diff --git a/Documentation/powerpc/associativity.rst b/Documentation/powerpc/associativity.rst
new file mode 100644
index 000000000000..4d01c7368561
--- /dev/null
+++ b/Documentation/powerpc/associativity.rst
@@ -0,0 +1,105 @@
+============================
+NUMA resource associativity
+============================
+
+Associativity represents the groupings of the various platform resources into
+domains of substantially similar mean performance relative to resources outside
+of that domain. Resources subsets of a given domain that exhibit better
+performance relative to each other than relative to other resources subsets
+are represented as being members of a sub-grouping domain. This performance
+characteristic is presented in terms of NUMA node distance within the Linux kernel.
+From the platform view, these groups are also referred to as domains.
+
+PAPR interface currently supports different ways of communicating these resource
+grouping details to the OS. These are referred to as Form 0, Form 1 and Form2
+associativity grouping. Form 0 is the oldest format and is now considered deprecated.
+
+Hypervisor indicates the type/form of associativity used via "ibm,architecture-vec-5 property".
+Bit 0 of byte 5 in the "ibm,architecture-vec-5" property indicates usage of Form 0 or Form 1.
+A value of 1 indicates the usage of Form 1 associativity. For Form 2 associativity
+bit 2 of byte 5 in the "ibm,architecture-vec-5" property is used.
+
+Form 0
+------
+Form 0 associativity supports only two NUMA distances (LOCAL and REMOTE).
+
+Form 1
+------
+With Form 1 a combination of ibm,associativity-reference-points, and ibm,associativity
+device tree properties are used to determine the NUMA distance between resource groups/domains.
+
+The “ibm,associativity” property contains a list of one or more numbers (domainID)
+representing the resource’s platform grouping domains.
+
+The “ibm,associativity-reference-points” property contains a list of one or more numbers
+(domainID index) that represents the 1 based ordinal in the associativity lists.
+The list of domainID indexes represents an increasing hierarchy of resource grouping.
+
+ex:
+{ primary domainID index, secondary domainID index, tertiary domainID index.. }
+
+Linux kernel uses the domainID at the primary domainID index as the NUMA node id.
+Linux kernel computes NUMA distance between two domains by recursively comparing
+if they belong to the same higher-level domains. For mismatch at every higher
+level of the resource group, the kernel doubles the NUMA distance between the
+comparing domains.
+
+Form 2
+-------
+Form 2 associativity format adds separate device tree properties representing NUMA node distance
+thereby making the node distance computation flexible. Form 2 also allows flexible primary
+domain numbering. With numa distance computation now detached from the index value in
+"ibm,associativity-reference-points" property, Form 2 allows a large number of primary domain
+ids at the same domainID index representing resource groups of different performance/latency
+characteristics.
+
+Hypervisor indicates the usage of FORM2 associativity using bit 2 of byte 5 in the
+"ibm,architecture-vec-5" property.
+
+"ibm,numa-lookup-index-table" property contains a list of one or more numbers representing
+the domainIDs present in the system. The offset of the domainID in this property is
+used as an index while computing numa distance information via "ibm,numa-distance-table".
+
+prop-encoded-array: The number N of the domainIDs encoded as with encode-int, followed by
+N domainID encoded as with encode-int
+
+For ex:
+"ibm,numa-lookup-index-table" =  {4, 0, 8, 250, 252}. The offset of domainID 8 (2) is used when
+computing the distance of domain 8 from other domains present in the system. For the rest of
+this document, this offset will be referred to as domain distance offset.
+
+"ibm,numa-distance-table" property contains a list of one or more numbers representing the NUMA
+distance between resource groups/domains present in the system.
+
+prop-encoded-array: The number N of the distance values encoded as with encode-int, followed by
+N distance values encoded as with encode-bytes. The max distance value we could encode is 255.
+The number N must be equal to the square of m where m is the number of domainIDs in the
+numa-lookup-index-table.
+
+For ex:
+ibm,numa-lookup-index-table = <3 0 8 40>;
+ibm,numa-distace-table = <9>, /bits/ 8 < 10  20  80 20  10 160 80 160  10>;
+
+::
+
+	  | 0    8   40
+	--|------------
+	  |
+	0 | 10   20  80
+	  |
+	8 | 20   10  160
+	  |
+	40| 80   160  10
+
+A possible "ibm,associativity" property for resources in node 0, 8 and 40
+
+{ 3, 6, 7, 0 }
+{ 3, 6, 9, 8 }
+{ 3, 6, 7, 40}
+
+With "ibm,associativity-reference-points"  { 0x3 }
+
+"ibm,lookup-index-table" helps in having a compact representation of distance matrix.
+Since domainID can be sparse, the matrix of distances can also be effectively sparse.
+With "ibm,lookup-index-table" we can achieve a compact representation of
+distance information.
diff --git a/Documentation/powerpc/index.rst b/Documentation/powerpc/index.rst
index bf5f1a2bdbdf..0f7d3c495693 100644
--- a/Documentation/powerpc/index.rst
+++ b/Documentation/powerpc/index.rst
@@ -7,6 +7,7 @@ powerpc
 .. toctree::
     :maxdepth: 1
 
+    associativity
     booting
     bootwrapper
     cpu_families
diff --git a/MAINTAINERS b/MAINTAINERS
index 59ff351369ec..fa87db67a249 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6853,7 +6853,6 @@ F:	Documentation/admin-guide/media/em28xx*
 F:	drivers/media/usb/em28xx/
 
 EMBEDDED LINUX
-M:	Paul Gortmaker <paul.gortmaker@windriver.com>
 M:	Matt Mackall <mpm@selenic.com>
 M:	David Woodhouse <dwmw2@infradead.org>
 L:	linux-embedded@vger.kernel.org
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 678a0acbad7b..8a93b509337d 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -123,6 +123,7 @@ config PPC
 	select ARCH_HAS_COPY_MC			if PPC64
 	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEBUG_VM_PGTABLE
+	select ARCH_HAS_DEBUG_WX		if STRICT_KERNEL_RWX
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_DMA_MAP_DIRECT 		if PPC_PSERIES
 	select ARCH_HAS_ELF_RANDOMIZE
@@ -182,6 +183,7 @@ config PPC
 	select GENERIC_IRQ_SHOW
 	select GENERIC_IRQ_SHOW_LEVEL
 	select GENERIC_PCI_IOMAP		if PCI
+	select GENERIC_PTDUMP
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_TIME_VSYSCALL
 	select GENERIC_VDSO_TIME_NS
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index 205cd77f321f..192f0ed0097f 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -365,36 +365,6 @@ config FAIL_IOMMU
 
 	  If you are unsure, say N.
 
-config PPC_PTDUMP
-	bool "Export kernel pagetable layout to userspace via debugfs"
-	depends on DEBUG_KERNEL && DEBUG_FS
-	help
-	  This option exports the state of the kernel pagetables to a
-	  debugfs file. This is only useful for kernel developers who are
-	  working in architecture specific areas of the kernel - probably
-	  not a good idea to enable this feature in a production kernel.
-
-	  If you are unsure, say N.
-
-config PPC_DEBUG_WX
-	bool "Warn on W+X mappings at boot"
-	depends on PPC_PTDUMP && STRICT_KERNEL_RWX
-	help
-	  Generate a warning if any W+X mappings are found at boot.
-
-	  This is useful for discovering cases where the kernel is leaving
-	  W+X mappings after applying NX, as such mappings are a security risk.
-
-	  Note that even if the check fails, your kernel is possibly
-	  still fine, as W+X mappings are not a security hole in
-	  themselves, what they do is that they make the exploitation
-	  of other unfixed kernel bugs easier.
-
-	  There is no runtime or memory usage effect of this option
-	  once the kernel has booted up - it's a one time check.
-
-	  If in doubt, say "Y".
-
 config PPC_FAST_ENDIAN_SWITCH
 	bool "Deprecated fast endian-switch syscall"
 	depends on DEBUG_KERNEL && PPC_BOOK3S_64
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 6505d66f1193..aa6808e70647 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -122,6 +122,7 @@ endif
 
 LDFLAGS_vmlinux-y := -Bstatic
 LDFLAGS_vmlinux-$(CONFIG_RELOCATABLE) := -pie
+LDFLAGS_vmlinux-$(CONFIG_RELOCATABLE) += -z notext
 LDFLAGS_vmlinux	:= $(LDFLAGS_vmlinux-y)
 
 ifdef CONFIG_PPC64
@@ -407,7 +408,8 @@ endef
 
 PHONY += install
 install:
-	$(Q)$(MAKE) $(build)=$(boot) install
+	sh -x $(srctree)/$(boot)/install.sh "$(KERNELRELEASE)" vmlinux \
+	System.map "$(INSTALL_PATH)"
 
 archclean:
 	$(Q)$(MAKE) $(clean)=$(boot)
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index e312ea802aa6..6900d0ac2421 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -341,7 +341,6 @@ image-$(CONFIG_TQM8541)			+= cuImage.tqm8541
 image-$(CONFIG_TQM8548)			+= cuImage.tqm8548
 image-$(CONFIG_TQM8555)			+= cuImage.tqm8555
 image-$(CONFIG_TQM8560)			+= cuImage.tqm8560
-image-$(CONFIG_SBC8548)			+= cuImage.sbc8548
 image-$(CONFIG_KSI8560)			+= cuImage.ksi8560
 
 # Board ports in arch/powerpc/platform/86xx/Kconfig
@@ -444,16 +443,6 @@ $(obj)/zImage:		$(addprefix $(obj)/, $(image-y))
 $(obj)/zImage.initrd:	$(addprefix $(obj)/, $(initrd-y))
 	$(Q)rm -f $@; ln $< $@
 
-# Only install the vmlinux
-install: $(CONFIGURE) $(addprefix $(obj)/, $(image-y))
-	sh -x $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" vmlinux System.map "$(INSTALL_PATH)"
-
-# Install the vmlinux and other built boot targets.
-zInstall: $(CONFIGURE) $(addprefix $(obj)/, $(image-y))
-	sh -x $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" vmlinux System.map "$(INSTALL_PATH)" $^
-
-PHONY += install zInstall
-
 # anything not in $(targets)
 clean-files += $(image-) $(initrd-) cuImage.* dtbImage.* treeImage.* \
 	zImage zImage.initrd zImage.chrp zImage.coff zImage.holly \
diff --git a/arch/powerpc/boot/dts/fsl/sbc8641d.dts b/arch/powerpc/boot/dts/fsl/sbc8641d.dts
deleted file mode 100644
index 3dca10acc161..000000000000
--- a/arch/powerpc/boot/dts/fsl/sbc8641d.dts
+++ /dev/null
@@ -1,176 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * SBC8641D Device Tree Source
- *
- * Copyright 2008 Wind River Systems Inc.
- *
- * Paul Gortmaker (see MAINTAINERS for contact information)
- *
- * Based largely on the mpc8641_hpcn.dts by Freescale Semiconductor Inc.
- */
-
-/include/ "mpc8641si-pre.dtsi"
-
-/ {
-	model = "SBC8641D";
-	compatible = "wind,sbc8641";
-
-	memory {
-		device_type = "memory";
-		reg = <0x00000000 0x20000000>;	// 512M at 0x0
-	};
-
-	lbc: localbus@f8005000 {
-		reg = <0xf8005000 0x1000>;
-
-		ranges = <0 0 0xff000000 0x01000000	// 16MB Boot flash
-			  1 0 0xf0000000 0x00010000	// 64KB EEPROM
-			  2 0 0xf1000000 0x00100000	// EPLD (1MB)
-			  3 0 0xe0000000 0x04000000	// 64MB LB SDRAM (CS3)
-			  4 0 0xe4000000 0x04000000	// 64MB LB SDRAM (CS4)
-			  6 0 0xf4000000 0x00100000	// LCD display (1MB)
-			  7 0 0xe8000000 0x04000000>;	// 64MB OneNAND
-
-		flash@0,0 {
-			compatible = "cfi-flash";
-			reg = <0 0 0x01000000>;
-			bank-width = <2>;
-			device-width = <2>;
-			#address-cells = <1>;
-			#size-cells = <1>;
-			partition@0 {
-				label = "dtb";
-				reg = <0x00000000 0x00100000>;
-				read-only;
-			};
-			partition@300000 {
-				label = "kernel";
-				reg = <0x00100000 0x00400000>;
-				read-only;
-			};
-			partition@400000 {
-				label = "fs";
-				reg = <0x00500000 0x00a00000>;
-			};
-			partition@700000 {
-				label = "firmware";
-				reg = <0x00f00000 0x00100000>;
-				read-only;
-			};
-		};
-
-		epld@2,0 {
-			compatible = "wrs,epld-localbus";
-			#address-cells = <2>;
-			#size-cells = <1>;
-			reg = <2 0 0x100000>;
-			ranges = <0 0 5 0 1	// User switches
-				  1 0 5 1 1	// Board ID/Rev
-				  3 0 5 3 1>;	// LEDs
-		};
-	};
-
-	soc: soc@f8000000 {
-		ranges = <0x00000000 0xf8000000 0x00100000>;
-
-		enet0: ethernet@24000 {
-			tbi-handle = <&tbi0>;
-			phy-handle = <&phy0>;
-			phy-connection-type = "rgmii-id";
-		};
-
-		mdio@24520 {
-			phy0: ethernet-phy@1f {
-				reg = <0x1f>;
-			};
-			phy1: ethernet-phy@0 {
-				reg = <0>;
-			};
-			phy2: ethernet-phy@1 {
-				reg = <1>;
-			};
-			phy3: ethernet-phy@2 {
-				reg = <2>;
-			};
-			tbi0: tbi-phy@11 {
-				reg = <0x11>;
-				device_type = "tbi-phy";
-			};
-		};
-
-		enet1: ethernet@25000 {
-			tbi-handle = <&tbi1>;
-			phy-handle = <&phy1>;
-			phy-connection-type = "rgmii-id";
-		};
-
-		mdio@25520 {
-			tbi1: tbi-phy@11 {
-				reg = <0x11>;
-				device_type = "tbi-phy";
-			};
-		};
-
-		enet2: ethernet@26000 {
-			tbi-handle = <&tbi2>;
-			phy-handle = <&phy2>;
-			phy-connection-type = "rgmii-id";
-		};
-
-		mdio@26520 {
-			tbi2: tbi-phy@11 {
-				reg = <0x11>;
-				device_type = "tbi-phy";
-			};
-		};
-
-		enet3: ethernet@27000 {
-			tbi-handle = <&tbi3>;
-			phy-handle = <&phy3>;
-			phy-connection-type = "rgmii-id";
-		};
-
-		mdio@27520 {
-			tbi3: tbi-phy@11 {
-				reg = <0x11>;
-				device_type = "tbi-phy";
-			};
-		};
-	};
-
-	pci0: pcie@f8008000 {
-		reg = <0xf8008000 0x1000>;
-		ranges = <0x02000000 0x0 0x80000000 0x80000000 0x0 0x20000000
-			  0x01000000 0x0 0x00000000 0xe2000000 0x0 0x00100000>;
-		interrupt-map-mask = <0xff00 0 0 7>;
-
-		pcie@0 {
-			ranges = <0x02000000 0x0 0x80000000
-				  0x02000000 0x0 0x80000000
-				  0x0 0x20000000
-
-				  0x01000000 0x0 0x00000000
-				  0x01000000 0x0 0x00000000
-				  0x0 0x00100000>;
-		};
-
-	};
-
-	pci1: pcie@f8009000 {
-		reg = <0xf8009000 0x1000>;
-		ranges = <0x02000000 0x0 0xa0000000 0xa0000000 0x0 0x20000000
-			  0x01000000 0x0 0x00000000 0xe3000000 0x0 0x00100000>;
-
-		pcie@0 {
-			ranges = <0x02000000 0x0 0xa0000000
-				  0x02000000 0x0 0xa0000000
-				  0x0 0x20000000
-
-				  0x01000000 0x0 0x00000000
-				  0x01000000 0x0 0x00000000
-				  0x0 0x00100000>;
-		};
-	};
-};
-
-/include/ "mpc8641si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/microwatt.dts b/arch/powerpc/boot/dts/microwatt.dts
index 974abbdda249..65b270a90f94 100644
--- a/arch/powerpc/boot/dts/microwatt.dts
+++ b/arch/powerpc/boot/dts/microwatt.dts
@@ -127,6 +127,18 @@
 			fifo-size = <16>;
 			interrupts = <0x10 0x1>;
 		};
+
+		ethernet@8020000 {
+			compatible = "litex,liteeth";
+			reg = <0x8021000 0x100
+				0x8020800 0x100
+				0x8030000 0x2000>;
+			reg-names = "mac", "mido", "buffer";
+			litex,rx-slots = <2>;
+			litex,tx-slots = <2>;
+			litex,slot-size = <0x800>;
+			interrupts = <0x11 0x1>;
+		};
 	};
 
 	chosen {
diff --git a/arch/powerpc/boot/dts/sbc8548-altflash.dts b/arch/powerpc/boot/dts/sbc8548-altflash.dts
deleted file mode 100644
index bb7a1e712bb7..000000000000
--- a/arch/powerpc/boot/dts/sbc8548-altflash.dts
+++ /dev/null
@@ -1,111 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * SBC8548 Device Tree Source
- *
- * Configured for booting off the alternate (64MB SODIMM) flash.
- * Requires switching JP12 jumpers and changing SW2.8 setting.
- *
- * Copyright 2013 Wind River Systems Inc.
- *
- * Paul Gortmaker (see MAINTAINERS for contact information)
- */
-
-
-/dts-v1/;
-
-/include/ "sbc8548-pre.dtsi"
-
-/{
-	localbus@e0000000 {
-		#address-cells = <2>;
-		#size-cells = <1>;
-		compatible = "simple-bus";
-		reg = <0xe0000000 0x5000>;
-		interrupt-parent = <&mpic>;
-
-		ranges = <0x0 0x0 0xfc000000 0x04000000		/*64MB Flash*/
-			  0x3 0x0 0xf0000000 0x04000000		/*64MB SDRAM*/
-			  0x4 0x0 0xf4000000 0x04000000 	/*64MB SDRAM*/
-			  0x5 0x0 0xf8000000 0x00b10000		/* EPLD */
-			  0x6 0x0 0xef800000 0x00800000>;	/*8MB Flash*/
-
-		flash@0,0 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			reg = <0x0 0x0 0x04000000>;
-			compatible = "intel,JS28F128", "cfi-flash";
-			bank-width = <4>;
-			device-width = <1>;
-			partition@0 {
-				label = "space";
-				/* FC000000 -> FFEFFFFF */
-				reg = <0x00000000 0x03f00000>;
-			};
-			partition@3f00000 {
-				label = "bootloader";
-				/* FFF00000 -> FFFFFFFF */
-				reg = <0x03f00000 0x00100000>;
-				read-only;
-			};
-                };
-
-
-		epld@5,0 {
-			compatible = "wrs,epld-localbus";
-			#address-cells = <2>;
-			#size-cells = <1>;
-			reg = <0x5 0x0 0x00b10000>;
-			ranges = <
-				0x0 0x0 0x5 0x000000 0x1fff	/* LED */
-				0x1 0x0 0x5 0x100000 0x1fff	/* Switches */
-				0x3 0x0 0x5 0x300000 0x1fff	/* HW Rev. */
-				0xb 0x0	0x5 0xb00000 0x1fff	/* EEPROM */
-			>;
-
-			led@0,0 {
-				compatible = "led";
-				reg = <0x0 0x0 0x1fff>;
-			};
-
-			switches@1,0 {
-				compatible = "switches";
-				reg = <0x1 0x0 0x1fff>;
-			};
-
-			hw-rev@3,0 {
-				compatible = "hw-rev";
-				reg = <0x3 0x0 0x1fff>;
-			};
-
-			eeprom@b,0 {
-				compatible = "eeprom";
-				reg = <0xb 0 0x1fff>;
-			};
-
-		};
-
-		alt-flash@6,0 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			compatible = "intel,JS28F640", "cfi-flash";
-			reg = <0x6 0x0 0x800000>;
-			bank-width = <1>;
-			device-width = <1>;
-			partition@0 {
-				label = "space";
-				/* EF800000 -> EFF9FFFF */
-				reg = <0x00000000 0x007a0000>;
-			};
-			partition@7a0000 {
-				label = "bootloader";
-				/* EFFA0000 -> EFFFFFFF */
-				reg = <0x007a0000 0x00060000>;
-				read-only;
-			};
-		};
-
-
-        };
-};
-
-/include/ "sbc8548-post.dtsi"
diff --git a/arch/powerpc/boot/dts/sbc8548-post.dtsi b/arch/powerpc/boot/dts/sbc8548-post.dtsi
deleted file mode 100644
index 9d848d409408..000000000000
--- a/arch/powerpc/boot/dts/sbc8548-post.dtsi
+++ /dev/null
@@ -1,289 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * SBC8548 Device Tree Source
- *
- * Copyright 2007 Wind River Systems Inc.
- *
- * Paul Gortmaker (see MAINTAINERS for contact information)
- */
-
-/{
-	soc8548@e0000000 {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		device_type = "soc";
-		ranges = <0x00000000 0xe0000000 0x00100000>;
-		bus-frequency = <0>;
-		compatible = "simple-bus";
-
-		ecm-law@0 {
-			compatible = "fsl,ecm-law";
-			reg = <0x0 0x1000>;
-			fsl,num-laws = <10>;
-		};
-
-		ecm@1000 {
-			compatible = "fsl,mpc8548-ecm", "fsl,ecm";
-			reg = <0x1000 0x1000>;
-			interrupts = <17 2>;
-			interrupt-parent = <&mpic>;
-		};
-
-		memory-controller@2000 {
-			compatible = "fsl,mpc8548-memory-controller";
-			reg = <0x2000 0x1000>;
-			interrupt-parent = <&mpic>;
-			interrupts = <0x12 0x2>;
-		};
-
-		L2: l2-cache-controller@20000 {
-			compatible = "fsl,mpc8548-l2-cache-controller";
-			reg = <0x20000 0x1000>;
-			cache-line-size = <0x20>;	// 32 bytes
-			cache-size = <0x80000>;	// L2, 512K
-			interrupt-parent = <&mpic>;
-			interrupts = <0x10 0x2>;
-		};
-
-		i2c@3000 {
-			#address-cells = <1>;
-			#size-cells = <0>;
-			cell-index = <0>;
-			compatible = "fsl-i2c";
-			reg = <0x3000 0x100>;
-			interrupts = <0x2b 0x2>;
-			interrupt-parent = <&mpic>;
-			dfsrr;
-		};
-
-		i2c@3100 {
-			#address-cells = <1>;
-			#size-cells = <0>;
-			cell-index = <1>;
-			compatible = "fsl-i2c";
-			reg = <0x3100 0x100>;
-			interrupts = <0x2b 0x2>;
-			interrupt-parent = <&mpic>;
-			dfsrr;
-		};
-
-		dma@21300 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			compatible = "fsl,mpc8548-dma", "fsl,eloplus-dma";
-			reg = <0x21300 0x4>;
-			ranges = <0x0 0x21100 0x200>;
-			cell-index = <0>;
-			dma-channel@0 {
-				compatible = "fsl,mpc8548-dma-channel",
-						"fsl,eloplus-dma-channel";
-				reg = <0x0 0x80>;
-				cell-index = <0>;
-				interrupt-parent = <&mpic>;
-				interrupts = <20 2>;
-			};
-			dma-channel@80 {
-				compatible = "fsl,mpc8548-dma-channel",
-						"fsl,eloplus-dma-channel";
-				reg = <0x80 0x80>;
-				cell-index = <1>;
-				interrupt-parent = <&mpic>;
-				interrupts = <21 2>;
-			};
-			dma-channel@100 {
-				compatible = "fsl,mpc8548-dma-channel",
-						"fsl,eloplus-dma-channel";
-				reg = <0x100 0x80>;
-				cell-index = <2>;
-				interrupt-parent = <&mpic>;
-				interrupts = <22 2>;
-			};
-			dma-channel@180 {
-				compatible = "fsl,mpc8548-dma-channel",
-						"fsl,eloplus-dma-channel";
-				reg = <0x180 0x80>;
-				cell-index = <3>;
-				interrupt-parent = <&mpic>;
-				interrupts = <23 2>;
-			};
-		};
-
-		enet0: ethernet@24000 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			cell-index = <0>;
-			device_type = "network";
-			model = "eTSEC";
-			compatible = "gianfar";
-			reg = <0x24000 0x1000>;
-			ranges = <0x0 0x24000 0x1000>;
-			local-mac-address = [ 00 00 00 00 00 00 ];
-			interrupts = <0x1d 0x2 0x1e 0x2 0x22 0x2>;
-			interrupt-parent = <&mpic>;
-			tbi-handle = <&tbi0>;
-			phy-handle = <&phy0>;
-
-			mdio@520 {
-				#address-cells = <1>;
-				#size-cells = <0>;
-				compatible = "fsl,gianfar-mdio";
-				reg = <0x520 0x20>;
-
-				phy0: ethernet-phy@19 {
-					interrupt-parent = <&mpic>;
-					interrupts = <0x6 0x1>;
-					reg = <0x19>;
-				};
-				phy1: ethernet-phy@1a {
-					interrupt-parent = <&mpic>;
-					interrupts = <0x7 0x1>;
-					reg = <0x1a>;
-				};
-				tbi0: tbi-phy@11 {
-					reg = <0x11>;
-					device_type = "tbi-phy";
-				};
-			};
-		};
-
-		enet1: ethernet@25000 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			cell-index = <1>;
-			device_type = "network";
-			model = "eTSEC";
-			compatible = "gianfar";
-			reg = <0x25000 0x1000>;
-			ranges = <0x0 0x25000 0x1000>;
-			local-mac-address = [ 00 00 00 00 00 00 ];
-			interrupts = <0x23 0x2 0x24 0x2 0x28 0x2>;
-			interrupt-parent = <&mpic>;
-			tbi-handle = <&tbi1>;
-			phy-handle = <&phy1>;
-
-			mdio@520 {
-				#address-cells = <1>;
-				#size-cells = <0>;
-				compatible = "fsl,gianfar-tbi";
-				reg = <0x520 0x20>;
-
-				tbi1: tbi-phy@11 {
-					reg = <0x11>;
-					device_type = "tbi-phy";
-				};
-			};
-		};
-
-		serial0: serial@4500 {
-			cell-index = <0>;
-			device_type = "serial";
-			compatible = "fsl,ns16550", "ns16550";
-			reg = <0x4500 0x100>;	// reg base, size
-			clock-frequency = <0>;	// should we fill in in uboot?
-			interrupts = <0x2a 0x2>;
-			interrupt-parent = <&mpic>;
-		};
-
-		serial1: serial@4600 {
-			cell-index = <1>;
-			device_type = "serial";
-			compatible = "fsl,ns16550", "ns16550";
-			reg = <0x4600 0x100>;	// reg base, size
-			clock-frequency = <0>;	// should we fill in in uboot?
-			interrupts = <0x2a 0x2>;
-			interrupt-parent = <&mpic>;
-		};
-
-		global-utilities@e0000 {	//global utilities reg
-			compatible = "fsl,mpc8548-guts";
-			reg = <0xe0000 0x1000>;
-			fsl,has-rstcr;
-		};
-
-		crypto@30000 {
-			compatible = "fsl,sec2.1", "fsl,sec2.0";
-			reg = <0x30000 0x10000>;
-			interrupts = <45 2>;
-			interrupt-parent = <&mpic>;
-			fsl,num-channels = <4>;
-			fsl,channel-fifo-len = <24>;
-			fsl,exec-units-mask = <0xfe>;
-			fsl,descriptor-types-mask = <0x12b0ebf>;
-		};
-
-		mpic: pic@40000 {
-			interrupt-controller;
-			#address-cells = <0>;
-			#interrupt-cells = <2>;
-			reg = <0x40000 0x40000>;
-			compatible = "chrp,open-pic";
-			device_type = "open-pic";
-		};
-	};
-
-	pci0: pci@e0008000 {
-		interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
-		interrupt-map = <
-			/* IDSEL 0x01 (PCI-X slot) @66MHz */
-			0x0800 0x0 0x0 0x1 &mpic 0x2 0x1
-			0x0800 0x0 0x0 0x2 &mpic 0x3 0x1
-			0x0800 0x0 0x0 0x3 &mpic 0x4 0x1
-			0x0800 0x0 0x0 0x4 &mpic 0x1 0x1
-
-			/* IDSEL 0x11 (PCI, 3.3V 32bit) @33MHz */
-			0x8800 0x0 0x0 0x1 &mpic 0x2 0x1
-			0x8800 0x0 0x0 0x2 &mpic 0x3 0x1
-			0x8800 0x0 0x0 0x3 &mpic 0x4 0x1
-			0x8800 0x0 0x0 0x4 &mpic 0x1 0x1>;
-
-		interrupt-parent = <&mpic>;
-		interrupts = <0x18 0x2>;
-		bus-range = <0 0>;
-		ranges = <0x02000000 0x0 0x80000000 0x80000000 0x0 0x10000000
-			  0x01000000 0x0 0x00000000 0xe2000000 0x0 0x00800000>;
-		clock-frequency = <66000000>;
-		#interrupt-cells = <1>;
-		#size-cells = <2>;
-		#address-cells = <3>;
-		reg = <0xe0008000 0x1000>;
-		compatible = "fsl,mpc8540-pcix", "fsl,mpc8540-pci";
-		device_type = "pci";
-	};
-
-	pci1: pcie@e000a000 {
-		interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
-		interrupt-map = <
-
-			/* IDSEL 0x0 (PEX) */
-			0x0000 0x0 0x0 0x1 &mpic 0x0 0x1
-			0x0000 0x0 0x0 0x2 &mpic 0x1 0x1
-			0x0000 0x0 0x0 0x3 &mpic 0x2 0x1
-			0x0000 0x0 0x0 0x4 &mpic 0x3 0x1>;
-
-		interrupt-parent = <&mpic>;
-		interrupts = <0x1a 0x2>;
-		bus-range = <0x0 0xff>;
-		ranges = <0x02000000 0x0 0xa0000000 0xa0000000 0x0 0x10000000
-			  0x01000000 0x0 0x00000000 0xe2800000 0x0 0x08000000>;
-		clock-frequency = <33000000>;
-		#interrupt-cells = <1>;
-		#size-cells = <2>;
-		#address-cells = <3>;
-		reg = <0xe000a000 0x1000>;
-		compatible = "fsl,mpc8548-pcie";
-		device_type = "pci";
-		pcie@0 {
-			reg = <0x0 0x0 0x0 0x0 0x0>;
-			#size-cells = <2>;
-			#address-cells = <3>;
-			device_type = "pci";
-			ranges = <0x02000000 0x0 0xa0000000
-				  0x02000000 0x0 0xa0000000
-				  0x0 0x10000000
-
-				  0x01000000 0x0 0x00000000
-				  0x01000000 0x0 0x00000000
-				  0x0 0x00800000>;
-		};
-	};
-};
diff --git a/arch/powerpc/boot/dts/sbc8548-pre.dtsi b/arch/powerpc/boot/dts/sbc8548-pre.dtsi
deleted file mode 100644
index 0e3665fd15d0..000000000000
--- a/arch/powerpc/boot/dts/sbc8548-pre.dtsi
+++ /dev/null
@@ -1,48 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * SBC8548 Device Tree Source
- *
- * Copyright 2007 Wind River Systems Inc.
- *
- * Paul Gortmaker (see MAINTAINERS for contact information)
- */
-
-/{
-	model = "SBC8548";
-	compatible = "SBC8548";
-	#address-cells = <1>;
-	#size-cells = <1>;
-
-	aliases {
-		ethernet0 = &enet0;
-		ethernet1 = &enet1;
-		serial0 = &serial0;
-		serial1 = &serial1;
-		pci0 = &pci0;
-		pci1 = &pci1;
-	};
-
-	cpus {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		PowerPC,8548@0 {
-			device_type = "cpu";
-			reg = <0>;
-			d-cache-line-size = <0x20>;	// 32 bytes
-			i-cache-line-size = <0x20>;	// 32 bytes
-			d-cache-size = <0x8000>;	// L1, 32K
-			i-cache-size = <0x8000>;	// L1, 32K
-			timebase-frequency = <0>;	// From uboot
-			bus-frequency = <0>;
-			clock-frequency = <0>;
-			next-level-cache = <&L2>;
-		};
-	};
-
-	memory {
-		device_type = "memory";
-		reg = <0x00000000 0x10000000>;
-	};
-
-};
diff --git a/arch/powerpc/boot/dts/sbc8548.dts b/arch/powerpc/boot/dts/sbc8548.dts
deleted file mode 100644
index ce0a119f496e..000000000000
--- a/arch/powerpc/boot/dts/sbc8548.dts
+++ /dev/null
@@ -1,106 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * SBC8548 Device Tree Source
- *
- * Copyright 2007 Wind River Systems Inc.
- *
- * Paul Gortmaker (see MAINTAINERS for contact information)
- */
-
-
-/dts-v1/;
-
-/include/ "sbc8548-pre.dtsi"
-
-/{
-	localbus@e0000000 {
-		#address-cells = <2>;
-		#size-cells = <1>;
-		compatible = "simple-bus";
-		reg = <0xe0000000 0x5000>;
-		interrupt-parent = <&mpic>;
-
-		ranges = <0x0 0x0 0xff800000 0x00800000		/*8MB Flash*/
-			  0x3 0x0 0xf0000000 0x04000000		/*64MB SDRAM*/
-			  0x4 0x0 0xf4000000 0x04000000 	/*64MB SDRAM*/
-			  0x5 0x0 0xf8000000 0x00b10000		/* EPLD */
-			  0x6 0x0 0xec000000 0x04000000>;	/*64MB Flash*/
-
-
-		flash@0,0 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			compatible = "intel,JS28F640", "cfi-flash";
-			reg = <0x0 0x0 0x800000>;
-			bank-width = <1>;
-			device-width = <1>;
-			partition@0 {
-				label = "space";
-				/* FF800000 -> FFF9FFFF */
-				reg = <0x00000000 0x007a0000>;
-			};
-			partition@7a0000 {
-				label = "bootloader";
-				/* FFFA0000 -> FFFFFFFF */
-				reg = <0x007a0000 0x00060000>;
-				read-only;
-			};
-		};
-
-		epld@5,0 {
-			compatible = "wrs,epld-localbus";
-			#address-cells = <2>;
-			#size-cells = <1>;
-			reg = <0x5 0x0 0x00b10000>;
-			ranges = <
-				0x0 0x0 0x5 0x000000 0x1fff	/* LED */
-				0x1 0x0 0x5 0x100000 0x1fff	/* Switches */
-				0x3 0x0 0x5 0x300000 0x1fff	/* HW Rev. */
-				0xb 0x0	0x5 0xb00000 0x1fff	/* EEPROM */
-			>;
-
-			led@0,0 {
-				compatible = "led";
-				reg = <0x0 0x0 0x1fff>;
-			};
-
-			switches@1,0 {
-				compatible = "switches";
-				reg = <0x1 0x0 0x1fff>;
-			};
-
-			hw-rev@3,0 {
-				compatible = "hw-rev";
-				reg = <0x3 0x0 0x1fff>;
-			};
-
-			eeprom@b,0 {
-				compatible = "eeprom";
-				reg = <0xb 0 0x1fff>;
-			};
-
-		};
-
-		alt-flash@6,0 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			reg = <0x6 0x0 0x04000000>;
-			compatible = "intel,JS28F128", "cfi-flash";
-			bank-width = <4>;
-			device-width = <1>;
-			partition@0 {
-				label = "space";
-				/* EC000000 -> EFEFFFFF */
-				reg = <0x00000000 0x03f00000>;
-			};
-			partition@3f00000 {
-				label = "bootloader";
-				/* EFF00000 -> EFFFFFFF */
-				reg = <0x03f00000 0x00100000>;
-				read-only;
-			};
-                };
-        };
-};
-
-/include/ "sbc8548-post.dtsi"
diff --git a/arch/powerpc/boot/dts/wii.dts b/arch/powerpc/boot/dts/wii.dts
index aaa381da1906..e9c945b123c6 100644
--- a/arch/powerpc/boot/dts/wii.dts
+++ b/arch/powerpc/boot/dts/wii.dts
@@ -216,7 +216,18 @@
 
 		control@d800100 {
 			compatible = "nintendo,hollywood-control";
-			reg = <0x0d800100 0x300>;
+			/*
+			 * Both the address and length are wrong, according to
+			 * Wiibrew this should be <0x0d800000 0x400>, but it
+			 * requires refactoring the PIC1, GPIO and OTP nodes
+			 * before changing that.
+			 */
+			reg = <0x0d800100 0xa0>;
+		};
+
+		otp@d8001ec {
+			compatible = "nintendo,hollywood-otp";
+			reg = <0x0d8001ec 0x8>;
 		};
 
 		disk@d806000 {
diff --git a/arch/powerpc/boot/install.sh b/arch/powerpc/boot/install.sh
index b6a256bc96ee..14473150ddb4 100644
--- a/arch/powerpc/boot/install.sh
+++ b/arch/powerpc/boot/install.sh
@@ -15,12 +15,25 @@
 #   $2 - kernel image file
 #   $3 - kernel map file
 #   $4 - default install path (blank if root directory)
-#   $5 and more - kernel boot files; zImage*, uImage, cuImage.*, etc.
 #
 
 # Bail with error code if anything goes wrong
 set -e
 
+verify () {
+	if [ ! -f "$1" ]; then
+		echo ""                                                   1>&2
+		echo " *** Missing file: $1"                              1>&2
+		echo ' *** You need to run "make" before "make install".' 1>&2
+		echo ""                                                   1>&2
+		exit 1
+	fi
+}
+
+# Make sure the files actually exist
+verify "$2"
+verify "$3"
+
 # User may have a custom install script
 
 if [ -x ~/bin/${INSTALLKERNEL} ]; then exec ~/bin/${INSTALLKERNEL} "$@"; fi
@@ -41,15 +54,3 @@ fi
 
 cat $2 > $4/$image_name
 cp $3 $4/System.map
-
-# Copy all the bootable image files
-path=$4
-shift 4
-while [ $# -ne 0 ]; do
-	image_name=`basename $1`
-	if [ -f $path/$image_name ]; then
-		mv $path/$image_name $path/$image_name.old
-	fi
-	cat $1 > $path/$image_name
-	shift
-done;
diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper
index 1f4676bab786..1cd82564c996 100755
--- a/arch/powerpc/boot/wrapper
+++ b/arch/powerpc/boot/wrapper
@@ -298,7 +298,7 @@ cuboot*)
     *-tqm8541|*-mpc8560*|*-tqm8560|*-tqm8555|*-ksi8560*)
         platformo=$object/cuboot-85xx-cpm2.o
         ;;
-    *-mpc85*|*-tqm85*|*-sbc85*)
+    *-mpc85*|*-tqm85*)
         platformo=$object/cuboot-85xx.o
         ;;
     *-amigaone)
diff --git a/arch/powerpc/configs/85xx/sbc8548_defconfig b/arch/powerpc/configs/85xx/sbc8548_defconfig
deleted file mode 100644
index 258881727119..000000000000
--- a/arch/powerpc/configs/85xx/sbc8548_defconfig
+++ /dev/null
@@ -1,50 +0,0 @@
-CONFIG_PPC_85xx=y
-CONFIG_SYSVIPC=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
-CONFIG_SLAB=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_SBC8548=y
-CONFIG_GEN_RTC=y
-CONFIG_BINFMT_MISC=y
-CONFIG_MATH_EMULATION=y
-# CONFIG_SECCOMP is not set
-CONFIG_PCI=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-CONFIG_SYN_COOKIES=y
-# CONFIG_IPV6 is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_ADV_OPTIONS=y
-CONFIG_MTD_CFI_GEOMETRY=y
-CONFIG_MTD_CFI_I4=y
-CONFIG_MTD_CFI_INTELEXT=y
-CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_NETDEVICES=y
-CONFIG_GIANFAR=y
-CONFIG_BROADCOM_PHY=y
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-# CONFIG_USB_SUPPORT is not set
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
diff --git a/arch/powerpc/configs/microwatt_defconfig b/arch/powerpc/configs/microwatt_defconfig
index a08b739123da..9465209b8c5b 100644
--- a/arch/powerpc/configs/microwatt_defconfig
+++ b/arch/powerpc/configs/microwatt_defconfig
@@ -5,6 +5,7 @@ CONFIG_PREEMPT_VOLUNTARY=y
 CONFIG_TICK_CPU_ACCOUNTING=y
 CONFIG_LOG_BUF_SHIFT=16
 CONFIG_PRINTK_SAFE_LOG_BUF_SHIFT=12
+CONFIG_CGROUPS=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_KALLSYMS_ALL=y
@@ -53,10 +54,12 @@ CONFIG_MTD_SPI_NOR=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_NETDEVICES=y
+CONFIG_LITEX_LITEETH=y
 # CONFIG_WLAN is not set
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
+# CONFIG_LEGACY_PTYS is not set
 CONFIG_SERIAL_8250=y
 # CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set
 CONFIG_SERIAL_8250_CONSOLE=y
@@ -76,8 +79,10 @@ CONFIG_SPI_SPIDEV=y
 CONFIG_EXT4_FS=y
 # CONFIG_FILE_LOCKING is not set
 # CONFIG_DNOTIFY is not set
-# CONFIG_INOTIFY_USER is not set
+CONFIG_AUTOFS_FS=y
+CONFIG_TMPFS=y
 # CONFIG_MISC_FILESYSTEMS is not set
+CONFIG_CRYPTO_SHA256=y
 # CONFIG_CRYPTO_HW is not set
 # CONFIG_XZ_DEC_X86 is not set
 # CONFIG_XZ_DEC_IA64 is not set
diff --git a/arch/powerpc/configs/mpc85xx_base.config b/arch/powerpc/configs/mpc85xx_base.config
index b1593fe6f70b..85907b776908 100644
--- a/arch/powerpc/configs/mpc85xx_base.config
+++ b/arch/powerpc/configs/mpc85xx_base.config
@@ -13,7 +13,6 @@ 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
 CONFIG_TQM8540=y
diff --git a/arch/powerpc/configs/mpc86xx_base.config b/arch/powerpc/configs/mpc86xx_base.config
index 67bd1fa036ee..588870e6af3b 100644
--- a/arch/powerpc/configs/mpc86xx_base.config
+++ b/arch/powerpc/configs/mpc86xx_base.config
@@ -1,6 +1,5 @@
 CONFIG_PPC_86xx=y
 CONFIG_MPC8641_HPCN=y
-CONFIG_SBC8641D=y
 CONFIG_MPC8610_HPCD=y
 CONFIG_GEF_PPC9A=y
 CONFIG_GEF_SBC310=y
diff --git a/arch/powerpc/configs/mpc885_ads_defconfig b/arch/powerpc/configs/mpc885_ads_defconfig
index d21f266cea9a..c74dc76b1d0d 100644
--- a/arch/powerpc/configs/mpc885_ads_defconfig
+++ b/arch/powerpc/configs/mpc885_ads_defconfig
@@ -1,19 +1,30 @@
-CONFIG_PPC_8xx=y
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
+CONFIG_BPF_JIT=y
+CONFIG_VIRT_CPU_ACCOUNTING_NATIVE=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_EXPERT=y
 # CONFIG_ELF_CORE is not set
 # CONFIG_BASE_FULL is not set
 # CONFIG_FUTEX is not set
+CONFIG_PERF_EVENTS=y
 # CONFIG_VM_EVENT_COUNTERS is not set
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_PARTITION_ADVANCED=y
+CONFIG_PPC_8xx=y
+CONFIG_8xx_GPIO=y
+CONFIG_SMC_UCODE_PATCH=y
+CONFIG_PIN_TLB=y
 CONFIG_GEN_RTC=y
 CONFIG_HZ_100=y
+CONFIG_MATH_EMULATION=y
+CONFIG_PPC_16K_PAGES=y
+CONFIG_ADVANCED_OPTIONS=y
 # CONFIG_SECCOMP is not set
+CONFIG_STRICT_KERNEL_RWX=y
+CONFIG_MODULES=y
+# CONFIG_BLK_DEV_BSG is not set
+CONFIG_PARTITION_ADVANCED=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
@@ -21,7 +32,6 @@ CONFIG_INET=y
 CONFIG_IP_MULTICAST=y
 CONFIG_IP_PNP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_IPV6 is not set
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
 CONFIG_MTD_BLOCK=y
@@ -34,6 +44,7 @@ CONFIG_MTD_CFI_GEOMETRY=y
 # CONFIG_MTD_CFI_I2 is not set
 CONFIG_MTD_CFI_I4=y
 CONFIG_MTD_CFI_AMDSTD=y
+CONFIG_MTD_PHYSMAP=y
 CONFIG_MTD_PHYSMAP_OF=y
 # CONFIG_BLK_DEV is not set
 CONFIG_NETDEVICES=y
@@ -46,39 +57,25 @@ CONFIG_DAVICOM_PHY=y
 # CONFIG_LEGACY_PTYS is not set
 CONFIG_SERIAL_CPM=y
 CONFIG_SERIAL_CPM_CONSOLE=y
+CONFIG_SPI=y
+CONFIG_SPI_FSL_SPI=y
 # CONFIG_HWMON is not set
+CONFIG_WATCHDOG=y
+CONFIG_8xxx_WDT=y
 # CONFIG_USB_SUPPORT is not set
 # CONFIG_DNOTIFY is not set
 CONFIG_TMPFS=y
 CONFIG_CRAMFS=y
 CONFIG_NFS_FS=y
 CONFIG_ROOT_NFS=y
+CONFIG_CRYPTO=y
+CONFIG_CRYPTO_DEV_TALITOS=y
 CONFIG_CRC32_SLICEBY4=y
 CONFIG_DEBUG_INFO=y
 CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_PPC_16K_PAGES=y
-CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_FS=y
-CONFIG_PPC_PTDUMP=y
-CONFIG_MODULES=y
-CONFIG_SPI=y
-CONFIG_SPI_FSL_SPI=y
-CONFIG_CRYPTO=y
-CONFIG_CRYPTO_DEV_TALITOS=y
-CONFIG_8xx_GPIO=y
-CONFIG_WATCHDOG=y
-CONFIG_8xxx_WDT=y
-CONFIG_SMC_UCODE_PATCH=y
-CONFIG_ADVANCED_OPTIONS=y
-CONFIG_PIN_TLB=y
-CONFIG_PERF_EVENTS=y
-CONFIG_MATH_EMULATION=y
-CONFIG_VIRT_CPU_ACCOUNTING_NATIVE=y
-CONFIG_STRICT_KERNEL_RWX=y
-CONFIG_IPV6=y
-CONFIG_BPF_JIT=y
 CONFIG_DEBUG_VM_PGTABLE=y
+CONFIG_DETECT_HUNG_TASK=y
 CONFIG_BDI_SWITCH=y
 CONFIG_PPC_EARLY_DEBUG=y
-CONFIG_PPC_EARLY_DEBUG_CPM_ADDR=0xff002008
+CONFIG_PPC_PTDUMP=y
diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig
index ee09f7bb6ea9..6697c5e6682f 100644
--- a/arch/powerpc/configs/ppc6xx_defconfig
+++ b/arch/powerpc/configs/ppc6xx_defconfig
@@ -55,7 +55,6 @@ CONFIG_MPC837x_RDB=y
 CONFIG_ASP834x=y
 CONFIG_PPC_86xx=y
 CONFIG_MPC8641_HPCN=y
-CONFIG_SBC8641D=y
 CONFIG_MPC8610_HPCD=y
 CONFIG_GEF_SBC610=y
 CONFIG_CPU_FREQ=y
diff --git a/arch/powerpc/configs/wii_defconfig b/arch/powerpc/configs/wii_defconfig
index 379c171f3ddd..a0c45bf2bfb1 100644
--- a/arch/powerpc/configs/wii_defconfig
+++ b/arch/powerpc/configs/wii_defconfig
@@ -99,6 +99,7 @@ CONFIG_LEDS_TRIGGER_HEARTBEAT=y
 CONFIG_LEDS_TRIGGER_PANIC=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=y
+CONFIG_NVMEM_NINTENDO_OTP=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT4_FS=y
 CONFIG_FUSE_FS=m
diff --git a/arch/powerpc/include/asm/asm-compat.h b/arch/powerpc/include/asm/asm-compat.h
index 19b70c5b5f18..2b736d9fbb1b 100644
--- a/arch/powerpc/include/asm/asm-compat.h
+++ b/arch/powerpc/include/asm/asm-compat.h
@@ -17,7 +17,7 @@
 #define PPC_LONG	stringify_in_c(.8byte)
 #define PPC_LONG_ALIGN	stringify_in_c(.balign 8)
 #define PPC_TLNEI	stringify_in_c(tdnei)
-#define PPC_LLARX(t, a, b, eh)	PPC_LDARX(t, a, b, eh)
+#define PPC_LLARX	stringify_in_c(ldarx)
 #define PPC_STLCX	stringify_in_c(stdcx.)
 #define PPC_CNTLZL	stringify_in_c(cntlzd)
 #define PPC_MTOCRF(FXM, RS) MTOCRF((FXM), RS)
@@ -50,7 +50,7 @@
 #define PPC_LONG	stringify_in_c(.long)
 #define PPC_LONG_ALIGN	stringify_in_c(.balign 4)
 #define PPC_TLNEI	stringify_in_c(twnei)
-#define PPC_LLARX(t, a, b, eh)	PPC_LWARX(t, a, b, eh)
+#define PPC_LLARX	stringify_in_c(lwarx)
 #define PPC_STLCX	stringify_in_c(stwcx.)
 #define PPC_CNTLZL	stringify_in_c(cntlzw)
 #define PPC_MTOCRF	stringify_in_c(mtcrf)
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index a1732a79e92a..6a53ef178bfd 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -207,7 +207,7 @@ arch_atomic_try_cmpxchg_lock(atomic_t *v, int *old, int new)
 	int r, o = *old;
 
 	__asm__ __volatile__ (
-"1:\t"	PPC_LWARX(%0,0,%2,1) "	# atomic_try_cmpxchg_acquire	\n"
+"1:	lwarx	%0,0,%2,%5	# atomic_try_cmpxchg_acquire		\n"
 "	cmpw	0,%0,%3							\n"
 "	bne-	2f							\n"
 "	stwcx.	%4,0,%2							\n"
@@ -215,7 +215,7 @@ arch_atomic_try_cmpxchg_lock(atomic_t *v, int *old, int new)
 "\t"	PPC_ACQUIRE_BARRIER "						\n"
 "2:									\n"
 	: "=&r" (r), "+m" (v->counter)
-	: "r" (&v->counter), "r" (o), "r" (new)
+	: "r" (&v->counter), "r" (o), "r" (new), "i" (IS_ENABLED(CONFIG_PPC64) ? 1 : 0)
 	: "cr0", "memory");
 
 	if (unlikely(r != o))
diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h
index 299ab33505a6..11847b6a244e 100644
--- a/arch/powerpc/include/asm/bitops.h
+++ b/arch/powerpc/include/asm/bitops.h
@@ -70,7 +70,7 @@ static inline void fn(unsigned long mask,	\
 	unsigned long *p = (unsigned long *)_p;	\
 	__asm__ __volatile__ (			\
 	prefix					\
-"1:"	PPC_LLARX(%0,0,%3,0) "\n"		\
+"1:"	PPC_LLARX "%0,0,%3,0\n"			\
 	stringify_in_c(op) "%0,%0,%2\n"		\
 	PPC_STLCX "%0,0,%3\n"			\
 	"bne- 1b\n"				\
@@ -115,13 +115,13 @@ static inline unsigned long fn(			\
 	unsigned long *p = (unsigned long *)_p;		\
 	__asm__ __volatile__ (				\
 	prefix						\
-"1:"	PPC_LLARX(%0,0,%3,eh) "\n"			\
+"1:"	PPC_LLARX "%0,0,%3,%4\n"			\
 	stringify_in_c(op) "%1,%0,%2\n"			\
 	PPC_STLCX "%1,0,%3\n"				\
 	"bne- 1b\n"					\
 	postfix						\
 	: "=&r" (old), "=&r" (t)			\
-	: "r" (mask), "r" (p)				\
+	: "r" (mask), "r" (p), "i" (IS_ENABLED(CONFIG_PPC64) ? eh : 0)	\
 	: "cc", "memory");				\
 	return (old & mask);				\
 }
@@ -170,7 +170,7 @@ clear_bit_unlock_return_word(int nr, volatile unsigned long *addr)
 
 	__asm__ __volatile__ (
 	PPC_RELEASE_BARRIER
-"1:"	PPC_LLARX(%0,0,%3,0) "\n"
+"1:"	PPC_LLARX "%0,0,%3,0\n"
 	"andc %1,%0,%2\n"
 	PPC_STLCX "%1,0,%3\n"
 	"bne- 1b\n"
diff --git a/arch/powerpc/include/asm/book3s/64/kup.h b/arch/powerpc/include/asm/book3s/64/kup.h
index a1cc73a88710..170339969b7c 100644
--- a/arch/powerpc/include/asm/book3s/64/kup.h
+++ b/arch/powerpc/include/asm/book3s/64/kup.h
@@ -90,7 +90,7 @@
 	/* Prevent access to userspace using any key values */
 	LOAD_REG_IMMEDIATE(\gpr2, AMR_KUAP_BLOCKED)
 999:	tdne	\gpr1, \gpr2
-	EMIT_BUG_ENTRY 999b, __FILE__, __LINE__, (BUGFLAG_WARNING | BUGFLAG_ONCE)
+	EMIT_WARN_ENTRY 999b, __FILE__, __LINE__, (BUGFLAG_WARNING | BUGFLAG_ONCE)
 	END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_BOOK3S_KUAP, 67)
 #endif
 .endm
diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h
index 0b2162890d8b..02c08d1492f8 100644
--- a/arch/powerpc/include/asm/bug.h
+++ b/arch/powerpc/include/asm/bug.h
@@ -4,6 +4,7 @@
 #ifdef __KERNEL__
 
 #include <asm/asm-compat.h>
+#include <asm/extable.h>
 
 #ifdef CONFIG_BUG
 
@@ -30,6 +31,11 @@
 .endm
 #endif /* verbose */
 
+.macro EMIT_WARN_ENTRY addr,file,line,flags
+	EX_TABLE(\addr,\addr+4)
+	EMIT_BUG_ENTRY \addr,\file,\line,\flags
+.endm
+
 #else /* !__ASSEMBLY__ */
 /* _EMIT_BUG_ENTRY expects args %0,%1,%2,%3 to be FILE, LINE, flags and
    sizeof(struct bug_entry), respectively */
@@ -58,6 +64,16 @@
 		  "i" (sizeof(struct bug_entry)),	\
 		  ##__VA_ARGS__)
 
+#define WARN_ENTRY(insn, flags, label, ...)		\
+	asm_volatile_goto(				\
+		"1:	" insn "\n"			\
+		EX_TABLE(1b, %l[label])			\
+		_EMIT_BUG_ENTRY				\
+		: : "i" (__FILE__), "i" (__LINE__),	\
+		  "i" (flags),				\
+		  "i" (sizeof(struct bug_entry)),	\
+		  ##__VA_ARGS__ : : label)
+
 /*
  * BUG_ON() and WARN_ON() do their best to cooperate with compile-time
  * optimisations. However depending on the complexity of the condition
@@ -68,7 +84,19 @@
 	BUG_ENTRY("twi 31, 0, 0", 0);				\
 	unreachable();						\
 } while (0)
+#define HAVE_ARCH_BUG
 
+#define __WARN_FLAGS(flags) do {				\
+	__label__ __label_warn_on;				\
+								\
+	WARN_ENTRY("twi 31, 0, 0", BUGFLAG_WARNING | (flags), __label_warn_on); \
+	unreachable();						\
+								\
+__label_warn_on:						\
+	break;							\
+} while (0)
+
+#ifdef CONFIG_PPC64
 #define BUG_ON(x) do {						\
 	if (__builtin_constant_p(x)) {				\
 		if (x)						\
@@ -78,31 +106,43 @@
 	}							\
 } while (0)
 
-#define __WARN_FLAGS(flags) BUG_ENTRY("twi 31, 0, 0", BUGFLAG_WARNING | (flags))
-
 #define WARN_ON(x) ({						\
-	int __ret_warn_on = !!(x);				\
-	if (__builtin_constant_p(__ret_warn_on)) {		\
-		if (__ret_warn_on)				\
+	bool __ret_warn_on = false;				\
+	do {							\
+		if (__builtin_constant_p((x))) {		\
+			if (!(x)) 				\
+				break; 				\
 			__WARN();				\
-	} else {						\
-		BUG_ENTRY(PPC_TLNEI " %4, 0",			\
-			  BUGFLAG_WARNING | BUGFLAG_TAINT(TAINT_WARN),	\
-			  "r" (__ret_warn_on));	\
-	}							\
+			__ret_warn_on = true;			\
+		} else {					\
+			__label__ __label_warn_on;		\
+								\
+			WARN_ENTRY(PPC_TLNEI " %4, 0",		\
+				   BUGFLAG_WARNING | BUGFLAG_TAINT(TAINT_WARN),	\
+				   __label_warn_on,		\
+				   "r" ((__force long)(x)));	\
+			break;					\
+__label_warn_on:						\
+			__ret_warn_on = true;			\
+		}						\
+	} while (0);						\
 	unlikely(__ret_warn_on);				\
 })
 
-#define HAVE_ARCH_BUG
 #define HAVE_ARCH_BUG_ON
 #define HAVE_ARCH_WARN_ON
+#endif
+
 #endif /* __ASSEMBLY __ */
 #else
 #ifdef __ASSEMBLY__
 .macro EMIT_BUG_ENTRY addr,file,line,flags
 .endm
+.macro EMIT_WARN_ENTRY addr,file,line,flags
+.endm
 #else /* !__ASSEMBLY__ */
 #define _EMIT_BUG_ENTRY
+#define _EMIT_WARN_ENTRY
 #endif
 #endif /* CONFIG_BUG */
 
diff --git a/arch/powerpc/include/asm/debugfs.h b/arch/powerpc/include/asm/debugfs.h
deleted file mode 100644
index 2c5c48571d75..000000000000
--- a/arch/powerpc/include/asm/debugfs.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-#ifndef _ASM_POWERPC_DEBUGFS_H
-#define _ASM_POWERPC_DEBUGFS_H
-
-/*
- * Copyright 2017, Michael Ellerman, IBM Corporation.
- */
-
-#include <linux/debugfs.h>
-
-extern struct dentry *powerpc_debugfs_root;
-
-#endif /* _ASM_POWERPC_DEBUGFS_H */
diff --git a/arch/powerpc/include/asm/drmem.h b/arch/powerpc/include/asm/drmem.h
index bf2402fed3e0..4265d5e95c2c 100644
--- a/arch/powerpc/include/asm/drmem.h
+++ b/arch/powerpc/include/asm/drmem.h
@@ -111,6 +111,7 @@ int drmem_update_dt(void);
 int __init
 walk_drmem_lmbs_early(unsigned long node, void *data,
 		      int (*func)(struct drmem_lmb *, const __be32 **, void *));
+void drmem_update_lmbs(struct property *prop);
 #endif
 
 static inline void invalidate_lmb_associativity_index(struct drmem_lmb *lmb)
diff --git a/arch/powerpc/include/asm/extable.h b/arch/powerpc/include/asm/extable.h
index eb91b2d2935a..26ce2e5c0fa8 100644
--- a/arch/powerpc/include/asm/extable.h
+++ b/arch/powerpc/include/asm/extable.h
@@ -17,6 +17,8 @@
 
 #define ARCH_HAS_RELATIVE_EXTABLE
 
+#ifndef __ASSEMBLY__
+
 struct exception_table_entry {
 	int insn;
 	int fixup;
@@ -28,3 +30,15 @@ static inline unsigned long extable_fixup(const struct exception_table_entry *x)
 }
 
 #endif
+
+/*
+ * Helper macro for exception table entries
+ */
+#define EX_TABLE(_fault, _target)		\
+	stringify_in_c(.section __ex_table,"a";)\
+	stringify_in_c(.balign 4;)		\
+	stringify_in_c(.long (_fault) - . ;)	\
+	stringify_in_c(.long (_target) - . ;)	\
+	stringify_in_c(.previous)
+
+#endif
diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h
index 7604673787d6..97a3bd9ffeb9 100644
--- a/arch/powerpc/include/asm/firmware.h
+++ b/arch/powerpc/include/asm/firmware.h
@@ -44,7 +44,7 @@
 #define FW_FEATURE_OPAL		ASM_CONST(0x0000000010000000)
 #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_FORM1_AFFINITY ASM_CONST(0x0000000100000000)
 #define FW_FEATURE_PRRN		ASM_CONST(0x0000000200000000)
 #define FW_FEATURE_DRMEM_V2	ASM_CONST(0x0000000400000000)
 #define FW_FEATURE_DRC_INFO	ASM_CONST(0x0000000800000000)
@@ -53,6 +53,7 @@
 #define FW_FEATURE_ULTRAVISOR	ASM_CONST(0x0000004000000000)
 #define FW_FEATURE_STUFF_TCE	ASM_CONST(0x0000008000000000)
 #define FW_FEATURE_RPT_INVALIDATE ASM_CONST(0x0000010000000000)
+#define FW_FEATURE_FORM2_AFFINITY ASM_CONST(0x0000020000000000)
 
 #ifndef __ASSEMBLY__
 
@@ -69,11 +70,11 @@ enum {
 		FW_FEATURE_SPLPAR | FW_FEATURE_LPAR |
 		FW_FEATURE_CMO | FW_FEATURE_VPHN | FW_FEATURE_XCMO |
 		FW_FEATURE_SET_MODE | FW_FEATURE_BEST_ENERGY |
-		FW_FEATURE_TYPE1_AFFINITY | FW_FEATURE_PRRN |
+		FW_FEATURE_FORM1_AFFINITY | FW_FEATURE_PRRN |
 		FW_FEATURE_HPT_RESIZE | FW_FEATURE_DRMEM_V2 |
 		FW_FEATURE_DRC_INFO | FW_FEATURE_BLOCK_REMOVE |
 		FW_FEATURE_PAPR_SCM | FW_FEATURE_ULTRAVISOR |
-		FW_FEATURE_RPT_INVALIDATE,
+		FW_FEATURE_RPT_INVALIDATE | FW_FEATURE_FORM2_AFFINITY,
 	FW_FEATURE_PSERIES_ALWAYS = 0,
 	FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL | FW_FEATURE_ULTRAVISOR,
 	FW_FEATURE_POWERNV_ALWAYS = 0,
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index deef7c94d7b6..bf3b84128525 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -154,6 +154,7 @@ extern int iommu_tce_table_put(struct iommu_table *tbl);
  */
 extern struct iommu_table *iommu_init_table(struct iommu_table *tbl,
 		int nid, unsigned long res_start, unsigned long res_end);
+bool iommu_table_in_use(struct iommu_table *tbl);
 
 #define IOMMU_TABLE_GROUP_MAX_TABLES	2
 
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index eaf3a562bf1e..19b6942c6969 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -39,6 +39,7 @@ struct kvm_nested_guest {
 	pgd_t *shadow_pgtable;		/* our page table for this guest */
 	u64 l1_gr_to_hr;		/* L1's addr of part'n-scoped table */
 	u64 process_table;		/* process table entry for this guest */
+	u64 hfscr;			/* HFSCR that the L1 requested for this nested guest */
 	long refcnt;			/* number of pointers to this struct */
 	struct mutex tlb_lock;		/* serialize page faults and tlbies */
 	struct kvm_nested_guest *next;
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 9f52f282b1aa..a779f7849cfb 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -811,6 +811,8 @@ struct kvm_vcpu_arch {
 
 	u32 online;
 
+	u64 hfscr_permitted;	/* A mask of permitted HFSCR facilities */
+
 	/* For support of nested guests */
 	struct kvm_nested_guest *nested;
 	u32 nested_vcpu_id;
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 2d88944f9f34..671fbd1a765e 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -664,9 +664,9 @@ extern int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 				    struct kvm_vcpu *vcpu, u32 cpu);
 extern void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu);
 extern int kvmppc_xive_set_mapped(struct kvm *kvm, unsigned long guest_irq,
-				  struct irq_desc *host_desc);
+				  unsigned long host_irq);
 extern int kvmppc_xive_clr_mapped(struct kvm *kvm, unsigned long guest_irq,
-				  struct irq_desc *host_desc);
+				  unsigned long host_irq);
 extern u64 kvmppc_xive_get_icp(struct kvm_vcpu *vcpu);
 extern int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval);
 
diff --git a/arch/powerpc/include/asm/membarrier.h b/arch/powerpc/include/asm/membarrier.h
index 6e20bb5c74ea..de7f79157918 100644
--- a/arch/powerpc/include/asm/membarrier.h
+++ b/arch/powerpc/include/asm/membarrier.h
@@ -12,7 +12,8 @@ static inline void membarrier_arch_switch_mm(struct mm_struct *prev,
 	 * when switching from userspace to kernel is not needed after
 	 * store to rq->curr.
 	 */
-	if (likely(!(atomic_read(&next->membarrier_state) &
+	if (IS_ENABLED(CONFIG_SMP) &&
+	    likely(!(atomic_read(&next->membarrier_state) &
 		     (MEMBARRIER_STATE_PRIVATE_EXPEDITED |
 		      MEMBARRIER_STATE_GLOBAL_EXPEDITED)) || !prev))
 		return;
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index 27016b98ecb2..8abe8e42e045 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -324,7 +324,7 @@ static inline void assert_pte_locked(struct mm_struct *mm, unsigned long addr)
 }
 #endif /* !CONFIG_DEBUG_VM */
 
-static inline bool radix_enabled(void)
+static __always_inline bool radix_enabled(void)
 {
 	return mmu_has_feature(MMU_FTR_TYPE_RADIX);
 }
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 74424c14515c..90f488fa4c17 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -126,6 +126,11 @@ struct pci_controller {
 #endif	/* CONFIG_PPC64 */
 
 	void *private_data;
+
+	/* IRQ domain hierarchy */
+	struct irq_domain	*dev_domain;
+	struct irq_domain	*msi_domain;
+	struct fwnode_handle	*fwnode;
 };
 
 /* These are used for config access before all the PCI probing
diff --git a/arch/powerpc/include/asm/pmc.h b/arch/powerpc/include/asm/pmc.h
index c6bbe9778d3c..3c09109e708e 100644
--- a/arch/powerpc/include/asm/pmc.h
+++ b/arch/powerpc/include/asm/pmc.h
@@ -34,6 +34,13 @@ static inline void ppc_set_pmu_inuse(int inuse)
 #endif
 }
 
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+static inline int ppc_get_pmu_inuse(void)
+{
+	return get_paca()->pmcregs_in_use;
+}
+#endif
+
 extern void power4_enable_pmcs(void);
 
 #else /* CONFIG_PPC64 */
diff --git a/arch/powerpc/include/asm/pnv-pci.h b/arch/powerpc/include/asm/pnv-pci.h
index d0ee0ede5767..b3f480799352 100644
--- a/arch/powerpc/include/asm/pnv-pci.h
+++ b/arch/powerpc/include/asm/pnv-pci.h
@@ -33,7 +33,7 @@ int pnv_cxl_alloc_hwirqs(struct pci_dev *dev, int num);
 void pnv_cxl_release_hwirqs(struct pci_dev *dev, int hwirq, int num);
 int pnv_cxl_get_irq_count(struct pci_dev *dev);
 struct device_node *pnv_pci_get_phb_node(struct pci_dev *dev);
-int64_t pnv_opal_pci_msi_eoi(struct irq_chip *chip, unsigned int hw_irq);
+int64_t pnv_opal_pci_msi_eoi(struct irq_data *d);
 bool is_pnv_opal_msi(struct irq_chip *chip);
 
 #ifdef CONFIG_CXL_BASE
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index bede76dd3db7..baea657bc868 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -576,8 +576,6 @@
 #define	PPC_DIVDE(t, a, b)	stringify_in_c(.long PPC_RAW_DIVDE(t, a, b))
 #define	PPC_DIVDEU(t, a, b)	stringify_in_c(.long PPC_RAW_DIVDEU(t, a, b))
 #define PPC_LQARX(t, a, b, eh)	stringify_in_c(.long PPC_RAW_LQARX(t, a, b, eh))
-#define PPC_LDARX(t, a, b, eh)	stringify_in_c(.long PPC_RAW_LDARX(t, a, b, eh))
-#define PPC_LWARX(t, a, b, eh)	stringify_in_c(.long PPC_RAW_LWARX(t, a, b, eh))
 #define PPC_STQCX(t, a, b)	stringify_in_c(.long PPC_RAW_STQCX(t, a, b))
 #define PPC_MADDHD(t, a, b, c)	stringify_in_c(.long PPC_RAW_MADDHD(t, a, b, c))
 #define PPC_MADDHDU(t, a, b, c)	stringify_in_c(.long PPC_RAW_MADDHDU(t, a, b, c))
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 116c1519728a..1c538a9a11e0 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -10,6 +10,7 @@
 #include <asm/ppc-opcode.h>
 #include <asm/firmware.h>
 #include <asm/feature-fixups.h>
+#include <asm/extable.h>
 
 #ifdef __ASSEMBLY__
 
@@ -259,7 +260,7 @@ n:
 
 /* Be careful, this will clobber the lr register. */
 #define LOAD_REG_ADDR_PIC(reg, name)		\
-	bl	0f;				\
+	bcl	20,31,$+4;			\
 0:	mflr	reg;				\
 	addis	reg,reg,(name - 0b)@ha;		\
 	addi	reg,reg,(name - 0b)@l;
@@ -752,16 +753,6 @@ END_FTR_SECTION_NESTED(CPU_FTR_CELL_TB_BUG, CPU_FTR_CELL_TB_BUG, 96)
 
 #endif /*  __ASSEMBLY__ */
 
-/*
- * Helper macro for exception table entries
- */
-#define EX_TABLE(_fault, _target)		\
-	stringify_in_c(.section __ex_table,"a";)\
-	stringify_in_c(.balign 4;)		\
-	stringify_in_c(.long (_fault) - . ;)	\
-	stringify_in_c(.long (_target) - . ;)	\
-	stringify_in_c(.previous)
-
 #define SOFT_MASK_TABLE(_start, _end)		\
 	stringify_in_c(.section __soft_mask_table,"a";)\
 	stringify_in_c(.balign 8;)		\
diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index 324a13351749..5c80152e8f18 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -147,8 +147,9 @@ extern int of_read_drc_info_cell(struct property **prop,
 #define OV5_MSI			0x0201	/* PCIe/MSI support */
 #define OV5_CMO			0x0480	/* Cooperative Memory Overcommitment */
 #define OV5_XCMO		0x0440	/* Page Coalescing */
-#define OV5_TYPE1_AFFINITY	0x0580	/* Type 1 NUMA affinity */
+#define OV5_FORM1_AFFINITY	0x0580	/* FORM1 NUMA affinity */
 #define OV5_PRRN		0x0540	/* Platform Resource Reassignment */
+#define OV5_FORM2_AFFINITY	0x0520	/* Form2 NUMA affinity */
 #define OV5_HP_EVT		0x0604	/* Hot Plug Event support */
 #define OV5_RESIZE_HPT		0x0601	/* Hash Page Table resizing */
 #define OV5_PFO_HW_RNG		0x1180	/* PFO Random Number Generator */
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index 14422e851494..6e560f035614 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -22,6 +22,7 @@
 #include <linux/err.h>
 #include <uapi/asm/ptrace.h>
 #include <asm/asm-const.h>
+#include <asm/reg.h>
 
 #ifndef __ASSEMBLY__
 struct pt_regs
@@ -43,8 +44,14 @@ struct pt_regs
 			unsigned long mq;
 #endif
 			unsigned long trap;
-			unsigned long dar;
-			unsigned long dsisr;
+			union {
+				unsigned long dar;
+				unsigned long dear;
+			};
+			union {
+				unsigned long dsisr;
+				unsigned long esr;
+			};
 			unsigned long result;
 		};
 	};
@@ -197,11 +204,7 @@ static inline unsigned long frame_pointer(struct pt_regs *regs)
 	return 0;
 }
 
-#ifdef __powerpc64__
-#define user_mode(regs) ((((regs)->msr) >> MSR_PR_LG) & 0x1)
-#else
 #define user_mode(regs) (((regs)->msr & MSR_PR) != 0)
-#endif
 
 #define force_successful_syscall_return()   \
 	do { \
@@ -286,6 +289,28 @@ static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
 	regs->gpr[3] = rc;
 }
 
+static inline bool cpu_has_msr_ri(void)
+{
+	return !IS_ENABLED(CONFIG_BOOKE) && !IS_ENABLED(CONFIG_40x);
+}
+
+static inline bool regs_is_unrecoverable(struct pt_regs *regs)
+{
+	return unlikely(cpu_has_msr_ri() && !(regs->msr & MSR_RI));
+}
+
+static inline void regs_set_recoverable(struct pt_regs *regs)
+{
+	if (cpu_has_msr_ri())
+		regs_set_return_msr(regs, regs->msr | MSR_RI);
+}
+
+static inline void regs_set_unrecoverable(struct pt_regs *regs)
+{
+	if (cpu_has_msr_ri())
+		regs_set_return_msr(regs, regs->msr & ~MSR_RI);
+}
+
 #define arch_has_single_step()	(1)
 #define arch_has_block_step()	(true)
 #define ARCH_HAS_USER_SINGLE_STEP_REPORT
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index be85cf156a1f..e9d27265253b 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -415,6 +415,7 @@
 #define   FSCR_TAR	__MASK(FSCR_TAR_LG)
 #define   FSCR_EBB	__MASK(FSCR_EBB_LG)
 #define   FSCR_DSCR	__MASK(FSCR_DSCR_LG)
+#define   FSCR_INTR_CAUSE (ASM_CONST(0xFF) << 56)	/* interrupt cause */
 #define SPRN_HFSCR	0xbe	/* HV=1 Facility Status & Control Register */
 #define   HFSCR_PREFIX	__MASK(FSCR_PREFIX_LG)
 #define   HFSCR_MSGP	__MASK(FSCR_MSGP_LG)
@@ -426,7 +427,7 @@
 #define   HFSCR_DSCR	__MASK(FSCR_DSCR_LG)
 #define   HFSCR_VECVSX	__MASK(FSCR_VECVSX_LG)
 #define   HFSCR_FP	__MASK(FSCR_FP_LG)
-#define   HFSCR_INTR_CAUSE (ASM_CONST(0xFF) << 56)	/* interrupt cause */
+#define   HFSCR_INTR_CAUSE FSCR_INTR_CAUSE
 #define SPRN_TAR	0x32f	/* Target Address Register */
 #define SPRN_LPCR	0x13E	/* LPAR Control Register */
 #define   LPCR_VPM0		ASM_CONST(0x8000000000000000)
diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h
index 324d7b298ec3..6e4af4492a14 100644
--- a/arch/powerpc/include/asm/sections.h
+++ b/arch/powerpc/include/asm/sections.h
@@ -38,14 +38,6 @@ extern char start_virt_trampolines[];
 extern char end_virt_trampolines[];
 #endif
 
-static inline int in_kernel_text(unsigned long addr)
-{
-	if (addr >= (unsigned long)_stext && addr < (unsigned long)__init_end)
-		return 1;
-
-	return 0;
-}
-
 static inline unsigned long kernel_toc_addr(void)
 {
 	/* Defined by the linker, see vmlinux.lds.S */
diff --git a/arch/powerpc/include/asm/simple_spinlock.h b/arch/powerpc/include/asm/simple_spinlock.h
index 552f325412cc..8985791a2ba5 100644
--- a/arch/powerpc/include/asm/simple_spinlock.h
+++ b/arch/powerpc/include/asm/simple_spinlock.h
@@ -51,7 +51,7 @@ static inline unsigned long __arch_spin_trylock(arch_spinlock_t *lock)
 
 	token = LOCK_TOKEN;
 	__asm__ __volatile__(
-"1:	" PPC_LWARX(%0,0,%2,1) "\n\
+"1:	lwarx		%0,0,%2,1\n\
 	cmpwi		0,%0,0\n\
 	bne-		2f\n\
 	stwcx.		%1,0,%2\n\
@@ -179,7 +179,7 @@ static inline long __arch_read_trylock(arch_rwlock_t *rw)
 	long tmp;
 
 	__asm__ __volatile__(
-"1:	" PPC_LWARX(%0,0,%1,1) "\n"
+"1:	lwarx		%0,0,%1,1\n"
 	__DO_SIGN_EXTEND
 "	addic.		%0,%0,1\n\
 	ble-		2f\n"
@@ -203,7 +203,7 @@ static inline long __arch_write_trylock(arch_rwlock_t *rw)
 
 	token = WRLOCK_TOKEN;
 	__asm__ __volatile__(
-"1:	" PPC_LWARX(%0,0,%2,1) "\n\
+"1:	lwarx		%0,0,%2,1\n\
 	cmpwi		0,%0,0\n\
 	bne-		2f\n"
 "	stwcx.		%1,0,%2\n\
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index 03b3d010cbab..7ef1cd8168a0 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -33,6 +33,10 @@ extern bool coregroup_enabled;
 extern int cpu_to_chip_id(int cpu);
 extern int *chip_id_lookup_table;
 
+DECLARE_PER_CPU(cpumask_var_t, thread_group_l1_cache_map);
+DECLARE_PER_CPU(cpumask_var_t, thread_group_l2_cache_map);
+DECLARE_PER_CPU(cpumask_var_t, thread_group_l3_cache_map);
+
 #ifdef CONFIG_SMP
 
 struct smp_ops_t {
@@ -141,6 +145,7 @@ extern int cpu_to_core_id(int cpu);
 
 extern bool has_big_cores;
 extern bool thread_group_shares_l2;
+extern bool thread_group_shares_l3;
 
 #define cpu_smt_mask cpu_smt_mask
 #ifdef CONFIG_SCHED_SMT
@@ -195,6 +200,7 @@ extern void __cpu_die(unsigned int cpu);
 #define hard_smp_processor_id()		get_hard_smp_processor_id(0)
 #define smp_setup_cpu_maps()
 #define thread_group_shares_l2  0
+#define thread_group_shares_l3	0
 static inline void inhibit_secondary_onlining(void) {}
 static inline void uninhibit_secondary_onlining(void) {}
 static inline const struct cpumask *cpu_sibling_mask(int cpu)
diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h
index ba0f88f3a30d..c60ebd04b2ed 100644
--- a/arch/powerpc/include/asm/syscall.h
+++ b/arch/powerpc/include/asm/syscall.h
@@ -90,10 +90,9 @@ static inline void syscall_get_arguments(struct task_struct *task,
 	unsigned long val, mask = -1UL;
 	unsigned int n = 6;
 
-#ifdef CONFIG_COMPAT
-	if (test_tsk_thread_flag(task, TIF_32BIT))
+	if (is_32bit_task())
 		mask = 0xffffffff;
-#endif
+
 	while (n--) {
 		if (n == 0)
 			val = regs->orig_gpr3;
@@ -116,16 +115,11 @@ static inline void syscall_set_arguments(struct task_struct *task,
 
 static inline int syscall_get_arch(struct task_struct *task)
 {
-	int arch;
-
-	if (IS_ENABLED(CONFIG_PPC64) && !test_tsk_thread_flag(task, TIF_32BIT))
-		arch = AUDIT_ARCH_PPC64;
+	if (is_32bit_task())
+		return AUDIT_ARCH_PPC;
+	else if (IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN))
+		return AUDIT_ARCH_PPC64LE;
 	else
-		arch = AUDIT_ARCH_PPC;
-
-#ifdef __LITTLE_ENDIAN__
-	arch |= __AUDIT_ARCH_LE;
-#endif
-	return arch;
+		return AUDIT_ARCH_PPC64;
 }
 #endif	/* _ASM_SYSCALL_H */
diff --git a/arch/powerpc/include/asm/syscalls.h b/arch/powerpc/include/asm/syscalls.h
index 398171fdcd9f..7ee66ae5444d 100644
--- a/arch/powerpc/include/asm/syscalls.h
+++ b/arch/powerpc/include/asm/syscalls.h
@@ -6,6 +6,7 @@
 #include <linux/compiler.h>
 #include <linux/linkage.h>
 #include <linux/types.h>
+#include <linux/compat.h>
 
 struct rtas_args;
 
@@ -18,5 +19,34 @@ asmlinkage long sys_mmap2(unsigned long addr, size_t len,
 asmlinkage long ppc64_personality(unsigned long personality);
 asmlinkage long sys_rtas(struct rtas_args __user *uargs);
 
+#ifdef CONFIG_COMPAT
+unsigned long compat_sys_mmap2(unsigned long addr, size_t len,
+			       unsigned long prot, unsigned long flags,
+			       unsigned long fd, unsigned long pgoff);
+
+compat_ssize_t compat_sys_pread64(unsigned int fd, char __user *ubuf, compat_size_t count,
+				  u32 reg6, u32 pos1, u32 pos2);
+
+compat_ssize_t compat_sys_pwrite64(unsigned int fd, const char __user *ubuf, compat_size_t count,
+				   u32 reg6, u32 pos1, u32 pos2);
+
+compat_ssize_t compat_sys_readahead(int fd, u32 r4, u32 offset1, u32 offset2, u32 count);
+
+int compat_sys_truncate64(const char __user *path, u32 reg4,
+			  unsigned long len1, unsigned long len2);
+
+long compat_sys_fallocate(int fd, int mode, u32 offset1, u32 offset2, u32 len1, u32 len2);
+
+int compat_sys_ftruncate64(unsigned int fd, u32 reg4, unsigned long len1,
+			   unsigned long len2);
+
+long ppc32_fadvise64(int fd, u32 unused, u32 offset1, u32 offset2,
+		     size_t len, int advice);
+
+long compat_sys_sync_file_range2(int fd, unsigned int flags,
+				 unsigned int offset1, unsigned int offset2,
+				 unsigned int nbytes1, unsigned int nbytes2);
+#endif
+
 #endif /* __KERNEL__ */
 #endif /* __ASM_POWERPC_SYSCALLS_H */
diff --git a/arch/powerpc/include/asm/tce.h b/arch/powerpc/include/asm/tce.h
index db5fc2f2262d..0c34d2756d92 100644
--- a/arch/powerpc/include/asm/tce.h
+++ b/arch/powerpc/include/asm/tce.h
@@ -19,15 +19,7 @@
 #define TCE_VB			0
 #define TCE_PCI			1
 
-/* TCE page size is 4096 bytes (1 << 12) */
-
-#define TCE_SHIFT	12
-#define TCE_PAGE_SIZE	(1 << TCE_SHIFT)
-
 #define TCE_ENTRY_SIZE		8		/* each TCE is 64 bits */
-
-#define TCE_RPN_MASK		0xfffffffffful  /* 40-bit RPN (4K pages) */
-#define TCE_RPN_SHIFT		12
 #define TCE_VALID		0x800		/* TCE valid */
 #define TCE_ALLIO		0x400		/* TCE valid for all lpars */
 #define TCE_PCI_WRITE		0x2		/* write from PCI allowed */
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index e4db64c0e184..36fcafb1fd6d 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -36,7 +36,7 @@ static inline int pcibus_to_node(struct pci_bus *bus)
 				 cpu_all_mask :				\
 				 cpumask_of_node(pcibus_to_node(bus)))
 
-extern int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc);
+int cpu_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc);
 extern int __node_distance(int, int);
 #define node_distance(a, b) __node_distance(a, b)
 
@@ -64,6 +64,12 @@ static inline int early_cpu_to_node(int cpu)
 }
 
 int of_drconf_to_nid_single(struct drmem_lmb *lmb);
+void update_numa_distance(struct device_node *node);
+
+extern void map_cpu_to_node(int cpu, int node);
+#ifdef CONFIG_HOTPLUG_CPU
+extern void unmap_cpu_from_node(unsigned long cpu);
+#endif /* CONFIG_HOTPLUG_CPU */
 
 #else
 
@@ -83,7 +89,7 @@ static inline void sysfs_remove_device_from_node(struct device *dev,
 
 static inline void update_numa_cpu_lookup_table(unsigned int cpu, int node) {}
 
-static inline int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
+static inline int cpu_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
 {
 	return 0;
 }
@@ -93,6 +99,15 @@ static inline int of_drconf_to_nid_single(struct drmem_lmb *lmb)
 	return first_online_node;
 }
 
+static inline void update_numa_distance(struct device_node *node) {}
+
+#ifdef CONFIG_SMP
+static inline void map_cpu_to_node(int cpu, int node) {}
+#ifdef CONFIG_HOTPLUG_CPU
+static inline void unmap_cpu_from_node(unsigned long cpu) {}
+#endif /* CONFIG_HOTPLUG_CPU */
+#endif /* CONFIG_SMP */
+
 #endif /* CONFIG_NUMA */
 
 #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR)
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index b541c690a31c..5eb462af6766 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/arch/powerpc/include/asm/unistd.h
@@ -9,8 +9,6 @@
 
 #define NR_syscalls	__NR_syscalls
 
-#define __NR__exit __NR_exit
-
 #ifndef __ASSEMBLY__
 
 #include <linux/types.h>
diff --git a/arch/powerpc/include/asm/vdso/processor.h b/arch/powerpc/include/asm/vdso/processor.h
index e072577bc7c0..8d79f994b4aa 100644
--- a/arch/powerpc/include/asm/vdso/processor.h
+++ b/arch/powerpc/include/asm/vdso/processor.h
@@ -5,12 +5,21 @@
 #ifndef __ASSEMBLY__
 
 /* Macros for adjusting thread priority (hardware multi-threading) */
+#ifdef CONFIG_PPC64
 #define HMT_very_low()		asm volatile("or 31, 31, 31	# very low priority")
 #define HMT_low()		asm volatile("or 1, 1, 1	# low priority")
 #define HMT_medium_low()	asm volatile("or 6, 6, 6	# medium low priority")
 #define HMT_medium()		asm volatile("or 2, 2, 2	# medium priority")
 #define HMT_medium_high()	asm volatile("or 5, 5, 5	# medium high priority")
 #define HMT_high()		asm volatile("or 3, 3, 3	# high priority")
+#else
+#define HMT_very_low()
+#define HMT_low()
+#define HMT_medium_low()
+#define HMT_medium()
+#define HMT_medium_high()
+#define HMT_high()
+#endif
 
 #ifdef CONFIG_PPC64
 #define cpu_relax()	do { HMT_low(); HMT_medium(); barrier(); } while (0)
diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h
index d9cf192368ad..0ac9bfddf704 100644
--- a/arch/powerpc/include/asm/xics.h
+++ b/arch/powerpc/include/asm/xics.h
@@ -89,10 +89,11 @@ static inline int ics_opal_init(void) { return -ENODEV; }
 /* ICS instance, hooked up to chip_data of an irq */
 struct ics {
 	struct list_head link;
-	int (*map)(struct ics *ics, unsigned int virq);
+	int (*check)(struct ics *ics, unsigned int hwirq);
 	void (*mask_unknown)(struct ics *ics, unsigned long vec);
 	long (*get_server)(struct ics *ics, unsigned long vec);
 	int (*host_match)(struct ics *ics, struct device_node *node);
+	struct irq_chip *chip;
 	char data[];
 };
 
diff --git a/arch/powerpc/include/asm/xive-regs.h b/arch/powerpc/include/asm/xive-regs.h
index 8b211faa0e42..cf8bb6ac4463 100644
--- a/arch/powerpc/include/asm/xive-regs.h
+++ b/arch/powerpc/include/asm/xive-regs.h
@@ -80,10 +80,13 @@
 #define   TM_QW0W2_VU		PPC_BIT32(0)
 #define   TM_QW0W2_LOGIC_SERV	PPC_BITMASK32(1,31) // XX 2,31 ?
 #define   TM_QW1W2_VO		PPC_BIT32(0)
+#define   TM_QW1W2_HO           PPC_BIT32(1) /* P10 XIVE2 */
 #define   TM_QW1W2_OS_CAM	PPC_BITMASK32(8,31)
 #define   TM_QW2W2_VP		PPC_BIT32(0)
+#define   TM_QW2W2_HP           PPC_BIT32(1) /* P10 XIVE2 */
 #define   TM_QW2W2_POOL_CAM	PPC_BITMASK32(8,31)
 #define   TM_QW3W2_VT		PPC_BIT32(0)
+#define   TM_QW3W2_HT           PPC_BIT32(1) /* P10 XIVE2 */
 #define   TM_QW3W2_LP		PPC_BIT32(6)
 #define   TM_QW3W2_LE		PPC_BIT32(7)
 #define   TM_QW3W2_T		PPC_BIT32(31)
diff --git a/arch/powerpc/include/asm/xive.h b/arch/powerpc/include/asm/xive.h
index aa094a8655b0..92930b0b5d0e 100644
--- a/arch/powerpc/include/asm/xive.h
+++ b/arch/powerpc/include/asm/xive.h
@@ -111,6 +111,7 @@ void xive_native_free_vp_block(u32 vp_base);
 int xive_native_populate_irq_data(u32 hw_irq,
 				  struct xive_irq_data *data);
 void xive_cleanup_irq_data(struct xive_irq_data *xd);
+void xive_irq_free_data(unsigned int virq);
 void xive_native_free_irq(u32 irq);
 int xive_native_configure_irq(u32 hw_irq, u32 target, u8 prio, u32 sw_irq);
 
@@ -125,6 +126,7 @@ int xive_native_enable_vp(u32 vp_id, bool single_escalation);
 int xive_native_disable_vp(u32 vp_id);
 int xive_native_get_vp_info(u32 vp_id, u32 *out_cam_id, u32 *out_chip_id);
 bool xive_native_has_single_escalation(void);
+bool xive_native_has_save_restore(void);
 
 int xive_native_get_queue_info(u32 vp_id, uint32_t prio,
 			       u64 *out_qpage,
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index f66b63e81c3b..7be36c1e1db6 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -46,7 +46,8 @@ obj-y				:= cputable.o syscalls.o \
 				   prom.o traps.o setup-common.o \
 				   udbg.o misc.o io.o misc_$(BITS).o \
 				   of_platform.o prom_parse.o firmware.o \
-				   hw_breakpoint_constraints.o interrupt.o
+				   hw_breakpoint_constraints.o interrupt.o \
+				   kdebugfs.o
 obj-y				+= ptrace/
 obj-$(CONFIG_PPC64)		+= setup_64.o \
 				   paca.o nvram_64.o note.o
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 5bee245d832b..e563d3222d69 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -286,23 +286,16 @@ int main(void)
 	STACK_PT_REGS_OFFSET(_CCR, ccr);
 	STACK_PT_REGS_OFFSET(_XER, xer);
 	STACK_PT_REGS_OFFSET(_DAR, dar);
+	STACK_PT_REGS_OFFSET(_DEAR, dear);
 	STACK_PT_REGS_OFFSET(_DSISR, dsisr);
+	STACK_PT_REGS_OFFSET(_ESR, esr);
 	STACK_PT_REGS_OFFSET(ORIG_GPR3, orig_gpr3);
 	STACK_PT_REGS_OFFSET(RESULT, result);
 	STACK_PT_REGS_OFFSET(_TRAP, trap);
-#ifndef CONFIG_PPC64
-	/*
-	 * The PowerPC 400-class & Book-E processors have neither the DAR
-	 * nor the DSISR SPRs. Hence, we overload them to hold the similar
-	 * DEAR and ESR SPRs for such processors.  For critical interrupts
-	 * we use them to hold SRR0 and SRR1.
-	 */
-	STACK_PT_REGS_OFFSET(_DEAR, dar);
-	STACK_PT_REGS_OFFSET(_ESR, dsisr);
-#else /* CONFIG_PPC64 */
+#ifdef CONFIG_PPC64
 	STACK_PT_REGS_OFFSET(SOFTE, softe);
 	STACK_PT_REGS_OFFSET(_PPR, ppr);
-#endif /* CONFIG_PPC64 */
+#endif
 
 #ifdef CONFIG_PPC_PKEY
 	STACK_PT_REGS_OFFSET(STACK_REGS_AMR, amr);
diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c
index 6f903e9aa20b..cf1be75b7833 100644
--- a/arch/powerpc/kernel/cacheinfo.c
+++ b/arch/powerpc/kernel/cacheinfo.c
@@ -120,6 +120,7 @@ struct cache {
 	struct cpumask shared_cpu_map; /* online CPUs using this cache */
 	int type;                      /* split cache disambiguation */
 	int level;                     /* level not explicit in device tree */
+	int group_id;                  /* id of the group of threads that share this cache */
 	struct list_head list;         /* global list of cache objects */
 	struct cache *next_local;      /* next cache of >= level */
 };
@@ -142,22 +143,24 @@ static const char *cache_type_string(const struct cache *cache)
 }
 
 static void cache_init(struct cache *cache, int type, int level,
-		       struct device_node *ofnode)
+		       struct device_node *ofnode, int group_id)
 {
 	cache->type = type;
 	cache->level = level;
 	cache->ofnode = of_node_get(ofnode);
+	cache->group_id = group_id;
 	INIT_LIST_HEAD(&cache->list);
 	list_add(&cache->list, &cache_list);
 }
 
-static struct cache *new_cache(int type, int level, struct device_node *ofnode)
+static struct cache *new_cache(int type, int level,
+			       struct device_node *ofnode, int group_id)
 {
 	struct cache *cache;
 
 	cache = kzalloc(sizeof(*cache), GFP_KERNEL);
 	if (cache)
-		cache_init(cache, type, level, ofnode);
+		cache_init(cache, type, level, ofnode, group_id);
 
 	return cache;
 }
@@ -309,20 +312,24 @@ static struct cache *cache_find_first_sibling(struct cache *cache)
 		return cache;
 
 	list_for_each_entry(iter, &cache_list, list)
-		if (iter->ofnode == cache->ofnode && iter->next_local == cache)
+		if (iter->ofnode == cache->ofnode &&
+		    iter->group_id == cache->group_id &&
+		    iter->next_local == cache)
 			return iter;
 
 	return cache;
 }
 
-/* return the first cache on a local list matching node */
-static struct cache *cache_lookup_by_node(const struct device_node *node)
+/* return the first cache on a local list matching node and thread-group id */
+static struct cache *cache_lookup_by_node_group(const struct device_node *node,
+						int group_id)
 {
 	struct cache *cache = NULL;
 	struct cache *iter;
 
 	list_for_each_entry(iter, &cache_list, list) {
-		if (iter->ofnode != node)
+		if (iter->ofnode != node ||
+		    iter->group_id != group_id)
 			continue;
 		cache = cache_find_first_sibling(iter);
 		break;
@@ -352,14 +359,15 @@ static int cache_is_unified_d(const struct device_node *np)
 		CACHE_TYPE_UNIFIED_D : CACHE_TYPE_UNIFIED;
 }
 
-static struct cache *cache_do_one_devnode_unified(struct device_node *node, int level)
+static struct cache *cache_do_one_devnode_unified(struct device_node *node, int group_id,
+						  int level)
 {
 	pr_debug("creating L%d ucache for %pOFP\n", level, node);
 
-	return new_cache(cache_is_unified_d(node), level, node);
+	return new_cache(cache_is_unified_d(node), level, node, group_id);
 }
 
-static struct cache *cache_do_one_devnode_split(struct device_node *node,
+static struct cache *cache_do_one_devnode_split(struct device_node *node, int group_id,
 						int level)
 {
 	struct cache *dcache, *icache;
@@ -367,8 +375,8 @@ static struct cache *cache_do_one_devnode_split(struct device_node *node,
 	pr_debug("creating L%d dcache and icache for %pOFP\n", level,
 		 node);
 
-	dcache = new_cache(CACHE_TYPE_DATA, level, node);
-	icache = new_cache(CACHE_TYPE_INSTRUCTION, level, node);
+	dcache = new_cache(CACHE_TYPE_DATA, level, node, group_id);
+	icache = new_cache(CACHE_TYPE_INSTRUCTION, level, node, group_id);
 
 	if (!dcache || !icache)
 		goto err;
@@ -382,31 +390,32 @@ err:
 	return NULL;
 }
 
-static struct cache *cache_do_one_devnode(struct device_node *node, int level)
+static struct cache *cache_do_one_devnode(struct device_node *node, int group_id, int level)
 {
 	struct cache *cache;
 
 	if (cache_node_is_unified(node))
-		cache = cache_do_one_devnode_unified(node, level);
+		cache = cache_do_one_devnode_unified(node, group_id, level);
 	else
-		cache = cache_do_one_devnode_split(node, level);
+		cache = cache_do_one_devnode_split(node, group_id, level);
 
 	return cache;
 }
 
 static struct cache *cache_lookup_or_instantiate(struct device_node *node,
+						 int group_id,
 						 int level)
 {
 	struct cache *cache;
 
-	cache = cache_lookup_by_node(node);
+	cache = cache_lookup_by_node_group(node, group_id);
 
 	WARN_ONCE(cache && cache->level != level,
 		  "cache level mismatch on lookup (got %d, expected %d)\n",
 		  cache->level, level);
 
 	if (!cache)
-		cache = cache_do_one_devnode(node, level);
+		cache = cache_do_one_devnode(node, group_id, level);
 
 	return cache;
 }
@@ -443,7 +452,30 @@ static void do_subsidiary_caches_debugcheck(struct cache *cache)
 		  of_node_get_device_type(cache->ofnode));
 }
 
-static void do_subsidiary_caches(struct cache *cache)
+/*
+ * If sub-groups of threads in a core containing @cpu_id share the
+ * L@level-cache (information obtained via "ibm,thread-groups"
+ * device-tree property), then we identify the group by the first
+ * thread-sibling in the group. We define this to be the group-id.
+ *
+ * In the absence of any thread-group information for L@level-cache,
+ * this function returns -1.
+ */
+static int get_group_id(unsigned int cpu_id, int level)
+{
+	if (has_big_cores && level == 1)
+		return cpumask_first(per_cpu(thread_group_l1_cache_map,
+					     cpu_id));
+	else if (thread_group_shares_l2 && level == 2)
+		return cpumask_first(per_cpu(thread_group_l2_cache_map,
+					     cpu_id));
+	else if (thread_group_shares_l3 && level == 3)
+		return cpumask_first(per_cpu(thread_group_l3_cache_map,
+					     cpu_id));
+	return -1;
+}
+
+static void do_subsidiary_caches(struct cache *cache, unsigned int cpu_id)
 {
 	struct device_node *subcache_node;
 	int level = cache->level;
@@ -452,9 +484,11 @@ static void do_subsidiary_caches(struct cache *cache)
 
 	while ((subcache_node = of_find_next_cache_node(cache->ofnode))) {
 		struct cache *subcache;
+		int group_id;
 
 		level++;
-		subcache = cache_lookup_or_instantiate(subcache_node, level);
+		group_id = get_group_id(cpu_id, level);
+		subcache = cache_lookup_or_instantiate(subcache_node, group_id, level);
 		of_node_put(subcache_node);
 		if (!subcache)
 			break;
@@ -468,6 +502,7 @@ static struct cache *cache_chain_instantiate(unsigned int cpu_id)
 {
 	struct device_node *cpu_node;
 	struct cache *cpu_cache = NULL;
+	int group_id;
 
 	pr_debug("creating cache object(s) for CPU %i\n", cpu_id);
 
@@ -476,11 +511,13 @@ static struct cache *cache_chain_instantiate(unsigned int cpu_id)
 	if (!cpu_node)
 		goto out;
 
-	cpu_cache = cache_lookup_or_instantiate(cpu_node, 1);
+	group_id = get_group_id(cpu_id, 1);
+
+	cpu_cache = cache_lookup_or_instantiate(cpu_node, group_id, 1);
 	if (!cpu_cache)
 		goto out;
 
-	do_subsidiary_caches(cpu_cache);
+	do_subsidiary_caches(cpu_cache, cpu_id);
 
 	cache_cpu_set(cpu_cache, cpu_id);
 out:
@@ -641,45 +678,6 @@ static ssize_t level_show(struct kobject *k, struct kobj_attribute *attr, char *
 static struct kobj_attribute cache_level_attr =
 	__ATTR(level, 0444, level_show, NULL);
 
-static unsigned int index_dir_to_cpu(struct cache_index_dir *index)
-{
-	struct kobject *index_dir_kobj = &index->kobj;
-	struct kobject *cache_dir_kobj = index_dir_kobj->parent;
-	struct kobject *cpu_dev_kobj = cache_dir_kobj->parent;
-	struct device *dev = kobj_to_dev(cpu_dev_kobj);
-
-	return dev->id;
-}
-
-/*
- * On big-core systems, each core has two groups of CPUs each of which
- * has its own L1-cache. The thread-siblings which share l1-cache with
- * @cpu can be obtained via cpu_smallcore_mask().
- *
- * On some big-core systems, the L2 cache is shared only between some
- * groups of siblings. This is already parsed and encoded in
- * cpu_l2_cache_mask().
- *
- * TODO: cache_lookup_or_instantiate() needs to be made aware of the
- *       "ibm,thread-groups" property so that cache->shared_cpu_map
- *       reflects the correct siblings on platforms that have this
- *       device-tree property. This helper function is only a stop-gap
- *       solution so that we report the correct siblings to the
- *       userspace via sysfs.
- */
-static const struct cpumask *get_shared_cpu_map(struct cache_index_dir *index, struct cache *cache)
-{
-	if (has_big_cores) {
-		int cpu = index_dir_to_cpu(index);
-		if (cache->level == 1)
-			return cpu_smallcore_mask(cpu);
-		if (cache->level == 2 && thread_group_shares_l2)
-			return cpu_l2_cache_mask(cpu);
-	}
-
-	return &cache->shared_cpu_map;
-}
-
 static ssize_t
 show_shared_cpumap(struct kobject *k, struct kobj_attribute *attr, char *buf, bool list)
 {
@@ -690,7 +688,7 @@ show_shared_cpumap(struct kobject *k, struct kobj_attribute *attr, char *buf, bo
 	index = kobj_to_cache_index_dir(k);
 	cache = index->cache;
 
-	mask = get_shared_cpu_map(index, cache);
+	mask = &cache->shared_cpu_map;
 
 	return cpumap_print_to_pagebuf(list, buf, mask);
 }
@@ -848,13 +846,15 @@ static struct cache *cache_lookup_by_cpu(unsigned int cpu_id)
 {
 	struct device_node *cpu_node;
 	struct cache *cache;
+	int group_id;
 
 	cpu_node = of_get_cpu_node(cpu_id, NULL);
 	WARN_ONCE(!cpu_node, "no OF node found for CPU %i\n", cpu_id);
 	if (!cpu_node)
 		return NULL;
 
-	cache = cache_lookup_by_node(cpu_node);
+	group_id = get_group_id(cpu_id, 1);
+	cache = cache_lookup_by_node_group(cpu_node, group_id);
 	of_node_put(cpu_node);
 
 	return cache;
diff --git a/arch/powerpc/kernel/dawr.c b/arch/powerpc/kernel/dawr.c
index cdc2dccb987d..64e423d2fe0f 100644
--- a/arch/powerpc/kernel/dawr.c
+++ b/arch/powerpc/kernel/dawr.c
@@ -9,7 +9,6 @@
 #include <linux/export.h>
 #include <linux/fs.h>
 #include <linux/debugfs.h>
-#include <asm/debugfs.h>
 #include <asm/machdep.h>
 #include <asm/hvcall.h>
 
@@ -101,7 +100,7 @@ static int __init dawr_force_setup(void)
 	if (PVR_VER(mfspr(SPRN_PVR)) == PVR_POWER9) {
 		/* Turn DAWR off by default, but allow admin to turn it on */
 		debugfs_create_file_unsafe("dawr_enable_dangerous", 0600,
-					   powerpc_debugfs_root,
+					   arch_debugfs_dir,
 					   &dawr_force_enable,
 					   &dawr_enable_fops);
 	}
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 3bbdcc86d01b..e9b597ed423c 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -21,9 +21,9 @@
 #include <linux/spinlock.h>
 #include <linux/export.h>
 #include <linux/of.h>
+#include <linux/debugfs.h>
 
 #include <linux/atomic.h>
-#include <asm/debugfs.h>
 #include <asm/eeh.h>
 #include <asm/eeh_event.h>
 #include <asm/io.h>
@@ -1901,24 +1901,24 @@ static int __init eeh_init_proc(void)
 		proc_create_single("powerpc/eeh", 0, NULL, proc_eeh_show);
 #ifdef CONFIG_DEBUG_FS
 		debugfs_create_file_unsafe("eeh_enable", 0600,
-					   powerpc_debugfs_root, NULL,
+					   arch_debugfs_dir, NULL,
 					   &eeh_enable_dbgfs_ops);
 		debugfs_create_u32("eeh_max_freezes", 0600,
-				powerpc_debugfs_root, &eeh_max_freezes);
+				arch_debugfs_dir, &eeh_max_freezes);
 		debugfs_create_bool("eeh_disable_recovery", 0600,
-				powerpc_debugfs_root,
+				arch_debugfs_dir,
 				&eeh_debugfs_no_recover);
 		debugfs_create_file_unsafe("eeh_dev_check", 0600,
-				powerpc_debugfs_root, NULL,
+				arch_debugfs_dir, NULL,
 				&eeh_dev_check_fops);
 		debugfs_create_file_unsafe("eeh_dev_break", 0600,
-				powerpc_debugfs_root, NULL,
+				arch_debugfs_dir, NULL,
 				&eeh_dev_break_fops);
 		debugfs_create_file_unsafe("eeh_force_recover", 0600,
-				powerpc_debugfs_root, NULL,
+				arch_debugfs_dir, NULL,
 				&eeh_force_recover_fops);
 		debugfs_create_file_unsafe("eeh_dev_can_recover", 0600,
-				powerpc_debugfs_root, NULL,
+				arch_debugfs_dir, NULL,
 				&eeh_dev_can_recover_fops);
 		eeh_cache_debugfs_init();
 #endif
diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c
index bf3270426d82..9bdaaf7fddc9 100644
--- a/arch/powerpc/kernel/eeh_cache.c
+++ b/arch/powerpc/kernel/eeh_cache.c
@@ -12,8 +12,8 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/atomic.h>
+#include <linux/debugfs.h>
 #include <asm/pci-bridge.h>
-#include <asm/debugfs.h>
 #include <asm/ppc-pci.h>
 
 
@@ -283,6 +283,6 @@ DEFINE_SHOW_ATTRIBUTE(eeh_addr_cache);
 void eeh_cache_debugfs_init(void)
 {
 	debugfs_create_file_unsafe("eeh_address_cache", 0400,
-			powerpc_debugfs_root, NULL,
+			arch_debugfs_dir, NULL,
 			&eeh_addr_cache_fops);
 }
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 0273a1349006..61fdd53cdd9a 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -161,10 +161,10 @@ ret_from_fork:
 ret_from_kernel_thread:
 	REST_NVGPRS(r1)
 	bl	schedule_tail
-	mtlr	r14
+	mtctr	r14
 	mr	r3,r15
 	PPC440EP_ERR42
-	blrl
+	bctrl
 	li	r3,0
 	b	ret_from_syscall
 
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 15720f8661a1..70cff7b49e17 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -309,7 +309,7 @@ _GLOBAL(enter_rtas)
 	 */
 	lbz	r0,PACAIRQSOFTMASK(r13)
 1:	tdeqi	r0,IRQS_ENABLED
-	EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING
+	EMIT_WARN_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING
 #endif
 
 	/* Hard-disable interrupts */
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 1401787b0b93..711c66b76df1 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -545,8 +545,8 @@ __end_interrupts:
 				PROLOG_ADDITION_2REGS)
 	mfspr	r14,SPRN_DEAR
 	mfspr	r15,SPRN_ESR
-	std	r14,_DAR(r1)
-	std	r15,_DSISR(r1)
+	std	r14,_DEAR(r1)
+	std	r15,_ESR(r1)
 	ld	r14,PACA_EXGEN+EX_R14(r13)
 	ld	r15,PACA_EXGEN+EX_R15(r13)
 	EXCEPTION_COMMON(0x300)
@@ -558,8 +558,8 @@ __end_interrupts:
 				PROLOG_ADDITION_2REGS)
 	li	r15,0
 	mr	r14,r10
-	std	r14,_DAR(r1)
-	std	r15,_DSISR(r1)
+	std	r14,_DEAR(r1)
+	std	r15,_ESR(r1)
 	ld	r14,PACA_EXGEN+EX_R14(r13)
 	ld	r15,PACA_EXGEN+EX_R15(r13)
 	EXCEPTION_COMMON(0x400)
@@ -575,8 +575,8 @@ __end_interrupts:
 				PROLOG_ADDITION_2REGS)
 	mfspr	r14,SPRN_DEAR
 	mfspr	r15,SPRN_ESR
-	std	r14,_DAR(r1)
-	std	r15,_DSISR(r1)
+	std	r14,_DEAR(r1)
+	std	r15,_ESR(r1)
 	ld	r14,PACA_EXGEN+EX_R14(r13)
 	ld	r15,PACA_EXGEN+EX_R15(r13)
 	EXCEPTION_COMMON(0x600)
@@ -587,7 +587,7 @@ __end_interrupts:
 	NORMAL_EXCEPTION_PROLOG(0x700, BOOKE_INTERRUPT_PROGRAM,
 				PROLOG_ADDITION_1REG)
 	mfspr	r14,SPRN_ESR
-	std	r14,_DSISR(r1)
+	std	r14,_ESR(r1)
 	ld	r14,PACA_EXGEN+EX_R14(r13)
 	EXCEPTION_COMMON(0x700)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
@@ -1057,8 +1057,8 @@ bad_stack_book3e:
 	std	r11,_CCR(r1)
 	mfspr	r10,SPRN_DEAR
 	mfspr	r11,SPRN_ESR
-	std	r10,_DAR(r1)
-	std	r11,_DSISR(r1)
+	std	r10,_DEAR(r1)
+	std	r11,_ESR(r1)
 	std	r0,GPR0(r1);		/* save r0 in stackframe */	    \
 	std	r2,GPR2(r1);		/* save r2 in stackframe */	    \
 	SAVE_4GPRS(3, r1);		/* save r3 - r6 in stackframe */    \
@@ -1127,7 +1127,7 @@ found_iprot:
  * r3 = MAS0_TLBSEL (for the iprot array)
  * r4 = SPRN_TLBnCFG
  */
-	bl	invstr				/* Find our address */
+	bcl	20,31,$+4			/* Find our address */
 invstr:	mflr	r6				/* Make it accessible */
 	mfmsr	r7
 	rlwinm	r5,r7,27,31,31			/* extract MSR[IS] */
@@ -1196,7 +1196,7 @@ skpinv:	addi	r6,r6,1				/* Increment */
 	mfmsr	r6
 	xori	r6,r6,MSR_IS
 	mtspr	SPRN_SRR1,r6
-	bl	1f		/* Find our address */
+	bcl	20,31,$+4	/* Find our address */
 1:	mflr	r6
 	addi	r6,r6,(2f - 1b)
 	mtspr	SPRN_SRR0,r6
@@ -1256,7 +1256,7 @@ skpinv:	addi	r6,r6,1				/* Increment */
  * r4 = MAS0 w/TLBSEL & ESEL for the temp mapping
  */
 	/* Now we branch the new virtual address mapped by this entry */
-	bl	1f		/* Find our address */
+	bcl	20,31,$+4	/* Find our address */
 1:	mflr	r6
 	addi	r6,r6,(2f - 1b)
 	tovirt(r6,r6)
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index b990075285f5..b7ceb041743c 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -24,8 +24,8 @@
 #include <linux/slab.h>
 #include <linux/cma.h>
 #include <linux/hugetlb.h>
+#include <linux/debugfs.h>
 
-#include <asm/debugfs.h>
 #include <asm/page.h>
 #include <asm/prom.h>
 #include <asm/fadump.h>
@@ -1557,7 +1557,7 @@ static void fadump_init_files(void)
 		return;
 	}
 
-	debugfs_create_file("fadump_region", 0444, powerpc_debugfs_root, NULL,
+	debugfs_create_file("fadump_region", 0444, arch_debugfs_dir, NULL,
 			    &fadump_region_fops);
 
 	if (fw_dump.dump_active) {
diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S
index 6010adcee16e..ba4afe3b5a9c 100644
--- a/arch/powerpc/kernel/fpu.S
+++ b/arch/powerpc/kernel/fpu.S
@@ -91,8 +91,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 	isync
 	/* enable use of FP after return */
 #ifdef CONFIG_PPC32
-	mfspr	r5,SPRN_SPRG_THREAD	/* current task's THREAD (phys) */
-	tovirt(r5, r5)
+	addi	r5,r2,THREAD
 	lwz	r4,THREAD_FPEXC_MODE(r5)
 	ori	r9,r9,MSR_FP		/* enable FP for current */
 	or	r9,r9,r4
diff --git a/arch/powerpc/kernel/fsl_booke_entry_mapping.S b/arch/powerpc/kernel/fsl_booke_entry_mapping.S
index 8bccce6544b5..dedc17fac8f8 100644
--- a/arch/powerpc/kernel/fsl_booke_entry_mapping.S
+++ b/arch/powerpc/kernel/fsl_booke_entry_mapping.S
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 
 /* 1. Find the index of the entry we're executing in */
-	bl	invstr				/* Find our address */
+	bcl	20,31,$+4				/* Find our address */
 invstr:	mflr	r6				/* Make it accessible */
 	mfmsr	r7
 	rlwinm	r4,r7,27,31,31			/* extract MSR[IS] */
@@ -85,7 +85,7 @@ skpinv:	addi	r6,r6,1				/* Increment */
 	addi	r6,r6,10
 	slw	r6,r8,r6	/* convert to mask */
 
-	bl	1f		/* Find our address */
+	bcl	20,31,$+4	/* Find our address */
 1:	mflr	r7
 
 	mfspr	r8,SPRN_MAS3
@@ -117,7 +117,7 @@ skpinv:	addi	r6,r6,1				/* Increment */
 
 	xori	r6,r4,1
 	slwi	r6,r6,5		/* setup new context with other address space */
-	bl	1f		/* Find our address */
+	bcl	20,31,$+4	/* Find our address */
 1:	mflr	r9
 	rlwimi	r7,r9,0,20,31
 	addi	r7,r7,(2f - 1b)
@@ -207,7 +207,7 @@ next_tlb_setup:
 
 	lis	r7,MSR_KERNEL@h
 	ori	r7,r7,MSR_KERNEL@l
-	bl	1f			/* Find our address */
+	bcl	20,31,$+4		/* Find our address */
 1:	mflr	r9
 	rlwimi	r6,r9,0,20,31
 	addi	r6,r6,(2f - 1b)
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index ddc978a2d381..02d2928d1e01 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -70,7 +70,7 @@ _ENTRY(_start);
  * address.
  * r21 will be loaded with the physical runtime address of _stext
  */
-	bl	0f				/* Get our runtime address */
+	bcl	20,31,$+4			/* Get our runtime address */
 0:	mflr	r21				/* Make it accessible */
 	addis	r21,r21,(_stext - 0b)@ha
 	addi	r21,r21,(_stext - 0b)@l 	/* Get our current runtime base */
@@ -853,7 +853,7 @@ _GLOBAL(init_cpu_state)
 wmmucr:	mtspr	SPRN_MMUCR,r3			/* Put MMUCR */
 	sync
 
-	bl	invstr				/* Find our address */
+	bcl	20,31,$+4			/* Find our address */
 invstr:	mflr	r5				/* Make it accessible */
 	tlbsx	r23,0,r5			/* Find entry we are in */
 	li	r4,0				/* Start at TLB entry 0 */
@@ -1045,7 +1045,7 @@ head_start_47x:
 	sync
 
 	/* Find the entry we are running from */
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r23
 	tlbsx	r23,0,r23
 	tlbre	r24,r23,0
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 79930b0bc781..f17ae2083733 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -712,6 +712,8 @@ _GLOBAL(copy_and_flush)
 	isync
 	blr
 
+_ASM_NOKPROBE_SYMBOL(copy_and_flush); /* Called in real mode */
+
 .align 8
 copy_to_here:
 
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 9a2f4265e6d2..0a9a0f301474 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -79,7 +79,7 @@ _ENTRY(_start);
 	mr	r23,r3
 	mr	r25,r4
 
-	bl	0f
+	bcl	20,31,$+4
 0:	mflr	r8
 	addis	r3,r8,(is_second_reloc - 0b)@ha
 	lwz	r19,(is_second_reloc - 0b)@l(r3)
@@ -1132,7 +1132,7 @@ _GLOBAL(switch_to_as1)
 	bne	1b
 
 	/* Get the tlb entry used by the current running code */
-	bl	0f
+	bcl	20,31,$+4
 0:	mflr	r4
 	tlbsx	0,r4
 
@@ -1166,7 +1166,7 @@ _GLOBAL(switch_to_as1)
 _GLOBAL(restore_to_as0)
 	mflr	r0
 
-	bl	0f
+	bcl	20,31,$+4
 0:	mflr	r9
 	addi	r9,r9,1f - 0b
 
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index 21a638aff72f..91a3be14808b 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -22,7 +22,6 @@
 #include <asm/processor.h>
 #include <asm/sstep.h>
 #include <asm/debug.h>
-#include <asm/debugfs.h>
 #include <asm/hvcall.h>
 #include <asm/inst.h>
 #include <linux/uaccess.h>
diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index 21bbd615ca41..a73f3f70a657 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -8,7 +8,6 @@
 #include <asm/asm-prototypes.h>
 #include <asm/kup.h>
 #include <asm/cputime.h>
-#include <asm/interrupt.h>
 #include <asm/hw_irq.h>
 #include <asm/interrupt.h>
 #include <asm/kprobes.h>
@@ -93,8 +92,7 @@ notrace long system_call_exception(long r3, long r4, long r5,
 	CT_WARN_ON(ct_state() == CONTEXT_KERNEL);
 	user_exit_irqoff();
 
-	if (!IS_ENABLED(CONFIG_BOOKE) && !IS_ENABLED(CONFIG_40x))
-		BUG_ON(!(regs->msr & MSR_RI));
+	BUG_ON(regs_is_unrecoverable(regs));
 	BUG_ON(!(regs->msr & MSR_PR));
 	BUG_ON(arch_irq_disabled_regs(regs));
 
@@ -463,9 +461,7 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs)
 {
 	unsigned long ret;
 
-	if (!IS_ENABLED(CONFIG_BOOKE) && !IS_ENABLED(CONFIG_40x))
-		BUG_ON(!(regs->msr & MSR_RI));
-	BUG_ON(!(regs->msr & MSR_PR));
+	BUG_ON(regs_is_unrecoverable(regs));
 	BUG_ON(arch_irq_disabled_regs(regs));
 	CT_WARN_ON(ct_state() == CONTEXT_USER);
 
@@ -496,10 +492,8 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs)
 	bool stack_store = current_thread_info()->flags &
 						_TIF_EMULATE_STACK_STORE;
 
-	if (!IS_ENABLED(CONFIG_BOOKE) && !IS_ENABLED(CONFIG_40x) &&
-	    unlikely(!(regs->msr & MSR_RI)))
+	if (regs_is_unrecoverable(regs))
 		unrecoverable_exception(regs);
-	BUG_ON(regs->msr & MSR_PR);
 	/*
 	 * CT_WARN_ON comes here via program_check_exception,
 	 * so avoid recursion.
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 30b7736f0896..07093b7cdcb9 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -688,34 +688,26 @@ static void iommu_table_reserve_pages(struct iommu_table *tbl,
 	if (tbl->it_offset == 0)
 		set_bit(0, tbl->it_map);
 
+	if (res_start < tbl->it_offset)
+		res_start = tbl->it_offset;
+
+	if (res_end > (tbl->it_offset + tbl->it_size))
+		res_end = tbl->it_offset + tbl->it_size;
+
+	/* Check if res_start..res_end is a valid range in the table */
+	if (res_start >= res_end) {
+		tbl->it_reserved_start = tbl->it_offset;
+		tbl->it_reserved_end = tbl->it_offset;
+		return;
+	}
+
 	tbl->it_reserved_start = res_start;
 	tbl->it_reserved_end = res_end;
 
-	/* Check if res_start..res_end isn't empty and overlaps the table */
-	if (res_start && res_end &&
-			(tbl->it_offset + tbl->it_size < res_start ||
-			 res_end < tbl->it_offset))
-		return;
-
 	for (i = tbl->it_reserved_start; i < tbl->it_reserved_end; ++i)
 		set_bit(i - tbl->it_offset, tbl->it_map);
 }
 
-static void iommu_table_release_pages(struct iommu_table *tbl)
-{
-	int i;
-
-	/*
-	 * In case we have reserved the first bit, we should not emit
-	 * the warning below.
-	 */
-	if (tbl->it_offset == 0)
-		clear_bit(0, tbl->it_map);
-
-	for (i = tbl->it_reserved_start; i < tbl->it_reserved_end; ++i)
-		clear_bit(i - tbl->it_offset, tbl->it_map);
-}
-
 /*
  * Build a iommu_table structure.  This contains a bit map which
  * is used to manage allocation of the tce space.
@@ -777,6 +769,22 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid,
 	return tbl;
 }
 
+bool iommu_table_in_use(struct iommu_table *tbl)
+{
+	unsigned long start = 0, end;
+
+	/* ignore reserved bit0 */
+	if (tbl->it_offset == 0)
+		start = 1;
+	end = tbl->it_reserved_start - tbl->it_offset;
+	if (find_next_bit(tbl->it_map, end, start) != end)
+		return true;
+
+	start = tbl->it_reserved_end - tbl->it_offset;
+	end = tbl->it_size;
+	return find_next_bit(tbl->it_map, end, start) != end;
+}
+
 static void iommu_table_free(struct kref *kref)
 {
 	struct iommu_table *tbl;
@@ -793,10 +801,8 @@ static void iommu_table_free(struct kref *kref)
 
 	iommu_debugfs_del(tbl);
 
-	iommu_table_release_pages(tbl);
-
 	/* verify that table contains no entries */
-	if (!bitmap_empty(tbl->it_map, tbl->it_size))
+	if (iommu_table_in_use(tbl))
 		pr_warn("%s: Unexpected TCEs\n", __func__);
 
 	/* free bitmap */
@@ -1097,14 +1103,9 @@ int iommu_take_ownership(struct iommu_table *tbl)
 	for (i = 0; i < tbl->nr_pools; i++)
 		spin_lock_nest_lock(&tbl->pools[i].lock, &tbl->large_pool.lock);
 
-	iommu_table_release_pages(tbl);
-
-	if (!bitmap_empty(tbl->it_map, tbl->it_size)) {
+	if (iommu_table_in_use(tbl)) {
 		pr_err("iommu_tce: it_map is not empty");
 		ret = -EBUSY;
-		/* Undo iommu_table_release_pages, i.e. restore bit#0, etc */
-		iommu_table_reserve_pages(tbl, tbl->it_reserved_start,
-				tbl->it_reserved_end);
 	} else {
 		memset(tbl->it_map, 0xff, sz);
 	}
diff --git a/arch/powerpc/kernel/kdebugfs.c b/arch/powerpc/kernel/kdebugfs.c
new file mode 100644
index 000000000000..36d3124d5a8b
--- /dev/null
+++ b/arch/powerpc/kernel/kdebugfs.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/debugfs.h>
+#include <linux/export.h>
+#include <linux/init.h>
+
+struct dentry *arch_debugfs_dir;
+EXPORT_SYMBOL(arch_debugfs_dir);
+
+static int __init arch_kdebugfs_init(void)
+{
+	arch_debugfs_dir = debugfs_create_dir("powerpc", NULL);
+	return 0;
+}
+arch_initcall(arch_kdebugfs_init);
diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S
index 5be96feccb55..fb7de3543c03 100644
--- a/arch/powerpc/kernel/misc.S
+++ b/arch/powerpc/kernel/misc.S
@@ -29,7 +29,7 @@ _GLOBAL(reloc_offset)
 	li	r3, 0
 _GLOBAL(add_reloc_offset)
 	mflr	r0
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r5
 	PPC_LL	r4,(2f-1b)(r5)
 	subf	r5,r4,r5
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 39ab15419592..e5127b19fec2 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -67,7 +67,7 @@ _GLOBAL(reloc_got2)
 	srwi.	r8,r8,2
 	beqlr
 	mtctr	r8
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r0
 	lis	r4,1b@ha
 	addi	r4,r4,1b@l
@@ -237,7 +237,7 @@ _GLOBAL(copy_page)
 	addi	r3,r3,-4
 
 0:	twnei	r5, 0	/* WARN if r3 is not cache aligned */
-	EMIT_BUG_ENTRY 0b,__FILE__,__LINE__, BUGFLAG_WARNING
+	EMIT_WARN_ENTRY 0b,__FILE__,__LINE__, BUGFLAG_WARNING
 
 	addi	r4,r4,-4
 
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 4b761a18a74d..d38a019b38e1 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -255,7 +255,7 @@ _GLOBAL(scom970_write)
  * Physical (hardware) cpu id should be in r3.
  */
 _GLOBAL(kexec_wait)
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r5
 	addi	r5,r5,kexec_flag-1b
 
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 001e90cd8948..c3573430919d 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -29,6 +29,7 @@
 #include <linux/slab.h>
 #include <linux/vgaarb.h>
 #include <linux/numa.h>
+#include <linux/msi.h>
 
 #include <asm/processor.h>
 #include <asm/io.h>
@@ -1060,11 +1061,16 @@ void pcibios_bus_add_device(struct pci_dev *dev)
 
 int pcibios_add_device(struct pci_dev *dev)
 {
+	struct irq_domain *d;
+
 #ifdef CONFIG_PCI_IOV
 	if (ppc_md.pcibios_fixup_sriov)
 		ppc_md.pcibios_fixup_sriov(dev);
 #endif /* CONFIG_PCI_IOV */
 
+	d = dev_get_msi_domain(&dev->bus->dev);
+	if (d)
+		dev_set_msi_domain(&dev->dev, d);
 	return 0;
 }
 
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 185beb290580..50436b52c213 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1499,7 +1499,7 @@ static void __show_regs(struct pt_regs *regs)
 	    trap == INTERRUPT_DATA_STORAGE ||
 	    trap == INTERRUPT_ALIGNMENT) {
 		if (IS_ENABLED(CONFIG_4xx) || IS_ENABLED(CONFIG_BOOKE))
-			pr_cont("DEAR: "REG" ESR: "REG" ", regs->dar, regs->dsisr);
+			pr_cont("DEAR: "REG" ESR: "REG" ", regs->dear, regs->esr);
 		else
 			pr_cont("DAR: "REG" DSISR: %08lx ", regs->dar, regs->dsisr);
 	}
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index f620e04dc9bf..44b2cdc0aae3 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -640,7 +640,9 @@ static void __init early_reserve_mem(void)
 	}
 #endif /* CONFIG_BLK_DEV_INITRD */
 
-#ifdef CONFIG_PPC32
+	if (!IS_ENABLED(CONFIG_PPC32))
+		return;
+
 	/* 
 	 * Handle the case where we might be booting from an old kexec
 	 * image that setup the mem_rsvmap as pairs of 32-bit values
@@ -661,7 +663,6 @@ static void __init early_reserve_mem(void)
 		}
 		return;
 	}
-#endif
 }
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index a5bf355ce1d6..95a42d49e291 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -1096,7 +1096,8 @@ static const struct ibm_arch_vec ibm_architecture_vec_template __initconst = {
 #else
 		0,
 #endif
-		.associativity = OV5_FEAT(OV5_TYPE1_AFFINITY) | OV5_FEAT(OV5_PRRN),
+		.associativity = OV5_FEAT(OV5_FORM1_AFFINITY) | OV5_FEAT(OV5_PRRN) |
+		OV5_FEAT(OV5_FORM2_AFFINITY),
 		.bin_opts = OV5_FEAT(OV5_RESIZE_HPT) | OV5_FEAT(OV5_HP_EVT),
 		.micro_checkpoint = 0,
 		.reserved0 = 0,
diff --git a/arch/powerpc/kernel/ptrace/ptrace.c b/arch/powerpc/kernel/ptrace/ptrace.c
index 0a0a33eb0d28..7c7093c17c45 100644
--- a/arch/powerpc/kernel/ptrace/ptrace.c
+++ b/arch/powerpc/kernel/ptrace/ptrace.c
@@ -373,8 +373,12 @@ void __init pt_regs_check(void)
 		     offsetof(struct user_pt_regs, trap));
 	BUILD_BUG_ON(offsetof(struct pt_regs, dar) !=
 		     offsetof(struct user_pt_regs, dar));
+	BUILD_BUG_ON(offsetof(struct pt_regs, dear) !=
+		     offsetof(struct user_pt_regs, dar));
 	BUILD_BUG_ON(offsetof(struct pt_regs, dsisr) !=
 		     offsetof(struct user_pt_regs, dsisr));
+	BUILD_BUG_ON(offsetof(struct pt_regs, esr) !=
+		     offsetof(struct user_pt_regs, dsisr));
 	BUILD_BUG_ON(offsetof(struct pt_regs, result) !=
 		     offsetof(struct user_pt_regs, result));
 
diff --git a/arch/powerpc/kernel/reloc_32.S b/arch/powerpc/kernel/reloc_32.S
index 10e96f3e22fe..0508c14b4c28 100644
--- a/arch/powerpc/kernel/reloc_32.S
+++ b/arch/powerpc/kernel/reloc_32.S
@@ -30,7 +30,7 @@ R_PPC_RELATIVE = 22
 _GLOBAL(relocate)
 
 	mflr	r0		/* Save our LR */
-	bl	0f		/* Find our current runtime address */
+	bcl	20,31,$+4	/* Find our current runtime address */
 0:	mflr	r12		/* Make it accessible */
 	mtlr	r0
 
diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c
index 8561dfb33f24..32ee17753eb4 100644
--- a/arch/powerpc/kernel/rtasd.c
+++ b/arch/powerpc/kernel/rtasd.c
@@ -429,7 +429,7 @@ static void rtas_event_scan(struct work_struct *w)
 
 	do_event_scan();
 
-	get_online_cpus();
+	cpus_read_lock();
 
 	/* raw_ OK because just using CPU as starting point. */
 	cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask);
@@ -451,7 +451,7 @@ static void rtas_event_scan(struct work_struct *w)
 	schedule_delayed_work_on(cpu, &event_scan_work,
 		__round_jiffies_relative(event_scan_delay, cpu));
 
-	put_online_cpus();
+	cpus_read_unlock();
 }
 
 #ifdef CONFIG_PPC64
diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c
index cc51fa52e783..1a998490fe60 100644
--- a/arch/powerpc/kernel/security.c
+++ b/arch/powerpc/kernel/security.c
@@ -11,10 +11,10 @@
 #include <linux/nospec.h>
 #include <linux/prctl.h>
 #include <linux/seq_buf.h>
+#include <linux/debugfs.h>
 
 #include <asm/asm-prototypes.h>
 #include <asm/code-patching.h>
-#include <asm/debugfs.h>
 #include <asm/security_features.h>
 #include <asm/setup.h>
 #include <asm/inst.h>
@@ -106,7 +106,7 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_barrier_nospec, barrier_nospec_get,
 static __init int barrier_nospec_debugfs_init(void)
 {
 	debugfs_create_file_unsafe("barrier_nospec", 0600,
-				   powerpc_debugfs_root, NULL,
+				   arch_debugfs_dir, NULL,
 				   &fops_barrier_nospec);
 	return 0;
 }
@@ -114,7 +114,7 @@ device_initcall(barrier_nospec_debugfs_init);
 
 static __init int security_feature_debugfs_init(void)
 {
-	debugfs_create_x64("security_features", 0400, powerpc_debugfs_root,
+	debugfs_create_x64("security_features", 0400, arch_debugfs_dir,
 			   &powerpc_security_features);
 	return 0;
 }
@@ -420,7 +420,7 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_stf_barrier, stf_barrier_get, stf_barrier_set,
 
 static __init int stf_barrier_debugfs_init(void)
 {
-	debugfs_create_file_unsafe("stf_barrier", 0600, powerpc_debugfs_root,
+	debugfs_create_file_unsafe("stf_barrier", 0600, arch_debugfs_dir,
 				   NULL, &fops_stf_barrier);
 	return 0;
 }
@@ -748,7 +748,7 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_count_cache_flush, count_cache_flush_get,
 static __init int count_cache_flush_debugfs_init(void)
 {
 	debugfs_create_file_unsafe("count_cache_flush", 0600,
-				   powerpc_debugfs_root, NULL,
+				   arch_debugfs_dir, NULL,
 				   &fops_count_cache_flush);
 	return 0;
 }
@@ -834,9 +834,9 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_uaccess_flush, uaccess_flush_get, uaccess_flush_set
 
 static __init int rfi_flush_debugfs_init(void)
 {
-	debugfs_create_file("rfi_flush", 0600, powerpc_debugfs_root, NULL, &fops_rfi_flush);
-	debugfs_create_file("entry_flush", 0600, powerpc_debugfs_root, NULL, &fops_entry_flush);
-	debugfs_create_file("uaccess_flush", 0600, powerpc_debugfs_root, NULL, &fops_uaccess_flush);
+	debugfs_create_file("rfi_flush", 0600, arch_debugfs_dir, NULL, &fops_rfi_flush);
+	debugfs_create_file("entry_flush", 0600, arch_debugfs_dir, NULL, &fops_entry_flush);
+	debugfs_create_file("uaccess_flush", 0600, arch_debugfs_dir, NULL, &fops_uaccess_flush);
 	return 0;
 }
 device_initcall(rfi_flush_debugfs_init);
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index aa9c2d01424a..b1e43b69a559 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -33,7 +33,6 @@
 #include <linux/of_platform.h>
 #include <linux/hugetlb.h>
 #include <linux/pgtable.h>
-#include <asm/debugfs.h>
 #include <asm/io.h>
 #include <asm/paca.h>
 #include <asm/prom.h>
@@ -773,18 +772,6 @@ static int __init check_cache_coherency(void)
 late_initcall(check_cache_coherency);
 #endif /* CONFIG_CHECK_CACHE_COHERENCY */
 
-#ifdef CONFIG_DEBUG_FS
-struct dentry *powerpc_debugfs_root;
-EXPORT_SYMBOL(powerpc_debugfs_root);
-
-static int powerpc_debugfs_init(void)
-{
-	powerpc_debugfs_root = debugfs_create_dir("powerpc", NULL);
-	return 0;
-}
-arch_initcall(powerpc_debugfs_init);
-#endif
-
 void ppc_printk_progress(char *s, unsigned short hex)
 {
 	pr_info("%s\n", s);
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 1ff258f6c76c..eaa79a0996d1 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -32,7 +32,6 @@
 #include <linux/nmi.h>
 #include <linux/pgtable.h>
 
-#include <asm/debugfs.h>
 #include <asm/kvm_guest.h>
 #include <asm/io.h>
 #include <asm/kdump.h>
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 447b78a87c8f..9cc7d3dbf439 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -78,6 +78,7 @@ struct task_struct *secondary_current;
 bool has_big_cores;
 bool coregroup_enabled;
 bool thread_group_shares_l2;
+bool thread_group_shares_l3;
 
 DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
 DEFINE_PER_CPU(cpumask_var_t, cpu_smallcore_map);
@@ -101,7 +102,7 @@ enum {
 
 #define MAX_THREAD_LIST_SIZE	8
 #define THREAD_GROUP_SHARE_L1   1
-#define THREAD_GROUP_SHARE_L2   2
+#define THREAD_GROUP_SHARE_L2_L3 2
 struct thread_groups {
 	unsigned int property;
 	unsigned int nr_groups;
@@ -122,14 +123,20 @@ static struct thread_groups_list tgl[NR_CPUS] __initdata;
  * On big-cores system, thread_group_l1_cache_map for each CPU corresponds to
  * the set its siblings that share the L1-cache.
  */
-static DEFINE_PER_CPU(cpumask_var_t, thread_group_l1_cache_map);
+DEFINE_PER_CPU(cpumask_var_t, thread_group_l1_cache_map);
 
 /*
  * On some big-cores system, thread_group_l2_cache_map for each CPU
  * corresponds to the set its siblings within the core that share the
  * L2-cache.
  */
-static DEFINE_PER_CPU(cpumask_var_t, thread_group_l2_cache_map);
+DEFINE_PER_CPU(cpumask_var_t, thread_group_l2_cache_map);
+
+/*
+ * On P10, thread_group_l3_cache_map for each CPU is equal to the
+ * thread_group_l2_cache_map
+ */
+DEFINE_PER_CPU(cpumask_var_t, thread_group_l3_cache_map);
 
 /* SMP operations for this machine */
 struct smp_ops_t *smp_ops;
@@ -889,33 +896,10 @@ out:
 	return tg;
 }
 
-static int __init init_thread_group_cache_map(int cpu, int cache_property)
-
+static int update_mask_from_threadgroup(cpumask_var_t *mask, struct thread_groups *tg, int cpu, int cpu_group_start)
 {
 	int first_thread = cpu_first_thread_sibling(cpu);
-	int i, cpu_group_start = -1, err = 0;
-	struct thread_groups *tg = NULL;
-	cpumask_var_t *mask = NULL;
-
-	if (cache_property != THREAD_GROUP_SHARE_L1 &&
-	    cache_property != THREAD_GROUP_SHARE_L2)
-		return -EINVAL;
-
-	tg = get_thread_groups(cpu, cache_property, &err);
-	if (!tg)
-		return err;
-
-	cpu_group_start = get_cpu_thread_group_start(cpu, tg);
-
-	if (unlikely(cpu_group_start == -1)) {
-		WARN_ON_ONCE(1);
-		return -ENODATA;
-	}
-
-	if (cache_property == THREAD_GROUP_SHARE_L1)
-		mask = &per_cpu(thread_group_l1_cache_map, cpu);
-	else if (cache_property == THREAD_GROUP_SHARE_L2)
-		mask = &per_cpu(thread_group_l2_cache_map, cpu);
+	int i;
 
 	zalloc_cpumask_var_node(mask, GFP_KERNEL, cpu_to_node(cpu));
 
@@ -934,6 +918,44 @@ static int __init init_thread_group_cache_map(int cpu, int cache_property)
 	return 0;
 }
 
+static int __init init_thread_group_cache_map(int cpu, int cache_property)
+
+{
+	int cpu_group_start = -1, err = 0;
+	struct thread_groups *tg = NULL;
+	cpumask_var_t *mask = NULL;
+
+	if (cache_property != THREAD_GROUP_SHARE_L1 &&
+	    cache_property != THREAD_GROUP_SHARE_L2_L3)
+		return -EINVAL;
+
+	tg = get_thread_groups(cpu, cache_property, &err);
+
+	if (!tg)
+		return err;
+
+	cpu_group_start = get_cpu_thread_group_start(cpu, tg);
+
+	if (unlikely(cpu_group_start == -1)) {
+		WARN_ON_ONCE(1);
+		return -ENODATA;
+	}
+
+	if (cache_property == THREAD_GROUP_SHARE_L1) {
+		mask = &per_cpu(thread_group_l1_cache_map, cpu);
+		update_mask_from_threadgroup(mask, tg, cpu, cpu_group_start);
+	}
+	else if (cache_property == THREAD_GROUP_SHARE_L2_L3) {
+		mask = &per_cpu(thread_group_l2_cache_map, cpu);
+		update_mask_from_threadgroup(mask, tg, cpu, cpu_group_start);
+		mask = &per_cpu(thread_group_l3_cache_map, cpu);
+		update_mask_from_threadgroup(mask, tg, cpu, cpu_group_start);
+	}
+
+
+	return 0;
+}
+
 static bool shared_caches;
 
 #ifdef CONFIG_SCHED_SMT
@@ -1020,14 +1042,16 @@ static int __init init_big_cores(void)
 	has_big_cores = true;
 
 	for_each_possible_cpu(cpu) {
-		int err = init_thread_group_cache_map(cpu, THREAD_GROUP_SHARE_L2);
+		int err = init_thread_group_cache_map(cpu, THREAD_GROUP_SHARE_L2_L3);
 
 		if (err)
 			return err;
 	}
 
 	thread_group_shares_l2 = true;
-	pr_debug("L2 cache only shared by the threads in the small core\n");
+	thread_group_shares_l3 = true;
+	pr_debug("L2/L3 cache only shared by the threads in the small core\n");
+
 	return 0;
 }
 
@@ -1085,7 +1109,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	}
 
 	if (cpu_to_chip_id(boot_cpuid) != -1) {
-		int idx = num_possible_cpus() / threads_per_core;
+		int idx = DIV_ROUND_UP(num_possible_cpus(), threads_per_core);
 
 		/*
 		 * All threads of a core will all belong to the same core,
@@ -1376,7 +1400,7 @@ static bool update_mask_by_l2(int cpu, cpumask_var_t *mask)
 	l2_cache = cpu_to_l2cache(cpu);
 	if (!l2_cache || !*mask) {
 		/* Assume only core siblings share cache with this CPU */
-		for_each_cpu(i, submask_fn(cpu))
+		for_each_cpu(i, cpu_sibling_mask(cpu))
 			set_cpus_related(cpu, i, cpu_l2_cache_mask);
 
 		return false;
@@ -1418,6 +1442,8 @@ static void remove_cpu_from_masks(int cpu)
 	struct cpumask *(*mask_fn)(int) = cpu_sibling_mask;
 	int i;
 
+	unmap_cpu_from_node(cpu);
+
 	if (shared_caches)
 		mask_fn = cpu_l2_cache_mask;
 
@@ -1502,7 +1528,9 @@ static void add_cpu_to_masks(int cpu)
 	 * This CPU will not be in the online mask yet so we need to manually
 	 * add it to it's own thread sibling mask.
 	 */
+	map_cpu_to_node(cpu, cpu_to_node(cpu));
 	cpumask_set_cpu(cpu, cpu_sibling_mask(cpu));
+	cpumask_set_cpu(cpu, cpu_core_mask(cpu));
 
 	for (i = first_thread; i < first_thread + threads_per_core; i++)
 		if (cpu_online(i))
@@ -1520,11 +1548,6 @@ static void add_cpu_to_masks(int cpu)
 	if (chip_id_lookup_table && ret)
 		chip_id = cpu_to_chip_id(cpu);
 
-	if (chip_id == -1) {
-		cpumask_copy(per_cpu(cpu_core_map, cpu), cpu_cpu_mask(cpu));
-		goto out;
-	}
-
 	if (shared_caches)
 		submask_fn = cpu_l2_cache_mask;
 
@@ -1534,6 +1557,10 @@ static void add_cpu_to_masks(int cpu)
 	/* Skip all CPUs already part of current CPU core mask */
 	cpumask_andnot(mask, cpu_online_mask, cpu_core_mask(cpu));
 
+	/* If chip_id is -1; limit the cpu_core_mask to within DIE*/
+	if (chip_id == -1)
+		cpumask_and(mask, mask, cpu_cpu_mask(cpu));
+
 	for_each_cpu(i, mask) {
 		if (chip_id == cpu_to_chip_id(i)) {
 			or_cpumasks_related(cpu, i, submask_fn, cpu_core_mask);
@@ -1543,7 +1570,6 @@ static void add_cpu_to_masks(int cpu)
 		}
 	}
 
-out:
 	free_cpumask_var(mask);
 }
 
diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c
index 2b0d04a1b7d2..9e4a4a7af380 100644
--- a/arch/powerpc/kernel/stacktrace.c
+++ b/arch/powerpc/kernel/stacktrace.c
@@ -8,6 +8,7 @@
  * Copyright 2018 Nick Piggin, Michael Ellerman, IBM Corp.
  */
 
+#include <linux/delay.h>
 #include <linux/export.h>
 #include <linux/kallsyms.h>
 #include <linux/module.h>
diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c
index bf4ae0f0e36c..825931e400df 100644
--- a/arch/powerpc/kernel/syscalls.c
+++ b/arch/powerpc/kernel/syscalls.c
@@ -41,20 +41,13 @@ static inline long do_mmap2(unsigned long addr, size_t len,
 			unsigned long prot, unsigned long flags,
 			unsigned long fd, unsigned long off, int shift)
 {
-	long ret = -EINVAL;
-
 	if (!arch_validate_prot(prot, addr))
-		goto out;
+		return -EINVAL;
 
-	if (shift) {
-		if (off & ((1 << shift) - 1))
-			goto out;
-		off >>= shift;
-	}
+	if (!IS_ALIGNED(off, 1 << shift))
+		return -EINVAL;
 
-	ret = ksys_mmap_pgoff(addr, len, prot, flags, fd, off);
-out:
-	return ret;
+	return ksys_mmap_pgoff(addr, len, prot, flags, fd, off >> shift);
 }
 
 SYSCALL_DEFINE6(mmap2, unsigned long, addr, size_t, len,
diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c
index b9a047d92ec0..8e83d19fe8fa 100644
--- a/arch/powerpc/kernel/tau_6xx.c
+++ b/arch/powerpc/kernel/tau_6xx.c
@@ -164,7 +164,7 @@ static void tau_work_func(struct work_struct *work)
 	queue_work(tau_workq, work);
 }
 
-DECLARE_WORK(tau_work, tau_work_func);
+static DECLARE_WORK(tau_work, tau_work_func);
 
 /*
  * setup the TAU
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index c487ba5a6e11..934d8ae66cc6 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -31,6 +31,7 @@
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
+#include <linux/sched/cputime.h>
 #include <linux/kernel.h>
 #include <linux/param.h>
 #include <linux/string.h>
@@ -52,8 +53,6 @@
 #include <linux/irq_work.h>
 #include <linux/of_clk.h>
 #include <linux/suspend.h>
-#include <linux/sched/cputime.h>
-#include <linux/sched/clock.h>
 #include <linux/processor.h>
 #include <asm/trace.h>
 
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index cd5f633c9b1b..4390f8d72126 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -37,10 +37,10 @@
 #include <linux/smp.h>
 #include <linux/console.h>
 #include <linux/kmsg_dump.h>
+#include <linux/debugfs.h>
 
 #include <asm/emulated_ops.h>
 #include <linux/uaccess.h>
-#include <asm/debugfs.h>
 #include <asm/interrupt.h>
 #include <asm/io.h>
 #include <asm/machdep.h>
@@ -427,7 +427,7 @@ void hv_nmi_check_nonrecoverable(struct pt_regs *regs)
 	return;
 
 nonrecoverable:
-	regs_set_return_msr(regs, regs->msr & ~MSR_RI);
+	regs_set_unrecoverable(regs);
 #endif
 }
 DEFINE_INTERRUPT_HANDLER_NMI(system_reset_exception)
@@ -497,7 +497,7 @@ out:
 		die("Unrecoverable nested System Reset", regs, SIGABRT);
 #endif
 	/* Must die if the interrupt is not recoverable */
-	if (!(regs->msr & MSR_RI)) {
+	if (regs_is_unrecoverable(regs)) {
 		/* For the reason explained in die_mce, nmi_exit before die */
 		nmi_exit();
 		die("Unrecoverable System Reset", regs, SIGABRT);
@@ -549,7 +549,7 @@ static inline int check_io_access(struct pt_regs *regs)
 			printk(KERN_DEBUG "%s bad port %lx at %p\n",
 			       (*nip & 0x100)? "OUT to": "IN from",
 			       regs->gpr[rb] - _IO_BASE, nip);
-			regs_set_return_msr(regs, regs->msr | MSR_RI);
+			regs_set_recoverable(regs);
 			regs_set_return_ip(regs, extable_fixup(entry));
 			return 1;
 		}
@@ -561,7 +561,7 @@ static inline int check_io_access(struct pt_regs *regs)
 #ifdef CONFIG_PPC_ADV_DEBUG_REGS
 /* On 4xx, the reason for the machine check or program exception
    is in the ESR. */
-#define get_reason(regs)	((regs)->dsisr)
+#define get_reason(regs)	((regs)->esr)
 #define REASON_FP		ESR_FP
 #define REASON_ILLEGAL		(ESR_PIL | ESR_PUO)
 #define REASON_PRIVILEGED	ESR_PPR
@@ -839,7 +839,7 @@ DEFINE_INTERRUPT_HANDLER_NMI(machine_check_exception)
 
 bail:
 	/* Must die if the interrupt is not recoverable */
-	if (!(regs->msr & MSR_RI))
+	if (regs_is_unrecoverable(regs))
 		die_mce("Unrecoverable Machine check", regs, SIGBUS);
 
 #ifdef CONFIG_PPC_BOOK3S_64
@@ -1481,8 +1481,13 @@ static void do_program_check(struct pt_regs *regs)
 
 		if (!(regs->msr & MSR_PR) &&  /* not user-mode */
 		    report_bug(bugaddr, regs) == BUG_TRAP_TYPE_WARN) {
-			regs_add_return_ip(regs, 4);
-			return;
+			const struct exception_table_entry *entry;
+
+			entry = search_exception_tables(bugaddr);
+			if (entry) {
+				regs_set_return_ip(regs, extable_fixup(entry) + regs->nip - bugaddr);
+				return;
+			}
 		}
 		_exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
 		return;
@@ -2271,7 +2276,7 @@ static int __init ppc_warn_emulated_init(void)
 	struct ppc_emulated_entry *entries = (void *)&ppc_emulated;
 
 	dir = debugfs_create_dir("emulated_instructions",
-				 powerpc_debugfs_root);
+				 arch_debugfs_dir);
 
 	debugfs_create_u32("do_warn", 0644, dir, &ppc_warn_emulated);
 
diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S
index fc120fac1910..ba03eedfdcd8 100644
--- a/arch/powerpc/kernel/vector.S
+++ b/arch/powerpc/kernel/vector.S
@@ -65,9 +65,8 @@ _GLOBAL(load_up_altivec)
 1:
 	/* enable use of VMX after return */
 #ifdef CONFIG_PPC32
-	mfspr	r5,SPRN_SPRG_THREAD		/* current task's THREAD (phys) */
+	addi	r5,r2,THREAD
 	oris	r9,r9,MSR_VEC@h
-	tovirt(r5, r5)
 #else
 	ld	r4,PACACURRENT(r13)
 	addi	r5,r4,THREAD		/* Get THREAD */
@@ -81,7 +80,6 @@ _GLOBAL(load_up_altivec)
 	li	r4,1
 	stb	r4,THREAD_LOAD_VEC(r5)
 	addi	r6,r5,THREAD_VRSTATE
-	li	r4,1
 	li	r10,VRSTATE_VSCR
 	stw	r4,THREAD_USED_VR(r5)
 	lvx	v0,r10,r6
diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c
index 8a449b2d8715..89c069d664a5 100644
--- a/arch/powerpc/kexec/core_64.c
+++ b/arch/powerpc/kexec/core_64.c
@@ -64,15 +64,18 @@ int default_machine_kexec_prepare(struct kimage *image)
 			begin = image->segment[i].mem;
 			end = begin + image->segment[i].memsz;
 
-			if ((begin < high) && (end > low))
+			if ((begin < high) && (end > low)) {
+				of_node_put(node);
 				return -ETXTBSY;
+			}
 		}
 	}
 
 	return 0;
 }
 
-static void copy_segments(unsigned long ind)
+/* Called during kexec sequence with MMU off */
+static notrace void copy_segments(unsigned long ind)
 {
 	unsigned long entry;
 	unsigned long *ptr;
@@ -105,7 +108,8 @@ static void copy_segments(unsigned long ind)
 	}
 }
 
-void kexec_copy_flush(struct kimage *image)
+/* Called during kexec sequence with MMU off */
+notrace void kexec_copy_flush(struct kimage *image)
 {
 	long i, nr_segments = image->nr_segments;
 	struct  kexec_segment ranges[KEXEC_SEGMENT_MAX];
diff --git a/arch/powerpc/kexec/relocate_32.S b/arch/powerpc/kexec/relocate_32.S
index 61946c19e07c..cf6e52bdf8d8 100644
--- a/arch/powerpc/kexec/relocate_32.S
+++ b/arch/powerpc/kexec/relocate_32.S
@@ -93,7 +93,7 @@ wmmucr:
 	 * Invalidate all the TLB entries except the current entry
 	 * where we are running from
 	 */
-	bl	0f				/* Find our address */
+	bcl	20,31,$+4			/* Find our address */
 0:	mflr	r5				/* Make it accessible */
 	tlbsx	r23,0,r5			/* Find entry we are in */
 	li	r4,0				/* Start at TLB entry 0 */
@@ -158,7 +158,7 @@ write_out:
 	/* Switch to other address space in MSR */
 	insrwi	r9, r7, 1, 26		/* Set MSR[IS] = r7 */
 
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r8
 	addi	r8, r8, (2f-1b)		/* Find the target offset */
 
@@ -202,7 +202,7 @@ next_tlb:
 	li	r9,0
 	insrwi	r9, r7, 1, 26			/* Set MSR[IS] = r7 */
 
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r8
 	and	r8, r8, r11			/* Get our offset within page */
 	addi	r8, r8, (2f-1b)
@@ -240,7 +240,7 @@ setup_map_47x:
 	sync
 
 	/* Find the entry we are running from */
-	bl	2f
+	bcl	20,31,$+4
 2:	mflr	r23
 	tlbsx	r23, 0, r23
 	tlbre	r24, r23, 0			/* TLB Word 0 */
@@ -296,7 +296,7 @@ clear_utlb_entry:
 	/* Update the msr to the new TS */
 	insrwi	r5, r7, 1, 26
 
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r6
 	addi	r6, r6, (2f-1b)
 
@@ -355,7 +355,7 @@ write_utlb:
 	/* Defaults to 256M */
 	lis	r10, 0x1000
 
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r4
 	addi	r4, r4, (2f-1b)			/* virtual address  of 2f */
 
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index e45644657d49..ff581d70f20c 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -38,7 +38,6 @@ config KVM_BOOK3S_32_HANDLER
 config KVM_BOOK3S_64_HANDLER
 	bool
 	select KVM_BOOK3S_HANDLER
-	select PPC_DAWR_FORCE_ENABLE
 
 config KVM_BOOK3S_PR_POSSIBLE
 	bool
diff --git a/arch/powerpc/kvm/book3s.h b/arch/powerpc/kvm/book3s.h
index 740e51def5a5..58391b4b32ed 100644
--- a/arch/powerpc/kvm/book3s.h
+++ b/arch/powerpc/kvm/book3s.h
@@ -23,7 +23,8 @@ extern int kvmppc_core_emulate_mtspr_pr(struct kvm_vcpu *vcpu,
 extern int kvmppc_core_emulate_mfspr_pr(struct kvm_vcpu *vcpu,
 					int sprn, ulong *spr_val);
 extern int kvmppc_book3s_init_pr(void);
-extern void kvmppc_book3s_exit_pr(void);
+void kvmppc_book3s_exit_pr(void);
+extern int kvmppc_handle_exit_pr(struct kvm_vcpu *vcpu, unsigned int exit_nr);
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 extern void kvmppc_emulate_tabort(struct kvm_vcpu *vcpu, int ra_val);
diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c
index 26b8b27a3755..feee40cb2ba1 100644
--- a/arch/powerpc/kvm/book3s_64_mmu.c
+++ b/arch/powerpc/kvm/book3s_64_mmu.c
@@ -196,7 +196,7 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	hva_t ptegp;
 	u64 pteg[16];
 	u64 avpn = 0;
-	u64 v, r;
+	u64 r;
 	u64 v_val, v_mask;
 	u64 eaddr_mask;
 	int i;
@@ -285,7 +285,6 @@ do_second:
 		goto do_second;
 	}
 
-	v = be64_to_cpu(pteg[i]);
 	r = be64_to_cpu(pteg[i+1]);
 	pp = (r & HPTE_R_PP) | key;
 	if (r & HPTE_R_PP0)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index b5905ae4377c..16359525a40f 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -44,6 +44,9 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid,
 					  (to != NULL) ? __pa(to): 0,
 					  (from != NULL) ? __pa(from): 0, n);
 
+	if (eaddr & (0xFFFUL << 52))
+		return ret;
+
 	quadrant = 1;
 	if (!pid)
 		quadrant = 2;
@@ -65,10 +68,12 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid,
 	}
 	isync();
 
+	pagefault_disable();
 	if (is_load)
-		ret = copy_from_user_nofault(to, (const void __user *)from, n);
+		ret = __copy_from_user_inatomic(to, (const void __user *)from, n);
 	else
-		ret = copy_to_user_nofault((void __user *)to, from, n);
+		ret = __copy_to_user_inatomic((void __user *)to, from, n);
+	pagefault_enable();
 
 	/* switch the pid first to avoid running host with unallocated pid */
 	if (quadrant == 1 && pid != old_pid)
@@ -81,7 +86,6 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid,
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(__kvmhv_copy_tofrom_guest_radix);
 
 static long kvmhv_copy_tofrom_guest_radix(struct kvm_vcpu *vcpu, gva_t eaddr,
 					  void *to, void *from, unsigned long n)
@@ -117,14 +121,12 @@ long kvmhv_copy_from_guest_radix(struct kvm_vcpu *vcpu, gva_t eaddr, void *to,
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(kvmhv_copy_from_guest_radix);
 
 long kvmhv_copy_to_guest_radix(struct kvm_vcpu *vcpu, gva_t eaddr, void *from,
 			       unsigned long n)
 {
 	return kvmhv_copy_tofrom_guest_radix(vcpu, eaddr, NULL, from, n);
 }
-EXPORT_SYMBOL_GPL(kvmhv_copy_to_guest_radix);
 
 int kvmppc_mmu_walk_radix_tree(struct kvm_vcpu *vcpu, gva_t eaddr,
 			       struct kvmppc_pte *gpte, u64 root,
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index dc6591548f0c..636c6ae0939b 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -173,10 +173,13 @@ static void kvmppc_rm_tce_put(struct kvmppc_spapr_tce_table *stt,
 	idx -= stt->offset;
 	page = stt->pages[idx / TCES_PER_PAGE];
 	/*
-	 * page must not be NULL in real mode,
-	 * kvmppc_rm_ioba_validate() must have taken care of this.
+	 * kvmppc_rm_ioba_validate() allows pages not be allocated if TCE is
+	 * being cleared, otherwise it returns H_TOO_HARD and we skip this.
 	 */
-	WARN_ON_ONCE_RM(!page);
+	if (!page) {
+		WARN_ON_ONCE_RM(tce != 0);
+		return;
+	}
 	tbl = kvmppc_page_address(page);
 
 	tbl[idx % TCES_PER_PAGE] = tce;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 085fb8ecbf68..bb0dacf7cbec 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -59,6 +59,7 @@
 #include <asm/kvm_book3s.h>
 #include <asm/mmu_context.h>
 #include <asm/lppaca.h>
+#include <asm/pmc.h>
 #include <asm/processor.h>
 #include <asm/cputhreads.h>
 #include <asm/page.h>
@@ -1165,7 +1166,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 		break;
 #endif
 	case H_RANDOM:
-		if (!powernv_get_random_long(&vcpu->arch.regs.gpr[4]))
+		if (!arch_get_random_seed_long(&vcpu->arch.regs.gpr[4]))
 			ret = H_HARDWARE;
 		break;
 	case H_RPT_INVALIDATE:
@@ -1679,6 +1680,21 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
 			r = RESUME_GUEST;
 		}
 		break;
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	case BOOK3S_INTERRUPT_HV_SOFTPATCH:
+		/*
+		 * This occurs for various TM-related instructions that
+		 * we need to emulate on POWER9 DD2.2.  We have already
+		 * handled the cases where the guest was in real-suspend
+		 * mode and was transitioning to transactional state.
+		 */
+		r = kvmhv_p9_tm_emulation(vcpu);
+		if (r != -1)
+			break;
+		fallthrough; /* go to facility unavailable handler */
+#endif
+
 	/*
 	 * This occurs if the guest (kernel or userspace), does something that
 	 * is prohibited by HFSCR.
@@ -1697,18 +1713,6 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
 		}
 		break;
 
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-	case BOOK3S_INTERRUPT_HV_SOFTPATCH:
-		/*
-		 * This occurs for various TM-related instructions that
-		 * we need to emulate on POWER9 DD2.2.  We have already
-		 * handled the cases where the guest was in real-suspend
-		 * mode and was transitioning to transactional state.
-		 */
-		r = kvmhv_p9_tm_emulation(vcpu);
-		break;
-#endif
-
 	case BOOK3S_INTERRUPT_HV_RM_HARD:
 		r = RESUME_PASSTHROUGH;
 		break;
@@ -1727,6 +1731,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
 
 static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu)
 {
+	struct kvm_nested_guest *nested = vcpu->arch.nested;
 	int r;
 	int srcu_idx;
 
@@ -1811,9 +1816,41 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu)
 		 * mode and was transitioning to transactional state.
 		 */
 		r = kvmhv_p9_tm_emulation(vcpu);
-		break;
+		if (r != -1)
+			break;
+		fallthrough; /* go to facility unavailable handler */
 #endif
 
+	case BOOK3S_INTERRUPT_H_FAC_UNAVAIL: {
+		u64 cause = vcpu->arch.hfscr >> 56;
+
+		/*
+		 * Only pass HFU interrupts to the L1 if the facility is
+		 * permitted but disabled by the L1's HFSCR, otherwise
+		 * the interrupt does not make sense to the L1 so turn
+		 * it into a HEAI.
+		 */
+		if (!(vcpu->arch.hfscr_permitted & (1UL << cause)) ||
+					(nested->hfscr & (1UL << cause))) {
+			vcpu->arch.trap = BOOK3S_INTERRUPT_H_EMUL_ASSIST;
+
+			/*
+			 * If the fetch failed, return to guest and
+			 * try executing it again.
+			 */
+			r = kvmppc_get_last_inst(vcpu, INST_GENERIC,
+						 &vcpu->arch.emul_inst);
+			if (r != EMULATE_DONE)
+				r = RESUME_GUEST;
+			else
+				r = RESUME_HOST;
+		} else {
+			r = RESUME_HOST;
+		}
+
+		break;
+	}
+
 	case BOOK3S_INTERRUPT_HV_RM_HARD:
 		vcpu->arch.trap = 0;
 		r = RESUME_GUEST;
@@ -2684,6 +2721,7 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu)
 	spin_lock_init(&vcpu->arch.vpa_update_lock);
 	spin_lock_init(&vcpu->arch.tbacct_lock);
 	vcpu->arch.busy_preempt = TB_NIL;
+	vcpu->arch.shregs.msr = MSR_ME;
 	vcpu->arch.intr_msr = MSR_SF | MSR_ME;
 
 	/*
@@ -2705,6 +2743,8 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu)
 	if (cpu_has_feature(CPU_FTR_TM_COMP))
 		vcpu->arch.hfscr |= HFSCR_TM;
 
+	vcpu->arch.hfscr_permitted = vcpu->arch.hfscr;
+
 	kvmppc_mmu_book3s_hv_init(vcpu);
 
 	vcpu->arch.state = KVMPPC_VCPU_NOTREADY;
@@ -3727,7 +3767,6 @@ static void load_spr_state(struct kvm_vcpu *vcpu)
 	mtspr(SPRN_EBBHR, vcpu->arch.ebbhr);
 	mtspr(SPRN_EBBRR, vcpu->arch.ebbrr);
 	mtspr(SPRN_BESCR, vcpu->arch.bescr);
-	mtspr(SPRN_WORT, vcpu->arch.wort);
 	mtspr(SPRN_TIDR, vcpu->arch.tid);
 	mtspr(SPRN_AMR, vcpu->arch.amr);
 	mtspr(SPRN_UAMOR, vcpu->arch.uamor);
@@ -3754,7 +3793,6 @@ static void store_spr_state(struct kvm_vcpu *vcpu)
 	vcpu->arch.ebbhr = mfspr(SPRN_EBBHR);
 	vcpu->arch.ebbrr = mfspr(SPRN_EBBRR);
 	vcpu->arch.bescr = mfspr(SPRN_BESCR);
-	vcpu->arch.wort = mfspr(SPRN_WORT);
 	vcpu->arch.tid = mfspr(SPRN_TIDR);
 	vcpu->arch.amr = mfspr(SPRN_AMR);
 	vcpu->arch.uamor = mfspr(SPRN_UAMOR);
@@ -3786,7 +3824,6 @@ static void restore_p9_host_os_sprs(struct kvm_vcpu *vcpu,
 				    struct p9_host_os_sprs *host_os_sprs)
 {
 	mtspr(SPRN_PSPB, 0);
-	mtspr(SPRN_WORT, 0);
 	mtspr(SPRN_UAMOR, 0);
 
 	mtspr(SPRN_DSCR, host_os_sprs->dscr);
@@ -3852,6 +3889,18 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 	    cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST))
 		kvmppc_restore_tm_hv(vcpu, vcpu->arch.shregs.msr, true);
 
+#ifdef CONFIG_PPC_PSERIES
+	if (kvmhv_on_pseries()) {
+		barrier();
+		if (vcpu->arch.vpa.pinned_addr) {
+			struct lppaca *lp = vcpu->arch.vpa.pinned_addr;
+			get_lppaca()->pmcregs_in_use = lp->pmcregs_in_use;
+		} else {
+			get_lppaca()->pmcregs_in_use = 1;
+		}
+		barrier();
+	}
+#endif
 	kvmhv_load_guest_pmu(vcpu);
 
 	msr_check_and_set(MSR_FP | MSR_VEC | MSR_VSX);
@@ -3986,6 +4035,13 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 	save_pmu |= nesting_enabled(vcpu->kvm);
 
 	kvmhv_save_guest_pmu(vcpu, save_pmu);
+#ifdef CONFIG_PPC_PSERIES
+	if (kvmhv_on_pseries()) {
+		barrier();
+		get_lppaca()->pmcregs_in_use = ppc_get_pmu_inuse();
+		barrier();
+	}
+#endif
 
 	vc->entry_exit_map = 0x101;
 	vc->in_guest = 0;
@@ -5328,6 +5384,7 @@ static int kvmppc_set_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi)
 	struct kvmppc_passthru_irqmap *pimap;
 	struct irq_chip *chip;
 	int i, rc = 0;
+	struct irq_data *host_data;
 
 	if (!kvm_irq_bypass)
 		return 1;
@@ -5355,7 +5412,7 @@ static int kvmppc_set_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi)
 	 * what our real-mode EOI code does, or a XIVE interrupt
 	 */
 	chip = irq_data_get_irq_chip(&desc->irq_data);
-	if (!chip || !(is_pnv_opal_msi(chip) || is_xive_irq(chip))) {
+	if (!chip || !is_pnv_opal_msi(chip)) {
 		pr_warn("kvmppc_set_passthru_irq_hv: Could not assign IRQ map for (%d,%d)\n",
 			host_irq, guest_gsi);
 		mutex_unlock(&kvm->lock);
@@ -5392,15 +5449,22 @@ static int kvmppc_set_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi)
 	 * the KVM real mode handler.
 	 */
 	smp_wmb();
-	irq_map->r_hwirq = desc->irq_data.hwirq;
+
+	/*
+	 * The 'host_irq' number is mapped in the PCI-MSI domain but
+	 * the underlying calls, which will EOI the interrupt in real
+	 * mode, need an HW IRQ number mapped in the XICS IRQ domain.
+	 */
+	host_data = irq_domain_get_irq_data(irq_get_default_host(), host_irq);
+	irq_map->r_hwirq = (unsigned int)irqd_to_hwirq(host_data);
 
 	if (i == pimap->n_mapped)
 		pimap->n_mapped++;
 
 	if (xics_on_xive())
-		rc = kvmppc_xive_set_mapped(kvm, guest_gsi, desc);
+		rc = kvmppc_xive_set_mapped(kvm, guest_gsi, host_irq);
 	else
-		kvmppc_xics_set_mapped(kvm, guest_gsi, desc->irq_data.hwirq);
+		kvmppc_xics_set_mapped(kvm, guest_gsi, irq_map->r_hwirq);
 	if (rc)
 		irq_map->r_hwirq = 0;
 
@@ -5439,7 +5503,7 @@ static int kvmppc_clr_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi)
 	}
 
 	if (xics_on_xive())
-		rc = kvmppc_xive_clr_mapped(kvm, guest_gsi, pimap->mapped[i].desc);
+		rc = kvmppc_xive_clr_mapped(kvm, guest_gsi, host_irq);
 	else
 		kvmppc_xics_clr_mapped(kvm, guest_gsi, pimap->mapped[i].r_hwirq);
 
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index be8ef1c5b1bf..fcf4760a3a0e 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -137,23 +137,23 @@ long int kvmppc_rm_h_confer(struct kvm_vcpu *vcpu, int target,
  * exist in the system. We use a counter of VMs to track this.
  *
  * One of the operations we need to block is onlining of secondaries, so we
- * protect hv_vm_count with get/put_online_cpus().
+ * protect hv_vm_count with cpus_read_lock/unlock().
  */
 static atomic_t hv_vm_count;
 
 void kvm_hv_vm_activated(void)
 {
-	get_online_cpus();
+	cpus_read_lock();
 	atomic_inc(&hv_vm_count);
-	put_online_cpus();
+	cpus_read_unlock();
 }
 EXPORT_SYMBOL_GPL(kvm_hv_vm_activated);
 
 void kvm_hv_vm_deactivated(void)
 {
-	get_online_cpus();
+	cpus_read_lock();
 	atomic_dec(&hv_vm_count);
-	put_online_cpus();
+	cpus_read_unlock();
 }
 EXPORT_SYMBOL_GPL(kvm_hv_vm_deactivated);
 
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index 898f942eb198..ed8a2c9f5629 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -99,13 +99,12 @@ static void byteswap_hv_regs(struct hv_guest_state *hr)
 	hr->dawrx1 = swab64(hr->dawrx1);
 }
 
-static void save_hv_return_state(struct kvm_vcpu *vcpu, int trap,
+static void save_hv_return_state(struct kvm_vcpu *vcpu,
 				 struct hv_guest_state *hr)
 {
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 
 	hr->dpdes = vc->dpdes;
-	hr->hfscr = vcpu->arch.hfscr;
 	hr->purr = vcpu->arch.purr;
 	hr->spurr = vcpu->arch.spurr;
 	hr->ic = vcpu->arch.ic;
@@ -119,7 +118,7 @@ static void save_hv_return_state(struct kvm_vcpu *vcpu, int trap,
 	hr->pidr = vcpu->arch.pid;
 	hr->cfar = vcpu->arch.cfar;
 	hr->ppr = vcpu->arch.ppr;
-	switch (trap) {
+	switch (vcpu->arch.trap) {
 	case BOOK3S_INTERRUPT_H_DATA_STORAGE:
 		hr->hdar = vcpu->arch.fault_dar;
 		hr->hdsisr = vcpu->arch.fault_dsisr;
@@ -128,55 +127,17 @@ static void save_hv_return_state(struct kvm_vcpu *vcpu, int trap,
 	case BOOK3S_INTERRUPT_H_INST_STORAGE:
 		hr->asdr = vcpu->arch.fault_gpa;
 		break;
+	case BOOK3S_INTERRUPT_H_FAC_UNAVAIL:
+		hr->hfscr = ((~HFSCR_INTR_CAUSE & hr->hfscr) |
+			     (HFSCR_INTR_CAUSE & vcpu->arch.hfscr));
+		break;
 	case BOOK3S_INTERRUPT_H_EMUL_ASSIST:
 		hr->heir = vcpu->arch.emul_inst;
 		break;
 	}
 }
 
-/*
- * This can result in some L0 HV register state being leaked to an L1
- * hypervisor when the hv_guest_state is copied back to the guest after
- * being modified here.
- *
- * There is no known problem with such a leak, and in many cases these
- * register settings could be derived by the guest by observing behaviour
- * and timing, interrupts, etc., but it is an issue to consider.
- */
-static void sanitise_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
-{
-	struct kvmppc_vcore *vc = vcpu->arch.vcore;
-	u64 mask;
-
-	/*
-	 * Don't let L1 change LPCR bits for the L2 except these:
-	 */
-	mask = LPCR_DPFD | LPCR_ILE | LPCR_TC | LPCR_AIL | LPCR_LD |
-		LPCR_LPES | LPCR_MER;
-
-	/*
-	 * Additional filtering is required depending on hardware
-	 * and configuration.
-	 */
-	hr->lpcr = kvmppc_filter_lpcr_hv(vcpu->kvm,
-			(vc->lpcr & ~mask) | (hr->lpcr & mask));
-
-	/*
-	 * Don't let L1 enable features for L2 which we've disabled for L1,
-	 * but preserve the interrupt cause field.
-	 */
-	hr->hfscr &= (HFSCR_INTR_CAUSE | vcpu->arch.hfscr);
-
-	/* Don't let data address watchpoint match in hypervisor state */
-	hr->dawrx0 &= ~DAWRX_HYP;
-	hr->dawrx1 &= ~DAWRX_HYP;
-
-	/* Don't let completed instruction address breakpt match in HV state */
-	if ((hr->ciabr & CIABR_PRIV) == CIABR_PRIV_HYPER)
-		hr->ciabr &= ~CIABR_PRIV;
-}
-
-static void restore_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
+static void restore_hv_regs(struct kvm_vcpu *vcpu, const struct hv_guest_state *hr)
 {
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 
@@ -288,6 +249,43 @@ static int kvmhv_write_guest_state_and_regs(struct kvm_vcpu *vcpu,
 				     sizeof(struct pt_regs));
 }
 
+static void load_l2_hv_regs(struct kvm_vcpu *vcpu,
+			    const struct hv_guest_state *l2_hv,
+			    const struct hv_guest_state *l1_hv, u64 *lpcr)
+{
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+	u64 mask;
+
+	restore_hv_regs(vcpu, l2_hv);
+
+	/*
+	 * Don't let L1 change LPCR bits for the L2 except these:
+	 */
+	mask = LPCR_DPFD | LPCR_ILE | LPCR_TC | LPCR_AIL | LPCR_LD |
+		LPCR_LPES | LPCR_MER;
+
+	/*
+	 * Additional filtering is required depending on hardware
+	 * and configuration.
+	 */
+	*lpcr = kvmppc_filter_lpcr_hv(vcpu->kvm,
+				      (vc->lpcr & ~mask) | (*lpcr & mask));
+
+	/*
+	 * Don't let L1 enable features for L2 which we don't allow for L1,
+	 * but preserve the interrupt cause field.
+	 */
+	vcpu->arch.hfscr = l2_hv->hfscr & (HFSCR_INTR_CAUSE | vcpu->arch.hfscr_permitted);
+
+	/* Don't let data address watchpoint match in hypervisor state */
+	vcpu->arch.dawrx0 = l2_hv->dawrx0 & ~DAWRX_HYP;
+	vcpu->arch.dawrx1 = l2_hv->dawrx1 & ~DAWRX_HYP;
+
+	/* Don't let completed instruction address breakpt match in HV state */
+	if ((l2_hv->ciabr & CIABR_PRIV) == CIABR_PRIV_HYPER)
+		vcpu->arch.ciabr = l2_hv->ciabr & ~CIABR_PRIV;
+}
+
 long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
 {
 	long int err, r;
@@ -296,7 +294,7 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
 	struct hv_guest_state l2_hv = {0}, saved_l1_hv;
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 	u64 hv_ptr, regs_ptr;
-	u64 hdec_exp;
+	u64 hdec_exp, lpcr;
 	s64 delta_purr, delta_spurr, delta_ic, delta_vtb;
 
 	if (vcpu->kvm->arch.l1_ptcr == 0)
@@ -364,13 +362,14 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
 	/* set L1 state to L2 state */
 	vcpu->arch.nested = l2;
 	vcpu->arch.nested_vcpu_id = l2_hv.vcpu_token;
+	l2->hfscr = l2_hv.hfscr;
 	vcpu->arch.regs = l2_regs;
 
 	/* Guest must always run with ME enabled, HV disabled. */
 	vcpu->arch.shregs.msr = (vcpu->arch.regs.msr | MSR_ME) & ~MSR_HV;
 
-	sanitise_hv_regs(vcpu, &l2_hv);
-	restore_hv_regs(vcpu, &l2_hv);
+	lpcr = l2_hv.lpcr;
+	load_l2_hv_regs(vcpu, &l2_hv, &saved_l1_hv, &lpcr);
 
 	vcpu->arch.ret = RESUME_GUEST;
 	vcpu->arch.trap = 0;
@@ -380,7 +379,7 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
 			r = RESUME_HOST;
 			break;
 		}
-		r = kvmhv_run_single_vcpu(vcpu, hdec_exp, l2_hv.lpcr);
+		r = kvmhv_run_single_vcpu(vcpu, hdec_exp, lpcr);
 	} while (is_kvmppc_resume_guest(r));
 
 	/* save L2 state for return */
@@ -390,7 +389,7 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
 	delta_spurr = vcpu->arch.spurr - l2_hv.spurr;
 	delta_ic = vcpu->arch.ic - l2_hv.ic;
 	delta_vtb = vc->vtb - l2_hv.vtb;
-	save_hv_return_state(vcpu, vcpu->arch.trap, &l2_hv);
+	save_hv_return_state(vcpu, &l2_hv);
 
 	/* restore L1 state */
 	vcpu->arch.nested = NULL;
diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c
index 0a11ec88a0ae..587c33fc4564 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_xics.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c
@@ -706,6 +706,7 @@ static int ics_rm_eoi(struct kvm_vcpu *vcpu, u32 irq)
 		icp->rm_eoied_irq = irq;
 	}
 
+	/* Handle passthrough interrupts */
 	if (state->host_irq) {
 		++vcpu->stat.pthru_all;
 		if (state->intr_cpu != -1) {
@@ -759,12 +760,12 @@ int xics_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr)
 
 static unsigned long eoi_rc;
 
-static void icp_eoi(struct irq_chip *c, u32 hwirq, __be32 xirr, bool *again)
+static void icp_eoi(struct irq_data *d, u32 hwirq, __be32 xirr, bool *again)
 {
 	void __iomem *xics_phys;
 	int64_t rc;
 
-	rc = pnv_opal_pci_msi_eoi(c, hwirq);
+	rc = pnv_opal_pci_msi_eoi(d);
 
 	if (rc)
 		eoi_rc = rc;
@@ -872,8 +873,7 @@ long kvmppc_deliver_irq_passthru(struct kvm_vcpu *vcpu,
 		icp_rm_deliver_irq(xics, icp, irq, false);
 
 	/* EOI the interrupt */
-	icp_eoi(irq_desc_get_chip(irq_map->desc), irq_map->r_hwirq, xirr,
-		again);
+	icp_eoi(irq_desc_get_irq_data(irq_map->desc), irq_map->r_hwirq, xirr, again);
 
 	if (check_too_hard(xics, icp) == H_TOO_HARD)
 		return 2;
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 8dd437d7a2c6..75079397c2a5 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1088,12 +1088,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	cmpwi	r12, BOOK3S_INTERRUPT_H_INST_STORAGE
 	beq	kvmppc_hisi
 
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-	/* For softpatch interrupt, go off and do TM instruction emulation */
-	cmpwi	r12, BOOK3S_INTERRUPT_HV_SOFTPATCH
-	beq	kvmppc_tm_emul
-#endif
-
 	/* See if this is a leftover HDEC interrupt */
 	cmpwi	r12,BOOK3S_INTERRUPT_HV_DECREMENTER
 	bne	2f
@@ -1599,42 +1593,6 @@ maybe_reenter_guest:
 	blt	deliver_guest_interrupt
 	b	guest_exit_cont
 
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-/*
- * Softpatch interrupt for transactional memory emulation cases
- * on POWER9 DD2.2.  This is early in the guest exit path - we
- * haven't saved registers or done a treclaim yet.
- */
-kvmppc_tm_emul:
-	/* Save instruction image in HEIR */
-	mfspr	r3, SPRN_HEIR
-	stw	r3, VCPU_HEIR(r9)
-
-	/*
-	 * The cases we want to handle here are those where the guest
-	 * is in real suspend mode and is trying to transition to
-	 * transactional mode.
-	 */
-	lbz	r0, HSTATE_FAKE_SUSPEND(r13)
-	cmpwi	r0, 0		/* keep exiting guest if in fake suspend */
-	bne	guest_exit_cont
-	rldicl	r3, r11, 64 - MSR_TS_S_LG, 62
-	cmpwi	r3, 1		/* or if not in suspend state */
-	bne	guest_exit_cont
-
-	/* Call C code to do the emulation */
-	mr	r3, r9
-	bl	kvmhv_p9_tm_emulation_early
-	nop
-	ld	r9, HSTATE_KVM_VCPU(r13)
-	li	r12, BOOK3S_INTERRUPT_HV_SOFTPATCH
-	cmpwi	r3, 0
-	beq	guest_exit_cont		/* continue exiting if not handled */
-	ld	r10, VCPU_PC(r9)
-	ld	r11, VCPU_MSR(r9)
-	b	fast_interrupt_c_return	/* go back to guest if handled */
-#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
-
 /*
  * Check whether an HDSI is an HPTE not found fault or something else.
  * If it is an HPTE not found fault that is due to the guest accessing
diff --git a/arch/powerpc/kvm/book3s_hv_tm.c b/arch/powerpc/kvm/book3s_hv_tm.c
index cc90b8b82329..866cadd70094 100644
--- a/arch/powerpc/kvm/book3s_hv_tm.c
+++ b/arch/powerpc/kvm/book3s_hv_tm.c
@@ -46,6 +46,15 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 	u64 newmsr, bescr;
 	int ra, rs;
 
+	/*
+	 * The TM softpatch interrupt sets NIP to the instruction following
+	 * the faulting instruction, which is not executed. Rewind nip to the
+	 * faulting instruction so it looks like a normal synchronous
+	 * interrupt, then update nip in the places where the instruction is
+	 * emulated.
+	 */
+	vcpu->arch.regs.nip -= 4;
+
 	/*
 	 * rfid, rfebb, and mtmsrd encode bit 31 = 0 since it's a reserved bit
 	 * in these instructions, so masking bit 31 out doesn't change these
@@ -67,7 +76,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 			       (newmsr & MSR_TM)));
 		newmsr = sanitize_msr(newmsr);
 		vcpu->arch.shregs.msr = newmsr;
-		vcpu->arch.cfar = vcpu->arch.regs.nip - 4;
+		vcpu->arch.cfar = vcpu->arch.regs.nip;
 		vcpu->arch.regs.nip = vcpu->arch.shregs.srr0;
 		return RESUME_GUEST;
 
@@ -79,14 +88,15 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		}
 		/* check EBB facility is available */
 		if (!(vcpu->arch.hfscr & HFSCR_EBB)) {
-			/* generate an illegal instruction interrupt */
-			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
-			return RESUME_GUEST;
+			vcpu->arch.hfscr &= ~HFSCR_INTR_CAUSE;
+			vcpu->arch.hfscr |= (u64)FSCR_EBB_LG << 56;
+			vcpu->arch.trap = BOOK3S_INTERRUPT_H_FAC_UNAVAIL;
+			return -1; /* rerun host interrupt handler */
 		}
 		if ((msr & MSR_PR) && !(vcpu->arch.fscr & FSCR_EBB)) {
 			/* generate a facility unavailable interrupt */
-			vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
-				((u64)FSCR_EBB_LG << 56);
+			vcpu->arch.fscr &= ~FSCR_INTR_CAUSE;
+			vcpu->arch.fscr |= (u64)FSCR_EBB_LG << 56;
 			kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_FAC_UNAVAIL);
 			return RESUME_GUEST;
 		}
@@ -100,7 +110,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		vcpu->arch.bescr = bescr;
 		msr = (msr & ~MSR_TS_MASK) | MSR_TS_T;
 		vcpu->arch.shregs.msr = msr;
-		vcpu->arch.cfar = vcpu->arch.regs.nip - 4;
+		vcpu->arch.cfar = vcpu->arch.regs.nip;
 		vcpu->arch.regs.nip = vcpu->arch.ebbrr;
 		return RESUME_GUEST;
 
@@ -116,6 +126,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		newmsr = (newmsr & ~MSR_LE) | (msr & MSR_LE);
 		newmsr = sanitize_msr(newmsr);
 		vcpu->arch.shregs.msr = newmsr;
+		vcpu->arch.regs.nip += 4;
 		return RESUME_GUEST;
 
 	/* ignore bit 31, see comment above */
@@ -128,14 +139,15 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		}
 		/* check for TM disabled in the HFSCR or MSR */
 		if (!(vcpu->arch.hfscr & HFSCR_TM)) {
-			/* generate an illegal instruction interrupt */
-			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
-			return RESUME_GUEST;
+			vcpu->arch.hfscr &= ~HFSCR_INTR_CAUSE;
+			vcpu->arch.hfscr |= (u64)FSCR_TM_LG << 56;
+			vcpu->arch.trap = BOOK3S_INTERRUPT_H_FAC_UNAVAIL;
+			return -1; /* rerun host interrupt handler */
 		}
 		if (!(msr & MSR_TM)) {
 			/* generate a facility unavailable interrupt */
-			vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
-				((u64)FSCR_TM_LG << 56);
+			vcpu->arch.fscr &= ~FSCR_INTR_CAUSE;
+			vcpu->arch.fscr |= (u64)FSCR_TM_LG << 56;
 			kvmppc_book3s_queue_irqprio(vcpu,
 						BOOK3S_INTERRUPT_FAC_UNAVAIL);
 			return RESUME_GUEST;
@@ -152,20 +164,22 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 				msr = (msr & ~MSR_TS_MASK) | MSR_TS_S;
 		}
 		vcpu->arch.shregs.msr = msr;
+		vcpu->arch.regs.nip += 4;
 		return RESUME_GUEST;
 
 	/* ignore bit 31, see comment above */
 	case (PPC_INST_TRECLAIM & PO_XOP_OPCODE_MASK):
 		/* check for TM disabled in the HFSCR or MSR */
 		if (!(vcpu->arch.hfscr & HFSCR_TM)) {
-			/* generate an illegal instruction interrupt */
-			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
-			return RESUME_GUEST;
+			vcpu->arch.hfscr &= ~HFSCR_INTR_CAUSE;
+			vcpu->arch.hfscr |= (u64)FSCR_TM_LG << 56;
+			vcpu->arch.trap = BOOK3S_INTERRUPT_H_FAC_UNAVAIL;
+			return -1; /* rerun host interrupt handler */
 		}
 		if (!(msr & MSR_TM)) {
 			/* generate a facility unavailable interrupt */
-			vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
-				((u64)FSCR_TM_LG << 56);
+			vcpu->arch.fscr &= ~FSCR_INTR_CAUSE;
+			vcpu->arch.fscr |= (u64)FSCR_TM_LG << 56;
 			kvmppc_book3s_queue_irqprio(vcpu,
 						BOOK3S_INTERRUPT_FAC_UNAVAIL);
 			return RESUME_GUEST;
@@ -189,6 +203,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		vcpu->arch.regs.ccr = (vcpu->arch.regs.ccr & 0x0fffffff) |
 			(((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 29);
 		vcpu->arch.shregs.msr &= ~MSR_TS_MASK;
+		vcpu->arch.regs.nip += 4;
 		return RESUME_GUEST;
 
 	/* ignore bit 31, see comment above */
@@ -196,14 +211,15 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		/* XXX do we need to check for PR=0 here? */
 		/* check for TM disabled in the HFSCR or MSR */
 		if (!(vcpu->arch.hfscr & HFSCR_TM)) {
-			/* generate an illegal instruction interrupt */
-			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
-			return RESUME_GUEST;
+			vcpu->arch.hfscr &= ~HFSCR_INTR_CAUSE;
+			vcpu->arch.hfscr |= (u64)FSCR_TM_LG << 56;
+			vcpu->arch.trap = BOOK3S_INTERRUPT_H_FAC_UNAVAIL;
+			return -1; /* rerun host interrupt handler */
 		}
 		if (!(msr & MSR_TM)) {
 			/* generate a facility unavailable interrupt */
-			vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
-				((u64)FSCR_TM_LG << 56);
+			vcpu->arch.fscr &= ~FSCR_INTR_CAUSE;
+			vcpu->arch.fscr |= (u64)FSCR_TM_LG << 56;
 			kvmppc_book3s_queue_irqprio(vcpu,
 						BOOK3S_INTERRUPT_FAC_UNAVAIL);
 			return RESUME_GUEST;
@@ -220,6 +236,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		vcpu->arch.regs.ccr = (vcpu->arch.regs.ccr & 0x0fffffff) |
 			(((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 29);
 		vcpu->arch.shregs.msr = msr | MSR_TS_S;
+		vcpu->arch.regs.nip += 4;
 		return RESUME_GUEST;
 	}
 
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index 303e3cb096db..ebd5d920de8c 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -10,13 +10,13 @@
 #include <linux/gfp.h>
 #include <linux/anon_inodes.h>
 #include <linux/spinlock.h>
-
+#include <linux/debugfs.h>
 #include <linux/uaccess.h>
+
 #include <asm/kvm_book3s.h>
 #include <asm/kvm_ppc.h>
 #include <asm/hvcall.h>
 #include <asm/xics.h>
-#include <asm/debugfs.h>
 #include <asm/time.h>
 
 #include <linux/seq_file.h>
@@ -1024,7 +1024,7 @@ static void xics_debugfs_init(struct kvmppc_xics *xics)
 		return;
 	}
 
-	xics->dentry = debugfs_create_file(name, 0444, powerpc_debugfs_root,
+	xics->dentry = debugfs_create_file(name, 0444, arch_debugfs_dir,
 					   xics, &xics_debug_fops);
 
 	pr_debug("%s: created %s\n", __func__, name);
diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
index 8cfab3547494..a18db9e16ea4 100644
--- a/arch/powerpc/kvm/book3s_xive.c
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -22,7 +22,6 @@
 #include <asm/xive.h>
 #include <asm/xive-regs.h>
 #include <asm/debug.h>
-#include <asm/debugfs.h>
 #include <asm/time.h>
 #include <asm/opal.h>
 
@@ -59,6 +58,25 @@
  */
 #define XIVE_Q_GAP	2
 
+static bool kvmppc_xive_vcpu_has_save_restore(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+
+	/* Check enablement at VP level */
+	return xc->vp_cam & TM_QW1W2_HO;
+}
+
+bool kvmppc_xive_check_save_restore(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+	struct kvmppc_xive *xive = xc->xive;
+
+	if (xive->flags & KVMPPC_XIVE_FLAG_SAVE_RESTORE)
+		return kvmppc_xive_vcpu_has_save_restore(vcpu);
+
+	return true;
+}
+
 /*
  * Push a vcpu's context to the XIVE on guest entry.
  * This assumes we are in virtual mode (MMU on)
@@ -77,7 +95,8 @@ void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu)
 		return;
 
 	eieio();
-	__raw_writeq(vcpu->arch.xive_saved_state.w01, tima + TM_QW1_OS);
+	if (!kvmppc_xive_vcpu_has_save_restore(vcpu))
+		__raw_writeq(vcpu->arch.xive_saved_state.w01, tima + TM_QW1_OS);
 	__raw_writel(vcpu->arch.xive_cam_word, tima + TM_QW1_OS + TM_WORD2);
 	vcpu->arch.xive_pushed = 1;
 	eieio();
@@ -149,7 +168,8 @@ void kvmppc_xive_pull_vcpu(struct kvm_vcpu *vcpu)
 	/* First load to pull the context, we ignore the value */
 	__raw_readl(tima + TM_SPC_PULL_OS_CTX);
 	/* Second load to recover the context state (Words 0 and 1) */
-	vcpu->arch.xive_saved_state.w01 = __raw_readq(tima + TM_QW1_OS);
+	if (!kvmppc_xive_vcpu_has_save_restore(vcpu))
+		vcpu->arch.xive_saved_state.w01 = __raw_readq(tima + TM_QW1_OS);
 
 	/* Fixup some of the state for the next load */
 	vcpu->arch.xive_saved_state.lsmfb = 0;
@@ -363,9 +383,9 @@ static int xive_check_provisioning(struct kvm *kvm, u8 prio)
 		if (!vcpu->arch.xive_vcpu)
 			continue;
 		rc = xive_provision_queue(vcpu, prio);
-		if (rc == 0 && !xive->single_escalation)
+		if (rc == 0 && !kvmppc_xive_has_single_escalation(xive))
 			kvmppc_xive_attach_escalation(vcpu, prio,
-						      xive->single_escalation);
+						      kvmppc_xive_has_single_escalation(xive));
 		if (rc)
 			return rc;
 	}
@@ -922,13 +942,13 @@ int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval)
 }
 
 int kvmppc_xive_set_mapped(struct kvm *kvm, unsigned long guest_irq,
-			   struct irq_desc *host_desc)
+			   unsigned long host_irq)
 {
 	struct kvmppc_xive *xive = kvm->arch.xive;
 	struct kvmppc_xive_src_block *sb;
 	struct kvmppc_xive_irq_state *state;
-	struct irq_data *host_data = irq_desc_get_irq_data(host_desc);
-	unsigned int host_irq = irq_desc_get_irq(host_desc);
+	struct irq_data *host_data =
+		irq_domain_get_irq_data(irq_get_default_host(), host_irq);
 	unsigned int hw_irq = (unsigned int)irqd_to_hwirq(host_data);
 	u16 idx;
 	u8 prio;
@@ -937,7 +957,8 @@ int kvmppc_xive_set_mapped(struct kvm *kvm, unsigned long guest_irq,
 	if (!xive)
 		return -ENODEV;
 
-	pr_devel("set_mapped girq 0x%lx host HW irq 0x%x...\n",guest_irq, hw_irq);
+	pr_debug("%s: GIRQ 0x%lx host IRQ %ld XIVE HW IRQ 0x%x\n",
+		 __func__, guest_irq, host_irq, hw_irq);
 
 	sb = kvmppc_xive_find_source(xive, guest_irq, &idx);
 	if (!sb)
@@ -959,7 +980,7 @@ int kvmppc_xive_set_mapped(struct kvm *kvm, unsigned long guest_irq,
 	 */
 	rc = irq_set_vcpu_affinity(host_irq, state);
 	if (rc) {
-		pr_err("Failed to set VCPU affinity for irq %d\n", host_irq);
+		pr_err("Failed to set VCPU affinity for host IRQ %ld\n", host_irq);
 		return rc;
 	}
 
@@ -1019,12 +1040,11 @@ int kvmppc_xive_set_mapped(struct kvm *kvm, unsigned long guest_irq,
 EXPORT_SYMBOL_GPL(kvmppc_xive_set_mapped);
 
 int kvmppc_xive_clr_mapped(struct kvm *kvm, unsigned long guest_irq,
-			   struct irq_desc *host_desc)
+			   unsigned long host_irq)
 {
 	struct kvmppc_xive *xive = kvm->arch.xive;
 	struct kvmppc_xive_src_block *sb;
 	struct kvmppc_xive_irq_state *state;
-	unsigned int host_irq = irq_desc_get_irq(host_desc);
 	u16 idx;
 	u8 prio;
 	int rc;
@@ -1032,7 +1052,7 @@ int kvmppc_xive_clr_mapped(struct kvm *kvm, unsigned long guest_irq,
 	if (!xive)
 		return -ENODEV;
 
-	pr_devel("clr_mapped girq 0x%lx...\n", guest_irq);
+	pr_debug("%s: GIRQ 0x%lx host IRQ %ld\n", __func__, guest_irq, host_irq);
 
 	sb = kvmppc_xive_find_source(xive, guest_irq, &idx);
 	if (!sb)
@@ -1059,7 +1079,7 @@ int kvmppc_xive_clr_mapped(struct kvm *kvm, unsigned long guest_irq,
 	/* Release the passed-through interrupt to the host */
 	rc = irq_set_vcpu_affinity(host_irq, NULL);
 	if (rc) {
-		pr_err("Failed to clr VCPU affinity for irq %d\n", host_irq);
+		pr_err("Failed to clr VCPU affinity for host IRQ %ld\n", host_irq);
 		return rc;
 	}
 
@@ -1199,7 +1219,7 @@ void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu)
 	/* Free escalations */
 	for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
 		if (xc->esc_virq[i]) {
-			if (xc->xive->single_escalation)
+			if (kvmppc_xive_has_single_escalation(xc->xive))
 				xive_cleanup_single_escalation(vcpu, xc,
 							xc->esc_virq[i]);
 			free_irq(xc->esc_virq[i], vcpu);
@@ -1319,6 +1339,12 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 	if (r)
 		goto bail;
 
+	if (!kvmppc_xive_check_save_restore(vcpu)) {
+		pr_err("inconsistent save-restore setup for VCPU %d\n", cpu);
+		r = -EIO;
+		goto bail;
+	}
+
 	/* Configure VCPU fields for use by assembly push/pull */
 	vcpu->arch.xive_saved_state.w01 = cpu_to_be64(0xff000000);
 	vcpu->arch.xive_cam_word = cpu_to_be32(xc->vp_cam | TM_QW1W2_VO);
@@ -1340,7 +1366,7 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 	 * Enable the VP first as the single escalation mode will
 	 * affect escalation interrupts numbering
 	 */
-	r = xive_native_enable_vp(xc->vp_id, xive->single_escalation);
+	r = xive_native_enable_vp(xc->vp_id, kvmppc_xive_has_single_escalation(xive));
 	if (r) {
 		pr_err("Failed to enable VP in OPAL, err %d\n", r);
 		goto bail;
@@ -1357,15 +1383,15 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 		struct xive_q *q = &xc->queues[i];
 
 		/* Single escalation, no queue 7 */
-		if (i == 7 && xive->single_escalation)
+		if (i == 7 && kvmppc_xive_has_single_escalation(xive))
 			break;
 
 		/* Is queue already enabled ? Provision it */
 		if (xive->qmap & (1 << i)) {
 			r = xive_provision_queue(vcpu, i);
-			if (r == 0 && !xive->single_escalation)
+			if (r == 0 && !kvmppc_xive_has_single_escalation(xive))
 				kvmppc_xive_attach_escalation(
-					vcpu, i, xive->single_escalation);
+					vcpu, i, kvmppc_xive_has_single_escalation(xive));
 			if (r)
 				goto bail;
 		} else {
@@ -1380,7 +1406,7 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 	}
 
 	/* If not done above, attach priority 0 escalation */
-	r = kvmppc_xive_attach_escalation(vcpu, 0, xive->single_escalation);
+	r = kvmppc_xive_attach_escalation(vcpu, 0, kvmppc_xive_has_single_escalation(xive));
 	if (r)
 		goto bail;
 
@@ -2135,7 +2161,11 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type)
 	 */
 	xive->nr_servers = KVM_MAX_VCPUS;
 
-	xive->single_escalation = xive_native_has_single_escalation();
+	if (xive_native_has_single_escalation())
+		xive->flags |= KVMPPC_XIVE_FLAG_SINGLE_ESCALATION;
+
+	if (xive_native_has_save_restore())
+		xive->flags |= KVMPPC_XIVE_FLAG_SAVE_RESTORE;
 
 	kvm->arch.xive = xive;
 	return 0;
@@ -2329,7 +2359,7 @@ static void xive_debugfs_init(struct kvmppc_xive *xive)
 		return;
 	}
 
-	xive->dentry = debugfs_create_file(name, S_IRUGO, powerpc_debugfs_root,
+	xive->dentry = debugfs_create_file(name, S_IRUGO, arch_debugfs_dir,
 					   xive, &xive_debug_fops);
 
 	pr_debug("%s: created %s\n", __func__, name);
diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h
index afe9eeac6d56..e6a9651c6f1e 100644
--- a/arch/powerpc/kvm/book3s_xive.h
+++ b/arch/powerpc/kvm/book3s_xive.h
@@ -97,6 +97,9 @@ struct kvmppc_xive_ops {
 	int (*reset_mapped)(struct kvm *kvm, unsigned long guest_irq);
 };
 
+#define KVMPPC_XIVE_FLAG_SINGLE_ESCALATION 0x1
+#define KVMPPC_XIVE_FLAG_SAVE_RESTORE 0x2
+
 struct kvmppc_xive {
 	struct kvm *kvm;
 	struct kvm_device *dev;
@@ -133,7 +136,7 @@ struct kvmppc_xive {
 	u32	q_page_order;
 
 	/* Flags */
-	u8	single_escalation;
+	u8	flags;
 
 	/* Number of entries in the VP block */
 	u32	nr_servers;
@@ -307,6 +310,12 @@ void xive_cleanup_single_escalation(struct kvm_vcpu *vcpu,
 				    struct kvmppc_xive_vcpu *xc, int irq);
 int kvmppc_xive_compute_vp_id(struct kvmppc_xive *xive, u32 cpu, u32 *vp);
 int kvmppc_xive_set_nr_servers(struct kvmppc_xive *xive, u64 addr);
+bool kvmppc_xive_check_save_restore(struct kvm_vcpu *vcpu);
+
+static inline bool kvmppc_xive_has_single_escalation(struct kvmppc_xive *xive)
+{
+	return xive->flags & KVMPPC_XIVE_FLAG_SINGLE_ESCALATION;
+}
 
 #endif /* CONFIG_KVM_XICS */
 #endif /* _KVM_PPC_BOOK3S_XICS_H */
diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c
index 573ecaab3597..99db9ac49901 100644
--- a/arch/powerpc/kvm/book3s_xive_native.c
+++ b/arch/powerpc/kvm/book3s_xive_native.c
@@ -20,7 +20,6 @@
 #include <asm/xive.h>
 #include <asm/xive-regs.h>
 #include <asm/debug.h>
-#include <asm/debugfs.h>
 #include <asm/opal.h>
 
 #include <linux/debugfs.h>
@@ -93,7 +92,7 @@ void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu)
 	for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
 		/* Free the escalation irq */
 		if (xc->esc_virq[i]) {
-			if (xc->xive->single_escalation)
+			if (kvmppc_xive_has_single_escalation(xc->xive))
 				xive_cleanup_single_escalation(vcpu, xc,
 							xc->esc_virq[i]);
 			free_irq(xc->esc_virq[i], vcpu);
@@ -168,11 +167,17 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
 		goto bail;
 	}
 
+	if (!kvmppc_xive_check_save_restore(vcpu)) {
+		pr_err("inconsistent save-restore setup for VCPU %d\n", server_num);
+		rc = -EIO;
+		goto bail;
+	}
+
 	/*
 	 * Enable the VP first as the single escalation mode will
 	 * affect escalation interrupts numbering
 	 */
-	rc = xive_native_enable_vp(xc->vp_id, xive->single_escalation);
+	rc = xive_native_enable_vp(xc->vp_id, kvmppc_xive_has_single_escalation(xive));
 	if (rc) {
 		pr_err("Failed to enable VP in OPAL: %d\n", rc);
 		goto bail;
@@ -693,7 +698,7 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive,
 	}
 
 	rc = kvmppc_xive_attach_escalation(vcpu, priority,
-					   xive->single_escalation);
+					   kvmppc_xive_has_single_escalation(xive));
 error:
 	if (rc)
 		kvmppc_xive_native_cleanup_queue(vcpu, priority);
@@ -820,7 +825,7 @@ static int kvmppc_xive_reset(struct kvmppc_xive *xive)
 		for (prio = 0; prio < KVMPPC_XIVE_Q_COUNT; prio++) {
 
 			/* Single escalation, no queue 7 */
-			if (prio == 7 && xive->single_escalation)
+			if (prio == 7 && kvmppc_xive_has_single_escalation(xive))
 				break;
 
 			if (xc->esc_virq[prio]) {
@@ -1111,7 +1116,12 @@ static int kvmppc_xive_native_create(struct kvm_device *dev, u32 type)
 	 */
 	xive->nr_servers = KVM_MAX_VCPUS;
 
-	xive->single_escalation = xive_native_has_single_escalation();
+	if (xive_native_has_single_escalation())
+		xive->flags |= KVMPPC_XIVE_FLAG_SINGLE_ESCALATION;
+
+	if (xive_native_has_save_restore())
+		xive->flags |= KVMPPC_XIVE_FLAG_SAVE_RESTORE;
+
 	xive->ops = &kvmppc_xive_native_ops;
 
 	kvm->arch.xive = xive;
@@ -1257,7 +1267,7 @@ static void xive_native_debugfs_init(struct kvmppc_xive *xive)
 		return;
 	}
 
-	xive->dentry = debugfs_create_file(name, 0444, powerpc_debugfs_root,
+	xive->dentry = debugfs_create_file(name, 0444, arch_debugfs_dir,
 					   xive, &xive_native_debug_fops);
 
 	pr_debug("%s: created %s\n", __func__, name);
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index eae4ec2988fc..df8172da2301 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -18,5 +18,5 @@ obj-$(CONFIG_PPC_MM_SLICES)	+= slice.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o
 obj-$(CONFIG_PPC_COPRO_BASE)	+= copro_fault.o
-obj-$(CONFIG_PPC_PTDUMP)	+= ptdump/
+obj-$(CONFIG_PTDUMP_CORE)	+= ptdump/
 obj-$(CONFIG_KASAN)		+= kasan/
diff --git a/arch/powerpc/mm/book3s64/hash_native.c b/arch/powerpc/mm/book3s64/hash_native.c
index 52e170bd95ae..d8279bfe68ea 100644
--- a/arch/powerpc/mm/book3s64/hash_native.c
+++ b/arch/powerpc/mm/book3s64/hash_native.c
@@ -787,7 +787,7 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
  * TODO: add batching support when enabled.  remember, no dynamic memory here,
  * although there is the control page available...
  */
-static void native_hpte_clear(void)
+static notrace void native_hpte_clear(void)
 {
 	unsigned long vpn = 0;
 	unsigned long slot, slots;
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index ac5720371c0d..c145776d3ae5 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -36,8 +36,8 @@
 #include <linux/hugetlb.h>
 #include <linux/cpu.h>
 #include <linux/pgtable.h>
+#include <linux/debugfs.h>
 
-#include <asm/debugfs.h>
 #include <asm/interrupt.h>
 #include <asm/processor.h>
 #include <asm/mmu.h>
@@ -2072,7 +2072,7 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_hpt_order, hpt_order_get, hpt_order_set, "%llu\n")
 
 static int __init hash64_debugfs(void)
 {
-	debugfs_create_file("hpt_order", 0600, powerpc_debugfs_root, NULL,
+	debugfs_create_file("hpt_order", 0600, arch_debugfs_dir, NULL,
 			    &fops_hpt_order);
 	return 0;
 }
diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c
index 9ffa65074cb0..9e16c7b1a6c5 100644
--- a/arch/powerpc/mm/book3s64/pgtable.c
+++ b/arch/powerpc/mm/book3s64/pgtable.c
@@ -6,9 +6,9 @@
 #include <linux/sched.h>
 #include <linux/mm_types.h>
 #include <linux/memblock.h>
+#include <linux/debugfs.h>
 #include <misc/cxl-base.h>
 
-#include <asm/debugfs.h>
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
 #include <asm/trace.h>
@@ -172,8 +172,8 @@ pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
-/* For use by kexec */
-void mmu_cleanup_all(void)
+/* For use by kexec, called with MMU off */
+notrace void mmu_cleanup_all(void)
 {
 	if (radix_enabled())
 		radix__mmu_cleanup_all();
@@ -520,7 +520,7 @@ static int __init pgtable_debugfs_setup(void)
 	 * invalidated as expected.
 	 */
 	debugfs_create_bool("tlbie_enabled", 0600,
-			powerpc_debugfs_root,
+			arch_debugfs_dir,
 			&tlbie_enabled);
 
 	return 0;
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index e50ddf129c15..ae20add7954a 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -679,7 +679,8 @@ void radix__early_init_mmu_secondary(void)
 	mtspr(SPRN_UAMOR, 0);
 }
 
-void radix__mmu_cleanup_all(void)
+/* Called during kexec sequence with MMU off */
+notrace void radix__mmu_cleanup_all(void)
 {
 	unsigned long lpcr;
 
diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c
index aefc100d79a7..7724af19ed7e 100644
--- a/arch/powerpc/mm/book3s64/radix_tlb.c
+++ b/arch/powerpc/mm/book3s64/radix_tlb.c
@@ -10,6 +10,7 @@
 #include <linux/memblock.h>
 #include <linux/mmu_context.h>
 #include <linux/sched/mm.h>
+#include <linux/debugfs.h>
 
 #include <asm/ppc-opcode.h>
 #include <asm/tlb.h>
@@ -1106,8 +1107,8 @@ EXPORT_SYMBOL(radix__flush_tlb_kernel_range);
  * invalidating a full PID, so it has a far lower threshold to change from
  * individual page flushes to full-pid flushes.
  */
-static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33;
-static unsigned long tlb_local_single_page_flush_ceiling __read_mostly = POWER9_TLB_SETS_RADIX * 2;
+static u32 tlb_single_page_flush_ceiling __read_mostly = 33;
+static u32 tlb_local_single_page_flush_ceiling __read_mostly = POWER9_TLB_SETS_RADIX * 2;
 
 static inline void __radix__flush_tlb_range(struct mm_struct *mm,
 					    unsigned long start, unsigned long end)
@@ -1524,3 +1525,14 @@ void do_h_rpt_invalidate_prt(unsigned long pid, unsigned long lpid,
 EXPORT_SYMBOL_GPL(do_h_rpt_invalidate_prt);
 
 #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
+
+static int __init create_tlb_single_page_flush_ceiling(void)
+{
+	debugfs_create_u32("tlb_single_page_flush_ceiling", 0600,
+			   arch_debugfs_dir, &tlb_single_page_flush_ceiling);
+	debugfs_create_u32("tlb_local_single_page_flush_ceiling", 0600,
+			   arch_debugfs_dir, &tlb_local_single_page_flush_ceiling);
+	return 0;
+}
+late_initcall(create_tlb_single_page_flush_ceiling);
+
diff --git a/arch/powerpc/mm/book3s64/slb.c b/arch/powerpc/mm/book3s64/slb.c
index c91bd85eb90e..f0037bcc47a0 100644
--- a/arch/powerpc/mm/book3s64/slb.c
+++ b/arch/powerpc/mm/book3s64/slb.c
@@ -822,7 +822,7 @@ DEFINE_INTERRUPT_HANDLER_RAW(do_slb_fault)
 	/* IRQs are not reconciled here, so can't check irqs_disabled */
 	VM_WARN_ON(mfmsr() & MSR_EE);
 
-	if (unlikely(!(regs->msr & MSR_RI)))
+	if (regs_is_unrecoverable(regs))
 		return -EINVAL;
 
 	/*
diff --git a/arch/powerpc/mm/drmem.c b/arch/powerpc/mm/drmem.c
index 9af3832c9d8d..22197b18d85e 100644
--- a/arch/powerpc/mm/drmem.c
+++ b/arch/powerpc/mm/drmem.c
@@ -18,6 +18,7 @@ static int n_root_addr_cells, n_root_size_cells;
 
 static struct drmem_lmb_info __drmem_info;
 struct drmem_lmb_info *drmem_info = &__drmem_info;
+static bool in_drmem_update;
 
 u64 drmem_lmb_memory_max(void)
 {
@@ -178,6 +179,11 @@ int drmem_update_dt(void)
 	if (!memory)
 		return -1;
 
+	/*
+	 * Set in_drmem_update to prevent the notifier callback to process the
+	 * DT property back since the change is coming from the LMB tree.
+	 */
+	in_drmem_update = true;
 	prop = of_find_property(memory, "ibm,dynamic-memory", NULL);
 	if (prop) {
 		rc = drmem_update_dt_v1(memory, prop);
@@ -186,6 +192,7 @@ int drmem_update_dt(void)
 		if (prop)
 			rc = drmem_update_dt_v2(memory, prop);
 	}
+	in_drmem_update = false;
 
 	of_node_put(memory);
 	return rc;
@@ -307,6 +314,45 @@ int __init walk_drmem_lmbs_early(unsigned long node, void *data,
 	return ret;
 }
 
+/*
+ * Update the LMB associativity index.
+ */
+static int update_lmb(struct drmem_lmb *updated_lmb,
+		      __maybe_unused const __be32 **usm,
+		      __maybe_unused void *data)
+{
+	struct drmem_lmb *lmb;
+
+	for_each_drmem_lmb(lmb) {
+		if (lmb->drc_index != updated_lmb->drc_index)
+			continue;
+
+		lmb->aa_index = updated_lmb->aa_index;
+		break;
+	}
+	return 0;
+}
+
+/*
+ * Update the LMB associativity index.
+ *
+ * This needs to be called when the hypervisor is updating the
+ * dynamic-reconfiguration-memory node property.
+ */
+void drmem_update_lmbs(struct property *prop)
+{
+	/*
+	 * Don't update the LMBs if triggered by the update done in
+	 * drmem_update_dt(), the LMB values have been used to the update the DT
+	 * property in that case.
+	 */
+	if (in_drmem_update)
+		return;
+	if (!strcmp(prop->name, "ibm,dynamic-memory"))
+		__walk_drmem_v1_lmbs(prop->value, NULL, NULL, update_lmb);
+	else if (!strcmp(prop->name, "ibm,dynamic-memory-v2"))
+		__walk_drmem_v2_lmbs(prop->value, NULL, NULL, update_lmb);
+}
 #endif
 
 static int init_drmem_lmb_size(struct device_node *dn)
diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h
index 7dac910c0b21..dd1cabc2ea0f 100644
--- a/arch/powerpc/mm/mmu_decl.h
+++ b/arch/powerpc/mm/mmu_decl.h
@@ -180,7 +180,7 @@ static inline void mmu_mark_rodata_ro(void) { }
 void __init mmu_mapin_immr(void);
 #endif
 
-#ifdef CONFIG_PPC_DEBUG_WX
+#ifdef CONFIG_DEBUG_WX
 void ptdump_check_wx(void);
 #else
 static inline void ptdump_check_wx(void) { }
diff --git a/arch/powerpc/mm/nohash/tlb_low.S b/arch/powerpc/mm/nohash/tlb_low.S
index 4613bf8e9aae..5add4a51e51f 100644
--- a/arch/powerpc/mm/nohash/tlb_low.S
+++ b/arch/powerpc/mm/nohash/tlb_low.S
@@ -199,7 +199,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_476_DD2)
  * Touch enough instruction cache lines to ensure cache hits
  */
 1:	mflr	r9
-	bl	2f
+	bcl	20,31,$+4
 2:	mflr	r6
 	li	r7,32
 	PPC_ICBT(0,R6,R7)		/* touch next cache line */
@@ -414,7 +414,7 @@ _GLOBAL(loadcam_multi)
 	 * Set up temporary TLB entry that is the same as what we're
 	 * running from, but in AS=1.
 	 */
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r6
 	tlbsx	0,r8
 	mfspr	r6,SPRN_MAS1
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index f2bf98bdcea2..6f14c8fb6359 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -40,9 +40,6 @@ static int numa_enabled = 1;
 
 static char *cmdline __initdata;
 
-static int numa_debug;
-#define dbg(args...) if (numa_debug) { printk(KERN_INFO args); }
-
 int numa_cpu_lookup_table[NR_CPUS];
 cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
 struct pglist_data *node_data[MAX_NUMNODES];
@@ -51,14 +48,22 @@ EXPORT_SYMBOL(numa_cpu_lookup_table);
 EXPORT_SYMBOL(node_to_cpumask_map);
 EXPORT_SYMBOL(node_data);
 
-static int min_common_depth;
+static int primary_domain_index;
 static int n_mem_addr_cells, n_mem_size_cells;
-static int form1_affinity;
+
+#define FORM0_AFFINITY 0
+#define FORM1_AFFINITY 1
+#define FORM2_AFFINITY 2
+static int affinity_form;
 
 #define MAX_DISTANCE_REF_POINTS 4
 static int distance_ref_points_depth;
 static const __be32 *distance_ref_points;
 static int distance_lookup_table[MAX_NUMNODES][MAX_DISTANCE_REF_POINTS];
+static int numa_distance_table[MAX_NUMNODES][MAX_NUMNODES] = {
+	[0 ... MAX_NUMNODES - 1] = { [0 ... MAX_NUMNODES - 1] = -1 }
+};
+static int numa_id_index_table[MAX_NUMNODES] = { [0 ... MAX_NUMNODES - 1] = NUMA_NO_NODE };
 
 /*
  * Allocate node_to_cpumask_map based on number of available nodes
@@ -79,7 +84,7 @@ static void __init setup_node_to_cpumask_map(void)
 		alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]);
 
 	/* cpumask_of_node() will now work */
-	dbg("Node to cpumask map for %u nodes\n", nr_node_ids);
+	pr_debug("Node to cpumask map for %u nodes\n", nr_node_ids);
 }
 
 static int __init fake_numa_create_new_node(unsigned long end_pfn,
@@ -123,7 +128,7 @@ static int __init fake_numa_create_new_node(unsigned long end_pfn,
 		cmdline = p;
 		fake_nid++;
 		*nid = fake_nid;
-		dbg("created new fake_node with id %d\n", fake_nid);
+		pr_debug("created new fake_node with id %d\n", fake_nid);
 		return 1;
 	}
 	return 0;
@@ -137,33 +142,79 @@ static void reset_numa_cpu_lookup_table(void)
 		numa_cpu_lookup_table[cpu] = -1;
 }
 
-static void map_cpu_to_node(int cpu, int node)
+void map_cpu_to_node(int cpu, int node)
 {
 	update_numa_cpu_lookup_table(cpu, node);
 
-	dbg("adding cpu %d to node %d\n", cpu, node);
-
-	if (!(cpumask_test_cpu(cpu, node_to_cpumask_map[node])))
+	if (!(cpumask_test_cpu(cpu, node_to_cpumask_map[node]))) {
+		pr_debug("adding cpu %d to node %d\n", cpu, node);
 		cpumask_set_cpu(cpu, node_to_cpumask_map[node]);
+	}
 }
 
 #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_PPC_SPLPAR)
-static void unmap_cpu_from_node(unsigned long cpu)
+void unmap_cpu_from_node(unsigned long cpu)
 {
 	int node = numa_cpu_lookup_table[cpu];
 
-	dbg("removing cpu %lu from node %d\n", cpu, node);
-
 	if (cpumask_test_cpu(cpu, node_to_cpumask_map[node])) {
 		cpumask_clear_cpu(cpu, node_to_cpumask_map[node]);
+		pr_debug("removing cpu %lu from node %d\n", cpu, node);
 	} else {
-		printk(KERN_ERR "WARNING: cpu %lu not found in node %d\n",
-		       cpu, node);
+		pr_warn("Warning: cpu %lu not found in node %d\n", cpu, node);
 	}
 }
 #endif /* CONFIG_HOTPLUG_CPU || CONFIG_PPC_SPLPAR */
 
-int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
+static int __associativity_to_nid(const __be32 *associativity,
+				  int max_array_sz)
+{
+	int nid;
+	/*
+	 * primary_domain_index is 1 based array index.
+	 */
+	int index = primary_domain_index  - 1;
+
+	if (!numa_enabled || index >= max_array_sz)
+		return NUMA_NO_NODE;
+
+	nid = of_read_number(&associativity[index], 1);
+
+	/* POWER4 LPAR uses 0xffff as invalid node */
+	if (nid == 0xffff || nid >= nr_node_ids)
+		nid = NUMA_NO_NODE;
+	return nid;
+}
+/*
+ * Returns nid in the range [0..nr_node_ids], or -1 if no useful NUMA
+ * info is found.
+ */
+static int associativity_to_nid(const __be32 *associativity)
+{
+	int array_sz = of_read_number(associativity, 1);
+
+	/* Skip the first element in the associativity array */
+	return __associativity_to_nid((associativity + 1), array_sz);
+}
+
+static int __cpu_form2_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
+{
+	int dist;
+	int node1, node2;
+
+	node1 = associativity_to_nid(cpu1_assoc);
+	node2 = associativity_to_nid(cpu2_assoc);
+
+	dist = numa_distance_table[node1][node2];
+	if (dist <= LOCAL_DISTANCE)
+		return 0;
+	else if (dist <= REMOTE_DISTANCE)
+		return 1;
+	else
+		return 2;
+}
+
+static int __cpu_form1_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
 {
 	int dist = 0;
 
@@ -179,6 +230,15 @@ int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
 	return dist;
 }
 
+int cpu_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
+{
+	/* We should not get called with FORM0 */
+	VM_WARN_ON(affinity_form == FORM0_AFFINITY);
+	if (affinity_form == FORM1_AFFINITY)
+		return __cpu_form1_relative_distance(cpu1_assoc, cpu2_assoc);
+	return __cpu_form2_relative_distance(cpu1_assoc, cpu2_assoc);
+}
+
 /* must hold reference to node during call */
 static const __be32 *of_get_associativity(struct device_node *dev)
 {
@@ -190,7 +250,9 @@ int __node_distance(int a, int b)
 	int i;
 	int distance = LOCAL_DISTANCE;
 
-	if (!form1_affinity)
+	if (affinity_form == FORM2_AFFINITY)
+		return numa_distance_table[a][b];
+	else if (affinity_form == FORM0_AFFINITY)
 		return ((a == b) ? LOCAL_DISTANCE : REMOTE_DISTANCE);
 
 	for (i = 0; i < distance_ref_points_depth; i++) {
@@ -205,52 +267,6 @@ int __node_distance(int a, int b)
 }
 EXPORT_SYMBOL(__node_distance);
 
-static void initialize_distance_lookup_table(int nid,
-		const __be32 *associativity)
-{
-	int i;
-
-	if (!form1_affinity)
-		return;
-
-	for (i = 0; i < distance_ref_points_depth; i++) {
-		const __be32 *entry;
-
-		entry = &associativity[be32_to_cpu(distance_ref_points[i]) - 1];
-		distance_lookup_table[nid][i] = of_read_number(entry, 1);
-	}
-}
-
-/*
- * Returns nid in the range [0..nr_node_ids], or -1 if no useful NUMA
- * info is found.
- */
-static int associativity_to_nid(const __be32 *associativity)
-{
-	int nid = NUMA_NO_NODE;
-
-	if (!numa_enabled)
-		goto out;
-
-	if (of_read_number(associativity, 1) >= min_common_depth)
-		nid = of_read_number(&associativity[min_common_depth], 1);
-
-	/* POWER4 LPAR uses 0xffff as invalid node */
-	if (nid == 0xffff || nid >= nr_node_ids)
-		nid = NUMA_NO_NODE;
-
-	if (nid > 0 &&
-		of_read_number(associativity, 1) >= distance_ref_points_depth) {
-		/*
-		 * Skip the length field and send start of associativity array
-		 */
-		initialize_distance_lookup_table(nid, associativity + 1);
-	}
-
-out:
-	return nid;
-}
-
 /* Returns the nid associated with the given device tree node,
  * or -1 if not found.
  */
@@ -284,10 +300,158 @@ int of_node_to_nid(struct device_node *device)
 }
 EXPORT_SYMBOL(of_node_to_nid);
 
-static int __init find_min_common_depth(void)
+static void __initialize_form1_numa_distance(const __be32 *associativity,
+					     int max_array_sz)
 {
-	int depth;
+	int i, nid;
+
+	if (affinity_form != FORM1_AFFINITY)
+		return;
+
+	nid = __associativity_to_nid(associativity, max_array_sz);
+	if (nid != NUMA_NO_NODE) {
+		for (i = 0; i < distance_ref_points_depth; i++) {
+			const __be32 *entry;
+			int index = be32_to_cpu(distance_ref_points[i]) - 1;
+
+			/*
+			 * broken hierarchy, return with broken distance table
+			 */
+			if (WARN(index >= max_array_sz, "Broken ibm,associativity property"))
+				return;
+
+			entry = &associativity[index];
+			distance_lookup_table[nid][i] = of_read_number(entry, 1);
+		}
+	}
+}
+
+static void initialize_form1_numa_distance(const __be32 *associativity)
+{
+	int array_sz;
+
+	array_sz = of_read_number(associativity, 1);
+	/* Skip the first element in the associativity array */
+	__initialize_form1_numa_distance(associativity + 1, array_sz);
+}
+
+/*
+ * Used to update distance information w.r.t newly added node.
+ */
+void update_numa_distance(struct device_node *node)
+{
+	int nid;
+
+	if (affinity_form == FORM0_AFFINITY)
+		return;
+	else if (affinity_form == FORM1_AFFINITY) {
+		const __be32 *associativity;
+
+		associativity = of_get_associativity(node);
+		if (!associativity)
+			return;
+
+		initialize_form1_numa_distance(associativity);
+		return;
+	}
+
+	/* FORM2 affinity  */
+	nid = of_node_to_nid_single(node);
+	if (nid == NUMA_NO_NODE)
+		return;
+
+	/*
+	 * With FORM2 we expect NUMA distance of all possible NUMA
+	 * nodes to be provided during boot.
+	 */
+	WARN(numa_distance_table[nid][nid] == -1,
+	     "NUMA distance details for node %d not provided\n", nid);
+}
+
+/*
+ * ibm,numa-lookup-index-table= {N, domainid1, domainid2, ..... domainidN}
+ * ibm,numa-distance-table = { N, 1, 2, 4, 5, 1, 6, .... N elements}
+ */
+static void initialize_form2_numa_distance_lookup_table(void)
+{
+	int i, j;
 	struct device_node *root;
+	const __u8 *numa_dist_table;
+	const __be32 *numa_lookup_index;
+	int numa_dist_table_length;
+	int max_numa_index, distance_index;
+
+	if (firmware_has_feature(FW_FEATURE_OPAL))
+		root = of_find_node_by_path("/ibm,opal");
+	else
+		root = of_find_node_by_path("/rtas");
+	if (!root)
+		root = of_find_node_by_path("/");
+
+	numa_lookup_index = of_get_property(root, "ibm,numa-lookup-index-table", NULL);
+	max_numa_index = of_read_number(&numa_lookup_index[0], 1);
+
+	/* first element of the array is the size and is encode-int */
+	numa_dist_table = of_get_property(root, "ibm,numa-distance-table", NULL);
+	numa_dist_table_length = of_read_number((const __be32 *)&numa_dist_table[0], 1);
+	/* Skip the size which is encoded int */
+	numa_dist_table += sizeof(__be32);
+
+	pr_debug("numa_dist_table_len = %d, numa_dist_indexes_len = %d\n",
+		 numa_dist_table_length, max_numa_index);
+
+	for (i = 0; i < max_numa_index; i++)
+		/* +1 skip the max_numa_index in the property */
+		numa_id_index_table[i] = of_read_number(&numa_lookup_index[i + 1], 1);
+
+
+	if (numa_dist_table_length != max_numa_index * max_numa_index) {
+		WARN(1, "Wrong NUMA distance information\n");
+		/* consider everybody else just remote. */
+		for (i = 0;  i < max_numa_index; i++) {
+			for (j = 0; j < max_numa_index; j++) {
+				int nodeA = numa_id_index_table[i];
+				int nodeB = numa_id_index_table[j];
+
+				if (nodeA == nodeB)
+					numa_distance_table[nodeA][nodeB] = LOCAL_DISTANCE;
+				else
+					numa_distance_table[nodeA][nodeB] = REMOTE_DISTANCE;
+			}
+		}
+	}
+
+	distance_index = 0;
+	for (i = 0;  i < max_numa_index; i++) {
+		for (j = 0; j < max_numa_index; j++) {
+			int nodeA = numa_id_index_table[i];
+			int nodeB = numa_id_index_table[j];
+
+			numa_distance_table[nodeA][nodeB] = numa_dist_table[distance_index++];
+			pr_debug("dist[%d][%d]=%d ", nodeA, nodeB, numa_distance_table[nodeA][nodeB]);
+		}
+	}
+	of_node_put(root);
+}
+
+static int __init find_primary_domain_index(void)
+{
+	int index;
+	struct device_node *root;
+
+	/*
+	 * Check for which form of affinity.
+	 */
+	if (firmware_has_feature(FW_FEATURE_OPAL)) {
+		affinity_form = FORM1_AFFINITY;
+	} else if (firmware_has_feature(FW_FEATURE_FORM2_AFFINITY)) {
+		pr_debug("Using form 2 affinity\n");
+		affinity_form = FORM2_AFFINITY;
+	} else if (firmware_has_feature(FW_FEATURE_FORM1_AFFINITY)) {
+		pr_debug("Using form 1 affinity\n");
+		affinity_form = FORM1_AFFINITY;
+	} else
+		affinity_form = FORM0_AFFINITY;
 
 	if (firmware_has_feature(FW_FEATURE_OPAL))
 		root = of_find_node_by_path("/ibm,opal");
@@ -313,42 +477,37 @@ static int __init find_min_common_depth(void)
 					&distance_ref_points_depth);
 
 	if (!distance_ref_points) {
-		dbg("NUMA: ibm,associativity-reference-points not found.\n");
+		pr_debug("ibm,associativity-reference-points not found.\n");
 		goto err;
 	}
 
 	distance_ref_points_depth /= sizeof(int);
-
-	if (firmware_has_feature(FW_FEATURE_OPAL) ||
-	    firmware_has_feature(FW_FEATURE_TYPE1_AFFINITY)) {
-		dbg("Using form 1 affinity\n");
-		form1_affinity = 1;
-	}
-
-	if (form1_affinity) {
-		depth = of_read_number(distance_ref_points, 1);
-	} else {
+	if (affinity_form == FORM0_AFFINITY) {
 		if (distance_ref_points_depth < 2) {
-			printk(KERN_WARNING "NUMA: "
-				"short ibm,associativity-reference-points\n");
+			pr_warn("short ibm,associativity-reference-points\n");
 			goto err;
 		}
 
-		depth = of_read_number(&distance_ref_points[1], 1);
+		index = of_read_number(&distance_ref_points[1], 1);
+	} else {
+		/*
+		 * Both FORM1 and FORM2 affinity find the primary domain details
+		 * at the same offset.
+		 */
+		index = of_read_number(distance_ref_points, 1);
 	}
-
 	/*
 	 * Warn and cap if the hardware supports more than
 	 * MAX_DISTANCE_REF_POINTS domains.
 	 */
 	if (distance_ref_points_depth > MAX_DISTANCE_REF_POINTS) {
-		printk(KERN_WARNING "NUMA: distance array capped at "
-			"%d entries\n", MAX_DISTANCE_REF_POINTS);
+		pr_warn("distance array capped at %d entries\n",
+			MAX_DISTANCE_REF_POINTS);
 		distance_ref_points_depth = MAX_DISTANCE_REF_POINTS;
 	}
 
 	of_node_put(root);
-	return depth;
+	return index;
 
 err:
 	of_node_put(root);
@@ -426,6 +585,38 @@ static int of_get_assoc_arrays(struct assoc_arrays *aa)
 	return 0;
 }
 
+static int get_nid_and_numa_distance(struct drmem_lmb *lmb)
+{
+	struct assoc_arrays aa = { .arrays = NULL };
+	int default_nid = NUMA_NO_NODE;
+	int nid = default_nid;
+	int rc, index;
+
+	if ((primary_domain_index < 0) || !numa_enabled)
+		return default_nid;
+
+	rc = of_get_assoc_arrays(&aa);
+	if (rc)
+		return default_nid;
+
+	if (primary_domain_index <= aa.array_sz &&
+	    !(lmb->flags & DRCONF_MEM_AI_INVALID) && lmb->aa_index < aa.n_arrays) {
+		const __be32 *associativity;
+
+		index = lmb->aa_index * aa.array_sz;
+		associativity = &aa.arrays[index];
+		nid = __associativity_to_nid(associativity, aa.array_sz);
+		if (nid > 0 && affinity_form == FORM1_AFFINITY) {
+			/*
+			 * lookup array associativity entries have
+			 * no length of the array as the first element.
+			 */
+			__initialize_form1_numa_distance(associativity, aa.array_sz);
+		}
+	}
+	return nid;
+}
+
 /*
  * This is like of_node_to_nid_single() for memory represented in the
  * ibm,dynamic-reconfiguration-memory node.
@@ -437,35 +628,28 @@ int of_drconf_to_nid_single(struct drmem_lmb *lmb)
 	int nid = default_nid;
 	int rc, index;
 
-	if ((min_common_depth < 0) || !numa_enabled)
+	if ((primary_domain_index < 0) || !numa_enabled)
 		return default_nid;
 
 	rc = of_get_assoc_arrays(&aa);
 	if (rc)
 		return default_nid;
 
-	if (min_common_depth <= aa.array_sz &&
+	if (primary_domain_index <= aa.array_sz &&
 	    !(lmb->flags & DRCONF_MEM_AI_INVALID) && lmb->aa_index < aa.n_arrays) {
-		index = lmb->aa_index * aa.array_sz + min_common_depth - 1;
-		nid = of_read_number(&aa.arrays[index], 1);
+		const __be32 *associativity;
 
-		if (nid == 0xffff || nid >= nr_node_ids)
-			nid = default_nid;
-
-		if (nid > 0) {
-			index = lmb->aa_index * aa.array_sz;
-			initialize_distance_lookup_table(nid,
-							&aa.arrays[index]);
-		}
+		index = lmb->aa_index * aa.array_sz;
+		associativity = &aa.arrays[index];
+		nid = __associativity_to_nid(associativity, aa.array_sz);
 	}
-
 	return nid;
 }
 
 #ifdef CONFIG_PPC_SPLPAR
-static int vphn_get_nid(long lcpu)
+
+static int __vphn_get_associativity(long lcpu, __be32 *associativity)
 {
-	__be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
 	long rc, hwid;
 
 	/*
@@ -485,12 +669,30 @@ static int vphn_get_nid(long lcpu)
 
 		rc = hcall_vphn(hwid, VPHN_FLAG_VCPU, associativity);
 		if (rc == H_SUCCESS)
-			return associativity_to_nid(associativity);
+			return 0;
 	}
 
+	return -1;
+}
+
+static int vphn_get_nid(long lcpu)
+{
+	__be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
+
+
+	if (!__vphn_get_associativity(lcpu, associativity))
+		return associativity_to_nid(associativity);
+
 	return NUMA_NO_NODE;
+
 }
 #else
+
+static int __vphn_get_associativity(long lcpu, __be32 *associativity)
+{
+	return -1;
+}
+
 static int vphn_get_nid(long unused)
 {
 	return NUMA_NO_NODE;
@@ -598,9 +800,6 @@ static int ppc_numa_cpu_prepare(unsigned int cpu)
 
 static int ppc_numa_cpu_dead(unsigned int cpu)
 {
-#ifdef CONFIG_HOTPLUG_CPU
-	unmap_cpu_from_node(cpu);
-#endif
 	return 0;
 }
 
@@ -685,7 +884,7 @@ static int __init numa_setup_drmem_lmb(struct drmem_lmb *lmb,
 			size = read_n_cells(n_mem_size_cells, usm);
 		}
 
-		nid = of_drconf_to_nid_single(lmb);
+		nid = get_nid_and_numa_distance(lmb);
 		fake_numa_create_new_node(((base + size) >> PAGE_SHIFT),
 					  &nid);
 		node_set_online(nid);
@@ -702,24 +901,31 @@ static int __init parse_numa_properties(void)
 	struct device_node *memory;
 	int default_nid = 0;
 	unsigned long i;
+	const __be32 *associativity;
 
 	if (numa_enabled == 0) {
-		printk(KERN_WARNING "NUMA disabled by user\n");
+		pr_warn("disabled by user\n");
 		return -1;
 	}
 
-	min_common_depth = find_min_common_depth();
+	primary_domain_index = find_primary_domain_index();
 
-	if (min_common_depth < 0) {
+	if (primary_domain_index < 0) {
 		/*
-		 * if we fail to parse min_common_depth from device tree
+		 * if we fail to parse primary_domain_index from device tree
 		 * mark the numa disabled, boot with numa disabled.
 		 */
 		numa_enabled = false;
-		return min_common_depth;
+		return primary_domain_index;
 	}
 
-	dbg("NUMA associativity depth for CPU/Memory: %d\n", min_common_depth);
+	pr_debug("associativity depth for CPU/Memory: %d\n", primary_domain_index);
+
+	/*
+	 * If it is FORM2 initialize the distance table here.
+	 */
+	if (affinity_form == FORM2_AFFINITY)
+		initialize_form2_numa_distance_lookup_table();
 
 	/*
 	 * Even though we connect cpus to numa domains later in SMP
@@ -727,18 +933,30 @@ static int __init parse_numa_properties(void)
 	 * each node to be onlined must have NODE_DATA etc backing it.
 	 */
 	for_each_present_cpu(i) {
+		__be32 vphn_assoc[VPHN_ASSOC_BUFSIZE];
 		struct device_node *cpu;
-		int nid = vphn_get_nid(i);
+		int nid = NUMA_NO_NODE;
 
-		/*
-		 * Don't fall back to default_nid yet -- we will plug
-		 * cpus into nodes once the memory scan has discovered
-		 * the topology.
-		 */
-		if (nid == NUMA_NO_NODE) {
+		memset(vphn_assoc, 0, VPHN_ASSOC_BUFSIZE * sizeof(__be32));
+
+		if (__vphn_get_associativity(i, vphn_assoc) == 0) {
+			nid = associativity_to_nid(vphn_assoc);
+			initialize_form1_numa_distance(vphn_assoc);
+		} else {
+
+			/*
+			 * Don't fall back to default_nid yet -- we will plug
+			 * cpus into nodes once the memory scan has discovered
+			 * the topology.
+			 */
 			cpu = of_get_cpu_node(i, NULL);
 			BUG_ON(!cpu);
-			nid = of_node_to_nid_single(cpu);
+
+			associativity = of_get_associativity(cpu);
+			if (associativity) {
+				nid = associativity_to_nid(associativity);
+				initialize_form1_numa_distance(associativity);
+			}
 			of_node_put(cpu);
 		}
 
@@ -774,8 +992,11 @@ new_range:
 		 * have associativity properties.  If none, then
 		 * everything goes to default_nid.
 		 */
-		nid = of_node_to_nid_single(memory);
-		if (nid < 0)
+		associativity = of_get_associativity(memory);
+		if (associativity) {
+			nid = associativity_to_nid(associativity);
+			initialize_form1_numa_distance(associativity);
+		} else
 			nid = default_nid;
 
 		fake_numa_create_new_node(((start + size) >> PAGE_SHIFT), &nid);
@@ -811,10 +1032,8 @@ static void __init setup_nonnuma(void)
 	unsigned int nid = 0;
 	int i;
 
-	printk(KERN_DEBUG "Top of RAM: 0x%lx, Total RAM: 0x%lx\n",
-	       top_of_ram, total_ram);
-	printk(KERN_DEBUG "Memory hole size: %ldMB\n",
-	       (top_of_ram - total_ram) >> 20);
+	pr_debug("Top of RAM: 0x%lx, Total RAM: 0x%lx\n", top_of_ram, total_ram);
+	pr_debug("Memory hole size: %ldMB\n", (top_of_ram - total_ram) >> 20);
 
 	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) {
 		fake_numa_create_new_node(end_pfn, &nid);
@@ -893,7 +1112,7 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
 static void __init find_possible_nodes(void)
 {
 	struct device_node *rtas;
-	const __be32 *domains;
+	const __be32 *domains = NULL;
 	int prop_length, max_nodes;
 	u32 i;
 
@@ -909,9 +1128,14 @@ static void __init find_possible_nodes(void)
 	 * it doesn't exist, then fallback on ibm,max-associativity-domains.
 	 * Current denotes what the platform can support compared to max
 	 * which denotes what the Hypervisor can support.
+	 *
+	 * If the LPAR is migratable, new nodes might be activated after a LPM,
+	 * so we should consider the max number in that case.
 	 */
-	domains = of_get_property(rtas, "ibm,current-associativity-domains",
-					&prop_length);
+	if (!of_get_property(of_root, "ibm,migratable-partition", NULL))
+		domains = of_get_property(rtas,
+					  "ibm,current-associativity-domains",
+					  &prop_length);
 	if (!domains) {
 		domains = of_get_property(rtas, "ibm,max-associativity-domains",
 					&prop_length);
@@ -919,14 +1143,16 @@ static void __init find_possible_nodes(void)
 			goto out;
 	}
 
-	max_nodes = of_read_number(&domains[min_common_depth], 1);
+	max_nodes = of_read_number(&domains[primary_domain_index], 1);
+	pr_info("Partition configured for %d NUMA nodes.\n", max_nodes);
+
 	for (i = 0; i < max_nodes; i++) {
 		if (!node_possible(i))
 			node_set(i, node_possible_map);
 	}
 
 	prop_length /= sizeof(int);
-	if (prop_length > min_common_depth + 2)
+	if (prop_length > primary_domain_index + 2)
 		coregroup_enabled = 1;
 
 out:
@@ -1014,9 +1240,6 @@ static int __init early_numa(char *p)
 	if (strstr(p, "off"))
 		numa_enabled = 0;
 
-	if (strstr(p, "debug"))
-		numa_debug = 1;
-
 	p = strstr(p, "fake=");
 	if (p)
 		cmdline = p + strlen("fake=");
@@ -1179,7 +1402,7 @@ static long vphn_get_associativity(unsigned long cpu,
 
 	switch (rc) {
 	case H_SUCCESS:
-		dbg("VPHN hcall succeeded. Reset polling...\n");
+		pr_debug("VPHN hcall succeeded. Reset polling...\n");
 		goto out;
 
 	case H_FUNCTION:
@@ -1259,7 +1482,7 @@ int cpu_to_coregroup_id(int cpu)
 		goto out;
 
 	index = of_read_number(associativity, 1);
-	if (index > min_common_depth + 1)
+	if (index > primary_domain_index + 1)
 		return of_read_number(&associativity[index - 1], 1);
 
 out:
diff --git a/arch/powerpc/mm/ptdump/8xx.c b/arch/powerpc/mm/ptdump/8xx.c
index 86da2a669680..fac932eb8f9a 100644
--- a/arch/powerpc/mm/ptdump/8xx.c
+++ b/arch/powerpc/mm/ptdump/8xx.c
@@ -75,8 +75,10 @@ static const struct flag_info flag_array[] = {
 };
 
 struct pgtable_level pg_level[5] = {
-	{
-	}, { /* pgd */
+	{ /* pgd */
+		.flag	= flag_array,
+		.num	= ARRAY_SIZE(flag_array),
+	}, { /* p4d */
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	}, { /* pud */
diff --git a/arch/powerpc/mm/ptdump/Makefile b/arch/powerpc/mm/ptdump/Makefile
index 712762be3cb1..4050cbb55acf 100644
--- a/arch/powerpc/mm/ptdump/Makefile
+++ b/arch/powerpc/mm/ptdump/Makefile
@@ -5,5 +5,10 @@ obj-y	+= ptdump.o
 obj-$(CONFIG_4xx)		+= shared.o
 obj-$(CONFIG_PPC_8xx)		+= 8xx.o
 obj-$(CONFIG_PPC_BOOK3E_MMU)	+= shared.o
-obj-$(CONFIG_PPC_BOOK3S_32)	+= shared.o bats.o segment_regs.o
-obj-$(CONFIG_PPC_BOOK3S_64)	+= book3s64.o hashpagetable.o
+obj-$(CONFIG_PPC_BOOK3S_32)	+= shared.o
+obj-$(CONFIG_PPC_BOOK3S_64)	+= book3s64.o
+
+ifdef CONFIG_PTDUMP_DEBUGFS
+obj-$(CONFIG_PPC_BOOK3S_32)	+= bats.o segment_regs.o
+obj-$(CONFIG_PPC_BOOK3S_64)	+= hashpagetable.o
+endif
diff --git a/arch/powerpc/mm/ptdump/bats.c b/arch/powerpc/mm/ptdump/bats.c
index c4c628b03cf8..820c119013e4 100644
--- a/arch/powerpc/mm/ptdump/bats.c
+++ b/arch/powerpc/mm/ptdump/bats.c
@@ -7,7 +7,7 @@
  */
 
 #include <linux/pgtable.h>
-#include <asm/debugfs.h>
+#include <linux/debugfs.h>
 #include <asm/cpu_has_feature.h>
 
 #include "ptdump.h"
@@ -57,7 +57,7 @@ static void bat_show_603(struct seq_file *m, int idx, u32 lower, u32 upper, bool
 
 #define BAT_SHOW_603(_m, _n, _l, _u, _d) bat_show_603(_m, _n, mfspr(_l), mfspr(_u), _d)
 
-static int bats_show_603(struct seq_file *m, void *v)
+static int bats_show(struct seq_file *m, void *v)
 {
 	seq_puts(m, "---[ Instruction Block Address Translation ]---\n");
 
@@ -88,22 +88,12 @@ static int bats_show_603(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int bats_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, bats_show_603, NULL);
-}
-
-static const struct file_operations bats_fops = {
-	.open		= bats_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(bats);
 
 static int __init bats_init(void)
 {
 	debugfs_create_file("block_address_translation", 0400,
-			    powerpc_debugfs_root, NULL, &bats_fops);
+			    arch_debugfs_dir, NULL, &bats_fops);
 	return 0;
 }
 device_initcall(bats_init);
diff --git a/arch/powerpc/mm/ptdump/book3s64.c b/arch/powerpc/mm/ptdump/book3s64.c
index 14f73868db66..5ad92d9dc5d1 100644
--- a/arch/powerpc/mm/ptdump/book3s64.c
+++ b/arch/powerpc/mm/ptdump/book3s64.c
@@ -103,8 +103,10 @@ static const struct flag_info flag_array[] = {
 };
 
 struct pgtable_level pg_level[5] = {
-	{
-	}, { /* pgd */
+	{ /* pgd */
+		.flag	= flag_array,
+		.num	= ARRAY_SIZE(flag_array),
+	}, { /* p4d */
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	}, { /* pud */
diff --git a/arch/powerpc/mm/ptdump/hashpagetable.c b/arch/powerpc/mm/ptdump/hashpagetable.c
index ad6df9a2e7c8..c7f824d294b2 100644
--- a/arch/powerpc/mm/ptdump/hashpagetable.c
+++ b/arch/powerpc/mm/ptdump/hashpagetable.c
@@ -526,17 +526,7 @@ static int ptdump_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int ptdump_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, ptdump_show, NULL);
-}
-
-static const struct file_operations ptdump_fops = {
-	.open		= ptdump_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(ptdump);
 
 static int ptdump_init(void)
 {
diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c
index 5062c58b1e5b..bf251191e78d 100644
--- a/arch/powerpc/mm/ptdump/ptdump.c
+++ b/arch/powerpc/mm/ptdump/ptdump.c
@@ -16,6 +16,7 @@
 #include <linux/io.h>
 #include <linux/mm.h>
 #include <linux/highmem.h>
+#include <linux/ptdump.h>
 #include <linux/sched.h>
 #include <linux/seq_file.h>
 #include <asm/fixmap.h>
@@ -54,11 +55,12 @@
  *
  */
 struct pg_state {
+	struct ptdump_state ptdump;
 	struct seq_file *seq;
 	const struct addr_marker *marker;
 	unsigned long start_address;
 	unsigned long start_pa;
-	unsigned int level;
+	int level;
 	u64 current_flags;
 	bool check_wx;
 	unsigned long wx_pages;
@@ -102,6 +104,11 @@ static struct addr_marker address_markers[] = {
 	{ -1,	NULL },
 };
 
+static struct ptdump_range ptdump_range[] __ro_after_init = {
+	{TASK_SIZE_MAX, ~0UL},
+	{0, 0}
+};
+
 #define pt_dump_seq_printf(m, fmt, args...)	\
 ({						\
 	if (m)					\
@@ -188,10 +195,9 @@ static void note_prot_wx(struct pg_state *st, unsigned long addr)
 	st->wx_pages += (addr - st->start_address) / PAGE_SIZE;
 }
 
-static void note_page_update_state(struct pg_state *st, unsigned long addr,
-				   unsigned int level, u64 val, unsigned long page_size)
+static void note_page_update_state(struct pg_state *st, unsigned long addr, int level, u64 val)
 {
-	u64 flag = val & pg_level[level].mask;
+	u64 flag = level >= 0 ? val & pg_level[level].mask : 0;
 	u64 pa = val & PTE_RPN_MASK;
 
 	st->level = level;
@@ -205,15 +211,15 @@ static void note_page_update_state(struct pg_state *st, unsigned long addr,
 	}
 }
 
-static void note_page(struct pg_state *st, unsigned long addr,
-	       unsigned int level, u64 val, unsigned long page_size)
+static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level, u64 val)
 {
-	u64 flag = val & pg_level[level].mask;
+	u64 flag = level >= 0 ? val & pg_level[level].mask : 0;
+	struct pg_state *st = container_of(pt_st, struct pg_state, ptdump);
 
 	/* At first no level is set */
-	if (!st->level) {
+	if (st->level == -1) {
 		pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
-		note_page_update_state(st, addr, level, val, page_size);
+		note_page_update_state(st, addr, level, val);
 	/*
 	 * Dump the section of virtual memory when:
 	 *   - the PTE flags from one entry to the next differs.
@@ -242,95 +248,7 @@ static void note_page(struct pg_state *st, unsigned long addr,
 		 * Address indicates we have passed the end of the
 		 * current section of virtual memory
 		 */
-		note_page_update_state(st, addr, level, val, page_size);
-	}
-}
-
-static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start)
-{
-	pte_t *pte = pte_offset_kernel(pmd, 0);
-	unsigned long addr;
-	unsigned int i;
-
-	for (i = 0; i < PTRS_PER_PTE; i++, pte++) {
-		addr = start + i * PAGE_SIZE;
-		note_page(st, addr, 4, pte_val(*pte), PAGE_SIZE);
-
-	}
-}
-
-static void walk_hugepd(struct pg_state *st, hugepd_t *phpd, unsigned long start,
-			int pdshift, int level)
-{
-#ifdef CONFIG_ARCH_HAS_HUGEPD
-	unsigned int i;
-	int shift = hugepd_shift(*phpd);
-	int ptrs_per_hpd = pdshift - shift > 0 ? 1 << (pdshift - shift) : 1;
-
-	if (start & ((1 << shift) - 1))
-		return;
-
-	for (i = 0; i < ptrs_per_hpd; i++) {
-		unsigned long addr = start + (i << shift);
-		pte_t *pte = hugepte_offset(*phpd, addr, pdshift);
-
-		note_page(st, addr, level + 1, pte_val(*pte), 1 << shift);
-	}
-#endif
-}
-
-static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start)
-{
-	pmd_t *pmd = pmd_offset(pud, 0);
-	unsigned long addr;
-	unsigned int i;
-
-	for (i = 0; i < PTRS_PER_PMD; i++, pmd++) {
-		addr = start + i * PMD_SIZE;
-		if (!pmd_none(*pmd) && !pmd_is_leaf(*pmd))
-			/* pmd exists */
-			walk_pte(st, pmd, addr);
-		else
-			note_page(st, addr, 3, pmd_val(*pmd), PMD_SIZE);
-	}
-}
-
-static void walk_pud(struct pg_state *st, p4d_t *p4d, unsigned long start)
-{
-	pud_t *pud = pud_offset(p4d, 0);
-	unsigned long addr;
-	unsigned int i;
-
-	for (i = 0; i < PTRS_PER_PUD; i++, pud++) {
-		addr = start + i * PUD_SIZE;
-		if (!pud_none(*pud) && !pud_is_leaf(*pud))
-			/* pud exists */
-			walk_pmd(st, pud, addr);
-		else
-			note_page(st, addr, 2, pud_val(*pud), PUD_SIZE);
-	}
-}
-
-static void walk_pagetables(struct pg_state *st)
-{
-	unsigned int i;
-	unsigned long addr = st->start_address & PGDIR_MASK;
-	pgd_t *pgd = pgd_offset_k(addr);
-
-	/*
-	 * Traverse the linux pagetable structure and dump pages that are in
-	 * the hash pagetable.
-	 */
-	for (i = pgd_index(addr); i < PTRS_PER_PGD; i++, pgd++, addr += PGDIR_SIZE) {
-		p4d_t *p4d = p4d_offset(pgd, 0);
-
-		if (p4d_none(*p4d) || p4d_is_leaf(*p4d))
-			note_page(st, addr, 1, p4d_val(*p4d), PGDIR_SIZE);
-		else if (is_hugepd(__hugepd(p4d_val(*p4d))))
-			walk_hugepd(st, (hugepd_t *)p4d, addr, PGDIR_SHIFT, 1);
-		else
-			/* p4d exists */
-			walk_pud(st, p4d, addr);
+		note_page_update_state(st, addr, level, val);
 	}
 }
 
@@ -383,32 +301,19 @@ static int ptdump_show(struct seq_file *m, void *v)
 	struct pg_state st = {
 		.seq = m,
 		.marker = address_markers,
-		.start_address = IS_ENABLED(CONFIG_PPC64) ? PAGE_OFFSET : TASK_SIZE,
+		.level = -1,
+		.ptdump = {
+			.note_page = note_page,
+			.range = ptdump_range,
+		}
 	};
 
-#ifdef CONFIG_PPC64
-	if (!radix_enabled())
-		st.start_address = KERN_VIRT_START;
-#endif
-
 	/* Traverse kernel page tables */
-	walk_pagetables(&st);
-	note_page(&st, 0, 0, 0, 0);
+	ptdump_walk_pgd(&st.ptdump, &init_mm, NULL);
 	return 0;
 }
 
-
-static int ptdump_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, ptdump_show, NULL);
-}
-
-static const struct file_operations ptdump_fops = {
-	.open		= ptdump_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(ptdump);
 
 static void build_pgtable_complete_mask(void)
 {
@@ -420,22 +325,24 @@ static void build_pgtable_complete_mask(void)
 				pg_level[i].mask |= pg_level[i].flag[j].mask;
 }
 
-#ifdef CONFIG_PPC_DEBUG_WX
+#ifdef CONFIG_DEBUG_WX
 void ptdump_check_wx(void)
 {
 	struct pg_state st = {
 		.seq = NULL,
-		.marker = address_markers,
+		.marker = (struct addr_marker[]) {
+			{ 0, NULL},
+			{ -1, NULL},
+		},
+		.level = -1,
 		.check_wx = true,
-		.start_address = IS_ENABLED(CONFIG_PPC64) ? PAGE_OFFSET : TASK_SIZE,
+		.ptdump = {
+			.note_page = note_page,
+			.range = ptdump_range,
+		}
 	};
 
-#ifdef CONFIG_PPC64
-	if (!radix_enabled())
-		st.start_address = KERN_VIRT_START;
-#endif
-
-	walk_pagetables(&st);
+	ptdump_walk_pgd(&st.ptdump, &init_mm, NULL);
 
 	if (st.wx_pages)
 		pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found\n",
@@ -445,12 +352,23 @@ void ptdump_check_wx(void)
 }
 #endif
 
-static int ptdump_init(void)
+static int __init ptdump_init(void)
 {
+#ifdef CONFIG_PPC64
+	if (!radix_enabled())
+		ptdump_range[0].start = KERN_VIRT_START;
+	else
+		ptdump_range[0].start = PAGE_OFFSET;
+
+	ptdump_range[0].end = PAGE_OFFSET + (PGDIR_SIZE * PTRS_PER_PGD);
+#endif
+
 	populate_markers();
 	build_pgtable_complete_mask();
-	debugfs_create_file("kernel_page_tables", 0400, NULL, NULL,
-			    &ptdump_fops);
+
+	if (IS_ENABLED(CONFIG_PTDUMP_DEBUGFS))
+		debugfs_create_file("kernel_page_tables", 0400, NULL, NULL, &ptdump_fops);
+
 	return 0;
 }
 device_initcall(ptdump_init);
diff --git a/arch/powerpc/mm/ptdump/segment_regs.c b/arch/powerpc/mm/ptdump/segment_regs.c
index 565048a0c9be..9df3af8d481f 100644
--- a/arch/powerpc/mm/ptdump/segment_regs.c
+++ b/arch/powerpc/mm/ptdump/segment_regs.c
@@ -6,7 +6,7 @@
  * This dumps the content of Segment Registers
  */
 
-#include <asm/debugfs.h>
+#include <linux/debugfs.h>
 
 static void seg_show(struct seq_file *m, int i)
 {
@@ -41,21 +41,11 @@ static int sr_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int sr_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, sr_show, NULL);
-}
-
-static const struct file_operations sr_fops = {
-	.open		= sr_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(sr);
 
 static int __init sr_init(void)
 {
-	debugfs_create_file("segment_registers", 0400, powerpc_debugfs_root,
+	debugfs_create_file("segment_registers", 0400, arch_debugfs_dir,
 			    NULL, &sr_fops);
 	return 0;
 }
diff --git a/arch/powerpc/mm/ptdump/shared.c b/arch/powerpc/mm/ptdump/shared.c
index c005fe041c18..03607ab90c66 100644
--- a/arch/powerpc/mm/ptdump/shared.c
+++ b/arch/powerpc/mm/ptdump/shared.c
@@ -68,8 +68,10 @@ static const struct flag_info flag_array[] = {
 };
 
 struct pgtable_level pg_level[5] = {
-	{
-	}, { /* pgd */
+	{ /* pgd */
+		.flag	= flag_array,
+		.num	= ARRAY_SIZE(flag_array),
+	}, { /* p4d */
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	}, { /* pud */
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index bb0ee716de91..73e62e9b179b 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -340,6 +340,13 @@ static inline void perf_read_regs(struct pt_regs *regs)
 	 * If the PMU doesn't update the SIAR for non marked events use
 	 * pt_regs.
 	 *
+	 * If regs is a kernel interrupt, always use SIAR. Some PMUs have an
+	 * issue with regs_sipr not being in synch with SIAR in interrupt entry
+	 * and return sequences, which can result in regs_sipr being true for
+	 * kernel interrupts and SIAR, which has the effect of causing samples
+	 * to pile up at mtmsrd MSR[EE] 0->1 or pending irq replay around
+	 * interrupt entry/exit.
+	 *
 	 * If the PMU has HV/PR flags then check to see if they
 	 * place the exception in userspace. If so, use pt_regs. In
 	 * continuous sampling mode the SIAR and the PMU exception are
@@ -356,6 +363,8 @@ static inline void perf_read_regs(struct pt_regs *regs)
 		use_siar = 1;
 	else if ((ppmu->flags & PPMU_NO_CONT_SAMPLING))
 		use_siar = 0;
+	else if (!user_mode(regs))
+		use_siar = 1;
 	else if (!(ppmu->flags & PPMU_NO_SIPR) && regs_sipr(regs))
 		use_siar = 0;
 	else
@@ -2251,18 +2260,10 @@ unsigned long perf_misc_flags(struct pt_regs *regs)
  */
 unsigned long perf_instruction_pointer(struct pt_regs *regs)
 {
-	bool use_siar = regs_use_siar(regs);
 	unsigned long siar = mfspr(SPRN_SIAR);
 
-	if (ppmu && (ppmu->flags & PPMU_P10_DD1)) {
-		if (siar)
-			return siar;
-		else
-			return regs->nip;
-	} else if (use_siar && siar_valid(regs))
-		return mfspr(SPRN_SIAR) + perf_ip_adjust(regs);
-	else if (use_siar)
-		return 0;		// no valid instruction pointer
+	if (regs_use_siar(regs) && siar_valid(regs) && siar)
+		return siar + perf_ip_adjust(regs);
 	else
 		return regs->nip;
 }
diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c
index d48413e28c39..c756228a081f 100644
--- a/arch/powerpc/perf/hv-gpci.c
+++ b/arch/powerpc/perf/hv-gpci.c
@@ -175,7 +175,7 @@ static unsigned long single_gpci_request(u32 req, u32 starting_index,
 	 */
 	count = 0;
 	for (i = offset; i < offset + length; i++)
-		count |= arg->bytes[i] << (i - offset);
+		count |= (u64)(arg->bytes[i]) << ((length - 1 - (i - offset)) * 8);
 
 	*value = count;
 out:
diff --git a/arch/powerpc/platforms/44x/machine_check.c b/arch/powerpc/platforms/44x/machine_check.c
index a5c898bb9bab..5d19daacd78a 100644
--- a/arch/powerpc/platforms/44x/machine_check.c
+++ b/arch/powerpc/platforms/44x/machine_check.c
@@ -11,7 +11,7 @@
 
 int machine_check_440A(struct pt_regs *regs)
 {
-	unsigned long reason = regs->dsisr;
+	unsigned long reason = regs->esr;
 
 	printk("Machine check in kernel mode.\n");
 	if (reason & ESR_IMCP){
@@ -48,7 +48,7 @@ int machine_check_440A(struct pt_regs *regs)
 #ifdef CONFIG_PPC_47x
 int machine_check_47x(struct pt_regs *regs)
 {
-	unsigned long reason = regs->dsisr;
+	unsigned long reason = regs->esr;
 	u32 mcsr;
 
 	printk(KERN_ERR "Machine check in kernel mode.\n");
diff --git a/arch/powerpc/platforms/4xx/machine_check.c b/arch/powerpc/platforms/4xx/machine_check.c
index a71c29892a91..a905da1d6f41 100644
--- a/arch/powerpc/platforms/4xx/machine_check.c
+++ b/arch/powerpc/platforms/4xx/machine_check.c
@@ -10,7 +10,7 @@
 
 int machine_check_4xx(struct pt_regs *regs)
 {
-	unsigned long reason = regs->dsisr;
+	unsigned long reason = regs->esr;
 
 	if (reason & ESR_IMCP) {
 		printk("Instruction");
diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig
index b77cbb0a50e1..4142ebf01382 100644
--- a/arch/powerpc/platforms/85xx/Kconfig
+++ b/arch/powerpc/platforms/85xx/Kconfig
@@ -208,12 +208,6 @@ config TQM8560
 	select TQM85xx
 	select CPM2
 
-config SBC8548
-	bool "Wind River SBC8548"
-	select DEFAULT_UIMAGE
-	help
-	  This option enables support for the Wind River SBC8548 board
-
 config PPA8548
 	bool "Prodrive PPA8548"
 	help
diff --git a/arch/powerpc/platforms/85xx/Makefile b/arch/powerpc/platforms/85xx/Makefile
index d1dd0dca5ebf..60e4e97a929d 100644
--- a/arch/powerpc/platforms/85xx/Makefile
+++ b/arch/powerpc/platforms/85xx/Makefile
@@ -26,7 +26,6 @@ obj-$(CONFIG_CORENET_GENERIC)   += corenet_generic.o
 obj-$(CONFIG_FB_FSL_DIU)	+= t1042rdb_diu.o
 obj-$(CONFIG_STX_GP3)	  += stx_gp3.o
 obj-$(CONFIG_TQM85xx)	  += tqm85xx.o
-obj-$(CONFIG_SBC8548)     += sbc8548.o
 obj-$(CONFIG_PPA8548)     += ppa8548.o
 obj-$(CONFIG_SOCRATES)    += socrates.o socrates_fpga_pic.o
 obj-$(CONFIG_KSI8560)	  += ksi8560.o
diff --git a/arch/powerpc/platforms/85xx/sbc8548.c b/arch/powerpc/platforms/85xx/sbc8548.c
deleted file mode 100644
index e4acf5ce6b07..000000000000
--- a/arch/powerpc/platforms/85xx/sbc8548.c
+++ /dev/null
@@ -1,134 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Wind River SBC8548 setup and early boot code.
- *
- * Copyright 2007 Wind River Systems Inc.
- *
- * By Paul Gortmaker (see MAINTAINERS for contact information)
- *
- * Based largely on the MPC8548CDS support - Copyright 2005 Freescale Inc.
- */
-
-#include <linux/stddef.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/errno.h>
-#include <linux/reboot.h>
-#include <linux/pci.h>
-#include <linux/kdev_t.h>
-#include <linux/major.h>
-#include <linux/console.h>
-#include <linux/delay.h>
-#include <linux/seq_file.h>
-#include <linux/initrd.h>
-#include <linux/interrupt.h>
-#include <linux/fsl_devices.h>
-#include <linux/of_platform.h>
-#include <linux/pgtable.h>
-
-#include <asm/page.h>
-#include <linux/atomic.h>
-#include <asm/time.h>
-#include <asm/io.h>
-#include <asm/machdep.h>
-#include <asm/ipic.h>
-#include <asm/pci-bridge.h>
-#include <asm/irq.h>
-#include <mm/mmu_decl.h>
-#include <asm/prom.h>
-#include <asm/udbg.h>
-#include <asm/mpic.h>
-
-#include <sysdev/fsl_soc.h>
-#include <sysdev/fsl_pci.h>
-
-#include "mpc85xx.h"
-
-static int sbc_rev;
-
-static void __init sbc8548_pic_init(void)
-{
-	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
-			0, 256, " OpenPIC  ");
-	BUG_ON(mpic == NULL);
-	mpic_init(mpic);
-}
-
-/* Extract the HW Rev from the EPLD on the board */
-static int __init sbc8548_hw_rev(void)
-{
-	struct device_node *np;
-	struct resource res;
-	unsigned int *rev;
-	int board_rev = 0;
-
-	np = of_find_compatible_node(NULL, NULL, "hw-rev");
-	if (np == NULL) {
-		printk("No HW-REV found in DTB.\n");
-		return -ENODEV;
-	}
-
-	of_address_to_resource(np, 0, &res);
-	of_node_put(np);
-
-	rev = ioremap(res.start,sizeof(unsigned int));
-	board_rev = (*rev) >> 28;
-	iounmap(rev);
-
-	return board_rev;
-}
-
-/*
- * Setup the architecture
- */
-static void __init sbc8548_setup_arch(void)
-{
-	if (ppc_md.progress)
-		ppc_md.progress("sbc8548_setup_arch()", 0);
-
-	fsl_pci_assign_primary();
-
-	sbc_rev = sbc8548_hw_rev();
-}
-
-static void sbc8548_show_cpuinfo(struct seq_file *m)
-{
-	uint pvid, svid, phid1;
-
-	pvid = mfspr(SPRN_PVR);
-	svid = mfspr(SPRN_SVR);
-
-	seq_printf(m, "Vendor\t\t: Wind River\n");
-	seq_printf(m, "Machine\t\t: SBC8548 v%d\n", sbc_rev);
-	seq_printf(m, "PVR\t\t: 0x%x\n", pvid);
-	seq_printf(m, "SVR\t\t: 0x%x\n", svid);
-
-	/* Display cpu Pll setting */
-	phid1 = mfspr(SPRN_HID1);
-	seq_printf(m, "PLL setting\t: 0x%x\n", ((phid1 >> 24) & 0x3f));
-}
-
-machine_arch_initcall(sbc8548, mpc85xx_common_publish_devices);
-
-/*
- * Called very early, device-tree isn't unflattened
- */
-static int __init sbc8548_probe(void)
-{
-	return of_machine_is_compatible("SBC8548");
-}
-
-define_machine(sbc8548) {
-	.name		= "SBC8548",
-	.probe		= sbc8548_probe,
-	.setup_arch	= sbc8548_setup_arch,
-	.init_IRQ	= sbc8548_pic_init,
-	.show_cpuinfo	= sbc8548_show_cpuinfo,
-	.get_irq	= mpic_get_irq,
-#ifdef CONFIG_PCI
-	.pcibios_fixup_bus	= fsl_pcibios_fixup_bus,
-	.pcibios_fixup_phb      = fsl_pcibios_fixup_phb,
-#endif
-	.calibrate_decr = generic_calibrate_decr,
-	.progress	= udbg_progress,
-};
diff --git a/arch/powerpc/platforms/86xx/Kconfig b/arch/powerpc/platforms/86xx/Kconfig
index 07a9d60c618a..be867abebc83 100644
--- a/arch/powerpc/platforms/86xx/Kconfig
+++ b/arch/powerpc/platforms/86xx/Kconfig
@@ -20,12 +20,6 @@ config MPC8641_HPCN
 	help
 	  This option enables support for the MPC8641 HPCN board.
 
-config SBC8641D
-	bool "Wind River SBC8641D"
-	select DEFAULT_UIMAGE
-	help
-	  This option enables support for the WRS SBC8641D board.
-
 config MPC8610_HPCD
 	bool "Freescale MPC8610 HPCD"
 	select DEFAULT_UIMAGE
@@ -74,7 +68,7 @@ config MPC8641
 	select FSL_PCI if PCI
 	select PPC_UDBG_16550
 	select MPIC
-	default y if MPC8641_HPCN || SBC8641D || GEF_SBC610 || GEF_SBC310 || GEF_PPC9A \
+	default y if MPC8641_HPCN || GEF_SBC610 || GEF_SBC310 || GEF_PPC9A \
 			|| MVME7100
 
 config MPC8610
diff --git a/arch/powerpc/platforms/86xx/Makefile b/arch/powerpc/platforms/86xx/Makefile
index 2c04449be107..5bbe1475bf26 100644
--- a/arch/powerpc/platforms/86xx/Makefile
+++ b/arch/powerpc/platforms/86xx/Makefile
@@ -6,7 +6,6 @@
 obj-y				:= pic.o common.o
 obj-$(CONFIG_SMP)		+= mpc86xx_smp.o
 obj-$(CONFIG_MPC8641_HPCN)	+= mpc86xx_hpcn.o
-obj-$(CONFIG_SBC8641D)		+= sbc8641d.o
 obj-$(CONFIG_MPC8610_HPCD)	+= mpc8610_hpcd.o
 obj-$(CONFIG_GEF_SBC610)	+= gef_sbc610.o
 obj-$(CONFIG_GEF_SBC310)	+= gef_sbc310.o
diff --git a/arch/powerpc/platforms/86xx/sbc8641d.c b/arch/powerpc/platforms/86xx/sbc8641d.c
deleted file mode 100644
index dc23dd383d6e..000000000000
--- a/arch/powerpc/platforms/86xx/sbc8641d.c
+++ /dev/null
@@ -1,87 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * SBC8641D board specific routines
- *
- * Copyright 2008 Wind River Systems Inc.
- *
- * By Paul Gortmaker (see MAINTAINERS for contact information)
- *
- * Based largely on the 8641 HPCN support by Freescale Semiconductor Inc.
- */
-
-#include <linux/stddef.h>
-#include <linux/kernel.h>
-#include <linux/pci.h>
-#include <linux/kdev_t.h>
-#include <linux/delay.h>
-#include <linux/seq_file.h>
-#include <linux/of_platform.h>
-
-#include <asm/time.h>
-#include <asm/machdep.h>
-#include <asm/pci-bridge.h>
-#include <asm/prom.h>
-#include <mm/mmu_decl.h>
-#include <asm/udbg.h>
-
-#include <asm/mpic.h>
-
-#include <sysdev/fsl_pci.h>
-#include <sysdev/fsl_soc.h>
-
-#include "mpc86xx.h"
-
-static void __init
-sbc8641_setup_arch(void)
-{
-	if (ppc_md.progress)
-		ppc_md.progress("sbc8641_setup_arch()", 0);
-
-	printk("SBC8641 board from Wind River\n");
-
-#ifdef CONFIG_SMP
-	mpc86xx_smp_init();
-#endif
-
-	fsl_pci_assign_primary();
-}
-
-
-static void
-sbc8641_show_cpuinfo(struct seq_file *m)
-{
-	uint svid = mfspr(SPRN_SVR);
-
-	seq_printf(m, "Vendor\t\t: Wind River Systems\n");
-
-	seq_printf(m, "SVR\t\t: 0x%x\n", svid);
-}
-
-
-/*
- * Called very early, device-tree isn't unflattened
- */
-static int __init sbc8641_probe(void)
-{
-	if (of_machine_is_compatible("wind,sbc8641"))
-		return 1;	/* Looks good */
-
-	return 0;
-}
-
-machine_arch_initcall(sbc8641, mpc86xx_common_publish_devices);
-
-define_machine(sbc8641) {
-	.name			= "SBC8641D",
-	.probe			= sbc8641_probe,
-	.setup_arch		= sbc8641_setup_arch,
-	.init_IRQ		= mpc86xx_init_irq,
-	.show_cpuinfo		= sbc8641_show_cpuinfo,
-	.get_irq		= mpic_get_irq,
-	.time_init		= mpc86xx_time_init,
-	.calibrate_decr		= generic_calibrate_decr,
-	.progress		= udbg_progress,
-#ifdef CONFIG_PCI
-	.pcibios_fixup_bus	= fsl_pcibios_fixup_bus,
-#endif
-};
diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c
index ca2555b8a0c2..82335e364c44 100644
--- a/arch/powerpc/platforms/cell/axon_msi.c
+++ b/arch/powerpc/platforms/cell/axon_msi.c
@@ -12,8 +12,8 @@
 #include <linux/export.h>
 #include <linux/of_platform.h>
 #include <linux/slab.h>
+#include <linux/debugfs.h>
 
-#include <asm/debugfs.h>
 #include <asm/dcr.h>
 #include <asm/machdep.h>
 #include <asm/prom.h>
@@ -480,6 +480,6 @@ void axon_msi_debug_setup(struct device_node *dn, struct axon_msic *msic)
 
 	snprintf(name, sizeof(name), "msic_%d", of_node_to_nid(dn));
 
-	debugfs_create_file(name, 0600, powerpc_debugfs_root, msic, &fops_msic);
+	debugfs_create_file(name, 0600, arch_debugfs_dir, msic, &fops_msic);
 }
 #endif /* DEBUG */
diff --git a/arch/powerpc/platforms/embedded6xx/holly.c b/arch/powerpc/platforms/embedded6xx/holly.c
index 85521b3e7098..7a85b117f7a4 100644
--- a/arch/powerpc/platforms/embedded6xx/holly.c
+++ b/arch/powerpc/platforms/embedded6xx/holly.c
@@ -251,7 +251,7 @@ static int ppc750_machine_check_exception(struct pt_regs *regs)
 	/* Are we prepared to handle this fault */
 	if ((entry = search_exception_tables(regs->nip)) != NULL) {
 		tsi108_clear_pci_cfg_error();
-		regs_set_return_msr(regs, regs->msr | MSR_RI);
+		regs_set_recoverable(regs);
 		regs_set_return_ip(regs, extable_fixup(entry));
 		return 1;
 	}
diff --git a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
index d8da6a483e59..9eb9abb5bce2 100644
--- a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
+++ b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
@@ -173,7 +173,7 @@ static int mpc7448_machine_check_exception(struct pt_regs *regs)
 	/* Are we prepared to handle this fault */
 	if ((entry = search_exception_tables(regs->nip)) != NULL) {
 		tsi108_clear_pci_cfg_error();
-		regs_set_return_msr(regs, regs->msr | MSR_RI);
+		regs_set_recoverable(regs);
 		regs_set_return_ip(regs, extable_fixup(entry));
 		return 1;
 	}
diff --git a/arch/powerpc/platforms/pasemi/idle.c b/arch/powerpc/platforms/pasemi/idle.c
index 534b0317fc15..6087c70ed2ef 100644
--- a/arch/powerpc/platforms/pasemi/idle.c
+++ b/arch/powerpc/platforms/pasemi/idle.c
@@ -59,7 +59,7 @@ static int pasemi_system_reset_exception(struct pt_regs *regs)
 	restore_astate(hard_smp_processor_id());
 
 	/* everything handled */
-	regs_set_return_msr(regs, regs->msr | MSR_RI);
+	regs_set_recoverable(regs);
 	return 1;
 }
 
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
index 528a7e0cf83a..e3ffdc8e8567 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -199,12 +199,12 @@ static ssize_t store_fastsleep_workaround_applyonce(struct device *dev,
 	 */
 	power7_fastsleep_workaround_exit = false;
 
-	get_online_cpus();
+	cpus_read_lock();
 	primary_thread_mask = cpu_online_cores_map();
 	on_each_cpu_mask(&primary_thread_mask,
 				pnv_fastsleep_workaround_apply,
 				&err, 1);
-	put_online_cpus();
+	cpus_read_unlock();
 	if (err) {
 		pr_err("fastsleep_workaround_applyonce change failed while running pnv_fastsleep_workaround_apply");
 		goto fail;
@@ -667,7 +667,6 @@ static unsigned long power9_idle_stop(unsigned long psscr)
 		sprs.purr	= mfspr(SPRN_PURR);
 		sprs.spurr	= mfspr(SPRN_SPURR);
 		sprs.dscr	= mfspr(SPRN_DSCR);
-		sprs.wort	= mfspr(SPRN_WORT);
 		sprs.ciabr	= mfspr(SPRN_CIABR);
 
 		sprs.mmcra	= mfspr(SPRN_MMCRA);
@@ -785,7 +784,6 @@ core_woken:
 	mtspr(SPRN_PURR,	sprs.purr);
 	mtspr(SPRN_SPURR,	sprs.spurr);
 	mtspr(SPRN_DSCR,	sprs.dscr);
-	mtspr(SPRN_WORT,	sprs.wort);
 	mtspr(SPRN_CIABR,	sprs.ciabr);
 
 	mtspr(SPRN_MMCRA,	sprs.mmcra);
diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c
index 537a4daed614..877720c64515 100644
--- a/arch/powerpc/platforms/powernv/memtrace.c
+++ b/arch/powerpc/platforms/powernv/memtrace.c
@@ -18,7 +18,6 @@
 #include <linux/memory_hotplug.h>
 #include <linux/numa.h>
 #include <asm/machdep.h>
-#include <asm/debugfs.h>
 #include <asm/cacheflush.h>
 
 /* This enables us to keep track of the memory removed from each node. */
@@ -330,7 +329,7 @@ DEFINE_SIMPLE_ATTRIBUTE(memtrace_init_fops, memtrace_enable_get,
 static int memtrace_init(void)
 {
 	memtrace_debugfs_dir = debugfs_create_dir("memtrace",
-						  powerpc_debugfs_root);
+						  arch_debugfs_dir);
 
 	debugfs_create_file("enable", 0600, memtrace_debugfs_dir,
 			    NULL, &memtrace_init_fops);
diff --git a/arch/powerpc/platforms/powernv/opal-imc.c b/arch/powerpc/platforms/powernv/opal-imc.c
index 7824cc364bc4..05d3832019b9 100644
--- a/arch/powerpc/platforms/powernv/opal-imc.c
+++ b/arch/powerpc/platforms/powernv/opal-imc.c
@@ -13,11 +13,11 @@
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
 #include <linux/crash_dump.h>
+#include <linux/debugfs.h>
 #include <asm/opal.h>
 #include <asm/io.h>
 #include <asm/imc-pmu.h>
 #include <asm/cputhreads.h>
-#include <asm/debugfs.h>
 
 static struct dentry *imc_debugfs_parent;
 
@@ -56,7 +56,7 @@ static void export_imc_mode_and_cmd(struct device_node *node,
 	u32 cb_offset;
 	struct imc_mem_info *ptr = pmu_ptr->mem_info;
 
-	imc_debugfs_parent = debugfs_create_dir("imc", powerpc_debugfs_root);
+	imc_debugfs_parent = debugfs_create_dir("imc", arch_debugfs_dir);
 
 	if (of_property_read_u32(node, "cb_offset", &cb_offset))
 		cb_offset = IMC_CNTL_BLK_OFFSET;
@@ -186,7 +186,7 @@ static void disable_nest_pmu_counters(void)
 	int nid, cpu;
 	const struct cpumask *l_cpumask;
 
-	get_online_cpus();
+	cpus_read_lock();
 	for_each_node_with_cpus(nid) {
 		l_cpumask = cpumask_of_node(nid);
 		cpu = cpumask_first_and(l_cpumask, cpu_online_mask);
@@ -195,7 +195,7 @@ static void disable_nest_pmu_counters(void)
 		opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST,
 				       get_hard_smp_processor_id(cpu));
 	}
-	put_online_cpus();
+	cpus_read_unlock();
 }
 
 static void disable_core_pmu_counters(void)
@@ -203,7 +203,7 @@ static void disable_core_pmu_counters(void)
 	cpumask_t cores_map;
 	int cpu, rc;
 
-	get_online_cpus();
+	cpus_read_lock();
 	/* Disable the IMC Core functions */
 	cores_map = cpu_online_cores_map();
 	for_each_cpu(cpu, &cores_map) {
@@ -213,7 +213,7 @@ static void disable_core_pmu_counters(void)
 			pr_err("%s: Failed to stop Core (cpu = %d)\n",
 				__FUNCTION__, cpu);
 	}
-	put_online_cpus();
+	cpus_read_unlock();
 }
 
 int get_max_nest_dev(void)
diff --git a/arch/powerpc/platforms/powernv/opal-lpc.c b/arch/powerpc/platforms/powernv/opal-lpc.c
index 608569082ba0..1e5d51db40f8 100644
--- a/arch/powerpc/platforms/powernv/opal-lpc.c
+++ b/arch/powerpc/platforms/powernv/opal-lpc.c
@@ -10,13 +10,13 @@
 #include <linux/bug.h>
 #include <linux/io.h>
 #include <linux/slab.h>
+#include <linux/debugfs.h>
 
 #include <asm/machdep.h>
 #include <asm/firmware.h>
 #include <asm/opal.h>
 #include <asm/prom.h>
 #include <linux/uaccess.h>
-#include <asm/debugfs.h>
 #include <asm/isa-bridge.h>
 
 static int opal_lpc_chip_id = -1;
@@ -371,7 +371,7 @@ static int opal_lpc_init_debugfs(void)
 	if (opal_lpc_chip_id < 0)
 		return -ENODEV;
 
-	root = debugfs_create_dir("lpc", powerpc_debugfs_root);
+	root = debugfs_create_dir("lpc", arch_debugfs_dir);
 
 	rc |= opal_lpc_debugfs_create_type(root, "io", OPAL_LPC_IO);
 	rc |= opal_lpc_debugfs_create_type(root, "mem", OPAL_LPC_MEM);
diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c
index fd510d961b8c..6b4eed2ef4fa 100644
--- a/arch/powerpc/platforms/powernv/opal-xscom.c
+++ b/arch/powerpc/platforms/powernv/opal-xscom.c
@@ -14,11 +14,11 @@
 #include <linux/gfp.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
+#include <linux/debugfs.h>
 
 #include <asm/machdep.h>
 #include <asm/firmware.h>
 #include <asm/opal.h>
-#include <asm/debugfs.h>
 #include <asm/prom.h>
 
 static u64 opal_scom_unmangle(u64 addr)
@@ -189,7 +189,7 @@ static int scom_debug_init(void)
 	if (!firmware_has_feature(FW_FEATURE_OPAL))
 		return 0;
 
-	root = debugfs_create_dir("scom", powerpc_debugfs_root);
+	root = debugfs_create_dir("scom", arch_debugfs_dir);
 	if (!root)
 		return -1;
 
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 2835376e61a4..e9d18519e650 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -588,7 +588,7 @@ static int opal_recover_mce(struct pt_regs *regs,
 {
 	int recovered = 0;
 
-	if (!(regs->msr & MSR_RI)) {
+	if (regs_is_unrecoverable(regs)) {
 		/* If MSR_RI isn't set, we cannot recover */
 		pr_err("Machine check interrupt unrecoverable: MSR(RI=0)\n");
 		recovered = 0;
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 7de464679292..3dd35c327d1c 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -20,6 +20,7 @@
 #include <linux/iommu.h>
 #include <linux/rculist.h>
 #include <linux/sizes.h>
+#include <linux/debugfs.h>
 
 #include <asm/sections.h>
 #include <asm/io.h>
@@ -32,10 +33,10 @@
 #include <asm/iommu.h>
 #include <asm/tce.h>
 #include <asm/xics.h>
-#include <asm/debugfs.h>
 #include <asm/firmware.h>
 #include <asm/pnv-pci.h>
 #include <asm/mmzone.h>
+#include <asm/xive.h>
 
 #include <misc/cxl-base.h>
 
@@ -1962,27 +1963,40 @@ void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 	pe->dma_setup_done = true;
 }
 
-int64_t pnv_opal_pci_msi_eoi(struct irq_chip *chip, unsigned int hw_irq)
+/*
+ * Called from KVM in real mode to EOI passthru interrupts. The ICP
+ * EOI is handled directly in KVM in kvmppc_deliver_irq_passthru().
+ *
+ * The IRQ data is mapped in the PCI-MSI domain and the EOI OPAL call
+ * needs an HW IRQ number mapped in the XICS IRQ domain. The HW IRQ
+ * numbers of the in-the-middle MSI domain are vector numbers and it's
+ * good enough for OPAL. Use that.
+ */
+int64_t pnv_opal_pci_msi_eoi(struct irq_data *d)
 {
-	struct pnv_phb *phb = container_of(chip, struct pnv_phb,
-					   ioda.irq_chip);
+	struct pci_controller *hose = irq_data_get_irq_chip_data(d->parent_data);
+	struct pnv_phb *phb = hose->private_data;
 
-	return opal_pci_msi_eoi(phb->opal_id, hw_irq);
+	return opal_pci_msi_eoi(phb->opal_id, d->parent_data->hwirq);
 }
 
+/*
+ * The IRQ data is mapped in the XICS domain, with OPAL HW IRQ numbers
+ */
 static void pnv_ioda2_msi_eoi(struct irq_data *d)
 {
 	int64_t rc;
 	unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
-	struct irq_chip *chip = irq_data_get_irq_chip(d);
+	struct pci_controller *hose = irq_data_get_irq_chip_data(d);
+	struct pnv_phb *phb = hose->private_data;
 
-	rc = pnv_opal_pci_msi_eoi(chip, hw_irq);
+	rc = opal_pci_msi_eoi(phb->opal_id, hw_irq);
 	WARN_ON_ONCE(rc);
 
 	icp_native_eoi(d);
 }
 
-
+/* P8/CXL only */
 void pnv_set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq)
 {
 	struct irq_data *idata;
@@ -2004,27 +2018,32 @@ void pnv_set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq)
 		phb->ioda.irq_chip.irq_eoi = pnv_ioda2_msi_eoi;
 	}
 	irq_set_chip(virq, &phb->ioda.irq_chip);
+	irq_set_chip_data(virq, phb->hose);
 }
 
+static struct irq_chip pnv_pci_msi_irq_chip;
+
 /*
  * Returns true iff chip is something that we could call
  * pnv_opal_pci_msi_eoi for.
  */
 bool is_pnv_opal_msi(struct irq_chip *chip)
 {
-	return chip->irq_eoi == pnv_ioda2_msi_eoi;
+	return chip == &pnv_pci_msi_irq_chip;
 }
 EXPORT_SYMBOL_GPL(is_pnv_opal_msi);
 
-static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
-				  unsigned int hwirq, unsigned int virq,
-				  unsigned int is_64, struct msi_msg *msg)
+static int __pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
+				    unsigned int xive_num,
+				    unsigned int is_64, struct msi_msg *msg)
 {
 	struct pnv_ioda_pe *pe = pnv_ioda_get_pe(dev);
-	unsigned int xive_num = hwirq - phb->msi_base;
 	__be32 data;
 	int rc;
 
+	dev_dbg(&dev->dev, "%s: setup %s-bit MSI for vector #%d\n", __func__,
+		is_64 ? "64" : "32", xive_num);
+
 	/* No PE assigned ? bail out ... no MSI for you ! */
 	if (pe == NULL)
 		return -ENXIO;
@@ -2072,12 +2091,209 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
 	}
 	msg->data = be32_to_cpu(data);
 
-	pnv_set_msi_irq_chip(phb, virq);
+	return 0;
+}
 
-	pr_devel("%s: %s-bit MSI on hwirq %x (xive #%d),"
-		 " address=%x_%08x data=%x PE# %x\n",
-		 pci_name(dev), is_64 ? "64" : "32", hwirq, xive_num,
-		 msg->address_hi, msg->address_lo, data, pe->pe_number);
+/*
+ * The msi_free() op is called before irq_domain_free_irqs_top() when
+ * the handler data is still available. Use that to clear the XIVE
+ * controller.
+ */
+static void pnv_msi_ops_msi_free(struct irq_domain *domain,
+				 struct msi_domain_info *info,
+				 unsigned int irq)
+{
+	if (xive_enabled())
+		xive_irq_free_data(irq);
+}
+
+static struct msi_domain_ops pnv_pci_msi_domain_ops = {
+	.msi_free	= pnv_msi_ops_msi_free,
+};
+
+static void pnv_msi_shutdown(struct irq_data *d)
+{
+	d = d->parent_data;
+	if (d->chip->irq_shutdown)
+		d->chip->irq_shutdown(d);
+}
+
+static void pnv_msi_mask(struct irq_data *d)
+{
+	pci_msi_mask_irq(d);
+	irq_chip_mask_parent(d);
+}
+
+static void pnv_msi_unmask(struct irq_data *d)
+{
+	pci_msi_unmask_irq(d);
+	irq_chip_unmask_parent(d);
+}
+
+static struct irq_chip pnv_pci_msi_irq_chip = {
+	.name		= "PNV-PCI-MSI",
+	.irq_shutdown	= pnv_msi_shutdown,
+	.irq_mask	= pnv_msi_mask,
+	.irq_unmask	= pnv_msi_unmask,
+	.irq_eoi	= irq_chip_eoi_parent,
+};
+
+static struct msi_domain_info pnv_msi_domain_info = {
+	.flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+		  MSI_FLAG_MULTI_PCI_MSI  | MSI_FLAG_PCI_MSIX),
+	.ops   = &pnv_pci_msi_domain_ops,
+	.chip  = &pnv_pci_msi_irq_chip,
+};
+
+static void pnv_msi_compose_msg(struct irq_data *d, struct msi_msg *msg)
+{
+	struct msi_desc *entry = irq_data_get_msi_desc(d);
+	struct pci_dev *pdev = msi_desc_to_pci_dev(entry);
+	struct pci_controller *hose = irq_data_get_irq_chip_data(d);
+	struct pnv_phb *phb = hose->private_data;
+	int rc;
+
+	rc = __pnv_pci_ioda_msi_setup(phb, pdev, d->hwirq,
+				      entry->msi_attrib.is_64, msg);
+	if (rc)
+		dev_err(&pdev->dev, "Failed to setup %s-bit MSI #%ld : %d\n",
+			entry->msi_attrib.is_64 ? "64" : "32", d->hwirq, rc);
+}
+
+/*
+ * The IRQ data is mapped in the MSI domain in which HW IRQ numbers
+ * correspond to vector numbers.
+ */
+static void pnv_msi_eoi(struct irq_data *d)
+{
+	struct pci_controller *hose = irq_data_get_irq_chip_data(d);
+	struct pnv_phb *phb = hose->private_data;
+
+	if (phb->model == PNV_PHB_MODEL_PHB3) {
+		/*
+		 * The EOI OPAL call takes an OPAL HW IRQ number but
+		 * since it is translated into a vector number in
+		 * OPAL, use that directly.
+		 */
+		WARN_ON_ONCE(opal_pci_msi_eoi(phb->opal_id, d->hwirq));
+	}
+
+	irq_chip_eoi_parent(d);
+}
+
+static struct irq_chip pnv_msi_irq_chip = {
+	.name			= "PNV-MSI",
+	.irq_shutdown		= pnv_msi_shutdown,
+	.irq_mask		= irq_chip_mask_parent,
+	.irq_unmask		= irq_chip_unmask_parent,
+	.irq_eoi		= pnv_msi_eoi,
+	.irq_set_affinity	= irq_chip_set_affinity_parent,
+	.irq_compose_msi_msg	= pnv_msi_compose_msg,
+};
+
+static int pnv_irq_parent_domain_alloc(struct irq_domain *domain,
+				       unsigned int virq, int hwirq)
+{
+	struct irq_fwspec parent_fwspec;
+	int ret;
+
+	parent_fwspec.fwnode = domain->parent->fwnode;
+	parent_fwspec.param_count = 2;
+	parent_fwspec.param[0] = hwirq;
+	parent_fwspec.param[1] = IRQ_TYPE_EDGE_RISING;
+
+	ret = irq_domain_alloc_irqs_parent(domain, virq, 1, &parent_fwspec);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int pnv_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				unsigned int nr_irqs, void *arg)
+{
+	struct pci_controller *hose = domain->host_data;
+	struct pnv_phb *phb = hose->private_data;
+	msi_alloc_info_t *info = arg;
+	struct pci_dev *pdev = msi_desc_to_pci_dev(info->desc);
+	int hwirq;
+	int i, ret;
+
+	hwirq = msi_bitmap_alloc_hwirqs(&phb->msi_bmp, nr_irqs);
+	if (hwirq < 0) {
+		dev_warn(&pdev->dev, "failed to find a free MSI\n");
+		return -ENOSPC;
+	}
+
+	dev_dbg(&pdev->dev, "%s bridge %pOF %d/%x #%d\n", __func__,
+		hose->dn, virq, hwirq, nr_irqs);
+
+	for (i = 0; i < nr_irqs; i++) {
+		ret = pnv_irq_parent_domain_alloc(domain, virq + i,
+						  phb->msi_base + hwirq + i);
+		if (ret)
+			goto out;
+
+		irq_domain_set_hwirq_and_chip(domain, virq + i, hwirq + i,
+					      &pnv_msi_irq_chip, hose);
+	}
+
+	return 0;
+
+out:
+	irq_domain_free_irqs_parent(domain, virq, i - 1);
+	msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq, nr_irqs);
+	return ret;
+}
+
+static void pnv_irq_domain_free(struct irq_domain *domain, unsigned int virq,
+				unsigned int nr_irqs)
+{
+	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
+	struct pci_controller *hose = irq_data_get_irq_chip_data(d);
+	struct pnv_phb *phb = hose->private_data;
+
+	pr_debug("%s bridge %pOF %d/%lx #%d\n", __func__, hose->dn,
+		 virq, d->hwirq, nr_irqs);
+
+	msi_bitmap_free_hwirqs(&phb->msi_bmp, d->hwirq, nr_irqs);
+	/* XIVE domain is cleared through ->msi_free() */
+}
+
+static const struct irq_domain_ops pnv_irq_domain_ops = {
+	.alloc  = pnv_irq_domain_alloc,
+	.free   = pnv_irq_domain_free,
+};
+
+static int pnv_msi_allocate_domains(struct pci_controller *hose, unsigned int count)
+{
+	struct pnv_phb *phb = hose->private_data;
+	struct irq_domain *parent = irq_get_default_host();
+
+	hose->fwnode = irq_domain_alloc_named_id_fwnode("PNV-MSI", phb->opal_id);
+	if (!hose->fwnode)
+		return -ENOMEM;
+
+	hose->dev_domain = irq_domain_create_hierarchy(parent, 0, count,
+						       hose->fwnode,
+						       &pnv_irq_domain_ops, hose);
+	if (!hose->dev_domain) {
+		pr_err("PCI: failed to create IRQ domain bridge %pOF (domain %d)\n",
+		       hose->dn, hose->global_number);
+		irq_domain_free_fwnode(hose->fwnode);
+		return -ENOMEM;
+	}
+
+	hose->msi_domain = pci_msi_create_irq_domain(of_node_to_fwnode(hose->dn),
+						     &pnv_msi_domain_info,
+						     hose->dev_domain);
+	if (!hose->msi_domain) {
+		pr_err("PCI: failed to create MSI IRQ domain bridge %pOF (domain %d)\n",
+		       hose->dn, hose->global_number);
+		irq_domain_free_fwnode(hose->fwnode);
+		irq_domain_remove(hose->dev_domain);
+		return -ENOMEM;
+	}
 
 	return 0;
 }
@@ -2102,10 +2318,10 @@ static void pnv_pci_init_ioda_msis(struct pnv_phb *phb)
 		return;
 	}
 
-	phb->msi_setup = pnv_pci_ioda_msi_setup;
-	phb->msi32_support = 1;
 	pr_info("  Allocated bitmap for %d MSIs (base IRQ 0x%x)\n",
 		count, phb->msi_base);
+
+	pnv_msi_allocate_domains(phb->hose, count);
 }
 
 static void pnv_ioda_setup_pe_res(struct pnv_ioda_pe *pe,
@@ -2259,7 +2475,7 @@ static void pnv_pci_ioda_create_dbgfs(void)
 		phb = hose->private_data;
 
 		sprintf(name, "PCI%04x", hose->global_number);
-		phb->dbgfs = debugfs_create_dir(name, powerpc_debugfs_root);
+		phb->dbgfs = debugfs_create_dir(name, arch_debugfs_dir);
 
 		debugfs_create_file_unsafe("dump_diag_regs", 0200, phb->dbgfs,
 					   phb, &pnv_pci_diag_data_fops);
@@ -2709,8 +2925,6 @@ static const struct pci_controller_ops pnv_pci_ioda_controller_ops = {
 	.dma_dev_setup		= pnv_pci_ioda_dma_dev_setup,
 	.dma_bus_setup		= pnv_pci_ioda_dma_bus_setup,
 	.iommu_bypass_supported	= pnv_pci_ioda_iommu_bypass_supported,
-	.setup_msi_irqs		= pnv_setup_msi_irqs,
-	.teardown_msi_irqs	= pnv_teardown_msi_irqs,
 	.enable_device_hook	= pnv_pci_enable_device_hook,
 	.release_device		= pnv_pci_release_device,
 	.window_alignment	= pnv_pci_window_alignment,
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 6bb3c52633fb..9a8391b983d1 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -160,73 +160,6 @@ exit:
 }
 EXPORT_SYMBOL_GPL(pnv_pci_set_power_state);
 
-int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
-{
-	struct pnv_phb *phb = pci_bus_to_pnvhb(pdev->bus);
-	struct msi_desc *entry;
-	struct msi_msg msg;
-	int hwirq;
-	unsigned int virq;
-	int rc;
-
-	if (WARN_ON(!phb) || !phb->msi_bmp.bitmap)
-		return -ENODEV;
-
-	if (pdev->no_64bit_msi && !phb->msi32_support)
-		return -ENODEV;
-
-	for_each_pci_msi_entry(entry, pdev) {
-		if (!entry->msi_attrib.is_64 && !phb->msi32_support) {
-			pr_warn("%s: Supports only 64-bit MSIs\n",
-				pci_name(pdev));
-			return -ENXIO;
-		}
-		hwirq = msi_bitmap_alloc_hwirqs(&phb->msi_bmp, 1);
-		if (hwirq < 0) {
-			pr_warn("%s: Failed to find a free MSI\n",
-				pci_name(pdev));
-			return -ENOSPC;
-		}
-		virq = irq_create_mapping(NULL, phb->msi_base + hwirq);
-		if (!virq) {
-			pr_warn("%s: Failed to map MSI to linux irq\n",
-				pci_name(pdev));
-			msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq, 1);
-			return -ENOMEM;
-		}
-		rc = phb->msi_setup(phb, pdev, phb->msi_base + hwirq,
-				    virq, entry->msi_attrib.is_64, &msg);
-		if (rc) {
-			pr_warn("%s: Failed to setup MSI\n", pci_name(pdev));
-			irq_dispose_mapping(virq);
-			msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq, 1);
-			return rc;
-		}
-		irq_set_msi_desc(virq, entry);
-		pci_write_msi_msg(virq, &msg);
-	}
-	return 0;
-}
-
-void pnv_teardown_msi_irqs(struct pci_dev *pdev)
-{
-	struct pnv_phb *phb = pci_bus_to_pnvhb(pdev->bus);
-	struct msi_desc *entry;
-	irq_hw_number_t hwirq;
-
-	if (WARN_ON(!phb))
-		return;
-
-	for_each_pci_msi_entry(entry, pdev) {
-		if (!entry->irq)
-			continue;
-		hwirq = virq_to_hw(entry->irq);
-		irq_set_msi_desc(entry->irq, NULL);
-		irq_dispose_mapping(entry->irq);
-		msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq - phb->msi_base, 1);
-	}
-}
-
 /* Nicely print the contents of the PE State Tables (PEST). */
 static void pnv_pci_dump_pest(__be64 pestA[], __be64 pestB[], int pest_size)
 {
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index c8d4f222a86f..966a9eb64339 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -123,11 +123,7 @@ struct pnv_phb {
 #endif
 
 	unsigned int		msi_base;
-	unsigned int		msi32_support;
 	struct msi_bitmap	msi_bmp;
-	int (*msi_setup)(struct pnv_phb *phb, struct pci_dev *dev,
-			 unsigned int hwirq, unsigned int virq,
-			 unsigned int is_64, struct msi_msg *msg);
 	int (*init_m64)(struct pnv_phb *phb);
 	int (*get_pe_state)(struct pnv_phb *phb, int pe_no);
 	void (*freeze_pe)(struct pnv_phb *phb, int pe_no);
@@ -289,8 +285,6 @@ extern void pnv_pci_init_npu2_opencapi_phb(struct device_node *np);
 extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev);
 extern int pnv_eeh_phb_reset(struct pci_controller *hose, int option);
 
-extern int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type);
-extern void pnv_teardown_msi_irqs(struct pci_dev *pdev);
 extern struct pnv_ioda_pe *pnv_pci_bdfn_to_pe(struct pnv_phb *phb, u16 bdfn);
 extern struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev);
 extern void pnv_set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq);
diff --git a/arch/powerpc/platforms/ps3/htab.c b/arch/powerpc/platforms/ps3/htab.c
index 7ddc7ec6a7c0..ef710a715903 100644
--- a/arch/powerpc/platforms/ps3/htab.c
+++ b/arch/powerpc/platforms/ps3/htab.c
@@ -169,7 +169,8 @@ static void ps3_hpte_invalidate(unsigned long slot, unsigned long vpn,
 	spin_unlock_irqrestore(&ps3_htab_lock, flags);
 }
 
-static void ps3_hpte_clear(void)
+/* Called during kexec sequence with MMU off */
+static notrace void ps3_hpte_clear(void)
 {
 	unsigned long hpte_count = (1UL << ppc64_pft_size) >> 4;
 	u64 i;
diff --git a/arch/powerpc/platforms/ps3/mm.c b/arch/powerpc/platforms/ps3/mm.c
index a81eac35d900..9c44f335c0b9 100644
--- a/arch/powerpc/platforms/ps3/mm.c
+++ b/arch/powerpc/platforms/ps3/mm.c
@@ -195,9 +195,11 @@ fail:
 
 /**
  * ps3_mm_vas_destroy -
+ *
+ * called during kexec sequence with MMU off.
  */
 
-void ps3_mm_vas_destroy(void)
+notrace void ps3_mm_vas_destroy(void)
 {
 	int result;
 
@@ -1243,9 +1245,11 @@ void __init ps3_mm_init(void)
 
 /**
  * ps3_mm_shutdown - final cleanup of address space
+ *
+ * called during kexec sequence with MMU off.
  */
 
-void ps3_mm_shutdown(void)
+notrace void ps3_mm_shutdown(void)
 {
 	ps3_mm_region_destroy(&map.r1);
 }
diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c
index 982f069e4c31..352af5b14a0f 100644
--- a/arch/powerpc/platforms/pseries/dtl.c
+++ b/arch/powerpc/platforms/pseries/dtl.c
@@ -11,10 +11,10 @@
 #include <linux/spinlock.h>
 #include <asm/smp.h>
 #include <linux/uaccess.h>
+#include <linux/debugfs.h>
 #include <asm/firmware.h>
 #include <asm/dtl.h>
 #include <asm/lppaca.h>
-#include <asm/debugfs.h>
 #include <asm/plpar_wrappers.h>
 #include <asm/machdep.h>
 
@@ -338,7 +338,7 @@ static int dtl_init(void)
 
 	/* set up common debugfs structure */
 
-	dtl_dir = debugfs_create_dir("dtl", powerpc_debugfs_root);
+	dtl_dir = debugfs_create_dir("dtl", arch_debugfs_dir);
 
 	debugfs_create_x8("dtl_event_mask", 0600, dtl_dir, &dtl_event_mask);
 	debugfs_create_u32("dtl_buf_entries", 0400, dtl_dir, &dtl_buf_entries);
diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c
index 4c7b7f5a2ebc..f162156b7b68 100644
--- a/arch/powerpc/platforms/pseries/firmware.c
+++ b/arch/powerpc/platforms/pseries/firmware.c
@@ -119,10 +119,11 @@ struct vec5_fw_feature {
 
 static __initdata struct vec5_fw_feature
 vec5_fw_features_table[] = {
-	{FW_FEATURE_TYPE1_AFFINITY,	OV5_TYPE1_AFFINITY},
+	{FW_FEATURE_FORM1_AFFINITY,	OV5_FORM1_AFFINITY},
 	{FW_FEATURE_PRRN,		OV5_PRRN},
 	{FW_FEATURE_DRMEM_V2,		OV5_DRMEM_V2},
 	{FW_FEATURE_DRC_INFO,		OV5_DRC_INFO},
+	{FW_FEATURE_FORM2_AFFINITY,	OV5_FORM2_AFFINITY},
 };
 
 static void __init fw_vec5_feature_init(const char *vec5, unsigned long len)
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 7e970f81d8ff..d646c22e94ab 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -39,6 +39,12 @@
 /* This version can't take the spinlock, because it never returns */
 static int rtas_stop_self_token = RTAS_UNKNOWN_SERVICE;
 
+/*
+ * Record the CPU ids used on each nodes.
+ * Protected by cpu_add_remove_lock.
+ */
+static cpumask_var_t node_recorded_ids_map[MAX_NUMNODES];
+
 static void rtas_stop_self(void)
 {
 	static struct rtas_args args;
@@ -139,72 +145,148 @@ static void pseries_cpu_die(unsigned int cpu)
 	paca_ptrs[cpu]->cpu_start = 0;
 }
 
+/**
+ * find_cpu_id_range - found a linear ranger of @nthreads free CPU ids.
+ * @nthreads : the number of threads (cpu ids)
+ * @assigned_node : the node it belongs to or NUMA_NO_NODE if free ids from any
+ *                  node can be peek.
+ * @cpu_mask: the returned CPU mask.
+ *
+ * Returns 0 on success.
+ */
+static int find_cpu_id_range(unsigned int nthreads, int assigned_node,
+			     cpumask_var_t *cpu_mask)
+{
+	cpumask_var_t candidate_mask;
+	unsigned int cpu, node;
+	int rc = -ENOSPC;
+
+	if (!zalloc_cpumask_var(&candidate_mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	cpumask_clear(*cpu_mask);
+	for (cpu = 0; cpu < nthreads; cpu++)
+		cpumask_set_cpu(cpu, *cpu_mask);
+
+	BUG_ON(!cpumask_subset(cpu_present_mask, cpu_possible_mask));
+
+	/* Get a bitmap of unoccupied slots. */
+	cpumask_xor(candidate_mask, cpu_possible_mask, cpu_present_mask);
+
+	if (assigned_node != NUMA_NO_NODE) {
+		/*
+		 * Remove free ids previously assigned on the other nodes. We
+		 * can walk only online nodes because once a node became online
+		 * it is not turned offlined back.
+		 */
+		for_each_online_node(node) {
+			if (node == assigned_node)
+				continue;
+			cpumask_andnot(candidate_mask, candidate_mask,
+				       node_recorded_ids_map[node]);
+		}
+	}
+
+	if (cpumask_empty(candidate_mask))
+		goto out;
+
+	while (!cpumask_empty(*cpu_mask)) {
+		if (cpumask_subset(*cpu_mask, candidate_mask))
+			/* Found a range where we can insert the new cpu(s) */
+			break;
+		cpumask_shift_left(*cpu_mask, *cpu_mask, nthreads);
+	}
+
+	if (!cpumask_empty(*cpu_mask))
+		rc = 0;
+
+out:
+	free_cpumask_var(candidate_mask);
+	return rc;
+}
+
 /*
  * Update cpu_present_mask and paca(s) for a new cpu node.  The wrinkle
- * here is that a cpu device node may represent up to two logical cpus
+ * here is that a cpu device node may represent multiple logical cpus
  * in the SMT case.  We must honor the assumption in other code that
  * the logical ids for sibling SMT threads x and y are adjacent, such
  * that x^1 == y and y^1 == x.
  */
 static int pseries_add_processor(struct device_node *np)
 {
-	unsigned int cpu;
-	cpumask_var_t candidate_mask, tmp;
-	int err = -ENOSPC, len, nthreads, i;
+	int len, nthreads, node, cpu, assigned_node;
+	int rc = 0;
+	cpumask_var_t cpu_mask;
 	const __be32 *intserv;
 
 	intserv = of_get_property(np, "ibm,ppc-interrupt-server#s", &len);
 	if (!intserv)
 		return 0;
 
-	zalloc_cpumask_var(&candidate_mask, GFP_KERNEL);
-	zalloc_cpumask_var(&tmp, GFP_KERNEL);
-
 	nthreads = len / sizeof(u32);
-	for (i = 0; i < nthreads; i++)
-		cpumask_set_cpu(i, tmp);
+
+	if (!alloc_cpumask_var(&cpu_mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	/*
+	 * Fetch from the DT nodes read by dlpar_configure_connector() the NUMA
+	 * node id the added CPU belongs to.
+	 */
+	node = of_node_to_nid(np);
+	if (node < 0 || !node_possible(node))
+		node = first_online_node;
+
+	BUG_ON(node == NUMA_NO_NODE);
+	assigned_node = node;
 
 	cpu_maps_update_begin();
 
-	BUG_ON(!cpumask_subset(cpu_present_mask, cpu_possible_mask));
-
-	/* Get a bitmap of unoccupied slots. */
-	cpumask_xor(candidate_mask, cpu_possible_mask, cpu_present_mask);
-	if (cpumask_empty(candidate_mask)) {
-		/* If we get here, it most likely means that NR_CPUS is
-		 * less than the partition's max processors setting.
+	rc = find_cpu_id_range(nthreads, node, &cpu_mask);
+	if (rc && nr_node_ids > 1) {
+		/*
+		 * Try again, considering the free CPU ids from the other node.
 		 */
-		printk(KERN_ERR "Cannot add cpu %pOF; this system configuration"
-		       " supports %d logical cpus.\n", np,
-		       num_possible_cpus());
-		goto out_unlock;
+		node = NUMA_NO_NODE;
+		rc = find_cpu_id_range(nthreads, NUMA_NO_NODE, &cpu_mask);
 	}
 
-	while (!cpumask_empty(tmp))
-		if (cpumask_subset(tmp, candidate_mask))
-			/* Found a range where we can insert the new cpu(s) */
-			break;
-		else
-			cpumask_shift_left(tmp, tmp, nthreads);
-
-	if (cpumask_empty(tmp)) {
-		printk(KERN_ERR "Unable to find space in cpu_present_mask for"
-		       " processor %pOFn with %d thread(s)\n", np,
-		       nthreads);
-		goto out_unlock;
+	if (rc) {
+		pr_err("Cannot add cpu %pOF; this system configuration"
+		       " supports %d logical cpus.\n", np, num_possible_cpus());
+		goto out;
 	}
 
-	for_each_cpu(cpu, tmp) {
+	for_each_cpu(cpu, cpu_mask) {
 		BUG_ON(cpu_present(cpu));
 		set_cpu_present(cpu, true);
 		set_hard_smp_processor_id(cpu, be32_to_cpu(*intserv++));
 	}
-	err = 0;
-out_unlock:
+
+	/* Record the newly used CPU ids for the associate node. */
+	cpumask_or(node_recorded_ids_map[assigned_node],
+		   node_recorded_ids_map[assigned_node], cpu_mask);
+
+	/*
+	 * If node is set to NUMA_NO_NODE, CPU ids have be reused from
+	 * another node, remove them from its mask.
+	 */
+	if (node == NUMA_NO_NODE) {
+		cpu = cpumask_first(cpu_mask);
+		pr_warn("Reusing free CPU ids %d-%d from another node\n",
+			cpu, cpu + nthreads - 1);
+		for_each_online_node(node) {
+			if (node == assigned_node)
+				continue;
+			cpumask_andnot(node_recorded_ids_map[node],
+				       node_recorded_ids_map[node],
+				       cpu_mask);
+		}
+	}
+
+out:
 	cpu_maps_update_done();
-	free_cpumask_var(candidate_mask);
-	free_cpumask_var(tmp);
-	return err;
+	free_cpumask_var(cpu_mask);
+	return rc;
 }
 
 /*
@@ -498,6 +580,8 @@ static ssize_t dlpar_cpu_add(u32 drc_index)
 		return saved_rc;
 	}
 
+	update_numa_distance(dn);
+
 	rc = dlpar_online_cpu(dn);
 	if (rc) {
 		saved_rc = rc;
@@ -908,6 +992,7 @@ static struct notifier_block pseries_smp_nb = {
 static int __init pseries_cpu_hotplug_init(void)
 {
 	int qcss_tok;
+	unsigned int node;
 
 #ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
 	ppc_md.cpu_probe = dlpar_cpu_probe;
@@ -929,8 +1014,18 @@ static int __init pseries_cpu_hotplug_init(void)
 	smp_ops->cpu_die = pseries_cpu_die;
 
 	/* Processors can be added/removed only on LPAR */
-	if (firmware_has_feature(FW_FEATURE_LPAR))
+	if (firmware_has_feature(FW_FEATURE_LPAR)) {
+		for_each_node(node) {
+			alloc_bootmem_cpumask_var(&node_recorded_ids_map[node]);
+
+			/* Record ids of CPU added at boot time */
+			cpumask_or(node_recorded_ids_map[node],
+				   node_recorded_ids_map[node],
+				   cpumask_of_node(node));
+		}
+
 		of_reconfig_notifier_register(&pseries_smp_nb);
+	}
 
 	return 0;
 }
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index d4f28ee4d5dc..44246ba59768 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -180,6 +180,8 @@ static int update_lmb_associativity_index(struct drmem_lmb *lmb)
 		return -ENODEV;
 	}
 
+	update_numa_distance(lmb_node);
+
 	dr_node = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
 	if (!dr_node) {
 		dlpar_free_cc_nodes(lmb_node);
@@ -977,6 +979,10 @@ static int pseries_memory_notifier(struct notifier_block *nb,
 	case OF_RECONFIG_DETACH_NODE:
 		err = pseries_remove_mem_node(rd->dn);
 		break;
+	case OF_RECONFIG_UPDATE_PROPERTY:
+		if (!strcmp(rd->dn->name,
+			    "ibm,dynamic-reconfiguration-memory"))
+			drmem_update_lmbs(rd->prop);
 	}
 	return notifier_from_errno(err);
 }
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 0c55b991f665..dab5c56ffd0e 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -53,28 +53,31 @@ enum {
 	DDW_EXT_QUERY_OUT_SIZE = 2
 };
 
-static struct iommu_table_group *iommu_pseries_alloc_group(int node)
+static struct iommu_table *iommu_pseries_alloc_table(int node)
 {
-	struct iommu_table_group *table_group;
 	struct iommu_table *tbl;
 
-	table_group = kzalloc_node(sizeof(struct iommu_table_group), GFP_KERNEL,
-			   node);
-	if (!table_group)
-		return NULL;
-
 	tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, node);
 	if (!tbl)
-		goto free_group;
+		return NULL;
 
 	INIT_LIST_HEAD_RCU(&tbl->it_group_list);
 	kref_init(&tbl->it_kref);
+	return tbl;
+}
 
-	table_group->tables[0] = tbl;
+static struct iommu_table_group *iommu_pseries_alloc_group(int node)
+{
+	struct iommu_table_group *table_group;
 
-	return table_group;
+	table_group = kzalloc_node(sizeof(*table_group), GFP_KERNEL, node);
+	if (!table_group)
+		return NULL;
+
+	table_group->tables[0] = iommu_pseries_alloc_table(node);
+	if (table_group->tables[0])
+		return table_group;
 
-free_group:
 	kfree(table_group);
 	return NULL;
 }
@@ -107,6 +110,8 @@ static int tce_build_pSeries(struct iommu_table *tbl, long index,
 	u64 proto_tce;
 	__be64 *tcep;
 	u64 rpn;
+	const unsigned long tceshift = tbl->it_page_shift;
+	const unsigned long pagesize = IOMMU_PAGE_SIZE(tbl);
 
 	proto_tce = TCE_PCI_READ; // Read allowed
 
@@ -117,10 +122,10 @@ static int tce_build_pSeries(struct iommu_table *tbl, long index,
 
 	while (npages--) {
 		/* can't move this out since we might cross MEMBLOCK boundary */
-		rpn = __pa(uaddr) >> TCE_SHIFT;
-		*tcep = cpu_to_be64(proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT);
+		rpn = __pa(uaddr) >> tceshift;
+		*tcep = cpu_to_be64(proto_tce | rpn << tceshift);
 
-		uaddr += TCE_PAGE_SIZE;
+		uaddr += pagesize;
 		tcep++;
 	}
 	return 0;
@@ -146,7 +151,7 @@ static unsigned long tce_get_pseries(struct iommu_table *tbl, long index)
 	return be64_to_cpu(*tcep);
 }
 
-static void tce_free_pSeriesLP(unsigned long liobn, long, long);
+static void tce_free_pSeriesLP(unsigned long liobn, long, long, long);
 static void tce_freemulti_pSeriesLP(struct iommu_table*, long, long);
 
 static int tce_build_pSeriesLP(unsigned long liobn, long tcenum, long tceshift,
@@ -166,12 +171,12 @@ static int tce_build_pSeriesLP(unsigned long liobn, long tcenum, long tceshift,
 		proto_tce |= TCE_PCI_WRITE;
 
 	while (npages--) {
-		tce = proto_tce | (rpn & TCE_RPN_MASK) << tceshift;
+		tce = proto_tce | rpn << tceshift;
 		rc = plpar_tce_put((u64)liobn, (u64)tcenum << tceshift, tce);
 
 		if (unlikely(rc == H_NOT_ENOUGH_RESOURCES)) {
 			ret = (int)rc;
-			tce_free_pSeriesLP(liobn, tcenum_start,
+			tce_free_pSeriesLP(liobn, tcenum_start, tceshift,
 			                   (npages_start - (npages + 1)));
 			break;
 		}
@@ -205,10 +210,11 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 	long tcenum_start = tcenum, npages_start = npages;
 	int ret = 0;
 	unsigned long flags;
+	const unsigned long tceshift = tbl->it_page_shift;
 
 	if ((npages == 1) || !firmware_has_feature(FW_FEATURE_PUT_TCE_IND)) {
 		return tce_build_pSeriesLP(tbl->it_index, tcenum,
-					   tbl->it_page_shift, npages, uaddr,
+					   tceshift, npages, uaddr,
 		                           direction, attrs);
 	}
 
@@ -225,13 +231,13 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 		if (!tcep) {
 			local_irq_restore(flags);
 			return tce_build_pSeriesLP(tbl->it_index, tcenum,
-					tbl->it_page_shift,
+					tceshift,
 					npages, uaddr, direction, attrs);
 		}
 		__this_cpu_write(tce_page, tcep);
 	}
 
-	rpn = __pa(uaddr) >> TCE_SHIFT;
+	rpn = __pa(uaddr) >> tceshift;
 	proto_tce = TCE_PCI_READ;
 	if (direction != DMA_TO_DEVICE)
 		proto_tce |= TCE_PCI_WRITE;
@@ -245,12 +251,12 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 		limit = min_t(long, npages, 4096/TCE_ENTRY_SIZE);
 
 		for (l = 0; l < limit; l++) {
-			tcep[l] = cpu_to_be64(proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT);
+			tcep[l] = cpu_to_be64(proto_tce | rpn << tceshift);
 			rpn++;
 		}
 
 		rc = plpar_tce_put_indirect((u64)tbl->it_index,
-					    (u64)tcenum << 12,
+					    (u64)tcenum << tceshift,
 					    (u64)__pa(tcep),
 					    limit);
 
@@ -277,12 +283,13 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 	return ret;
 }
 
-static void tce_free_pSeriesLP(unsigned long liobn, long tcenum, long npages)
+static void tce_free_pSeriesLP(unsigned long liobn, long tcenum, long tceshift,
+			       long npages)
 {
 	u64 rc;
 
 	while (npages--) {
-		rc = plpar_tce_put((u64)liobn, (u64)tcenum << 12, 0);
+		rc = plpar_tce_put((u64)liobn, (u64)tcenum << tceshift, 0);
 
 		if (rc && printk_ratelimit()) {
 			printk("tce_free_pSeriesLP: plpar_tce_put failed. rc=%lld\n", rc);
@@ -301,9 +308,11 @@ static void tce_freemulti_pSeriesLP(struct iommu_table *tbl, long tcenum, long n
 	u64 rc;
 
 	if (!firmware_has_feature(FW_FEATURE_STUFF_TCE))
-		return tce_free_pSeriesLP(tbl->it_index, tcenum, npages);
+		return tce_free_pSeriesLP(tbl->it_index, tcenum,
+					  tbl->it_page_shift, npages);
 
-	rc = plpar_tce_stuff((u64)tbl->it_index, (u64)tcenum << 12, 0, npages);
+	rc = plpar_tce_stuff((u64)tbl->it_index,
+			     (u64)tcenum << tbl->it_page_shift, 0, npages);
 
 	if (rc && printk_ratelimit()) {
 		printk("tce_freemulti_pSeriesLP: plpar_tce_stuff failed\n");
@@ -319,7 +328,8 @@ static unsigned long tce_get_pSeriesLP(struct iommu_table *tbl, long tcenum)
 	u64 rc;
 	unsigned long tce_ret;
 
-	rc = plpar_tce_get((u64)tbl->it_index, (u64)tcenum << 12, &tce_ret);
+	rc = plpar_tce_get((u64)tbl->it_index,
+			   (u64)tcenum << tbl->it_page_shift, &tce_ret);
 
 	if (rc && printk_ratelimit()) {
 		printk("tce_get_pSeriesLP: plpar_tce_get failed. rc=%lld\n", rc);
@@ -339,7 +349,7 @@ struct dynamic_dma_window_prop {
 	__be32	window_shift;	/* ilog2(tce_window_size) */
 };
 
-struct direct_window {
+struct dma_win {
 	struct device_node *device;
 	const struct dynamic_dma_window_prop *prop;
 	struct list_head list;
@@ -359,12 +369,13 @@ struct ddw_create_response {
 	u32 addr_lo;
 };
 
-static LIST_HEAD(direct_window_list);
+static LIST_HEAD(dma_win_list);
 /* prevents races between memory on/offline and window creation */
-static DEFINE_SPINLOCK(direct_window_list_lock);
+static DEFINE_SPINLOCK(dma_win_list_lock);
 /* protects initializing window twice for same device */
-static DEFINE_MUTEX(direct_window_init_mutex);
+static DEFINE_MUTEX(dma_win_init_mutex);
 #define DIRECT64_PROPNAME "linux,direct64-ddr-window-info"
+#define DMA64_PROPNAME "linux,dma64-ddr-window-info"
 
 static int tce_clearrange_multi_pSeriesLP(unsigned long start_pfn,
 					unsigned long num_pfn, const void *arg)
@@ -491,6 +502,24 @@ static int tce_setrange_multi_pSeriesLP_walk(unsigned long start_pfn,
 	return tce_setrange_multi_pSeriesLP(start_pfn, num_pfn, arg);
 }
 
+static void iommu_table_setparms_common(struct iommu_table *tbl, unsigned long busno,
+					unsigned long liobn, unsigned long win_addr,
+					unsigned long window_size, unsigned long page_shift,
+					void *base, struct iommu_table_ops *table_ops)
+{
+	tbl->it_busno = busno;
+	tbl->it_index = liobn;
+	tbl->it_offset = win_addr >> page_shift;
+	tbl->it_size = window_size >> page_shift;
+	tbl->it_page_shift = page_shift;
+	tbl->it_base = (unsigned long)base;
+	tbl->it_blocksize = 16;
+	tbl->it_type = TCE_PCI;
+	tbl->it_ops = table_ops;
+}
+
+struct iommu_table_ops iommu_table_pseries_ops;
+
 static void iommu_table_setparms(struct pci_controller *phb,
 				 struct device_node *dn,
 				 struct iommu_table *tbl)
@@ -499,8 +528,13 @@ static void iommu_table_setparms(struct pci_controller *phb,
 	const unsigned long *basep;
 	const u32 *sizep;
 
-	node = phb->dn;
+	/* Test if we are going over 2GB of DMA space */
+	if (phb->dma_window_base_cur + phb->dma_window_size > SZ_2G) {
+		udbg_printf("PCI_DMA: Unexpected number of IOAs under this PHB.\n");
+		panic("PCI_DMA: Unexpected number of IOAs under this PHB.\n");
+	}
 
+	node = phb->dn;
 	basep = of_get_property(node, "linux,tce-base", NULL);
 	sizep = of_get_property(node, "linux,tce-size", NULL);
 	if (basep == NULL || sizep == NULL) {
@@ -509,33 +543,18 @@ static void iommu_table_setparms(struct pci_controller *phb,
 		return;
 	}
 
-	tbl->it_base = (unsigned long)__va(*basep);
+	iommu_table_setparms_common(tbl, phb->bus->number, 0, phb->dma_window_base_cur,
+				    phb->dma_window_size, IOMMU_PAGE_SHIFT_4K,
+				    __va(*basep), &iommu_table_pseries_ops);
 
 	if (!is_kdump_kernel())
 		memset((void *)tbl->it_base, 0, *sizep);
 
-	tbl->it_busno = phb->bus->number;
-	tbl->it_page_shift = IOMMU_PAGE_SHIFT_4K;
-
-	/* Units of tce entries */
-	tbl->it_offset = phb->dma_window_base_cur >> tbl->it_page_shift;
-
-	/* Test if we are going over 2GB of DMA space */
-	if (phb->dma_window_base_cur + phb->dma_window_size > 0x80000000ul) {
-		udbg_printf("PCI_DMA: Unexpected number of IOAs under this PHB.\n");
-		panic("PCI_DMA: Unexpected number of IOAs under this PHB.\n");
-	}
-
 	phb->dma_window_base_cur += phb->dma_window_size;
-
-	/* Set the tce table size - measured in entries */
-	tbl->it_size = phb->dma_window_size >> tbl->it_page_shift;
-
-	tbl->it_index = 0;
-	tbl->it_blocksize = 16;
-	tbl->it_type = TCE_PCI;
 }
 
+struct iommu_table_ops iommu_table_lpar_multi_ops;
+
 /*
  * iommu_table_setparms_lpar
  *
@@ -547,17 +566,13 @@ static void iommu_table_setparms_lpar(struct pci_controller *phb,
 				      struct iommu_table_group *table_group,
 				      const __be32 *dma_window)
 {
-	unsigned long offset, size;
+	unsigned long offset, size, liobn;
 
-	of_parse_dma_window(dn, dma_window, &tbl->it_index, &offset, &size);
+	of_parse_dma_window(dn, dma_window, &liobn, &offset, &size);
+
+	iommu_table_setparms_common(tbl, phb->bus->number, liobn, offset, size, IOMMU_PAGE_SHIFT_4K, NULL,
+				    &iommu_table_lpar_multi_ops);
 
-	tbl->it_busno = phb->bus->number;
-	tbl->it_page_shift = IOMMU_PAGE_SHIFT_4K;
-	tbl->it_base   = 0;
-	tbl->it_blocksize  = 16;
-	tbl->it_type = TCE_PCI;
-	tbl->it_offset = offset >> tbl->it_page_shift;
-	tbl->it_size = size >> tbl->it_page_shift;
 
 	table_group->tce32_start = offset;
 	table_group->tce32_size = size;
@@ -637,7 +652,7 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
 	tbl = pci->table_group->tables[0];
 
 	iommu_table_setparms(pci->phb, dn, tbl);
-	tbl->it_ops = &iommu_table_pseries_ops;
+
 	if (!iommu_init_table(tbl, pci->phb->node, 0, 0))
 		panic("Failed to initialize iommu table");
 
@@ -698,7 +713,10 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
 	pr_debug("pci_dma_bus_setup_pSeriesLP: setting up bus %pOF\n",
 		 dn);
 
-	/* Find nearest ibm,dma-window, walking up the device tree */
+	/*
+	 * Find nearest ibm,dma-window (default DMA window), walking up the
+	 * device tree
+	 */
 	for (pdn = dn; pdn != NULL; pdn = pdn->parent) {
 		dma_window = of_get_property(pdn, "ibm,dma-window", NULL);
 		if (dma_window != NULL)
@@ -720,7 +738,7 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
 		tbl = ppci->table_group->tables[0];
 		iommu_table_setparms_lpar(ppci->phb, pdn, tbl,
 				ppci->table_group, dma_window);
-		tbl->it_ops = &iommu_table_lpar_multi_ops;
+
 		if (!iommu_init_table(tbl, ppci->phb->node, 0, 0))
 			panic("Failed to initialize iommu table");
 		iommu_register_group(ppci->table_group,
@@ -750,7 +768,7 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev)
 		PCI_DN(dn)->table_group = iommu_pseries_alloc_group(phb->node);
 		tbl = PCI_DN(dn)->table_group->tables[0];
 		iommu_table_setparms(phb, dn, tbl);
-		tbl->it_ops = &iommu_table_pseries_ops;
+
 		if (!iommu_init_table(tbl, phb->node, 0, 0))
 			panic("Failed to initialize iommu table");
 
@@ -785,17 +803,10 @@ static int __init disable_ddw_setup(char *str)
 
 early_param("disable_ddw", disable_ddw_setup);
 
-static void remove_dma_window(struct device_node *np, u32 *ddw_avail,
-			      struct property *win)
+static void clean_dma_window(struct device_node *np, struct dynamic_dma_window_prop *dwp)
 {
-	struct dynamic_dma_window_prop *dwp;
-	u64 liobn;
 	int ret;
 
-	dwp = win->value;
-	liobn = (u64)be32_to_cpu(dwp->liobn);
-
-	/* clear the whole window, note the arg is in kernel pages */
 	ret = tce_clearrange_multi_pSeriesLP(0,
 		1ULL << (be32_to_cpu(dwp->window_shift) - PAGE_SHIFT), dwp);
 	if (ret)
@@ -804,94 +815,136 @@ static void remove_dma_window(struct device_node *np, u32 *ddw_avail,
 	else
 		pr_debug("%pOF successfully cleared tces in window.\n",
 			 np);
+}
+
+/*
+ * Call only if DMA window is clean.
+ */
+static void __remove_dma_window(struct device_node *np, u32 *ddw_avail, u64 liobn)
+{
+	int ret;
 
 	ret = rtas_call(ddw_avail[DDW_REMOVE_PE_DMA_WIN], 1, 1, NULL, liobn);
 	if (ret)
-		pr_warn("%pOF: failed to remove direct window: rtas returned "
+		pr_warn("%pOF: failed to remove DMA window: rtas returned "
 			"%d to ibm,remove-pe-dma-window(%x) %llx\n",
 			np, ret, ddw_avail[DDW_REMOVE_PE_DMA_WIN], liobn);
 	else
-		pr_debug("%pOF: successfully removed direct window: rtas returned "
+		pr_debug("%pOF: successfully removed DMA window: rtas returned "
 			"%d to ibm,remove-pe-dma-window(%x) %llx\n",
 			np, ret, ddw_avail[DDW_REMOVE_PE_DMA_WIN], liobn);
 }
 
-static void remove_ddw(struct device_node *np, bool remove_prop)
+static void remove_dma_window(struct device_node *np, u32 *ddw_avail,
+			      struct property *win)
+{
+	struct dynamic_dma_window_prop *dwp;
+	u64 liobn;
+
+	dwp = win->value;
+	liobn = (u64)be32_to_cpu(dwp->liobn);
+
+	clean_dma_window(np, dwp);
+	__remove_dma_window(np, ddw_avail, liobn);
+}
+
+static int remove_ddw(struct device_node *np, bool remove_prop, const char *win_name)
 {
 	struct property *win;
 	u32 ddw_avail[DDW_APPLICABLE_SIZE];
 	int ret = 0;
 
+	win = of_find_property(np, win_name, NULL);
+	if (!win)
+		return -EINVAL;
+
 	ret = of_property_read_u32_array(np, "ibm,ddw-applicable",
 					 &ddw_avail[0], DDW_APPLICABLE_SIZE);
 	if (ret)
-		return;
+		return 0;
 
-	win = of_find_property(np, DIRECT64_PROPNAME, NULL);
-	if (!win)
-		return;
 
 	if (win->length >= sizeof(struct dynamic_dma_window_prop))
 		remove_dma_window(np, ddw_avail, win);
 
 	if (!remove_prop)
-		return;
+		return 0;
 
 	ret = of_remove_property(np, win);
 	if (ret)
-		pr_warn("%pOF: failed to remove direct window property: %d\n",
+		pr_warn("%pOF: failed to remove DMA window property: %d\n",
 			np, ret);
+	return 0;
 }
 
-static u64 find_existing_ddw(struct device_node *pdn, int *window_shift)
+static bool find_existing_ddw(struct device_node *pdn, u64 *dma_addr, int *window_shift)
 {
-	struct direct_window *window;
-	const struct dynamic_dma_window_prop *direct64;
-	u64 dma_addr = 0;
+	struct dma_win *window;
+	const struct dynamic_dma_window_prop *dma64;
+	bool found = false;
 
-	spin_lock(&direct_window_list_lock);
+	spin_lock(&dma_win_list_lock);
 	/* check if we already created a window and dupe that config if so */
-	list_for_each_entry(window, &direct_window_list, list) {
+	list_for_each_entry(window, &dma_win_list, list) {
 		if (window->device == pdn) {
-			direct64 = window->prop;
-			dma_addr = be64_to_cpu(direct64->dma_base);
-			*window_shift = be32_to_cpu(direct64->window_shift);
+			dma64 = window->prop;
+			*dma_addr = be64_to_cpu(dma64->dma_base);
+			*window_shift = be32_to_cpu(dma64->window_shift);
+			found = true;
 			break;
 		}
 	}
-	spin_unlock(&direct_window_list_lock);
+	spin_unlock(&dma_win_list_lock);
 
-	return dma_addr;
+	return found;
+}
+
+static struct dma_win *ddw_list_new_entry(struct device_node *pdn,
+					  const struct dynamic_dma_window_prop *dma64)
+{
+	struct dma_win *window;
+
+	window = kzalloc(sizeof(*window), GFP_KERNEL);
+	if (!window)
+		return NULL;
+
+	window->device = pdn;
+	window->prop = dma64;
+
+	return window;
+}
+
+static void find_existing_ddw_windows_named(const char *name)
+{
+	int len;
+	struct device_node *pdn;
+	struct dma_win *window;
+	const struct dynamic_dma_window_prop *dma64;
+
+	for_each_node_with_property(pdn, name) {
+		dma64 = of_get_property(pdn, name, &len);
+		if (!dma64 || len < sizeof(*dma64)) {
+			remove_ddw(pdn, true, name);
+			continue;
+		}
+
+		window = ddw_list_new_entry(pdn, dma64);
+		if (!window)
+			break;
+
+		spin_lock(&dma_win_list_lock);
+		list_add(&window->list, &dma_win_list);
+		spin_unlock(&dma_win_list_lock);
+	}
 }
 
 static int find_existing_ddw_windows(void)
 {
-	int len;
-	struct device_node *pdn;
-	struct direct_window *window;
-	const struct dynamic_dma_window_prop *direct64;
-
 	if (!firmware_has_feature(FW_FEATURE_LPAR))
 		return 0;
 
-	for_each_node_with_property(pdn, DIRECT64_PROPNAME) {
-		direct64 = of_get_property(pdn, DIRECT64_PROPNAME, &len);
-		if (!direct64)
-			continue;
-
-		window = kzalloc(sizeof(*window), GFP_KERNEL);
-		if (!window || len < sizeof(struct dynamic_dma_window_prop)) {
-			kfree(window);
-			remove_ddw(pdn, true);
-			continue;
-		}
-
-		window->device = pdn;
-		window->prop = direct64;
-		spin_lock(&direct_window_list_lock);
-		list_add(&window->list, &direct_window_list);
-		spin_unlock(&direct_window_list_lock);
-	}
+	find_existing_ddw_windows_named(DIRECT64_PROPNAME);
+	find_existing_ddw_windows_named(DMA64_PROPNAME);
 
 	return 0;
 }
@@ -1130,6 +1183,35 @@ static int iommu_get_page_shift(u32 query_page_size)
 	return 0;
 }
 
+static struct property *ddw_property_create(const char *propname, u32 liobn, u64 dma_addr,
+					    u32 page_shift, u32 window_shift)
+{
+	struct dynamic_dma_window_prop *ddwprop;
+	struct property *win64;
+
+	win64 = kzalloc(sizeof(*win64), GFP_KERNEL);
+	if (!win64)
+		return NULL;
+
+	win64->name = kstrdup(propname, GFP_KERNEL);
+	ddwprop = kzalloc(sizeof(*ddwprop), GFP_KERNEL);
+	win64->value = ddwprop;
+	win64->length = sizeof(*ddwprop);
+	if (!win64->name || !win64->value) {
+		kfree(win64->name);
+		kfree(win64->value);
+		kfree(win64);
+		return NULL;
+	}
+
+	ddwprop->liobn = cpu_to_be32(liobn);
+	ddwprop->dma_base = cpu_to_be64(dma_addr);
+	ddwprop->tce_shift = cpu_to_be32(page_shift);
+	ddwprop->window_shift = cpu_to_be32(window_shift);
+
+	return win64;
+}
+
 /*
  * If the PE supports dynamic dma windows, and there is space for a table
  * that can map all pages in a linear offset, then setup such a table,
@@ -1139,34 +1221,39 @@ static int iommu_get_page_shift(u32 query_page_size)
  * pdn: the parent pe node with the ibm,dma_window property
  * Future: also check if we can remap the base window for our base page size
  *
- * returns the dma offset for use by the direct mapped DMA code.
+ * returns true if can map all pages (direct mapping), false otherwise..
  */
-static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
+static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 {
 	int len = 0, ret;
 	int max_ram_len = order_base_2(ddw_memory_hotplug_max());
 	struct ddw_query_response query;
 	struct ddw_create_response create;
 	int page_shift;
-	u64 dma_addr;
+	u64 win_addr;
+	const char *win_name;
 	struct device_node *dn;
 	u32 ddw_avail[DDW_APPLICABLE_SIZE];
-	struct direct_window *window;
+	struct dma_win *window;
 	struct property *win64;
-	struct dynamic_dma_window_prop *ddwprop;
+	bool ddw_enabled = false;
 	struct failed_ddw_pdn *fpdn;
-	bool default_win_removed = false;
+	bool default_win_removed = false, direct_mapping = false;
 	bool pmem_present;
+	struct pci_dn *pci = PCI_DN(pdn);
+	struct iommu_table *tbl = pci->table_group->tables[0];
 
 	dn = of_find_node_by_type(NULL, "ibm,pmemory");
 	pmem_present = dn != NULL;
 	of_node_put(dn);
 
-	mutex_lock(&direct_window_init_mutex);
+	mutex_lock(&dma_win_init_mutex);
 
-	dma_addr = find_existing_ddw(pdn, &len);
-	if (dma_addr != 0)
+	if (find_existing_ddw(pdn, &dev->dev.archdata.dma_offset, &len)) {
+		direct_mapping = (len >= max_ram_len);
+		ddw_enabled = true;
 		goto out_unlock;
+	}
 
 	/*
 	 * If we already went through this for a previous function of
@@ -1240,12 +1327,12 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 
 	page_shift = iommu_get_page_shift(query.page_size);
 	if (!page_shift) {
-		dev_dbg(&dev->dev, "no supported direct page size in mask %x",
-			  query.page_size);
+		dev_dbg(&dev->dev, "no supported page size in mask %x",
+			query.page_size);
 		goto out_failed;
 	}
-	/* verify the window * number of ptes will map the partition */
-	/* check largest block * page size > max memory hotplug addr */
+
+
 	/*
 	 * The "ibm,pmemory" can appear anywhere in the address space.
 	 * Assuming it is still backed by page structs, try MAX_PHYSMEM_BITS
@@ -1261,81 +1348,127 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 			dev_info(&dev->dev, "Skipping ibm,pmemory");
 	}
 
+	/* check if the available block * number of ptes will map everything */
 	if (query.largest_available_block < (1ULL << (len - page_shift))) {
 		dev_dbg(&dev->dev,
 			"can't map partition max 0x%llx with %llu %llu-sized pages\n",
 			1ULL << len,
 			query.largest_available_block,
 			1ULL << page_shift);
-		goto out_failed;
-	}
-	win64 = kzalloc(sizeof(struct property), GFP_KERNEL);
-	if (!win64) {
-		dev_info(&dev->dev,
-			"couldn't allocate property for 64bit dma window\n");
-		goto out_failed;
-	}
-	win64->name = kstrdup(DIRECT64_PROPNAME, GFP_KERNEL);
-	win64->value = ddwprop = kmalloc(sizeof(*ddwprop), GFP_KERNEL);
-	win64->length = sizeof(*ddwprop);
-	if (!win64->name || !win64->value) {
-		dev_info(&dev->dev,
-			"couldn't allocate property name and value\n");
-		goto out_free_prop;
+
+		/* DDW + IOMMU on single window may fail if there is any allocation */
+		if (default_win_removed && iommu_table_in_use(tbl)) {
+			dev_dbg(&dev->dev, "current IOMMU table in use, can't be replaced.\n");
+			goto out_failed;
+		}
+
+		len = order_base_2(query.largest_available_block << page_shift);
+		win_name = DMA64_PROPNAME;
+	} else {
+		direct_mapping = true;
+		win_name = DIRECT64_PROPNAME;
 	}
 
 	ret = create_ddw(dev, ddw_avail, &create, page_shift, len);
 	if (ret != 0)
-		goto out_free_prop;
-
-	ddwprop->liobn = cpu_to_be32(create.liobn);
-	ddwprop->dma_base = cpu_to_be64(((u64)create.addr_hi << 32) |
-			create.addr_lo);
-	ddwprop->tce_shift = cpu_to_be32(page_shift);
-	ddwprop->window_shift = cpu_to_be32(len);
+		goto out_failed;
 
 	dev_dbg(&dev->dev, "created tce table LIOBN 0x%x for %pOF\n",
 		  create.liobn, dn);
 
-	window = kzalloc(sizeof(*window), GFP_KERNEL);
-	if (!window)
-		goto out_clear_window;
+	win_addr = ((u64)create.addr_hi << 32) | create.addr_lo;
+	win64 = ddw_property_create(win_name, create.liobn, win_addr, page_shift, len);
 
-	ret = walk_system_ram_range(0, memblock_end_of_DRAM() >> PAGE_SHIFT,
-			win64->value, tce_setrange_multi_pSeriesLP_walk);
-	if (ret) {
-		dev_info(&dev->dev, "failed to map direct window for %pOF: %d\n",
-			 dn, ret);
-		goto out_free_window;
+	if (!win64) {
+		dev_info(&dev->dev,
+			 "couldn't allocate property, property name, or value\n");
+		goto out_remove_win;
 	}
 
 	ret = of_add_property(pdn, win64);
 	if (ret) {
-		dev_err(&dev->dev, "unable to add dma window property for %pOF: %d",
-			 pdn, ret);
-		goto out_free_window;
+		dev_err(&dev->dev, "unable to add DMA window property for %pOF: %d",
+			pdn, ret);
+		goto out_free_prop;
 	}
 
-	window->device = pdn;
-	window->prop = ddwprop;
-	spin_lock(&direct_window_list_lock);
-	list_add(&window->list, &direct_window_list);
-	spin_unlock(&direct_window_list_lock);
+	window = ddw_list_new_entry(pdn, win64->value);
+	if (!window)
+		goto out_del_prop;
 
-	dma_addr = be64_to_cpu(ddwprop->dma_base);
+	if (direct_mapping) {
+		/* DDW maps the whole partition, so enable direct DMA mapping */
+		ret = walk_system_ram_range(0, memblock_end_of_DRAM() >> PAGE_SHIFT,
+					    win64->value, tce_setrange_multi_pSeriesLP_walk);
+		if (ret) {
+			dev_info(&dev->dev, "failed to map DMA window for %pOF: %d\n",
+				 dn, ret);
+
+		/* Make sure to clean DDW if any TCE was set*/
+		clean_dma_window(pdn, win64->value);
+			goto out_del_list;
+		}
+	} else {
+		struct iommu_table *newtbl;
+		int i;
+
+		for (i = 0; i < ARRAY_SIZE(pci->phb->mem_resources); i++) {
+			const unsigned long mask = IORESOURCE_MEM_64 | IORESOURCE_MEM;
+
+			/* Look for MMIO32 */
+			if ((pci->phb->mem_resources[i].flags & mask) == IORESOURCE_MEM)
+				break;
+		}
+
+		if (i == ARRAY_SIZE(pci->phb->mem_resources))
+			goto out_del_list;
+
+		/* New table for using DDW instead of the default DMA window */
+		newtbl = iommu_pseries_alloc_table(pci->phb->node);
+		if (!newtbl) {
+			dev_dbg(&dev->dev, "couldn't create new IOMMU table\n");
+			goto out_del_list;
+		}
+
+		iommu_table_setparms_common(newtbl, pci->phb->bus->number, create.liobn, win_addr,
+					    1UL << len, page_shift, NULL, &iommu_table_lpar_multi_ops);
+		iommu_init_table(newtbl, pci->phb->node, pci->phb->mem_resources[i].start,
+				 pci->phb->mem_resources[i].end);
+
+		pci->table_group->tables[1] = newtbl;
+
+		/* Keep default DMA window stuct if removed */
+		if (default_win_removed) {
+			tbl->it_size = 0;
+			kfree(tbl->it_map);
+		}
+
+		set_iommu_table_base(&dev->dev, newtbl);
+	}
+
+	spin_lock(&dma_win_list_lock);
+	list_add(&window->list, &dma_win_list);
+	spin_unlock(&dma_win_list_lock);
+
+	dev->dev.archdata.dma_offset = win_addr;
+	ddw_enabled = true;
 	goto out_unlock;
 
-out_free_window:
+out_del_list:
 	kfree(window);
 
-out_clear_window:
-	remove_ddw(pdn, true);
+out_del_prop:
+	of_remove_property(pdn, win64);
 
 out_free_prop:
 	kfree(win64->name);
 	kfree(win64->value);
 	kfree(win64);
 
+out_remove_win:
+	/* DDW is clean, so it's ok to call this directly. */
+	__remove_dma_window(pdn, ddw_avail, create.liobn);
+
 out_failed:
 	if (default_win_removed)
 		reset_dma_window(dev, pdn);
@@ -1347,17 +1480,17 @@ out_failed:
 	list_add(&fpdn->list, &failed_ddw_pdn_list);
 
 out_unlock:
-	mutex_unlock(&direct_window_init_mutex);
+	mutex_unlock(&dma_win_init_mutex);
 
 	/*
 	 * If we have persistent memory and the window size is only as big
 	 * as RAM, then we failed to create a window to cover persistent
 	 * memory and need to set the DMA limit.
 	 */
-	if (pmem_present && dma_addr && (len == max_ram_len))
-		dev->dev.bus_dma_limit = dma_addr + (1ULL << len);
+	if (pmem_present && ddw_enabled && direct_mapping && len == max_ram_len)
+		dev->dev.bus_dma_limit = dev->dev.archdata.dma_offset + (1ULL << len);
 
-	return dma_addr;
+    return ddw_enabled && direct_mapping;
 }
 
 static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
@@ -1399,7 +1532,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 		tbl = pci->table_group->tables[0];
 		iommu_table_setparms_lpar(pci->phb, pdn, tbl,
 				pci->table_group, dma_window);
-		tbl->it_ops = &iommu_table_lpar_multi_ops;
+
 		iommu_init_table(tbl, pci->phb->node, 0, 0);
 		iommu_register_group(pci->table_group,
 				pci_domain_nr(pci->phb->bus), 0);
@@ -1436,11 +1569,8 @@ static bool iommu_bypass_supported_pSeriesLP(struct pci_dev *pdev, u64 dma_mask)
 			break;
 	}
 
-	if (pdn && PCI_DN(pdn)) {
-		pdev->dev.archdata.dma_offset = enable_ddw(pdev, pdn);
-		if (pdev->dev.archdata.dma_offset)
-			return true;
-	}
+	if (pdn && PCI_DN(pdn))
+		return enable_ddw(pdev, pdn);
 
 	return false;
 }
@@ -1448,29 +1578,29 @@ static bool iommu_bypass_supported_pSeriesLP(struct pci_dev *pdev, u64 dma_mask)
 static int iommu_mem_notifier(struct notifier_block *nb, unsigned long action,
 		void *data)
 {
-	struct direct_window *window;
+	struct dma_win *window;
 	struct memory_notify *arg = data;
 	int ret = 0;
 
 	switch (action) {
 	case MEM_GOING_ONLINE:
-		spin_lock(&direct_window_list_lock);
-		list_for_each_entry(window, &direct_window_list, list) {
+		spin_lock(&dma_win_list_lock);
+		list_for_each_entry(window, &dma_win_list, list) {
 			ret |= tce_setrange_multi_pSeriesLP(arg->start_pfn,
 					arg->nr_pages, window->prop);
 			/* XXX log error */
 		}
-		spin_unlock(&direct_window_list_lock);
+		spin_unlock(&dma_win_list_lock);
 		break;
 	case MEM_CANCEL_ONLINE:
 	case MEM_OFFLINE:
-		spin_lock(&direct_window_list_lock);
-		list_for_each_entry(window, &direct_window_list, list) {
+		spin_lock(&dma_win_list_lock);
+		list_for_each_entry(window, &dma_win_list, list) {
 			ret |= tce_clearrange_multi_pSeriesLP(arg->start_pfn,
 					arg->nr_pages, window->prop);
 			/* XXX log error */
 		}
-		spin_unlock(&direct_window_list_lock);
+		spin_unlock(&dma_win_list_lock);
 		break;
 	default:
 		break;
@@ -1491,7 +1621,7 @@ static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long acti
 	struct of_reconfig_data *rd = data;
 	struct device_node *np = rd->dn;
 	struct pci_dn *pci = PCI_DN(np);
-	struct direct_window *window;
+	struct dma_win *window;
 
 	switch (action) {
 	case OF_RECONFIG_DETACH_NODE:
@@ -1502,20 +1632,22 @@ static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long acti
 		 * we have to remove the property when releasing
 		 * the device node.
 		 */
-		remove_ddw(np, false);
+		if (remove_ddw(np, false, DIRECT64_PROPNAME))
+			remove_ddw(np, false, DMA64_PROPNAME);
+
 		if (pci && pci->table_group)
 			iommu_pseries_free_group(pci->table_group,
 					np->full_name);
 
-		spin_lock(&direct_window_list_lock);
-		list_for_each_entry(window, &direct_window_list, list) {
+		spin_lock(&dma_win_list_lock);
+		list_for_each_entry(window, &dma_win_list, list) {
 			if (window->device == np) {
 				list_del(&window->list);
 				kfree(window);
 				break;
 			}
 		}
-		spin_unlock(&direct_window_list_lock);
+		spin_unlock(&dma_win_list_lock);
 		break;
 	default:
 		err = NOTIFY_DONE;
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index dab356e3ff87..3df6bdfea475 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -22,6 +22,8 @@
 #include <linux/workqueue.h>
 #include <linux/proc_fs.h>
 #include <linux/pgtable.h>
+#include <linux/debugfs.h>
+
 #include <asm/processor.h>
 #include <asm/mmu.h>
 #include <asm/page.h>
@@ -39,7 +41,6 @@
 #include <asm/kexec.h>
 #include <asm/fadump.h>
 #include <asm/asm-prototypes.h>
-#include <asm/debugfs.h>
 #include <asm/dtl.h>
 
 #include "pseries.h"
@@ -261,7 +262,7 @@ static int cpu_relative_dispatch_distance(int last_disp_cpu, int cur_disp_cpu)
 	if (!last_disp_cpu_assoc || !cur_disp_cpu_assoc)
 		return -EIO;
 
-	return cpu_distance(last_disp_cpu_assoc, cur_disp_cpu_assoc);
+	return cpu_relative_distance(last_disp_cpu_assoc, cur_disp_cpu_assoc);
 }
 
 static int cpu_home_node_dispatch_distance(int disp_cpu)
@@ -281,7 +282,7 @@ static int cpu_home_node_dispatch_distance(int disp_cpu)
 	if (!disp_cpu_assoc || !vcpu_assoc)
 		return -EIO;
 
-	return cpu_distance(disp_cpu_assoc, vcpu_assoc);
+	return cpu_relative_distance(disp_cpu_assoc, vcpu_assoc);
 }
 
 static void update_vcpu_disp_stat(int disp_cpu)
@@ -801,7 +802,8 @@ static long pSeries_lpar_hpte_remove(unsigned long hpte_group)
 	return -1;
 }
 
-static void manual_hpte_clear_all(void)
+/* Called during kexec sequence with MMU off */
+static notrace void manual_hpte_clear_all(void)
 {
 	unsigned long size_bytes = 1UL << ppc64_pft_size;
 	unsigned long hpte_count = size_bytes >> 4;
@@ -834,7 +836,8 @@ static void manual_hpte_clear_all(void)
 	}
 }
 
-static int hcall_hpte_clear_all(void)
+/* Called during kexec sequence with MMU off */
+static notrace int hcall_hpte_clear_all(void)
 {
 	int rc;
 
@@ -845,7 +848,8 @@ static int hcall_hpte_clear_all(void)
 	return rc;
 }
 
-static void pseries_hpte_clear_all(void)
+/* Called during kexec sequence with MMU off */
+static notrace void pseries_hpte_clear_all(void)
 {
 	int rc;
 
@@ -2016,7 +2020,7 @@ static int __init vpa_debugfs_init(void)
 	if (!firmware_has_feature(FW_FEATURE_SPLPAR))
 		return 0;
 
-	vpa_dir = debugfs_create_dir("vpa", powerpc_debugfs_root);
+	vpa_dir = debugfs_create_dir("vpa", arch_debugfs_dir);
 
 	/* set up the per-cpu vpa file*/
 	for_each_possible_cpu(i) {
diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c
index 637300330507..1b305e411862 100644
--- a/arch/powerpc/platforms/pseries/msi.c
+++ b/arch/powerpc/platforms/pseries/msi.c
@@ -13,6 +13,7 @@
 #include <asm/hw_irq.h>
 #include <asm/ppc-pci.h>
 #include <asm/machdep.h>
+#include <asm/xive.h>
 
 #include "pseries.h"
 
@@ -110,21 +111,6 @@ static int rtas_query_irq_number(struct pci_dn *pdn, int offset)
 	return rtas_ret[0];
 }
 
-static void rtas_teardown_msi_irqs(struct pci_dev *pdev)
-{
-	struct msi_desc *entry;
-
-	for_each_pci_msi_entry(entry, pdev) {
-		if (!entry->irq)
-			continue;
-
-		irq_set_msi_desc(entry->irq, NULL);
-		irq_dispose_mapping(entry->irq);
-	}
-
-	rtas_disable_msi(pdev);
-}
-
 static int check_req(struct pci_dev *pdev, int nvec, char *prop_name)
 {
 	struct device_node *dn;
@@ -164,12 +150,12 @@ static int check_req_msix(struct pci_dev *pdev, int nvec)
 
 /* Quota calculation */
 
-static struct device_node *find_pe_total_msi(struct pci_dev *dev, int *total)
+static struct device_node *__find_pe_total_msi(struct device_node *node, int *total)
 {
 	struct device_node *dn;
 	const __be32 *p;
 
-	dn = of_node_get(pci_device_to_OF_node(dev));
+	dn = of_node_get(node);
 	while (dn) {
 		p = of_get_property(dn, "ibm,pe-total-#msi", NULL);
 		if (p) {
@@ -185,6 +171,11 @@ static struct device_node *find_pe_total_msi(struct pci_dev *dev, int *total)
 	return NULL;
 }
 
+static struct device_node *find_pe_total_msi(struct pci_dev *dev, int *total)
+{
+	return __find_pe_total_msi(pci_device_to_OF_node(dev), total);
+}
+
 static struct device_node *find_pe_dn(struct pci_dev *dev, int *total)
 {
 	struct device_node *dn;
@@ -368,12 +359,11 @@ static void rtas_hack_32bit_msi_gen2(struct pci_dev *pdev)
 	pci_write_config_dword(pdev, pdev->msi_cap + PCI_MSI_ADDRESS_HI, 0);
 }
 
-static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec_in, int type)
+static int rtas_prepare_msi_irqs(struct pci_dev *pdev, int nvec_in, int type,
+				 msi_alloc_info_t *arg)
 {
 	struct pci_dn *pdn;
-	int hwirq, virq, i, quota, rc;
-	struct msi_desc *entry;
-	struct msi_msg msg;
+	int quota, rc;
 	int nvec = nvec_in;
 	int use_32bit_msi_hack = 0;
 
@@ -451,51 +441,227 @@ again:
 		return rc;
 	}
 
-	i = 0;
-	for_each_pci_msi_entry(entry, pdev) {
-		hwirq = rtas_query_irq_number(pdn, i++);
-		if (hwirq < 0) {
-			pr_debug("rtas_msi: error (%d) getting hwirq\n", rc);
-			return hwirq;
-		}
+	return 0;
+}
 
-		/*
-		 * Depending on the number of online CPUs in the original
-		 * kernel, it is likely for CPU #0 to be offline in a kdump
-		 * kernel. The associated IRQs in the affinity mappings
-		 * provided by irq_create_affinity_masks() are thus not
-		 * started by irq_startup(), as per-design for managed IRQs.
-		 * This can be a problem with multi-queue block devices driven
-		 * by blk-mq : such a non-started IRQ is very likely paired
-		 * with the single queue enforced by blk-mq during kdump (see
-		 * blk_mq_alloc_tag_set()). This causes the device to remain
-		 * silent and likely hangs the guest at some point.
-		 *
-		 * We don't really care for fine-grained affinity when doing
-		 * kdump actually : simply ignore the pre-computed affinity
-		 * masks in this case and let the default mask with all CPUs
-		 * be used when creating the IRQ mappings.
-		 */
-		if (is_kdump_kernel())
-			virq = irq_create_mapping(NULL, hwirq);
-		else
-			virq = irq_create_mapping_affinity(NULL, hwirq,
-							   entry->affinity);
+static int pseries_msi_ops_prepare(struct irq_domain *domain, struct device *dev,
+				   int nvec, msi_alloc_info_t *arg)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct msi_desc *desc = first_pci_msi_entry(pdev);
+	int type = desc->msi_attrib.is_msix ? PCI_CAP_ID_MSIX : PCI_CAP_ID_MSI;
 
-		if (!virq) {
-			pr_debug("rtas_msi: Failed mapping hwirq %d\n", hwirq);
-			return -ENOSPC;
-		}
+	return rtas_prepare_msi_irqs(pdev, nvec, type, arg);
+}
 
-		dev_dbg(&pdev->dev, "rtas_msi: allocated virq %d\n", virq);
-		irq_set_msi_desc(virq, entry);
+/*
+ * ->msi_free() is called before irq_domain_free_irqs_top() when the
+ * handler data is still available. Use that to clear the XIVE
+ * controller data.
+ */
+static void pseries_msi_ops_msi_free(struct irq_domain *domain,
+				     struct msi_domain_info *info,
+				     unsigned int irq)
+{
+	if (xive_enabled())
+		xive_irq_free_data(irq);
+}
 
-		/* Read config space back so we can restore after reset */
-		__pci_read_msi_msg(entry, &msg);
-		entry->msg = msg;
+/*
+ * RTAS can not disable one MSI at a time. It's all or nothing. Do it
+ * at the end after all IRQs have been freed.
+ */
+static void pseries_msi_domain_free_irqs(struct irq_domain *domain,
+					 struct device *dev)
+{
+	if (WARN_ON_ONCE(!dev_is_pci(dev)))
+		return;
+
+	__msi_domain_free_irqs(domain, dev);
+
+	rtas_disable_msi(to_pci_dev(dev));
+}
+
+static struct msi_domain_ops pseries_pci_msi_domain_ops = {
+	.msi_prepare	= pseries_msi_ops_prepare,
+	.msi_free	= pseries_msi_ops_msi_free,
+	.domain_free_irqs = pseries_msi_domain_free_irqs,
+};
+
+static void pseries_msi_shutdown(struct irq_data *d)
+{
+	d = d->parent_data;
+	if (d->chip->irq_shutdown)
+		d->chip->irq_shutdown(d);
+}
+
+static void pseries_msi_mask(struct irq_data *d)
+{
+	pci_msi_mask_irq(d);
+	irq_chip_mask_parent(d);
+}
+
+static void pseries_msi_unmask(struct irq_data *d)
+{
+	pci_msi_unmask_irq(d);
+	irq_chip_unmask_parent(d);
+}
+
+static struct irq_chip pseries_pci_msi_irq_chip = {
+	.name		= "pSeries-PCI-MSI",
+	.irq_shutdown	= pseries_msi_shutdown,
+	.irq_mask	= pseries_msi_mask,
+	.irq_unmask	= pseries_msi_unmask,
+	.irq_eoi	= irq_chip_eoi_parent,
+};
+
+static struct msi_domain_info pseries_msi_domain_info = {
+	.flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+		  MSI_FLAG_MULTI_PCI_MSI  | MSI_FLAG_PCI_MSIX),
+	.ops   = &pseries_pci_msi_domain_ops,
+	.chip  = &pseries_pci_msi_irq_chip,
+};
+
+static void pseries_msi_compose_msg(struct irq_data *data, struct msi_msg *msg)
+{
+	__pci_read_msi_msg(irq_data_get_msi_desc(data), msg);
+}
+
+static struct irq_chip pseries_msi_irq_chip = {
+	.name			= "pSeries-MSI",
+	.irq_shutdown		= pseries_msi_shutdown,
+	.irq_mask		= irq_chip_mask_parent,
+	.irq_unmask		= irq_chip_unmask_parent,
+	.irq_eoi		= irq_chip_eoi_parent,
+	.irq_set_affinity	= irq_chip_set_affinity_parent,
+	.irq_compose_msi_msg	= pseries_msi_compose_msg,
+};
+
+static int pseries_irq_parent_domain_alloc(struct irq_domain *domain, unsigned int virq,
+					   irq_hw_number_t hwirq)
+{
+	struct irq_fwspec parent_fwspec;
+	int ret;
+
+	parent_fwspec.fwnode = domain->parent->fwnode;
+	parent_fwspec.param_count = 2;
+	parent_fwspec.param[0] = hwirq;
+	parent_fwspec.param[1] = IRQ_TYPE_EDGE_RISING;
+
+	ret = irq_domain_alloc_irqs_parent(domain, virq, 1, &parent_fwspec);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int pseries_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				    unsigned int nr_irqs, void *arg)
+{
+	struct pci_controller *phb = domain->host_data;
+	msi_alloc_info_t *info = arg;
+	struct msi_desc *desc = info->desc;
+	struct pci_dev *pdev = msi_desc_to_pci_dev(desc);
+	int hwirq;
+	int i, ret;
+
+	hwirq = rtas_query_irq_number(pci_get_pdn(pdev), desc->msi_attrib.entry_nr);
+	if (hwirq < 0) {
+		dev_err(&pdev->dev, "Failed to query HW IRQ: %d\n", hwirq);
+		return hwirq;
+	}
+
+	dev_dbg(&pdev->dev, "%s bridge %pOF %d/%x #%d\n", __func__,
+		phb->dn, virq, hwirq, nr_irqs);
+
+	for (i = 0; i < nr_irqs; i++) {
+		ret = pseries_irq_parent_domain_alloc(domain, virq + i, hwirq + i);
+		if (ret)
+			goto out;
+
+		irq_domain_set_hwirq_and_chip(domain, virq + i, hwirq + i,
+					      &pseries_msi_irq_chip, domain->host_data);
 	}
 
 	return 0;
+
+out:
+	/* TODO: handle RTAS cleanup in ->msi_finish() ? */
+	irq_domain_free_irqs_parent(domain, virq, i - 1);
+	return ret;
+}
+
+static void pseries_irq_domain_free(struct irq_domain *domain, unsigned int virq,
+				    unsigned int nr_irqs)
+{
+	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
+	struct pci_controller *phb = irq_data_get_irq_chip_data(d);
+
+	pr_debug("%s bridge %pOF %d #%d\n", __func__, phb->dn, virq, nr_irqs);
+
+	/* XIVE domain data is cleared through ->msi_free() */
+}
+
+static const struct irq_domain_ops pseries_irq_domain_ops = {
+	.alloc  = pseries_irq_domain_alloc,
+	.free   = pseries_irq_domain_free,
+};
+
+static int __pseries_msi_allocate_domains(struct pci_controller *phb,
+					  unsigned int count)
+{
+	struct irq_domain *parent = irq_get_default_host();
+
+	phb->fwnode = irq_domain_alloc_named_id_fwnode("pSeries-MSI",
+						       phb->global_number);
+	if (!phb->fwnode)
+		return -ENOMEM;
+
+	phb->dev_domain = irq_domain_create_hierarchy(parent, 0, count,
+						      phb->fwnode,
+						      &pseries_irq_domain_ops, phb);
+	if (!phb->dev_domain) {
+		pr_err("PCI: failed to create IRQ domain bridge %pOF (domain %d)\n",
+		       phb->dn, phb->global_number);
+		irq_domain_free_fwnode(phb->fwnode);
+		return -ENOMEM;
+	}
+
+	phb->msi_domain = pci_msi_create_irq_domain(of_node_to_fwnode(phb->dn),
+						    &pseries_msi_domain_info,
+						    phb->dev_domain);
+	if (!phb->msi_domain) {
+		pr_err("PCI: failed to create MSI IRQ domain bridge %pOF (domain %d)\n",
+		       phb->dn, phb->global_number);
+		irq_domain_free_fwnode(phb->fwnode);
+		irq_domain_remove(phb->dev_domain);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+int pseries_msi_allocate_domains(struct pci_controller *phb)
+{
+	int count;
+
+	if (!__find_pe_total_msi(phb->dn, &count)) {
+		pr_err("PCI: failed to find MSIs for bridge %pOF (domain %d)\n",
+		       phb->dn, phb->global_number);
+		return -ENOSPC;
+	}
+
+	return __pseries_msi_allocate_domains(phb, count);
+}
+
+void pseries_msi_free_domains(struct pci_controller *phb)
+{
+	if (phb->msi_domain)
+		irq_domain_remove(phb->msi_domain);
+	if (phb->dev_domain)
+		irq_domain_remove(phb->dev_domain);
+	if (phb->fwnode)
+		irq_domain_free_fwnode(phb->fwnode);
 }
 
 static void rtas_msi_pci_irq_fixup(struct pci_dev *pdev)
@@ -518,8 +684,6 @@ static void rtas_msi_pci_irq_fixup(struct pci_dev *pdev)
 
 static int rtas_msi_init(void)
 {
-	struct pci_controller *phb;
-
 	query_token  = rtas_token("ibm,query-interrupt-source-number");
 	change_token = rtas_token("ibm,change-msi");
 
@@ -531,16 +695,6 @@ static int rtas_msi_init(void)
 
 	pr_debug("rtas_msi: Registering RTAS MSI callbacks.\n");
 
-	WARN_ON(pseries_pci_controller_ops.setup_msi_irqs);
-	pseries_pci_controller_ops.setup_msi_irqs = rtas_setup_msi_irqs;
-	pseries_pci_controller_ops.teardown_msi_irqs = rtas_teardown_msi_irqs;
-
-	list_for_each_entry(phb, &hose_list, list_node) {
-		WARN_ON(phb->controller_ops.setup_msi_irqs);
-		phb->controller_ops.setup_msi_irqs = rtas_setup_msi_irqs;
-		phb->controller_ops.teardown_msi_irqs = rtas_teardown_msi_irqs;
-	}
-
 	WARN_ON(ppc_md.pci_irq_fixup);
 	ppc_md.pci_irq_fixup = rtas_msi_pci_irq_fixup;
 
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index a8f9140a24fa..90c9d3531694 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -33,6 +33,8 @@ struct pci_controller *init_phb_dynamic(struct device_node *dn)
 
 	pci_devs_phb_init_dynamic(phb);
 
+	pseries_msi_allocate_domains(phb);
+
 	/* Create EEH devices for the PHB */
 	eeh_phb_pe_create(phb);
 
@@ -74,6 +76,8 @@ int remove_phb_dynamic(struct pci_controller *phb)
 		}
 	}
 
+	pseries_msi_free_domains(phb);
+
 	/* Remove the PCI bus and unregister the bridge device from sysfs */
 	phb->bus = NULL;
 	pci_remove_bus(b);
diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h
index 1f051a786fb3..3544778e06d0 100644
--- a/arch/powerpc/platforms/pseries/pseries.h
+++ b/arch/powerpc/platforms/pseries/pseries.h
@@ -85,6 +85,8 @@ struct pci_host_bridge;
 int pseries_root_bridge_prepare(struct pci_host_bridge *bridge);
 
 extern struct pci_controller_ops pseries_pci_controller_ops;
+int pseries_msi_allocate_domains(struct pci_controller *phb);
+void pseries_msi_free_domains(struct pci_controller *phb);
 
 unsigned long pseries_memory_block_size(void);
 
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index 167f2e1b8d39..56092dccfdb8 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -783,7 +783,7 @@ static int recover_mce(struct pt_regs *regs, struct machine_check_event *evt)
 {
 	int recovered = 0;
 
-	if (!(regs->msr & MSR_RI)) {
+	if (regs_is_unrecoverable(regs)) {
 		/* If MSR_RI isn't set, we cannot recover */
 		pr_err("Machine check interrupt unrecoverable: MSR(RI=0)\n");
 		recovered = 0;
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 0dfaa6ab44cc..f79126f16258 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -486,6 +486,8 @@ static void __init pSeries_discover_phbs(void)
 
 		/* create pci_dn's for DT nodes under this PHB */
 		pci_devs_phb_init_dynamic(phb);
+
+		pseries_msi_allocate_domains(phb);
 	}
 
 	of_node_put(root);
diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c
index b5c1cf1bc64d..b043e3936d21 100644
--- a/arch/powerpc/platforms/pseries/vas.c
+++ b/arch/powerpc/platforms/pseries/vas.c
@@ -184,7 +184,7 @@ static int h_get_nx_fault(u32 winid, u64 buffer)
  * Note: The hypervisor forwards an interrupt for each fault request.
  *	So one fault CRB to process for each H_GET_NX_FAULT hcall.
  */
-irqreturn_t pseries_vas_fault_thread_fn(int irq, void *data)
+static irqreturn_t pseries_vas_fault_thread_fn(int irq, void *data)
 {
 	struct pseries_vas_window *txwin = data;
 	struct coprocessor_request_block crb;
diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c
index 5a95b8ea23d8..ff7906b48ca1 100644
--- a/arch/powerpc/sysdev/fsl_rio.c
+++ b/arch/powerpc/sysdev/fsl_rio.c
@@ -108,7 +108,7 @@ int fsl_rio_mcheck_exception(struct pt_regs *regs)
 				 __func__);
 			out_be32((u32 *)(rio_regs_win + RIO_LTLEDCSR),
 				 0);
-			regs_set_return_msr(regs, regs->msr | MSR_RI);
+			regs_set_recoverable(regs);
 			regs_set_return_ip(regs, extable_fixup(entry));
 			return 1;
 		}
diff --git a/arch/powerpc/sysdev/xics/ics-native.c b/arch/powerpc/sysdev/xics/ics-native.c
index d450502f4053..dec7d93a8ba1 100644
--- a/arch/powerpc/sysdev/xics/ics-native.c
+++ b/arch/powerpc/sysdev/xics/ics-native.c
@@ -131,19 +131,15 @@ static struct irq_chip ics_native_irq_chip = {
 	.irq_retrigger		= xics_retrigger,
 };
 
-static int ics_native_map(struct ics *ics, unsigned int virq)
+static int ics_native_check(struct ics *ics, unsigned int hw_irq)
 {
-	unsigned int vec = (unsigned int)virq_to_hw(virq);
 	struct ics_native *in = to_ics_native(ics);
 
-	pr_devel("%s: vec=0x%x\n", __func__, vec);
+	pr_devel("%s: hw_irq=0x%x\n", __func__, hw_irq);
 
-	if (vec < in->ibase || vec >= (in->ibase + in->icount))
+	if (hw_irq < in->ibase || hw_irq >= (in->ibase + in->icount))
 		return -EINVAL;
 
-	irq_set_chip_and_handler(virq, &ics_native_irq_chip, handle_fasteoi_irq);
-	irq_set_chip_data(virq, ics);
-
 	return 0;
 }
 
@@ -177,10 +173,11 @@ static int ics_native_host_match(struct ics *ics, struct device_node *node)
 }
 
 static struct ics ics_native_template = {
-	.map		= ics_native_map,
+	.check		= ics_native_check,
 	.mask_unknown	= ics_native_mask_unknown,
 	.get_server	= ics_native_get_server,
 	.host_match	= ics_native_host_match,
+	.chip = &ics_native_irq_chip,
 };
 
 static int __init ics_native_add_one(struct device_node *np)
diff --git a/arch/powerpc/sysdev/xics/ics-opal.c b/arch/powerpc/sysdev/xics/ics-opal.c
index 823f6c9664cd..c4d95d8beb6f 100644
--- a/arch/powerpc/sysdev/xics/ics-opal.c
+++ b/arch/powerpc/sysdev/xics/ics-opal.c
@@ -62,17 +62,6 @@ static void ics_opal_unmask_irq(struct irq_data *d)
 
 static unsigned int ics_opal_startup(struct irq_data *d)
 {
-#ifdef CONFIG_PCI_MSI
-	/*
-	 * The generic MSI code returns with the interrupt disabled on the
-	 * card, using the MSI mask bits. Firmware doesn't appear to unmask
-	 * at that level, so we do it here by hand.
-	 */
-	if (irq_data_get_msi_desc(d))
-		pci_msi_unmask_irq(d);
-#endif
-
-	/* unmask it */
 	ics_opal_unmask_irq(d);
 	return 0;
 }
@@ -133,7 +122,7 @@ static int ics_opal_set_affinity(struct irq_data *d,
 	}
 	server = ics_opal_mangle_server(wanted_server);
 
-	pr_devel("ics-hal: set-affinity irq %d [hw 0x%x] server: 0x%x/0x%x\n",
+	pr_debug("ics-hal: set-affinity irq %d [hw 0x%x] server: 0x%x/0x%x\n",
 		 d->irq, hw_irq, wanted_server, server);
 
 	rc = opal_set_xive(hw_irq, server, priority);
@@ -157,26 +146,13 @@ static struct irq_chip ics_opal_irq_chip = {
 	.irq_retrigger = xics_retrigger,
 };
 
-static int ics_opal_map(struct ics *ics, unsigned int virq);
-static void ics_opal_mask_unknown(struct ics *ics, unsigned long vec);
-static long ics_opal_get_server(struct ics *ics, unsigned long vec);
-
 static int ics_opal_host_match(struct ics *ics, struct device_node *node)
 {
 	return 1;
 }
 
-/* Only one global & state struct ics */
-static struct ics ics_hal = {
-	.map		= ics_opal_map,
-	.mask_unknown	= ics_opal_mask_unknown,
-	.get_server	= ics_opal_get_server,
-	.host_match	= ics_opal_host_match,
-};
-
-static int ics_opal_map(struct ics *ics, unsigned int virq)
+static int ics_opal_check(struct ics *ics, unsigned int hw_irq)
 {
-	unsigned int hw_irq = (unsigned int)virq_to_hw(virq);
 	int64_t rc;
 	__be16 server;
 	int8_t priority;
@@ -189,9 +165,6 @@ static int ics_opal_map(struct ics *ics, unsigned int virq)
 	if (rc != OPAL_SUCCESS)
 		return -ENXIO;
 
-	irq_set_chip_and_handler(virq, &ics_opal_irq_chip, handle_fasteoi_irq);
-	irq_set_chip_data(virq, &ics_hal);
-
 	return 0;
 }
 
@@ -222,6 +195,15 @@ static long ics_opal_get_server(struct ics *ics, unsigned long vec)
 	return ics_opal_unmangle_server(be16_to_cpu(server));
 }
 
+/* Only one global & state struct ics */
+static struct ics ics_hal = {
+	.check		= ics_opal_check,
+	.mask_unknown	= ics_opal_mask_unknown,
+	.get_server	= ics_opal_get_server,
+	.host_match	= ics_opal_host_match,
+	.chip		= &ics_opal_irq_chip,
+};
+
 int __init ics_opal_init(void)
 {
 	if (!firmware_has_feature(FW_FEATURE_OPAL))
diff --git a/arch/powerpc/sysdev/xics/ics-rtas.c b/arch/powerpc/sysdev/xics/ics-rtas.c
index 4cf18000f07c..b9da317b7a2d 100644
--- a/arch/powerpc/sysdev/xics/ics-rtas.c
+++ b/arch/powerpc/sysdev/xics/ics-rtas.c
@@ -24,19 +24,6 @@ static int ibm_set_xive;
 static int ibm_int_on;
 static int ibm_int_off;
 
-static int ics_rtas_map(struct ics *ics, unsigned int virq);
-static void ics_rtas_mask_unknown(struct ics *ics, unsigned long vec);
-static long ics_rtas_get_server(struct ics *ics, unsigned long vec);
-static int ics_rtas_host_match(struct ics *ics, struct device_node *node);
-
-/* Only one global & state struct ics */
-static struct ics ics_rtas = {
-	.map		= ics_rtas_map,
-	.mask_unknown	= ics_rtas_mask_unknown,
-	.get_server	= ics_rtas_get_server,
-	.host_match	= ics_rtas_host_match,
-};
-
 static void ics_rtas_unmask_irq(struct irq_data *d)
 {
 	unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
@@ -70,15 +57,6 @@ static void ics_rtas_unmask_irq(struct irq_data *d)
 
 static unsigned int ics_rtas_startup(struct irq_data *d)
 {
-#ifdef CONFIG_PCI_MSI
-	/*
-	 * The generic MSI code returns with the interrupt disabled on the
-	 * card, using the MSI mask bits. Firmware doesn't appear to unmask
-	 * at that level, so we do it here by hand.
-	 */
-	if (irq_data_get_msi_desc(d))
-		pci_msi_unmask_irq(d);
-#endif
 	/* unmask it */
 	ics_rtas_unmask_irq(d);
 	return 0;
@@ -146,6 +124,9 @@ static int ics_rtas_set_affinity(struct irq_data *d,
 		return -1;
 	}
 
+	pr_debug("%s: irq %d [hw 0x%x] server: 0x%x\n", __func__, d->irq,
+		 hw_irq, irq_server);
+
 	status = rtas_call_reentrant(ibm_set_xive, 3, 1, NULL,
 				     hw_irq, irq_server, xics_status[1]);
 
@@ -169,9 +150,8 @@ static struct irq_chip ics_rtas_irq_chip = {
 	.irq_retrigger = xics_retrigger,
 };
 
-static int ics_rtas_map(struct ics *ics, unsigned int virq)
+static int ics_rtas_check(struct ics *ics, unsigned int hw_irq)
 {
-	unsigned int hw_irq = (unsigned int)virq_to_hw(virq);
 	int status[2];
 	int rc;
 
@@ -183,9 +163,6 @@ static int ics_rtas_map(struct ics *ics, unsigned int virq)
 	if (rc)
 		return -ENXIO;
 
-	irq_set_chip_and_handler(virq, &ics_rtas_irq_chip, handle_fasteoi_irq);
-	irq_set_chip_data(virq, &ics_rtas);
-
 	return 0;
 }
 
@@ -213,6 +190,15 @@ static int ics_rtas_host_match(struct ics *ics, struct device_node *node)
 	return !of_device_is_compatible(node, "chrp,iic");
 }
 
+/* Only one global & state struct ics */
+static struct ics ics_rtas = {
+	.check		= ics_rtas_check,
+	.mask_unknown	= ics_rtas_mask_unknown,
+	.get_server	= ics_rtas_get_server,
+	.host_match	= ics_rtas_host_match,
+	.chip = &ics_rtas_irq_chip,
+};
+
 __init int ics_rtas_init(void)
 {
 	ibm_get_xive = rtas_token("ibm,get-xive");
diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c
index b14c502e56a8..5c1a157a83b8 100644
--- a/arch/powerpc/sysdev/xics/xics-common.c
+++ b/arch/powerpc/sysdev/xics/xics-common.c
@@ -38,7 +38,7 @@ DEFINE_PER_CPU(struct xics_cppr, xics_cppr);
 
 struct irq_domain *xics_host;
 
-static LIST_HEAD(ics_list);
+static struct ics *xics_ics;
 
 void xics_update_irq_servers(void)
 {
@@ -111,12 +111,11 @@ void xics_setup_cpu(void)
 
 void xics_mask_unknown_vec(unsigned int vec)
 {
-	struct ics *ics;
-
 	pr_err("Interrupt 0x%x (real) is invalid, disabling it.\n", vec);
 
-	list_for_each_entry(ics, &ics_list, link)
-		ics->mask_unknown(ics, vec);
+	if (WARN_ON(!xics_ics))
+		return;
+	xics_ics->mask_unknown(xics_ics, vec);
 }
 
 
@@ -133,7 +132,7 @@ static void xics_request_ipi(void)
 	 * IPIs are marked IRQF_PERCPU. The handler was set in map.
 	 */
 	BUG_ON(request_irq(ipi, icp_ops->ipi_action,
-			   IRQF_PERCPU | IRQF_NO_THREAD, "IPI", NULL));
+			   IRQF_NO_DEBUG | IRQF_PERCPU | IRQF_NO_THREAD, "IPI", NULL));
 }
 
 void __init xics_smp_probe(void)
@@ -184,6 +183,8 @@ void xics_migrate_irqs_away(void)
 	unsigned int irq, virq;
 	struct irq_desc *desc;
 
+	pr_debug("%s: CPU %u\n", __func__, cpu);
+
 	/* If we used to be the default server, move to the new "boot_cpuid" */
 	if (hw_cpu == xics_default_server)
 		xics_update_irq_servers();
@@ -198,7 +199,7 @@ void xics_migrate_irqs_away(void)
 		struct irq_chip *chip;
 		long server;
 		unsigned long flags;
-		struct ics *ics;
+		struct irq_data *irqd;
 
 		/* We can't set affinity on ISA interrupts */
 		if (virq < NR_IRQS_LEGACY)
@@ -206,9 +207,11 @@ void xics_migrate_irqs_away(void)
 		/* We only need to migrate enabled IRQS */
 		if (!desc->action)
 			continue;
-		if (desc->irq_data.domain != xics_host)
+		/* We need a mapping in the XICS IRQ domain */
+		irqd = irq_domain_get_irq_data(xics_host, virq);
+		if (!irqd)
 			continue;
-		irq = desc->irq_data.hwirq;
+		irq = irqd_to_hwirq(irqd);
 		/* We need to get IPIs still. */
 		if (irq == XICS_IPI || irq == XICS_IRQ_SPURIOUS)
 			continue;
@@ -219,13 +222,10 @@ void xics_migrate_irqs_away(void)
 		raw_spin_lock_irqsave(&desc->lock, flags);
 
 		/* Locate interrupt server */
-		server = -1;
-		ics = irq_desc_get_chip_data(desc);
-		if (ics)
-			server = ics->get_server(ics, irq);
+		server = xics_ics->get_server(xics_ics, irq);
 		if (server < 0) {
-			printk(KERN_ERR "%s: Can't find server for irq %d\n",
-			       __func__, irq);
+			pr_err("%s: Can't find server for irq %d/%x\n",
+			       __func__, virq, irq);
 			goto unlock;
 		}
 
@@ -307,13 +307,9 @@ int xics_get_irq_server(unsigned int virq, const struct cpumask *cpumask,
 static int xics_host_match(struct irq_domain *h, struct device_node *node,
 			   enum irq_domain_bus_token bus_token)
 {
-	struct ics *ics;
-
-	list_for_each_entry(ics, &ics_list, link)
-		if (ics->host_match(ics, node))
-			return 1;
-
-	return 0;
+	if (WARN_ON(!xics_ics))
+		return 0;
+	return xics_ics->host_match(xics_ics, node) ? 1 : 0;
 }
 
 /* Dummies */
@@ -327,12 +323,10 @@ static struct irq_chip xics_ipi_chip = {
 	.irq_unmask = xics_ipi_unmask,
 };
 
-static int xics_host_map(struct irq_domain *h, unsigned int virq,
-			 irq_hw_number_t hw)
+static int xics_host_map(struct irq_domain *domain, unsigned int virq,
+			 irq_hw_number_t hwirq)
 {
-	struct ics *ics;
-
-	pr_devel("xics: map virq %d, hwirq 0x%lx\n", virq, hw);
+	pr_devel("xics: map virq %d, hwirq 0x%lx\n", virq, hwirq);
 
 	/*
 	 * Mark interrupts as edge sensitive by default so that resend
@@ -342,18 +336,23 @@ static int xics_host_map(struct irq_domain *h, unsigned int virq,
 	irq_clear_status_flags(virq, IRQ_LEVEL);
 
 	/* Don't call into ICS for IPIs */
-	if (hw == XICS_IPI) {
+	if (hwirq == XICS_IPI) {
 		irq_set_chip_and_handler(virq, &xics_ipi_chip,
 					 handle_percpu_irq);
 		return 0;
 	}
 
-	/* Let the ICS setup the chip data */
-	list_for_each_entry(ics, &ics_list, link)
-		if (ics->map(ics, virq) == 0)
-			return 0;
+	if (WARN_ON(!xics_ics))
+		return -EINVAL;
 
-	return -EINVAL;
+	if (xics_ics->check(xics_ics, hwirq))
+		return -EINVAL;
+
+	/* No chip data for the XICS domain */
+	irq_domain_set_info(domain, virq, hwirq, xics_ics->chip,
+			    NULL, handle_fasteoi_irq, NULL, NULL);
+
+	return 0;
 }
 
 static int xics_host_xlate(struct irq_domain *h, struct device_node *ct,
@@ -412,22 +411,76 @@ int xics_retrigger(struct irq_data *data)
 	return 0;
 }
 
+#ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
+static int xics_host_domain_translate(struct irq_domain *d, struct irq_fwspec *fwspec,
+				      unsigned long *hwirq, unsigned int *type)
+{
+	return xics_host_xlate(d, to_of_node(fwspec->fwnode), fwspec->param,
+			       fwspec->param_count, hwirq, type);
+}
+
+static int xics_host_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				  unsigned int nr_irqs, void *arg)
+{
+	struct irq_fwspec *fwspec = arg;
+	irq_hw_number_t hwirq;
+	unsigned int type = IRQ_TYPE_NONE;
+	int i, rc;
+
+	rc = xics_host_domain_translate(domain, fwspec, &hwirq, &type);
+	if (rc)
+		return rc;
+
+	pr_debug("%s %d/%lx #%d\n", __func__, virq, hwirq, nr_irqs);
+
+	for (i = 0; i < nr_irqs; i++)
+		irq_domain_set_info(domain, virq + i, hwirq + i, xics_ics->chip,
+				    xics_ics, handle_fasteoi_irq, NULL, NULL);
+
+	return 0;
+}
+
+static void xics_host_domain_free(struct irq_domain *domain,
+				  unsigned int virq, unsigned int nr_irqs)
+{
+	pr_debug("%s %d #%d\n", __func__, virq, nr_irqs);
+}
+#endif
+
 static const struct irq_domain_ops xics_host_ops = {
+#ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
+	.alloc	= xics_host_domain_alloc,
+	.free	= xics_host_domain_free,
+	.translate = xics_host_domain_translate,
+#endif
 	.match = xics_host_match,
 	.map = xics_host_map,
 	.xlate = xics_host_xlate,
 };
 
-static void __init xics_init_host(void)
+static int __init xics_allocate_domain(void)
 {
-	xics_host = irq_domain_add_tree(NULL, &xics_host_ops, NULL);
-	BUG_ON(xics_host == NULL);
+	struct fwnode_handle *fn;
+
+	fn = irq_domain_alloc_named_fwnode("XICS");
+	if (!fn)
+		return -ENOMEM;
+
+	xics_host = irq_domain_create_tree(fn, &xics_host_ops, NULL);
+	if (!xics_host) {
+		irq_domain_free_fwnode(fn);
+		return -ENOMEM;
+	}
+
 	irq_set_default_host(xics_host);
+	return 0;
 }
 
 void __init xics_register_ics(struct ics *ics)
 {
-	list_add(&ics->link, &ics_list);
+	if (WARN_ONCE(xics_ics, "XICS: Source Controller is already defined !"))
+		return;
+	xics_ics = ics;
 }
 
 static void __init xics_get_server_size(void)
@@ -484,6 +537,8 @@ void __init xics_init(void)
 	/* Initialize common bits */
 	xics_get_server_size();
 	xics_update_irq_servers();
-	xics_init_host();
+	rc = xics_allocate_domain();
+	if (rc < 0)
+		pr_err("XICS: Failed to create IRQ domain");
 	xics_setup_cpu();
 }
diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c
index 8183ca343675..c732ce5a3e1a 100644
--- a/arch/powerpc/sysdev/xive/common.c
+++ b/arch/powerpc/sysdev/xive/common.c
@@ -21,7 +21,6 @@
 #include <linux/msi.h>
 #include <linux/vmalloc.h>
 
-#include <asm/debugfs.h>
 #include <asm/prom.h>
 #include <asm/io.h>
 #include <asm/smp.h>
@@ -313,11 +312,10 @@ void xmon_xive_get_irq_all(void)
 	struct irq_desc *desc;
 
 	for_each_irq_desc(i, desc) {
-		struct irq_data *d = irq_desc_get_irq_data(desc);
-		unsigned int hwirq = (unsigned int)irqd_to_hwirq(d);
+		struct irq_data *d = irq_domain_get_irq_data(xive_irq_domain, i);
 
-		if (d->domain == xive_irq_domain)
-			xmon_xive_get_irq_config(hwirq, d);
+		if (d)
+			xmon_xive_get_irq_config(irqd_to_hwirq(d), d);
 	}
 }
 
@@ -617,16 +615,6 @@ static unsigned int xive_irq_startup(struct irq_data *d)
 	pr_devel("xive_irq_startup: irq %d [0x%x] data @%p\n",
 		 d->irq, hw_irq, d);
 
-#ifdef CONFIG_PCI_MSI
-	/*
-	 * The generic MSI code returns with the interrupt disabled on the
-	 * card, using the MSI mask bits. Firmware doesn't appear to unmask
-	 * at that level, so we do it here by hand.
-	 */
-	if (irq_data_get_msi_desc(d))
-		pci_msi_unmask_irq(d);
-#endif
-
 	/* Pick a target */
 	target = xive_pick_irq_target(d, irq_data_get_affinity_mask(d));
 	if (target == XIVE_INVALID_TARGET) {
@@ -714,16 +702,12 @@ static int xive_irq_set_affinity(struct irq_data *d,
 	u32 target, old_target;
 	int rc = 0;
 
-	pr_devel("xive_irq_set_affinity: irq %d\n", d->irq);
+	pr_debug("%s: irq %d/%x\n", __func__, d->irq, hw_irq);
 
 	/* Is this valid ? */
 	if (cpumask_any_and(cpumask, cpu_online_mask) >= nr_cpu_ids)
 		return -EINVAL;
 
-	/* Don't do anything if the interrupt isn't started */
-	if (!irqd_is_started(d))
-		return IRQ_SET_MASK_OK;
-
 	/*
 	 * If existing target is already in the new mask, and is
 	 * online then do nothing.
@@ -759,7 +743,7 @@ static int xive_irq_set_affinity(struct irq_data *d,
 		return rc;
 	}
 
-	pr_devel("  target: 0x%x\n", target);
+	pr_debug("  target: 0x%x\n", target);
 	xd->target = target;
 
 	/* Give up previous target */
@@ -990,6 +974,8 @@ EXPORT_SYMBOL_GPL(is_xive_irq);
 
 void xive_cleanup_irq_data(struct xive_irq_data *xd)
 {
+	pr_debug("%s for HW %x\n", __func__, xd->hw_irq);
+
 	if (xd->eoi_mmio) {
 		iounmap(xd->eoi_mmio);
 		if (xd->eoi_mmio == xd->trig_mmio)
@@ -1031,7 +1017,7 @@ static int xive_irq_alloc_data(unsigned int virq, irq_hw_number_t hw)
 	return 0;
 }
 
-static void xive_irq_free_data(unsigned int virq)
+void xive_irq_free_data(unsigned int virq)
 {
 	struct xive_irq_data *xd = irq_get_handler_data(virq);
 
@@ -1041,6 +1027,7 @@ static void xive_irq_free_data(unsigned int virq)
 	xive_cleanup_irq_data(xd);
 	kfree(xd);
 }
+EXPORT_SYMBOL_GPL(xive_irq_free_data);
 
 #ifdef CONFIG_SMP
 
@@ -1179,7 +1166,7 @@ static int xive_request_ipi(unsigned int cpu)
 		return 0;
 
 	ret = request_irq(xid->irq, xive_muxed_ipi_action,
-			  IRQF_PERCPU | IRQF_NO_THREAD,
+			  IRQF_NO_DEBUG | IRQF_PERCPU | IRQF_NO_THREAD,
 			  xid->name, NULL);
 
 	WARN(ret < 0, "Failed to request IPI %d: %d\n", xid->irq, ret);
@@ -1379,7 +1366,71 @@ static void xive_irq_domain_debug_show(struct seq_file *m, struct irq_domain *d,
 }
 #endif
 
+#ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
+static int xive_irq_domain_translate(struct irq_domain *d,
+				     struct irq_fwspec *fwspec,
+				     unsigned long *hwirq,
+				     unsigned int *type)
+{
+	return xive_irq_domain_xlate(d, to_of_node(fwspec->fwnode),
+				     fwspec->param, fwspec->param_count,
+				     hwirq, type);
+}
+
+static int xive_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				 unsigned int nr_irqs, void *arg)
+{
+	struct irq_fwspec *fwspec = arg;
+	irq_hw_number_t hwirq;
+	unsigned int type = IRQ_TYPE_NONE;
+	int i, rc;
+
+	rc = xive_irq_domain_translate(domain, fwspec, &hwirq, &type);
+	if (rc)
+		return rc;
+
+	pr_debug("%s %d/%lx #%d\n", __func__, virq, hwirq, nr_irqs);
+
+	for (i = 0; i < nr_irqs; i++) {
+		/* TODO: call xive_irq_domain_map() */
+
+		/*
+		 * Mark interrupts as edge sensitive by default so that resend
+		 * actually works. Will fix that up below if needed.
+		 */
+		irq_clear_status_flags(virq, IRQ_LEVEL);
+
+		/* allocates and sets handler data */
+		rc = xive_irq_alloc_data(virq + i, hwirq + i);
+		if (rc)
+			return rc;
+
+		irq_domain_set_hwirq_and_chip(domain, virq + i, hwirq + i,
+					      &xive_irq_chip, domain->host_data);
+		irq_set_handler(virq + i, handle_fasteoi_irq);
+	}
+
+	return 0;
+}
+
+static void xive_irq_domain_free(struct irq_domain *domain,
+				 unsigned int virq, unsigned int nr_irqs)
+{
+	int i;
+
+	pr_debug("%s %d #%d\n", __func__, virq, nr_irqs);
+
+	for (i = 0; i < nr_irqs; i++)
+		xive_irq_free_data(virq + i);
+}
+#endif
+
 static const struct irq_domain_ops xive_irq_domain_ops = {
+#ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
+	.alloc	= xive_irq_domain_alloc,
+	.free	= xive_irq_domain_free,
+	.translate = xive_irq_domain_translate,
+#endif
 	.match = xive_irq_domain_match,
 	.map = xive_irq_domain_map,
 	.unmap = xive_irq_domain_unmap,
@@ -1717,9 +1768,9 @@ static int xive_core_debug_show(struct seq_file *m, void *private)
 		xive_debug_show_cpu(m, cpu);
 
 	for_each_irq_desc(i, desc) {
-		struct irq_data *d = irq_desc_get_irq_data(desc);
+		struct irq_data *d = irq_domain_get_irq_data(xive_irq_domain, i);
 
-		if (d->domain == xive_irq_domain)
+		if (d)
 			xive_debug_show_irq(m, d);
 	}
 	return 0;
@@ -1729,7 +1780,7 @@ DEFINE_SHOW_ATTRIBUTE(xive_core_debug);
 int xive_core_debug_init(void)
 {
 	if (xive_enabled())
-		debugfs_create_file("xive", 0400, powerpc_debugfs_root,
+		debugfs_create_file("xive", 0400, arch_debugfs_dir,
 				    NULL, &xive_core_debug_fops);
 	return 0;
 }
diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c
index 57e3f1540435..1aec282cd650 100644
--- a/arch/powerpc/sysdev/xive/native.c
+++ b/arch/powerpc/sysdev/xive/native.c
@@ -41,6 +41,7 @@ static u32 xive_queue_shift;
 static u32 xive_pool_vps = XIVE_INVALID_VP;
 static struct kmem_cache *xive_provision_cache;
 static bool xive_has_single_esc;
+static bool xive_has_save_restore;
 
 int xive_native_populate_irq_data(u32 hw_irq, struct xive_irq_data *data)
 {
@@ -588,6 +589,9 @@ bool __init xive_native_init(void)
 	if (of_get_property(np, "single-escalation-support", NULL) != NULL)
 		xive_has_single_esc = true;
 
+	if (of_get_property(np, "vp-save-restore", NULL))
+		xive_has_save_restore = true;
+
 	/* Configure Thread Management areas for KVM */
 	for_each_possible_cpu(cpu)
 		kvmppc_set_xive_tima(cpu, r.start, tima);
@@ -752,6 +756,12 @@ bool xive_native_has_single_escalation(void)
 }
 EXPORT_SYMBOL_GPL(xive_native_has_single_escalation);
 
+bool xive_native_has_save_restore(void)
+{
+	return xive_has_save_restore;
+}
+EXPORT_SYMBOL_GPL(xive_native_has_save_restore);
+
 int xive_native_get_queue_info(u32 vp_id, u32 prio,
 			       u64 *out_qpage,
 			       u64 *out_qsize,
diff --git a/arch/powerpc/tools/head_check.sh b/arch/powerpc/tools/head_check.sh
index e32d3162e5ed..689907cda996 100644
--- a/arch/powerpc/tools/head_check.sh
+++ b/arch/powerpc/tools/head_check.sh
@@ -49,30 +49,30 @@ vmlinux="$2"
 $nm "$vmlinux" | grep -e " [TA] _stext$" -e " t start_first_256B$" -e " a text_start$" -e " t start_text$" > .tmp_symbols.txt
 
 
-vma=$(cat .tmp_symbols.txt | grep -e " [TA] _stext$" | cut -d' ' -f1)
+vma=$(grep -e " [TA] _stext$" .tmp_symbols.txt | cut -d' ' -f1)
 
-expected_start_head_addr=$vma
+expected_start_head_addr="$vma"
 
-start_head_addr=$(cat .tmp_symbols.txt | grep " t start_first_256B$" | cut -d' ' -f1)
+start_head_addr=$(grep " t start_first_256B$" .tmp_symbols.txt | cut -d' ' -f1)
 
 if [ "$start_head_addr" != "$expected_start_head_addr" ]; then
-	echo "ERROR: head code starts at $start_head_addr, should be $expected_start_head_addr"
-	echo "ERROR: try to enable LD_HEAD_STUB_CATCH config option"
-	echo "ERROR: see comments in arch/powerpc/tools/head_check.sh"
+	echo "ERROR: head code starts at $start_head_addr, should be $expected_start_head_addr" 1>&2
+	echo "ERROR: try to enable LD_HEAD_STUB_CATCH config option" 1>&2
+	echo "ERROR: see comments in arch/powerpc/tools/head_check.sh" 1>&2
 
 	exit 1
 fi
 
-top_vma=$(echo $vma | cut -d'0' -f1)
+top_vma=$(echo "$vma" | cut -d'0' -f1)
 
-expected_start_text_addr=$(cat .tmp_symbols.txt | grep " a text_start$" | cut -d' ' -f1 | sed "s/^0/$top_vma/")
+expected_start_text_addr=$(grep " a text_start$" .tmp_symbols.txt | cut -d' ' -f1 | sed "s/^0/$top_vma/")
 
-start_text_addr=$(cat .tmp_symbols.txt | grep " t start_text$" | cut -d' ' -f1)
+start_text_addr=$(grep " t start_text$" .tmp_symbols.txt | cut -d' ' -f1)
 
 if [ "$start_text_addr" != "$expected_start_text_addr" ]; then
-	echo "ERROR: start_text address is $start_text_addr, should be $expected_start_text_addr"
-	echo "ERROR: try to enable LD_HEAD_STUB_CATCH config option"
-	echo "ERROR: see comments in arch/powerpc/tools/head_check.sh"
+	echo "ERROR: start_text address is $start_text_addr, should be $expected_start_text_addr" 1>&2
+	echo "ERROR: try to enable LD_HEAD_STUB_CATCH config option" 1>&2
+	echo "ERROR: see comments in arch/powerpc/tools/head_check.sh" 1>&2
 
 	exit 1
 fi
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index da4d7f225a40..dd8241c009e5 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -26,8 +26,8 @@
 #include <linux/ctype.h>
 #include <linux/highmem.h>
 #include <linux/security.h>
+#include <linux/debugfs.h>
 
-#include <asm/debugfs.h>
 #include <asm/ptrace.h>
 #include <asm/smp.h>
 #include <asm/string.h>
@@ -482,16 +482,6 @@ static inline void get_output_lock(void) {}
 static inline void release_output_lock(void) {}
 #endif
 
-static inline int unrecoverable_excp(struct pt_regs *regs)
-{
-#if defined(CONFIG_4xx) || defined(CONFIG_PPC_BOOK3E)
-	/* We have no MSR_RI bit on 4xx or Book3e, so we simply return false */
-	return 0;
-#else
-	return ((regs->msr & MSR_RI) == 0);
-#endif
-}
-
 static void xmon_touch_watchdogs(void)
 {
 	touch_softlockup_watchdog_sync();
@@ -565,7 +555,7 @@ static int xmon_core(struct pt_regs *regs, volatile int fromipi)
 	bp = NULL;
 	if ((regs->msr & (MSR_IR|MSR_PR|MSR_64BIT)) == (MSR_IR|MSR_64BIT))
 		bp = at_breakpoint(regs->nip);
-	if (bp || unrecoverable_excp(regs))
+	if (bp || regs_is_unrecoverable(regs))
 		fromipi = 0;
 
 	if (!fromipi) {
@@ -577,7 +567,7 @@ static int xmon_core(struct pt_regs *regs, volatile int fromipi)
 			       cpu, BP_NUM(bp));
 			xmon_print_symbol(regs->nip, " ", ")\n");
 		}
-		if (unrecoverable_excp(regs))
+		if (regs_is_unrecoverable(regs))
 			printf("WARNING: exception is not recoverable, "
 			       "can't continue\n");
 		release_output_lock();
@@ -693,7 +683,7 @@ static int xmon_core(struct pt_regs *regs, volatile int fromipi)
 			printf("Stopped at breakpoint %tx (", BP_NUM(bp));
 			xmon_print_symbol(regs->nip, " ", ")\n");
 		}
-		if (unrecoverable_excp(regs))
+		if (regs_is_unrecoverable(regs))
 			printf("WARNING: exception is not recoverable, "
 			       "can't continue\n");
 		remove_bpts();
@@ -4077,8 +4067,8 @@ DEFINE_SIMPLE_ATTRIBUTE(xmon_dbgfs_ops, xmon_dbgfs_get,
 
 static int __init setup_xmon_dbgfs(void)
 {
-	debugfs_create_file("xmon", 0600, powerpc_debugfs_root, NULL,
-				&xmon_dbgfs_ops);
+	debugfs_create_file("xmon", 0600, arch_debugfs_dir, NULL,
+			    &xmon_dbgfs_ops);
 	return 0;
 }
 device_initcall(setup_xmon_dbgfs);
diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c
index 23a06cba392c..5a2cf5f91ccb 100644
--- a/drivers/cpufreq/powernv-cpufreq.c
+++ b/drivers/cpufreq/powernv-cpufreq.c
@@ -36,6 +36,7 @@
 #define MAX_PSTATE_SHIFT	32
 #define LPSTATE_SHIFT		48
 #define GPSTATE_SHIFT		56
+#define MAX_NR_CHIPS		32
 
 #define MAX_RAMP_DOWN_TIME				5120
 /*
@@ -1046,12 +1047,20 @@ static int init_chip_info(void)
 	unsigned int *chip;
 	unsigned int cpu, i;
 	unsigned int prev_chip_id = UINT_MAX;
+	cpumask_t *chip_cpu_mask;
 	int ret = 0;
 
 	chip = kcalloc(num_possible_cpus(), sizeof(*chip), GFP_KERNEL);
 	if (!chip)
 		return -ENOMEM;
 
+	/* Allocate a chip cpu mask large enough to fit mask for all chips */
+	chip_cpu_mask = kcalloc(MAX_NR_CHIPS, sizeof(cpumask_t), GFP_KERNEL);
+	if (!chip_cpu_mask) {
+		ret = -ENOMEM;
+		goto free_and_return;
+	}
+
 	for_each_possible_cpu(cpu) {
 		unsigned int id = cpu_to_chip_id(cpu);
 
@@ -1059,22 +1068,25 @@ static int init_chip_info(void)
 			prev_chip_id = id;
 			chip[nr_chips++] = id;
 		}
+		cpumask_set_cpu(cpu, &chip_cpu_mask[nr_chips-1]);
 	}
 
 	chips = kcalloc(nr_chips, sizeof(struct chip), GFP_KERNEL);
 	if (!chips) {
 		ret = -ENOMEM;
-		goto free_and_return;
+		goto out_free_chip_cpu_mask;
 	}
 
 	for (i = 0; i < nr_chips; i++) {
 		chips[i].id = chip[i];
-		cpumask_copy(&chips[i].mask, cpumask_of_node(chip[i]));
+		cpumask_copy(&chips[i].mask, &chip_cpu_mask[i]);
 		INIT_WORK(&chips[i].throttle, powernv_cpufreq_work_fn);
 		for_each_cpu(cpu, &chips[i].mask)
 			per_cpu(chip_info, cpu) =  &chips[i];
 	}
 
+out_free_chip_cpu_mask:
+	kfree(chip_cpu_mask);
 free_and_return:
 	kfree(chip);
 	return ret;
diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c
index a2b5c6f60cf0..7e7ab5597d7a 100644
--- a/drivers/cpuidle/cpuidle-pseries.c
+++ b/drivers/cpuidle/cpuidle-pseries.c
@@ -346,11 +346,9 @@ static int pseries_cpuidle_driver_init(void)
 static void __init fixup_cede0_latency(void)
 {
 	struct xcede_latency_payload *payload;
-	u64 min_latency_us;
+	u64 min_xcede_latency_us = UINT_MAX;
 	int i;
 
-	min_latency_us = dedicated_states[1].exit_latency; // CEDE latency
-
 	if (parse_cede_parameters())
 		return;
 
@@ -358,42 +356,45 @@ static void __init fixup_cede0_latency(void)
 		nr_xcede_records);
 
 	payload = &xcede_latency_parameter.payload;
+
+	/*
+	 * The CEDE idle state maps to CEDE(0). While the hypervisor
+	 * does not advertise CEDE(0) exit latency values, it does
+	 * advertise the latency values of the extended CEDE states.
+	 * We use the lowest advertised exit latency value as a proxy
+	 * for the exit latency of CEDE(0).
+	 */
 	for (i = 0; i < nr_xcede_records; i++) {
 		struct xcede_latency_record *record = &payload->records[i];
+		u8 hint = record->hint;
 		u64 latency_tb = be64_to_cpu(record->latency_ticks);
 		u64 latency_us = DIV_ROUND_UP_ULL(tb_to_ns(latency_tb), NSEC_PER_USEC);
 
-		if (latency_us == 0)
-			pr_warn("cpuidle: xcede record %d has an unrealistic latency of 0us.\n", i);
+		/*
+		 * We expect the exit latency of an extended CEDE
+		 * state to be non-zero, it to since it takes at least
+		 * a few nanoseconds to wakeup the idle CPU and
+		 * dispatch the virtual processor into the Linux
+		 * Guest.
+		 *
+		 * So we consider only non-zero value for performing
+		 * the fixup of CEDE(0) latency.
+		 */
+		if (latency_us == 0) {
+			pr_warn("cpuidle: Skipping xcede record %d [hint=%d]. Exit latency = 0us\n",
+				i, hint);
+			continue;
+		}
 
-		if (latency_us < min_latency_us)
-			min_latency_us = latency_us;
+		if (latency_us < min_xcede_latency_us)
+			min_xcede_latency_us = latency_us;
 	}
 
-	/*
-	 * By default, we assume that CEDE(0) has exit latency 10us,
-	 * since there is no way for us to query from the platform.
-	 *
-	 * However, if the wakeup latency of an Extended CEDE state is
-	 * smaller than 10us, then we can be sure that CEDE(0)
-	 * requires no more than that.
-	 *
-	 * Perform the fix-up.
-	 */
-	if (min_latency_us < dedicated_states[1].exit_latency) {
-		/*
-		 * We set a minimum of 1us wakeup latency for cede0 to
-		 * distinguish it from snooze
-		 */
-		u64 cede0_latency = 1;
-
-		if (min_latency_us > cede0_latency)
-			cede0_latency = min_latency_us - 1;
-
-		dedicated_states[1].exit_latency = cede0_latency;
-		dedicated_states[1].target_residency = 10 * (cede0_latency);
+	if (min_xcede_latency_us != UINT_MAX) {
+		dedicated_states[1].exit_latency = min_xcede_latency_us;
+		dedicated_states[1].target_residency = 10 * (min_xcede_latency_us);
 		pr_info("cpuidle: Fixed up CEDE exit latency to %llu us\n",
-			cede0_latency);
+			min_xcede_latency_us);
 	}
 
 }
@@ -402,7 +403,7 @@ static void __init fixup_cede0_latency(void)
  * pseries_idle_probe()
  * Choose state table for shared versus dedicated partition
  */
-static int pseries_idle_probe(void)
+static int __init pseries_idle_probe(void)
 {
 
 	if (cpuidle_disable != IDLE_NO_OVERRIDE)
@@ -419,7 +420,21 @@ static int pseries_idle_probe(void)
 			cpuidle_state_table = shared_states;
 			max_idle_state = ARRAY_SIZE(shared_states);
 		} else {
-			fixup_cede0_latency();
+			/*
+			 * Use firmware provided latency values
+			 * starting with POWER10 platforms. In the
+			 * case that we are running on a POWER10
+			 * platform but in an earlier compat mode, we
+			 * can still use the firmware provided values.
+			 *
+			 * However, on platforms prior to POWER10, we
+			 * cannot rely on the accuracy of the firmware
+			 * provided latency values. On such platforms,
+			 * go with the conservative default estimate
+			 * of 10us.
+			 */
+			if (cpu_has_feature(CPU_FTR_ARCH_31) || pvr_version_is(PVR_POWER10))
+				fixup_cede0_latency();
 			cpuidle_state_table = dedicated_states;
 			max_idle_state = NR_DEDICATED_STATES;
 		}
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 62be16135e7c..19e83e9b723c 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -491,6 +491,7 @@ struct irq_domain *irq_get_default_host(void)
 {
 	return irq_default_domain;
 }
+EXPORT_SYMBOL_GPL(irq_get_default_host);
 
 static bool irq_domain_is_nomap(struct irq_domain *domain)
 {
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 270a7df898e2..1209e1786af7 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -931,7 +931,7 @@ static void check_section(const char *modname, struct elf_info *elf,
 		".kprobes.text", ".cpuidle.text", ".noinstr.text"
 #define OTHER_TEXT_SECTIONS ".ref.text", ".head.text", ".spinlock.text", \
 		".fixup", ".entry.text", ".exception.text", ".text.*", \
-		".coldtext"
+		".coldtext", ".softirqentry.text"
 
 #define INIT_SECTIONS      ".init.*"
 #define MEM_INIT_SECTIONS  ".meminit.*"
diff --git a/tools/testing/selftests/powerpc/primitives/asm/extable.h b/tools/testing/selftests/powerpc/primitives/asm/extable.h
new file mode 120000
index 000000000000..6385f059a951
--- /dev/null
+++ b/tools/testing/selftests/powerpc/primitives/asm/extable.h
@@ -0,0 +1 @@
+../../../../../../arch/powerpc/include/asm/extable.h
\ No newline at end of file
diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-gpr.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-gpr.c
index 82f7bdc2e5e6..67ca297c5cca 100644
--- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-gpr.c
+++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-gpr.c
@@ -57,7 +57,7 @@ trans:
 		: [gpr_1]"i"(GPR_1), [gpr_2]"i"(GPR_2),
 		[sprn_texasr] "i" (SPRN_TEXASR), [flt_1] "b" (&a),
 		[flt_2] "b" (&b), [cptr1] "b" (&cptr[1])
-		: "memory", "r7", "r8", "r9", "r10",
+		: "memory", "r0", "r7", "r8", "r9", "r10",
 		"r11", "r12", "r13", "r14", "r15", "r16",
 		"r17", "r18", "r19", "r20", "r21", "r22",
 		"r23", "r24", "r25", "r26", "r27", "r28",
@@ -113,6 +113,7 @@ int ptrace_tm_gpr(void)
 	int ret, status;
 
 	SKIP_IF(!have_htm());
+	SKIP_IF(htm_is_synthetic());
 	shm_id = shmget(IPC_PRIVATE, sizeof(int) * 2, 0777|IPC_CREAT);
 	pid = fork();
 	if (pid < 0) {
diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-gpr.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-gpr.c
index ad65be6e8e85..6f2bce1b6c5d 100644
--- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-gpr.c
+++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-gpr.c
@@ -65,7 +65,7 @@ trans:
 		: [gpr_1]"i"(GPR_1), [gpr_2]"i"(GPR_2), [gpr_4]"i"(GPR_4),
 		[sprn_texasr] "i" (SPRN_TEXASR), [flt_1] "b" (&a),
 		[flt_4] "b" (&d)
-		: "memory", "r5", "r6", "r7",
+		: "memory", "r0", "r5", "r6", "r7",
 		"r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15",
 		"r16", "r17", "r18", "r19", "r20", "r21", "r22", "r23",
 		"r24", "r25", "r26", "r27", "r28", "r29", "r30", "r31"
@@ -119,6 +119,7 @@ int ptrace_tm_spd_gpr(void)
 	int ret, status;
 
 	SKIP_IF(!have_htm());
+	SKIP_IF(htm_is_synthetic());
 	shm_id = shmget(IPC_PRIVATE, sizeof(int) * 3, 0777|IPC_CREAT);
 	pid = fork();
 	if (pid < 0) {
diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-tar.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-tar.c
index 2ecfa1158e2b..e112a34fbe59 100644
--- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-tar.c
+++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-tar.c
@@ -129,6 +129,7 @@ int ptrace_tm_spd_tar(void)
 	int ret, status;
 
 	SKIP_IF(!have_htm());
+	SKIP_IF(htm_is_synthetic());
 	shm_id = shmget(IPC_PRIVATE, sizeof(int) * 3, 0777|IPC_CREAT);
 	pid = fork();
 	if (pid == 0)
diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-vsx.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-vsx.c
index 6f7fb51f0809..40133d49fe39 100644
--- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-vsx.c
+++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-vsx.c
@@ -129,6 +129,7 @@ int ptrace_tm_spd_vsx(void)
 	int ret, status, i;
 
 	SKIP_IF(!have_htm());
+	SKIP_IF(htm_is_synthetic());
 	shm_id = shmget(IPC_PRIVATE, sizeof(int) * 3, 0777|IPC_CREAT);
 
 	for (i = 0; i < 128; i++) {
diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spr.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spr.c
index 068bfed2e606..880ba6a29a48 100644
--- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spr.c
+++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spr.c
@@ -114,6 +114,7 @@ int ptrace_tm_spr(void)
 	int ret, status;
 
 	SKIP_IF(!have_htm());
+	SKIP_IF(htm_is_synthetic());
 	shm_id = shmget(IPC_PRIVATE, sizeof(struct shared), 0777|IPC_CREAT);
 	shm_id1 = shmget(IPC_PRIVATE, sizeof(int), 0777|IPC_CREAT);
 	pid = fork();
diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-tar.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-tar.c
index 46ef378a15ec..d0db6df0f0ea 100644
--- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-tar.c
+++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-tar.c
@@ -117,6 +117,7 @@ int ptrace_tm_tar(void)
 	int ret, status;
 
 	SKIP_IF(!have_htm());
+	SKIP_IF(htm_is_synthetic());
 	shm_id = shmget(IPC_PRIVATE, sizeof(int) * 2, 0777|IPC_CREAT);
 	pid = fork();
 	if (pid == 0)
diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-vsx.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-vsx.c
index 70ca01234f79..4f05ce4fd282 100644
--- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-vsx.c
+++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-vsx.c
@@ -113,6 +113,7 @@ int ptrace_tm_vsx(void)
 	int ret, status, i;
 
 	SKIP_IF(!have_htm());
+	SKIP_IF(htm_is_synthetic());
 	shm_id = shmget(IPC_PRIVATE, sizeof(int) * 2, 0777|IPC_CREAT);
 
 	for (i = 0; i < 128; i++) {
diff --git a/tools/testing/selftests/powerpc/signal/signal_tm.c b/tools/testing/selftests/powerpc/signal/signal_tm.c
index 5bf2224ef7f2..c9cf66a3daa2 100644
--- a/tools/testing/selftests/powerpc/signal/signal_tm.c
+++ b/tools/testing/selftests/powerpc/signal/signal_tm.c
@@ -56,6 +56,7 @@ static int test_signal_tm()
 	}
 
 	SKIP_IF(!have_htm());
+	SKIP_IF(htm_is_synthetic());
 
 	for (i = 0; i < MAX_ATTEMPT; i++) {
 		/*
diff --git a/tools/testing/selftests/powerpc/tm/tm-exec.c b/tools/testing/selftests/powerpc/tm/tm-exec.c
index 260cfdb97d23..c59919d6710d 100644
--- a/tools/testing/selftests/powerpc/tm/tm-exec.c
+++ b/tools/testing/selftests/powerpc/tm/tm-exec.c
@@ -27,6 +27,7 @@ static char *path;
 static int test_exec(void)
 {
 	SKIP_IF(!have_htm());
+	SKIP_IF(htm_is_synthetic());
 
 	asm __volatile__(
 		"tbegin.;"
diff --git a/tools/testing/selftests/powerpc/tm/tm-fork.c b/tools/testing/selftests/powerpc/tm/tm-fork.c
index 6efa5a685a77..c27b935f0e9f 100644
--- a/tools/testing/selftests/powerpc/tm/tm-fork.c
+++ b/tools/testing/selftests/powerpc/tm/tm-fork.c
@@ -21,6 +21,7 @@
 int test_fork(void)
 {
 	SKIP_IF(!have_htm());
+	SKIP_IF(htm_is_synthetic());
 
 	asm __volatile__(
 		"tbegin.;"
diff --git a/tools/testing/selftests/powerpc/tm/tm-poison.c b/tools/testing/selftests/powerpc/tm/tm-poison.c
index 29e5f26af7b9..a7bbf034b5bb 100644
--- a/tools/testing/selftests/powerpc/tm/tm-poison.c
+++ b/tools/testing/selftests/powerpc/tm/tm-poison.c
@@ -20,7 +20,6 @@
 #include <sched.h>
 #include <sys/types.h>
 #include <signal.h>
-#include <inttypes.h>
 
 #include "tm.h"
 
@@ -34,6 +33,7 @@ int tm_poison_test(void)
 	bool fail_vr = false;
 
 	SKIP_IF(!have_htm());
+	SKIP_IF(htm_is_synthetic());
 
 	cpu = pick_online_cpu();
 	FAIL_IF(cpu < 0);
diff --git a/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c b/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c
index 4cdb83964bb3..85c940ae6ff8 100644
--- a/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c
+++ b/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c
@@ -40,6 +40,7 @@ int test_body(void)
 	uint64_t rv, dscr1 = 1, dscr2, texasr;
 
 	SKIP_IF(!have_htm());
+	SKIP_IF(htm_is_synthetic());
 
 	printf("Check DSCR TM context switch: ");
 	fflush(stdout);
diff --git a/tools/testing/selftests/powerpc/tm/tm-signal-context-chk-fpu.c b/tools/testing/selftests/powerpc/tm/tm-signal-context-chk-fpu.c
index 254f912ad611..657d755b2905 100644
--- a/tools/testing/selftests/powerpc/tm/tm-signal-context-chk-fpu.c
+++ b/tools/testing/selftests/powerpc/tm/tm-signal-context-chk-fpu.c
@@ -79,6 +79,7 @@ static int tm_signal_context_chk_fpu()
 	pid_t pid = getpid();
 
 	SKIP_IF(!have_htm());
+	SKIP_IF(htm_is_synthetic());
 
 	act.sa_sigaction = signal_usr1;
 	sigemptyset(&act.sa_mask);
diff --git a/tools/testing/selftests/powerpc/tm/tm-signal-context-chk-gpr.c b/tools/testing/selftests/powerpc/tm/tm-signal-context-chk-gpr.c
index 0cc680f61828..400fa70ca71e 100644
--- a/tools/testing/selftests/powerpc/tm/tm-signal-context-chk-gpr.c
+++ b/tools/testing/selftests/powerpc/tm/tm-signal-context-chk-gpr.c
@@ -81,6 +81,7 @@ static int tm_signal_context_chk_gpr()
 	pid_t pid = getpid();
 
 	SKIP_IF(!have_htm());
+	SKIP_IF(htm_is_synthetic());
 
 	act.sa_sigaction = signal_usr1;
 	sigemptyset(&act.sa_mask);
diff --git a/tools/testing/selftests/powerpc/tm/tm-signal-context-chk-vmx.c b/tools/testing/selftests/powerpc/tm/tm-signal-context-chk-vmx.c
index b6d52730a0d8..d628fd302b28 100644
--- a/tools/testing/selftests/powerpc/tm/tm-signal-context-chk-vmx.c
+++ b/tools/testing/selftests/powerpc/tm/tm-signal-context-chk-vmx.c
@@ -104,6 +104,7 @@ static int tm_signal_context_chk()
 	pid_t pid = getpid();
 
 	SKIP_IF(!have_htm());
+	SKIP_IF(htm_is_synthetic());
 
 	act.sa_sigaction = signal_usr1;
 	sigemptyset(&act.sa_mask);
diff --git a/tools/testing/selftests/powerpc/tm/tm-signal-context-chk-vsx.c b/tools/testing/selftests/powerpc/tm/tm-signal-context-chk-vsx.c
index 8e25e2072ecd..9bd869245bad 100644
--- a/tools/testing/selftests/powerpc/tm/tm-signal-context-chk-vsx.c
+++ b/tools/testing/selftests/powerpc/tm/tm-signal-context-chk-vsx.c
@@ -153,6 +153,7 @@ static int tm_signal_context_chk()
 	pid_t pid = getpid();
 
 	SKIP_IF(!have_htm());
+	SKIP_IF(htm_is_synthetic());
 
 	act.sa_sigaction = signal_usr1;
 	sigemptyset(&act.sa_mask);
diff --git a/tools/testing/selftests/powerpc/tm/tm-signal-pagefault.c b/tools/testing/selftests/powerpc/tm/tm-signal-pagefault.c
index 5908bc6abe60..0b84c9208d62 100644
--- a/tools/testing/selftests/powerpc/tm/tm-signal-pagefault.c
+++ b/tools/testing/selftests/powerpc/tm/tm-signal-pagefault.c
@@ -226,6 +226,7 @@ int tm_signal_pagefault(void)
 	stack_t ss;
 
 	SKIP_IF(!have_htm());
+	SKIP_IF(htm_is_synthetic());
 	SKIP_IF(!have_userfaultfd());
 
 	setup_uf_mem();
diff --git a/tools/testing/selftests/powerpc/tm/tm-signal-sigreturn-nt.c b/tools/testing/selftests/powerpc/tm/tm-signal-sigreturn-nt.c
index 07c388147b75..06b801906f27 100644
--- a/tools/testing/selftests/powerpc/tm/tm-signal-sigreturn-nt.c
+++ b/tools/testing/selftests/powerpc/tm/tm-signal-sigreturn-nt.c
@@ -32,6 +32,7 @@ int tm_signal_sigreturn_nt(void)
 	struct sigaction trap_sa;
 
 	SKIP_IF(!have_htm());
+	SKIP_IF(htm_is_synthetic());
 
 	trap_sa.sa_flags = SA_SIGINFO;
 	trap_sa.sa_sigaction = trap_signal_handler;
diff --git a/tools/testing/selftests/powerpc/tm/tm-signal-stack.c b/tools/testing/selftests/powerpc/tm/tm-signal-stack.c
index cdcf8c5bbbc7..68807aac8dd3 100644
--- a/tools/testing/selftests/powerpc/tm/tm-signal-stack.c
+++ b/tools/testing/selftests/powerpc/tm/tm-signal-stack.c
@@ -35,6 +35,7 @@ int tm_signal_stack()
 	int pid;
 
 	SKIP_IF(!have_htm());
+	SKIP_IF(htm_is_synthetic());
 
 	pid = fork();
 	if (pid < 0)
diff --git a/tools/testing/selftests/powerpc/tm/tm-sigreturn.c b/tools/testing/selftests/powerpc/tm/tm-sigreturn.c
index 9a6017a1d769..ffe4e5515f33 100644
--- a/tools/testing/selftests/powerpc/tm/tm-sigreturn.c
+++ b/tools/testing/selftests/powerpc/tm/tm-sigreturn.c
@@ -55,6 +55,7 @@ int tm_sigreturn(void)
 	uint64_t ret = 0;
 
 	SKIP_IF(!have_htm());
+	SKIP_IF(htm_is_synthetic());
 	SKIP_IF(!is_ppc64le());
 
 	memset(&sa, 0, sizeof(sa));
diff --git a/tools/testing/selftests/powerpc/tm/tm-syscall.c b/tools/testing/selftests/powerpc/tm/tm-syscall.c
index becb8207b432..467a6b3134b2 100644
--- a/tools/testing/selftests/powerpc/tm/tm-syscall.c
+++ b/tools/testing/selftests/powerpc/tm/tm-syscall.c
@@ -25,7 +25,6 @@ extern int getppid_tm_suspended(void);
 unsigned retries = 0;
 
 #define TEST_DURATION 10 /* seconds */
-#define TM_RETRIES 100
 
 pid_t getppid_tm(bool suspend)
 {
@@ -67,6 +66,7 @@ int tm_syscall(void)
 	struct timeval end, now;
 
 	SKIP_IF(!have_htm_nosc());
+	SKIP_IF(htm_is_synthetic());
 
 	setbuf(stdout, NULL);
 
diff --git a/tools/testing/selftests/powerpc/tm/tm-tar.c b/tools/testing/selftests/powerpc/tm/tm-tar.c
index 03be8c47292b..f2a9137f3c1e 100644
--- a/tools/testing/selftests/powerpc/tm/tm-tar.c
+++ b/tools/testing/selftests/powerpc/tm/tm-tar.c
@@ -26,6 +26,7 @@ int test_tar(void)
 	int i;
 
 	SKIP_IF(!have_htm());
+	SKIP_IF(htm_is_synthetic());
 	SKIP_IF(!is_ppc64le());
 
 	for (i = 0; i < num_loops; i++)
diff --git a/tools/testing/selftests/powerpc/tm/tm-tmspr.c b/tools/testing/selftests/powerpc/tm/tm-tmspr.c
index 794d574db784..dd5ddffa28b7 100644
--- a/tools/testing/selftests/powerpc/tm/tm-tmspr.c
+++ b/tools/testing/selftests/powerpc/tm/tm-tmspr.c
@@ -96,6 +96,7 @@ int test_tmspr()
 	unsigned long	i;
 
 	SKIP_IF(!have_htm());
+	SKIP_IF(htm_is_synthetic());
 
 	/* To cause some context switching */
 	thread_num = 10 * sysconf(_SC_NPROCESSORS_ONLN);
diff --git a/tools/testing/selftests/powerpc/tm/tm-trap.c b/tools/testing/selftests/powerpc/tm/tm-trap.c
index 11521077f915..97cb74768e30 100644
--- a/tools/testing/selftests/powerpc/tm/tm-trap.c
+++ b/tools/testing/selftests/powerpc/tm/tm-trap.c
@@ -255,6 +255,7 @@ int tm_trap_test(void)
 	struct sigaction trap_sa;
 
 	SKIP_IF(!have_htm());
+	SKIP_IF(htm_is_synthetic());
 
 	trap_sa.sa_flags = SA_SIGINFO;
 	trap_sa.sa_sigaction = trap_signal_handler;
diff --git a/tools/testing/selftests/powerpc/tm/tm-unavailable.c b/tools/testing/selftests/powerpc/tm/tm-unavailable.c
index a1348a5f721a..6bf1b65b020d 100644
--- a/tools/testing/selftests/powerpc/tm/tm-unavailable.c
+++ b/tools/testing/selftests/powerpc/tm/tm-unavailable.c
@@ -344,6 +344,7 @@ int tm_unavailable_test(void)
 	cpu_set_t cpuset;
 
 	SKIP_IF(!have_htm());
+	SKIP_IF(htm_is_synthetic());
 
 	cpu = pick_online_cpu();
 	FAIL_IF(cpu < 0);
diff --git a/tools/testing/selftests/powerpc/tm/tm-vmx-unavail.c b/tools/testing/selftests/powerpc/tm/tm-vmx-unavail.c
index 9ef37a9836ac..34364ed2b6b7 100644
--- a/tools/testing/selftests/powerpc/tm/tm-vmx-unavail.c
+++ b/tools/testing/selftests/powerpc/tm/tm-vmx-unavail.c
@@ -91,6 +91,7 @@ int tm_vmx_unavail_test()
 	pthread_t *thread;
 
 	SKIP_IF(!have_htm());
+	SKIP_IF(htm_is_synthetic());
 
 	passed = 1;
 
diff --git a/tools/testing/selftests/powerpc/tm/tm-vmxcopy.c b/tools/testing/selftests/powerpc/tm/tm-vmxcopy.c
index c1e788a6df47..1640e7ead69b 100644
--- a/tools/testing/selftests/powerpc/tm/tm-vmxcopy.c
+++ b/tools/testing/selftests/powerpc/tm/tm-vmxcopy.c
@@ -46,6 +46,7 @@ int test_vmxcopy()
 	uint64_t aborted = 0;
 
 	SKIP_IF(!have_htm());
+	SKIP_IF(htm_is_synthetic());
 	SKIP_IF(!is_ppc64le());
 
 	fd = mkstemp(tmpfile);
diff --git a/tools/testing/selftests/powerpc/tm/tm.h b/tools/testing/selftests/powerpc/tm/tm.h
index c5a1e5c163fc..c03c6e778876 100644
--- a/tools/testing/selftests/powerpc/tm/tm.h
+++ b/tools/testing/selftests/powerpc/tm/tm.h
@@ -10,6 +10,9 @@
 #include <asm/tm.h>
 
 #include "utils.h"
+#include "reg.h"
+
+#define TM_RETRIES 100
 
 static inline bool have_htm(void)
 {
@@ -31,6 +34,39 @@ static inline bool have_htm_nosc(void)
 #endif
 }
 
+/*
+ * Transactional Memory was removed in ISA 3.1. A synthetic TM implementation
+ * is provided on P10 for threads running in P8/P9 compatibility  mode. The
+ * synthetic implementation immediately fails after tbegin. This failure sets
+ * Bit 7 (Failure Persistent) and Bit 15 (Implementation-specific).
+ */
+static inline bool htm_is_synthetic(void)
+{
+	int i;
+
+	/*
+	 * Per the ISA, the Failure Persistent bit may be incorrect. Try a few
+	 * times in case we got an Implementation-specific failure on a non ISA
+	 * v3.1 system. On these systems the Implementation-specific failure
+	 * should not be persistent.
+	 */
+	for (i = 0; i < TM_RETRIES; i++) {
+		asm volatile(
+		"tbegin.;"
+		"beq 1f;"
+		"tend.;"
+		"1:"
+		:
+		:
+		: "memory");
+
+		if ((__builtin_get_texasr() & (TEXASR_FP | TEXASR_IC)) !=
+		    (TEXASR_FP | TEXASR_IC))
+			break;
+	}
+	return i == TM_RETRIES;
+}
+
 static inline long failure_code(void)
 {
 	return __builtin_get_texasru() >> 24;