From 7296f2301a057493e97b07739213c6e864f76891 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Mon, 8 Jul 2024 12:41:00 -0700 Subject: swiotlb: reduce swiotlb pool lookups With CONFIG_SWIOTLB_DYNAMIC enabled, each round-trip map/unmap pair in the swiotlb results in 6 calls to swiotlb_find_pool(). In multiple places, the pool is found and used in one function, and then must be found again in the next function that is called because only the tlb_addr is passed as an argument. These are the six call sites: dma_direct_map_page: 1. swiotlb_map -> swiotlb_tbl_map_single -> swiotlb_bounce dma_direct_unmap_page: 2. dma_direct_sync_single_for_cpu -> is_swiotlb_buffer 3. dma_direct_sync_single_for_cpu -> swiotlb_sync_single_for_cpu -> swiotlb_bounce 4. is_swiotlb_buffer 5. swiotlb_tbl_unmap_single -> swiotlb_del_transient 6. swiotlb_tbl_unmap_single -> swiotlb_release_slots Reduce the number of calls by finding the pool at a higher level, and passing it as an argument instead of searching again. A key change is for is_swiotlb_buffer() to return a pool pointer instead of a boolean, and then pass this pool pointer to subsequent swiotlb functions. There are 9 occurrences of is_swiotlb_buffer() used to test if a buffer is a swiotlb buffer before calling a swiotlb function. To reduce code duplication in getting the pool pointer and passing it as an argument, introduce inline wrappers for this pattern. The generated code is essentially unchanged. Since is_swiotlb_buffer() no longer returns a boolean, rename some functions to reflect the change: * swiotlb_find_pool() becomes __swiotlb_find_pool() * is_swiotlb_buffer() becomes swiotlb_find_pool() * is_xen_swiotlb_buffer() becomes xen_swiotlb_find_pool() With these changes, a round-trip map/unmap pair requires only 2 pool lookups (listed using the new names and wrappers): dma_direct_unmap_page: 1. dma_direct_sync_single_for_cpu -> swiotlb_find_pool 2. swiotlb_tbl_unmap_single -> swiotlb_find_pool These changes come from noticing the inefficiencies in a code review, not from performance measurements. With CONFIG_SWIOTLB_DYNAMIC, __swiotlb_find_pool() is not trivial, and it uses an RCU read lock, so avoiding the redundant calls helps performance in a hot path. When CONFIG_SWIOTLB_DYNAMIC is *not* set, the code size reduction is minimal and the perf benefits are likely negligible, but no harm is done. No functional change is intended. Signed-off-by: Michael Kelley Reviewed-by: Petr Tesarik Signed-off-by: Christoph Hellwig --- drivers/iommu/dma-iommu.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) (limited to 'drivers/iommu/dma-iommu.c') diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 43520e7275cc..7b4486238427 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -1081,8 +1081,7 @@ static void iommu_dma_sync_single_for_cpu(struct device *dev, if (!dev_is_dma_coherent(dev)) arch_sync_dma_for_cpu(phys, size, dir); - if (is_swiotlb_buffer(dev, phys)) - swiotlb_sync_single_for_cpu(dev, phys, size, dir); + swiotlb_sync_single_for_cpu(dev, phys, size, dir); } static void iommu_dma_sync_single_for_device(struct device *dev, @@ -1094,8 +1093,7 @@ static void iommu_dma_sync_single_for_device(struct device *dev, return; phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dma_handle); - if (is_swiotlb_buffer(dev, phys)) - swiotlb_sync_single_for_device(dev, phys, size, dir); + swiotlb_sync_single_for_device(dev, phys, size, dir); if (!dev_is_dma_coherent(dev)) arch_sync_dma_for_device(phys, size, dir); @@ -1189,7 +1187,7 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page, arch_sync_dma_for_device(phys, size, dir); iova = __iommu_dma_map(dev, phys, size, prot, dma_mask); - if (iova == DMA_MAPPING_ERROR && is_swiotlb_buffer(dev, phys)) + if (iova == DMA_MAPPING_ERROR) swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs); return iova; } @@ -1209,8 +1207,7 @@ static void iommu_dma_unmap_page(struct device *dev, dma_addr_t dma_handle, __iommu_dma_unmap(dev, dma_handle, size); - if (unlikely(is_swiotlb_buffer(dev, phys))) - swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs); + swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs); } /* -- cgit v1.2.3