Merge tag 'gic-v3-for-lsk-v3.14-v1' of http://git.linaro.org/git-ro/people/christoffer.dall/linux-kvm-arm into lsk-v3.14-gicv3v3.14/topic/gicv3

GICv3 Support for LSK v3.14

76 files changed, 3092 insertions, 825 deletions

diff --git a/Documentation/arm64/booting.txt b/Documentation/arm64/booting.txt
index a9691cc48fe3..beb754e87c65 100644
--- a/Documentation/arm64/booting.txt
+++ b/Documentation/arm64/booting.txt
@@ -111,8 +111,14 @@ Before jumping into the kernel, the following conditions must be met:
 - Caches, MMUs
   The MMU must be off.
   Instruction cache may be on or off.
-  Data cache must be off and invalidated.
-  External caches (if present) must be configured and disabled.
+  The address range corresponding to the loaded kernel image must be
+  cleaned to the PoC. In the presence of a system cache or other
+  coherent masters with caches enabled, this will typically require
+  cache maintenance by VA rather than set/way operations.
+  System caches which respect the architected cache maintenance by VA
+  operations must be configured and may be enabled.
+  System caches which do not respect architected cache maintenance by VA
+  operations (not recommended) must be configured and disabled.
 
 - Architected timers
   CNTFRQ must be programmed with the timer frequency and CNTVOFF must
diff --git a/Documentation/arm64/memory.txt b/Documentation/arm64/memory.txt
index 5e054bfe4dde..1b84f2b7e65a 100644
--- a/Documentation/arm64/memory.txt
+++ b/Documentation/arm64/memory.txt
@@ -35,7 +35,11 @@ ffffffbc00000000	ffffffbdffffffff	   8GB		vmemmap
 
 ffffffbe00000000	ffffffbffbbfffff	  ~8GB		[guard, future vmmemap]
 
-ffffffbffbc00000	ffffffbffbdfffff	   2MB		earlyprintk device
+ffffffbffa000000	ffffffbffaffffff	  16MB		PCI I/O space
+
+ffffffbffb000000	ffffffbffbbfffff	  12MB		[guard]
+
+ffffffbffbc00000	ffffffbffbdfffff	   2MB		fixed mappings
 
 ffffffbffbe00000	ffffffbffbe0ffff	  64KB		PCI I/O space
 
@@ -60,7 +64,11 @@ fffffdfc00000000	fffffdfdffffffff	   8GB		vmemmap
 
 fffffdfe00000000	fffffdfffbbfffff	  ~8GB		[guard, future vmmemap]
 
-fffffdfffbc00000	fffffdfffbdfffff	   2MB		earlyprintk device
+fffffdfffa000000	fffffdfffaffffff	  16MB		PCI I/O space
+
+fffffdfffb000000	fffffdfffbbfffff	  12MB		[guard]
+
+fffffdfffbc00000	fffffdfffbdfffff	   2MB		fixed mappings
 
 fffffdfffbe00000	fffffdfffbe0ffff	  64KB		PCI I/O space
 
diff --git a/Documentation/devicetree/bindings/arm/gic.txt b/Documentation/devicetree/bindings/arm/gic.txt
index bae0d87a38b2..5573c08d3180 100644
--- a/Documentation/devicetree/bindings/arm/gic.txt
+++ b/Documentation/devicetree/bindings/arm/gic.txt
@@ -50,6 +50,11 @@ Optional
   regions, used when the GIC doesn't have banked registers. The offset is
   cpu-offset * cpu-nr.
 
+- arm,routable-irqs : Total number of gic irq inputs which are not directly
+		  connected from the peripherals, but are routed dynamically
+		  by a crossbar/multiplexer preceding the GIC. The GIC irq
+		  input line is assigned dynamically when the corresponding
+		  peripheral's crossbar line is mapped.
 Example:
 
 	intc: interrupt-controller@fff11000 {
@@ -57,6 +62,7 @@ Example:
 		#interrupt-cells = <3>;
 		#address-cells = <1>;
 		interrupt-controller;
+		arm,routable-irqs = <160>;
 		reg = <0xfff11000 0x1000>,
 		      <0xfff10100 0x100>;
 	};
diff --git a/arch/arc/kernel/devtree.c b/arch/arc/kernel/devtree.c
index b6dc4e21fd32..0b3ef4025d89 100644
--- a/arch/arc/kernel/devtree.c
+++ b/arch/arc/kernel/devtree.c
@@ -42,7 +42,7 @@ const struct machine_desc * __init setup_machine_fdt(void *dt)
 	const struct machine_desc *mdesc;
 	unsigned long dt_root;
 	void *clk;
-	unsigned long len;
+	int len;
 
 	if (!early_init_dt_scan(dt))
 		return NULL;
diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
index f751714d52c1..97707977144c 100644
--- a/arch/arm/kernel/devtree.c
+++ b/arch/arm/kernel/devtree.c
@@ -212,7 +212,7 @@ const struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys)
 
 	if (!mdesc) {
 		const char *prop;
-		long size;
+		int size;
 		unsigned long dt_root;
 
 		early_print("\nError: unrecognized/unsupported "
diff --git a/arch/arm/mach-exynos/common.c b/arch/arm/mach-exynos/common.c
index f18be40e5b21..1bf303f8dfe3 100644
--- a/arch/arm/mach-exynos/common.c
+++ b/arch/arm/mach-exynos/common.c
@@ -322,7 +322,7 @@ static int __init exynos_fdt_map_chipid(unsigned long node, const char *uname,
 {
 	struct map_desc iodesc;
 	__be32 *reg;
-	unsigned long len;
+	int len;
 
 	if (!of_flat_dt_is_compatible(node, "samsung,exynos4210-chipid") &&
 		!of_flat_dt_is_compatible(node, "samsung,exynos5440-clock"))
diff --git a/arch/arm/mach-vexpress/platsmp.c b/arch/arm/mach-vexpress/platsmp.c
index 993c9ae5dc5e..b4a5f0d8390d 100644
--- a/arch/arm/mach-vexpress/platsmp.c
+++ b/arch/arm/mach-vexpress/platsmp.c
@@ -53,7 +53,7 @@ static int __init vexpress_dt_find_scu(unsigned long node,
 {
 	if (of_flat_dt_match(node, vexpress_dt_cortex_a9_match)) {
 		phys_addr_t phys_addr;
-		__be32 *reg = of_get_flat_dt_prop(node, "reg", NULL);
+		const __be32 *reg = of_get_flat_dt_prop(node, "reg", NULL);
 
 		if (WARN_ON(!reg))
 			return -EINVAL;
diff --git a/arch/arm/plat-samsung/s5p-dev-mfc.c b/arch/arm/plat-samsung/s5p-dev-mfc.c
index ad51f85fbd01..a29272818c36 100644
--- a/arch/arm/plat-samsung/s5p-dev-mfc.c
+++ b/arch/arm/plat-samsung/s5p-dev-mfc.c
@@ -125,8 +125,8 @@ device_initcall(s5p_mfc_memory_init);
 int __init s5p_fdt_find_mfc_mem(unsigned long node, const char *uname,
 				int depth, void *data)
 {
-	__be32 *prop;
-	unsigned long len;
+	const __be32 *prop;
+	int len;
 	struct s5p_mfc_dt_meminfo *mfc_mem = data;
 
 	if (!data)
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 27bbcfc7202a..6dc93675e701 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -9,6 +9,7 @@ config ARM64
 	select ARM_AMBA
 	select ARM_ARCH_TIMER
 	select ARM_GIC
+	select ARM_GIC_V3
 	select BUILDTIME_EXTABLE_SORT
 	select CLONE_BACKWARDS
 	select COMMON_CLK
@@ -16,6 +17,7 @@ config ARM64
 	select DCACHE_WORD_ACCESS
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
+	select GENERIC_EARLY_IOREMAP
 	select GENERIC_IOMAP
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
@@ -43,6 +45,7 @@ config ARM64
 	select NO_BOOTMEM
 	select OF
 	select OF_EARLY_FLATTREE
+	select OF_RESERVED_MEM
 	select PERF_USE_VMALLOC
 	select POWER_RESET
 	select POWER_SUPPLY
@@ -85,7 +88,7 @@ config GENERIC_CSUM
 config GENERIC_CALIBRATE_DELAY
 	def_bool y
 
-config ZONE_DMA32
+config ZONE_DMA
 	def_bool y
 
 config ARCH_DMA_ADDR_T_64BIT
@@ -106,6 +109,9 @@ config IOMMU_HELPER
 config KERNEL_MODE_NEON
 	def_bool y
 
+config FIX_EARLYCON_MEM
+	def_bool y
+
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
diff --git a/arch/arm64/boot/dts/apm-storm.dtsi b/arch/arm64/boot/dts/apm-storm.dtsi
index d37d7369e260..6d4f493aac9a 100644
--- a/arch/arm64/boot/dts/apm-storm.dtsi
+++ b/arch/arm64/boot/dts/apm-storm.dtsi
@@ -176,6 +176,48 @@
 				reg-names = "csr-reg";
 				clock-output-names = "eth8clk";
 			};
+
+			sataphy1clk: sataphy1clk@1f21c000 {
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&socplldiv2 0>;
+				reg = <0x0 0x1f21c000 0x0 0x1000>;
+				reg-names = "csr-reg";
+				clock-output-names = "sataphy1clk";
+				status = "disabled";
+				csr-offset = <0x4>;
+				csr-mask = <0x00>;
+				enable-offset = <0x0>;
+				enable-mask = <0x06>;
+			};
+
+			sataphy2clk: sataphy1clk@1f22c000 {
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&socplldiv2 0>;
+				reg = <0x0 0x1f22c000 0x0 0x1000>;
+				reg-names = "csr-reg";
+				clock-output-names = "sataphy2clk";
+				status = "ok";
+				csr-offset = <0x4>;
+				csr-mask = <0x3a>;
+				enable-offset = <0x0>;
+				enable-mask = <0x06>;
+			};
+
+			sataphy3clk: sataphy1clk@1f23c000 {
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&socplldiv2 0>;
+				reg = <0x0 0x1f23c000 0x0 0x1000>;
+				reg-names = "csr-reg";
+				clock-output-names = "sataphy3clk";
+				status = "ok";
+				csr-offset = <0x4>;
+				csr-mask = <0x3a>;
+				enable-offset = <0x0>;
+				enable-mask = <0x06>;
+			};
 		};
 
 		serial0: serial@1c020000 {
@@ -187,5 +229,35 @@
 			interrupt-parent = <&gic>;
 			interrupts = <0x0 0x4c 0x4>;
 		};
+
+		phy1: phy@1f21a000 {
+			compatible = "apm,xgene-phy";
+			reg = <0x0 0x1f21a000 0x0 0x100>;
+			#phy-cells = <1>;
+			clocks = <&sataphy1clk 0>;
+			status = "disabled";
+			apm,tx-boost-gain = <30 30 30 30 30 30>;
+			apm,tx-eye-tuning = <2 10 10 2 10 10>;
+		};
+
+		phy2: phy@1f22a000 {
+			compatible = "apm,xgene-phy";
+			reg = <0x0 0x1f22a000 0x0 0x100>;
+			#phy-cells = <1>;
+			clocks = <&sataphy2clk 0>;
+			status = "ok";
+			apm,tx-boost-gain = <30 30 30 30 30 30>;
+			apm,tx-eye-tuning = <1 10 10 2 10 10>;
+		};
+
+		phy3: phy@1f23a000 {
+			compatible = "apm,xgene-phy";
+			reg = <0x0 0x1f23a000 0x0 0x100>;
+			#phy-cells = <1>;
+			clocks = <&sataphy3clk 0>;
+			status = "ok";
+			apm,tx-boost-gain = <31 31 31 31 31 31>;
+			apm,tx-eye-tuning = <2 10 10 2 10 10>;
+		};
 	};
 };
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 71c53ecfcc3a..27e3c6bccf62 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -10,6 +10,7 @@ generic-y += delay.h
 generic-y += div64.h
 generic-y += dma.h
 generic-y += emergency-restart.h
+generic-y += early_ioremap.h
 generic-y += errno.h
 generic-y += ftrace.h
 generic-y += hw_irq.h
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index 0237f0867e37..9c48d74652cb 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -162,7 +162,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
  */
 #define ATOMIC64_INIT(i) { (i) }
 
-#define atomic64_read(v)	(*(volatile long long *)&(v)->counter)
+#define atomic64_read(v)	(*(volatile long *)&(v)->counter)
 #define atomic64_set(v,i)	(((v)->counter) = (i))
 
 static inline void atomic64_add(u64 i, atomic64_t *v)
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 409ca370cfe2..5c436e3457dd 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -27,7 +27,7 @@
 #define isb()		asm volatile("isb" : : : "memory")
 #define dsb(opt)	asm volatile("dsb sy" : : : "memory")
 
-#define mb()		dsb()
+#define mb()		dsb(sy)
 #define rmb()		asm volatile("dsb ld" : : : "memory")
 #define wmb()		asm volatile("dsb st" : : : "memory")
 
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index 889324981aa4..f2defe1c380c 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -85,6 +85,13 @@ static inline void flush_cache_page(struct vm_area_struct *vma,
 }
 
 /*
+ * Cache maintenance functions used by the DMA API. No to be used directly.
+ */
+extern void __dma_map_area(const void *, size_t, int);
+extern void __dma_unmap_area(const void *, size_t, int);
+extern void __dma_flush_range(const void *, const void *);
+
+/*
  * Copy user data from/to a page which is mapped into a different
  * processes address space.  Really, we want to allow our "user
  * space" model to handle this.
@@ -116,7 +123,7 @@ extern void flush_dcache_page(struct page *);
 static inline void __flush_icache_all(void)
 {
 	asm("ic	ialluis");
-	dsb();
+	dsb(ish);
 }
 
 #define flush_dcache_mmap_lock(mapping) \
@@ -131,19 +138,10 @@ static inline void __flush_icache_all(void)
 #define flush_icache_page(vma,page)	do { } while (0)
 
 /*
- * flush_cache_vmap() is used when creating mappings (eg, via vmap,
- * vmalloc, ioremap etc) in kernel space for pages.  On non-VIPT
- * caches, since the direct-mappings of these pages may contain cached
- * data, we need to do a full cache flush to ensure that writebacks
- * don't corrupt data placed into these pages via the new mappings.
+ * Not required on AArch64 (PIPT or VIPT non-aliasing D-cache).
  */
 static inline void flush_cache_vmap(unsigned long start, unsigned long end)
 {
-	/*
-	 * set_pte_at() called from vmap_pte_range() does not
-	 * have a DSB after cleaning the cache line.
-	 */
-	dsb();
 }
 
 static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index 57c0fa7bf711..ddb9d7830558 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -72,7 +72,12 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 }
 
 #define xchg(ptr,x) \
-	((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
+({ \
+	__typeof__(*(ptr)) __ret; \
+	__ret = (__typeof__(*(ptr))) \
+		__xchg((unsigned long)(x), (ptr), sizeof(*(ptr))); \
+	__ret; \
+})
 
 static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 				      unsigned long new, int size)
diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h
index fd0c0c0e447a..3a4572ec3273 100644
--- a/arch/arm64/include/asm/dma-mapping.h
+++ b/arch/arm64/include/asm/dma-mapping.h
@@ -30,6 +30,8 @@
 
 #define DMA_ERROR_CODE	(~(dma_addr_t)0)
 extern struct dma_map_ops *dma_ops;
+extern struct dma_map_ops coherent_swiotlb_dma_ops;
+extern struct dma_map_ops noncoherent_swiotlb_dma_ops;
 
 static inline struct dma_map_ops *__generic_dma_ops(struct device *dev)
 {
@@ -47,6 +49,11 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 		return __generic_dma_ops(dev);
 }
 
+static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops)
+{
+	dev->archdata.dma_ops = ops;
+}
+
 #include <asm-generic/dma-mapping-common.h>
 
 static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h
new file mode 100644
index 000000000000..5f7bfe6df723
--- /dev/null
+++ b/arch/arm64/include/asm/fixmap.h
@@ -0,0 +1,67 @@
+/*
+ * fixmap.h: compile-time virtual memory allocation
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1998 Ingo Molnar
+ * Copyright (C) 2013 Mark Salter <msalter@redhat.com>
+ *
+ * Adapted from arch/x86_64 version.
+ *
+ */
+
+#ifndef _ASM_ARM64_FIXMAP_H
+#define _ASM_ARM64_FIXMAP_H
+
+#ifndef __ASSEMBLY__
+#include <linux/kernel.h>
+#include <asm/page.h>
+
+/*
+ * Here we define all the compile-time 'special' virtual
+ * addresses. The point is to have a constant address at
+ * compile time, but to set the physical address only
+ * in the boot process.
+ *
+ * These 'compile-time allocated' memory buffers are
+ * page-sized. Use set_fixmap(idx,phys) to associate
+ * physical memory with fixmap indices.
+ *
+ */
+enum fixed_addresses {
+	FIX_EARLYCON_MEM_BASE,
+	__end_of_permanent_fixed_addresses,
+
+	/*
+	 * Temporary boot-time mappings, used by early_ioremap(),
+	 * before ioremap() is functional.
+	 */
+#ifdef CONFIG_ARM64_64K_PAGES
+#define NR_FIX_BTMAPS		4
+#else
+#define NR_FIX_BTMAPS		64
+#endif
+#define FIX_BTMAPS_SLOTS	7
+#define TOTAL_FIX_BTMAPS	(NR_FIX_BTMAPS * FIX_BTMAPS_SLOTS)
+
+	FIX_BTMAP_END = __end_of_permanent_fixed_addresses,
+	FIX_BTMAP_BEGIN = FIX_BTMAP_END + TOTAL_FIX_BTMAPS - 1,
+	__end_of_fixed_addresses
+};
+
+#define FIXADDR_SIZE	(__end_of_permanent_fixed_addresses << PAGE_SHIFT)
+#define FIXADDR_START	(FIXADDR_TOP - FIXADDR_SIZE)
+
+#define FIXMAP_PAGE_IO     __pgprot(PROT_DEVICE_nGnRE)
+
+extern void __early_set_fixmap(enum fixed_addresses idx,
+			       phys_addr_t phys, pgprot_t flags);
+
+#define __set_fixmap __early_set_fixmap
+
+#include <asm-generic/fixmap.h>
+
+#endif /* !__ASSEMBLY__ */
+#endif /* _ASM_ARM64_FIXMAP_H */
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 4cc813eddacb..6d5e328575d4 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -27,6 +27,7 @@
 #include <asm/byteorder.h>
 #include <asm/barrier.h>
 #include <asm/pgtable.h>
+#include <asm/early_ioremap.h>
 
 #include <xen/xen.h>
 
@@ -229,19 +230,11 @@ extern void __iomem *__ioremap(phys_addr_t phys_addr, size_t size, pgprot_t prot
 extern void __iounmap(volatile void __iomem *addr);
 extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size);
 
-#define PROT_DEFAULT		(PTE_TYPE_PAGE | PTE_AF | PTE_DIRTY)
-#define PROT_DEVICE_nGnRE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRE))
-#define PROT_NORMAL_NC		(PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL_NC))
-#define PROT_NORMAL		(PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL))
-
 #define ioremap(addr, size)		__ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE))
 #define ioremap_nocache(addr, size)	__ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE))
 #define ioremap_wc(addr, size)		__ioremap((addr), (size), __pgprot(PROT_NORMAL_NC))
 #define iounmap				__iounmap
 
-#define PROT_SECT_DEFAULT	(PMD_TYPE_SECT | PMD_SECT_AF)
-#define PROT_SECT_DEVICE_nGnRE	(PROT_SECT_DEFAULT | PTE_PXN | PTE_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE))
-
 #define ARCH_HAS_IOREMAP_WC
 #include <asm-generic/iomap.h>
 
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 9dc5dc39fded..993bce527b85 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -49,7 +49,7 @@
 #define PAGE_OFFSET		(UL(0xffffffffffffffff) << (VA_BITS - 1))
 #define MODULES_END		(PAGE_OFFSET)
 #define MODULES_VADDR		(MODULES_END - SZ_64M)
-#define EARLYCON_IOBASE		(MODULES_VADDR - SZ_4M)
+#define FIXADDR_TOP		(MODULES_VADDR - SZ_2M - PAGE_SIZE)
 #define TASK_SIZE_64		(UL(1) << VA_BITS)
 
 #ifdef CONFIG_COMPAT
@@ -138,6 +138,7 @@ static inline void *phys_to_virt(phys_addr_t x)
 #define __pa(x)			__virt_to_phys((unsigned long)(x))
 #define __va(x)			((void *)__phys_to_virt((phys_addr_t)(x)))
 #define pfn_to_kaddr(pfn)	__va((pfn) << PAGE_SHIFT)
+#define virt_to_pfn(x)      __phys_to_pfn(__virt_to_phys(x))
 
 /*
  *  virt_to_page(k)	convert a _valid_ virtual address to struct page *
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 2494fc01896a..c2f006c48bdb 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -22,10 +22,16 @@ typedef struct {
 	void *vdso;
 } mm_context_t;
 
+#define INIT_MM_CONTEXT(name) \
+	.context.id_lock = __RAW_SPIN_LOCK_UNLOCKED(name.context.id_lock),
+
 #define ASID(mm)	((mm)->context.id & 0xffff)
 
 extern void paging_init(void);
 extern void setup_mm_for_reboot(void);
 extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt);
+extern void init_mem_pgprot(void);
+/* create an identity mapping for memory (or io if map_io is true) */
+extern void create_id_mapping(phys_addr_t addr, phys_addr_t size, int map_io);
 
 #endif
diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
index 46bf66628b6a..a6331e6a92b5 100644
--- a/arch/arm64/include/asm/page.h
+++ b/arch/arm64/include/asm/page.h
@@ -31,6 +31,15 @@
 /* We do define AT_SYSINFO_EHDR but don't use the gate mechanism */
 #define __HAVE_ARCH_GATE_AREA		1
 
+/*
+ * The idmap and swapper page tables need some space reserved in the kernel
+ * image. The idmap only requires a pgd and a next level table to (section) map
+ * the kernel, while the swapper also maps the FDT and requires an additional
+ * table to map an early UART. See __create_page_tables for more information.
+ */
+#define SWAPPER_DIR_SIZE	(3 * PAGE_SIZE)
+#define IDMAP_DIR_SIZE		(2 * PAGE_SIZE)
+
 #ifndef __ASSEMBLY__
 
 #ifdef CONFIG_ARM64_64K_PAGES
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index aa3917c8b623..33608f263ad0 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -52,66 +52,60 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
 #endif
 #define pgd_ERROR(pgd)		__pgd_error(__FILE__, __LINE__, pgd_val(pgd))
 
-/*
- * The pgprot_* and protection_map entries will be fixed up at runtime to
- * include the cachable and bufferable bits based on memory policy, as well as
- * any architecture dependent bits like global/ASID and SMP shared mapping
- * bits.
- */
-#define _PAGE_DEFAULT		PTE_TYPE_PAGE | PTE_AF
+#ifdef CONFIG_SMP
+#define PROT_DEFAULT		(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
+#define PROT_SECT_DEFAULT	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
+#else
+#define PROT_DEFAULT		(PTE_TYPE_PAGE | PTE_AF)
+#define PROT_SECT_DEFAULT	(PMD_TYPE_SECT | PMD_SECT_AF)
+#endif
 
-extern pgprot_t pgprot_default;
+#define PROT_DEVICE_nGnRE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRE))
+#define PROT_NORMAL_NC		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL_NC))
+#define PROT_NORMAL		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL))
 
-#define __pgprot_modify(prot,mask,bits) \
-	__pgprot((pgprot_val(prot) & ~(mask)) | (bits))
+#define PROT_SECT_DEVICE_nGnRE	(PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE))
+#define PROT_SECT_NORMAL	(PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL))
+#define PROT_SECT_NORMAL_EXEC	(PROT_SECT_DEFAULT | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL))
 
-#define _MOD_PROT(p, b)		__pgprot_modify(p, 0, b)
+#define _PAGE_DEFAULT		(PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL))
 
-#define PAGE_NONE		__pgprot_modify(pgprot_default, PTE_TYPE_MASK, PTE_PROT_NONE | PTE_PXN | PTE_UXN)
-#define PAGE_SHARED		_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
-#define PAGE_SHARED_EXEC	_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE)
-#define PAGE_COPY		_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
-#define PAGE_COPY_EXEC		_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN)
-#define PAGE_READONLY		_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
-#define PAGE_READONLY_EXEC	_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN)
-#define PAGE_KERNEL		_MOD_PROT(pgprot_default, PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE)
-#define PAGE_KERNEL_EXEC	_MOD_PROT(pgprot_default, PTE_UXN | PTE_DIRTY | PTE_WRITE)
+#define PAGE_KERNEL		__pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE)
+#define PAGE_KERNEL_EXEC	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE)
 
-#define PAGE_HYP		_MOD_PROT(pgprot_default, PTE_HYP)
+#define PAGE_HYP		__pgprot(_PAGE_DEFAULT | PTE_HYP)
 #define PAGE_HYP_DEVICE		__pgprot(PROT_DEVICE_nGnRE | PTE_HYP)
 
-#define PAGE_S2			__pgprot_modify(pgprot_default, PTE_S2_MEMATTR_MASK, PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY)
+#define PAGE_S2			__pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY)
 #define PAGE_S2_DEVICE		__pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDWR | PTE_UXN)
 
-#define __PAGE_NONE		__pgprot(((_PAGE_DEFAULT) & ~PTE_TYPE_MASK) | PTE_PROT_NONE | PTE_PXN | PTE_UXN)
-#define __PAGE_SHARED		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
-#define __PAGE_SHARED_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE)
-#define __PAGE_COPY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
-#define __PAGE_COPY_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN)
-#define __PAGE_READONLY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
-#define __PAGE_READONLY_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN)
-
-#endif /* __ASSEMBLY__ */
-
-#define __P000  __PAGE_NONE
-#define __P001  __PAGE_READONLY
-#define __P010  __PAGE_COPY
-#define __P011  __PAGE_COPY
-#define __P100  __PAGE_READONLY_EXEC
-#define __P101  __PAGE_READONLY_EXEC
-#define __P110  __PAGE_COPY_EXEC
-#define __P111  __PAGE_COPY_EXEC
-
-#define __S000  __PAGE_NONE
-#define __S001  __PAGE_READONLY
-#define __S010  __PAGE_SHARED
-#define __S011  __PAGE_SHARED
-#define __S100  __PAGE_READONLY_EXEC
-#define __S101  __PAGE_READONLY_EXEC
-#define __S110  __PAGE_SHARED_EXEC
-#define __S111  __PAGE_SHARED_EXEC
+#define PAGE_NONE		__pgprot(((_PAGE_DEFAULT) & ~PTE_TYPE_MASK) | PTE_PROT_NONE | PTE_PXN | PTE_UXN)
+#define PAGE_SHARED		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
+#define PAGE_SHARED_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE)
+#define PAGE_COPY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
+#define PAGE_COPY_EXEC		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN)
+#define PAGE_READONLY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
+#define PAGE_READONLY_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN)
+#define PAGE_EXECONLY		__pgprot(_PAGE_DEFAULT | PTE_NG | PTE_PXN)
+
+#define __P000  PAGE_NONE
+#define __P001  PAGE_READONLY
+#define __P010  PAGE_COPY
+#define __P011  PAGE_COPY
+#define __P100  PAGE_READONLY_EXEC
+#define __P101  PAGE_READONLY_EXEC
+#define __P110  PAGE_COPY_EXEC
+#define __P111  PAGE_COPY_EXEC
+
+#define __S000  PAGE_NONE
+#define __S001  PAGE_READONLY
+#define __S010  PAGE_SHARED
+#define __S011  PAGE_SHARED
+#define __S100  PAGE_READONLY_EXEC
+#define __S101  PAGE_READONLY_EXEC
+#define __S110  PAGE_SHARED_EXEC
+#define __S111  PAGE_SHARED_EXEC
 
-#ifndef __ASSEMBLY__
 /*
  * ZERO_PAGE is a global shared page that is always zero: used
  * for zero-mapped memory areas etc..
@@ -145,6 +139,8 @@ extern struct page *empty_zero_page;
 
 #define pte_valid_user(pte) \
 	((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER))
+#define pte_valid_not_user(pte) \
+	((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID)
 
 static inline pte_t pte_wrprotect(pte_t pte)
 {
@@ -191,6 +187,15 @@ static inline pte_t pte_mkspecial(pte_t pte)
 static inline void set_pte(pte_t *ptep, pte_t pte)
 {
 	*ptep = pte;
+
+	/*
+	 * Only if the new pte is valid and kernel, otherwise TLB maintenance
+	 * or update_mmu_cache() have the necessary barriers.
+	 */
+	if (pte_valid_not_user(pte)) {
+		dsb(ishst);
+		isb();
+	}
 }
 
 extern void __sync_icache_dcache(pte_t pteval, unsigned long addr);
@@ -199,7 +204,7 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep, pte_t pte)
 {
 	if (pte_valid_user(pte)) {
-		if (pte_exec(pte))
+		if (!pte_special(pte) && pte_exec(pte))
 			__sync_icache_dcache(pte, addr);
 		if (pte_dirty(pte) && pte_write(pte))
 			pte_val(pte) &= ~PTE_RDONLY;
@@ -227,36 +232,36 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 
 #define __HAVE_ARCH_PTE_SPECIAL
 
-/*
- * Software PMD bits for THP
- */
+static inline pte_t pmd_pte(pmd_t pmd)
+{
+	return __pte(pmd_val(pmd));
+}
 
-#define PMD_SECT_DIRTY		(_AT(pmdval_t, 1) << 55)
-#define PMD_SECT_SPLITTING	(_AT(pmdval_t, 1) << 57)
+static inline pmd_t pte_pmd(pte_t pte)
+{
+	return __pmd(pte_val(pte));
+}
 
 /*
  * THP definitions.
  */
-#define pmd_young(pmd)		(pmd_val(pmd) & PMD_SECT_AF)
-
-#define __HAVE_ARCH_PMD_WRITE
-#define pmd_write(pmd)		(!(pmd_val(pmd) & PMD_SECT_RDONLY))
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define pmd_trans_huge(pmd)	(pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT))
-#define pmd_trans_splitting(pmd) (pmd_val(pmd) & PMD_SECT_SPLITTING)
+#define pmd_trans_splitting(pmd)	pte_special(pmd_pte(pmd))
 #endif
 
-#define PMD_BIT_FUNC(fn,op) \
-static inline pmd_t pmd_##fn(pmd_t pmd) { pmd_val(pmd) op; return pmd; }
+#define pmd_young(pmd)		pte_young(pmd_pte(pmd))
+#define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
+#define pmd_mksplitting(pmd)	pte_pmd(pte_mkspecial(pmd_pte(pmd)))
+#define pmd_mkold(pmd)		pte_pmd(pte_mkold(pmd_pte(pmd)))
+#define pmd_mkwrite(pmd)	pte_pmd(pte_mkwrite(pmd_pte(pmd)))
+#define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
+#define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
+#define pmd_mknotpresent(pmd)	(__pmd(pmd_val(pmd) &= ~PMD_TYPE_MASK))
 
-PMD_BIT_FUNC(wrprotect,	|= PMD_SECT_RDONLY);
-PMD_BIT_FUNC(mkold,	&= ~PMD_SECT_AF);
-PMD_BIT_FUNC(mksplitting, |= PMD_SECT_SPLITTING);
-PMD_BIT_FUNC(mkwrite,   &= ~PMD_SECT_RDONLY);
-PMD_BIT_FUNC(mkdirty,   |= PMD_SECT_DIRTY);
-PMD_BIT_FUNC(mkyoung,   |= PMD_SECT_AF);
-PMD_BIT_FUNC(mknotpresent, &= ~PMD_TYPE_MASK);
+#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write(pmd)		pte_write(pmd_pte(pmd))
 
 #define pmd_mkhuge(pmd)		(__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))
 
@@ -266,15 +271,6 @@ PMD_BIT_FUNC(mknotpresent, &= ~PMD_TYPE_MASK);
 
 #define pmd_page(pmd)           pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK))
 
-static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
-{
-	const pmdval_t mask = PMD_SECT_USER | PMD_SECT_PXN | PMD_SECT_UXN |
-			      PMD_SECT_RDONLY | PMD_SECT_PROT_NONE |
-			      PMD_SECT_VALID;
-	pmd_val(pmd) = (pmd_val(pmd) & ~mask) | (pgprot_val(newprot) & mask);
-	return pmd;
-}
-
 #define set_pmd_at(mm, addr, pmdp, pmd)	set_pmd(pmdp, pmd)
 
 static inline int has_transparent_hugepage(void)
@@ -282,15 +278,16 @@ static inline int has_transparent_hugepage(void)
 	return 1;
 }
 
+#define __pgprot_modify(prot,mask,bits) \
+	__pgprot((pgprot_val(prot) & ~(mask)) | (bits))
+
 /*
  * Mark the prot value as uncacheable and unbufferable.
  */
 #define pgprot_noncached(prot) \
-	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRnE))
+	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRnE) | PTE_PXN | PTE_UXN)
 #define pgprot_writecombine(prot) \
-	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC))
-#define pgprot_dmacoherent(prot) \
-	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC))
+	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN)
 #define __HAVE_PHYS_MEM_ACCESS_PROT
 struct file;
 extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
@@ -310,7 +307,8 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
 {
 	*pmdp = pmd;
-	dsb();
+	dsb(ishst);
+	isb();
 }
 
 static inline void pmd_clear(pmd_t *pmdp)
@@ -340,7 +338,8 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
 static inline void set_pud(pud_t *pudp, pud_t pud)
 {
 	*pudp = pud;
-	dsb();
+	dsb(ishst);
+	isb();
 }
 
 static inline void pud_clear(pud_t *pudp)
@@ -383,12 +382,14 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 	return pte;
 }
 
+static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
+{
+	return pte_pmd(pte_modify(pmd_pte(pmd), newprot));
+}
+
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
 
-#define SWAPPER_DIR_SIZE	(3 * PAGE_SIZE)
-#define IDMAP_DIR_SIZE		(2 * PAGE_SIZE)
-
 /*
  * Encode and decode a swap entry:
  *	bits 0-1:	present (must be zero)
@@ -412,7 +413,7 @@ extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
 
 /*
  * Ensure that there are not more swap files than can be encoded in the kernel
- * the PTEs.
+ * PTEs.
  */
 #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > __SWP_TYPE_BITS)
 
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
new file mode 100644
index 000000000000..5c89df0acbcb
--- /dev/null
+++ b/arch/arm64/include/asm/sysreg.h
@@ -0,0 +1,60 @@
+/*
+ * Macros for accessing system registers with older binutils.
+ *
+ * Copyright (C) 2014 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ASM_SYSREG_H
+#define __ASM_SYSREG_H
+
+#define sys_reg(op0, op1, crn, crm, op2) \
+	((((op0)-2)<<19)|((op1)<<16)|((crn)<<12)|((crm)<<8)|((op2)<<5))
+
+#ifdef __ASSEMBLY__
+
+	.irp	num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30
+	.equ	__reg_num_x\num, \num
+	.endr
+	.equ	__reg_num_xzr, 31
+
+	.macro	mrs_s, rt, sreg
+	.inst	0xd5300000|(\sreg)|(__reg_num_\rt)
+	.endm
+
+	.macro	msr_s, sreg, rt
+	.inst	0xd5100000|(\sreg)|(__reg_num_\rt)
+	.endm
+
+#else
+
+asm(
+"	.irp	num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30\n"
+"	.equ	__reg_num_x\\num, \\num\n"
+"	.endr\n"
+"	.equ	__reg_num_xzr, 31\n"
+"\n"
+"	.macro	mrs_s, rt, sreg\n"
+"	.inst	0xd5300000|(\\sreg)|(__reg_num_\\rt)\n"
+"	.endm\n"
+"\n"
+"	.macro	msr_s, sreg, rt\n"
+"	.inst	0xd5100000|(\\sreg)|(__reg_num_\\rt)\n"
+"	.endm\n"
+);
+
+#endif
+
+#endif	/* __ASM_SYSREG_H */
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index 8b482035cfc2..3796ea6bb734 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -72,9 +72,9 @@ extern struct cpu_tlb_fns cpu_tlb;
  */
 static inline void flush_tlb_all(void)
 {
-	dsb();
+	dsb(ishst);
 	asm("tlbi	vmalle1is");
-	dsb();
+	dsb(ish);
 	isb();
 }
 
@@ -82,9 +82,9 @@ static inline void flush_tlb_mm(struct mm_struct *mm)
 {
 	unsigned long asid = (unsigned long)ASID(mm) << 48;
 
-	dsb();
+	dsb(ishst);
 	asm("tlbi	aside1is, %0" : : "r" (asid));
-	dsb();
+	dsb(ish);
 }
 
 static inline void flush_tlb_page(struct vm_area_struct *vma,
@@ -93,16 +93,37 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
 	unsigned long addr = uaddr >> 12 |
 		((unsigned long)ASID(vma->vm_mm) << 48);
 
-	dsb();
+	dsb(ishst);
 	asm("tlbi	vae1is, %0" : : "r" (addr));
-	dsb();
+	dsb(ish);
 }
 
-/*
- * Convert calls to our calling convention.
- */
-#define flush_tlb_range(vma,start,end)	__cpu_flush_user_tlb_range(start,end,vma)
-#define flush_tlb_kernel_range(s,e)	__cpu_flush_kern_tlb_range(s,e)
+static inline void flush_tlb_range(struct vm_area_struct *vma,
+					unsigned long start, unsigned long end)
+{
+	unsigned long asid = (unsigned long)ASID(vma->vm_mm) << 48;
+	unsigned long addr;
+	start = asid | (start >> 12);
+	end = asid | (end >> 12);
+
+	dsb(ishst);
+	for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12))
+		asm("tlbi vae1is, %0" : : "r"(addr));
+	dsb(ish);
+}
+
+static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	unsigned long addr;
+	start >>= 12;
+	end >>= 12;
+
+	dsb(ishst);
+	for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12))
+		asm("tlbi vaae1is, %0" : : "r"(addr));
+	dsb(ish);
+	isb();
+}
 
 /*
  * On AArch64, the cache coherency is handled via the set_pte_at() function.
@@ -111,10 +132,10 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
 				    unsigned long addr, pte_t *ptep)
 {
 	/*
-	 * set_pte() does not have a DSB, so make sure that the page table
-	 * write is visible.
+	 * set_pte() does not have a DSB for user mappings, so make sure that
+	 * the page table write is visible.
 	 */
-	dsb();
+	dsb(ishst);
 }
 
 #define update_mmu_cache_pmd(vma, address, pmd) do { } while (0)
diff --git a/arch/arm64/kernel/early_printk.c b/arch/arm64/kernel/early_printk.c
index fbb6e1843659..ffbbdde7aba1 100644
--- a/arch/arm64/kernel/early_printk.c
+++ b/arch/arm64/kernel/early_printk.c
@@ -26,6 +26,8 @@
 #include <linux/amba/serial.h>
 #include <linux/serial_reg.h>
 
+#include <asm/fixmap.h>
+
 static void __iomem *early_base;
 static void (*printch)(char ch);
 
@@ -141,8 +143,10 @@ static int __init setup_early_printk(char *buf)
 	}
 	/* no options parsing yet */
 
-	if (paddr)
-		early_base = early_io_map(paddr, EARLYCON_IOBASE);
+	if (paddr) {
+		set_fixmap_io(FIX_EARLYCON_MEM_BASE, paddr);
+		early_base = (void __iomem *)fix_to_virt(FIX_EARLYCON_MEM_BASE);
+	}
 
 	printch = match->printch;
 	early_console = &early_console_dev;
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 0b281fffda51..650ec9ea42fd 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -22,10 +22,12 @@
 
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/irqchip/arm-gic-v3.h>
 
 #include <asm/assembler.h>
 #include <asm/ptrace.h>
 #include <asm/asm-offsets.h>
+#include <asm/cache.h>
 #include <asm/cputype.h>
 #include <asm/memory.h>
 #include <asm/thread_info.h>
@@ -34,29 +36,17 @@
 #include <asm/page.h>
 #include <asm/virt.h>
 
-/*
- * swapper_pg_dir is the virtual address of the initial page table. We place
- * the page tables 3 * PAGE_SIZE below KERNEL_RAM_VADDR. The idmap_pg_dir has
- * 2 pages and is placed below swapper_pg_dir.
- */
 #define KERNEL_RAM_VADDR	(PAGE_OFFSET + TEXT_OFFSET)
 
 #if (KERNEL_RAM_VADDR & 0xfffff) != 0x80000
 #error KERNEL_RAM_VADDR must start at 0xXXX80000
 #endif
 
-#define SWAPPER_DIR_SIZE	(3 * PAGE_SIZE)
-#define IDMAP_DIR_SIZE		(2 * PAGE_SIZE)
-
-	.globl	swapper_pg_dir
-	.equ	swapper_pg_dir, KERNEL_RAM_VADDR - SWAPPER_DIR_SIZE
-
-	.globl	idmap_pg_dir
-	.equ	idmap_pg_dir, swapper_pg_dir - IDMAP_DIR_SIZE
-
-	.macro	pgtbl, ttb0, ttb1, phys
-	add	\ttb1, \phys, #TEXT_OFFSET - SWAPPER_DIR_SIZE
-	sub	\ttb0, \ttb1, #IDMAP_DIR_SIZE
+	.macro	pgtbl, ttb0, ttb1, virt_to_phys
+	ldr	\ttb1, =swapper_pg_dir
+	ldr	\ttb0, =idmap_pg_dir
+	add	\ttb1, \ttb1, \virt_to_phys
+	add	\ttb0, \ttb0, \virt_to_phys
 	.endm
 
 #ifdef CONFIG_ARM64_64K_PAGES
@@ -183,6 +173,23 @@ CPU_LE(	bic	x0, x0, #(3 << 24)	)	// Clear the EE and E0E bits for EL1
 	msr	cnthctl_el2, x0
 	msr	cntvoff_el2, xzr		// Clear virtual offset
 
+#ifdef CONFIG_ARM_GIC_V3
+	/* GICv3 system register access */
+	mrs	x0, id_aa64pfr0_el1
+	ubfx	x0, x0, #24, #4
+	cmp	x0, #1
+	b.ne	3f
+
+	mrs_s	x0, ICC_SRE_EL2
+	orr	x0, x0, #ICC_SRE_EL2_SRE	// Set ICC_SRE_EL2.SRE==1
+	orr	x0, x0, #ICC_SRE_EL2_ENABLE	// Set ICC_SRE_EL2.Enable==1
+	msr_s	ICC_SRE_EL2, x0
+	isb					// Make sure SRE is now set
+	msr_s	ICH_HCR_EL2, xzr		// Reset ICC_HCR_EL2 to defaults
+
+3:
+#endif
+
 	/* Populate ID registers. */
 	mrs	x0, midr_el1
 	mrs	x1, mpidr_el1
@@ -240,8 +247,9 @@ ENDPROC(set_cpu_boot_mode_flag)
  * This is not in .bss, because we set it sufficiently early that the boot-time
  * zeroing of .bss would clobber it.
  */
-	.pushsection	.data
+	.pushsection	.data..cacheline_aligned
 ENTRY(__boot_cpu_mode)
+	.align	L1_CACHE_SHIFT
 	.long	BOOT_CPU_MODE_EL2
 	.long	0
 	.popsection
@@ -298,7 +306,7 @@ ENTRY(secondary_startup)
 	mov	x23, x0				// x23=current cpu_table
 	cbz	x23, __error_p			// invalid processor (x23=0)?
 
-	pgtbl	x25, x26, x24			// x25=TTBR0, x26=TTBR1
+	pgtbl	x25, x26, x28			// x25=TTBR0, x26=TTBR1
 	ldr	x12, [x23, #CPU_INFO_SETUP]
 	add	x12, x12, x28			// __virt_to_phys
 	blr	x12				// initialise processor
@@ -340,8 +348,13 @@ ENDPROC(__enable_mmu)
  *  x27 = *virtual* address to jump to upon completion
  *
  * other registers depend on the function called upon completion
+ *
+ * We align the entire function to the smallest power of two larger than it to
+ * ensure it fits within a single block map entry. Otherwise were PHYS_OFFSET
+ * close to the end of a 512MB or 1GB block we might require an additional
+ * table to map the entire function.
  */
-	.align	6
+	.align	4
 __turn_mmu_on:
 	msr	sctlr_el1, x0
 	isb
@@ -384,26 +397,18 @@ ENDPROC(__calc_phys_offset)
  * Preserves:	tbl, flags
  * Corrupts:	phys, start, end, pstate
  */
-	.macro	create_block_map, tbl, flags, phys, start, end, idmap=0
+	.macro	create_block_map, tbl, flags, phys, start, end
 	lsr	\phys, \phys, #BLOCK_SHIFT
-	.if	\idmap
-	and	\start, \phys, #PTRS_PER_PTE - 1	// table index
-	.else
 	lsr	\start, \start, #BLOCK_SHIFT
 	and	\start, \start, #PTRS_PER_PTE - 1	// table index
-	.endif
 	orr	\phys, \flags, \phys, lsl #BLOCK_SHIFT	// table entry
-	.ifnc	\start,\end
 	lsr	\end, \end, #BLOCK_SHIFT
 	and	\end, \end, #PTRS_PER_PTE - 1		// table end index
-	.endif
 9999:	str	\phys, [\tbl, \start, lsl #3]		// store the entry
-	.ifnc	\start,\end
 	add	\start, \start, #1			// next entry
 	add	\phys, \phys, #BLOCK_SIZE		// next block
 	cmp	\start, \end
 	b.ls	9999b
-	.endif
 	.endm
 
 /*
@@ -412,10 +417,19 @@ ENDPROC(__calc_phys_offset)
  *   - identity mapping to enable the MMU (low address, TTBR0)
  *   - first few MB of the kernel linear mapping to jump to once the MMU has
  *     been enabled, including the FDT blob (TTBR1)
- *   - UART mapping if CONFIG_EARLY_PRINTK is enabled (TTBR1)
+ *   - pgd entry for fixed mappings (TTBR1)
  */
 __create_page_tables:
-	pgtbl	x25, x26, x24			// idmap_pg_dir and swapper_pg_dir addresses
+	pgtbl	x25, x26, x28			// idmap_pg_dir and swapper_pg_dir addresses
+	mov	x27, lr
+
+	/*
+	 * Invalidate the idmap and swapper page tables to avoid potential
+	 * dirty cache lines being evicted.
+	 */
+	mov	x0, x25
+	add	x1, x26, #SWAPPER_DIR_SIZE
+	bl	__inval_cache_range
 
 	/*
 	 * Clear the idmap and swapper page tables.
@@ -435,9 +449,13 @@ __create_page_tables:
 	 * Create the identity mapping.
 	 */
 	add	x0, x25, #PAGE_SIZE		// section table address
-	adr	x3, __turn_mmu_on		// virtual/physical address
+	ldr	x3, =KERNEL_START
+	add	x3, x3, x28			// __pa(KERNEL_START)
 	create_pgd_entry x25, x0, x3, x5, x6
-	create_block_map x0, x7, x3, x5, x5, idmap=1
+	ldr	x6, =KERNEL_END
+	mov	x5, x3				// __pa(KERNEL_START)
+	add	x6, x6, x28			// __pa(KERNEL_END)
+	create_block_map x0, x7, x3, x5, x6
 
 	/*
 	 * Map the kernel image (starting with PHYS_OFFSET).
@@ -445,7 +463,7 @@ __create_page_tables:
 	add	x0, x26, #PAGE_SIZE		// section table address
 	mov	x5, #PAGE_OFFSET
 	create_pgd_entry x26, x0, x5, x3, x6
-	ldr	x6, =KERNEL_END - 1
+	ldr	x6, =KERNEL_END
 	mov	x3, x24				// phys offset
 	create_block_map x0, x7, x3, x5, x6
 
@@ -465,15 +483,23 @@ __create_page_tables:
 	sub	x6, x6, #1			// inclusive range
 	create_block_map x0, x7, x3, x5, x6
 1:
-#ifdef CONFIG_EARLY_PRINTK
 	/*
-	 * Create the pgd entry for the UART mapping. The full mapping is done
-	 * later based earlyprintk kernel parameter.
+	 * Create the pgd entry for the fixed mappings.
 	 */
-	ldr	x5, =EARLYCON_IOBASE		// UART virtual address
+	ldr	x5, =FIXADDR_TOP		// Fixed mapping virtual address
 	add	x0, x26, #2 * PAGE_SIZE		// section table address
 	create_pgd_entry x26, x0, x5, x6, x7
-#endif
+
+	/*
+	 * Since the page tables have been populated with non-cacheable
+	 * accesses (MMU disabled), invalidate the idmap and swapper page
+	 * tables again to remove any speculatively loaded cache lines.
+	 */
+	mov	x0, x25
+	add	x1, x26, #SWAPPER_DIR_SIZE
+	bl	__inval_cache_range
+
+	mov	lr, x27
 	ret
 ENDPROC(__create_page_tables)
 	.ltorg
@@ -483,7 +509,7 @@ ENDPROC(__create_page_tables)
 __switch_data:
 	.quad	__mmap_switched
 	.quad	__bss_start			// x6
-	.quad	_end				// x7
+	.quad	__bss_stop			// x7
 	.quad	processor_id			// x4
 	.quad	__fdt_pointer			// x5
 	.quad	memstart_addr			// x6
diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S
index 0959611d9ff1..a272f335c289 100644
--- a/arch/arm64/kernel/hyp-stub.S
+++ b/arch/arm64/kernel/hyp-stub.S
@@ -19,6 +19,7 @@
 
 #include <linux/init.h>
 #include <linux/linkage.h>
+#include <linux/irqchip/arm-gic-v3.h>
 
 #include <asm/assembler.h>
 #include <asm/ptrace.h>
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 1c0a9be2ffa8..8e78cb238376 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -294,7 +294,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
 	 * Complete any pending TLB or cache maintenance on this CPU in case
 	 * the thread migrates to a different CPU.
 	 */
-	dsb();
+	dsb(ish);
 
 	/* the actual thread switch */
 	last = cpu_switch_to(prev, next);
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index c8e9effe52e1..0fe5fdf666ec 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -42,6 +42,7 @@
 #include <linux/of_fdt.h>
 #include <linux/of_platform.h>
 
+#include <asm/fixmap.h>
 #include <asm/cputype.h>
 #include <asm/elf.h>
 #include <asm/cputable.h>
@@ -327,6 +328,8 @@ void __init setup_arch(char **cmdline_p)
 
 	*cmdline_p = boot_command_line;
 
+	early_ioremap_init();
+
 	parse_early_param();
 
 	arm64_memblock_init();
@@ -360,7 +363,7 @@ static int __init arm64_device_init(void)
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 	return 0;
 }
-arch_initcall(arm64_device_init);
+arch_initcall_sync(arm64_device_init);
 
 static DEFINE_PER_CPU(struct cpu, cpu_data);
 
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 890a591f75dd..7ff2eee96c6b 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -100,8 +100,7 @@ static int restore_sigframe(struct pt_regs *regs,
 {
 	sigset_t set;
 	int i, err;
-	struct aux_context __user *aux =
-		(struct aux_context __user *)sf->uc.uc_mcontext.__reserved;
+	void *aux = sf->uc.uc_mcontext.__reserved;
 
 	err = __copy_from_user(&set, &sf->uc.uc_sigmask, sizeof(set));
 	if (err == 0)
@@ -121,8 +120,11 @@ static int restore_sigframe(struct pt_regs *regs,
 
 	err |= !valid_user_regs(&regs->user_regs);
 
-	if (err == 0)
-		err |= restore_fpsimd_context(&aux->fpsimd);
+	if (err == 0) {
+		struct fpsimd_context *fpsimd_ctx =
+			container_of(aux, struct fpsimd_context, head);
+		err |= restore_fpsimd_context(fpsimd_ctx);
+	}
 
 	return err;
 }
@@ -167,8 +169,8 @@ static int setup_sigframe(struct rt_sigframe __user *sf,
 			  struct pt_regs *regs, sigset_t *set)
 {
 	int i, err = 0;
-	struct aux_context __user *aux =
-		(struct aux_context __user *)sf->uc.uc_mcontext.__reserved;
+	void *aux = sf->uc.uc_mcontext.__reserved;
+	struct _aarch64_ctx *end;
 
 	/* set up the stack frame for unwinding */
 	__put_user_error(regs->regs[29], &sf->fp, err);
@@ -185,12 +187,17 @@ static int setup_sigframe(struct rt_sigframe __user *sf,
 
 	err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(*set));
 
-	if (err == 0)
-		err |= preserve_fpsimd_context(&aux->fpsimd);
+	if (err == 0) {
+		struct fpsimd_context *fpsimd_ctx =
+			container_of(aux, struct fpsimd_context, head);
+		err |= preserve_fpsimd_context(fpsimd_ctx);
+		aux += sizeof(*fpsimd_ctx);
+	}
 
 	/* set the "end" magic */
-	__put_user_error(0, &aux->end.magic, err);
-	__put_user_error(0, &aux->end.size, err);
+	end = aux;
+	__put_user_error(0, &end->magic, err);
+	__put_user_error(0, &end->size, err);
 
 	return err;
 }
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index 44c22805d2e2..0347d38eea29 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -30,7 +30,6 @@ extern void secondary_holding_pen(void);
 volatile unsigned long secondary_holding_pen_release = INVALID_HWID;
 
 static phys_addr_t cpu_release_addr[NR_CPUS];
-static DEFINE_RAW_SPINLOCK(boot_lock);
 
 /*
  * Write secondary_holding_pen_release in a way that is guaranteed to be
@@ -94,14 +93,6 @@ static int smp_spin_table_cpu_prepare(unsigned int cpu)
 
 static int smp_spin_table_cpu_boot(unsigned int cpu)
 {
-	unsigned long timeout;
-
-	/*
-	 * Set synchronisation state between this boot processor
-	 * and the secondary one
-	 */
-	raw_spin_lock(&boot_lock);
-
 	/*
 	 * Update the pen release flag.
 	 */
@@ -112,34 +103,7 @@ static int smp_spin_table_cpu_boot(unsigned int cpu)
 	 */
 	sev();
 
-	timeout = jiffies + (1 * HZ);
-	while (time_before(jiffies, timeout)) {
-		if (secondary_holding_pen_release == INVALID_HWID)
-			break;
-		udelay(10);
-	}
-
-	/*
-	 * Now the secondary core is starting up let it run its
-	 * calibrations, then wait for it to finish
-	 */
-	raw_spin_unlock(&boot_lock);
-
-	return secondary_holding_pen_release != INVALID_HWID ? -ENOSYS : 0;
-}
-
-void smp_spin_table_cpu_postboot(void)
-{
-	/*
-	 * Let the primary processor know we're out of the pen.
-	 */
-	write_pen_release(INVALID_HWID);
-
-	/*
-	 * Synchronise with the boot thread.
-	 */
-	raw_spin_lock(&boot_lock);
-	raw_spin_unlock(&boot_lock);
+	return 0;
 }
 
 const struct cpu_operations smp_spin_table_ops = {
@@ -147,5 +111,4 @@ const struct cpu_operations smp_spin_table_ops = {
 	.cpu_init	= smp_spin_table_cpu_init,
 	.cpu_prepare	= smp_spin_table_cpu_prepare,
 	.cpu_boot	= smp_spin_table_cpu_boot,
-	.cpu_postboot	= smp_spin_table_cpu_postboot,
 };
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index a7149cae1615..7931d6916683 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -156,11 +156,12 @@ int arch_setup_additional_pages(struct linux_binprm *bprm,
 				int uses_interp)
 {
 	struct mm_struct *mm = current->mm;
-	unsigned long vdso_base, vdso_mapping_len;
+	unsigned long vdso_base, vdso_text_len, vdso_mapping_len;
 	int ret;
 
+	vdso_text_len = vdso_pages << PAGE_SHIFT;
 	/* Be sure to map the data page */
-	vdso_mapping_len = (vdso_pages + 1) << PAGE_SHIFT;
+	vdso_mapping_len = vdso_text_len + PAGE_SIZE;
 
 	down_write(&mm->mmap_sem);
 	vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0);
@@ -170,35 +171,52 @@ int arch_setup_additional_pages(struct linux_binprm *bprm,
 	}
 	mm->context.vdso = (void *)vdso_base;
 
-	ret = install_special_mapping(mm, vdso_base, vdso_mapping_len,
+	ret = install_special_mapping(mm, vdso_base, vdso_text_len,
 				      VM_READ|VM_EXEC|
 				      VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
 				      vdso_pagelist);
-	if (ret) {
-		mm->context.vdso = NULL;
+	if (ret)
+		goto up_fail;
+
+	vdso_base += vdso_text_len;
+	ret = install_special_mapping(mm, vdso_base, PAGE_SIZE,
+				      VM_READ|VM_MAYREAD,
+				      vdso_pagelist + vdso_pages);
+	if (ret)
 		goto up_fail;
-	}
 
-up_fail:
 	up_write(&mm->mmap_sem);
+	return 0;
 
+up_fail:
+	mm->context.vdso = NULL;
+	up_write(&mm->mmap_sem);
 	return ret;
 }
 
 const char *arch_vma_name(struct vm_area_struct *vma)
 {
+	unsigned long vdso_text;
+
+	if (!vma->vm_mm)
+		return NULL;
+
+	vdso_text = (unsigned long)vma->vm_mm->context.vdso;
+
 	/*
 	 * We can re-use the vdso pointer in mm_context_t for identifying
 	 * the vectors page for compat applications. The vDSO will always
 	 * sit above TASK_UNMAPPED_BASE and so we don't need to worry about
 	 * it conflicting with the vectors base.
 	 */
-	if (vma->vm_mm && vma->vm_start == (long)vma->vm_mm->context.vdso) {
+	if (vma->vm_start == vdso_text) {
 #ifdef CONFIG_COMPAT
 		if (vma->vm_start == AARCH32_VECTORS_BASE)
 			return "[vectors]";
 #endif
 		return "[vdso]";
+	} else if (vma->vm_start == (vdso_text + (vdso_pages << PAGE_SHIFT))) {
+		return "[vvar]";
 	}
 
 	return NULL;
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index 6d20b7d162d8..84b942612051 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -47,9 +47,9 @@ $(obj-vdso): %.o: %.S
 	$(call if_changed_dep,vdsoas)
 
 # Actual build commands
-quiet_cmd_vdsold = VDSOL $@
+quiet_cmd_vdsold = VDSOL   $@
       cmd_vdsold = $(CC) $(c_flags) -Wl,-n -Wl,-T $^ -o $@
-quiet_cmd_vdsoas = VDSOA $@
+quiet_cmd_vdsoas = VDSOA   $@
       cmd_vdsoas = $(CC) $(a_flags) -c -o $@ $<
 
 # Install commands for the unstripped file
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 4ba7a55b49c7..51258bc4cb08 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -104,6 +104,13 @@ SECTIONS
 	_edata = .;
 
 	BSS_SECTION(0, 0, 0)
+
+	. = ALIGN(PAGE_SIZE);
+	idmap_pg_dir = .;
+	. += IDMAP_DIR_SIZE;
+	swapper_pg_dir = .;
+	. += SWAPPER_DIR_SIZE;
+
 	_end = .;
 
 	STABS_DEBUG
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 02e9d09e1d80..d800dbc8693a 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -70,13 +70,13 @@ static u32 get_ccsidr(u32 csselr)
 static void do_dc_cisw(u32 val)
 {
 	asm volatile("dc cisw, %x0" : : "r" (val));
-	dsb();
+	dsb(ish);
 }
 
 static void do_dc_csw(u32 val)
 {
 	asm volatile("dc csw, %x0" : : "r" (val));
-	dsb();
+	dsb(ish);
 }
 
 /* See note at ARM ARM B1.14.4 */
diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile
index b51d36401d83..3ecb56c624d3 100644
--- a/arch/arm64/mm/Makefile
+++ b/arch/arm64/mm/Makefile
@@ -1,5 +1,5 @@
 obj-y				:= dma-mapping.o extable.o fault.o init.o \
 				   cache.o copypage.o flush.o \
 				   ioremap.o mmap.o pgd.o mmu.o \
-				   context.o tlb.o proc.o
+				   context.o proc.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 1ea9f26d1b70..fda756875fa6 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -30,7 +30,7 @@
  *
  *	Corrupted registers: x0-x7, x9-x11
  */
-ENTRY(__flush_dcache_all)
+__flush_dcache_all:
 	dsb	sy				// ensure ordering with previous memory accesses
 	mrs	x0, clidr_el1			// read clidr
 	and	x3, x0, #0x7000000		// extract loc from clidr
@@ -166,3 +166,97 @@ ENTRY(__flush_dcache_area)
 	dsb	sy
 	ret
 ENDPROC(__flush_dcache_area)
+
+/*
+ *	__inval_cache_range(start, end)
+ *	- start   - start address of region
+ *	- end     - end address of region
+ */
+ENTRY(__inval_cache_range)
+	/* FALLTHROUGH */
+
+/*
+ *	__dma_inv_range(start, end)
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
+ */
+__dma_inv_range:
+	dcache_line_size x2, x3
+	sub	x3, x2, #1
+	tst	x1, x3				// end cache line aligned?
+	bic	x1, x1, x3
+	b.eq	1f
+	dc	civac, x1			// clean & invalidate D / U line
+1:	tst	x0, x3				// start cache line aligned?
+	bic	x0, x0, x3
+	b.eq	2f
+	dc	civac, x0			// clean & invalidate D / U line
+	b	3f
+2:	dc	ivac, x0			// invalidate D / U line
+3:	add	x0, x0, x2
+	cmp	x0, x1
+	b.lo	2b
+	dsb	sy
+	ret
+ENDPROC(__inval_cache_range)
+ENDPROC(__dma_inv_range)
+
+/*
+ *	__dma_clean_range(start, end)
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
+ */
+__dma_clean_range:
+	dcache_line_size x2, x3
+	sub	x3, x2, #1
+	bic	x0, x0, x3
+1:	dc	cvac, x0			// clean D / U line
+	add	x0, x0, x2
+	cmp	x0, x1
+	b.lo	1b
+	dsb	sy
+	ret
+ENDPROC(__dma_clean_range)
+
+/*
+ *	__dma_flush_range(start, end)
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
+ */
+ENTRY(__dma_flush_range)
+	dcache_line_size x2, x3
+	sub	x3, x2, #1
+	bic	x0, x0, x3
+1:	dc	civac, x0			// clean & invalidate D / U line
+	add	x0, x0, x2
+	cmp	x0, x1
+	b.lo	1b
+	dsb	sy
+	ret
+ENDPROC(__dma_flush_range)
+
+/*
+ *	__dma_map_area(start, size, dir)
+ *	- start	- kernel virtual start address
+ *	- size	- size of region
+ *	- dir	- DMA direction
+ */
+ENTRY(__dma_map_area)
+	add	x1, x1, x0
+	cmp	w2, #DMA_FROM_DEVICE
+	b.eq	__dma_inv_range
+	b	__dma_clean_range
+ENDPROC(__dma_map_area)
+
+/*
+ *	__dma_unmap_area(start, size, dir)
+ *	- start	- kernel virtual start address
+ *	- size	- size of region
+ *	- dir	- DMA direction
+ */
+ENTRY(__dma_unmap_area)
+	add	x1, x1, x0
+	cmp	w2, #DMA_TO_DEVICE
+	b.ne	__dma_inv_range
+	ret
+ENDPROC(__dma_unmap_area)
diff --git a/arch/arm64/mm/copypage.c b/arch/arm64/mm/copypage.c
index 9aecbace4128..13bbc3be6f5a 100644
--- a/arch/arm64/mm/copypage.c
+++ b/arch/arm64/mm/copypage.c
@@ -27,8 +27,10 @@ void __cpu_copy_user_page(void *kto, const void *kfrom, unsigned long vaddr)
 	copy_page(kto, kfrom);
 	__flush_dcache_area(kto, PAGE_SIZE);
 }
+EXPORT_SYMBOL_GPL(__cpu_copy_user_page);
 
 void __cpu_clear_user_page(void *kaddr, unsigned long vaddr)
 {
 	clear_page(kaddr);
 }
+EXPORT_SYMBOL_GPL(__cpu_clear_user_page);
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index fbd76785c5db..4164c5ace9f8 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -22,26 +22,37 @@
 #include <linux/slab.h>
 #include <linux/dma-mapping.h>
 #include <linux/dma-contiguous.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
 #include <linux/vmalloc.h>
 #include <linux/swiotlb.h>
+#include <linux/amba/bus.h>
 
 #include <asm/cacheflush.h>
 
 struct dma_map_ops *dma_ops;
 EXPORT_SYMBOL(dma_ops);
 
-static void *arm64_swiotlb_alloc_coherent(struct device *dev, size_t size,
-					  dma_addr_t *dma_handle, gfp_t flags,
-					  struct dma_attrs *attrs)
+static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot,
+				 bool coherent)
+{
+	if (!coherent || dma_get_attr(DMA_ATTR_WRITE_COMBINE, attrs))
+		return pgprot_writecombine(prot);
+	return prot;
+}
+
+static void *__dma_alloc_coherent(struct device *dev, size_t size,
+				  dma_addr_t *dma_handle, gfp_t flags,
+				  struct dma_attrs *attrs)
 {
 	if (dev == NULL) {
 		WARN_ONCE(1, "Use an actual device structure for DMA allocation\n");
 		return NULL;
 	}
 
-	if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
+	if (IS_ENABLED(CONFIG_ZONE_DMA) &&
 	    dev->coherent_dma_mask <= DMA_BIT_MASK(32))
-		flags |= GFP_DMA32;
+		flags |= GFP_DMA;
 	if (IS_ENABLED(CONFIG_DMA_CMA)) {
 		struct page *page;
 
@@ -58,9 +69,9 @@ static void *arm64_swiotlb_alloc_coherent(struct device *dev, size_t size,
 	}
 }
 
-static void arm64_swiotlb_free_coherent(struct device *dev, size_t size,
-					void *vaddr, dma_addr_t dma_handle,
-					struct dma_attrs *attrs)
+static void __dma_free_coherent(struct device *dev, size_t size,
+				void *vaddr, dma_addr_t dma_handle,
+				struct dma_attrs *attrs)
 {
 	if (dev == NULL) {
 		WARN_ONCE(1, "Use an actual device structure for DMA allocation\n");
@@ -78,9 +89,212 @@ static void arm64_swiotlb_free_coherent(struct device *dev, size_t size,
 	}
 }
 
-static struct dma_map_ops arm64_swiotlb_dma_ops = {
-	.alloc = arm64_swiotlb_alloc_coherent,
-	.free = arm64_swiotlb_free_coherent,
+static void *__dma_alloc_noncoherent(struct device *dev, size_t size,
+				     dma_addr_t *dma_handle, gfp_t flags,
+				     struct dma_attrs *attrs)
+{
+	struct page *page, **map;
+	void *ptr, *coherent_ptr;
+	int order, i;
+
+	size = PAGE_ALIGN(size);
+	order = get_order(size);
+
+	ptr = __dma_alloc_coherent(dev, size, dma_handle, flags, attrs);
+	if (!ptr)
+		goto no_mem;
+	map = kmalloc(sizeof(struct page *) << order, flags & ~GFP_DMA);
+	if (!map)
+		goto no_map;
+
+	/* remove any dirty cache lines on the kernel alias */
+	__dma_flush_range(ptr, ptr + size);
+
+	/* create a coherent mapping */
+	page = virt_to_page(ptr);
+	for (i = 0; i < (size >> PAGE_SHIFT); i++)
+		map[i] = page + i;
+	coherent_ptr = vmap(map, size >> PAGE_SHIFT, VM_MAP,
+			    __get_dma_pgprot(attrs, __pgprot(PROT_NORMAL_NC), false));
+	kfree(map);
+	if (!coherent_ptr)
+		goto no_map;
+
+	return coherent_ptr;
+
+no_map:
+	__dma_free_coherent(dev, size, ptr, *dma_handle, attrs);
+no_mem:
+	*dma_handle = ~0;
+	return NULL;
+}
+
+static void __dma_free_noncoherent(struct device *dev, size_t size,
+				   void *vaddr, dma_addr_t dma_handle,
+				   struct dma_attrs *attrs)
+{
+	void *swiotlb_addr = phys_to_virt(dma_to_phys(dev, dma_handle));
+
+	vunmap(vaddr);
+	__dma_free_coherent(dev, size, swiotlb_addr, dma_handle, attrs);
+}
+
+static dma_addr_t __swiotlb_map_page(struct device *dev, struct page *page,
+				     unsigned long offset, size_t size,
+				     enum dma_data_direction dir,
+				     struct dma_attrs *attrs)
+{
+	dma_addr_t dev_addr;
+
+	dev_addr = swiotlb_map_page(dev, page, offset, size, dir, attrs);
+	__dma_map_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
+
+	return dev_addr;
+}
+
+
+static void __swiotlb_unmap_page(struct device *dev, dma_addr_t dev_addr,
+				 size_t size, enum dma_data_direction dir,
+				 struct dma_attrs *attrs)
+{
+	__dma_unmap_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
+	swiotlb_unmap_page(dev, dev_addr, size, dir, attrs);
+}
+
+static int __swiotlb_map_sg_attrs(struct device *dev, struct scatterlist *sgl,
+				  int nelems, enum dma_data_direction dir,
+				  struct dma_attrs *attrs)
+{
+	struct scatterlist *sg;
+	int i, ret;
+
+	ret = swiotlb_map_sg_attrs(dev, sgl, nelems, dir, attrs);
+	for_each_sg(sgl, sg, ret, i)
+		__dma_map_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
+			       sg->length, dir);
+
+	return ret;
+}
+
+static void __swiotlb_unmap_sg_attrs(struct device *dev,
+				     struct scatterlist *sgl, int nelems,
+				     enum dma_data_direction dir,
+				     struct dma_attrs *attrs)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nelems, i)
+		__dma_unmap_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
+				 sg->length, dir);
+	swiotlb_unmap_sg_attrs(dev, sgl, nelems, dir, attrs);
+}
+
+static void __swiotlb_sync_single_for_cpu(struct device *dev,
+					  dma_addr_t dev_addr, size_t size,
+					  enum dma_data_direction dir)
+{
+	__dma_unmap_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
+	swiotlb_sync_single_for_cpu(dev, dev_addr, size, dir);
+}
+
+static void __swiotlb_sync_single_for_device(struct device *dev,
+					     dma_addr_t dev_addr, size_t size,
+					     enum dma_data_direction dir)
+{
+	swiotlb_sync_single_for_device(dev, dev_addr, size, dir);
+	__dma_map_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
+}
+
+static void __swiotlb_sync_sg_for_cpu(struct device *dev,
+				      struct scatterlist *sgl, int nelems,
+				      enum dma_data_direction dir)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nelems, i)
+		__dma_unmap_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
+				 sg->length, dir);
+	swiotlb_sync_sg_for_cpu(dev, sgl, nelems, dir);
+}
+
+static void __swiotlb_sync_sg_for_device(struct device *dev,
+					 struct scatterlist *sgl, int nelems,
+					 enum dma_data_direction dir)
+{
+	struct scatterlist *sg;
+	int i;
+
+	swiotlb_sync_sg_for_device(dev, sgl, nelems, dir);
+	for_each_sg(sgl, sg, nelems, i)
+		__dma_map_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
+			       sg->length, dir);
+}
+
+/* vma->vm_page_prot must be set appropriately before calling this function */
+static int __dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
+			     void *cpu_addr, dma_addr_t dma_addr, size_t size)
+{
+	int ret = -ENXIO;
+	unsigned long nr_vma_pages = (vma->vm_end - vma->vm_start) >>
+					PAGE_SHIFT;
+	unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	unsigned long pfn = dma_to_phys(dev, dma_addr) >> PAGE_SHIFT;
+	unsigned long off = vma->vm_pgoff;
+
+	if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
+		return ret;
+
+	if (off < nr_pages && nr_vma_pages <= (nr_pages - off)) {
+		ret = remap_pfn_range(vma, vma->vm_start,
+				      pfn + off,
+				      vma->vm_end - vma->vm_start,
+				      vma->vm_page_prot);
+	}
+
+	return ret;
+}
+
+static int __swiotlb_mmap_noncoherent(struct device *dev,
+		struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		struct dma_attrs *attrs)
+{
+	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot, false);
+	return __dma_common_mmap(dev, vma, cpu_addr, dma_addr, size);
+}
+
+static int __swiotlb_mmap_coherent(struct device *dev,
+		struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		struct dma_attrs *attrs)
+{
+	/* Just use whatever page_prot attributes were specified */
+	return __dma_common_mmap(dev, vma, cpu_addr, dma_addr, size);
+}
+
+struct dma_map_ops noncoherent_swiotlb_dma_ops = {
+	.alloc = __dma_alloc_noncoherent,
+	.free = __dma_free_noncoherent,
+	.mmap = __swiotlb_mmap_noncoherent,
+	.map_page = __swiotlb_map_page,
+	.unmap_page = __swiotlb_unmap_page,
+	.map_sg = __swiotlb_map_sg_attrs,
+	.unmap_sg = __swiotlb_unmap_sg_attrs,
+	.sync_single_for_cpu = __swiotlb_sync_single_for_cpu,
+	.sync_single_for_device = __swiotlb_sync_single_for_device,
+	.sync_sg_for_cpu = __swiotlb_sync_sg_for_cpu,
+	.sync_sg_for_device = __swiotlb_sync_sg_for_device,
+	.dma_supported = swiotlb_dma_supported,
+	.mapping_error = swiotlb_dma_mapping_error,
+};
+EXPORT_SYMBOL(noncoherent_swiotlb_dma_ops);
+
+struct dma_map_ops coherent_swiotlb_dma_ops = {
+	.alloc = __dma_alloc_coherent,
+	.free = __dma_free_coherent,
+	.mmap = __swiotlb_mmap_coherent,
 	.map_page = swiotlb_map_page,
 	.unmap_page = swiotlb_unmap_page,
 	.map_sg = swiotlb_map_sg_attrs,
@@ -92,12 +306,47 @@ static struct dma_map_ops arm64_swiotlb_dma_ops = {
 	.dma_supported = swiotlb_dma_supported,
 	.mapping_error = swiotlb_dma_mapping_error,
 };
+EXPORT_SYMBOL(coherent_swiotlb_dma_ops);
 
-void __init arm64_swiotlb_init(void)
+static int dma_bus_notifier(struct notifier_block *nb,
+			    unsigned long event, void *_dev)
 {
-	dma_ops = &arm64_swiotlb_dma_ops;
-	swiotlb_init(1);
+	struct device *dev = _dev;
+
+	if (event != BUS_NOTIFY_ADD_DEVICE)
+		return NOTIFY_DONE;
+
+	if (of_property_read_bool(dev->of_node, "dma-coherent"))
+		set_dma_ops(dev, &coherent_swiotlb_dma_ops);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block platform_bus_nb = {
+	.notifier_call = dma_bus_notifier,
+};
+
+static struct notifier_block amba_bus_nb = {
+	.notifier_call = dma_bus_notifier,
+};
+
+extern int swiotlb_late_init_with_default_size(size_t default_size);
+
+static int __init swiotlb_late_init(void)
+{
+	size_t swiotlb_size = min(SZ_64M, MAX_ORDER_NR_PAGES << PAGE_SHIFT);
+
+	/*
+	 * These must be registered before of_platform_populate().
+	 */
+	bus_register_notifier(&platform_bus_type, &platform_bus_nb);
+	bus_register_notifier(&amba_bustype, &amba_bus_nb);
+
+	dma_ops = &noncoherent_swiotlb_dma_ops;
+
+	return swiotlb_late_init_with_default_size(swiotlb_size);
 }
+arch_initcall(swiotlb_late_init);
 
 #define PREALLOC_DMA_DEBUG_ENTRIES	4096
 
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index d0b4c2efda90..cc3339d0a276 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -30,6 +30,7 @@
 #include <linux/memblock.h>
 #include <linux/sort.h>
 #include <linux/of_fdt.h>
+#include <linux/dma-mapping.h>
 #include <linux/dma-contiguous.h>
 
 #include <asm/sections.h>
@@ -59,22 +60,22 @@ static int __init early_initrd(char *p)
 early_param("initrd", early_initrd);
 #endif
 
-#define MAX_DMA32_PFN ((4UL * 1024 * 1024 * 1024) >> PAGE_SHIFT)
-
 static void __init zone_sizes_init(unsigned long min, unsigned long max)
 {
 	struct memblock_region *reg;
 	unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES];
-	unsigned long max_dma32 = min;
+	unsigned long max_dma = min;
 
 	memset(zone_size, 0, sizeof(zone_size));
 
-#ifdef CONFIG_ZONE_DMA32
 	/* 4GB maximum for 32-bit only capable devices */
-	max_dma32 = max(min, min(max, MAX_DMA32_PFN));
-	zone_size[ZONE_DMA32] = max_dma32 - min;
-#endif
-	zone_size[ZONE_NORMAL] = max - max_dma32;
+	if (IS_ENABLED(CONFIG_ZONE_DMA)) {
+		unsigned long max_dma_phys =
+			(unsigned long)dma_to_phys(NULL, DMA_BIT_MASK(32) + 1);
+		max_dma = max(min, min(max, max_dma_phys >> PAGE_SHIFT));
+		zone_size[ZONE_DMA] = max_dma - min;
+	}
+	zone_size[ZONE_NORMAL] = max - max_dma;
 
 	memcpy(zhole_size, zone_size, sizeof(zhole_size));
 
@@ -84,15 +85,15 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 
 		if (start >= max)
 			continue;
-#ifdef CONFIG_ZONE_DMA32
-		if (start < max_dma32) {
-			unsigned long dma_end = min(end, max_dma32);
-			zhole_size[ZONE_DMA32] -= dma_end - start;
+
+		if (IS_ENABLED(CONFIG_ZONE_DMA) && start < max_dma) {
+			unsigned long dma_end = min(end, max_dma);
+			zhole_size[ZONE_DMA] -= dma_end - start;
 		}
-#endif
-		if (end > max_dma32) {
+
+		if (end > max_dma) {
 			unsigned long normal_end = min(end, max);
-			unsigned long normal_start = max(start, max_dma32);
+			unsigned long normal_start = max(start, max_dma);
 			zhole_size[ZONE_NORMAL] -= normal_end - normal_start;
 		}
 	}
@@ -127,20 +128,16 @@ void __init arm64_memblock_init(void)
 {
 	u64 *reserve_map, base, size;
 
-	/* Register the kernel text, kernel data and initrd with memblock */
+	/*
+	 * Register the kernel text, kernel data, initrd, and initial
+	 * pagetables with memblock.
+	 */
 	memblock_reserve(__pa(_text), _end - _text);
 #ifdef CONFIG_BLK_DEV_INITRD
 	if (initrd_start)
 		memblock_reserve(__virt_to_phys(initrd_start), initrd_end - initrd_start);
 #endif
 
-	/*
-	 * Reserve the page tables.  These are already in use,
-	 * and can only be in node 0.
-	 */
-	memblock_reserve(__pa(swapper_pg_dir), SWAPPER_DIR_SIZE);
-	memblock_reserve(__pa(idmap_pg_dir), IDMAP_DIR_SIZE);
-
 	/* Reserve the dtb region */
 	memblock_reserve(virt_to_phys(initial_boot_params),
 			 be32_to_cpu(initial_boot_params->totalsize));
@@ -160,6 +157,7 @@ void __init arm64_memblock_init(void)
 		memblock_reserve(base, size);
 	}
 
+	early_init_fdt_scan_reserved_mem();
 	dma_contiguous_reserve(0);
 
 	memblock_allow_resize();
@@ -261,8 +259,6 @@ static void __init free_unused_memmap(void)
  */
 void __init mem_init(void)
 {
-	arm64_swiotlb_init();
-
 	max_mapnr   = pfn_to_page(max_pfn + PHYS_PFN_OFFSET) - mem_map;
 
 #ifndef CONFIG_SPARSEMEM_VMEMMAP
diff --git a/arch/arm64/mm/ioremap.c b/arch/arm64/mm/ioremap.c
index 2bb1d586664c..7ec328392ae0 100644
--- a/arch/arm64/mm/ioremap.c
+++ b/arch/arm64/mm/ioremap.c
@@ -25,6 +25,10 @@
 #include <linux/vmalloc.h>
 #include <linux/io.h>
 
+#include <asm/fixmap.h>
+#include <asm/tlbflush.h>
+#include <asm/pgalloc.h>
+
 static void __iomem *__ioremap_caller(phys_addr_t phys_addr, size_t size,
 				      pgprot_t prot, void *caller)
 {
@@ -98,3 +102,84 @@ void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size)
 				__builtin_return_address(0));
 }
 EXPORT_SYMBOL(ioremap_cache);
+
+#ifndef CONFIG_ARM64_64K_PAGES
+static pte_t bm_pte[PTRS_PER_PTE] __page_aligned_bss;
+#endif
+
+static inline pmd_t * __init early_ioremap_pmd(unsigned long addr)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+
+	pgd = pgd_offset_k(addr);
+	BUG_ON(pgd_none(*pgd) || pgd_bad(*pgd));
+
+	pud = pud_offset(pgd, addr);
+	BUG_ON(pud_none(*pud) || pud_bad(*pud));
+
+	return pmd_offset(pud, addr);
+}
+
+static inline pte_t * __init early_ioremap_pte(unsigned long addr)
+{
+	pmd_t *pmd = early_ioremap_pmd(addr);
+
+	BUG_ON(pmd_none(*pmd) || pmd_bad(*pmd));
+
+	return pte_offset_kernel(pmd, addr);
+}
+
+void __init early_ioremap_init(void)
+{
+	pmd_t *pmd;
+
+	pmd = early_ioremap_pmd(fix_to_virt(FIX_BTMAP_BEGIN));
+#ifndef CONFIG_ARM64_64K_PAGES
+	/* need to populate pmd for 4k pagesize only */
+	pmd_populate_kernel(&init_mm, pmd, bm_pte);
+#endif
+	/*
+	 * The boot-ioremap range spans multiple pmds, for which
+	 * we are not prepared:
+	 */
+	BUILD_BUG_ON((__fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT)
+		     != (__fix_to_virt(FIX_BTMAP_END) >> PMD_SHIFT));
+
+	if (pmd != early_ioremap_pmd(fix_to_virt(FIX_BTMAP_END))) {
+		WARN_ON(1);
+		pr_warn("pmd %p != %p\n",
+			pmd, early_ioremap_pmd(fix_to_virt(FIX_BTMAP_END)));
+		pr_warn("fix_to_virt(FIX_BTMAP_BEGIN): %08lx\n",
+			fix_to_virt(FIX_BTMAP_BEGIN));
+		pr_warn("fix_to_virt(FIX_BTMAP_END):   %08lx\n",
+			fix_to_virt(FIX_BTMAP_END));
+
+		pr_warn("FIX_BTMAP_END:       %d\n", FIX_BTMAP_END);
+		pr_warn("FIX_BTMAP_BEGIN:     %d\n",
+			FIX_BTMAP_BEGIN);
+	}
+
+	early_ioremap_setup();
+}
+
+void __init __early_set_fixmap(enum fixed_addresses idx,
+			       phys_addr_t phys, pgprot_t flags)
+{
+	unsigned long addr = __fix_to_virt(idx);
+	pte_t *pte;
+
+	if (idx >= __end_of_fixed_addresses) {
+		BUG();
+		return;
+	}
+
+	pte = early_ioremap_pte(addr);
+
+	if (pgprot_val(flags))
+		set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags));
+	else {
+		pte_clear(&init_mm, addr, pte);
+		flush_tlb_kernel_range(addr, addr+PAGE_SIZE);
+	}
+}
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index f8dc7e8fce6f..a2155ca6921c 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -43,11 +43,6 @@
 struct page *empty_zero_page;
 EXPORT_SYMBOL(empty_zero_page);
 
-pgprot_t pgprot_default;
-EXPORT_SYMBOL(pgprot_default);
-
-static pmdval_t prot_sect_kernel;
-
 struct cachepolicy {
 	const char	policy[16];
 	u64		mair;
@@ -122,33 +117,6 @@ static int __init early_cachepolicy(char *p)
 }
 early_param("cachepolicy", early_cachepolicy);
 
-/*
- * Adjust the PMD section entries according to the CPU in use.
- */
-static void __init init_mem_pgprot(void)
-{
-	pteval_t default_pgprot;
-	int i;
-
-	default_pgprot = PTE_ATTRINDX(MT_NORMAL);
-	prot_sect_kernel = PMD_TYPE_SECT | PMD_SECT_AF | PMD_ATTRINDX(MT_NORMAL);
-
-#ifdef CONFIG_SMP
-	/*
-	 * Mark memory with the "shared" attribute for SMP systems
-	 */
-	default_pgprot |= PTE_SHARED;
-	prot_sect_kernel |= PMD_SECT_S;
-#endif
-
-	for (i = 0; i < 16; i++) {
-		unsigned long v = pgprot_val(protection_map[i]);
-		protection_map[i] = __pgprot(v | default_pgprot);
-	}
-
-	pgprot_default = __pgprot(PTE_TYPE_PAGE | PTE_AF | default_pgprot);
-}
-
 pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 			      unsigned long size, pgprot_t vma_prot)
 {
@@ -168,7 +136,8 @@ static void __init *early_alloc(unsigned long sz)
 }
 
 static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr,
-				  unsigned long end, unsigned long pfn)
+				  unsigned long end, unsigned long pfn,
+				  pgprot_t prot)
 {
 	pte_t *pte;
 
@@ -180,16 +149,28 @@ static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr,
 
 	pte = pte_offset_kernel(pmd, addr);
 	do {
-		set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC));
+		set_pte(pte, pfn_pte(pfn, prot));
 		pfn++;
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 }
 
 static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
-				  unsigned long end, phys_addr_t phys)
+				  unsigned long end, phys_addr_t phys,
+				  int map_io)
 {
 	pmd_t *pmd;
 	unsigned long next;
+	pmdval_t prot_sect;
+	pgprot_t prot_pte;
+
+	if (map_io) {
+		prot_sect = PMD_TYPE_SECT | PMD_SECT_AF |
+			    PMD_ATTRINDX(MT_DEVICE_nGnRE);
+		prot_pte = __pgprot(PROT_DEVICE_nGnRE);
+	} else {
+		prot_sect = PROT_SECT_NORMAL_EXEC;
+		prot_pte = PAGE_KERNEL_EXEC;
+	}
 
 	/*
 	 * Check for initial section mappings in the pgd/pud and remove them.
@@ -205,7 +186,7 @@ static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
 		/* try section mapping first */
 		if (((addr | next | phys) & ~SECTION_MASK) == 0) {
 			pmd_t old_pmd =*pmd;
-			set_pmd(pmd, __pmd(phys | prot_sect_kernel));
+			set_pmd(pmd, __pmd(phys | prot_sect));
 			/*
 			 * Check for previous table entries created during
 			 * boot (__create_page_tables) and flush them.
@@ -213,21 +194,23 @@ static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
 			if (!pmd_none(old_pmd))
 				flush_tlb_all();
 		} else {
-			alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys));
+			alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys),
+				       prot_pte);
 		}
 		phys += next - addr;
 	} while (pmd++, addr = next, addr != end);
 }
 
 static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr,
-				  unsigned long end, unsigned long phys)
+				  unsigned long end, unsigned long phys,
+				  int map_io)
 {
 	pud_t *pud = pud_offset(pgd, addr);
 	unsigned long next;
 
 	do {
 		next = pud_addr_end(addr, end);
-		alloc_init_pmd(pud, addr, next, phys);
+		alloc_init_pmd(pud, addr, next, phys, map_io);
 		phys += next - addr;
 	} while (pud++, addr = next, addr != end);
 }
@@ -236,70 +219,43 @@ static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr,
  * Create the page directory entries and any necessary page tables for the
  * mapping specified by 'md'.
  */
-static void __init create_mapping(phys_addr_t phys, unsigned long virt,
-				  phys_addr_t size)
+static void __init __create_mapping(pgd_t *pgd, phys_addr_t phys,
+				    unsigned long virt, phys_addr_t size,
+				    int map_io)
 {
 	unsigned long addr, length, end, next;
-	pgd_t *pgd;
-
-	if (virt < VMALLOC_START) {
-		pr_warning("BUG: not creating mapping for 0x%016llx at 0x%016lx - outside kernel range\n",
-			   phys, virt);
-		return;
-	}
 
 	addr = virt & PAGE_MASK;
 	length = PAGE_ALIGN(size + (virt & ~PAGE_MASK));
 
-	pgd = pgd_offset_k(addr);
 	end = addr + length;
 	do {
 		next = pgd_addr_end(addr, end);
-		alloc_init_pud(pgd, addr, next, phys);
+		alloc_init_pud(pgd, addr, next, phys, map_io);
 		phys += next - addr;
 	} while (pgd++, addr = next, addr != end);
 }
 
-#ifdef CONFIG_EARLY_PRINTK
-/*
- * Create an early I/O mapping using the pgd/pmd entries already populated
- * in head.S as this function is called too early to allocated any memory. The
- * mapping size is 2MB with 4KB pages or 64KB or 64KB pages.
- */
-void __iomem * __init early_io_map(phys_addr_t phys, unsigned long virt)
+static void __init create_mapping(phys_addr_t phys, unsigned long virt,
+				  phys_addr_t size)
 {
-	unsigned long size, mask;
-	bool page64k = IS_ENABLED(CONFIG_ARM64_64K_PAGES);
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
-
-	/*
-	 * No early pte entries with !ARM64_64K_PAGES configuration, so using
-	 * sections (pmd).
-	 */
-	size = page64k ? PAGE_SIZE : SECTION_SIZE;
-	mask = ~(size - 1);
-
-	pgd = pgd_offset_k(virt);
-	pud = pud_offset(pgd, virt);
-	if (pud_none(*pud))
-		return NULL;
-	pmd = pmd_offset(pud, virt);
-
-	if (page64k) {
-		if (pmd_none(*pmd))
-			return NULL;
-		pte = pte_offset_kernel(pmd, virt);
-		set_pte(pte, __pte((phys & mask) | PROT_DEVICE_nGnRE));
-	} else {
-		set_pmd(pmd, __pmd((phys & mask) | PROT_SECT_DEVICE_nGnRE));
+	if (virt < VMALLOC_START) {
+		pr_warn("BUG: not creating mapping for %pa at 0x%016lx - outside kernel range\n",
+			&phys, virt);
+		return;
 	}
+	__create_mapping(pgd_offset_k(virt & PAGE_MASK), phys, virt, size, 0);
+}
 
-	return (void __iomem *)((virt & mask) + (phys & ~mask));
+void __init create_id_mapping(phys_addr_t addr, phys_addr_t size, int map_io)
+{
+	if ((addr >> PGDIR_SHIFT) >= ARRAY_SIZE(idmap_pg_dir)) {
+		pr_warn("BUG: not creating id mapping for %pa\n", &addr);
+		return;
+	}
+	__create_mapping(&idmap_pg_dir[pgd_index(addr)],
+			 addr, addr, size, map_io);
 }
-#endif
 
 static void __init map_mem(void)
 {
@@ -357,7 +313,6 @@ void __init paging_init(void)
 {
 	void *zero_page;
 
-	init_mem_pgprot();
 	map_mem();
 
 	/*
@@ -416,6 +371,9 @@ int kern_addr_valid(unsigned long addr)
 	if (pmd_none(*pmd))
 		return 0;
 
+	if (pmd_sect(*pmd))
+		return pfn_valid(pmd_pfn(*pmd));
+
 	pte = pte_offset_kernel(pmd, addr);
 	if (pte_none(*pte))
 		return 0;
@@ -456,7 +414,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 			if (!p)
 				return -ENOMEM;
 
-			set_pmd(pmd, __pmd(__pa(p) | prot_sect_kernel));
+			set_pmd(pmd, __pmd(__pa(p) | PROT_SECT_NORMAL));
 		} else
 			vmemmap_verify((pte_t *)pmd, node, addr, next);
 	} while (addr = next, addr != end);
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 1333e6f9a8e5..e0ef63cd05dc 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -173,12 +173,6 @@ ENDPROC(cpu_do_switch_mm)
  *	value of the SCTLR_EL1 register.
  */
 ENTRY(__cpu_setup)
-	/*
-	 * Preserve the link register across the function call.
-	 */
-	mov	x28, lr
-	bl	__flush_dcache_all
-	mov	lr, x28
 	ic	iallu				// I+BTB cache invalidate
 	tlbi	vmalle1is			// invalidate I + D TLBs
 	dsb	sy
diff --git a/arch/arm64/mm/tlb.S b/arch/arm64/mm/tlb.S
deleted file mode 100644
index 19da91e0cd27..000000000000
--- a/arch/arm64/mm/tlb.S
+++ /dev/null
@@ -1,71 +0,0 @@
-/*
- * Based on arch/arm/mm/tlb.S
- *
- * Copyright (C) 1997-2002 Russell King
- * Copyright (C) 2012 ARM Ltd.
- * Written by Catalin Marinas <catalin.marinas@arm.com>
- *
- * 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-#include <asm/asm-offsets.h>
-#include <asm/page.h>
-#include <asm/tlbflush.h>
-#include "proc-macros.S"
-
-/*
- *	__cpu_flush_user_tlb_range(start, end, vma)
- *
- *	Invalidate a range of TLB entries in the specified address space.
- *
- *	- start - start address (may not be aligned)
- *	- end   - end address (exclusive, may not be aligned)
- *	- vma   - vma_struct describing address range
- */
-ENTRY(__cpu_flush_user_tlb_range)
-	vma_vm_mm x3, x2			// get vma->vm_mm
-	mmid	w3, x3				// get vm_mm->context.id
-	dsb	sy
-	lsr	x0, x0, #12			// align address
-	lsr	x1, x1, #12
-	bfi	x0, x3, #48, #16		// start VA and ASID
-	bfi	x1, x3, #48, #16		// end VA and ASID
-1:	tlbi	vae1is, x0			// TLB invalidate by address and ASID
-	add	x0, x0, #1
-	cmp	x0, x1
-	b.lo	1b
-	dsb	sy
-	ret
-ENDPROC(__cpu_flush_user_tlb_range)
-
-/*
- *	__cpu_flush_kern_tlb_range(start,end)
- *
- *	Invalidate a range of kernel TLB entries.
- *
- *	- start - start address (may not be aligned)
- *	- end   - end address (exclusive, may not be aligned)
- */
-ENTRY(__cpu_flush_kern_tlb_range)
-	dsb	sy
-	lsr	x0, x0, #12			// align address
-	lsr	x1, x1, #12
-1:	tlbi	vaae1is, x0			// TLB invalidate by address
-	add	x0, x0, #1
-	cmp	x0, x1
-	b.lo	1b
-	dsb	sy
-	isb
-	ret
-ENDPROC(__cpu_flush_kern_tlb_range)
diff --git a/arch/microblaze/kernel/prom.c b/arch/microblaze/kernel/prom.c
index abdfb10e7eca..c76630603058 100644
--- a/arch/microblaze/kernel/prom.c
+++ b/arch/microblaze/kernel/prom.c
@@ -43,13 +43,13 @@
 #include <asm/pci-bridge.h>
 
 #ifdef CONFIG_EARLY_PRINTK
-static char *stdout;
+static const char *stdout;
 
 static int __init early_init_dt_scan_chosen_serial(unsigned long node,
 				const char *uname, int depth, void *data)
 {
-	unsigned long l;
-	char *p;
+	int l;
+	const char *p;
 
 	pr_debug("%s: depth: %d, uname: %s\n", __func__, depth, uname);
 
@@ -80,7 +80,7 @@ static int __init early_init_dt_scan_chosen_serial(unsigned long node,
 				(strncmp(p, "xlnx,opb-uartlite", 17) == 0) ||
 				(strncmp(p, "xlnx,axi-uartlite", 17) == 0) ||
 				(strncmp(p, "xlnx,mdm", 8) == 0)) {
-			unsigned int *addrp;
+			const unsigned int *addrp;
 
 			*(u32 *)data = UARTLITE;
 
diff --git a/arch/powerpc/kernel/epapr_paravirt.c b/arch/powerpc/kernel/epapr_paravirt.c
index 7898be90f2dc..d64e92b22dd8 100644
--- a/arch/powerpc/kernel/epapr_paravirt.c
+++ b/arch/powerpc/kernel/epapr_paravirt.c
@@ -36,7 +36,7 @@ static int __init early_init_dt_scan_epapr(unsigned long node,
 					   int depth, void *data)
 {
 	const u32 *insts;
-	unsigned long len;
+	int len;
 	int i;
 
 	insts = of_get_flat_dt_prop(node, "hcall-instructions", &len);
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 2230fd0ca3e4..7213d930918d 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -55,9 +55,9 @@ int crash_mem_ranges;
 int __init early_init_dt_scan_fw_dump(unsigned long node,
 			const char *uname, int depth, void *data)
 {
-	__be32 *sections;
+	const __be32 *sections;
 	int i, num_sections;
-	unsigned long size;
+	int size;
 	const int *token;
 
 	if (depth != 1 || strcmp(uname, "rtas") != 0)
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index f58c0d3aaeb4..8dd5a093195b 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -162,7 +162,7 @@ static struct ibm_pa_feature {
 	{CPU_FTR_REAL_LE, PPC_FEATURE_TRUE_LE, 5, 0, 0},
 };
 
-static void __init scan_features(unsigned long node, unsigned char *ftrs,
+static void __init scan_features(unsigned long node, const unsigned char *ftrs,
 				 unsigned long tablelen,
 				 struct ibm_pa_feature *fp,
 				 unsigned long ft_size)
@@ -201,8 +201,8 @@ static void __init scan_features(unsigned long node, unsigned char *ftrs,
 
 static void __init check_cpu_pa_features(unsigned long node)
 {
-	unsigned char *pa_ftrs;
-	unsigned long tablelen;
+	const unsigned char *pa_ftrs;
+	int tablelen;
 
 	pa_ftrs = of_get_flat_dt_prop(node, "ibm,pa-features", &tablelen);
 	if (pa_ftrs == NULL)
@@ -215,7 +215,7 @@ static void __init check_cpu_pa_features(unsigned long node)
 #ifdef CONFIG_PPC_STD_MMU_64
 static void __init check_cpu_slb_size(unsigned long node)
 {
-	__be32 *slb_size_ptr;
+	const __be32 *slb_size_ptr;
 
 	slb_size_ptr = of_get_flat_dt_prop(node, "slb-size", NULL);
 	if (slb_size_ptr != NULL) {
@@ -256,7 +256,7 @@ static struct feature_property {
 static inline void identical_pvr_fixup(unsigned long node)
 {
 	unsigned int pvr;
-	char *model = of_get_flat_dt_prop(node, "model", NULL);
+	const char *model = of_get_flat_dt_prop(node, "model", NULL);
 
 	/*
 	 * Since 440GR(x)/440EP(x) processors have the same pvr,
@@ -294,11 +294,11 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 					  const char *uname, int depth,
 					  void *data)
 {
-	char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
 	const __be32 *prop;
 	const __be32 *intserv;
 	int i, nthreads;
-	unsigned long len;
+	int len;
 	int found = -1;
 	int found_thread = 0;
 
@@ -391,7 +391,7 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 int __init early_init_dt_scan_chosen_ppc(unsigned long node, const char *uname,
 					 int depth, void *data)
 {
-	unsigned long *lprop; /* All these set by kernel, so no need to convert endian */
+	const unsigned long *lprop; /* All these set by kernel, so no need to convert endian */
 
 	/* Use common scan routine to determine if this is the chosen node */
 	if (early_init_dt_scan_chosen(node, uname, depth, data) == 0)
@@ -442,8 +442,9 @@ int __init early_init_dt_scan_chosen_ppc(unsigned long node, const char *uname,
  */
 static int __init early_init_dt_scan_drconf_memory(unsigned long node)
 {
-	__be32 *dm, *ls, *usm;
-	unsigned long l, n, flags;
+	const __be32 *dm, *ls, *usm;
+	int l;
+	unsigned long n, flags;
 	u64 base, size, memblock_size;
 	unsigned int is_kexec_kdump = 0, rngs;
 
@@ -563,7 +564,8 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 
 static void __init early_reserve_mem_dt(void)
 {
-	unsigned long i, len, dt_root;
+	unsigned long i, dt_root;
+	int len;
 	const __be32 *prop;
 
 	dt_root = of_get_flat_dt_root();
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 4cf674d7d5ae..8c923bac430f 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -1135,7 +1135,7 @@ void __init rtas_initialize(void)
 int __init early_init_dt_scan_rtas(unsigned long node,
 		const char *uname, int depth, void *data)
 {
-	u32 *basep, *entryp, *sizep;
+	const u32 *basep, *entryp, *sizep;
 
 	if (depth != 1 || strcmp(uname, "rtas") != 0)
 		return 0;
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index d766d6ee33fe..59cc19a23a7a 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -265,9 +265,9 @@ static int __init htab_dt_scan_seg_sizes(unsigned long node,
 					 const char *uname, int depth,
 					 void *data)
 {
-	char *type = of_get_flat_dt_prop(node, "device_type", NULL);
-	__be32 *prop;
-	unsigned long size = 0;
+	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+	const __be32 *prop;
+	int size = 0;
 
 	/* We are scanning "cpu" nodes only */
 	if (type == NULL || strcmp(type, "cpu") != 0)
@@ -320,9 +320,9 @@ static int __init htab_dt_scan_page_sizes(unsigned long node,
 					  const char *uname, int depth,
 					  void *data)
 {
-	char *type = of_get_flat_dt_prop(node, "device_type", NULL);
-	__be32 *prop;
-	unsigned long size = 0;
+	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+	const __be32 *prop;
+	int size = 0;
 
 	/* We are scanning "cpu" nodes only */
 	if (type == NULL || strcmp(type, "cpu") != 0)
@@ -402,9 +402,9 @@ static int __init htab_dt_scan_page_sizes(unsigned long node,
 static int __init htab_dt_scan_hugepage_blocks(unsigned long node,
 					const char *uname, int depth,
 					void *data) {
-	char *type = of_get_flat_dt_prop(node, "device_type", NULL);
-	__be64 *addr_prop;
-	__be32 *page_count_prop;
+	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+	const __be64 *addr_prop;
+	const __be32 *page_count_prop;
 	unsigned int expected_pages;
 	long unsigned int phys_addr;
 	long unsigned int block_size;
@@ -546,8 +546,8 @@ static int __init htab_dt_scan_pftsize(unsigned long node,
 				       const char *uname, int depth,
 				       void *data)
 {
-	char *type = of_get_flat_dt_prop(node, "device_type", NULL);
-	__be32 *prop;
+	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+	const __be32 *prop;
 
 	/* We are scanning "cpu" nodes only */
 	if (type == NULL || strcmp(type, "cpu") != 0)
diff --git a/arch/powerpc/platforms/52xx/efika.c b/arch/powerpc/platforms/52xx/efika.c
index 18c104820198..6e19b0ad5d26 100644
--- a/arch/powerpc/platforms/52xx/efika.c
+++ b/arch/powerpc/platforms/52xx/efika.c
@@ -199,8 +199,8 @@ static void __init efika_setup_arch(void)
 
 static int __init efika_probe(void)
 {
-	char *model = of_get_flat_dt_prop(of_get_flat_dt_root(),
-					  "model", NULL);
+	const char *model = of_get_flat_dt_prop(of_get_flat_dt_root(),
+						"model", NULL);
 
 	if (model == NULL)
 		return 0;
diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c
index c665d7de6c99..7044fd36197b 100644
--- a/arch/powerpc/platforms/chrp/setup.c
+++ b/arch/powerpc/platforms/chrp/setup.c
@@ -574,8 +574,8 @@ chrp_init2(void)
 
 static int __init chrp_probe(void)
 {
- 	char *dtype = of_get_flat_dt_prop(of_get_flat_dt_root(),
- 					  "device_type", NULL);
+	const char *dtype = of_get_flat_dt_prop(of_get_flat_dt_root(),
+						"device_type", NULL);
  	if (dtype == NULL)
  		return 0;
  	if (strcmp(dtype, "chrp"))
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 65499adaecff..3bf1eb433112 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -50,7 +50,7 @@ int __init early_init_dt_scan_opal(unsigned long node,
 				   const char *uname, int depth, void *data)
 {
 	const void *basep, *entryp;
-	unsigned long basesz, entrysz;
+	int basesz, entrysz, runtimesz;
 
 	if (depth != 1 || strcmp(uname, "ibm,opal") != 0)
 		return 0;
@@ -64,10 +64,10 @@ int __init early_init_dt_scan_opal(unsigned long node,
 	opal.base = of_read_number(basep, basesz/4);
 	opal.entry = of_read_number(entryp, entrysz/4);
 
-	pr_debug("OPAL Base  = 0x%llx (basep=%p basesz=%ld)\n",
+	pr_debug("OPAL Base  = 0x%llx (basep=%p basesz=%d)\n",
 		 opal.base, basep, basesz);
-	pr_debug("OPAL Entry = 0x%llx (entryp=%p basesz=%ld)\n",
-		 opal.entry, entryp, entrysz);
+	pr_debug("OPAL Entry = 0x%llx (sizep=%p runtimesz=%d)\n",
+		 opal.size, sizep, runtimesz);
 
 	powerpc_firmware_features |= FW_FEATURE_OPAL;
 	if (of_flat_dt_is_compatible(node, "ibm,opal-v3")) {
@@ -84,6 +84,68 @@ int __init early_init_dt_scan_opal(unsigned long node,
 	return 1;
 }
 
+<<<<<<< HEAD
+=======
+int __init early_init_dt_scan_recoverable_ranges(unsigned long node,
+				   const char *uname, int depth, void *data)
+{
+	int i, psize, size;
+	const __be32 *prop;
+
+	if (depth != 1 || strcmp(uname, "ibm,opal") != 0)
+		return 0;
+
+	prop = of_get_flat_dt_prop(node, "mcheck-recoverable-ranges", &psize);
+
+	if (!prop)
+		return 1;
+
+	pr_debug("Found machine check recoverable ranges.\n");
+
+	/*
+	 * Calculate number of available entries.
+	 *
+	 * Each recoverable address range entry is (start address, len,
+	 * recovery address), 2 cells each for start and recovery address,
+	 * 1 cell for len, totalling 5 cells per entry.
+	 */
+	mc_recoverable_range_len = psize / (sizeof(*prop) * 5);
+
+	/* Sanity check */
+	if (!mc_recoverable_range_len)
+		return 1;
+
+	/* Size required to hold all the entries. */
+	size = mc_recoverable_range_len *
+			sizeof(struct mcheck_recoverable_range);
+
+	/*
+	 * Allocate a buffer to hold the MC recoverable ranges. We would be
+	 * accessing them in real mode, hence it needs to be within
+	 * RMO region.
+	 */
+	mc_recoverable_range =__va(memblock_alloc_base(size, __alignof__(u64),
+							ppc64_rma_size));
+	memset(mc_recoverable_range, 0, size);
+
+	for (i = 0; i < mc_recoverable_range_len; i++) {
+		mc_recoverable_range[i].start_addr =
+					of_read_number(prop + (i * 5) + 0, 2);
+		mc_recoverable_range[i].end_addr =
+					mc_recoverable_range[i].start_addr +
+					of_read_number(prop + (i * 5) + 2, 1);
+		mc_recoverable_range[i].recover_addr =
+					of_read_number(prop + (i * 5) + 3, 2);
+
+		pr_debug("Machine check recoverable range: %llx..%llx: %llx\n",
+				mc_recoverable_range[i].start_addr,
+				mc_recoverable_range[i].end_addr,
+				mc_recoverable_range[i].recover_addr);
+	}
+	return 1;
+}
+
+>>>>>>> 9d0c4dfedd96... of/fdt: update of_get_flat_dt_prop in prep for libfdt
 static int __init opal_register_exception_handlers(void)
 {
 #ifdef __BIG_ENDIAN__
@@ -269,7 +331,7 @@ int opal_get_chars(uint32_t vtermno, char *buf, int count)
 	if ((be64_to_cpu(evt) & OPAL_EVENT_CONSOLE_INPUT) == 0)
 		return 0;
 	len = cpu_to_be64(count);
-	rc = opal_console_read(vtermno, &len, buf);	
+	rc = opal_console_read(vtermno, &len, buf);
 	if (rc == OPAL_SUCCESS)
 		return be64_to_cpu(len);
 	return 0;
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 972df0ffd4dc..0b84df948ed6 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -671,7 +671,7 @@ static int __init pseries_probe_fw_features(unsigned long node,
 					    void *data)
 {
 	const char *prop;
-	unsigned long len;
+	int len;
 	static int hypertas_found;
 	static int vec5_found;
 
@@ -704,7 +704,7 @@ static int __init pseries_probe_fw_features(unsigned long node,
 static int __init pSeries_probe(void)
 {
 	unsigned long root = of_get_flat_dt_root();
- 	char *dtype = of_get_flat_dt_prop(root, "device_type", NULL);
+	const char *dtype = of_get_flat_dt_prop(root, "device_type", NULL);
 
  	if (dtype == NULL)
  		return 0;
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index 84fe931bb60e..555f75cff7d3 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -221,7 +221,7 @@ static int __init xtensa_dt_io_area(unsigned long node, const char *uname,
 		int depth, void *data)
 {
 	const __be32 *ranges;
-	unsigned long len;
+	int len;
 
 	if (depth > 1)
 		return 0;
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index 61ffdca96e25..5b55c46fcde8 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -10,6 +10,11 @@ config ARM_GIC
 config GIC_NON_BANKED
 	bool
 
+config ARM_GIC_V3
+	bool
+	select IRQ_DOMAIN
+	select MULTI_IRQ_HANDLER
+
 config ARM_NVIC
 	bool
 	select IRQ_DOMAIN
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index 5194afb39e78..4adfda843424 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -13,7 +13,8 @@ obj-$(CONFIG_ARCH_MOXART)		+= irq-moxart.o
 obj-$(CONFIG_ORION_IRQCHIP)		+= irq-orion.o
 obj-$(CONFIG_ARCH_SUNXI)		+= irq-sun4i.o
 obj-$(CONFIG_ARCH_SPEAR3XX)		+= spear-shirq.o
-obj-$(CONFIG_ARM_GIC)			+= irq-gic.o
+obj-$(CONFIG_ARM_GIC)			+= irq-gic.o irq-gic-common.o
+obj-$(CONFIG_ARM_GIC_V3)		+= irq-gic-v3.o irq-gic-common.o
 obj-$(CONFIG_ARM_NVIC)			+= irq-nvic.o
 obj-$(CONFIG_ARM_VIC)			+= irq-vic.o
 obj-$(CONFIG_IMGPDC_IRQ)		+= irq-imgpdc.o
diff --git a/drivers/irqchip/irq-gic-common.c b/drivers/irqchip/irq-gic-common.c
new file mode 100644
index 000000000000..60ac704d2090
--- /dev/null
+++ b/drivers/irqchip/irq-gic-common.c
@@ -0,0 +1,115 @@
+/*
+ * Copyright (C) 2002 ARM Limited, All Rights Reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/irqchip/arm-gic.h>
+
+#include "irq-gic-common.h"
+
+void gic_configure_irq(unsigned int irq, unsigned int type,
+		       void __iomem *base, void (*sync_access)(void))
+{
+	u32 enablemask = 1 << (irq % 32);
+	u32 enableoff = (irq / 32) * 4;
+	u32 confmask = 0x2 << ((irq % 16) * 2);
+	u32 confoff = (irq / 16) * 4;
+	bool enabled = false;
+	u32 val;
+
+	/*
+	 * Read current configuration register, and insert the config
+	 * for "irq", depending on "type".
+	 */
+	val = readl_relaxed(base + GIC_DIST_CONFIG + confoff);
+	if (type == IRQ_TYPE_LEVEL_HIGH)
+		val &= ~confmask;
+	else if (type == IRQ_TYPE_EDGE_RISING)
+		val |= confmask;
+
+	/*
+	 * As recommended by the spec, disable the interrupt before changing
+	 * the configuration
+	 */
+	if (readl_relaxed(base + GIC_DIST_ENABLE_SET + enableoff) & enablemask) {
+		writel_relaxed(enablemask, base + GIC_DIST_ENABLE_CLEAR + enableoff);
+		if (sync_access)
+			sync_access();
+		enabled = true;
+	}
+
+	/*
+	 * Write back the new configuration, and possibly re-enable
+	 * the interrupt.
+	 */
+	writel_relaxed(val, base + GIC_DIST_CONFIG + confoff);
+
+	if (enabled)
+		writel_relaxed(enablemask, base + GIC_DIST_ENABLE_SET + enableoff);
+
+	if (sync_access)
+		sync_access();
+}
+
+void __init gic_dist_config(void __iomem *base, int gic_irqs,
+			    void (*sync_access)(void))
+{
+	unsigned int i;
+
+	/*
+	 * Set all global interrupts to be level triggered, active low.
+	 */
+	for (i = 32; i < gic_irqs; i += 16)
+		writel_relaxed(0, base + GIC_DIST_CONFIG + i / 4);
+
+	/*
+	 * Set priority on all global interrupts.
+	 */
+	for (i = 32; i < gic_irqs; i += 4)
+		writel_relaxed(0xa0a0a0a0, base + GIC_DIST_PRI + i);
+
+	/*
+	 * Disable all interrupts.  Leave the PPI and SGIs alone
+	 * as they are enabled by redistributor registers.
+	 */
+	for (i = 32; i < gic_irqs; i += 32)
+		writel_relaxed(0xffffffff, base + GIC_DIST_ENABLE_CLEAR + i / 8);
+
+	if (sync_access)
+		sync_access();
+}
+
+void gic_cpu_config(void __iomem *base, void (*sync_access)(void))
+{
+	int i;
+
+	/*
+	 * Deal with the banked PPI and SGI interrupts - disable all
+	 * PPI interrupts, ensure all SGI interrupts are enabled.
+	 */
+	writel_relaxed(0xffff0000, base + GIC_DIST_ENABLE_CLEAR);
+	writel_relaxed(0x0000ffff, base + GIC_DIST_ENABLE_SET);
+
+	/*
+	 * Set priority on PPI and SGI interrupts
+	 */
+	for (i = 0; i < 32; i += 4)
+		writel_relaxed(0xa0a0a0a0, base + GIC_DIST_PRI + i * 4 / 4);
+
+	if (sync_access)
+		sync_access();
+}
diff --git a/arch/arm64/include/asm/sigcontext.h b/drivers/irqchip/irq-gic-common.h
index dca1094acc74..b41f02481c3a 100644
--- a/arch/arm64/include/asm/sigcontext.h
+++ b/drivers/irqchip/irq-gic-common.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2002 ARM Limited, All Rights Reserved.
  *
  * 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
@@ -13,19 +13,17 @@
  * You should have received a copy of the GNU General Public License
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
-#ifndef __ASM_SIGCONTEXT_H
-#define __ASM_SIGCONTEXT_H
 
-#include <uapi/asm/sigcontext.h>
+#ifndef _IRQ_GIC_COMMON_H
+#define _IRQ_GIC_COMMON_H
 
-/*
- * Auxiliary context saved in the sigcontext.__reserved array. Not exported to
- * user space as it will change with the addition of new context. User space
- * should check the magic/size information.
- */
-struct aux_context {
-	struct fpsimd_context fpsimd;
-	/* additional context to be added before "end" */
-	struct _aarch64_ctx end;
-};
-#endif
+#include <linux/of.h>
+#include <linux/irqdomain.h>
+
+void gic_configure_irq(unsigned int irq, unsigned int type,
+                       void __iomem *base, void (*sync_access)(void));
+void gic_dist_config(void __iomem *base, int gic_irqs,
+		     void (*sync_access)(void));
+void gic_cpu_config(void __iomem *base, void (*sync_access)(void));
+
+#endif /* _IRQ_GIC_COMMON_H */
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
new file mode 100644
index 000000000000..57eaa5a0b1e3
--- /dev/null
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -0,0 +1,692 @@
+/*
+ * Copyright (C) 2013, 2014 ARM Limited, All Rights Reserved.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/cpu.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/percpu.h>
+#include <linux/slab.h>
+
+#include <linux/irqchip/arm-gic-v3.h>
+
+#include <asm/cputype.h>
+#include <asm/exception.h>
+#include <asm/smp_plat.h>
+
+#include "irq-gic-common.h"
+#include "irqchip.h"
+
+struct gic_chip_data {
+	void __iomem		*dist_base;
+	void __iomem		**redist_base;
+	void __percpu __iomem	**rdist;
+	struct irq_domain	*domain;
+	u64			redist_stride;
+	u32			redist_regions;
+	unsigned int		irq_nr;
+};
+
+static struct gic_chip_data gic_data __read_mostly;
+
+#define gic_data_rdist()		(this_cpu_ptr(gic_data.rdist))
+#define gic_data_rdist_rd_base()	(*gic_data_rdist())
+#define gic_data_rdist_sgi_base()	(gic_data_rdist_rd_base() + SZ_64K)
+
+/* Our default, arbitrary priority value. Linux only uses one anyway. */
+#define DEFAULT_PMR_VALUE	0xf0
+
+static inline unsigned int gic_irq(struct irq_data *d)
+{
+	return d->hwirq;
+}
+
+static inline int gic_irq_in_rdist(struct irq_data *d)
+{
+	return gic_irq(d) < 32;
+}
+
+static inline void __iomem *gic_dist_base(struct irq_data *d)
+{
+	if (gic_irq_in_rdist(d))	/* SGI+PPI -> SGI_base for this CPU */
+		return gic_data_rdist_sgi_base();
+
+	if (d->hwirq <= 1023)		/* SPI -> dist_base */
+		return gic_data.dist_base;
+
+	if (d->hwirq >= 8192)
+		BUG();		/* LPI Detected!!! */
+
+	return NULL;
+}
+
+static void gic_do_wait_for_rwp(void __iomem *base)
+{
+	u32 count = 1000000;	/* 1s! */
+
+	while (readl_relaxed(base + GICD_CTLR) & GICD_CTLR_RWP) {
+		count--;
+		if (!count) {
+			pr_err_ratelimited("RWP timeout, gone fishing\n");
+			return;
+		}
+		cpu_relax();
+		udelay(1);
+	};
+}
+
+/* Wait for completion of a distributor change */
+static void gic_dist_wait_for_rwp(void)
+{
+	gic_do_wait_for_rwp(gic_data.dist_base);
+}
+
+/* Wait for completion of a redistributor change */
+static void gic_redist_wait_for_rwp(void)
+{
+	gic_do_wait_for_rwp(gic_data_rdist_rd_base());
+}
+
+/* Low level accessors */
+static u64 gic_read_iar(void)
+{
+	u64 irqstat;
+
+	asm volatile("mrs_s %0, " __stringify(ICC_IAR1_EL1) : "=r" (irqstat));
+	return irqstat;
+}
+
+static void gic_write_pmr(u64 val)
+{
+	asm volatile("msr_s " __stringify(ICC_PMR_EL1) ", %0" : : "r" (val));
+}
+
+static void gic_write_ctlr(u64 val)
+{
+	asm volatile("msr_s " __stringify(ICC_CTLR_EL1) ", %0" : : "r" (val));
+	isb();
+}
+
+static void gic_write_grpen1(u64 val)
+{
+	asm volatile("msr_s " __stringify(ICC_GRPEN1_EL1) ", %0" : : "r" (val));
+	isb();
+}
+
+static void gic_write_sgi1r(u64 val)
+{
+	asm volatile("msr_s " __stringify(ICC_SGI1R_EL1) ", %0" : : "r" (val));
+}
+
+static void gic_enable_sre(void)
+{
+	u64 val;
+
+	asm volatile("mrs_s %0, " __stringify(ICC_SRE_EL1) : "=r" (val));
+	val |= ICC_SRE_EL1_SRE;
+	asm volatile("msr_s " __stringify(ICC_SRE_EL1) ", %0" : : "r" (val));
+	isb();
+
+	/*
+	 * Need to check that the SRE bit has actually been set. If
+	 * not, it means that SRE is disabled at EL2. We're going to
+	 * die painfully, and there is nothing we can do about it.
+	 *
+	 * Kindly inform the luser.
+	 */
+	asm volatile("mrs_s %0, " __stringify(ICC_SRE_EL1) : "=r" (val));
+	if (!(val & ICC_SRE_EL1_SRE))
+		pr_err("GIC: unable to set SRE (disabled at EL2), panic ahead\n");
+}
+
+static void gic_enable_redist(void)
+{
+	void __iomem *rbase;
+	u32 count = 1000000;	/* 1s! */
+	u32 val;
+
+	rbase = gic_data_rdist_rd_base();
+
+	/* Wake up this CPU redistributor */
+	val = readl_relaxed(rbase + GICR_WAKER);
+	val &= ~GICR_WAKER_ProcessorSleep;
+	writel_relaxed(val, rbase + GICR_WAKER);
+
+	while (readl_relaxed(rbase + GICR_WAKER) & GICR_WAKER_ChildrenAsleep) {
+		count--;
+		if (!count) {
+			pr_err_ratelimited("redist didn't wake up...\n");
+			return;
+		}
+		cpu_relax();
+		udelay(1);
+	};
+}
+
+/*
+ * Routines to disable, enable, EOI and route interrupts
+ */
+static void gic_poke_irq(struct irq_data *d, u32 offset)
+{
+	u32 mask = 1 << (gic_irq(d) % 32);
+	void (*rwp_wait)(void);
+	void __iomem *base;
+
+	if (gic_irq_in_rdist(d)) {
+		base = gic_data_rdist_sgi_base();
+		rwp_wait = gic_redist_wait_for_rwp;
+	} else {
+		base = gic_data.dist_base;
+		rwp_wait = gic_dist_wait_for_rwp;
+	}
+
+	writel_relaxed(mask, base + offset + (gic_irq(d) / 32) * 4);
+	rwp_wait();
+}
+
+static int gic_peek_irq(struct irq_data *d, u32 offset)
+{
+	u32 mask = 1 << (gic_irq(d) % 32);
+	void __iomem *base;
+
+	if (gic_irq_in_rdist(d))
+		base = gic_data_rdist_sgi_base();
+	else
+		base = gic_data.dist_base;
+
+	return !!(readl_relaxed(base + offset + (gic_irq(d) / 32) * 4) & mask);
+}
+
+static void gic_mask_irq(struct irq_data *d)
+{
+	gic_poke_irq(d, GICD_ICENABLER);
+}
+
+static void gic_unmask_irq(struct irq_data *d)
+{
+	gic_poke_irq(d, GICD_ISENABLER);
+}
+
+static void gic_eoi_irq(struct irq_data *d)
+{
+	gic_write_eoir(gic_irq(d));
+}
+
+static int gic_set_type(struct irq_data *d, unsigned int type)
+{
+	unsigned int irq = gic_irq(d);
+	void (*rwp_wait)(void);
+	void __iomem *base;
+
+	/* Interrupt configuration for SGIs can't be changed */
+	if (irq < 16)
+		return -EINVAL;
+
+	if (type != IRQ_TYPE_LEVEL_HIGH && type != IRQ_TYPE_EDGE_RISING)
+		return -EINVAL;
+
+	if (gic_irq_in_rdist(d)) {
+		base = gic_data_rdist_sgi_base();
+		rwp_wait = gic_redist_wait_for_rwp;
+	} else {
+		base = gic_data.dist_base;
+		rwp_wait = gic_dist_wait_for_rwp;
+	}
+
+	gic_configure_irq(irq, type, base, rwp_wait);
+
+	return 0;
+}
+
+static u64 gic_mpidr_to_affinity(u64 mpidr)
+{
+	u64 aff;
+
+	aff = (MPIDR_AFFINITY_LEVEL(mpidr, 3) << 32 |
+	       MPIDR_AFFINITY_LEVEL(mpidr, 2) << 16 |
+	       MPIDR_AFFINITY_LEVEL(mpidr, 1) << 8  |
+	       MPIDR_AFFINITY_LEVEL(mpidr, 0));
+
+	return aff;
+}
+
+static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
+{
+	u64 irqnr;
+
+	do {
+		irqnr = gic_read_iar();
+
+		if (likely(irqnr > 15 && irqnr < 1020)) {
+			u64 irq = irq_find_mapping(gic_data.domain, irqnr);
+			if (likely(irq)) {
+				handle_IRQ(irq, regs);
+				continue;
+			}
+
+			WARN_ONCE(true, "Unexpected SPI received!\n");
+			gic_write_eoir(irqnr);
+		}
+		if (irqnr < 16) {
+			gic_write_eoir(irqnr);
+#ifdef CONFIG_SMP
+			handle_IPI(irqnr, regs);
+#else
+			WARN_ONCE(true, "Unexpected SGI received!\n");
+#endif
+			continue;
+		}
+	} while (irqnr != ICC_IAR1_EL1_SPURIOUS);
+}
+
+static void __init gic_dist_init(void)
+{
+	unsigned int i;
+	u64 affinity;
+	void __iomem *base = gic_data.dist_base;
+
+	/* Disable the distributor */
+	writel_relaxed(0, base + GICD_CTLR);
+	gic_dist_wait_for_rwp();
+
+	gic_dist_config(base, gic_data.irq_nr, gic_dist_wait_for_rwp);
+
+	/* Enable distributor with ARE, Group1 */
+	writel_relaxed(GICD_CTLR_ARE_NS | GICD_CTLR_ENABLE_G1A | GICD_CTLR_ENABLE_G1,
+		       base + GICD_CTLR);
+
+	/*
+	 * Set all global interrupts to the boot CPU only. ARE must be
+	 * enabled.
+	 */
+	affinity = gic_mpidr_to_affinity(cpu_logical_map(smp_processor_id()));
+	for (i = 32; i < gic_data.irq_nr; i++)
+		writeq_relaxed(affinity, base + GICD_IROUTER + i * 8);
+}
+
+static int gic_populate_rdist(void)
+{
+	u64 mpidr = cpu_logical_map(smp_processor_id());
+	u64 typer;
+	u32 aff;
+	int i;
+
+	/*
+	 * Convert affinity to a 32bit value that can be matched to
+	 * GICR_TYPER bits [63:32].
+	 */
+	aff = (MPIDR_AFFINITY_LEVEL(mpidr, 3) << 24 |
+	       MPIDR_AFFINITY_LEVEL(mpidr, 2) << 16 |
+	       MPIDR_AFFINITY_LEVEL(mpidr, 1) << 8 |
+	       MPIDR_AFFINITY_LEVEL(mpidr, 0));
+
+	for (i = 0; i < gic_data.redist_regions; i++) {
+		void __iomem *ptr = gic_data.redist_base[i];
+		u32 reg;
+
+		reg = readl_relaxed(ptr + GICR_PIDR2) & GIC_PIDR2_ARCH_MASK;
+		if (reg != GIC_PIDR2_ARCH_GICv3 &&
+		    reg != GIC_PIDR2_ARCH_GICv4) { /* We're in trouble... */
+			pr_warn("No redistributor present @%p\n", ptr);
+			break;
+		}
+
+		do {
+			typer = readq_relaxed(ptr + GICR_TYPER);
+			if ((typer >> 32) == aff) {
+				gic_data_rdist_rd_base() = ptr;
+				pr_info("CPU%d: found redistributor %llx @%p\n",
+					smp_processor_id(),
+					(unsigned long long)mpidr, ptr);
+				return 0;
+			}
+
+			if (gic_data.redist_stride) {
+				ptr += gic_data.redist_stride;
+			} else {
+				ptr += SZ_64K * 2; /* Skip RD_base + SGI_base */
+				if (typer & GICR_TYPER_VLPIS)
+					ptr += SZ_64K * 2; /* Skip VLPI_base + reserved page */
+			}
+		} while (!(typer & GICR_TYPER_LAST));
+	}
+
+	/* We couldn't even deal with ourselves... */
+	WARN(true, "CPU%d: mpidr %llx has no re-distributor!\n",
+	     smp_processor_id(), (unsigned long long)mpidr);
+	return -ENODEV;
+}
+
+static void gic_cpu_init(void)
+{
+	void __iomem *rbase;
+
+	/* Register ourselves with the rest of the world */
+	if (gic_populate_rdist())
+		return;
+
+	gic_enable_redist();
+
+	rbase = gic_data_rdist_sgi_base();
+
+	gic_cpu_config(rbase, gic_redist_wait_for_rwp);
+
+	/* Enable system registers */
+	gic_enable_sre();
+
+	/* Set priority mask register */
+	gic_write_pmr(DEFAULT_PMR_VALUE);
+
+	/* EOI deactivates interrupt too (mode 0) */
+	gic_write_ctlr(ICC_CTLR_EL1_EOImode_drop_dir);
+
+	/* ... and let's hit the road... */
+	gic_write_grpen1(1);
+}
+
+#ifdef CONFIG_SMP
+static int gic_secondary_init(struct notifier_block *nfb,
+			      unsigned long action, void *hcpu)
+{
+	if (action == CPU_STARTING || action == CPU_STARTING_FROZEN)
+		gic_cpu_init();
+	return NOTIFY_OK;
+}
+
+/*
+ * Notifier for enabling the GIC CPU interface. Set an arbitrarily high
+ * priority because the GIC needs to be up before the ARM generic timers.
+ */
+static struct notifier_block gic_cpu_notifier = {
+	.notifier_call = gic_secondary_init,
+	.priority = 100,
+};
+
+static u16 gic_compute_target_list(int *base_cpu, const struct cpumask *mask,
+				   u64 cluster_id)
+{
+	int cpu = *base_cpu;
+	u64 mpidr = cpu_logical_map(cpu);
+	u16 tlist = 0;
+
+	while (cpu < nr_cpu_ids) {
+		/*
+		 * If we ever get a cluster of more than 16 CPUs, just
+		 * scream and skip that CPU.
+		 */
+		if (WARN_ON((mpidr & 0xff) >= 16))
+			goto out;
+
+		tlist |= 1 << (mpidr & 0xf);
+
+		cpu = cpumask_next(cpu, mask);
+		if (cpu == nr_cpu_ids)
+			goto out;
+
+		mpidr = cpu_logical_map(cpu);
+
+		if (cluster_id != (mpidr & ~0xffUL)) {
+			cpu--;
+			goto out;
+		}
+	}
+out:
+	*base_cpu = cpu;
+	return tlist;
+}
+
+static void gic_send_sgi(u64 cluster_id, u16 tlist, unsigned int irq)
+{
+	u64 val;
+
+	val = (MPIDR_AFFINITY_LEVEL(cluster_id, 3) << 48	|
+	       MPIDR_AFFINITY_LEVEL(cluster_id, 2) << 32	|
+	       irq << 24			    		|
+	       MPIDR_AFFINITY_LEVEL(cluster_id, 1) << 16	|
+	       tlist);
+
+	pr_debug("CPU%d: ICC_SGI1R_EL1 %llx\n", smp_processor_id(), val);
+	gic_write_sgi1r(val);
+}
+
+static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
+{
+	int cpu;
+
+	if (WARN_ON(irq >= 16))
+		return;
+
+	/*
+	 * Ensure that stores to Normal memory are visible to the
+	 * other CPUs before issuing the IPI.
+	 */
+	smp_wmb();
+
+	for_each_cpu_mask(cpu, *mask) {
+		u64 cluster_id = cpu_logical_map(cpu) & ~0xffUL;
+		u16 tlist;
+
+		tlist = gic_compute_target_list(&cpu, mask, cluster_id);
+		gic_send_sgi(cluster_id, tlist, irq);
+	}
+
+	/* Force the above writes to ICC_SGI1R_EL1 to be executed */
+	isb();
+}
+
+static void gic_smp_init(void)
+{
+	set_smp_cross_call(gic_raise_softirq);
+	register_cpu_notifier(&gic_cpu_notifier);
+}
+
+static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
+			    bool force)
+{
+	unsigned int cpu = cpumask_any_and(mask_val, cpu_online_mask);
+	void __iomem *reg;
+	int enabled;
+	u64 val;
+
+	if (gic_irq_in_rdist(d))
+		return -EINVAL;
+
+	/* If interrupt was enabled, disable it first */
+	enabled = gic_peek_irq(d, GICD_ISENABLER);
+	if (enabled)
+		gic_mask_irq(d);
+
+	reg = gic_dist_base(d) + GICD_IROUTER + (gic_irq(d) * 8);
+	val = gic_mpidr_to_affinity(cpu_logical_map(cpu));
+
+	writeq_relaxed(val, reg);
+
+	/*
+	 * If the interrupt was enabled, enabled it again. Otherwise,
+	 * just wait for the distributor to have digested our changes.
+	 */
+	if (enabled)
+		gic_unmask_irq(d);
+	else
+		gic_dist_wait_for_rwp();
+
+	return IRQ_SET_MASK_OK;
+}
+#else
+#define gic_set_affinity	NULL
+#define gic_smp_init()		do { } while(0)
+#endif
+
+static struct irq_chip gic_chip = {
+	.name			= "GICv3",
+	.irq_mask		= gic_mask_irq,
+	.irq_unmask		= gic_unmask_irq,
+	.irq_eoi		= gic_eoi_irq,
+	.irq_set_type		= gic_set_type,
+	.irq_set_affinity	= gic_set_affinity,
+};
+
+static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
+			      irq_hw_number_t hw)
+{
+	/* SGIs are private to the core kernel */
+	if (hw < 16)
+		return -EPERM;
+	/* PPIs */
+	if (hw < 32) {
+		irq_set_percpu_devid(irq);
+		irq_set_chip_and_handler(irq, &gic_chip,
+					 handle_percpu_devid_irq);
+		set_irq_flags(irq, IRQF_VALID | IRQF_NOAUTOEN);
+	}
+	/* SPIs */
+	if (hw >= 32 && hw < gic_data.irq_nr) {
+		irq_set_chip_and_handler(irq, &gic_chip,
+					 handle_fasteoi_irq);
+		set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+	}
+	irq_set_chip_data(irq, d->host_data);
+	return 0;
+}
+
+static int gic_irq_domain_xlate(struct irq_domain *d,
+				struct device_node *controller,
+				const u32 *intspec, unsigned int intsize,
+				unsigned long *out_hwirq, unsigned int *out_type)
+{
+	if (d->of_node != controller)
+		return -EINVAL;
+	if (intsize < 3)
+		return -EINVAL;
+
+	switch(intspec[0]) {
+	case 0:			/* SPI */
+		*out_hwirq = intspec[1] + 32;
+		break;
+	case 1:			/* PPI */
+		*out_hwirq = intspec[1] + 16;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	*out_type = intspec[2] & IRQ_TYPE_SENSE_MASK;
+	return 0;
+}
+
+static const struct irq_domain_ops gic_irq_domain_ops = {
+	.map = gic_irq_domain_map,
+	.xlate = gic_irq_domain_xlate,
+};
+
+static int __init gic_of_init(struct device_node *node, struct device_node *parent)
+{
+	void __iomem *dist_base;
+	void __iomem **redist_base;
+	u64 redist_stride;
+	u32 redist_regions;
+	u32 reg;
+	int gic_irqs;
+	int err;
+	int i;
+
+	dist_base = of_iomap(node, 0);
+	if (!dist_base) {
+		pr_err("%s: unable to map gic dist registers\n",
+			node->full_name);
+		return -ENXIO;
+	}
+
+	reg = readl_relaxed(dist_base + GICD_PIDR2) & GIC_PIDR2_ARCH_MASK;
+	if (reg != GIC_PIDR2_ARCH_GICv3 && reg != GIC_PIDR2_ARCH_GICv4) {
+		pr_err("%s: no distributor detected, giving up\n",
+			node->full_name);
+		err = -ENODEV;
+		goto out_unmap_dist;
+	}
+
+	if (of_property_read_u32(node, "#redistributor-regions", &redist_regions))
+		redist_regions = 1;
+
+	redist_base = kzalloc(sizeof(*redist_base) * redist_regions, GFP_KERNEL);
+	if (!redist_base) {
+		err = -ENOMEM;
+		goto out_unmap_dist;
+	}
+
+	for (i = 0; i < redist_regions; i++) {
+		redist_base[i] = of_iomap(node, 1 + i);
+		if (!redist_base[i]) {
+			pr_err("%s: couldn't map region %d\n",
+			       node->full_name, i);
+			err = -ENODEV;
+			goto out_unmap_rdist;
+		}
+	}
+
+	if (of_property_read_u64(node, "redistributor-stride", &redist_stride))
+		redist_stride = 0;
+
+	gic_data.dist_base = dist_base;
+	gic_data.redist_base = redist_base;
+	gic_data.redist_regions = redist_regions;
+	gic_data.redist_stride = redist_stride;
+
+	/*
+	 * Find out how many interrupts are supported.
+	 * The GIC only supports up to 1020 interrupt sources (SGI+PPI+SPI)
+	 */
+	gic_irqs = readl_relaxed(gic_data.dist_base + GICD_TYPER) & 0x1f;
+	gic_irqs = (gic_irqs + 1) * 32;
+	if (gic_irqs > 1020)
+		gic_irqs = 1020;
+	gic_data.irq_nr = gic_irqs;
+
+	gic_data.domain = irq_domain_add_tree(node, &gic_irq_domain_ops,
+					      &gic_data);
+	gic_data.rdist = alloc_percpu(typeof(*gic_data.rdist));
+
+	if (WARN_ON(!gic_data.domain) || WARN_ON(!gic_data.rdist)) {
+		err = -ENOMEM;
+		goto out_free;
+	}
+
+	set_handle_irq(gic_handle_irq);
+
+	gic_smp_init();
+	gic_dist_init();
+	gic_cpu_init();
+
+	return 0;
+
+out_free:
+	if (gic_data.domain)
+		irq_domain_remove(gic_data.domain);
+	free_percpu(gic_data.rdist);
+out_unmap_rdist:
+	for (i = 0; i < redist_regions; i++)
+		if (redist_base[i])
+			iounmap(redist_base[i]);
+	kfree(redist_base);
+out_unmap_dist:
+	iounmap(dist_base);
+	return err;
+}
+
+IRQCHIP_DECLARE(gic_v3, "arm,gic-v3", gic_of_init);
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 341c6016812d..afb37b13b6ed 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -1,6 +1,4 @@
 /*
- *  linux/arch/arm/common/gic.c
- *
  *  Copyright (C) 2002 ARM Limited, All Rights Reserved.
  *
  * This program is free software; you can redistribute it and/or modify
@@ -42,15 +40,17 @@
 #include <linux/irqchip/chained_irq.h>
 #include <linux/irqchip/arm-gic.h>
 
+#include <asm/cputype.h>
 #include <asm/irq.h>
 #include <asm/exception.h>
 #include <asm/smp_plat.h>
 
+#include "irq-gic-common.h"
 #include "irqchip.h"
 
 union gic_base {
 	void __iomem *common_base;
-	void __percpu __iomem **percpu_base;
+	void __percpu * __iomem *percpu_base;
 };
 
 struct gic_chip_data {
@@ -188,12 +188,6 @@ static int gic_set_type(struct irq_data *d, unsigned int type)
 {
 	void __iomem *base = gic_dist_base(d);
 	unsigned int gicirq = gic_irq(d);
-	u32 enablemask = 1 << (gicirq % 32);
-	u32 enableoff = (gicirq / 32) * 4;
-	u32 confmask = 0x2 << ((gicirq % 16) * 2);
-	u32 confoff = (gicirq / 16) * 4;
-	bool enabled = false;
-	u32 val;
 
 	/* Interrupt configuration for SGIs can't be changed */
 	if (gicirq < 16)
@@ -207,25 +201,7 @@ static int gic_set_type(struct irq_data *d, unsigned int type)
 	if (gic_arch_extn.irq_set_type)
 		gic_arch_extn.irq_set_type(d, type);
 
-	val = readl_relaxed(base + GIC_DIST_CONFIG + confoff);
-	if (type == IRQ_TYPE_LEVEL_HIGH)
-		val &= ~confmask;
-	else if (type == IRQ_TYPE_EDGE_RISING)
-		val |= confmask;
-
-	/*
-	 * As recommended by the spec, disable the interrupt before changing
-	 * the configuration
-	 */
-	if (readl_relaxed(base + GIC_DIST_ENABLE_SET + enableoff) & enablemask) {
-		writel_relaxed(enablemask, base + GIC_DIST_ENABLE_CLEAR + enableoff);
-		enabled = true;
-	}
-
-	writel_relaxed(val, base + GIC_DIST_CONFIG + confoff);
-
-	if (enabled)
-		writel_relaxed(enablemask, base + GIC_DIST_ENABLE_SET + enableoff);
+	gic_configure_irq(gicirq, type, base, NULL);
 
 	raw_spin_unlock(&irq_controller_lock);
 
@@ -279,7 +255,7 @@ static int gic_set_wake(struct irq_data *d, unsigned int on)
 #define gic_set_wake	NULL
 #endif
 
-static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
+static void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
 {
 	u32 irqstat, irqnr;
 	struct gic_chip_data *gic = &gic_data[0];
@@ -287,7 +263,7 @@ static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs
 
 	do {
 		irqstat = readl_relaxed(cpu_base + GIC_CPU_INTACK);
-		irqnr = irqstat & ~0x1c00;
+		irqnr = irqstat & GICC_IAR_INT_ID_MASK;
 
 		if (likely(irqnr > 15 && irqnr < 1021)) {
 			irqnr = irq_find_mapping(gic->domain, irqnr);
@@ -383,12 +359,6 @@ static void __init gic_dist_init(struct gic_chip_data *gic)
 	writel_relaxed(0, base + GIC_DIST_CTRL);
 
 	/*
-	 * Set all global interrupts to be level triggered, active low.
-	 */
-	for (i = 32; i < gic_irqs; i += 16)
-		writel_relaxed(0, base + GIC_DIST_CONFIG + i * 4 / 16);
-
-	/*
 	 * Set all global interrupts to this CPU only.
 	 */
 	cpumask = gic_get_cpumask(gic);
@@ -397,18 +367,7 @@ static void __init gic_dist_init(struct gic_chip_data *gic)
 	for (i = 32; i < gic_irqs; i += 4)
 		writel_relaxed(cpumask, base + GIC_DIST_TARGET + i * 4 / 4);
 
-	/*
-	 * Set priority on all global interrupts.
-	 */
-	for (i = 32; i < gic_irqs; i += 4)
-		writel_relaxed(0xa0a0a0a0, base + GIC_DIST_PRI + i * 4 / 4);
-
-	/*
-	 * Disable all interrupts.  Leave the PPI and SGIs alone
-	 * as these enables are banked registers.
-	 */
-	for (i = 32; i < gic_irqs; i += 32)
-		writel_relaxed(0xffffffff, base + GIC_DIST_ENABLE_CLEAR + i * 4 / 32);
+	gic_dist_config(base, gic_irqs, NULL);
 
 	writel_relaxed(1, base + GIC_DIST_CTRL);
 }
@@ -435,18 +394,7 @@ static void gic_cpu_init(struct gic_chip_data *gic)
 		if (i != cpu)
 			gic_cpu_map[i] &= ~cpu_mask;
 
-	/*
-	 * Deal with the banked PPI and SGI interrupts - disable all
-	 * PPI interrupts, ensure all SGI interrupts are enabled.
-	 */
-	writel_relaxed(0xffff0000, dist_base + GIC_DIST_ENABLE_CLEAR);
-	writel_relaxed(0x0000ffff, dist_base + GIC_DIST_ENABLE_SET);
-
-	/*
-	 * Set priority on PPI and SGI interrupts
-	 */
-	for (i = 0; i < 32; i += 4)
-		writel_relaxed(0xa0a0a0a0, dist_base + GIC_DIST_PRI + i * 4 / 4);
+	gic_cpu_config(dist_base, NULL);
 
 	writel_relaxed(0xf0, base + GIC_CPU_PRIMASK);
 	writel_relaxed(1, base + GIC_CPU_CTRL);
@@ -648,7 +596,7 @@ static void __init gic_pm_init(struct gic_chip_data *gic)
 #endif
 
 #ifdef CONFIG_SMP
-void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
+static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 {
 	int cpu;
 	unsigned long flags, map = 0;
@@ -661,9 +609,9 @@ void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 
 	/*
 	 * Ensure that stores to Normal memory are visible to the
-	 * other CPUs before issuing the IPI.
+	 * other CPUs before they observe us issuing the IPI.
 	 */
-	dsb();
+	dmb(ishst);
 
 	/* this always happens on GIC0 */
 	writel_relaxed(map << 16 | irq, gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT);
@@ -824,16 +772,25 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
 		irq_set_chip_and_handler(irq, &gic_chip,
 					 handle_fasteoi_irq);
 		set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+
+		gic_routable_irq_domain_ops->map(d, irq, hw);
 	}
 	irq_set_chip_data(irq, d->host_data);
 	return 0;
 }
 
+static void gic_irq_domain_unmap(struct irq_domain *d, unsigned int irq)
+{
+	gic_routable_irq_domain_ops->unmap(d, irq);
+}
+
 static int gic_irq_domain_xlate(struct irq_domain *d,
 				struct device_node *controller,
 				const u32 *intspec, unsigned int intsize,
 				unsigned long *out_hwirq, unsigned int *out_type)
 {
+	unsigned long ret = 0;
+
 	if (d->of_node != controller)
 		return -EINVAL;
 	if (intsize < 3)
@@ -843,11 +800,20 @@ static int gic_irq_domain_xlate(struct irq_domain *d,
 	*out_hwirq = intspec[1] + 16;
 
 	/* For SPIs, we need to add 16 more to get the GIC irq ID number */
-	if (!intspec[0])
-		*out_hwirq += 16;
+	if (!intspec[0]) {
+		ret = gic_routable_irq_domain_ops->xlate(d, controller,
+							 intspec,
+							 intsize,
+							 out_hwirq,
+							 out_type);
+
+		if (IS_ERR_VALUE(ret))
+			return ret;
+	}
 
 	*out_type = intspec[2] & IRQ_TYPE_SENSE_MASK;
-	return 0;
+
+	return ret;
 }
 
 #ifdef CONFIG_SMP
@@ -869,11 +835,43 @@ static struct notifier_block gic_cpu_notifier = {
 };
 #endif
 
-const struct irq_domain_ops gic_irq_domain_ops = {
+static const struct irq_domain_ops gic_irq_domain_ops = {
 	.map = gic_irq_domain_map,
+	.unmap = gic_irq_domain_unmap,
 	.xlate = gic_irq_domain_xlate,
 };
 
+/* Default functions for routable irq domain */
+static int gic_routable_irq_domain_map(struct irq_domain *d, unsigned int irq,
+			      irq_hw_number_t hw)
+{
+	return 0;
+}
+
+static void gic_routable_irq_domain_unmap(struct irq_domain *d,
+					  unsigned int irq)
+{
+}
+
+static int gic_routable_irq_domain_xlate(struct irq_domain *d,
+				struct device_node *controller,
+				const u32 *intspec, unsigned int intsize,
+				unsigned long *out_hwirq,
+				unsigned int *out_type)
+{
+	*out_hwirq += 16;
+	return 0;
+}
+
+const struct irq_domain_ops gic_default_routable_irq_domain_ops = {
+	.map = gic_routable_irq_domain_map,
+	.unmap = gic_routable_irq_domain_unmap,
+	.xlate = gic_routable_irq_domain_xlate,
+};
+
+const struct irq_domain_ops *gic_routable_irq_domain_ops =
+					&gic_default_routable_irq_domain_ops;
+
 void __init gic_init_bases(unsigned int gic_nr, int irq_start,
 			   void __iomem *dist_base, void __iomem *cpu_base,
 			   u32 percpu_offset, struct device_node *node)
@@ -881,6 +879,7 @@ void __init gic_init_bases(unsigned int gic_nr, int irq_start,
 	irq_hw_number_t hwirq_base;
 	struct gic_chip_data *gic;
 	int gic_irqs, irq_base, i;
+	int nr_routable_irqs;
 
 	BUG_ON(gic_nr >= MAX_GIC_NR);
 
@@ -899,7 +898,9 @@ void __init gic_init_bases(unsigned int gic_nr, int irq_start,
 		}
 
 		for_each_possible_cpu(cpu) {
-			unsigned long offset = percpu_offset * cpu_logical_map(cpu);
+			u32 mpidr = cpu_logical_map(cpu);
+			u32 core_id = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+			unsigned long offset = percpu_offset * core_id;
 			*per_cpu_ptr(gic->dist_base.percpu_base, cpu) = dist_base + offset;
 			*per_cpu_ptr(gic->cpu_base.percpu_base, cpu) = cpu_base + offset;
 		}
@@ -946,14 +947,25 @@ void __init gic_init_bases(unsigned int gic_nr, int irq_start,
 	gic->gic_irqs = gic_irqs;
 
 	gic_irqs -= hwirq_base; /* calculate # of irqs to allocate */
-	irq_base = irq_alloc_descs(irq_start, 16, gic_irqs, numa_node_id());
-	if (IS_ERR_VALUE(irq_base)) {
-		WARN(1, "Cannot allocate irq_descs @ IRQ%d, assuming pre-allocated\n",
-		     irq_start);
-		irq_base = irq_start;
+
+	if (of_property_read_u32(node, "arm,routable-irqs",
+				 &nr_routable_irqs)) {
+		irq_base = irq_alloc_descs(irq_start, 16, gic_irqs,
+					   numa_node_id());
+		if (IS_ERR_VALUE(irq_base)) {
+			WARN(1, "Cannot allocate irq_descs @ IRQ%d, assuming pre-allocated\n",
+			     irq_start);
+			irq_base = irq_start;
+		}
+
+		gic->domain = irq_domain_add_legacy(node, gic_irqs, irq_base,
+					hwirq_base, &gic_irq_domain_ops, gic);
+	} else {
+		gic->domain = irq_domain_add_linear(node, nr_routable_irqs,
+						    &gic_irq_domain_ops,
+						    gic);
 	}
-	gic->domain = irq_domain_add_legacy(node, gic_irqs, irq_base,
-				    hwirq_base, &gic_irq_domain_ops, gic);
+
 	if (WARN_ON(!gic->domain))
 		return;
 
@@ -974,7 +986,8 @@ void __init gic_init_bases(unsigned int gic_nr, int irq_start,
 #ifdef CONFIG_OF
 static int gic_cnt __initdata;
 
-int __init gic_of_init(struct device_node *node, struct device_node *parent)
+static int __init
+gic_of_init(struct device_node *node, struct device_node *parent)
 {
 	void __iomem *cpu_base;
 	void __iomem *dist_base;
@@ -1004,8 +1017,10 @@ int __init gic_of_init(struct device_node *node, struct device_node *parent)
 	gic_cnt++;
 	return 0;
 }
+IRQCHIP_DECLARE(gic_400, "arm,gic-400", gic_of_init);
 IRQCHIP_DECLARE(cortex_a15_gic, "arm,cortex-a15-gic", gic_of_init);
 IRQCHIP_DECLARE(cortex_a9_gic, "arm,cortex-a9-gic", gic_of_init);
+IRQCHIP_DECLARE(cortex_a7_gic, "arm,cortex-a7-gic", gic_of_init);
 IRQCHIP_DECLARE(msm_8660_qgic, "qcom,msm-8660-qgic", gic_of_init);
 IRQCHIP_DECLARE(msm_qgic2, "qcom,msm-qgic2", gic_of_init);
 
diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig
index c6973f101a3e..ec919a9160a5 100644
--- a/drivers/of/Kconfig
+++ b/drivers/of/Kconfig
@@ -28,6 +28,7 @@ config OF_SELFTEST
 config OF_FLATTREE
 	bool
 	select DTC
+	select LIBFDT
 
 config OF_EARLY_FLATTREE
 	bool
@@ -75,4 +76,10 @@ config OF_MTD
 	depends on MTD
 	def_bool y
 
+config OF_RESERVED_MEM
+	depends on OF_EARLY_FLATTREE
+	bool
+	help
+	  Helpers to allow for reservation of memory regions
+
 endmenu # OF
diff --git a/drivers/of/Makefile b/drivers/of/Makefile
index efd05102c405..9891232f999e 100644
--- a/drivers/of/Makefile
+++ b/drivers/of/Makefile
@@ -9,3 +9,6 @@ obj-$(CONFIG_OF_MDIO)	+= of_mdio.o
 obj-$(CONFIG_OF_PCI)	+= of_pci.o
 obj-$(CONFIG_OF_PCI_IRQ)  += of_pci_irq.o
 obj-$(CONFIG_OF_MTD)	+= of_mtd.o
+obj-$(CONFIG_OF_RESERVED_MEM) += of_reserved_mem.o
+
+CFLAGS_fdt.o = -I$(src)/../../scripts/dtc/libfdt
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 758b4f8b30b7..024b8f99d480 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -15,9 +15,12 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_fdt.h>
+#include <linux/of_reserved_mem.h>
+#include <linux/sizes.h>
 #include <linux/string.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
+#include <linux/libfdt.h>
 
 #include <asm/setup.h>  /* for COMMAND_LINE_SIZE */
 #ifdef CONFIG_PPC
@@ -26,54 +29,6 @@
 
 #include <asm/page.h>
 
-char *of_fdt_get_string(struct boot_param_header *blob, u32 offset)
-{
-	return ((char *)blob) +
-		be32_to_cpu(blob->off_dt_strings) + offset;
-}
-
-/**
- * of_fdt_get_property - Given a node in the given flat blob, return
- * the property ptr
- */
-void *of_fdt_get_property(struct boot_param_header *blob,
-		       unsigned long node, const char *name,
-		       unsigned long *size)
-{
-	unsigned long p = node;
-
-	do {
-		u32 tag = be32_to_cpup((__be32 *)p);
-		u32 sz, noff;
-		const char *nstr;
-
-		p += 4;
-		if (tag == OF_DT_NOP)
-			continue;
-		if (tag != OF_DT_PROP)
-			return NULL;
-
-		sz = be32_to_cpup((__be32 *)p);
-		noff = be32_to_cpup((__be32 *)(p + 4));
-		p += 8;
-		if (be32_to_cpu(blob->version) < 0x10)
-			p = ALIGN(p, sz >= 8 ? 8 : 4);
-
-		nstr = of_fdt_get_string(blob, noff);
-		if (nstr == NULL) {
-			pr_warning("Can't find property index name !\n");
-			return NULL;
-		}
-		if (strcmp(name, nstr) == 0) {
-			if (size)
-				*size = sz;
-			return (void *)p;
-		}
-		p += sz;
-		p = ALIGN(p, 4);
-	} while (1);
-}
-
 /**
  * of_fdt_is_compatible - Return true if given node from the given blob has
  * compat in its compatible list
@@ -88,9 +43,10 @@ int of_fdt_is_compatible(struct boot_param_header *blob,
 		      unsigned long node, const char *compat)
 {
 	const char *cp;
-	unsigned long cplen, l, score = 0;
+	int cplen;
+	unsigned long l, score = 0;
 
-	cp = of_fdt_get_property(blob, node, "compatible", &cplen);
+	cp = fdt_getprop(blob, node, "compatible", &cplen);
 	if (cp == NULL)
 		return 0;
 	while (cplen > 0) {
@@ -149,28 +105,27 @@ static void *unflatten_dt_alloc(void **mem, unsigned long size,
  */
 static void * unflatten_dt_node(struct boot_param_header *blob,
 				void *mem,
-				void **p,
+				int *poffset,
 				struct device_node *dad,
 				struct device_node ***allnextpp,
 				unsigned long fpsize)
 {
+	const __be32 *p;
 	struct device_node *np;
 	struct property *pp, **prev_pp = NULL;
-	char *pathp;
-	u32 tag;
+	const char *pathp;
 	unsigned int l, allocl;
+	static int depth = 0;
+	int old_depth;
+	int offset;
 	int has_name = 0;
 	int new_format = 0;
 
-	tag = be32_to_cpup(*p);
-	if (tag != OF_DT_BEGIN_NODE) {
-		pr_err("Weird tag at start of node: %x\n", tag);
+	pathp = fdt_get_name(blob, *poffset, &l);
+	if (!pathp)
 		return mem;
-	}
-	*p += 4;
-	pathp = *p;
-	l = allocl = strlen(pathp) + 1;
-	*p = PTR_ALIGN(*p + l, 4);
+
+	allocl = l++;
 
 	/* version 0x10 has a more compact unit name here instead of the full
 	 * path. we accumulate the full path size using "fpsize", we'll rebuild
@@ -188,7 +143,7 @@ static void * unflatten_dt_node(struct boot_param_header *blob,
 			fpsize = 1;
 			allocl = 2;
 			l = 1;
-			*pathp = '\0';
+			pathp = "";
 		} else {
 			/* account for '/' and path size minus terminal 0
 			 * already in 'l'
@@ -235,32 +190,23 @@ static void * unflatten_dt_node(struct boot_param_header *blob,
 		kref_init(&np->kref);
 	}
 	/* process properties */
-	while (1) {
-		u32 sz, noff;
-		char *pname;
-
-		tag = be32_to_cpup(*p);
-		if (tag == OF_DT_NOP) {
-			*p += 4;
-			continue;
-		}
-		if (tag != OF_DT_PROP)
+	for (offset = fdt_first_property_offset(blob, *poffset);
+	     (offset >= 0);
+	     (offset = fdt_next_property_offset(blob, offset))) {
+		const char *pname;
+		u32 sz;
+
+		if (!(p = fdt_getprop_by_offset(blob, offset, &pname, &sz))) {
+			offset = -FDT_ERR_INTERNAL;
 			break;
-		*p += 4;
-		sz = be32_to_cpup(*p);
-		noff = be32_to_cpup(*p + 4);
-		*p += 8;
-		if (be32_to_cpu(blob->version) < 0x10)
-			*p = PTR_ALIGN(*p, sz >= 8 ? 8 : 4);
-
-		pname = of_fdt_get_string(blob, noff);
+		}
+
 		if (pname == NULL) {
 			pr_info("Can't find property name in list !\n");
 			break;
 		}
 		if (strcmp(pname, "name") == 0)
 			has_name = 1;
-		l = strlen(pname) + 1;
 		pp = unflatten_dt_alloc(&mem, sizeof(struct property),
 					__alignof__(struct property));
 		if (allnextpp) {
@@ -272,26 +218,25 @@ static void * unflatten_dt_node(struct boot_param_header *blob,
 			if ((strcmp(pname, "phandle") == 0) ||
 			    (strcmp(pname, "linux,phandle") == 0)) {
 				if (np->phandle == 0)
-					np->phandle = be32_to_cpup((__be32*)*p);
+					np->phandle = be32_to_cpup(p);
 			}
 			/* And we process the "ibm,phandle" property
 			 * used in pSeries dynamic device tree
 			 * stuff */
 			if (strcmp(pname, "ibm,phandle") == 0)
-				np->phandle = be32_to_cpup((__be32 *)*p);
-			pp->name = pname;
+				np->phandle = be32_to_cpup(p);
+			pp->name = (char *)pname;
 			pp->length = sz;
-			pp->value = *p;
+			pp->value = (__be32 *)p;
 			*prev_pp = pp;
 			prev_pp = &pp->next;
 		}
-		*p = PTR_ALIGN((*p) + sz, 4);
 	}
 	/* with version 0x10 we may not have the name property, recreate
 	 * it here from the unit name if absent
 	 */
 	if (!has_name) {
-		char *p1 = pathp, *ps = pathp, *pa = NULL;
+		const char *p1 = pathp, *ps = pathp, *pa = NULL;
 		int sz;
 
 		while (*p1) {
@@ -328,19 +273,18 @@ static void * unflatten_dt_node(struct boot_param_header *blob,
 		if (!np->type)
 			np->type = "<NULL>";
 	}
-	while (tag == OF_DT_BEGIN_NODE || tag == OF_DT_NOP) {
-		if (tag == OF_DT_NOP)
-			*p += 4;
-		else
-			mem = unflatten_dt_node(blob, mem, p, np, allnextpp,
-						fpsize);
-		tag = be32_to_cpup(*p);
-	}
-	if (tag != OF_DT_END_NODE) {
-		pr_err("Weird tag at end of node: %x\n", tag);
-		return mem;
-	}
-	*p += 4;
+
+	old_depth = depth;
+	*poffset = fdt_next_node(blob, *poffset, &depth);
+	if (depth < 0)
+		depth = 0;
+	while (*poffset > 0 && depth > old_depth)
+		mem = unflatten_dt_node(blob, mem, poffset, np, allnextpp,
+					fpsize);
+
+	if (*poffset < 0 && *poffset != -FDT_ERR_NOTFOUND)
+		pr_err("unflatten: error %d processing FDT\n", *poffset);
+
 	return mem;
 }
 
@@ -361,7 +305,8 @@ static void __unflatten_device_tree(struct boot_param_header *blob,
 			     void * (*dt_alloc)(u64 size, u64 align))
 {
 	unsigned long size;
-	void *start, *mem;
+	int start;
+	void *mem;
 	struct device_node **allnextp = mynodes;
 
 	pr_debug(" -> unflatten_device_tree()\n");
@@ -382,7 +327,7 @@ static void __unflatten_device_tree(struct boot_param_header *blob,
 	}
 
 	/* First pass, scan for size */
-	start = ((void *)blob) + be32_to_cpu(blob->off_dt_struct);
+	start = 0;
 	size = (unsigned long)unflatten_dt_node(blob, 0, &start, NULL, NULL, 0);
 	size = ALIGN(size, 4);
 
@@ -397,10 +342,8 @@ static void __unflatten_device_tree(struct boot_param_header *blob,
 	pr_debug("  unflattening %p...\n", mem);
 
 	/* Second pass, do actual unflattening */
-	start = ((void *)blob) + be32_to_cpu(blob->off_dt_struct);
+	start = 0;
 	unflatten_dt_node(blob, mem, &start, NULL, &allnextp, 0);
-	if (be32_to_cpup(start) != OF_DT_END)
-		pr_warning("Weird tag at end of tree: %08x\n", be32_to_cpup(start));
 	if (be32_to_cpup(mem + size) != 0xdeadbeef)
 		pr_warning("End of tree marker overwritten: %08x\n",
 			   be32_to_cpup(mem + size));
@@ -440,6 +383,129 @@ struct boot_param_header *initial_boot_params;
 #ifdef CONFIG_OF_EARLY_FLATTREE
 
 /**
+ * res_mem_reserve_reg() - reserve all memory described in 'reg' property
+ */
+static int __init __reserved_mem_reserve_reg(unsigned long node,
+					     const char *uname)
+{
+	int t_len = (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32);
+	phys_addr_t base, size;
+	int len;
+	const __be32 *prop;
+	int nomap, first = 1;
+
+	prop = of_get_flat_dt_prop(node, "reg", &len);
+	if (!prop)
+		return -ENOENT;
+
+	if (len && len % t_len != 0) {
+		pr_err("Reserved memory: invalid reg property in '%s', skipping node.\n",
+		       uname);
+		return -EINVAL;
+	}
+
+	nomap = of_get_flat_dt_prop(node, "no-map", NULL) != NULL;
+
+	while (len >= t_len) {
+		base = dt_mem_next_cell(dt_root_addr_cells, &prop);
+		size = dt_mem_next_cell(dt_root_size_cells, &prop);
+
+		if (base && size &&
+		    early_init_dt_reserve_memory_arch(base, size, nomap) == 0)
+			pr_debug("Reserved memory: reserved region for node '%s': base %pa, size %ld MiB\n",
+				uname, &base, (unsigned long)size / SZ_1M);
+		else
+			pr_info("Reserved memory: failed to reserve memory for node '%s': base %pa, size %ld MiB\n",
+				uname, &base, (unsigned long)size / SZ_1M);
+
+		len -= t_len;
+		if (first) {
+			fdt_reserved_mem_save_node(node, uname, base, size);
+			first = 0;
+		}
+	}
+	return 0;
+}
+
+/**
+ * __reserved_mem_check_root() - check if #size-cells, #address-cells provided
+ * in /reserved-memory matches the values supported by the current implementation,
+ * also check if ranges property has been provided
+ */
+static int __init __reserved_mem_check_root(unsigned long node)
+{
+	const __be32 *prop;
+
+	prop = of_get_flat_dt_prop(node, "#size-cells", NULL);
+	if (!prop || be32_to_cpup(prop) != dt_root_size_cells)
+		return -EINVAL;
+
+	prop = of_get_flat_dt_prop(node, "#address-cells", NULL);
+	if (!prop || be32_to_cpup(prop) != dt_root_addr_cells)
+		return -EINVAL;
+
+	prop = of_get_flat_dt_prop(node, "ranges", NULL);
+	if (!prop)
+		return -EINVAL;
+	return 0;
+}
+
+/**
+ * fdt_scan_reserved_mem() - scan a single FDT node for reserved memory
+ */
+static int __init __fdt_scan_reserved_mem(unsigned long node, const char *uname,
+					  int depth, void *data)
+{
+	static int found;
+	const char *status;
+	int err;
+
+	if (!found && depth == 1 && strcmp(uname, "reserved-memory") == 0) {
+		if (__reserved_mem_check_root(node) != 0) {
+			pr_err("Reserved memory: unsupported node format, ignoring\n");
+			/* break scan */
+			return 1;
+		}
+		found = 1;
+		/* scan next node */
+		return 0;
+	} else if (!found) {
+		/* scan next node */
+		return 0;
+	} else if (found && depth < 2) {
+		/* scanning of /reserved-memory has been finished */
+		return 1;
+	}
+
+	status = of_get_flat_dt_prop(node, "status", NULL);
+	if (status && strcmp(status, "okay") != 0 && strcmp(status, "ok") != 0)
+		return 0;
+
+	err = __reserved_mem_reserve_reg(node, uname);
+	if (err == -ENOENT && of_get_flat_dt_prop(node, "size", NULL))
+		fdt_reserved_mem_save_node(node, uname, 0, 0);
+
+	/* scan next node */
+	return 0;
+}
+
+/**
+ * early_init_fdt_scan_reserved_mem() - create reserved memory regions
+ *
+ * This function grabs memory from early allocator for device exclusive use
+ * defined in device tree structures. It should be called by arch specific code
+ * once the early allocator (i.e. memblock) has been fully activated.
+ */
+void __init early_init_fdt_scan_reserved_mem(void)
+{
+	if (!initial_boot_params)
+		return;
+
+	of_scan_flat_dt(__fdt_scan_reserved_mem, NULL);
+	fdt_init_reserved_mem();
+}
+
+/**
  * of_scan_flat_dt - scan flattened tree blob and call callback on each.
  * @it: callback function
  * @data: context data pointer
@@ -453,47 +519,19 @@ int __init of_scan_flat_dt(int (*it)(unsigned long node,
 				     void *data),
 			   void *data)
 {
-	unsigned long p = ((unsigned long)initial_boot_params) +
-		be32_to_cpu(initial_boot_params->off_dt_struct);
-	int rc = 0;
-	int depth = -1;
-
-	do {
-		u32 tag = be32_to_cpup((__be32 *)p);
-		const char *pathp;
-
-		p += 4;
-		if (tag == OF_DT_END_NODE) {
-			depth--;
-			continue;
-		}
-		if (tag == OF_DT_NOP)
-			continue;
-		if (tag == OF_DT_END)
-			break;
-		if (tag == OF_DT_PROP) {
-			u32 sz = be32_to_cpup((__be32 *)p);
-			p += 8;
-			if (be32_to_cpu(initial_boot_params->version) < 0x10)
-				p = ALIGN(p, sz >= 8 ? 8 : 4);
-			p += sz;
-			p = ALIGN(p, 4);
-			continue;
-		}
-		if (tag != OF_DT_BEGIN_NODE) {
-			pr_err("Invalid tag %x in flat device tree!\n", tag);
-			return -EINVAL;
-		}
-		depth++;
-		pathp = (char *)p;
-		p = ALIGN(p + strlen(pathp) + 1, 4);
+	const void *blob = initial_boot_params;
+	const char *pathp;
+	int offset, rc = 0, depth = -1;
+
+        for (offset = fdt_next_node(blob, -1, &depth);
+             offset >= 0 && depth >= 0 && !rc;
+             offset = fdt_next_node(blob, offset, &depth)) {
+
+		pathp = fdt_get_name(blob, offset, NULL);
 		if (*pathp == '/')
 			pathp = kbasename(pathp);
-		rc = it(p, pathp, depth, data);
-		if (rc != 0)
-			break;
-	} while (1);
-
+		rc = it(offset, pathp, depth, data);
+	}
 	return rc;
 }
 
@@ -502,14 +540,7 @@ int __init of_scan_flat_dt(int (*it)(unsigned long node,
  */
 unsigned long __init of_get_flat_dt_root(void)
 {
-	unsigned long p = ((unsigned long)initial_boot_params) +
-		be32_to_cpu(initial_boot_params->off_dt_struct);
-
-	while (be32_to_cpup((__be32 *)p) == OF_DT_NOP)
-		p += 4;
-	BUG_ON(be32_to_cpup((__be32 *)p) != OF_DT_BEGIN_NODE);
-	p += 4;
-	return ALIGN(p + strlen((char *)p) + 1, 4);
+	return 0;
 }
 
 /**
@@ -518,10 +549,10 @@ unsigned long __init of_get_flat_dt_root(void)
  * This function can be used within scan_flattened_dt callback to get
  * access to properties
  */
-void *__init of_get_flat_dt_prop(unsigned long node, const char *name,
-				 unsigned long *size)
+const void *__init of_get_flat_dt_prop(unsigned long node, const char *name,
+				       int *size)
 {
-	return of_fdt_get_property(initial_boot_params, node, name, size);
+	return fdt_getprop(initial_boot_params, node, name, size);
 }
 
 /**
@@ -551,73 +582,6 @@ struct fdt_scan_status {
 	void *data;
 };
 
-/**
- * fdt_scan_node_by_path - iterator for of_scan_flat_dt_by_path function
- */
-static int __init fdt_scan_node_by_path(unsigned long node, const char *uname,
-					int depth, void *data)
-{
-	struct fdt_scan_status *st = data;
-
-	/*
-	 * if scan at the requested fdt node has been completed,
-	 * return -ENXIO to abort further scanning
-	 */
-	if (depth <= st->depth)
-		return -ENXIO;
-
-	/* requested fdt node has been found, so call iterator function */
-	if (st->found)
-		return st->iterator(node, uname, depth, st->data);
-
-	/* check if scanning automata is entering next level of fdt nodes */
-	if (depth == st->depth + 1 &&
-	    strncmp(st->name, uname, st->namelen) == 0 &&
-	    uname[st->namelen] == 0) {
-		st->depth += 1;
-		if (st->name[st->namelen] == 0) {
-			st->found = 1;
-		} else {
-			const char *next = st->name + st->namelen + 1;
-			st->name = next;
-			st->namelen = strcspn(next, "/");
-		}
-		return 0;
-	}
-
-	/* scan next fdt node */
-	return 0;
-}
-
-/**
- * of_scan_flat_dt_by_path - scan flattened tree blob and call callback on each
- *			     child of the given path.
- * @path: path to start searching for children
- * @it: callback function
- * @data: context data pointer
- *
- * This function is used to scan the flattened device-tree starting from the
- * node given by path. It is used to extract information (like reserved
- * memory), which is required on ealy boot before we can unflatten the tree.
- */
-int __init of_scan_flat_dt_by_path(const char *path,
-	int (*it)(unsigned long node, const char *name, int depth, void *data),
-	void *data)
-{
-	struct fdt_scan_status st = {path, 0, -1, 0, it, data};
-	int ret = 0;
-
-	if (initial_boot_params)
-                ret = of_scan_flat_dt(fdt_scan_node_by_path, &st);
-
-	if (!st.found)
-		return -ENOENT;
-	else if (ret == -ENXIO)	/* scan has been completed */
-		return 0;
-	else
-		return ret;
-}
-
 const char * __init of_flat_dt_get_machine_name(void)
 {
 	const char *name;
@@ -657,7 +621,7 @@ const void * __init of_flat_dt_match_machine(const void *default_match,
 	}
 	if (!best_data) {
 		const char *prop;
-		long size;
+		int size;
 
 		pr_err("\n unrecognized device tree list:\n[ ");
 
@@ -686,8 +650,8 @@ const void * __init of_flat_dt_match_machine(const void *default_match,
 static void __init early_init_dt_check_for_initrd(unsigned long node)
 {
 	u64 start, end;
-	unsigned long len;
-	__be32 *prop;
+	int len;
+	const __be32 *prop;
 
 	pr_debug("Looking for initrd properties... ");
 
@@ -720,7 +684,7 @@ static inline void early_init_dt_check_for_initrd(unsigned long node)
 int __init early_init_dt_scan_root(unsigned long node, const char *uname,
 				   int depth, void *data)
 {
-	__be32 *prop;
+	const __be32 *prop;
 
 	if (depth != 0)
 		return 0;
@@ -742,9 +706,9 @@ int __init early_init_dt_scan_root(unsigned long node, const char *uname,
 	return 1;
 }
 
-u64 __init dt_mem_next_cell(int s, __be32 **cellp)
+u64 __init dt_mem_next_cell(int s, const __be32 **cellp)
 {
-	__be32 *p = *cellp;
+	const __be32 *p = *cellp;
 
 	*cellp = p + s;
 	return of_read_number(p, s);
@@ -756,9 +720,9 @@ u64 __init dt_mem_next_cell(int s, __be32 **cellp)
 int __init early_init_dt_scan_memory(unsigned long node, const char *uname,
 				     int depth, void *data)
 {
-	char *type = of_get_flat_dt_prop(node, "device_type", NULL);
-	__be32 *reg, *endp;
-	unsigned long l;
+	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+	const __be32 *reg, *endp;
+	int l;
 
 	/* We are scanning "memory" nodes only */
 	if (type == NULL) {
@@ -779,7 +743,7 @@ int __init early_init_dt_scan_memory(unsigned long node, const char *uname,
 
 	endp = reg + (l / sizeof(__be32));
 
-	pr_debug("memory scan node %s, reg size %ld, data: %x %x %x %x,\n",
+	pr_debug("memory scan node %s, reg size %d, data: %x %x %x %x,\n",
 	    uname, l, reg[0], reg[1], reg[2], reg[3]);
 
 	while ((endp - reg) >= (dt_root_addr_cells + dt_root_size_cells)) {
@@ -802,8 +766,8 @@ int __init early_init_dt_scan_memory(unsigned long node, const char *uname,
 int __init early_init_dt_scan_chosen(unsigned long node, const char *uname,
 				     int depth, void *data)
 {
-	unsigned long l;
-	char *p;
+	int l;
+	const char *p;
 
 	pr_debug("search \"chosen\", depth: %d, uname: %s\n", depth, uname);
 
@@ -856,6 +820,16 @@ void __init __weak early_init_dt_add_memory_arch(u64 base, u64 size)
 	memblock_add(base, size);
 }
 
+int __init __weak early_init_dt_reserve_memory_arch(phys_addr_t base,
+					phys_addr_t size, bool nomap)
+{
+	if (memblock_is_region_reserved(base, size))
+		return -EBUSY;
+	if (nomap)
+		return memblock_remove(base, size);
+	return memblock_reserve(base, size);
+}
+
 /*
  * called from unflatten_device_tree() to bootstrap devicetree itself
  * Architectures can override this definition if memblock isn't used
@@ -864,6 +838,14 @@ void * __init __weak early_init_dt_alloc_memory_arch(u64 size, u64 align)
 {
 	return __va(memblock_alloc(size, align));
 }
+#else
+int __init __weak early_init_dt_reserve_memory_arch(phys_addr_t base,
+					phys_addr_t size, bool nomap)
+{
+	pr_err("Reserved memory not supported, ignoring range 0x%llx - 0x%llx%s\n",
+		  base, size, nomap ? " (nomap)" : "");
+	return -ENOSYS;
+}
 #endif
 
 bool __init early_init_dt_scan(void *params)
diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
new file mode 100644
index 000000000000..e420eb52e5c9
--- /dev/null
+++ b/drivers/of/of_reserved_mem.c
@@ -0,0 +1,217 @@
+/*
+ * Device tree based initialization code for reserved memory.
+ *
+ * Copyright (c) 2013, The Linux Foundation. All Rights Reserved.
+ * Copyright (c) 2013,2014 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ * Author: Marek Szyprowski <m.szyprowski@samsung.com>
+ * Author: Josh Cartwright <joshc@codeaurora.org>
+ *
+ * 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 optional) any later version of the license.
+ */
+
+#include <linux/err.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/of_platform.h>
+#include <linux/mm.h>
+#include <linux/sizes.h>
+#include <linux/of_reserved_mem.h>
+
+#define MAX_RESERVED_REGIONS	16
+static struct reserved_mem reserved_mem[MAX_RESERVED_REGIONS];
+static int reserved_mem_count;
+
+#if defined(CONFIG_HAVE_MEMBLOCK)
+#include <linux/memblock.h>
+int __init __weak early_init_dt_alloc_reserved_memory_arch(phys_addr_t size,
+	phys_addr_t align, phys_addr_t start, phys_addr_t end, bool nomap,
+	phys_addr_t *res_base)
+{
+	/*
+	 * We use __memblock_alloc_base() because memblock_alloc_base()
+	 * panic()s on allocation failure.
+	 */
+	phys_addr_t base = __memblock_alloc_base(size, align, end);
+	if (!base)
+		return -ENOMEM;
+
+	/*
+	 * Check if the allocated region fits in to start..end window
+	 */
+	if (base < start) {
+		memblock_free(base, size);
+		return -ENOMEM;
+	}
+
+	*res_base = base;
+	if (nomap)
+		return memblock_remove(base, size);
+	return 0;
+}
+#else
+int __init __weak early_init_dt_alloc_reserved_memory_arch(phys_addr_t size,
+	phys_addr_t align, phys_addr_t start, phys_addr_t end, bool nomap,
+	phys_addr_t *res_base)
+{
+	pr_err("Reserved memory not supported, ignoring region 0x%llx%s\n",
+		  size, nomap ? " (nomap)" : "");
+	return -ENOSYS;
+}
+#endif
+
+/**
+ * res_mem_save_node() - save fdt node for second pass initialization
+ */
+void __init fdt_reserved_mem_save_node(unsigned long node, const char *uname,
+				      phys_addr_t base, phys_addr_t size)
+{
+	struct reserved_mem *rmem = &reserved_mem[reserved_mem_count];
+
+	if (reserved_mem_count == ARRAY_SIZE(reserved_mem)) {
+		pr_err("Reserved memory: not enough space all defined regions.\n");
+		return;
+	}
+
+	rmem->fdt_node = node;
+	rmem->name = uname;
+	rmem->base = base;
+	rmem->size = size;
+
+	reserved_mem_count++;
+	return;
+}
+
+/**
+ * res_mem_alloc_size() - allocate reserved memory described by 'size', 'align'
+ *			  and 'alloc-ranges' properties
+ */
+static int __init __reserved_mem_alloc_size(unsigned long node,
+	const char *uname, phys_addr_t *res_base, phys_addr_t *res_size)
+{
+	int t_len = (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32);
+	phys_addr_t start = 0, end = 0;
+	phys_addr_t base = 0, align = 0, size;
+	int len;
+	const __be32 *prop;
+	int nomap;
+	int ret;
+
+	prop = of_get_flat_dt_prop(node, "size", &len);
+	if (!prop)
+		return -EINVAL;
+
+	if (len != dt_root_size_cells * sizeof(__be32)) {
+		pr_err("Reserved memory: invalid size property in '%s' node.\n",
+				uname);
+		return -EINVAL;
+	}
+	size = dt_mem_next_cell(dt_root_size_cells, &prop);
+
+	nomap = of_get_flat_dt_prop(node, "no-map", NULL) != NULL;
+
+	prop = of_get_flat_dt_prop(node, "alignment", &len);
+	if (prop) {
+		if (len != dt_root_addr_cells * sizeof(__be32)) {
+			pr_err("Reserved memory: invalid alignment property in '%s' node.\n",
+				uname);
+			return -EINVAL;
+		}
+		align = dt_mem_next_cell(dt_root_addr_cells, &prop);
+	}
+
+	prop = of_get_flat_dt_prop(node, "alloc-ranges", &len);
+	if (prop) {
+
+		if (len % t_len != 0) {
+			pr_err("Reserved memory: invalid alloc-ranges property in '%s', skipping node.\n",
+			       uname);
+			return -EINVAL;
+		}
+
+		base = 0;
+
+		while (len > 0) {
+			start = dt_mem_next_cell(dt_root_addr_cells, &prop);
+			end = start + dt_mem_next_cell(dt_root_size_cells,
+						       &prop);
+
+			ret = early_init_dt_alloc_reserved_memory_arch(size,
+					align, start, end, nomap, &base);
+			if (ret == 0) {
+				pr_debug("Reserved memory: allocated memory for '%s' node: base %pa, size %ld MiB\n",
+					uname, &base,
+					(unsigned long)size / SZ_1M);
+				break;
+			}
+			len -= t_len;
+		}
+
+	} else {
+		ret = early_init_dt_alloc_reserved_memory_arch(size, align,
+							0, 0, nomap, &base);
+		if (ret == 0)
+			pr_debug("Reserved memory: allocated memory for '%s' node: base %pa, size %ld MiB\n",
+				uname, &base, (unsigned long)size / SZ_1M);
+	}
+
+	if (base == 0) {
+		pr_info("Reserved memory: failed to allocate memory for node '%s'\n",
+			uname);
+		return -ENOMEM;
+	}
+
+	*res_base = base;
+	*res_size = size;
+
+	return 0;
+}
+
+static const struct of_device_id __rmem_of_table_sentinel
+	__used __section(__reservedmem_of_table_end);
+
+/**
+ * res_mem_init_node() - call region specific reserved memory init code
+ */
+static int __init __reserved_mem_init_node(struct reserved_mem *rmem)
+{
+	extern const struct of_device_id __reservedmem_of_table[];
+	const struct of_device_id *i;
+
+	for (i = __reservedmem_of_table; i < &__rmem_of_table_sentinel; i++) {
+		reservedmem_of_init_fn initfn = i->data;
+		const char *compat = i->compatible;
+
+		if (!of_flat_dt_is_compatible(rmem->fdt_node, compat))
+			continue;
+
+		if (initfn(rmem, rmem->fdt_node, rmem->name) == 0) {
+			pr_info("Reserved memory: initialized node %s, compatible id %s\n",
+				rmem->name, compat);
+			return 0;
+		}
+	}
+	return -ENOENT;
+}
+
+/**
+ * fdt_init_reserved_mem - allocate and init all saved reserved memory regions
+ */
+void __init fdt_init_reserved_mem(void)
+{
+	int i;
+	for (i = 0; i < reserved_mem_count; i++) {
+		struct reserved_mem *rmem = &reserved_mem[i];
+		unsigned long node = rmem->fdt_node;
+		int err = 0;
+
+		if (rmem->size == 0)
+			err = __reserved_mem_alloc_size(node, rmem->name,
+						 &rmem->base, &rmem->size);
+		if (err == 0)
+			__reserved_mem_init_node(rmem);
+	}
+}
diff --git a/include/asm-generic/early_ioremap.h b/include/asm-generic/early_ioremap.h
new file mode 100644
index 000000000000..a5de55c04fb2
--- /dev/null
+++ b/include/asm-generic/early_ioremap.h
@@ -0,0 +1,42 @@
+#ifndef _ASM_EARLY_IOREMAP_H_
+#define _ASM_EARLY_IOREMAP_H_
+
+#include <linux/types.h>
+
+/*
+ * early_ioremap() and early_iounmap() are for temporary early boot-time
+ * mappings, before the real ioremap() is functional.
+ */
+extern void __iomem *early_ioremap(resource_size_t phys_addr,
+				   unsigned long size);
+extern void *early_memremap(resource_size_t phys_addr,
+			    unsigned long size);
+extern void early_iounmap(void __iomem *addr, unsigned long size);
+extern void early_memunmap(void *addr, unsigned long size);
+
+/*
+ * Weak function called by early_ioremap_reset(). It does nothing, but
+ * architectures may provide their own version to do any needed cleanups.
+ */
+extern void early_ioremap_shutdown(void);
+
+#if defined(CONFIG_GENERIC_EARLY_IOREMAP) && defined(CONFIG_MMU)
+/* Arch-specific initialization */
+extern void early_ioremap_init(void);
+
+/* Generic initialization called by architecture code */
+extern void early_ioremap_setup(void);
+
+/*
+ * Called as last step in paging_init() so library can act
+ * accordingly for subsequent map/unmap requests.
+ */
+extern void early_ioremap_reset(void);
+
+#else
+static inline void early_ioremap_init(void) { }
+static inline void early_ioremap_setup(void) { }
+static inline void early_ioremap_reset(void) { }
+#endif
+
+#endif /* _ASM_EARLY_IOREMAP_H_ */
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index bc2121fa9132..f10f64fcc815 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -167,6 +167,16 @@
 #define CLK_OF_TABLES()
 #endif
 
+#ifdef CONFIG_OF_RESERVED_MEM
+#define RESERVEDMEM_OF_TABLES()				\
+	. = ALIGN(8);					\
+	VMLINUX_SYMBOL(__reservedmem_of_table) = .;	\
+	*(__reservedmem_of_table)			\
+	*(__reservedmem_of_table_end)
+#else
+#define RESERVEDMEM_OF_TABLES()
+#endif
+
 #define KERNEL_DTB()							\
 	STRUCT_ALIGN();							\
 	VMLINUX_SYMBOL(__dtb_start) = .;				\
@@ -490,6 +500,7 @@
 	TRACE_SYSCALLS()						\
 	MEM_DISCARD(init.rodata)					\
 	CLK_OF_TABLES()							\
+	RESERVEDMEM_OF_TABLES()						\
 	CLKSRC_OF_TABLES()						\
 	KERNEL_DTB()							\
 	IRQCHIP_OF_MATCH_TABLE()
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
new file mode 100644
index 000000000000..03a4ea37ba86
--- /dev/null
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -0,0 +1,200 @@
+/*
+ * Copyright (C) 2013, 2014 ARM Limited, All Rights Reserved.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __LINUX_IRQCHIP_ARM_GIC_V3_H
+#define __LINUX_IRQCHIP_ARM_GIC_V3_H
+
+#include <asm/sysreg.h>
+
+/*
+ * Distributor registers. We assume we're running non-secure, with ARE
+ * being set. Secure-only and non-ARE registers are not described.
+ */
+#define GICD_CTLR			0x0000
+#define GICD_TYPER			0x0004
+#define GICD_IIDR			0x0008
+#define GICD_STATUSR			0x0010
+#define GICD_SETSPI_NSR			0x0040
+#define GICD_CLRSPI_NSR			0x0048
+#define GICD_SETSPI_SR			0x0050
+#define GICD_CLRSPI_SR			0x0058
+#define GICD_SEIR			0x0068
+#define GICD_ISENABLER			0x0100
+#define GICD_ICENABLER			0x0180
+#define GICD_ISPENDR			0x0200
+#define GICD_ICPENDR			0x0280
+#define GICD_ISACTIVER			0x0300
+#define GICD_ICACTIVER			0x0380
+#define GICD_IPRIORITYR			0x0400
+#define GICD_ICFGR			0x0C00
+#define GICD_IROUTER			0x6000
+#define GICD_PIDR2			0xFFE8
+
+#define GICD_CTLR_RWP			(1U << 31)
+#define GICD_CTLR_ARE_NS		(1U << 4)
+#define GICD_CTLR_ENABLE_G1A		(1U << 1)
+#define GICD_CTLR_ENABLE_G1		(1U << 0)
+
+#define GICD_IROUTER_SPI_MODE_ONE	(0U << 31)
+#define GICD_IROUTER_SPI_MODE_ANY	(1U << 31)
+
+#define GIC_PIDR2_ARCH_MASK		0xf0
+#define GIC_PIDR2_ARCH_GICv3		0x30
+#define GIC_PIDR2_ARCH_GICv4		0x40
+
+/*
+ * Re-Distributor registers, offsets from RD_base
+ */
+#define GICR_CTLR			GICD_CTLR
+#define GICR_IIDR			0x0004
+#define GICR_TYPER			0x0008
+#define GICR_STATUSR			GICD_STATUSR
+#define GICR_WAKER			0x0014
+#define GICR_SETLPIR			0x0040
+#define GICR_CLRLPIR			0x0048
+#define GICR_SEIR			GICD_SEIR
+#define GICR_PROPBASER			0x0070
+#define GICR_PENDBASER			0x0078
+#define GICR_INVLPIR			0x00A0
+#define GICR_INVALLR			0x00B0
+#define GICR_SYNCR			0x00C0
+#define GICR_MOVLPIR			0x0100
+#define GICR_MOVALLR			0x0110
+#define GICR_PIDR2			GICD_PIDR2
+
+#define GICR_WAKER_ProcessorSleep	(1U << 1)
+#define GICR_WAKER_ChildrenAsleep	(1U << 2)
+
+/*
+ * Re-Distributor registers, offsets from SGI_base
+ */
+#define GICR_ISENABLER0			GICD_ISENABLER
+#define GICR_ICENABLER0			GICD_ICENABLER
+#define GICR_ISPENDR0			GICD_ISPENDR
+#define GICR_ICPENDR0			GICD_ICPENDR
+#define GICR_ISACTIVER0			GICD_ISACTIVER
+#define GICR_ICACTIVER0			GICD_ICACTIVER
+#define GICR_IPRIORITYR0		GICD_IPRIORITYR
+#define GICR_ICFGR0			GICD_ICFGR
+
+#define GICR_TYPER_VLPIS		(1U << 1)
+#define GICR_TYPER_LAST			(1U << 4)
+
+/*
+ * CPU interface registers
+ */
+#define ICC_CTLR_EL1_EOImode_drop_dir	(0U << 1)
+#define ICC_CTLR_EL1_EOImode_drop	(1U << 1)
+#define ICC_SRE_EL1_SRE			(1U << 0)
+
+/*
+ * Hypervisor interface registers (SRE only)
+ */
+#define ICH_LR_VIRTUAL_ID_MASK		((1UL << 32) - 1)
+
+#define ICH_LR_EOI			(1UL << 41)
+#define ICH_LR_GROUP			(1UL << 60)
+#define ICH_LR_STATE			(3UL << 62)
+#define ICH_LR_PENDING_BIT		(1UL << 62)
+#define ICH_LR_ACTIVE_BIT		(1UL << 63)
+
+#define ICH_MISR_EOI			(1 << 0)
+#define ICH_MISR_U			(1 << 1)
+
+#define ICH_HCR_EN			(1 << 0)
+#define ICH_HCR_UIE			(1 << 1)
+
+#define ICH_VMCR_CTLR_SHIFT		0
+#define ICH_VMCR_CTLR_MASK		(0x21f << ICH_VMCR_CTLR_SHIFT)
+#define ICH_VMCR_BPR1_SHIFT		18
+#define ICH_VMCR_BPR1_MASK		(7 << ICH_VMCR_BPR1_SHIFT)
+#define ICH_VMCR_BPR0_SHIFT		21
+#define ICH_VMCR_BPR0_MASK		(7 << ICH_VMCR_BPR0_SHIFT)
+#define ICH_VMCR_PMR_SHIFT		24
+#define ICH_VMCR_PMR_MASK		(0xffUL << ICH_VMCR_PMR_SHIFT)
+
+#define ICC_EOIR1_EL1			sys_reg(3, 0, 12, 12, 1)
+#define ICC_IAR1_EL1			sys_reg(3, 0, 12, 12, 0)
+#define ICC_SGI1R_EL1			sys_reg(3, 0, 12, 11, 5)
+#define ICC_PMR_EL1			sys_reg(3, 0, 4, 6, 0)
+#define ICC_CTLR_EL1			sys_reg(3, 0, 12, 12, 4)
+#define ICC_SRE_EL1			sys_reg(3, 0, 12, 12, 5)
+#define ICC_GRPEN1_EL1			sys_reg(3, 0, 12, 12, 7)
+
+#define ICC_IAR1_EL1_SPURIOUS		0x3ff
+
+#define ICC_SRE_EL2			sys_reg(3, 4, 12, 9, 5)
+
+#define ICC_SRE_EL2_SRE			(1 << 0)
+#define ICC_SRE_EL2_ENABLE		(1 << 3)
+
+/*
+ * System register definitions
+ */
+#define ICH_VSEIR_EL2			sys_reg(3, 4, 12, 9, 4)
+#define ICH_HCR_EL2			sys_reg(3, 4, 12, 11, 0)
+#define ICH_VTR_EL2			sys_reg(3, 4, 12, 11, 1)
+#define ICH_MISR_EL2			sys_reg(3, 4, 12, 11, 2)
+#define ICH_EISR_EL2			sys_reg(3, 4, 12, 11, 3)
+#define ICH_ELSR_EL2			sys_reg(3, 4, 12, 11, 5)
+#define ICH_VMCR_EL2			sys_reg(3, 4, 12, 11, 7)
+
+#define __LR0_EL2(x)			sys_reg(3, 4, 12, 12, x)
+#define __LR8_EL2(x)			sys_reg(3, 4, 12, 13, x)
+
+#define ICH_LR0_EL2			__LR0_EL2(0)
+#define ICH_LR1_EL2			__LR0_EL2(1)
+#define ICH_LR2_EL2			__LR0_EL2(2)
+#define ICH_LR3_EL2			__LR0_EL2(3)
+#define ICH_LR4_EL2			__LR0_EL2(4)
+#define ICH_LR5_EL2			__LR0_EL2(5)
+#define ICH_LR6_EL2			__LR0_EL2(6)
+#define ICH_LR7_EL2			__LR0_EL2(7)
+#define ICH_LR8_EL2			__LR8_EL2(0)
+#define ICH_LR9_EL2			__LR8_EL2(1)
+#define ICH_LR10_EL2			__LR8_EL2(2)
+#define ICH_LR11_EL2			__LR8_EL2(3)
+#define ICH_LR12_EL2			__LR8_EL2(4)
+#define ICH_LR13_EL2			__LR8_EL2(5)
+#define ICH_LR14_EL2			__LR8_EL2(6)
+#define ICH_LR15_EL2			__LR8_EL2(7)
+
+#define __AP0Rx_EL2(x)			sys_reg(3, 4, 12, 8, x)
+#define ICH_AP0R0_EL2			__AP0Rx_EL2(0)
+#define ICH_AP0R1_EL2			__AP0Rx_EL2(1)
+#define ICH_AP0R2_EL2			__AP0Rx_EL2(2)
+#define ICH_AP0R3_EL2			__AP0Rx_EL2(3)
+
+#define __AP1Rx_EL2(x)			sys_reg(3, 4, 12, 9, x)
+#define ICH_AP1R0_EL2			__AP1Rx_EL2(0)
+#define ICH_AP1R1_EL2			__AP1Rx_EL2(1)
+#define ICH_AP1R2_EL2			__AP1Rx_EL2(2)
+#define ICH_AP1R3_EL2			__AP1Rx_EL2(3)
+
+#ifndef __ASSEMBLY__
+
+#include <linux/stringify.h>
+
+static inline void gic_write_eoir(u64 irq)
+{
+	asm volatile("msr_s " __stringify(ICC_EOIR1_EL1) ", %0" : : "r" (irq));
+	isb();
+}
+
+#endif
+
+#endif
diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h
index 0ceb389dba6c..45e2d8c15bd2 100644
--- a/include/linux/irqchip/arm-gic.h
+++ b/include/linux/irqchip/arm-gic.h
@@ -21,6 +21,8 @@
 #define GIC_CPU_ACTIVEPRIO		0xd0
 #define GIC_CPU_IDENT			0xfc
 
+#define GICC_IAR_INT_ID_MASK		0x3ff
+
 #define GIC_DIST_CTRL			0x000
 #define GIC_DIST_CTR			0x004
 #define GIC_DIST_IGROUP			0x080
@@ -93,6 +95,11 @@ int gic_get_cpu_id(unsigned int cpu);
 void gic_migrate_target(unsigned int new_cpu_id);
 unsigned long gic_get_sgir_physaddr(void);
 
+extern const struct irq_domain_ops *gic_routable_irq_domain_ops;
+static inline void __init register_routable_domain_ops
+					(const struct irq_domain_ops *ops)
+{
+	gic_routable_irq_domain_ops = ops;
+}
 #endif /* __ASSEMBLY */
-
 #endif
diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h
index 2b77058a7335..5f5b83461a81 100644
--- a/include/linux/of_fdt.h
+++ b/include/linux/of_fdt.h
@@ -66,7 +66,7 @@ extern char *of_fdt_get_string(struct boot_param_header *blob, u32 offset);
 extern void *of_fdt_get_property(struct boot_param_header *blob,
 				 unsigned long node,
 				 const char *name,
-				 unsigned long *size);
+				 int *size);
 extern int of_fdt_is_compatible(struct boot_param_header *blob,
 				unsigned long node,
 				const char *compat);
@@ -81,26 +81,25 @@ extern int __initdata dt_root_size_cells;
 extern struct boot_param_header *initial_boot_params;
 
 /* For scanning the flat device-tree at boot time */
-extern char *find_flat_dt_string(u32 offset);
 extern int of_scan_flat_dt(int (*it)(unsigned long node, const char *uname,
 				     int depth, void *data),
 			   void *data);
-extern void *of_get_flat_dt_prop(unsigned long node, const char *name,
-				 unsigned long *size);
+extern const void *of_get_flat_dt_prop(unsigned long node, const char *name,
+				       int *size);
 extern int of_flat_dt_is_compatible(unsigned long node, const char *name);
 extern int of_flat_dt_match(unsigned long node, const char *const *matches);
 extern unsigned long of_get_flat_dt_root(void);
-extern int of_scan_flat_dt_by_path(const char *path,
-	int (*it)(unsigned long node, const char *name, int depth, void *data),
-	void *data);
 
 extern int early_init_dt_scan_chosen(unsigned long node, const char *uname,
 				     int depth, void *data);
 extern int early_init_dt_scan_memory(unsigned long node, const char *uname,
 				     int depth, void *data);
+extern void early_init_fdt_scan_reserved_mem(void);
 extern void early_init_dt_add_memory_arch(u64 base, u64 size);
+extern int early_init_dt_reserve_memory_arch(phys_addr_t base, phys_addr_t size,
+					     bool no_map);
 extern void * early_init_dt_alloc_memory_arch(u64 size, u64 align);
-extern u64 dt_mem_next_cell(int s, __be32 **cellp);
+extern u64 dt_mem_next_cell(int s, const __be32 **cellp);
 
 /* Early flat tree scan hooks */
 extern int early_init_dt_scan_root(unsigned long node, const char *uname,
@@ -118,6 +117,7 @@ extern void unflatten_and_copy_device_tree(void);
 extern void early_init_devtree(void *);
 extern void early_get_first_memblock_info(void *, phys_addr_t *);
 #else /* CONFIG_OF_FLATTREE */
+static inline void early_init_fdt_scan_reserved_mem(void) {}
 static inline const char *of_flat_dt_get_machine_name(void) { return NULL; }
 static inline void unflatten_device_tree(void) {}
 static inline void unflatten_and_copy_device_tree(void) {}
diff --git a/include/linux/of_reserved_mem.h b/include/linux/of_reserved_mem.h
new file mode 100644
index 000000000000..9b1fbb7f29fc
--- /dev/null
+++ b/include/linux/of_reserved_mem.h
@@ -0,0 +1,53 @@
+#ifndef __OF_RESERVED_MEM_H
+#define __OF_RESERVED_MEM_H
+
+struct device;
+struct of_phandle_args;
+struct reserved_mem_ops;
+
+struct reserved_mem {
+	const char			*name;
+	unsigned long			fdt_node;
+	const struct reserved_mem_ops	*ops;
+	phys_addr_t			base;
+	phys_addr_t			size;
+	void				*priv;
+};
+
+struct reserved_mem_ops {
+	void	(*device_init)(struct reserved_mem *rmem,
+			       struct device *dev);
+	void	(*device_release)(struct reserved_mem *rmem,
+				  struct device *dev);
+};
+
+typedef int (*reservedmem_of_init_fn)(struct reserved_mem *rmem,
+				      unsigned long node, const char *uname);
+
+#ifdef CONFIG_OF_RESERVED_MEM
+void fdt_init_reserved_mem(void);
+void fdt_reserved_mem_save_node(unsigned long node, const char *uname,
+			       phys_addr_t base, phys_addr_t size);
+
+#define RESERVEDMEM_OF_DECLARE(name, compat, init)			\
+	static const struct of_device_id __reservedmem_of_table_##name	\
+		__used __section(__reservedmem_of_table)		\
+		 = { .compatible = compat,				\
+		     .data = (init == (reservedmem_of_init_fn)NULL) ?	\
+				init : init }
+
+#else
+static inline void fdt_init_reserved_mem(void) { }
+static inline void fdt_reserved_mem_save_node(unsigned long node,
+		const char *uname, phys_addr_t base, phys_addr_t size) { }
+
+#define RESERVEDMEM_OF_DECLARE(name, compat, init)			\
+	static const struct of_device_id __reservedmem_of_table_##name	\
+		__attribute__((unused))					\
+		 = { .compatible = compat,				\
+		     .data = (init == (reservedmem_of_init_fn)NULL) ?	\
+				init : init }
+
+#endif
+
+#endif /* __OF_RESERVED_MEM_H */
diff --git a/lib/Makefile b/lib/Makefile
index 48140e3ba73f..befe5554a34f 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -147,7 +147,8 @@ obj-$(CONFIG_GENERIC_NET_UTILS) += net_utils.o
 
 obj-$(CONFIG_STMP_DEVICE) += stmp_device.o
 
-libfdt_files = fdt.o fdt_ro.o fdt_wip.o fdt_rw.o fdt_sw.o fdt_strerror.o
+libfdt_files = fdt.o fdt_ro.o fdt_wip.o fdt_rw.o fdt_sw.o fdt_strerror.o \
+	       fdt_empty_tree.o
 $(foreach file, $(libfdt_files), \
 	$(eval CFLAGS_$(file) = -I$(src)/../scripts/dtc/libfdt))
 lib-$(CONFIG_LIBFDT) += $(libfdt_files)
diff --git a/lib/fdt_empty_tree.c b/lib/fdt_empty_tree.c
new file mode 100644
index 000000000000..5d30c58150ad
--- /dev/null
+++ b/lib/fdt_empty_tree.c
@@ -0,0 +1,2 @@
+#include <linux/libfdt_env.h>
+#include "../scripts/dtc/libfdt/fdt_empty_tree.c"
diff --git a/mm/Kconfig b/mm/Kconfig
index 2888024e0b0a..4f9f965bc135 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -577,3 +577,6 @@ config PGTABLE_MAPPING
 
 	  You can check speed with zsmalloc benchmark:
 	  https://github.com/spartacus06/zsmapbench
+
+config GENERIC_EARLY_IOREMAP
+	bool
diff --git a/mm/Makefile b/mm/Makefile
index 310c90a09264..9d9c587620a3 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -61,3 +61,4 @@ obj-$(CONFIG_CLEANCACHE) += cleancache.o
 obj-$(CONFIG_MEMORY_ISOLATION) += page_isolation.o
 obj-$(CONFIG_ZBUD)	+= zbud.o
 obj-$(CONFIG_ZSMALLOC)	+= zsmalloc.o
+obj-$(CONFIG_GENERIC_EARLY_IOREMAP) += early_ioremap.o
diff --git a/mm/early_ioremap.c b/mm/early_ioremap.c
new file mode 100644
index 000000000000..e10ccd299d66
--- /dev/null
+++ b/mm/early_ioremap.c
@@ -0,0 +1,245 @@
+/*
+ * Provide common bits of early_ioremap() support for architectures needing
+ * temporary mappings during boot before ioremap() is available.
+ *
+ * This is mostly a direct copy of the x86 early_ioremap implementation.
+ *
+ * (C) Copyright 1995 1996, 2014 Linus Torvalds
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
+#include <asm/fixmap.h>
+
+#ifdef CONFIG_MMU
+static int early_ioremap_debug __initdata;
+
+static int __init early_ioremap_debug_setup(char *str)
+{
+	early_ioremap_debug = 1;
+
+	return 0;
+}
+early_param("early_ioremap_debug", early_ioremap_debug_setup);
+
+static int after_paging_init __initdata;
+
+void __init __weak early_ioremap_shutdown(void)
+{
+}
+
+void __init early_ioremap_reset(void)
+{
+	early_ioremap_shutdown();
+	after_paging_init = 1;
+}
+
+/*
+ * Generally, ioremap() is available after paging_init() has been called.
+ * Architectures wanting to allow early_ioremap after paging_init() can
+ * define __late_set_fixmap and __late_clear_fixmap to do the right thing.
+ */
+#ifndef __late_set_fixmap
+static inline void __init __late_set_fixmap(enum fixed_addresses idx,
+					    phys_addr_t phys, pgprot_t prot)
+{
+	BUG();
+}
+#endif
+
+#ifndef __late_clear_fixmap
+static inline void __init __late_clear_fixmap(enum fixed_addresses idx)
+{
+	BUG();
+}
+#endif
+
+static void __iomem *prev_map[FIX_BTMAPS_SLOTS] __initdata;
+static unsigned long prev_size[FIX_BTMAPS_SLOTS] __initdata;
+static unsigned long slot_virt[FIX_BTMAPS_SLOTS] __initdata;
+
+void __init early_ioremap_setup(void)
+{
+	int i;
+
+	for (i = 0; i < FIX_BTMAPS_SLOTS; i++)
+		if (WARN_ON(prev_map[i]))
+			break;
+
+	for (i = 0; i < FIX_BTMAPS_SLOTS; i++)
+		slot_virt[i] = __fix_to_virt(FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*i);
+}
+
+static int __init check_early_ioremap_leak(void)
+{
+	int count = 0;
+	int i;
+
+	for (i = 0; i < FIX_BTMAPS_SLOTS; i++)
+		if (prev_map[i])
+			count++;
+
+	if (WARN(count, KERN_WARNING
+		 "Debug warning: early ioremap leak of %d areas detected.\n"
+		 "please boot with early_ioremap_debug and report the dmesg.\n",
+		 count))
+		return 1;
+	return 0;
+}
+late_initcall(check_early_ioremap_leak);
+
+static void __init __iomem *
+__early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot)
+{
+	unsigned long offset;
+	resource_size_t last_addr;
+	unsigned int nrpages;
+	enum fixed_addresses idx;
+	int i, slot;
+
+	WARN_ON(system_state != SYSTEM_BOOTING);
+
+	slot = -1;
+	for (i = 0; i < FIX_BTMAPS_SLOTS; i++) {
+		if (!prev_map[i]) {
+			slot = i;
+			break;
+		}
+	}
+
+	if (WARN(slot < 0, "%s(%08llx, %08lx) not found slot\n",
+		 __func__, (u64)phys_addr, size))
+		return NULL;
+
+	/* Don't allow wraparound or zero size */
+	last_addr = phys_addr + size - 1;
+	if (WARN_ON(!size || last_addr < phys_addr))
+		return NULL;
+
+	prev_size[slot] = size;
+	/*
+	 * Mappings have to be page-aligned
+	 */
+	offset = phys_addr & ~PAGE_MASK;
+	phys_addr &= PAGE_MASK;
+	size = PAGE_ALIGN(last_addr + 1) - phys_addr;
+
+	/*
+	 * Mappings have to fit in the FIX_BTMAP area.
+	 */
+	nrpages = size >> PAGE_SHIFT;
+	if (WARN_ON(nrpages > NR_FIX_BTMAPS))
+		return NULL;
+
+	/*
+	 * Ok, go for it..
+	 */
+	idx = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot;
+	while (nrpages > 0) {
+		if (after_paging_init)
+			__late_set_fixmap(idx, phys_addr, prot);
+		else
+			__early_set_fixmap(idx, phys_addr, prot);
+		phys_addr += PAGE_SIZE;
+		--idx;
+		--nrpages;
+	}
+	WARN(early_ioremap_debug, "%s(%08llx, %08lx) [%d] => %08lx + %08lx\n",
+	     __func__, (u64)phys_addr, size, slot, offset, slot_virt[slot]);
+
+	prev_map[slot] = (void __iomem *)(offset + slot_virt[slot]);
+	return prev_map[slot];
+}
+
+void __init early_iounmap(void __iomem *addr, unsigned long size)
+{
+	unsigned long virt_addr;
+	unsigned long offset;
+	unsigned int nrpages;
+	enum fixed_addresses idx;
+	int i, slot;
+
+	slot = -1;
+	for (i = 0; i < FIX_BTMAPS_SLOTS; i++) {
+		if (prev_map[i] == addr) {
+			slot = i;
+			break;
+		}
+	}
+
+	if (WARN(slot < 0, "early_iounmap(%p, %08lx) not found slot\n",
+		 addr, size))
+		return;
+
+	if (WARN(prev_size[slot] != size,
+		 "early_iounmap(%p, %08lx) [%d] size not consistent %08lx\n",
+		 addr, size, slot, prev_size[slot]))
+		return;
+
+	WARN(early_ioremap_debug, "early_iounmap(%p, %08lx) [%d]\n",
+	     addr, size, slot);
+
+	virt_addr = (unsigned long)addr;
+	if (WARN_ON(virt_addr < fix_to_virt(FIX_BTMAP_BEGIN)))
+		return;
+
+	offset = virt_addr & ~PAGE_MASK;
+	nrpages = PAGE_ALIGN(offset + size) >> PAGE_SHIFT;
+
+	idx = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot;
+	while (nrpages > 0) {
+		if (after_paging_init)
+			__late_clear_fixmap(idx);
+		else
+			__early_set_fixmap(idx, 0, FIXMAP_PAGE_CLEAR);
+		--idx;
+		--nrpages;
+	}
+	prev_map[slot] = NULL;
+}
+
+/* Remap an IO device */
+void __init __iomem *
+early_ioremap(resource_size_t phys_addr, unsigned long size)
+{
+	return __early_ioremap(phys_addr, size, FIXMAP_PAGE_IO);
+}
+
+/* Remap memory */
+void __init *
+early_memremap(resource_size_t phys_addr, unsigned long size)
+{
+	return (__force void *)__early_ioremap(phys_addr, size,
+					       FIXMAP_PAGE_NORMAL);
+}
+#else /* CONFIG_MMU */
+
+void __init __iomem *
+early_ioremap(resource_size_t phys_addr, unsigned long size)
+{
+	return (__force void __iomem *)phys_addr;
+}
+
+/* Remap memory */
+void __init *
+early_memremap(resource_size_t phys_addr, unsigned long size)
+{
+	return (void *)phys_addr;
+}
+
+void __init early_iounmap(void __iomem *addr, unsigned long size)
+{
+}
+
+#endif /* CONFIG_MMU */
+
+
+void __init early_memunmap(void *addr, unsigned long size)
+{
+	early_iounmap((__force void __iomem *)addr, size);
+}