Message ID | 1450071971-30321-4-git-send-email-ankitprasad.r.sharma@intel.com (mailing list archive) |
---|---|
State | New, archived |
Headers | show |
On Mon, Dec 14, 2015 at 11:16:05AM +0530, ankitprasad.r.sharma@intel.com wrote: > From: Ankitprasad Sharma <ankitprasad.r.sharma@intel.com> > > This patch adds support for clearing buffer objects via CPU/GTT. This > is particularly useful for clearing out the non shmem backed objects. > Currently intend to use this only for buffers allocated from stolen > region. > > v2: Added kernel doc for i915_gem_clear_object(), corrected/removed > variable assignments (Tvrtko) > > v3: Map object page by page to the gtt if the pinning of the whole object > to the ggtt fails, Corrected function name (Chris) > > v4: Clear the buffer page by page, and not map the whole object in the gtt > aperture. Use i915 wrapper function in place of drm_mm_insert_node_in_range. > > Testcase: igt/gem_stolen > > Signed-off-by: Ankitprasad Sharma <ankitprasad.r.sharma@intel.com> > --- > drivers/gpu/drm/i915/i915_drv.h | 1 + > drivers/gpu/drm/i915/i915_gem.c | 44 +++++++++++++++++++++++++++++++++++++++++ > 2 files changed, 45 insertions(+) > > diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h > index a10b866..e195fee 100644 > --- a/drivers/gpu/drm/i915/i915_drv.h > +++ b/drivers/gpu/drm/i915/i915_drv.h > @@ -2897,6 +2897,7 @@ int i915_gem_obj_prepare_shmem_read(struct drm_i915_gem_object *obj, > int *needs_clflush); > > int __must_check i915_gem_object_get_pages(struct drm_i915_gem_object *obj); > +int i915_gem_object_clear(struct drm_i915_gem_object *obj); > > static inline int __sg_page_count(struct scatterlist *sg) > { > diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c > index 46c1e75..e50a91b 100644 > --- a/drivers/gpu/drm/i915/i915_gem.c > +++ b/drivers/gpu/drm/i915/i915_gem.c > @@ -5293,3 +5293,47 @@ fail: > drm_gem_object_unreference(&obj->base); > return ERR_PTR(ret); > } > + > +/** > + * i915_gem_object_clear() - Clear buffer object via CPU/GTT > + * @obj: Buffer object to be cleared > + * > + * Return: 0 - success, non-zero - failure > + */ > +int i915_gem_object_clear(struct drm_i915_gem_object *obj) > +{ > + int ret, i; > + char __iomem *base; > + size_t size = obj->base.size; > + struct drm_i915_private *i915 = to_i915(obj->base.dev); > + struct drm_mm_node node; > + > + lockdep_assert_held(&obj->base.dev->struct_mutex); > + memset(&node, 0, sizeof(node)); > + ret = i915_gem_insert_node_in_range(i915, &node, 4096, 0, > + 0, i915->gtt.mappable_end); I do not like this wrapper because you have no idea what it is meant to do. > + if (ret) > + goto out; > + > + i915_gem_object_pin_pages(obj); > + base = io_mapping_map_wc(i915->gtt.mappable, node.start); > + for (i = 0; i < size/PAGE_SIZE; i++) { > + wmb(); > + i915->gtt.base.insert_page(&i915->gtt.base, > + i915_gem_object_get_dma_address(obj, i), > + node.start, > + I915_CACHE_NONE, 0); > + wmb(); > + memset_io(base, 0, 4096); The barriers can just be written as: for (;;) { insert_page(); wmb(); memset_io() wmb(); } -Chris
Hi, On 14/12/15 05:46, ankitprasad.r.sharma@intel.com wrote: > From: Ankitprasad Sharma <ankitprasad.r.sharma@intel.com> > > This patch adds support for clearing buffer objects via CPU/GTT. This > is particularly useful for clearing out the non shmem backed objects. > Currently intend to use this only for buffers allocated from stolen > region. > > v2: Added kernel doc for i915_gem_clear_object(), corrected/removed > variable assignments (Tvrtko) > > v3: Map object page by page to the gtt if the pinning of the whole object > to the ggtt fails, Corrected function name (Chris) > > v4: Clear the buffer page by page, and not map the whole object in the gtt > aperture. Use i915 wrapper function in place of drm_mm_insert_node_in_range. > > Testcase: igt/gem_stolen > > Signed-off-by: Ankitprasad Sharma <ankitprasad.r.sharma@intel.com> > --- > drivers/gpu/drm/i915/i915_drv.h | 1 + > drivers/gpu/drm/i915/i915_gem.c | 44 +++++++++++++++++++++++++++++++++++++++++ > 2 files changed, 45 insertions(+) > > diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h > index a10b866..e195fee 100644 > --- a/drivers/gpu/drm/i915/i915_drv.h > +++ b/drivers/gpu/drm/i915/i915_drv.h > @@ -2897,6 +2897,7 @@ int i915_gem_obj_prepare_shmem_read(struct drm_i915_gem_object *obj, > int *needs_clflush); > > int __must_check i915_gem_object_get_pages(struct drm_i915_gem_object *obj); > +int i915_gem_object_clear(struct drm_i915_gem_object *obj); > > static inline int __sg_page_count(struct scatterlist *sg) > { > diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c > index 46c1e75..e50a91b 100644 > --- a/drivers/gpu/drm/i915/i915_gem.c > +++ b/drivers/gpu/drm/i915/i915_gem.c > @@ -5293,3 +5293,47 @@ fail: > drm_gem_object_unreference(&obj->base); > return ERR_PTR(ret); > } > + > +/** > + * i915_gem_object_clear() - Clear buffer object via CPU/GTT > + * @obj: Buffer object to be cleared > + * > + * Return: 0 - success, non-zero - failure > + */ > +int i915_gem_object_clear(struct drm_i915_gem_object *obj) > +{ > + int ret, i; > + char __iomem *base; > + size_t size = obj->base.size; > + struct drm_i915_private *i915 = to_i915(obj->base.dev); > + struct drm_mm_node node; > + > + lockdep_assert_held(&obj->base.dev->struct_mutex); > + memset(&node, 0, sizeof(node)); > + ret = i915_gem_insert_node_in_range(i915, &node, 4096, 0, Use PAGE_SIZE instead of 4096 since it is used it the for loop below? > + 0, i915->gtt.mappable_end); > + if (ret) > + goto out; > + > + i915_gem_object_pin_pages(obj); Does it need a call to i915_gem_object_get_pages to work with all objects in all scenarios? > + base = io_mapping_map_wc(i915->gtt.mappable, node.start); > + for (i = 0; i < size/PAGE_SIZE; i++) { > + wmb(); > + i915->gtt.base.insert_page(&i915->gtt.base, > + i915_gem_object_get_dma_address(obj, i), > + node.start, > + I915_CACHE_NONE, 0); > + wmb(); > + memset_io(base, 0, 4096); Again, maybe also use PAGE_SIZE so it is consistent with the for loop? > + } > + > + wmb(); > + io_mapping_unmap(base); > + i915->gtt.base.clear_range(&i915->gtt.base, > + node.start, node.size, > + true); > + drm_mm_remove_node(&node); > + i915_gem_object_unpin_pages(obj); > +out: > + return ret; > +} > Regards, Tvrtko
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index a10b866..e195fee 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -2897,6 +2897,7 @@ int i915_gem_obj_prepare_shmem_read(struct drm_i915_gem_object *obj, int *needs_clflush); int __must_check i915_gem_object_get_pages(struct drm_i915_gem_object *obj); +int i915_gem_object_clear(struct drm_i915_gem_object *obj); static inline int __sg_page_count(struct scatterlist *sg) { diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 46c1e75..e50a91b 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -5293,3 +5293,47 @@ fail: drm_gem_object_unreference(&obj->base); return ERR_PTR(ret); } + +/** + * i915_gem_object_clear() - Clear buffer object via CPU/GTT + * @obj: Buffer object to be cleared + * + * Return: 0 - success, non-zero - failure + */ +int i915_gem_object_clear(struct drm_i915_gem_object *obj) +{ + int ret, i; + char __iomem *base; + size_t size = obj->base.size; + struct drm_i915_private *i915 = to_i915(obj->base.dev); + struct drm_mm_node node; + + lockdep_assert_held(&obj->base.dev->struct_mutex); + memset(&node, 0, sizeof(node)); + ret = i915_gem_insert_node_in_range(i915, &node, 4096, 0, + 0, i915->gtt.mappable_end); + if (ret) + goto out; + + i915_gem_object_pin_pages(obj); + base = io_mapping_map_wc(i915->gtt.mappable, node.start); + for (i = 0; i < size/PAGE_SIZE; i++) { + wmb(); + i915->gtt.base.insert_page(&i915->gtt.base, + i915_gem_object_get_dma_address(obj, i), + node.start, + I915_CACHE_NONE, 0); + wmb(); + memset_io(base, 0, 4096); + } + + wmb(); + io_mapping_unmap(base); + i915->gtt.base.clear_range(&i915->gtt.base, + node.start, node.size, + true); + drm_mm_remove_node(&node); + i915_gem_object_unpin_pages(obj); +out: + return ret; +}