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

* 'fixes' of git://git.linaro.org/people/rmk/linux-arm:
  ARM: 7314/1: kuser: consistently use usr_ret for returning from helpers
  ARM: 7302/1: Add TLB flushing for both entries in a PMD
  ARM: 7303/1: perf: add empty NODE event definitions for Cortex-A5 and Cortex-A15
  ARM: 7308/1: vfp: flush thread hwstate before copying ptrace registers
  ARM: 7307/1: vfp: fix ptrace regset modification race
  ARM: 7306/1: vfp: flush thread hwstate before restoring context from sigframe
  Revert "ARM: 7304/1: ioremap: fix boundary check when reusing static mapping"

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);
 }
 

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)
 

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,
+		},
+	},
 };
 
 /*

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;
 }

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;
 }
 

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);