Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Will Deacon:
 "Here's the usual mixed bag of arm64 updates, also including some
  related EFI changes (Acked by Matt) and the MMU gather range cleanup
  (Acked by you).

  Changes include:
   - support for alternative instruction patching from Andre
   - seccomp from Akashi
   - some AArch32 instruction emulation, required by the Android folks
   - optimisations for exception entry/exit code, cmpxchg, pcpu atomics
   - mmu_gather range calculations moved into core code
   - EFI updates from Ard, including long-awaited SMBIOS support
   - /proc/cpuinfo fixes to align with the format used by arch/arm/
   - a few non-critical fixes across the architecture"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (70 commits)
  arm64: remove the unnecessary arm64_swiotlb_init()
  arm64: add module support for alternatives fixups
  arm64: perf: Prevent wraparound during overflow
  arm64/include/asm: Fixed a warning about 'struct pt_regs'
  arm64: Provide a namespace to NCAPS
  arm64: bpf: lift restriction on last instruction
  arm64: Implement support for read-mostly sections
  arm64: compat: align cacheflush syscall with arch/arm
  arm64: add seccomp support
  arm64: add SIGSYS siginfo for compat task
  arm64: add seccomp syscall for compat task
  asm-generic: add generic seccomp.h for secure computing mode 1
  arm64: ptrace: allow tracer to skip a system call
  arm64: ptrace: add NT_ARM_SYSTEM_CALL regset
  arm64: Move some head.text functions to executable section
  arm64: jump labels: NOP out NOP -> NOP replacement
  arm64: add support to dump the kernel page tables
  arm64: Add FIX_HOLE to permanent fixed addresses
  arm64: alternatives: fix pr_fmt string for consistency
  arm64: vmlinux.lds.S: don't discard .exit.* sections at link-time
  ...

24 files changed, 540 insertions, 88 deletions

diff --git a/arch/arm64/include/asm/alternative-asm.h b/arch/arm64/include/asm/alternative-asm.h
new file mode 100644
index 00000000000..919a67855b6
--- /dev/null
+++ b/arch/arm64/include/asm/alternative-asm.h
@@ -0,0 +1,29 @@
+#ifndef __ASM_ALTERNATIVE_ASM_H
+#define __ASM_ALTERNATIVE_ASM_H
+
+#ifdef __ASSEMBLY__
+
+.macro altinstruction_entry orig_offset alt_offset feature orig_len alt_len
+	.word \orig_offset - .
+	.word \alt_offset - .
+	.hword \feature
+	.byte \orig_len
+	.byte \alt_len
+.endm
+
+.macro alternative_insn insn1 insn2 cap
+661:	\insn1
+662:	.pushsection .altinstructions, "a"
+	altinstruction_entry 661b, 663f, \cap, 662b-661b, 664f-663f
+	.popsection
+	.pushsection .altinstr_replacement, "ax"
+663:	\insn2
+664:	.popsection
+	.if ((664b-663b) != (662b-661b))
+		.error "Alternatives instruction length mismatch"
+	.endif
+.endm
+
+#endif  /*  __ASSEMBLY__  */
+
+#endif /* __ASM_ALTERNATIVE_ASM_H */
diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h
new file mode 100644
index 00000000000..d261f01e2ba
--- /dev/null
+++ b/arch/arm64/include/asm/alternative.h
@@ -0,0 +1,44 @@
+#ifndef __ASM_ALTERNATIVE_H
+#define __ASM_ALTERNATIVE_H
+
+#include <linux/types.h>
+#include <linux/stddef.h>
+#include <linux/stringify.h>
+
+struct alt_instr {
+	s32 orig_offset;	/* offset to original instruction */
+	s32 alt_offset;		/* offset to replacement instruction */
+	u16 cpufeature;		/* cpufeature bit set for replacement */
+	u8  orig_len;		/* size of original instruction(s) */
+	u8  alt_len;		/* size of new instruction(s), <= orig_len */
+};
+
+void apply_alternatives_all(void);
+void apply_alternatives(void *start, size_t length);
+void free_alternatives_memory(void);
+
+#define ALTINSTR_ENTRY(feature)						      \
+	" .word 661b - .\n"				/* label           */ \
+	" .word 663f - .\n"				/* new instruction */ \
+	" .hword " __stringify(feature) "\n"		/* feature bit     */ \
+	" .byte 662b-661b\n"				/* source len      */ \
+	" .byte 664f-663f\n"				/* replacement len */
+
+/* alternative assembly primitive: */
+#define ALTERNATIVE(oldinstr, newinstr, feature)			\
+	"661:\n\t"							\
+	oldinstr "\n"							\
+	"662:\n"							\
+	".pushsection .altinstructions,\"a\"\n"				\
+	ALTINSTR_ENTRY(feature)						\
+	".popsection\n"							\
+	".pushsection .altinstr_replacement, \"a\"\n"			\
+	"663:\n\t"							\
+	newinstr "\n"							\
+	"664:\n\t"							\
+	".popsection\n\t"						\
+	".if ((664b-663b) != (662b-661b))\n\t"				\
+	"	.error \"Alternatives instruction length mismatch\"\n\t"\
+	".endif\n"
+
+#endif /* __ASM_ALTERNATIVE_H */
diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
index 88cc05b5f3a..bde449936e2 100644
--- a/arch/arm64/include/asm/cache.h
+++ b/arch/arm64/include/asm/cache.h
@@ -32,6 +32,8 @@
 
 #ifndef __ASSEMBLY__
 
+#define __read_mostly __attribute__((__section__(".data..read_mostly")))
+
 static inline int cache_line_size(void)
 {
 	u32 cwg = cache_type_cwg();
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index 689b6379188..7ae31a2cc6c 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -73,7 +73,7 @@ extern void flush_cache_all(void);
 extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
 extern void flush_icache_range(unsigned long start, unsigned long end);
 extern void __flush_dcache_area(void *addr, size_t len);
-extern void __flush_cache_user_range(unsigned long start, unsigned long end);
+extern long __flush_cache_user_range(unsigned long start, unsigned long end);
 
 static inline void flush_cache_mm(struct mm_struct *mm)
 {
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index ddb9d783055..cb9593079f2 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -19,6 +19,7 @@
 #define __ASM_CMPXCHG_H
 
 #include <linux/bug.h>
+#include <linux/mmdebug.h>
 
 #include <asm/barrier.h>
 
@@ -152,6 +153,51 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 	return oldval;
 }
 
+#define system_has_cmpxchg_double()     1
+
+static inline int __cmpxchg_double(volatile void *ptr1, volatile void *ptr2,
+		unsigned long old1, unsigned long old2,
+		unsigned long new1, unsigned long new2, int size)
+{
+	unsigned long loop, lost;
+
+	switch (size) {
+	case 8:
+		VM_BUG_ON((unsigned long *)ptr2 - (unsigned long *)ptr1 != 1);
+		do {
+			asm volatile("// __cmpxchg_double8\n"
+			"	ldxp	%0, %1, %2\n"
+			"	eor	%0, %0, %3\n"
+			"	eor	%1, %1, %4\n"
+			"	orr	%1, %0, %1\n"
+			"	mov	%w0, #0\n"
+			"	cbnz	%1, 1f\n"
+			"	stxp	%w0, %5, %6, %2\n"
+			"1:\n"
+				: "=&r"(loop), "=&r"(lost), "+Q" (*(u64 *)ptr1)
+				: "r" (old1), "r"(old2), "r"(new1), "r"(new2));
+		} while (loop);
+		break;
+	default:
+		BUILD_BUG();
+	}
+
+	return !lost;
+}
+
+static inline int __cmpxchg_double_mb(volatile void *ptr1, volatile void *ptr2,
+			unsigned long old1, unsigned long old2,
+			unsigned long new1, unsigned long new2, int size)
+{
+	int ret;
+
+	smp_mb();
+	ret = __cmpxchg_double(ptr1, ptr2, old1, old2, new1, new2, size);
+	smp_mb();
+
+	return ret;
+}
+
 static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
 					 unsigned long new, int size)
 {
@@ -182,6 +228,33 @@ static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
 	__ret; \
 })
 
+#define cmpxchg_double(ptr1, ptr2, o1, o2, n1, n2) \
+({\
+	int __ret;\
+	__ret = __cmpxchg_double_mb((ptr1), (ptr2), (unsigned long)(o1), \
+			(unsigned long)(o2), (unsigned long)(n1), \
+			(unsigned long)(n2), sizeof(*(ptr1)));\
+	__ret; \
+})
+
+#define cmpxchg_double_local(ptr1, ptr2, o1, o2, n1, n2) \
+({\
+	int __ret;\
+	__ret = __cmpxchg_double((ptr1), (ptr2), (unsigned long)(o1), \
+			(unsigned long)(o2), (unsigned long)(n1), \
+			(unsigned long)(n2), sizeof(*(ptr1)));\
+	__ret; \
+})
+
+#define this_cpu_cmpxchg_1(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n)
+#define this_cpu_cmpxchg_2(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n)
+#define this_cpu_cmpxchg_4(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n)
+#define this_cpu_cmpxchg_8(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n)
+
+#define this_cpu_cmpxchg_double_8(ptr1, ptr2, o1, o2, n1, n2) \
+	cmpxchg_double_local(raw_cpu_ptr(&(ptr1)), raw_cpu_ptr(&(ptr2)), \
+				o1, o2, n1, n2)
+
 #define cmpxchg64(ptr,o,n)		cmpxchg((ptr),(o),(n))
 #define cmpxchg64_local(ptr,o,n)	cmpxchg_local((ptr),(o),(n))
 
diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h
index 56de5aadede..3fb053fa6e9 100644
--- a/arch/arm64/include/asm/compat.h
+++ b/arch/arm64/include/asm/compat.h
@@ -205,6 +205,13 @@ typedef struct compat_siginfo {
 			compat_long_t _band;	/* POLL_IN, POLL_OUT, POLL_MSG */
 			int _fd;
 		} _sigpoll;
+
+		/* SIGSYS */
+		struct {
+			compat_uptr_t _call_addr; /* calling user insn */
+			int _syscall;	/* triggering system call number */
+			compat_uint_t _arch;	/* AUDIT_ARCH_* of syscall */
+		} _sigsys;
 	} _sifields;
 } compat_siginfo_t;
 
diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h
index 05644308601..ace70682499 100644
--- a/arch/arm64/include/asm/cpu.h
+++ b/arch/arm64/include/asm/cpu.h
@@ -30,6 +30,8 @@ struct cpuinfo_arm64 {
 	u32		reg_dczid;
 	u32		reg_midr;
 
+	u64		reg_id_aa64dfr0;
+	u64		reg_id_aa64dfr1;
 	u64		reg_id_aa64isar0;
 	u64		reg_id_aa64isar1;
 	u64		reg_id_aa64mmfr0;
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index cd4ac051648..07547ccc1f2 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -21,9 +21,38 @@
 #define MAX_CPU_FEATURES	(8 * sizeof(elf_hwcap))
 #define cpu_feature(x)		ilog2(HWCAP_ ## x)
 
+#define ARM64_WORKAROUND_CLEAN_CACHE		0
+#define ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE	1
+
+#define ARM64_NCAPS				2
+
+#ifndef __ASSEMBLY__
+
+extern DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
+
 static inline bool cpu_have_feature(unsigned int num)
 {
 	return elf_hwcap & (1UL << num);
 }
 
+static inline bool cpus_have_cap(unsigned int num)
+{
+	if (num >= ARM64_NCAPS)
+		return false;
+	return test_bit(num, cpu_hwcaps);
+}
+
+static inline void cpus_set_cap(unsigned int num)
+{
+	if (num >= ARM64_NCAPS)
+		pr_warn("Attempt to set an illegal CPU capability (%d >= %d)\n",
+			num, ARM64_NCAPS);
+	else
+		__set_bit(num, cpu_hwcaps);
+}
+
+void check_local_cpu_errata(void);
+
+#endif /* __ASSEMBLY__ */
+
 #endif
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 379d0b87432..8adb986a308 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -57,6 +57,11 @@
 #define MIDR_IMPLEMENTOR(midr)	\
 	(((midr) & MIDR_IMPLEMENTOR_MASK) >> MIDR_IMPLEMENTOR_SHIFT)
 
+#define MIDR_CPU_PART(imp, partnum) \
+	(((imp)			<< MIDR_IMPLEMENTOR_SHIFT) | \
+	(0xf			<< MIDR_ARCHITECTURE_SHIFT) | \
+	((partnum)		<< MIDR_PARTNUM_SHIFT))
+
 #define ARM_CPU_IMP_ARM		0x41
 #define ARM_CPU_IMP_APM		0x50
 
diff --git a/arch/arm64/include/asm/dmi.h b/arch/arm64/include/asm/dmi.h
new file mode 100644
index 00000000000..69d37d87b15
--- /dev/null
+++ b/arch/arm64/include/asm/dmi.h
@@ -0,0 +1,31 @@
+/*
+ * arch/arm64/include/asm/dmi.h
+ *
+ * Copyright (C) 2013 Linaro Limited.
+ * Written by: Yi Li (yi.li@linaro.org)
+ *
+ * based on arch/ia64/include/asm/dmi.h
+ *
+ * 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.
+ */
+
+#ifndef __ASM_DMI_H
+#define __ASM_DMI_H
+
+#include <linux/io.h>
+#include <linux/slab.h>
+
+/*
+ * According to section 2.3.6 of the UEFI spec, the firmware should not
+ * request a virtual mapping for configuration tables such as SMBIOS.
+ * This means we have to map them before use.
+ */
+#define dmi_early_remap(x, l)		ioremap_cache(x, l)
+#define dmi_early_unmap(x, l)		iounmap(x)
+#define dmi_remap(x, l)			ioremap_cache(x, l)
+#define dmi_unmap(x)			iounmap(x)
+#define dmi_alloc(l)			kzalloc(l, GFP_KERNEL)
+
+#endif
diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h
index 5f7bfe6df72..9ef6eca905c 100644
--- a/arch/arm64/include/asm/fixmap.h
+++ b/arch/arm64/include/asm/fixmap.h
@@ -31,6 +31,7 @@
  *
  */
 enum fixed_addresses {
+	FIX_HOLE,
 	FIX_EARLYCON_MEM_BASE,
 	__end_of_permanent_fixed_addresses,
 
@@ -56,10 +57,11 @@ enum fixed_addresses {
 
 #define FIXMAP_PAGE_IO     __pgprot(PROT_DEVICE_nGnRE)
 
-extern void __early_set_fixmap(enum fixed_addresses idx,
-			       phys_addr_t phys, pgprot_t flags);
+void __init early_fixmap_init(void);
 
-#define __set_fixmap __early_set_fixmap
+#define __early_set_fixmap __set_fixmap
+
+extern void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot);
 
 #include <asm-generic/fixmap.h>
 
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index 024c46183c3..0ad735166d9 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -30,6 +30,7 @@
 #define COMPAT_HWCAP_IDIVA	(1 << 17)
 #define COMPAT_HWCAP_IDIVT	(1 << 18)
 #define COMPAT_HWCAP_IDIV	(COMPAT_HWCAP_IDIVA|COMPAT_HWCAP_IDIVT)
+#define COMPAT_HWCAP_LPAE	(1 << 20)
 #define COMPAT_HWCAP_EVTSTRM	(1 << 21)
 
 #define COMPAT_HWCAP2_AES	(1 << 0)
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index 56a9e63b6c3..e2ff32a93b5 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -354,6 +354,16 @@ bool aarch64_insn_hotpatch_safe(u32 old_insn, u32 new_insn);
 int aarch64_insn_patch_text_nosync(void *addr, u32 insn);
 int aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt);
 int aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt);
+
+bool aarch32_insn_is_wide(u32 insn);
+
+#define A32_RN_OFFSET	16
+#define A32_RT_OFFSET	12
+#define A32_RT2_OFFSET	 0
+
+u32 aarch32_insn_extract_reg_num(u32 insn, int offset);
+u32 aarch32_insn_mcr_extract_opc2(u32 insn);
+u32 aarch32_insn_mcr_extract_crm(u32 insn);
 #endif /* __ASSEMBLY__ */
 
 #endif	/* __ASM_INSN_H */
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 79f1d519221..75825b63464 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -28,6 +28,8 @@
 #include <asm/barrier.h>
 #include <asm/pgtable.h>
 #include <asm/early_ioremap.h>
+#include <asm/alternative.h>
+#include <asm/cpufeature.h>
 
 #include <xen/xen.h>
 
@@ -57,28 +59,41 @@ static inline void __raw_writeq(u64 val, volatile void __iomem *addr)
 static inline u8 __raw_readb(const volatile void __iomem *addr)
 {
 	u8 val;
-	asm volatile("ldrb %w0, [%1]" : "=r" (val) : "r" (addr));
+	asm volatile(ALTERNATIVE("ldrb %w0, [%1]",
+				 "ldarb %w0, [%1]",
+				 ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)
+		     : "=r" (val) : "r" (addr));
 	return val;
 }
 
 static inline u16 __raw_readw(const volatile void __iomem *addr)
 {
 	u16 val;
-	asm volatile("ldrh %w0, [%1]" : "=r" (val) : "r" (addr));
+
+	asm volatile(ALTERNATIVE("ldrh %w0, [%1]",
+				 "ldarh %w0, [%1]",
+				 ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)
+		     : "=r" (val) : "r" (addr));
 	return val;
 }
 
 static inline u32 __raw_readl(const volatile void __iomem *addr)
 {
 	u32 val;
-	asm volatile("ldr %w0, [%1]" : "=r" (val) : "r" (addr));
+	asm volatile(ALTERNATIVE("ldr %w0, [%1]",
+				 "ldar %w0, [%1]",
+				 ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)
+		     : "=r" (val) : "r" (addr));
 	return val;
 }
 
 static inline u64 __raw_readq(const volatile void __iomem *addr)
 {
 	u64 val;
-	asm volatile("ldr %0, [%1]" : "=r" (val) : "r" (addr));
+	asm volatile(ALTERNATIVE("ldr %0, [%1]",
+				 "ldar %0, [%1]",
+				 ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)
+		     : "=r" (val) : "r" (addr));
 	return val;
 }
 
diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h
index e1f7ecdde11..94c53674a31 100644
--- a/arch/arm64/include/asm/irq.h
+++ b/arch/arm64/include/asm/irq.h
@@ -3,7 +3,8 @@
 
 #include <asm-generic/irq.h>
 
-extern void (*handle_arch_irq)(struct pt_regs *);
+struct pt_regs;
+
 extern void migrate_irqs(void);
 extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
 
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 7fd3e27e3cc..8afb863f5a9 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -18,6 +18,7 @@
 #ifndef __ARM64_KVM_ARM_H__
 #define __ARM64_KVM_ARM_H__
 
+#include <asm/memory.h>
 #include <asm/types.h>
 
 /* Hyp Configuration Register (HCR) bits */
@@ -160,9 +161,9 @@
 #endif
 
 #define VTTBR_BADDR_SHIFT (VTTBR_X - 1)
-#define VTTBR_BADDR_MASK  (((1LLU << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
-#define VTTBR_VMID_SHIFT  (48LLU)
-#define VTTBR_VMID_MASK	  (0xffLLU << VTTBR_VMID_SHIFT)
+#define VTTBR_BADDR_MASK  (((UL(1) << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
+#define VTTBR_VMID_SHIFT  (UL(48))
+#define VTTBR_VMID_MASK	  (UL(0xFF) << VTTBR_VMID_SHIFT)
 
 /* Hyp System Trap Register */
 #define HSTR_EL2_TTEE	(1 << 16)
@@ -185,13 +186,13 @@
 
 /* Exception Syndrome Register (ESR) bits */
 #define ESR_EL2_EC_SHIFT	(26)
-#define ESR_EL2_EC		(0x3fU << ESR_EL2_EC_SHIFT)
-#define ESR_EL2_IL		(1U << 25)
+#define ESR_EL2_EC		(UL(0x3f) << ESR_EL2_EC_SHIFT)
+#define ESR_EL2_IL		(UL(1) << 25)
 #define ESR_EL2_ISS		(ESR_EL2_IL - 1)
 #define ESR_EL2_ISV_SHIFT	(24)
-#define ESR_EL2_ISV		(1U << ESR_EL2_ISV_SHIFT)
+#define ESR_EL2_ISV		(UL(1) << ESR_EL2_ISV_SHIFT)
 #define ESR_EL2_SAS_SHIFT	(22)
-#define ESR_EL2_SAS		(3U << ESR_EL2_SAS_SHIFT)
+#define ESR_EL2_SAS		(UL(3) << ESR_EL2_SAS_SHIFT)
 #define ESR_EL2_SSE		(1 << 21)
 #define ESR_EL2_SRT_SHIFT	(16)
 #define ESR_EL2_SRT_MASK	(0x1f << ESR_EL2_SRT_SHIFT)
@@ -205,16 +206,16 @@
 #define ESR_EL2_FSC_TYPE	(0x3c)
 
 #define ESR_EL2_CV_SHIFT	(24)
-#define ESR_EL2_CV		(1U << ESR_EL2_CV_SHIFT)
+#define ESR_EL2_CV		(UL(1) << ESR_EL2_CV_SHIFT)
 #define ESR_EL2_COND_SHIFT	(20)
-#define ESR_EL2_COND		(0xfU << ESR_EL2_COND_SHIFT)
+#define ESR_EL2_COND		(UL(0xf) << ESR_EL2_COND_SHIFT)
 
 
 #define FSC_FAULT	(0x04)
 #define FSC_PERM	(0x0c)
 
 /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
-#define HPFAR_MASK	(~0xFUL)
+#define HPFAR_MASK	(~UL(0xf))
 
 #define ESR_EL2_EC_UNKNOWN	(0x00)
 #define ESR_EL2_EC_WFI		(0x01)
diff --git a/arch/arm64/include/asm/opcodes.h b/arch/arm64/include/asm/opcodes.h
new file mode 100644
index 00000000000..4e603ea36ad
--- /dev/null
+++ b/arch/arm64/include/asm/opcodes.h
@@ -0,0 +1 @@
+#include <../../arm/include/asm/opcodes.h>
diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
index 5279e573338..09da25bc596 100644
--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -44,6 +44,221 @@ static inline unsigned long __my_cpu_offset(void)
 
 #endif /* CONFIG_SMP */
 
+#define PERCPU_OP(op, asm_op)						\
+static inline unsigned long __percpu_##op(void *ptr,			\
+			unsigned long val, int size)			\
+{									\
+	unsigned long loop, ret;					\
+									\
+	switch (size) {							\
+	case 1:								\
+		do {							\
+			asm ("//__per_cpu_" #op "_1\n"			\
+			"ldxrb	  %w[ret], %[ptr]\n"			\
+			#asm_op " %w[ret], %w[ret], %w[val]\n"		\
+			"stxrb	  %w[loop], %w[ret], %[ptr]\n"		\
+			: [loop] "=&r" (loop), [ret] "=&r" (ret),	\
+			  [ptr] "+Q"(*(u8 *)ptr)			\
+			: [val] "Ir" (val));				\
+		} while (loop);						\
+		break;							\
+	case 2:								\
+		do {							\
+			asm ("//__per_cpu_" #op "_2\n"			\
+			"ldxrh	  %w[ret], %[ptr]\n"			\
+			#asm_op " %w[ret], %w[ret], %w[val]\n"		\
+			"stxrh	  %w[loop], %w[ret], %[ptr]\n"		\
+			: [loop] "=&r" (loop), [ret] "=&r" (ret),	\
+			  [ptr]  "+Q"(*(u16 *)ptr)			\
+			: [val] "Ir" (val));				\
+		} while (loop);						\
+		break;							\
+	case 4:								\
+		do {							\
+			asm ("//__per_cpu_" #op "_4\n"			\
+			"ldxr	  %w[ret], %[ptr]\n"			\
+			#asm_op " %w[ret], %w[ret], %w[val]\n"		\
+			"stxr	  %w[loop], %w[ret], %[ptr]\n"		\
+			: [loop] "=&r" (loop), [ret] "=&r" (ret),	\
+			  [ptr] "+Q"(*(u32 *)ptr)			\
+			: [val] "Ir" (val));				\
+		} while (loop);						\
+		break;							\
+	case 8:								\
+		do {							\
+			asm ("//__per_cpu_" #op "_8\n"			\
+			"ldxr	  %[ret], %[ptr]\n"			\
+			#asm_op " %[ret], %[ret], %[val]\n"		\
+			"stxr	  %w[loop], %[ret], %[ptr]\n"		\
+			: [loop] "=&r" (loop), [ret] "=&r" (ret),	\
+			  [ptr] "+Q"(*(u64 *)ptr)			\
+			: [val] "Ir" (val));				\
+		} while (loop);						\
+		break;							\
+	default:							\
+		BUILD_BUG();						\
+	}								\
+									\
+	return ret;							\
+}
+
+PERCPU_OP(add, add)
+PERCPU_OP(and, and)
+PERCPU_OP(or, orr)
+#undef PERCPU_OP
+
+static inline unsigned long __percpu_read(void *ptr, int size)
+{
+	unsigned long ret;
+
+	switch (size) {
+	case 1:
+		ret = ACCESS_ONCE(*(u8 *)ptr);
+		break;
+	case 2:
+		ret = ACCESS_ONCE(*(u16 *)ptr);
+		break;
+	case 4:
+		ret = ACCESS_ONCE(*(u32 *)ptr);
+		break;
+	case 8:
+		ret = ACCESS_ONCE(*(u64 *)ptr);
+		break;
+	default:
+		BUILD_BUG();
+	}
+
+	return ret;
+}
+
+static inline void __percpu_write(void *ptr, unsigned long val, int size)
+{
+	switch (size) {
+	case 1:
+		ACCESS_ONCE(*(u8 *)ptr) = (u8)val;
+		break;
+	case 2:
+		ACCESS_ONCE(*(u16 *)ptr) = (u16)val;
+		break;
+	case 4:
+		ACCESS_ONCE(*(u32 *)ptr) = (u32)val;
+		break;
+	case 8:
+		ACCESS_ONCE(*(u64 *)ptr) = (u64)val;
+		break;
+	default:
+		BUILD_BUG();
+	}
+}
+
+static inline unsigned long __percpu_xchg(void *ptr, unsigned long val,
+						int size)
+{
+	unsigned long ret, loop;
+
+	switch (size) {
+	case 1:
+		do {
+			asm ("//__percpu_xchg_1\n"
+			"ldxrb %w[ret], %[ptr]\n"
+			"stxrb %w[loop], %w[val], %[ptr]\n"
+			: [loop] "=&r"(loop), [ret] "=&r"(ret),
+			  [ptr] "+Q"(*(u8 *)ptr)
+			: [val] "r" (val));
+		} while (loop);
+		break;
+	case 2:
+		do {
+			asm ("//__percpu_xchg_2\n"
+			"ldxrh %w[ret], %[ptr]\n"
+			"stxrh %w[loop], %w[val], %[ptr]\n"
+			: [loop] "=&r"(loop), [ret] "=&r"(ret),
+			  [ptr] "+Q"(*(u16 *)ptr)
+			: [val] "r" (val));
+		} while (loop);
+		break;
+	case 4:
+		do {
+			asm ("//__percpu_xchg_4\n"
+			"ldxr %w[ret], %[ptr]\n"
+			"stxr %w[loop], %w[val], %[ptr]\n"
+			: [loop] "=&r"(loop), [ret] "=&r"(ret),
+			  [ptr] "+Q"(*(u32 *)ptr)
+			: [val] "r" (val));
+		} while (loop);
+		break;
+	case 8:
+		do {
+			asm ("//__percpu_xchg_8\n"
+			"ldxr %[ret], %[ptr]\n"
+			"stxr %w[loop], %[val], %[ptr]\n"
+			: [loop] "=&r"(loop), [ret] "=&r"(ret),
+			  [ptr] "+Q"(*(u64 *)ptr)
+			: [val] "r" (val));
+		} while (loop);
+		break;
+	default:
+		BUILD_BUG();
+	}
+
+	return ret;
+}
+
+#define _percpu_add(pcp, val) \
+	__percpu_add(raw_cpu_ptr(&(pcp)), val, sizeof(pcp))
+
+#define _percpu_add_return(pcp, val) (typeof(pcp)) (_percpu_add(pcp, val))
+
+#define _percpu_and(pcp, val) \
+	__percpu_and(raw_cpu_ptr(&(pcp)), val, sizeof(pcp))
+
+#define _percpu_or(pcp, val) \
+	__percpu_or(raw_cpu_ptr(&(pcp)), val, sizeof(pcp))
+
+#define _percpu_read(pcp) (typeof(pcp))	\
+	(__percpu_read(raw_cpu_ptr(&(pcp)), sizeof(pcp)))
+
+#define _percpu_write(pcp, val) \
+	__percpu_write(raw_cpu_ptr(&(pcp)), (unsigned long)(val), sizeof(pcp))
+
+#define _percpu_xchg(pcp, val) (typeof(pcp)) \
+	(__percpu_xchg(raw_cpu_ptr(&(pcp)), (unsigned long)(val), sizeof(pcp)))
+
+#define this_cpu_add_1(pcp, val) _percpu_add(pcp, val)
+#define this_cpu_add_2(pcp, val) _percpu_add(pcp, val)
+#define this_cpu_add_4(pcp, val) _percpu_add(pcp, val)
+#define this_cpu_add_8(pcp, val) _percpu_add(pcp, val)
+
+#define this_cpu_add_return_1(pcp, val) _percpu_add_return(pcp, val)
+#define this_cpu_add_return_2(pcp, val) _percpu_add_return(pcp, val)
+#define this_cpu_add_return_4(pcp, val) _percpu_add_return(pcp, val)
+#define this_cpu_add_return_8(pcp, val) _percpu_add_return(pcp, val)
+
+#define this_cpu_and_1(pcp, val) _percpu_and(pcp, val)
+#define this_cpu_and_2(pcp, val) _percpu_and(pcp, val)
+#define this_cpu_and_4(pcp, val) _percpu_and(pcp, val)
+#define this_cpu_and_8(pcp, val) _percpu_and(pcp, val)
+
+#define this_cpu_or_1(pcp, val) _percpu_or(pcp, val)
+#define this_cpu_or_2(pcp, val) _percpu_or(pcp, val)
+#define this_cpu_or_4(pcp, val) _percpu_or(pcp, val)
+#define this_cpu_or_8(pcp, val) _percpu_or(pcp, val)
+
+#define this_cpu_read_1(pcp) _percpu_read(pcp)
+#define this_cpu_read_2(pcp) _percpu_read(pcp)
+#define this_cpu_read_4(pcp) _percpu_read(pcp)
+#define this_cpu_read_8(pcp) _percpu_read(pcp)
+
+#define this_cpu_write_1(pcp, val) _percpu_write(pcp, val)
+#define this_cpu_write_2(pcp, val) _percpu_write(pcp, val)
+#define this_cpu_write_4(pcp, val) _percpu_write(pcp, val)
+#define this_cpu_write_8(pcp, val) _percpu_write(pcp, val)
+
+#define this_cpu_xchg_1(pcp, val) _percpu_xchg(pcp, val)
+#define this_cpu_xchg_2(pcp, val) _percpu_xchg(pcp, val)
+#define this_cpu_xchg_4(pcp, val) _percpu_xchg(pcp, val)
+#define this_cpu_xchg_8(pcp, val) _percpu_xchg(pcp, val)
+
 #include <asm-generic/percpu.h>
 
 #endif /* __ASM_PERCPU_H */
diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index d5bed02073d..e20df38a8ff 100644
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -26,11 +26,13 @@
 
 #define check_pgt_cache()		do { } while (0)
 
+#define PGALLOC_GFP	(GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+
 #if CONFIG_ARM64_PGTABLE_LEVELS > 2
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return (pmd_t *)get_zeroed_page(GFP_KERNEL | __GFP_REPEAT);
+	return (pmd_t *)__get_free_page(PGALLOC_GFP);
 }
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
@@ -50,7 +52,7 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return (pud_t *)get_zeroed_page(GFP_KERNEL | __GFP_REPEAT);
+	return (pud_t *)__get_free_page(PGALLOC_GFP);
 }
 
 static inline void pud_free(struct mm_struct *mm, pud_t *pud)
@@ -69,8 +71,6 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
 extern pgd_t *pgd_alloc(struct mm_struct *mm);
 extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
 
-#define PGALLOC_GFP	(GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
-
 static inline pte_t *
 pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr)
 {
diff --git a/arch/arm64/include/asm/seccomp.h b/arch/arm64/include/asm/seccomp.h
new file mode 100644
index 00000000000..c76fac97962
--- /dev/null
+++ b/arch/arm64/include/asm/seccomp.h
@@ -0,0 +1,25 @@
+/*
+ * arch/arm64/include/asm/seccomp.h
+ *
+ * Copyright (C) 2014 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ *
+ * 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.
+ */
+#ifndef _ASM_SECCOMP_H
+#define _ASM_SECCOMP_H
+
+#include <asm/unistd.h>
+
+#ifdef CONFIG_COMPAT
+#define __NR_seccomp_read_32		__NR_compat_read
+#define __NR_seccomp_write_32		__NR_compat_write
+#define __NR_seccomp_exit_32		__NR_compat_exit
+#define __NR_seccomp_sigreturn_32	__NR_compat_rt_sigreturn
+#endif /* CONFIG_COMPAT */
+
+#include <asm-generic/seccomp.h>
+
+#endif /* _ASM_SECCOMP_H */
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index a82c0c5c8b5..c028fe37456 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -19,10 +19,6 @@
 #ifndef __ASM_TLB_H
 #define __ASM_TLB_H
 
-#define  __tlb_remove_pmd_tlb_entry __tlb_remove_pmd_tlb_entry
-
-#include <asm-generic/tlb.h>
-
 #include <linux/pagemap.h>
 #include <linux/swap.h>
 
@@ -37,71 +33,22 @@ static inline void __tlb_remove_table(void *_table)
 #define tlb_remove_entry(tlb, entry)	tlb_remove_page(tlb, entry)
 #endif /* CONFIG_HAVE_RCU_TABLE_FREE */
 
-/*
- * There's three ways the TLB shootdown code is used:
- *  1. Unmapping a range of vmas.  See zap_page_range(), unmap_region().
- *     tlb->fullmm = 0, and tlb_start_vma/tlb_end_vma will be called.
- *  2. Unmapping all vmas.  See exit_mmap().
- *     tlb->fullmm = 1, and tlb_start_vma/tlb_end_vma will be called.
- *     Page tables will be freed.
- *  3. Unmapping argument pages.  See shift_arg_pages().
- *     tlb->fullmm = 0, but tlb_start_vma/tlb_end_vma will not be called.
- */
+#include <asm-generic/tlb.h>
+
 static inline void tlb_flush(struct mmu_gather *tlb)
 {
 	if (tlb->fullmm) {
 		flush_tlb_mm(tlb->mm);
-	} else if (tlb->end > 0) {
+	} else {
 		struct vm_area_struct vma = { .vm_mm = tlb->mm, };
 		flush_tlb_range(&vma, tlb->start, tlb->end);
-		tlb->start = TASK_SIZE;
-		tlb->end = 0;
-	}
-}
-
-static inline void tlb_add_flush(struct mmu_gather *tlb, unsigned long addr)
-{
-	if (!tlb->fullmm) {
-		tlb->start = min(tlb->start, addr);
-		tlb->end = max(tlb->end, addr + PAGE_SIZE);
-	}
-}
-
-/*
- * Memorize the range for the TLB flush.
- */
-static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep,
-					  unsigned long addr)
-{
-	tlb_add_flush(tlb, addr);
-}
-
-/*
- * In the case of tlb vma handling, we can optimise these away in the
- * case where we're doing a full MM flush.  When we're doing a munmap,
- * the vmas are adjusted to only cover the region to be torn down.
- */
-static inline void tlb_start_vma(struct mmu_gather *tlb,
-				 struct vm_area_struct *vma)
-{
-	if (!tlb->fullmm) {
-		tlb->start = TASK_SIZE;
-		tlb->end = 0;
 	}
 }
 
-static inline void tlb_end_vma(struct mmu_gather *tlb,
-			       struct vm_area_struct *vma)
-{
-	if (!tlb->fullmm)
-		tlb_flush(tlb);
-}
-
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 				  unsigned long addr)
 {
 	pgtable_page_dtor(pte);
-	tlb_add_flush(tlb, addr);
 	tlb_remove_entry(tlb, pte);
 }
 
@@ -109,7 +56,6 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 				  unsigned long addr)
 {
-	tlb_add_flush(tlb, addr);
 	tlb_remove_entry(tlb, virt_to_page(pmdp));
 }
 #endif
@@ -118,15 +64,8 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp,
 				  unsigned long addr)
 {
-	tlb_add_flush(tlb, addr);
 	tlb_remove_entry(tlb, virt_to_page(pudp));
 }
 #endif
 
-static inline void __tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp,
-						unsigned long address)
-{
-	tlb_add_flush(tlb, address);
-}
-
 #endif
diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h
index 10ca8ff93cc..232e4ba5d31 100644
--- a/arch/arm64/include/asm/traps.h
+++ b/arch/arm64/include/asm/traps.h
@@ -18,6 +18,22 @@
 #ifndef __ASM_TRAP_H
 #define __ASM_TRAP_H
 
+#include <linux/list.h>
+
+struct pt_regs;
+
+struct undef_hook {
+	struct list_head node;
+	u32 instr_mask;
+	u32 instr_val;
+	u64 pstate_mask;
+	u64 pstate_val;
+	int (*fn)(struct pt_regs *regs, u32 instr);
+};
+
+void register_undef_hook(struct undef_hook *hook);
+void unregister_undef_hook(struct undef_hook *hook);
+
 static inline int in_exception_text(unsigned long ptr)
 {
 	extern char __exception_text_start[];
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 6d2bf419431..49c9aefd24a 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -31,6 +31,9 @@
  * Compat syscall numbers used by the AArch64 kernel.
  */
 #define __NR_compat_restart_syscall	0
+#define __NR_compat_exit		1
+#define __NR_compat_read		3
+#define __NR_compat_write		4
 #define __NR_compat_sigreturn		119
 #define __NR_compat_rt_sigreturn	173
 
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 9dfdac4a74a..8893cebcea5 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -787,7 +787,8 @@ __SYSCALL(__NR_sched_setattr, sys_sched_setattr)
 __SYSCALL(__NR_sched_getattr, sys_sched_getattr)
 #define __NR_renameat2 382
 __SYSCALL(__NR_renameat2, sys_renameat2)
-			/* 383 for seccomp */
+#define __NR_seccomp 383
+__SYSCALL(__NR_seccomp, sys_seccomp)
 #define __NR_getrandom 384
 __SYSCALL(__NR_getrandom, sys_getrandom)
 #define __NR_memfd_create 385