1 files changed, 42 insertions, 6 deletions

diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 3b172275262e..cd956647c21a 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -33,6 +33,24 @@ ENTRY(v7_flush_icache_all)
         mov     pc, lr
 ENDPROC(v7_flush_icache_all)
 
+ /*
+ *     v7_flush_dcache_louis()
+ *
+ *     Flush the D-cache up to the Level of Unification Inner Shareable
+ *
+ *     Corrupted registers: r0-r7, r9-r11 (r6 only in Thumb mode)
+ */
+
+ENTRY(v7_flush_dcache_louis)
+        dmb                                     @ ensure ordering with previous memory accesses
+        mrc     p15, 1, r0, c0, c0, 1           @ read clidr, r0 = clidr
+        ands    r3, r0, #0xe00000               @ extract LoUIS from clidr
+        mov     r3, r3, lsr #20                 @ r3 = LoUIS * 2
+        moveq   pc, lr                          @ return if level == 0
+        mov     r10, #0                         @ r10 (starting level) = 0
+        b       flush_levels                    @ start flushing cache levels
+ENDPROC(v7_flush_dcache_louis)
+
 /*
  *      v7_flush_dcache_all()
  *
@@ -49,7 +67,7 @@ ENTRY(v7_flush_dcache_all)
         mov     r3, r3, lsr #23                 @ left align loc bit field
         beq     finished                        @ if loc is 0, then no need to clean
         mov     r10, #0                         @ start clean at cache level 0
-loop1:
+flush_levels:
         add     r2, r10, r10, lsr #1            @ work out 3x current cache level
         mov     r1, r0, lsr r2                  @ extract cache type bits from clidr
         and     r1, r1, #7                      @ mask of the bits for current cache only
@@ -71,9 +89,9 @@ loop1:
         clz     r5, r4                          @ find bit position of way size increment
         ldr     r7, =0x7fff
         ands    r7, r7, r1, lsr #13             @ extract max number of the index size
-loop2:
+loop1:
         mov     r9, r4                          @ create working copy of max way size
-loop3:
+loop2:
  ARM(   orr     r11, r10, r9, lsl r5    )       @ factor way and cache number into r11
  THUMB( lsl     r6, r9, r5              )
  THUMB( orr     r11, r10, r6            )       @ factor way and cache number into r11
@@ -82,13 +100,13 @@ loop3:
  THUMB( orr     r11, r11, r6            )       @ factor index number into r11
         mcr     p15, 0, r11, c7, c14, 2         @ clean & invalidate by set/way
         subs    r9, r9, #1                      @ decrement the way
-        bge     loop3
-        subs    r7, r7, #1                      @ decrement the index
         bge     loop2
+        subs    r7, r7, #1                      @ decrement the index
+        bge     loop1
 skip:
         add     r10, r10, #2                    @ increment cache number
         cmp     r3, r10
-        bgt     loop1
+        bgt     flush_levels
 finished:
         mov     r10, #0                         @ swith back to cache level 0
         mcr     p15, 2, r10, c0, c0, 0          @ select current cache level in cssr
@@ -120,6 +138,24 @@ ENTRY(v7_flush_kern_cache_all)
         mov     pc, lr
 ENDPROC(v7_flush_kern_cache_all)
 
+ /*
+ *     v7_flush_kern_cache_louis(void)
+ *
+ *     Flush the data cache up to Level of Unification Inner Shareable.
+ *     Invalidate the I-cache to the point of unification.
+ */
+ENTRY(v7_flush_kern_cache_louis)
+ ARM(   stmfd   sp!, {r4-r5, r7, r9-r11, lr}    )
+ THUMB( stmfd   sp!, {r4-r7, r9-r11, lr}        )
+        bl      v7_flush_dcache_louis
+        mov     r0, #0
+        ALT_SMP(mcr     p15, 0, r0, c7, c1, 0)  @ invalidate I-cache inner shareable
+        ALT_UP(mcr      p15, 0, r0, c7, c5, 0)  @ I+BTB cache invalidate
+ ARM(   ldmfd   sp!, {r4-r5, r7, r9-r11, lr}    )
+ THUMB( ldmfd   sp!, {r4-r7, r9-r11, lr}        )
+        mov     pc, lr
+ENDPROC(v7_flush_kern_cache_louis)
+
 /*
  *      v7_flush_cache_all()
  *