diff mbox series

[v3,2/4] dma-iommu: Add iommu_dma_opt_mapping_size()

Message ID 1654507822-168026-3-git-send-email-john.garry@huawei.com
State Superseded
Headers show
Series DMA mapping changes for SCSI core | expand

Commit Message

John Garry June 6, 2022, 9:30 a.m. UTC
Add the IOMMU callback for DMA mapping API dma_opt_mapping_size(), which
allows the drivers to know the optimal mapping limit and thus limit the
requested IOVA lengths.

This value is based on the IOVA rcache range limit, as IOVAs allocated
above this limit must always be newly allocated, which may be quite slow.

Signed-off-by: John Garry <john.garry@huawei.com>
Reviewed-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>
---
 drivers/iommu/dma-iommu.c | 6 ++++++
 drivers/iommu/iova.c      | 5 +++++
 include/linux/iova.h      | 2 ++
 3 files changed, 13 insertions(+)

Comments

Bart Van Assche June 8, 2022, 5:26 p.m. UTC | #1
On 6/6/22 02:30, John Garry via iommu wrote:
> +unsigned long iova_rcache_range(void)
> +{
> +	return PAGE_SIZE << (IOVA_RANGE_CACHE_MAX_SIZE - 1);
> +}

My understanding is that iova cache entries may be smaller than 
IOVA_RANGE_CACHE_MAX_SIZE and hence that even if code that uses the DMA 
mapping API respects this limit that a cache miss can still happen.

Thanks,

Bart.
John Garry June 8, 2022, 5:39 p.m. UTC | #2
On 08/06/2022 18:26, Bart Van Assche wrote:
> On 6/6/22 02:30, John Garry via iommu wrote:
>> +unsigned long iova_rcache_range(void)
>> +{
>> +    return PAGE_SIZE << (IOVA_RANGE_CACHE_MAX_SIZE - 1);
>> +}
> 
> My understanding is that iova cache entries may be smaller than 
> IOVA_RANGE_CACHE_MAX_SIZE and hence that even if code that uses the DMA 
> mapping API respects this limit that a cache miss can still happen.

Sure, a cache miss may still happen - however once we have stressed the 
system for a while then the rcaches fill up and don't fail often, or 
often enough to be noticeable compared to not having a cached IOVAs at all.

Thanks,
john
John Garry June 14, 2022, 1:12 p.m. UTC | #3
On 06/06/2022 10:30, John Garry wrote:
> Add the IOMMU callback for DMA mapping API dma_opt_mapping_size(), which
> allows the drivers to know the optimal mapping limit and thus limit the
> requested IOVA lengths.
> 
> This value is based on the IOVA rcache range limit, as IOVAs allocated
> above this limit must always be newly allocated, which may be quite slow.
> 

Can I please get some sort of ack from the IOMMU people on this one?

Thanks,
John

EOM

> Signed-off-by: John Garry <john.garry@huawei.com>
> Reviewed-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>
> ---
>   drivers/iommu/dma-iommu.c | 6 ++++++
>   drivers/iommu/iova.c      | 5 +++++
>   include/linux/iova.h      | 2 ++
>   3 files changed, 13 insertions(+)
> 
> diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
> index f90251572a5d..9e1586447ee8 100644
> --- a/drivers/iommu/dma-iommu.c
> +++ b/drivers/iommu/dma-iommu.c
> @@ -1459,6 +1459,11 @@ static unsigned long iommu_dma_get_merge_boundary(struct device *dev)
>   	return (1UL << __ffs(domain->pgsize_bitmap)) - 1;
>   }
>   
> +static size_t iommu_dma_opt_mapping_size(void)
> +{
> +	return iova_rcache_range();
> +}
> +
>   static const struct dma_map_ops iommu_dma_ops = {
>   	.alloc			= iommu_dma_alloc,
>   	.free			= iommu_dma_free,
> @@ -1479,6 +1484,7 @@ static const struct dma_map_ops iommu_dma_ops = {
>   	.map_resource		= iommu_dma_map_resource,
>   	.unmap_resource		= iommu_dma_unmap_resource,
>   	.get_merge_boundary	= iommu_dma_get_merge_boundary,
> +	.opt_mapping_size	= iommu_dma_opt_mapping_size,
>   };
>   
>   /*
> diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
> index db77aa675145..9f00b58d546e 100644
> --- a/drivers/iommu/iova.c
> +++ b/drivers/iommu/iova.c
> @@ -26,6 +26,11 @@ static unsigned long iova_rcache_get(struct iova_domain *iovad,
>   static void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad);
>   static void free_iova_rcaches(struct iova_domain *iovad);
>   
> +unsigned long iova_rcache_range(void)
> +{
> +	return PAGE_SIZE << (IOVA_RANGE_CACHE_MAX_SIZE - 1);
> +}
> +
>   static int iova_cpuhp_dead(unsigned int cpu, struct hlist_node *node)
>   {
>   	struct iova_domain *iovad;
> diff --git a/include/linux/iova.h b/include/linux/iova.h
> index 320a70e40233..c6ba6d95d79c 100644
> --- a/include/linux/iova.h
> +++ b/include/linux/iova.h
> @@ -79,6 +79,8 @@ static inline unsigned long iova_pfn(struct iova_domain *iovad, dma_addr_t iova)
>   int iova_cache_get(void);
>   void iova_cache_put(void);
>   
> +unsigned long iova_rcache_range(void);
> +
>   void free_iova(struct iova_domain *iovad, unsigned long pfn);
>   void __free_iova(struct iova_domain *iovad, struct iova *iova);
>   struct iova *alloc_iova(struct iova_domain *iovad, unsigned long size,
John Garry June 23, 2022, 8:38 a.m. UTC | #4
On 14/06/2022 14:12, John Garry wrote:
> On 06/06/2022 10:30, John Garry wrote:
>> Add the IOMMU callback for DMA mapping API dma_opt_mapping_size(), which
>> allows the drivers to know the optimal mapping limit and thus limit the
>> requested IOVA lengths.
>>
>> This value is based on the IOVA rcache range limit, as IOVAs allocated
>> above this limit must always be newly allocated, which may be quite slow.
>>
> 
> Can I please get some sort of ack from the IOMMU people on this one?
> 

Another request for an ack please.

Thanks,
john

> 
>> Signed-off-by: John Garry <john.garry@huawei.com>
>> Reviewed-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>
>> ---
>>   drivers/iommu/dma-iommu.c | 6 ++++++
>>   drivers/iommu/iova.c      | 5 +++++
>>   include/linux/iova.h      | 2 ++
>>   3 files changed, 13 insertions(+)
>>
>> diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
>> index f90251572a5d..9e1586447ee8 100644
>> --- a/drivers/iommu/dma-iommu.c
>> +++ b/drivers/iommu/dma-iommu.c
>> @@ -1459,6 +1459,11 @@ static unsigned long 
>> iommu_dma_get_merge_boundary(struct device *dev)
>>       return (1UL << __ffs(domain->pgsize_bitmap)) - 1;
>>   }
>> +static size_t iommu_dma_opt_mapping_size(void)
>> +{
>> +    return iova_rcache_range();
>> +}
>> +
>>   static const struct dma_map_ops iommu_dma_ops = {
>>       .alloc            = iommu_dma_alloc,
>>       .free            = iommu_dma_free,
>> @@ -1479,6 +1484,7 @@ static const struct dma_map_ops iommu_dma_ops = {
>>       .map_resource        = iommu_dma_map_resource,
>>       .unmap_resource        = iommu_dma_unmap_resource,
>>       .get_merge_boundary    = iommu_dma_get_merge_boundary,
>> +    .opt_mapping_size    = iommu_dma_opt_mapping_size,
>>   };
>>   /*
>> diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
>> index db77aa675145..9f00b58d546e 100644
>> --- a/drivers/iommu/iova.c
>> +++ b/drivers/iommu/iova.c
>> @@ -26,6 +26,11 @@ static unsigned long iova_rcache_get(struct 
>> iova_domain *iovad,
>>   static void free_cpu_cached_iovas(unsigned int cpu, struct 
>> iova_domain *iovad);
>>   static void free_iova_rcaches(struct iova_domain *iovad);
>> +unsigned long iova_rcache_range(void)
>> +{
>> +    return PAGE_SIZE << (IOVA_RANGE_CACHE_MAX_SIZE - 1);
>> +}
>> +
>>   static int iova_cpuhp_dead(unsigned int cpu, struct hlist_node *node)
>>   {
>>       struct iova_domain *iovad;
>> diff --git a/include/linux/iova.h b/include/linux/iova.h
>> index 320a70e40233..c6ba6d95d79c 100644
>> --- a/include/linux/iova.h
>> +++ b/include/linux/iova.h
>> @@ -79,6 +79,8 @@ static inline unsigned long iova_pfn(struct 
>> iova_domain *iovad, dma_addr_t iova)
>>   int iova_cache_get(void);
>>   void iova_cache_put(void);
>> +unsigned long iova_rcache_range(void);
>> +
>>   void free_iova(struct iova_domain *iovad, unsigned long pfn);
>>   void __free_iova(struct iova_domain *iovad, struct iova *iova);
>>   struct iova *alloc_iova(struct iova_domain *iovad, unsigned long size,
>
diff mbox series

Patch

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index f90251572a5d..9e1586447ee8 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -1459,6 +1459,11 @@  static unsigned long iommu_dma_get_merge_boundary(struct device *dev)
 	return (1UL << __ffs(domain->pgsize_bitmap)) - 1;
 }
 
+static size_t iommu_dma_opt_mapping_size(void)
+{
+	return iova_rcache_range();
+}
+
 static const struct dma_map_ops iommu_dma_ops = {
 	.alloc			= iommu_dma_alloc,
 	.free			= iommu_dma_free,
@@ -1479,6 +1484,7 @@  static const struct dma_map_ops iommu_dma_ops = {
 	.map_resource		= iommu_dma_map_resource,
 	.unmap_resource		= iommu_dma_unmap_resource,
 	.get_merge_boundary	= iommu_dma_get_merge_boundary,
+	.opt_mapping_size	= iommu_dma_opt_mapping_size,
 };
 
 /*
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index db77aa675145..9f00b58d546e 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -26,6 +26,11 @@  static unsigned long iova_rcache_get(struct iova_domain *iovad,
 static void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad);
 static void free_iova_rcaches(struct iova_domain *iovad);
 
+unsigned long iova_rcache_range(void)
+{
+	return PAGE_SIZE << (IOVA_RANGE_CACHE_MAX_SIZE - 1);
+}
+
 static int iova_cpuhp_dead(unsigned int cpu, struct hlist_node *node)
 {
 	struct iova_domain *iovad;
diff --git a/include/linux/iova.h b/include/linux/iova.h
index 320a70e40233..c6ba6d95d79c 100644
--- a/include/linux/iova.h
+++ b/include/linux/iova.h
@@ -79,6 +79,8 @@  static inline unsigned long iova_pfn(struct iova_domain *iovad, dma_addr_t iova)
 int iova_cache_get(void);
 void iova_cache_put(void);
 
+unsigned long iova_rcache_range(void);
+
 void free_iova(struct iova_domain *iovad, unsigned long pfn);
 void __free_iova(struct iova_domain *iovad, struct iova *iova);
 struct iova *alloc_iova(struct iova_domain *iovad, unsigned long size,