Merge branch 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm

Pull second set of ARM changes from Russell King:
 "This is the remainder of the ARM changes for this merge window.
  Included in this request are:

   - fixes for kprobes for big-endian support
   - fix tracing in soft_restart
   - avoid phys address overflow in kdump code
   - fix reporting of read-only pmd bits in kernel page table dump
   - remove unnecessary (and possibly buggy) call to outer_flush_all()
   - fix a three sparse warnings (missing header file for function
     prototypes)
   - fix pj4 crashing single zImage (thanks to arm-soc merging changes
     which enables this with knowledge that the corresponding fix had
     not even been submitted for my tree before the merge window opened)
   - vfp macro cleanups
   - dump register state on undefined instruction userspace faults when
     debugging"

* 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm:
  Dump the registers on undefined instruction userspace faults
  ARM: 8018/1: Add {inc,dec}_preempt_count asm macros
  ARM: 8017/1: Move asm macro get_thread_info to asm/assembler.h
  ARM: 8016/1: Check cpu id in pj4_cp0_init.
  ARM: 8015/1: Add cpu_is_pj4 to distinguish PJ4 because it has some differences with V7
  ARM: add missing system_misc.h include to process.c
  ARM: 8009/1: dcscb.c: remove call to outer_flush_all()
  ARM: 8014/1: mm: fix reporting of read-only PMD bits
  ARM: 8012/1: kdump: Avoid overflow when converting pfn to physaddr
  ARM: 8010/1: avoid tracers in soft_restart
  ARM: kprobes-test: Workaround GAS .align bug
  ARM: kprobes-test: use <asm/opcodes.h> for Thumb instruction building
  ARM: kprobes-test: use <asm/opcodes.h> for ARM instruction building
  ARM: kprobes-test: use <asm/opcodes.h> for instruction accesses
  ARM: probes: fix instruction fetch order with <asm/opcodes.h>

arch/arm/include/asm/assembler.h

@@ -23,6 +23,7 @@
 #include <asm/ptrace.h>
 #include <asm/domain.h>
 #include <asm/opcodes-virt.h>
+#include <asm/asm-offsets.h>
 
 #define IOMEM(x)	(x)
 
@@ -174,6 +175,47 @@
 	restore_irqs_notrace \oldcpsr
 	.endm
 
+/*
+ * Get current thread_info.
+ */
+	.macro	get_thread_info, rd
+ ARM(	mov	\rd, sp, lsr #13	)
+ THUMB(	mov	\rd, sp			)
+ THUMB(	lsr	\rd, \rd, #13		)
+	mov	\rd, \rd, lsl #13
+	.endm
+
+/*
+ * Increment/decrement the preempt count.
+ */
+#ifdef CONFIG_PREEMPT_COUNT
+	.macro	inc_preempt_count, ti, tmp
+	ldr	\tmp, [\ti, #TI_PREEMPT]	@ get preempt count
+	add	\tmp, \tmp, #1			@ increment it
+	str	\tmp, [\ti, #TI_PREEMPT]
+	.endm
+
+	.macro	dec_preempt_count, ti, tmp
+	ldr	\tmp, [\ti, #TI_PREEMPT]	@ get preempt count
+	sub	\tmp, \tmp, #1			@ decrement it
+	str	\tmp, [\ti, #TI_PREEMPT]
+	.endm
+
+	.macro	dec_preempt_count_ti, ti, tmp
+	get_thread_info \ti
+	dec_preempt_count \ti, \tmp
+	.endm
+#else
+	.macro	inc_preempt_count, ti, tmp
+	.endm
+
+	.macro	dec_preempt_count, ti, tmp
+	.endm
+
+	.macro	dec_preempt_count_ti, ti, tmp
+	.endm
+#endif
+
 #define USER(x...)				\
 9999:	x;					\
 	.pushsection __ex_table,"a";		\

arch/arm/include/asm/cputype.h

@@ -221,4 +221,23 @@ static inline int cpu_is_xsc3(void)
 #define	cpu_is_xscale()	1
 #endif
 
+/*
+ * Marvell's PJ4 core is based on V7 version. It has some modification
+ * for coprocessor setting. For this reason, we need a way to distinguish
+ * it.
+ */
+#ifndef CONFIG_CPU_PJ4
+#define cpu_is_pj4()	0
+#else
+static inline int cpu_is_pj4(void)
+{
+	unsigned int id;
+
+	id = read_cpuid_id();
+	if ((id & 0xfffffff0) == 0x562f5840)
+		return 1;
+
+	return 0;
+}
+#endif
 #endif

arch/arm/kernel/crash_dump.c

@@ -39,7 +39,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
 	if (!csize)
 		return 0;
 
-	vaddr = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE);
+	vaddr = ioremap(__pfn_to_phys(pfn), PAGE_SIZE);
 	if (!vaddr)
 		return -ENOMEM;
 

arch/arm/kernel/entry-header.S

@@ -236,11 +236,6 @@
 	movs	pc, lr				@ return & move spsr_svc into cpsr
 	.endm
 
-	.macro	get_thread_info, rd
-	mov	\rd, sp, lsr #13
-	mov	\rd, \rd, lsl #13
-	.endm
-
 	@
 	@ 32-bit wide "mov pc, reg"
 	@
@@ -306,12 +301,6 @@
 	.endm
 #endif	/* ifdef CONFIG_CPU_V7M / else */
 
-	.macro	get_thread_info, rd
-	mov	\rd, sp
-	lsr	\rd, \rd, #13
-	mov	\rd, \rd, lsl #13
-	.endm
-
 	@
 	@ 32-bit wide "mov pc, reg"
 	@

arch/arm/kernel/kprobes-common.c

@@ -13,6 +13,7 @@
 
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
+#include <asm/opcodes.h>
 
 #include "kprobes.h"
 
@@ -153,7 +154,8 @@ kprobe_decode_ldmstm(probes_opcode_t insn, struct arch_probes_insn *asi,
 
 	if (handler) {
 		/* We can emulate the instruction in (possibly) modified form */
-		asi->insn[0] = (insn & 0xfff00000) | (rn << 16) | reglist;
+		asi->insn[0] = __opcode_to_mem_arm((insn & 0xfff00000) |
+						   (rn << 16) | reglist);
 		asi->insn_handler = handler;
 		return INSN_GOOD;
 	}

arch/arm/kernel/kprobes-test.c

@@ -113,7 +113,7 @@
  *	@ start of inline data...
  *	.ascii "mov r0, r7"	@ text title for test case
  *	.byte	0
- *	.align	2
+ *	.align	2, 0
  *
  *	@ TEST_ARG_REG
  *	.byte	ARG_TYPE_REG
@@ -1333,7 +1333,8 @@ static void test_case_failed(const char *message)
 static unsigned long next_instruction(unsigned long pc)
 {
 #ifdef CONFIG_THUMB2_KERNEL
-	if ((pc & 1) && !is_wide_instruction(*(u16 *)(pc - 1)))
+	if ((pc & 1) &&
+	    !is_wide_instruction(__mem_to_opcode_thumb16(*(u16 *)(pc - 1))))
 		return pc + 2;
 	else
 #endif
@@ -1378,13 +1379,13 @@ static uintptr_t __used kprobes_test_case_start(const char *title, void *stack)
 
 	if (test_case_is_thumb) {
 		u16 *p = (u16 *)(test_code & ~1);
-		current_instruction = p[0];
+		current_instruction = __mem_to_opcode_thumb16(p[0]);
 		if (is_wide_instruction(current_instruction)) {
-			current_instruction <<= 16;
-			current_instruction |= p[1];
+			u16 instr2 = __mem_to_opcode_thumb16(p[1]);
+			current_instruction = __opcode_thumb32_compose(current_instruction, instr2);
 		}
 	} else {
-		current_instruction = *(u32 *)test_code;
+		current_instruction = __mem_to_opcode_arm(*(u32 *)test_code);
 	}
 
 	if (current_title[0] == '.')

arch/arm/kernel/kprobes-test.h

@@ -115,7 +115,7 @@ struct test_arg_end {
 	/* multiple strings to be concatenated.  */		\
 	".ascii "#title"				\n\t"	\
 	".byte	0					\n\t"	\
-	".align	2					\n\t"
+	".align	2, 0					\n\t"
 
 #define	TEST_ARG_REG(reg, val)					\
 	".byte	"__stringify(ARG_TYPE_REG)"		\n\t"	\

arch/arm/kernel/kprobes-thumb.c

@@ -149,9 +149,9 @@ t32_decode_ldmstm(probes_opcode_t insn, struct arch_probes_insn *asi,
 	enum probes_insn ret = kprobe_decode_ldmstm(insn, asi, d);
 
 	/* Fixup modified instruction to have halfwords in correct order...*/
-	insn = asi->insn[0];
-	((u16 *)asi->insn)[0] = insn >> 16;
-	((u16 *)asi->insn)[1] = insn & 0xffff;
+	insn = __mem_to_opcode_arm(asi->insn[0]);
+	((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(insn >> 16);
+	((u16 *)asi->insn)[1] = __opcode_to_mem_thumb16(insn & 0xffff);
 
 	return ret;
 }
@@ -516,7 +516,7 @@ t16_decode_hiregs(probes_opcode_t insn, struct arch_probes_insn *asi,
 {
 	insn &= ~0x00ff;
 	insn |= 0x001; /* Set Rdn = R1 and Rm = R0 */
-	((u16 *)asi->insn)[0] = insn;
+	((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(insn);
 	asi->insn_handler = t16_emulate_hiregs;
 	return INSN_GOOD;
 }
@@ -547,8 +547,10 @@ t16_decode_push(probes_opcode_t insn, struct arch_probes_insn *asi,
 	 * and call it with R9=SP and LR in the register list represented
 	 * by R8.
 	 */
-	((u16 *)asi->insn)[0] = 0xe929;		/* 1st half STMDB R9!,{} */
-	((u16 *)asi->insn)[1] = insn & 0x1ff;	/* 2nd half (register list) */
+	/* 1st half STMDB R9!,{} */
+	((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(0xe929);
+	/* 2nd half (register list) */
+	((u16 *)asi->insn)[1] = __opcode_to_mem_thumb16(insn & 0x1ff);
 	asi->insn_handler = t16_emulate_push;
 	return INSN_GOOD;
 }
@@ -600,8 +602,10 @@ t16_decode_pop(probes_opcode_t insn, struct arch_probes_insn *asi,
 	 * and call it with R9=SP and PC in the register list represented
 	 * by R8.
 	 */
-	((u16 *)asi->insn)[0] = 0xe8b9;		/* 1st half LDMIA R9!,{} */
-	((u16 *)asi->insn)[1] = insn & 0x1ff;	/* 2nd half (register list) */
+	/* 1st half LDMIA R9!,{} */
+	((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(0xe8b9);
+	/* 2nd half (register list) */
+	((u16 *)asi->insn)[1] = __opcode_to_mem_thumb16(insn & 0x1ff);
 	asi->insn_handler = insn & 0x100 ? t16_emulate_pop_pc
 					 : t16_emulate_pop_nopc;
 	return INSN_GOOD;

arch/arm/kernel/kprobes.c

@@ -26,6 +26,7 @@
 #include <linux/stop_machine.h>
 #include <linux/stringify.h>
 #include <asm/traps.h>
+#include <asm/opcodes.h>
 #include <asm/cacheflush.h>
 #include <linux/percpu.h>
 #include <linux/bug.h>
@@ -67,10 +68,10 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 #ifdef CONFIG_THUMB2_KERNEL
 	thumb = true;
 	addr &= ~1; /* Bit 0 would normally be set to indicate Thumb code */
-	insn = ((u16 *)addr)[0];
+	insn = __mem_to_opcode_thumb16(((u16 *)addr)[0]);
 	if (is_wide_instruction(insn)) {
-		insn <<= 16;
-		insn |= ((u16 *)addr)[1];
+		u16 inst2 = __mem_to_opcode_thumb16(((u16 *)addr)[1]);
+		insn = __opcode_thumb32_compose(insn, inst2);
 		decode_insn = thumb32_probes_decode_insn;
 		actions = kprobes_t32_actions;
 	} else {
@@ -81,7 +82,7 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 	thumb = false;
 	if (addr & 0x3)
 		return -EINVAL;
-	insn = *p->addr;
+	insn = __mem_to_opcode_arm(*p->addr);
 	decode_insn = arm_probes_decode_insn;
 	actions = kprobes_arm_actions;
 #endif

arch/arm/kernel/pj4-cp0.c

@@ -17,6 +17,7 @@
 #include <linux/init.h>
 #include <linux/io.h>
 #include <asm/thread_notify.h>
+#include <asm/cputype.h>
 
 static int iwmmxt_do(struct notifier_block *self, unsigned long cmd, void *t)
 {
@@ -80,6 +81,9 @@ static int __init pj4_cp0_init(void)
 {
 	u32 cp_access;
 
+	if (!cpu_is_pj4())
+		return 0;
+
 	cp_access = pj4_cp_access_read() & ~0xf;
 	pj4_cp_access_write(cp_access);
 

arch/arm/kernel/probes.c

@@ -202,13 +202,14 @@ prepare_emulated_insn(probes_opcode_t insn, struct arch_probes_insn *asi,
 #ifdef CONFIG_THUMB2_KERNEL
 	if (thumb) {
 		u16 *thumb_insn = (u16 *)asi->insn;
-		thumb_insn[1] = 0x4770; /* Thumb bx lr */
-		thumb_insn[2] = 0x4770; /* Thumb bx lr */
+		/* Thumb bx lr */
+		thumb_insn[1] = __opcode_to_mem_thumb16(0x4770);
+		thumb_insn[2] = __opcode_to_mem_thumb16(0x4770);
 		return insn;
 	}
-	asi->insn[1] = 0xe12fff1e; /* ARM bx lr */
+	asi->insn[1] = __opcode_to_mem_arm(0xe12fff1e); /* ARM bx lr */
 #else
-	asi->insn[1] = 0xe1a0f00e; /* mov pc, lr */
+	asi->insn[1] = __opcode_to_mem_arm(0xe1a0f00e); /* mov pc, lr */
 #endif
 	/* Make an ARM instruction unconditional */
 	if (insn < 0xe0000000)
@@ -228,12 +229,12 @@ set_emulated_insn(probes_opcode_t insn, struct arch_probes_insn *asi,
 	if (thumb) {
 		u16 *ip = (u16 *)asi->insn;
 		if (is_wide_instruction(insn))
-			*ip++ = insn >> 16;
-		*ip++ = insn;
+			*ip++ = __opcode_to_mem_thumb16(insn >> 16);
+		*ip++ = __opcode_to_mem_thumb16(insn);
 		return;
 	}
 #endif
-	asi->insn[0] = insn;
+	asi->insn[0] = __opcode_to_mem_arm(insn);
 }
 
 /*

arch/arm/kernel/process.c

@@ -38,6 +38,7 @@
 #include <asm/processor.h>
 #include <asm/thread_notify.h>
 #include <asm/stacktrace.h>
+#include <asm/system_misc.h>
 #include <asm/mach/time.h>
 #include <asm/tls.h>
 
@@ -99,7 +100,7 @@ void soft_restart(unsigned long addr)
 	u64 *stack = soft_restart_stack + ARRAY_SIZE(soft_restart_stack);
 
 	/* Disable interrupts first */
-	local_irq_disable();
+	raw_local_irq_disable();
 	local_fiq_disable();
 
 	/* Disable the L2 if we're the last man standing. */

arch/arm/kernel/traps.c

@@ -445,6 +445,7 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
 	if (user_debug & UDBG_UNDEFINED) {
 		printk(KERN_INFO "%s (%d): undefined instruction: pc=%p\n",
 			current->comm, task_pid_nr(current), pc);
+		__show_regs(regs);
 		dump_instr(KERN_INFO, regs);
 	}
 #endif

arch/arm/mach-vexpress/dcscb.c

@@ -137,11 +137,16 @@ static void dcscb_power_down(void)
 		v7_exit_coherency_flush(all);
 
 		/*
-		 * This is a harmless no-op.  On platforms with a real
-		 * outer cache this might either be needed or not,
-		 * depending on where the outer cache sits.
+		 * A full outer cache flush could be needed at this point
+		 * on platforms with such a cache, depending on where the
+		 * outer cache sits. In some cases the notion of a "last
+		 * cluster standing" would need to be implemented if the
+		 * outer cache is shared across clusters. In any case, when
+		 * the outer cache needs flushing, there is no concurrent
+		 * access to the cache controller to worry about and no
+		 * special locking besides what is already provided by the
+		 * MCPM state machinery is needed.
 		 */
-		outer_flush_all();
 
 		/*
 		 * Disable cluster-level coherency by masking

arch/arm/mm/dump.c

@@ -120,34 +120,51 @@ static const struct prot_bits pte_bits[] = {
 };
 
 static const struct prot_bits section_bits[] = {
-#ifndef CONFIG_ARM_LPAE
-	/* These are approximate */
+#ifdef CONFIG_ARM_LPAE
+	{
+		.mask	= PMD_SECT_USER,
+		.val	= PMD_SECT_USER,
+		.set	= "USR",
+	}, {
+		.mask	= PMD_SECT_RDONLY,
+		.val	= PMD_SECT_RDONLY,
+		.set	= "ro",
+		.clear	= "RW",
+#elif __LINUX_ARM_ARCH__ >= 6
 	{
-		.mask	= PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
-		.val	= 0,
+		.mask	= PMD_SECT_APX | PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
+		.val	= PMD_SECT_APX | PMD_SECT_AP_WRITE,
 		.set	= "    ro",
 	}, {
-		.mask	= PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
+		.mask	= PMD_SECT_APX | PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
 		.val	= PMD_SECT_AP_WRITE,
 		.set	= "    RW",
 	}, {
-		.mask	= PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
+		.mask	= PMD_SECT_APX | PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
 		.val	= PMD_SECT_AP_READ,
 		.set	= "USR ro",
 	}, {
-		.mask	= PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
+		.mask	= PMD_SECT_APX | PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
 		.val	= PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
 		.set	= "USR RW",
-#else
+#else /* ARMv4/ARMv5  */
+	/* These are approximate */
 	{
-		.mask	= PMD_SECT_USER,
-		.val	= PMD_SECT_USER,
-		.set	= "USR",
+		.mask   = PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
+		.val    = 0,
+		.set    = "    ro",
 	}, {
-		.mask	= PMD_SECT_RDONLY,
-		.val	= PMD_SECT_RDONLY,
-		.set	= "ro",
-		.clear	= "RW",
+		.mask   = PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
+		.val    = PMD_SECT_AP_WRITE,
+		.set    = "    RW",
+	}, {
+		.mask   = PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
+		.val    = PMD_SECT_AP_READ,
+		.set    = "USR ro",
+	}, {
+		.mask   = PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
+		.val    = PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
+		.set    = "USR RW",
 #endif
 	}, {
 		.mask	= PMD_SECT_XN,

arch/arm/vfp/entry.S

@@ -8,9 +8,12 @@
  * 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/linkage.h>
 #include <asm/thread_info.h>
 #include <asm/vfpmacros.h>
-#include "../kernel/entry-header.S"
+#include <asm/assembler.h>
+#include <asm/asm-offsets.h>
 
 @ VFP entry point.
 @
@@ -22,11 +25,7 @@
 @  IRQs disabled.
 @
 ENTRY(do_vfp)
-#ifdef CONFIG_PREEMPT_COUNT
-	ldr	r4, [r10, #TI_PREEMPT]	@ get preempt count
-	add	r11, r4, #1		@ increment it
-	str	r11, [r10, #TI_PREEMPT]
-#endif
+	inc_preempt_count r10, r4
 	enable_irq
  	ldr	r4, .LCvfp
 	ldr	r11, [r10, #TI_CPU]	@ CPU number
@@ -35,12 +34,7 @@ ENTRY(do_vfp)
 ENDPROC(do_vfp)
 
 ENTRY(vfp_null_entry)
-#ifdef CONFIG_PREEMPT_COUNT
-	get_thread_info	r10
-	ldr	r4, [r10, #TI_PREEMPT]	@ get preempt count
-	sub	r11, r4, #1		@ decrement it
-	str	r11, [r10, #TI_PREEMPT]
-#endif
+	dec_preempt_count_ti r10, r4
 	mov	pc, lr
 ENDPROC(vfp_null_entry)
 
@@ -53,12 +47,7 @@ ENDPROC(vfp_null_entry)
 
 	__INIT
 ENTRY(vfp_testing_entry)
-#ifdef CONFIG_PREEMPT_COUNT
-	get_thread_info	r10
-	ldr	r4, [r10, #TI_PREEMPT]	@ get preempt count
-	sub	r11, r4, #1		@ decrement it
-	str	r11, [r10, #TI_PREEMPT]
-#endif
+	dec_preempt_count_ti r10, r4
 	ldr	r0, VFP_arch_address
 	str	r0, [r0]		@ set to non-zero value
 	mov	pc, r9			@ we have handled the fault

arch/arm/vfp/vfphw.S

@@ -14,10 +14,13 @@
  * r10 points at the start of the private FP workspace in the thread structure
  * sp points to a struct pt_regs (as defined in include/asm/proc/ptrace.h)
  */
+#include <linux/init.h>
+#include <linux/linkage.h>
 #include <asm/thread_info.h>
 #include <asm/vfpmacros.h>
 #include <linux/kern_levels.h>
-#include "../kernel/entry-header.S"
+#include <asm/assembler.h>
+#include <asm/asm-offsets.h>
 
 	.macro	DBGSTR, str
 #ifdef DEBUG
@@ -179,12 +182,7 @@ vfp_hw_state_valid:
 					@ else it's one 32-bit instruction, so
 					@ always subtract 4 from the following
 					@ instruction address.
-#ifdef CONFIG_PREEMPT_COUNT
-	get_thread_info	r10
-	ldr	r4, [r10, #TI_PREEMPT]	@ get preempt count
-	sub	r11, r4, #1		@ decrement it
-	str	r11, [r10, #TI_PREEMPT]
-#endif
+	dec_preempt_count_ti r10, r4
 	mov	pc, r9			@ we think we have handled things
 
 
@@ -203,12 +201,7 @@ look_for_VFP_exceptions:
 	@ not recognised by VFP
 
 	DBGSTR	"not VFP"
-#ifdef CONFIG_PREEMPT_COUNT
-	get_thread_info	r10
-	ldr	r4, [r10, #TI_PREEMPT]	@ get preempt count
-	sub	r11, r4, #1		@ decrement it
-	str	r11, [r10, #TI_PREEMPT]
-#endif
+	dec_preempt_count_ti r10, r4
 	mov	pc, lr
 
 process_exception: