diff mbox

arm: dma mapping: export arm iommu functions

Message ID 1356592458-11077-1-git-send-email-prathyush.k@samsung.com
State Accepted
Commit 18177d12c0cee5646c7c2045ea90ddf882011c97
Headers show

Commit Message

Prathyush Dec. 27, 2012, 7:14 a.m. UTC
This patch adds EXPORT_SYMBOL calls to the three arm iommu
functions - arm_iommu_create_mapping, arm_iommu_free_mapping
and arm_iommu_attach_device. These functions can now be called
from dynamic modules.

Signed-off-by: Prathyush K <prathyush.k@samsung.com>
---
 arch/arm/mm/dma-mapping.c | 3 +++
 1 file changed, 3 insertions(+)

Comments

Marek Szyprowski Dec. 27, 2012, 2:15 p.m. UTC | #1
Hello,

On 12/27/2012 8:14 AM, Prathyush K wrote:
> This patch adds EXPORT_SYMBOL calls to the three arm iommu
> functions - arm_iommu_create_mapping, arm_iommu_free_mapping
> and arm_iommu_attach_device. These functions can now be called
> from dynamic modules.

Could You describe a bit more why those functions might be needed by 
dynamic modules?

> Signed-off-by: Prathyush K <prathyush.k@samsung.com>
> ---
>   arch/arm/mm/dma-mapping.c | 3 +++
>   1 file changed, 3 insertions(+)
>
> diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
> index 6b2fb87..c0f0f43 100644
> --- a/arch/arm/mm/dma-mapping.c
> +++ b/arch/arm/mm/dma-mapping.c
> @@ -1797,6 +1797,7 @@ err2:
>   err:
>   	return ERR_PTR(err);
>   }
> +EXPORT_SYMBOL(arm_iommu_create_mapping);

EXPORT_SYMOBL_GPL() ?

>   static void release_iommu_mapping(struct kref *kref)
>   {
> @@ -1813,6 +1814,7 @@ void arm_iommu_release_mapping(struct dma_iommu_mapping *mapping)
>   	if (mapping)
>   		kref_put(&mapping->kref, release_iommu_mapping);
>   }
> +EXPORT_SYMBOL(arm_iommu_release_mapping);
>   
>   /**
>    * arm_iommu_attach_device
> @@ -1841,5 +1843,6 @@ int arm_iommu_attach_device(struct device *dev,
>   	pr_debug("Attached IOMMU controller to %s device.\n", dev_name(dev));
>   	return 0;
>   }
> +EXPORT_SYMBOL(arm_iommu_attach_device);
>   
>   #endif

Best regards
Prathyush K Dec. 28, 2012, 4:23 a.m. UTC | #2
On Thu, Dec 27, 2012 at 7:45 PM, Marek Szyprowski
<m.szyprowski@samsung.com>wrote:

> Hello,
>
>
> On 12/27/2012 8:14 AM, Prathyush K wrote:
>
>> This patch adds EXPORT_SYMBOL calls to the three arm iommu
>> functions - arm_iommu_create_mapping, arm_iommu_free_mapping
>> and arm_iommu_attach_device. These functions can now be called
>> from dynamic modules.
>>
>
> Could You describe a bit more why those functions might be needed by
> dynamic modules?
>
> Hi Marek,

We are adding iommu support to exynos gsc and s5p-mfc.
And these two drivers need to be built as modules to improve boot time.

We're calling these three functions from inside these drivers:
e.g.
mapping = arm_iommu_create_mapping(&platform_bus_type, 0x20000000, SZ_256M,
4);
arm_iommu_attach_device(mdev, mapping);



>
>  Signed-off-by: Prathyush K <prathyush.k@samsung.com>
>> ---
>>   arch/arm/mm/dma-mapping.c | 3 +++
>>   1 file changed, 3 insertions(+)
>>
>> diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
>> index 6b2fb87..c0f0f43 100644
>> --- a/arch/arm/mm/dma-mapping.c
>> +++ b/arch/arm/mm/dma-mapping.c
>> @@ -1797,6 +1797,7 @@ err2:
>>   err:
>>         return ERR_PTR(err);
>>   }
>> +EXPORT_SYMBOL(arm_iommu_**create_mapping);
>>
>
> EXPORT_SYMOBL_GPL() ?
>
>
Right, it should be EXPORT_SYMOBL_GPL().

Will update in next patch.



>
>    static void release_iommu_mapping(struct kref *kref)
>>   {
>> @@ -1813,6 +1814,7 @@ void arm_iommu_release_mapping(**struct
>> dma_iommu_mapping *mapping)
>>         if (mapping)
>>                 kref_put(&mapping->kref, release_iommu_mapping);
>>   }
>> +EXPORT_SYMBOL(arm_iommu_**release_mapping);
>>     /**
>>    * arm_iommu_attach_device
>> @@ -1841,5 +1843,6 @@ int arm_iommu_attach_device(struct device *dev,
>>         pr_debug("Attached IOMMU controller to %s device.\n",
>> dev_name(dev));
>>         return 0;
>>   }
>> +EXPORT_SYMBOL(arm_iommu_**attach_device);
>>     #endif
>>
>
> Best regards
> --
> Marek Szyprowski
> Samsung Poland R&D Center
>
>
> Regards,
Prathyush
Olof Johansson Dec. 29, 2012, 6:53 a.m. UTC | #3
On Fri, Dec 28, 2012 at 09:53:47AM +0530, Prathyush K wrote:
> On Thu, Dec 27, 2012 at 7:45 PM, Marek Szyprowski
> <m.szyprowski@samsung.com>wrote:
> 
> > Hello,
> >
> >
> > On 12/27/2012 8:14 AM, Prathyush K wrote:
> >
> >> This patch adds EXPORT_SYMBOL calls to the three arm iommu
> >> functions - arm_iommu_create_mapping, arm_iommu_free_mapping
> >> and arm_iommu_attach_device. These functions can now be called
> >> from dynamic modules.
> >>
> >
> > Could You describe a bit more why those functions might be needed by
> > dynamic modules?
> >
> > Hi Marek,
> 
> We are adding iommu support to exynos gsc and s5p-mfc.
> And these two drivers need to be built as modules to improve boot time.
> 
> We're calling these three functions from inside these drivers:
> e.g.
> mapping = arm_iommu_create_mapping(&platform_bus_type, 0x20000000, SZ_256M,
> 4);
> arm_iommu_attach_device(mdev, mapping);

The driver shouldn't have to call these low-level functions directly,
something's wrong if you need that.

How is the DMA address management different here from other system/io mmus? is
that 256M window a hardware restriction?

-Olof
Subash Patel Jan. 1, 2013, 1:07 a.m. UTC | #4
On Friday 28 December 2012 10:53 PM, Olof Johansson wrote:
> On Fri, Dec 28, 2012 at 09:53:47AM +0530, Prathyush K wrote:
>> On Thu, Dec 27, 2012 at 7:45 PM, Marek Szyprowski
>> <m.szyprowski@samsung.com>wrote:
>>
>>> Hello,
>>>
>>>
>>> On 12/27/2012 8:14 AM, Prathyush K wrote:
>>>
>>>> This patch adds EXPORT_SYMBOL calls to the three arm iommu
>>>> functions - arm_iommu_create_mapping, arm_iommu_free_mapping
>>>> and arm_iommu_attach_device. These functions can now be called
>>>> from dynamic modules.
>>>>
>>>
>>> Could You describe a bit more why those functions might be needed by
>>> dynamic modules?
>>>
>>> Hi Marek,
>>
>> We are adding iommu support to exynos gsc and s5p-mfc.
>> And these two drivers need to be built as modules to improve boot time.
>>
>> We're calling these three functions from inside these drivers:
>> e.g.
>> mapping = arm_iommu_create_mapping(&platform_bus_type, 0x20000000, SZ_256M,
>> 4);
>> arm_iommu_attach_device(mdev, mapping);
>
> The driver shouldn't have to call these low-level functions directly,
> something's wrong if you need that.

These are not truly low-level calls, but arm specific wrappers to the 
dma-mapping implementations. Drivers need to call former to declare 
mappings requirement needed for their IOMMU and later to start using it.

>
> How is the DMA address management different here from other system/io mmus? is
> that 256M window a hardware restriction?

No, each IOMMU is capable of 4G. But to keep the IOMMU address space to 
what is required, various sizes were used earlier and later fixed on to 
256M. This can be increased if the drivers demand more buffers mapped to 
the device at anytime.


Regards,
Subash

>
> -Olof
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org.  For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
>
diff mbox

Patch

diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 6b2fb87..c0f0f43 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -1797,6 +1797,7 @@  err2:
 err:
 	return ERR_PTR(err);
 }
+EXPORT_SYMBOL(arm_iommu_create_mapping);
 
 static void release_iommu_mapping(struct kref *kref)
 {
@@ -1813,6 +1814,7 @@  void arm_iommu_release_mapping(struct dma_iommu_mapping *mapping)
 	if (mapping)
 		kref_put(&mapping->kref, release_iommu_mapping);
 }
+EXPORT_SYMBOL(arm_iommu_release_mapping);
 
 /**
  * arm_iommu_attach_device
@@ -1841,5 +1843,6 @@  int arm_iommu_attach_device(struct device *dev,
 	pr_debug("Attached IOMMU controller to %s device.\n", dev_name(dev));
 	return 0;
 }
+EXPORT_SYMBOL(arm_iommu_attach_device);
 
 #endif