iommu: Introduce the domain op enforce_cache_coherency()

This new mechanism will replace using IOMMU_CAP_CACHE_COHERENCY and
IOMMU_CACHE to control the no-snoop blocking behavior of the IOMMU.

Currently only Intel and AMD IOMMUs are known to support this
feature. They both implement it as an IOPTE bit, that when set, will cause
PCIe TLPs to that IOVA with the no-snoop bit set to be treated as though
the no-snoop bit was clear.

The new API is triggered by calling enforce_cache_coherency() before
mapping any IOVA to the domain which globally switches on no-snoop
blocking. This allows other implementations that might block no-snoop
globally and outside the IOPTE - AMD also documents such a HW capability.

Leave AMD out of sync with Intel and have it block no-snoop even for
in-kernel users. This can be trivially resolved in a follow up patch.

Only VFIO needs to call this API because it does not have detailed control
over the device to avoid requesting no-snoop behavior at the device
level. Other places using domains with real kernel drivers should simply
avoid asking their devices to set the no-snoop bit.

Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Acked-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/1-v3-2cf356649677+a32-intel_no_snoop_jgg@nvidia.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>

2 files changed, 20 insertions, 1 deletions

diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 038e104b922c..840831d5d2ad 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -2266,6 +2266,12 @@ static int amd_iommu_def_domain_type(struct device *dev)
 	return 0;
 }
 
+static bool amd_iommu_enforce_cache_coherency(struct iommu_domain *domain)
+{
+	/* IOMMU_PTE_FC is always set */
+	return true;
+}
+
 const struct iommu_ops amd_iommu_ops = {
 	.capable = amd_iommu_capable,
 	.domain_alloc = amd_iommu_domain_alloc,
@@ -2288,6 +2294,7 @@ const struct iommu_ops amd_iommu_ops = {
 		.flush_iotlb_all = amd_iommu_flush_iotlb_all,
 		.iotlb_sync	= amd_iommu_iotlb_sync,
 		.free		= amd_iommu_domain_free,
+		.enforce_cache_coherency = amd_iommu_enforce_cache_coherency,
 	}
 };
 
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 0edf6084dc14..161199f62270 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -4422,7 +4422,8 @@ 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)
+	if (((iommu_prot & IOMMU_CACHE) && dmar_domain->iommu_snooping) ||
+	    dmar_domain->force_snooping)
 		prot |= DMA_PTE_SNP;
 
 	max_addr = iova + size;
@@ -4545,6 +4546,16 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
 	return phys;
 }
 
+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)
+		return false;
+	dmar_domain->force_snooping = true;
+	return true;
+}
+
 static bool intel_iommu_capable(enum iommu_cap cap)
 {
 	if (cap == IOMMU_CAP_CACHE_COHERENCY)
@@ -4900,6 +4911,7 @@ const struct iommu_ops intel_iommu_ops = {
 		.iotlb_sync		= intel_iommu_tlb_sync,
 		.iova_to_phys		= intel_iommu_iova_to_phys,
 		.free			= intel_iommu_domain_free,
+		.enforce_cache_coherency = intel_iommu_enforce_cache_coherency,
 	}
 };