ARM: 6528/1: Use CTR for the I-cache line size on ARMv7

The current implementation of the v7_coherent_*_range function assumes
that the D and I cache lines have the same size, which is incorrect
architecturally. This patch adds the icache_line_size macro which reads
the CTR register. The main loop in v7_coherent_*_range is split in two
independent loops or the D and I caches. This also has the performance
advantage that the DSB is moved outside the main loop.

Reported-by: Kevin Sapp <ksapp@quicinc.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

2 files changed, 27 insertions, 10 deletions

diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index a3ebf7a4f49b..6136e68ce953 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -173,15 +173,22 @@ ENTRY(v7_coherent_user_range)
  UNWIND(.fnstart                )
         dcache_line_size r2, r3
         sub     r3, r2, #1
-        bic     r0, r0, r3
+        bic     r12, r0, r3
 1:
- USER(  mcr     p15, 0, r0, c7, c11, 1  )       @ clean D line to the point of unification
+ USER(  mcr     p15, 0, r12, c7, c11, 1 )       @ clean D line to the point of unification
+        add     r12, r12, r2
+        cmp     r12, r1
+        blo     1b
         dsb
- USER(  mcr     p15, 0, r0, c7, c5, 1   )       @ invalidate I line
-        add     r0, r0, r2
+        icache_line_size r2, r3
+        sub     r3, r2, #1
+        bic     r12, r0, r3
 2:
-        cmp     r0, r1
-        blo     1b
+ USER(  mcr     p15, 0, r12, c7, c5, 1  )       @ invalidate I line
+        add     r12, r12, r2
+        cmp     r12, r1
+        blo     2b
+3:
         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
@@ -194,10 +201,10 @@ ENTRY(v7_coherent_user_range)
  * isn't mapped, just try the next page.
  */
 9001:
-        mov     r0, r0, lsr #12
-        mov     r0, r0, lsl #12
-        add     r0, r0, #4096
-        b       2b
+        mov     r12, r12, lsr #12
+        mov     r12, r12, lsl #12
+        add     r12, r12, #4096
+        b       3b
  UNWIND(.fnend          )
 ENDPROC(v7_coherent_kern_range)
 ENDPROC(v7_coherent_user_range)
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index 321555b894d1..b795afd0a2c6 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -72,6 +72,16 @@
         mov     \reg, \reg, lsl \tmp            @ actual cache line size
         .endm
 
+/*
+ * icache_line_size - get the minimum I-cache line size from the CTR register
+ * on ARMv7.
+ */
+        .macro  icache_line_size, reg, tmp
+        mrc     p15, 0, \tmp, c0, c0, 1         @ read ctr
+        and     \tmp, \tmp, #0xf                @ cache line size encoding
+        mov     \reg, #4                        @ bytes per word
+        mov     \reg, \reg, lsl \tmp            @ actual cache line size
+        .endm
 
 /*
  * Sanity check the PTE configuration for the code below - which makes