Merge branch 'for-linus' of git://git.linaro.org/people/rmk/linux-arm

Pull core ARM updates from Russell King:
 "This is the bulk of the core ARM updates for this merge window.
  Included in here is a different way to handle the VIVT cache flushing
  on context switch, which should allow scheduler folk to remove a
  special case in their core code.

  We have architectured timer support here, which is a set of timers
  specified by the ARM architecture for future SoCs.  So we should see
  less variability in timer design going forward.

  The last big thing here is my cleanup to the way we handle PCI across
  ARM, fixing some oddities in some platforms which hadn't realised
  there was a way to deal with their private data already built in to
  our PCI backend.

  I've also removed support for the ARMv3 architecture; it hasn't worked
  properly for years so it seems pointless to keep it around."

* 'for-linus' of git://git.linaro.org/people/rmk/linux-arm: (47 commits)
  ARM: PCI: remove per-pci_hw list of buses
  ARM: PCI: dove/kirkwood/mv78xx0: use sys->private_data
  ARM: PCI: provide a default bus scan implementation
  ARM: PCI: get rid of pci_std_swizzle()
  ARM: PCI: versatile: fix PCI interrupt setup
  ARM: PCI: integrator: use common PCI swizzle
  ARM: 7416/1: LPAE: Remove unused L_PTE_(BUFFERABLE|CACHEABLE) macros
  ARM: 7415/1: vfp: convert printk's to pr_*'s
  ARM: decompressor: avoid speculative prefetch from non-RAM areas
  ARM: Remove ARMv3 support from decompressor
  ARM: 7413/1: move read_{boot,persistent}_clock to the architecture level
  ARM: Remove support for ARMv3 ARM610 and ARM710 CPUs
  ARM: 7363/1: DEBUG_LL: limit early mapping to the minimum
  ARM: 7391/1: versatile: add some auxdata for device trees
  ARM: 7389/2: plat-versatile: modernize FPGA IRQ controller
  AMBA: get rid of last two uses of NO_IRQ
  ARM: 7408/1: cacheflush: return error to userspace when flushing syscall fails
  ARM: 7409/1: Do not call flush_cache_user_range with mmap_sem held
  ARM: 7404/1: cmpxchg64: use atomic64 and local64 routines for cmpxchg64
  ARM: 7347/1: SCU: use cpu_logical_map for per-CPU low power mode
  ...

16 files changed, 227 insertions, 163 deletions

diff --git a/arch/arm/include/asm/arch_timer.h b/arch/arm/include/asm/arch_timer.h
new file mode 100644
index 000000000000..ed2e95d46e29
--- /dev/null
+++ b/arch/arm/include/asm/arch_timer.h
@@ -0,0 +1,19 @@
+#ifndef __ASMARM_ARCH_TIMER_H
+#define __ASMARM_ARCH_TIMER_H
+
+#ifdef CONFIG_ARM_ARCH_TIMER
+int arch_timer_of_register(void);
+int arch_timer_sched_clock_init(void);
+#else
+static inline int arch_timer_of_register(void)
+{
+	return -ENXIO;
+}
+
+static inline int arch_timer_sched_clock_init(void)
+{
+	return -ENXIO;
+}
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index d5d8d5c72682..004c1bc95d2b 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/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))
 
 /*
diff --git a/arch/arm/include/asm/cmpxchg.h b/arch/arm/include/asm/cmpxchg.h
index d41d7cbf0ada..7eb18c1d8d6c 100644
--- a/arch/arm/include/asm/cmpxchg.h
+++ b/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 */
 
diff --git a/arch/arm/include/asm/glue-df.h b/arch/arm/include/asm/glue-df.h
index 354d571e8bcc..8cacbcda76da 100644
--- a/arch/arm/include/asm/glue-df.h
+++ b/arch/arm/include/asm/glue-df.h
@@ -31,14 +31,6 @@
 #undef CPU_DABORT_HANDLER
 #undef MULTI_DABORT
 
-#if defined(CONFIG_CPU_ARM610)
-# ifdef CPU_DABORT_HANDLER
-#  define MULTI_DABORT 1
-# else
-#  define CPU_DABORT_HANDLER cpu_arm6_data_abort
-# endif
-#endif
-
 #if defined(CONFIG_CPU_ARM710)
 # ifdef CPU_DABORT_HANDLER
 #  define MULTI_DABORT 1
diff --git a/arch/arm/include/asm/glue-proc.h b/arch/arm/include/asm/glue-proc.h
index e2be7f142668..ac1dd54724b6 100644
--- a/arch/arm/include/asm/glue-proc.h
+++ b/arch/arm/include/asm/glue-proc.h
@@ -23,15 +23,6 @@
  * CPU_NAME - the prefix for CPU related functions
  */
 
-#ifdef CONFIG_CPU_ARM610
-# ifdef CPU_NAME
-#  undef  MULTI_CPU
-#  define MULTI_CPU
-# else
-#  define CPU_NAME cpu_arm6
-# endif
-#endif
-
 #ifdef CONFIG_CPU_ARM7TDMI
 # ifdef CPU_NAME
 #  undef  MULTI_CPU
@@ -41,15 +32,6 @@
 # endif
 #endif
 
-#ifdef CONFIG_CPU_ARM710
-# ifdef CPU_NAME
-#  undef  MULTI_CPU
-#  define MULTI_CPU
-# else
-#  define CPU_NAME cpu_arm7
-# endif
-#endif
-
 #ifdef CONFIG_CPU_ARM720T
 # ifdef CPU_NAME
 #  undef  MULTI_CPU
diff --git a/arch/arm/include/asm/hardware/it8152.h b/arch/arm/include/asm/hardware/it8152.h
index 73f84fa4f366..d36a73d7c0e8 100644
--- a/arch/arm/include/asm/hardware/it8152.h
+++ b/arch/arm/include/asm/hardware/it8152.h
@@ -110,6 +110,6 @@ extern void it8152_irq_demux(unsigned int irq, struct irq_desc *desc);
 extern void it8152_init_irq(void);
 extern int it8152_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin);
 extern int it8152_pci_setup(int nr, struct pci_sys_data *sys);
-extern struct pci_bus *it8152_pci_scan_bus(int nr, struct pci_sys_data *sys);
+extern struct pci_ops it8152_ops;
 
 #endif /* __ASM_HARDWARE_IT8152_H */
diff --git a/arch/arm/include/asm/mach/pci.h b/arch/arm/include/asm/mach/pci.h
index d943b7d20f11..26c511fddf8f 100644
--- a/arch/arm/include/asm/mach/pci.h
+++ b/arch/arm/include/asm/mach/pci.h
@@ -12,13 +12,14 @@
 #define __ASM_MACH_PCI_H
 
 struct pci_sys_data;
+struct pci_ops;
 struct pci_bus;
 
 struct hw_pci {
 #ifdef CONFIG_PCI_DOMAINS
 	int		domain;
 #endif
-	struct list_head buses;
+	struct pci_ops	*ops;
 	int		nr_controllers;
 	int		(*setup)(int nr, struct pci_sys_data *);
 	struct pci_bus *(*scan)(int nr, struct pci_sys_data *);
@@ -45,16 +46,10 @@ struct pci_sys_data {
 	u8		(*swizzle)(struct pci_dev *, u8 *);
 					/* IRQ mapping				*/
 	int		(*map_irq)(const struct pci_dev *, u8, u8);
-	struct hw_pci	*hw;
 	void		*private_data;	/* platform controller private data	*/
 };
 
 /*
- * This is the standard PCI-PCI bridge swizzling algorithm.
- */
-#define pci_std_swizzle pci_common_swizzle
-
-/*
  * Call this with your hw_pci struct to initialise the PCI system.
  */
 void pci_common_init(struct hw_pci *);
@@ -62,22 +57,22 @@ void pci_common_init(struct hw_pci *);
 /*
  * PCI controllers
  */
+extern struct pci_ops iop3xx_ops;
 extern int iop3xx_pci_setup(int nr, struct pci_sys_data *);
-extern struct pci_bus *iop3xx_pci_scan_bus(int nr, struct pci_sys_data *);
 extern void iop3xx_pci_preinit(void);
 extern void iop3xx_pci_preinit_cond(void);
 
+extern struct pci_ops dc21285_ops;
 extern int dc21285_setup(int nr, struct pci_sys_data *);
-extern struct pci_bus *dc21285_scan_bus(int nr, struct pci_sys_data *);
 extern void dc21285_preinit(void);
 extern void dc21285_postinit(void);
 
+extern struct pci_ops via82c505_ops;
 extern int via82c505_setup(int nr, struct pci_sys_data *);
-extern struct pci_bus *via82c505_scan_bus(int nr, struct pci_sys_data *);
 extern void via82c505_init(void *sysdata);
 
+extern struct pci_ops pci_v3_ops;
 extern int pci_v3_setup(int nr, struct pci_sys_data *);
-extern struct pci_bus *pci_v3_scan_bus(int nr, struct pci_sys_data *);
 extern void pci_v3_preinit(void);
 extern void pci_v3_postinit(void);
 
diff --git a/arch/arm/include/asm/mach/time.h b/arch/arm/include/asm/mach/time.h
index f73c908b7fa0..6ca945f534ab 100644
--- a/arch/arm/include/asm/mach/time.h
+++ b/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
diff --git a/arch/arm/include/asm/mmu.h b/arch/arm/include/asm/mmu.h
index b8e580a297e4..14965658a923 100644
--- a/arch/arm/include/asm/mmu.h
+++ b/arch/arm/include/asm/mmu.h
@@ -34,11 +34,4 @@ typedef struct {
 
 #endif
 
-/*
- * switch_mm() may do a full cache flush over the context switch,
- * so enable interrupts over the context switch to avoid high
- * latency.
- */
-#define __ARCH_WANT_INTERRUPTS_ON_CTXSW
-
 #endif
diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h
index a0b3cac0547c..0306bc642c0d 100644
--- a/arch/arm/include/asm/mmu_context.h
+++ b/arch/arm/include/asm/mmu_context.h
@@ -43,45 +43,104 @@ void __check_kvm_seq(struct mm_struct *mm);
 #define ASID_FIRST_VERSION	(1 << ASID_BITS)
 
 extern unsigned int cpu_last_asid;
-#ifdef CONFIG_SMP
-DECLARE_PER_CPU(struct mm_struct *, current_mm);
-#endif
 
 void __init_new_context(struct task_struct *tsk, struct mm_struct *mm);
 void __new_context(struct mm_struct *mm);
+void cpu_set_reserved_ttbr0(void);
 
-static inline void check_context(struct mm_struct *mm)
+static inline void switch_new_context(struct mm_struct *mm)
 {
-	/*
-	 * This code is executed with interrupts enabled. Therefore,
-	 * mm->context.id cannot be updated to the latest ASID version
-	 * on a different CPU (and condition below not triggered)
-	 * without first getting an IPI to reset the context. The
-	 * alternative is to take a read_lock on mm->context.id_lock
-	 * (after changing its type to rwlock_t).
-	 */
-	if (unlikely((mm->context.id ^ cpu_last_asid) >> ASID_BITS))
-		__new_context(mm);
+	unsigned long flags;
+
+	__new_context(mm);
+
+	local_irq_save(flags);
+	cpu_switch_mm(mm->pgd, mm);
+	local_irq_restore(flags);
+}
 
+static inline void check_and_switch_context(struct mm_struct *mm,
+					    struct task_struct *tsk)
+{
 	if (unlikely(mm->context.kvm_seq != init_mm.context.kvm_seq))
 		__check_kvm_seq(mm);
+
+	/*
+	 * Required during context switch to avoid speculative page table
+	 * walking with the wrong TTBR.
+	 */
+	cpu_set_reserved_ttbr0();
+
+	if (!((mm->context.id ^ cpu_last_asid) >> ASID_BITS))
+		/*
+		 * The ASID is from the current generation, just switch to the
+		 * new pgd. This condition is only true for calls from
+		 * context_switch() and interrupts are already disabled.
+		 */
+		cpu_switch_mm(mm->pgd, mm);
+	else if (irqs_disabled())
+		/*
+		 * Defer the new ASID allocation until after the context
+		 * switch critical region since __new_context() cannot be
+		 * called with interrupts disabled (it sends IPIs).
+		 */
+		set_ti_thread_flag(task_thread_info(tsk), TIF_SWITCH_MM);
+	else
+		/*
+		 * That is a direct call to switch_mm() or activate_mm() with
+		 * interrupts enabled and a new context.
+		 */
+		switch_new_context(mm);
 }
 
 #define init_new_context(tsk,mm)	(__init_new_context(tsk,mm),0)
 
-#else
-
-static inline void check_context(struct mm_struct *mm)
+#define finish_arch_post_lock_switch \
+	finish_arch_post_lock_switch
+static inline void finish_arch_post_lock_switch(void)
 {
+	if (test_and_clear_thread_flag(TIF_SWITCH_MM))
+		switch_new_context(current->mm);
+}
+
+#else	/* !CONFIG_CPU_HAS_ASID */
+
 #ifdef CONFIG_MMU
+
+static inline void check_and_switch_context(struct mm_struct *mm,
+					    struct task_struct *tsk)
+{
 	if (unlikely(mm->context.kvm_seq != init_mm.context.kvm_seq))
 		__check_kvm_seq(mm);
-#endif
+
+	if (irqs_disabled())
+		/*
+		 * cpu_switch_mm() needs to flush the VIVT caches. To avoid
+		 * high interrupt latencies, defer the call and continue
+		 * running with the old mm. Since we only support UP systems
+		 * on non-ASID CPUs, the old mm will remain valid until the
+		 * finish_arch_post_lock_switch() call.
+		 */
+		set_ti_thread_flag(task_thread_info(tsk), TIF_SWITCH_MM);
+	else
+		cpu_switch_mm(mm->pgd, mm);
 }
 
+#define finish_arch_post_lock_switch \
+	finish_arch_post_lock_switch
+static inline void finish_arch_post_lock_switch(void)
+{
+	if (test_and_clear_thread_flag(TIF_SWITCH_MM)) {
+		struct mm_struct *mm = current->mm;
+		cpu_switch_mm(mm->pgd, mm);
+	}
+}
+
+#endif	/* CONFIG_MMU */
+
 #define init_new_context(tsk,mm)	0
 
-#endif
+#endif	/* CONFIG_CPU_HAS_ASID */
 
 #define destroy_context(mm)		do { } while(0)
 
@@ -119,12 +178,7 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
 		__flush_icache_all();
 #endif
 	if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next) {
-#ifdef CONFIG_SMP
-		struct mm_struct **crt_mm = &per_cpu(current_mm, cpu);
-		*crt_mm = next;
-#endif
-		check_context(next);
-		cpu_switch_mm(next->pgd, next);
+		check_and_switch_context(next, tsk);
 		if (cache_is_vivt())
 			cpumask_clear_cpu(cpu, mm_cpumask(prev));
 	}
diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h
index 5838361c48b3..ecf901902e44 100644
--- a/arch/arm/include/asm/page.h
+++ b/arch/arm/include/asm/page.h
@@ -34,7 +34,6 @@
  *	processor(s) we're building for.
  *
  *	We have the following to choose from:
- *	  v3		- ARMv3
  *	  v4wt		- ARMv4 with writethrough cache, without minicache
  *	  v4wb		- ARMv4 with writeback cache, without minicache
  *	  v4_mc		- ARMv4 with minicache
@@ -44,14 +43,6 @@
 #undef _USER
 #undef MULTI_USER
 
-#ifdef CONFIG_CPU_COPY_V3
-# ifdef _USER
-#  define MULTI_USER 1
-# else
-#  define _USER v3
-# endif
-#endif
-
 #ifdef CONFIG_CPU_COPY_V4WT
 # ifdef _USER
 #  define MULTI_USER 1
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index 759af70f9a0a..b24903549d1c 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/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 */
diff --git a/arch/arm/include/asm/ptrace.h b/arch/arm/include/asm/ptrace.h
index 451808ba1211..355ece523f41 100644
--- a/arch/arm/include/asm/ptrace.h
+++ b/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__ */
diff --git a/arch/arm/include/asm/syscall.h b/arch/arm/include/asm/syscall.h
new file mode 100644
index 000000000000..c334a23ddf75
--- /dev/null
+++ b/arch/arm/include/asm/syscall.h
@@ -0,0 +1,93 @@
+/*
+ * 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 */
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index 0f04d84582e1..68388eb4946b 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -153,6 +153,7 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *,
 #define TIF_MEMDIE		18	/* is terminating due to OOM killer */
 #define TIF_RESTORE_SIGMASK	20
 #define TIF_SECCOMP		21
+#define TIF_SWITCH_MM		22	/* deferred switch_mm */
 
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h
index 85fe61e73202..6e924d3a77eb 100644
--- a/arch/arm/include/asm/tlbflush.h
+++ b/arch/arm/include/asm/tlbflush.h
@@ -65,21 +65,6 @@
 #define MULTI_TLB 1
 #endif
 
-#define v3_tlb_flags	(TLB_V3_FULL | TLB_V3_PAGE)
-
-#ifdef CONFIG_CPU_TLB_V3
-# define v3_possible_flags	v3_tlb_flags
-# define v3_always_flags	v3_tlb_flags
-# ifdef _TLB
-#  define MULTI_TLB 1
-# else
-#  define _TLB v3
-# endif
-#else
-# define v3_possible_flags	0
-# define v3_always_flags	(-1UL)
-#endif
-
 #define v4_tlb_flags	(TLB_V4_U_FULL | TLB_V4_U_PAGE)
 
 #ifdef CONFIG_CPU_TLB_V4WT
@@ -298,8 +283,7 @@ extern struct cpu_tlb_fns cpu_tlb;
  * implemented the "%?" method, but this has been discontinued due to too
  * many people getting it wrong.
  */
-#define possible_tlb_flags	(v3_possible_flags | \
-				 v4_possible_flags | \
+#define possible_tlb_flags	(v4_possible_flags | \
 				 v4wbi_possible_flags | \
 				 fr_possible_flags | \
 				 v4wb_possible_flags | \
@@ -307,8 +291,7 @@ extern struct cpu_tlb_fns cpu_tlb;
 				 v6wbi_possible_flags | \
 				 v7wbi_possible_flags)
 
-#define always_tlb_flags	(v3_always_flags & \
-				 v4_always_flags & \
+#define always_tlb_flags	(v4_always_flags & \
 				 v4wbi_always_flags & \
 				 fr_always_flags & \
 				 v4wb_always_flags & \