similar to: a saner API for allocating DMA addressable pages v2

Hi all, this series replaced the DMA_ATTR_NON_CONSISTENT flag to dma_alloc_attrs with a separate new dma_alloc_pages API, which is available on all platforms. In addition to cleaning up the convoluted code path, this ensures that other drivers that have asked for better support for non-coherent DMA to pages with incurring bounce buffering over can finally be properly supported. As a follow up I

Hi all, this series replaced the DMA_ATTR_NON_CONSISTENT flag to dma_alloc_attrs with a separate new dma_alloc_pages API, which is available on all platforms. In addition to cleaning up the convoluted code path, this ensures that other drivers that have asked for better support for non-coherent DMA to pages with incurring bounce buffering over can finally be properly supported. I'm still a

Switch the 53c700 driver to only use non-coherent descriptor memory if it really has to because dma_alloc_coherent fails. This doesn't matter for any of the platforms it runs on currently, but that will change soon. To help with this two new helpers to transfer ownership to and from the device are added that abstract the syncing of the non-coherent memory. The two current bidirectional cases

Use the new non-coherent DMA API including proper ownership transfers. This includes adding additional calls to dma_sync_desc_dev as the old syncing was rather ad-hoc. Thanks to Thomas Bogendoerfer for debugging the ownership transfer issues. Signed-off-by: Christoph Hellwig <hch at lst.de> --- drivers/net/ethernet/i825xx/lasi_82596.c | 25 ++--- drivers/net/ethernet/i825xx/lib82596.c

On Wed, Aug 19, 2020 at 1:51 PM Robin Murphy <robin.murphy at arm.com> wrote: > > Hi Tomasz, > > On 2020-08-19 12:16, Tomasz Figa wrote: > > Hi Christoph, > > > > On Wed, Aug 19, 2020 at 8:56 AM Christoph Hellwig <hch at lst.de> wrote: > >> > >> The V4L2-FLAG-MEMORY-NON-CONSISTENT flag is entirely unused, > > > > Could you

Hi Christoph, On Wed, Aug 19, 2020 at 8:56 AM Christoph Hellwig <hch at lst.de> wrote: > > The V4L2-FLAG-MEMORY-NON-CONSISTENT flag is entirely unused, Could you explain what makes you think it's unused? It's a feature of the UAPI generally supported by the videobuf2 framework and relied on by Chromium OS to get any kind of reasonable performance when accessing V4L2 buffers

Hi, This is third approach (complete this time) for replacing struct dma_attrs with unsigned long. The main patch (2/45) doing the change is split into many subpatches for easier review (3-43). They should be squashed together when applying. *Important:* Patchset is *only* build tested on allyesconfigs: ARM, ARM64, i386, x86_64 and powerpc. Please provide reviewes and tests for other

Add a new API to allocate and free pages that are guaranteed to be addressable by a device, but otherwise behave like pages allocated by alloc_pages. The intended APIs to sync them for use with the device and cpu are dma_sync_single_for_{device,cpu} that are also used for streaming mappings. Switch all drivers over to this new API, but keep the usage of the crufty dma_cache_sync API for now,

Use the new non-coherent DMA API including proper ownership transfers. This includes moving the DMA helpers to lib82596 based of an ifdef to avoid include order problems. Signed-off-by: Christoph Hellwig <hch at lst.de> --- drivers/net/ethernet/i825xx/lasi_82596.c | 25 ++--- drivers/net/ethernet/i825xx/lib82596.c | 114 ++++++++++++++--------- drivers/net/ethernet/i825xx/sni_82596.c |

On Thu, Aug 20, 2020 at 6:54 PM Christoph Hellwig <hch at lst.de> wrote: > > On Thu, Aug 20, 2020 at 12:05:29PM +0200, Tomasz Figa wrote: > > The UAPI and V4L2/videobuf2 changes are in good shape and the only > > wrong part is the use of DMA API, which was based on an earlier email > > guidance anyway, and a change to the synchronization part . I find > >

Use the proper modern API to transfer cache ownership for incoherent DMA. Note that this moves the DMA helpers to the main lib82596.c file, so that they can use virt_to_dma. Signed-off-by: Christoph Hellwig <hch at lst.de> --- drivers/net/ethernet/i825xx/lasi_82596.c | 11 +-- drivers/net/ethernet/i825xx/lib82596.c | 114 ++++++++++++++--------- drivers/net/ethernet/i825xx/sni_82596.c

On Wed, Aug 19, 2020 at 03:07:04PM +0100, Robin Murphy wrote: >> FWIW, I asked back in time what the plan is for non-coherent >> allocations and it seemed like DMA_ATTR_NON_CONSISTENT and >> dma_sync_*() was supposed to be the right thing to go with. [2] The >> same thread also explains why dma_alloc_pages() isn't suitable for the >> users of dma_alloc_attrs() and

On Wed, Aug 19, 2020 at 4:07 PM Robin Murphy <robin.murphy at arm.com> wrote: > > On 2020-08-19 13:49, Tomasz Figa wrote: > > On Wed, Aug 19, 2020 at 1:51 PM Robin Murphy <robin.murphy at arm.com> wrote: > >> > >> Hi Tomasz, > >> > >> On 2020-08-19 12:16, Tomasz Figa wrote: > >>> Hi Christoph, > >>> >

This allows us to get rid of the LIB82596_DMA_ATTR defined and prepare for untangling the coherent vs non-coherent DMA allocation API. Signed-off-by: Christoph Hellwig <hch at lst.de> --- drivers/net/ethernet/i825xx/lasi_82596.c | 24 ++++++++++------ drivers/net/ethernet/i825xx/lib82596.c | 36 ++++++++---------------- drivers/net/ethernet/i825xx/sni_82596.c | 19 +++++++++---- 3 files

This allows us to get rid of the LIB82596_DMA_ATTR defined and prepare for untangling the coherent vs non-coherent DMA allocation API. Signed-off-by: Christoph Hellwig <hch at lst.de> --- drivers/net/ethernet/i825xx/lasi_82596.c | 24 ++++++++++------ drivers/net/ethernet/i825xx/lib82596.c | 36 ++++++++---------------- drivers/net/ethernet/i825xx/sni_82596.c | 19 +++++++++---- 3 files

Switch the 53c700 driver to only use non-coherent descriptor memory if it really has to because dma_alloc_coherent fails. This doesn't matter for any of the platforms it runs on currently, but that will change soon. To help with this two new helpers to transfer ownership to and from the device are added that abstract the syncing of the non-coherent memory. The two current bidirectional cases

Switch the 53c700 driver to only use non-coherent descriptor memory if it really has to because dma_alloc_coherent fails. This doesn't matter for any of the platforms it runs on currently, but that will change soon. To help with this two new helpers to transfer ownership to and from the device are added that abstract the syncing of the non-coherent memory. The two current bidirectional cases

After switching DMA attributes to unsigned long it is easier to just compare the bits. Signed-off-by: Krzysztof Kozlowski <k.kozlowski at samsung.com> --- Documentation/DMA-API.txt | 4 +-- arch/arc/mm/dma.c | 4 +-- arch/arm/mm/dma-mapping.c | 36 ++++++++++++-------------- arch/arm/xen/mm.c

Use the new non-coherent DMA API including proper ownership transfers. This also means we can allocate the buffer memory with the proper direction instead of bidirectional. Signed-off-by: Christoph Hellwig <hch at lst.de> --- sound/mips/hal2.c | 58 ++++++++++++++++++++++------------------------- 1 file changed, 27 insertions(+), 31 deletions(-) diff --git a/sound/mips/hal2.c

Hi Christoph, On Wed, Aug 19, 2020 at 8:57 AM Christoph Hellwig <hch at lst.de> wrote: > > Add a new API to allocate and free pages that are guaranteed to be > addressable by a device, but otherwise behave like pages allocated by > alloc_pages. The intended APIs to sync them for use with the device > and cpu are dma_sync_single_for_{device,cpu} that are also used for >