intel-iommu: Clean up handling of "caching mode" vs. context flushing.

It really doesn't make a lot of sense to have some of the logic to
handle caching vs. non-caching mode duplicated in qi_flush_context() and
__iommu_flush_context(), while the return value indicates whether the
caller should take other action which depends on the same thing.

Especially since qi_flush_context() thought it was returning something
entirely different anyway.

This patch makes qi_flush_context() and __iommu_flush_context() both
return void, removes the 'non_present_entry_flush' argument and makes
the only call site which _set_ that argument to 1 do the right thing.

Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
diff --git a/drivers/pci/dmar.c b/drivers/pci/dmar.c
index d3d86b7..10a071b 100644
--- a/drivers/pci/dmar.c
+++ b/drivers/pci/dmar.c
@@ -723,23 +723,16 @@
 	qi_submit_sync(&desc, iommu);
 }
 
-int qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid, u8 fm,
-		     u64 type, int non_present_entry_flush)
+void qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid, u8 fm,
+		      u64 type)
 {
 	struct qi_desc desc;
 
-	if (non_present_entry_flush) {
-		if (!cap_caching_mode(iommu->cap))
-			return 1;
-		else
-			did = 0;
-	}
-
 	desc.low = QI_CC_FM(fm) | QI_CC_SID(sid) | QI_CC_DID(did)
 			| QI_CC_GRAN(type) | QI_CC_TYPE;
 	desc.high = 0;
 
-	return qi_submit_sync(&desc, iommu);
+	qi_submit_sync(&desc, iommu);
 }
 
 int qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr,
diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c
index d6f4ee5..9f5d915 100644
--- a/drivers/pci/intel-iommu.c
+++ b/drivers/pci/intel-iommu.c
@@ -857,26 +857,13 @@
 }
 
 /* return value determine if we need a write buffer flush */
-static int __iommu_flush_context(struct intel_iommu *iommu,
-	u16 did, u16 source_id, u8 function_mask, u64 type,
-	int non_present_entry_flush)
+static void __iommu_flush_context(struct intel_iommu *iommu,
+				  u16 did, u16 source_id, u8 function_mask,
+				  u64 type)
 {
 	u64 val = 0;
 	unsigned long flag;
 
-	/*
-	 * In the non-present entry flush case, if hardware doesn't cache
-	 * non-present entry we do nothing and if hardware cache non-present
-	 * entry, we flush entries of domain 0 (the domain id is used to cache
-	 * any non-present entries)
-	 */
-	if (non_present_entry_flush) {
-		if (!cap_caching_mode(iommu->cap))
-			return 1;
-		else
-			did = 0;
-	}
-
 	switch (type) {
 	case DMA_CCMD_GLOBAL_INVL:
 		val = DMA_CCMD_GLOBAL_INVL;
@@ -901,9 +888,6 @@
 		dmar_readq, (!(val & DMA_CCMD_ICC)), val);
 
 	spin_unlock_irqrestore(&iommu->register_lock, flag);
-
-	/* flush context entry will implicitly flush write buffer */
-	return 0;
 }
 
 /* return value determine if we need a write buffer flush */
@@ -1428,14 +1412,21 @@
 	context_set_present(context);
 	domain_flush_cache(domain, context, sizeof(*context));
 
-	/* it's a non-present to present mapping */
-	if (iommu->flush.flush_context(iommu, id,
-		(((u16)bus) << 8) | devfn, DMA_CCMD_MASK_NOBIT,
-		DMA_CCMD_DEVICE_INVL, 1))
-		iommu_flush_write_buffer(iommu);
-	else
+	/*
+	 * It's a non-present to present mapping. If hardware doesn't cache
+	 * non-present entry we only need to flush the write-buffer. If the
+	 * _does_ cache non-present entries, then it does so in the special
+	 * domain #0, which we have to flush:
+	 */
+	if (cap_caching_mode(iommu->cap)) {
+		iommu->flush.flush_context(iommu, 0,
+					   (((u16)bus) << 8) | devfn,
+					   DMA_CCMD_MASK_NOBIT,
+					   DMA_CCMD_DEVICE_INVL);
 		iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_DSI_FLUSH, 0);
-
+	} else {
+		iommu_flush_write_buffer(iommu);
+	}
 	spin_unlock_irqrestore(&iommu->lock, flags);
 
 	spin_lock_irqsave(&domain->iommu_lock, flags);
@@ -1566,7 +1557,7 @@
 
 	clear_context_table(iommu, bus, devfn);
 	iommu->flush.flush_context(iommu, 0, 0, 0,
-					   DMA_CCMD_GLOBAL_INVL, 0);
+					   DMA_CCMD_GLOBAL_INVL);
 	iommu->flush.flush_iotlb(iommu, 0, 0, 0,
 					 DMA_TLB_GLOBAL_FLUSH, 0);
 }
@@ -2104,8 +2095,7 @@
 
 		iommu_set_root_entry(iommu);
 
-		iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL,
-					   0);
+		iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL);
 		iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH,
 					 0);
 		iommu_disable_protect_mem_regions(iommu);
@@ -2721,7 +2711,7 @@
 		iommu_set_root_entry(iommu);
 
 		iommu->flush.flush_context(iommu, 0, 0, 0,
-						DMA_CCMD_GLOBAL_INVL, 0);
+						DMA_CCMD_GLOBAL_INVL);
 		iommu->flush.flush_iotlb(iommu, 0, 0, 0,
 						DMA_TLB_GLOBAL_FLUSH, 0);
 		iommu_disable_protect_mem_regions(iommu);
@@ -2738,7 +2728,7 @@
 
 	for_each_active_iommu(iommu, drhd) {
 		iommu->flush.flush_context(iommu, 0, 0, 0,
-						DMA_CCMD_GLOBAL_INVL, 0);
+						DMA_CCMD_GLOBAL_INVL);
 		iommu->flush.flush_iotlb(iommu, 0, 0, 0,
 						DMA_TLB_GLOBAL_FLUSH, 0);
 	}
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 7246971..f2b94da 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -281,8 +281,8 @@
 #endif
 
 struct iommu_flush {
-	int (*flush_context)(struct intel_iommu *iommu, u16 did, u16 sid, u8 fm,
-		u64 type, int non_present_entry_flush);
+	void (*flush_context)(struct intel_iommu *iommu, u16 did, u16 sid,
+			      u8 fm, u64 type);
 	int (*flush_iotlb)(struct intel_iommu *iommu, u16 did, u64 addr,
 		unsigned int size_order, u64 type, int non_present_entry_flush);
 };
@@ -339,8 +339,8 @@
 extern int dmar_reenable_qi(struct intel_iommu *iommu);
 extern void qi_global_iec(struct intel_iommu *iommu);
 
-extern int qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid,
-			        u8 fm, u64 type, int non_present_entry_flush);
+extern void qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid,
+			     u8 fm, u64 type);
 extern int qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr,
 			  unsigned int size_order, u64 type,
 			  int non_present_entry_flush);