG_SPE
+	if (usermsr & MSR_SPE)
+		__giveup_spe(tsk);
+#endif
+
+	msr_check_and_clear(msr_all_available);
+}
+EXPORT_SYMBOL(giveup_all);
+
+void flush_all_to_thread(struct task_struct *tsk)
+{
+	if (tsk->thread.regs) {
+		preempt_disable();
+		BUG_ON(tsk != current);
+		giveup_all(tsk);
+
+#ifdef CONFIG_SPE
+		if (tsk->thread.regs->msr & MSR_SPE)
+			tsk->thread.spefscr = mfspr(SPRN_SPEFSCR);
+#endif
+
+		preempt_enable();
+	}
 }
-#endif /* CONFIG_SMP */
+EXPORT_SYMBOL(flush_all_to_thread);
 
 #ifdef CONFIG_PPC_ADV_DEBUG_REGS
 void do_send_trap(struct pt_regs *regs, unsigned long address,
@@ -744,13 +833,15 @@ void restore_tm_state(struct pt_regs *regs)
 	msr_diff = current->thread.ckpt_regs.msr & ~regs->msr;
 	msr_diff &= MSR_FP | MSR_VEC | MSR_VSX;
 	if (msr_diff & MSR_FP) {
-		fp_enable();
+		msr_check_and_set(MSR_FP);
 		load_fp_state(&current->thread.fp_state);
+		msr_check_and_clear(MSR_FP);
 		regs->msr |= current->thread.fpexc_mode;
 	}
 	if (msr_diff & MSR_VEC) {
-		vec_enable();
+		msr_check_and_set(MSR_VEC);
 		load_vr_state(&current->thread.vr_state);
+		msr_check_and_clear(MSR_VEC);
 	}
 	regs->msr |= msr_diff;
 }
@@ -760,112 +851,87 @@ void restore_tm_state(struct pt_regs *regs)
 #define __switch_to_tm(prev)
 #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
 
-struct task_struct *__switch_to(struct task_struct *prev,
-	struct task_struct *new)
+static inline void save_sprs(struct thread_struct *t)
 {
-	struct thread_struct *new_thread, *old_thread;
-	struct task_struct *last;
-#ifdef CONFIG_PPC_BOOK3S_64
-	struct ppc64_tlb_batch *batch;
+#ifdef CONFIG_ALTIVEC
+	if (cpu_has_feature(cpu_has_feature(CPU_FTR_ALTIVEC)))
+		t->vrsave = mfspr(SPRN_VRSAVE);
 #endif
+#ifdef CONFIG_PPC_BOOK3S_64
+	if (cpu_has_feature(CPU_FTR_DSCR))
+		t->dscr = mfspr(SPRN_DSCR);
 
-	WARN_ON(!irqs_disabled());
+	if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
+		t->bescr = mfspr(SPRN_BESCR);
+		t->ebbhr = mfspr(SPRN_EBBHR);
+		t->ebbrr = mfspr(SPRN_EBBRR);
 
-	/* Back up the TAR and DSCR across context switches.
-	 * Note that the TAR is not available for use in the kernel.  (To
-	 * provide this, the TAR should be backed up/restored on exception
-	 * entry/exit instead, and be in pt_regs.  FIXME, this should be in
-	 * pt_regs anyway (for debug).)
-	 * Save the TAR and DSCR here before we do treclaim/trecheckpoint as
-	 * these will change them.
-	 */
-	save_early_sprs(&prev->thread);
+		t->fscr = mfspr(SPRN_FSCR);
 
-	__switch_to_tm(prev);
+		/*
+		 * Note that the TAR is not available for use in the kernel.
+		 * (To provide this, the TAR should be backed up/restored on
+		 * exception entry/exit instead, and be in pt_regs.  FIXME,
+		 * this should be in pt_regs anyway (for debug).)
+		 */
+		t->tar = mfspr(SPRN_TAR);
+	}
+#endif
+}
 
-#ifdef CONFIG_SMP
-	/* avoid complexity of lazy save/restore of fpu
-	 * by just saving it every time we switch out if
-	 * this task used the fpu during the last quantum.
-	 *
-	 * If it tries to use the fpu again, it'll trap and
-	 * reload its fp regs.  So we don't have to do a restore
-	 * every switch, just a save.
-	 *  -- Cort
-	 */
-	if (prev->thread.regs && (prev->thread.regs->msr & MSR_FP))
-		giveup_fpu(prev);
+static inline void restore_sprs(struct thread_struct *old_thread,
+				struct thread_struct *new_thread)
+{
 #ifdef CONFIG_ALTIVEC
-	/*
-	 * If the previous thread used altivec in the last quantum
-	 * (thus changing altivec regs) then save them.
-	 * We used to check the VRSAVE register but not all apps
-	 * set it, so we don't rely on it now (and in fact we need
-	 * to save & restore VSCR even if VRSAVE == 0).  -- paulus
-	 *
-	 * On SMP we always save/restore altivec regs just to avoid the
-	 * complexity of changing processors.
-	 *  -- Cort
-	 */
-	if (prev->thread.regs && (prev->thread.regs->msr & MSR_VEC))
-		giveup_altivec(prev);
-#endif /* CONFIG_ALTIVEC */
-#ifdef CONFIG_VSX
-	if (prev->thread.regs && (prev->thread.regs->msr & MSR_VSX))
-		/* VMX and FPU registers are already save here */
-		__giveup_vsx(prev);
-#endif /* CONFIG_VSX */
-#ifdef CONFIG_SPE
-	/*
-	 * If the previous thread used spe in the last quantum
-	 * (thus changing spe regs) then save them.
-	 *
-	 * On SMP we always save/restore spe regs just to avoid the
-	 * complexity of changing processors.
-	 */
-	if ((prev->thread.regs && (prev->thread.regs->msr & MSR_SPE)))
-		giveup_spe(prev);
-#endif /* CONFIG_SPE */
+	if (cpu_has_feature(CPU_FTR_ALTIVEC) &&
+	    old_thread->vrsave != new_thread->vrsave)
+		mtspr(SPRN_VRSAVE, new_thread->vrsave);
+#endif
+#ifdef CONFIG_PPC_BOOK3S_64
+	if (cpu_has_feature(CPU_FTR_DSCR)) {
+		u64 dscr = get_paca()->dscr_default;
+		u64 fscr = old_thread->fscr & ~FSCR_DSCR;
 
-#else  /* CONFIG_SMP */
-#ifdef CONFIG_ALTIVEC
-	/* Avoid the trap.  On smp this this never happens since
-	 * we don't set last_task_used_altivec -- Cort
-	 */
-	if (new->thread.regs && last_task_used_altivec == new)
-		new->thread.regs->msr |= MSR_VEC;
-#endif /* CONFIG_ALTIVEC */
-#ifdef CONFIG_VSX
-	if (new->thread.regs && last_task_used_vsx == new)
-		new->thread.regs->msr |= MSR_VSX;
-#endif /* CONFIG_VSX */
-#ifdef CONFIG_SPE
-	/* Avoid the trap.  On smp this this never happens since
-	 * we don't set last_task_used_spe
-	 */
-	if (new->thread.regs && last_task_used_spe == new)
-		new->thread.regs->msr |= MSR_SPE;
-#endif /* CONFIG_SPE */
+		if (new_thread->dscr_inherit) {
+			dscr = new_thread->dscr;
+			fscr |= FSCR_DSCR;
+		}
 
-#endif /* CONFIG_SMP */
+		if (old_thread->dscr != dscr)
+			mtspr(SPRN_DSCR, dscr);
 
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
-	switch_booke_debug_regs(&new->thread.debug);
-#else
-/*
- * For PPC_BOOK3S_64, we use the hw-breakpoint interfaces that would
- * schedule DABR
- */
-#ifndef CONFIG_HAVE_HW_BREAKPOINT
-	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 */
+		if (old_thread->fscr != fscr)
+			mtspr(SPRN_FSCR, fscr);
+	}
+
+	if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
+		if (old_thread->bescr != new_thread->bescr)
+			mtspr(SPRN_BESCR, new_thread->bescr);
+		if (old_thread->ebbhr != new_thread->ebbhr)
+			mtspr(SPRN_EBBHR, new_thread->ebbhr);
+		if (old_thread->ebbrr != new_thread->ebbrr)
+			mtspr(SPRN_EBBRR, new_thread->ebbrr);
+
+		if (old_thread->tar != new_thread->tar)
+			mtspr(SPRN_TAR, new_thread->tar);
+	}
 #endif
+}
 
+struct task_struct *__switch_to(struct task_struct *prev,
+	struct task_struct *new)
+{
+	struct thread_struct *new_thread, *old_thread;
+	struct task_struct *last;
+#ifdef CONFIG_PPC_BOOK3S_64
+	struct ppc64_tlb_batch *batch;
+#endif
 
 	new_thread = &new->thread;
 	old_thread = &current->thread;
 
+	WARN_ON(!irqs_disabled());
+
 #ifdef CONFIG_PPC64
 	/*
 	 * Collect processor utilization data per process
@@ -890,6 +956,30 @@ struct task_struct *__switch_to(struct task_struct *prev,
 	}
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+	switch_booke_debug_regs(&new->thread.debug);
+#else
+/*
+ * For PPC_BOOK3S_64, we use the hw-breakpoint interfaces that would
+ * schedule DABR
+ */
+#ifndef CONFIG_HAVE_HW_BREAKPOINT
+	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
+
+	/*
+	 * We need to save SPRs before treclaim/trecheckpoint as these will
+	 * change a number of them.
+	 */
+	save_sprs(&prev->thread);
+
+	__switch_to_tm(prev);
+
+	/* Save FPU, Altivec, VSX and SPE state */
+	giveup_all(prev);
+
 	/*
 	 * We can't take a PMU exception inside _switch() since there is a
 	 * window where the kernel stack SLB and the kernel stack are out
@@ -899,6 +989,15 @@ struct task_struct *__switch_to(struct task_struct *prev,
 
 	tm_recheckpoint_new_task(new);
 
+	/*
+	 * Call restore_sprs() before calling _switch(). If we move it after
+	 * _switch() then we miss out on calling it for new tasks. The reason
+	 * for this is we manually create a stack frame for new tasks that
+	 * directly returns through ret_from_fork() or
+	 * ret_from_kernel_thread(). See copy_thread() for details.
+	 */
+	restore_sprs(old_thread, new_thread);
+
 	last = _switch(old_thread, new_thread);
 
 #ifdef CONFIG_PPC_BOOK3S_64
@@ -952,10 +1051,12 @@ static void show_instructions(struct pt_regs *regs)
 	printk("\n");
 }
 
-static struct regbit {
+struct regbit {
 	unsigned long bit;
 	const char *name;
-} msr_bits[] = {
+};
+
+static struct regbit msr_bits[] = {
 #if defined(CONFIG_PPC64) && !defined(CONFIG_BOOKE)
 	{MSR_SF,	"SF"},
 	{MSR_HV,	"HV"},
@@ -985,16 +1086,49 @@ static struct regbit {
 	{0,		NULL}
 };
 
-static void printbits(unsigned long val, struct regbit *bits)
+static void print_bits(unsigned long val, struct regbit *bits, const char *sep)
 {
-	const char *sep = "";
+	const char *s = "";
 
-	printk("<");
 	for (; bits->bit; ++bits)
 		if (val & bits->bit) {
-			printk("%s%s", sep, bits->name);
-			sep = ",";
+			printk("%s%s", s, bits->name);
+			s = sep;
 		}
+}
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+static struct regbit msr_tm_bits[] = {
+	{MSR_TS_T,	"T"},
+	{MSR_TS_S,	"S"},
+	{MSR_TM,	"E"},
+	{0,		NULL}
+};
+
+static void print_tm_bits(unsigned long val)
+{
+/*
+ * This only prints something if at least one of the TM bit is set.
+ * Inside the TM[], the output means:
+ *   E: Enabled		(bit 32)
+ *   S: Suspended	(bit 33)
+ *   T: Transactional	(bit 34)
+ */
+	if (val & (MSR_TM | MSR_TS_S | MSR_TS_T)) {
+		printk(",TM[");
+		print_bits(val, msr_tm_bits, "");
+		printk("]");
+	}
+}
+#else
+static void print_tm_bits(unsigned long val) {}
+#endif
+
+static void print_msr_bits(unsigned long val)
+{
+	printk("<");
+	print_bits(val, msr_bits, ",");
+	print_tm_bits(val);
 	printk(">");
 }
 
@@ -1019,7 +1153,7 @@ void show_regs(struct pt_regs * regs)
 	printk("REGS: %p TRAP: %04lx   %s  (%s)\n",
 	       regs, regs->trap, print_tainted(), init_utsname()->release);
 	printk("MSR: "REG" ", regs->msr);
-	printbits(regs->msr, msr_bits);
+	print_msr_bits(regs->msr);
 	printk("  CR: %08lx  XER: %08lx\n", regs->ccr, regs->xer);
 	trap = TRAP(regs);
 	if ((regs->trap != 0xc00) && cpu_has_feature(CPU_FTR_CFAR))
@@ -1061,13 +1195,10 @@ void show_regs(struct pt_regs * regs)
 
 void exit_thread(void)
 {
-	discard_lazy_cpu_state();
 }
 
 void flush_thread(void)
 {
-	discard_lazy_cpu_state();
-
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 	flush_ptrace_hw_breakpoint(current);
 #else /* CONFIG_HAVE_HW_BREAKPOINT */
@@ -1086,10 +1217,7 @@ release_thread(struct task_struct *t)
  */
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
-	flush_fp_to_thread(src);
-	flush_altivec_to_thread(src);
-	flush_vsx_to_thread(src);
-	flush_spe_to_thread(src);
+	flush_all_to_thread(src);
 	/*
 	 * Flush TM state out so we can copy it.  __switch_to_tm() does this
 	 * flush but it removes the checkpointed state from the current CPU and
@@ -1212,7 +1340,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 #ifdef CONFIG_PPC64 
 	if (cpu_has_feature(CPU_FTR_DSCR)) {
 		p->thread.dscr_inherit = current->thread.dscr_inherit;
-		p->thread.dscr = current->thread.dscr;
+		p->thread.dscr = mfspr(SPRN_DSCR);
 	}
 	if (cpu_has_feature(CPU_FTR_HAS_PPR))
 		p->thread.ppr = INIT_PPR;
@@ -1305,7 +1433,6 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 		regs->msr = MSR_USER32;
 	}
 #endif
-	discard_lazy_cpu_state();
 #ifdef CONFIG_VSX
 	current->thread.used_vsr = 0;
 #endif

arch/powerpc/kernel/prom_init.c

@@ -389,6 +389,7 @@ static void __init prom_printf(const char *format, ...)
 			break;
 		}
 	}
+	va_end(args);
 }
 
 

arch/powerpc/kernel/ptrace.c

@@ -60,6 +60,7 @@ struct pt_regs_offset {
 #define STR(s)	#s			/* convert to string */
 #define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)}
 #define GPR_OFFSET_NAME(num)	\
+	{.name = STR(r##num), .offset = offsetof(struct pt_regs, gpr[num])}, \
 	{.name = STR(gpr##num), .offset = offsetof(struct pt_regs, gpr[num])}
 #define REG_OFFSET_END {.name = NULL, .offset = 0}
 

arch/powerpc/kernel/rtas.c

@@ -44,6 +44,9 @@
 #include <asm/mmu.h>
 #include <asm/topology.h>
 
+/* This is here deliberately so it's only used in this file */
+void enter_rtas(unsigned long);
+
 struct rtas_t rtas = {
 	.lock = __ARCH_SPIN_LOCK_UNLOCKED
 };
@@ -93,21 +96,13 @@ static void unlock_rtas(unsigned long flags)
  */
 static void call_rtas_display_status(unsigned char c)
 {
-	struct rtas_args *args = &rtas.args;
 	unsigned long s;
 
 	if (!rtas.base)
 		return;
-	s = lock_rtas();
-
-	args->token = cpu_to_be32(10);
-	args->nargs = cpu_to_be32(1);
-	args->nret  = cpu_to_be32(1);
-	args->rets  = &(args->args[1]);
-	args->args[0] = cpu_to_be32(c);
-
-	enter_rtas(__pa(args));
 
+	s = lock_rtas();
+	rtas_call_unlocked(&rtas.args, 10, 1, 1, NULL, c);
 	unlock_rtas(s);
 }
 
@@ -418,6 +413,36 @@ static char *__fetch_rtas_last_error(char *altbuf)
 #define get_errorlog_buffer()		NULL
 #endif
 
+
+static void
+va_rtas_call_unlocked(struct rtas_args *args, int token, int nargs, int nret,
+		      va_list list)
+{
+	int i;
+
+	args->token = cpu_to_be32(token);
+	args->nargs = cpu_to_be32(nargs);
+	args->nret  = cpu_to_be32(nret);
+	args->rets  = &(args->args[nargs]);
+
+	for (i = 0; i < nargs; ++i)
+		args->args[i] = cpu_to_be32(va_arg(list, __u32));
+
+	for (i = 0; i < nret; ++i)
+		args->rets[i] = 0;
+
+	enter_rtas(__pa(args));
+}
+
+void rtas_call_unlocked(struct rtas_args *args, int token, int nargs, int nret, ...)
+{
+	va_list list;
+
+	va_start(list, nret);
+	va_rtas_call_unlocked(args, token, nargs, nret, list);
+	va_end(list);
+}
+
 int rtas_call(int token, int nargs, int nret, int *outputs, ...)
 {
 	va_list list;
@@ -431,22 +456,14 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...)
 		return -1;
 
 	s = lock_rtas();
+
+	/* We use the global rtas args buffer */
 	rtas_args = &rtas.args;
 
-	rtas_args->token = cpu_to_be32(token);
-	rtas_args->nargs = cpu_to_be32(nargs);
-	rtas_args->nret  = cpu_to_be32(nret);
-	rtas_args->rets  = &(rtas_args->args[nargs]);
 	va_start(list, outputs);
-	for (i = 0; i < nargs; ++i)
-		rtas_args->args[i] = cpu_to_be32(va_arg(list, __u32));
+	va_rtas_call_unlocked(rtas_args, token, nargs, nret, list);
 	va_end(list);
 
-	for (i = 0; i < nret; ++i)
-		rtas_args->rets[i] = 0;
-
-	enter_rtas(__pa(rtas_args));
-
 	/* A -1 return code indicates that the last command couldn't
 	   be completed due to a hardware error. */
 	if (be32_to_cpu(rtas_args->rets[0]) == -1)

arch/powerpc/kernel/signal_32.c

@@ -458,7 +458,7 @@ static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame,
 	 * contains valid data
 	 */
 	if (current->thread.used_vsr && ctx_has_vsx_region) {
-		__giveup_vsx(current);
+		flush_vsx_to_thread(current);
 		if (copy_vsx_to_user(&frame->mc_vsregs, current))
 			return 1;
 		msr |= MSR_VSX;
@@ -606,7 +606,7 @@ static int save_tm_user_regs(struct pt_regs *regs,
 	 * contains valid data
 	 */
 	if (current->thread.used_vsr) {
-		__giveup_vsx(current);
+		flush_vsx_to_thread(current);
 		if (copy_vsx_to_user(&frame->mc_vsregs, current))
 			return 1;
 		if (msr & MSR_VSX) {
@@ -687,15 +687,6 @@ static long restore_user_regs(struct pt_regs *regs,
 	if (sig)
 		regs->msr = (regs->msr & ~MSR_LE) | (msr & MSR_LE);
 
-	/*
-	 * Do this before updating the thread state in
-	 * current->thread.fpr/vr/evr.  That way, if we get preempted
-	 * and another task grabs the FPU/Altivec/SPE, it won't be
-	 * tempted to save the current CPU state into the thread_struct
-	 * and corrupt what we are writing there.
-	 */
-	discard_lazy_cpu_state();
-
 #ifdef CONFIG_ALTIVEC
 	/*
 	 * Force the process to reload the altivec registers from
@@ -798,15 +789,6 @@ static long restore_tm_user_regs(struct pt_regs *regs,
 	/* Restore the previous little-endian mode */
 	regs->msr = (regs->msr & ~MSR_LE) | (msr & MSR_LE);
 
-	/*
-	 * Do this before updating the thread state in
-	 * current->thread.fpr/vr/evr.  That way, if we get preempted
-	 * and another task grabs the FPU/Altivec/SPE, it won't be
-	 * tempted to save the current CPU state into the thread_struct
-	 * and corrupt what we are writing there.
-	 */
-	discard_lazy_cpu_state();
-
 #ifdef CONFIG_ALTIVEC
 	regs->msr &= ~MSR_VEC;
 	if (msr & MSR_VEC) {

arch/powerpc/kernel/signal_64.c

@@ -147,7 +147,7 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs,
 	 * VMX data.
 	 */
 	if (current->thread.used_vsr && ctx_has_vsx_region) {
-		__giveup_vsx(current);
+		flush_vsx_to_thread(current);
 		v_regs += ELF_NVRREG;
 		err |= copy_vsx_to_user(v_regs, current);
 		/* set MSR_VSX in the MSR value in the frame to
@@ -270,7 +270,7 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc,
 	 * VMX data.
 	 */
 	if (current->thread.used_vsr) {
-		__giveup_vsx(current);
+		flush_vsx_to_thread(current);
 		v_regs += ELF_NVRREG;
 		tm_v_regs += ELF_NVRREG;
 
@@ -349,15 +349,6 @@ static long restore_sigcontext(struct pt_regs *regs, sigset_t *set, int sig,
 	if (set != NULL)
 		err |=  __get_user(set->sig[0], &sc->oldmask);
 
-	/*
-	 * Do this before updating the thread state in
-	 * current->thread.fpr/vr.  That way, if we get preempted
-	 * and another task grabs the FPU/Altivec, it won't be
-	 * tempted to save the current CPU state into the thread_struct
-	 * and corrupt what we are writing there.
-	 */
-	discard_lazy_cpu_state();
-
 	/*
 	 * Force reload of FP/VEC.
 	 * This has to be done before copying stuff into current->thread.fpr/vr
@@ -468,15 +459,6 @@ static long restore_tm_sigcontexts(struct pt_regs *regs,
 	err |= __get_user(regs->dsisr, &sc->gp_regs[PT_DSISR]);
 	err |= __get_user(regs->result, &sc->gp_regs[PT_RESULT]);
 
-	/*
-	 * Do this before updating the thread state in
-	 * current->thread.fpr/vr.  That way, if we get preempted
-	 * and another task grabs the FPU/Altivec, it won't be
-	 * tempted to save the current CPU state into the thread_struct
-	 * and corrupt what we are writing there.
-	 */
-	discard_lazy_cpu_state();
-
 	/*
 	 * Force reload of FP/VEC.
 	 * This has to be done before copying stuff into current->thread.fpr/vr

arch/powerpc/kernel/stacktrace.c

@@ -61,3 +61,10 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 	save_context_stack(trace, tsk->thread.ksp, tsk, 0);
 }
 EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
+
+void
+save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
+{
+	save_context_stack(trace, regs->gpr[1], current, 0);
+}
+EXPORT_SYMBOL_GPL(save_stack_trace_regs);

arch/powerpc/kernel/swsusp.c

@@ -20,9 +20,7 @@ void save_processor_state(void)
 	 * flush out all the special registers so we don't need
 	 * to save them in the snapshot
 	 */
-	flush_fp_to_thread(current);
-	flush_altivec_to_thread(current);
-	flush_spe_to_thread(current);
+	flush_all_to_thread(current);
 
 #ifdef CONFIG_PPC64
 	hard_irq_disable();