arm64: Increase ARCH_DMA_MINALIGN to 128

This patch increases the ARCH_DMA_MINALIGN to 128 so that it covers the
currently known Cache Writeback Granule (CTR_EL0.CWG) on arm64 and moves
the fallback in cache_line_size() from L1_CACHE_BYTES to this constant.
In addition, it warns (and taints) if the CWG is larger than
ARCH_DMA_MINALIGN as this is not safe with non-coherent DMA.

Cc: Will Deacon <will.deacon@arm.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm64/include/asm/cache.h

@@ -43,7 +43,7 @@
  * cache before the transfer is done, causing old data to be seen by
  * the CPU.
  */
-#define ARCH_DMA_MINALIGN	L1_CACHE_BYTES
+#define ARCH_DMA_MINALIGN	(128)
 
 #ifndef __ASSEMBLY__
 
@@ -77,7 +77,7 @@ static inline u32 cache_type_cwg(void)
 static inline int cache_line_size(void)
 {
 	u32 cwg = cache_type_cwg();
-	return cwg ? 4 << cwg : L1_CACHE_BYTES;
+	return cwg ? 4 << cwg : ARCH_DMA_MINALIGN;
 }
 
 #endif	/* __ASSEMBLY__ */

arch/arm64/kernel/cpufeature.c

@@ -1606,7 +1606,6 @@ static void __init setup_system_capabilities(void)
 void __init setup_cpu_features(void)
 {
 	u32 cwg;
-	int cls;
 
 	setup_system_capabilities();
 	mark_const_caps_ready();
@@ -1627,13 +1626,9 @@ void __init setup_cpu_features(void)
 	 * Check for sane CTR_EL0.CWG value.
 	 */
 	cwg = cache_type_cwg();
-	cls = cache_line_size();
 	if (!cwg)
-		pr_warn("No Cache Writeback Granule information, assuming cache line size %d\n",
-			cls);
-	if (L1_CACHE_BYTES < cls)
-		pr_warn("L1_CACHE_BYTES smaller than the Cache Writeback Granule (%d < %d)\n",
-			L1_CACHE_BYTES, cls);
+		pr_warn("No Cache Writeback Granule information, assuming %d\n",
+			ARCH_DMA_MINALIGN);
 }
 
 static bool __maybe_unused

arch/arm64/mm/dma-mapping.c

@@ -504,6 +504,11 @@ static int __init arm64_dma_init(void)
 	    max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT))
 		swiotlb = 1;
 
+	WARN_TAINT(ARCH_DMA_MINALIGN < cache_line_size(),
+		   TAINT_CPU_OUT_OF_SPEC,
+		   "ARCH_DMA_MINALIGN smaller than CTR_EL0.CWG (%d < %d)",
+		   ARCH_DMA_MINALIGN, cache_line_size());
+
 	return atomic_pool_init();
 }
 arch_initcall(arm64_dma_init);