@@ -187,16 +187,22 @@ static void __dma_free(struct device *dev, size_t size,
void *vaddr, dma_addr_t dma_handle,
struct dma_attrs *attrs)
{
- void *swiotlb_addr = phys_to_virt(dma_to_phys(dev, dma_handle));
-
size = PAGE_ALIGN(size);
if (!is_device_dma_coherent(dev)) {
if (__free_from_pool(vaddr, size))
return;
vunmap(vaddr);
+
+ /*
+ * For non-coherent DMA, the vaddr is not part of the linear
+ * mapping as it has been remapped by __dma_alloc() via
+ * dma_common_contiguous_remap(), hence for swiotlb freeing we
+ * need the actual linear map address.
+ */
+ vaddr = phys_to_virt(dma_to_phys(dev, dma_handle));
}
- __dma_free_coherent(dev, size, swiotlb_addr, dma_handle, attrs);
+ __dma_free_coherent(dev, size, vaddr, dma_handle, attrs);
}
static dma_addr_t __swiotlb_map_page(struct device *dev, struct page *page,
1.For coherent DMA In swiotlb_alloc_coherent, it directly return vaddr on success, and pass vaddr to free_pages on failure. So, we can directly transparent pass vaddr from __dma_free to swiotlb_free_coherent. According to my testing, it can save 8 clock cycles. 2.For non-coherent DMA. Keep no change for the original processing flow. Because all DDR memory mapped as cacheable by default. But for non-coherent devices, both CPUs and devices should use NC(non-cacheable) attributes to access memory, to keep consistency. So we can not directly use vaddr retured by __dma_alloc_coherent, but should further remap the physical memory as NC and return it. So in __dma_free, we first use the NC-vaddr to unmap, then get vaddr base upon dma_handle and use it to free memory back to buddy. Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com> --- arch/arm64/mm/dma-mapping.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) -- 2.5.0