From 71cfafda9c9bd9812cdb62ddb94daf65a1af12c1 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 11 Apr 2022 12:16:06 -0300 Subject: vfio: Move the Intel no-snoop control off of IOMMU_CACHE IOMMU_CACHE means "normal DMA to this iommu_domain's IOVA should be cache coherent" and is used by the DMA API. The definition allows for special non-coherent DMA to exist - ie processing of the no-snoop flag in PCIe TLPs - so long as this behavior is opt-in by the device driver. The flag is mainly used by the DMA API to synchronize the IOMMU setting with the expected cache behavior of the DMA master. eg based on dev_is_dma_coherent() in some case. For Intel IOMMU IOMMU_CACHE was redefined to mean 'force all DMA to be cache coherent' which has the practical effect of causing the IOMMU to ignore the no-snoop bit in a PCIe TLP. x86 platforms are always IOMMU_CACHE, so Intel should ignore this flag. Instead use the new domain op enforce_cache_coherency() which causes every IOPTE created in the domain to have the no-snoop blocking behavior. Reconfigure VFIO to always use IOMMU_CACHE and call enforce_cache_coherency() to operate the special Intel behavior. Remove the IOMMU_CACHE test from Intel IOMMU. Ultimately VFIO plumbs the result of enforce_cache_coherency() back into the x86 platform code through kvm_arch_register_noncoherent_dma() which controls if the WBINVD instruction is available in the guest. No other archs implement kvm_arch_register_noncoherent_dma() nor are there any other known consumers of VFIO_DMA_CC_IOMMU that might be affected by the user visible result change on non-x86 archs. Reviewed-by: Kevin Tian Reviewed-by: Lu Baolu Acked-by: Alex Williamson Acked-by: Robin Murphy Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/2-v3-2cf356649677+a32-intel_no_snoop_jgg@nvidia.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'drivers/iommu/intel') diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 161199f62270..38441cb06c8c 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -641,7 +641,6 @@ static unsigned long domain_super_pgsize_bitmap(struct dmar_domain *domain) static void domain_update_iommu_cap(struct dmar_domain *domain) { domain_update_iommu_coherency(domain); - domain->iommu_snooping = domain_update_iommu_snooping(NULL); domain->iommu_superpage = domain_update_iommu_superpage(domain, NULL); /* @@ -4283,7 +4282,6 @@ static int md_domain_init(struct dmar_domain *domain, int guest_width) domain->agaw = width_to_agaw(adjust_width); domain->iommu_coherency = false; - domain->iommu_snooping = false; domain->iommu_superpage = 0; domain->max_addr = 0; @@ -4422,8 +4420,7 @@ static int intel_iommu_map(struct iommu_domain *domain, prot |= DMA_PTE_READ; if (iommu_prot & IOMMU_WRITE) prot |= DMA_PTE_WRITE; - if (((iommu_prot & IOMMU_CACHE) && dmar_domain->iommu_snooping) || - dmar_domain->force_snooping) + if (dmar_domain->force_snooping) prot |= DMA_PTE_SNP; max_addr = iova + size; @@ -4550,7 +4547,7 @@ static bool intel_iommu_enforce_cache_coherency(struct iommu_domain *domain) { struct dmar_domain *dmar_domain = to_dmar_domain(domain); - if (!dmar_domain->iommu_snooping) + if (!domain_update_iommu_snooping(NULL)) return false; dmar_domain->force_snooping = true; return true; -- cgit v1.2.3