[PATCH v3] iommu/iova: Optimise attempts to allocate iova from 32bit address range

[PATCH v3] iommu/iova: Optimise attempts to allocate iova from 32bit address range

[Ganapatrao Kulkarni]

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.

Signed-off-by: Ganapatrao Kulkarni <ganapatrao.kulkarni-YGCgFSpz5w/QT0dZR+AlfA@public.gmane.org>
---
v3:
    Update with comments [3] from Robin Murphy <robin.murphy-5wv7dgnIgG8@public.gmane.org>

[3] https://lkml.org/lkml/2018/8/13/116

v2: update with comments [2] from Robin Murphy <robin.murphy-5wv7dgnIgG8@public.gmane.org>

[2] https://lkml.org/lkml/2018/8/7/166

v1: Based on comments from Robin Murphy <robin.murphy-5wv7dgnIgG8@public.gmane.org>
for patch [1]

[1] https://lkml.org/lkml/2018/4/19/780

 drivers/iommu/iova.c | 22 +++++++++++++++-------
 include/linux/iova.h |  1 +
 2 files changed, 16 insertions(+), 7 deletions(-)

diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index 83fe262..28ba8b6 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -56,6 +56,7 @@ init_iova_domain(struct iova_domain *iovad, unsigned long granule,
 	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;
@@ -139,8 +140,10 @@ __cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free)
 
 	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)
@@ -190,6 +193,10 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
 
 	/* 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 {
@@ -200,10 +207,8 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
 		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;
@@ -214,9 +219,12 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
 	__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;
diff --git a/include/linux/iova.h b/include/linux/iova.h
index 928442d..a930411 100644
--- 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 */
 
-- 
2.9.4

Re: [PATCH v3] iommu/iova: Optimise attempts to allocate iova from 32bit address range

[Robin Murphy]

On 14/08/18 04:21, Ganapatrao Kulkarni wrote:
> 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>
> ---
> v3:
>      Update with comments [3] from Robin Murphy <robin.murphy@arm.com>
> 
> [3] https://lkml.org/lkml/2018/8/13/116
> 
> v2: update with comments [2] from Robin Murphy <robin.murphy@arm.com>
> 
> [2] https://lkml.org/lkml/2018/8/7/166
> 
> v1: Based on comments from Robin Murphy <robin.murphy@arm.com>
> for patch [1]
> 
> [1] https://lkml.org/lkml/2018/4/19/780
> 
>   drivers/iommu/iova.c | 22 +++++++++++++++-------
>   include/linux/iova.h |  1 +
>   2 files changed, 16 insertions(+), 7 deletions(-)
> 
> diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
> index 83fe262..28ba8b6 100644
> --- a/drivers/iommu/iova.c
> +++ b/drivers/iommu/iova.c
> @@ -56,6 +56,7 @@ init_iova_domain(struct iova_domain *iovad, unsigned long granule,
>   	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;
> @@ -139,8 +140,10 @@ __cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free)
>   
>   	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)
> @@ -190,6 +193,10 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
>   
>   	/* 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 {
> @@ -200,10 +207,8 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
>   		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;
> @@ -214,9 +219,12 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
>   	__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;
> diff --git a/include/linux/iova.h b/include/linux/iova.h
> index 928442d..a930411 100644
> --- 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 */
>   
>