iommu/vt-d: Check domain force_snooping against attached devices

As domain->force_snooping only impacts the devices attached with the
domain, there's no need to check against all IOMMU units. On the other
hand, force_snooping could be set on a domain no matter whether it has
been attached or not, and once set it is an immutable flag. If no
device attached, the operation always succeeds. Then this empty domain
can be only attached to a device of which the IOMMU supports snoop
control.

Signed-off-by: Lu Baolu <[email protected]>
Reviewed-by: Kevin Tian <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Joerg Roedel <[email protected]>

Author: LuBaolu

drivers/iommu/intel/iommu.c

@@ -2438,7 +2438,7 @@ static int domain_setup_first_level(struct intel_iommu *iommu,
 	if (level == 5)
 		flags |= PASID_FLAG_FL5LP;
 
-	if (domain->domain.type == IOMMU_DOMAIN_UNMANAGED)
+	if (domain->force_snooping)
 		flags |= PASID_FLAG_PAGE_SNOOP;
 
 	return intel_pasid_setup_first_level(iommu, dev, (pgd_t *)pgd, pasid,
@@ -4410,7 +4410,7 @@ static int intel_iommu_map(struct iommu_domain *domain,
 		prot |= DMA_PTE_READ;
 	if (iommu_prot & IOMMU_WRITE)
 		prot |= DMA_PTE_WRITE;
-	if (dmar_domain->force_snooping)
+	if (dmar_domain->set_pte_snp)
 		prot |= DMA_PTE_SNP;
 
 	max_addr = iova + size;
@@ -4533,13 +4533,60 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
 	return phys;
 }
 
+static bool domain_support_force_snooping(struct dmar_domain *domain)
+{
+	struct device_domain_info *info;
+	bool support = true;
+
+	assert_spin_locked(&device_domain_lock);
+	list_for_each_entry(info, &domain->devices, link) {
+		if (!ecap_sc_support(info->iommu->ecap)) {
+			support = false;
+			break;
+		}
+	}
+
+	return support;
+}
+
+static void domain_set_force_snooping(struct dmar_domain *domain)
+{
+	struct device_domain_info *info;
+
+	assert_spin_locked(&device_domain_lock);
+
+	/*
+	 * Second level page table supports per-PTE snoop control. The
+	 * iommu_map() interface will handle this by setting SNP bit.
+	 */
+	if (!domain_use_first_level(domain)) {
+		domain->set_pte_snp = true;
+		return;
+	}
+
+	list_for_each_entry(info, &domain->devices, link)
+		intel_pasid_setup_page_snoop_control(info->iommu, info->dev,
+						     PASID_RID2PASID);
+}
+
 static bool intel_iommu_enforce_cache_coherency(struct iommu_domain *domain)
 {
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	unsigned long flags;
 
-	if (!domain_update_iommu_snooping(NULL))
+	if (dmar_domain->force_snooping)
+		return true;
+
+	spin_lock_irqsave(&device_domain_lock, flags);
+	if (!domain_support_force_snooping(dmar_domain)) {
+		spin_unlock_irqrestore(&device_domain_lock, flags);
 		return false;
+	}
+
+	domain_set_force_snooping(dmar_domain);
 	dmar_domain->force_snooping = true;
+	spin_unlock_irqrestore(&device_domain_lock, flags);
+
 	return true;
 }
 

drivers/iommu/intel/pasid.c

@@ -762,3 +762,45 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
 
 	return 0;
 }
+
+/*
+ * Set the page snoop control for a pasid entry which has been set up.
+ */
+void intel_pasid_setup_page_snoop_control(struct intel_iommu *iommu,
+					  struct device *dev, u32 pasid)
+{
+	struct pasid_entry *pte;
+	u16 did;
+
+	spin_lock(&iommu->lock);
+	pte = intel_pasid_get_entry(dev, pasid);
+	if (WARN_ON(!pte || !pasid_pte_is_present(pte))) {
+		spin_unlock(&iommu->lock);
+		return;
+	}
+
+	pasid_set_pgsnp(pte);
+	did = pasid_get_domain_id(pte);
+	spin_unlock(&iommu->lock);
+
+	if (!ecap_coherent(iommu->ecap))
+		clflush_cache_range(pte, sizeof(*pte));
+
+	/*
+	 * VT-d spec 3.4 table23 states guides for cache invalidation:
+	 *
+	 * - PASID-selective-within-Domain PASID-cache invalidation
+	 * - PASID-selective PASID-based IOTLB invalidation
+	 * - If (pasid is RID_PASID)
+	 *    - Global Device-TLB invalidation to affected functions
+	 *   Else
+	 *    - PASID-based Device-TLB invalidation (with S=1 and
+	 *      Addr[63:12]=0x7FFFFFFF_FFFFF) to affected functions
+	 */
+	pasid_cache_invalidation_with_pasid(iommu, did, pasid);
+	qi_flush_piotlb(iommu, did, pasid, 0, -1, 0);
+
+	/* Device IOTLB doesn't need to be flushed in caching mode. */
+	if (!cap_caching_mode(iommu->cap))
+		devtlb_invalidation_with_pasid(iommu, dev, pasid);
+}

drivers/iommu/intel/pasid.h

@@ -123,4 +123,6 @@ void intel_pasid_tear_down_entry(struct intel_iommu *iommu,
 				 bool fault_ignore);
 int vcmd_alloc_pasid(struct intel_iommu *iommu, u32 *pasid);
 void vcmd_free_pasid(struct intel_iommu *iommu, u32 pasid);
+void intel_pasid_setup_page_snoop_control(struct intel_iommu *iommu,
+					  struct device *dev, u32 pasid);
 #endif /* __INTEL_PASID_H */

include/linux/intel-iommu.h

@@ -540,6 +540,7 @@ struct dmar_domain {
 	u8 has_iotlb_device: 1;
 	u8 iommu_coherency: 1;		/* indicate coherency of iommu access */
 	u8 force_snooping : 1;		/* Create IOPTEs with snoop control */
+	u8 set_pte_snp:1;
 
 	struct list_head devices;	/* all devices' list */
 	struct iova_domain iovad;	/* iova's that belong to this domain */