From ad27c9e51256e084b474a073319feba1d2bcebcd Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Wed, 12 Sep 2018 16:24:14 +0100 Subject: [PATCH 1589/2944] arm64/dma-mapping: Mildly optimise non-coherent IOMMU ops fix #27432135 commit 7adb562c3e90f87b0da196c372afe251ad4ec62e upstream Whilst the symmetry of deferring to the existing sync callback in __iommu_map_page() is nice, taking a round-trip through iommu_iova_to_phys() is a pretty heavyweight way to get an address we can trivially compute from the page we already have. Tweaking it to just perform the cache maintenance directly when appropriate doesn't really make the code any more complicated, and the runtime efficiency gain can only be a benefit. Furthermore, the sync operations themselves know they can only be invoked on a managed DMA ops domain, so can use the fast specific domain lookup to avoid excessive manipulation of the group refcount (particularly in the scatterlist cases). Acked-by: Will Deacon Signed-off-by: Robin Murphy Tested-by: Will Deacon Signed-off-by: Joerg Roedel Signed-off-by: Rongwei Wang Acked-by: zou cao --- arch/arm64/mm/dma-mapping.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index d3a5bb1..f4d5765 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -722,7 +722,7 @@ static void __iommu_sync_single_for_cpu(struct device *dev, if (is_device_dma_coherent(dev)) return; - phys = iommu_iova_to_phys(iommu_get_domain_for_dev(dev), dev_addr); + phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dev_addr); __dma_unmap_area(phys_to_virt(phys), size, dir); } @@ -735,7 +735,7 @@ static void __iommu_sync_single_for_device(struct device *dev, if (is_device_dma_coherent(dev)) return; - phys = iommu_iova_to_phys(iommu_get_domain_for_dev(dev), dev_addr); + phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dev_addr); __dma_map_area(phys_to_virt(phys), size, dir); } @@ -748,9 +748,9 @@ static dma_addr_t __iommu_map_page(struct device *dev, struct page *page, int prot = dma_info_to_prot(dir, coherent, attrs); dma_addr_t dev_addr = iommu_dma_map_page(dev, page, offset, size, prot); - if (!iommu_dma_mapping_error(dev, dev_addr) && - (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) - __iommu_sync_single_for_device(dev, dev_addr, size, dir); + if (!coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC) && + !iommu_dma_mapping_error(dev, dev_addr)) + __dma_map_area(page_address(page) + offset, size, dir); return dev_addr; } -- 1.8.3.1