diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index f77dae7ba7d4..34ee8f28555f 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -1421,6 +1421,45 @@ void qi_flush_piotlb(struct intel_iommu *iommu, u16 did, u32 pasid, u64 addr,
 	qi_submit_sync(&desc, iommu);
 }
 
+/* PASID-based device IOTLB Invalidate */
+void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid,
+			      u32 pasid,  u16 qdep, u64 addr,
+			      unsigned int size_order, u64 granu)
+{
+	unsigned long mask = 1UL << (VTD_PAGE_SHIFT + size_order - 1);
+	struct qi_desc desc = {.qw1 = 0, .qw2 = 0, .qw3 = 0};
+
+	desc.qw0 = QI_DEV_EIOTLB_PASID(pasid) | QI_DEV_EIOTLB_SID(sid) |
+		QI_DEV_EIOTLB_QDEP(qdep) | QI_DEIOTLB_TYPE |
+		QI_DEV_IOTLB_PFSID(pfsid);
+	desc.qw1 = 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 invalidation address
+	 * range. VT-d spec 6.5.2.6.
+	 * e.g. address bit 12[0] indicates 8KB, 13[0] indicates 16KB.
+	 * size order = 0 is PAGE_SIZE 4KB
+	 * Max Invs Pending (MIP) is set to 0 for now until we have DIT in
+	 * ECAP.
+	 */
+	desc.qw1 |= addr & ~mask;
+	if (size_order)
+		desc.qw1 |= QI_DEV_EIOTLB_SIZE;
+
+	qi_submit_sync(&desc, iommu);
+}
+
+void qi_flush_pasid_cache(struct intel_iommu *iommu, u16 did,
+			  u64 granu, int pasid)
+{
+	struct qi_desc desc = {.qw1 = 0, .qw2 = 0, .qw3 = 0};
+
+	desc.qw0 = QI_PC_PASID(pasid) | QI_PC_DID(did) |
+			QI_PC_GRAN(granu) | QI_PC_TYPE;
+	qi_submit_sync(&desc, iommu);
+}
+
 /*
  * Disable Queued Invalidation interface.
  */
diff --git a/drivers/iommu/intel-pasid.c b/drivers/iommu/intel-pasid.c
index c7fa1b79eaf7..5d9d9ff49334 100644
--- a/drivers/iommu/intel-pasid.c
+++ b/drivers/iommu/intel-pasid.c
@@ -375,7 +375,8 @@ pasid_cache_invalidation_with_pasid(struct intel_iommu *iommu,
 {
 	struct qi_desc desc;
 
-	desc.qw0 = QI_PC_DID(did) | QI_PC_PASID_SEL | QI_PC_PASID(pasid);
+	desc.qw0 = QI_PC_DID(did) | QI_PC_GRAN(QI_PC_PASID_SEL) |
+		QI_PC_PASID(pasid) | QI_PC_TYPE;
 	desc.qw1 = 0;
 	desc.qw2 = 0;
 	desc.qw3 = 0;
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 3dfd426dfb03..a9c984b29a72 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -334,7 +334,7 @@ enum {
 #define QI_IOTLB_GRAN(gran) 	(((u64)gran) >> (DMA_TLB_FLUSH_GRANU_OFFSET-4))
 #define QI_IOTLB_ADDR(addr)	(((u64)addr) & VTD_PAGE_MASK)
 #define QI_IOTLB_IH(ih)		(((u64)ih) << 6)
-#define QI_IOTLB_AM(am)		(((u8)am))
+#define QI_IOTLB_AM(am)		(((u8)am) & 0x3f)
 
 #define QI_CC_FM(fm)		(((u64)fm) << 48)
 #define QI_CC_SID(sid)		(((u64)sid) << 32)
@@ -353,16 +353,21 @@ enum {
 #define QI_PC_DID(did)		(((u64)did) << 16)
 #define QI_PC_GRAN(gran)	(((u64)gran) << 4)
 
-#define QI_PC_ALL_PASIDS	(QI_PC_TYPE | QI_PC_GRAN(0))
-#define QI_PC_PASID_SEL		(QI_PC_TYPE | QI_PC_GRAN(1))
+/* PASID cache invalidation granu */
+#define QI_PC_ALL_PASIDS	0
+#define QI_PC_PASID_SEL		1
 
 #define QI_EIOTLB_ADDR(addr)	((u64)(addr) & VTD_PAGE_MASK)
 #define QI_EIOTLB_IH(ih)	(((u64)ih) << 6)
-#define QI_EIOTLB_AM(am)	(((u64)am))
+#define QI_EIOTLB_AM(am)	(((u64)am) & 0x3f)
 #define QI_EIOTLB_PASID(pasid) 	(((u64)pasid) << 32)
 #define QI_EIOTLB_DID(did)	(((u64)did) << 16)
 #define QI_EIOTLB_GRAN(gran) 	(((u64)gran) << 4)
 
+/* QI Dev-IOTLB inv granu */
+#define QI_DEV_IOTLB_GRAN_ALL		1
+#define QI_DEV_IOTLB_GRAN_PASID_SEL	0
+
 #define QI_DEV_EIOTLB_ADDR(a)	((u64)(a) & VTD_PAGE_MASK)
 #define QI_DEV_EIOTLB_SIZE	(((u64)1) << 11)
 #define QI_DEV_EIOTLB_GLOB(g)	((u64)g)
@@ -679,8 +684,16 @@ 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 pfsid,
 			u16 qdep, u64 addr, unsigned mask);
+
 void qi_flush_piotlb(struct intel_iommu *iommu, u16 did, u32 pasid, u64 addr,
 		     unsigned long npages, bool ih);
+
+void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid,
+			      u32 pasid, u16 qdep, u64 addr,
+			      unsigned int size_order, u64 granu);
+void qi_flush_pasid_cache(struct intel_iommu *iommu, u16 did, u64 granu,
+			  int pasid);
+
 extern int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu);
 
 extern int dmar_ir_support(void);