Merge commit 'dwmw2-iommu/master'

3 files changed, 30 insertions, 30 deletions

diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c
index ebc9b8dca881..a18845e311fb 100644
--- a/drivers/pci/intel-iommu.c
+++ b/drivers/pci/intel-iommu.c
@@ -1309,7 +1309,6 @@ static void iommu_detach_domain(struct dmar_domain *domain,
 }
 
 static struct iova_domain reserved_iova_list;
-static struct lock_class_key reserved_alloc_key;
 static struct lock_class_key reserved_rbtree_key;
 
 static void dmar_init_reserved_ranges(void)
@@ -1320,8 +1319,6 @@ static void dmar_init_reserved_ranges(void)
 
 	init_iova_domain(&reserved_iova_list, DMA_32BIT_PFN);
 
-	lockdep_set_class(&reserved_iova_list.iova_alloc_lock,
-		&reserved_alloc_key);
 	lockdep_set_class(&reserved_iova_list.iova_rbtree_lock,
 		&reserved_rbtree_key);
 
@@ -2455,8 +2452,7 @@ static struct iova *intel_alloc_iova(struct device *dev,
 	return iova;
 }
 
-static struct dmar_domain *
-get_valid_domain_for_dev(struct pci_dev *pdev)
+static struct dmar_domain *__get_valid_domain_for_dev(struct pci_dev *pdev)
 {
 	struct dmar_domain *domain;
 	int ret;
@@ -2484,6 +2480,18 @@ get_valid_domain_for_dev(struct pci_dev *pdev)
 	return domain;
 }
 
+static inline struct dmar_domain *get_valid_domain_for_dev(struct pci_dev *dev)
+{
+	struct device_domain_info *info;
+
+	/* No lock here, assumes no domain exit in normal case */
+	info = dev->dev.archdata.iommu;
+	if (likely(info))
+		return info->domain;
+
+	return __get_valid_domain_for_dev(dev);
+}
+
 static int iommu_dummy(struct pci_dev *pdev)
 {
 	return pdev->dev.archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO;
@@ -2733,12 +2741,6 @@ static void intel_unmap_page(struct device *dev, dma_addr_t dev_addr,
 	}
 }
 
-static void intel_unmap_single(struct device *dev, dma_addr_t dev_addr, size_t size,
-			       int dir)
-{
-	intel_unmap_page(dev, dev_addr, size, dir, NULL);
-}
-
 static void *intel_alloc_coherent(struct device *hwdev, size_t size,
 				  dma_addr_t *dma_handle, gfp_t flags)
 {
@@ -2771,7 +2773,7 @@ static void intel_free_coherent(struct device *hwdev, size_t size, void *vaddr,
 	size = PAGE_ALIGN(size);
 	order = get_order(size);
 
-	intel_unmap_single(hwdev, dma_handle, size, DMA_BIDIRECTIONAL);
+	intel_unmap_page(hwdev, dma_handle, size, DMA_BIDIRECTIONAL, NULL);
 	free_pages((unsigned long)vaddr, order);
 }
 
@@ -2807,11 +2809,18 @@ static void intel_unmap_sg(struct device *hwdev, struct scatterlist *sglist,
 	/* free page tables */
 	dma_pte_free_pagetable(domain, start_pfn, last_pfn);
 
-	iommu_flush_iotlb_psi(iommu, domain->id, start_pfn,
-			      (last_pfn - start_pfn + 1));
-
-	/* free iova */
-	__free_iova(&domain->iovad, iova);
+	if (intel_iommu_strict) {
+		iommu_flush_iotlb_psi(iommu, domain->id, start_pfn,
+				      last_pfn - start_pfn + 1);
+		/* free iova */
+		__free_iova(&domain->iovad, iova);
+	} else {
+		add_unmap(domain, iova);
+		/*
+		 * queue up the release of the unmap to save the 1/6th of the
+		 * cpu used up by the iotlb flush operation...
+		 */
+	}
 }
 
 static int intel_nontranslate_map_sg(struct device *hddev,
diff --git a/drivers/pci/iova.c b/drivers/pci/iova.c
index 46dd440e2315..7914951ef29a 100644
--- a/drivers/pci/iova.c
+++ b/drivers/pci/iova.c
@@ -22,7 +22,6 @@
 void
 init_iova_domain(struct iova_domain *iovad, unsigned long pfn_32bit)
 {
-	spin_lock_init(&iovad->iova_alloc_lock);
 	spin_lock_init(&iovad->iova_rbtree_lock);
 	iovad->rbroot = RB_ROOT;
 	iovad->cached32_node = NULL;
@@ -205,7 +204,6 @@ alloc_iova(struct iova_domain *iovad, unsigned long size,
 	unsigned long limit_pfn,
 	bool size_aligned)
 {
-	unsigned long flags;
 	struct iova *new_iova;
 	int ret;
 
@@ -219,11 +217,9 @@ alloc_iova(struct iova_domain *iovad, unsigned long size,
 	if (size_aligned)
 		size = __roundup_pow_of_two(size);
 
-	spin_lock_irqsave(&iovad->iova_alloc_lock, flags);
 	ret = __alloc_and_insert_iova_range(iovad, size, limit_pfn,
 			new_iova, size_aligned);
 
-	spin_unlock_irqrestore(&iovad->iova_alloc_lock, flags);
 	if (ret) {
 		free_iova_mem(new_iova);
 		return NULL;
@@ -381,8 +377,7 @@ reserve_iova(struct iova_domain *iovad,
 	struct iova *iova;
 	unsigned int overlap = 0;
 
-	spin_lock_irqsave(&iovad->iova_alloc_lock, flags);
-	spin_lock(&iovad->iova_rbtree_lock);
+	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
 	for (node = rb_first(&iovad->rbroot); node; node = rb_next(node)) {
 		if (__is_range_overlap(node, pfn_lo, pfn_hi)) {
 			iova = container_of(node, struct iova, node);
@@ -402,8 +397,7 @@ reserve_iova(struct iova_domain *iovad,
 	iova = __insert_new_range(iovad, pfn_lo, pfn_hi);
 finish:
 
-	spin_unlock(&iovad->iova_rbtree_lock);
-	spin_unlock_irqrestore(&iovad->iova_alloc_lock, flags);
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
 	return iova;
 }
 
@@ -420,8 +414,7 @@ copy_reserved_iova(struct iova_domain *from, struct iova_domain *to)
 	unsigned long flags;
 	struct rb_node *node;
 
-	spin_lock_irqsave(&from->iova_alloc_lock, flags);
-	spin_lock(&from->iova_rbtree_lock);
+	spin_lock_irqsave(&from->iova_rbtree_lock, flags);
 	for (node = rb_first(&from->rbroot); node; node = rb_next(node)) {
 		struct iova *iova = container_of(node, struct iova, node);
 		struct iova *new_iova;
@@ -430,6 +423,5 @@ copy_reserved_iova(struct iova_domain *from, struct iova_domain *to)
 			printk(KERN_ERR "Reserve iova range %lx@%lx failed\n",
 				iova->pfn_lo, iova->pfn_lo);
 	}
-	spin_unlock(&from->iova_rbtree_lock);
-	spin_unlock_irqrestore(&from->iova_alloc_lock, flags);
+	spin_unlock_irqrestore(&from->iova_rbtree_lock, flags);
 }
diff --git a/include/linux/iova.h b/include/linux/iova.h
index 228f6c94b69c..76a0759e88ec 100644
--- a/include/linux/iova.h
+++ b/include/linux/iova.h
@@ -28,7 +28,6 @@ struct iova {
 
 /* holds all the iova translations for a domain */
 struct iova_domain {
-	spinlock_t	iova_alloc_lock;/* Lock to protect iova  allocation */
 	spinlock_t	iova_rbtree_lock; /* Lock to protect update of rbtree */
 	struct rb_root	rbroot;		/* iova domain rbtree root */
 	struct rb_node	*cached32_node; /* Save last alloced node */