Merge remote branch 'arm/devel'

51 files changed, 720 insertions, 623 deletions

diff --git a/arch/arm/common/Makefile b/arch/arm/common/Makefile
index e6e8664a9413..e7521bca2c35 100644
--- a/arch/arm/common/Makefile
+++ b/arch/arm/common/Makefile
@@ -17,3 +17,4 @@ obj-$(CONFIG_ARCH_IXP2000)	+= uengine.o
 obj-$(CONFIG_ARCH_IXP23XX)	+= uengine.o
 obj-$(CONFIG_PCI_HOST_ITE8152)  += it8152.o
 obj-$(CONFIG_COMMON_CLKDEV)	+= clkdev.o
+obj-$(CONFIG_ARM_TIMER_SP804)	+= timer-sp.o
diff --git a/arch/arm/plat-versatile/timer-sp.c b/arch/arm/common/timer-sp.c
index fb0d1c299718..4740313daa5b 100644
--- a/arch/arm/plat-versatile/timer-sp.c
+++ b/arch/arm/common/timer-sp.c
@@ -1,5 +1,5 @@
 /*
- *  linux/arch/arm/plat-versatile/timer-sp.c
+ *  linux/arch/arm/common/timer-sp.c
  *
  *  Copyright (C) 1999 - 2003 ARM Limited
  *  Copyright (C) 2000 Deep Blue Solutions Ltd
@@ -26,8 +26,6 @@
 
 #include <asm/hardware/arm_timer.h>
 
-#include <plat/timer-sp.h>
-
 /*
  * These timers are currently always setup to be clocked at 1MHz.
  */
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 749bb6622404..793dd67a4626 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -18,6 +18,7 @@
 #endif
 
 #include <asm/ptrace.h>
+#include <asm/domain.h>
 
 /*
  * Endian independent macros for shifting bytes within registers.
@@ -206,12 +207,12 @@
  */
 #ifdef CONFIG_THUMB2_KERNEL
 
-	.macro	usraccoff, instr, reg, ptr, inc, off, cond, abort
+	.macro	usraccoff, instr, reg, ptr, inc, off, cond, abort, t=T()
 9999:
 	.if	\inc == 1
-	\instr\cond\()bt \reg, [\ptr, #\off]
+	\instr\cond\()b\()\t\().w \reg, [\ptr, #\off]
 	.elseif	\inc == 4
-	\instr\cond\()t \reg, [\ptr, #\off]
+	\instr\cond\()\t\().w \reg, [\ptr, #\off]
 	.else
 	.error	"Unsupported inc macro argument"
 	.endif
@@ -246,13 +247,13 @@
 
 #else	/* !CONFIG_THUMB2_KERNEL */
 
-	.macro	usracc, instr, reg, ptr, inc, cond, rept, abort
+	.macro	usracc, instr, reg, ptr, inc, cond, rept, abort, t=T()
 	.rept	\rept
 9999:
 	.if	\inc == 1
-	\instr\cond\()bt \reg, [\ptr], #\inc
+	\instr\cond\()b\()\t \reg, [\ptr], #\inc
 	.elseif	\inc == 4
-	\instr\cond\()t \reg, [\ptr], #\inc
+	\instr\cond\()\t \reg, [\ptr], #\inc
 	.else
 	.error	"Unsupported inc macro argument"
 	.endif
diff --git a/arch/arm/include/asm/domain.h b/arch/arm/include/asm/domain.h
index cc7ef4080711..af18ceaacf5d 100644
--- a/arch/arm/include/asm/domain.h
+++ b/arch/arm/include/asm/domain.h
@@ -45,13 +45,17 @@
  */
 #define DOMAIN_NOACCESS	0
 #define DOMAIN_CLIENT	1
+#ifdef CONFIG_CPU_USE_DOMAINS
 #define DOMAIN_MANAGER	3
+#else
+#define DOMAIN_MANAGER	1
+#endif
 
 #define domain_val(dom,type)	((type) << (2*(dom)))
 
 #ifndef __ASSEMBLY__
 
-#ifdef CONFIG_MMU
+#ifdef CONFIG_CPU_USE_DOMAINS
 #define set_domain(x)					\
 	do {						\
 	__asm__ __volatile__(				\
@@ -74,5 +78,28 @@
 #define modify_domain(dom,type)	do { } while (0)
 #endif
 
+/*
+ * Generate the T (user) versions of the LDR/STR and related
+ * instructions (inline assembly)
+ */
+#ifdef CONFIG_CPU_USE_DOMAINS
+#define T(instr)	#instr "t"
+#else
+#define T(instr)	#instr
 #endif
-#endif /* !__ASSEMBLY__ */
+
+#else /* __ASSEMBLY__ */
+
+/*
+ * Generate the T (user) versions of the LDR/STR and related
+ * instructions
+ */
+#ifdef CONFIG_CPU_USE_DOMAINS
+#define T(instr)	instr ## t
+#else
+#define T(instr)	instr
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* !__ASM_PROC_DOMAIN_H */
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index 540a044153a5..b33fe7065b38 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -13,12 +13,13 @@
 #include <linux/preempt.h>
 #include <linux/uaccess.h>
 #include <asm/errno.h>
+#include <asm/domain.h>
 
 #define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)	\
 	__asm__ __volatile__(					\
-	"1:	ldrt	%1, [%2]\n"				\
+	"1:	" T(ldr) "	%1, [%2]\n"			\
 	"	" insn "\n"					\
-	"2:	strt	%0, [%2]\n"				\
+	"2:	" T(str) "	%0, [%2]\n"			\
 	"	mov	%0, #0\n"				\
 	"3:\n"							\
 	"	.pushsection __ex_table,\"a\"\n"		\
@@ -97,10 +98,10 @@ futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
 	pagefault_disable();	/* implies preempt_disable() */
 
 	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
-	"1:	ldrt	%0, [%3]\n"
+	"1:	" T(ldr) "	%0, [%3]\n"
 	"	teq	%0, %1\n"
 	"	it	eq	@ explicit IT needed for the 2b label\n"
-	"2:	streqt	%2, [%3]\n"
+	"2:	" T(streq) "	%2, [%3]\n"
 	"3:\n"
 	"	.pushsection __ex_table,\"a\"\n"
 	"	.align	3\n"
diff --git a/arch/arm/include/asm/hardirq.h b/arch/arm/include/asm/hardirq.h
index 6d7485aff955..89ad1805e579 100644
--- a/arch/arm/include/asm/hardirq.h
+++ b/arch/arm/include/asm/hardirq.h
@@ -5,13 +5,31 @@
 #include <linux/threads.h>
 #include <asm/irq.h>
 
+#define NR_IPI	5
+
 typedef struct {
 	unsigned int __softirq_pending;
+#ifdef CONFIG_LOCAL_TIMERS
 	unsigned int local_timer_irqs;
+#endif
+#ifdef CONFIG_SMP
+	unsigned int ipi_irqs[NR_IPI];
+#endif
 } ____cacheline_aligned irq_cpustat_t;
 
 #include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
 
+#define __inc_irq_stat(cpu, member)	__IRQ_STAT(cpu, member)++
+#define __get_irq_stat(cpu, member)	__IRQ_STAT(cpu, member)
+
+#ifdef CONFIG_SMP
+u64 smp_irq_stat_cpu(unsigned int cpu);
+#else
+#define smp_irq_stat_cpu(cpu)	0
+#endif
+
+#define arch_irq_stat_cpu	smp_irq_stat_cpu
+
 #if NR_IRQS > 512
 #define HARDIRQ_BITS	10
 #elif NR_IRQS > 256
diff --git a/arch/arm/include/asm/hardware/entry-macro-gic.S b/arch/arm/include/asm/hardware/entry-macro-gic.S
new file mode 100644
index 000000000000..05587f125a13
--- /dev/null
+++ b/arch/arm/include/asm/hardware/entry-macro-gic.S
@@ -0,0 +1,68 @@
+/*
+ * arch/arm/include/asm/hardware/entry-macro-gic.S
+ *
+ * Low-level IRQ helper macros for GIC
+ *
+ * This file is licensed under  the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <asm/hardware/gic.h>
+
+/*
+ * The interrupt numbering scheme is defined in the
+ * interrupt controller spec.  To wit:
+ *
+ * Interrupts 0-15 are IPI
+ * 16-28 are reserved
+ * 29-31 are local.  We allow 30 to be used for the watchdog.
+ * 32-1020 are global
+ * 1021-1022 are reserved
+ * 1023 is "spurious" (no interrupt)
+ *
+ * For now, we ignore all local interrupts so only return an interrupt if it's
+ * between 30 and 1020.  The test_for_ipi routine below will pick up on IPIs.
+ *
+ * A simple read from the controller will tell us the number of the highest
+ * priority enabled interrupt.  We then just need to check whether it is in the
+ * valid range for an IRQ (30-1020 inclusive).
+ */
+
+	.macro  get_irqnr_and_base, irqnr, irqstat, base, tmp
+
+	ldr     \irqstat, [\base, #GIC_CPU_INTACK]
+	/* bits 12-10 = src CPU, 9-0 = int # */
+
+	ldr	\tmp, =1021
+	bic     \irqnr, \irqstat, #0x1c00
+	cmp     \irqnr, #29
+	cmpcc	\irqnr, \irqnr
+	cmpne	\irqnr, \tmp
+	cmpcs	\irqnr, \irqnr
+	.endm
+
+/* We assume that irqstat (the raw value of the IRQ acknowledge
+ * register) is preserved from the macro above.
+ * If there is an IPI, we immediately signal end of interrupt on the
+ * controller, since this requires the original irqstat value which
+ * we won't easily be able to recreate later.
+ */
+
+	.macro test_for_ipi, irqnr, irqstat, base, tmp
+	bic	\irqnr, \irqstat, #0x1c00
+	cmp	\irqnr, #16
+	strcc	\irqstat, [\base, #GIC_CPU_EOI]
+	cmpcs	\irqnr, \irqnr
+	.endm
+
+/* As above, this assumes that irqstat and base are preserved.. */
+
+	.macro test_for_ltirq, irqnr, irqstat, base, tmp
+	bic	\irqnr, \irqstat, #0x1c00
+	mov 	\tmp, #0
+	cmp	\irqnr, #29
+	moveq	\tmp, #1
+	streq	\irqstat, [\base, #GIC_CPU_EOI]
+	cmp	\tmp, #0
+	.endm
diff --git a/arch/arm/plat-versatile/include/plat/timer-sp.h b/arch/arm/include/asm/hardware/timer-sp.h
index 21e75e30d497..21e75e30d497 100644
--- a/arch/arm/plat-versatile/include/plat/timer-sp.h
+++ b/arch/arm/include/asm/hardware/timer-sp.h
diff --git a/arch/arm/include/asm/mach/irq.h b/arch/arm/include/asm/mach/irq.h
index ce3eee9fe26c..2bc47fb94d51 100644
--- a/arch/arm/include/asm/mach/irq.h
+++ b/arch/arm/include/asm/mach/irq.h
@@ -20,7 +20,7 @@ struct seq_file;
 extern unsigned int arch_nr_irqs;
 extern void (*init_arch_irq)(void);
 extern void init_FIQ(void);
-extern int show_fiq_list(struct seq_file *, void *);
+extern int show_fiq_list(struct seq_file *, int);
 
 /*
  * This is for easy migration, but should be changed in the source
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index 3d05190797cb..f93d0a637016 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -33,12 +33,12 @@ struct seq_file;
 /*
  * generate IPI list text
  */
-extern void show_ipi_list(struct seq_file *p);
+extern void show_ipi_list(struct seq_file *, int);
 
 /*
  * Called from assembly code, this handles an IPI.
  */
-asmlinkage void do_IPI(struct pt_regs *regs);
+asmlinkage void do_IPI(int ipinr, struct pt_regs *regs);
 
 /*
  * Setup the set of possible CPUs (via set_cpu_possible)
@@ -53,7 +53,7 @@ extern void smp_store_cpu_info(unsigned int cpuid);
 /*
  * Raise an IPI cross call on CPUs in callmap.
  */
-extern void smp_cross_call(const struct cpumask *mask);
+extern void smp_cross_call(const struct cpumask *mask, int ipi);
 
 /*
  * Boot a secondary CPU, and assign it the specified idle task.
@@ -97,6 +97,6 @@ extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 /*
  * show local interrupt info
  */
-extern void show_local_irqs(struct seq_file *);
+extern void show_local_irqs(struct seq_file *, int);
 
 #endif /* ifndef __ASM_ARM_SMP_H */
diff --git a/arch/arm/include/asm/traps.h b/arch/arm/include/asm/traps.h
index 491960bf4260..af5d5d1388c6 100644
--- a/arch/arm/include/asm/traps.h
+++ b/arch/arm/include/asm/traps.h
@@ -27,4 +27,6 @@ static inline int in_exception_text(unsigned long ptr)
 extern void __init early_trap_init(void);
 extern void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long frame);
 
+extern void *vectors_page;
+
 #endif
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 33e4a48fe103..b293616a1a1a 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -227,7 +227,7 @@ do {									\
 
 #define __get_user_asm_byte(x,addr,err)				\
 	__asm__ __volatile__(					\
-	"1:	ldrbt	%1,[%2]\n"				\
+	"1:	" T(ldrb) "	%1,[%2],#0\n"			\
 	"2:\n"							\
 	"	.pushsection .fixup,\"ax\"\n"			\
 	"	.align	2\n"					\
@@ -263,7 +263,7 @@ do {									\
 
 #define __get_user_asm_word(x,addr,err)				\
 	__asm__ __volatile__(					\
-	"1:	ldrt	%1,[%2]\n"				\
+	"1:	" T(ldr) "	%1,[%2],#0\n"			\
 	"2:\n"							\
 	"	.pushsection .fixup,\"ax\"\n"			\
 	"	.align	2\n"					\
@@ -308,7 +308,7 @@ do {									\
 
 #define __put_user_asm_byte(x,__pu_addr,err)			\
 	__asm__ __volatile__(					\
-	"1:	strbt	%1,[%2]\n"				\
+	"1:	" T(strb) "	%1,[%2],#0\n"			\
 	"2:\n"							\
 	"	.pushsection .fixup,\"ax\"\n"			\
 	"	.align	2\n"					\
@@ -341,7 +341,7 @@ do {									\
 
 #define __put_user_asm_word(x,__pu_addr,err)			\
 	__asm__ __volatile__(					\
-	"1:	strt	%1,[%2]\n"				\
+	"1:	" T(str) "	%1,[%2],#0\n"			\
 	"2:\n"							\
 	"	.pushsection .fixup,\"ax\"\n"			\
 	"	.align	2\n"					\
@@ -366,10 +366,10 @@ do {									\
 
 #define __put_user_asm_dword(x,__pu_addr,err)			\
 	__asm__ __volatile__(					\
- ARM(	"1:	strt	" __reg_oper1 ", [%1], #4\n"	)	\
- ARM(	"2:	strt	" __reg_oper0 ", [%1]\n"	)	\
- THUMB(	"1:	strt	" __reg_oper1 ", [%1]\n"	)	\
- THUMB(	"2:	strt	" __reg_oper0 ", [%1, #4]\n"	)	\
+ ARM(	"1:	" T(str) "	" __reg_oper1 ", [%1], #4\n"	)	\
+ ARM(	"2:	" T(str) "	" __reg_oper0 ", [%1]\n"	)	\
+ THUMB(	"1:	" T(str) "	" __reg_oper1 ", [%1]\n"	)	\
+ THUMB(	"2:	" T(str) "	" __reg_oper0 ", [%1, #4]\n"	)	\
 	"3:\n"							\
 	"	.pushsection .fixup,\"ax\"\n"			\
 	"	.align	2\n"					\
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 5b9b268f4fbb..4036a5926465 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -42,6 +42,8 @@ obj-$(CONFIG_KGDB)		+= kgdb.o
 obj-$(CONFIG_ARM_UNWIND)	+= unwind.o
 obj-$(CONFIG_HAVE_TCM)		+= tcm.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
+obj-$(CONFIG_SWP_EMULATE)	+= swp_emulate.o
+CFLAGS_swp_emulate.o		:= -Wa,-march=armv7-a
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 
 obj-$(CONFIG_CRUNCH)		+= crunch.o crunch-bits.o
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index c09e3573c5de..6cc89e3717f7 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -48,7 +48,7 @@
 	 */
 	ALT_SMP(test_for_ipi r0, r6, r5, lr)
 	ALT_UP_B(9997f)
-	movne	r0, sp
+	movne	r1, sp
 	adrne	lr, BSYM(1b)
 	bne	do_IPI
 
@@ -735,7 +735,7 @@ ENTRY(__switch_to)
  THUMB(	stmia	ip!, {r4 - sl, fp}	   )	@ Store most regs on stack
  THUMB(	str	sp, [ip], #4		   )
  THUMB(	str	lr, [ip], #4		   )
-#ifdef CONFIG_MMU
+#ifdef CONFIG_CPU_USE_DOMAINS
 	ldr	r6, [r2, #TI_CPU_DOMAIN]
 #endif
 	set_tls	r3, r4, r5
@@ -744,7 +744,7 @@ ENTRY(__switch_to)
 	ldr	r8, =__stack_chk_guard
 	ldr	r7, [r7, #TSK_STACK_CANARY]
 #endif
-#ifdef CONFIG_MMU
+#ifdef CONFIG_CPU_USE_DOMAINS
 	mcr	p15, 0, r6, c3, c0, 0		@ Set domain register
 #endif
 	mov	r5, r0
diff --git a/arch/arm/kernel/fiq.c b/arch/arm/kernel/fiq.c
index 6ff7919613d7..e72dc34eea1c 100644
--- a/arch/arm/kernel/fiq.c
+++ b/arch/arm/kernel/fiq.c
@@ -45,6 +45,7 @@
 #include <asm/fiq.h>
 #include <asm/irq.h>
 #include <asm/system.h>
+#include <asm/traps.h>
 
 static unsigned long no_fiq_insn;
 
@@ -67,17 +68,22 @@ static struct fiq_handler default_owner = {
 
 static struct fiq_handler *current_fiq = &default_owner;
 
-int show_fiq_list(struct seq_file *p, void *v)
+int show_fiq_list(struct seq_file *p, int prec)
 {
 	if (current_fiq != &default_owner)
-		seq_printf(p, "FIQ:              %s\n", current_fiq->name);
+		seq_printf(p, "%*s:              %s\n", prec, "FIQ",
+			current_fiq->name);
 
 	return 0;
 }
 
 void set_fiq_handler(void *start, unsigned int length)
 {
+#if defined(CONFIG_CPU_USE_DOMAINS)
 	memcpy((void *)0xffff001c, start, length);
+#else
+	memcpy(vectors_page + 0x1c, start, length);
+#endif
 	flush_icache_range(0xffff001c, 0xffff001c + length);
 	if (!vectors_high())
 		flush_icache_range(0x1c, 0x1c + length);
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 36ad3be4692a..6276f01df9e4 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -57,11 +57,20 @@ int show_interrupts(struct seq_file *p, void *v)
 	struct irq_desc *desc;
 	struct irqaction * action;
 	unsigned long flags;
+	int prec, n;
+
+	for (prec = 3, n = 1000; prec < 10 && n <= nr_irqs; prec++)
+		n *= 10;
+
+#ifdef CONFIG_SMP
+	if (prec < 4)
+		prec = 4;
+#endif
 
 	if (i == 0) {
 		char cpuname[12];
 
-		seq_printf(p, "    ");
+		seq_printf(p, "%*s ", prec, "");
 		for_each_present_cpu(cpu) {
 			sprintf(cpuname, "CPU%d", cpu);
 			seq_printf(p, " %10s", cpuname);
@@ -76,7 +85,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		if (!action)
 			goto unlock;
 
-		seq_printf(p, "%3d: ", i);
+		seq_printf(p, "%*d: ", prec, i);
 		for_each_present_cpu(cpu)
 			seq_printf(p, "%10u ", kstat_irqs_cpu(i, cpu));
 		seq_printf(p, " %10s", desc->chip->name ? : "-");
@@ -89,13 +98,15 @@ unlock:
 		raw_spin_unlock_irqrestore(&desc->lock, flags);
 	} else if (i == nr_irqs) {
 #ifdef CONFIG_FIQ
-		show_fiq_list(p, v);
+		show_fiq_list(p, prec);
 #endif
 #ifdef CONFIG_SMP
-		show_ipi_list(p);
-		show_local_irqs(p);
+		show_ipi_list(p, prec);
+#endif
+#ifdef CONFIG_LOCAL_TIMERS
+		show_local_irqs(p, prec);
 #endif
-		seq_printf(p, "Err: %10lu\n", irq_err_count);
+		seq_printf(p, "%*s: %10lu\n", prec, "Err", irq_err_count);
 	}
 	return 0;
 }
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 8c1959590252..5d0dc16958bf 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -46,22 +46,8 @@
  */
 struct secondary_data secondary_data;
 
-/*
- * structures for inter-processor calls
- * - A collection of single bit ipi messages.
- */
-struct ipi_data {
-	spinlock_t lock;
-	unsigned long ipi_count;
-	unsigned long bits;
-};
-
-static DEFINE_PER_CPU(struct ipi_data, ipi_data) = {
-	.lock	= SPIN_LOCK_UNLOCKED,
-};
-
 enum ipi_msg_type {
-	IPI_TIMER,
+	IPI_TIMER = 2,
 	IPI_RESCHEDULE,
 	IPI_CALL_FUNC,
 	IPI_CALL_FUNC_SINGLE,
@@ -389,22 +375,13 @@ void __init smp_prepare_boot_cpu(void)
 static void send_ipi_message(const struct cpumask *mask, enum ipi_msg_type msg)
 {
 	unsigned long flags;
-	unsigned int cpu;
 
 	local_irq_save(flags);
 
-	for_each_cpu(cpu, mask) {
-		struct ipi_data *ipi = &per_cpu(ipi_data, cpu);
-
-		spin_lock(&ipi->lock);
-		ipi->bits |= 1 << msg;
-		spin_unlock(&ipi->lock);
-	}
-
 	/*
 	 * Call the platform specific cross-CPU call function.
 	 */
-	smp_cross_call(mask);
+	smp_cross_call(mask, msg);
 
 	local_irq_restore(flags);
 }
@@ -419,28 +396,43 @@ void arch_send_call_function_single_ipi(int cpu)
 	send_ipi_message(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
 }
 
-void show_ipi_list(struct seq_file *p)
+static const char *ipi_types[NR_IPI] = {
+#define S(x,s)	[x - IPI_TIMER] = s
+	S(IPI_TIMER, "Timer broadcast interrupts"),
+	S(IPI_RESCHEDULE, "Rescheduling interrupts"),
+	S(IPI_CALL_FUNC, "Function call interrupts"),
+	S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"),
+	S(IPI_CPU_STOP, "CPU stop interrupts"),
+};
+
+void show_ipi_list(struct seq_file *p, int prec)
 {
-	unsigned int cpu;
+	unsigned int cpu, i;
 
-	seq_puts(p, "IPI:");
+	for (i = 0; i < NR_IPI; i++) {
+		seq_printf(p, "%*s%u: ", prec - 1, "IPI", i);
 
-	for_each_present_cpu(cpu)
-		seq_printf(p, " %10lu", per_cpu(ipi_data, cpu).ipi_count);
+		for_each_present_cpu(cpu)
+			seq_printf(p, "%10u ",
+				   __get_irq_stat(cpu, ipi_irqs[i]));
 
-	seq_putc(p, '\n');
+		seq_printf(p, " %s\n", ipi_types[i]);
+	}
 }
 
-void show_local_irqs(struct seq_file *p)
+u64 smp_irq_stat_cpu(unsigned int cpu)
 {
-	unsigned int cpu;
+	u64 sum = 0;
+	int i;
 
-	seq_printf(p, "LOC: ");
+	for (i = 0; i < NR_IPI; i++)
+		sum += __get_irq_stat(cpu, ipi_irqs[i]);
 
-	for_each_present_cpu(cpu)
-		seq_printf(p, "%10u ", irq_stat[cpu].local_timer_irqs);
+#ifdef CONFIG_LOCAL_TIMERS
+	sum += __get_irq_stat(cpu, local_timer_irqs);
+#endif
 
-	seq_putc(p, '\n');
+	return sum;
 }
 
 /*
@@ -463,12 +455,24 @@ asmlinkage void __exception do_local_timer(struct pt_regs *regs)
 	int cpu = smp_processor_id();
 
 	if (local_timer_ack()) {
-		irq_stat[cpu].local_timer_irqs++;
+		__inc_irq_stat(cpu, local_timer_irqs);
 		ipi_timer();
 	}
 
 	set_irq_regs(old_regs);
 }
+
+void show_local_irqs(struct seq_file *p, int prec)
+{
+	unsigned int cpu;
+
+	seq_printf(p, "%*s: ", prec, "LOC");
+
+	for_each_present_cpu(cpu)
+		seq_printf(p, "%10u ", __get_irq_stat(cpu, local_timer_irqs));
+
+	seq_printf(p, " Local timer interrupts\n");
+}
 #endif
 
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
@@ -537,71 +541,44 @@ static void ipi_cpu_stop(unsigned int cpu)
 
 /*
  * Main handler for inter-processor interrupts
- *
- * For ARM, the ipimask now only identifies a single
- * category of IPI (Bit 1 IPIs have been replaced by a
- * different mechanism):
- *
- *  Bit 0 - Inter-processor function call
  */
-asmlinkage void __exception do_IPI(struct pt_regs *regs)
+asmlinkage void __exception do_IPI(int ipinr, struct pt_regs *regs)
 {
 	unsigned int cpu = smp_processor_id();
-	struct ipi_data *ipi = &per_cpu(ipi_data, cpu);
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
-	ipi->ipi_count++;
-
-	for (;;) {
-		unsigned long msgs;
-
-		spin_lock(&ipi->lock);
-		msgs = ipi->bits;
-		ipi->bits = 0;
-		spin_unlock(&ipi->lock);
-
-		if (!msgs)
-			break;
-
-		do {
-			unsigned nextmsg;
+	if (ipinr >= IPI_TIMER && ipinr < IPI_TIMER + NR_IPI)
+		__inc_irq_stat(cpu, ipi_irqs[ipinr - IPI_TIMER]);
 
-			nextmsg = msgs & -msgs;
-			msgs &= ~nextmsg;
-			nextmsg = ffz(~nextmsg);
+	switch (ipinr) {
+	case IPI_TIMER:
+		ipi_timer();
+		break;
 
-			switch (nextmsg) {
-			case IPI_TIMER:
-				ipi_timer();
-				break;
+	case IPI_RESCHEDULE:
+		/*
+		 * nothing more to do - eveything is
+		 * done on the interrupt return path
+		 */
+		break;
 
-			case IPI_RESCHEDULE:
-				/*
-				 * nothing more to do - eveything is
-				 * done on the interrupt return path
-				 */
-				break;
+	case IPI_CALL_FUNC:
+		generic_smp_call_function_interrupt();
+		break;
 
-			case IPI_CALL_FUNC:
-				generic_smp_call_function_interrupt();
-				break;
+	case IPI_CALL_FUNC_SINGLE:
+		generic_smp_call_function_single_interrupt();
+		break;
 
-			case IPI_CALL_FUNC_SINGLE:
-				generic_smp_call_function_single_interrupt();
-				break;
-
-			case IPI_CPU_STOP:
-				ipi_cpu_stop(cpu);
-				break;
+	case IPI_CPU_STOP:
+		ipi_cpu_stop(cpu);
+		break;
 
-			default:
-				printk(KERN_CRIT "CPU%u: Unknown IPI message 0x%x\n",
-				       cpu, nextmsg);
-				break;
-			}
-		} while (msgs);
+	default:
+		printk(KERN_CRIT "CPU%u: Unknown IPI message 0x%x\n",
+		       cpu, ipinr);
+		break;
 	}
-
 	set_irq_regs(old_regs);
 }
 
diff --git a/arch/arm/kernel/swp_emulate.c b/arch/arm/kernel/swp_emulate.c
new file mode 100644
index 000000000000..7a5760922914
--- /dev/null
+++ b/arch/arm/kernel/swp_emulate.c
@@ -0,0 +1,267 @@
+/*
+ *  linux/arch/arm/kernel/swp_emulate.c
+ *
+ *  Copyright (C) 2009 ARM Limited
+ *  __user_* functions adapted from include/asm/uaccess.h
+ *
+ * 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.
+ *
+ *  Implements emulation of the SWP/SWPB instructions using load-exclusive and
+ *  store-exclusive for processors that have them disabled (or future ones that
+ *  might not implement them).
+ *
+ *  Syntax of SWP{B} instruction: SWP{B}<c> <Rt>, <Rt2>, [<Rn>]
+ *  Where: Rt  = destination
+ *	   Rt2 = source
+ *	   Rn  = address
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/proc_fs.h>
+#include <linux/sched.h>
+#include <linux/syscalls.h>
+#include <linux/perf_event.h>
+
+#include <asm/traps.h>
+#include <asm/uaccess.h>
+
+/*
+ * Error-checking SWP macros implemented using ldrex{b}/strex{b}
+ */
+#define __user_swpX_asm(data, addr, res, temp, B)		\
+	__asm__ __volatile__(					\
+	"	mov		%2, %1\n"			\
+	"0:	ldrex"B"	%1, [%3]\n"			\
+	"1:	strex"B"	%0, %2, [%3]\n"			\
+	"	cmp		%0, #0\n"			\
+	"	movne		%0, %4\n"			\
+	"2:\n"							\
+	"	.section	 .fixup,\"ax\"\n"		\
+	"	.align		2\n"				\
+	"3:	mov		%0, %5\n"			\
+	"	b		2b\n"				\
+	"	.previous\n"					\
+	"	.section	 __ex_table,\"a\"\n"		\
+	"	.align		3\n"				\
+	"	.long		0b, 3b\n"			\
+	"	.long		1b, 3b\n"			\
+	"	.previous"					\
+	: "=&r" (res), "+r" (data), "=&r" (temp)		\
+	: "r" (addr), "i" (-EAGAIN), "i" (-EFAULT)		\
+	: "cc", "memory")
+
+#define __user_swp_asm(data, addr, res, temp) \
+	__user_swpX_asm(data, addr, res, temp, "")
+#define __user_swpb_asm(data, addr, res, temp) \
+	__user_swpX_asm(data, addr, res, temp, "b")
+
+/*
+ * Macros/defines for extracting register numbers from instruction.
+ */
+#define EXTRACT_REG_NUM(instruction, offset) \
+	(((instruction) & (0xf << (offset))) >> (offset))
+#define RN_OFFSET  16
+#define RT_OFFSET  12
+#define RT2_OFFSET  0
+/*
+ * Bit 22 of the instruction encoding distinguishes between
+ * the SWP and SWPB variants (bit set means SWPB).
+ */
+#define TYPE_SWPB (1 << 22)
+
+static unsigned long swpcounter;
+static unsigned long swpbcounter;
+static unsigned long abtcounter;
+static pid_t         previous_pid;
+
+#ifdef CONFIG_PROC_FS
+static int proc_read_status(char *page, char **start, off_t off, int count,
+			    int *eof, void *data)
+{
+	char *p = page;
+	int len;
+
+	p += sprintf(p, "Emulated SWP:\t\t%lu\n", swpcounter);
+	p += sprintf(p, "Emulated SWPB:\t\t%lu\n", swpbcounter);
+	p += sprintf(p, "Aborted SWP{B}:\t\t%lu\n", abtcounter);
+	if (previous_pid != 0)
+		p += sprintf(p, "Last process:\t\t%d\n", previous_pid);
+
+	len = (p - page) - off;
+	if (len < 0)
+		len = 0;
+
+	*eof = (len <= count) ? 1 : 0;
+	*start = page + off;
+
+	return len;
+}
+#endif
+
+/*
+ * Set up process info to signal segmentation fault - called on access error.
+ */
+static void set_segfault(struct pt_regs *regs, unsigned long addr)
+{
+	siginfo_t info;
+
+	if (find_vma(current->mm, addr) == NULL)
+		info.si_code = SEGV_MAPERR;
+	else
+		info.si_code = SEGV_ACCERR;
+
+	info.si_signo = SIGSEGV;
+	info.si_errno = 0;
+	info.si_addr  = (void *) instruction_pointer(regs);
+
+	pr_debug("SWP{B} emulation: access caused memory abort!\n");
+	arm_notify_die("Illegal memory access", regs, &info, 0, 0);
+
+	abtcounter++;
+}
+
+static int emulate_swpX(unsigned int address, unsigned int *data,
+			unsigned int type)
+{
+	unsigned int res = 0;
+
+	if ((type != TYPE_SWPB) && (address & 0x3)) {
+		/* SWP to unaligned address not permitted */
+		pr_debug("SWP instruction on unaligned pointer!\n");
+		return -EFAULT;
+	}
+
+	while (1) {
+		unsigned long temp;
+
+		/*
+		 * Barrier required between accessing protected resource and
+		 * releasing a lock for it. Legacy code might not have done
+		 * this, and we cannot determine that this is not the case
+		 * being emulated, so insert always.
+		 */
+		smp_mb();
+
+		if (type == TYPE_SWPB)
+			__user_swpb_asm(*data, address, res, temp);
+		else
+			__user_swp_asm(*data, address, res, temp);
+
+		if (likely(res != -EAGAIN) || signal_pending(current))
+			break;
+
+		cond_resched();
+	}
+
+	if (res == 0) {
+		/*
+		 * Barrier also required between aquiring a lock for a
+		 * protected resource and accessing the resource. Inserted for
+		 * same reason as above.
+		 */
+		smp_mb();
+
+		if (type == TYPE_SWPB)
+			swpbcounter++;
+		else
+			swpcounter++;
+	}
+
+	return res;
+}
+
+/*
+ * swp_handler logs the id of calling process, dissects the instruction, sanity
+ * checks the memory location, calls emulate_swpX for the actual operation and
+ * deals with fixup/error handling before returning
+ */
+static int swp_handler(struct pt_regs *regs, unsigned int instr)
+{
+	unsigned int address, destreg, data, type;
+	unsigned int res = 0;
+
+	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, 0, regs, regs->ARM_pc);
+
+	if (current->pid != previous_pid) {
+		pr_debug("\"%s\" (%ld) uses deprecated SWP{B} instruction\n",
+			 current->comm, (unsigned long)current->pid);
+		previous_pid = current->pid;
+	}
+
+	address = regs->uregs[EXTRACT_REG_NUM(instr, RN_OFFSET)];
+	data	= regs->uregs[EXTRACT_REG_NUM(instr, RT2_OFFSET)];
+	destreg = EXTRACT_REG_NUM(instr, RT_OFFSET);
+
+	type = instr & TYPE_SWPB;
+
+	pr_debug("addr in r%d->0x%08x, dest is r%d, source in r%d->0x%08x)\n",
+		 EXTRACT_REG_NUM(instr, RN_OFFSET), address,
+		 destreg, EXTRACT_REG_NUM(instr, RT2_OFFSET), data);
+
+	/* Check access in reasonable access range for both SWP and SWPB */
+	if (!access_ok(VERIFY_WRITE, (address & ~3), 4)) {
+		pr_debug("SWP{B} emulation: access to %p not allowed!\n",
+			 (void *)address);
+		res = -EFAULT;
+	} else {
+		res = emulate_swpX(address, &data, type);
+	}
+
+	if (res == 0) {
+		/*
+		 * On successful emulation, revert the adjustment to the PC
+		 * made in kernel/traps.c in order to resume execution at the
+		 * instruction following the SWP{B}.
+		 */
+		regs->ARM_pc += 4;
+		regs->uregs[destreg] = data;
+	} else if (res == -EFAULT) {
+		/*
+		 * Memory errors do not mean emulation failed.
+		 * Set up signal info to return SEGV, then return OK
+		 */
+		set_segfault(regs, address);
+	}
+
+	return 0;
+}
+
+/*
+ * Only emulate SWP/SWPB executed in ARM state/User mode.
+ * The kernel must be SWP free and SWP{B} does not exist in Thumb/ThumbEE.
+ */
+static struct undef_hook swp_hook = {
+	.instr_mask = 0x0fb00ff0,
+	.instr_val  = 0x01000090,
+	.cpsr_mask  = MODE_MASK | PSR_T_BIT | PSR_J_BIT,
+	.cpsr_val   = USR_MODE,
+	.fn	    = swp_handler
+};
+
+/*
+ * Register handler and create status file in /proc/cpu
+ * Invoked as late_initcall, since not needed before init spawned.
+ */
+static int __init swp_emulation_init(void)
+{
+#ifdef CONFIG_PROC_FS
+	struct proc_dir_entry *res;
+
+	res = create_proc_entry("cpu/swp_emulation", S_IRUGO, NULL);
+
+	if (!res)
+		return -ENOMEM;
+
+	res->read_proc = proc_read_status;
+#endif /* CONFIG_PROC_FS */
+
+	printk(KERN_NOTICE "Registering SWP/SWPB emulation handler\n");
+	register_undef_hook(&swp_hook);
+
+	return 0;
+}
+
+late_initcall(swp_emulation_init);
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 446aee97436f..e02f4f7537c5 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -37,6 +37,8 @@
 
 static const char *handler[]= { "prefetch abort", "data abort", "address exception", "interrupt" };
 
+void *vectors_page;
+
 #ifdef CONFIG_DEBUG_USER
 unsigned int user_debug;
 
@@ -756,7 +758,11 @@ static void __init kuser_get_tls_init(unsigned long vectors)
 
 void __init early_trap_init(void)
 {
+#if defined(CONFIG_CPU_USE_DOMAINS)
 	unsigned long vectors = CONFIG_VECTORS_BASE;
+#else
+	unsigned long vectors = (unsigned long)vectors_page;
+#endif
 	extern char __stubs_start[], __stubs_end[];
 	extern char __vectors_start[], __vectors_end[];
 	extern char __kuser_helper_start[], __kuser_helper_end[];
@@ -780,10 +786,10 @@ void __init early_trap_init(void)
 	 * Copy signal return handlers into the vector page, and
 	 * set sigreturn to be a pointer to these.
 	 */
-	memcpy((void *)KERN_SIGRETURN_CODE, sigreturn_codes,
-	       sizeof(sigreturn_codes));
-	memcpy((void *)KERN_RESTART_CODE, syscall_restart_code,
-	       sizeof(syscall_restart_code));
+	memcpy((void *)(vectors + KERN_SIGRETURN_CODE - CONFIG_VECTORS_BASE),
+	       sigreturn_codes, sizeof(sigreturn_codes));
+	memcpy((void *)(vectors + KERN_RESTART_CODE - CONFIG_VECTORS_BASE),
+	       syscall_restart_code, sizeof(syscall_restart_code));
 
 	flush_icache_range(vectors, vectors + PAGE_SIZE);
 	modify_domain(DOMAIN_USER, DOMAIN_CLIENT);
diff --git a/arch/arm/lib/getuser.S b/arch/arm/lib/getuser.S
index b1631a7dbe75..1b049cd7a49a 100644
--- a/arch/arm/lib/getuser.S
+++ b/arch/arm/lib/getuser.S
@@ -28,20 +28,21 @@
  */
 #include <linux/linkage.h>
 #include <asm/errno.h>
+#include <asm/domain.h>
 
 ENTRY(__get_user_1)
-1:	ldrbt	r2, [r0]
+1:	T(ldrb)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__get_user_1)
 
 ENTRY(__get_user_2)
 #ifdef CONFIG_THUMB2_KERNEL
-2:	ldrbt	r2, [r0]
-3:	ldrbt	r3, [r0, #1]
+2:	T(ldrb)	r2, [r0]
+3:	T(ldrb)	r3, [r0, #1]
 #else
-2:	ldrbt	r2, [r0], #1
-3:	ldrbt	r3, [r0]
+2:	T(ldrb)	r2, [r0], #1
+3:	T(ldrb)	r3, [r0]
 #endif
 #ifndef __ARMEB__
 	orr	r2, r2, r3, lsl #8
@@ -53,7 +54,7 @@ ENTRY(__get_user_2)
 ENDPROC(__get_user_2)
 
 ENTRY(__get_user_4)
-4:	ldrt	r2, [r0]
+4:	T(ldr)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__get_user_4)
diff --git a/arch/arm/lib/putuser.S b/arch/arm/lib/putuser.S
index 5a01a23c6c06..c023fc11e86c 100644
--- a/arch/arm/lib/putuser.S
+++ b/arch/arm/lib/putuser.S
@@ -28,9 +28,10 @@
  */
 #include <linux/linkage.h>
 #include <asm/errno.h>
+#include <asm/domain.h>
 
 ENTRY(__put_user_1)
-1:	strbt	r2, [r0]
+1:	T(strb)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__put_user_1)
@@ -39,19 +40,19 @@ ENTRY(__put_user_2)
 	mov	ip, r2, lsr #8
 #ifdef CONFIG_THUMB2_KERNEL
 #ifndef __ARMEB__
-2:	strbt	r2, [r0]
-3:	strbt	ip, [r0, #1]
+2:	T(strb)	r2, [r0]
+3:	T(strb)	ip, [r0, #1]
 #else
-2:	strbt	ip, [r0]
-3:	strbt	r2, [r0, #1]
+2:	T(strb)	ip, [r0]
+3:	T(strb)	r2, [r0, #1]
 #endif
 #else	/* !CONFIG_THUMB2_KERNEL */
 #ifndef __ARMEB__
-2:	strbt	r2, [r0], #1
-3:	strbt	ip, [r0]
+2:	T(strb)	r2, [r0], #1
+3:	T(strb)	ip, [r0]
 #else
-2:	strbt	ip, [r0], #1
-3:	strbt	r2, [r0]
+2:	T(strb)	ip, [r0], #1
+3:	T(strb)	r2, [r0]
 #endif
 #endif	/* CONFIG_THUMB2_KERNEL */
 	mov	r0, #0
@@ -59,18 +60,18 @@ ENTRY(__put_user_2)
 ENDPROC(__put_user_2)
 
 ENTRY(__put_user_4)
-4:	strt	r2, [r0]
+4:	T(str)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__put_user_4)
 
 ENTRY(__put_user_8)
 #ifdef CONFIG_THUMB2_KERNEL
-5:	strt	r2, [r0]
-6:	strt	r3, [r0, #4]
+5:	T(str)	r2, [r0]
+6:	T(str)	r3, [r0, #4]
 #else
-5:	strt	r2, [r0], #4
-6:	strt	r3, [r0]
+5:	T(str)	r2, [r0], #4
+6:	T(str)	r3, [r0]
 #endif
 	mov	r0, #0
 	mov	pc, lr
diff --git a/arch/arm/lib/uaccess.S b/arch/arm/lib/uaccess.S
index fee9f6f88adb..d0ece2aeb70d 100644
--- a/arch/arm/lib/uaccess.S
+++ b/arch/arm/lib/uaccess.S
@@ -14,6 +14,7 @@
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 #include <asm/errno.h>
+#include <asm/domain.h>
 
 		.text
 
@@ -31,11 +32,11 @@
 		rsb	ip, ip, #4
 		cmp	ip, #2
 		ldrb	r3, [r1], #1
-USER(		strbt	r3, [r0], #1)			@ May fault
+USER(		T(strb)	r3, [r0], #1)			@ May fault
 		ldrgeb	r3, [r1], #1
-USER(		strgebt	r3, [r0], #1)			@ May fault
+USER(		T(strgeb) r3, [r0], #1)			@ May fault
 		ldrgtb	r3, [r1], #1
-USER(		strgtbt	r3, [r0], #1)			@ May fault
+USER(		T(strgtb) r3, [r0], #1)			@ May fault
 		sub	r2, r2, ip
 		b	.Lc2u_dest_aligned
 
@@ -58,7 +59,7 @@ ENTRY(__copy_to_user)
 		addmi	ip, r2, #4
 		bmi	.Lc2u_0nowords
 		ldr	r3, [r1], #4
-USER(		strt	r3, [r0], #4)			@ May fault
+USER(		T(str)	r3, [r0], #4)			@ May fault
 		mov	ip, r0, lsl #32 - PAGE_SHIFT	@ On each page, use a ld/st??t instruction
 		rsb	ip, ip, #0
 		movs	ip, ip, lsr #32 - PAGE_SHIFT
@@ -87,18 +88,18 @@ USER(		strt	r3, [r0], #4)			@ May fault
 		stmneia	r0!, {r3 - r4}			@ Shouldnt fault
 		tst	ip, #4
 		ldrne	r3, [r1], #4
-		strnet	r3, [r0], #4			@ Shouldnt fault
+		T(strne) r3, [r0], #4			@ Shouldnt fault
 		ands	ip, ip, #3
 		beq	.Lc2u_0fupi
 .Lc2u_0nowords:	teq	ip, #0
 		beq	.Lc2u_finished
 .Lc2u_nowords:	cmp	ip, #2
 		ldrb	r3, [r1], #1
-USER(		strbt	r3, [r0], #1)			@ May fault
+USER(		T(strb)	r3, [r0], #1)			@ May fault
 		ldrgeb	r3, [r1], #1
-USER(		strgebt	r3, [r0], #1)			@ May fault
+USER(		T(strgeb) r3, [r0], #1)			@ May fault
 		ldrgtb	r3, [r1], #1
-USER(		strgtbt	r3, [r0], #1)			@ May fault
+USER(		T(strgtb) r3, [r0], #1)			@ May fault
 		b	.Lc2u_finished
 
 .Lc2u_not_enough:
@@ -119,7 +120,7 @@ USER(		strgtbt	r3, [r0], #1)			@ May fault
 		mov	r3, r7, pull #8
 		ldr	r7, [r1], #4
 		orr	r3, r3, r7, push #24
-USER(		strt	r3, [r0], #4)			@ May fault
+USER(		T(str)	r3, [r0], #4)			@ May fault
 		mov	ip, r0, lsl #32 - PAGE_SHIFT
 		rsb	ip, ip, #0
 		movs	ip, ip, lsr #32 - PAGE_SHIFT
@@ -154,18 +155,18 @@ USER(		strt	r3, [r0], #4)			@ May fault
 		movne	r3, r7, pull #8
 		ldrne	r7, [r1], #4
 		orrne	r3, r3, r7, push #24
-		strnet	r3, [r0], #4			@ Shouldnt fault
+		T(strne) r3, [r0], #4			@ Shouldnt fault
 		ands	ip, ip, #3
 		beq	.Lc2u_1fupi
 .Lc2u_1nowords:	mov	r3, r7, get_byte_1
 		teq	ip, #0
 		beq	.Lc2u_finished
 		cmp	ip, #2
-USER(		strbt	r3, [r0], #1)			@ May fault
+USER(		T(strb)	r3, [r0], #1)			@ May fault
 		movge	r3, r7, get_byte_2
-USER(		strgebt	r3, [r0], #1)			@ May fault
+USER(		T(strgeb) r3, [r0], #1)			@ May fault
 		movgt	r3, r7, get_byte_3
-USER(		strgtbt	r3, [r0], #1)			@ May fault
+USER(		T(strgtb) r3, [r0], #1)			@ May fault
 		b	.Lc2u_finished
 
 .Lc2u_2fupi:	subs	r2, r2, #4
@@ -174,7 +175,7 @@ USER(		strgtbt	r3, [r0], #1)			@ May fault
 		mov	r3, r7, pull #16
 		ldr	r7, [r1], #4
 		orr	r3, r3, r7, push #16
-USER(		strt	r3, [r0], #4)			@ May fault
+USER(		T(str)	r3, [r0], #4)			@ May fault
 		mov	ip, r0, lsl #32 - PAGE_SHIFT
 		rsb	ip, ip, #0
 		movs	ip, ip, lsr #32 - PAGE_SHIFT
@@ -209,18 +210,18 @@ USER(		strt	r3, [r0], #4)			@ May fault
 		movne	r3, r7, pull #16
 		ldrne	r7, [r1], #4
 		orrne	r3, r3, r7, push #16
-		strnet	r3, [r0], #4			@ Shouldnt fault
+		T(strne) r3, [r0], #4			@ Shouldnt fault
 		ands	ip, ip, #3
 		beq	.Lc2u_2fupi
 .Lc2u_2nowords:	mov	r3, r7, get_byte_2
 		teq	ip, #0
 		beq	.Lc2u_finished
 		cmp	ip, #2
-USER(		strbt	r3, [r0], #1)			@ May fault
+USER(		T(strb)	r3, [r0], #1)			@ May fault
 		movge	r3, r7, get_byte_3
-USER(		strgebt	r3, [r0], #1)			@ May fault
+USER(		T(strgeb) r3, [r0], #1)			@ May fault
 		ldrgtb	r3, [r1], #0
-USER(		strgtbt	r3, [r0], #1)			@ May fault
+USER(		T(strgtb) r3, [r0], #1)			@ May fault
 		b	.Lc2u_finished
 
 .Lc2u_3fupi:	subs	r2, r2, #4
@@ -229,7 +230,7 @@ USER(		strgtbt	r3, [r0], #1)			@ May fault
 		mov	r3, r7, pull #24
 		ldr	r7, [r1], #4
 		orr	r3, r3, r7, push #8
-USER(		strt	r3, [r0], #4)			@ May fault
+USER(		T(str)	r3, [r0], #4)			@ May fault
 		mov	ip, r0, lsl #32 - PAGE_SHIFT
 		rsb	ip, ip, #0
 		movs	ip, ip, lsr #32 - PAGE_SHIFT
@@ -264,18 +265,18 @@ USER(		strt	r3, [r0], #4)			@ May fault
 		movne	r3, r7, pull #24
 		ldrne	r7, [r1], #4
 		orrne	r3, r3, r7, push #8
-		strnet	r3, [r0], #4			@ Shouldnt fault
+		T(strne) r3, [r0], #4			@ Shouldnt fault
 		ands	ip, ip, #3
 		beq	.Lc2u_3fupi
 .Lc2u_3nowords:	mov	r3, r7, get_byte_3
 		teq	ip, #0
 		beq	.Lc2u_finished
 		cmp	ip, #2
-USER(		strbt	r3, [r0], #1)			@ May fault
+USER(		T(strb)	r3, [r0], #1)			@ May fault
 		ldrgeb	r3, [r1], #1
-USER(		strgebt	r3, [r0], #1)			@ May fault
+USER(		T(strgeb) r3, [r0], #1)			@ May fault
 		ldrgtb	r3, [r1], #0
-USER(		strgtbt	r3, [r0], #1)			@ May fault
+USER(		T(strgtb) r3, [r0], #1)			@ May fault
 		b	.Lc2u_finished
 ENDPROC(__copy_to_user)
 
@@ -294,11 +295,11 @@ ENDPROC(__copy_to_user)
 .Lcfu_dest_not_aligned:
 		rsb	ip, ip, #4
 		cmp	ip, #2
-USER(		ldrbt	r3, [r1], #1)			@ May fault
+USER(		T(ldrb)	r3, [r1], #1)			@ May fault
 		strb	r3, [r0], #1
-USER(		ldrgebt	r3, [r1], #1)			@ May fault
+USER(		T(ldrgeb) r3, [r1], #1)			@ May fault
 		strgeb	r3, [r0], #1
-USER(		ldrgtbt	r3, [r1], #1)			@ May fault
+USER(		T(ldrgtb) r3, [r1], #1)			@ May fault
 		strgtb	r3, [r0], #1
 		sub	r2, r2, ip
 		b	.Lcfu_dest_aligned
@@ -321,7 +322,7 @@ ENTRY(__copy_from_user)
 .Lcfu_0fupi:	subs	r2, r2, #4
 		addmi	ip, r2, #4
 		bmi	.Lcfu_0nowords
-USER(		ldrt	r3, [r1], #4)
+USER(		T(ldr)	r3, [r1], #4)
 		str	r3, [r0], #4
 		mov	ip, r1, lsl #32 - PAGE_SHIFT	@ On each page, use a ld/st??t instruction
 		rsb	ip, ip, #0
@@ -350,18 +351,18 @@ USER(		ldrt	r3, [r1], #4)
 		ldmneia	r1!, {r3 - r4}			@ Shouldnt fault
 		stmneia	r0!, {r3 - r4}
 		tst	ip, #4
-		ldrnet	r3, [r1], #4			@ Shouldnt fault
+		T(ldrne) r3, [r1], #4			@ Shouldnt fault
 		strne	r3, [r0], #4
 		ands	ip, ip, #3
 		beq	.Lcfu_0fupi
 .Lcfu_0nowords:	teq	ip, #0
 		beq	.Lcfu_finished
 .Lcfu_nowords:	cmp	ip, #2
-USER(		ldrbt	r3, [r1], #1)			@ May fault
+USER(		T(ldrb)	r3, [r1], #1)			@ May fault
 		strb	r3, [r0], #1
-USER(		ldrgebt	r3, [r1], #1)			@ May fault
+USER(		T(ldrgeb) r3, [r1], #1)			@ May fault
 		strgeb	r3, [r0], #1
-USER(		ldrgtbt	r3, [r1], #1)			@ May fault
+USER(		T(ldrgtb) r3, [r1], #1)			@ May fault
 		strgtb	r3, [r0], #1
 		b	.Lcfu_finished
 
@@ -374,7 +375,7 @@ USER(		ldrgtbt	r3, [r1], #1)			@ May fault
 
 .Lcfu_src_not_aligned:
 		bic	r1, r1, #3
-USER(		ldrt	r7, [r1], #4)			@ May fault
+USER(		T(ldr)	r7, [r1], #4)			@ May fault
 		cmp	ip, #2
 		bgt	.Lcfu_3fupi
 		beq	.Lcfu_2fupi
@@ -382,7 +383,7 @@ USER(		ldrt	r7, [r1], #4)			@ May fault
 		addmi	ip, r2, #4
 		bmi	.Lcfu_1nowords
 		mov	r3, r7, pull #8
-USER(		ldrt	r7, [r1], #4)			@ May fault
+USER(		T(ldr)	r7, [r1], #4)			@ May fault
 		orr	r3, r3, r7, push #24
 		str	r3, [r0], #4
 		mov	ip, r1, lsl #32 - PAGE_SHIFT
@@ -417,7 +418,7 @@ USER(		ldrt	r7, [r1], #4)			@ May fault
 		stmneia	r0!, {r3 - r4}
 		tst	ip, #4
 		movne	r3, r7, pull #8
-USER(		ldrnet	r7, [r1], #4)			@ May fault
+USER(		T(ldrne) r7, [r1], #4)			@ May fault
 		orrne	r3, r3, r7, push #24
 		strne	r3, [r0], #4
 		ands	ip, ip, #3
@@ -437,7 +438,7 @@ USER(		ldrnet	r7, [r1], #4)			@ May fault
 		addmi	ip, r2, #4
 		bmi	.Lcfu_2nowords
 		mov	r3, r7, pull #16
-USER(		ldrt	r7, [r1], #4)			@ May fault
+USER(		T(ldr)	r7, [r1], #4)			@ May fault
 		orr	r3, r3, r7, push #16
 		str	r3, [r0], #4
 		mov	ip, r1, lsl #32 - PAGE_SHIFT
@@ -473,7 +474,7 @@ USER(		ldrt	r7, [r1], #4)			@ May fault
 		stmneia	r0!, {r3 - r4}
 		tst	ip, #4
 		movne	r3, r7, pull #16
-USER(		ldrnet	r7, [r1], #4)			@ May fault
+USER(		T(ldrne) r7, [r1], #4)			@ May fault
 		orrne	r3, r3, r7, push #16
 		strne	r3, [r0], #4
 		ands	ip, ip, #3
@@ -485,7 +486,7 @@ USER(		ldrnet	r7, [r1], #4)			@ May fault
 		strb	r3, [r0], #1
 		movge	r3, r7, get_byte_3
 		strgeb	r3, [r0], #1
-USER(		ldrgtbt	r3, [r1], #0)			@ May fault
+USER(		T(ldrgtb) r3, [r1], #0)			@ May fault
 		strgtb	r3, [r0], #1
 		b	.Lcfu_finished
 
@@ -493,7 +494,7 @@ USER(		ldrgtbt	r3, [r1], #0)			@ May fault
 		addmi	ip, r2, #4
 		bmi	.Lcfu_3nowords
 		mov	r3, r7, pull #24
-USER(		ldrt	r7, [r1], #4)			@ May fault
+USER(		T(ldr)	r7, [r1], #4)			@ May fault
 		orr	r3, r3, r7, push #8
 		str	r3, [r0], #4
 		mov	ip, r1, lsl #32 - PAGE_SHIFT
@@ -528,7 +529,7 @@ USER(		ldrt	r7, [r1], #4)			@ May fault
 		stmneia	r0!, {r3 - r4}
 		tst	ip, #4
 		movne	r3, r7, pull #24
-USER(		ldrnet	r7, [r1], #4)			@ May fault
+USER(		T(ldrne) r7, [r1], #4)			@ May fault
 		orrne	r3, r3, r7, push #8
 		strne	r3, [r0], #4
 		ands	ip, ip, #3
@@ -538,9 +539,9 @@ USER(		ldrnet	r7, [r1], #4)			@ May fault
 		beq	.Lcfu_finished
 		cmp	ip, #2
 		strb	r3, [r0], #1
-USER(		ldrgebt	r3, [r1], #1)			@ May fault
+USER(		T(ldrgeb) r3, [r1], #1)			@ May fault
 		strgeb	r3, [r0], #1
-USER(		ldrgtbt	r3, [r1], #1)			@ May fault
+USER(		T(ldrgtb) r3, [r1], #1)			@ May fault
 		strgtb	r3, [r0], #1
 		b	.Lcfu_finished
 ENDPROC(__copy_from_user)
diff --git a/arch/arm/mach-cns3xxx/include/mach/entry-macro.S b/arch/arm/mach-cns3xxx/include/mach/entry-macro.S
index 5e1c5545680f..e793c3376728 100644
--- a/arch/arm/mach-cns3xxx/include/mach/entry-macro.S
+++ b/arch/arm/mach-cns3xxx/include/mach/entry-macro.S
@@ -9,7 +9,7 @@
  */
 
 #include <mach/hardware.h>
-#include <asm/hardware/gic.h>
+#include <asm/hardware/entry-macro-gic.S>
 
 		.macro	disable_fiq
 		.endm
@@ -21,62 +21,3 @@
 
 		.macro  arch_ret_to_user, tmp1, tmp2
 		.endm
-
-		/*
-		 * The interrupt numbering scheme is defined in the
-		 * interrupt controller spec.  To wit:
-		 *
-		 * Interrupts 0-15 are IPI
-		 * 16-28 are reserved
-		 * 29-31 are local.  We allow 30 to be used for the watchdog.
-		 * 32-1020 are global
-		 * 1021-1022 are reserved
-		 * 1023 is "spurious" (no interrupt)
-		 *
-		 * For now, we ignore all local interrupts so only return an interrupt if it's
-		 * between 30 and 1020.  The test_for_ipi routine below will pick up on IPIs.
-		 *
-		 * A simple read from the controller will tell us the number of the highest
-                 * priority enabled interrupt.  We then just need to check whether it is in the
-		 * valid range for an IRQ (30-1020 inclusive).
-		 */
-
-		.macro  get_irqnr_and_base, irqnr, irqstat, base, tmp
-
-		ldr     \irqstat, [\base, #GIC_CPU_INTACK] /* bits 12-10 = src CPU, 9-0 = int # */
-
-		ldr	\tmp, =1021
-
-		bic     \irqnr, \irqstat, #0x1c00
-
-		cmp     \irqnr, #29
-		cmpcc	\irqnr, \irqnr
-		cmpne	\irqnr, \tmp
-		cmpcs	\irqnr, \irqnr
-
-		.endm
-
-		/* We assume that irqstat (the raw value of the IRQ acknowledge
-		 * register) is preserved from the macro above.
-		 * If there is an IPI, we immediately signal end of interrupt on the
-		 * controller, since this requires the original irqstat value which
-		 * we won't easily be able to recreate later.
-		 */
-
-		.macro test_for_ipi, irqnr, irqstat, base, tmp
-		bic	\irqnr, \irqstat, #0x1c00
-		cmp	\irqnr, #16
-		strcc	\irqstat, [\base, #GIC_CPU_EOI]
-		cmpcs	\irqnr, \irqnr
-		.endm
-
-		/* As above, this assumes that irqstat and base are preserved.. */
-
-		.macro test_for_ltirq, irqnr, irqstat, base, tmp
-		bic	\irqnr, \irqstat, #0x1c00
-		mov 	\tmp, #0
-		cmp	\irqnr, #29
-		moveq	\tmp, #1
-		streq	\irqstat, [\base, #GIC_CPU_EOI]
-		cmp	\tmp, #0
-		.endm
diff --git a/arch/arm/mach-integrator/integrator_cp.c b/arch/arm/mach-integrator/integrator_cp.c
index 6258c90d020c..1713ecf0c95f 100644
--- a/arch/arm/mach-integrator/integrator_cp.c
+++ b/arch/arm/mach-integrator/integrator_cp.c
@@ -41,7 +41,7 @@
 #include <asm/mach/map.h>
 #include <asm/mach/time.h>
 
-#include <plat/timer-sp.h>
+#include <asm/hardware/timer-sp.h>
 
 #include "common.h"
 
diff --git a/arch/arm/mach-msm/include/mach/smp.h b/arch/arm/mach-msm/include/mach/smp.h
index 3ff7bf5e679e..a95f7b9efe31 100644
--- a/arch/arm/mach-msm/include/mach/smp.h
+++ b/arch/arm/mach-msm/include/mach/smp.h
@@ -31,9 +31,9 @@
 
 #include <asm/hardware/gic.h>
 
-static inline void smp_cross_call(const struct cpumask *mask)
+static inline void smp_cross_call(const struct cpumask *mask, int ipi)
 {
-	gic_raise_softirq(mask, 1);
+	gic_raise_softirq(mask, ipi);
 }
 
 #endif
diff --git a/arch/arm/mach-omap2/include/mach/entry-macro.S b/arch/arm/mach-omap2/include/mach/entry-macro.S
index 06e64e1fc28a..2e358df3fe19 100644
--- a/arch/arm/mach-omap2/include/mach/entry-macro.S
+++ b/arch/arm/mach-omap2/include/mach/entry-macro.S
@@ -105,6 +105,35 @@ omap_irq_base:	.word	0
 9999:
 		.endm
 
+#ifdef CONFIG_SMP
+		/* We assume that irqstat (the raw value of the IRQ acknowledge
+		 * register) is preserved from the macro above.
+		 * If there is an IPI, we immediately signal end of interrupt
+		 * on the controller, since this requires the original irqstat
+		 * value which we won't easily be able to recreate later.
+		 */
+
+		.macro test_for_ipi, irqnr, irqstat, base, tmp
+		bic	\irqnr, \irqstat, #0x1c00
+		cmp	\irqnr, #16
+		it	cc
+		strcc	\irqstat, [\base, #GIC_CPU_EOI]
+		it	cs
+		cmpcs	\irqnr, \irqnr
+		.endm
+
+		/* As above, this assumes that irqstat and base are preserved */
+
+		.macro test_for_ltirq, irqnr, irqstat, base, tmp
+		bic	\irqnr, \irqstat, #0x1c00
+		mov 	\tmp, #0
+		cmp	\irqnr, #29
+		itt	eq
+		moveq	\tmp, #1
+		streq	\irqstat, [\base, #GIC_CPU_EOI]
+		cmp	\tmp, #0
+		.endm
+#endif	/* CONFIG_SMP */
 
 #else	/* MULTI_OMAP2 */
 
@@ -141,74 +170,15 @@ omap_irq_base:	.word	0
 
 
 #ifdef CONFIG_ARCH_OMAP4
+#include <asm/hardware/entry-macro-gic.S>
 
 		.macro  get_irqnr_preamble, base, tmp
 		ldr     \base, =OMAP4_IRQ_BASE
 		.endm
 
-		/*
-		 * The interrupt numbering scheme is defined in the
-		 * interrupt controller spec.  To wit:
-		 *
-		 * Interrupts 0-15 are IPI
-		 * 16-28 are reserved
-		 * 29-31 are local.  We allow 30 to be used for the watchdog.
-		 * 32-1020 are global
-		 * 1021-1022 are reserved
-		 * 1023 is "spurious" (no interrupt)
-		 *
-		 * For now, we ignore all local interrupts so only return an
-		 * interrupt if it's between 30 and 1020.  The test_for_ipi
-		 * routine below will pick up on IPIs.
-		 * A simple read from the controller will tell us the number
-		 * of the highest priority enabled interrupt.
-		 * We then just need to check whether it is in the
-		 * valid range for an IRQ (30-1020 inclusive).
-		 */
-		.macro  get_irqnr_and_base, irqnr, irqstat, base, tmp
-		ldr     \irqstat, [\base, #GIC_CPU_INTACK]
-
-		ldr     \tmp, =1021
-
-		bic     \irqnr, \irqstat, #0x1c00
-
-		cmp     \irqnr, #29
-		cmpcc   \irqnr, \irqnr
-		cmpne   \irqnr, \tmp
-		cmpcs   \irqnr, \irqnr
-		.endm
 #endif
-#endif	/* MULTI_OMAP2 */
-
-#ifdef CONFIG_SMP
-		/* We assume that irqstat (the raw value of the IRQ acknowledge
-		 * register) is preserved from the macro above.
-		 * If there is an IPI, we immediately signal end of interrupt
-		 * on the controller, since this requires the original irqstat
-		 * value which we won't easily be able to recreate later.
-		 */
 
-		.macro test_for_ipi, irqnr, irqstat, base, tmp
-		bic	\irqnr, \irqstat, #0x1c00
-		cmp	\irqnr, #16
-		it	cc
-		strcc	\irqstat, [\base, #GIC_CPU_EOI]
-		it	cs
-		cmpcs	\irqnr, \irqnr
-		.endm
-
-		/* As above, this assumes that irqstat and base are preserved */
-
-		.macro test_for_ltirq, irqnr, irqstat, base, tmp
-		bic	\irqnr, \irqstat, #0x1c00
-		mov 	\tmp, #0
-		cmp	\irqnr, #29
-		itt	eq
-		moveq	\tmp, #1
-		streq	\irqstat, [\base, #GIC_CPU_EOI]
-		cmp	\tmp, #0
-		.endm
-#endif	/* CONFIG_SMP */
+#endif	/* MULTI_OMAP2 */
 
 		.macro	irq_prio_table
 		.endm
diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c
index 9e9f70e18e3c..56a8bce247c8 100644
--- a/arch/arm/mach-omap2/omap-smp.c
+++ b/arch/arm/mach-omap2/omap-smp.c
@@ -76,7 +76,7 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
 	omap_modify_auxcoreboot0(0x200, 0xfffffdff);
 	flush_cache_all();
 	smp_wmb();
-	smp_cross_call(cpumask_of(cpu));
+	smp_cross_call(cpumask_of(cpu), 1);
 
 	/*
 	 * Now the secondary core is starting up let it run its
diff --git a/arch/arm/mach-realview/core.c b/arch/arm/mach-realview/core.c
index 07c08151dfe6..aa54b577fc1e 100644
--- a/arch/arm/mach-realview/core.c
+++ b/arch/arm/mach-realview/core.c
@@ -50,7 +50,7 @@
 #include <mach/clkdev.h>
 #include <mach/platform.h>
 #include <mach/irqs.h>
-#include <plat/timer-sp.h>
+#include <asm/hardware/timer-sp.h>
 
 #include "core.h"
 
diff --git a/arch/arm/mach-realview/include/mach/entry-macro.S b/arch/arm/mach-realview/include/mach/entry-macro.S
index 340a5c276946..4417b1039615 100644
--- a/arch/arm/mach-realview/include/mach/entry-macro.S
+++ b/arch/arm/mach-realview/include/mach/entry-macro.S
@@ -8,7 +8,7 @@
  * warranty of any kind, whether express or implied.
  */
 #include <mach/hardware.h>
-#include <asm/hardware/gic.h>
+#include <asm/hardware/entry-macro-gic.S>
 
 		.macro	disable_fiq
 		.endm
@@ -21,61 +21,3 @@
 		.macro  arch_ret_to_user, tmp1, tmp2
 		.endm
 
-		/*
-		 * The interrupt numbering scheme is defined in the
-		 * interrupt controller spec.  To wit:
-		 *
-		 * Interrupts 0-15 are IPI
-		 * 16-28 are reserved
-		 * 29-31 are local.  We allow 30 to be used for the watchdog.
-		 * 32-1020 are global
-		 * 1021-1022 are reserved
-		 * 1023 is "spurious" (no interrupt)
-		 *
-		 * For now, we ignore all local interrupts so only return an interrupt if it's
-		 * between 30 and 1020.  The test_for_ipi routine below will pick up on IPIs.
-		 *
-		 * A simple read from the controller will tell us the number of the highest
-                 * priority enabled interrupt.  We then just need to check whether it is in the
-		 * valid range for an IRQ (30-1020 inclusive).
-		 */
-
-		.macro  get_irqnr_and_base, irqnr, irqstat, base, tmp
-
-		ldr     \irqstat, [\base, #GIC_CPU_INTACK] /* bits 12-10 = src CPU, 9-0 = int # */
-
-		ldr	\tmp, =1021
-
-		bic     \irqnr, \irqstat, #0x1c00
-
-		cmp     \irqnr, #29
-		cmpcc	\irqnr, \irqnr
-		cmpne	\irqnr, \tmp
-		cmpcs	\irqnr, \irqnr
-
-		.endm
-
-		/* We assume that irqstat (the raw value of the IRQ acknowledge
-		 * register) is preserved from the macro above.
-		 * If there is an IPI, we immediately signal end of interrupt on the
-		 * controller, since this requires the original irqstat value which
-		 * we won't easily be able to recreate later.
-		 */
-
-		.macro test_for_ipi, irqnr, irqstat, base, tmp
-		bic	\irqnr, \irqstat, #0x1c00
-		cmp	\irqnr, #16
-		strcc	\irqstat, [\base, #GIC_CPU_EOI]
-		cmpcs	\irqnr, \irqnr
-		.endm
-
-		/* As above, this assumes that irqstat and base are preserved.. */
-
-		.macro test_for_ltirq, irqnr, irqstat, base, tmp
-		bic	\irqnr, \irqstat, #0x1c00
-		mov 	\tmp, #0
-		cmp	\irqnr, #29
-		moveq	\tmp, #1
-		streq	\irqstat, [\base, #GIC_CPU_EOI]
-		cmp	\tmp, #0
-		.endm
diff --git a/arch/arm/mach-realview/include/mach/smp.h b/arch/arm/mach-realview/include/mach/smp.h
index d3cd265cb058..d1aa70415a4e 100644
--- a/arch/arm/mach-realview/include/mach/smp.h
+++ b/arch/arm/mach-realview/include/mach/smp.h
@@ -7,9 +7,9 @@
 /*
  * We use IRQ1 as the IPI
  */
-static inline void smp_cross_call(const struct cpumask *mask)
+static inline void smp_cross_call(const struct cpumask *mask, int ipi)
 {
-	gic_raise_softirq(mask, 1);
+	gic_raise_softirq(mask, ipi);
 }
 
 #endif
diff --git a/arch/arm/mach-realview/platsmp.c b/arch/arm/mach-realview/platsmp.c
index 009265818d55..af3d9093390b 100644
--- a/arch/arm/mach-realview/platsmp.c
+++ b/arch/arm/mach-realview/platsmp.c
@@ -116,7 +116,7 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
 	 * Use smp_cross_call() for this, since there's little
 	 * point duplicating the code here
 	 */
-	smp_cross_call(cpumask_of(cpu));
+	smp_cross_call(cpumask_of(cpu), 1);
 
 	timeout = jiffies + (1 * HZ);
 	while (time_before(jiffies, timeout)) {
diff --git a/arch/arm/mach-s5pv310/include/mach/smp.h b/arch/arm/mach-s5pv310/include/mach/smp.h
index b7ec252384f4..2897747bcb07 100644
--- a/arch/arm/mach-s5pv310/include/mach/smp.h
+++ b/arch/arm/mach-s5pv310/include/mach/smp.h
@@ -14,9 +14,9 @@ extern void __iomem *gic_cpu_base_addr;
 /*
  * We use IRQ1 as the IPI
  */
-static inline void smp_cross_call(const struct cpumask *mask)
+static inline void smp_cross_call(const struct cpumask *mask, int ipi)
 {
-	gic_raise_softirq(mask, 1);
+	gic_raise_softirq(mask, ipi);
 }
 
 #endif
diff --git a/arch/arm/mach-s5pv310/platsmp.c b/arch/arm/mach-s5pv310/platsmp.c
index d357c198edee..d474426f37b7 100644
--- a/arch/arm/mach-s5pv310/platsmp.c
+++ b/arch/arm/mach-s5pv310/platsmp.c
@@ -97,7 +97,7 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
 	 * the boot monitor to read the system wide flags register,
 	 * and branch to the address found there.
 	 */
-	smp_cross_call(cpumask_of(cpu));
+	smp_cross_call(cpumask_of(cpu), 1);
 
 	timeout = jiffies + (1 * HZ);
 	while (time_before(jiffies, timeout)) {
diff --git a/arch/arm/mach-sa1100/cpu-sa1100.c b/arch/arm/mach-sa1100/cpu-sa1100.c
index 96f7dc103b59..07d4e8ba3719 100644
--- a/arch/arm/mach-sa1100/cpu-sa1100.c
+++ b/arch/arm/mach-sa1100/cpu-sa1100.c
@@ -94,48 +94,47 @@
 
 #include "generic.h"
 
-typedef struct {
+struct sa1100_dram_regs {
 	int speed;
 	u32 mdcnfg;
 	u32 mdcas0;
 	u32 mdcas1;
 	u32 mdcas2;
-} sa1100_dram_regs_t;
+};
 
 
 static struct cpufreq_driver sa1100_driver;
 
-static sa1100_dram_regs_t sa1100_dram_settings[] =
-{
-	/* speed,     mdcnfg,     mdcas0,     mdcas1,     mdcas2  clock frequency */
-	{  59000, 0x00dc88a3, 0xcccccccf, 0xfffffffc, 0xffffffff }, /*  59.0 MHz */
-	{  73700, 0x011490a3, 0xcccccccf, 0xfffffffc, 0xffffffff }, /*  73.7 MHz */
-	{  88500, 0x014e90a3, 0xcccccccf, 0xfffffffc, 0xffffffff }, /*  88.5 MHz */
-	{ 103200, 0x01889923, 0xcccccccf, 0xfffffffc, 0xffffffff }, /* 103.2 MHz */
-	{ 118000, 0x01c29923, 0x9999998f, 0xfffffff9, 0xffffffff }, /* 118.0 MHz */
-	{ 132700, 0x01fb2123, 0x9999998f, 0xfffffff9, 0xffffffff }, /* 132.7 MHz */
-	{ 147500, 0x02352123, 0x3333330f, 0xfffffff3, 0xffffffff }, /* 147.5 MHz */
-	{ 162200, 0x026b29a3, 0x38e38e1f, 0xfff8e38e, 0xffffffff }, /* 162.2 MHz */
-	{ 176900, 0x02a329a3, 0x71c71c1f, 0xfff1c71c, 0xffffffff }, /* 176.9 MHz */
-	{ 191700, 0x02dd31a3, 0xe38e383f, 0xffe38e38, 0xffffffff }, /* 191.7 MHz */
-	{ 206400, 0x03153223, 0xc71c703f, 0xffc71c71, 0xffffffff }, /* 206.4 MHz */
-	{ 221200, 0x034fba23, 0xc71c703f, 0xffc71c71, 0xffffffff }, /* 221.2 MHz */
-	{ 235900, 0x03853a23, 0xe1e1e07f, 0xe1e1e1e1, 0xffffffe1 }, /* 235.9 MHz */
-	{ 250700, 0x03bf3aa3, 0xc3c3c07f, 0xc3c3c3c3, 0xffffffc3 }, /* 250.7 MHz */
-	{ 265400, 0x03f7c2a3, 0xc3c3c07f, 0xc3c3c3c3, 0xffffffc3 }, /* 265.4 MHz */
-	{ 280200, 0x0431c2a3, 0x878780ff, 0x87878787, 0xffffff87 }, /* 280.2 MHz */
+static struct sa1100_dram_regs sa1100_dram_settings[] = {
+	/*speed,     mdcnfg,     mdcas0,     mdcas1,     mdcas2,   clock freq */
+	{ 59000, 0x00dc88a3, 0xcccccccf, 0xfffffffc, 0xffffffff},/*  59.0 MHz */
+	{ 73700, 0x011490a3, 0xcccccccf, 0xfffffffc, 0xffffffff},/*  73.7 MHz */
+	{ 88500, 0x014e90a3, 0xcccccccf, 0xfffffffc, 0xffffffff},/*  88.5 MHz */
+	{103200, 0x01889923, 0xcccccccf, 0xfffffffc, 0xffffffff},/* 103.2 MHz */
+	{118000, 0x01c29923, 0x9999998f, 0xfffffff9, 0xffffffff},/* 118.0 MHz */
+	{132700, 0x01fb2123, 0x9999998f, 0xfffffff9, 0xffffffff},/* 132.7 MHz */
+	{147500, 0x02352123, 0x3333330f, 0xfffffff3, 0xffffffff},/* 147.5 MHz */
+	{162200, 0x026b29a3, 0x38e38e1f, 0xfff8e38e, 0xffffffff},/* 162.2 MHz */
+	{176900, 0x02a329a3, 0x71c71c1f, 0xfff1c71c, 0xffffffff},/* 176.9 MHz */
+	{191700, 0x02dd31a3, 0xe38e383f, 0xffe38e38, 0xffffffff},/* 191.7 MHz */
+	{206400, 0x03153223, 0xc71c703f, 0xffc71c71, 0xffffffff},/* 206.4 MHz */
+	{221200, 0x034fba23, 0xc71c703f, 0xffc71c71, 0xffffffff},/* 221.2 MHz */
+	{235900, 0x03853a23, 0xe1e1e07f, 0xe1e1e1e1, 0xffffffe1},/* 235.9 MHz */
+	{250700, 0x03bf3aa3, 0xc3c3c07f, 0xc3c3c3c3, 0xffffffc3},/* 250.7 MHz */
+	{265400, 0x03f7c2a3, 0xc3c3c07f, 0xc3c3c3c3, 0xffffffc3},/* 265.4 MHz */
+	{280200, 0x0431c2a3, 0x878780ff, 0x87878787, 0xffffff87},/* 280.2 MHz */
 	{ 0, 0, 0, 0, 0 } /* last entry */
 };
 
 static void sa1100_update_dram_timings(int current_speed, int new_speed)
 {
-	sa1100_dram_regs_t *settings = sa1100_dram_settings;
+	struct sa1100_dram_regs *settings = sa1100_dram_settings;
 
 	/* find speed */
 	while (settings->speed != 0) {
-		if(new_speed == settings->speed)
+		if (new_speed == settings->speed)
 			break;
-		
+
 		settings++;
 	}
 
@@ -149,7 +148,7 @@ static void sa1100_update_dram_timings(int current_speed, int new_speed)
 		/* We're going FASTER, so first relax the memory
 		 * timings before changing the core frequency
 		 */
-		
+
 		/* Half the memory access clock */
 		MDCNFG |= MDCNFG_CDB2;
 
@@ -187,7 +186,7 @@ static int sa1100_target(struct cpufreq_policy *policy,
 	struct cpufreq_freqs freqs;
 
 	new_ppcr = sa11x0_freq_to_ppcr(target_freq);
-	switch(relation){
+	switch (relation) {
 	case CPUFREQ_RELATION_L:
 		if (sa11x0_ppcr_to_freq(new_ppcr) > policy->max)
 			new_ppcr--;
diff --git a/arch/arm/mach-tegra/include/mach/entry-macro.S b/arch/arm/mach-tegra/include/mach/entry-macro.S
index 2ba9e5c9d2f6..dc0924915183 100644
--- a/arch/arm/mach-tegra/include/mach/entry-macro.S
+++ b/arch/arm/mach-tegra/include/mach/entry-macro.S
@@ -17,7 +17,7 @@
 
 #if defined(CONFIG_ARM_GIC)
 
-#include <asm/hardware/gic.h>
+#include <asm/hardware/entry-macro-gic.S>
 
 	/* Uses the GIC interrupt controller built into the cpu */
 #define ICTRL_BASE (IO_CPU_VIRT + 0x100)
@@ -32,68 +32,6 @@
 
 	.macro  arch_ret_to_user, tmp1, tmp2
 	.endm
-
-	/*
-	 * The interrupt numbering scheme is defined in the
-	 * interrupt controller spec.  To wit:
-	 *
-	 * Interrupts 0-15 are IPI
-	 * 16-28 are reserved
-	 * 29-31 are local.  We allow 30 to be used for the watchdog.
-	 * 32-1020 are global
-	 * 1021-1022 are reserved
-	 * 1023 is "spurious" (no interrupt)
-	 *
-	 * For now, we ignore all local interrupts so only return an interrupt
-	 * if it's between 30 and 1020.  The test_for_ipi routine below will
-	 * pick up on IPIs.
-	 *
-	 * A simple read from the controller will tell us the number of the
-	 * highest priority enabled interrupt.  We then just need to check
-	 * whether it is in the valid range for an IRQ (30-1020 inclusive).
-	 */
-
-	.macro  get_irqnr_and_base, irqnr, irqstat, base, tmp
-
-	/* bits 12-10 = src CPU, 9-0 = int # */
-	ldr     \irqstat, [\base, #GIC_CPU_INTACK]
-
-	ldr		\tmp, =1021
-
-	bic     \irqnr, \irqstat, #0x1c00
-
-	cmp     \irqnr, #29
-	cmpcc	\irqnr, \irqnr
-	cmpne	\irqnr, \tmp
-	cmpcs	\irqnr, \irqnr
-
-	.endm
-
-	/* We assume that irqstat (the raw value of the IRQ acknowledge
-	 * register) is preserved from the macro above.
-	 * If there is an IPI, we immediately signal end of interrupt on the
-	 * controller, since this requires the original irqstat value which
-	 * we won't easily be able to recreate later.
-	 */
-
-	.macro test_for_ipi, irqnr, irqstat, base, tmp
-	bic	\irqnr, \irqstat, #0x1c00
-	cmp	\irqnr, #16
-	strcc	\irqstat, [\base, #GIC_CPU_EOI]
-	cmpcs	\irqnr, \irqnr
-	.endm
-
-	/* As above, this assumes that irqstat and base are preserved.. */
-
-	.macro test_for_ltirq, irqnr, irqstat, base, tmp
-	bic	\irqnr, \irqstat, #0x1c00
-	mov 	\tmp, #0
-	cmp	\irqnr, #29
-	moveq	\tmp, #1
-	streq	\irqstat, [\base, #GIC_CPU_EOI]
-	cmp	\tmp, #0
-	.endm
-
 #else
 	/* legacy interrupt controller for AP16 */
 	.macro	disable_fiq
diff --git a/arch/arm/mach-tegra/include/mach/smp.h b/arch/arm/mach-tegra/include/mach/smp.h
index e4a34a35a544..d1aa70415a4e 100644
--- a/arch/arm/mach-tegra/include/mach/smp.h
+++ b/arch/arm/mach-tegra/include/mach/smp.h
@@ -7,16 +7,9 @@
 /*
  * We use IRQ1 as the IPI
  */
-static inline void smp_cross_call(const struct cpumask *mask)
-{
-	gic_raise_softirq(mask, 1);
-}
-
-/*
- * Do nothing on MPcore.
- */
-static inline void smp_cross_call_done(cpumask_t callmap)
+static inline void smp_cross_call(const struct cpumask *mask, int ipi)
 {
+	gic_raise_softirq(mask, ipi);
 }
 
 #endif
diff --git a/arch/arm/mach-ux500/include/mach/entry-macro.S b/arch/arm/mach-ux500/include/mach/entry-macro.S
index 60ea88db8283..3cc3cdf55180 100644
--- a/arch/arm/mach-ux500/include/mach/entry-macro.S
+++ b/arch/arm/mach-ux500/include/mach/entry-macro.S
@@ -11,7 +11,7 @@
  * warranty of any kind, whether express or implied.
  */
 #include <mach/hardware.h>
-#include <asm/hardware/gic.h>
+#include <asm/hardware/entry-macro-gic.S>
 
 		.macro	disable_fiq
 		.endm
@@ -22,68 +22,3 @@
 
 		.macro  arch_ret_to_user, tmp1, tmp2
 		.endm
-
-		/*
-		 * The interrupt numbering scheme is defined in the
-		 * interrupt controller spec.  To wit:
-		 *
-		 * Interrupts 0-15 are IPI
-		 * 16-28 are reserved
-		 * 29-31 are local.  We allow 30 to be used for the watchdog.
-		 * 32-1020 are global
-		 * 1021-1022 are reserved
-		 * 1023 is "spurious" (no interrupt)
-		 *
-		 * For now, we ignore all local interrupts so only return an
-		 * interrupt if it's between 30 and 1020. The test_for_ipi
-		 * routine below will pick up on IPIs.
-		 *
-		 * A simple read from the controller will tell us the number
-		 * of the highest priority enabled interrupt. We then just
-		 * need to check whether it is in the valid range for an
-		 * IRQ (30-1020 inclusive).
-		 */
-
-		.macro  get_irqnr_and_base, irqnr, irqstat, base, tmp
-
-		/* bits 12-10 = src CPU, 9-0 = int # */
-		ldr     \irqstat, [\base, #GIC_CPU_INTACK]
-
-		ldr	\tmp, =1021
-
-		bic     \irqnr, \irqstat, #0x1c00
-
-		cmp     \irqnr, #29
-		cmpcc	\irqnr, \irqnr
-		cmpne	\irqnr, \tmp
-		cmpcs	\irqnr, \irqnr
-
-		.endm
-
-		/* We assume that irqstat (the raw value of the IRQ
-		 * acknowledge register) is preserved from the macro above.
-		 * If there is an IPI, we immediately signal end of
-		 * interrupt on the controller, since this requires the
-		 * original irqstat value which we won't easily be able
-		 * to recreate later.
-		 */
-
-		.macro test_for_ipi, irqnr, irqstat, base, tmp
-		bic	\irqnr, \irqstat, #0x1c00
-		cmp	\irqnr, #16
-		strcc	\irqstat, [\base, #GIC_CPU_EOI]
-		cmpcs	\irqnr, \irqnr
-		.endm
-
-		/* As above, this assumes that irqstat and base
-		 * are preserved..
-		 */
-
-		.macro test_for_ltirq, irqnr, irqstat, base, tmp
-		bic	\irqnr, \irqstat, #0x1c00
-		mov 	\tmp, #0
-		cmp	\irqnr, #29
-		moveq	\tmp, #1
-		streq	\irqstat, [\base, #GIC_CPU_EOI]
-		cmp	\tmp, #0
-		.endm
diff --git a/arch/arm/mach-ux500/include/mach/smp.h b/arch/arm/mach-ux500/include/mach/smp.h
index 197e8417375e..bd57c50a5b86 100644
--- a/arch/arm/mach-ux500/include/mach/smp.h
+++ b/arch/arm/mach-ux500/include/mach/smp.h
@@ -18,8 +18,8 @@ extern void u8500_secondary_startup(void);
 /*
  * We use IRQ1 as the IPI
  */
-static inline void smp_cross_call(const struct cpumask *mask)
+static inline void smp_cross_call(const struct cpumask *mask, int ipi)
 {
-	gic_raise_softirq(mask, 1);
+	gic_raise_softirq(mask, ipi);
 }
 #endif
diff --git a/arch/arm/mach-ux500/platsmp.c b/arch/arm/mach-ux500/platsmp.c
index 9e4c678de785..b8987bd21249 100644
--- a/arch/arm/mach-ux500/platsmp.c
+++ b/arch/arm/mach-ux500/platsmp.c
@@ -78,7 +78,7 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
 	__cpuc_flush_dcache_area((void *)&pen_release, sizeof(pen_release));
 	outer_clean_range(__pa(&pen_release), __pa(&pen_release) + 1);
 
-	smp_cross_call(cpumask_of(cpu));
+	smp_cross_call(cpumask_of(cpu), 1);
 
 	timeout = jiffies + (1 * HZ);
 	while (time_before(jiffies, timeout)) {
diff --git a/arch/arm/mach-versatile/core.c b/arch/arm/mach-versatile/core.c
index e38acb0f89c8..6b93bd600271 100644
--- a/arch/arm/mach-versatile/core.c
+++ b/arch/arm/mach-versatile/core.c
@@ -49,7 +49,7 @@
 #include <mach/clkdev.h>
 #include <mach/hardware.h>
 #include <mach/platform.h>
-#include <plat/timer-sp.h>
+#include <asm/hardware/timer-sp.h>
 
 #include "core.h"
 
diff --git a/arch/arm/mach-vexpress/ct-ca9x4.c b/arch/arm/mach-vexpress/ct-ca9x4.c
index fd25ccd7272f..cd7eecd44a6f 100644
--- a/arch/arm/mach-vexpress/ct-ca9x4.c
+++ b/arch/arm/mach-vexpress/ct-ca9x4.c
@@ -21,7 +21,7 @@
 #include <mach/clkdev.h>
 #include <mach/ct-ca9x4.h>
 
-#include <plat/timer-sp.h>
+#include <asm/hardware/timer-sp.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
diff --git a/arch/arm/mach-vexpress/include/mach/entry-macro.S b/arch/arm/mach-vexpress/include/mach/entry-macro.S
index 20e9fb514f0a..19d5ac8ba071 100644
--- a/arch/arm/mach-vexpress/include/mach/entry-macro.S
+++ b/arch/arm/mach-vexpress/include/mach/entry-macro.S
@@ -1,4 +1,4 @@
-#include <asm/hardware/gic.h>
+#include <asm/hardware/entry-macro-gic.S>
 
 	.macro	disable_fiq
 	.endm
@@ -10,58 +10,3 @@
 
 	.macro	arch_ret_to_user, tmp1, tmp2
 	.endm
-
-	/*
-	 * The interrupt numbering scheme is defined in the
-	 * interrupt controller spec.  To wit:
-	 *
-	 * Interrupts 0-15 are IPI
-	 * 16-28 are reserved
-	 * 29-31 are local.  We allow 30 to be used for the watchdog.
-	 * 32-1020 are global
-	 * 1021-1022 are reserved
-	 * 1023 is "spurious" (no interrupt)
-	 *
-	 * For now, we ignore all local interrupts so only return an interrupt if it's
-	 * between 30 and 1020.  The test_for_ipi routine below will pick up on IPIs.
-	 *
-	 * A simple read from the controller will tell us the number of the highest
-	 * priority enabled interrupt.  We then just need to check whether it is in the
-	 * valid range for an IRQ (30-1020 inclusive).
-	 */
-
-	.macro	get_irqnr_and_base, irqnr, irqstat, base, tmp
-	ldr     \irqstat, [\base, #GIC_CPU_INTACK] /* bits 12-10 = src CPU, 9-0 = int # */
-	ldr	\tmp, =1021
-	bic     \irqnr, \irqstat, #0x1c00
-	cmp     \irqnr, #29
-	cmpcc	\irqnr, \irqnr
-	cmpne	\irqnr, \tmp
-	cmpcs	\irqnr, \irqnr
-	.endm
-
-	/* We assume that irqstat (the raw value of the IRQ acknowledge
-	 * register) is preserved from the macro above.
-	 * If there is an IPI, we immediately signal end of interrupt on the
-	 * controller, since this requires the original irqstat value which
-	 * we won't easily be able to recreate later.
-	 */
-
-	.macro test_for_ipi, irqnr, irqstat, base, tmp
-	bic	\irqnr, \irqstat, #0x1c00
-	cmp	\irqnr, #16
-	strcc	\irqstat, [\base, #GIC_CPU_EOI]
-	cmpcs	\irqnr, \irqnr
-	.endm
-
-	/* As above, this assumes that irqstat and base are preserved.. */
-
-	.macro test_for_ltirq, irqnr, irqstat, base, tmp
-	bic	\irqnr, \irqstat, #0x1c00
-	mov 	\tmp, #0
-	cmp	\irqnr, #29
-	moveq	\tmp, #1
-	streq	\irqstat, [\base, #GIC_CPU_EOI]
-	cmp	\tmp, #0
-	.endm
-
diff --git a/arch/arm/mach-vexpress/include/mach/smp.h b/arch/arm/mach-vexpress/include/mach/smp.h
index 5a6da4fd247e..721be0f0311d 100644
--- a/arch/arm/mach-vexpress/include/mach/smp.h
+++ b/arch/arm/mach-vexpress/include/mach/smp.h
@@ -7,8 +7,8 @@
 /*
  * We use IRQ1 as the IPI
  */
-static inline void smp_cross_call(const struct cpumask *mask)
+static inline void smp_cross_call(const struct cpumask *mask, int ipi)
 {
-	gic_raise_softirq(mask, 1);
+	gic_raise_softirq(mask, ipi);
 }
 #endif
diff --git a/arch/arm/mach-vexpress/platsmp.c b/arch/arm/mach-vexpress/platsmp.c
index 670970699ba9..276f916014c1 100644
--- a/arch/arm/mach-vexpress/platsmp.c
+++ b/arch/arm/mach-vexpress/platsmp.c
@@ -92,7 +92,7 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
 	 * the boot monitor to read the system wide flags register,
 	 * and branch to the address found there.
 	 */
-	smp_cross_call(cpumask_of(cpu));
+	smp_cross_call(cpumask_of(cpu), 1);
 
 	timeout = jiffies + (1 * HZ);
 	while (time_before(jiffies, timeout)) {
diff --git a/arch/arm/mach-vexpress/v2m.c b/arch/arm/mach-vexpress/v2m.c
index 7eaa232180a5..91ff2e0df856 100644
--- a/arch/arm/mach-vexpress/v2m.c
+++ b/arch/arm/mach-vexpress/v2m.c
@@ -22,7 +22,7 @@
 #include <mach/clkdev.h>
 #include <mach/motherboard.h>
 
-#include <plat/timer-sp.h>
+#include <asm/hardware/timer-sp.h>
 
 #include "core.h"
 
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 4414a01e1e8a..8493ed04797a 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -599,6 +599,14 @@ config CPU_CP15_MPU
 	help
 	  Processor has the CP15 register, which has MPU related registers.
 
+config CPU_USE_DOMAINS
+	bool
+	depends on MMU
+	default y if !CPU_32v6K
+	help
+	  This option enables or disables the use of domain switching
+	  via the set_fs() function.
+
 #
 # CPU supports 36-bit I/O
 #
@@ -628,6 +636,33 @@ config ARM_THUMBEE
 	  Say Y here if you have a CPU with the ThumbEE extension and code to
 	  make use of it. Say N for code that can run on CPUs without ThumbEE.
 
+config SWP_EMULATE
+	bool "Emulate SWP/SWPB instructions"
+	depends on CPU_V7
+	select HAVE_PROC_CPU if PROC_FS
+	default y if SMP
+	help
+	  ARMv6 architecture deprecates use of the SWP/SWPB instructions.
+	  ARMv7 multiprocessing extensions introduce the ability to disable
+	  these instructions, triggering an undefined instruction exception
+	  when executed. Say Y here to enable software emulation of these
+	  instructions for userspace (not kernel) using LDREX/STREX.
+	  Also creates /proc/cpu/swp_emulation for statistics.
+
+	  In some older versions of glibc [<=2.8] SWP is used during futex
+	  trylock() operations with the assumption that the code will not
+	  be preempted. This invalid assumption may be more likely to fail
+	  with SWP emulation enabled, leading to deadlock of the user
+	  application.
+
+	  NOTE: when accessing uncached shared regions, LDREX/STREX rely
+	  on an external transaction monitoring block called a global
+	  monitor to maintain update atomicity. If your system does not
+	  implement a global monitor, this option can cause programs that
+	  perform SWP operations to uncached memory to deadlock.
+
+	  If unsure, say Y.
+
 config CPU_BIG_ENDIAN
 	bool "Build big-endian kernel"
 	depends on ARCH_SUPPORTS_BIG_ENDIAN
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 72ad3e1f56cf..79c01f540cbe 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -24,6 +24,7 @@
 #include <asm/smp_plat.h>
 #include <asm/tlb.h>
 #include <asm/highmem.h>
+#include <asm/traps.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
@@ -914,12 +915,11 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
 {
 	struct map_desc map;
 	unsigned long addr;
-	void *vectors;
 
 	/*
 	 * Allocate the vector page early.
 	 */
-	vectors = early_alloc(PAGE_SIZE);
+	vectors_page = early_alloc(PAGE_SIZE);
 
 	for (addr = VMALLOC_END; addr; addr += PGDIR_SIZE)
 		pmd_clear(pmd_off_k(addr));
@@ -959,7 +959,7 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
 	 * location (0xffff0000).  If we aren't using high-vectors, also
 	 * create a mapping at the low-vectors virtual address.
 	 */
-	map.pfn = __phys_to_pfn(virt_to_phys(vectors));
+	map.pfn = __phys_to_pfn(virt_to_phys(vectors_page));
 	map.virtual = 0xffff0000;
 	map.length = PAGE_SIZE;
 	map.type = MT_HIGH_VECTORS;
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index 7d63beaf9745..337f10256cd6 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -99,6 +99,10 @@
  *  110x   0   1   0	r/w	r/o
  *  11x0   0   1   0	r/w	r/o
  *  1111   0   1   1	r/w	r/w
+ *
+ * If !CONFIG_CPU_USE_DOMAINS, the following permissions are changed:
+ *  110x   1   1   1	r/o	r/o
+ *  11x0   1   1   1	r/o	r/o
  */
 	.macro	armv6_mt_table pfx
 \pfx\()_mt_table:
@@ -138,8 +142,11 @@
 
 	tst	r1, #L_PTE_USER
 	orrne	r3, r3, #PTE_EXT_AP1
+#ifdef CONFIG_CPU_USE_DOMAINS
+	@ allow kernel read/write access to read-only user pages
 	tstne	r3, #PTE_EXT_APX
 	bicne	r3, r3, #PTE_EXT_APX | PTE_EXT_AP0
+#endif
 
 	tst	r1, #L_PTE_EXEC
 	orreq	r3, r3, #PTE_EXT_XN
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 53cbe2225153..2b5b20baf80d 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -148,8 +148,11 @@ ENTRY(cpu_v7_set_pte_ext)
 
 	tst	r1, #L_PTE_USER
 	orrne	r3, r3, #PTE_EXT_AP1
+#ifdef CONFIG_CPU_USE_DOMAINS
+	@ allow kernel read/write access to read-only user pages
 	tstne	r3, #PTE_EXT_APX
 	bicne	r3, r3, #PTE_EXT_APX | PTE_EXT_AP0
+#endif
 
 	tst	r1, #L_PTE_EXEC
 	orreq	r3, r3, #PTE_EXT_XN
@@ -273,8 +276,6 @@ __v7_setup:
 	ALT_SMP(orr	r4, r4, #TTB_FLAGS_SMP)
 	ALT_UP(orr	r4, r4, #TTB_FLAGS_UP)
 	mcr	p15, 0, r4, c2, c0, 1		@ load TTB1
-	mov	r10, #0x1f			@ domains 0, 1 = manager
-	mcr	p15, 0, r10, c3, c0, 0		@ load domain access register
 	/*
 	 * Memory region attributes with SCTLR.TRE=1
 	 *
@@ -313,6 +314,10 @@ __v7_setup:
 #ifdef CONFIG_CPU_ENDIAN_BE8
 	orr	r6, r6, #1 << 25		@ big-endian page tables
 #endif
+#ifdef CONFIG_SWP_EMULATE
+	orr     r5, r5, #(1 << 10)              @ set SW bit in "clear"
+	bic     r6, r6, #(1 << 10)              @ clear it in "mmuset"
+#endif
    	mrc	p15, 0, r0, c1, c0, 0		@ read control register
 	bic	r0, r0, r5			@ clear bits them
 	orr	r0, r0, r6			@ set them
diff --git a/arch/arm/plat-omap/include/plat/smp.h b/arch/arm/plat-omap/include/plat/smp.h
index ecd6a488c497..e5541e5388be 100644
--- a/arch/arm/plat-omap/include/plat/smp.h
+++ b/arch/arm/plat-omap/include/plat/smp.h
@@ -29,9 +29,9 @@ extern u32 omap_read_auxcoreboot0(void);
 /*
  * We use Soft IRQ1 as the IPI
  */
-static inline void smp_cross_call(const struct cpumask *mask)
+static inline void smp_cross_call(const struct cpumask *mask, int ipi)
 {
-	gic_raise_softirq(mask, 1);
+	gic_raise_softirq(mask, ipi);
 }
 
 #endif
diff --git a/arch/arm/plat-versatile/Makefile b/arch/arm/plat-versatile/Makefile
index 5cf88e8427b1..aaa571d17924 100644
--- a/arch/arm/plat-versatile/Makefile
+++ b/arch/arm/plat-versatile/Makefile
@@ -1,5 +1,4 @@
 obj-y	:= clock.o
-obj-$(CONFIG_ARM_TIMER_SP804) += timer-sp.o
 obj-$(CONFIG_ARCH_REALVIEW) += sched-clock.o
 obj-$(CONFIG_ARCH_VERSATILE) += sched-clock.o
 ifeq ($(CONFIG_LEDS_CLASS),y)