diff mbox

ARM: relax conditions required for enabling Contiguous Memory Allocator

Message ID 1345443372-3824-1-git-send-email-m.szyprowski@samsung.com
State Accepted
Commit e092705bcd53de3bafc3053b0b55bf83e5d6711f
Headers show

Commit Message

Marek Szyprowski Aug. 20, 2012, 6:16 a.m. UTC
Contiguous Memory Allocator requires only paging and MMU enabled not
particular CPU architectures, so there is no need for strict dependency
on CPU type. This enables to use CMA on some older ARM v5 systems which
also might need large contiguous blocks for the multimedia processing hw
modules.

Reported-by: Prabhakar Lad <prabhakar.csengg@gmail.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
---
 arch/arm/Kconfig |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

Comments

Prabhakar Lad Aug. 20, 2012, 11:29 a.m. UTC | #1
Hi Marek,

Thanks for the patch.

On Monday 20 August 2012 11:46 AM, Marek Szyprowski wrote:
> Contiguous Memory Allocator requires only paging and MMU enabled not
> particular CPU architectures, so there is no need for strict dependency
> on CPU type. This enables to use CMA on some older ARM v5 systems which
> also might need large contiguous blocks for the multimedia processing hw
> modules.
> 
> Reported-by: Prabhakar Lad <prabhakar.csengg@gmail.com>

  Reported-by: Prabhakar Lad <prabhakar.lad@ti.com>
  Tested-by: Prabhakar Lad <prabhakar.lad@ti.com>

Thx,
--Prabhakar

> Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
> ---
>  arch/arm/Kconfig |    2 +-
>  1 files changed, 1 insertions(+), 1 deletions(-)
> 
> diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
> index e91c7cd..6ef75e2 100644
> --- a/arch/arm/Kconfig
> +++ b/arch/arm/Kconfig
> @@ -6,7 +6,7 @@ config ARM
>  	select HAVE_DMA_API_DEBUG
>  	select HAVE_IDE if PCI || ISA || PCMCIA
>  	select HAVE_DMA_ATTRS
> -	select HAVE_DMA_CONTIGUOUS if (CPU_V6 || CPU_V6K || CPU_V7)
> +	select HAVE_DMA_CONTIGUOUS if MMU
>  	select HAVE_MEMBLOCK
>  	select RTC_LIB
>  	select SYS_SUPPORTS_APM_EMULATION
>
Arnd Bergmann Aug. 20, 2012, 8:01 p.m. UTC | #2
On Monday 20 August 2012, Marek Szyprowski wrote:
> Contiguous Memory Allocator requires only paging and MMU enabled not
> particular CPU architectures, so there is no need for strict dependency
> on CPU type. This enables to use CMA on some older ARM v5 systems which
> also might need large contiguous blocks for the multimedia processing hw
> modules.
> 
> Reported-by: Prabhakar Lad <prabhakar.csengg@gmail.com>
> Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>

The patch looks simple, but I want a better explanation for it.
When we went through all possible cases, we decided that:

* ARMv6+ need CMA to avoid the double mapping problem.
* ARMv4/v5 cannot generally use CMA because it doesn't work
  together with DMABOUNCE. I don't remember if it was the
  only problem, but I definitely remember this was intentional.
* We want a common kernel for all ARMv6+ eventually, and a
  separate kernel for all ARMv4/v5 ones.

If the reasoning has changed, please try to explain the full
situation. On a related topic, what happened to the idea that
ARMv6+ is broken without CMA? I noticed that it's optional
now.

	Arnd
Russell King - ARM Linux Aug. 21, 2012, 12:12 p.m. UTC | #3
On Mon, Aug 20, 2012 at 08:01:23PM +0000, Arnd Bergmann wrote:
> The patch looks simple, but I want a better explanation for it.
> When we went through all possible cases, we decided that:
> 
> * ARMv6+ need CMA to avoid the double mapping problem.
> * ARMv4/v5 cannot generally use CMA because it doesn't work
>   together with DMABOUNCE. I don't remember if it was the
>   only problem, but I definitely remember this was intentional.
> * We want a common kernel for all ARMv6+ eventually, and a
>   separate kernel for all ARMv4/v5 ones.
> 
> If the reasoning has changed, please try to explain the full
> situation.

Indeed.

> On a related topic, what happened to the idea that
> ARMv6+ is broken without CMA? I noticed that it's optional
> now.

With Marek's patch, it's always selected for MMU-based builds (it can't
be disabled).  Before the patch, it was always selected for V6 and later
CPUs.

And the description doesn't make sense:

"Contiguous Memory Allocator requires only paging and MMU enabled not
particular CPU architectures,"

what does "only paging and MMU enabled" mean?  Are you trying to say that
CMA only requires a kernel with MMU support?
Marek Szyprowski Aug. 21, 2012, 2:46 p.m. UTC | #4
Hello,

On Monday, August 20, 2012 10:01 PM Arnd Bergmann wrote:

> On Monday 20 August 2012, Marek Szyprowski wrote:
> > Contiguous Memory Allocator requires only paging and MMU enabled not
> > particular CPU architectures, so there is no need for strict dependency
> > on CPU type. This enables to use CMA on some older ARM v5 systems which
> > also might need large contiguous blocks for the multimedia processing hw
> > modules.
> >
> > Reported-by: Prabhakar Lad <prabhakar.csengg@gmail.com>
> > Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
> 
> The patch looks simple, but I want a better explanation for it.
> When we went through all possible cases, we decided that:
> 
> * ARMv6+ need CMA to avoid the double mapping problem.

Right. CMA can be used to avoid double mapping issues, but we also should keep in
mind that right now no one observed any issues with the real hw, so this discussion
is still a bit hypothetical.

> * ARMv4/v5 cannot generally use CMA because it doesn't work
>   together with DMABOUNCE. I don't remember if it was the
>   only problem, but I definitely remember this was intentional.

DMABOUNCE is used only by a few machines. I also tested and see no reason why it 
might cause problems with such machines. I've used DMABOUNCE code to test atomic 
allocations many times and found no problems. The only issue I might suspect is 
a very limited DMA zone. CMA needs 4Mib alignment of the contiguous area base and
size to meet requirements of the memory management core (mainly for migration and
page isolation purposes), so it might not fit into some small DMA zones.

> * We want a common kernel for all ARMv6+ eventually, and a
>   separate kernel for all ARMv4/v5 ones.

I see no problem here, if required why may have even a separate dma_map_ops for
CMA and use it only for selected devices.

> 
> If the reasoning has changed, please try to explain the full
> situation. On a related topic, what happened to the idea that
> ARMv6+ is broken without CMA? I noticed that it's optional
> now.

Right. I removed unconditional dependency on CMA on Russell's request. CMA is
still experimental and there are still some known issues with it, which we are 
investigating. It doesn't make sense to make the whole architecture depending
on the experimental stuff. The old method of allocating and managing coherent
buffers was stable and worked well enough for the drivers and platforms already
present in the mainline kernel, so if one want to use stable stuff I see no 
reason to disable it.

Best regards
Marek Szyprowski Aug. 21, 2012, 2:47 p.m. UTC | #5
Hello,

On Tuesday, August 21, 2012 2:13 PM Russell King - ARM Linux wrote:

> On Mon, Aug 20, 2012 at 08:01:23PM +0000, Arnd Bergmann wrote:
> > The patch looks simple, but I want a better explanation for it.
> > When we went through all possible cases, we decided that:
> >
> > * ARMv6+ need CMA to avoid the double mapping problem.
> > * ARMv4/v5 cannot generally use CMA because it doesn't work
> >   together with DMABOUNCE. I don't remember if it was the
> >   only problem, but I definitely remember this was intentional.
> > * We want a common kernel for all ARMv6+ eventually, and a
> >   separate kernel for all ARMv4/v5 ones.
> >
> > If the reasoning has changed, please try to explain the full
> > situation.
> 
> Indeed.
> 
> > On a related topic, what happened to the idea that
> > ARMv6+ is broken without CMA? I noticed that it's optional
> > now.
> 
> With Marek's patch, it's always selected for MMU-based builds (it can't
> be disabled).  Before the patch, it was always selected for V6 and later
> CPUs.

My patch only alters dependences of HAVE_DMA_CONTIGUOUS symbol, by changing
them from CPU_V6+ to MMU. It doesn't change or select CMA for any of the 
systems - this is done by the CONFIG_CMA symbol from drivers/base/KConfig 
which depends on HAVE_DMA_CONTIGUOUS. It is up to user to enable it or not.

> And the description doesn't make sense:
> 
> "Contiguous Memory Allocator requires only paging and MMU enabled not
> particular CPU architectures,"
> 
> what does "only paging and MMU enabled" mean?  Are you trying to say that
> CMA only requires a kernel with MMU support?

On ARM architecture CMA can be enabled on any system which has MMU support, 
MMU is required for page migration. The integration layer in dma-mapping is 
generic enough to work on any ARM architecture.

Best regards
diff mbox

Patch

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index e91c7cd..6ef75e2 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -6,7 +6,7 @@  config ARM
 	select HAVE_DMA_API_DEBUG
 	select HAVE_IDE if PCI || ISA || PCMCIA
 	select HAVE_DMA_ATTRS
-	select HAVE_DMA_CONTIGUOUS if (CPU_V6 || CPU_V6K || CPU_V7)
+	select HAVE_DMA_CONTIGUOUS if MMU
 	select HAVE_MEMBLOCK
 	select RTC_LIB
 	select SYS_SUPPORTS_APM_EMULATION