24 files changed, 178 insertions, 316 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 7ff68c9..20b688c 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1,11 +1,14 @@
 config ARM64
 	def_bool y
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
+	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_HARDIRQS_NO_DEPRECATED
 	select GENERIC_IOMAP
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
+	select GENERIC_KERNEL_EXECVE
+	select GENERIC_KERNEL_THREAD
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_TIME_VSYSCALL
 	select HARDIRQS_SW_RESEND
@@ -22,6 +25,7 @@ config ARM64
 	select HAVE_PERF_EVENTS
 	select HAVE_SPARSE_IRQ
 	select IRQ_DOMAIN
+	select MODULES_USE_ELF_RELA
 	select NO_BOOTMEM
 	select OF
 	select OF_EARLY_FLATTREE
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index fe77e51..a581a22 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -18,7 +18,6 @@ generic-y += ipcbuf.h
 generic-y += irq_regs.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
-generic-y += linkage.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mman.h
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index cf28464..07fea29 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -25,12 +25,10 @@
 #include <asm/user.h>
 
 typedef unsigned long elf_greg_t;
-typedef unsigned long elf_freg_t[3];
 
 #define ELF_NGREG (sizeof (struct pt_regs) / sizeof(elf_greg_t))
 typedef elf_greg_t elf_gregset_t[ELF_NGREG];
-
-typedef struct user_fp elf_fpregset_t;
+typedef struct user_fpsimd_state elf_fpregset_t;
 
 #define EM_AARCH64		183
 
@@ -87,7 +85,6 @@ typedef struct user_fp elf_fpregset_t;
 #define R_AARCH64_MOVW_PREL_G2_NC	292
 #define R_AARCH64_MOVW_PREL_G3		293
 
-
 /*
  * These are used to set parameters in the core dumps.
  */
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index b42fab9..c43b4ac 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -25,9 +25,8 @@
  *  - FPSR and FPCR
  *  - 32 128-bit data registers
  *
- * Note that user_fp forms a prefix of this structure, which is relied
- * upon in the ptrace FP/SIMD accessors. struct user_fpsimd_state must
- * form a prefix of struct fpsimd_state.
+ * Note that user_fpsimd forms a prefix of this structure, which is
+ * relied upon in the ptrace FP/SIMD accessors.
  */
 struct fpsimd_state {
 	union {
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 74a2a7d..d2f05a6 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -114,7 +114,7 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
  *  I/O port access primitives.
  */
 #define IO_SPACE_LIMIT		0xffff
-#define PCI_IOBASE		((void __iomem *)0xffffffbbfffe0000UL)
+#define PCI_IOBASE		((void __iomem *)(MODULES_VADDR - SZ_2M))
 
 static inline u8 inb(unsigned long addr)
 {
@@ -222,12 +222,12 @@ extern void __iomem *__ioremap(phys_addr_t phys_addr, size_t size, pgprot_t prot
 extern void __iounmap(volatile void __iomem *addr);
 
 #define PROT_DEFAULT		(PTE_TYPE_PAGE | PTE_AF | PTE_DIRTY)
-#define PROT_DEVICE_nGnRE	(PROT_DEFAULT | PTE_XN | PTE_ATTRINDX(MT_DEVICE_nGnRE))
+#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 ioremap(addr, size)		__ioremap((addr), (size), PROT_DEVICE_nGnRE)
-#define ioremap_nocache(addr, size)	__ioremap((addr), (size), PROT_DEVICE_nGnRE)
-#define ioremap_wc(addr, size)		__ioremap((addr), (size), PROT_NORMAL_NC)
+#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 ARCH_HAS_IOREMAP_WC
diff --git a/arch/arm64/include/asm/linkage.h b/arch/arm64/include/asm/linkage.h
new file mode 100644
index 0000000..636c1bc
--- /dev/null
+++ b/arch/arm64/include/asm/linkage.h
@@ -0,0 +1,7 @@
+#ifndef __ASM_LINKAGE_H
+#define __ASM_LINKAGE_H
+
+#define __ALIGN		.align 4
+#define __ALIGN_STR	".align 4"
+
+#endif
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index 0f3b458..75fd13d 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -38,7 +38,8 @@
 #define PMD_SECT_S		(_AT(pmdval_t, 3) << 8)
 #define PMD_SECT_AF		(_AT(pmdval_t, 1) << 10)
 #define PMD_SECT_NG		(_AT(pmdval_t, 1) << 11)
-#define PMD_SECT_XN		(_AT(pmdval_t, 1) << 54)
+#define PMD_SECT_PXN		(_AT(pmdval_t, 1) << 53)
+#define PMD_SECT_UXN		(_AT(pmdval_t, 1) << 54)
 
 /*
  * AttrIndx[2:0] encoding (mapping attributes defined in the MAIR* registers).
@@ -57,7 +58,8 @@
 #define PTE_SHARED		(_AT(pteval_t, 3) << 8)		/* SH[1:0], inner shareable */
 #define PTE_AF			(_AT(pteval_t, 1) << 10)	/* Access Flag */
 #define PTE_NG			(_AT(pteval_t, 1) << 11)	/* nG */
-#define PTE_XN			(_AT(pteval_t, 1) << 54)	/* XN */
+#define PTE_PXN			(_AT(pteval_t, 1) << 53)	/* Privileged XN */
+#define PTE_UXN			(_AT(pteval_t, 1) << 54)	/* User XN */
 
 /*
  * AttrIndx[2:0] encoding (mapping attributes defined in the MAIR* registers).
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 8960239..14aba2d 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -62,23 +62,23 @@ extern pgprot_t pgprot_default;
 
 #define _MOD_PROT(p, b)	__pgprot(pgprot_val(p) | (b))
 
-#define PAGE_NONE		_MOD_PROT(pgprot_default, PTE_NG | PTE_XN | PTE_RDONLY)
-#define PAGE_SHARED		_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_XN)
-#define PAGE_SHARED_EXEC	_MOD_PROT(pgprot_default, PTE_USER | PTE_NG)
-#define PAGE_COPY		_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_XN | PTE_RDONLY)
-#define PAGE_COPY_EXEC		_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_RDONLY)
-#define PAGE_READONLY		_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_XN | PTE_RDONLY)
-#define PAGE_READONLY_EXEC	_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_RDONLY)
-#define PAGE_KERNEL		_MOD_PROT(pgprot_default, PTE_XN | PTE_DIRTY)
-#define PAGE_KERNEL_EXEC	_MOD_PROT(pgprot_default, PTE_DIRTY)
-
-#define __PAGE_NONE		__pgprot(_PAGE_DEFAULT | PTE_NG | PTE_XN | PTE_RDONLY)
-#define __PAGE_SHARED		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_XN)
-#define __PAGE_SHARED_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG)
-#define __PAGE_COPY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_XN | PTE_RDONLY)
-#define __PAGE_COPY_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_RDONLY)
-#define __PAGE_READONLY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_XN | PTE_RDONLY)
-#define __PAGE_READONLY_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_RDONLY)
+#define PAGE_NONE		_MOD_PROT(pgprot_default, PTE_NG | PTE_PXN | PTE_UXN | PTE_RDONLY)
+#define PAGE_SHARED		_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
+#define PAGE_SHARED_EXEC	_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN)
+#define PAGE_COPY		_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_RDONLY)
+#define PAGE_COPY_EXEC		_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_RDONLY)
+#define PAGE_READONLY		_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_RDONLY)
+#define PAGE_READONLY_EXEC	_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_RDONLY)
+#define PAGE_KERNEL		_MOD_PROT(pgprot_default, PTE_PXN | PTE_UXN | PTE_DIRTY)
+#define PAGE_KERNEL_EXEC	_MOD_PROT(pgprot_default, PTE_UXN | PTE_DIRTY)
+
+#define __PAGE_NONE		__pgprot(_PAGE_DEFAULT | PTE_NG | PTE_PXN | PTE_UXN | PTE_RDONLY)
+#define __PAGE_SHARED		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
+#define __PAGE_SHARED_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN)
+#define __PAGE_COPY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_RDONLY)
+#define __PAGE_COPY_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_RDONLY)
+#define __PAGE_READONLY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_RDONLY)
+#define __PAGE_READONLY_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_RDONLY)
 
 #endif /* __ASSEMBLY__ */
 
@@ -130,10 +130,10 @@ extern struct page *empty_zero_page;
 #define pte_young(pte)		(pte_val(pte) & PTE_AF)
 #define pte_special(pte)	(pte_val(pte) & PTE_SPECIAL)
 #define pte_write(pte)		(!(pte_val(pte) & PTE_RDONLY))
-#define pte_exec(pte)		(!(pte_val(pte) & PTE_XN))
+#define pte_exec(pte)		(!(pte_val(pte) & PTE_UXN))
 
 #define pte_present_exec_user(pte) \
-	((pte_val(pte) & (PTE_VALID | PTE_USER | PTE_XN)) == \
+	((pte_val(pte) & (PTE_VALID | PTE_USER | PTE_UXN)) == \
 	 (PTE_VALID | PTE_USER))
 
 #define PTE_BIT_FUNC(fn,op) \
@@ -262,7 +262,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
-	const pteval_t mask = PTE_USER | PTE_XN | PTE_RDONLY;
+	const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY;
 	pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask);
 	return pte;
 }
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 39a208a..ab239b2 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -43,6 +43,8 @@
 #else
 #define STACK_TOP		STACK_TOP_MAX
 #endif /* CONFIG_COMPAT */
+
+#define ARCH_LOW_ADDRESS_LIMIT	PHYS_MASK
 #endif /* __KERNEL__ */
 
 struct debug_info {
@@ -92,30 +94,20 @@ static inline void start_thread_common(struct pt_regs *regs, unsigned long pc)
 static inline void start_thread(struct pt_regs *regs, unsigned long pc,
 				unsigned long sp)
 {
-	unsigned long *stack = (unsigned long *)sp;
-
 	start_thread_common(regs, pc);
 	regs->pstate = PSR_MODE_EL0t;
 	regs->sp = sp;
-	regs->regs[2] = stack[2];	/* x2 (envp) */
-	regs->regs[1] = stack[1];	/* x1 (argv) */
-	regs->regs[0] = stack[0];	/* x0 (argc) */
 }
 
 #ifdef CONFIG_COMPAT
 static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc,
 				       unsigned long sp)
 {
-	unsigned int *stack = (unsigned int *)sp;
-
 	start_thread_common(regs, pc);
 	regs->pstate = COMPAT_PSR_MODE_USR;
 	if (pc & 1)
 		regs->pstate |= COMPAT_PSR_T_BIT;
 	regs->compat_sp = sp;
-	regs->regs[2] = stack[2];	/* x2 (envp) */
-	regs->regs[1] = stack[1];	/* x1 (argv) */
-	regs->regs[0] = stack[0];	/* x0 (argc) */
 }
 #endif
 
@@ -136,11 +128,6 @@ unsigned long get_wchan(struct task_struct *p);
 extern struct task_struct *cpu_switch_to(struct task_struct *prev,
 					 struct task_struct *next);
 
-/*
- * Create a new kernel thread
- */
-extern int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
-
 #define task_pt_regs(p) \
 	((struct pt_regs *)(THREAD_START_SP + task_stack_page(p)) - 1)
 
diff --git a/arch/arm64/include/asm/syscalls.h b/arch/arm64/include/asm/syscalls.h
index 09ff335..a1b00cd 100644
--- a/arch/arm64/include/asm/syscalls.h
+++ b/arch/arm64/include/asm/syscalls.h
@@ -23,18 +23,16 @@
 /*
  * System call wrappers implemented in kernel/entry.S.
  */
-asmlinkage long sys_execve_wrapper(const char __user *filename,
-				   const char __user *const __user *argv,
-				   const char __user *const __user *envp);
-asmlinkage long sys_clone_wrapper(unsigned long clone_flags,
-				  unsigned long newsp,
-				  void __user *parent_tid,
-				  unsigned long tls_val,
-				  void __user *child_tid);
 asmlinkage long sys_rt_sigreturn_wrapper(void);
 asmlinkage long sys_sigaltstack_wrapper(const stack_t __user *uss,
 					stack_t __user *uoss);
 
+/*
+ * AArch64 sys_clone implementation has a different prototype than the generic
+ * one (additional TLS value argument).
+ */
+#define sys_clone	sys_clone
+
 #include <asm-generic/syscalls.h>
 
 #endif	/* __ASM_SYSCALLS_H */
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 63f853f..43064a8 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -14,7 +14,6 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 #ifdef CONFIG_COMPAT
-#define __ARCH_WANT_COMPAT_IPC_PARSE_VERSION
 #define __ARCH_WANT_COMPAT_STAT64
 #define __ARCH_WANT_SYS_GETHOSTNAME
 #define __ARCH_WANT_SYS_PAUSE
@@ -26,4 +25,5 @@
 #define __ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND
 #define __ARCH_WANT_COMPAT_SYS_SENDFILE
 #endif
+#define __ARCH_WANT_SYS_EXECVE
 #include <uapi/asm/unistd.h>
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 6d909fa..d9850cf 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -23,7 +23,7 @@
 
 __SYSCALL(0,   sys_restart_syscall)
 __SYSCALL(1,   sys_exit)
-__SYSCALL(2,   compat_sys_fork_wrapper)
+__SYSCALL(2,   compat_sys_fork)
 __SYSCALL(3,   sys_read)
 __SYSCALL(4,   sys_write)
 __SYSCALL(5,   compat_sys_open)
@@ -32,7 +32,7 @@ __SYSCALL(7,   sys_ni_syscall)			/* 7 was sys_waitpid */
 __SYSCALL(8,   sys_creat)
 __SYSCALL(9,   sys_link)
 __SYSCALL(10,  sys_unlink)
-__SYSCALL(11,  compat_sys_execve_wrapper)
+__SYSCALL(11,  compat_sys_execve)
 __SYSCALL(12,  sys_chdir)
 __SYSCALL(13,  sys_ni_syscall)			/* 13 was sys_time */
 __SYSCALL(14,  sys_mknod)
@@ -141,7 +141,7 @@ __SYSCALL(116, compat_sys_sysinfo)
 __SYSCALL(117, sys_ni_syscall)			/* 117 was sys_ipc */
 __SYSCALL(118, sys_fsync)
 __SYSCALL(119, compat_sys_sigreturn_wrapper)
-__SYSCALL(120, compat_sys_clone_wrapper)
+__SYSCALL(120, sys_clone)
 __SYSCALL(121, sys_setdomainname)
 __SYSCALL(122, sys_newuname)
 __SYSCALL(123, sys_ni_syscall)			/* 123 was sys_modify_ldt */
@@ -211,7 +211,7 @@ __SYSCALL(186, compat_sys_sigaltstack_wrapper)
 __SYSCALL(187, compat_sys_sendfile)
 __SYSCALL(188, sys_ni_syscall)			/* 188 reserved */
 __SYSCALL(189, sys_ni_syscall)			/* 189 reserved */
-__SYSCALL(190, compat_sys_vfork_wrapper)
+__SYSCALL(190, compat_sys_vfork)
 __SYSCALL(191, compat_sys_getrlimit)		/* SuS compliant getrlimit */
 __SYSCALL(192, sys_mmap_pgoff)
 __SYSCALL(193, compat_sys_truncate64_wrapper)
diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h
index 9b131b4..6913643 100644
--- a/arch/arm64/include/uapi/asm/ptrace.h
+++ b/arch/arm64/include/uapi/asm/ptrace.h
@@ -79,13 +79,14 @@ struct user_fpsimd_state {
 
 struct user_hwdebug_state {
 	__u32		dbg_info;
+	__u32		pad;
 	struct {
 		__u64	addr;
 		__u32	ctrl;
+		__u32	pad;
 	}		dbg_regs[16];
 };
 
-
 #endif /* __ASSEMBLY__ */
 
 #endif /* _UAPI__ASM_PTRACE_H */
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index a6f3f7d..cbfa4d2 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -594,7 +594,7 @@ work_resched:
 /*
  * "slow" syscall return path.
  */
-ENTRY(ret_to_user)
+ret_to_user:
 	disable_irq				// disable interrupts
 	ldr	x1, [tsk, #TI_FLAGS]
 	and	x2, x1, #_TIF_WORK_MASK
@@ -611,7 +611,10 @@ ENDPROC(ret_to_user)
  */
 ENTRY(ret_from_fork)
 	bl	schedule_tail
-	get_thread_info tsk
+	cbz	x19, 1f				// not a kernel thread
+	mov	x0, x20
+	blr	x19
+1:	get_thread_info tsk
 	b	ret_to_user
 ENDPROC(ret_from_fork)
 
@@ -673,16 +676,6 @@ __sys_trace_return:
 /*
  * Special system call wrappers.
  */
-ENTRY(sys_execve_wrapper)
-	mov	x3, sp
-	b	sys_execve
-ENDPROC(sys_execve_wrapper)
-
-ENTRY(sys_clone_wrapper)
-	mov	x5, sp
-	b	sys_clone
-ENDPROC(sys_clone_wrapper)
-
 ENTRY(sys_rt_sigreturn_wrapper)
 	mov	x0, sp
 	b	sys_rt_sigreturn
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index ecbf2d8..c76c724 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -613,17 +613,11 @@ enum armv8_pmuv3_perf_types {
 	ARMV8_PMUV3_PERFCTR_BUS_ACCESS				= 0x19,
 	ARMV8_PMUV3_PERFCTR_MEM_ERROR				= 0x1A,
 	ARMV8_PMUV3_PERFCTR_BUS_CYCLES				= 0x1D,
-
-	/*
-	 * This isn't an architected event.
-	 * We detect this event number and use the cycle counter instead.
-	 */
-	ARMV8_PMUV3_PERFCTR_CPU_CYCLES				= 0xFF,
 };
 
 /* PMUv3 HW events mapping. */
 static const unsigned armv8_pmuv3_perf_map[PERF_COUNT_HW_MAX] = {
-	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV8_PMUV3_PERFCTR_CPU_CYCLES,
+	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES,
 	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV8_PMUV3_PERFCTR_INSTR_EXECUTED,
 	[PERF_COUNT_HW_CACHE_REFERENCES]	= ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS,
 	[PERF_COUNT_HW_CACHE_MISSES]		= ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL,
@@ -1106,7 +1100,7 @@ static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc,
 	unsigned long evtype = event->config_base & ARMV8_EVTYPE_EVENT;
 
 	/* Always place a cycle counter into the cycle counter. */
-	if (evtype == ARMV8_PMUV3_PERFCTR_CPU_CYCLES) {
+	if (evtype == ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES) {
 		if (test_and_set_bit(ARMV8_IDX_CYCLE_COUNTER, cpuc->used_mask))
 			return -EAGAIN;
 
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index f22965e..8a5f334 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -240,27 +240,41 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 	struct pt_regs *childregs = task_pt_regs(p);
 	unsigned long tls = p->thread.tp_value;
 
-	*childregs = *regs;
-	childregs->regs[0] = 0;
+	memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context));
 
-	if (is_compat_thread(task_thread_info(p)))
-		childregs->compat_sp = stack_start;
-	else {
+	if (likely(regs)) {
+		*childregs = *regs;
+		childregs->regs[0] = 0;
+		if (is_compat_thread(task_thread_info(p))) {
+			if (stack_start)
+				childregs->compat_sp = stack_start;
+		} else {
+			/*
+			 * Read the current TLS pointer from tpidr_el0 as it may be
+			 * out-of-sync with the saved value.
+			 */
+			asm("mrs %0, tpidr_el0" : "=r" (tls));
+			if (stack_start) {
+				/* 16-byte aligned stack mandatory on AArch64 */
+				if (stack_start & 15)
+					return -EINVAL;
+				childregs->sp = stack_start;
+			}
+		}
 		/*
-		 * Read the current TLS pointer from tpidr_el0 as it may be
-		 * out-of-sync with the saved value.
+		 * If a TLS pointer was passed to clone (4th argument), use it
+		 * for the new thread.
 		 */
-		asm("mrs %0, tpidr_el0" : "=r" (tls));
-		childregs->sp = stack_start;
+		if (clone_flags & CLONE_SETTLS)
+			tls = regs->regs[3];
+	} else {
+		memset(childregs, 0, sizeof(struct pt_regs));
+		childregs->pstate = PSR_MODE_EL1h;
+		p->thread.cpu_context.x19 = stack_start;
+		p->thread.cpu_context.x20 = stk_sz;
 	}
-
-	memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context));
-	p->thread.cpu_context.sp = (unsigned long)childregs;
 	p->thread.cpu_context.pc = (unsigned long)ret_from_fork;
-
-	/* If a TLS pointer was passed to clone, use that for the new thread. */
-	if (clone_flags & CLONE_SETTLS)
-		tls = regs->regs[3];
+	p->thread.cpu_context.sp = (unsigned long)childregs;
 	p->thread.tp_value = tls;
 
 	ptrace_hw_copy_thread(p);
@@ -309,61 +323,6 @@ struct task_struct *__switch_to(struct task_struct *prev,
 	return last;
 }
 
-/*
- * Fill in the task's elfregs structure for a core dump.
- */
-int dump_task_regs(struct task_struct *t, elf_gregset_t *elfregs)
-{
-	elf_core_copy_regs(elfregs, task_pt_regs(t));
-	return 1;
-}
-
-/*
- * fill in the fpe structure for a core dump...
- */
-int dump_fpu (struct pt_regs *regs, struct user_fp *fp)
-{
-	return 0;
-}
-EXPORT_SYMBOL(dump_fpu);
-
-/*
- * Shuffle the argument into the correct register before calling the
- * thread function.  x1 is the thread argument, x2 is the pointer to
- * the thread function, and x3 points to the exit function.
- */
-extern void kernel_thread_helper(void);
-asm(	".section .text\n"
-"	.align\n"
-"	.type	kernel_thread_helper, #function\n"
-"kernel_thread_helper:\n"
-"	mov	x0, x1\n"
-"	mov	x30, x3\n"
-"	br	x2\n"
-"	.size	kernel_thread_helper, . - kernel_thread_helper\n"
-"	.previous");
-
-#define kernel_thread_exit	do_exit
-
-/*
- * Create a kernel thread.
- */
-pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
-{
-	struct pt_regs regs;
-
-	memset(&regs, 0, sizeof(regs));
-
-	regs.regs[1] = (unsigned long)arg;
-	regs.regs[2] = (unsigned long)fn;
-	regs.regs[3] = (unsigned long)kernel_thread_exit;
-	regs.pc = (unsigned long)kernel_thread_helper;
-	regs.pstate = PSR_MODE_EL1h;
-
-	return do_fork(flags|CLONE_VM|CLONE_UNTRACED, 0, &regs, 0, NULL, NULL);
-}
-EXPORT_SYMBOL(kernel_thread);
-
 unsigned long get_wchan(struct task_struct *p)
 {
 	struct stackframe frame;
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 2ea3968..6e1e77f 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -234,28 +234,33 @@ static int ptrace_hbp_fill_attr_ctrl(unsigned int note_type,
 				     struct arch_hw_breakpoint_ctrl ctrl,
 				     struct perf_event_attr *attr)
 {
-	int err, len, type;
+	int err, len, type, disabled = !ctrl.enabled;
 
-	err = arch_bp_generic_fields(ctrl, &len, &type);
-	if (err)
-		return err;
-
-	switch (note_type) {
-	case NT_ARM_HW_BREAK:
-		if ((type & HW_BREAKPOINT_X) != type)
-			return -EINVAL;
-		break;
-	case NT_ARM_HW_WATCH:
-		if ((type & HW_BREAKPOINT_RW) != type)
+	if (disabled) {
+		len = 0;
+		type = HW_BREAKPOINT_EMPTY;
+	} else {
+		err = arch_bp_generic_fields(ctrl, &len, &type);
+		if (err)
+			return err;
+
+		switch (note_type) {
+		case NT_ARM_HW_BREAK:
+			if ((type & HW_BREAKPOINT_X) != type)
+				return -EINVAL;
+			break;
+		case NT_ARM_HW_WATCH:
+			if ((type & HW_BREAKPOINT_RW) != type)
+				return -EINVAL;
+			break;
+		default:
 			return -EINVAL;
-		break;
-	default:
-		return -EINVAL;
+		}
 	}
 
 	attr->bp_len	= len;
 	attr->bp_type	= type;
-	attr->disabled	= !ctrl.enabled;
+	attr->disabled	= disabled;
 
 	return 0;
 }
@@ -372,7 +377,7 @@ static int ptrace_hbp_set_addr(unsigned int note_type,
 
 #define PTRACE_HBP_ADDR_SZ	sizeof(u64)
 #define PTRACE_HBP_CTRL_SZ	sizeof(u32)
-#define PTRACE_HBP_REG_OFF	sizeof(u32)
+#define PTRACE_HBP_PAD_SZ	sizeof(u32)
 
 static int hw_break_get(struct task_struct *target,
 			const struct user_regset *regset,
@@ -380,7 +385,7 @@ static int hw_break_get(struct task_struct *target,
 			void *kbuf, void __user *ubuf)
 {
 	unsigned int note_type = regset->core_note_type;
-	int ret, idx = 0, offset = PTRACE_HBP_REG_OFF, limit;
+	int ret, idx = 0, offset, limit;
 	u32 info, ctrl;
 	u64 addr;
 
@@ -389,11 +394,20 @@ static int hw_break_get(struct task_struct *target,
 	if (ret)
 		return ret;
 
-	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &info, 0, 4);
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &info, 0,
+				  sizeof(info));
+	if (ret)
+		return ret;
+
+	/* Pad */
+	offset = offsetof(struct user_hwdebug_state, pad);
+	ret = user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf, offset,
+				       offset + PTRACE_HBP_PAD_SZ);
 	if (ret)
 		return ret;
 
 	/* (address, ctrl) registers */
+	offset = offsetof(struct user_hwdebug_state, dbg_regs);
 	limit = regset->n * regset->size;
 	while (count && offset < limit) {
 		ret = ptrace_hbp_get_addr(note_type, target, idx, &addr);
@@ -413,6 +427,13 @@ static int hw_break_get(struct task_struct *target,
 		if (ret)
 			return ret;
 		offset += PTRACE_HBP_CTRL_SZ;
+
+		ret = user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
+					       offset,
+					       offset + PTRACE_HBP_PAD_SZ);
+		if (ret)
+			return ret;
+		offset += PTRACE_HBP_PAD_SZ;
 		idx++;
 	}
 
@@ -425,12 +446,13 @@ static int hw_break_set(struct task_struct *target,
 			const void *kbuf, const void __user *ubuf)
 {
 	unsigned int note_type = regset->core_note_type;
-	int ret, idx = 0, offset = PTRACE_HBP_REG_OFF, limit;
+	int ret, idx = 0, offset, limit;
 	u32 ctrl;
 	u64 addr;
 
-	/* Resource info */
-	ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, 0, 4);
+	/* Resource info and pad */
+	offset = offsetof(struct user_hwdebug_state, dbg_regs);
+	ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, 0, offset);
 	if (ret)
 		return ret;
 
@@ -454,6 +476,13 @@ static int hw_break_set(struct task_struct *target,
 		if (ret)
 			return ret;
 		offset += PTRACE_HBP_CTRL_SZ;
+
+		ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+						offset,
+						offset + PTRACE_HBP_PAD_SZ);
+		if (ret)
+			return ret;
+		offset += PTRACE_HBP_PAD_SZ;
 		idx++;
 	}
 
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 48ffb9f..7665a9b 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -170,7 +170,19 @@ static void __init setup_machine_fdt(phys_addr_t dt_phys)
 
 void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 {
+	base &= PAGE_MASK;
 	size &= PAGE_MASK;
+	if (base + size < PHYS_OFFSET) {
+		pr_warning("Ignoring memory block 0x%llx - 0x%llx\n",
+			   base, base + size);
+		return;
+	}
+	if (base < PHYS_OFFSET) {
+		pr_warning("Ignoring memory range 0x%llx - 0x%llx\n",
+			   base, PHYS_OFFSET);
+		size -= PHYS_OFFSET - base;
+		base = PHYS_OFFSET;
+	}
 	memblock_add(base, size);
 }
 
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index b711525..538300f 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -46,7 +46,6 @@
 #include <asm/sections.h>
 #include <asm/tlbflush.h>
 #include <asm/ptrace.h>
-#include <asm/mmu_context.h>
 
 /*
  * as from 2.5, kernels no longer have an init_tasks structure
@@ -212,8 +211,7 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	 * before we continue.
 	 */
 	set_cpu_online(cpu, true);
-	while (!cpu_active(cpu))
-		cpu_relax();
+	complete(&cpu_running);
 
 	/*
 	 * OK, it's off to the idle thread for us
diff --git a/arch/arm64/kernel/sys.c b/arch/arm64/kernel/sys.c
index b120df3..4364df8 100644
--- a/arch/arm64/kernel/sys.c
+++ b/arch/arm64/kernel/sys.c
@@ -31,79 +31,11 @@
  */
 asmlinkage long sys_clone(unsigned long clone_flags, unsigned long newsp,
 			  int __user *parent_tidptr, unsigned long tls_val,
-			  int __user *child_tidptr, struct pt_regs *regs)
+			  int __user *child_tidptr)
 {
-	if (!newsp)
-		newsp = regs->sp;
-	/* 16-byte aligned stack mandatory on AArch64 */
-	if (newsp & 15)
-		return -EINVAL;
-	return do_fork(clone_flags, newsp, regs, 0, parent_tidptr, child_tidptr);
-}
-
-/*
- * sys_execve() executes a new program.
- */
-asmlinkage long sys_execve(const char __user *filenamei,
-			   const char __user *const __user *argv,
-			   const char __user *const __user *envp,
-			   struct pt_regs *regs)
-{
-	long error;
-	struct filename *filename;
-
-	filename = getname(filenamei);
-	error = PTR_ERR(filename);
-	if (IS_ERR(filename))
-		goto out;
-	error = do_execve(filename->name, argv, envp, regs);
-	putname(filename);
-out:
-	return error;
-}
-
-int kernel_execve(const char *filename,
-		  const char *const argv[],
-		  const char *const envp[])
-{
-	struct pt_regs regs;
-	int ret;
-
-	memset(&regs, 0, sizeof(struct pt_regs));
-	ret = do_execve(filename,
-			(const char __user *const __user *)argv,
-			(const char __user *const __user *)envp, &regs);
-	if (ret < 0)
-		goto out;
-
-	/*
-	 * Save argc to the register structure for userspace.
-	 */
-	regs.regs[0] = ret;
-
-	/*
-	 * We were successful.  We won't be returning to our caller, but
-	 * instead to user space by manipulating the kernel stack.
-	 */
-	asm(	"add	x0, %0, %1\n\t"
-		"mov	x1, %2\n\t"
-		"mov	x2, %3\n\t"
-		"bl	memmove\n\t"	/* copy regs to top of stack */
-		"mov	x27, #0\n\t"	/* not a syscall */
-		"mov	x28, %0\n\t"	/* thread structure */
-		"mov	sp, x0\n\t"	/* reposition stack pointer */
-		"b	ret_to_user"
-		:
-		: "r" (current_thread_info()),
-		  "Ir" (THREAD_START_SP - sizeof(regs)),
-		  "r" (&regs),
-		  "Ir" (sizeof(regs))
-		: "x0", "x1", "x2", "x27", "x28", "x30", "memory");
-
- out:
-	return ret;
+	return do_fork(clone_flags, newsp, current_pt_regs(), 0,
+			parent_tidptr, child_tidptr);
 }
-EXPORT_SYMBOL(kernel_execve);
 
 asmlinkage long sys_mmap(unsigned long addr, unsigned long len,
 			 unsigned long prot, unsigned long flags,
@@ -118,8 +50,6 @@ asmlinkage long sys_mmap(unsigned long addr, unsigned long len,
 /*
  * Wrappers to pass the pt_regs argument.
  */
-#define sys_execve		sys_execve_wrapper
-#define sys_clone		sys_clone_wrapper
 #define sys_rt_sigreturn	sys_rt_sigreturn_wrapper
 #define sys_sigaltstack		sys_sigaltstack_wrapper
 
diff --git a/arch/arm64/kernel/sys32.S b/arch/arm64/kernel/sys32.S
index 54c4aec..7ef59e9 100644
--- a/arch/arm64/kernel/sys32.S
+++ b/arch/arm64/kernel/sys32.S
@@ -26,25 +26,6 @@
 /*
  * System call wrappers for the AArch32 compatibility layer.
  */
-compat_sys_fork_wrapper:
-	mov	x0, sp
-	b	compat_sys_fork
-ENDPROC(compat_sys_fork_wrapper)
-
-compat_sys_vfork_wrapper:
-	mov	x0, sp
-	b	compat_sys_vfork
-ENDPROC(compat_sys_vfork_wrapper)
-
-compat_sys_execve_wrapper:
-	mov	x3, sp
-	b	compat_sys_execve
-ENDPROC(compat_sys_execve_wrapper)
-
-compat_sys_clone_wrapper:
-	mov	x5, sp
-	b	compat_sys_clone
-ENDPROC(compat_sys_clone_wrapper)
 
 compat_sys_sigreturn_wrapper:
 	mov	x0, sp
diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c
index 906e3bd..6fabc19 100644
--- a/arch/arm64/kernel/sys_compat.c
+++ b/arch/arm64/kernel/sys_compat.c
@@ -28,43 +28,15 @@
 #include <asm/cacheflush.h>
 #include <asm/unistd32.h>
 
-asmlinkage int compat_sys_fork(struct pt_regs *regs)
+asmlinkage int compat_sys_fork(void)
 {
-	return do_fork(SIGCHLD, regs->compat_sp, regs, 0, NULL, NULL);
+	return do_fork(SIGCHLD, 0, current_pt_regs(), 0, NULL, NULL);
 }
 
-asmlinkage int compat_sys_clone(unsigned long clone_flags, unsigned long newsp,
-			  int __user *parent_tidptr, int tls_val,
-			  int __user *child_tidptr, struct pt_regs *regs)
+asmlinkage int compat_sys_vfork(void)
 {
-	if (!newsp)
-		newsp = regs->compat_sp;
-
-	return do_fork(clone_flags, newsp, regs, 0, parent_tidptr, child_tidptr);
-}
-
-asmlinkage int compat_sys_vfork(struct pt_regs *regs)
-{
-	return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs->compat_sp,
-		       regs, 0, NULL, NULL);
-}
-
-asmlinkage int compat_sys_execve(const char __user *filenamei,
-				 compat_uptr_t argv, compat_uptr_t envp,
-				 struct pt_regs *regs)
-{
-	int error;
-	struct filename *filename;
-
-	filename = getname(filenamei);
-	error = PTR_ERR(filename);
-	if (IS_ERR(filename))
-		goto out;
-	error = compat_do_execve(filename->name, compat_ptr(argv),
-					compat_ptr(envp), regs);
-	putname(filename);
-out:
-	return error;
+	return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, 0,
+		       current_pt_regs(), 0, NULL, NULL);
 }
 
 asmlinkage int compat_sys_sched_rr_get_interval(compat_pid_t pid,
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 17948fc..ba45794 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -28,6 +28,7 @@
 #include <linux/sched.h>
 #include <linux/signal.h>
 #include <linux/slab.h>
+#include <linux/timekeeper_internal.h>
 #include <linux/vmalloc.h>
 
 #include <asm/cacheflush.h>
@@ -222,11 +223,10 @@ struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
 /*
  * Update the vDSO data page to keep in sync with kernel timekeeping.
  */
-void update_vsyscall(struct timespec *ts, struct timespec *wtm,
-		     struct clocksource *clock, u32 mult)
+void update_vsyscall(struct timekeeper *tk)
 {
 	struct timespec xtime_coarse;
-	u32 use_syscall = strcmp(clock->name, "arch_sys_counter");
+	u32 use_syscall = strcmp(tk->clock->name, "arch_sys_counter");
 
 	++vdso_data->tb_seq_count;
 	smp_wmb();
@@ -237,13 +237,13 @@ void update_vsyscall(struct timespec *ts, struct timespec *wtm,
 	vdso_data->xtime_coarse_nsec		= xtime_coarse.tv_nsec;
 
 	if (!use_syscall) {
-		vdso_data->cs_cycle_last	= clock->cycle_last;
-		vdso_data->xtime_clock_sec	= ts->tv_sec;
-		vdso_data->xtime_clock_nsec	= ts->tv_nsec;
-		vdso_data->cs_mult		= mult;
-		vdso_data->cs_shift		= clock->shift;
-		vdso_data->wtm_clock_sec	= wtm->tv_sec;
-		vdso_data->wtm_clock_nsec	= wtm->tv_nsec;
+		vdso_data->cs_cycle_last	= tk->clock->cycle_last;
+		vdso_data->xtime_clock_sec	= tk->xtime_sec;
+		vdso_data->xtime_clock_nsec	= tk->xtime_nsec >> tk->shift;
+		vdso_data->cs_mult		= tk->mult;
+		vdso_data->cs_shift		= tk->shift;
+		vdso_data->wtm_clock_sec	= tk->wall_to_monotonic.tv_sec;
+		vdso_data->wtm_clock_nsec	= tk->wall_to_monotonic.tv_nsec;
 	}
 
 	smp_wmb();
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index efbf7df..4cd2893 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -80,7 +80,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 #ifdef CONFIG_ZONE_DMA32
 	/* 4GB maximum for 32-bit only capable devices */
 	max_dma32 = min(max, MAX_DMA32_PFN);
-	zone_size[ZONE_DMA32] = max_dma32 - min;
+	zone_size[ZONE_DMA32] = max(min, max_dma32) - min;
 #endif
 	zone_size[ZONE_NORMAL] = max - max_dma32;