From 3c0468d4451eb6b4f6604370639f163f9637a479 Mon Sep 17 00:00:00 2001 From: Leonardo Bras Date: Thu, 18 Mar 2021 14:44:14 -0300 Subject: [PATCH] powerpc/kernel/iommu: Align size for IOMMU_PAGE_SIZE() to save TCEs Currently both iommu_alloc_coherent() and iommu_free_coherent() align the desired allocation size to PAGE_SIZE, and gets system pages and IOMMU mappings (TCEs) for that value. When IOMMU_PAGE_SIZE < PAGE_SIZE, this behavior may cause unnecessary TCEs to be created for mapping the whole system page. Example: - PAGE_SIZE = 64k, IOMMU_PAGE_SIZE() = 4k - iommu_alloc_coherent() is called for 128 bytes - 1 system page (64k) is allocated - 16 IOMMU pages (16 x 4k) are allocated (16 TCEs used) It would be enough to use a single TCE for this, so 15 TCEs are wasted in the process. Update iommu_*_coherent() to make sure the size alignment happens only for IOMMU_PAGE_SIZE() before calling iommu_alloc() and iommu_free(). Also, on iommu_range_alloc(), replace ALIGN(n, 1 << tbl->it_page_shift) with IOMMU_PAGE_ALIGN(n, tbl), which is easier to read and does the same. Signed-off-by: Leonardo Bras Reviewed-by: Alexey Kardashevskiy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20210318174414.684630-1-leobras.c@gmail.com --- arch/powerpc/kernel/iommu.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 560be519ad05..24208cd00aef 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -889,6 +889,7 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl, unsigned int order; unsigned int nio_pages, io_order; struct page *page; + size_t size_io = size; size = PAGE_ALIGN(size); order = get_order(size); @@ -915,8 +916,9 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl, memset(ret, 0, size); /* Set up tces to cover the allocated range */ - nio_pages = size >> tbl->it_page_shift; - io_order = get_iommu_order(size, tbl); + size_io = IOMMU_PAGE_ALIGN(size_io, tbl); + nio_pages = size_io >> tbl->it_page_shift; + io_order = get_iommu_order(size_io, tbl); mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL, mask >> tbl->it_page_shift, io_order, 0); if (mapping == DMA_MAPPING_ERROR) { @@ -931,10 +933,9 @@ void iommu_free_coherent(struct iommu_table *tbl, size_t size, void *vaddr, dma_addr_t dma_handle) { if (tbl) { - unsigned int nio_pages; + size_t size_io = IOMMU_PAGE_ALIGN(size, tbl); + unsigned int nio_pages = size_io >> tbl->it_page_shift; - size = PAGE_ALIGN(size); - nio_pages = size >> tbl->it_page_shift; iommu_free(tbl, dma_handle, nio_pages); size = PAGE_ALIGN(size); free_pages((unsigned long)vaddr, get_order(size)); -- 2.20.1