From 6f6a00e40aa3fdd3b29c30e3ef1fc9690506bc03 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Sun, 28 Jun 2009 20:38:49 +0100 Subject: [PATCH] intel-iommu: Performance improvement for domain_pfn_mapping() As with dma_pte_clear_range(), don't keep flushing a single PTE at a time. And also micro-optimise the setting of PTE values rather than using the helper functions to do all the masking. Signed-off-by: David Woodhouse --- drivers/pci/intel-iommu.c | 26 +++++++++++++++++--------- 1 file changed, 17 insertions(+), 9 deletions(-) diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c index ba7e37f7111a..f8074236bcce 100644 --- a/drivers/pci/intel-iommu.c +++ b/drivers/pci/intel-iommu.c @@ -1639,7 +1639,7 @@ static int domain_pfn_mapping(struct dmar_domain *domain, unsigned long iov_pfn, unsigned long phys_pfn, unsigned long nr_pages, int prot) { - struct dma_pte *pte; + struct dma_pte *first_pte = NULL, *pte = NULL; int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT; BUG_ON(addr_width < BITS_PER_LONG && (iov_pfn + nr_pages - 1) >> addr_width); @@ -1647,19 +1647,27 @@ static int domain_pfn_mapping(struct dmar_domain *domain, unsigned long iov_pfn, if ((prot & (DMA_PTE_READ|DMA_PTE_WRITE)) == 0) return -EINVAL; + prot &= DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP; + while (nr_pages--) { - pte = pfn_to_dma_pte(domain, iov_pfn); - if (!pte) - return -ENOMEM; + if (!pte) { + first_pte = pte = pfn_to_dma_pte(domain, iov_pfn); + if (!pte) + return -ENOMEM; + } /* We don't need lock here, nobody else * touches the iova range */ BUG_ON(dma_pte_addr(pte)); - dma_set_pte_pfn(pte, phys_pfn); - dma_set_pte_prot(pte, prot); - if (prot & DMA_PTE_SNP) - dma_set_pte_snp(pte); - domain_flush_cache(domain, pte, sizeof(*pte)); + pte->val = (phys_pfn << VTD_PAGE_SHIFT) | prot; + pte++; + if (!nr_pages || + (unsigned long)pte >> VTD_PAGE_SHIFT != + (unsigned long)first_pte >> VTD_PAGE_SHIFT) { + domain_flush_cache(domain, first_pte, + (void *)pte - (void *)first_pte); + pte = NULL; + } iov_pfn++; phys_pfn++; } -- 2.34.1