search for: ttm_dma

Hi guys, at least on amdgpu and radeon the page array allocated by ttm_dma_tt_init is completely unused in the case of DMA-buf sharing. So I'm trying to get rid of that by only allocating the DMA address array. Now the only other user of DMA-buf together with ttm_dma_tt_init is Nouveau. So my question is are you guys using the page array anywhere in your kernel dr...

Ping? Am 27.02.2018 um 13:07 schrieb Christian König: > Hi guys, > > at least on amdgpu and radeon the page array allocated by > ttm_dma_tt_init is completely unused in the case of DMA-buf sharing. > So I'm trying to get rid of that by only allocating the DMA address > array. > > Now the only other user of DMA-buf together with ttm_dma_tt_init is > Nouveau. So my question is are you guys using the page array an...

Another revision of this patchset critical for GK20A to operate. Previous attempts were exclusively using either TTM's regular page allocator or the DMA API one. Both have their advantages and drawbacks: the page allocator is fast but requires explicit synchronization on non-coherent architectures, whereas the DMA allocator always returns coherent memory, but is also slower, creates a

....c @@ -402,6 +402,60 @@ nouveau_bo_unmap(struct nouveau_bo *nvbo) ttm_bo_kunmap(&nvbo->kmap); } +void +nouveau_bo_sync_for_device(struct nouveau_bo *nvbo) +{ + struct nouveau_drm *drm = nouveau_bdev(nvbo->bo.bdev); + struct nouveau_device *device = nouveau_dev(drm->dev); + struct ttm_dma_tt *ttm_dma = (struct ttm_dma_tt *)nvbo->bo.ttm; + int i; + + if (!ttm_dma) + return; + + if (nv_device_is_cpu_coherent(device) || nvbo->force_coherent) + return; + + if (nv_device_is_pci(device)) { + for (i = 0; i < ttm_dma->ttm.num_pages; i++) + pci_dma_sync_single_for_device(dev...

...ct nouveau_bo *nvbo) > ttm_bo_kunmap(&nvbo->kmap); > } > > +void > +nouveau_bo_sync_for_device(struct nouveau_bo *nvbo) > +{ > + struct nouveau_drm *drm = nouveau_bdev(nvbo->bo.bdev); > + struct nouveau_device *device = nouveau_dev(drm->dev); > + struct ttm_dma_tt *ttm_dma = (struct ttm_dma_tt *)nvbo->bo.ttm; > + int i; > + > + if (!ttm_dma) > + return; > + > + if (nv_device_is_cpu_coherent(device) || nvbo->force_coherent) > + return; Is the is_cpu_coherent check really required? On coherent platforms the sync_for_foo should...

...ouveau_bdev(ttm->bdev); device = nv_device(drm->device); dev = drm->dev; + pdev = nv_device_base(device); #if __OS_HAS_AGP if (drm->agp.stat == ENABLED) { @@ -1377,17 +1379,22 @@ nouveau_ttm_tt_populate(struct ttm_tt *ttm) } for (i = 0; i < ttm->num_pages; i++) { - ttm_dma->dma_address[i] = nv_device_map_page(device, - ttm->pages[i]); - if (!ttm_dma->dma_address[i]) { + dma_addr_t addr; + + addr = dma_map_page(pdev, ttm->pages[i], 0, PAGE_SIZE, + DMA_BIDIRECTIONAL); + + if (dma_mapping_error(pdev, addr)) { while (--i) { - nv_d...

...ttm/ttm_tt.c @@ -38,6 +38,7 @@ #include <linux/swap.h> #include <linux/slab.h> #include <linux/export.h> +#include <linux/dma-mapping.h> #include <drm/drm_cache.h> #include <drm/drm_mem_util.h> #include <drm/ttm/ttm_module.h> @@ -248,6 +249,30 @@ void ttm_dma_tt_fini(struct ttm_dma_tt *ttm_dma) } EXPORT_SYMBOL(ttm_dma_tt_fini); +void ttm_dma_tt_cache_sync_for_device(struct ttm_dma_tt *ttm_dma, + struct device *dev) +{ + int i; + + for (i = 0; i < ttm_dma->ttm.num_pages; i++) { + dma_sync_single_for_device(dev, ttm_dma->dma_address...

...ttm/ttm_tt.c @@ -38,6 +38,7 @@ #include <linux/swap.h> #include <linux/slab.h> #include <linux/export.h> +#include <linux/dma-mapping.h> #include <drm/drm_cache.h> #include <drm/drm_mem_util.h> #include <drm/ttm/ttm_module.h> @@ -248,6 +249,30 @@ void ttm_dma_tt_fini(struct ttm_dma_tt *ttm_dma) } EXPORT_SYMBOL(ttm_dma_tt_fini); +void ttm_dma_tt_cache_sync_for_device(struct ttm_dma_tt *ttm_dma, + struct device *dev) +{ + unsigned long i; + + for (i = 0; i < ttm_dma->ttm.num_pages; i++) { + dma_sync_single_for_device(dev, ttm_dma->d...

...ttm_pool_populate(ttm); - if (r) { - return r; - } - - for (i = 0; i < ttm->num_pages; i++) { - dma_addr_t addr; - - addr = dma_map_page(pdev, ttm->pages[i], 0, PAGE_SIZE, - DMA_BIDIRECTIONAL); - - if (dma_mapping_error(pdev, addr)) { - while (i--) { - dma_unmap_page(pdev, ttm_dma->dma_address[i], - PAGE_SIZE, DMA_BIDIRECTIONAL); - ttm_dma->dma_address[i] = 0; - } - ttm_pool_unpopulate(ttm); - return -EFAULT; - } - - ttm_dma->dma_address[i] = addr; - } - return 0; + return ttm_populate_and_map_pages(pdev, ttm_dma); } static void @@ -1514,7...

...m->device); > dev = drm->dev; > + pdev = nv_device_base(device); > > #if __OS_HAS_AGP > if (drm->agp.stat == ENABLED) { > @@ -1377,17 +1379,22 @@ nouveau_ttm_tt_populate(struct ttm_tt *ttm) > } > > for (i = 0; i < ttm->num_pages; i++) { > - ttm_dma->dma_address[i] = nv_device_map_page(device, > - ttm->pages[i]); > - if (!ttm_dma->dma_address[i]) { > + dma_addr_t addr; > + > + addr = dma_map_page(pdev, ttm->pages[i], 0, PAGE_SIZE, > + DMA_BIDIRECTIONAL); > + > + if (dma_mapping_error(pd...

...= pci_resource_len(device->pdev, 1) >> PAGE_SHIFT; + u32 mappable = nv_device_resource_len(device, 1) >> PAGE_SHIFT; int ret; /* as long as the bo isn't in vram, and isn't tiled, we've got @@ -1331,6 +1331,7 @@ nouveau_ttm_tt_populate(struct ttm_tt *ttm) { struct ttm_dma_tt *ttm_dma = (void *)ttm; struct nouveau_drm *drm; + struct nouveau_device *device; struct drm_device *dev; unsigned i; int r; @@ -1348,6 +1349,7 @@ nouveau_ttm_tt_populate(struct ttm_tt *ttm) } drm = nouveau_bdev(ttm->bdev); + device = nv_device(drm->device); dev = drm->d...

...sted it and could not see any buffer corruption issue anymore. There is still one point which is not completely satisfying in my opinion: TTMs for TTM-backed objects are allocated in nouveau_sgdma_create_ttm() and populated in nouveau_ttm_tt_populate(). Coherently-allocated buffers need to use the ttm_dma API instead of the pool-based TTM API, and whether an object is coherent or not is stored in its instance of nouveau_bo. The problem is that neither nouveau_sgdma_create_ttm() nor nouveau_ttm_tt_populate() have a way to access the nouveau_bo they are working for. This is in particular a problem fo...

For this v2 I have fixed the patches that are non-controversial (all Lucas' :)) and am resubmitting them in the hope that they will get merged. This will just leave the issue of Nouveau system-memory buffers mapping to be solved. This issue is quite complex, so let me summarize the situation and the data I have at hand. ARM caching is like a quantum world where Murphy's law constantly

This small series introduces TTM helper functions as well as Nouveau hooks that are needed to ensure buffer coherency on ARM. Most of this series is a forward-port of some patches Lucas Stach sent last year and that are also needed for Nouveau GK20A support: http://lists.freedesktop.org/archives/nouveau/2013-August/014026.html Another patch takes care of flushing the CPU write-buffer when

....com> > --- > drivers/gpu/drm/ttm/ttm_tt.c | 25 +++++++++++++++++++++++++ > include/drm/ttm/ttm_bo_driver.h | 28 ++++++++++++++++++++++++++++ > 2 files changed, 53 insertions(+) > > diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c [...] > +void ttm_dma_tt_cache_sync_for_device(struct ttm_dma_tt *ttm_dma, > + struct device *dev) > +{ > + int i; This should probably be unsigned long to match the type of ttm_dma->ttm.num_pages. Thierry -------------- next part -------------- A non-text attachment was scrubbed... Name: not avai...

This is the first set of patches to make Nouveau work on Tegra. Those are only the obvious correctness fixes, a lot of optimization work remains to be done, but at least it's enough to get accel working and let the machine survive a piglit run. A new BO flag is introduced to allow userspace to hint the kernel about possible optimizations. Lucas Stach (6): drm/ttm: recognize ARM arch in

...> >> } > >> > >>+void > >>+nouveau_bo_sync_for_device(struct nouveau_bo *nvbo) > >>+{ > >>+ struct nouveau_drm *drm = nouveau_bdev(nvbo->bo.bdev); > >>+ struct nouveau_device *device = nouveau_dev(drm->dev); > >>+ struct ttm_dma_tt *ttm_dma = (struct ttm_dma_tt *)nvbo->bo.ttm; > >>+ int i; > >>+ > >>+ if (!ttm_dma) > >>+ return; > >>+ > >>+ if (nv_device_is_cpu_coherent(device) || nvbo->force_coherent) > >>+ return; > > > >Is the is_cpu_cohe...

...= pci_resource_len(device->pdev, 1) >> PAGE_SHIFT; + u32 mappable = nv_device_resource_len(device, 1) >> PAGE_SHIFT; int ret; /* as long as the bo isn't in vram, and isn't tiled, we've got @@ -1331,6 +1331,7 @@ nouveau_ttm_tt_populate(struct ttm_tt *ttm) { struct ttm_dma_tt *ttm_dma = (void *)ttm; struct nouveau_drm *drm; + struct nouveau_device *device; struct drm_device *dev; unsigned i; int r; @@ -1348,6 +1349,7 @@ nouveau_ttm_tt_populate(struct ttm_tt *ttm) } drm = nouveau_bdev(ttm->bdev); + device = nv_device(drm->device); dev = drm->d...

...diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 7aa4286..9465f56 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -1228,7 +1228,6 @@ nouveau_ttm_tt_populate(struct ttm_bo_device *bdev, { struct ttm_tt *ttm_dma = (void *)ttm; struct nouveau_drm *drm; - struct device *dev; bool slave = !!(ttm->page_flags & TTM_PAGE_FLAG_SG); if (ttm_tt_is_populated(ttm)) @@ -1242,7 +1241,6 @@ nouveau_ttm_tt_populate(struct ttm_bo_device *bdev, } drm = nouveau_bdev(bdev); - dev = drm->dev->dev;...

...drivers/gpu/drm/ttm/ttm_tt.c | 25 +++++++++++++++++++++++++ >> include/drm/ttm/ttm_bo_driver.h | 28 ++++++++++++++++++++++++++++ >> 2 files changed, 53 insertions(+) >> >> diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c > [...] >> +void ttm_dma_tt_cache_sync_for_device(struct ttm_dma_tt *ttm_dma, >> + struct device *dev) >> +{ >> + int i; > > This should probably be unsigned long to match the type of > ttm_dma->ttm.num_pages. Fixed. Thanks, Alex.