Re: allow larger than require DMA masks

2019-09-24 Thread James Bottomley
On Tue, 2019-09-24 at 23:25 +0200, Christoph Hellwig wrote: > On Mon, Sep 23, 2019 at 08:59:42PM -0400, James Bottomley wrote: > > > if (mask > ~0U) > > > » » return 0; > > > > > > Removing the if() makes the DMA mapping work. It's almost > > > midnight here, so i won't look into that

Re: allow larger than require DMA masks

2019-09-24 Thread Christoph Hellwig
On Mon, Sep 23, 2019 at 08:59:42PM -0400, James Bottomley wrote: > > if (mask > ~0U) > > » » return 0; > > > > Removing the if() makes the DMA mapping work. It's almost midnight > > here, so i won't look into that any further today. Does anyone have > > an opinion on this behaviour?

Re: allow larger than require DMA masks

2019-09-23 Thread James Bottomley
On Mon, 2019-09-23 at 23:14 +0200, Sven Schnelle wrote: > Hi, > > On Fri, Feb 15, 2019 at 03:45:54PM +0100, Christoph Hellwig wrote: > > Hi all, > > > > this series finishes off converting our dma mask model to split > > between device capabilities (dev->dma_mask and dev- > > >coherent_dma_mask)

Re: allow larger than require DMA masks

2019-09-23 Thread Sven Schnelle
Hi, On Fri, Feb 15, 2019 at 03:45:54PM +0100, Christoph Hellwig wrote: > Hi all, > > this series finishes off converting our dma mask model to split between > device capabilities (dev->dma_mask and dev->coherent_dma_mask) and system > limitations (dev->bus_dma_mask). We already accept larger

allow larger than require DMA masks

2019-02-15 Thread Christoph Hellwig
Hi all, this series finishes off converting our dma mask model to split between device capabilities (dev->dma_mask and dev->coherent_dma_mask) and system limitations (dev->bus_dma_mask). We already accept larger than required masks in most dma_map_ops implementation, in case of x86 and