21 files changed, 166 insertions, 80 deletions

diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index 1f031ddd0667..85e664b6a5f1 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@@ -35,6 +35,8 @@ extern void __ucmpdi2(void);
 extern void __udivsi3(void);
 extern void __umodsi3(void);
 extern void __do_div64(void);
+extern void __bswapsi2(void);
+extern void __bswapdi2(void);
 
 extern void __aeabi_idiv(void);
 extern void __aeabi_idivmod(void);
@@ -114,6 +116,8 @@ EXPORT_SYMBOL(__ucmpdi2);
 EXPORT_SYMBOL(__udivsi3);
 EXPORT_SYMBOL(__umodsi3);
 EXPORT_SYMBOL(__do_div64);
+EXPORT_SYMBOL(__bswapsi2);
+EXPORT_SYMBOL(__bswapdi2);
 
 #ifdef CONFIG_AEABI
 EXPORT_SYMBOL(__aeabi_idiv);
diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S
index c6ca7e376773..166e945de832 100644
--- a/arch/arm/kernel/calls.S
+++ b/arch/arm/kernel/calls.S
@@ -389,6 +389,8 @@
 		CALL(sys_process_vm_writev)
 		CALL(sys_kcmp)
 		CALL(sys_finit_module)
+/* 380 */	CALL(sys_sched_setattr)
+		CALL(sys_sched_getattr)
 #ifndef syscalls_counted
 .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
 #define syscalls_counted
diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
index 739c3dfc1da2..f751714d52c1 100644
--- a/arch/arm/kernel/devtree.c
+++ b/arch/arm/kernel/devtree.c
@@ -33,7 +33,7 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 
 void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
 {
-	return alloc_bootmem_align(size, align);
+	return memblock_virt_alloc(size, align);
 }
 
 void __init arm_dt_memblock_reserve(void)
@@ -171,7 +171,7 @@ void __init arm_dt_init_cpu_maps(void)
 
 bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
 {
-	return (phys_id & MPIDR_HWID_BITMASK) == cpu_logical_map(cpu);
+	return phys_id == cpu_logical_map(cpu);
 }
 
 static const void * __init arch_get_next_mach(const char *const **match)
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index b3fb8c9e1ff2..1879e8dd2acc 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -451,9 +451,11 @@ __und_usr_thumb:
 	.arch	armv6t2
 #endif
 2:	ldrht	r5, [r4]
+ARM_BE8(rev16	r5, r5)				@ little endian instruction
 	cmp	r5, #0xe800			@ 32bit instruction if xx != 0
 	blo	__und_usr_fault_16		@ 16bit undefined instruction
 3:	ldrht	r0, [r2]
+ARM_BE8(rev16	r0, r0)				@ little endian instruction
 	add	r2, r2, #2			@ r2 is PC + 2, make it PC + 4
 	str	r2, [sp, #S_PC]			@ it's a 2x16bit instr, update
 	orr	r0, r0, r5, lsl #16
diff --git a/arch/arm/kernel/entry-v7m.S b/arch/arm/kernel/entry-v7m.S
index 52b26432c9a9..2260f1855820 100644
--- a/arch/arm/kernel/entry-v7m.S
+++ b/arch/arm/kernel/entry-v7m.S
@@ -14,8 +14,6 @@
 #include <asm/thread_notify.h>
 #include <asm/v7m.h>
 
-#include <mach/entry-macro.S>
-
 #include "entry-header.S"
 
 #ifdef CONFIG_TRACE_IRQFLAGS
diff --git a/arch/arm/kernel/etm.c b/arch/arm/kernel/etm.c
index 8ff0ecdc637f..131a6ab5f355 100644
--- a/arch/arm/kernel/etm.c
+++ b/arch/arm/kernel/etm.c
@@ -385,7 +385,6 @@ out:
 	return ret;
 
 out_unmap:
-	amba_set_drvdata(dev, NULL);
 	iounmap(t->etb_regs);
 
 out_release:
@@ -398,8 +397,6 @@ static int etb_remove(struct amba_device *dev)
 {
 	struct tracectx *t = amba_get_drvdata(dev);
 
-	amba_set_drvdata(dev, NULL);
-
 	iounmap(t->etb_regs);
 	t->etb_regs = NULL;
 
@@ -588,7 +585,6 @@ out:
 	return ret;
 
 out_unmap:
-	amba_set_drvdata(dev, NULL);
 	iounmap(t->etm_regs);
 
 out_release:
@@ -601,8 +597,6 @@ static int etm_remove(struct amba_device *dev)
 {
 	struct tracectx *t = amba_get_drvdata(dev);
 
-	amba_set_drvdata(dev, NULL);
-
 	iounmap(t->etm_regs);
 	t->etm_regs = NULL;
 
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index 14235ba64a90..716249cc2ee1 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -68,7 +68,7 @@ ENTRY(stext)
 
 #ifdef CONFIG_ARM_MPU
 	/* Calculate the size of a region covering just the kernel */
-	ldr	r5, =PHYS_OFFSET		@ Region start: PHYS_OFFSET
+	ldr	r5, =PLAT_PHYS_OFFSET		@ Region start: PHYS_OFFSET
 	ldr     r6, =(_end)			@ Cover whole kernel
 	sub	r6, r6, r5			@ Minimum size of region to map
 	clz	r6, r6				@ Region size must be 2^N...
@@ -213,7 +213,7 @@ ENTRY(__setup_mpu)
 	set_region_nr r0, #MPU_RAM_REGION
 	isb
 	/* Full access from PL0, PL1, shared for CONFIG_SMP, cacheable */
-	ldr	r0, =PHYS_OFFSET		@ RAM starts at PHYS_OFFSET
+	ldr	r0, =PLAT_PHYS_OFFSET		@ RAM starts at PHYS_OFFSET
 	ldr	r5,=(MPU_AP_PL1RW_PL0RW | MPU_RGN_NORMAL)
 
 	setup_region r0, r5, r6, MPU_DATA_SIDE	@ PHYS_OFFSET, shared, enabled
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 11d59b32fb8d..914616e0bdcd 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -52,7 +52,8 @@
 	.equ	swapper_pg_dir, KERNEL_RAM_VADDR - PG_DIR_SIZE
 
 	.macro	pgtbl, rd, phys
-	add	\rd, \phys, #TEXT_OFFSET - PG_DIR_SIZE
+	add	\rd, \phys, #TEXT_OFFSET
+	sub	\rd, \rd, #PG_DIR_SIZE
 	.endm
 
 /*
@@ -110,7 +111,7 @@ ENTRY(stext)
 	sub	r4, r3, r4			@ (PHYS_OFFSET - PAGE_OFFSET)
 	add	r8, r8, r4			@ PHYS_OFFSET
 #else
-	ldr	r8, =PHYS_OFFSET		@ always constant in this case
+	ldr	r8, =PLAT_PHYS_OFFSET		@ always constant in this case
 #endif
 
 	/*
diff --git a/arch/arm/kernel/io.c b/arch/arm/kernel/io.c
index dcd5b4d86143..9203cf883330 100644
--- a/arch/arm/kernel/io.c
+++ b/arch/arm/kernel/io.c
@@ -1,6 +1,41 @@
 #include <linux/export.h>
 #include <linux/types.h>
 #include <linux/io.h>
+#include <linux/spinlock.h>
+
+static DEFINE_RAW_SPINLOCK(__io_lock);
+
+/*
+ * Generic atomic MMIO modify.
+ *
+ * Allows thread-safe access to registers shared by unrelated subsystems.
+ * The access is protected by a single MMIO-wide lock.
+ */
+void atomic_io_modify_relaxed(void __iomem *reg, u32 mask, u32 set)
+{
+	unsigned long flags;
+	u32 value;
+
+	raw_spin_lock_irqsave(&__io_lock, flags);
+	value = readl_relaxed(reg) & ~mask;
+	value |= (set & mask);
+	writel_relaxed(value, reg);
+	raw_spin_unlock_irqrestore(&__io_lock, flags);
+}
+EXPORT_SYMBOL(atomic_io_modify_relaxed);
+
+void atomic_io_modify(void __iomem *reg, u32 mask, u32 set)
+{
+	unsigned long flags;
+	u32 value;
+
+	raw_spin_lock_irqsave(&__io_lock, flags);
+	value = readl_relaxed(reg) & ~mask;
+	value |= (set & mask);
+	writel(value, reg);
+	raw_spin_unlock_irqrestore(&__io_lock, flags);
+}
+EXPORT_SYMBOL(atomic_io_modify);
 
 /*
  * Copy data from IO memory space to "real" memory space.
diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index 57221e349a7c..f0d180d8b29f 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -14,11 +14,12 @@
 #include <asm/pgalloc.h>
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
+#include <asm/fncpy.h>
 #include <asm/mach-types.h>
 #include <asm/smp_plat.h>
 #include <asm/system_misc.h>
 
-extern const unsigned char relocate_new_kernel[];
+extern void relocate_new_kernel(void);
 extern const unsigned int relocate_new_kernel_size;
 
 extern unsigned long kexec_start_address;
@@ -142,6 +143,8 @@ void machine_kexec(struct kimage *image)
 {
 	unsigned long page_list;
 	unsigned long reboot_code_buffer_phys;
+	unsigned long reboot_entry = (unsigned long)relocate_new_kernel;
+	unsigned long reboot_entry_phys;
 	void *reboot_code_buffer;
 
 	/*
@@ -168,16 +171,16 @@ void machine_kexec(struct kimage *image)
 
 
 	/* copy our kernel relocation code to the control code page */
-	memcpy(reboot_code_buffer,
-	       relocate_new_kernel, relocate_new_kernel_size);
+	reboot_entry = fncpy(reboot_code_buffer,
+			     reboot_entry,
+			     relocate_new_kernel_size);
+	reboot_entry_phys = (unsigned long)reboot_entry +
+		(reboot_code_buffer_phys - (unsigned long)reboot_code_buffer);
 
-
-	flush_icache_range((unsigned long) reboot_code_buffer,
-			   (unsigned long) reboot_code_buffer + KEXEC_CONTROL_PAGE_SIZE);
 	printk(KERN_INFO "Bye!\n");
 
 	if (kexec_reinit)
 		kexec_reinit();
 
-	soft_restart(reboot_code_buffer_phys);
+	soft_restart(reboot_entry_phys);
 }
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index bc3f2efa0d86..789d846a9184 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -99,10 +99,6 @@ int armpmu_event_set_period(struct perf_event *event)
 	s64 period = hwc->sample_period;
 	int ret = 0;
 
-	/* The period may have been changed by PERF_EVENT_IOC_PERIOD */
-	if (unlikely(period != hwc->last_period))
-		left = period - (hwc->last_period - left);
-
 	if (unlikely(left <= -period)) {
 		left = period;
 		local64_set(&hwc->period_left, left);
diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
index d85055cd24ba..20d553c9f5e2 100644
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -254,7 +254,7 @@ static int probe_current_pmu(struct arm_pmu *pmu)
 static int cpu_pmu_device_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *of_id;
-	int (*init_fn)(struct arm_pmu *);
+	const int (*init_fn)(struct arm_pmu *);
 	struct device_node *node = pdev->dev.of_node;
 	struct arm_pmu *pmu;
 	int ret = -ENODEV;
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 94f6b05f9e24..92f7b15dd221 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -404,6 +404,7 @@ EXPORT_SYMBOL(dump_fpu);
 unsigned long get_wchan(struct task_struct *p)
 {
 	struct stackframe frame;
+	unsigned long stack_page;
 	int count = 0;
 	if (!p || p == current || p->state == TASK_RUNNING)
 		return 0;
@@ -412,9 +413,11 @@ unsigned long get_wchan(struct task_struct *p)
 	frame.sp = thread_saved_sp(p);
 	frame.lr = 0;			/* recovered from the stack */
 	frame.pc = thread_saved_pc(p);
+	stack_page = (unsigned long)task_stack_page(p);
 	do {
-		int ret = unwind_frame(&frame);
-		if (ret < 0)
+		if (frame.sp < stack_page ||
+		    frame.sp >= stack_page + THREAD_SIZE ||
+		    unwind_frame(&frame) < 0)
 			return 0;
 		if (!in_sched_functions(frame.pc))
 			return frame.pc;
diff --git a/arch/arm/kernel/relocate_kernel.S b/arch/arm/kernel/relocate_kernel.S
index d0cdedf4864d..95858966d84e 100644
--- a/arch/arm/kernel/relocate_kernel.S
+++ b/arch/arm/kernel/relocate_kernel.S
@@ -2,10 +2,12 @@
  * relocate_kernel.S - put the kernel image in place to boot
  */
 
+#include <linux/linkage.h>
 #include <asm/kexec.h>
 
-	.globl relocate_new_kernel
-relocate_new_kernel:
+	.align	3	/* not needed for this code, but keeps fncpy() happy */
+
+ENTRY(relocate_new_kernel)
 
 	ldr	r0,kexec_indirection_page
 	ldr	r1,kexec_start_address
@@ -79,6 +81,8 @@ kexec_mach_type:
 kexec_boot_atags:
 	.long	0x0
 
+ENDPROC(relocate_new_kernel)
+
 relocate_new_kernel_end:
 
 	.globl relocate_new_kernel_size
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 6a1b8a81b1ae..b0df9761de6d 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -334,7 +334,7 @@ static void __init cacheid_init(void)
 		cacheid = CACHEID_VIVT;
 	}
 
-	printk("CPU: %s data cache, %s instruction cache\n",
+	pr_info("CPU: %s data cache, %s instruction cache\n",
 		cache_is_vivt() ? "VIVT" :
 		cache_is_vipt_aliasing() ? "VIPT aliasing" :
 		cache_is_vipt_nonaliasing() ? "PIPT / VIPT nonaliasing" : "unknown",
@@ -416,7 +416,7 @@ void notrace cpu_init(void)
 	struct stack *stk = &stacks[cpu];
 
 	if (cpu >= NR_CPUS) {
-		printk(KERN_CRIT "CPU%u: bad primary CPU number\n", cpu);
+		pr_crit("CPU%u: bad primary CPU number\n", cpu);
 		BUG();
 	}
 
@@ -484,7 +484,7 @@ void __init smp_setup_processor_id(void)
 	 */
 	set_my_cpu_offset(0);
 
-	printk(KERN_INFO "Booting Linux on physical CPU 0x%x\n", mpidr);
+	pr_info("Booting Linux on physical CPU 0x%x\n", mpidr);
 }
 
 struct mpidr_hash mpidr_hash;
@@ -564,8 +564,8 @@ static void __init setup_processor(void)
 	 */
 	list = lookup_processor_type(read_cpuid_id());
 	if (!list) {
-		printk("CPU configuration botched (ID %08x), unable "
-		       "to continue.\n", read_cpuid_id());
+		pr_err("CPU configuration botched (ID %08x), unable to continue.\n",
+		       read_cpuid_id());
 		while (1);
 	}
 
@@ -585,9 +585,9 @@ static void __init setup_processor(void)
 	cpu_cache = *list->cache;
 #endif
 
-	printk("CPU: %s [%08x] revision %d (ARMv%s), cr=%08lx\n",
-	       cpu_name, read_cpuid_id(), read_cpuid_id() & 15,
-	       proc_arch[cpu_architecture()], cr_alignment);
+	pr_info("CPU: %s [%08x] revision %d (ARMv%s), cr=%08lx\n",
+		cpu_name, read_cpuid_id(), read_cpuid_id() & 15,
+		proc_arch[cpu_architecture()], cr_alignment);
 
 	snprintf(init_utsname()->machine, __NEW_UTS_LEN + 1, "%s%c",
 		 list->arch_name, ENDIANNESS);
@@ -629,8 +629,8 @@ int __init arm_add_memory(u64 start, u64 size)
 	u64 aligned_start;
 
 	if (meminfo.nr_banks >= NR_BANKS) {
-		printk(KERN_CRIT "NR_BANKS too low, "
-			"ignoring memory at 0x%08llx\n", (long long)start);
+		pr_crit("NR_BANKS too low, ignoring memory at 0x%08llx\n",
+			(long long)start);
 		return -EINVAL;
 	}
 
@@ -643,14 +643,14 @@ int __init arm_add_memory(u64 start, u64 size)
 
 #ifndef CONFIG_ARCH_PHYS_ADDR_T_64BIT
 	if (aligned_start > ULONG_MAX) {
-		printk(KERN_CRIT "Ignoring memory at 0x%08llx outside "
-		       "32-bit physical address space\n", (long long)start);
+		pr_crit("Ignoring memory at 0x%08llx outside 32-bit physical address space\n",
+			(long long)start);
 		return -EINVAL;
 	}
 
 	if (aligned_start + size > ULONG_MAX) {
-		printk(KERN_CRIT "Truncating memory at 0x%08llx to fit in "
-			"32-bit physical address space\n", (long long)start);
+		pr_crit("Truncating memory at 0x%08llx to fit in 32-bit physical address space\n",
+			(long long)start);
 		/*
 		 * To ensure bank->start + bank->size is representable in
 		 * 32 bits, we use ULONG_MAX as the upper limit rather than 4GB.
@@ -660,6 +660,20 @@ int __init arm_add_memory(u64 start, u64 size)
 	}
 #endif
 
+	if (aligned_start < PHYS_OFFSET) {
+		if (aligned_start + size <= PHYS_OFFSET) {
+			pr_info("Ignoring memory below PHYS_OFFSET: 0x%08llx-0x%08llx\n",
+				aligned_start, aligned_start + size);
+			return -EINVAL;
+		}
+
+		pr_info("Ignoring memory below PHYS_OFFSET: 0x%08llx-0x%08llx\n",
+			aligned_start, (u64)PHYS_OFFSET);
+
+		size -= PHYS_OFFSET - aligned_start;
+		aligned_start = PHYS_OFFSET;
+	}
+
 	bank->start = aligned_start;
 	bank->size = size & ~(phys_addr_t)(PAGE_SIZE - 1);
 
@@ -717,7 +731,7 @@ static void __init request_standard_resources(const struct machine_desc *mdesc)
 	kernel_data.end     = virt_to_phys(_end - 1);
 
 	for_each_memblock(memory, region) {
-		res = alloc_bootmem_low(sizeof(*res));
+		res = memblock_virt_alloc_low(sizeof(*res), 0);
 		res->name  = "System RAM";
 		res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region));
 		res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1;
@@ -817,18 +831,17 @@ static void __init reserve_crashkernel(void)
 	if (ret)
 		return;
 
-	ret = reserve_bootmem(crash_base, crash_size, BOOTMEM_EXCLUSIVE);
+	ret = memblock_reserve(crash_base, crash_size);
 	if (ret < 0) {
-		printk(KERN_WARNING "crashkernel reservation failed - "
-		       "memory is in use (0x%lx)\n", (unsigned long)crash_base);
+		pr_warn("crashkernel reservation failed - memory is in use (0x%lx)\n",
+			(unsigned long)crash_base);
 		return;
 	}
 
-	printk(KERN_INFO "Reserving %ldMB of memory at %ldMB "
-	       "for crashkernel (System RAM: %ldMB)\n",
-	       (unsigned long)(crash_size >> 20),
-	       (unsigned long)(crash_base >> 20),
-	       (unsigned long)(total_mem >> 20));
+	pr_info("Reserving %ldMB of memory at %ldMB for crashkernel (System RAM: %ldMB)\n",
+		(unsigned long)(crash_size >> 20),
+		(unsigned long)(crash_base >> 20),
+		(unsigned long)(total_mem >> 20));
 
 	crashk_res.start = crash_base;
 	crashk_res.end = crash_base + crash_size - 1;
@@ -873,8 +886,6 @@ void __init setup_arch(char **cmdline_p)
 	machine_desc = mdesc;
 	machine_name = mdesc->name;
 
-	setup_dma_zone(mdesc);
-
 	if (mdesc->reboot_mode != REBOOT_HARD)
 		reboot_mode = mdesc->reboot_mode;
 
@@ -892,6 +903,7 @@ void __init setup_arch(char **cmdline_p)
 	sort(&meminfo.bank, meminfo.nr_banks, sizeof(meminfo.bank[0]), meminfo_cmp, NULL);
 
 	early_paging_init(mdesc, lookup_processor_type(read_cpuid_id()));
+	setup_dma_zone(mdesc);
 	sanity_check_meminfo();
 	arm_memblock_init(&meminfo, mdesc);
 
diff --git a/arch/arm/kernel/sigreturn_codes.S b/arch/arm/kernel/sigreturn_codes.S
index 3c5d0f2170fd..b84d0cb13682 100644
--- a/arch/arm/kernel/sigreturn_codes.S
+++ b/arch/arm/kernel/sigreturn_codes.S
@@ -30,6 +30,27 @@
  * snippets.
  */
 
+/*
+ * In CPU_THUMBONLY case kernel arm opcodes are not allowed.
+ * Note in this case codes skips those instructions but it uses .org
+ * directive to keep correct layout of sigreturn_codes array.
+ */
+#ifndef CONFIG_CPU_THUMBONLY
+#define ARM_OK(code...)	code
+#else
+#define ARM_OK(code...)
+#endif
+
+	.macro arm_slot n
+	.org	sigreturn_codes + 12 * (\n)
+ARM_OK(	.arm	)
+	.endm
+
+	.macro thumb_slot n
+	.org	sigreturn_codes + 12 * (\n) + 8
+	.thumb
+	.endm
+
 #if __LINUX_ARM_ARCH__ <= 4
 	/*
 	 * Note we manually set minimally required arch that supports
@@ -45,26 +66,27 @@
 	.global sigreturn_codes
 	.type	sigreturn_codes, #object
 
-	.arm
+	.align
 
 sigreturn_codes:
 
 	/* ARM sigreturn syscall code snippet */
-	mov	r7, #(__NR_sigreturn - __NR_SYSCALL_BASE)
-	swi	#(__NR_sigreturn)|(__NR_OABI_SYSCALL_BASE)
+	arm_slot 0
+ARM_OK(	mov	r7, #(__NR_sigreturn - __NR_SYSCALL_BASE)	)
+ARM_OK(	swi	#(__NR_sigreturn)|(__NR_OABI_SYSCALL_BASE)	)
 
 	/* Thumb sigreturn syscall code snippet */
-	.thumb
+	thumb_slot 0
 	movs	r7, #(__NR_sigreturn - __NR_SYSCALL_BASE)
 	swi	#0
 
 	/* ARM sigreturn_rt syscall code snippet */
-	.arm
-	mov	r7, #(__NR_rt_sigreturn - __NR_SYSCALL_BASE)
-	swi	#(__NR_rt_sigreturn)|(__NR_OABI_SYSCALL_BASE)
+	arm_slot 1
+ARM_OK(	mov	r7, #(__NR_rt_sigreturn - __NR_SYSCALL_BASE)	)
+ARM_OK(	swi	#(__NR_rt_sigreturn)|(__NR_OABI_SYSCALL_BASE)	)
 
 	/* Thumb sigreturn_rt syscall code snippet */
-	.thumb
+	thumb_slot 1
 	movs	r7, #(__NR_rt_sigreturn - __NR_SYSCALL_BASE)
 	swi	#0
 
@@ -74,7 +96,7 @@ sigreturn_codes:
 	 * it is thumb case or not, so we need additional
 	 * word after real last entry.
 	 */
-	.arm
+	arm_slot 2
 	.space	4
 
 	.size	sigreturn_codes, . - sigreturn_codes
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index dc894ab3622b..b7b4c86e338b 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -105,8 +105,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 	secondary_data.pgdir = get_arch_pgd(idmap_pgd);
 	secondary_data.swapper_pg_dir = get_arch_pgd(swapper_pg_dir);
 #endif
-	__cpuc_flush_dcache_area(&secondary_data, sizeof(secondary_data));
-	outer_clean_range(__pa(&secondary_data), __pa(&secondary_data + 1));
+	sync_cache_w(&secondary_data);
 
 	/*
 	 * Now bring the CPU into our world.
@@ -294,6 +293,9 @@ void __ref cpu_die(void)
 	if (smp_ops.cpu_die)
 		smp_ops.cpu_die(cpu);
 
+	pr_warn("CPU%u: smp_ops.cpu_die() returned, trying to resuscitate\n",
+		cpu);
+
 	/*
 	 * Do not return to the idle loop - jump back to the secondary
 	 * cpu initialisation.  There's some initialisation which needs
diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c
index 00f79e59985b..af4e8c8a5422 100644
--- a/arch/arm/kernel/stacktrace.c
+++ b/arch/arm/kernel/stacktrace.c
@@ -31,7 +31,7 @@ int notrace unwind_frame(struct stackframe *frame)
 	high = ALIGN(low, THREAD_SIZE);
 
 	/* check current frame pointer is within bounds */
-	if (fp < (low + 12) || fp + 4 >= high)
+	if (fp < low + 12 || fp > high - 4)
 		return -EINVAL;
 
 	/* restore the registers from the stack frame */
diff --git a/arch/arm/kernel/tcm.c b/arch/arm/kernel/tcm.c
index f50f19e5c138..7a3be1d4d0b1 100644
--- a/arch/arm/kernel/tcm.c
+++ b/arch/arm/kernel/tcm.c
@@ -52,7 +52,7 @@ static struct map_desc dtcm_iomap[] __initdata = {
 		.virtual	= DTCM_OFFSET,
 		.pfn		= __phys_to_pfn(DTCM_OFFSET),
 		.length		= 0,
-		.type		= MT_MEMORY_DTCM
+		.type		= MT_MEMORY_RW_DTCM
 	}
 };
 
@@ -61,7 +61,7 @@ static struct map_desc itcm_iomap[] __initdata = {
 		.virtual	= ITCM_OFFSET,
 		.pfn		= __phys_to_pfn(ITCM_OFFSET),
 		.length		= 0,
-		.type		= MT_MEMORY_ITCM
+		.type		= MT_MEMORY_RWX_ITCM,
 	}
 };
 
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index 85a87370f144..0bc94b1fd1ae 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -68,16 +68,16 @@ struct cpu_efficiency {
  * Processors that are not defined in the table,
  * use the default SCHED_POWER_SCALE value for cpu_scale.
  */
-struct cpu_efficiency table_efficiency[] = {
+static const struct cpu_efficiency table_efficiency[] = {
 	{"arm,cortex-a15", 3891},
 	{"arm,cortex-a7",  2048},
 	{NULL, },
 };
 
-unsigned long *__cpu_capacity;
+static unsigned long *__cpu_capacity;
 #define cpu_capacity(cpu)	__cpu_capacity[cpu]
 
-unsigned long middle_capacity = 1;
+static unsigned long middle_capacity = 1;
 
 /*
  * Iterate all CPUs' descriptor in DT and compute the efficiency
@@ -89,7 +89,7 @@ unsigned long middle_capacity = 1;
  */
 static void __init parse_dt_topology(void)
 {
-	struct cpu_efficiency *cpu_eff;
+	const struct cpu_efficiency *cpu_eff;
 	struct device_node *cn = NULL;
 	unsigned long min_capacity = (unsigned long)(-1);
 	unsigned long max_capacity = 0;
@@ -158,7 +158,7 @@ static void __init parse_dt_topology(void)
  * boot. The update of all CPUs is in O(n^2) for heteregeneous system but the
  * function returns directly for SMP system.
  */
-void update_cpu_power(unsigned int cpu)
+static void update_cpu_power(unsigned int cpu)
 {
 	if (!cpu_capacity(cpu))
 		return;
@@ -185,7 +185,7 @@ const struct cpumask *cpu_coregroup_mask(int cpu)
 	return &cpu_topology[cpu].core_sibling;
 }
 
-void update_siblings_masks(unsigned int cpuid)
+static void update_siblings_masks(unsigned int cpuid)
 {
 	struct cputopo_arm *cpu_topo, *cpuid_topo = &cpu_topology[cpuid];
 	int cpu;
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index dbf0923e8d76..172ee18ff124 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -36,7 +36,13 @@
 #include <asm/system_misc.h>
 #include <asm/opcodes.h>
 
-static const char *handler[]= { "prefetch abort", "data abort", "address exception", "interrupt" };
+static const char *handler[]= {
+	"prefetch abort",
+	"data abort",
+	"address exception",
+	"interrupt",
+	"undefined instruction",
+};
 
 void *vectors_page;
 
@@ -56,7 +62,7 @@ static void dump_mem(const char *, const char *, unsigned long, unsigned long);
 void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long frame)
 {
 #ifdef CONFIG_KALLSYMS
-	printk("[<%08lx>] (%pS) from [<%08lx>] (%pS)\n", where, (void *)where, from, (void *)from);
+	printk("[<%08lx>] (%ps) from [<%08lx>] (%pS)\n", where, (void *)where, from, (void *)from);
 #else
 	printk("Function entered at [<%08lx>] from [<%08lx>]\n", where, from);
 #endif
@@ -425,9 +431,10 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
 			instr2 = __mem_to_opcode_thumb16(instr2);
 			instr = __opcode_thumb32_compose(instr, instr2);
 		}
-	} else if (get_user(instr, (u32 __user *)pc)) {
+	} else {
+		if (get_user(instr, (u32 __user *)pc))
+			goto die_sig;
 		instr = __mem_to_opcode_arm(instr);
-		goto die_sig;
 	}
 
 	if (call_undef_hook(regs, instr) == 0)
@@ -509,9 +516,10 @@ static inline int
 __do_cache_op(unsigned long start, unsigned long end)
 {
 	int ret;
-	unsigned long chunk = PAGE_SIZE;
 
 	do {
+		unsigned long chunk = min(PAGE_SIZE, end - start);
+
 		if (signal_pending(current)) {
 			struct thread_info *ti = current_thread_info();