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

Pull arm64 updates from Catalin Marinas:
 - Optimised assembly string/memory routines (based on the AArch64
   Cortex Strings library contributed to glibc but re-licensed under
   GPLv2)
 - Optimised crypto algorithms making use of the ARMv8 crypto extensions
   (together with kernel API for using FPSIMD instructions in interrupt
   context)
 - Ftrace support
 - CPU topology parsing from DT
 - ESR_EL1 (Exception Syndrome Register) exposed to user space signal
   handlers for SIGSEGV/SIGBUS (useful to emulation tools like Qemu)
 - 1GB section linear mapping if applicable
 - Barriers usage clean-up
 - Default pgprot clean-up

Conflicts as per Catalin.

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (57 commits)
  arm64: kernel: initialize broadcast hrtimer based clock event device
  arm64: ftrace: Add system call tracepoint
  arm64: ftrace: Add CALLER_ADDRx macros
  arm64: ftrace: Add dynamic ftrace support
  arm64: Add ftrace support
  ftrace: Add arm64 support to recordmcount
  arm64: Add 'notrace' attribute to unwind_frame() for ftrace
  arm64: add __ASSEMBLY__ in asm/insn.h
  arm64: Fix linker script entry point
  arm64: lib: Implement optimized string length routines
  arm64: lib: Implement optimized string compare routines
  arm64: lib: Implement optimized memcmp routine
  arm64: lib: Implement optimized memset routine
  arm64: lib: Implement optimized memmove routine
  arm64: lib: Implement optimized memcpy routine
  arm64: defconfig: enable a few more common/useful options in defconfig
  ftrace: Make CALLER_ADDRx macros more generic
  arm64: Fix deadlock scenario with smp_send_stop()
  arm64: Fix machine_shutdown() definition
  arm64: Support arch_irq_work_raise() via self IPIs
  ...

22 files changed, 1063 insertions, 191 deletions

diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index ba5e17a522d..cdaedad3afe 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -7,14 +7,19 @@ AFLAGS_head.o		:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 CFLAGS_efi-stub.o 	:= -DTEXT_OFFSET=$(TEXT_OFFSET) \
 			   -I$(src)/../../../scripts/dtc/libfdt
 
+CFLAGS_REMOVE_ftrace.o = -pg
+CFLAGS_REMOVE_insn.o = -pg
+CFLAGS_REMOVE_return_address.o = -pg
+
 # Object file lists.
 arm64-obj-y		:= cputable.o debug-monitors.o entry.o irq.o fpsimd.o	\
 			   entry-fpsimd.o process.o ptrace.o setup.o signal.o	\
 			   sys.o stacktrace.o time.o traps.o io.o vdso.o	\
-			   hyp-stub.o psci.o cpu_ops.o insn.o
+			   hyp-stub.o psci.o cpu_ops.o insn.o return_address.o
 
 arm64-obj-$(CONFIG_COMPAT)		+= sys32.o kuser32.o signal32.o 	\
 					   sys_compat.o
+arm64-obj-$(CONFIG_FUNCTION_TRACER)	+= ftrace.o entry-ftrace.o
 arm64-obj-$(CONFIG_MODULES)		+= arm64ksyms.o module.o
 arm64-obj-$(CONFIG_SMP)			+= smp.o smp_spin_table.o topology.o
 arm64-obj-$(CONFIG_PERF_EVENTS)		+= perf_regs.o
diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c
index 338b568cd8a..a85843ddbde 100644
--- a/arch/arm64/kernel/arm64ksyms.c
+++ b/arch/arm64/kernel/arm64ksyms.c
@@ -44,10 +44,15 @@ EXPORT_SYMBOL(memstart_addr);
 	/* string / mem functions */
 EXPORT_SYMBOL(strchr);
 EXPORT_SYMBOL(strrchr);
+EXPORT_SYMBOL(strcmp);
+EXPORT_SYMBOL(strncmp);
+EXPORT_SYMBOL(strlen);
+EXPORT_SYMBOL(strnlen);
 EXPORT_SYMBOL(memset);
 EXPORT_SYMBOL(memcpy);
 EXPORT_SYMBOL(memmove);
 EXPORT_SYMBOL(memchr);
+EXPORT_SYMBOL(memcmp);
 
 	/* atomic bitops */
 EXPORT_SYMBOL(set_bit);
@@ -56,3 +61,7 @@ EXPORT_SYMBOL(clear_bit);
 EXPORT_SYMBOL(test_and_clear_bit);
 EXPORT_SYMBOL(change_bit);
 EXPORT_SYMBOL(test_and_change_bit);
+
+#ifdef CONFIG_FUNCTION_TRACER
+EXPORT_SYMBOL(_mcount);
+#endif
diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S
index 6a27cd6dbfa..d358ccacfc0 100644
--- a/arch/arm64/kernel/entry-fpsimd.S
+++ b/arch/arm64/kernel/entry-fpsimd.S
@@ -41,3 +41,27 @@ ENTRY(fpsimd_load_state)
 	fpsimd_restore x0, 8
 	ret
 ENDPROC(fpsimd_load_state)
+
+#ifdef CONFIG_KERNEL_MODE_NEON
+
+/*
+ * Save the bottom n FP registers.
+ *
+ * x0 - pointer to struct fpsimd_partial_state
+ */
+ENTRY(fpsimd_save_partial_state)
+	fpsimd_save_partial x0, 1, 8, 9
+	ret
+ENDPROC(fpsimd_load_partial_state)
+
+/*
+ * Load the bottom n FP registers.
+ *
+ * x0 - pointer to struct fpsimd_partial_state
+ */
+ENTRY(fpsimd_load_partial_state)
+	fpsimd_restore_partial x0, 8, 9
+	ret
+ENDPROC(fpsimd_load_partial_state)
+
+#endif
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
new file mode 100644
index 00000000000..b051871f296
--- /dev/null
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -0,0 +1,218 @@
+/*
+ * arch/arm64/kernel/entry-ftrace.S
+ *
+ * Copyright (C) 2013 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.
+ */
+
+#include <linux/linkage.h>
+#include <asm/ftrace.h>
+#include <asm/insn.h>
+
+/*
+ * Gcc with -pg will put the following code in the beginning of each function:
+ *      mov x0, x30
+ *      bl _mcount
+ *	[function's body ...]
+ * "bl _mcount" may be replaced to "bl ftrace_caller" or NOP if dynamic
+ * ftrace is enabled.
+ *
+ * Please note that x0 as an argument will not be used here because we can
+ * get lr(x30) of instrumented function at any time by winding up call stack
+ * as long as the kernel is compiled without -fomit-frame-pointer.
+ * (or CONFIG_FRAME_POINTER, this is forced on arm64)
+ *
+ * stack layout after mcount_enter in _mcount():
+ *
+ * current sp/fp =>  0:+-----+
+ * in _mcount()        | x29 | -> instrumented function's fp
+ *                     +-----+
+ *                     | x30 | -> _mcount()'s lr (= instrumented function's pc)
+ * old sp       => +16:+-----+
+ * when instrumented   |     |
+ * function calls      | ... |
+ * _mcount()           |     |
+ *                     |     |
+ * instrumented => +xx:+-----+
+ * function's fp       | x29 | -> parent's fp
+ *                     +-----+
+ *                     | x30 | -> instrumented function's lr (= parent's pc)
+ *                     +-----+
+ *                     | ... |
+ */
+
+	.macro mcount_enter
+	stp	x29, x30, [sp, #-16]!
+	mov	x29, sp
+	.endm
+
+	.macro mcount_exit
+	ldp	x29, x30, [sp], #16
+	ret
+	.endm
+
+	.macro mcount_adjust_addr rd, rn
+	sub	\rd, \rn, #AARCH64_INSN_SIZE
+	.endm
+
+	/* for instrumented function's parent */
+	.macro mcount_get_parent_fp reg
+	ldr	\reg, [x29]
+	ldr	\reg, [\reg]
+	.endm
+
+	/* for instrumented function */
+	.macro mcount_get_pc0 reg
+	mcount_adjust_addr	\reg, x30
+	.endm
+
+	.macro mcount_get_pc reg
+	ldr	\reg, [x29, #8]
+	mcount_adjust_addr	\reg, \reg
+	.endm
+
+	.macro mcount_get_lr reg
+	ldr	\reg, [x29]
+	ldr	\reg, [\reg, #8]
+	mcount_adjust_addr	\reg, \reg
+	.endm
+
+	.macro mcount_get_lr_addr reg
+	ldr	\reg, [x29]
+	add	\reg, \reg, #8
+	.endm
+
+#ifndef CONFIG_DYNAMIC_FTRACE
+/*
+ * void _mcount(unsigned long return_address)
+ * @return_address: return address to instrumented function
+ *
+ * This function makes calls, if enabled, to:
+ *     - tracer function to probe instrumented function's entry,
+ *     - ftrace_graph_caller to set up an exit hook
+ */
+ENTRY(_mcount)
+#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
+	ldr	x0, =ftrace_trace_stop
+	ldr	x0, [x0]		// if ftrace_trace_stop
+	ret				//   return;
+#endif
+	mcount_enter
+
+	ldr	x0, =ftrace_trace_function
+	ldr	x2, [x0]
+	adr	x0, ftrace_stub
+	cmp	x0, x2			// if (ftrace_trace_function
+	b.eq	skip_ftrace_call	//     != ftrace_stub) {
+
+	mcount_get_pc	x0		//       function's pc
+	mcount_get_lr	x1		//       function's lr (= parent's pc)
+	blr	x2			//   (*ftrace_trace_function)(pc, lr);
+
+#ifndef CONFIG_FUNCTION_GRAPH_TRACER
+skip_ftrace_call:			//   return;
+	mcount_exit			// }
+#else
+	mcount_exit			//   return;
+					// }
+skip_ftrace_call:
+	ldr	x1, =ftrace_graph_return
+	ldr	x2, [x1]		//   if ((ftrace_graph_return
+	cmp	x0, x2			//        != ftrace_stub)
+	b.ne	ftrace_graph_caller
+
+	ldr	x1, =ftrace_graph_entry	//     || (ftrace_graph_entry
+	ldr	x2, [x1]		//        != ftrace_graph_entry_stub))
+	ldr	x0, =ftrace_graph_entry_stub
+	cmp	x0, x2
+	b.ne	ftrace_graph_caller	//     ftrace_graph_caller();
+
+	mcount_exit
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+ENDPROC(_mcount)
+
+#else /* CONFIG_DYNAMIC_FTRACE */
+/*
+ * _mcount() is used to build the kernel with -pg option, but all the branch
+ * instructions to _mcount() are replaced to NOP initially at kernel start up,
+ * and later on, NOP to branch to ftrace_caller() when enabled or branch to
+ * NOP when disabled per-function base.
+ */
+ENTRY(_mcount)
+	ret
+ENDPROC(_mcount)
+
+/*
+ * void ftrace_caller(unsigned long return_address)
+ * @return_address: return address to instrumented function
+ *
+ * This function is a counterpart of _mcount() in 'static' ftrace, and
+ * makes calls to:
+ *     - tracer function to probe instrumented function's entry,
+ *     - ftrace_graph_caller to set up an exit hook
+ */
+ENTRY(ftrace_caller)
+	mcount_enter
+
+	mcount_get_pc0	x0		//     function's pc
+	mcount_get_lr	x1		//     function's lr
+
+	.global ftrace_call
+ftrace_call:				// tracer(pc, lr);
+	nop				// This will be replaced with "bl xxx"
+					// where xxx can be any kind of tracer.
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	.global ftrace_graph_call
+ftrace_graph_call:			// ftrace_graph_caller();
+	nop				// If enabled, this will be replaced
+					// "b ftrace_graph_caller"
+#endif
+
+	mcount_exit
+ENDPROC(ftrace_caller)
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+ENTRY(ftrace_stub)
+	ret
+ENDPROC(ftrace_stub)
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+/*
+ * void ftrace_graph_caller(void)
+ *
+ * Called from _mcount() or ftrace_caller() when function_graph tracer is
+ * selected.
+ * This function w/ prepare_ftrace_return() fakes link register's value on
+ * the call stack in order to intercept instrumented function's return path
+ * and run return_to_handler() later on its exit.
+ */
+ENTRY(ftrace_graph_caller)
+	mcount_get_lr_addr	  x0	//     pointer to function's saved lr
+	mcount_get_pc		  x1	//     function's pc
+	mcount_get_parent_fp	  x2	//     parent's fp
+	bl	prepare_ftrace_return	// prepare_ftrace_return(&lr, pc, fp)
+
+	mcount_exit
+ENDPROC(ftrace_graph_caller)
+
+/*
+ * void return_to_handler(void)
+ *
+ * Run ftrace_return_to_handler() before going back to parent.
+ * @fp is checked against the value passed by ftrace_graph_caller()
+ * only when CONFIG_FUNCTION_GRAPH_FP_TEST is enabled.
+ */
+ENTRY(return_to_handler)
+	str	x0, [sp, #-16]!
+	mov	x0, x29			//     parent's fp
+	bl	ftrace_return_to_handler// addr = ftrace_return_to_hander(fp);
+	mov	x30, x0			// restore the original return address
+	ldr	x0, [sp], #16
+	ret
+END(return_to_handler)
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 39ac630d83d..bf017f4ffb4 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -60,6 +60,9 @@
 	push	x0, x1
 	.if	\el == 0
 	mrs	x21, sp_el0
+	get_thread_info tsk			// Ensure MDSCR_EL1.SS is clear,
+	ldr	x19, [tsk, #TI_FLAGS]		// since we can unmask debug
+	disable_step_tsk x19, x20		// exceptions when scheduling.
 	.else
 	add	x21, sp, #S_FRAME_SIZE
 	.endif
@@ -259,7 +262,7 @@ el1_da:
 	 * Data abort handling
 	 */
 	mrs	x0, far_el1
-	enable_dbg_if_not_stepping x2
+	enable_dbg
 	// re-enable interrupts if they were enabled in the aborted context
 	tbnz	x23, #7, 1f			// PSR_I_BIT
 	enable_irq
@@ -275,6 +278,7 @@ el1_sp_pc:
 	 * Stack or PC alignment exception handling
 	 */
 	mrs	x0, far_el1
+	enable_dbg
 	mov	x1, x25
 	mov	x2, sp
 	b	do_sp_pc_abort
@@ -282,6 +286,7 @@ el1_undef:
 	/*
 	 * Undefined instruction
 	 */
+	enable_dbg
 	mov	x0, sp
 	b	do_undefinstr
 el1_dbg:
@@ -294,10 +299,11 @@ el1_dbg:
 	mrs	x0, far_el1
 	mov	x2, sp				// struct pt_regs
 	bl	do_debug_exception
-
+	enable_dbg
 	kernel_exit 1
 el1_inv:
 	// TODO: add support for undefined instructions in kernel mode
+	enable_dbg
 	mov	x0, sp
 	mov	x1, #BAD_SYNC
 	mrs	x2, esr_el1
@@ -307,7 +313,7 @@ ENDPROC(el1_sync)
 	.align	6
 el1_irq:
 	kernel_entry 1
-	enable_dbg_if_not_stepping x0
+	enable_dbg
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
 #endif
@@ -332,8 +338,7 @@ ENDPROC(el1_irq)
 #ifdef CONFIG_PREEMPT
 el1_preempt:
 	mov	x24, lr
-1:	enable_dbg
-	bl	preempt_schedule_irq		// irq en/disable is done inside
+1:	bl	preempt_schedule_irq		// irq en/disable is done inside
 	ldr	x0, [tsk, #TI_FLAGS]		// get new tasks TI_FLAGS
 	tbnz	x0, #TIF_NEED_RESCHED, 1b	// needs rescheduling?
 	ret	x24
@@ -349,7 +354,7 @@ el0_sync:
 	lsr	x24, x25, #ESR_EL1_EC_SHIFT	// exception class
 	cmp	x24, #ESR_EL1_EC_SVC64		// SVC in 64-bit state
 	b.eq	el0_svc
-	adr	lr, ret_from_exception
+	adr	lr, ret_to_user
 	cmp	x24, #ESR_EL1_EC_DABT_EL0	// data abort in EL0
 	b.eq	el0_da
 	cmp	x24, #ESR_EL1_EC_IABT_EL0	// instruction abort in EL0
@@ -378,7 +383,7 @@ el0_sync_compat:
 	lsr	x24, x25, #ESR_EL1_EC_SHIFT	// exception class
 	cmp	x24, #ESR_EL1_EC_SVC32		// SVC in 32-bit state
 	b.eq	el0_svc_compat
-	adr	lr, ret_from_exception
+	adr	lr, ret_to_user
 	cmp	x24, #ESR_EL1_EC_DABT_EL0	// data abort in EL0
 	b.eq	el0_da
 	cmp	x24, #ESR_EL1_EC_IABT_EL0	// instruction abort in EL0
@@ -423,11 +428,8 @@ el0_da:
 	 */
 	mrs	x0, far_el1
 	bic	x0, x0, #(0xff << 56)
-	disable_step x1
-	isb
-	enable_dbg
 	// enable interrupts before calling the main handler
-	enable_irq
+	enable_dbg_and_irq
 	mov	x1, x25
 	mov	x2, sp
 	b	do_mem_abort
@@ -436,11 +438,8 @@ el0_ia:
 	 * Instruction abort handling
 	 */
 	mrs	x0, far_el1
-	disable_step x1
-	isb
-	enable_dbg
 	// enable interrupts before calling the main handler
-	enable_irq
+	enable_dbg_and_irq
 	orr	x1, x25, #1 << 24		// use reserved ISS bit for instruction aborts
 	mov	x2, sp
 	b	do_mem_abort
@@ -448,6 +447,7 @@ el0_fpsimd_acc:
 	/*
 	 * Floating Point or Advanced SIMD access
 	 */
+	enable_dbg
 	mov	x0, x25
 	mov	x1, sp
 	b	do_fpsimd_acc
@@ -455,6 +455,7 @@ el0_fpsimd_exc:
 	/*
 	 * Floating Point or Advanced SIMD exception
 	 */
+	enable_dbg
 	mov	x0, x25
 	mov	x1, sp
 	b	do_fpsimd_exc
@@ -463,11 +464,8 @@ el0_sp_pc:
 	 * Stack or PC alignment exception handling
 	 */
 	mrs	x0, far_el1
-	disable_step x1
-	isb
-	enable_dbg
 	// enable interrupts before calling the main handler
-	enable_irq
+	enable_dbg_and_irq
 	mov	x1, x25
 	mov	x2, sp
 	b	do_sp_pc_abort
@@ -475,9 +473,9 @@ el0_undef:
 	/*
 	 * Undefined instruction
 	 */
-	mov	x0, sp
 	// enable interrupts before calling the main handler
-	enable_irq
+	enable_dbg_and_irq
+	mov	x0, sp
 	b	do_undefinstr
 el0_dbg:
 	/*
@@ -485,11 +483,13 @@ el0_dbg:
 	 */
 	tbnz	x24, #0, el0_inv		// EL0 only
 	mrs	x0, far_el1
-	disable_step x1
 	mov	x1, x25
 	mov	x2, sp
-	b	do_debug_exception
+	bl	do_debug_exception
+	enable_dbg
+	b	ret_to_user
 el0_inv:
+	enable_dbg
 	mov	x0, sp
 	mov	x1, #BAD_SYNC
 	mrs	x2, esr_el1
@@ -500,15 +500,12 @@ ENDPROC(el0_sync)
 el0_irq:
 	kernel_entry 0
 el0_irq_naked:
-	disable_step x1
-	isb
 	enable_dbg
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
 #endif
 
 	irq_handler
-	get_thread_info tsk
 
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_on
@@ -517,14 +514,6 @@ el0_irq_naked:
 ENDPROC(el0_irq)
 
 /*
- * This is the return code to user mode for abort handlers
- */
-ret_from_exception:
-	get_thread_info tsk
-	b	ret_to_user
-ENDPROC(ret_from_exception)
-
-/*
  * Register switch for AArch64. The callee-saved registers need to be saved
  * and restored. On entry:
  *   x0 = previous task_struct (must be preserved across the switch)
@@ -563,10 +552,7 @@ ret_fast_syscall:
 	ldr	x1, [tsk, #TI_FLAGS]
 	and	x2, x1, #_TIF_WORK_MASK
 	cbnz	x2, fast_work_pending
-	tbz	x1, #TIF_SINGLESTEP, fast_exit
-	disable_dbg
-	enable_step x2
-fast_exit:
+	enable_step_tsk x1, x2
 	kernel_exit 0, ret = 1
 
 /*
@@ -576,7 +562,7 @@ fast_work_pending:
 	str	x0, [sp, #S_X0]			// returned x0
 work_pending:
 	tbnz	x1, #TIF_NEED_RESCHED, work_resched
-	/* TIF_SIGPENDING or TIF_NOTIFY_RESUME case */
+	/* TIF_SIGPENDING, TIF_NOTIFY_RESUME or TIF_FOREIGN_FPSTATE case */
 	ldr	x2, [sp, #S_PSTATE]
 	mov	x0, sp				// 'regs'
 	tst	x2, #PSR_MODE_MASK		// user mode regs?
@@ -585,7 +571,6 @@ work_pending:
 	bl	do_notify_resume
 	b	ret_to_user
 work_resched:
-	enable_dbg
 	bl	schedule
 
 /*
@@ -596,9 +581,7 @@ ret_to_user:
 	ldr	x1, [tsk, #TI_FLAGS]
 	and	x2, x1, #_TIF_WORK_MASK
 	cbnz	x2, work_pending
-	tbz	x1, #TIF_SINGLESTEP, no_work_pending
-	disable_dbg
-	enable_step x2
+	enable_step_tsk x1, x2
 no_work_pending:
 	kernel_exit 0, ret = 0
 ENDPROC(ret_to_user)
@@ -625,14 +608,11 @@ el0_svc:
 	mov	sc_nr, #__NR_syscalls
 el0_svc_naked:					// compat entry point
 	stp	x0, scno, [sp, #S_ORIG_X0]	// save the original x0 and syscall number
-	disable_step x16
-	isb
-	enable_dbg
-	enable_irq
+	enable_dbg_and_irq
 
-	get_thread_info tsk
-	ldr	x16, [tsk, #TI_FLAGS]		// check for syscall tracing
-	tbnz	x16, #TIF_SYSCALL_TRACE, __sys_trace // are we tracing syscalls?
+	ldr	x16, [tsk, #TI_FLAGS]		// check for syscall hooks
+	tst	x16, #_TIF_SYSCALL_WORK
+	b.ne	__sys_trace
 	adr	lr, ret_fast_syscall		// return address
 	cmp     scno, sc_nr                     // check upper syscall limit
 	b.hs	ni_sys
@@ -648,9 +628,8 @@ ENDPROC(el0_svc)
 	 * switches, and waiting for our parent to respond.
 	 */
 __sys_trace:
-	mov	x1, sp
-	mov	w0, #0				// trace entry
-	bl	syscall_trace
+	mov	x0, sp
+	bl	syscall_trace_enter
 	adr	lr, __sys_trace_return		// return address
 	uxtw	scno, w0			// syscall number (possibly new)
 	mov	x1, sp				// pointer to regs
@@ -665,9 +644,8 @@ __sys_trace:
 
 __sys_trace_return:
 	str	x0, [sp]			// save returned x0
-	mov	x1, sp
-	mov	w0, #1				// trace exit
-	bl	syscall_trace
+	mov	x0, sp
+	bl	syscall_trace_exit
 	b	ret_to_user
 
 /*
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 4aef42a04bd..ad8aebb1cde 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -35,6 +35,60 @@
 #define FPEXC_IDF	(1 << 7)
 
 /*
+ * In order to reduce the number of times the FPSIMD state is needlessly saved
+ * and restored, we need to keep track of two things:
+ * (a) for each task, we need to remember which CPU was the last one to have
+ *     the task's FPSIMD state loaded into its FPSIMD registers;
+ * (b) for each CPU, we need to remember which task's userland FPSIMD state has
+ *     been loaded into its FPSIMD registers most recently, or whether it has
+ *     been used to perform kernel mode NEON in the meantime.
+ *
+ * For (a), we add a 'cpu' field to struct fpsimd_state, which gets updated to
+ * the id of the current CPU everytime the state is loaded onto a CPU. For (b),
+ * we add the per-cpu variable 'fpsimd_last_state' (below), which contains the
+ * address of the userland FPSIMD state of the task that was loaded onto the CPU
+ * the most recently, or NULL if kernel mode NEON has been performed after that.
+ *
+ * With this in place, we no longer have to restore the next FPSIMD state right
+ * when switching between tasks. Instead, we can defer this check to userland
+ * resume, at which time we verify whether the CPU's fpsimd_last_state and the
+ * task's fpsimd_state.cpu are still mutually in sync. If this is the case, we
+ * can omit the FPSIMD restore.
+ *
+ * As an optimization, we use the thread_info flag TIF_FOREIGN_FPSTATE to
+ * indicate whether or not the userland FPSIMD state of the current task is
+ * present in the registers. The flag is set unless the FPSIMD registers of this
+ * CPU currently contain the most recent userland FPSIMD state of the current
+ * task.
+ *
+ * For a certain task, the sequence may look something like this:
+ * - the task gets scheduled in; if both the task's fpsimd_state.cpu field
+ *   contains the id of the current CPU, and the CPU's fpsimd_last_state per-cpu
+ *   variable points to the task's fpsimd_state, the TIF_FOREIGN_FPSTATE flag is
+ *   cleared, otherwise it is set;
+ *
+ * - the task returns to userland; if TIF_FOREIGN_FPSTATE is set, the task's
+ *   userland FPSIMD state is copied from memory to the registers, the task's
+ *   fpsimd_state.cpu field is set to the id of the current CPU, the current
+ *   CPU's fpsimd_last_state pointer is set to this task's fpsimd_state and the
+ *   TIF_FOREIGN_FPSTATE flag is cleared;
+ *
+ * - the task executes an ordinary syscall; upon return to userland, the
+ *   TIF_FOREIGN_FPSTATE flag will still be cleared, so no FPSIMD state is
+ *   restored;
+ *
+ * - the task executes a syscall which executes some NEON instructions; this is
+ *   preceded by a call to kernel_neon_begin(), which copies the task's FPSIMD
+ *   register contents to memory, clears the fpsimd_last_state per-cpu variable
+ *   and sets the TIF_FOREIGN_FPSTATE flag;
+ *
+ * - the task gets preempted after kernel_neon_end() is called; as we have not
+ *   returned from the 2nd syscall yet, TIF_FOREIGN_FPSTATE is still set so
+ *   whatever is in the FPSIMD registers is not saved to memory, but discarded.
+ */
+static DEFINE_PER_CPU(struct fpsimd_state *, fpsimd_last_state);
+
+/*
  * Trapped FP/ASIMD access.
  */
 void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs)
@@ -72,43 +126,137 @@ void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs)
 
 void fpsimd_thread_switch(struct task_struct *next)
 {
-	/* check if not kernel threads */
-	if (current->mm)
+	/*
+	 * Save the current FPSIMD state to memory, but only if whatever is in
+	 * the registers is in fact the most recent userland FPSIMD state of
+	 * 'current'.
+	 */
+	if (current->mm && !test_thread_flag(TIF_FOREIGN_FPSTATE))
 		fpsimd_save_state(&current->thread.fpsimd_state);
-	if (next->mm)
-		fpsimd_load_state(&next->thread.fpsimd_state);
+
+	if (next->mm) {
+		/*
+		 * If we are switching to a task whose most recent userland
+		 * FPSIMD state is already in the registers of *this* cpu,
+		 * we can skip loading the state from memory. Otherwise, set
+		 * the TIF_FOREIGN_FPSTATE flag so the state will be loaded
+		 * upon the next return to userland.
+		 */
+		struct fpsimd_state *st = &next->thread.fpsimd_state;
+
+		if (__this_cpu_read(fpsimd_last_state) == st
+		    && st->cpu == smp_processor_id())
+			clear_ti_thread_flag(task_thread_info(next),
+					     TIF_FOREIGN_FPSTATE);
+		else
+			set_ti_thread_flag(task_thread_info(next),
+					   TIF_FOREIGN_FPSTATE);
+	}
 }
 
 void fpsimd_flush_thread(void)
 {
-	preempt_disable();
 	memset(&current->thread.fpsimd_state, 0, sizeof(struct fpsimd_state));
-	fpsimd_load_state(&current->thread.fpsimd_state);
+	set_thread_flag(TIF_FOREIGN_FPSTATE);
+}
+
+/*
+ * Save the userland FPSIMD state of 'current' to memory, but only if the state
+ * currently held in the registers does in fact belong to 'current'
+ */
+void fpsimd_preserve_current_state(void)
+{
+	preempt_disable();
+	if (!test_thread_flag(TIF_FOREIGN_FPSTATE))
+		fpsimd_save_state(&current->thread.fpsimd_state);
+	preempt_enable();
+}
+
+/*
+ * Load the userland FPSIMD state of 'current' from memory, but only if the
+ * FPSIMD state already held in the registers is /not/ the most recent FPSIMD
+ * state of 'current'
+ */
+void fpsimd_restore_current_state(void)
+{
+	preempt_disable();
+	if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {
+		struct fpsimd_state *st = &current->thread.fpsimd_state;
+
+		fpsimd_load_state(st);
+		this_cpu_write(fpsimd_last_state, st);
+		st->cpu = smp_processor_id();
+	}
+	preempt_enable();
+}
+
+/*
+ * Load an updated userland FPSIMD state for 'current' from memory and set the
+ * flag that indicates that the FPSIMD register contents are the most recent
+ * FPSIMD state of 'current'
+ */
+void fpsimd_update_current_state(struct fpsimd_state *state)
+{
+	preempt_disable();
+	fpsimd_load_state(state);
+	if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {
+		struct fpsimd_state *st = &current->thread.fpsimd_state;
+
+		this_cpu_write(fpsimd_last_state, st);
+		st->cpu = smp_processor_id();
+	}
 	preempt_enable();
 }
 
+/*
+ * Invalidate live CPU copies of task t's FPSIMD state
+ */
+void fpsimd_flush_task_state(struct task_struct *t)
+{
+	t->thread.fpsimd_state.cpu = NR_CPUS;
+}
+
 #ifdef CONFIG_KERNEL_MODE_NEON
 
+static DEFINE_PER_CPU(struct fpsimd_partial_state, hardirq_fpsimdstate);
+static DEFINE_PER_CPU(struct fpsimd_partial_state, softirq_fpsimdstate);
+
 /*
  * Kernel-side NEON support functions
  */
-void kernel_neon_begin(void)
+void kernel_neon_begin_partial(u32 num_regs)
 {
-	/* Avoid using the NEON in interrupt context */
-	BUG_ON(in_interrupt());
-	preempt_disable();
+	if (in_interrupt()) {
+		struct fpsimd_partial_state *s = this_cpu_ptr(
+			in_irq() ? &hardirq_fpsimdstate : &softirq_fpsimdstate);
 
-	if (current->mm)
-		fpsimd_save_state(&current->thread.fpsimd_state);
+		BUG_ON(num_regs > 32);
+		fpsimd_save_partial_state(s, roundup(num_regs, 2));
+	} else {
+		/*
+		 * Save the userland FPSIMD state if we have one and if we
+		 * haven't done so already. Clear fpsimd_last_state to indicate
+		 * that there is no longer userland FPSIMD state in the
+		 * registers.
+		 */
+		preempt_disable();
+		if (current->mm &&
+		    !test_and_set_thread_flag(TIF_FOREIGN_FPSTATE))
+			fpsimd_save_state(&current->thread.fpsimd_state);
+		this_cpu_write(fpsimd_last_state, NULL);
+	}
 }
-EXPORT_SYMBOL(kernel_neon_begin);
+EXPORT_SYMBOL(kernel_neon_begin_partial);
 
 void kernel_neon_end(void)
 {
-	if (current->mm)
-		fpsimd_load_state(&current->thread.fpsimd_state);
-
-	preempt_enable();
+	if (in_interrupt()) {
+		struct fpsimd_partial_state *s = this_cpu_ptr(
+			in_irq() ? &hardirq_fpsimdstate : &softirq_fpsimdstate);
+		fpsimd_load_partial_state(s);
+	} else {
+		preempt_enable();
+	}
 }
 EXPORT_SYMBOL(kernel_neon_end);
 
@@ -120,12 +268,12 @@ static int fpsimd_cpu_pm_notifier(struct notifier_block *self,
 {
 	switch (cmd) {
 	case CPU_PM_ENTER:
-		if (current->mm)
+		if (current->mm && !test_thread_flag(TIF_FOREIGN_FPSTATE))
 			fpsimd_save_state(&current->thread.fpsimd_state);
 		break;
 	case CPU_PM_EXIT:
 		if (current->mm)
-			fpsimd_load_state(&current->thread.fpsimd_state);
+			set_thread_flag(TIF_FOREIGN_FPSTATE);
 		break;
 	case CPU_PM_ENTER_FAILED:
 	default:
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
new file mode 100644
index 00000000000..7924d73b647
--- /dev/null
+++ b/arch/arm64/kernel/ftrace.c
@@ -0,0 +1,176 @@
+/*
+ * arch/arm64/kernel/ftrace.c
+ *
+ * Copyright (C) 2013 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.
+ */
+
+#include <linux/ftrace.h>
+#include <linux/swab.h>
+#include <linux/uaccess.h>
+
+#include <asm/cacheflush.h>
+#include <asm/ftrace.h>
+#include <asm/insn.h>
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+/*
+ * Replace a single instruction, which may be a branch or NOP.
+ * If @validate == true, a replaced instruction is checked against 'old'.
+ */
+static int ftrace_modify_code(unsigned long pc, u32 old, u32 new,
+			      bool validate)
+{
+	u32 replaced;
+
+	/*
+	 * Note:
+	 * Due to modules and __init, code can disappear and change,
+	 * we need to protect against faulting as well as code changing.
+	 * We do this by aarch64_insn_*() which use the probe_kernel_*().
+	 *
+	 * No lock is held here because all the modifications are run
+	 * through stop_machine().
+	 */
+	if (validate) {
+		if (aarch64_insn_read((void *)pc, &replaced))
+			return -EFAULT;
+
+		if (replaced != old)
+			return -EINVAL;
+	}
+	if (aarch64_insn_patch_text_nosync((void *)pc, new))
+		return -EPERM;
+
+	return 0;
+}
+
+/*
+ * Replace tracer function in ftrace_caller()
+ */
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+	unsigned long pc;
+	u32 new;
+
+	pc = (unsigned long)&ftrace_call;
+	new = aarch64_insn_gen_branch_imm(pc, (unsigned long)func, true);
+
+	return ftrace_modify_code(pc, 0, new, false);
+}
+
+/*
+ * Turn on the call to ftrace_caller() in instrumented function
+ */
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned long pc = rec->ip;
+	u32 old, new;
+
+	old = aarch64_insn_gen_nop();
+	new = aarch64_insn_gen_branch_imm(pc, addr, true);
+
+	return ftrace_modify_code(pc, old, new, true);
+}
+
+/*
+ * Turn off the call to ftrace_caller() in instrumented function
+ */
+int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
+		    unsigned long addr)
+{
+	unsigned long pc = rec->ip;
+	u32 old, new;
+
+	old = aarch64_insn_gen_branch_imm(pc, addr, true);
+	new = aarch64_insn_gen_nop();
+
+	return ftrace_modify_code(pc, old, new, true);
+}
+
+int __init ftrace_dyn_arch_init(void)
+{
+	return 0;
+}
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+/*
+ * function_graph tracer expects ftrace_return_to_handler() to be called
+ * on the way back to parent. For this purpose, this function is called
+ * in _mcount() or ftrace_caller() to replace return address (*parent) on
+ * the call stack to return_to_handler.
+ *
+ * Note that @frame_pointer is used only for sanity check later.
+ */
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
+			   unsigned long frame_pointer)
+{
+	unsigned long return_hooker = (unsigned long)&return_to_handler;
+	unsigned long old;
+	struct ftrace_graph_ent trace;
+	int err;
+
+	if (unlikely(atomic_read(&current->tracing_graph_pause)))
+		return;
+
+	/*
+	 * Note:
+	 * No protection against faulting at *parent, which may be seen
+	 * on other archs. It's unlikely on AArch64.
+	 */
+	old = *parent;
+	*parent = return_hooker;
+
+	trace.func = self_addr;
+	trace.depth = current->curr_ret_stack + 1;
+
+	/* Only trace if the calling function expects to */
+	if (!ftrace_graph_entry(&trace)) {
+		*parent = old;
+		return;
+	}
+
+	err = ftrace_push_return_trace(old, self_addr, &trace.depth,
+				       frame_pointer);
+	if (err == -EBUSY) {
+		*parent = old;
+		return;
+	}
+}
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+/*
+ * Turn on/off the call to ftrace_graph_caller() in ftrace_caller()
+ * depending on @enable.
+ */
+static int ftrace_modify_graph_caller(bool enable)
+{
+	unsigned long pc = (unsigned long)&ftrace_graph_call;
+	u32 branch, nop;
+
+	branch = aarch64_insn_gen_branch_imm(pc,
+			(unsigned long)ftrace_graph_caller, false);
+	nop = aarch64_insn_gen_nop();
+
+	if (enable)
+		return ftrace_modify_code(pc, nop, branch, true);
+	else
+		return ftrace_modify_code(pc, branch, nop, true);
+}
+
+int ftrace_enable_ftrace_graph_caller(void)
+{
+	return ftrace_modify_graph_caller(true);
+}
+
+int ftrace_disable_ftrace_graph_caller(void)
+{
+	return ftrace_modify_graph_caller(false);
+}
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 738291b5be2..a96d3a6a63f 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -342,11 +342,9 @@ ENTRY(set_cpu_boot_mode_flag)
 	cmp	w20, #BOOT_CPU_MODE_EL2
 	b.ne	1f
 	add	x1, x1, #4
-1:	dc	cvac, x1			// Clean potentially dirty cache line
-	dsb	sy
-	str	w20, [x1]			// This CPU has booted in EL1
-	dc	civac, x1			// Clean&invalidate potentially stale cache line
-	dsb	sy
+1:	str	w20, [x1]			// This CPU has booted in EL1
+	dmb	sy
+	dc	ivac, x1			// Invalidate potentially stale cache line
 	ret
 ENDPROC(set_cpu_boot_mode_flag)
 
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index bee78975780..df1cf15377b 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -20,6 +20,7 @@
 
 #define pr_fmt(fmt) "hw-breakpoint: " fmt
 
+#include <linux/compat.h>
 #include <linux/cpu_pm.h>
 #include <linux/errno.h>
 #include <linux/hw_breakpoint.h>
@@ -27,7 +28,6 @@
 #include <linux/ptrace.h>
 #include <linux/smp.h>
 
-#include <asm/compat.h>
 #include <asm/current.h>
 #include <asm/debug-monitors.h>
 #include <asm/hw_breakpoint.h>
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 6391485f342..43b7c34f92c 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -20,6 +20,7 @@
 
 #include <stdarg.h>
 
+#include <linux/compat.h>
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
@@ -113,32 +114,62 @@ void arch_cpu_idle_dead(void)
 }
 #endif
 
+/*
+ * Called by kexec, immediately prior to machine_kexec().
+ *
+ * This must completely disable all secondary CPUs; simply causing those CPUs
+ * to execute e.g. a RAM-based pin loop is not sufficient. This allows the
+ * kexec'd kernel to use any and all RAM as it sees fit, without having to
+ * avoid any code or data used by any SW CPU pin loop. The CPU hotplug
+ * functionality embodied in disable_nonboot_cpus() to achieve this.
+ */
 void machine_shutdown(void)
 {
-#ifdef CONFIG_SMP
-	smp_send_stop();
-#endif
+	disable_nonboot_cpus();
 }
 
+/*
+ * Halting simply requires that the secondary CPUs stop performing any
+ * activity (executing tasks, handling interrupts). smp_send_stop()
+ * achieves this.
+ */
 void machine_halt(void)
 {
-	machine_shutdown();
+	local_irq_disable();
+	smp_send_stop();
 	while (1);
 }
 
+/*
+ * Power-off simply requires that the secondary CPUs stop performing any
+ * activity (executing tasks, handling interrupts). smp_send_stop()
+ * achieves this. When the system power is turned off, it will take all CPUs
+ * with it.
+ */
 void machine_power_off(void)
 {
-	machine_shutdown();
+	local_irq_disable();
+	smp_send_stop();
 	if (pm_power_off)
 		pm_power_off();
 }
 
+/*
+ * Restart requires that the secondary CPUs stop performing any activity
+ * while the primary CPU resets the system. Systems with a single CPU can
+ * use soft_restart() as their machine descriptor's .restart hook, since that
+ * will cause the only available CPU to reset. Systems with multiple CPUs must
+ * provide a HW restart implementation, to ensure that all CPUs reset at once.
+ * This is required so that any code running after reset on the primary CPU
+ * doesn't have to co-ordinate with other CPUs to ensure they aren't still
+ * executing pre-reset code, and using RAM that the primary CPU's code wishes
+ * to use. Implementing such co-ordination would be essentially impossible.
+ */
 void machine_restart(char *cmd)
 {
-	machine_shutdown();
-
 	/* Disable interrupts first */
 	local_irq_disable();
+	smp_send_stop();
 
 	/* Now call the architecture specific reboot code. */
 	if (arm_pm_restart)
@@ -205,7 +236,7 @@ void release_thread(struct task_struct *dead_task)
 
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
-	fpsimd_save_state(&current->thread.fpsimd_state);
+	fpsimd_preserve_current_state();
 	*dst = *src;
 	return 0;
 }
@@ -300,7 +331,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
 	 * Complete any pending TLB or cache maintenance on this CPU in case
 	 * the thread migrates to a different CPU.
 	 */
-	dsb();
+	dsb(ish);
 
 	/* the actual thread switch */
 	last = cpu_switch_to(prev, next);
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 6a8928bba03..3e926b9c064 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -19,6 +19,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/compat.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
@@ -41,6 +42,9 @@
 #include <asm/traps.h>
 #include <asm/system_misc.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
 /*
  * TODO: does not yet catch signals sent when the child dies.
  * in exit.c or in signal.c.
@@ -517,6 +521,7 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset,
 		return ret;
 
 	target->thread.fpsimd_state.user_fpsimd = newstate;
+	fpsimd_flush_task_state(target);
 	return ret;
 }
 
@@ -764,6 +769,7 @@ static int compat_vfp_set(struct task_struct *target,
 		uregs->fpcr = fpscr & VFP_FPSCR_CTRL_MASK;
 	}
 
+	fpsimd_flush_task_state(target);
 	return ret;
 }
 
@@ -1058,35 +1064,49 @@ long arch_ptrace(struct task_struct *child, long request,
 	return ptrace_request(child, request, addr, data);
 }
 
-asmlinkage int syscall_trace(int dir, struct pt_regs *regs)
+enum ptrace_syscall_dir {
+	PTRACE_SYSCALL_ENTER = 0,
+	PTRACE_SYSCALL_EXIT,
+};
+
+static void tracehook_report_syscall(struct pt_regs *regs,
+				     enum ptrace_syscall_dir dir)
 {
+	int regno;
 	unsigned long saved_reg;
 
-	if (!test_thread_flag(TIF_SYSCALL_TRACE))
-		return regs->syscallno;
-
-	if (is_compat_task()) {
-		/* AArch32 uses ip (r12) for scratch */
-		saved_reg = regs->regs[12];
-		regs->regs[12] = dir;
-	} else {
-		/*
-		 * Save X7. X7 is used to denote syscall entry/exit:
-		 *   X7 = 0 -> entry, = 1 -> exit
-		 */
-		saved_reg = regs->regs[7];
-		regs->regs[7] = dir;
-	}
+	/*
+	 * A scratch register (ip(r12) on AArch32, x7 on AArch64) is
+	 * used to denote syscall entry/exit:
+	 */
+	regno = (is_compat_task() ? 12 : 7);
+	saved_reg = regs->regs[regno];
+	regs->regs[regno] = dir;
 
-	if (dir)
+	if (dir == PTRACE_SYSCALL_EXIT)
 		tracehook_report_syscall_exit(regs, 0);
 	else if (tracehook_report_syscall_entry(regs))
 		regs->syscallno = ~0UL;
 
-	if (is_compat_task())
-		regs->regs[12] = saved_reg;
-	else
-		regs->regs[7] = saved_reg;
+	regs->regs[regno] = saved_reg;
+}
+
+asmlinkage int syscall_trace_enter(struct pt_regs *regs)
+{
+	if (test_thread_flag(TIF_SYSCALL_TRACE))
+		tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER);
+
+	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+		trace_sys_enter(regs, regs->syscallno);
 
 	return regs->syscallno;
 }
+
+asmlinkage void syscall_trace_exit(struct pt_regs *regs)
+{
+	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+		trace_sys_exit(regs, regs_return_value(regs));
+
+	if (test_thread_flag(TIF_SYSCALL_TRACE))
+		tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT);
+}
diff --git a/arch/arm64/kernel/return_address.c b/arch/arm64/kernel/return_address.c
new file mode 100644
index 00000000000..89102a6ffad
--- /dev/null
+++ b/arch/arm64/kernel/return_address.c
@@ -0,0 +1,55 @@
+/*
+ * arch/arm64/kernel/return_address.c
+ *
+ * Copyright (C) 2013 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.
+ */
+
+#include <linux/export.h>
+#include <linux/ftrace.h>
+
+#include <asm/stacktrace.h>
+
+struct return_address_data {
+	unsigned int level;
+	void *addr;
+};
+
+static int save_return_addr(struct stackframe *frame, void *d)
+{
+	struct return_address_data *data = d;
+
+	if (!data->level) {
+		data->addr = (void *)frame->pc;
+		return 1;
+	} else {
+		--data->level;
+		return 0;
+	}
+}
+
+void *return_address(unsigned int level)
+{
+	struct return_address_data data;
+	struct stackframe frame;
+	register unsigned long current_sp asm ("sp");
+
+	data.level = level + 2;
+	data.addr = NULL;
+
+	frame.fp = (unsigned long)__builtin_frame_address(0);
+	frame.sp = current_sp;
+	frame.pc = (unsigned long)return_address; /* dummy */
+
+	walk_stackframe(&frame, save_return_addr, &data);
+
+	if (!data.level)
+		return data.addr;
+	else
+		return NULL;
+}
+EXPORT_SYMBOL_GPL(return_address);
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index e578171b22f..46d1125571f 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -25,6 +25,7 @@
 #include <linux/utsname.h>
 #include <linux/initrd.h>
 #include <linux/console.h>
+#include <linux/cache.h>
 #include <linux/bootmem.h>
 #include <linux/seq_file.h>
 #include <linux/screen_info.h>
@@ -200,6 +201,8 @@ static void __init setup_processor(void)
 {
 	struct cpu_info *cpu_info;
 	u64 features, block;
+	u32 cwg;
+	int cls;
 
 	cpu_info = lookup_processor_type(read_cpuid_id());
 	if (!cpu_info) {
@@ -217,6 +220,18 @@ static void __init setup_processor(void)
 	elf_hwcap = 0;
 
 	/*
+	 * Check for sane CTR_EL0.CWG value.
+	 */
+	cwg = cache_type_cwg();
+	cls = cache_line_size();
+	if (!cwg)
+		pr_warn("No Cache Writeback Granule information, assuming cache line size %d\n",
+			cls);
+	if (L1_CACHE_BYTES < cls)
+		pr_warn("L1_CACHE_BYTES smaller than the Cache Writeback Granule (%d < %d)\n",
+			L1_CACHE_BYTES, cls);
+
+	/*
 	 * ID_AA64ISAR0_EL1 contains 4-bit wide signed feature blocks.
 	 * The blocks we test below represent incremental functionality
 	 * for non-negative values. Negative values are reserved.
@@ -363,7 +378,6 @@ void __init setup_arch(char **cmdline_p)
 
 	*cmdline_p = boot_command_line;
 
-	init_mem_pgprot();
 	early_ioremap_init();
 
 	parse_early_param();
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 890a591f75d..6357b9c6c90 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -17,6 +17,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/compat.h>
 #include <linux/errno.h>
 #include <linux/signal.h>
 #include <linux/personality.h>
@@ -25,7 +26,6 @@
 #include <linux/tracehook.h>
 #include <linux/ratelimit.h>
 
-#include <asm/compat.h>
 #include <asm/debug-monitors.h>
 #include <asm/elf.h>
 #include <asm/cacheflush.h>
@@ -51,7 +51,7 @@ static int preserve_fpsimd_context(struct fpsimd_context __user *ctx)
 	int err;
 
 	/* dump the hardware registers to the fpsimd_state structure */
-	fpsimd_save_state(fpsimd);
+	fpsimd_preserve_current_state();
 
 	/* copy the FP and status/control registers */
 	err = __copy_to_user(ctx->vregs, fpsimd->vregs, sizeof(fpsimd->vregs));
@@ -86,11 +86,8 @@ static int restore_fpsimd_context(struct fpsimd_context __user *ctx)
 	__get_user_error(fpsimd.fpcr, &ctx->fpcr, err);
 
 	/* load the hardware registers from the fpsimd_state structure */
-	if (!err) {
-		preempt_disable();
-		fpsimd_load_state(&fpsimd);
-		preempt_enable();
-	}
+	if (!err)
+		fpsimd_update_current_state(&fpsimd);
 
 	return err ? -EFAULT : 0;
 }
@@ -100,8 +97,7 @@ static int restore_sigframe(struct pt_regs *regs,
 {
 	sigset_t set;
 	int i, err;
-	struct aux_context __user *aux =
-		(struct aux_context __user *)sf->uc.uc_mcontext.__reserved;
+	void *aux = sf->uc.uc_mcontext.__reserved;
 
 	err = __copy_from_user(&set, &sf->uc.uc_sigmask, sizeof(set));
 	if (err == 0)
@@ -121,8 +117,11 @@ static int restore_sigframe(struct pt_regs *regs,
 
 	err |= !valid_user_regs(&regs->user_regs);
 
-	if (err == 0)
-		err |= restore_fpsimd_context(&aux->fpsimd);
+	if (err == 0) {
+		struct fpsimd_context *fpsimd_ctx =
+			container_of(aux, struct fpsimd_context, head);
+		err |= restore_fpsimd_context(fpsimd_ctx);
+	}
 
 	return err;
 }
@@ -167,8 +166,8 @@ static int setup_sigframe(struct rt_sigframe __user *sf,
 			  struct pt_regs *regs, sigset_t *set)
 {
 	int i, err = 0;
-	struct aux_context __user *aux =
-		(struct aux_context __user *)sf->uc.uc_mcontext.__reserved;
+	void *aux = sf->uc.uc_mcontext.__reserved;
+	struct _aarch64_ctx *end;
 
 	/* set up the stack frame for unwinding */
 	__put_user_error(regs->regs[29], &sf->fp, err);
@@ -185,12 +184,27 @@ static int setup_sigframe(struct rt_sigframe __user *sf,
 
 	err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(*set));
 
-	if (err == 0)
-		err |= preserve_fpsimd_context(&aux->fpsimd);
+	if (err == 0) {
+		struct fpsimd_context *fpsimd_ctx =
+			container_of(aux, struct fpsimd_context, head);
+		err |= preserve_fpsimd_context(fpsimd_ctx);
+		aux += sizeof(*fpsimd_ctx);
+	}
+
+	/* fault information, if valid */
+	if (current->thread.fault_code) {
+		struct esr_context *esr_ctx =
+			container_of(aux, struct esr_context, head);
+		__put_user_error(ESR_MAGIC, &esr_ctx->head.magic, err);
+		__put_user_error(sizeof(*esr_ctx), &esr_ctx->head.size, err);
+		__put_user_error(current->thread.fault_code, &esr_ctx->esr, err);
+		aux += sizeof(*esr_ctx);
+	}
 
 	/* set the "end" magic */
-	__put_user_error(0, &aux->end.magic, err);
-	__put_user_error(0, &aux->end.size, err);
+	end = aux;
+	__put_user_error(0, &end->magic, err);
+	__put_user_error(0, &end->size, err);
 
 	return err;
 }
@@ -416,4 +430,8 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
 		clear_thread_flag(TIF_NOTIFY_RESUME);
 		tracehook_notify_resume(regs);
 	}
+
+	if (thread_flags & _TIF_FOREIGN_FPSTATE)
+		fpsimd_restore_current_state();
+
 }
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index b3fc9f5ec6d..3491c638f17 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -23,6 +23,7 @@
 #include <linux/syscalls.h>
 #include <linux/ratelimit.h>
 
+#include <asm/esr.h>
 #include <asm/fpsimd.h>
 #include <asm/signal32.h>
 #include <asm/uaccess.h>
@@ -81,6 +82,8 @@ struct compat_vfp_sigframe {
 #define VFP_MAGIC		0x56465001
 #define VFP_STORAGE_SIZE	sizeof(struct compat_vfp_sigframe)
 
+#define FSR_WRITE_SHIFT		(11)
+
 struct compat_aux_sigframe {
 	struct compat_vfp_sigframe	vfp;
 
@@ -219,7 +222,7 @@ static int compat_preserve_vfp_context(struct compat_vfp_sigframe __user *frame)
 	 * Note that this also saves V16-31, which aren't visible
 	 * in AArch32.
 	 */
-	fpsimd_save_state(fpsimd);
+	fpsimd_preserve_current_state();
 
 	/* Place structure header on the stack */
 	__put_user_error(magic, &frame->magic, err);
@@ -282,11 +285,8 @@ static int compat_restore_vfp_context(struct compat_vfp_sigframe __user *frame)
 	 * We don't need to touch the exception register, so
 	 * reload the hardware state.
 	 */
-	if (!err) {
-		preempt_disable();
-		fpsimd_load_state(&fpsimd);
-		preempt_enable();
-	}
+	if (!err)
+		fpsimd_update_current_state(&fpsimd);
 
 	return err ? -EFAULT : 0;
 }
@@ -500,7 +500,9 @@ static int compat_setup_sigframe(struct compat_sigframe __user *sf,
 	__put_user_error(regs->pstate, &sf->uc.uc_mcontext.arm_cpsr, err);
 
 	__put_user_error((compat_ulong_t)0, &sf->uc.uc_mcontext.trap_no, err);
-	__put_user_error((compat_ulong_t)0, &sf->uc.uc_mcontext.error_code, err);
+	/* set the compat FSR WnR */
+	__put_user_error(!!(current->thread.fault_code & ESR_EL1_WRITE) <<
+			 FSR_WRITE_SHIFT, &sf->uc.uc_mcontext.error_code, err);
 	__put_user_error(current->thread.fault_address, &sf->uc.uc_mcontext.fault_address, err);
 	__put_user_error(set->sig[0], &sf->uc.uc_mcontext.oldmask, err);
 
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index c3cb160edc6..40f38f46c8e 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -35,6 +35,7 @@
 #include <linux/clockchips.h>
 #include <linux/completion.h>
 #include <linux/of.h>
+#include <linux/irq_work.h>
 
 #include <asm/atomic.h>
 #include <asm/cacheflush.h>
@@ -62,6 +63,7 @@ enum ipi_msg_type {
 	IPI_CALL_FUNC_SINGLE,
 	IPI_CPU_STOP,
 	IPI_TIMER,
+	IPI_IRQ_WORK,
 };
 
 /*
@@ -477,6 +479,14 @@ void arch_send_call_function_single_ipi(int cpu)
 	smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
 }
 
+#ifdef CONFIG_IRQ_WORK
+void arch_irq_work_raise(void)
+{
+	if (smp_cross_call)
+		smp_cross_call(cpumask_of(smp_processor_id()), IPI_IRQ_WORK);
+}
+#endif
+
 static const char *ipi_types[NR_IPI] = {
 #define S(x,s)	[x - IPI_RESCHEDULE] = s
 	S(IPI_RESCHEDULE, "Rescheduling interrupts"),
@@ -484,6 +494,7 @@ static const char *ipi_types[NR_IPI] = {
 	S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"),
 	S(IPI_CPU_STOP, "CPU stop interrupts"),
 	S(IPI_TIMER, "Timer broadcast interrupts"),
+	S(IPI_IRQ_WORK, "IRQ work interrupts"),
 };
 
 void show_ipi_list(struct seq_file *p, int prec)
@@ -576,6 +587,14 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 		break;
 #endif
 
+#ifdef CONFIG_IRQ_WORK
+	case IPI_IRQ_WORK:
+		irq_enter();
+		irq_work_run();
+		irq_exit();
+		break;
+#endif
+
 	default:
 		pr_crit("CPU%u: Unknown IPI message 0x%x\n", cpu, ipinr);
 		break;
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index 7a530d2cc80..0347d38eea2 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -30,7 +30,6 @@ extern void secondary_holding_pen(void);
 volatile unsigned long secondary_holding_pen_release = INVALID_HWID;
 
 static phys_addr_t cpu_release_addr[NR_CPUS];
-static DEFINE_RAW_SPINLOCK(boot_lock);
 
 /*
  * Write secondary_holding_pen_release in a way that is guaranteed to be
@@ -94,14 +93,6 @@ static int smp_spin_table_cpu_prepare(unsigned int cpu)
 
 static int smp_spin_table_cpu_boot(unsigned int cpu)
 {
-	unsigned long timeout;
-
-	/*
-	 * Set synchronisation state between this boot processor
-	 * and the secondary one
-	 */
-	raw_spin_lock(&boot_lock);
-
 	/*
 	 * Update the pen release flag.
 	 */
@@ -112,34 +103,7 @@ static int smp_spin_table_cpu_boot(unsigned int cpu)
 	 */
 	sev();
 
-	timeout = jiffies + (1 * HZ);
-	while (time_before(jiffies, timeout)) {
-		if (secondary_holding_pen_release == INVALID_HWID)
-			break;
-		udelay(10);
-	}
-
-	/*
-	 * Now the secondary core is starting up let it run its
-	 * calibrations, then wait for it to finish
-	 */
-	raw_spin_unlock(&boot_lock);
-
-	return secondary_holding_pen_release != INVALID_HWID ? -ENOSYS : 0;
-}
-
-static void smp_spin_table_cpu_postboot(void)
-{
-	/*
-	 * Let the primary processor know we're out of the pen.
-	 */
-	write_pen_release(INVALID_HWID);
-
-	/*
-	 * Synchronise with the boot thread.
-	 */
-	raw_spin_lock(&boot_lock);
-	raw_spin_unlock(&boot_lock);
+	return 0;
 }
 
 const struct cpu_operations smp_spin_table_ops = {
@@ -147,5 +111,4 @@ const struct cpu_operations smp_spin_table_ops = {
 	.cpu_init	= smp_spin_table_cpu_init,
 	.cpu_prepare	= smp_spin_table_cpu_prepare,
 	.cpu_boot	= smp_spin_table_cpu_boot,
-	.cpu_postboot	= smp_spin_table_cpu_postboot,
 };
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 38f0558f0c0..55437ba1f5a 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -35,7 +35,7 @@
  *	ldp	x29, x30, [sp]
  *	add	sp, sp, #0x10
  */
-int unwind_frame(struct stackframe *frame)
+int notrace unwind_frame(struct stackframe *frame)
 {
 	unsigned long high, low;
 	unsigned long fp = frame->fp;
diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c
index 6815987b50f..1a7125c3099 100644
--- a/arch/arm64/kernel/time.c
+++ b/arch/arm64/kernel/time.c
@@ -18,6 +18,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/clockchips.h>
 #include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/interrupt.h>
@@ -69,6 +70,8 @@ void __init time_init(void)
 	of_clk_init(NULL);
 	clocksource_of_init();
 
+	tick_setup_hrtimer_broadcast();
+
 	arch_timer_rate = arch_timer_get_rate();
 	if (!arch_timer_rate)
 		panic("Unable to initialise architected timer.\n");
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 3e06b0be4ec..43514f90591 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -17,10 +17,192 @@
 #include <linux/percpu.h>
 #include <linux/node.h>
 #include <linux/nodemask.h>
+#include <linux/of.h>
 #include <linux/sched.h>
 
 #include <asm/topology.h>
 
+static int __init get_cpu_for_node(struct device_node *node)
+{
+	struct device_node *cpu_node;
+	int cpu;
+
+	cpu_node = of_parse_phandle(node, "cpu", 0);
+	if (!cpu_node)
+		return -1;
+
+	for_each_possible_cpu(cpu) {
+		if (of_get_cpu_node(cpu, NULL) == cpu_node) {
+			of_node_put(cpu_node);
+			return cpu;
+		}
+	}
+
+	pr_crit("Unable to find CPU node for %s\n", cpu_node->full_name);
+
+	of_node_put(cpu_node);
+	return -1;
+}
+
+static int __init parse_core(struct device_node *core, int cluster_id,
+			     int core_id)
+{
+	char name[10];
+	bool leaf = true;
+	int i = 0;
+	int cpu;
+	struct device_node *t;
+
+	do {
+		snprintf(name, sizeof(name), "thread%d", i);
+		t = of_get_child_by_name(core, name);
+		if (t) {
+			leaf = false;
+			cpu = get_cpu_for_node(t);
+			if (cpu >= 0) {
+				cpu_topology[cpu].cluster_id = cluster_id;
+				cpu_topology[cpu].core_id = core_id;
+				cpu_topology[cpu].thread_id = i;
+			} else {
+				pr_err("%s: Can't get CPU for thread\n",
+				       t->full_name);
+				of_node_put(t);
+				return -EINVAL;
+			}
+			of_node_put(t);
+		}
+		i++;
+	} while (t);
+
+	cpu = get_cpu_for_node(core);
+	if (cpu >= 0) {
+		if (!leaf) {
+			pr_err("%s: Core has both threads and CPU\n",
+			       core->full_name);
+			return -EINVAL;
+		}
+
+		cpu_topology[cpu].cluster_id = cluster_id;
+		cpu_topology[cpu].core_id = core_id;
+	} else if (leaf) {
+		pr_err("%s: Can't get CPU for leaf core\n", core->full_name);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int __init parse_cluster(struct device_node *cluster, int depth)
+{
+	char name[10];
+	bool leaf = true;
+	bool has_cores = false;
+	struct device_node *c;
+	static int cluster_id __initdata;
+	int core_id = 0;
+	int i, ret;
+
+	/*
+	 * First check for child clusters; we currently ignore any
+	 * information about the nesting of clusters and present the
+	 * scheduler with a flat list of them.
+	 */
+	i = 0;
+	do {
+		snprintf(name, sizeof(name), "cluster%d", i);
+		c = of_get_child_by_name(cluster, name);
+		if (c) {
+			leaf = false;
+			ret = parse_cluster(c, depth + 1);
+			of_node_put(c);
+			if (ret != 0)
+				return ret;
+		}
+		i++;
+	} while (c);
+
+	/* Now check for cores */
+	i = 0;
+	do {
+		snprintf(name, sizeof(name), "core%d", i);
+		c = of_get_child_by_name(cluster, name);
+		if (c) {
+			has_cores = true;
+
+			if (depth == 0) {
+				pr_err("%s: cpu-map children should be clusters\n",
+				       c->full_name);
+				of_node_put(c);
+				return -EINVAL;
+			}
+
+			if (leaf) {
+				ret = parse_core(c, cluster_id, core_id++);
+			} else {
+				pr_err("%s: Non-leaf cluster with core %s\n",
+				       cluster->full_name, name);
+				ret = -EINVAL;
+			}
+
+			of_node_put(c);
+			if (ret != 0)
+				return ret;
+		}
+		i++;
+	} while (c);
+
+	if (leaf && !has_cores)
+		pr_warn("%s: empty cluster\n", cluster->full_name);
+
+	if (leaf)
+		cluster_id++;
+
+	return 0;
+}
+
+static int __init parse_dt_topology(void)
+{
+	struct device_node *cn, *map;
+	int ret = 0;
+	int cpu;
+
+	cn = of_find_node_by_path("/cpus");
+	if (!cn) {
+		pr_err("No CPU information found in DT\n");
+		return 0;
+	}
+
+	/*
+	 * When topology is provided cpu-map is essentially a root
+	 * cluster with restricted subnodes.
+	 */
+	map = of_get_child_by_name(cn, "cpu-map");
+	if (!map)
+		goto out;
+
+	ret = parse_cluster(map, 0);
+	if (ret != 0)
+		goto out_map;
+
+	/*
+	 * Check that all cores are in the topology; the SMP code will
+	 * only mark cores described in the DT as possible.
+	 */
+	for_each_possible_cpu(cpu) {
+		if (cpu_topology[cpu].cluster_id == -1) {
+			pr_err("CPU%d: No topology information specified\n",
+			       cpu);
+			ret = -EINVAL;
+		}
+	}
+
+out_map:
+	of_node_put(map);
+out:
+	of_node_put(cn);
+	return ret;
+}
+
 /*
  * cpu topology table
  */
@@ -39,13 +221,9 @@ static void update_siblings_masks(unsigned int cpuid)
 
 	if (cpuid_topo->cluster_id == -1) {
 		/*
-		 * DT does not contain topology information for this cpu
-		 * reset it to default behaviour
+		 * DT does not contain topology information for this cpu.
 		 */
 		pr_debug("CPU%u: No topology information configured\n", cpuid);
-		cpuid_topo->core_id = 0;
-		cpumask_set_cpu(cpuid, &cpuid_topo->core_sibling);
-		cpumask_set_cpu(cpuid, &cpuid_topo->thread_sibling);
 		return;
 	}
 
@@ -74,22 +252,32 @@ void store_cpu_topology(unsigned int cpuid)
 	update_siblings_masks(cpuid);
 }
 
-/*
- * init_cpu_topology is called at boot when only one cpu is running
- * which prevent simultaneous write access to cpu_topology array
- */
-void __init init_cpu_topology(void)
+static void __init reset_cpu_topology(void)
 {
 	unsigned int cpu;
 
-	/* init core mask and power*/
 	for_each_possible_cpu(cpu) {
 		struct cpu_topology *cpu_topo = &cpu_topology[cpu];
 
 		cpu_topo->thread_id = -1;
-		cpu_topo->core_id =  -1;
+		cpu_topo->core_id = 0;
 		cpu_topo->cluster_id = -1;
+
 		cpumask_clear(&cpu_topo->core_sibling);
+		cpumask_set_cpu(cpu, &cpu_topo->core_sibling);
 		cpumask_clear(&cpu_topo->thread_sibling);
+		cpumask_set_cpu(cpu, &cpu_topo->thread_sibling);
 	}
 }
+
+void __init init_cpu_topology(void)
+{
+	reset_cpu_topology();
+
+	/*
+	 * Discard anything that was parsed if we hit an error so we
+	 * don't use partial information.
+	 */
+	if (parse_dt_topology())
+		reset_cpu_topology();
+}
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 7ffadddb645..c43cfa9b830 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -251,10 +251,13 @@ void die(const char *str, struct pt_regs *regs, int err)
 void arm64_notify_die(const char *str, struct pt_regs *regs,
 		      struct siginfo *info, int err)
 {
-	if (user_mode(regs))
+	if (user_mode(regs)) {
+		current->thread.fault_address = 0;
+		current->thread.fault_code = err;
 		force_sig_info(info->si_signo, info, current);
-	else
+	} else {
 		die(str, regs, err);
+	}
 }
 
 asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 4ba7a55b49c..f1e6d5c032e 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -13,7 +13,7 @@
 #define ARM_EXIT_DISCARD(x)	x
 
 OUTPUT_ARCH(aarch64)
-ENTRY(stext)
+ENTRY(_text)
 
 jiffies = jiffies_64;