Re: [dpdk-dev] [PATCH] vfio: map contiguous areas in one go

2020-03-27 Thread David Marchand
On Tue, Feb 25, 2020 at 2:25 PM Anatoly Burakov wrote: > > Currently, when we are creating DMA mappings for memory that's > either external or is backed by hugepages in IOVA as PA mode, we > assume that each page is necessarily discontiguous. This may not > actually be the case, especially for ext

Re: [dpdk-dev] [PATCH] vfio: map contiguous areas in one go

2020-02-25 Thread Burakov, Anatoly
On 25-Feb-20 1:49 PM, Ray Kinsella wrote: Hi Anatoly, On 25/02/2020 13:24, Anatoly Burakov wrote: Currently, when we are creating DMA mappings for memory that's either external or is backed by hugepages in IOVA as PA mode, we assume that each page is necessarily discontiguous. This may not actu

Re: [dpdk-dev] [PATCH] vfio: map contiguous areas in one go

2020-02-25 Thread Ray Kinsella
Hi Anatoly, On 25/02/2020 13:24, Anatoly Burakov wrote: > Currently, when we are creating DMA mappings for memory that's > either external or is backed by hugepages in IOVA as PA mode, we > assume that each page is necessarily discontiguous. This may not > actually be the case, especially for exte

[dpdk-dev] [PATCH] vfio: map contiguous areas in one go

2020-02-25 Thread Anatoly Burakov
Currently, when we are creating DMA mappings for memory that's either external or is backed by hugepages in IOVA as PA mode, we assume that each page is necessarily discontiguous. This may not actually be the case, especially for external memory, where the user is able to create their own IOVA tabl