Re: [RFC PATCH 2/7] swiotlb: Make io_tlb_start a physical address instead of a virtual address

2012-10-09 Thread Alexander Duyck
On 10/09/2012 09:43 AM, Konrad Rzeszutek Wilk wrote: > On Thu, Oct 04, 2012 at 01:22:58PM -0700, Alexander Duyck wrote: >> On 10/04/2012 10:19 AM, Konrad Rzeszutek Wilk wrote: >> @@ -450,7 +451,7 @@ void *swiotlb_tbl_map_single(struct device *hwdev, >> dma_addr_t tbl_dma_addr, >>

Re: [RFC PATCH 2/7] swiotlb: Make io_tlb_start a physical address instead of a virtual address

2012-10-09 Thread Konrad Rzeszutek Wilk
On Thu, Oct 04, 2012 at 01:22:58PM -0700, Alexander Duyck wrote: > On 10/04/2012 10:19 AM, Konrad Rzeszutek Wilk wrote: > @@ -450,7 +451,7 @@ void *swiotlb_tbl_map_single(struct device *hwdev, > dma_addr_t tbl_dma_addr, > io_tlb_list[i] = 0; >

Re: [RFC PATCH 2/7] swiotlb: Make io_tlb_start a physical address instead of a virtual address

2012-10-09 Thread Konrad Rzeszutek Wilk
On Thu, Oct 04, 2012 at 01:22:58PM -0700, Alexander Duyck wrote: On 10/04/2012 10:19 AM, Konrad Rzeszutek Wilk wrote: @@ -450,7 +451,7 @@ void *swiotlb_tbl_map_single(struct device *hwdev, dma_addr_t tbl_dma_addr, io_tlb_list[i] = 0;

Re: [RFC PATCH 2/7] swiotlb: Make io_tlb_start a physical address instead of a virtual address

2012-10-09 Thread Alexander Duyck
On 10/09/2012 09:43 AM, Konrad Rzeszutek Wilk wrote: On Thu, Oct 04, 2012 at 01:22:58PM -0700, Alexander Duyck wrote: On 10/04/2012 10:19 AM, Konrad Rzeszutek Wilk wrote: @@ -450,7 +451,7 @@ void *swiotlb_tbl_map_single(struct device *hwdev, dma_addr_t tbl_dma_addr,

Re: [RFC PATCH 2/7] swiotlb: Make io_tlb_start a physical address instead of a virtual address

2012-10-04 Thread Alexander Duyck
On 10/04/2012 10:19 AM, Konrad Rzeszutek Wilk wrote: @@ -450,7 +451,7 @@ void *swiotlb_tbl_map_single(struct device *hwdev, dma_addr_t tbl_dma_addr, io_tlb_list[i] = 0; for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) !=

Re: [RFC PATCH 2/7] swiotlb: Make io_tlb_start a physical address instead of a virtual address

2012-10-04 Thread Konrad Rzeszutek Wilk
> >> @@ -450,7 +451,7 @@ void *swiotlb_tbl_map_single(struct device *hwdev, > >> dma_addr_t tbl_dma_addr, > >>io_tlb_list[i] = 0; > >>for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != > >> IO_TLB_SEGSIZE - 1) && io_tlb_list[i]; i--) > >>

Re: [RFC PATCH 2/7] swiotlb: Make io_tlb_start a physical address instead of a virtual address

2012-10-04 Thread Alexander Duyck
On 10/04/2012 06:18 AM, Konrad Rzeszutek Wilk wrote: > On Wed, Oct 03, 2012 at 05:38:53PM -0700, Alexander Duyck wrote: >> This change makes it so that io_tlb_start contains a physical address instead >> of a virtual address. The advantage to this is that we can avoid costly >> translations

Re: [RFC PATCH 2/7] swiotlb: Make io_tlb_start a physical address instead of a virtual address

2012-10-04 Thread Konrad Rzeszutek Wilk
On Wed, Oct 03, 2012 at 05:38:53PM -0700, Alexander Duyck wrote: > This change makes it so that io_tlb_start contains a physical address instead > of a virtual address. The advantage to this is that we can avoid costly > translations between virtual and physical addresses when comparing the >

Re: [RFC PATCH 2/7] swiotlb: Make io_tlb_start a physical address instead of a virtual address

2012-10-04 Thread Konrad Rzeszutek Wilk
On Wed, Oct 03, 2012 at 05:38:53PM -0700, Alexander Duyck wrote: This change makes it so that io_tlb_start contains a physical address instead of a virtual address. The advantage to this is that we can avoid costly translations between virtual and physical addresses when comparing the

Re: [RFC PATCH 2/7] swiotlb: Make io_tlb_start a physical address instead of a virtual address

2012-10-04 Thread Alexander Duyck
On 10/04/2012 06:18 AM, Konrad Rzeszutek Wilk wrote: On Wed, Oct 03, 2012 at 05:38:53PM -0700, Alexander Duyck wrote: This change makes it so that io_tlb_start contains a physical address instead of a virtual address. The advantage to this is that we can avoid costly translations between

Re: [RFC PATCH 2/7] swiotlb: Make io_tlb_start a physical address instead of a virtual address

2012-10-04 Thread Konrad Rzeszutek Wilk
@@ -450,7 +451,7 @@ void *swiotlb_tbl_map_single(struct device *hwdev, dma_addr_t tbl_dma_addr, io_tlb_list[i] = 0; for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE - 1) io_tlb_list[i]; i--)

Re: [RFC PATCH 2/7] swiotlb: Make io_tlb_start a physical address instead of a virtual address

2012-10-04 Thread Alexander Duyck
On 10/04/2012 10:19 AM, Konrad Rzeszutek Wilk wrote: @@ -450,7 +451,7 @@ void *swiotlb_tbl_map_single(struct device *hwdev, dma_addr_t tbl_dma_addr, io_tlb_list[i] = 0; for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE - 1)

[RFC PATCH 2/7] swiotlb: Make io_tlb_start a physical address instead of a virtual address

2012-10-03 Thread Alexander Duyck
This change makes it so that io_tlb_start contains a physical address instead of a virtual address. The advantage to this is that we can avoid costly translations between virtual and physical addresses when comparing the io_tlb_start against DMA addresses. Signed-off-by: Alexander Duyck ---

[RFC PATCH 2/7] swiotlb: Make io_tlb_start a physical address instead of a virtual address

2012-10-03 Thread Alexander Duyck
This change makes it so that io_tlb_start contains a physical address instead of a virtual address. The advantage to this is that we can avoid costly translations between virtual and physical addresses when comparing the io_tlb_start against DMA addresses. Signed-off-by: Alexander Duyck