drm/ttm: cleanup and optimize ttm_bo_mem_compat v2
Subsystems (10)
PATCH 1/6 drm/ttm: cleanup and optimize ttm_bo_mem_compat v2
From: Christian König <[email protected]>
No need to implement the same logic twice. Also check if the busy placements are identical to the already scanned placements before checking them.
v2: improve check even more as suggested by Michel.
--- drivers/gpu/drm/ttm/ttm_bo.c | 45 ++++++++++++++++++++++++-------------------- 1 file changed, 25 insertions(+), 20 deletions(-)
drivers/gpu/drm/ttm/ttm_bo.c +25 -20
@@ -1046,29 +1046,17 @@ static int ttm_bo_move_buffer(struct ttm_buffer_object *bo,return ret; } -bool ttm_bo_mem_compat (struct ttm_placement *placement, -struct ttm_mem_reg *mem, -uint32_t *new_flags) +static bool ttm_bo_places_compat (const struct ttm_place *places, +unsigned num_placement, +struct ttm_mem_reg *mem, +uint32_t *new_flags) { -int i; +unsigned i; -for (i =0 ; i < placement->num_placement; i++) { -const struct ttm_place *heap = &placement->placement[i]; -if (mem->mm_node && - (mem->start < heap->fpfn || - (heap->lpfn !=0 && (mem->start + mem->num_pages) > heap->lpfn))) -continue ; +for (i =0 ; i < num_placement; i++) { +const struct ttm_place *heap = &places[i]; - *new_flags = heap->flags; -if ((*new_flags & mem->placement &TTM_PL_MASK_CACHING ) && - (*new_flags & mem->placement &TTM_PL_MASK_MEM )) -return true; - } - -for (i =0 ; i < placement->num_busy_placement; i++) { -const struct ttm_place *heap = &placement->busy_placement[i]; -if (mem->mm_node && - (mem->start < heap->fpfn || +if (mem->mm_node && (mem->start < heap->fpfn || (heap->lpfn !=0 && (mem->start + mem->num_pages) > heap->lpfn)))continue ;
@@ -1077,6 +1065,23 @@ bool ttm_bo_mem_compat(struct ttm_placement *placement, (*new_flags & mem->placement & TTM_PL_MASK_MEM))return true; } +return false; +} + +bool ttm_bo_mem_compat (struct ttm_placement *placement, +struct ttm_mem_reg *mem, +uint32_t *new_flags) +{ +if (ttm_bo_places_compat (placement->placement, placement->num_placement, + mem, new_flags)) +return true; + +if ((placement->busy_placement != placement->placement || + placement->num_busy_placement > placement->num_placement) && +ttm_bo_places_compat (placement->busy_placement, + placement->num_busy_placement, + mem, new_flags)) +return true;return false; }
Signature · 6 lines
2.5.0 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
PATCH 2/6 drm/ttm: add io_mem_pfn callback
From: Christian König <[email protected]>
This allows the driver to handle io_mem mappings on their own.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 1 + drivers/gpu/drm/ast/ast_ttm.c | 1 + drivers/gpu/drm/bochs/bochs_mm.c | 1 + drivers/gpu/drm/cirrus/cirrus_ttm.c | 1 + drivers/gpu/drm/mgag200/mgag200_ttm.c | 1 + drivers/gpu/drm/nouveau/nouveau_bo.c | 1 + drivers/gpu/drm/qxl/qxl_ttm.c | 1 + drivers/gpu/drm/radeon/radeon_ttm.c | 1 + drivers/gpu/drm/ttm/ttm_bo_vm.c | 10 +++++++++- drivers/gpu/drm/virtio/virtgpu_ttm.c | 1 + drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c | 1 + include/drm/ttm/ttm_bo_api.h | 11 +++++++++++ include/drm/ttm/ttm_bo_driver.h | 9 +++++++++ 13 files changed, 39 insertions(+), 1 deletion(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +1 -0
@@ -1089,6 +1089,7 @@ static struct ttm_bo_driver amdgpu_bo_driver = { .fault_reserve_notify = &amdgpu_bo_fault_reserve_notify, .io_mem_reserve = &amdgpu_ttm_io_mem_reserve, .io_mem_free = &amdgpu_ttm_io_mem_free, + .io_mem_pfn = ttm_bo_default_io_mem_pfn, };int amdgpu_ttm_init (struct amdgpu_device *adev)
drivers/gpu/drm/ast/ast_ttm.c +1 -0
@@ -236,6 +236,7 @@ struct ttm_bo_driver ast_bo_driver = { .verify_access = ast_bo_verify_access, .io_mem_reserve = &ast_ttm_io_mem_reserve, .io_mem_free = &ast_ttm_io_mem_free, + .io_mem_pfn = ttm_bo_default_io_mem_pfn, };int ast_mm_init (struct ast_private *ast)
drivers/gpu/drm/bochs/bochs_mm.c +1 -0
@@ -205,6 +205,7 @@ struct ttm_bo_driver bochs_bo_driver = { .verify_access = bochs_bo_verify_access, .io_mem_reserve = &bochs_ttm_io_mem_reserve, .io_mem_free = &bochs_ttm_io_mem_free, + .io_mem_pfn = ttm_bo_default_io_mem_pfn, };int bochs_mm_init (struct bochs_device *bochs)
drivers/gpu/drm/cirrus/cirrus_ttm.c +1 -0
@@ -236,6 +236,7 @@ struct ttm_bo_driver cirrus_bo_driver = { .verify_access = cirrus_bo_verify_access, .io_mem_reserve = &cirrus_ttm_io_mem_reserve, .io_mem_free = &cirrus_ttm_io_mem_free, + .io_mem_pfn = ttm_bo_default_io_mem_pfn, };int cirrus_mm_init (struct cirrus_device *cirrus)
drivers/gpu/drm/mgag200/mgag200_ttm.c +1 -0
@@ -236,6 +236,7 @@ struct ttm_bo_driver mgag200_bo_driver = { .verify_access = mgag200_bo_verify_access, .io_mem_reserve = &mgag200_ttm_io_mem_reserve, .io_mem_free = &mgag200_ttm_io_mem_free, + .io_mem_pfn = ttm_bo_default_io_mem_pfn, };int mgag200_mm_init (struct mga_device *mdev)
drivers/gpu/drm/nouveau/nouveau_bo.c +1 -0
@@ -1570,6 +1570,7 @@ struct ttm_bo_driver nouveau_bo_driver = { .fault_reserve_notify = &nouveau_ttm_fault_reserve_notify, .io_mem_reserve = &nouveau_ttm_io_mem_reserve, .io_mem_free = &nouveau_ttm_io_mem_free, + .io_mem_pfn = ttm_bo_default_io_mem_pfn, }; struct nvkm_vma *
drivers/gpu/drm/qxl/qxl_ttm.c +1 -0
@@ -394,6 +394,7 @@ static struct ttm_bo_driver qxl_bo_driver = { .verify_access = &qxl_verify_access, .io_mem_reserve = &qxl_ttm_io_mem_reserve, .io_mem_free = &qxl_ttm_io_mem_free, + .io_mem_pfn = ttm_bo_default_io_mem_pfn, .move_notify = &qxl_bo_move_notify, };
drivers/gpu/drm/radeon/radeon_ttm.c +1 -0
@@ -873,6 +873,7 @@ static struct ttm_bo_driver radeon_bo_driver = { .fault_reserve_notify = &radeon_bo_fault_reserve_notify, .io_mem_reserve = &radeon_ttm_io_mem_reserve, .io_mem_free = &radeon_ttm_io_mem_free, + .io_mem_pfn = ttm_bo_default_io_mem_pfn, };int radeon_ttm_init (struct radeon_device *rdev)
drivers/gpu/drm/ttm/ttm_bo_vm.c +9 -1
@@ -231,7 +231,7 @@ static int ttm_bo_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)*/ for (i =0 ; i <TTM_BO_VM_NUM_PREFAULT ; ++i) {if (bo->mem.bus.is_iomem) - pfn = ((bo->mem.bus.base + bo->mem.bus.offset) >>PAGE_SHIFT ) + page_offset; + pfn = bdev->driver->io_mem_pfn (bo, page_offset);else { page = ttm->pages[page_offset];if (unlikely (!page && i ==0 )) {
@@ -324,6 +324,14 @@ static struct ttm_buffer_object *ttm_bo_vm_lookup(struct ttm_bo_device *bdev,return bo; } +unsigned long ttm_bo_default_io_mem_pfn (struct ttm_buffer_object *bo, +unsigned long page_offset) +{ +return ((bo->mem.bus.base + bo->mem.bus.offset) >>PAGE_SHIFT ) + + page_offset; +} +EXPORT_SYMBOL (ttm_bo_default_io_mem_pfn); +int ttm_bo_mmap (struct file *filp,struct vm_area_struct *vma,struct ttm_bo_device *bdev) {
drivers/gpu/drm/virtio/virtgpu_ttm.c +1 -0
@@ -432,6 +432,7 @@ static struct ttm_bo_driver virtio_gpu_bo_driver = { .verify_access = &virtio_gpu_verify_access, .io_mem_reserve = &virtio_gpu_ttm_io_mem_reserve, .io_mem_free = &virtio_gpu_ttm_io_mem_free, + .io_mem_pfn = ttm_bo_default_io_mem_pfn, .move_notify = &virtio_gpu_bo_move_notify, .swap_notify = &virtio_gpu_bo_swap_notify, };
drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c +1 -0
@@ -859,4 +859,5 @@ struct ttm_bo_driver vmw_bo_driver = { .fault_reserve_notify = &vmw_ttm_fault_reserve_notify, .io_mem_reserve = &vmw_ttm_io_mem_reserve, .io_mem_free = &vmw_ttm_io_mem_free, + .io_mem_pfn = ttm_bo_default_io_mem_pfn, };
include/drm/ttm/ttm_bo_api.h +11 -0
@@ -724,6 +724,17 @@ extern int ttm_fbdev_mmap(struct vm_area_struct *vma, struct ttm_buffer_object *bo);/** +* ttm_bo_default_iomem_pfn - get a pfn for a page offset +* +* @bo: the BO we need to look up the pfn for +* @page_offset: offset inside the BO to look up. +* +* Calculate the PFN for iomem based mappings during page fault +*/ +unsigned long ttm_bo_default_io_mem_pfn (struct ttm_buffer_object *bo, +unsigned long page_offset); + +/** * ttm_bo_mmap - mmap out of the ttm device address space. * * @filp: filp as input from the mmap method.
include/drm/ttm/ttm_bo_driver.h +9 -0
@@ -462,6 +462,15 @@ struct ttm_bo_driver { struct ttm_mem_reg *mem);void (*io_mem_free)(struct ttm_bo_device *bdev,struct ttm_mem_reg *mem); + +/** +* Return the pfn for a given page_offset inside the BO. +* +* @bo: the BO to look up the pfn for +* @page_offset: the offset to look up +*/ +unsigned long (*io_mem_pfn)(struct ttm_buffer_object *bo, +unsigned long page_offset); };/**
Signature · 6 lines
2.5.0 _______________________________________________ dri-devel mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/dri-devel
A message that is not in the archive (sent off-list or not yet received): 1490953652-3703-1-git-send-email-deathsimple-ANTagKRnAhcb1SvskN2V4Q@public.gmane.org
PATCH 3/6 drm/ttm: add TTM_PL_FLAG_CONTIGUOUS v2
From: Christian König <[email protected]>
This allows drivers to specify if they need a contiguous allocation or not.
v2: use space instead of tab
--- drivers/gpu/drm/ttm/ttm_bo.c | 4 +++- include/drm/ttm/ttm_placement.h | 1 + 2 files changed, 4 insertions(+), 1 deletion(-)
drivers/gpu/drm/ttm/ttm_bo.c +3 -1
@@ -1062,7 +1062,9 @@ static bool ttm_bo_places_compat(const struct ttm_place *places, *new_flags = heap->flags;if ((*new_flags & mem->placement &TTM_PL_MASK_CACHING ) && - (*new_flags & mem->placement &TTM_PL_MASK_MEM )) + (*new_flags & mem->placement &TTM_PL_MASK_MEM ) && + (!(*new_flags &TTM_PL_FLAG_CONTIGUOUS ) || + (mem->placement &TTM_PL_FLAG_CONTIGUOUS )))return true; }return false;
include/drm/ttm/ttm_placement.h +1 -0
@@ -63,6 +63,7 @@#define TTM_PL_FLAG_CACHED (1 << 16)#define TTM_PL_FLAG_UNCACHED (1 << 17)#define TTM_PL_FLAG_WC (1 << 18) +#define TTM_PL_FLAG_CONTIGUOUS (1 << 19)#define TTM_PL_FLAG_NO_EVICT (1 << 21)#define TTM_PL_FLAG_TOPDOWN (1 << 22)
Signature · 6 lines
2.5.0 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
Re: [PATCH 3/6] drm/ttm: add TTM_PL_FLAG_CONTIGUOUS v2
Quoted 7 lines · Christian König
From: Christian König <[email protected]>
This allows drivers to specify if they need a contiguous allocation or not.
v2: use space instead of tab
Signed-off-by Christian König <[email protected]>
Patches 1-3:
Patch 4:
Quoted 33 lines
--- drivers/gpu/drm/ttm/ttm_bo.c | 4 +++- include/drm/ttm/ttm_placement.h | 1 + 2 files changed, 4 insertions(+), 1 deletion(-)drivers/gpu/drm/ttm/ttm_bo.c +3
-1@@ -1062,7 +1062,9 @@ static bool ttm_bo_places_compat(const struct ttm_place *places, *new_flags = heap->flags;if ((*new_flags & mem->placement &TTM_PL_MASK_CACHING ) && - (*new_flags & mem->placement &TTM_PL_MASK_MEM )) + (*new_flags & mem->placement &TTM_PL_MASK_MEM ) && + (!(*new_flags &TTM_PL_FLAG_CONTIGUOUS ) || + (mem->placement &TTM_PL_FLAG_CONTIGUOUS )))return true; }return false;include/drm/ttm/ttm_placement.h +1
-0@@ -63,6 +63,7 @@#define TTM_PL_FLAG_CACHED (1 << 16)#define TTM_PL_FLAG_UNCACHED (1 << 17)#define TTM_PL_FLAG_WC (1 << 18) +#define TTM_PL_FLAG_CONTIGUOUS (1 << 19)#define TTM_PL_FLAG_NO_EVICT (1 << 21)#define TTM_PL_FLAG_TOPDOWN (1 << 22)
Signature · 6 lines
Lerne, wie die Welt wirklich ist, Aber vergiss niemals, wie sie sein sollte. _______________________________________________ dri-devel mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/dri-devel
PATCH 5/6 drm/amdgpu: use TTM_PL_FLAG_CONTIGUOUS
In reply to a message not in the archiveFrom: Christian König <[email protected]>
Implement AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS using TTM_PL_FLAG_CONTIGUOUS instead of a placement limit. That allows us to better handle CPU accessible placements.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 11 +++++------ drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c | 14 ++++++++++---- 2 files changed, 15 insertions(+), 10 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +5 -6
@@ -122,20 +122,19 @@ static void amdgpu_ttm_placement_init(struct amdgpu_device *adev,if (domain &AMDGPU_GEM_DOMAIN_VRAM ) {unsigned visible_pfn = adev->mc.visible_vram_size >>PAGE_SHIFT ; -unsigned lpfn =0 ; - -/* This forces a reallocation if the flag wasn't set before */ -if (flags &AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS ) - lpfn = adev->mc.real_vram_size >>PAGE_SHIFT ; places[c].fpfn =0 ; - places[c].lpfn = lpfn; + places[c].lpfn =0 ; places[c].flags =TTM_PL_FLAG_WC |TTM_PL_FLAG_UNCACHED |TTM_PL_FLAG_VRAM ; +if (flags &AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED ) places[c].lpfn = visible_pfn;else places[c].flags |=TTM_PL_FLAG_TOPDOWN ; + +if (flags &AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS ) + places[c].flags |=TTM_PL_FLAG_CONTIGUOUS ; c++; }
drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +10 -4
@@ -93,7 +93,6 @@ static int amdgpu_vram_mgr_new(struct ttm_mem_type_manager *man,const struct ttm_place *place, struct ttm_mem_reg *mem) { - struct amdgpu_bo *bo = container_of(tbo, struct amdgpu_bo, tbo); struct amdgpu_vram_mgr *mgr = man->priv;struct drm_mm *mm = &mgr->mm;struct drm_mm_node *nodes;
@@ -107,8 +106,8 @@ static int amdgpu_vram_mgr_new(struct ttm_mem_type_manager *man,if (!lpfn) lpfn = man->size; -if (bo->flags &AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS || - place->lpfn || amdgpu_vram_page_split ==-1 ) { +if (place->flags &TTM_PL_FLAG_CONTIGUOUS || + amdgpu_vram_page_split ==-1 ) { pages_per_node = ~0ul ; num_nodes =1 ; }else {
@@ -126,12 +125,14 @@ static int amdgpu_vram_mgr_new(struct ttm_mem_type_manager *man, aflags =DRM_MM_CREATE_TOP ; } + mem->start =0 ; pages_left = mem->num_pages;spin_lock (&mgr->lock);for (i =0 ; i < num_nodes; ++i) {unsigned long pages =min (pages_left, pages_per_node);uint32_t alignment = mem->page_alignment; +unsigned long start;if (pages == pages_per_node) alignment = pages_per_node;
@@ -145,11 +146,16 @@ static int amdgpu_vram_mgr_new(struct ttm_mem_type_manager *man,if (unlikely (r)) goto error; +/* +* Calculate a virtual BO start address to easily check if +* everything is CPU accessible. +*/ + start = nodes[i].start + nodes[i].size - mem->num_pages; + mem->start =max (mem->start, start); pages_left -= pages; }spin_unlock (&mgr->lock); - mem->start = num_nodes ==1 ? nodes[0 ].start :AMDGPU_BO_INVALID_OFFSET ; mem->mm_node = nodes;return 0 ;
Signature · 6 lines
2.5.0 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): 1490953652-3703-5-git-send-email-deathsimple-ANTagKRnAhcb1SvskN2V4Q@public.gmane.org
Re: [PATCH 5/6] drm/amdgpu: use TTM_PL_FLAG_CONTIGUOUS
Quoted 82 lines · Christian König
From: Christian König <[email protected]>
Implement
AMDGPU_GEM_CREATE_VRAM_CONTIGUOUSusingTTM_PL_FLAG_CONTIGUOUSinstead of a placement limit. That allows us to better handle CPU accessible placements.Signed-off-by Christian König <[email protected]>Acked-by Michel Dänzer <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 11 +++++------ drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c | 14 ++++++++++---- 2 files changed, 15 insertions(+), 10 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +5
-6@@ -122,20 +122,19 @@ static void amdgpu_ttm_placement_init(struct amdgpu_device *adev,if (domain &AMDGPU_GEM_DOMAIN_VRAM ) {unsigned visible_pfn = adev->mc.visible_vram_size >>PAGE_SHIFT ; -unsigned lpfn =0 ; - -/* This forces a reallocation if the flag wasn't set before */ -if (flags &AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS ) - lpfn = adev->mc.real_vram_size >>PAGE_SHIFT ; places[c].fpfn =0 ; - places[c].lpfn = lpfn; + places[c].lpfn =0 ; places[c].flags =TTM_PL_FLAG_WC |TTM_PL_FLAG_UNCACHED |TTM_PL_FLAG_VRAM ; +if (flags &AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED ) places[c].lpfn = visible_pfn;else places[c].flags |=TTM_PL_FLAG_TOPDOWN ; + +if (flags &AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS ) + places[c].flags |=TTM_PL_FLAG_CONTIGUOUS ; c++; }drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +4
-3@@ -93,7 +93,6 @@ static int amdgpu_vram_mgr_new(struct ttm_mem_type_manager *man,const struct ttm_place *place, struct ttm_mem_reg *mem) { - struct amdgpu_bo *bo = container_of(tbo, struct amdgpu_bo, tbo); struct amdgpu_vram_mgr *mgr = man->priv;struct drm_mm *mm = &mgr->mm;struct drm_mm_node *nodes;@@ -107,8 +106,8 @@ static int amdgpu_vram_mgr_new(struct ttm_mem_type_manager *man,if (!lpfn) lpfn = man->size; -if (bo->flags &AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS || - place->lpfn || amdgpu_vram_page_split ==-1 ) { +if (place->flags &TTM_PL_FLAG_CONTIGUOUS || + amdgpu_vram_page_split ==-1 ) { pages_per_node = ~0ul ; num_nodes =1 ; }else {@@ -126,12 +125,14 @@ static int amdgpu_vram_mgr_new(struct ttm_mem_type_manager *man, aflags =DRM_MM_CREATE_TOP ; } + mem->start =0 ; pages_left = mem->num_pages;spin_lock (&mgr->lock);for (i =0 ; i < num_nodes; ++i) {unsigned long pages =min (pages_left, pages_per_node);uint32_t alignment = mem->page_alignment; +unsigned long start;if (pages == pages_per_node) alignment = pages_per_node;
drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c static int amdgpu_vram_mgr_new(struct ttm_mem_type_manager *man, · line 153
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +5
-0@@ -145,11 +146,16 @@ static int amdgpu_vram_mgr_new(struct ttm_mem_type_manager *man,if (unlikely (r)) goto error; +/* +* Calculate a virtual BO start address to easily check if +* everything is CPU accessible. +*/ + start = nodes[i].start + nodes[i].size - mem->num_pages;
This might wrap around (be a signed negative number), completely breaking the max() logic below.
drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c static int amdgpu_vram_mgr_new(struct ttm_mem_type_manager *man, · line 152
Quoted 6 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +1
-1+ mem->start =max (mem->start, start); pages_left -= pages; }spin_unlock (&mgr->lock); - mem->start = num_nodes ==1 ? nodes[0 ].start :AMDGPU_BO_INVALID_OFFSET ;
If we're going to abuse mem->start anyway, might I suggest just keeping track of max(nodes[i].start + nodes[i].size), and then setting mem->start to a magic (macro'd) constant based on whether everything is in visible VRAM or not?
Then the check in amdgpu_ttm_io_mem_reserve could be simplified accordingly.
Also, I think patches #6 and #5 should be exchanged, otherwise there's a temporary bug in handling split visible VRAM buffers.
Cheers,
Nicolai
Quoted 4 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +0
-0mem->mm_node = nodes;return 0 ;
Signature · 6 lines
Lerne, wie die Welt wirklich ist, Aber vergiss niemals, wie sie sein sollte. _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): 425dfa9e-c86b-6958-f7ff-31b91a0f9e21-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org
Re: [PATCH 5/6] drm/amdgpu: use TTM_PL_FLAG_CONTIGUOUS
Am 03.04.2017 um 18:22 schrieb Nicolai Hähnle:
Quoted 92 lines · Christian König
Quoted 91 lines
From: Christian König <[email protected]>
Implement
AMDGPU_GEM_CREATE_VRAM_CONTIGUOUSusingTTM_PL_FLAG_CONTIGUOUSinstead of a placement limit. That allows us to better handle CPU accessible placements.Signed-off-by Christian König <[email protected]>Acked-by Michel Dänzer <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 11 +++++------ drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c | 14 ++++++++++---- 2 files changed, 15 insertions(+), 10 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +5
-6@@ -122,20 +122,19 @@ static void amdgpu_ttm_placement_init(struct amdgpu_device *adev, if (domain & AMDGPU_GEM_DOMAIN_VRAM) {unsigned visible_pfn = adev->mc.visible_vram_size >>PAGE_SHIFT ; -unsigned lpfn =0 ; - -/* This forces a reallocation if the flag wasn't set before */ -if (flags &AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS ) - lpfn = adev->mc.real_vram_size >>PAGE_SHIFT ; places[c].fpfn =0 ; - places[c].lpfn = lpfn; + places[c].lpfn =0 ; places[c].flags =TTM_PL_FLAG_WC |TTM_PL_FLAG_UNCACHED |TTM_PL_FLAG_VRAM ; +if (flags &AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED ) places[c].lpfn = visible_pfn;else places[c].flags |=TTM_PL_FLAG_TOPDOWN ; + +if (flags &AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS ) + places[c].flags |=TTM_PL_FLAG_CONTIGUOUS ; c++;}drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +0
-1@@ -93,7 +93,6 @@ static int amdgpu_vram_mgr_new(structttm_mem_type_manager *man, const struct ttm_place *place, struct ttm_mem_reg *mem) { - struct amdgpu_bo *bo = container_of(tbo, struct amdgpu_bo, tbo); struct amdgpu_vram_mgr *mgr = man->priv;struct drm_mm *mm = &mgr->mm;struct drm_mm_node *nodes;drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +2
-2@@ -107,8 +106,8 @@ static int amdgpu_vram_mgr_new(struct ttm_mem_type_manager *man, if (!lpfn) lpfn = man->size; -if (bo->flags &AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS || - place->lpfn || amdgpu_vram_page_split ==-1 ) { +if (place->flags &TTM_PL_FLAG_CONTIGUOUS || + amdgpu_vram_page_split ==-1 ) { pages_per_node = ~0ul ; num_nodes =1 ;} else {drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +2
-0@@ -126,12 +125,14 @@ static int amdgpu_vram_mgr_new(structttm_mem_type_manager *man, aflags =DRM_MM_CREATE_TOP ; } + mem->start =0 ; pages_left = mem->num_pages;spin_lock (&mgr->lock);for (i =0 ; i < num_nodes; ++i) {unsigned long pages =min (pages_left, pages_per_node);uint32_t alignment = mem->page_alignment; +unsigned long start;if (pages == pages_per_node)alignment = pages_per_node;drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +0
-0@@ -145,11 +146,16 @@ static int amdgpu_vram_mgr_new(struct ttm_mem_type_manager *man, if (unlikely(r)) goto error;
Quoted 7 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c static int amdgpu_vram_mgr_new(struct ttm_mem_type_manager *man, · line 153
Quoted 5 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +5
-0+/* +* Calculate a virtual BO start address to easily check if +* everything is CPU accessible. +*/ + start = nodes[i].start + nodes[i].size - mem->num_pages;This might wrap around (be a signed negative number), completely breaking the
max()logic below.
Good point, going to fix that.
Quoted 11 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c static int amdgpu_vram_mgr_new(struct ttm_mem_type_manager *man,
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +1
-1+ mem->start =max (mem->start, start); pages_left -= pages; }spin_unlock (&mgr->lock); - mem->start = num_nodes ==1 ? nodes[0 ].start :AMDGPU_BO_INVALID_OFFSET ;If we're going to abuse
mem->startanyway, might I suggest just keeping track ofmax(nodes[i].start + nodes[i].size), and then settingmem->startto a magic (macro'd) constant based on whether everything is in visible VRAM or not?
No, that would break in kernel mappings.
Quoted 3 lines
Then the check in
amdgpu_ttm_io_mem_reservecould be simplified accordingly.Also, I think patches #6 and #5 should be exchanged, otherwise there's a temporary bug in handling split visible VRAM buffers.
Hui? Why? Patch #6 enables the whole thing by not making the contiguous flag mandatory for CPU mappings any more.
Switching those would cause problems with detecting when a BO is not in visible VRAM.
Regards,
Christian.
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
Re: [PATCH 5/6] drm/amdgpu: use TTM_PL_FLAG_CONTIGUOUS
Quoted 123 lines · Christian König
Am 03.04.2017 um 18:22 schrieb Nicolai Hähnle:
Quoted 94 lines · Christian König
Quoted 93 lines
From: Christian König <[email protected]>
Implement
AMDGPU_GEM_CREATE_VRAM_CONTIGUOUSusingTTM_PL_FLAG_CONTIGUOUSinstead of a placement limit. That allows us to better handle CPU accessible placements.Signed-off-by Christian König <[email protected]>Acked-by Michel Dänzer <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 11 +++++------ drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c | 14 ++++++++++---- 2 files changed, 15 insertions(+), 10 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +5
-6@@ -122,20 +122,19 @@ static void amdgpu_ttm_placement_init(struct amdgpu_device *adev, if (domain & AMDGPU_GEM_DOMAIN_VRAM) {unsigned visible_pfn = adev->mc.visible_vram_size >>PAGE_SHIFT ; -unsigned lpfn =0 ; - -/* This forces a reallocation if the flag wasn't set before */ -if (flags &AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS ) - lpfn = adev->mc.real_vram_size >>PAGE_SHIFT ; places[c].fpfn =0 ; - places[c].lpfn = lpfn; + places[c].lpfn =0 ; places[c].flags =TTM_PL_FLAG_WC |TTM_PL_FLAG_UNCACHED |TTM_PL_FLAG_VRAM ; +if (flags &AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED ) places[c].lpfn = visible_pfn;else places[c].flags |=TTM_PL_FLAG_TOPDOWN ; + +if (flags &AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS ) + places[c].flags |=TTM_PL_FLAG_CONTIGUOUS ; c++;}drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +0
-1@@ -93,7 +93,6 @@ static int amdgpu_vram_mgr_new(structttm_mem_type_manager *man, const struct ttm_place *place, struct ttm_mem_reg *mem) { - struct amdgpu_bo *bo = container_of(tbo, struct amdgpu_bo, tbo); struct amdgpu_vram_mgr *mgr = man->priv;struct drm_mm *mm = &mgr->mm;struct drm_mm_node *nodes;drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +2
-2@@ -107,8 +106,8 @@ static int amdgpu_vram_mgr_new(struct ttm_mem_type_manager *man, if (!lpfn) lpfn = man->size; -if (bo->flags &AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS || - place->lpfn || amdgpu_vram_page_split ==-1 ) { +if (place->flags &TTM_PL_FLAG_CONTIGUOUS || + amdgpu_vram_page_split ==-1 ) { pages_per_node = ~0ul ; num_nodes =1 ;} else {drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +2
-0@@ -126,12 +125,14 @@ static int amdgpu_vram_mgr_new(structttm_mem_type_manager *man, aflags =DRM_MM_CREATE_TOP ; } + mem->start =0 ; pages_left = mem->num_pages;spin_lock (&mgr->lock);for (i =0 ; i < num_nodes; ++i) {unsigned long pages =min (pages_left, pages_per_node);uint32_t alignment = mem->page_alignment; +unsigned long start;if (pages == pages_per_node)alignment = pages_per_node;drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +0
-0@@ -145,11 +146,16 @@ static int amdgpu_vram_mgr_new(struct ttm_mem_type_manager *man, if (unlikely(r)) goto error;Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c static int amdgpu_vram_mgr_new(struct ttm_mem_type_manager *man, · line 153
Quoted 5 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +5
-0+/* +* Calculate a virtual BO start address to easily check if +* everything is CPU accessible. +*/ + start = nodes[i].start + nodes[i].size - mem->num_pages;This might wrap around (be a signed negative number), completely breaking the
max()logic below.Good point, going to fix that.
Quoted 6 lines
Quoted 6 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +1
-0+ mem->start =max (mem->start, start); pages_left -= pages; }spin_unlock (&mgr->lock);Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c static int amdgpu_vram_mgr_new(struct · line 160
Quoted 2 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +0
-1- mem->start = num_nodes ==1 ? nodes[0 ].start :AMDGPU_BO_INVALID_OFFSET ;If we're going to abuse
mem->startanyway, might I suggest just keeping track ofmax(nodes[i].start + nodes[i].size), and then settingmem->startto a magic (macro'd) constant based on whether everything is in visible VRAM or not?No, that would break in kernel mappings.
Quoted 8 lines
Quoted 5 lines
Then the check in
amdgpu_ttm_io_mem_reservecould be simplified accordingly.Also, I think patches #6 and #5 should be exchanged, otherwise there's a temporary bug in handling split visible VRAM buffers.
Hui? Why? Patch #6 enables the whole thing by not making the contiguous flag mandatory for CPU mappings any more.
Ah, I missed the fact that it's guarded by the check in amdgpu_bo_fault_reserve_notify. You're right, the order of patches is good.
Cheers,
Nicolai
Quoted 7 lines
Switching those would cause problems with detecting when a BO is not in visible VRAM.
Regards,
Christian.
Signature · 6 lines
Lerne, wie die Welt wirklich ist, Aber vergiss niemals, wie sie sein sollte. _______________________________________________ dri-devel mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/dri-devel
PATCH 6/6 drm/amdgpu: handle CPU access for split VRAM buffers
In reply to a message not in the archiveFrom: Christian König <[email protected]>
This avoids merging them together on page fault.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 4 +--- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 16 ++++++++++++---- 2 files changed, 13 insertions(+), 7 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +1 -3
@@ -927,8 +927,7 @@ int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo) size = bo->mem.num_pages <<PAGE_SHIFT ; offset = bo->mem.start <<PAGE_SHIFT ;/* TODO: figure out how to map scattered VRAM to the CPU */ -if ((offset + size) <= adev->mc.visible_vram_size && - (abo->flags &AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS )) +if ((offset + size) <= adev->mc.visible_vram_size)return 0 ;/* Can't move a pinned BO to visible VRAM */
@@ -936,7 +935,6 @@ int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)return -EINVAL ;/* hurrah the memory is not visible ! */ - abo->flags |=AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS ;amdgpu_ttm_placement_from_domain (abo,AMDGPU_GEM_DOMAIN_VRAM ); lpfn = adev->mc.visible_vram_size >>PAGE_SHIFT ;for (i =0 ; i < abo->placement.num_placement; i++) {
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +12 -4
@@ -529,9 +529,6 @@ static int amdgpu_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_case TTM_PL_TT :break ;case TTM_PL_VRAM : -if (mem->start ==AMDGPU_BO_INVALID_OFFSET ) -return -EINVAL ; - mem->bus.offset = mem->start <<PAGE_SHIFT ;/* check if it's visible */ if ((mem->bus.offset + mem->bus.size) > adev->mc.visible_vram_size)
@@ -549,6 +546,17 @@ static void amdgpu_ttm_io_mem_free(struct ttm_bo_device *bdev, struct ttm_mem_re { } +static unsigned long amdgpu_ttm_io_mem_pfn (struct ttm_buffer_object *bo, +unsigned long page_offset) +{ +struct drm_mm_node *mm = bo->mem.mm_node; +uint64_t size = mm->size; + + mm += page_offset / size; + page_offset %= size; +return (bo->mem.bus.base >>PAGE_SHIFT ) + mm->start + page_offset; +} +/* * TTM backend functions. */
@@ -1064,7 +1072,7 @@ static struct ttm_bo_driver amdgpu_bo_driver = { .fault_reserve_notify = &amdgpu_bo_fault_reserve_notify, .io_mem_reserve = &amdgpu_ttm_io_mem_reserve, .io_mem_free = &amdgpu_ttm_io_mem_free, - .io_mem_pfn = ttm_bo_default_io_mem_pfn, + .io_mem_pfn = amdgpu_ttm_io_mem_pfn, };int amdgpu_ttm_init (struct amdgpu_device *adev)
Signature · 6 lines
2.5.0 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
Re: [PATCH 6/6] drm/amdgpu: handle CPU access for split VRAM buffers
Quoted 38 lines · Christian König
From: Christian König <[email protected]>
This avoids merging them together on page fault.
Signed-off-by Christian König <[email protected]>Acked-by Michel Dänzer <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 4 +--- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 16 ++++++++++++---- 2 files changed, 13 insertions(+), 7 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +1
-3@@ -927,8 +927,7 @@ int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo) size = bo->mem.num_pages <<PAGE_SHIFT ; offset = bo->mem.start <<PAGE_SHIFT ;/* TODO: figure out how to map scattered VRAM to the CPU */ -if ((offset + size) <= adev->mc.visible_vram_size && - (abo->flags &AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS )) +if ((offset + size) <= adev->mc.visible_vram_size)return 0 ;/* Can't move a pinned BO to visible VRAM */ @@ -936,7 +935,6 @@ int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)return -EINVAL ;/* hurrah the memory is not visible ! */ - abo->flags |=AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS ;amdgpu_ttm_placement_from_domain (abo,AMDGPU_GEM_DOMAIN_VRAM ); lpfn = adev->mc.visible_vram_size >>PAGE_SHIFT ;for (i =0 ; i < abo->placement.num_placement; i++) {drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +0
-0
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c static int amdgpu_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_ · line 534
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +0
-3@@ -529,9 +529,6 @@ static int amdgpu_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_case TTM_PL_TT :break ;case TTM_PL_VRAM : -if (mem->start ==AMDGPU_BO_INVALID_OFFSET ) -return -EINVAL ; - mem->bus.offset = mem->start <<PAGE_SHIFT ;/* check if it's visible */ if ((mem->bus.offset + mem->bus.size) > adev->mc.visible_vram_size)
I believe the various mem->bus members are now unused, aren't they? Unless I missed something, it's best to clean this up and no longer set them (or set them to some obvious poison values).
Cheers,
Nicolai
Quoted 28 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +12
-1@@ -549,6 +546,17 @@ static void amdgpu_ttm_io_mem_free(struct ttm_bo_device *bdev, struct ttm_mem_re { } +static unsigned long amdgpu_ttm_io_mem_pfn (struct ttm_buffer_object *bo, +unsigned long page_offset) +{ +struct drm_mm_node *mm = bo->mem.mm_node; +uint64_t size = mm->size; + + mm += page_offset / size; + page_offset %= size; +return (bo->mem.bus.base >>PAGE_SHIFT ) + mm->start + page_offset; +} +/* * TTM backend functions. */ @@ -1064,7 +1072,7 @@ static struct ttm_bo_driver amdgpu_bo_driver = { .fault_reserve_notify = &amdgpu_bo_fault_reserve_notify, .io_mem_reserve = &amdgpu_ttm_io_mem_reserve, .io_mem_free = &amdgpu_ttm_io_mem_free, - .io_mem_pfn = ttm_bo_default_io_mem_pfn, + .io_mem_pfn = amdgpu_ttm_io_mem_pfn, };int amdgpu_ttm_init (struct amdgpu_device *adev)
Signature · 6 lines
Lerne, wie die Welt wirklich ist, Aber vergiss niemals, wie sie sein sollte. _______________________________________________ dri-devel mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/dri-devel
Re: [PATCH 6/6] drm/amdgpu: handle CPU access for split VRAM buffers
Am 03.04.2017 um 18:25 schrieb Nicolai Hähnle:
Quoted 9 lines · Christian König
Quoted 6 lines
From: Christian König <[email protected]>
[SNIP]mem->bus.offset = mem->start << PAGE_SHIFT; /* check if it's visible */ if ((mem->bus.offset + mem->bus.size) >
adev->mc.visible_vram_size)I believe the various
mem->busmembers are now unused, aren't they? Unless I missed something, it's best to clean this up and no longer set them (or set them to some obvious poison values).
No, they are still needed for in kernel mappings. I only handle split mappings from userspace with the new callback.
Regards,
Christian.
_______________________________________________
dri-devel mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/dri-devel
Ping! Any more comments on that set or can I push it?
Thanks,
Christian.
Am 31.03.2017 um 11:47 schrieb Christian König:
Quoted 68 lines
From: Christian König <[email protected]>
No need to implement the same logic twice. Also check if the busy placements are identical to the already scanned placements before checking them.
v2: improve check even more as suggested by Michel.
Signed-off-by Christian König <[email protected]>--- drivers/gpu/drm/ttm/ttm_bo.c | 45 ++++++++++++++++++++++++-------------------- 1 file changed, 25 insertions(+), 20 deletions(-)drivers/gpu/drm/ttm/ttm_bo.c +18
-20@@ -1046,29 +1046,17 @@ static int ttm_bo_move_buffer(struct ttm_buffer_object *bo,return ret; } -bool ttm_bo_mem_compat (struct ttm_placement *placement, -struct ttm_mem_reg *mem, -uint32_t *new_flags) +static bool ttm_bo_places_compat (const struct ttm_place *places, +unsigned num_placement, +struct ttm_mem_reg *mem, +uint32_t *new_flags) { -int i; +unsigned i; -for (i =0 ; i < placement->num_placement; i++) { -const struct ttm_place *heap = &placement->placement[i]; -if (mem->mm_node && - (mem->start < heap->fpfn || - (heap->lpfn !=0 && (mem->start + mem->num_pages) > heap->lpfn))) -continue ; +for (i =0 ; i < num_placement; i++) { +const struct ttm_place *heap = &places[i]; - *new_flags = heap->flags; -if ((*new_flags & mem->placement &TTM_PL_MASK_CACHING ) && - (*new_flags & mem->placement &TTM_PL_MASK_MEM )) -return true; - } - -for (i =0 ; i < placement->num_busy_placement; i++) { -const struct ttm_place *heap = &placement->busy_placement[i]; -if (mem->mm_node && - (mem->start < heap->fpfn || +if (mem->mm_node && (mem->start < heap->fpfn || (heap->lpfn !=0 && (mem->start + mem->num_pages) > heap->lpfn)))continue ;@@ -1077,6 +1065,23 @@ bool ttm_bo_mem_compat(struct ttm_placement *placement, (*new_flags & mem->placement & TTM_PL_MASK_MEM))return true; } +return false; +} + +bool ttm_bo_mem_compat (struct ttm_placement *placement, +struct ttm_mem_reg *mem, +uint32_t *new_flags) +{ +if (ttm_bo_places_compat (placement->placement, placement->num_placement, + mem, new_flags)) +return true;
drivers/gpu/drm/ttm/ttm_bo.c bool ttm_bo_mem_compat(struct ttm_placement *placement, · line 1087
Quoted 10 lines
drivers/gpu/drm/ttm/ttm_bo.c +7
-0+ +if ((placement->busy_placement != placement->placement || + placement->num_busy_placement > placement->num_placement) && +ttm_bo_places_compat (placement->busy_placement, + placement->num_busy_placement, + mem, new_flags)) +return true;return false; }
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
PATCH 4/6 drm/amdgpu: drop alpha support
In reply to Christian KönigFrom: Christian König <[email protected]>
We will probably never see this combination.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 25 ------------------------- 1 file changed, 25 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +0 -25
@@ -538,31 +538,6 @@ static int amdgpu_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_return -EINVAL ; mem->bus.base = adev->mc.aper_base; mem->bus.is_iomem = true; -#ifdef __alpha__ -/* -* Alpha: use bus.addr to hold the ioremap() return, -* so we can modify bus.base below. -*/ -if (mem->placement &TTM_PL_FLAG_WC ) - mem->bus.addr = -ioremap_wc (mem->bus.base + mem->bus.offset, - mem->bus.size); -else - mem->bus.addr = -ioremap_nocache (mem->bus.base + mem->bus.offset, - mem->bus.size); -if (!mem->bus.addr) -return -ENOMEM ; - -/* -* Alpha: Use just the bus offset plus -* the hose/domain memory base for bus.base. -* It then can be used to build PTEs for VRAM -* access, as done in ttm_bo_vm_fault(). -*/ - mem->bus.base = (mem->bus.base &0x0ffffffffUL ) + - adev->ddev->hose->dense_mem_base; -#endif break ;default :return -EINVAL ;
Signature · 6 lines
2.5.0 _______________________________________________ dri-devel mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/dri-devel