Add a DSB after the TLB operations

The architecture specification states that TLB operations are
guaranteed to be complete only after the execution of a DSB (Data
Synchronisation Barrier, former Data Write Barrier or Drain Write
Buffer).
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm/mm/tlb-v6.S

@@ -53,6 +53,8 @@ ENTRY(v6wbi_flush_user_tlb_range)
 	add	r0, r0, #PAGE_SZ
 	cmp	r0, r1
 	blo	1b
+	mcr	p15, 0, ip, c7, c5, 6		@ flush BTAC/BTB
+	mcr	p15, 0, ip, c7, c10, 4		@ data synchronization barrier
 	mov	pc, lr
 
 /*
@@ -80,7 +82,9 @@ ENTRY(v6wbi_flush_kern_tlb_range)
 	add	r0, r0, #PAGE_SZ
 	cmp	r0, r1
 	blo	1b
+	mcr	p15, 0, r2, c7, c5, 6		@ flush BTAC/BTB
 	mcr	p15, 0, r2, c7, c10, 4		@ data synchronization barrier
+	mcr	p15, 0, r2, c7, c5, 4		@ prefetch flush
 	mov	pc, lr
 
 	.section ".text.init", #alloc, #execinstr

include/asm-arm/tlbflush.h

@@ -247,7 +247,7 @@ static inline void local_flush_tlb_all(void)
 	const unsigned int __tlb_flag = __cpu_tlb_flags;
 
 	if (tlb_flag(TLB_WB))
-		asm("mcr p15, 0, %0, c7, c10, 4" : : "r" (zero) : "cc");
+		dsb();
 
 	if (tlb_flag(TLB_V3_FULL))
 		asm("mcr p15, 0, %0, c6, c0, 0" : : "r" (zero) : "cc");
@@ -257,6 +257,15 @@ static inline void local_flush_tlb_all(void)
 		asm("mcr p15, 0, %0, c8, c6, 0" : : "r" (zero) : "cc");
 	if (tlb_flag(TLB_V4_I_FULL | TLB_V6_I_FULL))
 		asm("mcr p15, 0, %0, c8, c5, 0" : : "r" (zero) : "cc");
+
+	if (tlb_flag(TLB_V6_I_FULL | TLB_V6_D_FULL |
+		     TLB_V6_I_PAGE | TLB_V6_D_PAGE |
+		     TLB_V6_I_ASID | TLB_V6_D_ASID)) {
+		/* flush the branch target cache */
+		asm("mcr p15, 0, %0, c7, c5, 6" : : "r" (zero) : "cc");
+		dsb();
+		isb();
+	}
 }
 
 static inline void local_flush_tlb_mm(struct mm_struct *mm)
@@ -266,7 +275,7 @@ static inline void local_flush_tlb_mm(struct mm_struct *mm)
 	const unsigned int __tlb_flag = __cpu_tlb_flags;
 
 	if (tlb_flag(TLB_WB))
-		asm("mcr p15, 0, %0, c7, c10, 4" : : "r" (zero) : "cc");
+		dsb();
 
 	if (cpu_isset(smp_processor_id(), mm->cpu_vm_mask)) {
 		if (tlb_flag(TLB_V3_FULL))
@@ -285,6 +294,14 @@ static inline void local_flush_tlb_mm(struct mm_struct *mm)
 		asm("mcr p15, 0, %0, c8, c6, 2" : : "r" (asid) : "cc");
 	if (tlb_flag(TLB_V6_I_ASID))
 		asm("mcr p15, 0, %0, c8, c5, 2" : : "r" (asid) : "cc");
+
+	if (tlb_flag(TLB_V6_I_FULL | TLB_V6_D_FULL |
+		     TLB_V6_I_PAGE | TLB_V6_D_PAGE |
+		     TLB_V6_I_ASID | TLB_V6_D_ASID)) {
+		/* flush the branch target cache */
+		asm("mcr p15, 0, %0, c7, c5, 6" : : "r" (zero) : "cc");
+		dsb();
+	}
 }
 
 static inline void
@@ -296,7 +313,7 @@ local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 	uaddr = (uaddr & PAGE_MASK) | ASID(vma->vm_mm);
 
 	if (tlb_flag(TLB_WB))
-		asm("mcr p15, 0, %0, c7, c10, 4" : : "r" (zero));
+		dsb();
 
 	if (cpu_isset(smp_processor_id(), vma->vm_mm->cpu_vm_mask)) {
 		if (tlb_flag(TLB_V3_PAGE))
@@ -317,6 +334,14 @@ local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 		asm("mcr p15, 0, %0, c8, c6, 1" : : "r" (uaddr) : "cc");
 	if (tlb_flag(TLB_V6_I_PAGE))
 		asm("mcr p15, 0, %0, c8, c5, 1" : : "r" (uaddr) : "cc");
+
+	if (tlb_flag(TLB_V6_I_FULL | TLB_V6_D_FULL |
+		     TLB_V6_I_PAGE | TLB_V6_D_PAGE |
+		     TLB_V6_I_ASID | TLB_V6_D_ASID)) {
+		/* flush the branch target cache */
+		asm("mcr p15, 0, %0, c7, c5, 6" : : "r" (zero) : "cc");
+		dsb();
+	}
 }
 
 static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
@@ -327,7 +352,7 @@ static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
 	kaddr &= PAGE_MASK;
 
 	if (tlb_flag(TLB_WB))
-		asm("mcr p15, 0, %0, c7, c10, 4" : : "r" (zero) : "cc");
+		dsb();
 
 	if (tlb_flag(TLB_V3_PAGE))
 		asm("mcr p15, 0, %0, c6, c0, 0" : : "r" (kaddr) : "cc");
@@ -347,11 +372,14 @@ static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
 	if (tlb_flag(TLB_V6_I_PAGE))
 		asm("mcr p15, 0, %0, c8, c5, 1" : : "r" (kaddr) : "cc");
 
-	/* The ARM ARM states that the completion of a TLB maintenance
-	 * operation is only guaranteed by a DSB instruction
-	 */
-	if (tlb_flag(TLB_V6_U_PAGE | TLB_V6_D_PAGE | TLB_V6_I_PAGE))
-		asm("mcr p15, 0, %0, c7, c10, 4" : : "r" (zero) : "cc");
+	if (tlb_flag(TLB_V6_I_FULL | TLB_V6_D_FULL |
+		     TLB_V6_I_PAGE | TLB_V6_D_PAGE |
+		     TLB_V6_I_ASID | TLB_V6_D_ASID)) {
+		/* flush the branch target cache */
+		asm("mcr p15, 0, %0, c7, c5, 6" : : "r" (zero) : "cc");
+		dsb();
+		isb();
+	}
 }
 
 /*
@@ -369,15 +397,13 @@ static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
  */
 static inline void flush_pmd_entry(pmd_t *pmd)
 {
-	const unsigned int zero = 0;
 	const unsigned int __tlb_flag = __cpu_tlb_flags;
 
 	if (tlb_flag(TLB_DCLEAN))
 		asm("mcr	p15, 0, %0, c7, c10, 1	@ flush_pmd"
 			: : "r" (pmd) : "cc");
 	if (tlb_flag(TLB_WB))
-		asm("mcr	p15, 0, %0, c7, c10, 4	@ flush_pmd"
-			: : "r" (zero) : "cc");
+		dsb();
 }
 
 static inline void clean_pmd_entry(pmd_t *pmd)