Merge branch 'smp' into misc

Conflicts:
	arch/arm/kernel/entry-armv.S
	arch/arm/mm/ioremap.c

13 files changed, 355 insertions, 301 deletions

diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 4036a5926465..0e1067957029 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -29,7 +29,7 @@ obj-$(CONFIG_MODULES)		+= armksyms.o module.o
 obj-$(CONFIG_ARTHUR)		+= arthur.o
 obj-$(CONFIG_ISA_DMA)		+= dma-isa.o
 obj-$(CONFIG_PCI)		+= bios32.o isa.o
-obj-$(CONFIG_SMP)		+= smp.o
+obj-$(CONFIG_SMP)		+= smp.o smp_tlb.o
 obj-$(CONFIG_HAVE_ARM_SCU)	+= smp_scu.o
 obj-$(CONFIG_HAVE_ARM_TWD)	+= smp_twd.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index a866dce611d0..8e2dacdbdccb 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -822,7 +822,7 @@ __kuser_helper_start:
  */
 
 __kuser_memory_barrier:				@ 0xffff0fa0
-	smp_dmb
+	smp_dmb	arm
 	usr_ret	lr
 
 	.align	5
@@ -939,7 +939,7 @@ kuser_cmpxchg_fixup:
 
 #else
 
-	smp_dmb
+	smp_dmb	arm
 1:	ldrex	r3, [r2]
 	subs	r3, r3, r0
 	strexeq	r3, r1, [r2]
diff --git a/arch/arm/kernel/fiq.c b/arch/arm/kernel/fiq.c
index d601ef297eb6..e72dc34eea1c 100644
--- a/arch/arm/kernel/fiq.c
+++ b/arch/arm/kernel/fiq.c
@@ -68,10 +68,11 @@ static struct fiq_handler default_owner = {
 
 static struct fiq_handler *current_fiq = &default_owner;
 
-int show_fiq_list(struct seq_file *p, void *v)
+int show_fiq_list(struct seq_file *p, int prec)
 {
 	if (current_fiq != &default_owner)
-		seq_printf(p, "FIQ:              %s\n", current_fiq->name);
+		seq_printf(p, "%*s:              %s\n", prec, "FIQ",
+			current_fiq->name);
 
 	return 0;
 }
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index dd6b369ac69c..359e54e83bd5 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -89,6 +89,11 @@ ENTRY(stext)
 	bl	__lookup_machine_type		@ r5=machinfo
 	movs	r8, r5				@ invalid machine (r5=0)?
 	beq	__error_a			@ yes, error 'a'
+
+	/*
+	 * r1 = machine no, r2 = atags,
+	 * r8 = machinfo, r9 = cpuid, r10 = procinfo
+	 */
 	bl	__vet_atags
 #ifdef CONFIG_SMP_ON_UP
 	bl	__fixup_smp
@@ -381,19 +386,19 @@ ENDPROC(__turn_mmu_on)
 
 #ifdef CONFIG_SMP_ON_UP
 __fixup_smp:
-	mov	r7, #0x00070000
-	orr	r6, r7, #0xff000000	@ mask 0xff070000
-	orr	r7, r7, #0x41000000	@ val 0x41070000
-	and	r0, r9, r6
-	teq	r0, r7			@ ARM CPU and ARMv6/v7?
+	mov	r4, #0x00070000
+	orr	r3, r4, #0xff000000	@ mask 0xff070000
+	orr	r4, r4, #0x41000000	@ val 0x41070000
+	and	r0, r9, r3
+	teq	r0, r4			@ ARM CPU and ARMv6/v7?
 	bne	__fixup_smp_on_up	@ no, assume UP
 
-	orr	r6, r6, #0x0000ff00
-	orr	r6, r6, #0x000000f0	@ mask 0xff07fff0
-	orr	r7, r7, #0x0000b000
-	orr	r7, r7, #0x00000020	@ val 0x4107b020
-	and	r0, r9, r6
-	teq	r0, r7			@ ARM 11MPCore?
+	orr	r3, r3, #0x0000ff00
+	orr	r3, r3, #0x000000f0	@ mask 0xff07fff0
+	orr	r4, r4, #0x0000b000
+	orr	r4, r4, #0x00000020	@ val 0x4107b020
+	and	r0, r9, r3
+	teq	r0, r4			@ ARM 11MPCore?
 	moveq	pc, lr			@ yes, assume SMP
 
 	mrc	p15, 0, r0, c0, c0, 5	@ read MPIDR
@@ -402,15 +407,22 @@ __fixup_smp:
 
 __fixup_smp_on_up:
 	adr	r0, 1f
-	ldmia	r0, {r3, r6, r7}
+	ldmia	r0, {r3 - r5}
 	sub	r3, r0, r3
-	add	r6, r6, r3
-	add	r7, r7, r3
-2:	cmp	r6, r7
-	ldmia	r6!, {r0, r4}
-	strlo	r4, [r0, r3]
-	blo	2b
-	mov	pc, lr
+	add	r4, r4, r3
+	add	r5, r5, r3
+2:	cmp	r4, r5
+	movhs	pc, lr
+	ldmia	r4!, {r0, r6}
+ ARM(	str	r6, [r0, r3]	)
+ THUMB(	add	r0, r0, r3	)
+#ifdef __ARMEB__
+ THUMB(	mov	r6, r6, ror #16	)	@ Convert word order for big-endian.
+#endif
+ THUMB(	strh	r6, [r0], #2	)	@ For Thumb-2, store as two halfwords
+ THUMB(	mov	r6, r6, lsr #16	)	@ to be robust against misaligned r3.
+ THUMB(	strh	r6, [r0]	)
+	b	2b
 ENDPROC(__fixup_smp)
 
 1:	.word	.
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index 54593b0c241b..21e3a4ab3b8c 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -748,8 +748,7 @@ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr,
 		breakpoint_handler(addr, regs);
 		break;
 	case ARM_ENTRY_ASYNC_WATCHPOINT:
-		WARN_ON("Asynchronous watchpoint exception taken. "
-			"Debugging results may be unreliable");
+		WARN(1, "Asynchronous watchpoint exception taken. Debugging results may be unreliable\n");
 	case ARM_ENTRY_SYNC_WATCHPOINT:
 		watchpoint_handler(addr, regs);
 		break;
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index a591971dbf7b..c1269944cc59 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -56,11 +56,20 @@ int show_interrupts(struct seq_file *p, void *v)
 	struct irq_desc *desc;
 	struct irqaction * action;
 	unsigned long flags;
+	int prec, n;
+
+	for (prec = 3, n = 1000; prec < 10 && n <= nr_irqs; prec++)
+		n *= 10;
+
+#ifdef CONFIG_SMP
+	if (prec < 4)
+		prec = 4;
+#endif
 
 	if (i == 0) {
 		char cpuname[12];
 
-		seq_printf(p, "    ");
+		seq_printf(p, "%*s ", prec, "");
 		for_each_present_cpu(cpu) {
 			sprintf(cpuname, "CPU%d", cpu);
 			seq_printf(p, " %10s", cpuname);
@@ -75,7 +84,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		if (!action)
 			goto unlock;
 
-		seq_printf(p, "%3d: ", i);
+		seq_printf(p, "%*d: ", prec, i);
 		for_each_present_cpu(cpu)
 			seq_printf(p, "%10u ", kstat_irqs_cpu(i, cpu));
 		seq_printf(p, " %10s", desc->chip->name ? : "-");
@@ -88,13 +97,15 @@ unlock:
 		raw_spin_unlock_irqrestore(&desc->lock, flags);
 	} else if (i == nr_irqs) {
 #ifdef CONFIG_FIQ
-		show_fiq_list(p, v);
+		show_fiq_list(p, prec);
 #endif
 #ifdef CONFIG_SMP
-		show_ipi_list(p);
-		show_local_irqs(p);
+		show_ipi_list(p, prec);
+#endif
+#ifdef CONFIG_LOCAL_TIMERS
+		show_local_irqs(p, prec);
 #endif
-		seq_printf(p, "Err: %10lu\n", irq_err_count);
+		seq_printf(p, "%*s: %10lu\n", prec, "Err", irq_err_count);
 	}
 	return 0;
 }
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 49643b1467e6..07a50357492a 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -1749,7 +1749,7 @@ static inline int armv7_pmnc_has_overflowed(unsigned long pmnc)
 static inline int armv7_pmnc_counter_has_overflowed(unsigned long pmnc,
 					enum armv7_counters counter)
 {
-	int ret;
+	int ret = 0;
 
 	if (counter == ARMV7_CYCLE_COUNTER)
 		ret = pmnc & ARMV7_FLAG_C;
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 8c1959590252..5341b0b19701 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -24,6 +24,7 @@
 #include <linux/irq.h>
 #include <linux/percpu.h>
 #include <linux/clockchips.h>
+#include <linux/completion.h>
 
 #include <asm/atomic.h>
 #include <asm/cacheflush.h>
@@ -37,7 +38,6 @@
 #include <asm/tlbflush.h>
 #include <asm/ptrace.h>
 #include <asm/localtimer.h>
-#include <asm/smp_plat.h>
 
 /*
  * as from 2.5, kernels no longer have an init_tasks structure
@@ -46,22 +46,8 @@
  */
 struct secondary_data secondary_data;
 
-/*
- * structures for inter-processor calls
- * - A collection of single bit ipi messages.
- */
-struct ipi_data {
-	spinlock_t lock;
-	unsigned long ipi_count;
-	unsigned long bits;
-};
-
-static DEFINE_PER_CPU(struct ipi_data, ipi_data) = {
-	.lock	= SPIN_LOCK_UNLOCKED,
-};
-
 enum ipi_msg_type {
-	IPI_TIMER,
+	IPI_TIMER = 2,
 	IPI_RESCHEDULE,
 	IPI_CALL_FUNC,
 	IPI_CALL_FUNC_SINGLE,
@@ -177,8 +163,12 @@ int __cpuinit __cpu_up(unsigned int cpu)
 			barrier();
 		}
 
-		if (!cpu_online(cpu))
+		if (!cpu_online(cpu)) {
+			pr_crit("CPU%u: failed to come online\n", cpu);
 			ret = -EIO;
+		}
+	} else {
+		pr_err("CPU%u: failed to boot: %d\n", cpu, ret);
 	}
 
 	secondary_data.stack = NULL;
@@ -194,18 +184,12 @@ int __cpuinit __cpu_up(unsigned int cpu)
 
 	pgd_free(&init_mm, pgd);
 
-	if (ret) {
-		printk(KERN_CRIT "CPU%u: processor failed to boot\n", cpu);
-
-		/*
-		 * FIXME: We need to clean up the new idle thread. --rmk
-		 */
-	}
-
 	return ret;
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
+static void percpu_timer_stop(void);
+
 /*
  * __cpu_disable runs on the processor to be shutdown.
  */
@@ -233,7 +217,7 @@ int __cpu_disable(void)
 	/*
 	 * Stop the local timer for this CPU.
 	 */
-	local_timer_stop();
+	percpu_timer_stop();
 
 	/*
 	 * Flush user cache and TLB mappings, and then remove this CPU
@@ -252,12 +236,20 @@ int __cpu_disable(void)
 	return 0;
 }
 
+static DECLARE_COMPLETION(cpu_died);
+
 /*
  * called on the thread which is asking for a CPU to be shutdown -
  * waits until shutdown has completed, or it is timed out.
  */
 void __cpu_die(unsigned int cpu)
 {
+	if (!wait_for_completion_timeout(&cpu_died, msecs_to_jiffies(5000))) {
+		pr_err("CPU%u: cpu didn't die\n", cpu);
+		return;
+	}
+	printk(KERN_NOTICE "CPU%u: shutdown\n", cpu);
+
 	if (!platform_cpu_kill(cpu))
 		printk("CPU%u: unable to kill\n", cpu);
 }
@@ -274,12 +266,17 @@ void __ref cpu_die(void)
 {
 	unsigned int cpu = smp_processor_id();
 
-	local_irq_disable();
 	idle_task_exit();
 
+	local_irq_disable();
+	mb();
+
+	/* Tell __cpu_die() that this CPU is now safe to dispose of */
+	complete(&cpu_died);
+
 	/*
 	 * actual CPU shutdown procedure is at least platform (if not
-	 * CPU) specific
+	 * CPU) specific.
 	 */
 	platform_cpu_die(cpu);
 
@@ -289,6 +286,7 @@ void __ref cpu_die(void)
 	 * to be repeated to undo the effects of taking the CPU offline.
 	 */
 	__asm__("mov	sp, %0\n"
+	"	mov	fp, #0\n"
 	"	b	secondary_start_kernel"
 		:
 		: "r" (task_stack_page(current) + THREAD_SIZE - 8));
@@ -296,6 +294,17 @@ void __ref cpu_die(void)
 #endif /* CONFIG_HOTPLUG_CPU */
 
 /*
+ * Called by both boot and secondaries to move global data into
+ * per-processor storage.
+ */
+static void __cpuinit smp_store_cpu_info(unsigned int cpuid)
+{
+	struct cpuinfo_arm *cpu_info = &per_cpu(cpu_data, cpuid);
+
+	cpu_info->loops_per_jiffy = loops_per_jiffy;
+}
+
+/*
  * This is the secondary CPU boot entry.  We're using this CPUs
  * idle thread stack, but a set of temporary page tables.
  */
@@ -320,6 +329,7 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 
 	cpu_init();
 	preempt_disable();
+	trace_hardirqs_off();
 
 	/*
 	 * Give the platform a chance to do its own initialisation.
@@ -353,17 +363,6 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	cpu_idle();
 }
 
-/*
- * Called by both boot and secondaries to move global data into
- * per-processor storage.
- */
-void __cpuinit smp_store_cpu_info(unsigned int cpuid)
-{
-	struct cpuinfo_arm *cpu_info = &per_cpu(cpu_data, cpuid);
-
-	cpu_info->loops_per_jiffy = loops_per_jiffy;
-}
-
 void __init smp_cpus_done(unsigned int max_cpus)
 {
 	int cpu;
@@ -386,61 +385,80 @@ void __init smp_prepare_boot_cpu(void)
 	per_cpu(cpu_data, cpu).idle = current;
 }
 
-static void send_ipi_message(const struct cpumask *mask, enum ipi_msg_type msg)
+void __init smp_prepare_cpus(unsigned int max_cpus)
 {
-	unsigned long flags;
-	unsigned int cpu;
-
-	local_irq_save(flags);
+	unsigned int ncores = num_possible_cpus();
 
-	for_each_cpu(cpu, mask) {
-		struct ipi_data *ipi = &per_cpu(ipi_data, cpu);
-
-		spin_lock(&ipi->lock);
-		ipi->bits |= 1 << msg;
-		spin_unlock(&ipi->lock);
-	}
+	smp_store_cpu_info(smp_processor_id());
 
 	/*
-	 * Call the platform specific cross-CPU call function.
+	 * are we trying to boot more cores than exist?
 	 */
-	smp_cross_call(mask);
+	if (max_cpus > ncores)
+		max_cpus = ncores;
+
+	if (max_cpus > 1) {
+		/*
+		 * Enable the local timer or broadcast device for the
+		 * boot CPU, but only if we have more than one CPU.
+		 */
+		percpu_timer_setup();
 
-	local_irq_restore(flags);
+		/*
+		 * Initialise the SCU if there are more than one CPU
+		 * and let them know where to start.
+		 */
+		platform_smp_prepare_cpus(max_cpus);
+	}
 }
 
 void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 {
-	send_ipi_message(mask, IPI_CALL_FUNC);
+	smp_cross_call(mask, IPI_CALL_FUNC);
 }
 
 void arch_send_call_function_single_ipi(int cpu)
 {
-	send_ipi_message(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
+	smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
 }
 
-void show_ipi_list(struct seq_file *p)
+static const char *ipi_types[NR_IPI] = {
+#define S(x,s)	[x - IPI_TIMER] = s
+	S(IPI_TIMER, "Timer broadcast interrupts"),
+	S(IPI_RESCHEDULE, "Rescheduling interrupts"),
+	S(IPI_CALL_FUNC, "Function call interrupts"),
+	S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"),
+	S(IPI_CPU_STOP, "CPU stop interrupts"),
+};
+
+void show_ipi_list(struct seq_file *p, int prec)
 {
-	unsigned int cpu;
+	unsigned int cpu, i;
 
-	seq_puts(p, "IPI:");
+	for (i = 0; i < NR_IPI; i++) {
+		seq_printf(p, "%*s%u: ", prec - 1, "IPI", i);
 
-	for_each_present_cpu(cpu)
-		seq_printf(p, " %10lu", per_cpu(ipi_data, cpu).ipi_count);
+		for_each_present_cpu(cpu)
+			seq_printf(p, "%10u ",
+				   __get_irq_stat(cpu, ipi_irqs[i]));
 
-	seq_putc(p, '\n');
+		seq_printf(p, " %s\n", ipi_types[i]);
+	}
 }
 
-void show_local_irqs(struct seq_file *p)
+u64 smp_irq_stat_cpu(unsigned int cpu)
 {
-	unsigned int cpu;
+	u64 sum = 0;
+	int i;
 
-	seq_printf(p, "LOC: ");
+	for (i = 0; i < NR_IPI; i++)
+		sum += __get_irq_stat(cpu, ipi_irqs[i]);
 
-	for_each_present_cpu(cpu)
-		seq_printf(p, "%10u ", irq_stat[cpu].local_timer_irqs);
+#ifdef CONFIG_LOCAL_TIMERS
+	sum += __get_irq_stat(cpu, local_timer_irqs);
+#endif
 
-	seq_putc(p, '\n');
+	return sum;
 }
 
 /*
@@ -463,18 +481,30 @@ asmlinkage void __exception do_local_timer(struct pt_regs *regs)
 	int cpu = smp_processor_id();
 
 	if (local_timer_ack()) {
-		irq_stat[cpu].local_timer_irqs++;
+		__inc_irq_stat(cpu, local_timer_irqs);
 		ipi_timer();
 	}
 
 	set_irq_regs(old_regs);
 }
+
+void show_local_irqs(struct seq_file *p, int prec)
+{
+	unsigned int cpu;
+
+	seq_printf(p, "%*s: ", prec, "LOC");
+
+	for_each_present_cpu(cpu)
+		seq_printf(p, "%10u ", __get_irq_stat(cpu, local_timer_irqs));
+
+	seq_printf(p, " Local timer interrupts\n");
+}
 #endif
 
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 static void smp_timer_broadcast(const struct cpumask *mask)
 {
-	send_ipi_message(mask, IPI_TIMER);
+	smp_cross_call(mask, IPI_TIMER);
 }
 #else
 #define smp_timer_broadcast	NULL
@@ -511,6 +541,21 @@ void __cpuinit percpu_timer_setup(void)
 	local_timer_setup(evt);
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+/*
+ * The generic clock events code purposely does not stop the local timer
+ * on CPU_DEAD/CPU_DEAD_FROZEN hotplug events, so we have to do it
+ * manually here.
+ */
+static void percpu_timer_stop(void)
+{
+	unsigned int cpu = smp_processor_id();
+	struct clock_event_device *evt = &per_cpu(percpu_clockevent, cpu);
+
+	evt->set_mode(CLOCK_EVT_MODE_UNUSED, evt);
+}
+#endif
+
 static DEFINE_SPINLOCK(stop_lock);
 
 /*
@@ -537,216 +582,76 @@ static void ipi_cpu_stop(unsigned int cpu)
 
 /*
  * Main handler for inter-processor interrupts
- *
- * For ARM, the ipimask now only identifies a single
- * category of IPI (Bit 1 IPIs have been replaced by a
- * different mechanism):
- *
- *  Bit 0 - Inter-processor function call
  */
-asmlinkage void __exception do_IPI(struct pt_regs *regs)
+asmlinkage void __exception do_IPI(int ipinr, struct pt_regs *regs)
 {
 	unsigned int cpu = smp_processor_id();
-	struct ipi_data *ipi = &per_cpu(ipi_data, cpu);
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
-	ipi->ipi_count++;
-
-	for (;;) {
-		unsigned long msgs;
+	if (ipinr >= IPI_TIMER && ipinr < IPI_TIMER + NR_IPI)
+		__inc_irq_stat(cpu, ipi_irqs[ipinr - IPI_TIMER]);
 
-		spin_lock(&ipi->lock);
-		msgs = ipi->bits;
-		ipi->bits = 0;
-		spin_unlock(&ipi->lock);
-
-		if (!msgs)
-			break;
-
-		do {
-			unsigned nextmsg;
-
-			nextmsg = msgs & -msgs;
-			msgs &= ~nextmsg;
-			nextmsg = ffz(~nextmsg);
-
-			switch (nextmsg) {
-			case IPI_TIMER:
-				ipi_timer();
-				break;
+	switch (ipinr) {
+	case IPI_TIMER:
+		ipi_timer();
+		break;
 
-			case IPI_RESCHEDULE:
-				/*
-				 * nothing more to do - eveything is
-				 * done on the interrupt return path
-				 */
-				break;
+	case IPI_RESCHEDULE:
+		/*
+		 * nothing more to do - eveything is
+		 * done on the interrupt return path
+		 */
+		break;
 
-			case IPI_CALL_FUNC:
-				generic_smp_call_function_interrupt();
-				break;
+	case IPI_CALL_FUNC:
+		generic_smp_call_function_interrupt();
+		break;
 
-			case IPI_CALL_FUNC_SINGLE:
-				generic_smp_call_function_single_interrupt();
-				break;
+	case IPI_CALL_FUNC_SINGLE:
+		generic_smp_call_function_single_interrupt();
+		break;
 
-			case IPI_CPU_STOP:
-				ipi_cpu_stop(cpu);
-				break;
+	case IPI_CPU_STOP:
+		ipi_cpu_stop(cpu);
+		break;
 
-			default:
-				printk(KERN_CRIT "CPU%u: Unknown IPI message 0x%x\n",
-				       cpu, nextmsg);
-				break;
-			}
-		} while (msgs);
+	default:
+		printk(KERN_CRIT "CPU%u: Unknown IPI message 0x%x\n",
+		       cpu, ipinr);
+		break;
 	}
-
 	set_irq_regs(old_regs);
 }
 
 void smp_send_reschedule(int cpu)
 {
-	send_ipi_message(cpumask_of(cpu), IPI_RESCHEDULE);
+	smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE);
 }
 
 void smp_send_stop(void)
 {
-	cpumask_t mask = cpu_online_map;
-	cpu_clear(smp_processor_id(), mask);
-	if (!cpus_empty(mask))
-		send_ipi_message(&mask, IPI_CPU_STOP);
-}
+	unsigned long timeout;
 
-/*
- * not supported here
- */
-int setup_profiling_timer(unsigned int multiplier)
-{
-	return -EINVAL;
-}
+	if (num_online_cpus() > 1) {
+		cpumask_t mask = cpu_online_map;
+		cpu_clear(smp_processor_id(), mask);
 
-static void
-on_each_cpu_mask(void (*func)(void *), void *info, int wait,
-		const struct cpumask *mask)
-{
-	preempt_disable();
+		smp_cross_call(&mask, IPI_CPU_STOP);
+	}
 
-	smp_call_function_many(mask, func, info, wait);
-	if (cpumask_test_cpu(smp_processor_id(), mask))
-		func(info);
+	/* Wait up to one second for other CPUs to stop */
+	timeout = USEC_PER_SEC;
+	while (num_online_cpus() > 1 && timeout--)
+		udelay(1);
 
-	preempt_enable();
+	if (num_online_cpus() > 1)
+		pr_warning("SMP: failed to stop secondary CPUs\n");
 }
 
-/**********************************************************************/
-
 /*
- * TLB operations
+ * not supported here
  */
-struct tlb_args {
-	struct vm_area_struct *ta_vma;
-	unsigned long ta_start;
-	unsigned long ta_end;
-};
-
-static inline void ipi_flush_tlb_all(void *ignored)
-{
-	local_flush_tlb_all();
-}
-
-static inline void ipi_flush_tlb_mm(void *arg)
-{
-	struct mm_struct *mm = (struct mm_struct *)arg;
-
-	local_flush_tlb_mm(mm);
-}
-
-static inline void ipi_flush_tlb_page(void *arg)
-{
-	struct tlb_args *ta = (struct tlb_args *)arg;
-
-	local_flush_tlb_page(ta->ta_vma, ta->ta_start);
-}
-
-static inline void ipi_flush_tlb_kernel_page(void *arg)
-{
-	struct tlb_args *ta = (struct tlb_args *)arg;
-
-	local_flush_tlb_kernel_page(ta->ta_start);
-}
-
-static inline void ipi_flush_tlb_range(void *arg)
-{
-	struct tlb_args *ta = (struct tlb_args *)arg;
-
-	local_flush_tlb_range(ta->ta_vma, ta->ta_start, ta->ta_end);
-}
-
-static inline void ipi_flush_tlb_kernel_range(void *arg)
-{
-	struct tlb_args *ta = (struct tlb_args *)arg;
-
-	local_flush_tlb_kernel_range(ta->ta_start, ta->ta_end);
-}
-
-void flush_tlb_all(void)
-{
-	if (tlb_ops_need_broadcast())
-		on_each_cpu(ipi_flush_tlb_all, NULL, 1);
-	else
-		local_flush_tlb_all();
-}
-
-void flush_tlb_mm(struct mm_struct *mm)
-{
-	if (tlb_ops_need_broadcast())
-		on_each_cpu_mask(ipi_flush_tlb_mm, mm, 1, mm_cpumask(mm));
-	else
-		local_flush_tlb_mm(mm);
-}
-
-void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
-{
-	if (tlb_ops_need_broadcast()) {
-		struct tlb_args ta;
-		ta.ta_vma = vma;
-		ta.ta_start = uaddr;
-		on_each_cpu_mask(ipi_flush_tlb_page, &ta, 1, mm_cpumask(vma->vm_mm));
-	} else
-		local_flush_tlb_page(vma, uaddr);
-}
-
-void flush_tlb_kernel_page(unsigned long kaddr)
-{
-	if (tlb_ops_need_broadcast()) {
-		struct tlb_args ta;
-		ta.ta_start = kaddr;
-		on_each_cpu(ipi_flush_tlb_kernel_page, &ta, 1);
-	} else
-		local_flush_tlb_kernel_page(kaddr);
-}
-
-void flush_tlb_range(struct vm_area_struct *vma,
-                     unsigned long start, unsigned long end)
-{
-	if (tlb_ops_need_broadcast()) {
-		struct tlb_args ta;
-		ta.ta_vma = vma;
-		ta.ta_start = start;
-		ta.ta_end = end;
-		on_each_cpu_mask(ipi_flush_tlb_range, &ta, 1, mm_cpumask(vma->vm_mm));
-	} else
-		local_flush_tlb_range(vma, start, end);
-}
-
-void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+int setup_profiling_timer(unsigned int multiplier)
 {
-	if (tlb_ops_need_broadcast()) {
-		struct tlb_args ta;
-		ta.ta_start = start;
-		ta.ta_end = end;
-		on_each_cpu(ipi_flush_tlb_kernel_range, &ta, 1);
-	} else
-		local_flush_tlb_kernel_range(start, end);
+	return -EINVAL;
 }
diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c
new file mode 100644
index 000000000000..7dcb35285be7
--- /dev/null
+++ b/arch/arm/kernel/smp_tlb.c
@@ -0,0 +1,139 @@
+/*
+ *  linux/arch/arm/kernel/smp_tlb.c
+ *
+ *  Copyright (C) 2002 ARM Limited, All Rights Reserved.
+ *
+ * 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/preempt.h>
+#include <linux/smp.h>
+
+#include <asm/smp_plat.h>
+#include <asm/tlbflush.h>
+
+static void on_each_cpu_mask(void (*func)(void *), void *info, int wait,
+	const struct cpumask *mask)
+{
+	preempt_disable();
+
+	smp_call_function_many(mask, func, info, wait);
+	if (cpumask_test_cpu(smp_processor_id(), mask))
+		func(info);
+
+	preempt_enable();
+}
+
+/**********************************************************************/
+
+/*
+ * TLB operations
+ */
+struct tlb_args {
+	struct vm_area_struct *ta_vma;
+	unsigned long ta_start;
+	unsigned long ta_end;
+};
+
+static inline void ipi_flush_tlb_all(void *ignored)
+{
+	local_flush_tlb_all();
+}
+
+static inline void ipi_flush_tlb_mm(void *arg)
+{
+	struct mm_struct *mm = (struct mm_struct *)arg;
+
+	local_flush_tlb_mm(mm);
+}
+
+static inline void ipi_flush_tlb_page(void *arg)
+{
+	struct tlb_args *ta = (struct tlb_args *)arg;
+
+	local_flush_tlb_page(ta->ta_vma, ta->ta_start);
+}
+
+static inline void ipi_flush_tlb_kernel_page(void *arg)
+{
+	struct tlb_args *ta = (struct tlb_args *)arg;
+
+	local_flush_tlb_kernel_page(ta->ta_start);
+}
+
+static inline void ipi_flush_tlb_range(void *arg)
+{
+	struct tlb_args *ta = (struct tlb_args *)arg;
+
+	local_flush_tlb_range(ta->ta_vma, ta->ta_start, ta->ta_end);
+}
+
+static inline void ipi_flush_tlb_kernel_range(void *arg)
+{
+	struct tlb_args *ta = (struct tlb_args *)arg;
+
+	local_flush_tlb_kernel_range(ta->ta_start, ta->ta_end);
+}
+
+void flush_tlb_all(void)
+{
+	if (tlb_ops_need_broadcast())
+		on_each_cpu(ipi_flush_tlb_all, NULL, 1);
+	else
+		local_flush_tlb_all();
+}
+
+void flush_tlb_mm(struct mm_struct *mm)
+{
+	if (tlb_ops_need_broadcast())
+		on_each_cpu_mask(ipi_flush_tlb_mm, mm, 1, mm_cpumask(mm));
+	else
+		local_flush_tlb_mm(mm);
+}
+
+void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
+{
+	if (tlb_ops_need_broadcast()) {
+		struct tlb_args ta;
+		ta.ta_vma = vma;
+		ta.ta_start = uaddr;
+		on_each_cpu_mask(ipi_flush_tlb_page, &ta, 1, mm_cpumask(vma->vm_mm));
+	} else
+		local_flush_tlb_page(vma, uaddr);
+}
+
+void flush_tlb_kernel_page(unsigned long kaddr)
+{
+	if (tlb_ops_need_broadcast()) {
+		struct tlb_args ta;
+		ta.ta_start = kaddr;
+		on_each_cpu(ipi_flush_tlb_kernel_page, &ta, 1);
+	} else
+		local_flush_tlb_kernel_page(kaddr);
+}
+
+void flush_tlb_range(struct vm_area_struct *vma,
+                     unsigned long start, unsigned long end)
+{
+	if (tlb_ops_need_broadcast()) {
+		struct tlb_args ta;
+		ta.ta_vma = vma;
+		ta.ta_start = start;
+		ta.ta_end = end;
+		on_each_cpu_mask(ipi_flush_tlb_range, &ta, 1, mm_cpumask(vma->vm_mm));
+	} else
+		local_flush_tlb_range(vma, start, end);
+}
+
+void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	if (tlb_ops_need_broadcast()) {
+		struct tlb_args ta;
+		ta.ta_start = start;
+		ta.ta_end = end;
+		on_each_cpu(ipi_flush_tlb_kernel_range, &ta, 1);
+	} else
+		local_flush_tlb_kernel_range(start, end);
+}
+
diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
index 35882fbf37f9..24585d97c104 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -150,13 +150,3 @@ void __cpuinit twd_timer_setup(struct clock_event_device *clk)
 
 	clockevents_register_device(clk);
 }
-
-#ifdef CONFIG_HOTPLUG_CPU
-/*
- * take a local timer down
- */
-void twd_timer_stop(void)
-{
-	__raw_writel(0, twd_base + TWD_TIMER_CONTROL);
-}
-#endif
diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c
index 20b7411e47fd..c2e112e1a05f 100644
--- a/arch/arm/kernel/stacktrace.c
+++ b/arch/arm/kernel/stacktrace.c
@@ -28,7 +28,7 @@ int notrace unwind_frame(struct stackframe *frame)
 
 	/* only go to a higher address on the stack */
 	low = frame->sp;
-	high = ALIGN(low, THREAD_SIZE) + THREAD_SIZE;
+	high = ALIGN(low, THREAD_SIZE);
 
 	/* check current frame pointer is within bounds */
 	if (fp < (low + 12) || fp + 4 >= high)
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 87abca018054..e02f4f7537c5 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -55,10 +55,7 @@ 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
-	char sym1[KSYM_SYMBOL_LEN], sym2[KSYM_SYMBOL_LEN];
-	sprint_symbol(sym1, where);
-	sprint_symbol(sym2, from);
-	printk("[<%08lx>] (%s) from [<%08lx>] (%s)\n", where, sym1, from, sym2);
+	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
diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c
index 2a161765f6d5..d2cb0b3c9872 100644
--- a/arch/arm/kernel/unwind.c
+++ b/arch/arm/kernel/unwind.c
@@ -279,7 +279,7 @@ int unwind_frame(struct stackframe *frame)
 
 	/* only go to a higher address on the stack */
 	low = frame->sp;
-	high = ALIGN(low, THREAD_SIZE) + THREAD_SIZE;
+	high = ALIGN(low, THREAD_SIZE);
 
 	pr_debug("%s(pc = %08lx lr = %08lx sp = %08lx)\n", __func__,
 		 frame->pc, frame->lr, frame->sp);