| Message ID | 20240807100521.478266-3-andi.shyti@linux.intel.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | Allow partial memory mapping for cpu memory | expand |
On 8/7/2024 12:05 PM, Andi Shyti wrote: > To enable partial memory mapping of GPU virtual memory, it's > necessary to introduce an offset to the object's memory > (obj->mm.pages) scatterlist. This adjustment compensates for > instances when userspace mappings do not start from the beginning > of the object. > > Based on a patch by Chris Wilson. > > Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com> > Cc: Chris Wilson <chris.p.wilson@linux.intel.com> > Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Reviewed-by: Nirmoy Das <nirmoy.das@intel.com> > --- > drivers/gpu/drm/i915/gem/i915_gem_mman.c | 4 +++- > drivers/gpu/drm/i915/i915_mm.c | 12 +++++++++++- > drivers/gpu/drm/i915/i915_mm.h | 3 ++- > 3 files changed, 16 insertions(+), 3 deletions(-) > > diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c > index d3ee8ef7ea2f..bb00af317d59 100644 > --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c > +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c > @@ -252,6 +252,7 @@ static vm_fault_t vm_fault_cpu(struct vm_fault *vmf) > struct vm_area_struct *area = vmf->vma; > struct i915_mmap_offset *mmo = area->vm_private_data; > struct drm_i915_gem_object *obj = mmo->obj; > + unsigned long obj_offset; > resource_size_t iomap; > int err; > > @@ -273,10 +274,11 @@ static vm_fault_t vm_fault_cpu(struct vm_fault *vmf) > iomap -= obj->mm.region->region.start; > } > > + obj_offset = area->vm_pgoff - drm_vma_node_start(&mmo->vma_node); > /* PTEs are revoked in obj->ops->put_pages() */ > err = remap_io_sg(area, > area->vm_start, area->vm_end - area->vm_start, > - obj->mm.pages->sgl, iomap); > + obj->mm.pages->sgl, obj_offset, iomap); > > if (area->vm_flags & VM_WRITE) { > GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj)); > diff --git a/drivers/gpu/drm/i915/i915_mm.c b/drivers/gpu/drm/i915/i915_mm.c > index 7998bc74ab49..f5c97a620962 100644 > --- a/drivers/gpu/drm/i915/i915_mm.c > +++ b/drivers/gpu/drm/i915/i915_mm.c > @@ -122,13 +122,15 @@ int remap_io_mapping(struct vm_area_struct *vma, > * @addr: target user address to start at > * @size: size of map area > * @sgl: Start sg entry > + * @offset: offset from the start of the page > * @iobase: Use stored dma address offset by this address or pfn if -1 > * > * Note: this is only safe if the mm semaphore is held when called. > */ > int remap_io_sg(struct vm_area_struct *vma, > unsigned long addr, unsigned long size, > - struct scatterlist *sgl, resource_size_t iobase) > + struct scatterlist *sgl, unsigned long offset, > + resource_size_t iobase) > { > struct remap_pfn r = { > .mm = vma->vm_mm, > @@ -141,6 +143,14 @@ int remap_io_sg(struct vm_area_struct *vma, > /* We rely on prevalidation of the io-mapping to skip track_pfn(). */ > GEM_BUG_ON((vma->vm_flags & EXPECTED_FLAGS) != EXPECTED_FLAGS); > > + while (offset >= sg_dma_len(r.sgt.sgp) >> PAGE_SHIFT) { > + offset -= sg_dma_len(r.sgt.sgp) >> PAGE_SHIFT; > + r.sgt = __sgt_iter(__sg_next(r.sgt.sgp), use_dma(iobase)); > + if (!r.sgt.sgp) > + return -EINVAL; > + } > + r.sgt.curr = offset << PAGE_SHIFT; > + > if (!use_dma(iobase)) > flush_cache_range(vma, addr, size); > > diff --git a/drivers/gpu/drm/i915/i915_mm.h b/drivers/gpu/drm/i915/i915_mm.h > index 04c8974d822b..69f9351b1a1c 100644 > --- a/drivers/gpu/drm/i915/i915_mm.h > +++ b/drivers/gpu/drm/i915/i915_mm.h > @@ -30,6 +30,7 @@ int remap_io_mapping(struct vm_area_struct *vma, > > int remap_io_sg(struct vm_area_struct *vma, > unsigned long addr, unsigned long size, > - struct scatterlist *sgl, resource_size_t iobase); > + struct scatterlist *sgl, unsigned long offset, > + resource_size_t iobase); > > #endif /* __I915_MM_H__ */
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index d3ee8ef7ea2f..bb00af317d59 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -252,6 +252,7 @@ static vm_fault_t vm_fault_cpu(struct vm_fault *vmf) struct vm_area_struct *area = vmf->vma; struct i915_mmap_offset *mmo = area->vm_private_data; struct drm_i915_gem_object *obj = mmo->obj; + unsigned long obj_offset; resource_size_t iomap; int err; @@ -273,10 +274,11 @@ static vm_fault_t vm_fault_cpu(struct vm_fault *vmf) iomap -= obj->mm.region->region.start; } + obj_offset = area->vm_pgoff - drm_vma_node_start(&mmo->vma_node); /* PTEs are revoked in obj->ops->put_pages() */ err = remap_io_sg(area, area->vm_start, area->vm_end - area->vm_start, - obj->mm.pages->sgl, iomap); + obj->mm.pages->sgl, obj_offset, iomap); if (area->vm_flags & VM_WRITE) { GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj)); diff --git a/drivers/gpu/drm/i915/i915_mm.c b/drivers/gpu/drm/i915/i915_mm.c index 7998bc74ab49..f5c97a620962 100644 --- a/drivers/gpu/drm/i915/i915_mm.c +++ b/drivers/gpu/drm/i915/i915_mm.c @@ -122,13 +122,15 @@ int remap_io_mapping(struct vm_area_struct *vma, * @addr: target user address to start at * @size: size of map area * @sgl: Start sg entry + * @offset: offset from the start of the page * @iobase: Use stored dma address offset by this address or pfn if -1 * * Note: this is only safe if the mm semaphore is held when called. */ int remap_io_sg(struct vm_area_struct *vma, unsigned long addr, unsigned long size, - struct scatterlist *sgl, resource_size_t iobase) + struct scatterlist *sgl, unsigned long offset, + resource_size_t iobase) { struct remap_pfn r = { .mm = vma->vm_mm, @@ -141,6 +143,14 @@ int remap_io_sg(struct vm_area_struct *vma, /* We rely on prevalidation of the io-mapping to skip track_pfn(). */ GEM_BUG_ON((vma->vm_flags & EXPECTED_FLAGS) != EXPECTED_FLAGS); + while (offset >= sg_dma_len(r.sgt.sgp) >> PAGE_SHIFT) { + offset -= sg_dma_len(r.sgt.sgp) >> PAGE_SHIFT; + r.sgt = __sgt_iter(__sg_next(r.sgt.sgp), use_dma(iobase)); + if (!r.sgt.sgp) + return -EINVAL; + } + r.sgt.curr = offset << PAGE_SHIFT; + if (!use_dma(iobase)) flush_cache_range(vma, addr, size); diff --git a/drivers/gpu/drm/i915/i915_mm.h b/drivers/gpu/drm/i915/i915_mm.h index 04c8974d822b..69f9351b1a1c 100644 --- a/drivers/gpu/drm/i915/i915_mm.h +++ b/drivers/gpu/drm/i915/i915_mm.h @@ -30,6 +30,7 @@ int remap_io_mapping(struct vm_area_struct *vma, int remap_io_sg(struct vm_area_struct *vma, unsigned long addr, unsigned long size, - struct scatterlist *sgl, resource_size_t iobase); + struct scatterlist *sgl, unsigned long offset, + resource_size_t iobase); #endif /* __I915_MM_H__ */
To enable partial memory mapping of GPU virtual memory, it's necessary to introduce an offset to the object's memory (obj->mm.pages) scatterlist. This adjustment compensates for instances when userspace mappings do not start from the beginning of the object. Based on a patch by Chris Wilson. Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com> Cc: Chris Wilson <chris.p.wilson@linux.intel.com> Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com> --- drivers/gpu/drm/i915/gem/i915_gem_mman.c | 4 +++- drivers/gpu/drm/i915/i915_mm.c | 12 +++++++++++- drivers/gpu/drm/i915/i915_mm.h | 3 ++- 3 files changed, 16 insertions(+), 3 deletions(-)