23 files changed, 496 insertions, 254 deletions

diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 7b787d642af4..7ad2d5cf7008 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -34,6 +34,7 @@ obj-$(CONFIG_ARM_CPU_SUSPEND)	+= sleep.o suspend.o
 obj-$(CONFIG_SMP)		+= smp.o smp_tlb.o
 obj-$(CONFIG_HAVE_ARM_SCU)	+= smp_scu.o
 obj-$(CONFIG_HAVE_ARM_TWD)	+= smp_twd.o
+obj-$(CONFIG_ARM_ARCH_TIMER)	+= arch_timer.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o insn.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o insn.o
 obj-$(CONFIG_JUMP_LABEL)	+= jump_label.o insn.o patch.o
@@ -81,4 +82,4 @@ head-y			:= head$(MMUEXT).o
 obj-$(CONFIG_DEBUG_LL)	+= debug.o
 obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 
-extra-y := $(head-y) init_task.o vmlinux.lds
+extra-y := $(head-y) vmlinux.lds
diff --git a/arch/arm/kernel/arch_timer.c b/arch/arm/kernel/arch_timer.c
new file mode 100644
index 000000000000..dd58035621f7
--- /dev/null
+++ b/arch/arm/kernel/arch_timer.c
@@ -0,0 +1,350 @@
+/*
+ *  linux/arch/arm/kernel/arch_timer.c
+ *
+ *  Copyright (C) 2011 ARM Ltd.
+ *  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/init.h>
+#include <linux/kernel.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/smp.h>
+#include <linux/cpu.h>
+#include <linux/jiffies.h>
+#include <linux/clockchips.h>
+#include <linux/interrupt.h>
+#include <linux/of_irq.h>
+#include <linux/io.h>
+
+#include <asm/cputype.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;
+
+static struct clock_event_device __percpu **arch_timer_evt;
+
+/*
+ * Architected system timer support.
+ */
+
+#define ARCH_TIMER_CTRL_ENABLE		(1 << 0)
+#define ARCH_TIMER_CTRL_IT_MASK		(1 << 1)
+#define ARCH_TIMER_CTRL_IT_STAT		(1 << 2)
+
+#define ARCH_TIMER_REG_CTRL		0
+#define ARCH_TIMER_REG_FREQ		1
+#define ARCH_TIMER_REG_TVAL		2
+
+static void arch_timer_reg_write(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;
+	}
+
+	isb();
+}
+
+static u32 arch_timer_reg_read(int reg)
+{
+	u32 val;
+
+	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();
+	}
+
+	return val;
+}
+
+static irqreturn_t arch_timer_handler(int irq, void *dev_id)
+{
+	struct clock_event_device *evt = *(struct clock_event_device **)dev_id;
+	unsigned long ctrl;
+
+	ctrl = arch_timer_reg_read(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);
+		evt->event_handler(evt);
+		return IRQ_HANDLED;
+	}
+
+	return IRQ_NONE;
+}
+
+static void arch_timer_disable(void)
+{
+	unsigned long ctrl;
+
+	ctrl = arch_timer_reg_read(ARCH_TIMER_REG_CTRL);
+	ctrl &= ~ARCH_TIMER_CTRL_ENABLE;
+	arch_timer_reg_write(ARCH_TIMER_REG_CTRL, ctrl);
+}
+
+static void arch_timer_set_mode(enum clock_event_mode mode,
+				struct clock_event_device *clk)
+{
+	switch (mode) {
+	case CLOCK_EVT_MODE_UNUSED:
+	case CLOCK_EVT_MODE_SHUTDOWN:
+		arch_timer_disable();
+		break;
+	default:
+		break;
+	}
+}
+
+static int arch_timer_set_next_event(unsigned long evt,
+				     struct clock_event_device *unused)
+{
+	unsigned long ctrl;
+
+	ctrl = arch_timer_reg_read(ARCH_TIMER_REG_CTRL);
+	ctrl |= ARCH_TIMER_CTRL_ENABLE;
+	ctrl &= ~ARCH_TIMER_CTRL_IT_MASK;
+
+	arch_timer_reg_write(ARCH_TIMER_REG_TVAL, evt);
+	arch_timer_reg_write(ARCH_TIMER_REG_CTRL, ctrl);
+
+	return 0;
+}
+
+static int __cpuinit arch_timer_setup(struct clock_event_device *clk)
+{
+	/* Be safe... */
+	arch_timer_disable();
+
+	clk->features = CLOCK_EVT_FEAT_ONESHOT;
+	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;
+
+	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);
+
+	return 0;
+}
+
+/* Is the optional system timer available? */
+static int local_timer_is_architected(void)
+{
+	return (cpu_architecture() >= CPU_ARCH_ARMv7) &&
+	       ((read_cpuid_ext(CPUID_EXT_PFR1) >> 16) & 0xf) == 1;
+}
+
+static int arch_timer_available(void)
+{
+	unsigned long freq;
+
+	if (!local_timer_is_architected())
+		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);
+
+		/* Check the timer frequency. */
+		if (freq == 0) {
+			pr_warn("Architected timer frequency not available\n");
+			return -EINVAL;
+		}
+
+		arch_timer_rate = freq;
+	}
+
+	pr_info_once("Architected local timer running at %lu.%02luMHz.\n",
+		     arch_timer_rate / 1000000, (arch_timer_rate / 10000) % 100);
+	return 0;
+}
+
+static inline cycle_t arch_counter_get_cntpct(void)
+{
+	u32 cvall, cvalh;
+
+	asm volatile("mrrc p15, 0, %0, %1, c14" : "=r" (cvall), "=r" (cvalh));
+
+	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;
+}
+
+static u32 notrace arch_counter_get_cntvct32(void)
+{
+	cycle_t cntvct = 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);
+}
+
+static cycle_t arch_counter_read(struct clocksource *cs)
+{
+	return arch_counter_get_cntpct();
+}
+
+static struct clocksource clocksource_counter = {
+	.name	= "arch_sys_counter",
+	.rating	= 400,
+	.read	= arch_counter_read,
+	.mask	= CLOCKSOURCE_MASK(56),
+	.flags	= CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+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);
+}
+
+static struct local_timer_ops arch_timer_ops __cpuinitdata = {
+	.setup	= arch_timer_setup,
+	.stop	= arch_timer_stop,
+};
+
+static struct clock_event_device arch_timer_global_evt;
+
+static int __init arch_timer_register(void)
+{
+	int err;
+
+	err = arch_timer_available();
+	if (err)
+		return err;
+
+	arch_timer_evt = alloc_percpu(struct clock_event_device *);
+	if (!arch_timer_evt)
+		return -ENOMEM;
+
+	clocksource_register_hz(&clocksource_counter, arch_timer_rate);
+
+	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);
+		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) {
+		/*
+		 * We couldn't register as a local timer (could be
+		 * because we're on a UP platform, or because some
+		 * other local timer is already present...). Try as a
+		 * global timer instead.
+		 */
+		arch_timer_global_evt.cpumask = cpumask_of(0);
+		err = arch_timer_setup(&arch_timer_global_evt);
+	}
+
+	if (err)
+		goto out_free_irq;
+
+	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);
+
+out_free:
+	free_percpu(arch_timer_evt);
+
+	return err;
+}
+
+static const struct of_device_id arch_timer_of_match[] __initconst = {
+	{ .compatible	= "arm,armv7-timer",	},
+	{},
+};
+
+int __init arch_timer_of_register(void)
+{
+	struct device_node *np;
+	u32 freq;
+
+	np = of_find_matching_node(NULL, arch_timer_of_match);
+	if (!np) {
+		pr_err("arch_timer: can't find DT node\n");
+		return -ENODEV;
+	}
+
+	/* Try to determine the frequency from the device tree or CNTFRQ */
+	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);
+
+	return arch_timer_register();
+}
+
+int __init arch_timer_sched_clock_init(void)
+{
+	int err;
+
+	err = arch_timer_available();
+	if (err)
+		return err;
+
+	setup_sched_clock(arch_counter_get_cntvct32, 32, arch_timer_rate);
+	return 0;
+}
diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c
index 632df9a66f8c..25552508c3fd 100644
--- a/arch/arm/kernel/bios32.c
+++ b/arch/arm/kernel/bios32.c
@@ -299,7 +299,6 @@ static inline int pdev_bad_for_parity(struct pci_dev *dev)
  */
 void pcibios_fixup_bus(struct pci_bus *bus)
 {
-	struct pci_sys_data *root = bus->sysdata;
 	struct pci_dev *dev;
 	u16 features = PCI_COMMAND_SERR | PCI_COMMAND_PARITY | PCI_COMMAND_FAST_BACK;
 
@@ -375,16 +374,29 @@ EXPORT_SYMBOL(pcibios_fixup_bus);
 #endif
 
 /*
- * Swizzle the device pin each time we cross a bridge.
- * This might update pin and returns the slot number.
+ * Swizzle the device pin each time we cross a bridge.  If a platform does
+ * not provide a swizzle function, we perform the standard PCI swizzling.
+ *
+ * The default swizzling walks up the bus tree one level at a time, applying
+ * the standard swizzle function at each step, stopping when it finds the PCI
+ * root bus.  This will return the slot number of the bridge device on the
+ * root bus and the interrupt pin on that device which should correspond
+ * with the downstream device interrupt.
+ *
+ * Platforms may override this, in which case the slot and pin returned
+ * depend entirely on the platform code.  However, please note that the
+ * PCI standard swizzle is implemented on plug-in cards and Cardbus based
+ * PCI extenders, so it can not be ignored.
  */
 static u8 __devinit pcibios_swizzle(struct pci_dev *dev, u8 *pin)
 {
 	struct pci_sys_data *sys = dev->sysdata;
-	int slot = 0, oldpin = *pin;
+	int slot, oldpin = *pin;
 
 	if (sys->swizzle)
 		slot = sys->swizzle(dev, pin);
+	else
+		slot = pci_common_swizzle(dev, pin);
 
 	if (debug_pci)
 		printk("PCI: %s swizzling pin %d => pin %d slot %d\n",
@@ -411,7 +423,7 @@ static int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 	return irq;
 }
 
-static void __init pcibios_init_hw(struct hw_pci *hw)
+static void __init pcibios_init_hw(struct hw_pci *hw, struct list_head *head)
 {
 	struct pci_sys_data *sys = NULL;
 	int ret;
@@ -425,7 +437,6 @@ static void __init pcibios_init_hw(struct hw_pci *hw)
 #ifdef CONFIG_PCI_DOMAINS
 		sys->domain  = hw->domain;
 #endif
-		sys->hw      = hw;
 		sys->busnr   = busnr;
 		sys->swizzle = hw->swizzle;
 		sys->map_irq = hw->map_irq;
@@ -441,14 +452,18 @@ static void __init pcibios_init_hw(struct hw_pci *hw)
 					 &iomem_resource, sys->mem_offset);
 			}
 
-			sys->bus = hw->scan(nr, sys);
+			if (hw->scan)
+				sys->bus = hw->scan(nr, sys);
+			else
+				sys->bus = pci_scan_root_bus(NULL, sys->busnr,
+						hw->ops, sys, &sys->resources);
 
 			if (!sys->bus)
 				panic("PCI: unable to scan bus!");
 
 			busnr = sys->bus->subordinate + 1;
 
-			list_add(&sys->node, &hw->buses);
+			list_add(&sys->node, head);
 		} else {
 			kfree(sys);
 			if (ret < 0)
@@ -460,19 +475,18 @@ static void __init pcibios_init_hw(struct hw_pci *hw)
 void __init pci_common_init(struct hw_pci *hw)
 {
 	struct pci_sys_data *sys;
-
-	INIT_LIST_HEAD(&hw->buses);
+	LIST_HEAD(head);
 
 	pci_add_flags(PCI_REASSIGN_ALL_RSRC);
 	if (hw->preinit)
 		hw->preinit();
-	pcibios_init_hw(hw);
+	pcibios_init_hw(hw, &head);
 	if (hw->postinit)
 		hw->postinit();
 
 	pci_fixup_irqs(pcibios_swizzle, pcibios_map_irq);
 
-	list_for_each_entry(sys, &hw->buses, node) {
+	list_for_each_entry(sys, &head, node) {
 		struct pci_bus *bus = sys->bus;
 
 		if (!pci_has_flag(PCI_PROBE_ONLY)) {
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 7fd3ad048da9..437f0c426517 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -556,10 +556,6 @@ call_fpe:
 #endif
 	tst	r0, #0x08000000			@ only CDP/CPRT/LDC/STC have bit 27
 	tstne	r0, #0x04000000			@ bit 26 set on both ARM and Thumb-2
-#if defined(CONFIG_CPU_ARM610) || defined(CONFIG_CPU_ARM710)
-	and	r8, r0, #0x0f000000		@ mask out op-code bits
-	teqne	r8, #0x0f000000			@ SWI (ARM6/7 bug)?
-#endif
 	moveq	pc, lr
 	get_thread_info r10			@ get current thread
 	and	r8, r0, #0x00000f00		@ mask out CP number
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 54ee265dd819..7bd2d3cb8957 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -335,20 +335,6 @@ ENDPROC(ftrace_stub)
  *-----------------------------------------------------------------------------
  */
 
-	/* If we're optimising for StrongARM the resulting code won't 
-	   run on an ARM7 and we can save a couple of instructions.  
-								--pb */
-#ifdef CONFIG_CPU_ARM710
-#define A710(code...) code
-.Larm710bug:
-	ldmia	sp, {r0 - lr}^			@ Get calling r0 - lr
-	mov	r0, r0
-	add	sp, sp, #S_FRAME_SIZE
-	subs	pc, lr, #4
-#else
-#define A710(code...)
-#endif
-
 	.align	5
 ENTRY(vector_swi)
 	sub	sp, sp, #S_FRAME_SIZE
@@ -379,9 +365,6 @@ ENTRY(vector_swi)
 	ldreq	r10, [lr, #-4]			@ get SWI instruction
 #else
 	ldr	r10, [lr, #-4]			@ get SWI instruction
-  A710(	and	ip, r10, #0x0f000000		@ check for SWI		)
-  A710(	teq	ip, #0x0f000000						)
-  A710(	bne	.Larm710bug						)
 #endif
 #ifdef CONFIG_CPU_ENDIAN_BE8
 	rev	r10, r10			@ little endian instruction
@@ -392,26 +375,15 @@ ENTRY(vector_swi)
 	/*
 	 * Pure EABI user space always put syscall number into scno (r7).
 	 */
-  A710(	ldr	ip, [lr, #-4]			@ get SWI instruction	)
-  A710(	and	ip, ip, #0x0f000000		@ check for SWI		)
-  A710(	teq	ip, #0x0f000000						)
-  A710(	bne	.Larm710bug						)
-
 #elif defined(CONFIG_ARM_THUMB)
-
 	/* Legacy ABI only, possibly thumb mode. */
 	tst	r8, #PSR_T_BIT			@ this is SPSR from save_user_regs
 	addne	scno, r7, #__NR_SYSCALL_BASE	@ put OS number in
 	ldreq	scno, [lr, #-4]
 
 #else
-
 	/* Legacy ABI only. */
 	ldr	scno, [lr, #-4]			@ get SWI instruction
-  A710(	and	ip, scno, #0x0f000000		@ check for SWI		)
-  A710(	teq	ip, #0x0f000000						)
-  A710(	bne	.Larm710bug						)
-
 #endif
 
 #ifdef CONFIG_ALIGNMENT_TRAP
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 3bf0c7f8b043..835898e7d704 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -277,10 +277,6 @@ __create_page_tables:
 	mov	r3, r3, lsl #PMD_ORDER
 
 	add	r0, r4, r3
-	rsb	r3, r3, #0x4000			@ PTRS_PER_PGD*sizeof(long)
-	cmp	r3, #0x0800			@ limit to 512MB
-	movhi	r3, #0x0800
-	add	r6, r0, r3
 	mov	r3, r7, lsr #SECTION_SHIFT
 	ldr	r7, [r10, #PROCINFO_IO_MMUFLAGS] @ io_mmuflags
 	orr	r3, r7, r3, lsl #SECTION_SHIFT
@@ -289,13 +285,10 @@ __create_page_tables:
 #else
 	orr	r3, r3, #PMD_SECT_XN
 #endif
-1:	str	r3, [r0], #4
+	str	r3, [r0], #4
 #ifdef CONFIG_ARM_LPAE
 	str	r7, [r0], #4
 #endif
-	add	r3, r3, #1 << SECTION_SHIFT
-	cmp	r0, r6
-	blo	1b
 
 #else /* CONFIG_DEBUG_ICEDCC || CONFIG_DEBUG_SEMIHOSTING */
 	/* we don't need any serial debugging mappings */
diff --git a/arch/arm/kernel/init_task.c b/arch/arm/kernel/init_task.c
deleted file mode 100644
index e7cbb50dc356..000000000000
--- a/arch/arm/kernel/init_task.c
+++ /dev/null
@@ -1,37 +0,0 @@
-/*
- *  linux/arch/arm/kernel/init_task.c
- */
-#include <linux/mm.h>
-#include <linux/module.h>
-#include <linux/fs.h>
-#include <linux/sched.h>
-#include <linux/init.h>
-#include <linux/init_task.h>
-#include <linux/mqueue.h>
-#include <linux/uaccess.h>
-
-#include <asm/pgtable.h>
-
-static struct signal_struct init_signals = INIT_SIGNALS(init_signals);
-static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand);
-/*
- * Initial thread structure.
- *
- * We need to make sure that this is 8192-byte aligned due to the
- * way process stacks are handled. This is done by making sure
- * the linker maps this in the .text segment right after head.S,
- * and making head.S ensure the proper alignment.
- *
- * The things we do for performance..
- */
-union thread_union init_thread_union __init_task_data =
-	{ INIT_THREAD_INFO(init_task) };
-
-/*
- * Initial task structure.
- *
- * All other task structs will be allocated on slabs in fork.c
- */
-struct task_struct init_task = INIT_TASK(init_task);
-
-EXPORT_SYMBOL(init_task);
diff --git a/arch/arm/kernel/insn.c b/arch/arm/kernel/insn.c
index ab312e516546..b760340b7014 100644
--- a/arch/arm/kernel/insn.c
+++ b/arch/arm/kernel/insn.c
@@ -1,3 +1,4 @@
+#include <linux/bug.h>
 #include <linux/kernel.h>
 #include <asm/opcodes.h>
 
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 71ccdbfed662..8349d4e97e2b 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -155,10 +155,10 @@ static bool migrate_one_irq(struct irq_desc *desc)
 	}
 
 	c = irq_data_get_irq_chip(d);
-	if (c->irq_set_affinity)
-		c->irq_set_affinity(d, affinity, true);
-	else
+	if (!c->irq_set_affinity)
 		pr_debug("IRQ%u: unable to set affinity\n", d->irq);
+	else if (c->irq_set_affinity(d, affinity, true) == IRQ_SET_MASK_OK && ret)
+		cpumask_copy(d->affinity, affinity);
 
 	return ret;
 }
diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c
index ab1869dac97a..4dd41fc9e235 100644
--- a/arch/arm/kernel/kprobes.c
+++ b/arch/arm/kernel/kprobes.c
@@ -152,7 +152,7 @@ int __kprobes __arch_disarm_kprobe(void *p)
 
 void __kprobes arch_disarm_kprobe(struct kprobe *p)
 {
-	stop_machine(__arch_disarm_kprobe, p, &cpu_online_map);
+	stop_machine(__arch_disarm_kprobe, p, cpu_online_mask);
 }
 
 void __kprobes arch_remove_kprobe(struct kprobe *p)
diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c
index b78af0cc6ef3..ab627a740fa3 100644
--- a/arch/arm/kernel/perf_event_v6.c
+++ b/arch/arm/kernel/perf_event_v6.c
@@ -489,8 +489,6 @@ armv6pmu_handle_irq(int irq_num,
 	 */
 	armv6_pmcr_write(pmcr);
 
-	perf_sample_data_init(&data, 0);
-
 	cpuc = &__get_cpu_var(cpu_hw_events);
 	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
 		struct perf_event *event = cpuc->events[idx];
@@ -509,7 +507,7 @@ armv6pmu_handle_irq(int irq_num,
 
 		hwc = &event->hw;
 		armpmu_event_update(event, hwc, idx);
-		data.period = event->hw.last_period;
+		perf_sample_data_init(&data, 0, hwc->last_period);
 		if (!armpmu_event_set_period(event, hwc, idx))
 			continue;
 
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 00755d82e2f2..d3c536068162 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -1077,8 +1077,6 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
 	 */
 	regs = get_irq_regs();
 
-	perf_sample_data_init(&data, 0);
-
 	cpuc = &__get_cpu_var(cpu_hw_events);
 	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
 		struct perf_event *event = cpuc->events[idx];
@@ -1097,7 +1095,7 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
 
 		hwc = &event->hw;
 		armpmu_event_update(event, hwc, idx);
-		data.period = event->hw.last_period;
+		perf_sample_data_init(&data, 0, hwc->last_period);
 		if (!armpmu_event_set_period(event, hwc, idx))
 			continue;
 
diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c
index 71a21e6712f5..e34e7254e652 100644
--- a/arch/arm/kernel/perf_event_xscale.c
+++ b/arch/arm/kernel/perf_event_xscale.c
@@ -248,8 +248,6 @@ xscale1pmu_handle_irq(int irq_num, void *dev)
 
 	regs = get_irq_regs();
 
-	perf_sample_data_init(&data, 0);
-
 	cpuc = &__get_cpu_var(cpu_hw_events);
 	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
 		struct perf_event *event = cpuc->events[idx];
@@ -263,7 +261,7 @@ xscale1pmu_handle_irq(int irq_num, void *dev)
 
 		hwc = &event->hw;
 		armpmu_event_update(event, hwc, idx);
-		data.period = event->hw.last_period;
+		perf_sample_data_init(&data, 0, hwc->last_period);
 		if (!armpmu_event_set_period(event, hwc, idx))
 			continue;
 
@@ -588,8 +586,6 @@ xscale2pmu_handle_irq(int irq_num, void *dev)
 
 	regs = get_irq_regs();
 
-	perf_sample_data_init(&data, 0);
-
 	cpuc = &__get_cpu_var(cpu_hw_events);
 	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
 		struct perf_event *event = cpuc->events[idx];
@@ -603,7 +599,7 @@ xscale2pmu_handle_irq(int irq_num, void *dev)
 
 		hwc = &event->hw;
 		armpmu_event_update(event, hwc, idx);
-		data.period = event->hw.last_period;
+		perf_sample_data_init(&data, 0, hwc->last_period);
 		if (!armpmu_event_set_period(event, hwc, idx))
 			continue;
 
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 2b7b017a20cd..19c95ea65b2f 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -157,26 +157,6 @@ EXPORT_SYMBOL(pm_power_off);
 void (*arm_pm_restart)(char str, const char *cmd) = null_restart;
 EXPORT_SYMBOL_GPL(arm_pm_restart);
 
-static void do_nothing(void *unused)
-{
-}
-
-/*
- * cpu_idle_wait - Used to ensure that all the CPUs discard old value of
- * pm_idle and update to new pm_idle value. Required while changing pm_idle
- * handler on SMP systems.
- *
- * Caller must have changed pm_idle to the new value before the call. Old
- * pm_idle value will not be used by any CPU after the return of this function.
- */
-void cpu_idle_wait(void)
-{
-	smp_mb();
-	/* kick all the CPUs so that they exit out of pm_idle */
-	smp_call_function(do_nothing, NULL, 1);
-}
-EXPORT_SYMBOL_GPL(cpu_idle_wait);
-
 /*
  * This is our default idle handler.
  */
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 45956c9d0ef0..14e38261cd31 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -24,6 +24,7 @@
 #include <linux/hw_breakpoint.h>
 #include <linux/regset.h>
 #include <linux/audit.h>
+#include <linux/tracehook.h>
 
 #include <asm/pgtable.h>
 #include <asm/traps.h>
@@ -256,7 +257,7 @@ static int ptrace_read_user(struct task_struct *tsk, unsigned long off,
 {
 	unsigned long tmp;
 
-	if (off & 3 || off >= sizeof(struct user))
+	if (off & 3)
 		return -EIO;
 
 	tmp = 0;
@@ -268,6 +269,8 @@ static int ptrace_read_user(struct task_struct *tsk, unsigned long off,
 		tmp = tsk->mm->end_code;
 	else if (off < sizeof(struct pt_regs))
 		tmp = get_user_reg(tsk, off >> 2);
+	else if (off >= sizeof(struct user))
+		return -EIO;
 
 	return put_user(tmp, ret);
 }
@@ -904,49 +907,33 @@ long arch_ptrace(struct task_struct *child, long request,
 	return ret;
 }
 
-#ifdef __ARMEB__
-#define AUDIT_ARCH_NR AUDIT_ARCH_ARMEB
-#else
-#define AUDIT_ARCH_NR AUDIT_ARCH_ARM
-#endif
-
 asmlinkage int syscall_trace(int why, struct pt_regs *regs, int scno)
 {
 	unsigned long ip;
 
-	/*
-	 * Save IP.  IP is used to denote syscall entry/exit:
-	 *  IP = 0 -> entry, = 1 -> exit
-	 */
-	ip = regs->ARM_ip;
-	regs->ARM_ip = why;
-
-	if (!ip)
+	if (why)
 		audit_syscall_exit(regs);
 	else
-		audit_syscall_entry(AUDIT_ARCH_NR, scno, regs->ARM_r0,
+		audit_syscall_entry(AUDIT_ARCH_ARM, scno, regs->ARM_r0,
 				    regs->ARM_r1, regs->ARM_r2, regs->ARM_r3);
 
 	if (!test_thread_flag(TIF_SYSCALL_TRACE))
 		return scno;
-	if (!(current->ptrace & PT_PTRACED))
-		return scno;
 
 	current_thread_info()->syscall = scno;
 
-	/* the 0x80 provides a way for the tracing parent to distinguish
-	   between a syscall stop and SIGTRAP delivery */
-	ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD)
-				 ? 0x80 : 0));
 	/*
-	 * this isn't the same as continuing with a signal, but it will do
-	 * for normal use.  strace only continues with a signal if the
-	 * stopping signal is not SIGTRAP.  -brl
+	 * IP is used to denote syscall entry/exit:
+	 * IP = 0 -> entry, =1 -> exit
 	 */
-	if (current->exit_code) {
-		send_sig(current->exit_code, current, 1);
-		current->exit_code = 0;
-	}
+	ip = regs->ARM_ip;
+	regs->ARM_ip = why;
+
+	if (why)
+		tracehook_report_syscall_exit(regs, 0);
+	else if (tracehook_report_syscall_entry(regs))
+		current_thread_info()->syscall = -1;
+
 	regs->ARM_ip = ip;
 
 	return current_thread_info()->syscall;
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index b91411371ae1..ebfac782593f 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -523,7 +523,21 @@ int __init arm_add_memory(phys_addr_t start, unsigned long size)
 	 */
 	size -= start & ~PAGE_MASK;
 	bank->start = PAGE_ALIGN(start);
-	bank->size  = size & PAGE_MASK;
+
+#ifndef CONFIG_LPAE
+	if (bank->start + size < bank->start) {
+		printk(KERN_CRIT "Truncating memory at 0x%08llx to fit in "
+			"32-bit physical address space\n", (long long)start);
+		/*
+		 * To ensure bank->start + bank->size is representable in
+		 * 32 bits, we use ULONG_MAX as the upper limit rather than 4GB.
+		 * This means we lose a page after masking.
+		 */
+		size = ULONG_MAX - bank->start;
+	}
+#endif
+
+	bank->size = size & PAGE_MASK;
 
 	/*
 	 * Check whether this memory region has non-zero size or
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 7cb532fc8aa4..73d9a420850d 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -180,44 +180,23 @@ static int restore_iwmmxt_context(struct iwmmxt_sigframe *frame)
 
 static int preserve_vfp_context(struct vfp_sigframe __user *frame)
 {
-	struct thread_info *thread = current_thread_info();
-	struct vfp_hard_struct *h = &thread->vfpstate.hard;
 	const unsigned long magic = VFP_MAGIC;
 	const unsigned long size = VFP_STORAGE_SIZE;
 	int err = 0;
 
-	vfp_sync_hwstate(thread);
 	__put_user_error(magic, &frame->magic, err);
 	__put_user_error(size, &frame->size, err);
 
-	/*
-	 * Copy the floating point registers. There can be unused
-	 * registers see asm/hwcap.h for details.
-	 */
-	err |= __copy_to_user(&frame->ufp.fpregs, &h->fpregs,
-			      sizeof(h->fpregs));
-	/*
-	 * Copy the status and control register.
-	 */
-	__put_user_error(h->fpscr, &frame->ufp.fpscr, err);
-
-	/*
-	 * Copy the exception registers.
-	 */
-	__put_user_error(h->fpexc, &frame->ufp_exc.fpexc, err);
-	__put_user_error(h->fpinst, &frame->ufp_exc.fpinst, err);
-	__put_user_error(h->fpinst2, &frame->ufp_exc.fpinst2, err);
+	if (err)
+		return -EFAULT;
 
-	return err ? -EFAULT : 0;
+	return vfp_preserve_user_clear_hwstate(&frame->ufp, &frame->ufp_exc);
 }
 
 static int restore_vfp_context(struct vfp_sigframe __user *frame)
 {
-	struct thread_info *thread = current_thread_info();
-	struct vfp_hard_struct *h = &thread->vfpstate.hard;
 	unsigned long magic;
 	unsigned long size;
-	unsigned long fpexc;
 	int err = 0;
 
 	__get_user_error(magic, &frame->magic, err);
@@ -228,33 +207,7 @@ static int restore_vfp_context(struct vfp_sigframe __user *frame)
 	if (magic != VFP_MAGIC || size != VFP_STORAGE_SIZE)
 		return -EINVAL;
 
-	vfp_flush_hwstate(thread);
-
-	/*
-	 * Copy the floating point registers. There can be unused
-	 * registers see asm/hwcap.h for details.
-	 */
-	err |= __copy_from_user(&h->fpregs, &frame->ufp.fpregs,
-				sizeof(h->fpregs));
-	/*
-	 * Copy the status and control register.
-	 */
-	__get_user_error(h->fpscr, &frame->ufp.fpscr, err);
-
-	/*
-	 * Sanitise and restore the exception registers.
-	 */
-	__get_user_error(fpexc, &frame->ufp_exc.fpexc, err);
-	/* Ensure the VFP is enabled. */
-	fpexc |= FPEXC_EN;
-	/* Ensure FPINST2 is invalid and the exception flag is cleared. */
-	fpexc &= ~(FPEXC_EX | FPEXC_FP2V);
-	h->fpexc = fpexc;
-
-	__get_user_error(h->fpinst, &frame->ufp_exc.fpinst, err);
-	__get_user_error(h->fpinst2, &frame->ufp_exc.fpinst2, err);
-
-	return err ? -EFAULT : 0;
+	return vfp_restore_user_hwstate(&frame->ufp, &frame->ufp_exc);
 }
 
 #endif
@@ -636,6 +589,8 @@ handle_signal(unsigned long sig, struct k_sigaction *ka,
 	 */
 	block_sigmask(ka, sig);
 
+	tracehook_signal_handler(sig, info, ka, regs, 0);
+
 	return 0;
 }
 
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 2cee7d1eb958..b735521a4a54 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -60,32 +60,11 @@ enum ipi_msg_type {
 
 static DECLARE_COMPLETION(cpu_running);
 
-int __cpuinit __cpu_up(unsigned int cpu)
+int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *idle)
 {
-	struct cpuinfo_arm *ci = &per_cpu(cpu_data, cpu);
-	struct task_struct *idle = ci->idle;
 	int ret;
 
 	/*
-	 * Spawn a new process manually, if not already done.
-	 * Grab a pointer to its task struct so we can mess with it
-	 */
-	if (!idle) {
-		idle = fork_idle(cpu);
-		if (IS_ERR(idle)) {
-			printk(KERN_ERR "CPU%u: fork() failed\n", cpu);
-			return PTR_ERR(idle);
-		}
-		ci->idle = idle;
-	} else {
-		/*
-		 * Since this idle thread is being re-used, call
-		 * init_idle() to reinitialize the thread structure.
-		 */
-		init_idle(idle, cpu);
-	}
-
-	/*
 	 * We need to tell the secondary core where to find
 	 * its stack and the page tables.
 	 */
@@ -251,8 +230,6 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	struct mm_struct *mm = &init_mm;
 	unsigned int cpu = smp_processor_id();
 
-	printk("CPU%u: Booted secondary processor\n", cpu);
-
 	/*
 	 * All kernel threads share the same mm context; grab a
 	 * reference and switch to it.
@@ -264,6 +241,8 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	enter_lazy_tlb(mm, current);
 	local_flush_tlb_all();
 
+	printk("CPU%u: Booted secondary processor\n", cpu);
+
 	cpu_init();
 	preempt_disable();
 	trace_hardirqs_off();
@@ -318,9 +297,6 @@ void __init smp_cpus_done(unsigned int max_cpus)
 
 void __init smp_prepare_boot_cpu(void)
 {
-	unsigned int cpu = smp_processor_id();
-
-	per_cpu(cpu_data, cpu).idle = current;
 }
 
 void __init smp_prepare_cpus(unsigned int max_cpus)
@@ -349,7 +325,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 		 * re-initialize the map in platform_smp_prepare_cpus() if
 		 * present != possible (e.g. physical hotplug).
 		 */
-		init_cpu_present(&cpu_possible_map);
+		init_cpu_present(cpu_possible_mask);
 
 		/*
 		 * Initialise the SCU if there are more than one CPU
@@ -454,6 +430,9 @@ static struct local_timer_ops *lt_ops;
 #ifdef CONFIG_LOCAL_TIMERS
 int local_timer_register(struct local_timer_ops *ops)
 {
+	if (!is_smp() || !setup_max_cpus)
+		return -ENXIO;
+
 	if (lt_ops)
 		return -EBUSY;
 
@@ -510,10 +489,6 @@ static void ipi_cpu_stop(unsigned int cpu)
 	local_fiq_disable();
 	local_irq_disable();
 
-#ifdef CONFIG_HOTPLUG_CPU
-	platform_cpu_kill(cpu);
-#endif
-
 	while (1)
 		cpu_relax();
 }
@@ -576,16 +551,25 @@ void smp_send_reschedule(int cpu)
 	smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE);
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+static void smp_kill_cpus(cpumask_t *mask)
+{
+	unsigned int cpu;
+	for_each_cpu(cpu, mask)
+		platform_cpu_kill(cpu);
+}
+#else
+static void smp_kill_cpus(cpumask_t *mask) { }
+#endif
+
 void smp_send_stop(void)
 {
 	unsigned long timeout;
+	struct cpumask mask;
 
-	if (num_online_cpus() > 1) {
-		cpumask_t mask = cpu_online_map;
-		cpu_clear(smp_processor_id(), mask);
-
-		smp_cross_call(&mask, IPI_CPU_STOP);
-	}
+	cpumask_copy(&mask, cpu_online_mask);
+	cpumask_clear_cpu(smp_processor_id(), &mask);
+	smp_cross_call(&mask, IPI_CPU_STOP);
 
 	/* Wait up to one second for other CPUs to stop */
 	timeout = USEC_PER_SEC;
@@ -594,6 +578,8 @@ void smp_send_stop(void)
 
 	if (num_online_cpus() > 1)
 		pr_warning("SMP: failed to stop secondary CPUs\n");
+
+	smp_kill_cpus(&mask);
 }
 
 /*
diff --git a/arch/arm/kernel/smp_scu.c b/arch/arm/kernel/smp_scu.c
index 8f5dd7963356..b9f015e843d8 100644
--- a/arch/arm/kernel/smp_scu.c
+++ b/arch/arm/kernel/smp_scu.c
@@ -11,6 +11,7 @@
 #include <linux/init.h>
 #include <linux/io.h>
 
+#include <asm/smp_plat.h>
 #include <asm/smp_scu.h>
 #include <asm/cacheflush.h>
 #include <asm/cputype.h>
@@ -74,7 +75,7 @@ void scu_enable(void __iomem *scu_base)
 int scu_power_mode(void __iomem *scu_base, unsigned int mode)
 {
 	unsigned int val;
-	int cpu = smp_processor_id();
+	int cpu = cpu_logical_map(smp_processor_id());
 
 	if (mode > 3 || mode == 1 || cpu > 3)
 		return -EINVAL;
diff --git a/arch/arm/kernel/sys_arm.c b/arch/arm/kernel/sys_arm.c
index d2b177905cdb..76cbb055dd05 100644
--- a/arch/arm/kernel/sys_arm.c
+++ b/arch/arm/kernel/sys_arm.c
@@ -115,7 +115,7 @@ int kernel_execve(const char *filename,
 		  "Ir" (THREAD_START_SP - sizeof(regs)),
 		  "r" (&regs),
 		  "Ir" (sizeof(regs))
-		: "r0", "r1", "r2", "r3", "ip", "lr", "memory");
+		: "r0", "r1", "r2", "r3", "r8", "r9", "ip", "lr", "memory");
 
  out:
 	return ret;
diff --git a/arch/arm/kernel/thumbee.c b/arch/arm/kernel/thumbee.c
index aab899764053..7b8403b76666 100644
--- a/arch/arm/kernel/thumbee.c
+++ b/arch/arm/kernel/thumbee.c
@@ -20,6 +20,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 
+#include <asm/cputype.h>
 #include <asm/system_info.h>
 #include <asm/thread_notify.h>
 
@@ -67,8 +68,7 @@ static int __init thumbee_init(void)
 	if (cpu_arch < CPU_ARCH_ARMv7)
 		return 0;
 
-	/* processor feature register 0 */
-	asm("mrc	p15, 0, %0, c0, c1, 0\n" : "=r" (pfr0));
+	pfr0 = read_cpuid_ext(CPUID_EXT_PFR0);
 	if ((pfr0 & 0x0000f000) != 0x00001000)
 		return 0;
 
diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c
index fe31b22f18fd..af2afb019672 100644
--- a/arch/arm/kernel/time.c
+++ b/arch/arm/kernel/time.c
@@ -110,6 +110,42 @@ void timer_tick(void)
 }
 #endif
 
+static void dummy_clock_access(struct timespec *ts)
+{
+	ts->tv_sec = 0;
+	ts->tv_nsec = 0;
+}
+
+static clock_access_fn __read_persistent_clock = dummy_clock_access;
+static clock_access_fn __read_boot_clock = dummy_clock_access;;
+
+void read_persistent_clock(struct timespec *ts)
+{
+	__read_persistent_clock(ts);
+}
+
+void read_boot_clock(struct timespec *ts)
+{
+	__read_boot_clock(ts);
+}
+
+int __init register_persistent_clock(clock_access_fn read_boot,
+				     clock_access_fn read_persistent)
+{
+	/* Only allow the clockaccess functions to be registered once */
+	if (__read_persistent_clock == dummy_clock_access &&
+	    __read_boot_clock == dummy_clock_access) {
+		if (read_boot)
+			__read_boot_clock = read_boot;
+		if (read_persistent)
+			__read_persistent_clock = read_persistent;
+
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
 #if defined(CONFIG_PM) && !defined(CONFIG_GENERIC_CLOCKEVENTS)
 static int timer_suspend(void)
 {
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 778454750a6c..3647170e9a16 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -479,14 +479,14 @@ static int bad_syscall(int n, struct pt_regs *regs)
 	return regs->ARM_r0;
 }
 
-static inline void
+static inline int
 do_cache_op(unsigned long start, unsigned long end, int flags)
 {
 	struct mm_struct *mm = current->active_mm;
 	struct vm_area_struct *vma;
 
 	if (end < start || flags)
-		return;
+		return -EINVAL;
 
 	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, start);
@@ -496,9 +496,11 @@ do_cache_op(unsigned long start, unsigned long end, int flags)
 		if (end > vma->vm_end)
 			end = vma->vm_end;
 
-		flush_cache_user_range(vma, start, end);
+		up_read(&mm->mmap_sem);
+		return flush_cache_user_range(start, end);
 	}
 	up_read(&mm->mmap_sem);
+	return -EINVAL;
 }
 
 /*
@@ -544,8 +546,7 @@ asmlinkage int arm_syscall(int no, struct pt_regs *regs)
 	 * the specified region).
 	 */
 	case NR(cacheflush):
-		do_cache_op(regs->ARM_r0, regs->ARM_r1, regs->ARM_r2);
-		return 0;
+		return do_cache_op(regs->ARM_r0, regs->ARM_r1, regs->ARM_r2);
 
 	case NR(usr26):
 		if (!(elf_hwcap & HWCAP_26BIT))