diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index 5d3ed7e38561dd43553d1d3bf1b2af07e0d2b747..314d4664eae7d9976a5fe656f74918cb8d15ab8b 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -198,7 +198,15 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 	unsigned long addr)
 {
 	pgtable_page_dtor(pte);
-	tlb_add_flush(tlb, addr);
+
+	/*
+	 * With the classic ARM MMU, a pte page has two corresponding pmd
+	 * entries, each covering 1MB.
+	 */
+	addr &= PMD_MASK;
+	tlb_add_flush(tlb, addr + SZ_1M - PAGE_SIZE);
+	tlb_add_flush(tlb, addr + SZ_1M);
+
 	tlb_remove_page(tlb, pte);
 }
 
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 3a456c6c70056f9267f592792193d2176c045802..be16a48007b4b79fc5db0d3e48b016242b68d760 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -790,7 +790,7 @@ __kuser_cmpxchg64:				@ 0xffff0f60
 	smp_dmb	arm
 	rsbs	r0, r3, #0			@ set returned val and C flag
 	ldmfd	sp!, {r4, r5, r6, r7}
-	bx	lr
+	usr_ret	lr
 
 #elif !defined(CONFIG_SMP)
 
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 460bbbb6b88536ba18ded4983b6ee18baf1a4bf4..6933244c68f964ffed73f11cfbdaac1ca13b2f74 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -469,6 +469,20 @@ static const unsigned armv7_a5_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
 		},
 	},
+	[C(NODE)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
 };
 
 /*
@@ -579,6 +593,20 @@ static const unsigned armv7_a15_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
 		},
 	},
+	[C(NODE)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
 };
 
 /*
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index e1d5e1929fbd6a36e9266a2c4d254cba5060e438..e33870ff0ac092b25e31a49e3074899ee0ac6339 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -699,10 +699,13 @@ static int vfp_set(struct task_struct *target,
 {
 	int ret;
 	struct thread_info *thread = task_thread_info(target);
-	struct vfp_hard_struct new_vfp = thread->vfpstate.hard;
+	struct vfp_hard_struct new_vfp;
 	const size_t user_fpregs_offset = offsetof(struct user_vfp, fpregs);
 	const size_t user_fpscr_offset = offsetof(struct user_vfp, fpscr);
 
+	vfp_sync_hwstate(thread);
+	new_vfp = thread->vfpstate.hard;
+
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 				  &new_vfp.fpregs,
 				  user_fpregs_offset,
@@ -723,9 +726,8 @@ static int vfp_set(struct task_struct *target,
 	if (ret)
 		return ret;
 
-	vfp_sync_hwstate(thread);
-	thread->vfpstate.hard = new_vfp;
 	vfp_flush_hwstate(thread);
+	thread->vfpstate.hard = new_vfp;
 
 	return 0;
 }
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 0340224cf73c5c9db2d16185bd698a6ba6518fb8..9e617bd4a146250d7d3f453d50a45431fa261e08 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -227,6 +227,8 @@ static int restore_vfp_context(struct vfp_sigframe __user *frame)
 	if (magic != VFP_MAGIC || size != VFP_STORAGE_SIZE)
 		return -EINVAL;
 
+	vfp_flush_hwstate(thread);
+
 	/*
 	 * Copy the floating point registers. There can be unused
 	 * registers see asm/hwcap.h for details.
@@ -251,9 +253,6 @@ static int restore_vfp_context(struct vfp_sigframe __user *frame)
 	__get_user_error(h->fpinst, &frame->ufp_exc.fpinst, err);
 	__get_user_error(h->fpinst2, &frame->ufp_exc.fpinst2, err);
 
-	if (!err)
-		vfp_flush_hwstate(thread);
-
 	return err ? -EFAULT : 0;
 }
 
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index ba159370fa5f710633d6b00a078c23bc40ad6f6a..80632e8d7538f33d5a6539df5a72a90fff52e7ec 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -225,8 +225,7 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
 		if ((area->flags & VM_ARM_MTYPE_MASK) != VM_ARM_MTYPE(mtype))
 			continue;
 		if (__phys_to_pfn(area->phys_addr) > pfn ||
-		    __pfn_to_phys(pfn) + offset + size-1 >
-		    area->phys_addr + area->size-1)
+		    __pfn_to_phys(pfn) + size-1 > area->phys_addr + area->size-1)
 			continue;
 		/* we can drop the lock here as we know *area is static */
 		read_unlock(&vmlist_lock);