path: root/kernel-arm64.patch

 .../devicetree/bindings/pci/xgene-pci.txt          |  52 ++
 MAINTAINERS                                        |   7 +
 arch/arm64/Kconfig                                 |  19 +-
 arch/arm64/boot/dts/apm-mustang.dts                |   8 +
 arch/arm64/boot/dts/apm-storm.dtsi                 | 180 ++++-
 arch/arm64/include/asm/Kbuild                      |   1 +
 arch/arm64/include/asm/elf.h                       |   3 +-
 arch/arm64/include/asm/io.h                        |   3 +-
 arch/arm64/include/asm/pci.h                       |  49 ++
 arch/arm64/kernel/Makefile                         |   1 +
 arch/arm64/kernel/efi-stub.c                       |  16 +-
 arch/arm64/kernel/efi.c                            |  11 +
 arch/arm64/kernel/head.S                           |   6 +-
 arch/arm64/kernel/pci.c                            |  38 ++
 arch/arm64/kernel/process.c                        |   6 +
 arch/arm64/kernel/smp_spin_table.c                 |  21 +-
 drivers/ata/ahci_xgene.c                           |   3 +-
 drivers/irqchip/irq-gic.c                          |  32 +-
 drivers/of/address.c                               | 108 +++
 drivers/of/of_pci.c                                | 136 ++++
 drivers/pci/host-bridge.c                          |  18 +-
 drivers/pci/host/Kconfig                           |  10 +
 drivers/pci/host/Makefile                          |   1 +
 drivers/pci/host/pci-xgene.c                       | 725 +++++++++++++++++++++
 drivers/pci/pci.c                                  |  37 ++
 drivers/pci/probe.c                                |  68 +-
 include/asm-generic/io.h                           |   2 +-
 include/linux/of_address.h                         |  14 +-
 include/linux/of_pci.h                             |  10 +
 include/linux/pci.h                                |  15 +
 tools/perf/arch/arm64/include/perf_regs.h          |   2 +
 31 files changed, 1533 insertions(+), 69 deletions(-)

diff --git a/Documentation/devicetree/bindings/pci/xgene-pci.txt b/Documentation/devicetree/bindings/pci/xgene-pci.txt
new file mode 100644
index 0000000..e19fdb8
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/xgene-pci.txt
@@ -0,0 +1,52 @@
+* AppliedMicro X-Gene PCIe interface
+
+Required properties:
+- device_type: set to "pci"
+- compatible: should contain "apm,xgene-pcie" to identify the core.
+- reg: A list of physical base address and length for each set of controller
+       registers. Must contain an entry for each entry in the reg-names
+       property.
+- reg-names: Must include the following entries:
+  "csr": controller configuration registers.
+  "cfg": pcie configuration space registers.
+- #address-cells: set to <3>
+- #size-cells: set to <2>
+- ranges: ranges for the outbound memory, I/O regions.
+- dma-ranges: ranges for the inbound memory regions.
+- #interrupt-cells: set to <1>
+- interrupt-map-mask and interrupt-map: standard PCI properties
+	to define the mapping of the PCIe interface to interrupt
+	numbers.
+- clocks: from common clock binding: handle to pci clock.
+
+Optional properties:
+- status: Either "ok" or "disabled".
+
+Example:
+
+SoC specific DT Entry:
+	pcie0: pcie@1f2b0000 {
+		status = "disabled";
+		device_type = "pci";
+		compatible = "apm,xgene-storm-pcie", "apm,xgene-pcie";
+		#interrupt-cells = <1>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		reg = < 0x00 0x1f2b0000 0x0 0x00010000   /* Controller registers */
+			0xe0 0xd0000000 0x0 0x00200000>; /* PCI config space */
+		reg-names = "csr", "cfg";
+		ranges = <0x01000000 0x00 0x00000000 0xe0 0x00000000 0x00 0x00010000   /* io */
+			  0x02000000 0x00 0x10000000 0xe0 0x10000000 0x00 0x80000000>; /* mem */
+		dma-ranges = <0x42000000 0x40 0x00000000 0x40 0x00000000 0x40 0x00000000>;
+		interrupt-map-mask = <0x0 0x0 0x0 0x7>;
+		interrupt-map = <0x0 0x0 0x0 0x1 &gic 0x0 0xc2 0x1
+				 0x0 0x0 0x0 0x2 &gic 0x0 0xc3 0x1
+				 0x0 0x0 0x0 0x3 &gic 0x0 0xc4 0x1
+				 0x0 0x0 0x0 0x4 &gic 0x0 0xc5 0x1>;
+		clocks = <&pcie0clk 0>;
+	};
+
+Board specific DT Entry:
+	&pcie0 {
+		status = "ok";
+	};
diff --git a/MAINTAINERS b/MAINTAINERS
index 2f85f55..8980971 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6894,6 +6894,13 @@ L:	linux-pci@vger.kernel.org
 S:	Maintained
 F:	drivers/pci/host/*spear*
 
+PCI DRIVER FOR APPLIEDMICRO XGENE
+M:	Tanmay Inamdar <tinamdar@apm.com>
+L:	linux-pci@vger.kernel.org
+L:	linux-arm-kernel@lists.infradead.org
+S:	Maintained
+F:	drivers/pci/host/pci-xgene.c
+
 PCMCIA SUBSYSTEM
 P:	Linux PCMCIA Team
 L:	linux-pcmcia@lists.infradead.org
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index fd4e81a..e8559bb 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -81,7 +81,7 @@ config MMU
 	def_bool y
 
 config NO_IOPORT_MAP
-	def_bool y
+	def_bool y if !PCI
 
 config STACKTRACE_SUPPORT
 	def_bool y
@@ -156,6 +156,23 @@ menu "Bus support"
 config ARM_AMBA
 	bool
 
+config PCI
+	bool "PCI support"
+	help
+	  This feature enables support for PCIe bus system. If you say Y
+	  here, the kernel will include drivers and infrastructure code
+	  to support PCIe bus devices.
+
+config PCI_DOMAINS
+	def_bool PCI
+
+config PCI_SYSCALL
+	def_bool PCI
+
+source "drivers/pci/Kconfig"
+source "drivers/pci/pcie/Kconfig"
+source "drivers/pci/hotplug/Kconfig"
+
 endmenu
 
 menu "Kernel Features"
diff --git a/arch/arm64/boot/dts/apm-mustang.dts b/arch/arm64/boot/dts/apm-mustang.dts
index b2f5622..0cb67fc 100644
--- a/arch/arm64/boot/dts/apm-mustang.dts
+++ b/arch/arm64/boot/dts/apm-mustang.dts
@@ -32,3 +32,11 @@
 &menet {
 	status = "ok";
 };
+
+&pcie0clk {
+	status = "ok";
+};
+
+&pcie0 {
+	status = "ok";
+};
diff --git a/arch/arm64/boot/dts/apm-storm.dtsi b/arch/arm64/boot/dts/apm-storm.dtsi
index c0aceef..fb2ee54 100644
--- a/arch/arm64/boot/dts/apm-storm.dtsi
+++ b/arch/arm64/boot/dts/apm-storm.dtsi
@@ -24,56 +24,56 @@
 			compatible = "apm,potenza", "arm,armv8";
 			reg = <0x0 0x000>;
 			enable-method = "spin-table";
-			cpu-release-addr = <0x1 0x0000fff8>;
+			cpu-release-addr = <0x40 0x0000f000>;
 		};
 		cpu@001 {
 			device_type = "cpu";
 			compatible = "apm,potenza", "arm,armv8";
 			reg = <0x0 0x001>;
 			enable-method = "spin-table";
-			cpu-release-addr = <0x1 0x0000fff8>;
+			cpu-release-addr = <0x40 0x0000f000>;
 		};
 		cpu@100 {
 			device_type = "cpu";
 			compatible = "apm,potenza", "arm,armv8";
 			reg = <0x0 0x100>;
 			enable-method = "spin-table";
-			cpu-release-addr = <0x1 0x0000fff8>;
+			cpu-release-addr = <0x40 0x0000f000>;
 		};
 		cpu@101 {
 			device_type = "cpu";
 			compatible = "apm,potenza", "arm,armv8";
 			reg = <0x0 0x101>;
 			enable-method = "spin-table";
-			cpu-release-addr = <0x1 0x0000fff8>;
+			cpu-release-addr = <0x40 0x0000f000>;
 		};
 		cpu@200 {
 			device_type = "cpu";
 			compatible = "apm,potenza", "arm,armv8";
 			reg = <0x0 0x200>;
 			enable-method = "spin-table";
-			cpu-release-addr = <0x1 0x0000fff8>;
+			cpu-release-addr = <0x40 0x0000f000>;
 		};
 		cpu@201 {
 			device_type = "cpu";
 			compatible = "apm,potenza", "arm,armv8";
 			reg = <0x0 0x201>;
 			enable-method = "spin-table";
-			cpu-release-addr = <0x1 0x0000fff8>;
+			cpu-release-addr = <0x40 0x0000f000>;
 		};
 		cpu@300 {
 			device_type = "cpu";
 			compatible = "apm,potenza", "arm,armv8";
 			reg = <0x0 0x300>;
 			enable-method = "spin-table";
-			cpu-release-addr = <0x1 0x0000fff8>;
+			cpu-release-addr = <0x40 0x0000f000>;
 		};
 		cpu@301 {
 			device_type = "cpu";
 			compatible = "apm,potenza", "arm,armv8";
 			reg = <0x0 0x301>;
 			enable-method = "spin-table";
-			cpu-release-addr = <0x1 0x0000fff8>;
+			cpu-release-addr = <0x40 0x0000f000>;
 		};
 	};
 
@@ -97,6 +97,11 @@
 		clock-frequency = <50000000>;
 	};
 
+	pmu {
+		compatible = "arm,armv8-pmuv3";
+		interrupts = <1 12 0xff04>;
+	};
+
 	soc {
 		compatible = "simple-bus";
 		#address-cells = <2>;
@@ -269,6 +274,161 @@
 				enable-mask = <0x2>;
 				clock-output-names = "rtcclk";
 			};
+
+			pcie0clk: pcie0clk@1f2bc000 {
+				status = "disabled";
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&socplldiv2 0>;
+				reg = <0x0 0x1f2bc000 0x0 0x1000>;
+				reg-names = "csr-reg";
+				clock-output-names = "pcie0clk";
+			};
+
+			pcie1clk: pcie1clk@1f2cc000 {
+				status = "disabled";
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&socplldiv2 0>;
+				reg = <0x0 0x1f2cc000 0x0 0x1000>;
+				reg-names = "csr-reg";
+				clock-output-names = "pcie1clk";
+			};
+
+			pcie2clk: pcie2clk@1f2dc000 {
+				status = "disabled";
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&socplldiv2 0>;
+				reg = <0x0 0x1f2dc000 0x0 0x1000>;
+				reg-names = "csr-reg";
+				clock-output-names = "pcie2clk";
+			};
+
+			pcie3clk: pcie3clk@1f50c000 {
+				status = "disabled";
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&socplldiv2 0>;
+				reg = <0x0 0x1f50c000 0x0 0x1000>;
+				reg-names = "csr-reg";
+				clock-output-names = "pcie3clk";
+			};
+
+			pcie4clk: pcie4clk@1f51c000 {
+				status = "disabled";
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&socplldiv2 0>;
+				reg = <0x0 0x1f51c000 0x0 0x1000>;
+				reg-names = "csr-reg";
+				clock-output-names = "pcie4clk";
+			};
+		};
+
+		pcie0: pcie@1f2b0000 {
+			status = "disabled";
+			device_type = "pci";
+			compatible = "apm,xgene-storm-pcie", "apm,xgene-pcie";
+			#interrupt-cells = <1>;
+			#size-cells = <2>;
+			#address-cells = <3>;
+			reg = < 0x00 0x1f2b0000 0x0 0x00010000   /* Controller registers */
+				0xe0 0xd0000000 0x0 0x00200000>; /* PCI config space */
+			reg-names = "csr", "cfg";
+			ranges = <0x01000000 0x00 0x00000000 0xe0 0x00000000 0x00 0x00010000   /* io */
+				  0x02000000 0x00 0x10000000 0xe0 0x10000000 0x00 0x80000000>; /* mem */
+			dma-ranges = <0x42000000 0x40 0x00000000 0x40 0x00000000 0x40 0x00000000>;
+			interrupt-map-mask = <0x0 0x0 0x0 0x7>;
+			interrupt-map = <0x0 0x0 0x0 0x1 &gic 0x0 0xc2 0x1
+					 0x0 0x0 0x0 0x2 &gic 0x0 0xc3 0x1
+					 0x0 0x0 0x0 0x3 &gic 0x0 0xc4 0x1
+					 0x0 0x0 0x0 0x4 &gic 0x0 0xc5 0x1>;
+			clocks = <&pcie0clk 0>;
+		};
+
+		pcie1: pcie@1f2c0000 {
+			status = "disabled";
+			device_type = "pci";
+			compatible = "apm,xgene-storm-pcie", "apm,xgene-pcie";
+			#interrupt-cells = <1>;
+			#size-cells = <2>;
+			#address-cells = <3>;
+			reg = < 0x00 0x1f2c0000 0x0 0x00010000   /* Controller registers */
+				0xd0 0xd0000000 0x0 0x00200000>; /* PCI config space */
+			reg-names = "csr", "cfg";
+			ranges = <0x01000000 0x0 0x00000000 0xd0 0x00000000 0x00 0x00010000   /* io  */
+				  0x02000000 0x0 0x10000000 0xd0 0x10000000 0x00 0x80000000>; /* mem */
+			dma-ranges = <0x42000000 0x40 0x00000000 0x40 0x00000000 0x40 0x00000000>;
+			interrupt-map-mask = <0x0 0x0 0x0 0x7>;
+			interrupt-map = <0x0 0x0 0x0 0x1 &gic 0x0 0xc8 0x1
+					 0x0 0x0 0x0 0x2 &gic 0x0 0xc9 0x1
+					 0x0 0x0 0x0 0x3 &gic 0x0 0xca 0x1
+					 0x0 0x0 0x0 0x4 &gic 0x0 0xcb 0x1>;
+			clocks = <&pcie1clk 0>;
+		};
+
+		pcie2: pcie@1f2d0000 {
+			status = "disabled";
+			device_type = "pci";
+			compatible = "apm,xgene-storm-pcie", "apm,xgene-pcie";
+			#interrupt-cells = <1>;
+			#size-cells = <2>;
+			#address-cells = <3>;
+			reg =  < 0x00 0x1f2d0000 0x0 0x00010000   /* Controller registers */
+				 0x90 0xd0000000 0x0 0x00200000>; /* PCI config space */
+			reg-names = "csr", "cfg";
+			ranges = <0x01000000 0x0 0x00000000 0x90 0x00000000 0x0 0x00010000   /* io  */
+				  0x02000000 0x0 0x10000000 0x90 0x10000000 0x0 0x80000000>; /* mem */
+			dma-ranges = <0x42000000 0x40 0x00000000 0x40 0x00000000 0x40 0x00000000>;
+			interrupt-map-mask = <0x0 0x0 0x0 0x7>;
+			interrupt-map = <0x0 0x0 0x0 0x1 &gic 0x0 0xce 0x1
+					 0x0 0x0 0x0 0x2 &gic 0x0 0xcf 0x1
+					 0x0 0x0 0x0 0x3 &gic 0x0 0xd0 0x1
+					 0x0 0x0 0x0 0x4 &gic 0x0 0xd1 0x1>;
+			clocks = <&pcie2clk 0>;
+		};
+
+		pcie3: pcie@1f500000 {
+			status = "disabled";
+			device_type = "pci";
+			compatible = "apm,xgene-storm-pcie", "apm,xgene-pcie";
+			#interrupt-cells = <1>;
+			#size-cells = <2>;
+			#address-cells = <3>;
+			reg = < 0x00 0x1f500000 0x0 0x00010000   /* Controller registers */
+				0xa0 0xd0000000 0x0 0x00200000>; /* PCI config space */
+			reg-names = "csr", "cfg";
+			ranges = <0x01000000 0x0 0x00000000 0xa0 0x00000000 0x0 0x00010000  /* io */
+				  0x02000000 0x0 0x10000000 0xa0 0x10000000 0x0 0x80000000>; /* mem  */
+			dma-ranges = <0x42000000 0x40 0x00000000 0x40 0x00000000 0x40 0x00000000>;
+			interrupt-map-mask = <0x0 0x0 0x0 0x7>;
+			interrupt-map = <0x0 0x0 0x0 0x1 &gic 0x0 0xd4 0x1
+					 0x0 0x0 0x0 0x2 &gic 0x0 0xd5 0x1
+					 0x0 0x0 0x0 0x3 &gic 0x0 0xd6 0x1
+					 0x0 0x0 0x0 0x4 &gic 0x0 0xd7 0x1>;
+			clocks = <&pcie3clk 0>;
+		};
+
+		pcie4: pcie@1f510000 {
+			status = "disabled";
+			device_type = "pci";
+			compatible = "apm,xgene-storm-pcie", "apm,xgene-pcie";
+			#interrupt-cells = <1>;
+			#size-cells = <2>;
+			#address-cells = <3>;
+			reg = < 0x00 0x1f510000 0x0 0x00010000   /* Controller registers */
+				0xc0 0xd0000000 0x0 0x00200000>; /* PCI config space */
+			reg-names = "csr", "cfg";
+			ranges = <0x01000000 0x0 0x00000000 0xc0 0x00000000 0x0 0x00010000   /* io  */
+				  0x02000000 0x0 0x10000000 0xc0 0x10000000 0x0 0x80000000>; /* mem */
+			dma-ranges = <0x42000000 0x40 0x00000000 0x40 0x00000000 0x40 0x00000000>;
+			interrupt-map-mask = <0x0 0x0 0x0 0x7>;
+			interrupt-map = <0x0 0x0 0x0 0x1 &gic 0x0 0xda 0x1
+					 0x0 0x0 0x0 0x2 &gic 0x0 0xdb 0x1
+					 0x0 0x0 0x0 0x3 &gic 0x0 0xdc 0x1
+					 0x0 0x0 0x0 0x4 &gic 0x0 0xdd 0x1>;
+			clocks = <&pcie4clk 0>;
 		};
 
 		serial0: serial@1c020000 {
@@ -277,7 +437,7 @@
 			compatible = "ns16550a";
 			reg = <0 0x1c020000 0x0 0x1000>;
 			reg-shift = <2>;
-			clock-frequency = <10000000>; /* Updated by bootloader */
+			clock-frequency = <50000000>; /* Updated by bootloader */
 			interrupt-parent = <&gic>;
 			interrupts = <0x0 0x4c 0x4>;
 		};
@@ -407,7 +567,7 @@
 			interrupts = <0x0 0x3c 0x4>;
 			dma-coherent;
 			clocks = <&menetclk 0>;
-			local-mac-address = [00 01 73 00 00 01];
+			local-mac-address = [00 00 00 00 00 00];
 			phy-connection-type = "rgmii";
 			phy-handle = <&menetphy>;
 			mdio {
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 0b3fcf8..07cb417 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -29,6 +29,7 @@ generic-y += mman.h
 generic-y += msgbuf.h
 generic-y += mutex.h
 generic-y += pci.h
+generic-y += pci-bridge.h
 generic-y += poll.h
 generic-y += preempt.h
 generic-y += resource.h
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index 01d3aab..8186df6 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -114,7 +114,8 @@ typedef struct user_fpsimd_state elf_fpregset_t;
  */
 #define elf_check_arch(x)		((x)->e_machine == EM_AARCH64)
 
-#define elf_read_implies_exec(ex,stk)	(stk != EXSTACK_DISABLE_X)
+#define elf_read_implies_exec(ex,stk)	(test_thread_flag(TIF_32BIT) \
+					 ? (stk == EXSTACK_ENABLE_X) : 0)
 
 #define CORE_DUMP_USE_REGSET
 #define ELF_EXEC_PAGESIZE	PAGE_SIZE
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index e0ecdcf..dc34039 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -121,7 +121,8 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
 /*
  *  I/O port access primitives.
  */
-#define IO_SPACE_LIMIT		0xffff
+#define arch_has_dev_port()	(1)
+#define IO_SPACE_LIMIT		0x1ffffff
 #define PCI_IOBASE		((void __iomem *)(MODULES_VADDR - SZ_32M))
 
 static inline u8 inb(unsigned long addr)
diff --git a/arch/arm64/include/asm/pci.h b/arch/arm64/include/asm/pci.h
new file mode 100644
index 0000000..3f7856e
--- /dev/null
+++ b/arch/arm64/include/asm/pci.h
@@ -0,0 +1,49 @@
+#ifndef __ASM_PCI_H
+#define __ASM_PCI_H
+#ifdef __KERNEL__
+
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/dma-mapping.h>
+
+#include <asm/io.h>
+#include <asm-generic/pci-bridge.h>
+#include <asm-generic/pci-dma-compat.h>
+
+#define PCIBIOS_MIN_IO		0x1000
+#define PCIBIOS_MIN_MEM		0
+
+struct pci_host_bridge *find_pci_host_bridge(struct pci_bus *bus);
+
+/*
+ * Set to 1 if the kernel should re-assign all PCI bus numbers
+ */
+#define pcibios_assign_all_busses() \
+	(pci_has_flag(PCI_REASSIGN_ALL_BUS))
+
+/*
+ * PCI address space differs from physical memory address space
+ */
+#define PCI_DMA_BUS_IS_PHYS	(0)
+
+extern int isa_dma_bridge_buggy;
+
+#ifdef CONFIG_PCI
+static inline int pci_domain_nr(struct pci_bus *bus)
+{
+	struct pci_host_bridge *bridge = find_pci_host_bridge(bus);
+
+	if (bridge)
+		return bridge->domain_nr;
+
+	return 0;
+}
+
+static inline int pci_proc_domain(struct pci_bus *bus)
+{
+	return 1;
+}
+#endif  /* CONFIG_PCI */
+
+#endif  /* __KERNEL__ */
+#endif  /* __ASM_PCI_H */
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index df7ef87..1ed5a06 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -29,6 +29,7 @@ arm64-obj-$(CONFIG_ARM64_CPU_SUSPEND)	+= sleep.o suspend.o
 arm64-obj-$(CONFIG_JUMP_LABEL)		+= jump_label.o
 arm64-obj-$(CONFIG_KGDB)		+= kgdb.o
 arm64-obj-$(CONFIG_EFI)			+= efi.o efi-stub.o efi-entry.o
+arm64-obj-$(CONFIG_PCI)			+= pci.o
 
 obj-y					+= $(arm64-obj-y) vdso/
 obj-m					+= $(arm64-obj-m)
diff --git a/arch/arm64/kernel/efi-stub.c b/arch/arm64/kernel/efi-stub.c
index 1317fef..d27dd98 100644
--- a/arch/arm64/kernel/efi-stub.c
+++ b/arch/arm64/kernel/efi-stub.c
@@ -28,20 +28,16 @@ efi_status_t handle_kernel_image(efi_system_table_t *sys_table,
 	kernel_size = _edata - _text;
 	if (*image_addr != (dram_base + TEXT_OFFSET)) {
 		kernel_memsize = kernel_size + (_end - _edata);
-		status = efi_relocate_kernel(sys_table, image_addr,
-					     kernel_size, kernel_memsize,
-					     dram_base + TEXT_OFFSET,
-					     PAGE_SIZE);
+		status = efi_low_alloc(sys_table, kernel_memsize + TEXT_OFFSET,
+				       SZ_2M, reserve_addr);
 		if (status != EFI_SUCCESS) {
 			pr_efi_err(sys_table, "Failed to relocate kernel\n");
 			return status;
 		}
-		if (*image_addr != (dram_base + TEXT_OFFSET)) {
-			pr_efi_err(sys_table, "Failed to alloc kernel memory\n");
-			efi_free(sys_table, kernel_memsize, *image_addr);
-			return EFI_LOAD_ERROR;
-		}
-		*image_size = kernel_memsize;
+		memcpy((void *)*reserve_addr + TEXT_OFFSET, (void *)*image_addr,
+		       kernel_size);
+		*image_addr = *reserve_addr + TEXT_OFFSET;
+		*reserve_size = kernel_memsize + TEXT_OFFSET;
 	}
 
 
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index e72f310..72ee260 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -475,3 +475,14 @@ err_unmap:
 	return -1;
 }
 early_initcall(arm64_enter_virtual_mode);
+
+/*
+ * If nothing else is handling pm_power_off, use EFI
+ *
+ * This is called from a late_initcall after other mechanisms
+ * have had a chance to register a handler.
+ */
+bool efi_poweroff_required(void)
+{
+	return pm_power_off == NULL;
+}
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 144f105..b6ca95a 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -151,7 +151,7 @@ optional_header:
 	.short	0x20b				// PE32+ format
 	.byte	0x02				// MajorLinkerVersion
 	.byte	0x14				// MinorLinkerVersion
-	.long	_edata - stext			// SizeOfCode
+	.long	_end - stext			// SizeOfCode
 	.long	0				// SizeOfInitializedData
 	.long	0				// SizeOfUninitializedData
 	.long	efi_stub_entry - efi_head	// AddressOfEntryPoint
@@ -169,7 +169,7 @@ extra_header_fields:
 	.short	0				// MinorSubsystemVersion
 	.long	0				// Win32VersionValue
 
-	.long	_edata - efi_head		// SizeOfImage
+	.long	_end - efi_head			// SizeOfImage
 
 	// Everything before the kernel image is considered part of the header
 	.long	stext - efi_head		// SizeOfHeaders
@@ -216,7 +216,7 @@ section_table:
 	.byte	0
 	.byte	0
 	.byte	0        		// end of 0 padding of section name
-	.long	_edata - stext		// VirtualSize
+	.long	_end - stext		// VirtualSize
 	.long	stext - efi_head	// VirtualAddress
 	.long	_edata - stext		// SizeOfRawData
 	.long	stext - efi_head	// PointerToRawData
diff --git a/arch/arm64/kernel/pci.c b/arch/arm64/kernel/pci.c
new file mode 100644
index 0000000..955d6d1
--- /dev/null
+++ b/arch/arm64/kernel/pci.c
@@ -0,0 +1,38 @@
+/*
+ * Code borrowed from powerpc/kernel/pci-common.c
+ *
+ * Copyright (C) 2003 Anton Blanchard <anton@au.ibm.com>, IBM
+ * Copyright (C) 2014 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/of_pci.h>
+#include <linux/of_platform.h>
+#include <linux/slab.h>
+
+#include <asm/pci-bridge.h>
+
+/*
+ * Called after each bus is probed, but before its children are examined
+ */
+void pcibios_fixup_bus(struct pci_bus *bus)
+{
+	/* nothing to do, expected to be removed in the future */
+}
+
+/*
+ * We don't have to worry about legacy ISA devices, so nothing to do here
+ */
+resource_size_t pcibios_align_resource(void *data, const struct resource *res,
+				resource_size_t size, resource_size_t align)
+{
+	return res->start;
+}
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 1309d64..8ff5208 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -43,6 +43,7 @@
 #include <linux/hw_breakpoint.h>
 #include <linux/personality.h>
 #include <linux/notifier.h>
+#include <linux/efi.h>
 
 #include <asm/compat.h>
 #include <asm/cacheflush.h>
@@ -182,6 +183,11 @@ void machine_restart(char *cmd)
 		arm_pm_restart(reboot_mode, cmd);
 
 	/*
+	 * If all else fails, try EFI
+	 */
+	efi_reboot(reboot_mode, cmd);
+
+	/*
 	 * Whoops - the architecture was unable to reboot.
 	 */
 	printk("Reboot failed -- System halted\n");
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index 0347d38..70181c1 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -20,6 +20,7 @@
 #include <linux/init.h>
 #include <linux/of.h>
 #include <linux/smp.h>
+#include <linux/types.h>
 
 #include <asm/cacheflush.h>
 #include <asm/cpu_ops.h>
@@ -65,12 +66,21 @@ static int smp_spin_table_cpu_init(struct device_node *dn, unsigned int cpu)
 
 static int smp_spin_table_cpu_prepare(unsigned int cpu)
 {
-	void **release_addr;
+	__le64 __iomem *release_addr;
 
 	if (!cpu_release_addr[cpu])
 		return -ENODEV;
 
-	release_addr = __va(cpu_release_addr[cpu]);
+	/*
+	 * The cpu-release-addr may or may not be inside the linear mapping.
+	 * As ioremap_cache will either give us a new mapping or reuse the
+	 * existing linear mapping, we can use it to cover both cases. In
+	 * either case the memory will be MT_NORMAL.
+	 */
+	release_addr = ioremap_cache(cpu_release_addr[cpu],
+				     sizeof(*release_addr));
+	if (!release_addr)
+		return -ENOMEM;
 
 	/*
 	 * We write the release address as LE regardless of the native
@@ -79,15 +89,16 @@ static int smp_spin_table_cpu_prepare(unsigned int cpu)
 	 * boot-loader's endianess before jumping. This is mandated by
 	 * the boot protocol.
 	 */
-	release_addr[0] = (void *) cpu_to_le64(__pa(secondary_holding_pen));
-
-	__flush_dcache_area(release_addr, sizeof(release_addr[0]));
+	writeq_relaxed(__pa(secondary_holding_pen), release_addr);
+	__flush_dcache_area(release_addr, sizeof(*release_addr));
 
 	/*
 	 * Send an event to wake up the secondary CPU.
 	 */
 	sev();
 
+	iounmap(release_addr);
+
 	return 0;
 }
 
diff --git a/drivers/ata/ahci_xgene.c b/drivers/ata/ahci_xgene.c
index bc28111..00e5a0c 100644
--- a/drivers/ata/ahci_xgene.c
+++ b/drivers/ata/ahci_xgene.c
@@ -134,7 +134,8 @@ static unsigned int xgene_ahci_qc_issue(struct ata_queued_cmd *qc)
 	struct xgene_ahci_context *ctx = hpriv->plat_data;
 	int rc = 0;
 
-	if (unlikely(ctx->last_cmd[ap->port_no] == ATA_CMD_ID_ATA))
+	if (unlikely(ctx->last_cmd[ap->port_no] == ATA_CMD_ID_ATA ||
+		     ctx->last_cmd[ap->port_no] == ATA_CMD_SMART))
 		xgene_ahci_restart_engine(ap);
 
 	rc = ahci_qc_issue(qc);
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 4b959e6..c36c7ab55 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -381,6 +381,7 @@ static void gic_cpu_init(struct gic_chip_data *gic)
 	void __iomem *dist_base = gic_data_dist_base(gic);
 	void __iomem *base = gic_data_cpu_base(gic);
 	unsigned int cpu_mask, cpu = smp_processor_id();
+	unsigned int ctrl_mask;
 	int i;
 
 	/*
@@ -401,13 +402,29 @@ static void gic_cpu_init(struct gic_chip_data *gic)
 	gic_cpu_config(dist_base, NULL);
 
 	writel_relaxed(0xf0, base + GIC_CPU_PRIMASK);
-	writel_relaxed(1, base + GIC_CPU_CTRL);
+
+	ctrl_mask = readl(base + GIC_CPU_CTRL);
+
+	/* Mask out the gic v2 bypass bits */
+	ctrl_mask &= 0x1e0;
+
+	/* Enable group 0 */
+	ctrl_mask |= 0x1;
+	writel_relaxed(ctrl_mask, base + GIC_CPU_CTRL);
 }
 
 void gic_cpu_if_down(void)
 {
+	unsigned int ctrl_mask;
 	void __iomem *cpu_base = gic_data_cpu_base(&gic_data[0]);
-	writel_relaxed(0, cpu_base + GIC_CPU_CTRL);
+
+	ctrl_mask = readl(cpu_base + GIC_CPU_CTRL);
+	/*
+	 * Disable grp enable bit, leave the bypass bits alone as changing
+	 * them could leave the system unstable
+	 */
+	ctrl_mask &= 0x1e0;
+	writel_relaxed(ctrl_mask, cpu_base + GIC_CPU_CTRL);
 }
 
 #ifdef CONFIG_CPU_PM
@@ -518,6 +535,7 @@ static void gic_cpu_restore(unsigned int gic_nr)
 {
 	int i;
 	u32 *ptr;
+	unsigned int ctrl_mask;
 	void __iomem *dist_base;
 	void __iomem *cpu_base;
 
@@ -542,7 +560,15 @@ static void gic_cpu_restore(unsigned int gic_nr)
 		writel_relaxed(0xa0a0a0a0, dist_base + GIC_DIST_PRI + i * 4);
 
 	writel_relaxed(0xf0, cpu_base + GIC_CPU_PRIMASK);
-	writel_relaxed(1, cpu_base + GIC_CPU_CTRL);
+
+	ctrl_mask = readl(cpu_base + GIC_CPU_CTRL);
+
+	/* Mask out the gic v2 bypass bits */
+	ctrl_mask &= 0x1e0;
+
+	/* Enable group 0 */
+	ctrl_mask |= 0x1;
+	writel_relaxed(ctrl_mask, cpu_base + GIC_CPU_CTRL);
 }
 
 static int gic_notifier(struct notifier_block *self, unsigned long cmd,	void *v)
diff --git a/drivers/of/address.c b/drivers/of/address.c
index e371825..5eaadae 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -5,6 +5,7 @@
 #include <linux/module.h>
 #include <linux/of_address.h>
 #include <linux/pci_regs.h>
+#include <linux/slab.h>
 #include <linux/string.h>
 
 /* Max address size we deal with */
@@ -601,12 +602,72 @@ const __be32 *of_get_address(struct device_node *dev, int index, u64 *size,
 }
 EXPORT_SYMBOL(of_get_address);
 
+struct io_range {
+	struct list_head list;
+	phys_addr_t start;
+	resource_size_t size;
+};
+
+static LIST_HEAD(io_range_list);
+
+/*
+ * Record the PCI IO range (expressed as CPU physical address + size).
+ * Return a negative value if an error has occured, zero otherwise
+ */
+int __weak pci_register_io_range(phys_addr_t addr, resource_size_t size)
+{
+#ifdef PCI_IOBASE
+	struct io_range *res;
+	resource_size_t allocated_size = 0;
+
+	/* check if the range hasn't been previously recorded */
+	list_for_each_entry(res, &io_range_list, list) {
+		if (addr >= res->start && addr + size <= res->start + size)
+			return 0;
+		allocated_size += res->size;
+	}
+
+	/* range not registed yet, check for available space */
+	if (allocated_size + size - 1 > IO_SPACE_LIMIT)
+		return -E2BIG;
+
+	/* add the range to the list */
+	res = kzalloc(sizeof(*res), GFP_KERNEL);
+	if (!res)
+		return -ENOMEM;
+
+	res->start = addr;
+	res->size = size;
+
+	list_add_tail(&res->list, &io_range_list);
+
+	return 0;
+#else
+	return -EINVAL;
+#endif
+}
+
 unsigned long __weak pci_address_to_pio(phys_addr_t address)
 {
+#ifdef PCI_IOBASE
+	struct io_range *res;
+	resource_size_t offset = 0;
+
+	list_for_each_entry(res, &io_range_list, list) {
+		if (address >= res->start &&
+			address < res->start + res->size) {
+			return res->start - address + offset;
+		}
+		offset += res->size;
+	}
+
+	return (unsigned long)-1;
+#else
 	if (address > IO_SPACE_LIMIT)
 		return (unsigned long)-1;
 
 	return (unsigned long) address;
+#endif
 }
 
 static int __of_address_to_resource(struct device_node *dev,
@@ -847,3 +908,50 @@ bool of_dma_is_coherent(struct device_node *np)
 	return false;
 }
 EXPORT_SYMBOL_GPL(of_dma_is_coherent);
+
+/*
+ * of_pci_range_to_resource - Create a resource from an of_pci_range
+ * @range:	the PCI range that describes the resource
+ * @np:		device node where the range belongs to
+ * @res:	pointer to a valid resource that will be updated to
+ *              reflect the values contained in the range.
+ *
+ * Returns EINVAL if the range cannot be converted to resource.
+ *
+ * Note that if the range is an IO range, the resource will be converted
+ * using pci_address_to_pio() which can fail if it is called too early or
+ * if the range cannot be matched to any host bridge IO space (our case here).
+ * To guard against that we try to register the IO range first.
+ * If that fails we know that pci_address_to_pio() will do too.
+ */
+int of_pci_range_to_resource(struct of_pci_range *range,
+	struct device_node *np, struct resource *res)
+{
+	int err;
+	res->flags = range->flags;
+	res->parent = res->child = res->sibling = NULL;
+	res->name = np->full_name;
+
+	if (res->flags & IORESOURCE_IO) {
+		unsigned long port = -1;
+		err = pci_register_io_range(range->cpu_addr, range->size);
+		if (err)
+			goto invalid_range;
+		port = pci_address_to_pio(range->cpu_addr);
+		if (port == (unsigned long)-1) {
+			err = -EINVAL;
+			goto invalid_range;
+		}
+		res->start = port;
+	} else {
+		res->start = range->cpu_addr;
+	}
+	res->end = res->start + range->size - 1;
+	return 0;
+
+invalid_range:
+	res->start = (resource_size_t)OF_BAD_ADDR;
+	res->end = (resource_size_t)OF_BAD_ADDR;
+	return err;
+}
+
diff --git a/drivers/of/of_pci.c b/drivers/of/of_pci.c
index 8481996..e81402a 100644
--- a/drivers/of/of_pci.c
+++ b/drivers/of/of_pci.c
@@ -1,6 +1,7 @@
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/of_pci.h>
 
 static inline int __of_pci_pci_compare(struct device_node *node,
@@ -89,6 +90,141 @@ int of_pci_parse_bus_range(struct device_node *node, struct resource *res)
 }
 EXPORT_SYMBOL_GPL(of_pci_parse_bus_range);
 
+/**
+ * pci_host_bridge_of_get_ranges - Parse PCI host bridge resources from DT
+ * @dev: device node of the host bridge having the range property
+ * @resources: list where the range of resources will be added after DT parsing
+ * @io_base: pointer to a variable that will contain the physical address for
+ * the start of the I/O range.
+ *
+ * It is the callers job to free the @resources list if an error is returned.
+ *
+ * This function will parse the "ranges" property of a PCI host bridge device
+ * node and setup the resource mapping based on its content. It is expected
+ * that the property conforms with the Power ePAPR document.
+ *
+ * Each architecture is then offered the chance of applying their own
+ * filtering of pci_host_bridge_windows based on their own restrictions by
+ * calling pcibios_fixup_bridge_ranges(). The filtered list of windows
+ * can then be used when creating a pci_host_bridge structure.
+ */
+static int pci_host_bridge_of_get_ranges(struct device_node *dev,
+		struct list_head *resources, resource_size_t *io_base)
+{
+	struct resource *res;
+	struct of_pci_range range;
+	struct of_pci_range_parser parser;
+	int err;
+
+	pr_info("PCI host bridge %s ranges:\n", dev->full_name);
+
+	/* Check for ranges property */
+	err = of_pci_range_parser_init(&parser, dev);
+	if (err)
+		return err;
+
+	pr_debug("Parsing ranges property...\n");
+	for_each_of_pci_range(&parser, &range) {
+		/* Read next ranges element */
+		pr_debug("pci_space: 0x%08x pci_addr:0x%016llx cpu_addr:0x%016llx size:0x%016llx\n",
+			range.pci_space, range.pci_addr, range.cpu_addr, range.size);
+
+		/*
+		 * If we failed translation or got a zero-sized region
+		 * then skip this range
+		 */
+		if (range.cpu_addr == OF_BAD_ADDR || range.size == 0)
+			continue;
+
+		res = kzalloc(sizeof(struct resource), GFP_KERNEL);
+		if (!res)
+			return -ENOMEM;
+
+		err = of_pci_range_to_resource(&range, dev, res);
+		if (err)
+			return err;
+
+		if (resource_type(res) == IORESOURCE_IO)
+			*io_base = range.cpu_addr;
+
+		pci_add_resource_offset(resources, res,
+				res->start - range.pci_addr);
+	}
+
+	/* Apply architecture specific fixups for the ranges */
+	return pcibios_fixup_bridge_ranges(resources);
+}
+
+static atomic_t domain_nr = ATOMIC_INIT(-1);
+
+/**
+ * of_create_pci_host_bridge - Create a PCI host bridge structure using
+ * information passed in the DT.
+ * @parent: device owning this host bridge
+ * @ops: pci_ops associated with the host controller
+ * @host_data: opaque data structure used by the host controller.
+ *
+ * returns a pointer to the newly created pci_host_bridge structure, or
+ * NULL if the call failed.
+ *
+ * This function will try to obtain the host bridge domain number by
+ * using of_alias_get_id() call with "pci-domain" as a stem. If that
+ * fails, a local allocator will be used that will put each host bridge
+ * in a new domain.
+ */
+struct pci_host_bridge *
+of_create_pci_host_bridge(struct device *parent, struct pci_ops *ops, void *host_data)
+{
+	int err, domain, busno;
+	struct resource *bus_range;
+	struct pci_bus *root_bus;
+	struct pci_host_bridge *bridge;
+	resource_size_t io_base = 0;
+	LIST_HEAD(res);
+
+	bus_range = kzalloc(sizeof(*bus_range), GFP_KERNEL);
+	if (!bus_range)
+		return ERR_PTR(-ENOMEM);
+
+	domain = of_alias_get_id(parent->of_node, "pci-domain");
+	if (domain == -ENODEV)
+		domain = atomic_inc_return(&domain_nr);
+
+	err = of_pci_parse_bus_range(parent->of_node, bus_range);
+	if (err) {
+		dev_info(parent, "No bus range for %s, using default [0-255]\n",
+			parent->of_node->full_name);
+		bus_range->start = 0;
+		bus_range->end = 255;
+		bus_range->flags = IORESOURCE_BUS;
+	}
+	busno = bus_range->start;
+	pci_add_resource(&res, bus_range);
+
+	/* now parse the rest of host bridge bus ranges */
+	err = pci_host_bridge_of_get_ranges(parent->of_node, &res, &io_base);
+	if (err)
+		goto err_create;
+
+	/* then create the root bus */
+	root_bus = pci_create_root_bus_in_domain(parent, domain, busno,
+						ops, host_data, &res);
+	if (IS_ERR(root_bus)) {
+		err = PTR_ERR(root_bus);
+		goto err_create;
+	}
+
+	bridge = to_pci_host_bridge(root_bus->bridge);
+	bridge->io_base = io_base;
+
+	return bridge;
+
+err_create:
+	pci_free_resource_list(&res);
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL_GPL(of_create_pci_host_bridge);
+
 #ifdef CONFIG_PCI_MSI
 
 static LIST_HEAD(of_pci_msi_chip_list);
diff --git a/drivers/pci/host-bridge.c b/drivers/pci/host-bridge.c
index 0e5f3c9..54ceafd 100644
--- a/drivers/pci/host-bridge.c
+++ b/drivers/pci/host-bridge.c
@@ -16,12 +16,13 @@ static struct pci_bus *find_pci_root_bus(struct pci_bus *bus)
 	return bus;
 }
 
-static struct pci_host_bridge *find_pci_host_bridge(struct pci_bus *bus)
+struct pci_host_bridge *find_pci_host_bridge(struct pci_bus *bus)
 {
 	struct pci_bus *root_bus = find_pci_root_bus(bus);
 
 	return to_pci_host_bridge(root_bus->bridge);
 }
+EXPORT_SYMBOL_GPL(find_pci_host_bridge);
 
 void pci_set_host_bridge_release(struct pci_host_bridge *bridge,
 				 void (*release_fn)(struct pci_host_bridge *),
@@ -82,3 +83,18 @@ void pcibios_bus_to_resource(struct pci_bus *bus, struct resource *res,
 	res->end = region->end + offset;
 }
 EXPORT_SYMBOL(pcibios_bus_to_resource);
+
+/**
+ * Simple version of the platform specific code for filtering the list
+ * of resources obtained from the ranges declaration in DT.
+ *
+ * Platforms can override this function in order to impose stronger
+ * constraints onto the list of resources that a host bridge can use.
+ * The filtered list will then be used to create a root bus and associate
+ * it with the host bridge.
+ *
+ */
+int __weak pcibios_fixup_bridge_ranges(struct list_head *resources)
+{
+	return 0;
+}
diff --git a/drivers/pci/host/Kconfig b/drivers/pci/host/Kconfig
index 2d8a4d0..e17a28e 100644
--- a/drivers/pci/host/Kconfig
+++ b/drivers/pci/host/Kconfig
@@ -54,4 +54,14 @@ config PCIE_SPEAR13XX
 	help
 	  Say Y here if you want PCIe support on SPEAr13XX SoCs.
 
+config PCI_XGENE
+	bool "X-Gene PCIe controller"
+	depends on ARCH_XGENE
+	depends on OF
+	select PCIEPORTBUS
+	help
+	  Say Y here if you want internal PCI support on APM X-Gene SoC.
+	  There are 5 internal PCIe ports available. Each port is GEN3 capable
+	  and have varied lanes from x1 to x8.
+
 endmenu
diff --git a/drivers/pci/host/Makefile b/drivers/pci/host/Makefile
index 0daec79..7600482 100644
--- a/drivers/pci/host/Makefile
+++ b/drivers/pci/host/Makefile
@@ -7,3 +7,4 @@ obj-$(CONFIG_PCI_RCAR_GEN2) += pci-rcar-gen2.o
 obj-$(CONFIG_PCI_RCAR_GEN2_PCIE) += pcie-rcar.o
 obj-$(CONFIG_PCI_HOST_GENERIC) += pci-host-generic.o
 obj-$(CONFIG_PCIE_SPEAR13XX) += pcie-spear13xx.o
+obj-$(CONFIG_PCI_XGENE) += pci-xgene.o
diff --git a/drivers/pci/host/pci-xgene.c b/drivers/pci/host/pci-xgene.c
new file mode 100644
index 0000000..7bf4ac7
--- /dev/null
+++ b/drivers/pci/host/pci-xgene.c
@@ -0,0 +1,725 @@
+/**
+ * APM X-Gene PCIe Driver
+ *
+ * Copyright (c) 2013 Applied Micro Circuits Corporation.
+ *
+ * Author: Tanmay Inamdar <tinamdar@apm.com>.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+#include <linux/clk-private.h>
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/jiffies.h>
+#include <linux/memblock.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_pci.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#define PCIECORE_LTSSM			0x4c
+#define PCIECORE_CTLANDSTATUS		0x50
+#define INTXSTATUSMASK			0x6c
+#define PIM1_1L				0x80
+#define IBAR2				0x98
+#define IR2MSK				0x9c
+#define PIM2_1L				0xa0
+#define IBAR3L				0xb4
+#define IR3MSKL				0xbc
+#define PIM3_1L				0xc4
+#define OMR1BARL			0x100
+#define OMR2BARL			0x118
+#define OMR3BARL			0x130
+#define CFGBARL				0x154
+#define CFGBARH				0x158
+#define CFGCTL				0x15c
+#define RTDID				0x160
+#define BRIDGE_CFG_0			0x2000
+#define BRIDGE_CFG_1			0x2004
+#define BRIDGE_CFG_4			0x2010
+#define BRIDGE_CFG_32			0x2030
+#define BRIDGE_CFG_14			0x2038
+#define BRIDGE_CTRL_1			0x2204
+#define BRIDGE_CTRL_2			0x2208
+#define BRIDGE_CTRL_5			0x2214
+#define BRIDGE_STATUS_0			0x2600
+#define MEM_RAM_SHUTDOWN                0xd070
+#define BLOCK_MEM_RDY                   0xd074
+
+#define DEVICE_PORT_TYPE_MASK		0x03c00000
+#define PM_FORCE_RP_MODE_MASK		0x00000400
+#define SWITCH_PORT_MODE_MASK		0x00000800
+#define CLASS_CODE_MASK			0xffffff00
+#define LINK_UP_MASK			0x00000100
+#define AER_OPTIONAL_ERROR_EN		0xffc00000
+#define XGENE_PCIE_DEV_CTRL		0x2f0f
+#define AXI_EP_CFG_ACCESS		0x10000
+#define ENABLE_ASPM			0x08000000
+#define XGENE_PORT_TYPE_RC		0x05000000
+#define BLOCK_MEM_RDY_VAL               0xFFFFFFFF
+#define EN_COHERENCY			0xF0000000
+#define EN_REG				0x00000001
+#define OB_LO_IO			0x00000002
+#define XGENE_PCIE_VENDORID		0xE008
+#define XGENE_PCIE_DEVICEID		0xE004
+#define XGENE_PCIE_ECC_TIMEOUT		10 /* ms */
+#define XGENE_LTSSM_DETECT_WAIT		20 /* ms */
+#define XGENE_LTSSM_L0_WAIT		4  /* ms */
+#define SZ_1T				(SZ_1G*1024ULL)
+#define PIPE_PHY_RATE_RD(src)		((0xc000 & (u32)(src)) >> 0xe)
+
+struct xgene_pcie_port {
+	struct device_node	*node;
+	struct device		*dev;
+	struct clk		*clk;
+	void __iomem		*csr_base;
+	void __iomem		*cfg_base;
+	u8			link_up;
+};
+
+static inline u32 pcie_bar_low_val(u32 addr, u32 flags)
+{
+	return (addr & PCI_BASE_ADDRESS_MEM_MASK) | flags;
+}
+
+/* PCIE Configuration Out/In */
+static inline void xgene_pcie_cfg_out32(void __iomem *addr, int offset, u32 val)
+{
+	writel(val, addr + offset);
+}
+
+static inline void xgene_pcie_cfg_out16(void __iomem *addr, int offset, u16 val)
+{
+	u32 val32 = readl(addr + (offset & ~0x3));
+
+	switch (offset & 0x3) {
+	case 2:
+		val32 &= ~0xFFFF0000;
+		val32 |= (u32)val << 16;
+		break;
+	case 0:
+	default:
+		val32 &= ~0xFFFF;
+		val32 |= val;
+		break;
+	}
+	writel(val32, addr + (offset & ~0x3));
+}
+
+static inline void xgene_pcie_cfg_out8(void __iomem *addr, int offset, u8 val)
+{
+	u32 val32 = readl(addr + (offset & ~0x3));
+
+	switch (offset & 0x3) {
+	case 0:
+		val32 &= ~0xFF;
+		val32 |= val;
+		break;
+	case 1:
+		val32 &= ~0xFF00;
+		val32 |= (u32)val << 8;
+		break;
+	case 2:
+		val32 &= ~0xFF0000;
+		val32 |= (u32)val << 16;
+		break;
+	case 3:
+	default:
+		val32 &= ~0xFF000000;
+		val32 |= (u32)val << 24;
+		break;
+	}
+	writel(val32, addr + (offset & ~0x3));
+}
+
+static inline void xgene_pcie_cfg_in32(void __iomem *addr, int offset, u32 *val)
+{
+	*val = readl(addr + offset);
+}
+
+static inline void
+xgene_pcie_cfg_in16(void __iomem *addr, int offset, u32 *val)
+{
+	*val = readl(addr + (offset & ~0x3));
+
+	switch (offset & 0x3) {
+	case 2:
+		*val >>= 16;
+		break;
+	}
+
+	*val &= 0xFFFF;
+}
+
+static inline void
+xgene_pcie_cfg_in8(void __iomem *addr, int offset, u32 *val)
+{
+	*val = readl(addr + (offset & ~0x3));
+
+	switch (offset & 0x3) {
+	case 3:
+		*val = *val >> 24;
+		break;
+	case 2:
+		*val = *val >> 16;
+		break;
+	case 1:
+		*val = *val >> 8;
+		break;
+	}
+	*val &= 0xFF;
+}
+
+/* When the address bit [17:16] is 2'b01, the Configuration access will be
+ * treated as Type 1 and it will be forwarded to external PCIe device.
+ */
+static void __iomem *xgene_pcie_get_cfg_base(struct pci_bus *bus)
+{
+	struct xgene_pcie_port *port = bus->sysdata;
+
+	if (bus->number >= (bus->primary + 1))
+		return port->cfg_base + AXI_EP_CFG_ACCESS;
+
+	return port->cfg_base;
+}
+
+/* For Configuration request, RTDID register is used as Bus Number,
+ * Device Number and Function number of the header fields.
+ */
+static void xgene_pcie_set_rtdid_reg(struct pci_bus *bus, uint devfn)
+{
+	struct xgene_pcie_port *port = bus->sysdata;
+	unsigned int b, d, f;
+	u32 rtdid_val = 0;
+
+	b = bus->number;
+	d = PCI_SLOT(devfn);
+	f = PCI_FUNC(devfn);
+
+	if (!pci_is_root_bus(bus))
+		rtdid_val = (b << 8) | (d << 3) | f;
+
+	writel(rtdid_val, port->csr_base + RTDID);
+	/* read the register back to ensure flush */
+	readl(port->csr_base + RTDID);
+}
+
+static int xgene_pcie_read_config(struct pci_bus *bus, unsigned int devfn,
+				  int offset, int len, u32 *val)
+{
+	struct xgene_pcie_port *port = bus->sysdata;
+	void __iomem *addr;
+
+	if ((pci_is_root_bus(bus) && devfn != 0) || !port->link_up)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	xgene_pcie_set_rtdid_reg(bus, devfn);
+	addr = xgene_pcie_get_cfg_base(bus);
+	switch (len) {
+	case 1:
+		xgene_pcie_cfg_in8(addr, offset, val);
+		break;
+	case 2:
+		xgene_pcie_cfg_in16(addr, offset, val);
+		break;
+	default:
+		xgene_pcie_cfg_in32(addr, offset, val);
+		break;
+	}
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static int xgene_pcie_write_config(struct pci_bus *bus, unsigned int devfn,
+				   int offset, int len, u32 val)
+{
+	struct xgene_pcie_port *port = bus->sysdata;
+	void __iomem *addr;
+
+	if ((pci_is_root_bus(bus) && devfn != 0) || !port->link_up)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	xgene_pcie_set_rtdid_reg(bus, devfn);
+	addr = xgene_pcie_get_cfg_base(bus);
+	switch (len) {
+	case 1:
+		xgene_pcie_cfg_out8(addr, offset, (u8)val);
+		break;
+	case 2:
+		xgene_pcie_cfg_out16(addr, offset, (u16)val);
+		break;
+	default:
+		xgene_pcie_cfg_out32(addr, offset, val);
+		break;
+	}
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static struct pci_ops xgene_pcie_ops = {
+	.read = xgene_pcie_read_config,
+	.write = xgene_pcie_write_config
+};
+
+static void xgene_pcie_program_core(void __iomem *csr_base)
+{
+	u32 val;
+
+	val = readl(csr_base + BRIDGE_CFG_0);
+	val |= AER_OPTIONAL_ERROR_EN;
+	writel(val, csr_base + BRIDGE_CFG_0);
+	writel(0x0, csr_base + INTXSTATUSMASK);
+	val = readl(csr_base + BRIDGE_CTRL_1);
+	val = (val & ~0xffff) | XGENE_PCIE_DEV_CTRL;
+	writel(val, csr_base + BRIDGE_CTRL_1);
+}
+
+static u64 xgene_pcie_set_ib_mask(void __iomem *csr_base, u32 addr,
+				  u32 flags, u64 size)
+{
+	u64 mask = (~(size - 1) & PCI_BASE_ADDRESS_MEM_MASK) | flags;
+	u32 val32 = 0;
+	u32 val;
+
+	val32 = readl(csr_base + addr);
+	val = (val32 & 0x0000ffff) | (lower_32_bits(mask) << 16);
+	writel(val, csr_base + addr);
+
+	val32 = readl(csr_base + addr + 0x04);
+	val = (val32 & 0xffff0000) | (lower_32_bits(mask) >> 16);
+	writel(val, csr_base + addr + 0x04);
+
+	val32 = readl(csr_base + addr + 0x04);
+	val = (val32 & 0x0000ffff) | (upper_32_bits(mask) << 16);
+	writel(val, csr_base + addr + 0x04);
+
+	val32 = readl(csr_base + addr + 0x08);
+	val = (val32 & 0xffff0000) | (upper_32_bits(mask) >> 16);
+	writel(val, csr_base + addr + 0x08);
+
+	return mask;
+}
+
+static void xgene_pcie_poll_linkup(struct xgene_pcie_port *port,
+				   u32 *lanes, u32 *speed)
+{
+	void __iomem *csr_base = port->csr_base;
+	ulong timeout;
+	u32 val32;
+
+	/*
+	 * A component enters the LTSSM Detect state within
+	 * 20ms of the end of fundamental core reset.
+	 */
+	msleep(XGENE_LTSSM_DETECT_WAIT);
+	port->link_up = 0;
+	timeout = jiffies + msecs_to_jiffies(XGENE_LTSSM_L0_WAIT);
+	while (time_before(jiffies, timeout)) {
+		val32 = readl(csr_base + PCIECORE_CTLANDSTATUS);
+		if (val32 & LINK_UP_MASK) {
+			port->link_up = 1;
+			*speed = PIPE_PHY_RATE_RD(val32);
+			val32 = readl(csr_base + BRIDGE_STATUS_0);
+			*lanes = val32 >> 26;
+			break;
+		}
+		msleep(1);
+	}
+}
+
+static void xgene_pcie_setup_root_complex(struct xgene_pcie_port *port)
+{
+	void __iomem *csr_base = port->csr_base;
+	u32 val;
+
+	val = (XGENE_PCIE_DEVICEID << 16) | XGENE_PCIE_VENDORID;
+	writel(val, csr_base + BRIDGE_CFG_0);
+
+	val = readl(csr_base + BRIDGE_CFG_1);
+	val &= ~CLASS_CODE_MASK;
+	val |= PCI_CLASS_BRIDGE_PCI << 16;
+	writel(val, csr_base + BRIDGE_CFG_1);
+
+	val = readl(csr_base + BRIDGE_CFG_14);
+	val |= SWITCH_PORT_MODE_MASK;
+	val &= ~PM_FORCE_RP_MODE_MASK;
+	writel(val, csr_base + BRIDGE_CFG_14);
+
+	val = readl(csr_base + BRIDGE_CTRL_5);
+	val &= ~DEVICE_PORT_TYPE_MASK;
+	val |= XGENE_PORT_TYPE_RC;
+	writel(val, csr_base + BRIDGE_CTRL_5);
+
+	val = readl(csr_base + BRIDGE_CTRL_2);
+	val |= ENABLE_ASPM;
+	writel(val, csr_base + BRIDGE_CTRL_2);
+
+	val = readl(csr_base + BRIDGE_CFG_32);
+	writel(val | (1 << 19), csr_base + BRIDGE_CFG_32);
+}
+
+/* Return 0 on success */
+static int xgene_pcie_init_ecc(struct xgene_pcie_port *port)
+{
+	void __iomem *csr_base = port->csr_base;
+	ulong timeout;
+	u32 val;
+
+	val = readl(csr_base + MEM_RAM_SHUTDOWN);
+	if (!val)
+		return 0;
+	writel(0x0, csr_base + MEM_RAM_SHUTDOWN);
+	timeout = jiffies + msecs_to_jiffies(XGENE_PCIE_ECC_TIMEOUT);
+	while (time_before(jiffies, timeout)) {
+		val = readl(csr_base + BLOCK_MEM_RDY);
+		if (val == BLOCK_MEM_RDY_VAL)
+			return 0;
+		msleep(1);
+	}
+
+	return 1;
+}
+
+static int xgene_pcie_init_port(struct xgene_pcie_port *port)
+{
+	int rc;
+
+	port->clk = clk_get(port->dev, NULL);
+	if (IS_ERR(port->clk)) {
+		dev_err(port->dev, "clock not available\n");
+		return -ENODEV;
+	}
+
+	rc = clk_prepare_enable(port->clk);
+	if (rc) {
+		dev_err(port->dev, "clock enable failed\n");
+		return rc;
+	}
+
+	rc = xgene_pcie_init_ecc(port);
+	if (rc) {
+		dev_err(port->dev, "memory init failed\n");
+		return rc;
+	}
+
+	return 0;
+}
+
+static void xgene_pcie_fixup_bridge(struct pci_dev *dev)
+{
+	int i;
+
+	/* Hide the PCI host BARs from the kernel as their content doesn't
+	 * fit well in the resource management
+	 */
+	for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
+		dev->resource[i].start = dev->resource[i].end = 0;
+		dev->resource[i].flags = 0;
+	}
+	dev_info(&dev->dev, "Hiding X-Gene pci host bridge resources %s\n",
+		 pci_name(dev));
+}
+DECLARE_PCI_FIXUP_HEADER(XGENE_PCIE_VENDORID, XGENE_PCIE_DEVICEID,
+			 xgene_pcie_fixup_bridge);
+
+static int xgene_pcie_map_reg(struct xgene_pcie_port *port,
+			      struct platform_device *pdev, u64 *cfg_addr)
+{
+	struct resource *res;
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "csr");
+	port->csr_base = devm_ioremap_resource(port->dev, res);
+	if (IS_ERR(port->csr_base))
+		return PTR_ERR(port->csr_base);
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cfg");
+	port->cfg_base = devm_ioremap_resource(port->dev, res);
+	if (IS_ERR(port->cfg_base))
+		return PTR_ERR(port->cfg_base);
+	*cfg_addr = res->start;
+
+	return 0;
+}
+
+static void xgene_pcie_setup_ob_reg(struct xgene_pcie_port *port,
+				    struct resource *res, u32 offset, u64 addr)
+{
+	void __iomem *base = port->csr_base + offset;
+	resource_size_t size = resource_size(res);
+	u64 restype = resource_type(res);
+	u64 cpu_addr, pci_addr;
+	u64 mask = 0;
+	u32 min_size;
+	u32 flag = EN_REG;
+
+	if (restype == IORESOURCE_MEM) {
+		cpu_addr = res->start;
+		pci_addr = addr;
+		min_size = SZ_128M;
+	} else {
+		cpu_addr = addr;
+		pci_addr = res->start;
+		min_size = 128;
+		flag |= OB_LO_IO;
+	}
+	if (size >= min_size)
+		mask = ~(size - 1) | flag;
+	else
+		dev_warn(port->dev, "res size 0x%llx less than minimum 0x%x\n",
+			 (u64)size, min_size);
+	writel(lower_32_bits(cpu_addr), base);
+	writel(upper_32_bits(cpu_addr), base + 0x04);
+	writel(lower_32_bits(mask), base + 0x08);
+	writel(upper_32_bits(mask), base + 0x0c);
+	writel(lower_32_bits(pci_addr), base + 0x10);
+	writel(upper_32_bits(pci_addr), base + 0x14);
+}
+
+static void xgene_pcie_setup_cfg_reg(void __iomem *csr_base, u64 addr)
+{
+	writel(lower_32_bits(addr), csr_base + CFGBARL);
+	writel(upper_32_bits(addr), csr_base + CFGBARH);
+	writel(EN_REG, csr_base + CFGCTL);
+}
+
+static int xgene_pcie_map_ranges(struct xgene_pcie_port *port,
+				 struct pci_host_bridge *bridge,
+				 u64 cfg_addr)
+{
+	struct device *dev = port->dev;
+	struct pci_host_bridge_window *window;
+	int ret;
+
+	list_for_each_entry(window, &bridge->windows, list) {
+		struct resource *res = window->res;
+		u64 restype = resource_type(res);
+		dev_dbg(port->dev, "0x%08lx 0x%016llx...0x%016llx\n",
+			res->flags, res->start, res->end);
+
+		switch (restype) {
+		case IORESOURCE_IO:
+			xgene_pcie_setup_ob_reg(port, res, OMR2BARL,
+						bridge->io_base);
+			ret = pci_remap_iospace(res, bridge->io_base);
+			if (ret < 0)
+				return ret;
+			break;
+		case IORESOURCE_MEM:
+			xgene_pcie_setup_ob_reg(port, res, OMR3BARL,
+						res->start - window->offset);
+			break;
+		case IORESOURCE_BUS:
+			break;
+		default:
+			dev_err(dev, "invalid io resource!");
+			return -EINVAL;
+		}
+	}
+	xgene_pcie_setup_cfg_reg(port->csr_base, cfg_addr);
+	return 0;
+}
+
+static void xgene_pcie_setup_pims(void *addr, u64 pim, u64 size)
+{
+	writel(lower_32_bits(pim), addr);
+	writel(upper_32_bits(pim) | EN_COHERENCY, addr + 0x04);
+	writel(lower_32_bits(size), addr + 0x10);
+	writel(upper_32_bits(size), addr + 0x14);
+}
+
+/*
+ * X-Gene PCIe support maximum 3 inbound memory regions
+ * This function helps to select a region based on size of region
+ */
+static int xgene_pcie_select_ib_reg(u8 *ib_reg_mask, u64 size)
+{
+	if ((size > 4) && (size < SZ_16M) && !(*ib_reg_mask & (1 << 1))) {
+		*ib_reg_mask |= (1 << 1);
+		return 1;
+	}
+
+	if ((size > SZ_1K) && (size < SZ_1T) && !(*ib_reg_mask & (1 << 0))) {
+		*ib_reg_mask |= (1 << 0);
+		return 0;
+	}
+
+	if ((size > SZ_1M) && (size < SZ_1T) && !(*ib_reg_mask & (1 << 2))) {
+		*ib_reg_mask |= (1 << 2);
+		return 2;
+	}
+	return -EINVAL;
+}
+
+static void xgene_pcie_setup_ib_reg(struct xgene_pcie_port *port,
+				    struct of_pci_range *range, u8 *ib_reg_mask)
+{
+	void __iomem *csr_base = port->csr_base;
+	void __iomem *cfg_base = port->cfg_base;
+	void *bar_addr;
+	void *pim_addr;
+	u64 restype = range->flags & IORESOURCE_TYPE_BITS;
+	u64 cpu_addr = range->cpu_addr;
+	u64 pci_addr = range->pci_addr;
+	u64 size = range->size;
+	u64 mask = ~(size - 1) | EN_REG;
+	u32 flags = PCI_BASE_ADDRESS_MEM_TYPE_64;
+	u32 bar_low;
+	int region;
+
+	region = xgene_pcie_select_ib_reg(ib_reg_mask, range->size);
+	if (region < 0) {
+		dev_warn(port->dev, "invalid pcie dma-range config\n");
+		return;
+	}
+
+	if (restype == PCI_BASE_ADDRESS_MEM_PREFETCH)
+		flags |= PCI_BASE_ADDRESS_MEM_PREFETCH;
+
+	bar_low = pcie_bar_low_val((u32)cpu_addr, flags);
+	switch (region) {
+	case 0:
+		xgene_pcie_set_ib_mask(csr_base, BRIDGE_CFG_4, flags, size);
+		bar_addr = cfg_base + PCI_BASE_ADDRESS_0;
+		writel(bar_low, bar_addr);
+		writel(upper_32_bits(cpu_addr), bar_addr + 0x4);
+		pim_addr = csr_base + PIM1_1L;
+		break;
+	case 1:
+		bar_addr = csr_base + IBAR2;
+		writel(bar_low, bar_addr);
+		writel(lower_32_bits(mask), csr_base + IR2MSK);
+		pim_addr = csr_base + PIM2_1L;
+		break;
+	case 2:
+		bar_addr = csr_base + IBAR3L;
+		writel(bar_low, bar_addr);
+		writel(upper_32_bits(cpu_addr), bar_addr + 0x4);
+		writel(lower_32_bits(mask), csr_base + IR3MSKL);
+		writel(upper_32_bits(mask), csr_base + IR3MSKL + 0x4);
+		pim_addr = csr_base + PIM3_1L;
+		break;
+	}
+
+	xgene_pcie_setup_pims(pim_addr, pci_addr, size);
+}
+
+static int pci_dma_range_parser_init(struct of_pci_range_parser *parser,
+				     struct device_node *node)
+{
+	const int na = 3, ns = 2;
+	int rlen;
+
+	parser->node = node;
+	parser->pna = of_n_addr_cells(node);
+	parser->np = parser->pna + na + ns;
+
+	parser->range = of_get_property(node, "dma-ranges", &rlen);
+	if (!parser->range)
+		return -ENOENT;
+
+	parser->end = parser->range + rlen / sizeof(__be32);
+	return 0;
+}
+
+static int xgene_pcie_parse_map_dma_ranges(struct xgene_pcie_port *port)
+{
+	struct device_node *np = port->node;
+	struct of_pci_range range;
+	struct of_pci_range_parser parser;
+	struct device *dev = port->dev;
+	u8 ib_reg_mask = 0;
+
+	if (pci_dma_range_parser_init(&parser, np)) {
+		dev_err(dev, "missing dma-ranges property\n");
+		return -EINVAL;
+	}
+
+	/* Get the dma-ranges from DT */
+	for_each_of_pci_range(&parser, &range) {
+		u64 end = range.cpu_addr + range.size - 1;
+		dev_dbg(port->dev, "0x%08x 0x%016llx..0x%016llx -> 0x%016llx\n",
+			range.flags, range.cpu_addr, end, range.pci_addr);
+		xgene_pcie_setup_ib_reg(port, &range, &ib_reg_mask);
+	}
+	return 0;
+}
+
+static int xgene_pcie_probe_bridge(struct platform_device *pdev)
+{
+	struct device_node *np = of_node_get(pdev->dev.of_node);
+	struct xgene_pcie_port *port;
+	struct pci_host_bridge *bridge;
+	resource_size_t lastbus;
+	u32 lanes = 0, speed = 0;
+	u64 cfg_addr = 0;
+	int ret;
+
+	port = devm_kzalloc(&pdev->dev, sizeof(*port), GFP_KERNEL);
+	if (!port)
+		return -ENOMEM;
+	port->node = np;
+	port->dev = &pdev->dev;
+
+	ret = xgene_pcie_map_reg(port, pdev, &cfg_addr);
+	if (ret)
+		return ret;
+
+	ret = xgene_pcie_init_port(port);
+	if (ret)
+		return ret;
+	xgene_pcie_program_core(port->csr_base);
+	xgene_pcie_setup_root_complex(port);
+
+	bridge = of_create_pci_host_bridge(&pdev->dev, &xgene_pcie_ops, port);
+	if (IS_ERR_OR_NULL(bridge))
+		return PTR_ERR(bridge);
+
+	ret = xgene_pcie_map_ranges(port, bridge, cfg_addr);
+	if (ret)
+		return ret;
+
+	ret = xgene_pcie_parse_map_dma_ranges(port);
+	if (ret)
+		return ret;
+
+	xgene_pcie_poll_linkup(port, &lanes, &speed);
+	if (!port->link_up)
+		dev_info(port->dev, "(rc) link down\n");
+	else
+		dev_info(port->dev, "(rc) x%d gen-%d link up\n",
+				lanes, speed + 1);
+	platform_set_drvdata(pdev, port);
+	lastbus = pci_rescan_bus(bridge->bus);
+	pci_bus_update_busn_res_end(bridge->bus, lastbus);
+	return 0;
+}
+
+static const struct of_device_id xgene_pcie_match_table[] = {
+	{.compatible = "apm,xgene-pcie",},
+	{},
+};
+
+static struct platform_driver xgene_pcie_driver = {
+	.driver = {
+		   .name = "xgene-pcie",
+		   .owner = THIS_MODULE,
+		   .of_match_table = of_match_ptr(xgene_pcie_match_table),
+	},
+	.probe = xgene_pcie_probe_bridge,
+};
+module_platform_driver(xgene_pcie_driver);
+
+MODULE_AUTHOR("Tanmay Inamdar <tinamdar@apm.com>");
+MODULE_DESCRIPTION("APM X-Gene PCIe driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 2c9ac70..7bae0f9 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -17,6 +17,7 @@
 #include <linux/spinlock.h>
 #include <linux/string.h>
 #include <linux/log2.h>
+#include <linux/of_pci.h>
 #include <linux/pci-aspm.h>
 #include <linux/pm_wakeup.h>
 #include <linux/interrupt.h>
@@ -1453,6 +1454,9 @@ EXPORT_SYMBOL(pcim_pin_device);
  */
 int __weak pcibios_add_device(struct pci_dev *dev)
 {
+#ifdef CONFIG_OF
+	dev->irq = of_irq_parse_and_map_pci(dev, 0, 0);
+#endif
 	return 0;
 }
 
@@ -2704,6 +2708,39 @@ int pci_request_regions_exclusive(struct pci_dev *pdev, const char *res_name)
 }
 EXPORT_SYMBOL(pci_request_regions_exclusive);
 
+/**
+ *	pci_remap_iospace - Remap the memory mapped I/O space
+ *	@res: Resource describing the I/O space
+ *	@phys_addr: physical address where the range will be mapped.
+ *
+ *	Remap the memory mapped I/O space described by the @res
+ *	into the CPU physical address space. Only architectures
+ *	that have memory mapped IO defined (and hence PCI_IOBASE)
+ *	should call this function.
+ */
+int __weak pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr)
+{
+	int err = -ENODEV;
+
+#ifdef PCI_IOBASE
+	if (!(res->flags & IORESOURCE_IO))
+		return -EINVAL;
+
+	if (res->end > IO_SPACE_LIMIT)
+		return -EINVAL;
+
+	err = ioremap_page_range(res->start + (unsigned long)PCI_IOBASE,
+				res->end + 1 + (unsigned long)PCI_IOBASE,
+				phys_addr, __pgprot(PROT_DEVICE_nGnRE));
+#else
+	/* this architecture does not have memory mapped I/O space,
+	   so this function should never be called */
+	WARN_ON(1);
+#endif
+
+	return err;
+}
+
 static void __pci_set_master(struct pci_dev *dev, bool enable)
 {
 	u16 old_cmd, cmd;
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index e3cf8a2..abf5e82 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -515,7 +515,7 @@ static void pci_release_host_bridge_dev(struct device *dev)
 	kfree(bridge);
 }
 
-static struct pci_host_bridge *pci_alloc_host_bridge(struct pci_bus *b)
+static struct pci_host_bridge *pci_alloc_host_bridge(void)
 {
 	struct pci_host_bridge *bridge;
 
@@ -524,7 +524,6 @@ static struct pci_host_bridge *pci_alloc_host_bridge(struct pci_bus *b)
 		return NULL;
 
 	INIT_LIST_HEAD(&bridge->windows);
-	bridge->bus = b;
 	return bridge;
 }
 
@@ -1749,8 +1748,9 @@ void __weak pcibios_remove_bus(struct pci_bus *bus)
 {
 }
 
-struct pci_bus *pci_create_root_bus(struct device *parent, int bus,
-		struct pci_ops *ops, void *sysdata, struct list_head *resources)
+struct pci_bus *pci_create_root_bus_in_domain(struct device *parent,
+		int domain, int bus, struct pci_ops *ops, void *sysdata,
+		struct list_head *resources)
 {
 	int error;
 	struct pci_host_bridge *bridge;
@@ -1761,37 +1761,41 @@ struct pci_bus *pci_create_root_bus(struct device *parent, int bus,
 	char bus_addr[64];
 	char *fmt;
 
+	bridge = pci_alloc_host_bridge();
+	if (!bridge)
+		return ERR_PTR(-ENOMEM);
+
+	bridge->dev.parent = parent;
+	bridge->dev.release = pci_release_host_bridge_dev;
+	bridge->domain_nr = domain;
+
 	b = pci_alloc_bus();
-	if (!b)
-		return NULL;
+	if (!b) {
+		error = -ENOMEM;
+		goto err_out;
+	}
 
 	b->sysdata = sysdata;
 	b->ops = ops;
 	b->number = b->busn_res.start = bus;
-	b2 = pci_find_bus(pci_domain_nr(b), bus);
+	b2 = pci_find_bus(bridge->domain_nr, bus);
 	if (b2) {
 		/* If we already got to this bus through a different bridge, ignore it */
 		dev_dbg(&b2->dev, "bus already known\n");
-		goto err_out;
+		error = -EEXIST;
+		goto err_bus_out;
 	}
 
-	bridge = pci_alloc_host_bridge(b);
-	if (!bridge)
-		goto err_out;
-
-	bridge->dev.parent = parent;
-	bridge->dev.release = pci_release_host_bridge_dev;
-	dev_set_name(&bridge->dev, "pci%04x:%02x", pci_domain_nr(b), bus);
+	bridge->bus = b;
+	dev_set_name(&bridge->dev, "pci%04x:%02x", bridge->domain_nr, bus);
 	error = pcibios_root_bridge_prepare(bridge);
-	if (error) {
-		kfree(bridge);
+	if (error)
 		goto err_out;
-	}
 
 	error = device_register(&bridge->dev);
 	if (error) {
 		put_device(&bridge->dev);
-		goto err_out;
+		goto err_bus_out;
 	}
 	b->bridge = get_device(&bridge->dev);
 	device_enable_async_suspend(b->bridge);
@@ -1802,7 +1806,7 @@ struct pci_bus *pci_create_root_bus(struct device *parent, int bus,
 
 	b->dev.class = &pcibus_class;
 	b->dev.parent = b->bridge;
-	dev_set_name(&b->dev, "%04x:%02x", pci_domain_nr(b), bus);
+	dev_set_name(&b->dev, "%04x:%02x", bridge->domain_nr, bus);
 	error = device_register(&b->dev);
 	if (error)
 		goto class_dev_reg_err;
@@ -1848,9 +1852,31 @@ struct pci_bus *pci_create_root_bus(struct device *parent, int bus,
 class_dev_reg_err:
 	put_device(&bridge->dev);
 	device_unregister(&bridge->dev);
+err_bus_out:
+	kfree(b);
 err_out:
+	kfree(bridge);
+	return ERR_PTR(error);
+}
+
+struct pci_bus *pci_create_root_bus(struct device *parent, int bus,
+		struct pci_ops *ops, void *sysdata, struct list_head *resources)
+{
+	int domain_nr;
+	struct pci_bus *b = pci_alloc_bus();
+	if (!b)
+		return NULL;
+
+	b->sysdata = sysdata;
+	domain_nr = pci_domain_nr(b);
 	kfree(b);
-	return NULL;
+
+	b = pci_create_root_bus_in_domain(parent, domain_nr, bus,
+				ops, sysdata, resources);
+	if (IS_ERR(b))
+		return NULL;
+
+	return b;
 }
 
 int pci_bus_insert_busn_res(struct pci_bus *b, int bus, int bus_max)
diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index 975e1cc..2e2161b 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -331,7 +331,7 @@ static inline void iounmap(void __iomem *addr)
 #ifndef CONFIG_GENERIC_IOMAP
 static inline void __iomem *ioport_map(unsigned long port, unsigned int nr)
 {
-	return (void __iomem *) port;
+	return (void __iomem *)(PCI_IOBASE + (port & IO_SPACE_LIMIT));
 }
 
 static inline void ioport_unmap(void __iomem *p)
diff --git a/include/linux/of_address.h b/include/linux/of_address.h
index fb7b722..cb9479e4 100644
--- a/include/linux/of_address.h
+++ b/include/linux/of_address.h
@@ -23,17 +23,8 @@ struct of_pci_range {
 #define for_each_of_pci_range(parser, range) \
 	for (; of_pci_range_parser_one(parser, range);)
 
-static inline void of_pci_range_to_resource(struct of_pci_range *range,
-					    struct device_node *np,
-					    struct resource *res)
-{
-	res->flags = range->flags;
-	res->start = range->cpu_addr;
-	res->end = range->cpu_addr + range->size - 1;
-	res->parent = res->child = res->sibling = NULL;
-	res->name = np->full_name;
-}
-
+extern int of_pci_range_to_resource(struct of_pci_range *range,
+		struct device_node *np, struct resource *res);
 /* Translate a DMA address from device space to CPU space */
 extern u64 of_translate_dma_address(struct device_node *dev,
 				    const __be32 *in_addr);
@@ -55,6 +46,7 @@ extern void __iomem *of_iomap(struct device_node *device, int index);
 extern const __be32 *of_get_address(struct device_node *dev, int index,
 			   u64 *size, unsigned int *flags);
 
+extern int pci_register_io_range(phys_addr_t addr, resource_size_t size);
 extern unsigned long pci_address_to_pio(phys_addr_t addr);
 
 extern int of_pci_range_parser_init(struct of_pci_range_parser *parser,
diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h
index dde3a4a..71e36d0 100644
--- a/include/linux/of_pci.h
+++ b/include/linux/of_pci.h
@@ -15,6 +15,9 @@ struct device_node *of_pci_find_child_device(struct device_node *parent,
 int of_pci_get_devfn(struct device_node *np);
 int of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin);
 int of_pci_parse_bus_range(struct device_node *node, struct resource *res);
+struct pci_host_bridge *of_create_pci_host_bridge(struct device *parent,
+					struct pci_ops *ops, void *host_data);
+
 #else
 static inline int of_irq_parse_pci(const struct pci_dev *pdev, struct of_phandle_args *out_irq)
 {
@@ -43,6 +46,13 @@ of_pci_parse_bus_range(struct device_node *node, struct resource *res)
 {
 	return -EINVAL;
 }
+
+static inline struct pci_host_bridge *
+of_create_pci_host_bridge(struct device *parent, struct pci_ops *ops,
+			void *host_data)
+{
+	return NULL;
+}
 #endif
 
 #if defined(CONFIG_OF) && defined(CONFIG_PCI_MSI)
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 61978a4..f582746 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -401,6 +401,8 @@ struct pci_host_bridge_window {
 struct pci_host_bridge {
 	struct device dev;
 	struct pci_bus *bus;		/* root bus */
+	int domain_nr;
+	resource_size_t io_base;	/* physical address for the start of I/O area */
 	struct list_head windows;	/* pci_host_bridge_windows */
 	void (*release_fn)(struct pci_host_bridge *);
 	void *release_data;
@@ -769,6 +771,9 @@ struct pci_bus *pci_scan_bus(int bus, struct pci_ops *ops, void *sysdata);
 struct pci_bus *pci_create_root_bus(struct device *parent, int bus,
 				    struct pci_ops *ops, void *sysdata,
 				    struct list_head *resources);
+struct pci_bus *pci_create_root_bus_in_domain(struct device *parent,
+			int domain, int bus, struct pci_ops *ops,
+			void *sysdata, struct list_head *resources);
 int pci_bus_insert_busn_res(struct pci_bus *b, int bus, int busmax);
 int pci_bus_update_busn_res_end(struct pci_bus *b, int busmax);
 void pci_bus_release_busn_res(struct pci_bus *b);
@@ -1097,6 +1102,9 @@ int __must_check pci_bus_alloc_resource(struct pci_bus *bus,
 						  resource_size_t),
 			void *alignf_data);
 
+
+int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr);
+
 static inline dma_addr_t pci_bus_address(struct pci_dev *pdev, int bar)
 {
 	struct pci_bus_region region;
@@ -1815,8 +1823,15 @@ static inline void pci_set_of_node(struct pci_dev *dev) { }
 static inline void pci_release_of_node(struct pci_dev *dev) { }
 static inline void pci_set_bus_of_node(struct pci_bus *bus) { }
 static inline void pci_release_bus_of_node(struct pci_bus *bus) { }
+
 #endif  /* CONFIG_OF */
 
+/* Used by architecture code to apply any quirks to the list of
+ * pci_host_bridge resource ranges before they are being used
+ * by of_create_pci_host_bridge()
+ */
+extern int pcibios_fixup_bridge_ranges(struct list_head *resources);
+
 #ifdef CONFIG_EEH
 static inline struct eeh_dev *pci_dev_to_eeh_dev(struct pci_dev *pdev)
 {
diff --git a/tools/perf/arch/arm64/include/perf_regs.h b/tools/perf/arch/arm64/include/perf_regs.h
index e9441b9..1d3f39c 100644
--- a/tools/perf/arch/arm64/include/perf_regs.h
+++ b/tools/perf/arch/arm64/include/perf_regs.h
@@ -6,6 +6,8 @@
 #include <asm/perf_regs.h>
 
 #define PERF_REGS_MASK	((1ULL << PERF_REG_ARM64_MAX) - 1)
+#define PERF_REGS_MAX	PERF_REG_ARM64_MAX
+
 #define PERF_REG_IP	PERF_REG_ARM64_PC
 #define PERF_REG_SP	PERF_REG_ARM64_SP