[PATCH] iommu/dma: Use NUMA aware memory allocations in __iommu_dma_alloc_pages()

[PATCH] iommu/dma: Use NUMA aware memory allocations in __iommu_dma_alloc_pages()

[John Garry]

Change function __iommu_dma_alloc_pages() to allocate memory/pages
for DMA from respective device NUMA node.

Originally-from: Ganapatrao Kulkarni <ganapatrao.kulkarni@cavium.com>
Signed-off-by: John Garry <john.garry@huawei.com>
---

This patch was originally posted by Ganapatrao in [1] *.

However, after initial review, it was never reposted (due to lack of
cycles, I think). In addition, the functionality in its sibling patches
were merged through patches, as mentioned in [2]; this also refers to a
discussion on device local allocations vs CPU local allocations for DMA
pool, and which is better [3].

However, as mentioned in [3], dma_alloc_coherent() uses the locality
information from the device - as in direct DMA - so this patch is just
applying this same policy.

[1] https://lore.kernel.org/patchwork/patch/833004/
[2] https://lkml.org/lkml/2018/8/22/391
[3] https://www.mail-archive.com/linux-kernel@vger.kernel.org/msg1692998.html

* Authorship on this updated patch may need to be fixed - I add not want to
  add Ganapatrao's SOB without permission.

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index d1b0475..ada00bc 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -449,20 +449,17 @@ static void __iommu_dma_free_pages(struct page **pages, int count)
 	kvfree(pages);
 }
 
-static struct page **__iommu_dma_alloc_pages(unsigned int count,
-		unsigned long order_mask, gfp_t gfp)
+static struct page **__iommu_dma_alloc_pages(struct device *dev,
+		unsigned int count, unsigned long order_mask, gfp_t gfp)
 {
 	struct page **pages;
-	unsigned int i = 0, array_size = count * sizeof(*pages);
+	unsigned int i = 0, nid = dev_to_node(dev);
 
 	order_mask &= (2U << MAX_ORDER) - 1;
 	if (!order_mask)
 		return NULL;
 
-	if (array_size <= PAGE_SIZE)
-		pages = kzalloc(array_size, GFP_KERNEL);
-	else
-		pages = vzalloc(array_size);
+	pages = kvzalloc_node(count * sizeof(*pages), GFP_KERNEL, nid);
 	if (!pages)
 		return NULL;
 
@@ -483,8 +480,10 @@ static struct page **__iommu_dma_alloc_pages(unsigned int count,
 			unsigned int order = __fls(order_mask);
 
 			order_size = 1U << order;
-			page = alloc_pages((order_mask - order_size) ?
-					   gfp | __GFP_NORETRY : gfp, order);
+			page = alloc_pages_node(nid,
+						(order_mask - order_size) ?
+						gfp | __GFP_NORETRY : gfp,
+						order);
 			if (!page)
 				continue;
 			if (!order)
@@ -569,7 +568,8 @@ struct page **iommu_dma_alloc(struct device *dev, size_t size, gfp_t gfp,
 		alloc_sizes = min_size;
 
 	count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	pages = __iommu_dma_alloc_pages(count, alloc_sizes >> PAGE_SHIFT, gfp);
+	pages = __iommu_dma_alloc_pages(dev, count, alloc_sizes >> PAGE_SHIFT,
+					gfp);
 	if (!pages)
 		return NULL;
 
-- 
1.9.1

Re: [PATCH] iommu/dma: Use NUMA aware memory allocations in __iommu_dma_alloc_pages()

[John Garry]

On 08/11/2018 17:55, John Garry wrote:
> Change function __iommu_dma_alloc_pages() to allocate memory/pages
> for DMA from respective device NUMA node.
>

Ping.... a friendly reminder on this patch.

Thanks

> Originally-from: Ganapatrao Kulkarni <ganapatrao.kulkarni@cavium.com>
> Signed-off-by: John Garry <john.garry@huawei.com>
> ---
>
> This patch was originally posted by Ganapatrao in [1] *.
>
> However, after initial review, it was never reposted (due to lack of
> cycles, I think). In addition, the functionality in its sibling patches
> were merged through patches, as mentioned in [2]; this also refers to a
> discussion on device local allocations vs CPU local allocations for DMA
> pool, and which is better [3].
>
> However, as mentioned in [3], dma_alloc_coherent() uses the locality
> information from the device - as in direct DMA - so this patch is just
> applying this same policy.
>
> [1] https://lore.kernel.org/patchwork/patch/833004/
> [2] https://lkml.org/lkml/2018/8/22/391
> [3] https://www.mail-archive.com/linux-kernel@vger.kernel.org/msg1692998.html
>
> * Authorship on this updated patch may need to be fixed - I add not want to
>   add Ganapatrao's SOB without permission.
>
> diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
> index d1b0475..ada00bc 100644
> --- a/drivers/iommu/dma-iommu.c
> +++ b/drivers/iommu/dma-iommu.c
> @@ -449,20 +449,17 @@ static void __iommu_dma_free_pages(struct page **pages, int count)
>  	kvfree(pages);
>  }
>
> -static struct page **__iommu_dma_alloc_pages(unsigned int count,
> -		unsigned long order_mask, gfp_t gfp)
> +static struct page **__iommu_dma_alloc_pages(struct device *dev,
> +		unsigned int count, unsigned long order_mask, gfp_t gfp)
>  {
>  	struct page **pages;
> -	unsigned int i = 0, array_size = count * sizeof(*pages);
> +	unsigned int i = 0, nid = dev_to_node(dev);
>
>  	order_mask &= (2U << MAX_ORDER) - 1;
>  	if (!order_mask)
>  		return NULL;
>
> -	if (array_size <= PAGE_SIZE)
> -		pages = kzalloc(array_size, GFP_KERNEL);
> -	else
> -		pages = vzalloc(array_size);
> +	pages = kvzalloc_node(count * sizeof(*pages), GFP_KERNEL, nid);
>  	if (!pages)
>  		return NULL;
>
> @@ -483,8 +480,10 @@ static struct page **__iommu_dma_alloc_pages(unsigned int count,
>  			unsigned int order = __fls(order_mask);
>
>  			order_size = 1U << order;
> -			page = alloc_pages((order_mask - order_size) ?
> -					   gfp | __GFP_NORETRY : gfp, order);
> +			page = alloc_pages_node(nid,
> +						(order_mask - order_size) ?
> +						gfp | __GFP_NORETRY : gfp,
> +						order);
>  			if (!page)
>  				continue;
>  			if (!order)
> @@ -569,7 +568,8 @@ struct page **iommu_dma_alloc(struct device *dev, size_t size, gfp_t gfp,
>  		alloc_sizes = min_size;
>
>  	count = PAGE_ALIGN(size) >> PAGE_SHIFT;
> -	pages = __iommu_dma_alloc_pages(count, alloc_sizes >> PAGE_SHIFT, gfp);
> +	pages = __iommu_dma_alloc_pages(dev, count, alloc_sizes >> PAGE_SHIFT,
> +					gfp);
>  	if (!pages)
>  		return NULL;
>
>

Re: [PATCH] iommu/dma: Use NUMA aware memory allocations in __iommu_dma_alloc_pages()

[Ganapatrao Kulkarni]

Hi John,

On Tue, Nov 20, 2018 at 3:35 PM John Garry <john.garry@huawei.com> wrote:
>
> On 08/11/2018 17:55, John Garry wrote:
> > Change function __iommu_dma_alloc_pages() to allocate memory/pages
> > for DMA from respective device NUMA node.
> >
>
> Ping.... a friendly reminder on this patch.
>
> Thanks
>
> > Originally-from: Ganapatrao Kulkarni <ganapatrao.kulkarni@cavium.com>
> > Signed-off-by: John Garry <john.garry@huawei.com>
> > ---
> >
> > This patch was originally posted by Ganapatrao in [1] *.
> >
> > However, after initial review, it was never reposted (due to lack of
> > cycles, I think). In addition, the functionality in its sibling patches
> > were merged through patches, as mentioned in [2]; this also refers to a
> > discussion on device local allocations vs CPU local allocations for DMA
> > pool, and which is better [3].
> >
> > However, as mentioned in [3], dma_alloc_coherent() uses the locality
> > information from the device - as in direct DMA - so this patch is just
> > applying this same policy.
> >
> > [1] https://lore.kernel.org/patchwork/patch/833004/
> > [2] https://lkml.org/lkml/2018/8/22/391
> > [3] https://www.mail-archive.com/linux-kernel@vger.kernel.org/msg1692998.html
> >
> > * Authorship on this updated patch may need to be fixed - I add not want to
> >   add Ganapatrao's SOB without permission.

thanks for taking this up. please feel free to add my SoB.
> >
> > diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
> > index d1b0475..ada00bc 100644
> > --- a/drivers/iommu/dma-iommu.c
> > +++ b/drivers/iommu/dma-iommu.c
> > @@ -449,20 +449,17 @@ static void __iommu_dma_free_pages(struct page **pages, int count)
> >       kvfree(pages);
> >  }
> >
> > -static struct page **__iommu_dma_alloc_pages(unsigned int count,
> > -             unsigned long order_mask, gfp_t gfp)
> > +static struct page **__iommu_dma_alloc_pages(struct device *dev,
> > +             unsigned int count, unsigned long order_mask, gfp_t gfp)
> >  {
> >       struct page **pages;
> > -     unsigned int i = 0, array_size = count * sizeof(*pages);
> > +     unsigned int i = 0, nid = dev_to_node(dev);
> >
> >       order_mask &= (2U << MAX_ORDER) - 1;
> >       if (!order_mask)
> >               return NULL;
> >
> > -     if (array_size <= PAGE_SIZE)
> > -             pages = kzalloc(array_size, GFP_KERNEL);
> > -     else
> > -             pages = vzalloc(array_size);
> > +     pages = kvzalloc_node(count * sizeof(*pages), GFP_KERNEL, nid);
> >       if (!pages)
> >               return NULL;
> >
> > @@ -483,8 +480,10 @@ static struct page **__iommu_dma_alloc_pages(unsigned int count,
> >                       unsigned int order = __fls(order_mask);
> >
> >                       order_size = 1U << order;
> > -                     page = alloc_pages((order_mask - order_size) ?
> > -                                        gfp | __GFP_NORETRY : gfp, order);
> > +                     page = alloc_pages_node(nid,
> > +                                             (order_mask - order_size) ?
> > +                                             gfp | __GFP_NORETRY : gfp,
> > +                                             order);
> >                       if (!page)
> >                               continue;
> >                       if (!order)
> > @@ -569,7 +568,8 @@ struct page **iommu_dma_alloc(struct device *dev, size_t size, gfp_t gfp,
> >               alloc_sizes = min_size;
> >
> >       count = PAGE_ALIGN(size) >> PAGE_SHIFT;
> > -     pages = __iommu_dma_alloc_pages(count, alloc_sizes >> PAGE_SHIFT, gfp);
> > +     pages = __iommu_dma_alloc_pages(dev, count, alloc_sizes >> PAGE_SHIFT,
> > +                                     gfp);
> >       if (!pages)
> >               return NULL;
> >
> >
>
>

thanks
Ganapat

Re: [PATCH] iommu/dma: Use NUMA aware memory allocations in __iommu_dma_alloc_pages()

[John Garry]

On 20/11/2018 10:09, Ganapatrao Kulkarni wrote:
> Hi John,
>
> On Tue, Nov 20, 2018 at 3:35 PM John Garry <john.garry@huawei.com> wrote:
>>
>> On 08/11/2018 17:55, John Garry wrote:
>>> Change function __iommu_dma_alloc_pages() to allocate memory/pages
>>> for DMA from respective device NUMA node.
>>>
>>
>> Ping.... a friendly reminder on this patch.
>>
>> Thanks
>>
>>> Originally-from: Ganapatrao Kulkarni <ganapatrao.kulkarni@cavium.com>
>>> Signed-off-by: John Garry <john.garry@huawei.com>
>>> ---
>>>
>>> This patch was originally posted by Ganapatrao in [1] *.
>>>
>>> However, after initial review, it was never reposted (due to lack of
>>> cycles, I think). In addition, the functionality in its sibling patches
>>> were merged through patches, as mentioned in [2]; this also refers to a
>>> discussion on device local allocations vs CPU local allocations for DMA
>>> pool, and which is better [3].
>>>
>>> However, as mentioned in [3], dma_alloc_coherent() uses the locality
>>> information from the device - as in direct DMA - so this patch is just
>>> applying this same policy.
>>>
>>> [1] https://lore.kernel.org/patchwork/patch/833004/
>>> [2] https://lkml.org/lkml/2018/8/22/391
>>> [3] https://www.mail-archive.com/linux-kernel@vger.kernel.org/msg1692998.html
>>>
>>> * Authorship on this updated patch may need to be fixed - I add not want to
>>>   add Ganapatrao's SOB without permission.
>
> thanks for taking this up. please feel free to add my SoB.

OK, I will also make you the author and repost.

Thanks,
John

>>>
>>> diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
>>> index d1b0475..ada00bc 100644
>>> --- a/drivers/iommu/dma-iommu.c
>>> +++ b/drivers/iommu/dma-iommu.c
>>> @@ -449,20 +449,17 @@ static void __iommu_dma_free_pages(struct page **pages, int count)
>>>       kvfree(pages);
>>>  }
>>>
>>> -static struct page **__iommu_dma_alloc_pages(unsigned int count,
>>> -             unsigned long order_mask, gfp_t gfp)
>>> +static struct page **__iommu_dma_alloc_pages(struct device *dev,
>>> +             unsigned int count, unsigned long order_mask, gfp_t gfp)
>>>  {
>>>       struct page **pages;
>>> -     unsigned int i = 0, array_size = count * sizeof(*pages);
>>> +     unsigned int i = 0, nid = dev_to_node(dev);
>>>
>>>       order_mask &= (2U << MAX_ORDER) - 1;
>>>       if (!order_mask)
>>>               return NULL;
>>>
>>> -     if (array_size <= PAGE_SIZE)
>>> -             pages = kzalloc(array_size, GFP_KERNEL);
>>> -     else
>>> -             pages = vzalloc(array_size);
>>> +     pages = kvzalloc_node(count * sizeof(*pages), GFP_KERNEL, nid);
>>>       if (!pages)
>>>               return NULL;
>>>
>>> @@ -483,8 +480,10 @@ static struct page **__iommu_dma_alloc_pages(unsigned int count,
>>>                       unsigned int order = __fls(order_mask);
>>>
>>>                       order_size = 1U << order;
>>> -                     page = alloc_pages((order_mask - order_size) ?
>>> -                                        gfp | __GFP_NORETRY : gfp, order);
>>> +                     page = alloc_pages_node(nid,
>>> +                                             (order_mask - order_size) ?
>>> +                                             gfp | __GFP_NORETRY : gfp,
>>> +                                             order);
>>>                       if (!page)
>>>                               continue;
>>>                       if (!order)
>>> @@ -569,7 +568,8 @@ struct page **iommu_dma_alloc(struct device *dev, size_t size, gfp_t gfp,
>>>               alloc_sizes = min_size;
>>>
>>>       count = PAGE_ALIGN(size) >> PAGE_SHIFT;
>>> -     pages = __iommu_dma_alloc_pages(count, alloc_sizes >> PAGE_SHIFT, gfp);
>>> +     pages = __iommu_dma_alloc_pages(dev, count, alloc_sizes >> PAGE_SHIFT,
>>> +                                     gfp);
>>>       if (!pages)
>>>               return NULL;
>>>
>>>
>>
>>
>
> thanks
> Ganapat
>
> .
>