[PATCH 1/1] Fix PCI DMA flag propagation on SN (Altix) with PICs

[PATCH 1/1] Fix PCI DMA flag propagation on SN (Altix) with PICs

[Jeremy Higdon]

We recently discovered a problem with passing of DMA attributes on
SN systems with the older PIC chips.

Signed-off-by: Jeremy Higdon <jeremy@sgi.com>

--- a/arch/ia64/sn/pci/pcibr/pcibr_dma.c	2009-02-25 23:29:21.000000000 -0800
+++ b/arch/ia64/sn/pci/pcibr/pcibr_dma.c	2009-02-25 23:29:09.318611870 -0800
@@ -135,11 +135,10 @@ pcibr_dmatrans_direct64(struct pcidev_in
 	if (SN_DMA_ADDRTYPE(dma_flags) == SN_DMA_ADDR_PHYS)
 		pci_addr = IS_PIC_SOFT(pcibus_info) ?
 				PHYS_TO_DMA(paddr) :
-		    		PHYS_TO_TIODMA(paddr) | dma_attributes;
+		    		PHYS_TO_TIODMA(paddr);
 	else
-		pci_addr = IS_PIC_SOFT(pcibus_info) ?
-				paddr :
-				paddr | dma_attributes;
+		pci_addr = paddr;
+	pci_addr |= dma_attributes;
 
 	/* Handle Bus mode */
 	if (IS_PCIX(pcibus_info))

Re: [PATCH 1/1] Fix PCI DMA flag propagation on SN (Altix) with PICs

[Jesse Barnes]

On Friday, February 27, 2009 1:38:35 am Jeremy Higdon wrote:
> We recently discovered a problem with passing of DMA attributes on
> SN systems with the older PIC chips.
>
> Signed-off-by: Jeremy Higdon <jeremy@sgi.com>

Hm, doubt it will apply (it came through my Exchange account so probably not); 
I usually have people send to my personal addr for that reason.  Do you need 
this in 2.6.29?

Thanks,
-- 
Jesse Barnes, Intel Open Source Technology Center

Re: [PATCH 1/1] Fix PCI DMA flag propagation on SN (Altix) with PICs

[Matthew Wilcox]

On Fri, Feb 27, 2009 at 01:38:35AM -0800, Jeremy Higdon wrote:
> We recently discovered a problem with passing of DMA attributes on
> SN systems with the older PIC chips.

I think this should go in through the ia64 tree, not the PCI tree ...

> Signed-off-by: Jeremy Higdon <jeremy@sgi.com>
> 
> --- a/arch/ia64/sn/pci/pcibr/pcibr_dma.c	2009-02-25 23:29:21.000000000 -0800
> +++ b/arch/ia64/sn/pci/pcibr/pcibr_dma.c	2009-02-25 23:29:09.318611870 -0800
> @@ -135,11 +135,10 @@ pcibr_dmatrans_direct64(struct pcidev_in
>  	if (SN_DMA_ADDRTYPE(dma_flags) == SN_DMA_ADDR_PHYS)
>  		pci_addr = IS_PIC_SOFT(pcibus_info) ?
>  				PHYS_TO_DMA(paddr) :
> -		    		PHYS_TO_TIODMA(paddr) | dma_attributes;
> +		    		PHYS_TO_TIODMA(paddr);
>  	else
> -		pci_addr = IS_PIC_SOFT(pcibus_info) ?
> -				paddr :
> -				paddr | dma_attributes;
> +		pci_addr = paddr;
> +	pci_addr |= dma_attributes;
>  
>  	/* Handle Bus mode */
>  	if (IS_PCIX(pcibus_info))
> --
> To unsubscribe from this list: send the line "unsubscribe linux-pci" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html

-- 
Matthew Wilcox				Intel Open Source Technology Centre
"Bill, look, we understand that you're interested in selling us this
operating system, but compare it to ours.  We can't possibly take such
a retrograde step."