| Message ID | 20210520150947.803891-4-thomas.hellstrom@linux.intel.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | Core TTM changes for i915 TTM enabling | expand |
Am 20.05.21 um 17:09 schrieb Thomas Hellström: > Use fast wc memcpy for reading out of wc memory for TTM bo moves. > > Cc: Dave Airlie <airlied@gmail.com> > Cc: Christian König <christian.koenig@amd.com> > Cc: Daniel Vetter <daniel.vetter@ffwll.ch> > Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com> Oh, yes I really wanted to have that in TTM for quite some time. But I'm wondering if we shouldn't fix the memremap stuff first. Christian. > --- > drivers/gpu/drm/ttm/ttm_bo_util.c | 18 +++++++++++++++++- > 1 file changed, 17 insertions(+), 1 deletion(-) > > diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c > index bad9b16e96ba..919ee03f7eb3 100644 > --- a/drivers/gpu/drm/ttm/ttm_bo_util.c > +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c > @@ -31,6 +31,7 @@ > > #include <drm/ttm/ttm_bo_driver.h> > #include <drm/ttm/ttm_placement.h> > +#include <drm/drm_memcpy.h> > #include <drm/drm_vma_manager.h> > #include <linux/dma-buf-map.h> > #include <linux/io.h> > @@ -185,6 +186,7 @@ void ttm_move_memcpy(struct ttm_buffer_object *bo, > struct ttm_resource *old_mem = &bo->mem; > struct ttm_resource_manager *old_man = ttm_manager_type(bdev, old_mem->mem_type); > struct dma_buf_map old_map, new_map; > + bool wc_memcpy; > pgoff_t i; > > /* Single TTM move. NOP */ > @@ -208,11 +210,25 @@ void ttm_move_memcpy(struct ttm_buffer_object *bo, > return; > } > > + wc_memcpy = ((!old_man->use_tt || bo->ttm->caching != ttm_cached) && > + drm_has_memcpy_from_wc()); > + > + /* > + * We use some nasty aliasing for drm_memcpy_from_wc, but assuming > + * that we can move to memremapping in the not too distant future, > + * reduce the fragility for now with a build assert. > + */ > + BUILD_BUG_ON(offsetof(typeof(old_map), vaddr) != > + offsetof(typeof(old_map), vaddr_iomem)); > + > for (i = 0; i < new_mem->num_pages; ++i) { > new_iter->ops->kmap_local(new_iter, &new_map, i); > old_iter->ops->kmap_local(old_iter, &old_map, i); > > - if (!old_map.is_iomem && !new_map.is_iomem) { > + if (wc_memcpy) { > + drm_memcpy_from_wc(new_map.vaddr, old_map.vaddr, > + PAGE_SIZE); > + } else if (!old_map.is_iomem && !new_map.is_iomem) { > memcpy(new_map.vaddr, old_map.vaddr, PAGE_SIZE); > } else if (!old_map.is_iomem) { > dma_buf_map_memcpy_to(&new_map, old_map.vaddr,
On 5/21/21 10:10 AM, Christian König wrote: > Am 20.05.21 um 17:09 schrieb Thomas Hellström: >> Use fast wc memcpy for reading out of wc memory for TTM bo moves. >> >> Cc: Dave Airlie <airlied@gmail.com> >> Cc: Christian König <christian.koenig@amd.com> >> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> >> Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com> > > Oh, yes I really wanted to have that in TTM for quite some time. We should use it for swap copy from WC as well IMO. A todo-task for somebody. > > But I'm wondering if we shouldn't fix the memremap stuff first. Using memremap all over is a fairly big change probably with lots of opinions involved all over the place. What I can do for now is to add a dma_buf_map interface to the memcpy itself, to move the aliasing out of TTM to the arch specific code that knows what it's doing? /Thomas > > Christian. > >> --- >> drivers/gpu/drm/ttm/ttm_bo_util.c | 18 +++++++++++++++++- >> 1 file changed, 17 insertions(+), 1 deletion(-) >> >> diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c >> b/drivers/gpu/drm/ttm/ttm_bo_util.c >> index bad9b16e96ba..919ee03f7eb3 100644 >> --- a/drivers/gpu/drm/ttm/ttm_bo_util.c >> +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c >> @@ -31,6 +31,7 @@ >> #include <drm/ttm/ttm_bo_driver.h> >> #include <drm/ttm/ttm_placement.h> >> +#include <drm/drm_memcpy.h> >> #include <drm/drm_vma_manager.h> >> #include <linux/dma-buf-map.h> >> #include <linux/io.h> >> @@ -185,6 +186,7 @@ void ttm_move_memcpy(struct ttm_buffer_object *bo, >> struct ttm_resource *old_mem = &bo->mem; >> struct ttm_resource_manager *old_man = ttm_manager_type(bdev, >> old_mem->mem_type); >> struct dma_buf_map old_map, new_map; >> + bool wc_memcpy; >> pgoff_t i; >> /* Single TTM move. NOP */ >> @@ -208,11 +210,25 @@ void ttm_move_memcpy(struct ttm_buffer_object *bo, >> return; >> } >> + wc_memcpy = ((!old_man->use_tt || bo->ttm->caching != >> ttm_cached) && >> + drm_has_memcpy_from_wc()); >> + >> + /* >> + * We use some nasty aliasing for drm_memcpy_from_wc, but assuming >> + * that we can move to memremapping in the not too distant future, >> + * reduce the fragility for now with a build assert. >> + */ >> + BUILD_BUG_ON(offsetof(typeof(old_map), vaddr) != >> + offsetof(typeof(old_map), vaddr_iomem)); >> + >> for (i = 0; i < new_mem->num_pages; ++i) { >> new_iter->ops->kmap_local(new_iter, &new_map, i); >> old_iter->ops->kmap_local(old_iter, &old_map, i); >> - if (!old_map.is_iomem && !new_map.is_iomem) { >> + if (wc_memcpy) { >> + drm_memcpy_from_wc(new_map.vaddr, old_map.vaddr, >> + PAGE_SIZE); >> + } else if (!old_map.is_iomem && !new_map.is_iomem) { >> memcpy(new_map.vaddr, old_map.vaddr, PAGE_SIZE); >> } else if (!old_map.is_iomem) { >> dma_buf_map_memcpy_to(&new_map, old_map.vaddr, >
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index bad9b16e96ba..919ee03f7eb3 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -31,6 +31,7 @@ #include <drm/ttm/ttm_bo_driver.h> #include <drm/ttm/ttm_placement.h> +#include <drm/drm_memcpy.h> #include <drm/drm_vma_manager.h> #include <linux/dma-buf-map.h> #include <linux/io.h> @@ -185,6 +186,7 @@ void ttm_move_memcpy(struct ttm_buffer_object *bo, struct ttm_resource *old_mem = &bo->mem; struct ttm_resource_manager *old_man = ttm_manager_type(bdev, old_mem->mem_type); struct dma_buf_map old_map, new_map; + bool wc_memcpy; pgoff_t i; /* Single TTM move. NOP */ @@ -208,11 +210,25 @@ void ttm_move_memcpy(struct ttm_buffer_object *bo, return; } + wc_memcpy = ((!old_man->use_tt || bo->ttm->caching != ttm_cached) && + drm_has_memcpy_from_wc()); + + /* + * We use some nasty aliasing for drm_memcpy_from_wc, but assuming + * that we can move to memremapping in the not too distant future, + * reduce the fragility for now with a build assert. + */ + BUILD_BUG_ON(offsetof(typeof(old_map), vaddr) != + offsetof(typeof(old_map), vaddr_iomem)); + for (i = 0; i < new_mem->num_pages; ++i) { new_iter->ops->kmap_local(new_iter, &new_map, i); old_iter->ops->kmap_local(old_iter, &old_map, i); - if (!old_map.is_iomem && !new_map.is_iomem) { + if (wc_memcpy) { + drm_memcpy_from_wc(new_map.vaddr, old_map.vaddr, + PAGE_SIZE); + } else if (!old_map.is_iomem && !new_map.is_iomem) { memcpy(new_map.vaddr, old_map.vaddr, PAGE_SIZE); } else if (!old_map.is_iomem) { dma_buf_map_memcpy_to(&new_map, old_map.vaddr,
Use fast wc memcpy for reading out of wc memory for TTM bo moves. Cc: Dave Airlie <airlied@gmail.com> Cc: Christian König <christian.koenig@amd.com> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com> --- drivers/gpu/drm/ttm/ttm_bo_util.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-)