Re: [PATCH 10/22] swiotlb: refactor coherent buffer allocation

2018-01-15 Thread Christoph Hellwig
On Wed, Jan 10, 2018 at 05:02:30PM +, Robin Murphy wrote: >>> >>> Aren't we leaking the pages here? >> >> Yes, that free_pages got lost somewhere in the rebases, I've added >> it back. > > Cool. FYI, here is the fixed version, I don't want to re-send the whole series for this fix:

Re: [PATCH 10/22] swiotlb: refactor coherent buffer allocation

2018-01-10 Thread Robin Murphy
On 10/01/18 15:46, Christoph Hellwig wrote: On Wed, Jan 10, 2018 at 12:22:18PM +, Robin Murphy wrote: + if (phys_addr == SWIOTLB_MAP_ERROR) + goto out_warn; -/* Confirm address can be DMA'd by device */ - if (dev_addr + size - 1 > dma_mask) {

Re: [PATCH 10/22] swiotlb: refactor coherent buffer allocation

2018-01-10 Thread Christoph Hellwig
On Wed, Jan 10, 2018 at 12:22:18PM +, Robin Murphy wrote: >> +if (phys_addr == SWIOTLB_MAP_ERROR) >> +goto out_warn; >> - /* Confirm address can be DMA'd by device */ >> -if (dev_addr + size - 1 > dma_mask) { >> -printk("hwdev DMA mask

Re: [PATCH 10/22] swiotlb: refactor coherent buffer allocation

2018-01-10 Thread Robin Murphy
On 10/01/18 08:09, Christoph Hellwig wrote: Factor out a new swiotlb_alloc_buffer helper that allocates DMA coherent memory from the swiotlb bounce buffer. This allows to simplify the swiotlb_alloc implemenation that uses dma_direct_alloc to try to allocate a reachable buffer first.

[PATCH 10/22] swiotlb: refactor coherent buffer allocation

2018-01-10 Thread Christoph Hellwig
Factor out a new swiotlb_alloc_buffer helper that allocates DMA coherent memory from the swiotlb bounce buffer. This allows to simplify the swiotlb_alloc implemenation that uses dma_direct_alloc to try to allocate a reachable buffer first. Signed-off-by: Christoph Hellwig ---