[PATCH 1/3] dw_mmc: set fixed burst in BMOD register

[PATCH 1/3] dw_mmc: set fixed burst in BMOD register

[Jaehoon Chung]

This patch is applied fixed burst.
If use internal DMA controller, i think that need to set this bit.

I tested when set this bit or not. I found that increase performance with IDMAC

Signed-off-by: Jaehoon Chung <jh80.chung@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
---
 drivers/mmc/host/dw_mmc.c |    4 ++--
 1 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 58476c1..46e5a89 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -315,7 +315,7 @@ static void dw_mci_idmac_stop_dma(struct dw_mci *host)
 
 	/* Stop the IDMAC running */
 	temp = mci_readl(host, BMOD);
-	temp &= ~SDMMC_IDMAC_ENABLE;
+	temp &= ~(SDMMC_IDMAC_ENABLE | SDMMC_IDMAC_FB);
 	mci_writel(host, BMOD, temp);
 }
 
@@ -384,7 +384,7 @@ static void dw_mci_idmac_start_dma(struct dw_mci *host, unsigned int sg_len)
 
 	/* Enable the IDMAC */
 	temp = mci_readl(host, BMOD);
-	temp |= SDMMC_IDMAC_ENABLE;
+	temp |= SDMMC_IDMAC_ENABLE | SDMMC_IDMAC_FB;
 	mci_writel(host, BMOD, temp);
 
 	/* Start it running */

Re: [PATCH 1/3] dw_mmc: set fixed burst in BMOD register

[Chris Ball]

Hi Will,

On Thu, Feb 24 2011, Jaehoon Chung wrote:
> This patch is applied fixed burst.
> If use internal DMA controller, i think that need to set this bit.
>
> I tested when set this bit or not. I found that increase performance with IDMAC
>
> Signed-off-by: Jaehoon Chung <jh80.chung@samsung.com>
> Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
> ---
>  drivers/mmc/host/dw_mmc.c |    4 ++--
>  1 files changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
> index 58476c1..46e5a89 100644
> --- a/drivers/mmc/host/dw_mmc.c
> +++ b/drivers/mmc/host/dw_mmc.c
> @@ -315,7 +315,7 @@ static void dw_mci_idmac_stop_dma(struct dw_mci *host)
>  
>  	/* Stop the IDMAC running */
>  	temp = mci_readl(host, BMOD);
> -	temp &= ~SDMMC_IDMAC_ENABLE;
> +	temp &= ~(SDMMC_IDMAC_ENABLE | SDMMC_IDMAC_FB);
>  	mci_writel(host, BMOD, temp);
>  }
>  
> @@ -384,7 +384,7 @@ static void dw_mci_idmac_start_dma(struct dw_mci *host, unsigned int sg_len)
>  
>  	/* Enable the IDMAC */
>  	temp = mci_readl(host, BMOD);
> -	temp |= SDMMC_IDMAC_ENABLE;
> +	temp |= SDMMC_IDMAC_ENABLE | SDMMC_IDMAC_FB;
>  	mci_writel(host, BMOD, temp);
>  
>  	/* Start it running */

Any thoughts on this patch?

Thanks,

- Chris.
-- 
Chris Ball   <cjb@laptop.org>   <http://printf.net/>
One Laptop Per Child

Re: [PATCH 1/3] dw_mmc: set fixed burst in BMOD register

[Will Newton]

On Thu, Mar 17, 2011 at 6:24 PM, Chris Ball <cjb@laptop.org> wrote:
> Hi Will,
>
> On Thu, Feb 24 2011, Jaehoon Chung wrote:
>> This patch is applied fixed burst.
>> If use internal DMA controller, i think that need to set this bit.
>>
>> I tested when set this bit or not. I found that increase performance with IDMAC
>>
>> Signed-off-by: Jaehoon Chung <jh80.chung@samsung.com>
>> Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
>> ---
>>  drivers/mmc/host/dw_mmc.c |    4 ++--
>>  1 files changed, 2 insertions(+), 2 deletions(-)
>>
>> diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
>> index 58476c1..46e5a89 100644
>> --- a/drivers/mmc/host/dw_mmc.c
>> +++ b/drivers/mmc/host/dw_mmc.c
>> @@ -315,7 +315,7 @@ static void dw_mci_idmac_stop_dma(struct dw_mci *host)
>>
>>       /* Stop the IDMAC running */
>>       temp = mci_readl(host, BMOD);
>> -     temp &= ~SDMMC_IDMAC_ENABLE;
>> +     temp &= ~(SDMMC_IDMAC_ENABLE | SDMMC_IDMAC_FB);
>>       mci_writel(host, BMOD, temp);
>>  }
>>
>> @@ -384,7 +384,7 @@ static void dw_mci_idmac_start_dma(struct dw_mci *host, unsigned int sg_len)
>>
>>       /* Enable the IDMAC */
>>       temp = mci_readl(host, BMOD);
>> -     temp |= SDMMC_IDMAC_ENABLE;
>> +     temp |= SDMMC_IDMAC_ENABLE | SDMMC_IDMAC_FB;
>>       mci_writel(host, BMOD, temp);
>>
>>       /* Start it running */
>
> Any thoughts on this patch?

From the documentation I have it's not clear what this bit does. I
have very limited access to hardware with internal DMA support, so I
can't really test it either. I'm willing to believe the patch improves
things but I can't really say one way or the other.