Merge branch 'fixes' into for-linus

Conflicts:
	arch/arm/kernel/smp.c

26 files changed, 1157 insertions, 978 deletions

diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 49b61a3f5b2..5bbec7b8183 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -19,9 +19,10 @@ obj-y		:= elf.o entry-armv.o entry-common.o irq.o opcodes.o \
 		   process.o ptrace.o return_address.o sched_clock.o \
 		   setup.o signal.o stacktrace.o sys_arm.o time.o traps.o
 
-obj-$(CONFIG_DEPRECATED_PARAM_STRUCT) += compat.o
+obj-$(CONFIG_ATAGS)		+= atags_parse.o
+obj-$(CONFIG_ATAGS_PROC)	+= atags_proc.o
+obj-$(CONFIG_DEPRECATED_PARAM_STRUCT) += atags_compat.o
 
-obj-$(CONFIG_LEDS)		+= leds.o
 obj-$(CONFIG_OC_ETM)		+= etm.o
 obj-$(CONFIG_CPU_IDLE)		+= cpuidle.o
 obj-$(CONFIG_ISA_DMA_API)	+= dma.o
@@ -52,7 +53,6 @@ test-kprobes-objs		+= kprobes-test-thumb.o
 else
 test-kprobes-objs		+= kprobes-test-arm.o
 endif
-obj-$(CONFIG_ATAGS_PROC)	+= atags.o
 obj-$(CONFIG_OABI_COMPAT)	+= sys_oabi-compat.o
 obj-$(CONFIG_ARM_THUMBEE)	+= thumbee.o
 obj-$(CONFIG_KGDB)		+= kgdb.o
@@ -69,8 +69,7 @@ obj-$(CONFIG_CPU_XSC3)		+= xscale-cp0.o
 obj-$(CONFIG_CPU_MOHAWK)	+= xscale-cp0.o
 obj-$(CONFIG_CPU_PJ4)		+= pj4-cp0.o
 obj-$(CONFIG_IWMMXT)		+= iwmmxt.o
-obj-$(CONFIG_CPU_HAS_PMU)	+= pmu.o
-obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o
+obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o perf_event_cpu.o
 AFLAGS_iwmmxt.o			:= -Wa,-mcpu=iwmmxt
 obj-$(CONFIG_ARM_CPU_TOPOLOGY)  += topology.o
 
diff --git a/arch/arm/kernel/arch_timer.c b/arch/arm/kernel/arch_timer.c
index cf258807160..c8ef20747ee 100644
--- a/arch/arm/kernel/arch_timer.c
+++ b/arch/arm/kernel/arch_timer.c
@@ -21,18 +21,28 @@
 #include <linux/io.h>
 
 #include <asm/cputype.h>
+#include <asm/delay.h>
 #include <asm/localtimer.h>
 #include <asm/arch_timer.h>
 #include <asm/system_info.h>
 #include <asm/sched_clock.h>
 
 static unsigned long arch_timer_rate;
-static int arch_timer_ppi;
-static int arch_timer_ppi2;
+
+enum ppi_nr {
+	PHYS_SECURE_PPI,
+	PHYS_NONSECURE_PPI,
+	VIRT_PPI,
+	HYP_PPI,
+	MAX_TIMER_PPI
+};
+
+static int arch_timer_ppi[MAX_TIMER_PPI];
 
 static struct clock_event_device __percpu **arch_timer_evt;
+static struct delay_timer arch_delay_timer;
 
-extern void init_current_timer_delay(unsigned long freq);
+static bool arch_timer_use_virtual = true;
 
 /*
  * Architected system timer support.
@@ -46,50 +56,104 @@ extern void init_current_timer_delay(unsigned long freq);
 #define ARCH_TIMER_REG_FREQ		1
 #define ARCH_TIMER_REG_TVAL		2
 
-static void arch_timer_reg_write(int reg, u32 val)
+#define ARCH_TIMER_PHYS_ACCESS		0
+#define ARCH_TIMER_VIRT_ACCESS		1
+
+/*
+ * These register accessors are marked inline so the compiler can
+ * nicely work out which register we want, and chuck away the rest of
+ * the code. At least it does so with a recent GCC (4.6.3).
+ */
+static inline void arch_timer_reg_write(const int access, const int reg, u32 val)
 {
-	switch (reg) {
-	case ARCH_TIMER_REG_CTRL:
-		asm volatile("mcr p15, 0, %0, c14, c2, 1" : : "r" (val));
-		break;
-	case ARCH_TIMER_REG_TVAL:
-		asm volatile("mcr p15, 0, %0, c14, c2, 0" : : "r" (val));
-		break;
+	if (access == ARCH_TIMER_PHYS_ACCESS) {
+		switch (reg) {
+		case ARCH_TIMER_REG_CTRL:
+			asm volatile("mcr p15, 0, %0, c14, c2, 1" : : "r" (val));
+			break;
+		case ARCH_TIMER_REG_TVAL:
+			asm volatile("mcr p15, 0, %0, c14, c2, 0" : : "r" (val));
+			break;
+		}
+	}
+
+	if (access == ARCH_TIMER_VIRT_ACCESS) {
+		switch (reg) {
+		case ARCH_TIMER_REG_CTRL:
+			asm volatile("mcr p15, 0, %0, c14, c3, 1" : : "r" (val));
+			break;
+		case ARCH_TIMER_REG_TVAL:
+			asm volatile("mcr p15, 0, %0, c14, c3, 0" : : "r" (val));
+			break;
+		}
 	}
 
 	isb();
 }
 
-static u32 arch_timer_reg_read(int reg)
+static inline u32 arch_timer_reg_read(const int access, const int reg)
 {
-	u32 val;
+	u32 val = 0;
+
+	if (access == ARCH_TIMER_PHYS_ACCESS) {
+		switch (reg) {
+		case ARCH_TIMER_REG_CTRL:
+			asm volatile("mrc p15, 0, %0, c14, c2, 1" : "=r" (val));
+			break;
+		case ARCH_TIMER_REG_TVAL:
+			asm volatile("mrc p15, 0, %0, c14, c2, 0" : "=r" (val));
+			break;
+		case ARCH_TIMER_REG_FREQ:
+			asm volatile("mrc p15, 0, %0, c14, c0, 0" : "=r" (val));
+			break;
+		}
+	}
 
-	switch (reg) {
-	case ARCH_TIMER_REG_CTRL:
-		asm volatile("mrc p15, 0, %0, c14, c2, 1" : "=r" (val));
-		break;
-	case ARCH_TIMER_REG_FREQ:
-		asm volatile("mrc p15, 0, %0, c14, c0, 0" : "=r" (val));
-		break;
-	case ARCH_TIMER_REG_TVAL:
-		asm volatile("mrc p15, 0, %0, c14, c2, 0" : "=r" (val));
-		break;
-	default:
-		BUG();
+	if (access == ARCH_TIMER_VIRT_ACCESS) {
+		switch (reg) {
+		case ARCH_TIMER_REG_CTRL:
+			asm volatile("mrc p15, 0, %0, c14, c3, 1" : "=r" (val));
+			break;
+		case ARCH_TIMER_REG_TVAL:
+			asm volatile("mrc p15, 0, %0, c14, c3, 0" : "=r" (val));
+			break;
+		}
 	}
 
 	return val;
 }
 
-static irqreturn_t arch_timer_handler(int irq, void *dev_id)
+static inline cycle_t arch_timer_counter_read(const int access)
 {
-	struct clock_event_device *evt = *(struct clock_event_device **)dev_id;
-	unsigned long ctrl;
+	cycle_t cval = 0;
+
+	if (access == ARCH_TIMER_PHYS_ACCESS)
+		asm volatile("mrrc p15, 0, %Q0, %R0, c14" : "=r" (cval));
+
+	if (access == ARCH_TIMER_VIRT_ACCESS)
+		asm volatile("mrrc p15, 1, %Q0, %R0, c14" : "=r" (cval));
+
+	return cval;
+}
+
+static inline cycle_t arch_counter_get_cntpct(void)
+{
+	return arch_timer_counter_read(ARCH_TIMER_PHYS_ACCESS);
+}
 
-	ctrl = arch_timer_reg_read(ARCH_TIMER_REG_CTRL);
+static inline cycle_t arch_counter_get_cntvct(void)
+{
+	return arch_timer_counter_read(ARCH_TIMER_VIRT_ACCESS);
+}
+
+static irqreturn_t inline timer_handler(const int access,
+					struct clock_event_device *evt)
+{
+	unsigned long ctrl;
+	ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL);
 	if (ctrl & ARCH_TIMER_CTRL_IT_STAT) {
 		ctrl |= ARCH_TIMER_CTRL_IT_MASK;
-		arch_timer_reg_write(ARCH_TIMER_REG_CTRL, ctrl);
+		arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl);
 		evt->event_handler(evt);
 		return IRQ_HANDLED;
 	}
@@ -97,63 +161,100 @@ static irqreturn_t arch_timer_handler(int irq, void *dev_id)
 	return IRQ_NONE;
 }
 
-static void arch_timer_disable(void)
+static irqreturn_t arch_timer_handler_virt(int irq, void *dev_id)
 {
-	unsigned long ctrl;
+	struct clock_event_device *evt = *(struct clock_event_device **)dev_id;
 
-	ctrl = arch_timer_reg_read(ARCH_TIMER_REG_CTRL);
-	ctrl &= ~ARCH_TIMER_CTRL_ENABLE;
-	arch_timer_reg_write(ARCH_TIMER_REG_CTRL, ctrl);
+	return timer_handler(ARCH_TIMER_VIRT_ACCESS, evt);
 }
 
-static void arch_timer_set_mode(enum clock_event_mode mode,
-				struct clock_event_device *clk)
+static irqreturn_t arch_timer_handler_phys(int irq, void *dev_id)
 {
+	struct clock_event_device *evt = *(struct clock_event_device **)dev_id;
+
+	return timer_handler(ARCH_TIMER_PHYS_ACCESS, evt);
+}
+
+static inline void timer_set_mode(const int access, int mode)
+{
+	unsigned long ctrl;
 	switch (mode) {
 	case CLOCK_EVT_MODE_UNUSED:
 	case CLOCK_EVT_MODE_SHUTDOWN:
-		arch_timer_disable();
+		ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL);
+		ctrl &= ~ARCH_TIMER_CTRL_ENABLE;
+		arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl);
 		break;
 	default:
 		break;
 	}
 }
 
-static int arch_timer_set_next_event(unsigned long evt,
-				     struct clock_event_device *unused)
+static void arch_timer_set_mode_virt(enum clock_event_mode mode,
+				     struct clock_event_device *clk)
 {
-	unsigned long ctrl;
+	timer_set_mode(ARCH_TIMER_VIRT_ACCESS, mode);
+}
 
-	ctrl = arch_timer_reg_read(ARCH_TIMER_REG_CTRL);
+static void arch_timer_set_mode_phys(enum clock_event_mode mode,
+				     struct clock_event_device *clk)
+{
+	timer_set_mode(ARCH_TIMER_PHYS_ACCESS, mode);
+}
+
+static inline void set_next_event(const int access, unsigned long evt)
+{
+	unsigned long ctrl;
+	ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL);
 	ctrl |= ARCH_TIMER_CTRL_ENABLE;
 	ctrl &= ~ARCH_TIMER_CTRL_IT_MASK;
+	arch_timer_reg_write(access, ARCH_TIMER_REG_TVAL, evt);
+	arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl);
+}
 
-	arch_timer_reg_write(ARCH_TIMER_REG_TVAL, evt);
-	arch_timer_reg_write(ARCH_TIMER_REG_CTRL, ctrl);
+static int arch_timer_set_next_event_virt(unsigned long evt,
+					  struct clock_event_device *unused)
+{
+	set_next_event(ARCH_TIMER_VIRT_ACCESS, evt);
+	return 0;
+}
 
+static int arch_timer_set_next_event_phys(unsigned long evt,
+					  struct clock_event_device *unused)
+{
+	set_next_event(ARCH_TIMER_PHYS_ACCESS, evt);
 	return 0;
 }
 
 static int __cpuinit arch_timer_setup(struct clock_event_device *clk)
 {
-	/* Be safe... */
-	arch_timer_disable();
-
 	clk->features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP;
 	clk->name = "arch_sys_timer";
 	clk->rating = 450;
-	clk->set_mode = arch_timer_set_mode;
-	clk->set_next_event = arch_timer_set_next_event;
-	clk->irq = arch_timer_ppi;
+	if (arch_timer_use_virtual) {
+		clk->irq = arch_timer_ppi[VIRT_PPI];
+		clk->set_mode = arch_timer_set_mode_virt;
+		clk->set_next_event = arch_timer_set_next_event_virt;
+	} else {
+		clk->irq = arch_timer_ppi[PHYS_SECURE_PPI];
+		clk->set_mode = arch_timer_set_mode_phys;
+		clk->set_next_event = arch_timer_set_next_event_phys;
+	}
+
+	clk->set_mode(CLOCK_EVT_MODE_SHUTDOWN, NULL);
 
 	clockevents_config_and_register(clk, arch_timer_rate,
 					0xf, 0x7fffffff);
 
 	*__this_cpu_ptr(arch_timer_evt) = clk;
 
-	enable_percpu_irq(clk->irq, 0);
-	if (arch_timer_ppi2)
-		enable_percpu_irq(arch_timer_ppi2, 0);
+	if (arch_timer_use_virtual)
+		enable_percpu_irq(arch_timer_ppi[VIRT_PPI], 0);
+	else {
+		enable_percpu_irq(arch_timer_ppi[PHYS_SECURE_PPI], 0);
+		if (arch_timer_ppi[PHYS_NONSECURE_PPI])
+			enable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI], 0);
+	}
 
 	return 0;
 }
@@ -173,8 +274,8 @@ static int arch_timer_available(void)
 		return -ENXIO;
 
 	if (arch_timer_rate == 0) {
-		arch_timer_reg_write(ARCH_TIMER_REG_CTRL, 0);
-		freq = arch_timer_reg_read(ARCH_TIMER_REG_FREQ);
+		freq = arch_timer_reg_read(ARCH_TIMER_PHYS_ACCESS,
+					   ARCH_TIMER_REG_FREQ);
 
 		/* Check the timer frequency. */
 		if (freq == 0) {
@@ -185,52 +286,57 @@ static int arch_timer_available(void)
 		arch_timer_rate = freq;
 	}
 
-	pr_info_once("Architected local timer running at %lu.%02luMHz.\n",
-		     arch_timer_rate / 1000000, (arch_timer_rate / 10000) % 100);
+	pr_info_once("Architected local timer running at %lu.%02luMHz (%s).\n",
+		     arch_timer_rate / 1000000, (arch_timer_rate / 10000) % 100,
+		     arch_timer_use_virtual ? "virt" : "phys");
 	return 0;
 }
 
-static inline cycle_t arch_counter_get_cntpct(void)
+static u32 notrace arch_counter_get_cntpct32(void)
 {
-	u32 cvall, cvalh;
-
-	asm volatile("mrrc p15, 0, %0, %1, c14" : "=r" (cvall), "=r" (cvalh));
+	cycle_t cnt = arch_counter_get_cntpct();
 
-	return ((cycle_t) cvalh << 32) | cvall;
-}
-
-static inline cycle_t arch_counter_get_cntvct(void)
-{
-	u32 cvall, cvalh;
-
-	asm volatile("mrrc p15, 1, %0, %1, c14" : "=r" (cvall), "=r" (cvalh));
-
-	return ((cycle_t) cvalh << 32) | cvall;
+	/*
+	 * The sched_clock infrastructure only knows about counters
+	 * with at most 32bits. Forget about the upper 24 bits for the
+	 * time being...
+	 */
+	return (u32)cnt;
 }
 
 static u32 notrace arch_counter_get_cntvct32(void)
 {
-	cycle_t cntvct = arch_counter_get_cntvct();
+	cycle_t cnt = arch_counter_get_cntvct();
 
 	/*
 	 * The sched_clock infrastructure only knows about counters
 	 * with at most 32bits. Forget about the upper 24 bits for the
 	 * time being...
 	 */
-	return (u32)(cntvct & (u32)~0);
+	return (u32)cnt;
 }
 
 static cycle_t arch_counter_read(struct clocksource *cs)
 {
+	/*
+	 * Always use the physical counter for the clocksource.
+	 * CNTHCTL.PL1PCTEN must be set to 1.
+	 */
 	return arch_counter_get_cntpct();
 }
 
-int read_current_timer(unsigned long *timer_val)
+static unsigned long arch_timer_read_current_timer(void)
 {
-	if (!arch_timer_rate)
-		return -ENXIO;
-	*timer_val = arch_counter_get_cntpct();
-	return 0;
+	return arch_counter_get_cntpct();
+}
+
+static cycle_t arch_counter_read_cc(const struct cyclecounter *cc)
+{
+	/*
+	 * Always use the physical counter for the clocksource.
+	 * CNTHCTL.PL1PCTEN must be set to 1.
+	 */
+	return arch_counter_get_cntpct();
 }
 
 static struct clocksource clocksource_counter = {
@@ -241,14 +347,32 @@ static struct clocksource clocksource_counter = {
 	.flags	= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
+static struct cyclecounter cyclecounter = {
+	.read	= arch_counter_read_cc,
+	.mask	= CLOCKSOURCE_MASK(56),
+};
+
+static struct timecounter timecounter;
+
+struct timecounter *arch_timer_get_timecounter(void)
+{
+	return &timecounter;
+}
+
 static void __cpuinit arch_timer_stop(struct clock_event_device *clk)
 {
 	pr_debug("arch_timer_teardown disable IRQ%d cpu #%d\n",
 		 clk->irq, smp_processor_id());
-	disable_percpu_irq(clk->irq);
-	if (arch_timer_ppi2)
-		disable_percpu_irq(arch_timer_ppi2);
-	arch_timer_set_mode(CLOCK_EVT_MODE_UNUSED, clk);
+
+	if (arch_timer_use_virtual)
+		disable_percpu_irq(arch_timer_ppi[VIRT_PPI]);
+	else {
+		disable_percpu_irq(arch_timer_ppi[PHYS_SECURE_PPI]);
+		if (arch_timer_ppi[PHYS_NONSECURE_PPI])
+			disable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI]);
+	}
+
+	clk->set_mode(CLOCK_EVT_MODE_UNUSED, clk);
 }
 
 static struct local_timer_ops arch_timer_ops __cpuinitdata = {
@@ -261,36 +385,48 @@ static struct clock_event_device arch_timer_global_evt;
 static int __init arch_timer_register(void)
 {
 	int err;
+	int ppi;
 
 	err = arch_timer_available();
 	if (err)
-		return err;
+		goto out;
 
 	arch_timer_evt = alloc_percpu(struct clock_event_device *);
-	if (!arch_timer_evt)
-		return -ENOMEM;
+	if (!arch_timer_evt) {
+		err = -ENOMEM;
+		goto out;
+	}
 
 	clocksource_register_hz(&clocksource_counter, arch_timer_rate);
+	cyclecounter.mult = clocksource_counter.mult;
+	cyclecounter.shift = clocksource_counter.shift;
+	timecounter_init(&timecounter, &cyclecounter,
+			 arch_counter_get_cntpct());
+
+	if (arch_timer_use_virtual) {
+		ppi = arch_timer_ppi[VIRT_PPI];
+		err = request_percpu_irq(ppi, arch_timer_handler_virt,
+					 "arch_timer", arch_timer_evt);
+	} else {
+		ppi = arch_timer_ppi[PHYS_SECURE_PPI];
+		err = request_percpu_irq(ppi, arch_timer_handler_phys,
+					 "arch_timer", arch_timer_evt);
+		if (!err && arch_timer_ppi[PHYS_NONSECURE_PPI]) {
+			ppi = arch_timer_ppi[PHYS_NONSECURE_PPI];
+			err = request_percpu_irq(ppi, arch_timer_handler_phys,
+						 "arch_timer", arch_timer_evt);
+			if (err)
+				free_percpu_irq(arch_timer_ppi[PHYS_SECURE_PPI],
+						arch_timer_evt);
+		}
+	}
 
-	err = request_percpu_irq(arch_timer_ppi, arch_timer_handler,
-				 "arch_timer", arch_timer_evt);
 	if (err) {
 		pr_err("arch_timer: can't register interrupt %d (%d)\n",
-		       arch_timer_ppi, err);
+		       ppi, err);
 		goto out_free;
 	}
 
-	if (arch_timer_ppi2) {
-		err = request_percpu_irq(arch_timer_ppi2, arch_timer_handler,
-					 "arch_timer", arch_timer_evt);
-		if (err) {
-			pr_err("arch_timer: can't register interrupt %d (%d)\n",
-			       arch_timer_ppi2, err);
-			arch_timer_ppi2 = 0;
-			goto out_free_irq;
-		}
-	}
-
 	err = local_timer_register(&arch_timer_ops);
 	if (err) {
 		/*
@@ -302,21 +438,29 @@ static int __init arch_timer_register(void)
 		arch_timer_global_evt.cpumask = cpumask_of(0);
 		err = arch_timer_setup(&arch_timer_global_evt);
 	}
-
 	if (err)
 		goto out_free_irq;
 
-	init_current_timer_delay(arch_timer_rate);
+	/* Use the architected timer for the delay loop. */
+	arch_delay_timer.read_current_timer = &arch_timer_read_current_timer;
+	arch_delay_timer.freq = arch_timer_rate;
+	register_current_timer_delay(&arch_delay_timer);
 	return 0;
 
 out_free_irq:
-	free_percpu_irq(arch_timer_ppi, arch_timer_evt);
-	if (arch_timer_ppi2)
-		free_percpu_irq(arch_timer_ppi2, arch_timer_evt);
+	if (arch_timer_use_virtual)
+		free_percpu_irq(arch_timer_ppi[VIRT_PPI], arch_timer_evt);
+	else {
+		free_percpu_irq(arch_timer_ppi[PHYS_SECURE_PPI],
+				arch_timer_evt);
+		if (arch_timer_ppi[PHYS_NONSECURE_PPI])
+			free_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI],
+					arch_timer_evt);
+	}
 
 out_free:
 	free_percpu(arch_timer_evt);
-
+out:
 	return err;
 }
 
@@ -329,6 +473,7 @@ int __init arch_timer_of_register(void)
 {
 	struct device_node *np;
 	u32 freq;
+	int i;
 
 	np = of_find_matching_node(NULL, arch_timer_of_match);
 	if (!np) {
@@ -340,22 +485,40 @@ int __init arch_timer_of_register(void)
 	if (!of_property_read_u32(np, "clock-frequency", &freq))
 		arch_timer_rate = freq;
 
-	arch_timer_ppi = irq_of_parse_and_map(np, 0);
-	arch_timer_ppi2 = irq_of_parse_and_map(np, 1);
-	pr_info("arch_timer: found %s irqs %d %d\n",
-		np->name, arch_timer_ppi, arch_timer_ppi2);
+	for (i = PHYS_SECURE_PPI; i < MAX_TIMER_PPI; i++)
+		arch_timer_ppi[i] = irq_of_parse_and_map(np, i);
+
+	/*
+	 * If no interrupt provided for virtual timer, we'll have to
+	 * stick to the physical timer. It'd better be accessible...
+	 */
+	if (!arch_timer_ppi[VIRT_PPI]) {
+		arch_timer_use_virtual = false;
+
+		if (!arch_timer_ppi[PHYS_SECURE_PPI] ||
+		    !arch_timer_ppi[PHYS_NONSECURE_PPI]) {
+			pr_warn("arch_timer: No interrupt available, giving up\n");
+			return -EINVAL;
+		}
+	}
 
 	return arch_timer_register();
 }
 
 int __init arch_timer_sched_clock_init(void)
 {
+	u32 (*cnt32)(void);
 	int err;
 
 	err = arch_timer_available();
 	if (err)
 		return err;
 
-	setup_sched_clock(arch_counter_get_cntvct32, 32, arch_timer_rate);
+	if (arch_timer_use_virtual)
+		cnt32 = arch_counter_get_cntvct32;
+	else
+		cnt32 = arch_counter_get_cntpct32;
+
+	setup_sched_clock(cnt32, 32, arch_timer_rate);
 	return 0;
 }
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index 1429d8989fb..c985b481192 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -59,10 +59,12 @@ int main(void)
   DEFINE(TI_USED_CP,		offsetof(struct thread_info, used_cp));
   DEFINE(TI_TP_VALUE,		offsetof(struct thread_info, tp_value));
   DEFINE(TI_FPSTATE,		offsetof(struct thread_info, fpstate));
+#ifdef CONFIG_VFP
   DEFINE(TI_VFPSTATE,		offsetof(struct thread_info, vfpstate));
 #ifdef CONFIG_SMP
   DEFINE(VFP_CPU,		offsetof(union vfp_state, hard.cpu));
 #endif
+#endif
 #ifdef CONFIG_ARM_THUMBEE
   DEFINE(TI_THUMBEE_STATE,	offsetof(struct thread_info, thumbee_state));
 #endif
diff --git a/arch/arm/kernel/atags.h b/arch/arm/kernel/atags.h
index e5f028d214a..9edc9692332 100644
--- a/arch/arm/kernel/atags.h
+++ b/arch/arm/kernel/atags.h
@@ -3,3 +3,17 @@ extern void save_atags(struct tag *tags);
 #else
 static inline void save_atags(struct tag *tags) { }
 #endif
+
+void convert_to_tag_list(struct tag *tags);
+
+#ifdef CONFIG_ATAGS
+struct machine_desc *setup_machine_tags(phys_addr_t __atags_pointer, unsigned int machine_nr);
+#else
+static inline struct machine_desc *
+setup_machine_tags(phys_addr_t __atags_pointer, unsigned int machine_nr)
+{
+	early_print("no ATAGS support: can't continue\n");
+	while (true);
+	unreachable();
+}
+#endif
diff --git a/arch/arm/kernel/compat.c b/arch/arm/kernel/atags_compat.c
index 925652318b8..5236ad38f41 100644
--- a/arch/arm/kernel/compat.c
+++ b/arch/arm/kernel/atags_compat.c
@@ -1,5 +1,5 @@
 /*
- *  linux/arch/arm/kernel/compat.c
+ *  linux/arch/arm/kernel/atags_compat.c
  *
  *  Copyright (C) 2001 Russell King
  *
@@ -26,7 +26,7 @@
 
 #include <asm/mach/arch.h>
 
-#include "compat.h"
+#include "atags.h"
 
 /*
  * Usage:
diff --git a/arch/arm/kernel/atags_parse.c b/arch/arm/kernel/atags_parse.c
new file mode 100644
index 00000000000..14512e6931d
--- /dev/null
+++ b/arch/arm/kernel/atags_parse.c
@@ -0,0 +1,238 @@
+/*
+ * Tag parsing.
+ *
+ * Copyright (C) 1995-2001 Russell King
+ *
+ * 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.
+ */
+
+/*
+ * This is the traditional way of passing data to the kernel at boot time.  Rather
+ * than passing a fixed inflexible structure to the kernel, we pass a list
+ * of variable-sized tags to the kernel.  The first tag must be a ATAG_CORE
+ * tag for the list to be recognised (to distinguish the tagged list from
+ * a param_struct).  The list is terminated with a zero-length tag (this tag
+ * is not parsed in any way).
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/fs.h>
+#include <linux/root_dev.h>
+#include <linux/screen_info.h>
+
+#include <asm/setup.h>
+#include <asm/system_info.h>
+#include <asm/page.h>
+#include <asm/mach/arch.h>
+
+#include "atags.h"
+
+static char default_command_line[COMMAND_LINE_SIZE] __initdata = CONFIG_CMDLINE;
+
+#ifndef MEM_SIZE
+#define MEM_SIZE	(16*1024*1024)
+#endif
+
+static struct {
+	struct tag_header hdr1;
+	struct tag_core   core;
+	struct tag_header hdr2;
+	struct tag_mem32  mem;
+	struct tag_header hdr3;
+} default_tags __initdata = {
+	{ tag_size(tag_core), ATAG_CORE },
+	{ 1, PAGE_SIZE, 0xff },
+	{ tag_size(tag_mem32), ATAG_MEM },
+	{ MEM_SIZE },
+	{ 0, ATAG_NONE }
+};
+
+static int __init parse_tag_core(const struct tag *tag)
+{
+	if (tag->hdr.size > 2) {
+		if ((tag->u.core.flags & 1) == 0)
+			root_mountflags &= ~MS_RDONLY;
+		ROOT_DEV = old_decode_dev(tag->u.core.rootdev);
+	}
+	return 0;
+}
+
+__tagtable(ATAG_CORE, parse_tag_core);
+
+static int __init parse_tag_mem32(const struct tag *tag)
+{
+	return arm_add_memory(tag->u.mem.start, tag->u.mem.size);
+}
+
+__tagtable(ATAG_MEM, parse_tag_mem32);
+
+#if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_DUMMY_CONSOLE)
+static int __init parse_tag_videotext(const struct tag *tag)
+{
+	screen_info.orig_x            = tag->u.videotext.x;
+	screen_info.orig_y            = tag->u.videotext.y;
+	screen_info.orig_video_page   = tag->u.videotext.video_page;
+	screen_info.orig_video_mode   = tag->u.videotext.video_mode;
+	screen_info.orig_video_cols   = tag->u.videotext.video_cols;
+	screen_info.orig_video_ega_bx = tag->u.videotext.video_ega_bx;
+	screen_info.orig_video_lines  = tag->u.videotext.video_lines;
+	screen_info.orig_video_isVGA  = tag->u.videotext.video_isvga;
+	screen_info.orig_video_points = tag->u.videotext.video_points;
+	return 0;
+}
+
+__tagtable(ATAG_VIDEOTEXT, parse_tag_videotext);
+#endif
+
+#ifdef CONFIG_BLK_DEV_RAM
+static int __init parse_tag_ramdisk(const struct tag *tag)
+{
+	extern int rd_size, rd_image_start, rd_prompt, rd_doload;
+
+	rd_image_start = tag->u.ramdisk.start;
+	rd_doload = (tag->u.ramdisk.flags & 1) == 0;
+	rd_prompt = (tag->u.ramdisk.flags & 2) == 0;
+
+	if (tag->u.ramdisk.size)
+		rd_size = tag->u.ramdisk.size;
+
+	return 0;
+}
+
+__tagtable(ATAG_RAMDISK, parse_tag_ramdisk);
+#endif
+
+static int __init parse_tag_serialnr(const struct tag *tag)
+{
+	system_serial_low = tag->u.serialnr.low;
+	system_serial_high = tag->u.serialnr.high;
+	return 0;
+}
+
+__tagtable(ATAG_SERIAL, parse_tag_serialnr);
+
+static int __init parse_tag_revision(const struct tag *tag)
+{
+	system_rev = tag->u.revision.rev;
+	return 0;
+}
+
+__tagtable(ATAG_REVISION, parse_tag_revision);
+
+static int __init parse_tag_cmdline(const struct tag *tag)
+{
+#if defined(CONFIG_CMDLINE_EXTEND)
+	strlcat(default_command_line, " ", COMMAND_LINE_SIZE);
+	strlcat(default_command_line, tag->u.cmdline.cmdline,
+		COMMAND_LINE_SIZE);
+#elif defined(CONFIG_CMDLINE_FORCE)
+	pr_warning("Ignoring tag cmdline (using the default kernel command line)\n");
+#else
+	strlcpy(default_command_line, tag->u.cmdline.cmdline,
+		COMMAND_LINE_SIZE);
+#endif
+	return 0;
+}
+
+__tagtable(ATAG_CMDLINE, parse_tag_cmdline);
+
+/*
+ * Scan the tag table for this tag, and call its parse function.
+ * The tag table is built by the linker from all the __tagtable
+ * declarations.
+ */
+static int __init parse_tag(const struct tag *tag)
+{
+	extern struct tagtable __tagtable_begin, __tagtable_end;
+	struct tagtable *t;
+
+	for (t = &__tagtable_begin; t < &__tagtable_end; t++)
+		if (tag->hdr.tag == t->tag) {
+			t->parse(tag);
+			break;
+		}
+
+	return t < &__tagtable_end;
+}
+
+/*
+ * Parse all tags in the list, checking both the global and architecture
+ * specific tag tables.
+ */
+static void __init parse_tags(const struct tag *t)
+{
+	for (; t->hdr.size; t = tag_next(t))
+		if (!parse_tag(t))
+			printk(KERN_WARNING
+				"Ignoring unrecognised tag 0x%08x\n",
+				t->hdr.tag);
+}
+
+static void __init squash_mem_tags(struct tag *tag)
+{
+	for (; tag->hdr.size; tag = tag_next(tag))
+		if (tag->hdr.tag == ATAG_MEM)
+			tag->hdr.tag = ATAG_NONE;
+}
+
+struct machine_desc * __init setup_machine_tags(phys_addr_t __atags_pointer,
+						unsigned int machine_nr)
+{
+	struct tag *tags = (struct tag *)&default_tags;
+	struct machine_desc *mdesc = NULL, *p;
+	char *from = default_command_line;
+
+	default_tags.mem.start = PHYS_OFFSET;
+
+	/*
+	 * locate machine in the list of supported machines.
+	 */
+	for_each_machine_desc(p)
+		if (machine_nr == p->nr) {
+			printk("Machine: %s\n", p->name);
+			mdesc = p;
+			break;
+		}
+
+	if (!mdesc) {
+		early_print("\nError: unrecognized/unsupported machine ID"
+			    " (r1 = 0x%08x).\n\n", machine_nr);
+		dump_machine_table(); /* does not return */
+	}
+
+	if (__atags_pointer)
+		tags = phys_to_virt(__atags_pointer);
+	else if (mdesc->atag_offset)
+		tags = (void *)(PAGE_OFFSET + mdesc->atag_offset);
+
+#if defined(CONFIG_DEPRECATED_PARAM_STRUCT)
+	/*
+	 * If we have the old style parameters, convert them to
+	 * a tag list.
+	 */
+	if (tags->hdr.tag != ATAG_CORE)
+		convert_to_tag_list(tags);
+#endif
+	if (tags->hdr.tag != ATAG_CORE) {
+		early_print("Warning: Neither atags nor dtb found\n");
+		tags = (struct tag *)&default_tags;
+	}
+
+	if (mdesc->fixup)
+		mdesc->fixup(tags, &from, &meminfo);
+
+	if (tags->hdr.tag == ATAG_CORE) {
+		if (meminfo.nr_banks != 0)
+			squash_mem_tags(tags);
+		save_atags(tags);
+		parse_tags(tags);
+	}
+
+	/* parse_early_param needs a boot_command_line */
+	strlcpy(boot_command_line, from, COMMAND_LINE_SIZE);
+
+	return mdesc;
+}
diff --git a/arch/arm/kernel/atags.c b/arch/arm/kernel/atags_proc.c
index 42a1a1415fa..42a1a1415fa 100644
--- a/arch/arm/kernel/atags.c
+++ b/arch/arm/kernel/atags_proc.c
diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c
index 2b2f25e7fef..9b722612553 100644
--- a/arch/arm/kernel/bios32.c
+++ b/arch/arm/kernel/bios32.c
@@ -13,6 +13,7 @@
 #include <linux/io.h>
 
 #include <asm/mach-types.h>
+#include <asm/mach/map.h>
 #include <asm/mach/pci.h>
 
 static int debug_pci;
@@ -270,15 +271,6 @@ static void __devinit pci_fixup_it8152(struct pci_dev *dev)
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ITE, PCI_DEVICE_ID_ITE_8152, pci_fixup_it8152);
 
-
-
-void __devinit pcibios_update_irq(struct pci_dev *dev, int irq)
-{
-	if (debug_pci)
-		printk("PCI: Assigning IRQ %02d to %s\n", irq, pci_name(dev));
-	pci_write_config_byte(dev, PCI_INTERRUPT_LINE, irq);
-}
-
 /*
  * If the bus contains any of these devices, then we must not turn on
  * parity checking of any kind.  Currently this is CyberPro 20x0 only.
@@ -423,6 +415,38 @@ static int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 	return irq;
 }
 
+static int __init pcibios_init_resources(int busnr, struct pci_sys_data *sys)
+{
+	int ret;
+	struct pci_host_bridge_window *window;
+
+	if (list_empty(&sys->resources)) {
+		pci_add_resource_offset(&sys->resources,
+			 &iomem_resource, sys->mem_offset);
+	}
+
+	list_for_each_entry(window, &sys->resources, list) {
+		if (resource_type(window->res) == IORESOURCE_IO)
+			return 0;
+	}
+
+	sys->io_res.start = (busnr * SZ_64K) ?  : pcibios_min_io;
+	sys->io_res.end = (busnr + 1) * SZ_64K - 1;
+	sys->io_res.flags = IORESOURCE_IO;
+	sys->io_res.name = sys->io_res_name;
+	sprintf(sys->io_res_name, "PCI%d I/O", busnr);
+
+	ret = request_resource(&ioport_resource, &sys->io_res);
+	if (ret) {
+		pr_err("PCI: unable to allocate I/O port region (%d)\n", ret);
+		return ret;
+	}
+	pci_add_resource_offset(&sys->resources, &sys->io_res,
+				sys->io_offset);
+
+	return 0;
+}
+
 static void __init pcibios_init_hw(struct hw_pci *hw, struct list_head *head)
 {
 	struct pci_sys_data *sys = NULL;
@@ -445,11 +469,10 @@ static void __init pcibios_init_hw(struct hw_pci *hw, struct list_head *head)
 		ret = hw->setup(nr, sys);
 
 		if (ret > 0) {
-			if (list_empty(&sys->resources)) {
-				pci_add_resource_offset(&sys->resources,
-					 &ioport_resource, sys->io_offset);
-				pci_add_resource_offset(&sys->resources,
-					 &iomem_resource, sys->mem_offset);
+			ret = pcibios_init_resources(nr, sys);
+			if (ret)  {
+				kfree(sys);
+				break;
 			}
 
 			if (hw->scan)
@@ -627,3 +650,15 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
 
 	return 0;
 }
+
+void __init pci_map_io_early(unsigned long pfn)
+{
+	struct map_desc pci_io_desc = {
+		.virtual	= PCI_IO_VIRT_BASE,
+		.type		= MT_DEVICE,
+		.length		= SZ_64K,
+	};
+
+	pci_io_desc.pfn = pfn;
+	iotable_init(&pci_io_desc, 1);
+}
diff --git a/arch/arm/kernel/compat.h b/arch/arm/kernel/compat.h
deleted file mode 100644
index 39264ab1b9c..00000000000
--- a/arch/arm/kernel/compat.h
+++ /dev/null
@@ -1,11 +0,0 @@
-/*
- *  linux/arch/arm/kernel/compat.h
- *
- *  Copyright (C) 2001 Russell King
- *
- * 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.
-*/
-
-extern void convert_to_tag_list(struct tag *tags);
diff --git a/arch/arm/kernel/debug.S b/arch/arm/kernel/debug.S
index c45522c3678..66f711b2e0e 100644
--- a/arch/arm/kernel/debug.S
+++ b/arch/arm/kernel/debug.S
@@ -20,90 +20,9 @@
  * references to these in a production kernel!
  */
 
-#if defined(CONFIG_DEBUG_ICEDCC)
-		@@ debug using ARM EmbeddedICE DCC channel
-
-		.macro	addruart, rp, rv, tmp
-		.endm
-
-#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K) || defined(CONFIG_CPU_V7)
-
-		.macro	senduart, rd, rx
-		mcr	p14, 0, \rd, c0, c5, 0
-		.endm
-
-		.macro	busyuart, rd, rx
-1001:
-		mrc	p14, 0, \rx, c0, c1, 0
-		tst	\rx, #0x20000000
-		beq	1001b
-		.endm
-
-		.macro	waituart, rd, rx
-		mov	\rd, #0x2000000
-1001:
-		subs	\rd, \rd, #1
-		bmi	1002f
-		mrc	p14, 0, \rx, c0, c1, 0
-		tst	\rx, #0x20000000
-		bne	1001b
-1002:
-		.endm
-
-#elif defined(CONFIG_CPU_XSCALE)
-
-		.macro	senduart, rd, rx
-		mcr	p14, 0, \rd, c8, c0, 0
-		.endm
-
-		.macro	busyuart, rd, rx
-1001:
-		mrc	p14, 0, \rx, c14, c0, 0
-		tst	\rx, #0x10000000
-		beq	1001b
-		.endm
-
-		.macro	waituart, rd, rx
-		mov	\rd, #0x10000000
-1001:
-		subs	\rd, \rd, #1
-		bmi	1002f
-		mrc	p14, 0, \rx, c14, c0, 0
-		tst	\rx, #0x10000000
-		bne	1001b
-1002:
-		.endm
-
-#else
-
-		.macro	senduart, rd, rx
-		mcr	p14, 0, \rd, c1, c0, 0
-		.endm
-
-		.macro	busyuart, rd, rx
-1001:
-		mrc	p14, 0, \rx, c0, c0, 0
-		tst	\rx, #2
-		beq	1001b
-
-		.endm
-
-		.macro	waituart, rd, rx
-		mov	\rd, #0x2000000
-1001:
-		subs	\rd, \rd, #1
-		bmi	1002f
-		mrc	p14, 0, \rx, c0, c0, 0
-		tst	\rx, #2
-		bne	1001b
-1002:
-		.endm
-
-#endif	/* CONFIG_CPU_V6 */
-
-#elif !defined(CONFIG_DEBUG_SEMIHOSTING)
-#include <mach/debug-macro.S>
-#endif	/* CONFIG_DEBUG_ICEDCC */
+#if !defined(CONFIG_DEBUG_SEMIHOSTING)
+#include CONFIG_DEBUG_LL_INCLUDE
+#endif
 
 #ifdef CONFIG_MMU
 		.macro	addruart_current, rx, tmp1, tmp2
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 978eac57e04..f45987037bf 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -94,6 +94,15 @@ ENDPROC(ret_from_fork)
 	.equ NR_syscalls,0
 #define CALL(x) .equ NR_syscalls,NR_syscalls+1
 #include "calls.S"
+
+/*
+ * Ensure that the system call table is equal to __NR_syscalls,
+ * which is the value the rest of the system sees
+ */
+.ifne NR_syscalls - __NR_syscalls
+.error "__NR_syscalls is not equal to the size of the syscall table"
+.endif
+
 #undef CALL
 #define CALL(x) .long x
 
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 27093e4feef..4eee351f466 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -23,8 +23,8 @@
 #include <asm/thread_info.h>
 #include <asm/pgtable.h>
 
-#ifdef CONFIG_DEBUG_LL
-#include <mach/debug-macro.S>
+#if defined(CONFIG_DEBUG_LL) && !defined(CONFIG_DEBUG_SEMIHOSTING)
+#include CONFIG_DEBUG_LL_INCLUDE
 #endif
 
 /*
diff --git a/arch/arm/kernel/leds.c b/arch/arm/kernel/leds.c
deleted file mode 100644
index 1911dae19e4..00000000000
--- a/arch/arm/kernel/leds.c
+++ /dev/null
@@ -1,121 +0,0 @@
-/*
- * LED support code, ripped out of arch/arm/kernel/time.c
- *
- *  Copyright (C) 1994-2001 Russell King
- *
- * 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/init.h>
-#include <linux/device.h>
-#include <linux/syscore_ops.h>
-#include <linux/string.h>
-
-#include <asm/leds.h>
-
-static void dummy_leds_event(led_event_t evt)
-{
-}
-
-void (*leds_event)(led_event_t) = dummy_leds_event;
-
-struct leds_evt_name {
-	const char	name[8];
-	int		on;
-	int		off;
-};
-
-static const struct leds_evt_name evt_names[] = {
-	{ "amber", led_amber_on, led_amber_off },
-	{ "blue",  led_blue_on,  led_blue_off  },
-	{ "green", led_green_on, led_green_off },
-	{ "red",   led_red_on,   led_red_off   },
-};
-
-static ssize_t leds_store(struct device *dev,
-			struct device_attribute *attr,
-			const char *buf, size_t size)
-{
-	int ret = -EINVAL, len = strcspn(buf, " ");
-
-	if (len > 0 && buf[len] == '\0')
-		len--;
-
-	if (strncmp(buf, "claim", len) == 0) {
-		leds_event(led_claim);
-		ret = size;
-	} else if (strncmp(buf, "release", len) == 0) {
-		leds_event(led_release);
-		ret = size;
-	} else {
-		int i;
-
-		for (i = 0; i < ARRAY_SIZE(evt_names); i++) {
-			if (strlen(evt_names[i].name) != len ||
-			    strncmp(buf, evt_names[i].name, len) != 0)
-				continue;
-			if (strncmp(buf+len, " on", 3) == 0) {
-				leds_event(evt_names[i].on);
-				ret = size;
-			} else if (strncmp(buf+len, " off", 4) == 0) {
-				leds_event(evt_names[i].off);
-				ret = size;
-			}
-			break;
-		}
-	}
-	return ret;
-}
-
-static DEVICE_ATTR(event, 0200, NULL, leds_store);
-
-static struct bus_type leds_subsys = {
-	.name		= "leds",
-	.dev_name	= "leds",
-};
-
-static struct device leds_device = {
-	.id		= 0,
-	.bus		= &leds_subsys,
-};
-
-static int leds_suspend(void)
-{
-	leds_event(led_stop);
-	return 0;
-}
-
-static void leds_resume(void)
-{
-	leds_event(led_start);
-}
-
-static void leds_shutdown(void)
-{
-	leds_event(led_halted);
-}
-
-static struct syscore_ops leds_syscore_ops = {
-	.shutdown	= leds_shutdown,
-	.suspend	= leds_suspend,
-	.resume		= leds_resume,
-};
-
-static int __init leds_init(void)
-{
-	int ret;
-	ret = subsys_system_register(&leds_subsys, NULL);
-	if (ret == 0)
-		ret = device_register(&leds_device);
-	if (ret == 0)
-		ret = device_create_file(&leds_device, &dev_attr_event);
-	if (ret == 0)
-		register_syscore_ops(&leds_syscore_ops);
-	return ret;
-}
-
-device_initcall(leds_init);
-
-EXPORT_SYMBOL(leds_event);
diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index dfcdb9f7c12..e29c3337ca8 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -8,7 +8,9 @@
 #include <linux/reboot.h>
 #include <linux/io.h>
 #include <linux/irq.h>
+#include <linux/memblock.h>
 #include <asm/pgtable.h>
+#include <linux/of_fdt.h>
 #include <asm/pgalloc.h>
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
@@ -32,6 +34,29 @@ static atomic_t waiting_for_crash_ipi;
 
 int machine_kexec_prepare(struct kimage *image)
 {
+	struct kexec_segment *current_segment;
+	__be32 header;
+	int i, err;
+
+	/*
+	 * No segment at default ATAGs address. try to locate
+	 * a dtb using magic.
+	 */
+	for (i = 0; i < image->nr_segments; i++) {
+		current_segment = &image->segment[i];
+
+		err = memblock_is_region_memory(current_segment->mem,
+						current_segment->memsz);
+		if (err)
+			return - EINVAL;
+
+		err = get_user(header, (__be32*)current_segment->buf);
+		if (err)
+			return err;
+
+		if (be32_to_cpu(header) == OF_DT_HEADER)
+			kexec_boot_atags = current_segment->mem;
+	}
 	return 0;
 }
 
@@ -122,7 +147,9 @@ void machine_kexec(struct kimage *image)
 	kexec_start_address = image->start;
 	kexec_indirection_page = page_list;
 	kexec_mach_type = machine_arch_type;
-	kexec_boot_atags = image->start - KEXEC_ARM_ZIMAGE_OFFSET + KEXEC_ARM_ATAGS_OFFSET;
+	if (!kexec_boot_atags)
+		kexec_boot_atags = image->start - KEXEC_ARM_ZIMAGE_OFFSET + KEXEC_ARM_ATAGS_OFFSET;
+
 
 	/* copy our kernel relocation code to the control code page */
 	memcpy(reboot_code_buffer,
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index ab243b87118..93971b1a4f0 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -12,68 +12,15 @@
  */
 #define pr_fmt(fmt) "hw perfevents: " fmt
 
-#include <linux/bitmap.h>
-#include <linux/interrupt.h>
 #include <linux/kernel.h>
-#include <linux/export.h>
-#include <linux/perf_event.h>
 #include <linux/platform_device.h>
-#include <linux/spinlock.h>
+#include <linux/pm_runtime.h>
 #include <linux/uaccess.h>
 
-#include <asm/cputype.h>
-#include <asm/irq.h>
 #include <asm/irq_regs.h>
 #include <asm/pmu.h>
 #include <asm/stacktrace.h>
 
-/*
- * ARMv6 supports a maximum of 3 events, starting from index 0. If we add
- * another platform that supports more, we need to increase this to be the
- * largest of all platforms.
- *
- * ARMv7 supports up to 32 events:
- *  cycle counter CCNT + 31 events counters CNT0..30.
- *  Cortex-A8 has 1+4 counters, Cortex-A9 has 1+6 counters.
- */
-#define ARMPMU_MAX_HWEVENTS		32
-
-static DEFINE_PER_CPU(struct perf_event * [ARMPMU_MAX_HWEVENTS], hw_events);
-static DEFINE_PER_CPU(unsigned long [BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)], used_mask);
-static DEFINE_PER_CPU(struct pmu_hw_events, cpu_hw_events);
-
-#define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu))
-
-/* Set at runtime when we know what CPU type we are. */
-static struct arm_pmu *cpu_pmu;
-
-const char *perf_pmu_name(void)
-{
-	if (!cpu_pmu)
-		return NULL;
-
-	return cpu_pmu->pmu.name;
-}
-EXPORT_SYMBOL_GPL(perf_pmu_name);
-
-int perf_num_counters(void)
-{
-	int max_events = 0;
-
-	if (cpu_pmu != NULL)
-		max_events = cpu_pmu->num_events;
-
-	return max_events;
-}
-EXPORT_SYMBOL_GPL(perf_num_counters);
-
-#define HW_OP_UNSUPPORTED		0xFFFF
-
-#define C(_x) \
-	PERF_COUNT_HW_CACHE_##_x
-
-#define CACHE_OP_UNSUPPORTED		0xFFFF
-
 static int
 armpmu_map_cache_event(const unsigned (*cache_map)
 				      [PERF_COUNT_HW_CACHE_MAX]
@@ -104,7 +51,7 @@ armpmu_map_cache_event(const unsigned (*cache_map)
 }
 
 static int
-armpmu_map_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config)
+armpmu_map_hw_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config)
 {
 	int mapping = (*event_map)[config];
 	return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping;
@@ -116,19 +63,20 @@ armpmu_map_raw_event(u32 raw_event_mask, u64 config)
 	return (int)(config & raw_event_mask);
 }
 
-static int map_cpu_event(struct perf_event *event,
-			 const unsigned (*event_map)[PERF_COUNT_HW_MAX],
-			 const unsigned (*cache_map)
-					[PERF_COUNT_HW_CACHE_MAX]
-					[PERF_COUNT_HW_CACHE_OP_MAX]
-					[PERF_COUNT_HW_CACHE_RESULT_MAX],
-			 u32 raw_event_mask)
+int
+armpmu_map_event(struct perf_event *event,
+		 const unsigned (*event_map)[PERF_COUNT_HW_MAX],
+		 const unsigned (*cache_map)
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX],
+		 u32 raw_event_mask)
 {
 	u64 config = event->attr.config;
 
 	switch (event->attr.type) {
 	case PERF_TYPE_HARDWARE:
-		return armpmu_map_event(event_map, config);
+		return armpmu_map_hw_event(event_map, config);
 	case PERF_TYPE_HW_CACHE:
 		return armpmu_map_cache_event(cache_map, config);
 	case PERF_TYPE_RAW:
@@ -222,7 +170,6 @@ armpmu_stop(struct perf_event *event, int flags)
 	 */
 	if (!(hwc->state & PERF_HES_STOPPED)) {
 		armpmu->disable(hwc, hwc->idx);
-		barrier(); /* why? */
 		armpmu_event_update(event, hwc, hwc->idx);
 		hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
 	}
@@ -350,99 +297,41 @@ validate_group(struct perf_event *event)
 	return 0;
 }
 
-static irqreturn_t armpmu_platform_irq(int irq, void *dev)
+static irqreturn_t armpmu_dispatch_irq(int irq, void *dev)
 {
 	struct arm_pmu *armpmu = (struct arm_pmu *) dev;
 	struct platform_device *plat_device = armpmu->plat_device;
 	struct arm_pmu_platdata *plat = dev_get_platdata(&plat_device->dev);
 
-	return plat->handle_irq(irq, dev, armpmu->handle_irq);
+	if (plat && plat->handle_irq)
+		return plat->handle_irq(irq, dev, armpmu->handle_irq);
+	else
+		return armpmu->handle_irq(irq, dev);
 }
 
 static void
 armpmu_release_hardware(struct arm_pmu *armpmu)
 {
-	int i, irq, irqs;
-	struct platform_device *pmu_device = armpmu->plat_device;
-	struct arm_pmu_platdata *plat =
-		dev_get_platdata(&pmu_device->dev);
-
-	irqs = min(pmu_device->num_resources, num_possible_cpus());
-
-	for (i = 0; i < irqs; ++i) {
-		if (!cpumask_test_and_clear_cpu(i, &armpmu->active_irqs))
-			continue;
-		irq = platform_get_irq(pmu_device, i);
-		if (irq >= 0) {
-			if (plat && plat->disable_irq)
-				plat->disable_irq(irq);
-			free_irq(irq, armpmu);
-		}
-	}
-
-	release_pmu(armpmu->type);
+	armpmu->free_irq();
+	pm_runtime_put_sync(&armpmu->plat_device->dev);
 }
 
 static int
 armpmu_reserve_hardware(struct arm_pmu *armpmu)
 {
-	struct arm_pmu_platdata *plat;
-	irq_handler_t handle_irq;
-	int i, err, irq, irqs;
+	int err;
 	struct platform_device *pmu_device = armpmu->plat_device;
 
 	if (!pmu_device)
 		return -ENODEV;
 
-	err = reserve_pmu(armpmu->type);
+	pm_runtime_get_sync(&pmu_device->dev);
+	err = armpmu->request_irq(armpmu_dispatch_irq);
 	if (err) {
-		pr_warning("unable to reserve pmu\n");
+		armpmu_release_hardware(armpmu);
 		return err;
 	}
 
-	plat = dev_get_platdata(&pmu_device->dev);
-	if (plat && plat->handle_irq)
-		handle_irq = armpmu_platform_irq;
-	else
-		handle_irq = armpmu->handle_irq;
-
-	irqs = min(pmu_device->num_resources, num_possible_cpus());
-	if (irqs < 1) {
-		pr_err("no irqs for PMUs defined\n");
-		return -ENODEV;
-	}
-
-	for (i = 0; i < irqs; ++i) {
-		err = 0;
-		irq = platform_get_irq(pmu_device, i);
-		if (irq < 0)
-			continue;
-
-		/*
-		 * If we have a single PMU interrupt that we can't shift,
-		 * assume that we're running on a uniprocessor machine and
-		 * continue. Otherwise, continue without this interrupt.
-		 */
-		if (irq_set_affinity(irq, cpumask_of(i)) && irqs > 1) {
-			pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n",
-				    irq, i);
-			continue;
-		}
-
-		err = request_irq(irq, handle_irq,
-				  IRQF_DISABLED | IRQF_NOBALANCING,
-				  "arm-pmu", armpmu);
-		if (err) {
-			pr_err("unable to request IRQ%d for ARM PMU counters\n",
-				irq);
-			armpmu_release_hardware(armpmu);
-			return err;
-		} else if (plat && plat->enable_irq)
-			plat->enable_irq(irq);
-
-		cpumask_set_cpu(i, &armpmu->active_irqs);
-	}
-
 	return 0;
 }
 
@@ -581,6 +470,32 @@ static void armpmu_disable(struct pmu *pmu)
 	armpmu->stop();
 }
 
+#ifdef CONFIG_PM_RUNTIME
+static int armpmu_runtime_resume(struct device *dev)
+{
+	struct arm_pmu_platdata *plat = dev_get_platdata(dev);
+
+	if (plat && plat->runtime_resume)
+		return plat->runtime_resume(dev);
+
+	return 0;
+}
+
+static int armpmu_runtime_suspend(struct device *dev)
+{
+	struct arm_pmu_platdata *plat = dev_get_platdata(dev);
+
+	if (plat && plat->runtime_suspend)
+		return plat->runtime_suspend(dev);
+
+	return 0;
+}
+#endif
+
+const struct dev_pm_ops armpmu_dev_pm_ops = {
+	SET_RUNTIME_PM_OPS(armpmu_runtime_suspend, armpmu_runtime_resume, NULL)
+};
+
 static void __init armpmu_init(struct arm_pmu *armpmu)
 {
 	atomic_set(&armpmu->active_events, 0);
@@ -598,174 +513,14 @@ static void __init armpmu_init(struct arm_pmu *armpmu)
 	};
 }
 
-int __init armpmu_register(struct arm_pmu *armpmu, char *name, int type)
+int armpmu_register(struct arm_pmu *armpmu, char *name, int type)
 {
 	armpmu_init(armpmu);
+	pr_info("enabled with %s PMU driver, %d counters available\n",
+			armpmu->name, armpmu->num_events);
 	return perf_pmu_register(&armpmu->pmu, name, type);
 }
 
-/* Include the PMU-specific implementations. */
-#include "perf_event_xscale.c"
-#include "perf_event_v6.c"
-#include "perf_event_v7.c"
-
-/*
- * Ensure the PMU has sane values out of reset.
- * This requires SMP to be available, so exists as a separate initcall.
- */
-static int __init
-cpu_pmu_reset(void)
-{
-	if (cpu_pmu && cpu_pmu->reset)
-		return on_each_cpu(cpu_pmu->reset, NULL, 1);
-	return 0;
-}
-arch_initcall(cpu_pmu_reset);
-
-/*
- * PMU platform driver and devicetree bindings.
- */
-static struct of_device_id armpmu_of_device_ids[] = {
-	{.compatible = "arm,cortex-a9-pmu"},
-	{.compatible = "arm,cortex-a8-pmu"},
-	{.compatible = "arm,arm1136-pmu"},
-	{.compatible = "arm,arm1176-pmu"},
-	{},
-};
-
-static struct platform_device_id armpmu_plat_device_ids[] = {
-	{.name = "arm-pmu"},
-	{},
-};
-
-static int __devinit armpmu_device_probe(struct platform_device *pdev)
-{
-	if (!cpu_pmu)
-		return -ENODEV;
-
-	cpu_pmu->plat_device = pdev;
-	return 0;
-}
-
-static struct platform_driver armpmu_driver = {
-	.driver		= {
-		.name	= "arm-pmu",
-		.of_match_table = armpmu_of_device_ids,
-	},
-	.probe		= armpmu_device_probe,
-	.id_table	= armpmu_plat_device_ids,
-};
-
-static int __init register_pmu_driver(void)
-{
-	return platform_driver_register(&armpmu_driver);
-}
-device_initcall(register_pmu_driver);
-
-static struct pmu_hw_events *armpmu_get_cpu_events(void)
-{
-	return &__get_cpu_var(cpu_hw_events);
-}
-
-static void __init cpu_pmu_init(struct arm_pmu *armpmu)
-{
-	int cpu;
-	for_each_possible_cpu(cpu) {
-		struct pmu_hw_events *events = &per_cpu(cpu_hw_events, cpu);
-		events->events = per_cpu(hw_events, cpu);
-		events->used_mask = per_cpu(used_mask, cpu);
-		raw_spin_lock_init(&events->pmu_lock);
-	}
-	armpmu->get_hw_events = armpmu_get_cpu_events;
-	armpmu->type = ARM_PMU_DEVICE_CPU;
-}
-
-/*
- * PMU hardware loses all context when a CPU goes offline.
- * When a CPU is hotplugged back in, since some hardware registers are
- * UNKNOWN at reset, the PMU must be explicitly reset to avoid reading
- * junk values out of them.
- */
-static int __cpuinit pmu_cpu_notify(struct notifier_block *b,
-					unsigned long action, void *hcpu)
-{
-	if ((action & ~CPU_TASKS_FROZEN) != CPU_STARTING)
-		return NOTIFY_DONE;
-
-	if (cpu_pmu && cpu_pmu->reset)
-		cpu_pmu->reset(NULL);
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block __cpuinitdata pmu_cpu_notifier = {
-	.notifier_call = pmu_cpu_notify,
-};
-
-/*
- * CPU PMU identification and registration.
- */
-static int __init
-init_hw_perf_events(void)
-{
-	unsigned long cpuid = read_cpuid_id();
-	unsigned long implementor = (cpuid & 0xFF000000) >> 24;
-	unsigned long part_number = (cpuid & 0xFFF0);
-
-	/* ARM Ltd CPUs. */
-	if (0x41 == implementor) {
-		switch (part_number) {
-		case 0xB360:	/* ARM1136 */
-		case 0xB560:	/* ARM1156 */
-		case 0xB760:	/* ARM1176 */
-			cpu_pmu = armv6pmu_init();
-			break;
-		case 0xB020:	/* ARM11mpcore */
-			cpu_pmu = armv6mpcore_pmu_init();
-			break;
-		case 0xC080:	/* Cortex-A8 */
-			cpu_pmu = armv7_a8_pmu_init();
-			break;
-		case 0xC090:	/* Cortex-A9 */
-			cpu_pmu = armv7_a9_pmu_init();
-			break;
-		case 0xC050:	/* Cortex-A5 */
-			cpu_pmu = armv7_a5_pmu_init();
-			break;
-		case 0xC0F0:	/* Cortex-A15 */
-			cpu_pmu = armv7_a15_pmu_init();
-			break;
-		case 0xC070:	/* Cortex-A7 */
-			cpu_pmu = armv7_a7_pmu_init();
-			break;
-		}
-	/* Intel CPUs [xscale]. */
-	} else if (0x69 == implementor) {
-		part_number = (cpuid >> 13) & 0x7;
-		switch (part_number) {
-		case 1:
-			cpu_pmu = xscale1pmu_init();
-			break;
-		case 2:
-			cpu_pmu = xscale2pmu_init();
-			break;
-		}
-	}
-
-	if (cpu_pmu) {
-		pr_info("enabled with %s PMU driver, %d counters available\n",
-			cpu_pmu->name, cpu_pmu->num_events);
-		cpu_pmu_init(cpu_pmu);
-		register_cpu_notifier(&pmu_cpu_notifier);
-		armpmu_register(cpu_pmu, cpu_pmu->name, PERF_TYPE_RAW);
-	} else {
-		pr_info("no hardware support available\n");
-	}
-
-	return 0;
-}
-early_initcall(init_hw_perf_events);
-
 /*
  * Callchain handling code.
  */
diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
new file mode 100644
index 00000000000..8d7d8d4de9d
--- /dev/null
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -0,0 +1,295 @@
+/*
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) 2012 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+#define pr_fmt(fmt) "CPU PMU: " fmt
+
+#include <linux/bitmap.h>
+#include <linux/export.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/spinlock.h>
+
+#include <asm/cputype.h>
+#include <asm/irq_regs.h>
+#include <asm/pmu.h>
+
+/* Set at runtime when we know what CPU type we are. */
+static struct arm_pmu *cpu_pmu;
+
+static DEFINE_PER_CPU(struct perf_event * [ARMPMU_MAX_HWEVENTS], hw_events);
+static DEFINE_PER_CPU(unsigned long [BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)], used_mask);
+static DEFINE_PER_CPU(struct pmu_hw_events, cpu_hw_events);
+
+/*
+ * Despite the names, these two functions are CPU-specific and are used
+ * by the OProfile/perf code.
+ */
+const char *perf_pmu_name(void)
+{
+	if (!cpu_pmu)
+		return NULL;
+
+	return cpu_pmu->pmu.name;
+}
+EXPORT_SYMBOL_GPL(perf_pmu_name);
+
+int perf_num_counters(void)
+{
+	int max_events = 0;
+
+	if (cpu_pmu != NULL)
+		max_events = cpu_pmu->num_events;
+
+	return max_events;
+}
+EXPORT_SYMBOL_GPL(perf_num_counters);
+
+/* Include the PMU-specific implementations. */
+#include "perf_event_xscale.c"
+#include "perf_event_v6.c"
+#include "perf_event_v7.c"
+
+static struct pmu_hw_events *cpu_pmu_get_cpu_events(void)
+{
+	return &__get_cpu_var(cpu_hw_events);
+}
+
+static void cpu_pmu_free_irq(void)
+{
+	int i, irq, irqs;
+	struct platform_device *pmu_device = cpu_pmu->plat_device;
+
+	irqs = min(pmu_device->num_resources, num_possible_cpus());
+
+	for (i = 0; i < irqs; ++i) {
+		if (!cpumask_test_and_clear_cpu(i, &cpu_pmu->active_irqs))
+			continue;
+		irq = platform_get_irq(pmu_device, i);
+		if (irq >= 0)
+			free_irq(irq, cpu_pmu);
+	}
+}
+
+static int cpu_pmu_request_irq(irq_handler_t handler)
+{
+	int i, err, irq, irqs;
+	struct platform_device *pmu_device = cpu_pmu->plat_device;
+
+	if (!pmu_device)
+		return -ENODEV;
+
+	irqs = min(pmu_device->num_resources, num_possible_cpus());
+	if (irqs < 1) {
+		pr_err("no irqs for PMUs defined\n");
+		return -ENODEV;
+	}
+
+	for (i = 0; i < irqs; ++i) {
+		err = 0;
+		irq = platform_get_irq(pmu_device, i);
+		if (irq < 0)
+			continue;
+
+		/*
+		 * If we have a single PMU interrupt that we can't shift,
+		 * assume that we're running on a uniprocessor machine and
+		 * continue. Otherwise, continue without this interrupt.
+		 */
+		if (irq_set_affinity(irq, cpumask_of(i)) && irqs > 1) {
+			pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n",
+				    irq, i);
+			continue;
+		}
+
+		err = request_irq(irq, handler, IRQF_NOBALANCING, "arm-pmu",
+				  cpu_pmu);
+		if (err) {
+			pr_err("unable to request IRQ%d for ARM PMU counters\n",
+				irq);
+			return err;
+		}
+
+		cpumask_set_cpu(i, &cpu_pmu->active_irqs);
+	}
+
+	return 0;
+}
+
+static void __devinit cpu_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	int cpu;
+	for_each_possible_cpu(cpu) {
+		struct pmu_hw_events *events = &per_cpu(cpu_hw_events, cpu);
+		events->events = per_cpu(hw_events, cpu);
+		events->used_mask = per_cpu(used_mask, cpu);
+		raw_spin_lock_init(&events->pmu_lock);
+	}
+
+	cpu_pmu->get_hw_events	= cpu_pmu_get_cpu_events;
+	cpu_pmu->request_irq	= cpu_pmu_request_irq;
+	cpu_pmu->free_irq	= cpu_pmu_free_irq;
+
+	/* Ensure the PMU has sane values out of reset. */
+	if (cpu_pmu && cpu_pmu->reset)
+		on_each_cpu(cpu_pmu->reset, NULL, 1);
+}
+
+/*
+ * PMU hardware loses all context when a CPU goes offline.
+ * When a CPU is hotplugged back in, since some hardware registers are
+ * UNKNOWN at reset, the PMU must be explicitly reset to avoid reading
+ * junk values out of them.
+ */
+static int __cpuinit cpu_pmu_notify(struct notifier_block *b,
+				    unsigned long action, void *hcpu)
+{
+	if ((action & ~CPU_TASKS_FROZEN) != CPU_STARTING)
+		return NOTIFY_DONE;
+
+	if (cpu_pmu && cpu_pmu->reset)
+		cpu_pmu->reset(NULL);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block __cpuinitdata cpu_pmu_hotplug_notifier = {
+	.notifier_call = cpu_pmu_notify,
+};
+
+/*
+ * PMU platform driver and devicetree bindings.
+ */
+static struct of_device_id __devinitdata cpu_pmu_of_device_ids[] = {
+	{.compatible = "arm,cortex-a15-pmu",	.data = armv7_a15_pmu_init},
+	{.compatible = "arm,cortex-a9-pmu",	.data = armv7_a9_pmu_init},
+	{.compatible = "arm,cortex-a8-pmu",	.data = armv7_a8_pmu_init},
+	{.compatible = "arm,cortex-a7-pmu",	.data = armv7_a7_pmu_init},
+	{.compatible = "arm,cortex-a5-pmu",	.data = armv7_a5_pmu_init},
+	{.compatible = "arm,arm11mpcore-pmu",	.data = armv6mpcore_pmu_init},
+	{.compatible = "arm,arm1176-pmu",	.data = armv6pmu_init},
+	{.compatible = "arm,arm1136-pmu",	.data = armv6pmu_init},
+	{},
+};
+
+static struct platform_device_id __devinitdata cpu_pmu_plat_device_ids[] = {
+	{.name = "arm-pmu"},
+	{},
+};
+
+/*
+ * CPU PMU identification and probing.
+ */
+static struct arm_pmu *__devinit probe_current_pmu(void)
+{
+	struct arm_pmu *pmu = NULL;
+	int cpu = get_cpu();
+	unsigned long cpuid = read_cpuid_id();
+	unsigned long implementor = (cpuid & 0xFF000000) >> 24;
+	unsigned long part_number = (cpuid & 0xFFF0);
+
+	pr_info("probing PMU on CPU %d\n", cpu);
+
+	/* ARM Ltd CPUs. */
+	if (0x41 == implementor) {
+		switch (part_number) {
+		case 0xB360:	/* ARM1136 */
+		case 0xB560:	/* ARM1156 */
+		case 0xB760:	/* ARM1176 */
+			pmu = armv6pmu_init();
+			break;
+		case 0xB020:	/* ARM11mpcore */
+			pmu = armv6mpcore_pmu_init();
+			break;
+		case 0xC080:	/* Cortex-A8 */
+			pmu = armv7_a8_pmu_init();
+			break;
+		case 0xC090:	/* Cortex-A9 */
+			pmu = armv7_a9_pmu_init();
+			break;
+		case 0xC050:	/* Cortex-A5 */
+			pmu = armv7_a5_pmu_init();
+			break;
+		case 0xC0F0:	/* Cortex-A15 */
+			pmu = armv7_a15_pmu_init();
+			break;
+		case 0xC070:	/* Cortex-A7 */
+			pmu = armv7_a7_pmu_init();
+			break;
+		}
+	/* Intel CPUs [xscale]. */
+	} else if (0x69 == implementor) {
+		part_number = (cpuid >> 13) & 0x7;
+		switch (part_number) {
+		case 1:
+			pmu = xscale1pmu_init();
+			break;
+		case 2:
+			pmu = xscale2pmu_init();
+			break;
+		}
+	}
+
+	put_cpu();
+	return pmu;
+}
+
+static int __devinit cpu_pmu_device_probe(struct platform_device *pdev)
+{
+	const struct of_device_id *of_id;
+	struct arm_pmu *(*init_fn)(void);
+	struct device_node *node = pdev->dev.of_node;
+
+	if (cpu_pmu) {
+		pr_info("attempt to register multiple PMU devices!");
+		return -ENOSPC;
+	}
+
+	if (node && (of_id = of_match_node(cpu_pmu_of_device_ids, pdev->dev.of_node))) {
+		init_fn = of_id->data;
+		cpu_pmu = init_fn();
+	} else {
+		cpu_pmu = probe_current_pmu();
+	}
+
+	if (!cpu_pmu)
+		return -ENODEV;
+
+	cpu_pmu->plat_device = pdev;
+	cpu_pmu_init(cpu_pmu);
+	register_cpu_notifier(&cpu_pmu_hotplug_notifier);
+	armpmu_register(cpu_pmu, cpu_pmu->name, PERF_TYPE_RAW);
+
+	return 0;
+}
+
+static struct platform_driver cpu_pmu_driver = {
+	.driver		= {
+		.name	= "arm-pmu",
+		.pm	= &armpmu_dev_pm_ops,
+		.of_match_table = cpu_pmu_of_device_ids,
+	},
+	.probe		= cpu_pmu_device_probe,
+	.id_table	= cpu_pmu_plat_device_ids,
+};
+
+static int __init register_pmu_driver(void)
+{
+	return platform_driver_register(&cpu_pmu_driver);
+}
+device_initcall(register_pmu_driver);
diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c
index c90fcb2b696..6ccc0797174 100644
--- a/arch/arm/kernel/perf_event_v6.c
+++ b/arch/arm/kernel/perf_event_v6.c
@@ -645,7 +645,7 @@ armv6mpcore_pmu_disable_event(struct hw_perf_event *hwc,
 
 static int armv6_map_event(struct perf_event *event)
 {
-	return map_cpu_event(event, &armv6_perf_map,
+	return armpmu_map_event(event, &armv6_perf_map,
 				&armv6_perf_cache_map, 0xFF);
 }
 
@@ -664,7 +664,7 @@ static struct arm_pmu armv6pmu = {
 	.max_period		= (1LLU << 32) - 1,
 };
 
-static struct arm_pmu *__init armv6pmu_init(void)
+static struct arm_pmu *__devinit armv6pmu_init(void)
 {
 	return &armv6pmu;
 }
@@ -679,7 +679,7 @@ static struct arm_pmu *__init armv6pmu_init(void)
 
 static int armv6mpcore_map_event(struct perf_event *event)
 {
-	return map_cpu_event(event, &armv6mpcore_perf_map,
+	return armpmu_map_event(event, &armv6mpcore_perf_map,
 				&armv6mpcore_perf_cache_map, 0xFF);
 }
 
@@ -698,17 +698,17 @@ static struct arm_pmu armv6mpcore_pmu = {
 	.max_period		= (1LLU << 32) - 1,
 };
 
-static struct arm_pmu *__init armv6mpcore_pmu_init(void)
+static struct arm_pmu *__devinit armv6mpcore_pmu_init(void)
 {
 	return &armv6mpcore_pmu;
 }
 #else
-static struct arm_pmu *__init armv6pmu_init(void)
+static struct arm_pmu *__devinit armv6pmu_init(void)
 {
 	return NULL;
 }
 
-static struct arm_pmu *__init armv6mpcore_pmu_init(void)
+static struct arm_pmu *__devinit armv6mpcore_pmu_init(void)
 {
 	return NULL;
 }
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index f04070bd218..bd4b090ebcf 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -1204,31 +1204,31 @@ static void armv7pmu_reset(void *info)
 
 static int armv7_a8_map_event(struct perf_event *event)
 {
-	return map_cpu_event(event, &armv7_a8_perf_map,
+	return armpmu_map_event(event, &armv7_a8_perf_map,
 				&armv7_a8_perf_cache_map, 0xFF);
 }
 
 static int armv7_a9_map_event(struct perf_event *event)
 {
-	return map_cpu_event(event, &armv7_a9_perf_map,
+	return armpmu_map_event(event, &armv7_a9_perf_map,
 				&armv7_a9_perf_cache_map, 0xFF);
 }
 
 static int armv7_a5_map_event(struct perf_event *event)
 {
-	return map_cpu_event(event, &armv7_a5_perf_map,
+	return armpmu_map_event(event, &armv7_a5_perf_map,
 				&armv7_a5_perf_cache_map, 0xFF);
 }
 
 static int armv7_a15_map_event(struct perf_event *event)
 {
-	return map_cpu_event(event, &armv7_a15_perf_map,
+	return armpmu_map_event(event, &armv7_a15_perf_map,
 				&armv7_a15_perf_cache_map, 0xFF);
 }
 
 static int armv7_a7_map_event(struct perf_event *event)
 {
-	return map_cpu_event(event, &armv7_a7_perf_map,
+	return armpmu_map_event(event, &armv7_a7_perf_map,
 				&armv7_a7_perf_cache_map, 0xFF);
 }
 
@@ -1245,7 +1245,7 @@ static struct arm_pmu armv7pmu = {
 	.max_period		= (1LLU << 32) - 1,
 };
 
-static u32 __init armv7_read_num_pmnc_events(void)
+static u32 __devinit armv7_read_num_pmnc_events(void)
 {
 	u32 nb_cnt;
 
@@ -1256,7 +1256,7 @@ static u32 __init armv7_read_num_pmnc_events(void)
 	return nb_cnt + 1;
 }
 
-static struct arm_pmu *__init armv7_a8_pmu_init(void)
+static struct arm_pmu *__devinit armv7_a8_pmu_init(void)
 {
 	armv7pmu.name		= "ARMv7 Cortex-A8";
 	armv7pmu.map_event	= armv7_a8_map_event;
@@ -1264,7 +1264,7 @@ static struct arm_pmu *__init armv7_a8_pmu_init(void)
 	return &armv7pmu;
 }
 
-static struct arm_pmu *__init armv7_a9_pmu_init(void)
+static struct arm_pmu *__devinit armv7_a9_pmu_init(void)
 {
 	armv7pmu.name		= "ARMv7 Cortex-A9";
 	armv7pmu.map_event	= armv7_a9_map_event;
@@ -1272,7 +1272,7 @@ static struct arm_pmu *__init armv7_a9_pmu_init(void)
 	return &armv7pmu;
 }
 
-static struct arm_pmu *__init armv7_a5_pmu_init(void)
+static struct arm_pmu *__devinit armv7_a5_pmu_init(void)
 {
 	armv7pmu.name		= "ARMv7 Cortex-A5";
 	armv7pmu.map_event	= armv7_a5_map_event;
@@ -1280,7 +1280,7 @@ static struct arm_pmu *__init armv7_a5_pmu_init(void)
 	return &armv7pmu;
 }
 
-static struct arm_pmu *__init armv7_a15_pmu_init(void)
+static struct arm_pmu *__devinit armv7_a15_pmu_init(void)
 {
 	armv7pmu.name		= "ARMv7 Cortex-A15";
 	armv7pmu.map_event	= armv7_a15_map_event;
@@ -1289,7 +1289,7 @@ static struct arm_pmu *__init armv7_a15_pmu_init(void)
 	return &armv7pmu;
 }
 
-static struct arm_pmu *__init armv7_a7_pmu_init(void)
+static struct arm_pmu *__devinit armv7_a7_pmu_init(void)
 {
 	armv7pmu.name		= "ARMv7 Cortex-A7";
 	armv7pmu.map_event	= armv7_a7_map_event;
@@ -1298,27 +1298,27 @@ static struct arm_pmu *__init armv7_a7_pmu_init(void)
 	return &armv7pmu;
 }
 #else
-static struct arm_pmu *__init armv7_a8_pmu_init(void)
+static struct arm_pmu *__devinit armv7_a8_pmu_init(void)
 {
 	return NULL;
 }
 
-static struct arm_pmu *__init armv7_a9_pmu_init(void)
+static struct arm_pmu *__devinit armv7_a9_pmu_init(void)
 {
 	return NULL;
 }
 
-static struct arm_pmu *__init armv7_a5_pmu_init(void)
+static struct arm_pmu *__devinit armv7_a5_pmu_init(void)
 {
 	return NULL;
 }
 
-static struct arm_pmu *__init armv7_a15_pmu_init(void)
+static struct arm_pmu *__devinit armv7_a15_pmu_init(void)
 {
 	return NULL;
 }
 
-static struct arm_pmu *__init armv7_a7_pmu_init(void)
+static struct arm_pmu *__devinit armv7_a7_pmu_init(void)
 {
 	return NULL;
 }
diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c
index f759fe0bab6..426e19f380a 100644
--- a/arch/arm/kernel/perf_event_xscale.c
+++ b/arch/arm/kernel/perf_event_xscale.c
@@ -430,7 +430,7 @@ xscale1pmu_write_counter(int counter, u32 val)
 
 static int xscale_map_event(struct perf_event *event)
 {
-	return map_cpu_event(event, &xscale_perf_map,
+	return armpmu_map_event(event, &xscale_perf_map,
 				&xscale_perf_cache_map, 0xFF);
 }
 
@@ -449,7 +449,7 @@ static struct arm_pmu xscale1pmu = {
 	.max_period	= (1LLU << 32) - 1,
 };
 
-static struct arm_pmu *__init xscale1pmu_init(void)
+static struct arm_pmu *__devinit xscale1pmu_init(void)
 {
 	return &xscale1pmu;
 }
@@ -816,17 +816,17 @@ static struct arm_pmu xscale2pmu = {
 	.max_period	= (1LLU << 32) - 1,
 };
 
-static struct arm_pmu *__init xscale2pmu_init(void)
+static struct arm_pmu *__devinit xscale2pmu_init(void)
 {
 	return &xscale2pmu;
 }
 #else
-static struct arm_pmu *__init xscale1pmu_init(void)
+static struct arm_pmu *__devinit xscale1pmu_init(void)
 {
 	return NULL;
 }
 
-static struct arm_pmu *__init xscale2pmu_init(void)
+static struct arm_pmu *__devinit xscale2pmu_init(void)
 {
 	return NULL;
 }
diff --git a/arch/arm/kernel/pmu.c b/arch/arm/kernel/pmu.c
deleted file mode 100644
index 2334bf8a650..00000000000
--- a/arch/arm/kernel/pmu.c
+++ /dev/null
@@ -1,36 +0,0 @@
-/*
- *  linux/arch/arm/kernel/pmu.c
- *
- *  Copyright (C) 2009 picoChip Designs Ltd, Jamie Iles
- *  Copyright (C) 2010 ARM Ltd, Will Deacon
- *
- * 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/err.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-
-#include <asm/pmu.h>
-
-/*
- * PMU locking to ensure mutual exclusion between different subsystems.
- */
-static unsigned long pmu_lock[BITS_TO_LONGS(ARM_NUM_PMU_DEVICES)];
-
-int
-reserve_pmu(enum arm_pmu_type type)
-{
-	return test_and_set_bit_lock(type, pmu_lock) ? -EBUSY : 0;
-}
-EXPORT_SYMBOL_GPL(reserve_pmu);
-
-void
-release_pmu(enum arm_pmu_type type)
-{
-	clear_bit_unlock(type, pmu_lock);
-}
-EXPORT_SYMBOL_GPL(release_pmu);
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 693b744fd57..04eea22d795 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -31,9 +31,9 @@
 #include <linux/random.h>
 #include <linux/hw_breakpoint.h>
 #include <linux/cpuidle.h>
+#include <linux/leds.h>
 
 #include <asm/cacheflush.h>
-#include <asm/leds.h>
 #include <asm/processor.h>
 #include <asm/thread_notify.h>
 #include <asm/stacktrace.h>
@@ -189,7 +189,7 @@ void cpu_idle(void)
 	while (1) {
 		tick_nohz_idle_enter();
 		rcu_idle_enter();
-		leds_event(led_idle_start);
+		ledtrig_cpu(CPU_LED_IDLE_START);
 		while (!need_resched()) {
 #ifdef CONFIG_HOTPLUG_CPU
 			if (cpu_is_offline(smp_processor_id()))
@@ -220,7 +220,7 @@ void cpu_idle(void)
 			} else
 				local_irq_enable();
 		}
-		leds_event(led_idle_end);
+		ledtrig_cpu(CPU_LED_IDLE_END);
 		rcu_idle_exit();
 		tick_nohz_idle_exit();
 		schedule_preempt_disabled();
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 3e0fc5f7ed4..739db3a1b2d 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -30,6 +30,9 @@
 #include <asm/pgtable.h>
 #include <asm/traps.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
 #define REG_PC	15
 #define REG_PSR	16
 /*
@@ -918,11 +921,11 @@ static int ptrace_syscall_trace(struct pt_regs *regs, int scno,
 {
 	unsigned long ip;
 
+	current_thread_info()->syscall = scno;
+
 	if (!test_thread_flag(TIF_SYSCALL_TRACE))
 		return scno;
 
-	current_thread_info()->syscall = scno;
-
 	/*
 	 * IP is used to denote syscall entry/exit:
 	 * IP = 0 -> entry, =1 -> exit
@@ -941,15 +944,19 @@ static int ptrace_syscall_trace(struct pt_regs *regs, int scno,
 
 asmlinkage int syscall_trace_enter(struct pt_regs *regs, int scno)
 {
-	int ret = ptrace_syscall_trace(regs, scno, PTRACE_SYSCALL_ENTER);
+	scno = ptrace_syscall_trace(regs, scno, PTRACE_SYSCALL_ENTER);
+	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+		trace_sys_enter(regs, scno);
 	audit_syscall_entry(AUDIT_ARCH_ARM, scno, regs->ARM_r0, regs->ARM_r1,
 			    regs->ARM_r2, regs->ARM_r3);
-	return ret;
+	return scno;
 }
 
 asmlinkage int syscall_trace_exit(struct pt_regs *regs, int scno)
 {
-	int ret = ptrace_syscall_trace(regs, scno, PTRACE_SYSCALL_EXIT);
+	scno = ptrace_syscall_trace(regs, scno, PTRACE_SYSCALL_EXIT);
+	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+		trace_sys_exit(regs, scno);
 	audit_syscall_exit(regs);
-	return ret;
+	return scno;
 }
diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c
index f4515393248..e21bac20d90 100644
--- a/arch/arm/kernel/sched_clock.c
+++ b/arch/arm/kernel/sched_clock.c
@@ -9,6 +9,7 @@
 #include <linux/init.h>
 #include <linux/jiffies.h>
 #include <linux/kernel.h>
+#include <linux/moduleparam.h>
 #include <linux/sched.h>
 #include <linux/syscore_ops.h>
 #include <linux/timer.h>
@@ -27,6 +28,9 @@ struct clock_data {
 
 static void sched_clock_poll(unsigned long wrap_ticks);
 static DEFINE_TIMER(sched_clock_timer, sched_clock_poll, 0, 0);
+static int irqtime = -1;
+
+core_param(irqtime, irqtime, int, 0400);
 
 static struct clock_data cd = {
 	.mult	= NSEC_PER_SEC / HZ,
@@ -157,6 +161,10 @@ void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate)
 	 */
 	cd.epoch_ns = 0;
 
+	/* Enable IRQ time accounting if we have a fast enough sched_clock */
+	if (irqtime > 0 || (irqtime == -1 && rate >= 1000000))
+		enable_sched_clock_irqtime();
+
 	pr_debug("Registered %pF as sched_clock source\n", read);
 }
 
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 04fd01feea8..da1d1aa20ad 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -21,11 +21,9 @@
 #include <linux/init.h>
 #include <linux/kexec.h>
 #include <linux/of_fdt.h>
-#include <linux/root_dev.h>
 #include <linux/cpu.h>
 #include <linux/interrupt.h>
 #include <linux/smp.h>
-#include <linux/fs.h>
 #include <linux/proc_fs.h>
 #include <linux/memblock.h>
 #include <linux/bug.h>
@@ -57,15 +55,9 @@
 #include <asm/memblock.h>
 #include <asm/virt.h>
 
-#if defined(CONFIG_DEPRECATED_PARAM_STRUCT)
-#include "compat.h"
-#endif
 #include "atags.h"
 #include "tcm.h"
 
-#ifndef MEM_SIZE
-#define MEM_SIZE	(16*1024*1024)
-#endif
 
 #if defined(CONFIG_FPE_NWFPE) || defined(CONFIG_FPE_FASTFPE)
 char fpe_type[8];
@@ -146,7 +138,6 @@ static const char *machine_name;
 static char __initdata cmd_line[COMMAND_LINE_SIZE];
 struct machine_desc *machine_desc __initdata;
 
-static char default_command_line[COMMAND_LINE_SIZE] __initdata = CONFIG_CMDLINE;
 static union { char c[4]; unsigned long l; } endian_test __initdata = { { 'l', '?', '?', 'b' } };
 #define ENDIANNESS ((char)endian_test.l)
 
@@ -584,21 +575,6 @@ static int __init early_mem(char *p)
 }
 early_param("mem", early_mem);
 
-static void __init
-setup_ramdisk(int doload, int prompt, int image_start, unsigned int rd_sz)
-{
-#ifdef CONFIG_BLK_DEV_RAM
-	extern int rd_size, rd_image_start, rd_prompt, rd_doload;
-
-	rd_image_start = image_start;
-	rd_prompt = prompt;
-	rd_doload = doload;
-
-	if (rd_sz)
-		rd_size = rd_sz;
-#endif
-}
-
 static void __init request_standard_resources(struct machine_desc *mdesc)
 {
 	struct memblock_region *region;
@@ -644,35 +620,6 @@ static void __init request_standard_resources(struct machine_desc *mdesc)
 		request_resource(&ioport_resource, &lp2);
 }
 
-/*
- *  Tag parsing.
- *
- * This is the new way of passing data to the kernel at boot time.  Rather
- * than passing a fixed inflexible structure to the kernel, we pass a list
- * of variable-sized tags to the kernel.  The first tag must be a ATAG_CORE
- * tag for the list to be recognised (to distinguish the tagged list from
- * a param_struct).  The list is terminated with a zero-length tag (this tag
- * is not parsed in any way).
- */
-static int __init parse_tag_core(const struct tag *tag)
-{
-	if (tag->hdr.size > 2) {
-		if ((tag->u.core.flags & 1) == 0)
-			root_mountflags &= ~MS_RDONLY;
-		ROOT_DEV = old_decode_dev(tag->u.core.rootdev);
-	}
-	return 0;
-}
-
-__tagtable(ATAG_CORE, parse_tag_core);
-
-static int __init parse_tag_mem32(const struct tag *tag)
-{
-	return arm_add_memory(tag->u.mem.start, tag->u.mem.size);
-}
-
-__tagtable(ATAG_MEM, parse_tag_mem32);
-
 #if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_DUMMY_CONSOLE)
 struct screen_info screen_info = {
  .orig_video_lines	= 30,
@@ -682,116 +629,7 @@ struct screen_info screen_info = {
  .orig_video_isVGA	= 1,
  .orig_video_points	= 8
 };
-
-static int __init parse_tag_videotext(const struct tag *tag)
-{
-	screen_info.orig_x            = tag->u.videotext.x;
-	screen_info.orig_y            = tag->u.videotext.y;
-	screen_info.orig_video_page   = tag->u.videotext.video_page;
-	screen_info.orig_video_mode   = tag->u.videotext.video_mode;
-	screen_info.orig_video_cols   = tag->u.videotext.video_cols;
-	screen_info.orig_video_ega_bx = tag->u.videotext.video_ega_bx;
-	screen_info.orig_video_lines  = tag->u.videotext.video_lines;
-	screen_info.orig_video_isVGA  = tag->u.videotext.video_isvga;
-	screen_info.orig_video_points = tag->u.videotext.video_points;
-	return 0;
-}
-
-__tagtable(ATAG_VIDEOTEXT, parse_tag_videotext);
-#endif
-
-static int __init parse_tag_ramdisk(const struct tag *tag)
-{
-	setup_ramdisk((tag->u.ramdisk.flags & 1) == 0,
-		      (tag->u.ramdisk.flags & 2) == 0,
-		      tag->u.ramdisk.start, tag->u.ramdisk.size);
-	return 0;
-}
-
-__tagtable(ATAG_RAMDISK, parse_tag_ramdisk);
-
-static int __init parse_tag_serialnr(const struct tag *tag)
-{
-	system_serial_low = tag->u.serialnr.low;
-	system_serial_high = tag->u.serialnr.high;
-	return 0;
-}
-
-__tagtable(ATAG_SERIAL, parse_tag_serialnr);
-
-static int __init parse_tag_revision(const struct tag *tag)
-{
-	system_rev = tag->u.revision.rev;
-	return 0;
-}
-
-__tagtable(ATAG_REVISION, parse_tag_revision);
-
-static int __init parse_tag_cmdline(const struct tag *tag)
-{
-#if defined(CONFIG_CMDLINE_EXTEND)
-	strlcat(default_command_line, " ", COMMAND_LINE_SIZE);
-	strlcat(default_command_line, tag->u.cmdline.cmdline,
-		COMMAND_LINE_SIZE);
-#elif defined(CONFIG_CMDLINE_FORCE)
-	pr_warning("Ignoring tag cmdline (using the default kernel command line)\n");
-#else
-	strlcpy(default_command_line, tag->u.cmdline.cmdline,
-		COMMAND_LINE_SIZE);
 #endif
-	return 0;
-}
-
-__tagtable(ATAG_CMDLINE, parse_tag_cmdline);
-
-/*
- * Scan the tag table for this tag, and call its parse function.
- * The tag table is built by the linker from all the __tagtable
- * declarations.
- */
-static int __init parse_tag(const struct tag *tag)
-{
-	extern struct tagtable __tagtable_begin, __tagtable_end;
-	struct tagtable *t;
-
-	for (t = &__tagtable_begin; t < &__tagtable_end; t++)
-		if (tag->hdr.tag == t->tag) {
-			t->parse(tag);
-			break;
-		}
-
-	return t < &__tagtable_end;
-}
-
-/*
- * Parse all tags in the list, checking both the global and architecture
- * specific tag tables.
- */
-static void __init parse_tags(const struct tag *t)
-{
-	for (; t->hdr.size; t = tag_next(t))
-		if (!parse_tag(t))
-			printk(KERN_WARNING
-				"Ignoring unrecognised tag 0x%08x\n",
-				t->hdr.tag);
-}
-
-/*
- * This holds our defaults.
- */
-static struct init_tags {
-	struct tag_header hdr1;
-	struct tag_core   core;
-	struct tag_header hdr2;
-	struct tag_mem32  mem;
-	struct tag_header hdr3;
-} init_tags __initdata = {
-	{ tag_size(tag_core), ATAG_CORE },
-	{ 1, PAGE_SIZE, 0xff },
-	{ tag_size(tag_mem32), ATAG_MEM },
-	{ MEM_SIZE },
-	{ 0, ATAG_NONE }
-};
 
 static int __init customize_machine(void)
 {
@@ -859,78 +697,6 @@ static void __init reserve_crashkernel(void)
 static inline void reserve_crashkernel(void) {}
 #endif /* CONFIG_KEXEC */
 
-static void __init squash_mem_tags(struct tag *tag)
-{
-	for (; tag->hdr.size; tag = tag_next(tag))
-		if (tag->hdr.tag == ATAG_MEM)
-			tag->hdr.tag = ATAG_NONE;
-}
-
-static struct machine_desc * __init setup_machine_tags(unsigned int nr)
-{
-	struct tag *tags = (struct tag *)&init_tags;
-	struct machine_desc *mdesc = NULL, *p;
-	char *from = default_command_line;
-
-	init_tags.mem.start = PHYS_OFFSET;
-
-	/*
-	 * locate machine in the list of supported machines.
-	 */
-	for_each_machine_desc(p)
-		if (nr == p->nr) {
-			printk("Machine: %s\n", p->name);
-			mdesc = p;
-			break;
-		}
-
-	if (!mdesc) {
-		early_print("\nError: unrecognized/unsupported machine ID"
-			" (r1 = 0x%08x).\n\n", nr);
-		dump_machine_table(); /* does not return */
-	}
-
-	if (__atags_pointer)
-		tags = phys_to_virt(__atags_pointer);
-	else if (mdesc->atag_offset)
-		tags = (void *)(PAGE_OFFSET + mdesc->atag_offset);
-
-#if defined(CONFIG_DEPRECATED_PARAM_STRUCT)
-	/*
-	 * If we have the old style parameters, convert them to
-	 * a tag list.
-	 */
-	if (tags->hdr.tag != ATAG_CORE)
-		convert_to_tag_list(tags);
-#endif
-
-	if (tags->hdr.tag != ATAG_CORE) {
-#if defined(CONFIG_OF)
-		/*
-		 * If CONFIG_OF is set, then assume this is a reasonably
-		 * modern system that should pass boot parameters
-		 */
-		early_print("Warning: Neither atags nor dtb found\n");
-#endif
-		tags = (struct tag *)&init_tags;
-	}
-
-	if (mdesc->fixup)
-		mdesc->fixup(tags, &from, &meminfo);
-
-	if (tags->hdr.tag == ATAG_CORE) {
-		if (meminfo.nr_banks != 0)
-			squash_mem_tags(tags);
-		save_atags(tags);
-		parse_tags(tags);
-	}
-
-	/* parse_early_param needs a boot_command_line */
-	strlcpy(boot_command_line, from, COMMAND_LINE_SIZE);
-
-	return mdesc;
-}
-
 static int __init meminfo_cmp(const void *_a, const void *_b)
 {
 	const struct membank *a = _a, *b = _b;
@@ -960,7 +726,7 @@ void __init setup_arch(char **cmdline_p)
 	setup_processor();
 	mdesc = setup_machine_fdt(__atags_pointer);
 	if (!mdesc)
-		mdesc = setup_machine_tags(machine_arch_type);
+		mdesc = setup_machine_tags(__atags_pointer, machine_arch_type);
 	machine_desc = mdesc;
 	machine_name = mdesc->name;
 
@@ -993,8 +759,10 @@ void __init setup_arch(char **cmdline_p)
 	unflatten_device_tree();
 
 #ifdef CONFIG_SMP
-	if (is_smp())
+	if (is_smp()) {
+		smp_set_ops(mdesc->smp);
 		smp_init_cpus();
+	}
 #endif
 
 	if (!is_smp())
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index f34514a0834..8e20754dd31 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -19,14 +19,15 @@
 #include <linux/mm.h>
 #include <linux/err.h>
 #include <linux/cpu.h>
-#include <linux/smp.h>
 #include <linux/seq_file.h>
 #include <linux/irq.h>
 #include <linux/percpu.h>
 #include <linux/clockchips.h>
 #include <linux/completion.h>
+#include <linux/cpufreq.h>
 
 #include <linux/atomic.h>
+#include <asm/smp.h>
 #include <asm/cacheflush.h>
 #include <asm/cpu.h>
 #include <asm/cputype.h>
@@ -43,6 +44,7 @@
 #include <asm/localtimer.h>
 #include <asm/smp_plat.h>
 #include <asm/virt.h>
+#include <asm/mach/arch.h>
 
 /*
  * as from 2.5, kernels no longer have an init_tasks structure
@@ -51,8 +53,15 @@
  */
 struct secondary_data secondary_data;
 
+/*
+ * control for which core is the next to come out of the secondary
+ * boot "holding pen"
+ */
+volatile int __cpuinitdata pen_release = -1;
+
 enum ipi_msg_type {
-	IPI_TIMER = 2,
+	IPI_WAKEUP,
+	IPI_TIMER,
 	IPI_RESCHEDULE,
 	IPI_CALL_FUNC,
 	IPI_CALL_FUNC_SINGLE,
@@ -61,6 +70,14 @@ enum ipi_msg_type {
 
 static DECLARE_COMPLETION(cpu_running);
 
+static struct smp_operations smp_ops;
+
+void __init smp_set_ops(struct smp_operations *ops)
+{
+	if (ops)
+		smp_ops = *ops;
+};
+
 int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *idle)
 {
 	int ret;
@@ -101,13 +118,64 @@ int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *idle)
 	return ret;
 }
 
+/* platform specific SMP operations */
+void __init smp_init_cpus(void)
+{
+	if (smp_ops.smp_init_cpus)
+		smp_ops.smp_init_cpus();
+}
+
+static void __init platform_smp_prepare_cpus(unsigned int max_cpus)
+{
+	if (smp_ops.smp_prepare_cpus)
+		smp_ops.smp_prepare_cpus(max_cpus);
+}
+
+static void __cpuinit platform_secondary_init(unsigned int cpu)
+{
+	if (smp_ops.smp_secondary_init)
+		smp_ops.smp_secondary_init(cpu);
+}
+
+int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
+{
+	if (smp_ops.smp_boot_secondary)
+		return smp_ops.smp_boot_secondary(cpu, idle);
+	return -ENOSYS;
+}
+
 #ifdef CONFIG_HOTPLUG_CPU
 static void percpu_timer_stop(void);
 
+static int platform_cpu_kill(unsigned int cpu)
+{
+	if (smp_ops.cpu_kill)
+		return smp_ops.cpu_kill(cpu);
+	return 1;
+}
+
+static void platform_cpu_die(unsigned int cpu)
+{
+	if (smp_ops.cpu_die)
+		smp_ops.cpu_die(cpu);
+}
+
+static int platform_cpu_disable(unsigned int cpu)
+{
+	if (smp_ops.cpu_disable)
+		return smp_ops.cpu_disable(cpu);
+
+	/*
+	 * By default, allow disabling all CPUs except the first one,
+	 * since this is special on a lot of platforms, e.g. because
+	 * of clock tick interrupts.
+	 */
+	return cpu == 0 ? -EPERM : 0;
+}
 /*
  * __cpu_disable runs on the processor to be shutdown.
  */
-int __cpu_disable(void)
+int __cpuinit __cpu_disable(void)
 {
 	unsigned int cpu = smp_processor_id();
 	int ret;
@@ -153,7 +221,7 @@ 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)
+void __cpuinit __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);
@@ -353,7 +421,8 @@ void arch_send_call_function_single_ipi(int cpu)
 }
 
 static const char *ipi_types[NR_IPI] = {
-#define S(x,s)	[x - IPI_TIMER] = s
+#define S(x,s)	[x] = s
+	S(IPI_WAKEUP, "CPU wakeup interrupts"),
 	S(IPI_TIMER, "Timer broadcast interrupts"),
 	S(IPI_RESCHEDULE, "Rescheduling interrupts"),
 	S(IPI_CALL_FUNC, "Function call interrupts"),
@@ -506,10 +575,13 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 	unsigned int cpu = smp_processor_id();
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
-	if (ipinr >= IPI_TIMER && ipinr < IPI_TIMER + NR_IPI)
-		__inc_irq_stat(cpu, ipi_irqs[ipinr - IPI_TIMER]);
+	if (ipinr < NR_IPI)
+		__inc_irq_stat(cpu, ipi_irqs[ipinr]);
 
 	switch (ipinr) {
+	case IPI_WAKEUP:
+		break;
+
 	case IPI_TIMER:
 		irq_enter();
 		ipi_timer();
@@ -590,3 +662,56 @@ int setup_profiling_timer(unsigned int multiplier)
 {
 	return -EINVAL;
 }
+
+#ifdef CONFIG_CPU_FREQ
+
+static DEFINE_PER_CPU(unsigned long, l_p_j_ref);
+static DEFINE_PER_CPU(unsigned long, l_p_j_ref_freq);
+static unsigned long global_l_p_j_ref;
+static unsigned long global_l_p_j_ref_freq;
+
+static int cpufreq_callback(struct notifier_block *nb,
+					unsigned long val, void *data)
+{
+	struct cpufreq_freqs *freq = data;
+	int cpu = freq->cpu;
+
+	if (freq->flags & CPUFREQ_CONST_LOOPS)
+		return NOTIFY_OK;
+
+	if (!per_cpu(l_p_j_ref, cpu)) {
+		per_cpu(l_p_j_ref, cpu) =
+			per_cpu(cpu_data, cpu).loops_per_jiffy;
+		per_cpu(l_p_j_ref_freq, cpu) = freq->old;
+		if (!global_l_p_j_ref) {
+			global_l_p_j_ref = loops_per_jiffy;
+			global_l_p_j_ref_freq = freq->old;
+		}
+	}
+
+	if ((val == CPUFREQ_PRECHANGE  && freq->old < freq->new) ||
+	    (val == CPUFREQ_POSTCHANGE && freq->old > freq->new) ||
+	    (val == CPUFREQ_RESUMECHANGE || val == CPUFREQ_SUSPENDCHANGE)) {
+		loops_per_jiffy = cpufreq_scale(global_l_p_j_ref,
+						global_l_p_j_ref_freq,
+						freq->new);
+		per_cpu(cpu_data, cpu).loops_per_jiffy =
+			cpufreq_scale(per_cpu(l_p_j_ref, cpu),
+					per_cpu(l_p_j_ref_freq, cpu),
+					freq->new);
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block cpufreq_notifier = {
+	.notifier_call  = cpufreq_callback,
+};
+
+static int __init register_cpufreq_notifier(void)
+{
+	return cpufreq_register_notifier(&cpufreq_notifier,
+						CPUFREQ_TRANSITION_NOTIFIER);
+}
+core_initcall(register_cpufreq_notifier);
+
+#endif
diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c
index af2afb01967..09be0c3c906 100644
--- a/arch/arm/kernel/time.c
+++ b/arch/arm/kernel/time.c
@@ -25,7 +25,6 @@
 #include <linux/timer.h>
 #include <linux/irq.h>
 
-#include <asm/leds.h>
 #include <asm/thread_info.h>
 #include <asm/sched_clock.h>
 #include <asm/stacktrace.h>
@@ -80,21 +79,6 @@ u32 arch_gettimeoffset(void)
 }
 #endif /* CONFIG_ARCH_USES_GETTIMEOFFSET */
 
-#ifdef CONFIG_LEDS_TIMER
-static inline void do_leds(void)
-{
-	static unsigned int count = HZ/2;
-
-	if (--count == 0) {
-		count = HZ/2;
-		leds_event(led_timer);
-	}
-}
-#else
-#define	do_leds()
-#endif
-
-
 #ifndef CONFIG_GENERIC_CLOCKEVENTS
 /*
  * Kernel system timer support.
@@ -102,7 +86,6 @@ static inline void do_leds(void)
 void timer_tick(void)
 {
 	profile_tick(CPU_PROFILING);
-	do_leds();
 	xtime_update(1);
 #ifndef CONFIG_SMP
 	update_process_times(user_mode(get_irq_regs()));