ARM: mm: use inner-shareable barriers for TLB and user cache operations

System-wide barriers aren't required for situations where we only need
to make visibility and ordering guarantees in the inner-shareable domain
(i.e. we are not dealing with devices or potentially incoherent CPUs).

This patch changes the v7 TLB operations, coherent_user_range and
dcache_clean_area functions to user inner-shareable barriers. For cache
maintenance, only the store access type is required to ensure completion.

Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>

3 files changed, 7 insertions, 7 deletions

diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 515b00064da8..b5c467a65c27 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -282,7 +282,7 @@ ENTRY(v7_coherent_user_range)
         add     r12, r12, r2
         cmp     r12, r1
         blo     1b
-        dsb
+        dsb     ishst
         icache_line_size r2, r3
         sub     r3, r2, #1
         bic     r12, r0, r3
@@ -294,7 +294,7 @@ ENTRY(v7_coherent_user_range)
         mov     r0, #0
         ALT_SMP(mcr     p15, 0, r0, c7, c1, 6)  @ invalidate BTB Inner Shareable
         ALT_UP(mcr      p15, 0, r0, c7, c5, 6)  @ invalidate BTB
-        dsb
+        dsb     ishst
         isb
         mov     pc, lr
 
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 73398bcf9bd8..0b5462a941a6 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -83,7 +83,7 @@ ENTRY(cpu_v7_dcache_clean_area)
         add     r0, r0, r2
         subs    r1, r1, r2
         bhi     2b
-        dsb
+        dsb     ishst
         mov     pc, lr
 ENDPROC(cpu_v7_dcache_clean_area)
 
diff --git a/arch/arm/mm/tlb-v7.S b/arch/arm/mm/tlb-v7.S
index ea94765acf9a..355308767bae 100644
--- a/arch/arm/mm/tlb-v7.S
+++ b/arch/arm/mm/tlb-v7.S
@@ -35,7 +35,7 @@
 ENTRY(v7wbi_flush_user_tlb_range)
         vma_vm_mm r3, r2                        @ get vma->vm_mm
         mmid    r3, r3                          @ get vm_mm->context.id
-        dsb
+        dsb     ish
         mov     r0, r0, lsr #PAGE_SHIFT         @ align address
         mov     r1, r1, lsr #PAGE_SHIFT
         asid    r3, r3                          @ mask ASID
@@ -56,7 +56,7 @@ ENTRY(v7wbi_flush_user_tlb_range)
         add     r0, r0, #PAGE_SZ
         cmp     r0, r1
         blo     1b
-        dsb
+        dsb     ish
         mov     pc, lr
 ENDPROC(v7wbi_flush_user_tlb_range)
 
@@ -69,7 +69,7 @@ ENDPROC(v7wbi_flush_user_tlb_range)
  *      - end   - end address (exclusive, may not be aligned)
  */
 ENTRY(v7wbi_flush_kern_tlb_range)
-        dsb
+        dsb     ish
         mov     r0, r0, lsr #PAGE_SHIFT         @ align address
         mov     r1, r1, lsr #PAGE_SHIFT
         mov     r0, r0, lsl #PAGE_SHIFT
@@ -84,7 +84,7 @@ ENTRY(v7wbi_flush_kern_tlb_range)
         add     r0, r0, #PAGE_SZ
         cmp     r0, r1
         blo     1b
-        dsb
+        dsb     ish
         isb
         mov     pc, lr
 ENDPROC(v7wbi_flush_kern_tlb_range)