Re: [PATCH v3 2/2] drivers: remove force dma flag from buses

On Fri, Mar 30, 2018 at 01:24:45PM +0530, Nipun Gupta wrote: > With each bus implementing its own DMA configuration callback, > there is no need for bus to explicitly have force_dma in its > global structure. This patch modifies of_dma_configure API to > accept an input parameter which specifies

[PATCH v1 4/4] iommu/tegra: gart: Optimize map/unmap

Currently GART writes one page entry at a time. More optimal would be to aggregate the writes and flush BUS buffer in the end, this gives map/unmap 10-40% (depending on size of mapping) performance boost compared to a flushing after each entry update. Signed-off-by: Dmitry Osipenko

[PATCH v1 0/4] Tegra GART fixes and improvements

GART driver wasn't ever been utilized in upstream, but finally this should change sometime soon with Tegra's DRM driver rework. In general GART driver works fine, though there are couple things that could be improved. Dmitry Osipenko (4): iommu/tegra: gart: Add debugging facility iommu/tegra:

[PATCH v1 2/4] iommu/tegra: gart: Fix gart_iommu_unmap()

It must return the number of unmapped bytes on success, returning 0 means that unmapping failed and in result only one page is unmapped. Signed-off-by: Dmitry Osipenko --- drivers/iommu/tegra-gart.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git

[PATCH v1 1/4] iommu/tegra: gart: Add debugging facility

Page mapping could overwritten by an accident (a bug). We can catch this case by checking 'VALID' bit of GART's page entry prior to mapping of a page. Since that check introduces a small performance impact, it should be enabled explicitly using new GART's kernel module 'debug' parameter.

[PATCH v1 3/4] iommu/tegra: gart: Constify number of GART pages

GART has a fixed aperture size, hence the number of pages is constant. Signed-off-by: Dmitry Osipenko --- drivers/iommu/tegra-gart.c | 14 -- 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c index

[PATCH] base: dma-mapping: Postpone cpu addr translation on mmap()

Postpone calling virt_to_page() translation on memory locations not guaranteed to be backed by a struct page. This patch fixes a specific issue of SH architecture configured with SPARSEMEM memory model, when mapping buffers allocated with the memblock APIs at system initialization time, and thus

Re: [RFC v2 2/2] base: dma-mapping: Postpone page_to_pfn() on mmap()

On Mon, Apr 09, 2018 at 04:06:15PM +0300, Laurent Pinchart wrote: > Hello, > > On Monday, 9 April 2018 14:11:22 EEST Robin Murphy wrote: > > On 09/04/18 08:25, jacopo mondi wrote: > > > Hi Robin, Laurent, > > > > > > a long time passed, sorry about this. > > > > > > On Wed, Nov 15, 2017 at

Re: [RFC v2 2/2] base: dma-mapping: Postpone page_to_pfn() on mmap()

Hi Rich, On Monday, 9 April 2018 18:11:13 EEST Rich Felker wrote: > On Mon, Apr 09, 2018 at 04:06:15PM +0300, Laurent Pinchart wrote: > > On Monday, 9 April 2018 14:11:22 EEST Robin Murphy wrote: > >> On 09/04/18 08:25, jacopo mondi wrote: > >>> Hi Robin, Laurent, > >>> > >>> a long time

Re: [RFC v2 2/2] base: dma-mapping: Postpone page_to_pfn() on mmap()

Hello, On Monday, 9 April 2018 14:11:22 EEST Robin Murphy wrote: > On 09/04/18 08:25, jacopo mondi wrote: > > Hi Robin, Laurent, > > > > a long time passed, sorry about this. > > > > On Wed, Nov 15, 2017 at 01:38:23PM +, Robin Murphy wrote: > >> On 14/11/17 17:08, Jacopo Mondi wrote: >

Re: [RFC v2 2/2] base: dma-mapping: Postpone page_to_pfn() on mmap()

Hi Jacopo, On 09/04/18 08:25, jacopo mondi wrote: Hi Robin, Laurent, a long time passed, sorry about this. On Wed, Nov 15, 2017 at 01:38:23PM +, Robin Murphy wrote: On 14/11/17 17:08, Jacopo Mondi wrote: On SH4 architecture, with SPARSEMEM memory model, translating page to pfn hangs

dma-mapping: clear harmful GFP_* flags in common code

Hello, May we have e89f5b370153 ("dma-mapping: Don't clear GFP_ZERO in dma_alloc_attrs") back-ported to 4.16 kernel as it fixes: 57bf5a8 ("dma-mapping: clear harmful GFP_* flags in common code"). For more info about introduced problem see this thread:

fix x86 swiotlb regression

Hi all, this patch fixes a regression in the x86 swiotlb conversion. This mostly happend because swiotlb_dma_support does the wrong thing (and did so for a long time) and we switched x86 to use it. There are a few others users of swiotlb_dma_supported that also look rather broken, but I'll take

[PATCH] swiotlb: use dma_direct_supported for swiotlb_ops

swiotlb_alloc calls dma_direct_alloc, which can satisfy lower than 32-bit dma mask requests using GFP_DMA if the architecture supports it. Various x86 drivers rely on that, so we need to support that. At the same time the whole kernel expects 32-bit dma mask to just work, so the other magic in

Re: [RFC v2 2/2] base: dma-mapping: Postpone page_to_pfn() on mmap()

Hi Robin, Laurent, a long time passed, sorry about this. On Wed, Nov 15, 2017 at 01:38:23PM +, Robin Murphy wrote: > On 14/11/17 17:08, Jacopo Mondi wrote: > >On SH4 architecture, with SPARSEMEM memory model, translating page to > >pfn hangs the CPU. Post-pone translation to pfn after >