[PATCH v3 05/16] iommu/vt-d: support flushing more TLB types

[Jacob Pan <jacob.jun.pan@linux.intel.com>]

With shared virtual memory vitualization, extended IOTLB invalidation
may be passed down from outside IOMMU subsystems. This patch adds
invalidation functions that can be used for each IOTLB types.

Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Signed-off-by: Liu, Yi L <yi.l.liu@linux.intel.com>
Signed-off-by: Ashok Raj <ashok.raj@intel.com>
---
 drivers/iommu/dmar.c        | 54 ++++++++++++++++++++++++++++++++++++++++++---
 drivers/iommu/intel-iommu.c |  3 ++-
 include/linux/intel-iommu.h | 10 +++++++--
 3 files changed, 61 insertions(+), 6 deletions(-)

diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 57c920c..f69f6ee 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -1336,11 +1336,25 @@ void qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr,
 	qi_submit_sync(&desc, iommu);
 }
 
-void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 qdep,
-			u64 addr, unsigned mask)
+void qi_flush_eiotlb(struct intel_iommu *iommu, u16 did, u64 addr, u32 pasid,
+		unsigned int size_order, u64 granu, bool global)
 {
 	struct qi_desc desc;
 
+	desc.low = QI_EIOTLB_PASID(pasid) | QI_EIOTLB_DID(did) |
+		QI_EIOTLB_GRAN(granu) | QI_EIOTLB_TYPE;
+	desc.high = QI_EIOTLB_ADDR(addr) | QI_EIOTLB_GL(global) |
+		QI_EIOTLB_IH(0) | QI_EIOTLB_AM(size_order);
+	qi_submit_sync(&desc, iommu);
+}
+
+void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid,
+			u16 qdep, u64 addr, unsigned mask)
+{
+	struct qi_desc desc;
+
+	pr_debug_ratelimited("%s: sid %d, pfsid %d, qdep %d, addr %llx, mask %d\n",
+		__func__, sid, pfsid, qdep, addr, mask);
 	if (mask) {
 		BUG_ON(addr & ((1 << (VTD_PAGE_SHIFT + mask)) - 1));
 		addr |= (1ULL << (VTD_PAGE_SHIFT + mask - 1)) - 1;
@@ -1352,7 +1366,41 @@ void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 qdep,
 		qdep = 0;
 
 	desc.low = QI_DEV_IOTLB_SID(sid) | QI_DEV_IOTLB_QDEP(qdep) |
-		   QI_DIOTLB_TYPE;
+		   QI_DIOTLB_TYPE | QI_DEV_IOTLB_SID(pfsid);
+
+	qi_submit_sync(&desc, iommu);
+}
+
+void qi_flush_dev_eiotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid,
+		u32 pasid,  u16 qdep, u64 addr, unsigned size, u64 granu)
+{
+	struct qi_desc desc;
+
+	desc.low = QI_DEV_EIOTLB_PASID(pasid) | QI_DEV_EIOTLB_SID(sid) |
+		QI_DEV_EIOTLB_QDEP(qdep) | QI_DEIOTLB_TYPE |
+		QI_DEV_EIOTLB_PFSID(pfsid);
+	desc.high |= QI_DEV_EIOTLB_GLOB(granu);
+
+	/* If S bit is 0, we only flush a single page. If S bit is set,
+	 * The least significant zero bit indicates the size. VT-d spec
+	 * 6.5.2.6
+	 */
+	if (!size)
+		desc.high = QI_DEV_EIOTLB_ADDR(addr) & ~QI_DEV_EIOTLB_SIZE;
+	else {
+		unsigned long mask = 1UL << (VTD_PAGE_SHIFT + size);
+
+		desc.high = QI_DEV_EIOTLB_ADDR(addr & ~mask) | QI_DEV_EIOTLB_SIZE;
+	}
+	qi_submit_sync(&desc, iommu);
+}
+
+void qi_flush_pasid(struct intel_iommu *iommu, u16 did, u64 granu, int pasid)
+{
+	struct qi_desc desc;
+
+	desc.high = 0;
+	desc.low = QI_PC_TYPE | QI_PC_DID(did) | QI_PC_GRAN(granu) | QI_PC_PASID(pasid);
 
 	qi_submit_sync(&desc, iommu);
 }
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 399b504..556bdd2 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -1524,7 +1524,8 @@ static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
 
 		sid = info->bus << 8 | info->devfn;
 		qdep = info->ats_qdep;
-		qi_flush_dev_iotlb(info->iommu, sid, qdep, addr, mask);
+		qi_flush_dev_iotlb(info->iommu, sid, info->pfsid,
+				qdep, addr, mask);
 	}
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 }
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 8d38e24..3c83f7e 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -305,6 +305,7 @@ enum {
 #define QI_DEV_EIOTLB_PASID(p)	(((u64)p) << 32)
 #define QI_DEV_EIOTLB_SID(sid)	((u64)((sid) & 0xffff) << 16)
 #define QI_DEV_EIOTLB_QDEP(qd)	((u64)((qd) & 0x1f) << 4)
+#define QI_DEV_EIOTLB_PFSID(pfsid) (((u64)(pfsid & 0xf) << 12) | ((u64)(pfsid & 0xff0) << 48))
 #define QI_DEV_EIOTLB_MAX_INVS	32
 
 #define QI_PGRP_IDX(idx)	(((u64)(idx)) << 55)
@@ -496,8 +497,13 @@ extern void qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid,
 			     u8 fm, u64 type);
 extern void qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr,
 			  unsigned int size_order, u64 type);
-extern void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 qdep,
-			       u64 addr, unsigned mask);
+extern void qi_flush_eiotlb(struct intel_iommu *iommu, u16 did, u64 addr,
+			u32 pasid, unsigned int size_order, u64 type, bool global);
+extern void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid,
+			u16 qdep, u64 addr, unsigned mask);
+extern void qi_flush_dev_eiotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid,
+				u32 pasid, u16 qdep, u64 addr, unsigned size);
+extern void qi_flush_pasid(struct intel_iommu *iommu, u16 did, u64 granu, int pasid);
 
 extern int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu);
 
-- 
2.7.4