Merge branch 'misc' into for-linus

Conflicts:
	arch/arm/kernel/ptrace.c

arch/arm/Kconfig

@@ -11,6 +11,7 @@ config ARM
 	select HAVE_OPROFILE if (HAVE_PERF_EVENTS)
 	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL
 	select HAVE_ARCH_KGDB
+	select HAVE_ARCH_TRACEHOOK
 	select HAVE_KPROBES if !XIP_KERNEL
 	select HAVE_KRETPROBES if (HAVE_KPROBES)
 	select HAVE_FUNCTION_TRACER if (!XIP_KERNEL)
@@ -30,6 +31,8 @@ config ARM
 	select HAVE_HW_BREAKPOINT if (PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7))
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_GENERIC_HARDIRQS
+	select HARDIRQS_SW_RESEND
+	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
 	select CPU_PM if (SUSPEND || CPU_IDLE)
 	select GENERIC_PCI_IOMAP
@@ -126,14 +129,6 @@ config TRACE_IRQFLAGS_SUPPORT
 	bool
 	default y
 
-config HARDIRQS_SW_RESEND
-	bool
-	default y
-
-config GENERIC_IRQ_PROBE
-	bool
-	default y
-
 config GENERIC_LOCKBREAK
 	bool
 	default y
@@ -633,7 +628,6 @@ config ARCH_MMP
 	select CLKDEV_LOOKUP
 	select GENERIC_CLOCKEVENTS
 	select GPIO_PXA
-	select TICK_ONESHOT
 	select PLAT_PXA
 	select SPARSE_IRQ
 	select GENERIC_ALLOCATOR
@@ -717,7 +711,6 @@ config ARCH_PXA
 	select ARCH_REQUIRE_GPIOLIB
 	select GENERIC_CLOCKEVENTS
 	select GPIO_PXA
-	select TICK_ONESHOT
 	select PLAT_PXA
 	select SPARSE_IRQ
 	select AUTO_ZRELADDR
@@ -784,7 +777,6 @@ config ARCH_SA1100
 	select CPU_FREQ
 	select GENERIC_CLOCKEVENTS
 	select CLKDEV_LOOKUP
-	select TICK_ONESHOT
 	select ARCH_REQUIRE_GPIOLIB
 	select HAVE_IDE
 	select NEED_MACH_MEMORY_H
@@ -1562,7 +1554,6 @@ config ARM_ARCH_TIMER
 config HAVE_ARM_TWD
 	bool
 	depends on SMP
-	select TICK_ONESHOT
 	help
 	  This options enables support for the ARM timer and watchdog unit
 

arch/arm/boot/compressed/head.S

@@ -567,6 +567,12 @@ __armv3_mpu_cache_on:
 		mcr	p15, 0, r0, c7, c0, 0	@ invalidate whole cache v3
 		mov	pc, lr
 
+#ifdef CONFIG_CPU_DCACHE_WRITETHROUGH
+#define CB_BITS 0x08
+#else
+#define CB_BITS 0x0c
+#endif
+
 __setup_mmu:	sub	r3, r4, #16384		@ Page directory size
 		bic	r3, r3, #0xff		@ Align the pointer
 		bic	r3, r3, #0x3f00
@@ -578,17 +584,14 @@ __setup_mmu:	sub	r3, r4, #16384		@ Page directory size
 		mov	r9, r0, lsr #18
 		mov	r9, r9, lsl #18		@ start of RAM
 		add	r10, r9, #0x10000000	@ a reasonable RAM size
-		mov	r1, #0x12
-		orr	r1, r1, #3 << 10
+		mov	r1, #0x12		@ XN|U + section mapping
+		orr	r1, r1, #3 << 10	@ AP=11
 		add	r2, r3, #16384
 1:		cmp	r1, r9			@ if virt > start of RAM
-#ifdef CONFIG_CPU_DCACHE_WRITETHROUGH
-		orrhs	r1, r1, #0x08		@ set cacheable
-#else
-		orrhs	r1, r1, #0x0c		@ set cacheable, bufferable
-#endif
-		cmp	r1, r10			@ if virt > end of RAM
-		bichs	r1, r1, #0x0c		@ clear cacheable, bufferable
+		cmphs	r10, r1			@   && end of RAM > virt
+		bic	r1, r1, #0x1c		@ clear XN|U + C + B
+		orrlo	r1, r1, #0x10		@ Set XN|U for non-RAM
+		orrhs	r1, r1, r6		@ set RAM section settings
 		str	r1, [r0], #4		@ 1:1 mapping
 		add	r1, r1, #1048576
 		teq	r0, r2
@@ -599,7 +602,7 @@ __setup_mmu:	sub	r3, r4, #16384		@ Page directory size
  * so there is no map overlap problem for up to 1 MB compressed kernel.
  * If the execution is in RAM then we would only be duplicating the above.
  */
-		mov	r1, #0x1e
+		orr	r1, r6, #0x04		@ ensure B is set for this
 		orr	r1, r1, #3 << 10
 		mov	r2, pc
 		mov	r2, r2, lsr #20
@@ -620,6 +623,7 @@ __arm926ejs_mmu_cache_on:
 __armv4_mmu_cache_on:
 		mov	r12, lr
 #ifdef CONFIG_MMU
+		mov	r6, #CB_BITS | 0x12	@ U
 		bl	__setup_mmu
 		mov	r0, #0
 		mcr	p15, 0, r0, c7, c10, 4	@ drain write buffer
@@ -641,6 +645,7 @@ __armv7_mmu_cache_on:
 #ifdef CONFIG_MMU
 		mrc	p15, 0, r11, c0, c1, 4	@ read ID_MMFR0
 		tst	r11, #0xf		@ VMSA
+		movne	r6, #CB_BITS | 0x02	@ !XN
 		blne	__setup_mmu
 		mov	r0, #0
 		mcr	p15, 0, r0, c7, c10, 4	@ drain write buffer
@@ -655,7 +660,7 @@ __armv7_mmu_cache_on:
 		orr	r0, r0, #1 << 25	@ big-endian page tables
 #endif
 		orrne	r0, r0, #1		@ MMU enabled
-		movne	r1, #-1
+		movne	r1, #0xfffffffd		@ domain 0 = client
 		mcrne	p15, 0, r3, c2, c0, 0	@ load page table pointer
 		mcrne	p15, 0, r1, c3, c0, 0	@ load domain access control
 #endif
@@ -668,6 +673,7 @@ __armv7_mmu_cache_on:
 
 __fa526_cache_on:
 		mov	r12, lr
+		mov	r6, #CB_BITS | 0x12	@ U
 		bl	__setup_mmu
 		mov	r0, #0
 		mcr	p15, 0, r0, c7, c7, 0	@ Invalidate whole cache
@@ -682,6 +688,7 @@ __fa526_cache_on:
 
 __arm6_mmu_cache_on:
 		mov	r12, lr
+		mov	r6, #CB_BITS | 0x12	@ U
 		bl	__setup_mmu
 		mov	r0, #0
 		mcr	p15, 0, r0, c7, c0, 0	@ invalidate whole cache v3

arch/arm/common/vic.c

@@ -39,6 +39,7 @@
  * struct vic_device - VIC PM device
  * @irq: The IRQ number for the base of the VIC.
  * @base: The register base for the VIC.
+ * @valid_sources: A bitmask of valid interrupts
  * @resume_sources: A bitmask of interrupts for resume.
  * @resume_irqs: The IRQs enabled for resume.
  * @int_select: Save for VIC_INT_SELECT.
@@ -50,6 +51,7 @@
 struct vic_device {
 	void __iomem	*base;
 	int		irq;
+	u32		valid_sources;
 	u32		resume_sources;
 	u32		resume_irqs;
 	u32		int_select;
@@ -164,10 +166,32 @@ static int __init vic_pm_init(void)
 late_initcall(vic_pm_init);
 #endif /* CONFIG_PM */
 
+static struct irq_chip vic_chip;
+
+static int vic_irqdomain_map(struct irq_domain *d, unsigned int irq,
+			     irq_hw_number_t hwirq)
+{
+	struct vic_device *v = d->host_data;
+
+	/* Skip invalid IRQs, only register handlers for the real ones */
+	if (!(v->valid_sources & (1 << hwirq)))
+		return -ENOTSUPP;
+	irq_set_chip_and_handler(irq, &vic_chip, handle_level_irq);
+	irq_set_chip_data(irq, v->base);
+	set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+	return 0;
+}
+
+static struct irq_domain_ops vic_irqdomain_ops = {
+	.map = vic_irqdomain_map,
+	.xlate = irq_domain_xlate_onetwocell,
+};
+
 /**
  * vic_register() - Register a VIC.
  * @base: The base address of the VIC.
  * @irq: The base IRQ for the VIC.
+ * @valid_sources: bitmask of valid interrupts
  * @resume_sources: bitmask of interrupts allowed for resume sources.
  * @node: The device tree node associated with the VIC.
  *
@@ -178,7 +202,8 @@ late_initcall(vic_pm_init);
  * This also configures the IRQ domain for the VIC.
  */
 static void __init vic_register(void __iomem *base, unsigned int irq,
-				u32 resume_sources, struct device_node *node)
+				u32 valid_sources, u32 resume_sources,
+				struct device_node *node)
 {
 	struct vic_device *v;
 
@@ -189,11 +214,12 @@ static void __init vic_register(void __iomem *base, unsigned int irq,
 
 	v = &vic_devices[vic_id];
 	v->base = base;
+	v->valid_sources = valid_sources;
 	v->resume_sources = resume_sources;
 	v->irq = irq;
 	vic_id++;
-	v->domain = irq_domain_add_legacy(node, 32, irq, 0,
-					  &irq_domain_simple_ops, v);
+	v->domain = irq_domain_add_legacy(node, fls(valid_sources), irq, 0,
+					  &vic_irqdomain_ops, v);
 }
 
 static void vic_ack_irq(struct irq_data *d)
@@ -287,23 +313,6 @@ static void __init vic_clear_interrupts(void __iomem *base)
 	}
 }
 
-static void __init vic_set_irq_sources(void __iomem *base,
-				unsigned int irq_start, u32 vic_sources)
-{
-	unsigned int i;
-
-	for (i = 0; i < 32; i++) {
-		if (vic_sources & (1 << i)) {
-			unsigned int irq = irq_start + i;
-
-			irq_set_chip_and_handler(irq, &vic_chip,
-						 handle_level_irq);
-			irq_set_chip_data(irq, base);
-			set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
-		}
-	}
-}
-
 /*
  * The PL190 cell from ARM has been modified by ST to handle 64 interrupts.
  * The original cell has 32 interrupts, while the modified one has 64,
@@ -338,8 +347,7 @@ static void __init vic_init_st(void __iomem *base, unsigned int irq_start,
 		writel(32, base + VIC_PL190_DEF_VECT_ADDR);
 	}
 
-	vic_set_irq_sources(base, irq_start, vic_sources);
-	vic_register(base, irq_start, 0, node);
+	vic_register(base, irq_start, vic_sources, 0, node);
 }
 
 void __init __vic_init(void __iomem *base, unsigned int irq_start,
@@ -379,9 +387,7 @@ void __init __vic_init(void __iomem *base, unsigned int irq_start,
 
 	vic_init2(base);
 
-	vic_set_irq_sources(base, irq_start, vic_sources);
-
-	vic_register(base, irq_start, resume_sources, node);
+	vic_register(base, irq_start, vic_sources, resume_sources, node);
 }
 
 /**

arch/arm/include/asm/cacheflush.h

@@ -101,7 +101,7 @@ struct cpu_cache_fns {
 	void (*flush_user_range)(unsigned long, unsigned long, unsigned int);
 
 	void (*coherent_kern_range)(unsigned long, unsigned long);
-	void (*coherent_user_range)(unsigned long, unsigned long);
+	int  (*coherent_user_range)(unsigned long, unsigned long);
 	void (*flush_kern_dcache_area)(void *, size_t);
 
 	void (*dma_map_area)(const void *, size_t, int);
@@ -142,7 +142,7 @@ extern void __cpuc_flush_kern_all(void);
 extern void __cpuc_flush_user_all(void);
 extern void __cpuc_flush_user_range(unsigned long, unsigned long, unsigned int);
 extern void __cpuc_coherent_kern_range(unsigned long, unsigned long);
-extern void __cpuc_coherent_user_range(unsigned long, unsigned long);
+extern int  __cpuc_coherent_user_range(unsigned long, unsigned long);
 extern void __cpuc_flush_dcache_area(void *, size_t);
 
 /*
@@ -249,7 +249,7 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr
  * Harvard caches are synchronised for the user space address range.
  * This is used for the ARM private sys_cacheflush system call.
  */
-#define flush_cache_user_range(vma,start,end) \
+#define flush_cache_user_range(start,end) \
 	__cpuc_coherent_user_range((start) & PAGE_MASK, PAGE_ALIGN(end))
 
 /*

arch/arm/include/asm/cmpxchg.h

@@ -229,66 +229,19 @@ static inline unsigned long __cmpxchg_local(volatile void *ptr,
 				       (unsigned long)(n),		\
 				       sizeof(*(ptr))))
 
-#ifndef CONFIG_CPU_V6	/* min ARCH >= ARMv6K */
-
-/*
- * Note : ARMv7-M (currently unsupported by Linux) does not support
- * ldrexd/strexd. If ARMv7-M is ever supported by the Linux kernel, it should
- * not be allowed to use __cmpxchg64.
- */
-static inline unsigned long long __cmpxchg64(volatile void *ptr,
-					     unsigned long long old,
-					     unsigned long long new)
-{
-	register unsigned long long oldval asm("r0");
-	register unsigned long long __old asm("r2") = old;
-	register unsigned long long __new asm("r4") = new;
-	unsigned long res;
-
-	do {
-		asm volatile(
-		"	@ __cmpxchg8\n"
-		"	ldrexd	%1, %H1, [%2]\n"
-		"	mov	%0, #0\n"
-		"	teq	%1, %3\n"
-		"	teqeq	%H1, %H3\n"
-		"	strexdeq %0, %4, %H4, [%2]\n"
-			: "=&r" (res), "=&r" (oldval)
-			: "r" (ptr), "Ir" (__old), "r" (__new)
-			: "memory", "cc");
-	} while (res);
-
-	return oldval;
-}
-
-static inline unsigned long long __cmpxchg64_mb(volatile void *ptr,
-						unsigned long long old,
-						unsigned long long new)
-{
-	unsigned long long ret;
-
-	smp_mb();
-	ret = __cmpxchg64(ptr, old, new);
-	smp_mb();
-
-	return ret;
-}
-
-#define cmpxchg64(ptr,o,n)						\
-	((__typeof__(*(ptr)))__cmpxchg64_mb((ptr),			\
-					    (unsigned long long)(o),	\
-					    (unsigned long long)(n)))
-
-#define cmpxchg64_local(ptr,o,n)					\
-	((__typeof__(*(ptr)))__cmpxchg64((ptr),				\
-					 (unsigned long long)(o),	\
-					 (unsigned long long)(n)))
-
-#else /* min ARCH = ARMv6 */
-
-#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
-
-#endif
+#define cmpxchg64(ptr, o, n)						\
+	((__typeof__(*(ptr)))atomic64_cmpxchg(container_of((ptr),	\
+						atomic64_t,		\
+						counter),		\
+					      (unsigned long)(o),	\
+					      (unsigned long)(n)))
+
+#define cmpxchg64_local(ptr, o, n)					\
+	((__typeof__(*(ptr)))local64_cmpxchg(container_of((ptr),	\
+						local64_t,		\
+						a),			\
+					     (unsigned long)(o),	\
+					     (unsigned long)(n)))
 
 #endif	/* __LINUX_ARM_ARCH__ >= 6 */
 

arch/arm/include/asm/mach/time.h

@@ -42,4 +42,9 @@ struct sys_timer {
 
 extern void timer_tick(void);
 
+struct timespec;
+typedef void (*clock_access_fn)(struct timespec *);
+extern int register_persistent_clock(clock_access_fn read_boot,
+				     clock_access_fn read_persistent);
+
 #endif

arch/arm/include/asm/pgtable-3level.h

@@ -69,8 +69,6 @@
  */
 #define L_PTE_PRESENT		(_AT(pteval_t, 3) << 0)		/* Valid */
 #define L_PTE_FILE		(_AT(pteval_t, 1) << 2)		/* only when !PRESENT */
-#define L_PTE_BUFFERABLE	(_AT(pteval_t, 1) << 2)		/* AttrIndx[0] */
-#define L_PTE_CACHEABLE		(_AT(pteval_t, 1) << 3)		/* AttrIndx[1] */
 #define L_PTE_USER		(_AT(pteval_t, 1) << 6)		/* AP[1] */
 #define L_PTE_RDONLY		(_AT(pteval_t, 1) << 7)		/* AP[2] */
 #define L_PTE_SHARED		(_AT(pteval_t, 3) << 8)		/* SH[1:0], inner shareable */

arch/arm/include/asm/ptrace.h

@@ -249,6 +249,11 @@ static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
 	return regs->ARM_sp;
 }
 
+static inline unsigned long user_stack_pointer(struct pt_regs *regs)
+{
+	return regs->ARM_sp;
+}
+
 #endif /* __KERNEL__ */
 
 #endif /* __ASSEMBLY__ */

arch/arm/include/asm/syscall.h

+/*
+ * Access to user system call parameters and results
+ *
+ * See asm-generic/syscall.h for descriptions of what we must do here.
+ */
+
+#ifndef _ASM_ARM_SYSCALL_H
+#define _ASM_ARM_SYSCALL_H
+
+#include <linux/err.h>
+
+extern const unsigned long sys_call_table[];
+
+static inline int syscall_get_nr(struct task_struct *task,
+				 struct pt_regs *regs)
+{
+	return task_thread_info(task)->syscall;
+}
+
+static inline void syscall_rollback(struct task_struct *task,
+				    struct pt_regs *regs)
+{
+	regs->ARM_r0 = regs->ARM_ORIG_r0;
+}
+
+static inline long syscall_get_error(struct task_struct *task,
+				     struct pt_regs *regs)
+{
+	unsigned long error = regs->ARM_r0;
+	return IS_ERR_VALUE(error) ? error : 0;
+}
+
+static inline long syscall_get_return_value(struct task_struct *task,
+					    struct pt_regs *regs)
+{
+	return regs->ARM_r0;
+}
+
+static inline void syscall_set_return_value(struct task_struct *task,
+					    struct pt_regs *regs,
+					    int error, long val)
+{
+	regs->ARM_r0 = (long) error ? error : val;
+}
+
+#define SYSCALL_MAX_ARGS 7
+
+static inline void syscall_get_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned int i, unsigned int n,
+					 unsigned long *args)
+{
+	if (i + n > SYSCALL_MAX_ARGS) {
+		unsigned long *args_bad = args + SYSCALL_MAX_ARGS - i;
+		unsigned int n_bad = n + i - SYSCALL_MAX_ARGS;
+		pr_warning("%s called with max args %d, handling only %d\n",
+			   __func__, i + n, SYSCALL_MAX_ARGS);
+		memset(args_bad, 0, n_bad * sizeof(args[0]));
+		n = SYSCALL_MAX_ARGS - i;
+	}
+
+	if (i == 0) {
+		args[0] = regs->ARM_ORIG_r0;
+		args++;
+		i++;
+		n--;
+	}
+
+	memcpy(args, &regs->ARM_r0 + i, n * sizeof(args[0]));
+}
+
+static inline void syscall_set_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned int i, unsigned int n,
+					 const unsigned long *args)
+{
+	if (i + n > SYSCALL_MAX_ARGS) {
+		pr_warning("%s called with max args %d, handling only %d\n",
+			   __func__, i + n, SYSCALL_MAX_ARGS);
+		n = SYSCALL_MAX_ARGS - i;
+	}
+
+	if (i == 0) {
+		regs->ARM_ORIG_r0 = args[0];
+		args++;
+		i++;
+		n--;
+	}
+
+	memcpy(&regs->ARM_r0 + i, args, n * sizeof(args[0]));
+}
+
+#endif /* _ASM_ARM_SYSCALL_H */

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 */

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>
@@ -918,8 +919,6 @@ asmlinkage int syscall_trace(int why, struct pt_regs *regs, int scno)
 
 	if (!test_thread_flag(TIF_SYSCALL_TRACE))
 		return scno;
-	if (!(current->ptrace & PT_PTRACED))
-		return scno;
 
 	current_thread_info()->syscall = scno;
 
@@ -930,19 +929,11 @@ asmlinkage int syscall_trace(int why, struct pt_regs *regs, int scno)
 	ip = regs->ARM_ip;
 	regs->ARM_ip = why;
 
-	/* 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
-	 */
-	if (current->exit_code) {
-		send_sig(current->exit_code, current, 1);
-		current->exit_code = 0;
-	}
+	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;

arch/arm/kernel/signal.c

@@ -589,6 +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;
 }
 

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;

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;
 

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)
 {

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))

arch/arm/mach-tegra/timer.c

@@ -124,7 +124,7 @@ static u64 tegra_rtc_read_ms(void)
 }
 
 /*
- * read_persistent_clock -  Return time from a persistent clock.
+ * tegra_read_persistent_clock -  Return time from a persistent clock.
  *
  * Reads the time from a source which isn't disabled during PM, the
  * 32k sync timer.  Convert the cycles elapsed since last read into
@@ -133,7 +133,7 @@ static u64 tegra_rtc_read_ms(void)
  * tegra_rtc driver could be executing to avoid race conditions
  * on the RTC shadow register
  */
-void read_persistent_clock(struct timespec *ts)
+static void tegra_read_persistent_clock(struct timespec *ts)
 {
 	u64 delta;
 	struct timespec *tsp = &persistent_ts;
@@ -243,6 +243,7 @@ static void __init tegra_init_timer(void)
 	tegra_clockevent.irq = tegra_timer_irq.irq;
 	clockevents_register_device(&tegra_clockevent);
 	tegra_twd_init();
+	register_persistent_clock(NULL, tegra_read_persistent_clock);
 }
 
 struct sys_timer tegra_timer = {

arch/arm/mm/cache-v3.S

@@ -78,6 +78,7 @@ ENTRY(v3_coherent_kern_range)
  *	- end	 - virtual end address
  */
 ENTRY(v3_coherent_user_range)
+	mov	r0, #0
 	mov	pc, lr
 
 /*

arch/arm/mm/cache-v4.S

@@ -88,6 +88,7 @@ ENTRY(v4_coherent_kern_range)
  *	- end	 - virtual end address
  */
 ENTRY(v4_coherent_user_range)
+	mov	r0, #0
 	mov	pc, lr
 
 /*

arch/arm/mm/cache-v4wb.S

@@ -167,9 +167,9 @@ ENTRY(v4wb_coherent_user_range)
 	add	r0, r0, #CACHE_DLINESIZE
 	cmp	r0, r1
 	blo	1b
-	mov	ip, #0
-	mcr	p15, 0, ip, c7, c5, 0		@ invalidate I cache
-	mcr	p15, 0, ip, c7, c10, 4		@ drain WB
+	mov	r0, #0
+	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
+	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
 	mov	pc, lr
 
 

arch/arm/mm/cache-v4wt.S

@@ -125,6 +125,7 @@ ENTRY(v4wt_coherent_user_range)
 	add	r0, r0, #CACHE_DLINESIZE
 	cmp	r0, r1
 	blo	1b
+	mov	r0, #0
 	mov	pc, lr
 
 /*

arch/arm/mm/cache-v6.S

@@ -12,6 +12,7 @@
 #include <linux/linkage.h>
 #include <linux/init.h>
 #include <asm/assembler.h>
+#include <asm/errno.h>
 #include <asm/unwind.h>
 
 #include "proc-macros.S"
@@ -135,7 +136,6 @@ ENTRY(v6_coherent_user_range)
 1:
  USER(	mcr	p15, 0, r0, c7, c10, 1	)	@ clean D line
 	add	r0, r0, #CACHE_LINE_SIZE
-2:
 	cmp	r0, r1
 	blo	1b
 #endif
@@ -154,13 +154,11 @@ ENTRY(v6_coherent_user_range)
 
 /*
  * Fault handling for the cache operation above. If the virtual address in r0
- * isn't mapped, just try the next page.
+ * isn't mapped, fail with -EFAULT.
  */
 9001:
-	mov	r0, r0, lsr #12
-	mov	r0, r0, lsl #12
-	add	r0, r0, #4096
-	b	2b
+	mov	r0, #-EFAULT
+	mov	pc, lr
  UNWIND(.fnend		)
 ENDPROC(v6_coherent_user_range)
 ENDPROC(v6_coherent_kern_range)

arch/arm/mm/cache-v7.S

@@ -13,6 +13,7 @@
 #include <linux/linkage.h>
 #include <linux/init.h>
 #include <asm/assembler.h>
+#include <asm/errno.h>
 #include <asm/unwind.h>
 
 #include "proc-macros.S"
@@ -198,7 +199,6 @@ ENTRY(v7_coherent_user_range)
 	add	r12, r12, r2
 	cmp	r12, r1
 	blo	2b
-3:
 	mov	r0, #0
 	ALT_SMP(mcr	p15, 0, r0, c7, c1, 6)	@ invalidate BTB Inner Shareable
 	ALT_UP(mcr	p15, 0, r0, c7, c5, 6)	@ invalidate BTB
@@ -208,13 +208,11 @@ ENTRY(v7_coherent_user_range)
 
 /*
  * Fault handling for the cache operation above. If the virtual address in r0
- * isn't mapped, just try the next page.
+ * isn't mapped, fail with -EFAULT.
  */
 9001:
-	mov	r12, r12, lsr #12
-	mov	r12, r12, lsl #12
-	add	r12, r12, #4096
-	b	3b
+	mov	r0, #-EFAULT
+	mov	pc, lr
  UNWIND(.fnend		)
 ENDPROC(v7_coherent_kern_range)
 ENDPROC(v7_coherent_user_range)

arch/arm/mm/proc-arm1020.S

@@ -241,6 +241,7 @@ ENTRY(arm1020_coherent_user_range)
 	cmp	r0, r1
 	blo	1b
 	mcr	p15, 0, ip, c7, c10, 4		@ drain WB
+	mov	r0, #0
 	mov	pc, lr
 
 /*

arch/arm/mm/proc-arm1020e.S

@@ -235,6 +235,7 @@ ENTRY(arm1020e_coherent_user_range)
 	cmp	r0, r1
 	blo	1b
 	mcr	p15, 0, ip, c7, c10, 4		@ drain WB
+	mov	r0, #0
 	mov	pc, lr
 
 /*

arch/arm/mm/proc-arm1022.S

@@ -224,6 +224,7 @@ ENTRY(arm1022_coherent_user_range)
 	cmp	r0, r1
 	blo	1b
 	mcr	p15, 0, ip, c7, c10, 4		@ drain WB
+	mov	r0, #0
 	mov	pc, lr
 
 /*

arch/arm/mm/proc-arm1026.S

@@ -218,6 +218,7 @@ ENTRY(arm1026_coherent_user_range)
 	cmp	r0, r1
 	blo	1b
 	mcr	p15, 0, ip, c7, c10, 4		@ drain WB
+	mov	r0, #0
 	mov	pc, lr
 
 /*

arch/arm/mm/proc-arm920.S

@@ -210,6 +210,7 @@ ENTRY(arm920_coherent_user_range)
 	cmp	r0, r1
 	blo	1b
 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
+	mov	r0, #0
 	mov	pc, lr
 
 /*

arch/arm/mm/proc-arm922.S

@@ -212,6 +212,7 @@ ENTRY(arm922_coherent_user_range)
 	cmp	r0, r1
 	blo	1b
 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
+	mov	r0, #0
 	mov	pc, lr
 
 /*

arch/arm/mm/proc-arm925.S

@@ -258,6 +258,7 @@ ENTRY(arm925_coherent_user_range)
 	cmp	r0, r1
 	blo	1b
 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
+	mov	r0, #0
 	mov	pc, lr
 
 /*

arch/arm/mm/proc-arm926.S

@@ -221,6 +221,7 @@ ENTRY(arm926_coherent_user_range)
 	cmp	r0, r1
 	blo	1b
 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
+	mov	r0, #0
 	mov	pc, lr
 
 /*

arch/arm/mm/proc-arm940.S

@@ -160,7 +160,7 @@ ENTRY(arm940_coherent_user_range)
  *	- size	- region size
  */
 ENTRY(arm940_flush_kern_dcache_area)
-	mov	ip, #0
+	mov	r0, #0
 	mov	r1, #(CACHE_DSEGMENTS - 1) << 4	@ 4 segments
 1:	orr	r3, r1, #(CACHE_DENTRIES - 1) << 26 @ 64 entries
 2:	mcr	p15, 0, r3, c7, c14, 2		@ clean/flush D index
@@ -168,8 +168,8 @@ ENTRY(arm940_flush_kern_dcache_area)
 	bcs	2b				@ entries 63 to 0
 	subs	r1, r1, #1 << 4
 	bcs	1b				@ segments 7 to 0
-	mcr	p15, 0, ip, c7, c5, 0		@ invalidate I cache
-	mcr	p15, 0, ip, c7, c10, 4		@ drain WB
+	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
+	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
 	mov	pc, lr
 
 /*

arch/arm/mm/proc-arm946.S

@@ -190,6 +190,7 @@ ENTRY(arm946_coherent_user_range)
 	cmp	r0, r1
 	blo	1b
 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
+	mov	r0, #0
 	mov	pc, lr
 
 /*

arch/arm/mm/proc-feroceon.S

@@ -232,6 +232,7 @@ ENTRY(feroceon_coherent_user_range)
 	cmp	r0, r1
 	blo	1b
 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
+	mov	r0, #0
 	mov	pc, lr
 
 /*

arch/arm/mm/proc-mohawk.S

@@ -193,6 +193,7 @@ ENTRY(mohawk_coherent_user_range)
 	cmp	r0, r1
 	blo	1b
 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
+	mov	r0, #0
 	mov	pc, lr
 
 /*

arch/arm/plat-omap/counter_32k.c

@@ -19,6 +19,7 @@
 #include <linux/io.h>
 #include <linux/clocksource.h>
 
+#include <asm/mach/time.h>
 #include <asm/sched_clock.h>
 
 #include <plat/hardware.h>
@@ -43,7 +44,7 @@ static u32 notrace omap_32k_read_sched_clock(void)
 }
 
 /**
- * read_persistent_clock -  Return time from a persistent clock.
+ * omap_read_persistent_clock -  Return time from a persistent clock.
  *
  * Reads the time from a source which isn't disabled during PM, the
  * 32k sync timer.  Convert the cycles elapsed since last read into
@@ -52,7 +53,7 @@ static u32 notrace omap_32k_read_sched_clock(void)
 static struct timespec persistent_ts;
 static cycles_t cycles, last_cycles;
 static unsigned int persistent_mult, persistent_shift;
-void read_persistent_clock(struct timespec *ts)
+static void omap_read_persistent_clock(struct timespec *ts)
 {
 	unsigned long long nsecs;
 	cycles_t delta;
@@ -116,6 +117,7 @@ int __init omap_init_clocksource_32k(void)
 			printk(err, "32k_counter");
 
 		setup_sched_clock(omap_32k_read_sched_clock, 32, 32768);
+		register_persistent_clock(NULL, omap_read_persistent_clock);
 	}
 	return 0;
 }

arch/arm/vfp/vfpmodule.c

@@ -241,11 +241,11 @@ static void vfp_panic(char *reason, u32 inst)
 {
 	int i;
 
-	printk(KERN_ERR "VFP: Error: %s\n", reason);
-	printk(KERN_ERR "VFP: EXC 0x%08x SCR 0x%08x INST 0x%08x\n",
+	pr_err("VFP: Error: %s\n", reason);
+	pr_err("VFP: EXC 0x%08x SCR 0x%08x INST 0x%08x\n",
 		fmrx(FPEXC), fmrx(FPSCR), inst);
 	for (i = 0; i < 32; i += 2)
-		printk(KERN_ERR "VFP: s%2u: 0x%08x s%2u: 0x%08x\n",
+		pr_err("VFP: s%2u: 0x%08x s%2u: 0x%08x\n",
 		       i, vfp_get_float(i), i+1, vfp_get_float(i+1));
 }
 
@@ -452,7 +452,7 @@ static int vfp_pm_suspend(void)
 
 	/* if vfp is on, then save state for resumption */
 	if (fpexc & FPEXC_EN) {
-		printk(KERN_DEBUG "%s: saving vfp state\n", __func__);
+		pr_debug("%s: saving vfp state\n", __func__);
 		vfp_save_state(&ti->vfpstate, fpexc);
 
 		/* disable, just in case */
@@ -664,16 +664,16 @@ static int __init vfp_init(void)
 	barrier();
 	vfp_vector = vfp_null_entry;
 
-	printk(KERN_INFO "VFP support v0.3: ");
+	pr_info("VFP support v0.3: ");
 	if (VFP_arch)
-		printk("not present\n");
+		pr_cont("not present\n");
 	else if (vfpsid & FPSID_NODOUBLE) {
-		printk("no double precision support\n");
+		pr_cont("no double precision support\n");
 	} else {
 		hotcpu_notifier(vfp_hotplug, 0);
 
 		VFP_arch = (vfpsid & FPSID_ARCH_MASK) >> FPSID_ARCH_BIT;  /* Extract the architecture version */
-		printk("implementor %02x architecture %d part %02x variant %x rev %x\n",
+		pr_cont("implementor %02x architecture %d part %02x variant %x rev %x\n",
 			(vfpsid & FPSID_IMPLEMENTER_MASK) >> FPSID_IMPLEMENTER_BIT,
 			(vfpsid & FPSID_ARCH_MASK) >> FPSID_ARCH_BIT,
 			(vfpsid & FPSID_PART_MASK) >> FPSID_PART_BIT,