search for: shadow_list

...+ > + bo->tbo.base.funcs = &amdgpu_gem_object_funcs; And this should probably go into amdgpu_gem_object_create(). Apart from that looks like a good idea to me. Christian. > drm_gem_private_object_init(adev->ddev, &bo->tbo.base, size); > INIT_LIST_HEAD(&bo->shadow_list); > bo->vm_bo = NULL;

Hello! My attempt to build openoffice.org-3 seems to be hanging. Pressing Ctrl-T produces: load: 0.11 cmd: tcsh 79759 [sleeping without queue] 0.00u 0.00s 0% 0k (tcsh is used by OOo's build-script). What is this "sleeping without queue" state, and why is process in it for so long? This is an 4-CPU amd64 system with 4Gb of RAM. Only 16% of the swap is currently in use and

...wline is not unrelated. Apart from that the patch is Reviewed-by: Christian K?nig <christian.koenig at amd.com>. But I think we need some smoke testing of it. Christian. > drm_gem_private_object_init(adev_to_drm(adev), &bo->tbo.base, size); > INIT_LIST_HEAD(&bo->shadow_list); > bo->vm_bo = NULL;

...amdgpu_bo_do_create(struct amdgpu_device *adev, bo = kzalloc(sizeof(struct amdgpu_bo), GFP_KERNEL); if (bo == NULL) return -ENOMEM; + + bo->tbo.base.funcs = &amdgpu_gem_object_funcs; drm_gem_private_object_init(adev->ddev, &bo->tbo.base, size); INIT_LIST_HEAD(&bo->shadow_list); bo->vm_bo = NULL; -- 2.28.0

...? Wouldn't these miss the free callback for the GEM object? Best regards Thomas > > Apart from that looks like a good idea to me. > > Christian. > >> ????? drm_gem_private_object_init(adev->ddev, &bo->tbo.base, size); >> ????? INIT_LIST_HEAD(&bo->shadow_list); >> ????? bo->vm_bo = NULL; > -- Thomas Zimmermann Graphics Driver Developer SUSE Software Solutions Germany GmbH Maxfeldstr. 5, 90409 N?rnberg, Germany (HRB 36809, AG N?rnberg) Gesch?ftsf?hrer: Felix Imend?rffer -------------- next part -------------- A non-text attachment was scr...

...dgpu/amdgpu_object.c @@ -561,6 +561,7 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev, bo = kzalloc(sizeof(struct amdgpu_bo), GFP_KERNEL); if (bo == NULL) return -ENOMEM; + drm_gem_private_object_init(adev_to_drm(adev), &bo->tbo.base, size); INIT_LIST_HEAD(&bo->shadow_list); bo->vm_bo = NULL; -- 2.28.0

...> #define AMDGPU_BO_INVALID_OFFSET LONG_MAX > #define AMDGPU_BO_MAX_PLACEMENTS 3 > @@ -100,10 +103,12 @@ struct amdgpu_bo { > struct ttm_bo_kmap_obj dma_buf_vmap; > struct amdgpu_mn *mn; > > - union { > - struct list_head mn_list; > - struct list_head shadow_list; > - }; > + > +#ifdef CONFIG_MMU_NOTIFIER > + struct mmu_range_notifier notifier; > +#endif > + > + struct list_head shadow_list; > > struct kgd_mem *kfd_bo; > };

...FIER +#include <linux/mmu_notifier.h> +#endif #define AMDGPU_BO_INVALID_OFFSET LONG_MAX #define AMDGPU_BO_MAX_PLACEMENTS 3 @@ -100,10 +103,12 @@ struct amdgpu_bo { struct ttm_bo_kmap_obj dma_buf_vmap; struct amdgpu_mn *mn; - union { - struct list_head mn_list; - struct list_head shadow_list; - }; + +#ifdef CONFIG_MMU_NOTIFIER + struct mmu_range_notifier notifier; +#endif + + struct list_head shadow_list; struct kgd_mem *kfd_bo; }; -- 2.23.0

Did cvsup on a machine that does just mail processing (well, a lot of spam scanning) and it crashed not too much later. This kernel does not include MFC src/sys/kern/sys_process.c revisions 1.111 and 1.112: Use kmem_alloc_nofault() rather than kmem_alloc_pageable() in procfs_rwmem(). Use vm_page_hold() in place of vm_page_wire() since the page can be freed. Don't hold extra

The GEM and PRIME related callbacks in struct drm_driver are deprecated in favor of GEM object functions in struct drm_gem_object_funcs. This patchset converts the remaining drivers to object functions and removes most of the obsolete interfaces. Patches #1 to #18 convert DRM drivers to GEM object functions, one by one. Each patch moves existing callbacks from struct drm_driver to an instance of

From: Jason Gunthorpe <jgg at mellanox.com> 8 of the mmu_notifier using drivers (i915_gem, radeon_mn, umem_odp, hfi1, scif_dma, vhost, gntdev, hmm) drivers are using a common pattern where they only use invalidate_range_start/end and immediately check the invalidating range against some driver data structure to tell if the driver is interested. Half of them use an interval_tree, the others

The GEM and PRIME related callbacks in struct drm_driver are deprecated in favor of GEM object functions in struct drm_gem_object_funcs. This patchset converts the remaining drivers to object functions and removes most of the obsolete interfaces. Patches #1 to #16 and #18 to #19 convert DRM drivers to GEM object functions, one by one. Each patch moves existing callbacks from struct drm_driver to

From: Jason Gunthorpe <jgg at mellanox.com> 8 of the mmu_notifier using drivers (i915_gem, radeon_mn, umem_odp, hfi1, scif_dma, vhost, gntdev, hmm) drivers are using a common pattern where they only use invalidate_range_start/end and immediately check the invalidating range against some driver data structure to tell if the driver is interested. Half of them use an interval_tree, the others