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

Pull ARM fixes from Russell King:
 "The largest thing in this set of changes is bringing back some of the
  ARMv3 code to fix a compile problem noticed on RiscPC, which we still
  support, even though we only support ARMv4 there.

  (The reason is that the system bus doesn't support ARMv4 half-word
  accesses, so we need the ARMv3 library code for this platform.)

  The rest are all quite minor fixes."

* 'fixes' of git://git.linaro.org/people/rmk/linux-arm:
  ARM: 7490/1: Drop duplicate select for GENERIC_IRQ_PROBE
  ARM: Bring back ARMv3 IO and user access code
  ARM: 7489/1: errata: fix workaround for erratum #720789 on UP systems
  ARM: 7488/1: mm: use 5 bits for swapfile type encoding
  ARM: 7487/1: mm: avoid setting nG bit for user mappings that aren't present
  ARM: 7486/1: sched_clock: update epoch_cyc on resume
  ARM: 7484/1: Don't enable GENERIC_LOCKBREAK with ticket spinlocks
  ARM: 7483/1: vfp: only advertise VFPv4 in hwcaps if CONFIG_VFPv3 is enabled
  ARM: 7482/1: topology: fix section mismatch warning for init_cpu_topology

12 files changed, 869 insertions, 34 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index e91c7cdc6fe..6d6e18fee9f 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -38,7 +38,6 @@ config ARM
 	select HARDIRQS_SW_RESEND
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
-	select GENERIC_IRQ_PROBE
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select HARDIRQS_SW_RESEND
 	select CPU_PM if (SUSPEND || CPU_IDLE)
@@ -126,11 +125,6 @@ config TRACE_IRQFLAGS_SUPPORT
 	bool
 	default y
 
-config GENERIC_LOCKBREAK
-	bool
-	default y
-	depends on SMP && PREEMPT
-
 config RWSEM_GENERIC_SPINLOCK
 	bool
 	default y
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index f66626d71e7..41dc31f834c 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -195,6 +195,18 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
 
 #define pte_clear(mm,addr,ptep)	set_pte_ext(ptep, __pte(0), 0)
 
+#define pte_none(pte)		(!pte_val(pte))
+#define pte_present(pte)	(pte_val(pte) & L_PTE_PRESENT)
+#define pte_write(pte)		(!(pte_val(pte) & L_PTE_RDONLY))
+#define pte_dirty(pte)		(pte_val(pte) & L_PTE_DIRTY)
+#define pte_young(pte)		(pte_val(pte) & L_PTE_YOUNG)
+#define pte_exec(pte)		(!(pte_val(pte) & L_PTE_XN))
+#define pte_special(pte)	(0)
+
+#define pte_present_user(pte) \
+	((pte_val(pte) & (L_PTE_PRESENT | L_PTE_USER)) == \
+	 (L_PTE_PRESENT | L_PTE_USER))
+
 #if __LINUX_ARM_ARCH__ < 6
 static inline void __sync_icache_dcache(pte_t pteval)
 {
@@ -206,25 +218,15 @@ extern void __sync_icache_dcache(pte_t pteval);
 static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep, pte_t pteval)
 {
-	if (addr >= TASK_SIZE)
-		set_pte_ext(ptep, pteval, 0);
-	else {
+	unsigned long ext = 0;
+
+	if (addr < TASK_SIZE && pte_present_user(pteval)) {
 		__sync_icache_dcache(pteval);
-		set_pte_ext(ptep, pteval, PTE_EXT_NG);
+		ext |= PTE_EXT_NG;
 	}
-}
 
-#define pte_none(pte)		(!pte_val(pte))
-#define pte_present(pte)	(pte_val(pte) & L_PTE_PRESENT)
-#define pte_write(pte)		(!(pte_val(pte) & L_PTE_RDONLY))
-#define pte_dirty(pte)		(pte_val(pte) & L_PTE_DIRTY)
-#define pte_young(pte)		(pte_val(pte) & L_PTE_YOUNG)
-#define pte_exec(pte)		(!(pte_val(pte) & L_PTE_XN))
-#define pte_special(pte)	(0)
-
-#define pte_present_user(pte) \
-	((pte_val(pte) & (L_PTE_PRESENT | L_PTE_USER)) == \
-	 (L_PTE_PRESENT | L_PTE_USER))
+	set_pte_ext(ptep, pteval, ext);
+}
 
 #define PTE_BIT_FUNC(fn,op) \
 static inline pte_t pte_##fn(pte_t pte) { pte_val(pte) op; return pte; }
@@ -251,13 +253,13 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
  *
  *   3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1
  *   1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
- *   <--------------- offset --------------------> <- type --> 0 0 0
+ *   <--------------- offset ----------------------> < type -> 0 0 0
  *
- * This gives us up to 63 swap files and 32GB per swap file.  Note that
+ * This gives us up to 31 swap files and 64GB per swap file.  Note that
  * the offset field is always non-zero.
  */
 #define __SWP_TYPE_SHIFT	3
-#define __SWP_TYPE_BITS		6
+#define __SWP_TYPE_BITS		5
 #define __SWP_TYPE_MASK		((1 << __SWP_TYPE_BITS) - 1)
 #define __SWP_OFFSET_SHIFT	(__SWP_TYPE_BITS + __SWP_TYPE_SHIFT)
 
diff --git a/arch/arm/include/asm/sched_clock.h b/arch/arm/include/asm/sched_clock.h
index e3f75726343..05b8e82ec9f 100644
--- a/arch/arm/include/asm/sched_clock.h
+++ b/arch/arm/include/asm/sched_clock.h
@@ -10,5 +10,7 @@
 
 extern void sched_clock_postinit(void);
 extern void setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate);
+extern void setup_sched_clock_needs_suspend(u32 (*read)(void), int bits,
+		unsigned long rate);
 
 #endif
diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c
index 27d186abbc0..f4515393248 100644
--- a/arch/arm/kernel/sched_clock.c
+++ b/arch/arm/kernel/sched_clock.c
@@ -21,6 +21,8 @@ struct clock_data {
 	u32 epoch_cyc_copy;
 	u32 mult;
 	u32 shift;
+	bool suspended;
+	bool needs_suspend;
 };
 
 static void sched_clock_poll(unsigned long wrap_ticks);
@@ -49,6 +51,9 @@ static unsigned long long cyc_to_sched_clock(u32 cyc, u32 mask)
 	u64 epoch_ns;
 	u32 epoch_cyc;
 
+	if (cd.suspended)
+		return cd.epoch_ns;
+
 	/*
 	 * Load the epoch_cyc and epoch_ns atomically.  We do this by
 	 * ensuring that we always write epoch_cyc, epoch_ns and
@@ -98,6 +103,13 @@ static void sched_clock_poll(unsigned long wrap_ticks)
 	update_sched_clock();
 }
 
+void __init setup_sched_clock_needs_suspend(u32 (*read)(void), int bits,
+		unsigned long rate)
+{
+	setup_sched_clock(read, bits, rate);
+	cd.needs_suspend = true;
+}
+
 void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate)
 {
 	unsigned long r, w;
@@ -169,11 +181,23 @@ void __init sched_clock_postinit(void)
 static int sched_clock_suspend(void)
 {
 	sched_clock_poll(sched_clock_timer.data);
+	if (cd.needs_suspend)
+		cd.suspended = true;
 	return 0;
 }
 
+static void sched_clock_resume(void)
+{
+	if (cd.needs_suspend) {
+		cd.epoch_cyc = read_sched_clock();
+		cd.epoch_cyc_copy = cd.epoch_cyc;
+		cd.suspended = false;
+	}
+}
+
 static struct syscore_ops sched_clock_ops = {
 	.suspend = sched_clock_suspend,
+	.resume = sched_clock_resume,
 };
 
 static int __init sched_clock_syscore_init(void)
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index 198b08456e9..26c12c6440f 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -321,7 +321,7 @@ void store_cpu_topology(unsigned int cpuid)
  * init_cpu_topology is called at boot when only one cpu is running
  * which prevent simultaneous write access to cpu_topology array
  */
-void init_cpu_topology(void)
+void __init init_cpu_topology(void)
 {
 	unsigned int cpu;
 
diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index 2473fd1fd51..af72969820b 100644
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile
@@ -16,13 +16,30 @@ lib-y		:= backtrace.o changebit.o csumipv6.o csumpartial.o   \
 		   call_with_stack.o
 
 mmu-y	:= clear_user.o copy_page.o getuser.o putuser.o
-mmu-y	+= copy_from_user.o copy_to_user.o
+
+# the code in uaccess.S is not preemption safe and
+# probably faster on ARMv3 only
+ifeq ($(CONFIG_PREEMPT),y)
+  mmu-y	+= copy_from_user.o copy_to_user.o
+else
+ifneq ($(CONFIG_CPU_32v3),y)
+  mmu-y	+= copy_from_user.o copy_to_user.o
+else
+  mmu-y	+= uaccess.o
+endif
+endif
 
 # using lib_ here won't override already available weak symbols
 obj-$(CONFIG_UACCESS_WITH_MEMCPY) += uaccess_with_memcpy.o
 
-lib-$(CONFIG_MMU)		+= $(mmu-y)
-lib-y				+= io-readsw-armv4.o io-writesw-armv4.o
+lib-$(CONFIG_MMU) += $(mmu-y)
+
+ifeq ($(CONFIG_CPU_32v3),y)
+  lib-y	+= io-readsw-armv3.o io-writesw-armv3.o
+else
+  lib-y	+= io-readsw-armv4.o io-writesw-armv4.o
+endif
+
 lib-$(CONFIG_ARCH_RPC)		+= ecard.o io-acorn.o floppydma.o
 lib-$(CONFIG_ARCH_SHARK)	+= io-shark.o
 
diff --git a/arch/arm/lib/io-readsw-armv3.S b/arch/arm/lib/io-readsw-armv3.S
new file mode 100644
index 00000000000..88487c8c4f2
--- /dev/null
+++ b/arch/arm/lib/io-readsw-armv3.S
@@ -0,0 +1,106 @@
+/*
+ *  linux/arch/arm/lib/io-readsw-armv3.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+.Linsw_bad_alignment:
+		adr	r0, .Linsw_bad_align_msg
+		mov	r2, lr
+		b	panic
+.Linsw_bad_align_msg:
+		.asciz	"insw: bad buffer alignment (0x%p, lr=0x%08lX)\n"
+		.align
+
+.Linsw_align:	tst	r1, #1
+		bne	.Linsw_bad_alignment
+
+		ldr	r3, [r0]
+		strb	r3, [r1], #1
+		mov	r3, r3, lsr #8
+		strb	r3, [r1], #1
+
+		subs	r2, r2, #1
+		moveq	pc, lr
+
+ENTRY(__raw_readsw)
+		teq	r2, #0		@ do we have to check for the zero len?
+		moveq	pc, lr
+		tst	r1, #3
+		bne	.Linsw_align
+
+.Linsw_aligned:	mov	ip, #0xff
+		orr	ip, ip, ip, lsl #8
+		stmfd	sp!, {r4, r5, r6, lr}
+
+		subs	r2, r2, #8
+		bmi	.Lno_insw_8
+
+.Linsw_8_lp:	ldr	r3, [r0]
+		and	r3, r3, ip
+		ldr	r4, [r0]
+		orr	r3, r3, r4, lsl #16
+
+		ldr	r4, [r0]
+		and	r4, r4, ip
+		ldr	r5, [r0]
+		orr	r4, r4, r5, lsl #16
+
+		ldr	r5, [r0]
+		and	r5, r5, ip
+		ldr	r6, [r0]
+		orr	r5, r5, r6, lsl #16
+
+		ldr	r6, [r0]
+		and	r6, r6, ip
+		ldr	lr, [r0]
+		orr	r6, r6, lr, lsl #16
+
+		stmia	r1!, {r3 - r6}
+
+		subs	r2, r2, #8
+		bpl	.Linsw_8_lp
+
+		tst	r2, #7
+		ldmeqfd	sp!, {r4, r5, r6, pc}
+
+.Lno_insw_8:	tst	r2, #4
+		beq	.Lno_insw_4
+
+		ldr	r3, [r0]
+		and	r3, r3, ip
+		ldr	r4, [r0]
+		orr	r3, r3, r4, lsl #16
+
+		ldr	r4, [r0]
+		and	r4, r4, ip
+		ldr	r5, [r0]
+		orr	r4, r4, r5, lsl #16
+
+		stmia	r1!, {r3, r4}
+
+.Lno_insw_4:	tst	r2, #2
+		beq	.Lno_insw_2
+
+		ldr	r3, [r0]
+		and	r3, r3, ip
+		ldr	r4, [r0]
+		orr	r3, r3, r4, lsl #16
+
+		str	r3, [r1], #4
+
+.Lno_insw_2:	tst	r2, #1
+		ldrne	r3, [r0]
+		strneb	r3, [r1], #1
+		movne	r3, r3, lsr #8
+		strneb	r3, [r1]
+
+		ldmfd	sp!, {r4, r5, r6, pc}
+
+
diff --git a/arch/arm/lib/io-writesw-armv3.S b/arch/arm/lib/io-writesw-armv3.S
new file mode 100644
index 00000000000..49b800419e3
--- /dev/null
+++ b/arch/arm/lib/io-writesw-armv3.S
@@ -0,0 +1,126 @@
+/*
+ *  linux/arch/arm/lib/io-writesw-armv3.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+.Loutsw_bad_alignment:
+		adr	r0, .Loutsw_bad_align_msg
+		mov	r2, lr
+		b	panic
+.Loutsw_bad_align_msg:
+		.asciz	"outsw: bad buffer alignment (0x%p, lr=0x%08lX)\n"
+		.align
+
+.Loutsw_align:	tst	r1, #1
+		bne	.Loutsw_bad_alignment
+
+		add	r1, r1, #2
+
+		ldr	r3, [r1, #-4]
+		mov	r3, r3, lsr #16
+		orr	r3, r3, r3, lsl #16
+		str	r3, [r0]
+		subs	r2, r2, #1
+		moveq	pc, lr
+
+ENTRY(__raw_writesw)
+		teq	r2, #0		@ do we have to check for the zero len?
+		moveq	pc, lr
+		tst	r1, #3
+		bne	.Loutsw_align
+
+		stmfd	sp!, {r4, r5, r6, lr}
+
+		subs	r2, r2, #8
+		bmi	.Lno_outsw_8
+
+.Loutsw_8_lp:	ldmia	r1!, {r3, r4, r5, r6}
+
+		mov	ip, r3, lsl #16
+		orr	ip, ip, ip, lsr #16
+		str	ip, [r0]
+
+		mov	ip, r3, lsr #16
+		orr	ip, ip, ip, lsl #16
+		str	ip, [r0]
+
+		mov	ip, r4, lsl #16
+		orr	ip, ip, ip, lsr #16
+		str	ip, [r0]
+
+		mov	ip, r4, lsr #16
+		orr	ip, ip, ip, lsl #16
+		str	ip, [r0]
+
+		mov	ip, r5, lsl #16
+		orr	ip, ip, ip, lsr #16
+		str	ip, [r0]
+
+		mov	ip, r5, lsr #16
+		orr	ip, ip, ip, lsl #16
+		str	ip, [r0]
+
+		mov	ip, r6, lsl #16
+		orr	ip, ip, ip, lsr #16
+		str	ip, [r0]
+
+		mov	ip, r6, lsr #16
+		orr	ip, ip, ip, lsl #16
+		str	ip, [r0]
+
+		subs	r2, r2, #8
+		bpl	.Loutsw_8_lp
+
+		tst	r2, #7
+		ldmeqfd	sp!, {r4, r5, r6, pc}
+
+.Lno_outsw_8:	tst	r2, #4
+		beq	.Lno_outsw_4
+
+		ldmia	r1!, {r3, r4}
+
+		mov	ip, r3, lsl #16
+		orr	ip, ip, ip, lsr #16
+		str	ip, [r0]
+
+		mov	ip, r3, lsr #16
+		orr	ip, ip, ip, lsl #16
+		str	ip, [r0]
+
+		mov	ip, r4, lsl #16
+		orr	ip, ip, ip, lsr #16
+		str	ip, [r0]
+
+		mov	ip, r4, lsr #16
+		orr	ip, ip, ip, lsl #16
+		str	ip, [r0]
+
+.Lno_outsw_4:	tst	r2, #2
+		beq	.Lno_outsw_2
+
+		ldr	r3, [r1], #4
+
+		mov	ip, r3, lsl #16
+		orr	ip, ip, ip, lsr #16
+		str	ip, [r0]
+
+		mov	ip, r3, lsr #16
+		orr	ip, ip, ip, lsl #16
+		str	ip, [r0]
+
+.Lno_outsw_2:	tst	r2, #1
+
+		ldrne	r3, [r1]
+
+		movne	ip, r3, lsl #16
+		orrne	ip, ip, ip, lsr #16
+		strne	ip, [r0]
+
+		ldmfd	sp!, {r4, r5, r6, pc}
diff --git a/arch/arm/lib/uaccess.S b/arch/arm/lib/uaccess.S
new file mode 100644
index 00000000000..5c908b1cb8e
--- /dev/null
+++ b/arch/arm/lib/uaccess.S
@@ -0,0 +1,564 @@
+/*
+ *  linux/arch/arm/lib/uaccess.S
+ *
+ *  Copyright (C) 1995, 1996,1997,1998 Russell King
+ *
+ * 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.
+ *
+ *  Routines to block copy data to/from user memory
+ *   These are highly optimised both for the 4k page size
+ *   and for various alignments.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/errno.h>
+#include <asm/domain.h>
+
+		.text
+
+#define PAGE_SHIFT 12
+
+/* Prototype: int __copy_to_user(void *to, const char *from, size_t n)
+ * Purpose  : copy a block to user memory from kernel memory
+ * Params   : to   - user memory
+ *          : from - kernel memory
+ *          : n    - number of bytes to copy
+ * Returns  : Number of bytes NOT copied.
+ */
+
+.Lc2u_dest_not_aligned:
+		rsb	ip, ip, #4
+		cmp	ip, #2
+		ldrb	r3, [r1], #1
+USER(	TUSER(	strb)	r3, [r0], #1)			@ May fault
+		ldrgeb	r3, [r1], #1
+USER(	TUSER(	strgeb) r3, [r0], #1)			@ May fault
+		ldrgtb	r3, [r1], #1
+USER(	TUSER(	strgtb) r3, [r0], #1)			@ May fault
+		sub	r2, r2, ip
+		b	.Lc2u_dest_aligned
+
+ENTRY(__copy_to_user)
+		stmfd	sp!, {r2, r4 - r7, lr}
+		cmp	r2, #4
+		blt	.Lc2u_not_enough
+		ands	ip, r0, #3
+		bne	.Lc2u_dest_not_aligned
+.Lc2u_dest_aligned:
+
+		ands	ip, r1, #3
+		bne	.Lc2u_src_not_aligned
+/*
+ * Seeing as there has to be at least 8 bytes to copy, we can
+ * copy one word, and force a user-mode page fault...
+ */
+
+.Lc2u_0fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.Lc2u_0nowords
+		ldr	r3, [r1], #4
+USER(	TUSER(	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
+		beq	.Lc2u_0fupi
+/*
+ * ip = max no. of bytes to copy before needing another "strt" insn
+ */
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #32
+		blt	.Lc2u_0rem8lp
+
+.Lc2u_0cpy8lp:	ldmia	r1!, {r3 - r6}
+		stmia	r0!, {r3 - r6}			@ Shouldnt fault
+		ldmia	r1!, {r3 - r6}
+		subs	ip, ip, #32
+		stmia	r0!, {r3 - r6}			@ Shouldnt fault
+		bpl	.Lc2u_0cpy8lp
+
+.Lc2u_0rem8lp:	cmn	ip, #16
+		ldmgeia	r1!, {r3 - r6}
+		stmgeia	r0!, {r3 - r6}			@ Shouldnt fault
+		tst	ip, #8
+		ldmneia	r1!, {r3 - r4}
+		stmneia	r0!, {r3 - r4}			@ Shouldnt fault
+		tst	ip, #4
+		ldrne	r3, [r1], #4
+	TUSER(	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(	TUSER(	strb)	r3, [r0], #1)			@ May fault
+		ldrgeb	r3, [r1], #1
+USER(	TUSER(	strgeb) r3, [r0], #1)			@ May fault
+		ldrgtb	r3, [r1], #1
+USER(	TUSER(	strgtb) r3, [r0], #1)			@ May fault
+		b	.Lc2u_finished
+
+.Lc2u_not_enough:
+		movs	ip, r2
+		bne	.Lc2u_nowords
+.Lc2u_finished:	mov	r0, #0
+		ldmfd	sp!, {r2, r4 - r7, pc}
+
+.Lc2u_src_not_aligned:
+		bic	r1, r1, #3
+		ldr	r7, [r1], #4
+		cmp	ip, #2
+		bgt	.Lc2u_3fupi
+		beq	.Lc2u_2fupi
+.Lc2u_1fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.Lc2u_1nowords
+		mov	r3, r7, pull #8
+		ldr	r7, [r1], #4
+		orr	r3, r3, r7, push #24
+USER(	TUSER(	str)	r3, [r0], #4)			@ May fault
+		mov	ip, r0, lsl #32 - PAGE_SHIFT
+		rsb	ip, ip, #0
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.Lc2u_1fupi
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #16
+		blt	.Lc2u_1rem8lp
+
+.Lc2u_1cpy8lp:	mov	r3, r7, pull #8
+		ldmia	r1!, {r4 - r7}
+		subs	ip, ip, #16
+		orr	r3, r3, r4, push #24
+		mov	r4, r4, pull #8
+		orr	r4, r4, r5, push #24
+		mov	r5, r5, pull #8
+		orr	r5, r5, r6, push #24
+		mov	r6, r6, pull #8
+		orr	r6, r6, r7, push #24
+		stmia	r0!, {r3 - r6}			@ Shouldnt fault
+		bpl	.Lc2u_1cpy8lp
+
+.Lc2u_1rem8lp:	tst	ip, #8
+		movne	r3, r7, pull #8
+		ldmneia	r1!, {r4, r7}
+		orrne	r3, r3, r4, push #24
+		movne	r4, r4, pull #8
+		orrne	r4, r4, r7, push #24
+		stmneia	r0!, {r3 - r4}			@ Shouldnt fault
+		tst	ip, #4
+		movne	r3, r7, pull #8
+		ldrne	r7, [r1], #4
+		orrne	r3, r3, r7, push #24
+	TUSER(	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(	TUSER(	strb)	r3, [r0], #1)			@ May fault
+		movge	r3, r7, get_byte_2
+USER(	TUSER(	strgeb) r3, [r0], #1)			@ May fault
+		movgt	r3, r7, get_byte_3
+USER(	TUSER(	strgtb) r3, [r0], #1)			@ May fault
+		b	.Lc2u_finished
+
+.Lc2u_2fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.Lc2u_2nowords
+		mov	r3, r7, pull #16
+		ldr	r7, [r1], #4
+		orr	r3, r3, r7, push #16
+USER(	TUSER(	str)	r3, [r0], #4)			@ May fault
+		mov	ip, r0, lsl #32 - PAGE_SHIFT
+		rsb	ip, ip, #0
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.Lc2u_2fupi
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #16
+		blt	.Lc2u_2rem8lp
+
+.Lc2u_2cpy8lp:	mov	r3, r7, pull #16
+		ldmia	r1!, {r4 - r7}
+		subs	ip, ip, #16
+		orr	r3, r3, r4, push #16
+		mov	r4, r4, pull #16
+		orr	r4, r4, r5, push #16
+		mov	r5, r5, pull #16
+		orr	r5, r5, r6, push #16
+		mov	r6, r6, pull #16
+		orr	r6, r6, r7, push #16
+		stmia	r0!, {r3 - r6}			@ Shouldnt fault
+		bpl	.Lc2u_2cpy8lp
+
+.Lc2u_2rem8lp:	tst	ip, #8
+		movne	r3, r7, pull #16
+		ldmneia	r1!, {r4, r7}
+		orrne	r3, r3, r4, push #16
+		movne	r4, r4, pull #16
+		orrne	r4, r4, r7, push #16
+		stmneia	r0!, {r3 - r4}			@ Shouldnt fault
+		tst	ip, #4
+		movne	r3, r7, pull #16
+		ldrne	r7, [r1], #4
+		orrne	r3, r3, r7, push #16
+	TUSER(	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(	TUSER(	strb)	r3, [r0], #1)			@ May fault
+		movge	r3, r7, get_byte_3
+USER(	TUSER(	strgeb) r3, [r0], #1)			@ May fault
+		ldrgtb	r3, [r1], #0
+USER(	TUSER(	strgtb) r3, [r0], #1)			@ May fault
+		b	.Lc2u_finished
+
+.Lc2u_3fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.Lc2u_3nowords
+		mov	r3, r7, pull #24
+		ldr	r7, [r1], #4
+		orr	r3, r3, r7, push #8
+USER(	TUSER(	str)	r3, [r0], #4)			@ May fault
+		mov	ip, r0, lsl #32 - PAGE_SHIFT
+		rsb	ip, ip, #0
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.Lc2u_3fupi
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #16
+		blt	.Lc2u_3rem8lp
+
+.Lc2u_3cpy8lp:	mov	r3, r7, pull #24
+		ldmia	r1!, {r4 - r7}
+		subs	ip, ip, #16
+		orr	r3, r3, r4, push #8
+		mov	r4, r4, pull #24
+		orr	r4, r4, r5, push #8
+		mov	r5, r5, pull #24
+		orr	r5, r5, r6, push #8
+		mov	r6, r6, pull #24
+		orr	r6, r6, r7, push #8
+		stmia	r0!, {r3 - r6}			@ Shouldnt fault
+		bpl	.Lc2u_3cpy8lp
+
+.Lc2u_3rem8lp:	tst	ip, #8
+		movne	r3, r7, pull #24
+		ldmneia	r1!, {r4, r7}
+		orrne	r3, r3, r4, push #8
+		movne	r4, r4, pull #24
+		orrne	r4, r4, r7, push #8
+		stmneia	r0!, {r3 - r4}			@ Shouldnt fault
+		tst	ip, #4
+		movne	r3, r7, pull #24
+		ldrne	r7, [r1], #4
+		orrne	r3, r3, r7, push #8
+	TUSER(	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(	TUSER(	strb)	r3, [r0], #1)			@ May fault
+		ldrgeb	r3, [r1], #1
+USER(	TUSER(	strgeb) r3, [r0], #1)			@ May fault
+		ldrgtb	r3, [r1], #0
+USER(	TUSER(	strgtb) r3, [r0], #1)			@ May fault
+		b	.Lc2u_finished
+ENDPROC(__copy_to_user)
+
+		.pushsection .fixup,"ax"
+		.align	0
+9001:		ldmfd	sp!, {r0, r4 - r7, pc}
+		.popsection
+
+/* Prototype: unsigned long __copy_from_user(void *to,const void *from,unsigned long n);
+ * Purpose  : copy a block from user memory to kernel memory
+ * Params   : to   - kernel memory
+ *          : from - user memory
+ *          : n    - number of bytes to copy
+ * Returns  : Number of bytes NOT copied.
+ */
+.Lcfu_dest_not_aligned:
+		rsb	ip, ip, #4
+		cmp	ip, #2
+USER(	TUSER(	ldrb)	r3, [r1], #1)			@ May fault
+		strb	r3, [r0], #1
+USER(	TUSER(	ldrgeb) r3, [r1], #1)			@ May fault
+		strgeb	r3, [r0], #1
+USER(	TUSER(	ldrgtb) r3, [r1], #1)			@ May fault
+		strgtb	r3, [r0], #1
+		sub	r2, r2, ip
+		b	.Lcfu_dest_aligned
+
+ENTRY(__copy_from_user)
+		stmfd	sp!, {r0, r2, r4 - r7, lr}
+		cmp	r2, #4
+		blt	.Lcfu_not_enough
+		ands	ip, r0, #3
+		bne	.Lcfu_dest_not_aligned
+.Lcfu_dest_aligned:
+		ands	ip, r1, #3
+		bne	.Lcfu_src_not_aligned
+
+/*
+ * Seeing as there has to be at least 8 bytes to copy, we can
+ * copy one word, and force a user-mode page fault...
+ */
+
+.Lcfu_0fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.Lcfu_0nowords
+USER(	TUSER(	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
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.Lcfu_0fupi
+/*
+ * ip = max no. of bytes to copy before needing another "strt" insn
+ */
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #32
+		blt	.Lcfu_0rem8lp
+
+.Lcfu_0cpy8lp:	ldmia	r1!, {r3 - r6}			@ Shouldnt fault
+		stmia	r0!, {r3 - r6}
+		ldmia	r1!, {r3 - r6}			@ Shouldnt fault
+		subs	ip, ip, #32
+		stmia	r0!, {r3 - r6}
+		bpl	.Lcfu_0cpy8lp
+
+.Lcfu_0rem8lp:	cmn	ip, #16
+		ldmgeia	r1!, {r3 - r6}			@ Shouldnt fault
+		stmgeia	r0!, {r3 - r6}
+		tst	ip, #8
+		ldmneia	r1!, {r3 - r4}			@ Shouldnt fault
+		stmneia	r0!, {r3 - r4}
+		tst	ip, #4
+	TUSER(	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(	TUSER(	ldrb)	r3, [r1], #1)			@ May fault
+		strb	r3, [r0], #1
+USER(	TUSER(	ldrgeb) r3, [r1], #1)			@ May fault
+		strgeb	r3, [r0], #1
+USER(	TUSER(	ldrgtb) r3, [r1], #1)			@ May fault
+		strgtb	r3, [r0], #1
+		b	.Lcfu_finished
+
+.Lcfu_not_enough:
+		movs	ip, r2
+		bne	.Lcfu_nowords
+.Lcfu_finished:	mov	r0, #0
+		add	sp, sp, #8
+		ldmfd	sp!, {r4 - r7, pc}
+
+.Lcfu_src_not_aligned:
+		bic	r1, r1, #3
+USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
+		cmp	ip, #2
+		bgt	.Lcfu_3fupi
+		beq	.Lcfu_2fupi
+.Lcfu_1fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.Lcfu_1nowords
+		mov	r3, r7, pull #8
+USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
+		orr	r3, r3, r7, push #24
+		str	r3, [r0], #4
+		mov	ip, r1, lsl #32 - PAGE_SHIFT
+		rsb	ip, ip, #0
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.Lcfu_1fupi
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #16
+		blt	.Lcfu_1rem8lp
+
+.Lcfu_1cpy8lp:	mov	r3, r7, pull #8
+		ldmia	r1!, {r4 - r7}			@ Shouldnt fault
+		subs	ip, ip, #16
+		orr	r3, r3, r4, push #24
+		mov	r4, r4, pull #8
+		orr	r4, r4, r5, push #24
+		mov	r5, r5, pull #8
+		orr	r5, r5, r6, push #24
+		mov	r6, r6, pull #8
+		orr	r6, r6, r7, push #24
+		stmia	r0!, {r3 - r6}
+		bpl	.Lcfu_1cpy8lp
+
+.Lcfu_1rem8lp:	tst	ip, #8
+		movne	r3, r7, pull #8
+		ldmneia	r1!, {r4, r7}			@ Shouldnt fault
+		orrne	r3, r3, r4, push #24
+		movne	r4, r4, pull #8
+		orrne	r4, r4, r7, push #24
+		stmneia	r0!, {r3 - r4}
+		tst	ip, #4
+		movne	r3, r7, pull #8
+USER(	TUSER(	ldrne) r7, [r1], #4)			@ May fault
+		orrne	r3, r3, r7, push #24
+		strne	r3, [r0], #4
+		ands	ip, ip, #3
+		beq	.Lcfu_1fupi
+.Lcfu_1nowords:	mov	r3, r7, get_byte_1
+		teq	ip, #0
+		beq	.Lcfu_finished
+		cmp	ip, #2
+		strb	r3, [r0], #1
+		movge	r3, r7, get_byte_2
+		strgeb	r3, [r0], #1
+		movgt	r3, r7, get_byte_3
+		strgtb	r3, [r0], #1
+		b	.Lcfu_finished
+
+.Lcfu_2fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.Lcfu_2nowords
+		mov	r3, r7, pull #16
+USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
+		orr	r3, r3, r7, push #16
+		str	r3, [r0], #4
+		mov	ip, r1, lsl #32 - PAGE_SHIFT
+		rsb	ip, ip, #0
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.Lcfu_2fupi
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #16
+		blt	.Lcfu_2rem8lp
+
+
+.Lcfu_2cpy8lp:	mov	r3, r7, pull #16
+		ldmia	r1!, {r4 - r7}			@ Shouldnt fault
+		subs	ip, ip, #16
+		orr	r3, r3, r4, push #16
+		mov	r4, r4, pull #16
+		orr	r4, r4, r5, push #16
+		mov	r5, r5, pull #16
+		orr	r5, r5, r6, push #16
+		mov	r6, r6, pull #16
+		orr	r6, r6, r7, push #16
+		stmia	r0!, {r3 - r6}
+		bpl	.Lcfu_2cpy8lp
+
+.Lcfu_2rem8lp:	tst	ip, #8
+		movne	r3, r7, pull #16
+		ldmneia	r1!, {r4, r7}			@ Shouldnt fault
+		orrne	r3, r3, r4, push #16
+		movne	r4, r4, pull #16
+		orrne	r4, r4, r7, push #16
+		stmneia	r0!, {r3 - r4}
+		tst	ip, #4
+		movne	r3, r7, pull #16
+USER(	TUSER(	ldrne) r7, [r1], #4)			@ May fault
+		orrne	r3, r3, r7, push #16
+		strne	r3, [r0], #4
+		ands	ip, ip, #3
+		beq	.Lcfu_2fupi
+.Lcfu_2nowords:	mov	r3, r7, get_byte_2
+		teq	ip, #0
+		beq	.Lcfu_finished
+		cmp	ip, #2
+		strb	r3, [r0], #1
+		movge	r3, r7, get_byte_3
+		strgeb	r3, [r0], #1
+USER(	TUSER(	ldrgtb) r3, [r1], #0)			@ May fault
+		strgtb	r3, [r0], #1
+		b	.Lcfu_finished
+
+.Lcfu_3fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.Lcfu_3nowords
+		mov	r3, r7, pull #24
+USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
+		orr	r3, r3, r7, push #8
+		str	r3, [r0], #4
+		mov	ip, r1, lsl #32 - PAGE_SHIFT
+		rsb	ip, ip, #0
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.Lcfu_3fupi
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #16
+		blt	.Lcfu_3rem8lp
+
+.Lcfu_3cpy8lp:	mov	r3, r7, pull #24
+		ldmia	r1!, {r4 - r7}			@ Shouldnt fault
+		orr	r3, r3, r4, push #8
+		mov	r4, r4, pull #24
+		orr	r4, r4, r5, push #8
+		mov	r5, r5, pull #24
+		orr	r5, r5, r6, push #8
+		mov	r6, r6, pull #24
+		orr	r6, r6, r7, push #8
+		stmia	r0!, {r3 - r6}
+		subs	ip, ip, #16
+		bpl	.Lcfu_3cpy8lp
+
+.Lcfu_3rem8lp:	tst	ip, #8
+		movne	r3, r7, pull #24
+		ldmneia	r1!, {r4, r7}			@ Shouldnt fault
+		orrne	r3, r3, r4, push #8
+		movne	r4, r4, pull #24
+		orrne	r4, r4, r7, push #8
+		stmneia	r0!, {r3 - r4}
+		tst	ip, #4
+		movne	r3, r7, pull #24
+USER(	TUSER(	ldrne) r7, [r1], #4)			@ May fault
+		orrne	r3, r3, r7, push #8
+		strne	r3, [r0], #4
+		ands	ip, ip, #3
+		beq	.Lcfu_3fupi
+.Lcfu_3nowords:	mov	r3, r7, get_byte_3
+		teq	ip, #0
+		beq	.Lcfu_finished
+		cmp	ip, #2
+		strb	r3, [r0], #1
+USER(	TUSER(	ldrgeb) r3, [r1], #1)			@ May fault
+		strgeb	r3, [r0], #1
+USER(	TUSER(	ldrgtb) r3, [r1], #1)			@ May fault
+		strgtb	r3, [r0], #1
+		b	.Lcfu_finished
+ENDPROC(__copy_from_user)
+
+		.pushsection .fixup,"ax"
+		.align	0
+		/*
+		 * We took an exception.  r0 contains a pointer to
+		 * the byte not copied.
+		 */
+9001:		ldr	r2, [sp], #4			@ void *to
+		sub	r2, r0, r2			@ bytes copied
+		ldr	r1, [sp], #4			@ unsigned long count
+		subs	r4, r1, r2			@ bytes left to copy
+		movne	r1, r4
+		blne	__memzero
+		mov	r0, r4
+		ldmfd	sp!, {r4 - r7, pc}
+		.popsection
+
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 77458548e03..40ca11ed6e5 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -231,8 +231,6 @@ void __sync_icache_dcache(pte_t pteval)
 	struct page *page;
 	struct address_space *mapping;
 
-	if (!pte_present_user(pteval))
-		return;
 	if (cache_is_vipt_nonaliasing() && !pte_exec(pteval))
 		/* only flush non-aliasing VIPT caches for exec mappings */
 		return;
diff --git a/arch/arm/mm/tlb-v7.S b/arch/arm/mm/tlb-v7.S
index c2021139cb5..ea94765acf9 100644
--- a/arch/arm/mm/tlb-v7.S
+++ b/arch/arm/mm/tlb-v7.S
@@ -38,10 +38,10 @@ ENTRY(v7wbi_flush_user_tlb_range)
 	dsb
 	mov	r0, r0, lsr #PAGE_SHIFT		@ align address
 	mov	r1, r1, lsr #PAGE_SHIFT
-#ifdef CONFIG_ARM_ERRATA_720789
-	mov	r3, #0
-#else
 	asid	r3, r3				@ mask ASID
+#ifdef CONFIG_ARM_ERRATA_720789
+	ALT_SMP(W(mov)	r3, #0	)
+	ALT_UP(W(nop)		)
 #endif
 	orr	r0, r3, r0, lsl #PAGE_SHIFT	@ Create initial MVA
 	mov	r1, r1, lsl #PAGE_SHIFT
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index fb849d044bd..c834b32af27 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -719,8 +719,10 @@ static int __init vfp_init(void)
 			if ((fmrx(MVFR1) & 0x000fff00) == 0x00011100)
 				elf_hwcap |= HWCAP_NEON;
 #endif
+#ifdef CONFIG_VFPv3
 			if ((fmrx(MVFR1) & 0xf0000000) == 0x10000000)
 				elf_hwcap |= HWCAP_VFPv4;
+#endif
 		}
 	}
 	return 0;