Merge remote-tracking branch 'lsk/v3.10/topic/arm64-misc' into linux-linaro-lsk

Conflicts:
	Documentation/arm64/tagged-pointers.txt
	arch/arm64/Kconfig
	arch/arm64/boot/dts/Makefile
	arch/arm64/include/asm/arch_timer.h
	arch/arm64/include/asm/elf.h
	arch/arm64/include/asm/spinlock.h
	arch/arm64/kernel/smp.c

58 files changed, 545 insertions, 248 deletions

diff --git a/Documentation/arm64/booting.txt b/Documentation/arm64/booting.txt
index 9c4d388daddc..5273c4d60e65 100644
--- a/Documentation/arm64/booting.txt
+++ b/Documentation/arm64/booting.txt
@@ -68,13 +68,23 @@ Image target is available instead.
 
 Requirement: MANDATORY
 
-The decompressed kernel image contains a 32-byte header as follows:
+The decompressed kernel image contains a 64-byte header as follows:
 
-  u32 magic	= 0x14000008;	/* branch to stext, little-endian */
-  u32 res0	= 0;		/* reserved */
+  u32 code0;			/* Executable code */
+  u32 code1;			/* Executable code */
   u64 text_offset;		/* Image load offset */
+  u64 res0	= 0;		/* reserved */
   u64 res1	= 0;		/* reserved */
   u64 res2	= 0;		/* reserved */
+  u64 res3	= 0;		/* reserved */
+  u64 res4	= 0;		/* reserved */
+  u32 magic	= 0x644d5241;	/* Magic number, little endian, "ARM\x64" */
+  u32 res5 = 0;      		/* reserved */
+
+
+Header notes:
+
+- code0/code1 are responsible for branching to stext.
 
 The image must be placed at the specified offset (currently 0x80000)
 from the start of the system RAM and called there. The start of the
diff --git a/Documentation/arm64/memory.txt b/Documentation/arm64/memory.txt
index 5f583af0a6e1..a776d7a7c3cc 100644
--- a/Documentation/arm64/memory.txt
+++ b/Documentation/arm64/memory.txt
@@ -21,7 +21,7 @@ The swapper_pgd_dir address is written to TTBR1 and never written to
 TTBR0.
 
 
-AArch64 Linux memory layout:
+AArch64 Linux memory layout with 4KB pages:
 
 Start			End			Size		Use
 -----------------------------------------------------------------------
@@ -46,6 +46,31 @@ ffffffbffc000000	ffffffbfffffffff	  64MB		modules
 ffffffc000000000	ffffffffffffffff	 256GB		kernel logical memory map
 
 
+AArch64 Linux memory layout with 64KB pages:
+
+Start			End			Size		Use
+-----------------------------------------------------------------------
+0000000000000000	000003ffffffffff	   4TB		user
+
+fffffc0000000000	fffffdfbfffeffff	  ~2TB		vmalloc
+
+fffffdfbffff0000	fffffdfbffffffff	  64KB		[guard page]
+
+fffffdfc00000000	fffffdfdffffffff	   8GB		vmemmap
+
+fffffdfe00000000	fffffdfffbbfffff	  ~8GB		[guard, future vmmemap]
+
+fffffdfffbc00000	fffffdfffbdfffff	   2MB		earlyprintk device
+
+fffffdfffbe00000	fffffdfffbe0ffff	  64KB		PCI I/O space
+
+fffffdfffbe10000	fffffdfffbffffff	  ~2MB		[guard]
+
+fffffdfffc000000	fffffdffffffffff	  64MB		modules
+
+fffffe0000000000	ffffffffffffffff	   2TB		kernel logical memory map
+
+
 Translation table lookup with 4KB pages:
 
 +--------+--------+--------+--------+--------+--------+--------+--------+
diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c
index 4a177365b2c4..7991e08d606b 100644
--- a/arch/arc/mm/init.c
+++ b/arch/arc/mm/init.c
@@ -157,9 +157,8 @@ void __init free_initrd_mem(unsigned long start, unsigned long end)
 #endif
 
 #ifdef CONFIG_OF_FLATTREE
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
-					    unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
 {
-	pr_err("%s(%lx, %lx)\n", __func__, start, end);
+	pr_err("%s(%llx, %llx)\n", __func__, start, end);
 }
 #endif /* CONFIG_OF_FLATTREE */
diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h
index 56211f2084ef..f4b46d39b9cf 100644
--- a/arch/arm/include/asm/elf.h
+++ b/arch/arm/include/asm/elf.h
@@ -19,8 +19,6 @@ typedef elf_greg_t elf_gregset_t[ELF_NGREG];
 
 typedef struct user_fp elf_fpregset_t;
 
-#define EM_ARM	40
-
 #define EF_ARM_EABI_MASK	0xff000000
 #define EF_ARM_EABI_UNKNOWN	0x00000000
 #define EF_ARM_EABI_VER1	0x01000000
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 0ecc43fd6229..c12ae661d4ab 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -76,7 +76,7 @@ static int __init parse_tag_initrd2(const struct tag *tag)
 __tagtable(ATAG_INITRD2, parse_tag_initrd2);
 
 #ifdef CONFIG_OF_FLATTREE
-void __init early_init_dt_setup_initrd_arch(unsigned long start, unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
 {
 	phys_initrd_start = start;
 	phys_initrd_size = end - start;
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 5ee96e17c63c..73366a635c3b 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 BUILDTIME_EXTABLE_SORT
 	select CLONE_BACKWARDS
 	select COMMON_CLK
 	select CPU_PM if (SUSPEND || CPU_IDLE)
@@ -66,10 +67,6 @@ config LOCKDEP_SUPPORT
 config TRACE_IRQFLAGS_SUPPORT
 	def_bool y
 
-config GENERIC_LOCKBREAK
-	def_bool y
-	depends on SMP && PREEMPT
-
 config RWSEM_GENERIC_SPINLOCK
 	def_bool y
 
@@ -116,6 +113,11 @@ config ARCH_VEXPRESS
 	  This enables support for the ARMv8 software model (Versatile
 	  Express).
 
+config ARCH_XGENE
+	bool "AppliedMicro X-Gene SOC Family"
+	help
+	  This enables support for AppliedMicro X-Gene SOC Family
+
 endmenu
 
 menu "Bus support"
@@ -270,7 +272,8 @@ config NR_CPUS
 	int "Maximum number of CPUs (2-32)"
 	range 2 32
 	depends on SMP
-	default "4"
+	# These have to remain sorted largest to smallest
+	default "8"
 
 config HOTPLUG_CPU
 	bool "Support for hot-pluggable CPUs"
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 3a926eb93c95..a254d2c2c0dc 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -66,6 +66,10 @@ zinstall install: vmlinux
 dtbs: scripts
 	$(Q)$(MAKE) $(build)=$(boot)/dts dtbs
 
+PHONY += vdso_install
+vdso_install:
+	$(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso $@
+
 # We use MRPROPER_FILES and CLEAN_FILES now
 archclean:
 	$(Q)$(MAKE) $(clean)=$(boot)
diff --git a/arch/arm64/boot/dts/Makefile b/arch/arm64/boot/dts/Makefile
index 675be339c648..ef388176116d 100644
--- a/arch/arm64/boot/dts/Makefile
+++ b/arch/arm64/boot/dts/Makefile
@@ -1,6 +1,7 @@
 dtb-$(CONFIG_ARCH_VEXPRESS) += rtsm_ve-aemv8a.dtb foundation-v8.dtb \
 				fvp-base-gicv2-psci.dtb
 dtb-$(CONFIG_ARCH_VEXPRESS) += juno.dtb
+dtb-$(CONFIG_ARCH_XGENE) += apm-mustang.dtb
 
 targets += dtbs
 targets += $(dtb-y)
diff --git a/arch/arm64/boot/dts/apm-mustang.dts b/arch/arm64/boot/dts/apm-mustang.dts
new file mode 100644
index 000000000000..1247ca1200b1
--- /dev/null
+++ b/arch/arm64/boot/dts/apm-mustang.dts
@@ -0,0 +1,26 @@
+/*
+ * dts file for AppliedMicro (APM) Mustang Board
+ *
+ * Copyright (C) 2013, Applied Micro Circuits Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ */
+
+/dts-v1/;
+
+/include/ "apm-storm.dtsi"
+
+/ {
+	model = "APM X-Gene Mustang board";
+	compatible = "apm,mustang", "apm,xgene-storm";
+
+	chosen { };
+
+	memory {
+		device_type = "memory";
+		reg = < 0x1 0x00000000 0x0 0x80000000 >; /* Updated by bootloader */
+	};
+};
diff --git a/arch/arm64/boot/dts/apm-storm.dtsi b/arch/arm64/boot/dts/apm-storm.dtsi
new file mode 100644
index 000000000000..d37d7369e260
--- /dev/null
+++ b/arch/arm64/boot/dts/apm-storm.dtsi
@@ -0,0 +1,191 @@
+/*
+ * dts file for AppliedMicro (APM) X-Gene Storm SOC
+ *
+ * Copyright (C) 2013, Applied Micro Circuits Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ */
+
+/ {
+	compatible = "apm,xgene-storm";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	cpus {
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		cpu@000 {
+			device_type = "cpu";
+			compatible = "apm,potenza", "arm,armv8";
+			reg = <0x0 0x000>;
+			enable-method = "spin-table";
+			cpu-release-addr = <0x1 0x0000fff8>;
+		};
+		cpu@001 {
+			device_type = "cpu";
+			compatible = "apm,potenza", "arm,armv8";
+			reg = <0x0 0x001>;
+			enable-method = "spin-table";
+			cpu-release-addr = <0x1 0x0000fff8>;
+		};
+		cpu@100 {
+			device_type = "cpu";
+			compatible = "apm,potenza", "arm,armv8";
+			reg = <0x0 0x100>;
+			enable-method = "spin-table";
+			cpu-release-addr = <0x1 0x0000fff8>;
+		};
+		cpu@101 {
+			device_type = "cpu";
+			compatible = "apm,potenza", "arm,armv8";
+			reg = <0x0 0x101>;
+			enable-method = "spin-table";
+			cpu-release-addr = <0x1 0x0000fff8>;
+		};
+		cpu@200 {
+			device_type = "cpu";
+			compatible = "apm,potenza", "arm,armv8";
+			reg = <0x0 0x200>;
+			enable-method = "spin-table";
+			cpu-release-addr = <0x1 0x0000fff8>;
+		};
+		cpu@201 {
+			device_type = "cpu";
+			compatible = "apm,potenza", "arm,armv8";
+			reg = <0x0 0x201>;
+			enable-method = "spin-table";
+			cpu-release-addr = <0x1 0x0000fff8>;
+		};
+		cpu@300 {
+			device_type = "cpu";
+			compatible = "apm,potenza", "arm,armv8";
+			reg = <0x0 0x300>;
+			enable-method = "spin-table";
+			cpu-release-addr = <0x1 0x0000fff8>;
+		};
+		cpu@301 {
+			device_type = "cpu";
+			compatible = "apm,potenza", "arm,armv8";
+			reg = <0x0 0x301>;
+			enable-method = "spin-table";
+			cpu-release-addr = <0x1 0x0000fff8>;
+		};
+	};
+
+	gic: interrupt-controller@78010000 {
+		compatible = "arm,cortex-a15-gic";
+		#interrupt-cells = <3>;
+		interrupt-controller;
+		reg = <0x0 0x78010000 0x0 0x1000>,	/* GIC Dist */
+		      <0x0 0x78020000 0x0 0x1000>,	/* GIC CPU */
+		      <0x0 0x78040000 0x0 0x2000>,	/* GIC VCPU Control */
+		      <0x0 0x78060000 0x0 0x2000>;	/* GIC VCPU */
+		interrupts = <1 9 0xf04>;	/* GIC Maintenence IRQ */
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupts = <1 0 0xff01>,	/* Secure Phys IRQ */
+			     <1 13 0xff01>,	/* Non-secure Phys IRQ */
+			     <1 14 0xff01>,	/* Virt IRQ */
+			     <1 15 0xff01>;	/* Hyp IRQ */
+		clock-frequency = <50000000>;
+	};
+
+	soc {
+		compatible = "simple-bus";
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		clocks {
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
+			refclk: refclk {
+				compatible = "fixed-clock";
+				#clock-cells = <1>;
+				clock-frequency = <100000000>;
+				clock-output-names = "refclk";
+			};
+
+			pcppll: pcppll@17000100 {
+				compatible = "apm,xgene-pcppll-clock";
+				#clock-cells = <1>;
+				clocks = <&refclk 0>;
+				clock-names = "pcppll";
+				reg = <0x0 0x17000100 0x0 0x1000>;
+				clock-output-names = "pcppll";
+				type = <0>;
+			};
+
+			socpll: socpll@17000120 {
+				compatible = "apm,xgene-socpll-clock";
+				#clock-cells = <1>;
+				clocks = <&refclk 0>;
+				clock-names = "socpll";
+				reg = <0x0 0x17000120 0x0 0x1000>;
+				clock-output-names = "socpll";
+				type = <1>;
+			};
+
+			socplldiv2: socplldiv2  {
+				compatible = "fixed-factor-clock";
+				#clock-cells = <1>;
+				clocks = <&socpll 0>;
+				clock-names = "socplldiv2";
+				clock-mult = <1>;
+				clock-div = <2>;
+				clock-output-names = "socplldiv2";
+			};
+
+			qmlclk: qmlclk {
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&socplldiv2 0>;
+				clock-names = "qmlclk";
+				reg = <0x0 0x1703C000 0x0 0x1000>;
+				reg-names = "csr-reg";
+				clock-output-names = "qmlclk";
+			};
+
+			ethclk: ethclk {
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&socplldiv2 0>;
+				clock-names = "ethclk";
+				reg = <0x0 0x17000000 0x0 0x1000>;
+				reg-names = "div-reg";
+				divider-offset = <0x238>;
+				divider-width = <0x9>;
+				divider-shift = <0x0>;
+				clock-output-names = "ethclk";
+			};
+
+			eth8clk: eth8clk {
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&ethclk 0>;
+				clock-names = "eth8clk";
+				reg = <0x0 0x1702C000 0x0 0x1000>;
+				reg-names = "csr-reg";
+				clock-output-names = "eth8clk";
+			};
+		};
+
+		serial0: serial@1c020000 {
+			device_type = "serial";
+			compatible = "ns16550";
+			reg = <0 0x1c020000 0x0 0x1000>;
+			reg-shift = <2>;
+			clock-frequency = <10000000>; /* Updated by bootloader */
+			interrupt-parent = <&gic>;
+			interrupts = <0x0 0x4c 0x4>;
+		};
+	};
+};
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 778a251ab6d5..1c83ade5f405 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -24,6 +24,7 @@ CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 CONFIG_ARCH_VEXPRESS=y
+CONFIG_ARCH_XGENE=y
 CONFIG_SMP=y
 CONFIG_PREEMPT_VOLUNTARY=y
 CONFIG_CMDLINE="console=ttyAMA0"
@@ -54,6 +55,9 @@ CONFIG_INPUT_EVDEV=y
 # CONFIG_SERIO_I8042 is not set
 # CONFIG_SERIO_SERPORT is not set
 CONFIG_LEGACY_PTY_COUNT=16
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_OF_PLATFORM=y
 CONFIG_SERIAL_AMBA_PL011=y
 CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
 # CONFIG_HW_RANDOM is not set
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index d6ac12e11867..4c60e64a801c 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -131,9 +131,6 @@ static inline void __flush_icache_all(void)
 #define flush_dcache_mmap_unlock(mapping) \
 	spin_unlock_irq(&(mapping)->tree_lock)
 
-#define flush_icache_user_range(vma,page,addr,len) \
-	flush_dcache_page(page)
-
 /*
  * We don't appear to need to do anything here.  In fact, if we did, we'd
  * duplicate cache flushing elsewhere performed by flush_dcache_page().
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index 68d7c932a9c3..c558da59989e 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -179,4 +179,6 @@ static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
 #define cmpxchg64(ptr,o,n)		cmpxchg((ptr),(o),(n))
 #define cmpxchg64_local(ptr,o,n)	cmpxchg_local((ptr),(o),(n))
 
+#define cmpxchg64_relaxed(ptr,o,n)	cmpxchg_local((ptr),(o),(n))
+
 #endif	/* __ASM_CMPXCHG_H */
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index a8053d89512f..e371936b8ab2 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -47,11 +47,14 @@
 })
 
 #define ARM_CPU_IMP_ARM		0x41
+#define ARM_CPU_IMP_APM		0x50
 
 #define ARM_CPU_PART_AEM_V8	0xD0F0
 #define ARM_CPU_PART_FOUNDATION	0xD000
 #define ARM_CPU_PART_CORTEX_A57	0xD070
 
+#define APM_CPU_PART_POTENZA	0x0000
+
 #ifndef __ASSEMBLY__
 
 /*
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
index 7eaa0b302493..a2232d07be9d 100644
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -83,6 +83,8 @@ static inline int reinstall_suspended_bps(struct pt_regs *regs)
 }
 #endif
 
+int aarch32_break_handler(struct pt_regs *regs);
+
 #endif	/* __ASSEMBLY */
 #endif	/* __KERNEL__ */
 #endif	/* __ASM_DEBUG_MONITORS_H */
diff --git a/arch/arm64/include/asm/device.h b/arch/arm64/include/asm/device.h
index 0d8453c755a8..cf98b362094b 100644
--- a/arch/arm64/include/asm/device.h
+++ b/arch/arm64/include/asm/device.h
@@ -18,6 +18,9 @@
 
 struct dev_archdata {
 	struct dma_map_ops *dma_ops;
+#ifdef CONFIG_IOMMU_API
+	void *iommu;			/* private IOMMU data */
+#endif
 };
 
 struct pdev_archdata {
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index 212b0b615b4a..01d3aab64b79 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -33,8 +33,6 @@ typedef unsigned long elf_greg_t;
 typedef elf_greg_t elf_gregset_t[ELF_NGREG];
 typedef struct user_fpsimd_state elf_fpregset_t;
 
-#define EM_AARCH64		183
-
 /*
  * AArch64 static relocation types.
  */
@@ -164,7 +162,6 @@ extern unsigned long arch_randomize_brk(struct mm_struct *mm);
 #define arch_randomize_brk arch_randomize_brk
 
 #ifdef CONFIG_COMPAT
-#define EM_ARM				40
 
 #ifdef __AARCH64EB__
 #define COMPAT_ELF_PLATFORM		("v8b")
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index 3a48433dfb57..6cddbb0c9f54 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -44,6 +44,6 @@
 extern unsigned int compat_elf_hwcap;
 #endif
 
-extern unsigned int elf_hwcap;
+extern unsigned long elf_hwcap;
 #endif
 #endif
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 381f556b664e..9abb57d743b9 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -33,18 +33,23 @@
 #define UL(x) _AC(x, UL)
 
 /*
- * PAGE_OFFSET - the virtual address of the start of the kernel image.
+ * PAGE_OFFSET - the virtual address of the start of the kernel image (top
+ *		 (VA_BITS - 1))
  * VA_BITS - the maximum number of bits for virtual addresses.
  * TASK_SIZE - the maximum size of a user space task.
  * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area.
  * The module space lives between the addresses given by TASK_SIZE
  * and PAGE_OFFSET - it must be within 128MB of the kernel text.
  */
-#define PAGE_OFFSET		UL(0xffffffc000000000)
+#ifdef CONFIG_ARM64_64K_PAGES
+#define VA_BITS			(42)
+#else
+#define VA_BITS			(39)
+#endif
+#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 VA_BITS			(39)
 #define TASK_SIZE_64		(UL(1) << VA_BITS)
 
 #ifdef CONFIG_COMPAT
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index e2bc385adb6b..a9eee33dfa62 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -151,12 +151,6 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
 {
 	unsigned int cpu = smp_processor_id();
 
-#ifdef CONFIG_SMP
-	/* check for possible thread migration */
-	if (!cpumask_empty(mm_cpumask(next)) &&
-	    !cpumask_test_cpu(cpu, mm_cpumask(next)))
-		__flush_icache_all();
-#endif
 	if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next)
 		check_and_switch_context(next, tsk);
 }
diff --git a/arch/arm64/include/asm/pgtable-2level-hwdef.h b/arch/arm64/include/asm/pgtable-2level-hwdef.h
index 0a8ed3f94e93..2593b490c56a 100644
--- a/arch/arm64/include/asm/pgtable-2level-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-2level-hwdef.h
@@ -21,10 +21,10 @@
  * 8192 entries of 8 bytes each, occupying a 64KB page. Levels 0 and 1 are not
  * used. The 2nd level table (PGD for Linux) can cover a range of 4TB, each
  * entry representing 512MB. The user and kernel address spaces are limited to
- * 512GB and therefore we only use 1024 entries in the PGD.
+ * 4TB in the 64KB page configuration.
  */
 #define PTRS_PER_PTE		8192
-#define PTRS_PER_PGD		1024
+#define PTRS_PER_PGD		8192
 
 /*
  * PGDIR_SHIFT determines the size a top-level page table entry can map.
diff --git a/arch/arm64/include/asm/pgtable-2level-types.h b/arch/arm64/include/asm/pgtable-2level-types.h
index 3c3ca7d361e4..5f101e63dfc1 100644
--- a/arch/arm64/include/asm/pgtable-2level-types.h
+++ b/arch/arm64/include/asm/pgtable-2level-types.h
@@ -16,6 +16,8 @@
 #ifndef __ASM_PGTABLE_2LEVEL_TYPES_H
 #define __ASM_PGTABLE_2LEVEL_TYPES_H
 
+#include <asm/types.h>
+
 typedef u64 pteval_t;
 typedef u64 pgdval_t;
 typedef pgdval_t pmdval_t;
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index b8940733ee30..608ec24f2f52 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -34,7 +34,7 @@
 /*
  * VMALLOC and SPARSEMEM_VMEMMAP ranges.
  */
-#define VMALLOC_START		UL(0xffffff8000000000)
+#define VMALLOC_START		(UL(0xffffffffffffffff) << VA_BITS)
 #define VMALLOC_END		(PAGE_OFFSET - UL(0x400000000) - SZ_64K)
 
 #define vmemmap			((struct page *)(VMALLOC_END + SZ_64K))
@@ -120,7 +120,7 @@ extern struct page *empty_zero_page;
 #define pte_none(pte)		(!pte_val(pte))
 #define pte_clear(mm,addr,ptep)	set_pte(ptep, __pte(0))
 #define pte_page(pte)		(pfn_to_page(pte_pfn(pte)))
-#define pte_offset_kernel(dir,addr)	(pmd_page_vaddr(*(dir)) + __pte_index(addr))
+#define pte_offset_kernel(dir,addr)	(pmd_page_vaddr(*(dir)) + pte_index(addr))
 
 #define pte_offset_map(dir,addr)	pte_offset_kernel((dir), (addr))
 #define pte_offset_map_nested(dir,addr)	pte_offset_kernel((dir), (addr))
@@ -361,7 +361,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 #endif
 
 /* Find an entry in the third-level page table.. */
-#define __pte_index(addr)	(((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+#define pte_index(addr)		(((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 491bea413fb1..0e7fa4963735 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -172,7 +172,5 @@ extern unsigned long profile_pc(struct pt_regs *regs);
 #define profile_pc(regs) instruction_pointer(regs)
 #endif
 
-extern int aarch32_break_trap(struct pt_regs *regs);
-
 #endif /* __ASSEMBLY__ */
 #endif
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index 0defa0728a9b..3d5cf064d7a1 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -22,17 +22,10 @@
 /*
  * Spinlock implementation.
  *
- * The old value is read exclusively and the new one, if unlocked, is written
- * exclusively. In case of failure, the loop is restarted.
- *
  * The memory barriers are implicit with the load-acquire and store-release
  * instructions.
- *
- * Unlocked value: 0
- * Locked value: 1
  */
 
-#define arch_spin_is_locked(x)		((x)->lock != 0)
 #define arch_spin_unlock_wait(lock) \
 	do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
 
@@ -41,32 +34,51 @@
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
 	unsigned int tmp;
+	arch_spinlock_t lockval, newval;
 
 	asm volatile(
-	"	sevl\n"
-	"1:	wfe\n"
-	"2:	ldaxr	%w0, %1\n"
-	"	cbnz	%w0, 1b\n"
-	"	stxr	%w0, %w2, %1\n"
-	"	cbnz	%w0, 2b\n"
-	: "=&r" (tmp), "+Q" (lock->lock)
-	: "r" (1)
-	: "cc", "memory");
+	/* Atomically increment the next ticket. */
+"	prfm	pstl1strm, %3\n"
+"1:	ldaxr	%w0, %3\n"
+"	add	%w1, %w0, %w5\n"
+"	stxr	%w2, %w1, %3\n"
+"	cbnz	%w2, 1b\n"
+	/* Did we get the lock? */
+"	eor	%w1, %w0, %w0, ror #16\n"
+"	cbz	%w1, 3f\n"
+	/*
+	 * No: spin on the owner. Send a local event to avoid missing an
+	 * unlock before the exclusive load.
+	 */
+"	sevl\n"
+"2:	wfe\n"
+"	ldaxrh	%w2, %4\n"
+"	eor	%w1, %w2, %w0, lsr #16\n"
+"	cbnz	%w1, 2b\n"
+	/* We got the lock. Critical section starts here. */
+"3:"
+	: "=&r" (lockval), "=&r" (newval), "=&r" (tmp), "+Q" (*lock)
+	: "Q" (lock->owner), "I" (1 << TICKET_SHIFT)
+	: "memory");
 }
 
 static inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
 	unsigned int tmp;
+	arch_spinlock_t lockval;
 
 	asm volatile(
-	"2:	ldaxr	%w0, %1\n"
-	"	cbnz	%w0, 1f\n"
-	"	stxr	%w0, %w2, %1\n"
-	"	cbnz	%w0, 2b\n"
-	"1:\n"
-	: "=&r" (tmp), "+Q" (lock->lock)
-	: "r" (1)
-	: "cc", "memory");
+"	prfm	pstl1strm, %2\n"
+"1:	ldaxr	%w0, %2\n"
+"	eor	%w1, %w0, %w0, ror #16\n"
+"	cbnz	%w1, 2f\n"
+"	add	%w0, %w0, %3\n"
+"	stxr	%w1, %w0, %2\n"
+"	cbnz	%w1, 1b\n"
+"2:"
+	: "=&r" (lockval), "=&r" (tmp), "+Q" (*lock)
+	: "I" (1 << TICKET_SHIFT)
+	: "memory");
 
 	return !tmp;
 }
@@ -74,9 +86,28 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
 	asm volatile(
-	"	stlr	%w1, %0\n"
-	: "=Q" (lock->lock) : "r" (0) : "memory");
+"	stlrh	%w1, %0\n"
+	: "=Q" (lock->owner)
+	: "r" (lock->owner + 1)
+	: "memory");
+}
+
+static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
+{
+	return lock.owner == lock.next;
+}
+
+static inline int arch_spin_is_locked(arch_spinlock_t *lock)
+{
+	return !arch_spin_value_unlocked(ACCESS_ONCE(*lock));
+}
+
+static inline int arch_spin_is_contended(arch_spinlock_t *lock)
+{
+	arch_spinlock_t lockval = ACCESS_ONCE(*lock);
+	return (lockval.next - lockval.owner) > 1;
 }
+#define arch_spin_is_contended	arch_spin_is_contended
 
 /*
  * Write lock implementation.
diff --git a/arch/arm64/include/asm/spinlock_types.h b/arch/arm64/include/asm/spinlock_types.h
index 9a494346efed..87692750ed94 100644
--- a/arch/arm64/include/asm/spinlock_types.h
+++ b/arch/arm64/include/asm/spinlock_types.h
@@ -20,14 +20,14 @@
 # error "please don't include this file directly"
 #endif
 
-/* We only require natural alignment for exclusive accesses. */
-#define __lock_aligned
+#define TICKET_SHIFT	16
 
 typedef struct {
-	volatile unsigned int lock;
-} arch_spinlock_t;
+	u16 owner;
+	u16 next;
+} __aligned(4) arch_spinlock_t;
 
-#define __ARCH_SPIN_LOCK_UNLOCKED	{ 0 }
+#define __ARCH_SPIN_LOCK_UNLOCKED	{ 0 , 0 }
 
 typedef struct {
 	volatile unsigned int lock;
diff --git a/arch/arm64/include/asm/timex.h b/arch/arm64/include/asm/timex.h
index b24a31a7e2c9..81a076eb37fa 100644
--- a/arch/arm64/include/asm/timex.h
+++ b/arch/arm64/include/asm/timex.h
@@ -16,14 +16,14 @@
 #ifndef __ASM_TIMEX_H
 #define __ASM_TIMEX_H
 
+#include <asm/arch_timer.h>
+
 /*
  * Use the current timer as a cycle counter since this is what we use for
  * the delay loop.
  */
-#define get_cycles()	({ cycles_t c; read_current_timer(&c); c; })
+#define get_cycles()	arch_counter_get_cntvct()
 
 #include <asm-generic/timex.h>
 
-#define ARCH_HAS_READ_CURRENT_TIMER
-
 #endif
diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c
index 41b4f626d554..e7ee770c0697 100644
--- a/arch/arm64/kernel/arm64ksyms.c
+++ b/arch/arm64/kernel/arm64ksyms.c
@@ -39,6 +39,7 @@ EXPORT_SYMBOL(clear_page);
 EXPORT_SYMBOL(__copy_from_user);
 EXPORT_SYMBOL(__copy_to_user);
 EXPORT_SYMBOL(__clear_user);
+EXPORT_SYMBOL(__copy_in_user);
 
 	/* physical memory */
 EXPORT_SYMBOL(memstart_addr);
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index f4726dc054b3..08018e3df580 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -24,6 +24,7 @@
 #include <linux/init.h>
 #include <linux/ptrace.h>
 #include <linux/stat.h>
+#include <linux/uaccess.h>
 
 #include <asm/debug-monitors.h>
 #include <asm/local.h>
@@ -226,13 +227,74 @@ static int single_step_handler(unsigned long addr, unsigned int esr,
 	return 0;
 }
 
-static int __init single_step_init(void)
+static int brk_handler(unsigned long addr, unsigned int esr,
+		       struct pt_regs *regs)
+{
+	siginfo_t info;
+
+	if (!user_mode(regs))
+		return -EFAULT;
+
+	info = (siginfo_t) {
+		.si_signo = SIGTRAP,
+		.si_errno = 0,
+		.si_code  = TRAP_BRKPT,
+		.si_addr  = (void __user *)instruction_pointer(regs),
+	};
+
+	force_sig_info(SIGTRAP, &info, current);
+	return 0;
+}
+
+int aarch32_break_handler(struct pt_regs *regs)
+{
+	siginfo_t info;
+	unsigned int instr;
+	bool bp = false;
+	void __user *pc = (void __user *)instruction_pointer(regs);
+
+	if (!compat_user_mode(regs))
+		return -EFAULT;
+
+	if (compat_thumb_mode(regs)) {
+		/* get 16-bit Thumb instruction */
+		get_user(instr, (u16 __user *)pc);
+		if (instr == AARCH32_BREAK_THUMB2_LO) {
+			/* get second half of 32-bit Thumb-2 instruction */
+			get_user(instr, (u16 __user *)(pc + 2));
+			bp = instr == AARCH32_BREAK_THUMB2_HI;
+		} else {
+			bp = instr == AARCH32_BREAK_THUMB;
+		}
+	} else {
+		/* 32-bit ARM instruction */
+		get_user(instr, (u32 __user *)pc);
+		bp = (instr & ~0xf0000000) == AARCH32_BREAK_ARM;
+	}
+
+	if (!bp)
+		return -EFAULT;
+
+	info = (siginfo_t) {
+		.si_signo = SIGTRAP,
+		.si_errno = 0,
+		.si_code  = TRAP_BRKPT,
+		.si_addr  = pc,
+	};
+
+	force_sig_info(SIGTRAP, &info, current);
+	return 0;
+}
+
+static int __init debug_traps_init(void)
 {
 	hook_debug_fault_code(DBG_ESR_EVT_HWSS, single_step_handler, SIGTRAP,
 			      TRAP_HWBKPT, "single-step handler");
+	hook_debug_fault_code(DBG_ESR_EVT_BRK, brk_handler, SIGTRAP,
+			      TRAP_BRKPT, "ptrace BRK handler");
 	return 0;
 }
-arch_initcall(single_step_init);
+arch_initcall(debug_traps_init);
 
 /* Re-enable single step for syscall restarting. */
 void user_rewind_single_step(struct task_struct *task)
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 93f96098ae41..e1166145ca29 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -311,14 +311,14 @@ el1_irq:
 #endif
 #ifdef CONFIG_PREEMPT
 	get_thread_info tsk
-	ldr	x24, [tsk, #TI_PREEMPT]		// get preempt count
-	add	x0, x24, #1			// increment it
-	str	x0, [tsk, #TI_PREEMPT]
+	ldr	w24, [tsk, #TI_PREEMPT]		// get preempt count
+	add	w0, w24, #1			// increment it
+	str	w0, [tsk, #TI_PREEMPT]
 #endif
 	irq_handler
 #ifdef CONFIG_PREEMPT
-	str	x24, [tsk, #TI_PREEMPT]		// restore preempt count
-	cbnz	x24, 1f				// preempt count != 0
+	str	w24, [tsk, #TI_PREEMPT]		// restore preempt count
+	cbnz	w24, 1f				// preempt count != 0
 	ldr	x0, [tsk, #TI_FLAGS]		// get flags
 	tbz	x0, #TIF_NEED_RESCHED, 1f	// needs rescheduling?
 	bl	el1_preempt
@@ -477,6 +477,8 @@ el0_undef:
 	 * Undefined instruction
 	 */
 	mov	x0, sp
+	// enable interrupts before calling the main handler
+	enable_irq
 	b	do_undefinstr
 el0_dbg:
 	/*
@@ -507,15 +509,15 @@ el0_irq_naked:
 #endif
 	get_thread_info tsk
 #ifdef CONFIG_PREEMPT
-	ldr	x24, [tsk, #TI_PREEMPT]		// get preempt count
-	add	x23, x24, #1			// increment it
-	str	x23, [tsk, #TI_PREEMPT]
+	ldr	w24, [tsk, #TI_PREEMPT]		// get preempt count
+	add	w23, w24, #1			// increment it
+	str	w23, [tsk, #TI_PREEMPT]
 #endif
 	irq_handler
 #ifdef CONFIG_PREEMPT
-	ldr	x0, [tsk, #TI_PREEMPT]
-	str	x24, [tsk, #TI_PREEMPT]
-	cmp	x0, x23
+	ldr	w0, [tsk, #TI_PREEMPT]
+	str	w24, [tsk, #TI_PREEMPT]
+	cmp	w0, w23
 	b.eq	1f
 	mov	x1, #0
 	str	x1, [x1]			// BUG
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 999504b50c30..7009387348b7 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -112,6 +112,14 @@
 	.quad	TEXT_OFFSET			// Image load offset from start of RAM
 	.quad	0				// reserved
 	.quad	0				// reserved
+	.quad	0				// reserved
+	.quad	0				// reserved
+	.quad	0				// reserved
+	.byte	0x41				// Magic number, "ARM\x64"
+	.byte	0x52
+	.byte	0x4d
+	.byte	0x64
+	.word	0				// reserved
 
 ENTRY(stext)
 	mov	x21, x0				// x21=FDT
diff --git a/arch/arm64/kernel/kuser32.S b/arch/arm64/kernel/kuser32.S
index 1e4905d52d30..63c48ffdf230 100644
--- a/arch/arm64/kernel/kuser32.S
+++ b/arch/arm64/kernel/kuser32.S
@@ -38,33 +38,30 @@ __kuser_cmpxchg64:			// 0xffff0f60
 	.inst	0xe92d00f0		//	push		{r4, r5, r6, r7}
 	.inst	0xe1c040d0		//	ldrd		r4, r5, [r0]
 	.inst	0xe1c160d0		//	ldrd		r6, r7, [r1]
-	.inst	0xf57ff05f		//	dmb		sy
-	.inst	0xe1b20f9f		// 1:	ldrexd		r0, r1, [r2]
+	.inst	0xe1b20e9f		// 1:	ldaexd		r0, r1, [r2]
 	.inst	0xe0303004		//	eors		r3, r0, r4
 	.inst	0x00313005		//	eoreqs		r3, r1, r5
-	.inst	0x01a23f96		//	strexdeq	r3, r6, [r2]
+	.inst	0x01a23e96		//	stlexdeq	r3, r6, [r2]
 	.inst	0x03330001		//	teqeq		r3, #1
 	.inst	0x0afffff9		//	beq		1b
-	.inst	0xf57ff05f		//	dmb		sy
 	.inst	0xe2730000		//	rsbs		r0, r3, #0
 	.inst	0xe8bd00f0		//	pop		{r4, r5, r6, r7}
 	.inst	0xe12fff1e		//	bx		lr
 
 	.align	5
 __kuser_memory_barrier:			// 0xffff0fa0
-	.inst	0xf57ff05f		//	dmb		sy
+	.inst	0xf57ff05b		//	dmb		ish
 	.inst	0xe12fff1e		//	bx		lr
 
 	.align	5
 __kuser_cmpxchg:			// 0xffff0fc0
-	.inst	0xf57ff05f		//	dmb		sy
-	.inst	0xe1923f9f		// 1:	ldrex		r3, [r2]
+	.inst	0xe1923e9f		// 1:	ldaex		r3, [r2]
 	.inst	0xe0533000		//	subs		r3, r3, r0
-	.inst	0x01823f91		//	strexeq	r3, r1, [r2]
+	.inst	0x01823e91		//	stlexeq		r3, r1, [r2]
 	.inst	0x03330001		//	teqeq		r3, #1
 	.inst	0x0afffffa		//	beq		1b
 	.inst	0xe2730000		//	rsbs		r0, r3, #0
-	.inst	0xeaffffef		//	b		<__kuser_memory_barrier>
+	.inst	0xe12fff1e		//	bx		lr
 
 	.align	5
 __kuser_get_tls:			// 0xffff0fe0
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 8254875b67a0..5837ca228967 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -153,15 +153,26 @@ void machine_restart(char *cmd)
 
 void __show_regs(struct pt_regs *regs)
 {
-	int i;
+	int i, top_reg;
+	u64 lr, sp;
+
+	if (compat_user_mode(regs)) {
+		lr = regs->compat_lr;
+		sp = regs->compat_sp;
+		top_reg = 12;
+	} else {
+		lr = regs->regs[30];
+		sp = regs->sp;
+		top_reg = 29;
+	}
 
 	show_regs_print_info(KERN_DEFAULT);
 	print_symbol("PC is at %s\n", instruction_pointer(regs));
-	print_symbol("LR is at %s\n", regs->regs[30]);
+	print_symbol("LR is at %s\n", lr);
 	printk("pc : [<%016llx>] lr : [<%016llx>] pstate: %08llx\n",
-	       regs->pc, regs->regs[30], regs->pstate);
-	printk("sp : %016llx\n", regs->sp);
-	for (i = 29; i >= 0; i--) {
+	       regs->pc, lr, regs->pstate);
+	printk("sp : %016llx\n", sp);
+	for (i = top_reg; i >= 0; i--) {
 		printk("x%-2d: %016llx ", i, regs->regs[i]);
 		if (i % 2 == 0)
 			printk("\n");
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 7041be26d4af..6a8928bba03c 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -53,28 +53,6 @@ void ptrace_disable(struct task_struct *child)
 {
 }
 
-/*
- * Handle hitting a breakpoint.
- */
-static int ptrace_break(struct pt_regs *regs)
-{
-	siginfo_t info = {
-		.si_signo = SIGTRAP,
-		.si_errno = 0,
-		.si_code  = TRAP_BRKPT,
-		.si_addr  = (void __user *)instruction_pointer(regs),
-	};
-
-	force_sig_info(SIGTRAP, &info, current);
-	return 0;
-}
-
-static int arm64_break_trap(unsigned long addr, unsigned int esr,
-			    struct pt_regs *regs)
-{
-	return ptrace_break(regs);
-}
-
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 /*
  * Handle hitting a HW-breakpoint.
@@ -813,33 +791,6 @@ static const struct user_regset_view user_aarch32_view = {
 	.regsets = aarch32_regsets, .n = ARRAY_SIZE(aarch32_regsets)
 };
 
-int aarch32_break_trap(struct pt_regs *regs)
-{
-	unsigned int instr;
-	bool bp = false;
-	void __user *pc = (void __user *)instruction_pointer(regs);
-
-	if (compat_thumb_mode(regs)) {
-		/* get 16-bit Thumb instruction */
-		get_user(instr, (u16 __user *)pc);
-		if (instr == AARCH32_BREAK_THUMB2_LO) {
-			/* get second half of 32-bit Thumb-2 instruction */
-			get_user(instr, (u16 __user *)(pc + 2));
-			bp = instr == AARCH32_BREAK_THUMB2_HI;
-		} else {
-			bp = instr == AARCH32_BREAK_THUMB;
-		}
-	} else {
-		/* 32-bit ARM instruction */
-		get_user(instr, (u32 __user *)pc);
-		bp = (instr & ~0xf0000000) == AARCH32_BREAK_ARM;
-	}
-
-	if (bp)
-		return ptrace_break(regs);
-	return 1;
-}
-
 static int compat_ptrace_read_user(struct task_struct *tsk, compat_ulong_t off,
 				   compat_ulong_t __user *ret)
 {
@@ -1107,16 +1058,6 @@ long arch_ptrace(struct task_struct *child, long request,
 	return ptrace_request(child, request, addr, data);
 }
 
-
-static int __init ptrace_break_init(void)
-{
-	hook_debug_fault_code(DBG_ESR_EVT_BRK, arm64_break_trap, SIGTRAP,
-			      TRAP_BRKPT, "ptrace BRK handler");
-	return 0;
-}
-core_initcall(ptrace_break_init);
-
-
 asmlinkage int syscall_trace(int dir, struct pt_regs *regs)
 {
 	unsigned long saved_reg;
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 7b881f0a9cd1..8c7e81c0143f 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -58,7 +58,7 @@
 unsigned int processor_id;
 EXPORT_SYMBOL(processor_id);
 
-unsigned int elf_hwcap __read_mostly;
+unsigned long elf_hwcap __read_mostly;
 EXPORT_SYMBOL_GPL(elf_hwcap);
 
 #ifdef CONFIG_COMPAT
@@ -426,9 +426,6 @@ static int c_show(struct seq_file *m, void *v)
 #ifdef CONFIG_SMP
 		seq_printf(m, "processor\t: %d\n", i);
 #endif
-		seq_printf(m, "BogoMIPS\t: %lu.%02lu\n\n",
-			   loops_per_jiffy / (500000UL/HZ),
-			   loops_per_jiffy / (5000UL/HZ) % 100);
 	}
 
 	/* dump out the processor features */
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index e8772c07cf5c..e51bbe79f5b5 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -446,12 +446,13 @@ static void compat_setup_return(struct pt_regs *regs, struct k_sigaction *ka,
 	/* Check if the handler is written for ARM or Thumb */
 	thumb = handler & 1;
 
-	if (thumb) {
+	if (thumb)
 		spsr |= COMPAT_PSR_T_BIT;
-		spsr &= ~COMPAT_PSR_IT_MASK;
-	} else {
+	else
 		spsr &= ~COMPAT_PSR_T_BIT;
-	}
+
+	/* The IT state must be cleared for both ARM and Thumb-2 */
+	spsr &= ~COMPAT_PSR_IT_MASK;
 
 	if (ka->sa.sa_flags & SA_RESTORER) {
 		retcode = ptr_to_compat(ka->sa.sa_restorer);
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 4d101cbc0fee..6b0001216189 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -155,13 +155,13 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	if (cpu_ops[cpu]->cpu_postboot)
 		cpu_ops[cpu]->cpu_postboot();
 
-	smp_store_cpu_info(cpu);
-
 	/*
 	 * Enable GIC and timers.
 	 */
 	notify_cpu_starting(cpu);
 
+	smp_store_cpu_info(cpu);
+
 	/*
 	 * OK, now it's safe to let the boot CPU continue.  Wait for
 	 * the CPU migration code to notice that the CPU is online
@@ -173,6 +173,9 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	local_irq_enable();
 	local_fiq_enable();
 
+	local_irq_enable();
+	local_fiq_enable();
+
 	/*
 	 * OK, it's off to the idle thread for us
 	 */
@@ -477,7 +480,7 @@ void show_ipi_list(struct seq_file *p, int prec)
 	for (i = 0; i < NR_IPI; i++) {
 		seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i + IPI_RESCHEDULE,
 			   prec >= 4 ? " " : "");
-		for_each_present_cpu(cpu)
+		for_each_online_cpu(cpu)
 			seq_printf(p, "%10u ",
 				   __get_irq_stat(cpu, ipi_irqs[i]));
 		seq_printf(p, "      %s\n", ipi_types[i]);
diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c
index a551f88ae2c1..03dc3718eb13 100644
--- a/arch/arm64/kernel/time.c
+++ b/arch/arm64/kernel/time.c
@@ -68,12 +68,6 @@ unsigned long long notrace sched_clock(void)
 	return arch_timer_read_counter() * sched_clock_mult;
 }
 
-int read_current_timer(unsigned long *timer_value)
-{
-	*timer_value = arch_timer_read_counter();
-	return 0;
-}
-
 void __init time_init(void)
 {
 	u32 arch_timer_rate;
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index f30852d28590..7ffadddb645d 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -32,6 +32,7 @@
 #include <linux/syscalls.h>
 
 #include <asm/atomic.h>
+#include <asm/debug-monitors.h>
 #include <asm/traps.h>
 #include <asm/stacktrace.h>
 #include <asm/exception.h>
@@ -261,11 +262,9 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
 	siginfo_t info;
 	void __user *pc = (void __user *)instruction_pointer(regs);
 
-#ifdef CONFIG_COMPAT
 	/* check for AArch32 breakpoint instructions */
-	if (compat_user_mode(regs) && aarch32_break_trap(regs) == 0)
+	if (!aarch32_break_handler(regs))
 		return;
-#endif
 
 	if (show_unhandled_signals && unhandled_signal(current, SIGILL) &&
 	    printk_ratelimit()) {
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 2c8a95b539ce..af46c8e13737 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -55,7 +55,8 @@ SECTIONS
 	}
 
 	RO_DATA(PAGE_SIZE)
-
+	EXCEPTION_TABLE(8)
+	NOTES
 	_etext = .;			/* End of text and rodata section */
 
 	. = ALIGN(PAGE_SIZE);
@@ -81,42 +82,15 @@ SECTIONS
 	PERCPU_SECTION(64)
 
 	__init_end = .;
-	. = ALIGN(THREAD_SIZE);
-	__data_loc = .;
-
-	.data : AT(__data_loc) {
-		_data = .;		/* address in memory */
-		_sdata = .;
-
-		/*
-		 * first, the init task union, aligned
-		 * to an 8192 byte boundary.
-		 */
-		INIT_TASK_DATA(THREAD_SIZE)
-		NOSAVE_DATA
-		CACHELINE_ALIGNED_DATA(64)
-		READ_MOSTLY_DATA(64)
-
-		/*
-		 * The exception fixup table (might need resorting at runtime)
-		 */
-		. = ALIGN(32);
-		__start___ex_table = .;
-		*(__ex_table)
-		__stop___ex_table = .;
 
-		/*
-		 * and the usual data section
-		 */
-		DATA_DATA
-		CONSTRUCTORS
-
-		_edata = .;
-	}
+	. = ALIGN(PAGE_SIZE);
+	_data = .;
+	__data_loc = _data - LOAD_OFFSET;
+	_sdata = .;
+	RW_DATA_SECTION(64, PAGE_SIZE, THREAD_SIZE)
+	_edata = .;
 	_edata_loc = __data_loc + SIZEOF(.data);
 
-	NOTES
-
 	BSS_SECTION(0, 0, 0)
 	_end = .;
 
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 6c8ba25bf6bb..df4f2fd187c3 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -130,7 +130,7 @@ static void __do_user_fault(struct task_struct *tsk, unsigned long addr,
 	force_sig_info(sig, &si, tsk);
 }
 
-void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *regs)
+static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *regs)
 {
 	struct task_struct *tsk = current;
 	struct mm_struct *mm = tsk->active_mm;
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index 7c716634a671..e4193e3adc7f 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -70,11 +70,6 @@ void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
 #endif
 }
 
-void __flush_dcache_page(struct page *page)
-{
-	__flush_dcache_area(page_address(page), PAGE_SIZE);
-}
-
 void __sync_icache_dcache(pte_t pte, unsigned long addr)
 {
 	struct page *page = pte_page(pte);
@@ -84,7 +79,7 @@ void __sync_icache_dcache(pte_t pte, unsigned long addr)
 		return;
 
 	if (!test_and_set_bit(PG_dcache_clean, &page->flags)) {
-		__flush_dcache_page(page);
+		__flush_dcache_area(page_address(page), PAGE_SIZE);
 		__flush_icache_all();
 	} else if (icache_is_aivivt()) {
 		__flush_icache_all();
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index fa3651855334..5c47534fe47d 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -46,8 +46,7 @@ static unsigned long phys_initrd_size __initdata = 0;
 
 phys_addr_t memstart_addr __read_mostly = 0;
 
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
-					    unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
 {
 	phys_initrd_start = start;
 	phys_initrd_size = end - start;
diff --git a/arch/arm64/mm/mm.h b/arch/arm64/mm/mm.h
index 916701e6d040..d519f4f50c8c 100644
--- a/arch/arm64/mm/mm.h
+++ b/arch/arm64/mm/mm.h
@@ -1,3 +1,2 @@
-extern void __flush_dcache_page(struct page *page);
 extern void __init bootmem_init(void);
 extern void __init arm64_swiotlb_init(void);
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 49961d1fa033..f8dc7e8fce6f 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -304,6 +304,7 @@ void __iomem * __init early_io_map(phys_addr_t phys, unsigned long virt)
 static void __init map_mem(void)
 {
 	struct memblock_region *reg;
+	phys_addr_t limit;
 
 	/*
 	 * Temporarily limit the memblock range. We need to do this as
@@ -311,9 +312,11 @@ static void __init map_mem(void)
 	 * memory addressable from the initial direct kernel mapping.
 	 *
 	 * The initial direct kernel mapping, located at swapper_pg_dir,
-	 * gives us PGDIR_SIZE memory starting from PHYS_OFFSET (aligned).
+	 * gives us PGDIR_SIZE memory starting from PHYS_OFFSET (which must be
+	 * aligned to 2MB as per Documentation/arm64/booting.txt).
 	 */
-	memblock_set_current_limit((PHYS_OFFSET & PGDIR_MASK) + PGDIR_SIZE);
+	limit = PHYS_OFFSET + PGDIR_SIZE;
+	memblock_set_current_limit(limit);
 
 	/* map all the memory banks */
 	for_each_memblock(memory, reg) {
@@ -323,6 +326,22 @@ static void __init map_mem(void)
 		if (start >= end)
 			break;
 
+#ifndef CONFIG_ARM64_64K_PAGES
+		/*
+		 * For the first memory bank align the start address and
+		 * current memblock limit to prevent create_mapping() from
+		 * allocating pte page tables from unmapped memory.
+		 * When 64K pages are enabled, the pte page table for the
+		 * first PGDIR_SIZE is already present in swapper_pg_dir.
+		 */
+		if (start < limit)
+			start = ALIGN(start, PMD_SIZE);
+		if (end < limit) {
+			limit = end & PMD_MASK;
+			memblock_set_current_limit(limit);
+		}
+#endif
+
 		create_mapping(start, __phys_to_virt(start), end - start);
 	}
 
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index ef9104692d8b..bed1f1de1caf 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -180,12 +180,12 @@ ENTRY(__cpu_setup)
 	bl	__flush_dcache_all
 	mov	lr, x28
 	ic	iallu				// I+BTB cache invalidate
+	tlbi	vmalle1is			// invalidate I + D TLBs
 	dsb	sy
 
 	mov	x0, #3 << 20
 	msr	cpacr_el1, x0			// Enable FP/ASIMD
 	msr	mdscr_el1, xzr			// Reset mdscr_el1
-	tlbi	vmalle1is			// invalidate I + D TLBs
 	/*
 	 * Memory region attributes for LPAE:
 	 *
diff --git a/arch/c6x/kernel/devicetree.c b/arch/c6x/kernel/devicetree.c
index bdb56f09d0ac..287d0e64dfba 100644
--- a/arch/c6x/kernel/devicetree.c
+++ b/arch/c6x/kernel/devicetree.c
@@ -33,8 +33,7 @@ void __init early_init_devtree(void *params)
 
 
 #ifdef CONFIG_BLK_DEV_INITRD
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
-		unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
 {
 	initrd_start = (unsigned long)__va(start);
 	initrd_end = (unsigned long)__va(end);
diff --git a/arch/metag/mm/init.c b/arch/metag/mm/init.c
index d05b8455c44c..bdc48111f0df 100644
--- a/arch/metag/mm/init.c
+++ b/arch/metag/mm/init.c
@@ -419,10 +419,9 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 #endif
 
 #ifdef CONFIG_OF_FLATTREE
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
-					    unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
 {
-	pr_err("%s(%lx, %lx)\n",
+	pr_err("%s(%llx, %llx)\n",
 	       __func__, start, end);
 }
 #endif /* CONFIG_OF_FLATTREE */
diff --git a/arch/microblaze/kernel/prom.c b/arch/microblaze/kernel/prom.c
index 0a2c68f9f9b0..62e2e8f2c5d6 100644
--- a/arch/microblaze/kernel/prom.c
+++ b/arch/microblaze/kernel/prom.c
@@ -136,8 +136,7 @@ void __init early_init_devtree(void *params)
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
-		unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
 {
 	initrd_start = (unsigned long)__va(start);
 	initrd_end = (unsigned long)__va(end);
diff --git a/arch/mips/kernel/prom.c b/arch/mips/kernel/prom.c
index 5712bb532245..32b87882ac87 100644
--- a/arch/mips/kernel/prom.c
+++ b/arch/mips/kernel/prom.c
@@ -58,8 +58,7 @@ void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
-					    unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
 {
 	initrd_start = (unsigned long)__va(start);
 	initrd_end = (unsigned long)__va(end);
diff --git a/arch/openrisc/kernel/prom.c b/arch/openrisc/kernel/prom.c
index 5869e3fa5dd3..150215a91711 100644
--- a/arch/openrisc/kernel/prom.c
+++ b/arch/openrisc/kernel/prom.c
@@ -96,8 +96,7 @@ void __init early_init_devtree(void *params)
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
-		unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
 {
 	initrd_start = (unsigned long)__va(start);
 	initrd_end = (unsigned long)__va(end);
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 00610a34fb9a..eb4de78b7d9b 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -550,8 +550,7 @@ void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
-		unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
 {
 	initrd_start = (unsigned long)__va(start);
 	initrd_end = (unsigned long)__va(end);
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index b1581527a236..2fbad6b9f23c 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -52,8 +52,7 @@ void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
-					    unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
 {
 	initrd_start = (unsigned long)__va(start);
 	initrd_end = (unsigned long)__va(end);
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index 14c6c3a6f04b..a5214542f312 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -170,8 +170,7 @@ static int __init parse_tag_fdt(const bp_tag_t *tag)
 
 __tagtable(BP_TAG_FDT, parse_tag_fdt);
 
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
-		unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
 {
 	initrd_start = (void *)__va(start);
 	initrd_end = (void *)__va(end);
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 118773751ea4..a1ebaecc8122 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -552,7 +552,8 @@ int __init of_flat_dt_match(unsigned long node, const char *const *compat)
  */
 void __init early_init_dt_check_for_initrd(unsigned long node)
 {
-	unsigned long start, end, len;
+	u64 start, end;
+	unsigned long len;
 	__be32 *prop;
 
 	pr_debug("Looking for initrd properties... ");
@@ -560,15 +561,16 @@ void __init early_init_dt_check_for_initrd(unsigned long node)
 	prop = of_get_flat_dt_prop(node, "linux,initrd-start", &len);
 	if (!prop)
 		return;
-	start = of_read_ulong(prop, len/4);
+	start = of_read_number(prop, len/4);
 
 	prop = of_get_flat_dt_prop(node, "linux,initrd-end", &len);
 	if (!prop)
 		return;
-	end = of_read_ulong(prop, len/4);
+	end = of_read_number(prop, len/4);
 
 	early_init_dt_setup_initrd_arch(start, end);
-	pr_debug("initrd_start=0x%lx  initrd_end=0x%lx\n", start, end);
+	pr_debug("initrd_start=0x%llx  initrd_end=0x%llx\n",
+		 (unsigned long long)start, (unsigned long long)end);
 }
 #else
 inline void early_init_dt_check_for_initrd(unsigned long node)
diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h
index ed136ad698ce..4a17939b95cc 100644
--- a/include/linux/of_fdt.h
+++ b/include/linux/of_fdt.h
@@ -106,8 +106,7 @@ extern u64 dt_mem_next_cell(int s, __be32 **cellp);
  * physical addresses.
  */
 #ifdef CONFIG_BLK_DEV_INITRD
-extern void early_init_dt_setup_initrd_arch(unsigned long start,
-					    unsigned long end);
+extern void early_init_dt_setup_initrd_arch(u64 start, u64 end);
 #endif
 
 /* Early flat tree scan hooks */
diff --git a/include/uapi/linux/elf-em.h b/include/uapi/linux/elf-em.h
index 8e2b7bac4378..59c17a2d38ad 100644
--- a/include/uapi/linux/elf-em.h
+++ b/include/uapi/linux/elf-em.h
@@ -22,6 +22,7 @@
 #define EM_PPC		20	/* PowerPC */
 #define EM_PPC64	21	 /* PowerPC64 */
 #define EM_SPU		23	/* Cell BE SPU */
+#define EM_ARM		40	/* ARM 32 bit */
 #define EM_SH		42	/* SuperH */
 #define EM_SPARCV9	43	/* SPARC v9 64-bit */
 #define EM_IA_64	50	/* HP/Intel IA-64 */
@@ -34,6 +35,7 @@
 #define EM_MN10300	89	/* Panasonic/MEI MN10300, AM33 */
 #define EM_BLACKFIN     106     /* ADI Blackfin Processor */
 #define EM_TI_C6000	140	/* TI C6X DSPs */
+#define EM_AARCH64	183	/* ARM 64 bit */
 #define EM_FRV		0x5441	/* Fujitsu FR-V */
 #define EM_AVR32	0x18ad	/* Atmel AVR32 */
 
diff --git a/scripts/sortextable.c b/scripts/sortextable.c
index 1f10e89d15b4..f9ce1160419b 100644
--- a/scripts/sortextable.c
+++ b/scripts/sortextable.c
@@ -31,6 +31,10 @@
 #include <tools/be_byteshift.h>
 #include <tools/le_byteshift.h>
 
+#ifndef EM_AARCH64
+#define EM_AARCH64	183
+#endif
+
 static int fd_map;	/* File descriptor for file being modified. */
 static int mmap_failed; /* Boolean flag. */
 static void *ehdr_curr; /* current ElfXX_Ehdr *  for resource cleanup */
@@ -249,6 +253,7 @@ do_file(char const *const fname)
 		custom_sort = sort_relative_table;
 		break;
 	case EM_ARM:
+	case EM_AARCH64:
 	case EM_MIPS:
 		break;
 	}  /* end switch */