[PATCH] ARM: dma: Drop __GFP_COMP for iommu dma memory allocations

[PATCH] ARM: dma: Drop __GFP_COMP for iommu dma memory allocations

[Richard Zhao]

__iommu_alloc_buffer wants to split pages after allocation in order to
reduce the memory footprint. This does not work well with __GFP_COMP
pages, so drop this flag before allocation

One failure example is snd_malloc_dev_pages call dma_alloc_coherent with
__GFP_COMP.

Signed-off-by: Richard Zhao <rizhao@nvidia.com>
---
 arch/arm/mm/dma-mapping.c |    9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index ef3e0f3..f7efffd 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -1314,6 +1314,15 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	if (gfp & GFP_ATOMIC)
 		return __iommu_alloc_atomic(dev, size, handle);
 
+	/*
+	 * Following is a work-around (a.k.a. hack) to prevent pages
+	 * with __GFP_COMP being passed to split_page() which cannot
+	 * handle them.  The real problem is that this flag probably
+	 * should be 0 on ARM as it is not supported on this
+	 * platform; see CONFIG_HUGETLBFS.
+	 */
+	gfp &= ~(__GFP_COMP);
+
 	pages = __iommu_alloc_buffer(dev, size, gfp, attrs);
 	if (!pages)
 		return NULL;
-- 
1.7.9.5

[PATCH] ARM: dma: Drop __GFP_COMP for iommu dma memory allocations

[Sergei Shtylyov]

Hello.

On 20-06-2013 16:31, Richard Zhao wrote:

> __iommu_alloc_buffer wants to split pages after allocation in order to
> reduce the memory footprint. This does not work well with __GFP_COMP
> pages, so drop this flag before allocation

> One failure example is snd_malloc_dev_pages call dma_alloc_coherent with
> __GFP_COMP.

> Signed-off-by: Richard Zhao <rizhao@nvidia.com>
> ---
>   arch/arm/mm/dma-mapping.c |    9 +++++++++
>   1 file changed, 9 insertions(+)

> diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
> index ef3e0f3..f7efffd 100644
> --- a/arch/arm/mm/dma-mapping.c
> +++ b/arch/arm/mm/dma-mapping.c
> @@ -1314,6 +1314,15 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
>   	if (gfp & GFP_ATOMIC)
>   		return __iommu_alloc_atomic(dev, size, handle);
>
> +	/*
> +	 * Following is a work-around (a.k.a. hack) to prevent pages
> +	 * with __GFP_COMP being passed to split_page() which cannot
> +	 * handle them.  The real problem is that this flag probably
> +	 * should be 0 on ARM as it is not supported on this
> +	 * platform; see CONFIG_HUGETLBFS.
> +	 */
> +	gfp &= ~(__GFP_COMP);

    Hm, what exactly is the sense you meant in using ()?

WBR, Sergei

[PATCH] ARM: dma: Drop __GFP_COMP for iommu dma memory allocations

[Richard Zhao]

On Thu, Jun 20, 2013 at 9:04 PM, Sergei Shtylyov
<sergei.shtylyov@cogentembedded.com> wrote:
> Hello.
>
>
> On 20-06-2013 16:31, Richard Zhao wrote:
>
>> __iommu_alloc_buffer wants to split pages after allocation in order to
>> reduce the memory footprint. This does not work well with __GFP_COMP
>> pages, so drop this flag before allocation
>
>
>> One failure example is snd_malloc_dev_pages call dma_alloc_coherent with
>> __GFP_COMP.
>
>
>> Signed-off-by: Richard Zhao <rizhao@nvidia.com>
>> ---
>>   arch/arm/mm/dma-mapping.c |    9 +++++++++
>>   1 file changed, 9 insertions(+)
>
>
>> diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
>> index ef3e0f3..f7efffd 100644
>> --- a/arch/arm/mm/dma-mapping.c
>> +++ b/arch/arm/mm/dma-mapping.c
>> @@ -1314,6 +1314,15 @@ static void *arm_iommu_alloc_attrs(struct device
>> *dev, size_t size,
>>         if (gfp & GFP_ATOMIC)
>>                 return __iommu_alloc_atomic(dev, size, handle);
>>
>> +       /*
>> +        * Following is a work-around (a.k.a. hack) to prevent pages
>> +        * with __GFP_COMP being passed to split_page() which cannot
>> +        * handle them.  The real problem is that this flag probably
>> +        * should be 0 on ARM as it is not supported on this
>> +        * platform; see CONFIG_HUGETLBFS.
>> +        */
>> +       gfp &= ~(__GFP_COMP);
>
>
>    Hm, what exactly is the sense you meant in using ()?

It's copy/paste from elsewhere in this file. At least it's consistent? :)

Re: [PATCH] ARM: dma: Drop __GFP_COMP for iommu dma memory allocations

[Hiroshi Doyu]

Richard Zhao <linuxzsc-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org> wrote @ Thu, 20 Jun 2013 15:40:50 +0200:

> >> +       /*
> >> +        * Following is a work-around (a.k.a. hack) to prevent pages
> >> +        * with __GFP_COMP being passed to split_page() which cannot
> >> +        * handle them.  The real problem is that this flag probably
> >> +        * should be 0 on ARM as it is not supported on this
> >> +        * platform; see CONFIG_HUGETLBFS.
> >> +        */
> >> +       gfp &= ~(__GFP_COMP);
> >
> >
> >    Hm, what exactly is the sense you meant in using ()?
> 
> It's copy/paste from elsewhere in this file. At least it's consistent? :)

I almost sent the exact same one, actually it was under internal reivew;)

This patch is similar but is the iommu version of:


commit ea2e7057c0234cfb8b09467d8f137760d371fc72
Author: Sumit Bhattacharya <sumitb-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
Date:   Thu Nov 24 00:47:12 2011 +0100

    ARM: 7172/1: dma: Drop GFP_COMP for DMA memory allocations
    
    dma_alloc_coherent wants to split pages after allocation in order to
    reduce the memory footprint. This does not work well with GFP_COMP
    pages, so drop this flag before allocation.
    
    This patch is ported from arch/avr32
    (commit 3611553ef985ef7c5863c8a94641738addd04cff).
    
    [swarren: s/HUGETLB_PAGE/HUGETLBFS/ in comment, minor comment cleanup]
    
    Signed-off-by: Sumit Bhattacharya <sumitb-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
    Tested-by: Varun Colbert <vcolbert-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
    Signed-off-by: Stephen Warren <swarren-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
    Signed-off-by: Russell King <rmk+kernel-lFZ/pmaqli7XmaaqVzeoHQ@public.gmane.org>

diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index ab58456..1aa664a 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -332,6 +332,15 @@ __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp,
        struct page *page;
        void *addr;
 
+       /*
+        * Following is a work-around (a.k.a. hack) to prevent pages
+        * with __GFP_COMP being passed to split_page() which cannot
+        * handle them.  The real problem is that this flag probably
+        * should be 0 on ARM as it is not supported on this
+        * platform; see CONFIG_HUGETLBFS.
+        */
+       gfp &= ~(__GFP_COMP);
+
        *handle = ~0;
        size = PAGE_ALIGN(size);

[PATCH] ARM: dma: Drop __GFP_COMP for iommu dma memory allocations

[Hiroshi Doyu]

Richard Zhao <linuxzsc@gmail.com> wrote @ Thu, 20 Jun 2013 15:40:50 +0200:

> >> +       /*
> >> +        * Following is a work-around (a.k.a. hack) to prevent pages
> >> +        * with __GFP_COMP being passed to split_page() which cannot
> >> +        * handle them.  The real problem is that this flag probably
> >> +        * should be 0 on ARM as it is not supported on this
> >> +        * platform; see CONFIG_HUGETLBFS.
> >> +        */
> >> +       gfp &= ~(__GFP_COMP);
> >
> >
> >    Hm, what exactly is the sense you meant in using ()?
> 
> It's copy/paste from elsewhere in this file. At least it's consistent? :)

I almost sent the exact same one, actually it was under internal reivew;)

This patch is similar but is the iommu version of:


commit ea2e7057c0234cfb8b09467d8f137760d371fc72
Author: Sumit Bhattacharya <sumitb@nvidia.com>
Date:   Thu Nov 24 00:47:12 2011 +0100

    ARM: 7172/1: dma: Drop GFP_COMP for DMA memory allocations
    
    dma_alloc_coherent wants to split pages after allocation in order to
    reduce the memory footprint. This does not work well with GFP_COMP
    pages, so drop this flag before allocation.
    
    This patch is ported from arch/avr32
    (commit 3611553ef985ef7c5863c8a94641738addd04cff).
    
    [swarren: s/HUGETLB_PAGE/HUGETLBFS/ in comment, minor comment cleanup]
    
    Signed-off-by: Sumit Bhattacharya <sumitb@nvidia.com>
    Tested-by: Varun Colbert <vcolbert@nvidia.com>
    Signed-off-by: Stephen Warren <swarren@nvidia.com>
    Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index ab58456..1aa664a 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -332,6 +332,15 @@ __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp,
        struct page *page;
        void *addr;
 
+       /*
+        * Following is a work-around (a.k.a. hack) to prevent pages
+        * with __GFP_COMP being passed to split_page() which cannot
+        * handle them.  The real problem is that this flag probably
+        * should be 0 on ARM as it is not supported on this
+        * platform; see CONFIG_HUGETLBFS.
+        */
+       gfp &= ~(__GFP_COMP);
+
        *handle = ~0;
        size = PAGE_ALIGN(size);

Re: [PATCH] ARM: dma: Drop __GFP_COMP for iommu dma memory allocations

[Richard Zhao]

On Thu, Jun 20, 2013 at 10:35:11PM +0800, Hiroshi Doyu wrote:
> Richard Zhao <linuxzsc-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org> wrote @ Thu, 20 Jun 2013 15:40:50 +0200:
> 
> > >> +       /*
> > >> +        * Following is a work-around (a.k.a. hack) to prevent pages
> > >> +        * with __GFP_COMP being passed to split_page() which cannot
> > >> +        * handle them.  The real problem is that this flag probably
> > >> +        * should be 0 on ARM as it is not supported on this
> > >> +        * platform; see CONFIG_HUGETLBFS.
> > >> +        */
> > >> +       gfp &= ~(__GFP_COMP);
> > >
> > >
> > >    Hm, what exactly is the sense you meant in using ()?
> > 
> > It's copy/paste from elsewhere in this file. At least it's consistent? :)
> 
> I almost sent the exact same one, actually it was under internal reivew;)
Ah, sorry I didn't search internal mails but only arm mail list for related
fix, since I thought it's not specific to tegra. Why not give it a
Reviewed-by or Tested-by?
> 
> This patch is similar but is the iommu version of:
Exactly.

Thanks
Richard
> 
> 
> commit ea2e7057c0234cfb8b09467d8f137760d371fc72
> Author: Sumit Bhattacharya <sumitb-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
> Date:   Thu Nov 24 00:47:12 2011 +0100
> 
>     ARM: 7172/1: dma: Drop GFP_COMP for DMA memory allocations
>     
>     dma_alloc_coherent wants to split pages after allocation in order to
>     reduce the memory footprint. This does not work well with GFP_COMP
>     pages, so drop this flag before allocation.
>     
>     This patch is ported from arch/avr32
>     (commit 3611553ef985ef7c5863c8a94641738addd04cff).
>     
>     [swarren: s/HUGETLB_PAGE/HUGETLBFS/ in comment, minor comment cleanup]
>     
>     Signed-off-by: Sumit Bhattacharya <sumitb-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
>     Tested-by: Varun Colbert <vcolbert-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
>     Signed-off-by: Stephen Warren <swarren-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
>     Signed-off-by: Russell King <rmk+kernel-lFZ/pmaqli7XmaaqVzeoHQ@public.gmane.org>
> 
> diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
> index ab58456..1aa664a 100644
> --- a/arch/arm/mm/dma-mapping.c
> +++ b/arch/arm/mm/dma-mapping.c
> @@ -332,6 +332,15 @@ __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp,
>         struct page *page;
>         void *addr;
>  
> +       /*
> +        * Following is a work-around (a.k.a. hack) to prevent pages
> +        * with __GFP_COMP being passed to split_page() which cannot
> +        * handle them.  The real problem is that this flag probably
> +        * should be 0 on ARM as it is not supported on this
> +        * platform; see CONFIG_HUGETLBFS.
> +        */
> +       gfp &= ~(__GFP_COMP);
> +
>         *handle = ~0;
>         size = PAGE_ALIGN(size);

[PATCH] ARM: dma: Drop __GFP_COMP for iommu dma memory allocations

[Richard Zhao]

On Thu, Jun 20, 2013 at 10:35:11PM +0800, Hiroshi Doyu wrote:
> Richard Zhao <linuxzsc@gmail.com> wrote @ Thu, 20 Jun 2013 15:40:50 +0200:
> 
> > >> +       /*
> > >> +        * Following is a work-around (a.k.a. hack) to prevent pages
> > >> +        * with __GFP_COMP being passed to split_page() which cannot
> > >> +        * handle them.  The real problem is that this flag probably
> > >> +        * should be 0 on ARM as it is not supported on this
> > >> +        * platform; see CONFIG_HUGETLBFS.
> > >> +        */
> > >> +       gfp &= ~(__GFP_COMP);
> > >
> > >
> > >    Hm, what exactly is the sense you meant in using ()?
> > 
> > It's copy/paste from elsewhere in this file. At least it's consistent? :)
> 
> I almost sent the exact same one, actually it was under internal reivew;)
Ah, sorry I didn't search internal mails but only arm mail list for related
fix, since I thought it's not specific to tegra. Why not give it a
Reviewed-by or Tested-by?
> 
> This patch is similar but is the iommu version of:
Exactly.

Thanks
Richard
> 
> 
> commit ea2e7057c0234cfb8b09467d8f137760d371fc72
> Author: Sumit Bhattacharya <sumitb@nvidia.com>
> Date:   Thu Nov 24 00:47:12 2011 +0100
> 
>     ARM: 7172/1: dma: Drop GFP_COMP for DMA memory allocations
>     
>     dma_alloc_coherent wants to split pages after allocation in order to
>     reduce the memory footprint. This does not work well with GFP_COMP
>     pages, so drop this flag before allocation.
>     
>     This patch is ported from arch/avr32
>     (commit 3611553ef985ef7c5863c8a94641738addd04cff).
>     
>     [swarren: s/HUGETLB_PAGE/HUGETLBFS/ in comment, minor comment cleanup]
>     
>     Signed-off-by: Sumit Bhattacharya <sumitb@nvidia.com>
>     Tested-by: Varun Colbert <vcolbert@nvidia.com>
>     Signed-off-by: Stephen Warren <swarren@nvidia.com>
>     Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
> 
> diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
> index ab58456..1aa664a 100644
> --- a/arch/arm/mm/dma-mapping.c
> +++ b/arch/arm/mm/dma-mapping.c
> @@ -332,6 +332,15 @@ __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp,
>         struct page *page;
>         void *addr;
>  
> +       /*
> +        * Following is a work-around (a.k.a. hack) to prevent pages
> +        * with __GFP_COMP being passed to split_page() which cannot
> +        * handle them.  The real problem is that this flag probably
> +        * should be 0 on ARM as it is not supported on this
> +        * platform; see CONFIG_HUGETLBFS.
> +        */
> +       gfp &= ~(__GFP_COMP);
> +
>         *handle = ~0;
>         size = PAGE_ALIGN(size);

[PATCH] ARM: dma: Drop __GFP_COMP for iommu dma memory allocations

[Marek Szyprowski]

Hello,

On 6/20/2013 3:04 PM, Sergei Shtylyov wrote:
> Hello.
>
> On 20-06-2013 16:31, Richard Zhao wrote:
>
>> __iommu_alloc_buffer wants to split pages after allocation in order to
>> reduce the memory footprint. This does not work well with __GFP_COMP
>> pages, so drop this flag before allocation
>
>> One failure example is snd_malloc_dev_pages call dma_alloc_coherent with
>> __GFP_COMP.
>
>> Signed-off-by: Richard Zhao <rizhao@nvidia.com>
>> ---
>>   arch/arm/mm/dma-mapping.c |    9 +++++++++
>>   1 file changed, 9 insertions(+)
>
>> diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
>> index ef3e0f3..f7efffd 100644
>> --- a/arch/arm/mm/dma-mapping.c
>> +++ b/arch/arm/mm/dma-mapping.c
>> @@ -1314,6 +1314,15 @@ static void *arm_iommu_alloc_attrs(struct 
>> device *dev, size_t size,
>>       if (gfp & GFP_ATOMIC)
>>           return __iommu_alloc_atomic(dev, size, handle);
>>
>> +    /*
>> +     * Following is a work-around (a.k.a. hack) to prevent pages
>> +     * with __GFP_COMP being passed to split_page() which cannot
>> +     * handle them.  The real problem is that this flag probably
>> +     * should be 0 on ARM as it is not supported on this
>> +     * platform; see CONFIG_HUGETLBFS.
>> +     */
>> +    gfp &= ~(__GFP_COMP);
>
>    Hm, what exactly is the sense you meant in using ()?

I think that those parentheses come from the first patch, which disabled 
__GFP_COMP
in dma-mapping allocations: 3611553ef98 ("[AVR32] Drop GFP_COMP for DMA 
memory
allocations"). I would like to take this patch to the dma-mapping tree 
together with
other changes related to iommu integration code.

Best regards
-- 
Marek Szyprowski
Samsung R&D Institute Poland

[PATCH] ARM: dma: Drop __GFP_COMP for iommu dma memory allocations

[Richard Zhao]

On Fri, Jun 21, 2013 at 5:33 PM, Marek Szyprowski
<m.szyprowski@samsung.com> wrote:> Hello,
>
>
> On 6/20/2013 3:04 PM, Sergei Shtylyov wrote:
>>
>> Hello.
>>
>> On 20-06-2013 16:31, Richard Zhao wrote:
>>
>>> __iommu_alloc_buffer wants to split pages after allocation in order to
>>> reduce the memory footprint. This does not work well with __GFP_COMP
>>> pages, so drop this flag before allocation
>>
>>
>>> One failure example is snd_malloc_dev_pages call dma_alloc_coherent with
>>> __GFP_COMP.
>>
>>
>>> Signed-off-by: Richard Zhao <rizhao@nvidia.com>
>>> ---
>>>   arch/arm/mm/dma-mapping.c |    9 +++++++++
>>>   1 file changed, 9 insertions(+)
>>
>>
>>> diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
>>> index ef3e0f3..f7efffd 100644
>>> --- a/arch/arm/mm/dma-mapping.c
>>> +++ b/arch/arm/mm/dma-mapping.c
>>> @@ -1314,6 +1314,15 @@ static void *arm_iommu_alloc_attrs(struct device
>>> *dev, size_t size,
>>>       if (gfp & GFP_ATOMIC)
>>>           return __iommu_alloc_atomic(dev, size, handle);
>>>
>>> +    /*
>>> +     * Following is a work-around (a.k.a. hack) to prevent pages
>>> +     * with __GFP_COMP being passed to split_page() which cannot
>>> +     * handle them.  The real problem is that this flag probably
>>> +     * should be 0 on ARM as it is not supported on this
>>> +     * platform; see CONFIG_HUGETLBFS.
>>> +     */
>>> +    gfp &= ~(__GFP_COMP);
>>
>>
>>    Hm, what exactly is the sense you meant in using ()?
>
>
> I think that those parentheses come from the first patch, which disabled
> __GFP_COMP
> in dma-mapping allocations: 3611553ef98 ("[AVR32] Drop GFP_COMP for DMA
> memory
> allocations"). I would like to take this patch to the dma-mapping tree
> together with
> other changes related to iommu integration code.
Thanks! I'm not sure. Do we still have time to have this fix on 3.10?

Richard
>
> Best regards
> --
> Marek Szyprowski
> Samsung R&D Institute Poland
>
>
>
>
> _______________________________________________
> linux-arm-kernel mailing list
> linux-arm-kernel at lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/linux-arm-kernel