From: Ganapatrao Kulkarni <ganapatrao.kulkarni@cavium.com>
Date: Wed, 5 Sep 2018 09:57:36 +0530
Subject: iommu/iova: Optimise attempts to allocate iova from 32bit address
 range
Git-commit: bee60e94a1e20ec0b8ffdafae270731d8fda4551
Patch-mainline: v4.20-rc1
References: fate#326252

As an optimisation for PCI devices, there is always first attempt
been made to allocate iova from SAC address range. This will lead
to unnecessary attempts, when there are no free ranges
available. Adding fix to track recently failed iova address size and
allow further attempts, only if requested size is lesser than a failed
size. The size is updated when any replenish happens.

Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Ganapatrao Kulkarni <ganapatrao.kulkarni@cavium.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Matthias Brugger <mbrugger@suse.com>
---
 drivers/iommu/iova.c |   22 +++++++++++++++-------
 include/linux/iova.h |    1 +
 2 files changed, 16 insertions(+), 7 deletions(-)

--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -55,6 +55,7 @@ init_iova_domain(struct iova_domain *iov
 	iovad->granule = granule;
 	iovad->start_pfn = start_pfn;
 	iovad->dma_32bit_pfn = 1UL << (32 - iova_shift(iovad));
+	iovad->max32_alloc_size = iovad->dma_32bit_pfn;
 	iovad->flush_cb = NULL;
 	iovad->fq = NULL;
 	iovad->anchor.pfn_lo = iovad->anchor.pfn_hi = IOVA_ANCHOR;
@@ -138,8 +139,10 @@ __cached_rbnode_delete_update(struct iov
 
 	cached_iova = rb_entry(iovad->cached32_node, struct iova, node);
 	if (free->pfn_hi < iovad->dma_32bit_pfn &&
-	    free->pfn_lo >= cached_iova->pfn_lo)
+	    free->pfn_lo >= cached_iova->pfn_lo) {
 		iovad->cached32_node = rb_next(&free->node);
+		iovad->max32_alloc_size = iovad->dma_32bit_pfn;
+	}
 
 	cached_iova = rb_entry(iovad->cached_node, struct iova, node);
 	if (free->pfn_lo >= cached_iova->pfn_lo)
@@ -189,6 +192,10 @@ static int __alloc_and_insert_iova_range
 
 	/* Walk the tree backwards */
 	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
+	if (limit_pfn <= iovad->dma_32bit_pfn &&
+			size >= iovad->max32_alloc_size)
+		goto iova32_full;
+
 	curr = __get_cached_rbnode(iovad, limit_pfn);
 	curr_iova = rb_entry(curr, struct iova, node);
 	do {
@@ -199,10 +206,8 @@ static int __alloc_and_insert_iova_range
 		curr_iova = rb_entry(curr, struct iova, node);
 	} while (curr && new_pfn <= curr_iova->pfn_hi);
 
-	if (limit_pfn < size || new_pfn < iovad->start_pfn) {
-		spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
-		return -ENOMEM;
-	}
+	if (limit_pfn < size || new_pfn < iovad->start_pfn)
+		goto iova32_full;
 
 	/* pfn_lo will point to size aligned address if size_aligned is set */
 	new->pfn_lo = new_pfn;
@@ -213,9 +218,12 @@ static int __alloc_and_insert_iova_range
 	__cached_rbnode_insert_update(iovad, new);
 
 	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
-
-
 	return 0;
+
+iova32_full:
+	iovad->max32_alloc_size = size;
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+	return -ENOMEM;
 }
 
 static struct kmem_cache *iova_cache;
--- a/include/linux/iova.h
+++ b/include/linux/iova.h
@@ -75,6 +75,7 @@ struct iova_domain {
 	unsigned long	granule;	/* pfn granularity for this domain */
 	unsigned long	start_pfn;	/* Lower limit for this domain */
 	unsigned long	dma_32bit_pfn;
+	unsigned long	max32_alloc_size; /* Size of last failed allocation */
 	struct iova	anchor;		/* rbtree lookup anchor */
 	struct iova_rcache rcaches[IOVA_RANGE_CACHE_MAX_SIZE];	/* IOVA range caches */