xtensa: support DMA to high memory

- don't bugcheck if high memory page is passed to xtensa_map_page;
- turn empty dcache flush macros into functions so that they could be
  passed as function parameters;
- use kmap_atomic to map high memory pages for cache invalidation/
  flushing performed by xtensa_sync_single_for_{cpu,device}.

Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>

arch/xtensa/include/asm/cacheflush.h

@@ -55,8 +55,13 @@ extern void __flush_dcache_range(unsigned long, unsigned long);
 extern void __flush_invalidate_dcache_page(unsigned long);
 extern void __flush_invalidate_dcache_range(unsigned long, unsigned long);
 #else
-# define __flush_dcache_range(p,s)		do { } while(0)
+static inline void __flush_dcache_page(unsigned long va)
-# define __flush_dcache_page(p)			do { } while(0)
+{
+}
+static inline void __flush_dcache_range(unsigned long va, unsigned long sz)
+{
+}
+# define __flush_invalidate_dcache_all()	__invalidate_dcache_all()
 # define __flush_invalidate_dcache_page(p)	__invalidate_dcache_page(p)
 # define __flush_invalidate_dcache_range(p,s)	__invalidate_dcache_range(p,s)
 #endif

arch/xtensa/kernel/pci-dma.c

@@ -15,14 +15,15 @@
  * Joe Taylor <joe@tensilica.com, joetylr@yahoo.com>
  */
 
-#include <linux/types.h>
-#include <linux/mm.h>
-#include <linux/string.h>
-#include <linux/pci.h>
 #include <linux/gfp.h>
+#include <linux/highmem.h>
+#include <linux/mm.h>
 #include <linux/module.h>
-#include <asm/io.h>
+#include <linux/pci.h>
+#include <linux/string.h>
+#include <linux/types.h>
 #include <asm/cacheflush.h>
+#include <asm/io.h>
 
 void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 		    enum dma_data_direction dir)
@@ -47,17 +48,36 @@ void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 }
 EXPORT_SYMBOL(dma_cache_sync);
 
+static void do_cache_op(dma_addr_t dma_handle, size_t size,
+			void (*fn)(unsigned long, unsigned long))
+{
+	unsigned long off = dma_handle & (PAGE_SIZE - 1);
+	unsigned long pfn = PFN_DOWN(dma_handle);
+	struct page *page = pfn_to_page(pfn);
+
+	if (!PageHighMem(page))
+		fn((unsigned long)bus_to_virt(dma_handle), size);
+	else
+		while (size > 0) {
+			size_t sz = min_t(size_t, size, PAGE_SIZE - off);
+			void *vaddr = kmap_atomic(page);
+
+			fn((unsigned long)vaddr + off, sz);
+			kunmap_atomic(vaddr);
+			off = 0;
+			++page;
+			size -= sz;
+		}
+}
+
 static void xtensa_sync_single_for_cpu(struct device *dev,
 				       dma_addr_t dma_handle, size_t size,
 				       enum dma_data_direction dir)
 {
-	void *vaddr;
-
 	switch (dir) {
 	case DMA_BIDIRECTIONAL:
 	case DMA_FROM_DEVICE:
-		vaddr = bus_to_virt(dma_handle);
+		do_cache_op(dma_handle, size, __invalidate_dcache_range);
-		__invalidate_dcache_range((unsigned long)vaddr, size);
 		break;
 
 	case DMA_NONE:
@@ -73,13 +93,11 @@ static void xtensa_sync_single_for_device(struct device *dev,
 					  dma_addr_t dma_handle, size_t size,
 					  enum dma_data_direction dir)
 {
-	void *vaddr;
-
 	switch (dir) {
 	case DMA_BIDIRECTIONAL:
 	case DMA_TO_DEVICE:
-		vaddr = bus_to_virt(dma_handle);
+		if (XCHAL_DCACHE_IS_WRITEBACK)
-		__flush_dcache_range((unsigned long)vaddr, size);
+			do_cache_op(dma_handle, size, __flush_dcache_range);
 		break;
 
 	case DMA_NONE:
@@ -171,7 +189,6 @@ static dma_addr_t xtensa_map_page(struct device *dev, struct page *page,
 {
 	dma_addr_t dma_handle = page_to_phys(page) + offset;
 
-	BUG_ON(PageHighMem(page));
 	xtensa_sync_single_for_device(dev, dma_handle, size, dir);
 	return dma_handle;
 }