Re: dma_mmap_fault discussion

2019-09-10 Thread VMware
On 9/6/19 9:20 AM, Christoph Hellwig wrote: On Fri, Sep 06, 2019 at 09:10:08AM +0200, Thomas Hellström (VMware) wrote: It's definitely possible. I was just wondering whether it was necessary, but it seems like it. Yepp. I've pushed a new version out (even hotter off the press) that doesn't req

Re: dma_mmap_fault discussion

2019-09-06 Thread Christoph Hellwig
On Fri, Sep 06, 2019 at 09:10:08AM +0200, Thomas Hellström (VMware) wrote: > It's definitely possible. I was just wondering whether it was necessary, but > it seems like it. Yepp. I've pushed a new version out (even hotter off the press) that doesn't require the region for dma_mmap_prepare, and a

Re: dma_mmap_fault discussion

2019-09-06 Thread VMware
On 9/6/19 8:32 AM, Christoph Hellwig wrote: On Thu, Sep 05, 2019 at 07:05:43PM +0200, Thomas Hellström (VMware) wrote: I took a quick look at the interfaces and have two questions: 1) dma_mmap_prepare(), would it be possible to drop the references to the actual coherent region? The thing is tha

Re: dma_mmap_fault discussion

2019-09-05 Thread Christoph Hellwig
On Thu, Sep 05, 2019 at 07:05:43PM +0200, Thomas Hellström (VMware) wrote: > I took a quick look at the interfaces and have two questions: > > 1) dma_mmap_prepare(), would it be possible to drop the references to the > actual coherent region? The thing is that TTM doesn't know at mmap time what >