[6/6] VT-d: support the device IOTLB
diff mbox

Message ID 20090107150413.GG4697@yzhao12-linux.sh.intel.com
State Accepted, archived
Headers show

Commit Message

Yu Zhao Jan. 7, 2009, 3:04 p.m. UTC
Support device IOTLB (i.e. ATS) for both native and KVM environments.

Signed-off-by: Yu Zhao <yu.zhao@intel.com>

---
 drivers/pci/intel-iommu.c   |   97 +++++++++++++++++++++++++++++++++++++++++-
 include/linux/intel-iommu.h |    1 +
 2 files changed, 95 insertions(+), 3 deletions(-)

Patch
diff mbox

diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c
index 261b6bd..a7ff7cb 100644
--- a/drivers/pci/intel-iommu.c
+++ b/drivers/pci/intel-iommu.c
@@ -125,6 +125,7 @@  static inline void context_set_fault_enable(struct context_entry *context)
 }
 
 #define CONTEXT_TT_MULTI_LEVEL 0
+#define CONTEXT_TT_DEV_IOTLB	1
 
 static inline void context_set_translation_type(struct context_entry *context,
 						unsigned long value)
@@ -240,6 +241,8 @@  struct device_domain_info {
 	struct list_head global; /* link to global list */
 	u8 bus;			/* PCI bus numer */
 	u8 devfn;		/* PCI devfn number */
+	int qdep;		/* invalidate queue depth */
+	struct intel_iommu *iommu; /* IOMMU used by this device */
 	struct pci_dev *dev; /* it's NULL for PCIE-to-PCI bridge */
 	struct dmar_domain *domain; /* pointer to domain */
 };
@@ -913,6 +916,75 @@  static int __iommu_flush_iotlb(struct intel_iommu *iommu, u16 did,
 	return 0;
 }
 
+static struct device_domain_info *
+iommu_support_dev_iotlb(struct dmar_domain *domain, u8 bus, u8 devfn)
+{
+	int found = 0;
+	unsigned long flags;
+	struct device_domain_info *info;
+	struct intel_iommu *iommu = device_to_iommu(bus, devfn);
+
+	if (!ecap_dev_iotlb_support(iommu->ecap))
+		return NULL;
+
+	if (!iommu->qi)
+		return NULL;
+
+	spin_lock_irqsave(&device_domain_lock, flags);
+	list_for_each_entry(info, &domain->devices, link)
+		if (info->dev && info->bus == bus && info->devfn == devfn) {
+			found = 1;
+			break;
+		}
+	spin_unlock_irqrestore(&device_domain_lock, flags);
+
+	if (!found)
+		return NULL;
+
+	if (!dmar_find_matched_atsr_unit(info->dev))
+		return NULL;
+
+	info->iommu = iommu;
+	info->qdep = pci_ats_qdep(info->dev);
+	if (!info->qdep)
+		return NULL;
+
+	return info;
+}
+
+static void iommu_enable_dev_iotlb(struct device_domain_info *info)
+{
+	pci_enable_ats(info->dev, VTD_PAGE_SHIFT);
+}
+
+static void iommu_disable_dev_iotlb(struct device_domain_info *info)
+{
+	if (info->dev && pci_ats_enabled(info->dev))
+		pci_disable_ats(info->dev);
+}
+
+static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
+				  u64 addr, unsigned int mask)
+{
+	int rc;
+	u16 sid;
+	unsigned long flags;
+	struct device_domain_info *info;
+
+	spin_lock_irqsave(&device_domain_lock, flags);
+	list_for_each_entry(info, &domain->devices, link) {
+		if (!info->dev || !pci_ats_enabled(info->dev))
+			continue;
+
+		sid = info->bus << 8 | info->devfn;
+		rc = qi_flush_dev_iotlb(info->iommu, sid,
+					info->qdep, addr, mask);
+		if (rc)
+			printk(KERN_ERR "IOMMU: flush device IOTLB failed\n");
+	}
+	spin_unlock_irqrestore(&device_domain_lock, flags);
+}
+
 static int iommu_flush_iotlb_psi(struct intel_iommu *iommu, u16 did,
 	u64 addr, unsigned int pages, int non_present_entry_flush)
 {
@@ -936,6 +1008,9 @@  static int iommu_flush_iotlb_psi(struct intel_iommu *iommu, u16 did,
 		rc = iommu->flush.flush_iotlb(iommu, did, addr, mask,
 						DMA_TLB_PSI_FLUSH,
 						non_present_entry_flush);
+	if (!rc && !non_present_entry_flush)
+		iommu_flush_dev_iotlb(iommu->domains[did], addr, mask);
+
 	return rc;
 }
 
@@ -1460,6 +1535,7 @@  static int domain_context_mapping_one(struct dmar_domain *domain,
 	unsigned long ndomains;
 	int id;
 	int agaw;
+	struct device_domain_info *info;
 
 	pr_debug("Set context mapping for %02x:%02x.%d\n",
 		bus, PCI_SLOT(devfn), PCI_FUNC(devfn));
@@ -1525,7 +1601,11 @@  static int domain_context_mapping_one(struct dmar_domain *domain,
 	context_set_domain_id(context, id);
 	context_set_address_width(context, iommu->agaw);
 	context_set_address_root(context, virt_to_phys(pgd));
-	context_set_translation_type(context, CONTEXT_TT_MULTI_LEVEL);
+	info = iommu_support_dev_iotlb(domain, bus, devfn);
+	if (info)
+		context_set_translation_type(context, CONTEXT_TT_DEV_IOTLB);
+	else
+		context_set_translation_type(context, CONTEXT_TT_MULTI_LEVEL);
 	context_set_fault_enable(context);
 	context_set_present(context);
 	domain_flush_cache(domain, context, sizeof(*context));
@@ -1537,6 +1617,8 @@  static int domain_context_mapping_one(struct dmar_domain *domain,
 		iommu_flush_write_buffer(iommu);
 	else
 		iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_DSI_FLUSH, 0);
+	if (info)
+		iommu_enable_dev_iotlb(info);
 
 	spin_unlock_irqrestore(&iommu->lock, flags);
 
@@ -1678,6 +1760,7 @@  static void domain_remove_dev_info(struct dmar_domain *domain)
 			info->dev->dev.archdata.iommu = NULL;
 		spin_unlock_irqrestore(&device_domain_lock, flags);
 
+		iommu_disable_dev_iotlb(info);
 		iommu = device_to_iommu(info->bus, info->devfn);
 		iommu_detach_dev(iommu, info->bus, info->devfn);
 		free_devinfo_mem(info);
@@ -2295,8 +2378,14 @@  static void flush_unmaps(void)
 		iommu->flush.flush_iotlb(iommu, 0, 0, 0,
 					 DMA_TLB_GLOBAL_FLUSH, 0);
 		for (j = 0; j < deferred_flush[i].next; j++) {
-			__free_iova(&deferred_flush[i].domain[j]->iovad,
-					deferred_flush[i].iova[j]);
+			unsigned long mask;
+			struct iova *iova = deferred_flush[i].iova[j];
+
+			mask = (iova->pfn_hi - iova->pfn_lo + 1) << PAGE_SHIFT;
+			mask = ilog2(mask >> VTD_PAGE_SHIFT);
+			iommu_flush_dev_iotlb(deferred_flush[i].domain[j],
+					iova->pfn_lo << PAGE_SHIFT, mask);
+			__free_iova(&deferred_flush[i].domain[j]->iovad, iova);
 		}
 		deferred_flush[i].next = 0;
 	}
@@ -2783,6 +2872,7 @@  static void vm_domain_remove_one_dev_info(struct dmar_domain *domain,
 				info->dev->dev.archdata.iommu = NULL;
 			spin_unlock_irqrestore(&device_domain_lock, flags);
 
+			iommu_disable_dev_iotlb(info);
 			iommu_detach_dev(iommu, info->bus, info->devfn);
 			free_devinfo_mem(info);
 
@@ -2831,6 +2921,7 @@  static void vm_domain_remove_all_dev_info(struct dmar_domain *domain)
 
 		spin_unlock_irqrestore(&device_domain_lock, flags1);
 
+		iommu_disable_dev_iotlb(info);
 		iommu = device_to_iommu(info->bus, info->devfn);
 		iommu_detach_dev(iommu, info->bus, info->devfn);
 
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index d82bdac..609af82 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -123,6 +123,7 @@  static inline void dmar_writeq(void __iomem *addr, u64 val)
 #define ecap_qis(e)		((e) & 0x2)
 #define ecap_eim_support(e)	((e >> 4) & 0x1)
 #define ecap_ir_support(e)	((e >> 3) & 0x1)
+#define ecap_dev_iotlb_support(e)	(((e) >> 2) & 0x1)
 #define ecap_max_handle_mask(e) ((e >> 20) & 0xf)