arm64: cacheinfo: Update cache_line_size detected from DT or PPTT

cache_line_size is derived from CTR_EL0.CWG field and is called mostly
for I/O device drivers. For some platforms like the HiSilicon Kunpeng920
server SoC, cache line sizes are different between L1/2 cache and L3
cache while L1 cache line size is 64-byte and L3 is 128-byte, but
CTR_EL0.CWG is misreporting using L1 cache line size.

We shall correct the right value which is important for I/O performance.
Let's update the cache line size if it is detected from DT or PPTT
information.

Cc: Will Deacon <will.deacon@arm.com>
Cc: Jeremy Linton <jeremy.linton@arm.com>
Cc: Zhenfa Qiu <qiuzhenfa@hisilicon.com>
Reported-by: Zhenfa Qiu <qiuzhenfa@hisilicon.com>
Suggested-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Shaokun Zhang <zhangshaokun@hisilicon.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm64/include/asm/cache.h

@@ -91,11 +91,7 @@ static inline u32 cache_type_cwg(void)
 
 #define __read_mostly __attribute__((__section__(".data..read_mostly")))
 
-static inline int cache_line_size(void)
-{
-	u32 cwg = cache_type_cwg();
-	return cwg ? 4 << cwg : ARCH_DMA_MINALIGN;
-}
+int cache_line_size(void);
 
 /*
  * Read the effective value of CTR_EL0.

arch/arm64/kernel/cacheinfo.c

@@ -28,6 +28,17 @@
 #define CLIDR_CTYPE(clidr, level)	\
 	(((clidr) & CLIDR_CTYPE_MASK(level)) >> CLIDR_CTYPE_SHIFT(level))
 
+int cache_line_size(void)
+{
+	u32 cwg = cache_type_cwg();
+
+	if (coherency_max_size != 0)
+		return coherency_max_size;
+
+	return cwg ? 4 << cwg : ARCH_DMA_MINALIGN;
+}
+EXPORT_SYMBOL_GPL(cache_line_size);
+
 static inline enum cache_type get_cache_type(int level)
 {
 	u64 clidr;