With this patch series I am trying to remove GPU address dependency in TTM and moving GPU address calculation to individual drm drivers. This cleanup will simplify introduction of drm_mem_region/domain work started by Brian Welty[1].
It would be nice if someone test this for nouveau. Rest of the drivers are already tested.
v2: * set bo->offset = 0 for drm/nouveau if bo->mem.mm_node == NULL
v3: * catch return value of drm_gem_vram_offset() in drm/bochs * introduce drm_gem_vram_pg_offset() in vram helper * improve nbo->offset calculation for nouveau
v4: * minor coding style fixes in amdgpu and radeon * remove unnecessary kerneldoc for internal function
Nirmoy Das (8): drm/amdgpu: move ttm bo->offset to amdgpu_bo drm/radeon: don't use ttm bo->offset drm/vmwgfx: don't use ttm bo->offset drm/nouveau: don't use ttm bo->offset v3 drm/qxl: don't use ttm bo->offset drm/vram-helper: don't use ttm bo->offset v3 drm/bochs: use drm_gem_vram_offset to get bo offset v2 drm/ttm: do not keep GPU dependent addresses
drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 22 ++++++++++++++-- drivers/gpu/drm/amd/amdgpu/amdgpu_object.h | 1 + drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 29 ++++++++++++++++----- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h | 1 + drivers/gpu/drm/bochs/bochs_kms.c | 7 ++++- drivers/gpu/drm/drm_gem_vram_helper.c | 9 ++++++- drivers/gpu/drm/nouveau/dispnv04/crtc.c | 6 ++--- drivers/gpu/drm/nouveau/dispnv04/disp.c | 2 +- drivers/gpu/drm/nouveau/dispnv04/overlay.c | 6 ++--- drivers/gpu/drm/nouveau/dispnv50/base507c.c | 2 +- drivers/gpu/drm/nouveau/dispnv50/core507d.c | 2 +- drivers/gpu/drm/nouveau/dispnv50/ovly507e.c | 2 +- drivers/gpu/drm/nouveau/dispnv50/wndw.c | 2 +- drivers/gpu/drm/nouveau/dispnv50/wndwc37e.c | 2 +- drivers/gpu/drm/nouveau/nouveau_abi16.c | 8 +++--- drivers/gpu/drm/nouveau/nouveau_bo.c | 8 ++++++ drivers/gpu/drm/nouveau/nouveau_bo.h | 3 +++ drivers/gpu/drm/nouveau/nouveau_chan.c | 2 +- drivers/gpu/drm/nouveau/nouveau_dmem.c | 2 +- drivers/gpu/drm/nouveau/nouveau_fbcon.c | 2 +- drivers/gpu/drm/nouveau/nouveau_gem.c | 10 +++---- drivers/gpu/drm/qxl/qxl_drv.h | 6 ++--- drivers/gpu/drm/qxl/qxl_kms.c | 5 ++-- drivers/gpu/drm/qxl/qxl_object.h | 5 ---- drivers/gpu/drm/qxl/qxl_ttm.c | 9 ------- drivers/gpu/drm/radeon/radeon.h | 1 + drivers/gpu/drm/radeon/radeon_object.h | 16 +++++++++++- drivers/gpu/drm/radeon/radeon_ttm.c | 4 +-- drivers/gpu/drm/ttm/ttm_bo.c | 7 ----- drivers/gpu/drm/vmwgfx/vmwgfx_bo.c | 4 +-- drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c | 2 +- drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c | 2 +- drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c | 2 -- include/drm/ttm/ttm_bo_api.h | 2 -- include/drm/ttm/ttm_bo_driver.h | 1 - 35 files changed, 118 insertions(+), 76 deletions(-)
-- 2.25.0
GPU address should belong to driver not in memory management. This patch moves ttm bo.offset and gpu_offset calculation to amdgpu driver.
Signed-off-by: Nirmoy Das nirmoy.das@amd.com Acked-by: Huang Rui ray.huang@amd.com Reviewed-by: Christian König christian.koenig@amd.com --- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 22 ++++++++++++++-- drivers/gpu/drm/amd/amdgpu/amdgpu_object.h | 1 + drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 29 ++++++++++++++++------ drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h | 1 + 4 files changed, 44 insertions(+), 9 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 1791c084787d..52c7e579f2d1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -918,7 +918,7 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, bo->pin_count++;
if (max_offset != 0) { - u64 domain_start = bo->tbo.bdev->man[mem_type].gpu_offset; + u64 domain_start = amdgpu_ttm_domain_start(adev, mem_type); WARN_ON_ONCE(max_offset < (amdgpu_bo_gpu_offset(bo) - domain_start)); } @@ -1483,7 +1483,25 @@ u64 amdgpu_bo_gpu_offset(struct amdgpu_bo *bo) WARN_ON_ONCE(bo->tbo.mem.mem_type == TTM_PL_VRAM && !(bo->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS));
- return amdgpu_gmc_sign_extend(bo->tbo.offset); + return amdgpu_bo_gpu_offset_no_check(bo); +} + +/** + * amdgpu_bo_gpu_offset_no_check - return GPU offset of bo + * @bo: amdgpu object for which we query the offset + * + * Returns: + * current GPU offset of the object without raising warnings. + */ +u64 amdgpu_bo_gpu_offset_no_check(struct amdgpu_bo *bo) +{ + struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); + uint64_t offset; + + offset = (bo->tbo.mem.start << PAGE_SHIFT) + + amdgpu_ttm_domain_start(adev, bo->tbo.mem.mem_type); + + return amdgpu_gmc_sign_extend(offset); }
/** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h index 5e39ecd8cc28..32edd35d2ccf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h @@ -282,6 +282,7 @@ int amdgpu_bo_sync_wait_resv(struct amdgpu_device *adev, struct dma_resv *resv, bool intr); int amdgpu_bo_sync_wait(struct amdgpu_bo *bo, void *owner, bool intr); u64 amdgpu_bo_gpu_offset(struct amdgpu_bo *bo); +u64 amdgpu_bo_gpu_offset_no_check(struct amdgpu_bo *bo); int amdgpu_bo_validate(struct amdgpu_bo *bo); int amdgpu_bo_restore_shadow(struct amdgpu_bo *shadow, struct dma_fence **fence); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index fe131c21e8a3..87781fabf5f5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -96,7 +96,6 @@ static int amdgpu_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, case TTM_PL_TT: /* GTT memory */ man->func = &amdgpu_gtt_mgr_func; - man->gpu_offset = adev->gmc.gart_start; man->available_caching = TTM_PL_MASK_CACHING; man->default_caching = TTM_PL_FLAG_CACHED; man->flags = TTM_MEMTYPE_FLAG_MAPPABLE | TTM_MEMTYPE_FLAG_CMA; @@ -104,7 +103,6 @@ static int amdgpu_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, case TTM_PL_VRAM: /* "On-card" video ram */ man->func = &amdgpu_vram_mgr_func; - man->gpu_offset = adev->gmc.vram_start; man->flags = TTM_MEMTYPE_FLAG_FIXED | TTM_MEMTYPE_FLAG_MAPPABLE; man->available_caching = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC; @@ -115,7 +113,6 @@ static int amdgpu_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, case AMDGPU_PL_OA: /* On-chip GDS memory*/ man->func = &ttm_bo_manager_func; - man->gpu_offset = 0; man->flags = TTM_MEMTYPE_FLAG_FIXED | TTM_MEMTYPE_FLAG_CMA; man->available_caching = TTM_PL_FLAG_UNCACHED; man->default_caching = TTM_PL_FLAG_UNCACHED; @@ -263,7 +260,7 @@ static uint64_t amdgpu_mm_node_addr(struct ttm_buffer_object *bo,
if (mm_node->start != AMDGPU_BO_INVALID_OFFSET) { addr = mm_node->start << PAGE_SHIFT; - addr += bo->bdev->man[mem->mem_type].gpu_offset; + addr += amdgpu_ttm_domain_start(amdgpu_ttm_adev(bo->bdev), mem->mem_type); } return addr; } @@ -750,6 +747,27 @@ static unsigned long amdgpu_ttm_io_mem_pfn(struct ttm_buffer_object *bo, (offset >> PAGE_SHIFT); }
+/** + * amdgpu_ttm_domain_start - Returns GPU start address + * @adev: amdgpu device object + * @type: type of the memory + * + * Returns: + * GPU start address of a memory domain + */ + +uint64_t amdgpu_ttm_domain_start(struct amdgpu_device *adev, uint32_t type) +{ + switch (type) { + case TTM_PL_TT: + return adev->gmc.gart_start; + case TTM_PL_VRAM: + return adev->gmc.vram_start; + } + + return 0; +} + /* * TTM backend functions. */ @@ -1161,9 +1179,6 @@ int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo) bo->mem = tmp; }
- bo->offset = (bo->mem.start << PAGE_SHIFT) + - bo->bdev->man[bo->mem.mem_type].gpu_offset; - return 0; }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h index 7551f3729445..72875a0fbfcf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -102,6 +102,7 @@ int amdgpu_fill_buffer(struct amdgpu_bo *bo, int amdgpu_mmap(struct file *filp, struct vm_area_struct *vma); int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo); int amdgpu_ttm_recover_gart(struct ttm_buffer_object *tbo); +uint64_t amdgpu_ttm_domain_start(struct amdgpu_device *adev, uint32_t type);
#if IS_ENABLED(CONFIG_DRM_AMDGPU_USERPTR) int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages);
On 2020-03-05 08:29, Nirmoy Das wrote:
GPU address should belong to driver not in memory management. This patch moves ttm bo.offset and gpu_offset calculation to amdgpu driver.
Signed-off-by: Nirmoy Das nirmoy.das@amd.com Acked-by: Huang Rui ray.huang@amd.com Reviewed-by: Christian König christian.koenig@amd.com
drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 22 ++++++++++++++-- drivers/gpu/drm/amd/amdgpu/amdgpu_object.h | 1 + drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 29 ++++++++++++++++------ drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h | 1 + 4 files changed, 44 insertions(+), 9 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 1791c084787d..52c7e579f2d1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -918,7 +918,7 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, bo->pin_count++;
if (max_offset != 0) {
u64 domain_start = bo->tbo.bdev->man[mem_type].gpu_offset;
u64 domain_start = amdgpu_ttm_domain_start(adev, mem_type); WARN_ON_ONCE(max_offset < (amdgpu_bo_gpu_offset(bo) - domain_start));@@ -1483,7 +1483,25 @@ u64 amdgpu_bo_gpu_offset(struct amdgpu_bo *bo) WARN_ON_ONCE(bo->tbo.mem.mem_type == TTM_PL_VRAM && !(bo->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS));
- return amdgpu_gmc_sign_extend(bo->tbo.offset);
- return amdgpu_bo_gpu_offset_no_check(bo);
+}
+/**
- amdgpu_bo_gpu_offset_no_check - return GPU offset of bo
- @bo: amdgpu object for which we query the offset
- Returns:
- current GPU offset of the object without raising warnings.
- */
+u64 amdgpu_bo_gpu_offset_no_check(struct amdgpu_bo *bo) +{
- struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
- uint64_t offset;
offset = (bo->tbo.mem.start << PAGE_SHIFT) +amdgpu_ttm_domain_start(adev, bo->tbo.mem.mem_type);
Align the above assignment, "offset" is out of alignment, as is the line following it.
Regards, Luben
- return amdgpu_gmc_sign_extend(offset);
}
/** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h index 5e39ecd8cc28..32edd35d2ccf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h @@ -282,6 +282,7 @@ int amdgpu_bo_sync_wait_resv(struct amdgpu_device *adev, struct dma_resv *resv, bool intr); int amdgpu_bo_sync_wait(struct amdgpu_bo *bo, void *owner, bool intr); u64 amdgpu_bo_gpu_offset(struct amdgpu_bo *bo); +u64 amdgpu_bo_gpu_offset_no_check(struct amdgpu_bo *bo); int amdgpu_bo_validate(struct amdgpu_bo *bo); int amdgpu_bo_restore_shadow(struct amdgpu_bo *shadow, struct dma_fence **fence); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index fe131c21e8a3..87781fabf5f5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -96,7 +96,6 @@ static int amdgpu_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, case TTM_PL_TT: /* GTT memory */ man->func = &amdgpu_gtt_mgr_func;
man->gpu_offset = adev->gmc.gart_start;@@ -104,7 +103,6 @@ static int amdgpu_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, case TTM_PL_VRAM: /* "On-card" video ram */ man->func = &amdgpu_vram_mgr_func;
man->gpu_offset = adev->gmc.vram_start;@@ -115,7 +113,6 @@ static int amdgpu_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, case AMDGPU_PL_OA: /* On-chip GDS memory*/ man->func = &ttm_bo_manager_func;
man->gpu_offset = 0;@@ -263,7 +260,7 @@ static uint64_t amdgpu_mm_node_addr(struct ttm_buffer_object *bo,
if (mm_node->start != AMDGPU_BO_INVALID_OFFSET) { addr = mm_node->start << PAGE_SHIFT;
addr += bo->bdev->man[mem->mem_type].gpu_offset;
addr += amdgpu_ttm_domain_start(amdgpu_ttm_adev(bo->bdev), mem->mem_type);} @@ -750,6 +747,27 @@ static unsigned long amdgpu_ttm_io_mem_pfn(struct ttm_buffer_object *bo, (offset >> PAGE_SHIFT); }
+/**
- amdgpu_ttm_domain_start - Returns GPU start address
- @adev: amdgpu device object
- @type: type of the memory
- Returns:
- GPU start address of a memory domain
- */
+uint64_t amdgpu_ttm_domain_start(struct amdgpu_device *adev, uint32_t type) +{
- switch (type) {
- case TTM_PL_TT:
return adev->gmc.gart_start;- case TTM_PL_VRAM:
return adev->gmc.vram_start;- }
- return 0;
+}
/*
- TTM backend functions.
*/ @@ -1161,9 +1179,6 @@ int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo) bo->mem = tmp; }
- bo->offset = (bo->mem.start << PAGE_SHIFT) +
bo->bdev->man[bo->mem.mem_type].gpu_offset;- return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h index 7551f3729445..72875a0fbfcf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -102,6 +102,7 @@ int amdgpu_fill_buffer(struct amdgpu_bo *bo, int amdgpu_mmap(struct file *filp, struct vm_area_struct *vma); int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo); int amdgpu_ttm_recover_gart(struct ttm_buffer_object *tbo); +uint64_t amdgpu_ttm_domain_start(struct amdgpu_device *adev, uint32_t type);
#if IS_ENABLED(CONFIG_DRM_AMDGPU_USERPTR) int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages);
Calculate GPU offset in radeon_bo_gpu_offset without depending on bo->offset.
Signed-off-by: Nirmoy Das nirmoy.das@amd.com Reviewed-and-tested-by: Christian König christian.koenig@amd.com --- drivers/gpu/drm/radeon/radeon.h | 1 + drivers/gpu/drm/radeon/radeon_object.h | 16 +++++++++++++++- drivers/gpu/drm/radeon/radeon_ttm.c | 4 +--- 3 files changed, 17 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 30e32adc1fc6..b7c3fb2bfb54 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -2828,6 +2828,7 @@ extern void radeon_ttm_set_active_vram_size(struct radeon_device *rdev, u64 size extern void radeon_program_register_sequence(struct radeon_device *rdev, const u32 *registers, const u32 array_size); +struct radeon_device *radeon_get_rdev(struct ttm_bo_device *bdev);
/* * vm diff --git a/drivers/gpu/drm/radeon/radeon_object.h b/drivers/gpu/drm/radeon/radeon_object.h index d23f2ed4126e..60275b822f79 100644 --- a/drivers/gpu/drm/radeon/radeon_object.h +++ b/drivers/gpu/drm/radeon/radeon_object.h @@ -90,7 +90,21 @@ static inline void radeon_bo_unreserve(struct radeon_bo *bo) */ static inline u64 radeon_bo_gpu_offset(struct radeon_bo *bo) { - return bo->tbo.offset; + struct radeon_device *rdev; + u64 start = 0; + + rdev = radeon_get_rdev(bo->tbo.bdev); + + switch (bo->tbo.mem.mem_type) { + case TTM_PL_TT: + start = rdev->mc.gtt_start; + break; + case TTM_PL_VRAM: + start = rdev->mc.vram_start; + break; + } + + return (bo->tbo.mem.start << PAGE_SHIFT) + start; }
static inline unsigned long radeon_bo_size(struct radeon_bo *bo) diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index badf1b6d1549..1c8303468e8f 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -56,7 +56,7 @@ static int radeon_ttm_debugfs_init(struct radeon_device *rdev); static void radeon_ttm_debugfs_fini(struct radeon_device *rdev);
-static struct radeon_device *radeon_get_rdev(struct ttm_bo_device *bdev) +struct radeon_device *radeon_get_rdev(struct ttm_bo_device *bdev) { struct radeon_mman *mman; struct radeon_device *rdev; @@ -82,7 +82,6 @@ static int radeon_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, break; case TTM_PL_TT: man->func = &ttm_bo_manager_func; - man->gpu_offset = rdev->mc.gtt_start; man->available_caching = TTM_PL_MASK_CACHING; man->default_caching = TTM_PL_FLAG_CACHED; man->flags = TTM_MEMTYPE_FLAG_MAPPABLE | TTM_MEMTYPE_FLAG_CMA; @@ -104,7 +103,6 @@ static int radeon_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, case TTM_PL_VRAM: /* "On-card" video ram */ man->func = &ttm_bo_manager_func; - man->gpu_offset = rdev->mc.vram_start; man->flags = TTM_MEMTYPE_FLAG_FIXED | TTM_MEMTYPE_FLAG_MAPPABLE; man->available_caching = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC; -- 2.25.0
On 2020-03-05 08:29, Nirmoy Das wrote:
Calculate GPU offset in radeon_bo_gpu_offset without depending on bo->offset.
Signed-off-by: Nirmoy Das nirmoy.das@amd.com Reviewed-and-tested-by: Christian König christian.koenig@amd.com
drivers/gpu/drm/radeon/radeon.h | 1 + drivers/gpu/drm/radeon/radeon_object.h | 16 +++++++++++++++- drivers/gpu/drm/radeon/radeon_ttm.c | 4 +--- 3 files changed, 17 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 30e32adc1fc6..b7c3fb2bfb54 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -2828,6 +2828,7 @@ extern void radeon_ttm_set_active_vram_size(struct radeon_device *rdev, u64 size extern void radeon_program_register_sequence(struct radeon_device *rdev, const u32 *registers, const u32 array_size); +struct radeon_device *radeon_get_rdev(struct ttm_bo_device *bdev);
/*
- vm
diff --git a/drivers/gpu/drm/radeon/radeon_object.h b/drivers/gpu/drm/radeon/radeon_object.h index d23f2ed4126e..60275b822f79 100644 --- a/drivers/gpu/drm/radeon/radeon_object.h +++ b/drivers/gpu/drm/radeon/radeon_object.h @@ -90,7 +90,21 @@ static inline void radeon_bo_unreserve(struct radeon_bo *bo) */ static inline u64 radeon_bo_gpu_offset(struct radeon_bo *bo) {
- return bo->tbo.offset;
- struct radeon_device *rdev;
- u64 start = 0;
- rdev = radeon_get_rdev(bo->tbo.bdev);
- switch (bo->tbo.mem.mem_type) {
- case TTM_PL_TT:
start = rdev->mc.gtt_start;break;- case TTM_PL_VRAM:
start = rdev->mc.vram_start;break;- }
- return (bo->tbo.mem.start << PAGE_SHIFT) + start;
}
You're removing a "return bo->tbo.offset" and adding a switch-case statement. So, then, now instead of an instant lookup, you're adding branching. You're adding comparison and branching. Do you think that's better? Faster? Smaller?
I've written before about this for this patch: Why not create a map, whose index is "mem_type" which references the desired address? No comparison, no branching. Just an index-dereference and a value:
return rdev->mc.mem_start_map[bo->tbo.mem.mem_type];
Obviously, you'll have to create "mem_start_map".
That's a NAK from me on this patch using comparison and branching to return static data lookup value.
Regards, Luben
static inline unsigned long radeon_bo_size(struct radeon_bo *bo) diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index badf1b6d1549..1c8303468e8f 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -56,7 +56,7 @@ static int radeon_ttm_debugfs_init(struct radeon_device *rdev); static void radeon_ttm_debugfs_fini(struct radeon_device *rdev);
-static struct radeon_device *radeon_get_rdev(struct ttm_bo_device *bdev) +struct radeon_device *radeon_get_rdev(struct ttm_bo_device *bdev) { struct radeon_mman *mman; struct radeon_device *rdev; @@ -82,7 +82,6 @@ static int radeon_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, break; case TTM_PL_TT: man->func = &ttm_bo_manager_func;
man->gpu_offset = rdev->mc.gtt_start;@@ -104,7 +103,6 @@ static int radeon_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, case TTM_PL_VRAM: /* "On-card" video ram */ man->func = &ttm_bo_manager_func;
man->gpu_offset = rdev->mc.vram_start;-- 2.25.0
amd-gfx mailing list amd-gfx@lists.freedesktop.org https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Flists.free...
[AMD Official Use Only - Internal Distribution Only]
I believe bo->tbo.mem.mem_type is of uint32_t type and not an enum, is the index lookup method safe? (i.e., how do you deal with the possibility of having value TTM_PL_PRIV or above or are you suggesting those are not possible for this function.)
Kenny ________________________________ From: Tuikov, Luben Luben.Tuikov@amd.com Sent: Thursday, March 5, 2020 2:19 PM To: Nirmoy Das nirmoy.aiemd@gmail.com; dri-devel@lists.freedesktop.org dri-devel@lists.freedesktop.org Cc: Zhou, David(ChunMing) David1.Zhou@amd.com; thellstrom@vmware.com thellstrom@vmware.com; airlied@linux.ie airlied@linux.ie; Ho, Kenny Kenny.Ho@amd.com; brian.welty@intel.com brian.welty@intel.com; maarten.lankhorst@linux.intel.com maarten.lankhorst@linux.intel.com; amd-gfx@lists.freedesktop.org amd-gfx@lists.freedesktop.org; Das, Nirmoy Nirmoy.Das@amd.com; linux-graphics-maintainer@vmware.com linux-graphics-maintainer@vmware.com; bskeggs@redhat.com bskeggs@redhat.com; daniel@ffwll.ch daniel@ffwll.ch; Deucher, Alexander Alexander.Deucher@amd.com; sean@poorly.run sean@poorly.run; Koenig, Christian Christian.Koenig@amd.com; kraxel@redhat.com kraxel@redhat.com Subject: Re: [PATCH 2/8] drm/radeon: don't use ttm bo->offset
On 2020-03-05 08:29, Nirmoy Das wrote:
Calculate GPU offset in radeon_bo_gpu_offset without depending on bo->offset.
Signed-off-by: Nirmoy Das nirmoy.das@amd.com Reviewed-and-tested-by: Christian König christian.koenig@amd.com
drivers/gpu/drm/radeon/radeon.h | 1 + drivers/gpu/drm/radeon/radeon_object.h | 16 +++++++++++++++- drivers/gpu/drm/radeon/radeon_ttm.c | 4 +--- 3 files changed, 17 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 30e32adc1fc6..b7c3fb2bfb54 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -2828,6 +2828,7 @@ extern void radeon_ttm_set_active_vram_size(struct radeon_device *rdev, u64 size extern void radeon_program_register_sequence(struct radeon_device *rdev, const u32 *registers, const u32 array_size); +struct radeon_device *radeon_get_rdev(struct ttm_bo_device *bdev);
/*
- vm
diff --git a/drivers/gpu/drm/radeon/radeon_object.h b/drivers/gpu/drm/radeon/radeon_object.h index d23f2ed4126e..60275b822f79 100644 --- a/drivers/gpu/drm/radeon/radeon_object.h +++ b/drivers/gpu/drm/radeon/radeon_object.h @@ -90,7 +90,21 @@ static inline void radeon_bo_unreserve(struct radeon_bo *bo) */ static inline u64 radeon_bo_gpu_offset(struct radeon_bo *bo) {
return bo->tbo.offset;
struct radeon_device *rdev;u64 start = 0;rdev = radeon_get_rdev(bo->tbo.bdev);switch (bo->tbo.mem.mem_type) {case TTM_PL_TT:start = rdev->mc.gtt_start;break;case TTM_PL_VRAM:start = rdev->mc.vram_start;break;}return (bo->tbo.mem.start << PAGE_SHIFT) + start;}
You're removing a "return bo->tbo.offset" and adding a switch-case statement. So, then, now instead of an instant lookup, you're adding branching. You're adding comparison and branching. Do you think that's better? Faster? Smaller?
I've written before about this for this patch: Why not create a map, whose index is "mem_type" which references the desired address? No comparison, no branching. Just an index-dereference and a value:
return rdev->mc.mem_start_map[bo->tbo.mem.mem_type];
Obviously, you'll have to create "mem_start_map".
That's a NAK from me on this patch using comparison and branching to return static data lookup value.
Regards, Luben
static inline unsigned long radeon_bo_size(struct radeon_bo *bo) diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index badf1b6d1549..1c8303468e8f 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -56,7 +56,7 @@ static int radeon_ttm_debugfs_init(struct radeon_device *rdev); static void radeon_ttm_debugfs_fini(struct radeon_device *rdev);
-static struct radeon_device *radeon_get_rdev(struct ttm_bo_device *bdev) +struct radeon_device *radeon_get_rdev(struct ttm_bo_device *bdev) { struct radeon_mman *mman; struct radeon_device *rdev; @@ -82,7 +82,6 @@ static int radeon_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, break; case TTM_PL_TT: man->func = &ttm_bo_manager_func;
man->gpu_offset = rdev->mc.gtt_start; man->available_caching = TTM_PL_MASK_CACHING; man->default_caching = TTM_PL_FLAG_CACHED; man->flags = TTM_MEMTYPE_FLAG_MAPPABLE | TTM_MEMTYPE_FLAG_CMA;@@ -104,7 +103,6 @@ static int radeon_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, case TTM_PL_VRAM: /* "On-card" video ram */ man->func = &ttm_bo_manager_func;
man->gpu_offset = rdev->mc.vram_start; man->flags = TTM_MEMTYPE_FLAG_FIXED | TTM_MEMTYPE_FLAG_MAPPABLE; man->available_caching = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC;-- 2.25.0
amd-gfx mailing list amd-gfx@lists.freedesktop.org https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Flists.free...
On 2020-03-05 14:37, Ho, Kenny wrote:
[AMD Official Use Only - Internal Distribution Only]
I believe bo->tbo.mem.mem_type is of uint32_t type and not an enum, is the index lookup method safe? (i.e., how do you deal with the possibility of having value TTM_PL_PRIV or above or are you suggesting those are not possible for this function.)
Hi Kenny,
Good question. I'm not suggesting that those are not possible with this function. The driver provides this map. The format of the map is set by the infrastructure (TTM), it could be as simple as "u64 *mem_start_map; int map_size;" in an embedding struture or something more fancy. However the map array and values themselves are set by the driver when it answers about its capabilities, etc, when it first registers with TTM.
Notice how badly the switch statment below is written. (Inverview question.) It's missing a "default:" label! (it's why switch-case is powerful).
If you add a "default:" label, you see that the rest of the values in the map are 0s.
While TTM knows only of TTM_PL_PRIV number of maps (3), the driver can add more, allocate and initialize the map, and return it back to TTM, guaranteeing at least TTM_PL_PRIV maps in indices 0, 1, and 2.
I think it is not a good idea to use a compare-branch for a simple lookup like this. One naturally asks, "why isn't this a simple map lookup?"
Consider the following thought experiment: we continue to add switch-case and if-else for all sorts of simple things as we've seen being suggested in recent patches. In a few years, we'll not be able to understand the code.
Regards, Luben P.S. Code obfuscation isn't necessarily a bad thing--it causes a complete rewrite! :-D
Kenny
*From:* Tuikov, Luben Luben.Tuikov@amd.com *Sent:* Thursday, March 5, 2020 2:19 PM *To:* Nirmoy Das nirmoy.aiemd@gmail.com; dri-devel@lists.freedesktop.org dri-devel@lists.freedesktop.org *Cc:* Zhou, David(ChunMing) David1.Zhou@amd.com; thellstrom@vmware.com thellstrom@vmware.com; airlied@linux.ie airlied@linux.ie; Ho, Kenny Kenny.Ho@amd.com; brian.welty@intel.com brian.welty@intel.com; maarten.lankhorst@linux.intel.com maarten.lankhorst@linux.intel.com; amd-gfx@lists.freedesktop.org amd-gfx@lists.freedesktop.org; Das, Nirmoy Nirmoy.Das@amd.com; linux-graphics-maintainer@vmware.com linux-graphics-maintainer@vmware.com; bskeggs@redhat.com bskeggs@redhat.com; daniel@ffwll.ch daniel@ffwll.ch; Deucher, Alexander Alexander.Deucher@amd.com; sean@poorly.run sean@poorly.run; Koenig, Christian Christian.Koenig@amd.com; kraxel@redhat.com kraxel@redhat.com *Subject:* Re: [PATCH 2/8] drm/radeon: don't use ttm bo->offset On 2020-03-05 08:29, Nirmoy Das wrote:
Calculate GPU offset in radeon_bo_gpu_offset without depending on bo->offset.
Signed-off-by: Nirmoy Das nirmoy.das@amd.com Reviewed-and-tested-by: Christian König christian.koenig@amd.com
drivers/gpu/drm/radeon/radeon.h | 1 + drivers/gpu/drm/radeon/radeon_object.h | 16 +++++++++++++++- drivers/gpu/drm/radeon/radeon_ttm.c | 4 +--- 3 files changed, 17 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 30e32adc1fc6..b7c3fb2bfb54 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -2828,6 +2828,7 @@ extern void radeon_ttm_set_active_vram_size(struct radeon_device *rdev, u64 size extern void radeon_program_register_sequence(struct radeon_device *rdev, const u32 *registers, const u32 array_size); +struct radeon_device *radeon_get_rdev(struct ttm_bo_device *bdev);
/* * vm diff --git a/drivers/gpu/drm/radeon/radeon_object.h b/drivers/gpu/drm/radeon/radeon_object.h index d23f2ed4126e..60275b822f79 100644 --- a/drivers/gpu/drm/radeon/radeon_object.h +++ b/drivers/gpu/drm/radeon/radeon_object.h @@ -90,7 +90,21 @@ static inline void radeon_bo_unreserve(struct radeon_bo *bo) */ static inline u64 radeon_bo_gpu_offset(struct radeon_bo *bo) { - return bo->tbo.offset; + struct radeon_device *rdev; + u64 start = 0;
+ rdev = radeon_get_rdev(bo->tbo.bdev);
+ switch (bo->tbo.mem.mem_type) { + case TTM_PL_TT: + start = rdev->mc.gtt_start; + break; + case TTM_PL_VRAM: + start = rdev->mc.vram_start; + break; + }
+ return (bo->tbo.mem.start << PAGE_SHIFT) + start; }
You're removing a "return bo->tbo.offset" and adding a switch-case statement. So, then, now instead of an instant lookup, you're adding branching. You're adding comparison and branching. Do you think that's better? Faster? Smaller?
I've written before about this for this patch: Why not create a map, whose index is "mem_type" which references the desired address? No comparison, no branching. Just an index-dereference and a value:
return rdev->mc.mem_start_map[bo->tbo.mem.mem_type];
Obviously, you'll have to create "mem_start_map".
That's a NAK from me on this patch using comparison and branching to return static data lookup value.
Regards, Luben
static inline unsigned long radeon_bo_size(struct radeon_bo *bo) diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index badf1b6d1549..1c8303468e8f 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -56,7 +56,7 @@ static int radeon_ttm_debugfs_init(struct radeon_device *rdev); static void radeon_ttm_debugfs_fini(struct radeon_device *rdev);
-static struct radeon_device *radeon_get_rdev(struct ttm_bo_device *bdev) +struct radeon_device *radeon_get_rdev(struct ttm_bo_device *bdev) { struct radeon_mman *mman; struct radeon_device *rdev; @@ -82,7 +82,6 @@ static int radeon_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, break; case TTM_PL_TT: man->func = &ttm_bo_manager_func; - man->gpu_offset = rdev->mc.gtt_start; man->available_caching = TTM_PL_MASK_CACHING; man->default_caching = TTM_PL_FLAG_CACHED; man->flags = TTM_MEMTYPE_FLAG_MAPPABLE | TTM_MEMTYPE_FLAG_CMA; @@ -104,7 +103,6 @@ static int radeon_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, case TTM_PL_VRAM: /* "On-card" video ram */ man->func = &ttm_bo_manager_func; - man->gpu_offset = rdev->mc.vram_start; man->flags = TTM_MEMTYPE_FLAG_FIXED | TTM_MEMTYPE_FLAG_MAPPABLE; man->available_caching = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC; -- 2.25.0
amd-gfx mailing list amd-gfx@lists.freedesktop.org https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Flists.free...
Calculate GPU offset within vmwgfx driver itself without depending on bo->offset.
Signed-off-by: Nirmoy Das nirmoy.das@amd.com Acked-by: Christian König christian.koenig@amd.com Acked-by: Thomas Hellstrom thellstrom@vmware.com Tested-by: Thomas Hellstrom thellstrom@vmware.com --- drivers/gpu/drm/vmwgfx/vmwgfx_bo.c | 4 ++-- drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c | 2 +- drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c | 2 +- drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c | 2 -- 4 files changed, 4 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c index 8b71bf6b58ef..1e59c019affa 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c @@ -258,7 +258,7 @@ int vmw_bo_pin_in_start_of_vram(struct vmw_private *dev_priv, ret = ttm_bo_validate(bo, &placement, &ctx);
/* For some reason we didn't end up at the start of vram */ - WARN_ON(ret == 0 && bo->offset != 0); + WARN_ON(ret == 0 && bo->mem.start != 0); if (!ret) vmw_bo_pin_reserved(buf, true);
@@ -317,7 +317,7 @@ void vmw_bo_get_guest_ptr(const struct ttm_buffer_object *bo, { if (bo->mem.mem_type == TTM_PL_VRAM) { ptr->gmrId = SVGA_GMR_FRAMEBUFFER; - ptr->offset = bo->offset; + ptr->offset = bo->mem.start << PAGE_SHIFT; } else { ptr->gmrId = bo->mem.start; ptr->offset = 0; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 73489a45decb..72c2cf4053df 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -3313,7 +3313,7 @@ static void vmw_apply_relocations(struct vmw_sw_context *sw_context) bo = &reloc->vbo->base; switch (bo->mem.mem_type) { case TTM_PL_VRAM: - reloc->location->offset += bo->offset; + reloc->location->offset += bo->mem.start << PAGE_SHIFT; reloc->location->gmrId = SVGA_GMR_FRAMEBUFFER; break; case VMW_PL_GMR: diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c index e5252ef3812f..1cdc445b24c3 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c @@ -612,7 +612,7 @@ static int vmw_fifo_emit_dummy_legacy_query(struct vmw_private *dev_priv,
if (bo->mem.mem_type == TTM_PL_VRAM) { cmd->body.guestResult.gmrId = SVGA_GMR_FRAMEBUFFER; - cmd->body.guestResult.offset = bo->offset; + cmd->body.guestResult.offset = bo->mem.start << PAGE_SHIFT; } else { cmd->body.guestResult.gmrId = bo->mem.start; cmd->body.guestResult.offset = 0; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c index 3f3b2c7a208a..e7134aebeb81 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c @@ -750,7 +750,6 @@ static int vmw_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, case TTM_PL_VRAM: /* "On-card" video ram */ man->func = &ttm_bo_manager_func; - man->gpu_offset = 0; man->flags = TTM_MEMTYPE_FLAG_FIXED | TTM_MEMTYPE_FLAG_MAPPABLE; man->available_caching = TTM_PL_FLAG_CACHED; man->default_caching = TTM_PL_FLAG_CACHED; @@ -763,7 +762,6 @@ static int vmw_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, * slots as well as the bo size. */ man->func = &vmw_gmrid_manager_func; - man->gpu_offset = 0; man->flags = TTM_MEMTYPE_FLAG_CMA | TTM_MEMTYPE_FLAG_MAPPABLE; man->available_caching = TTM_PL_FLAG_CACHED; man->default_caching = TTM_PL_FLAG_CACHED; -- 2.25.0
Store ttm bo->offset in struct nouveau_bo instead.
Signed-off-by: Nirmoy Das nirmoy.das@amd.com --- drivers/gpu/drm/nouveau/dispnv04/crtc.c | 6 +++--- drivers/gpu/drm/nouveau/dispnv04/disp.c | 2 +- drivers/gpu/drm/nouveau/dispnv04/overlay.c | 6 +++--- drivers/gpu/drm/nouveau/dispnv50/base507c.c | 2 +- drivers/gpu/drm/nouveau/dispnv50/core507d.c | 2 +- drivers/gpu/drm/nouveau/dispnv50/ovly507e.c | 2 +- drivers/gpu/drm/nouveau/dispnv50/wndw.c | 2 +- drivers/gpu/drm/nouveau/dispnv50/wndwc37e.c | 2 +- drivers/gpu/drm/nouveau/nouveau_abi16.c | 8 ++++---- drivers/gpu/drm/nouveau/nouveau_bo.c | 8 ++++++++ drivers/gpu/drm/nouveau/nouveau_bo.h | 3 +++ drivers/gpu/drm/nouveau/nouveau_chan.c | 2 +- drivers/gpu/drm/nouveau/nouveau_dmem.c | 2 +- drivers/gpu/drm/nouveau/nouveau_fbcon.c | 2 +- drivers/gpu/drm/nouveau/nouveau_gem.c | 10 +++++----- 15 files changed, 35 insertions(+), 24 deletions(-)
diff --git a/drivers/gpu/drm/nouveau/dispnv04/crtc.c b/drivers/gpu/drm/nouveau/dispnv04/crtc.c index 1f08de4241e0..d06a93f2b38a 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/crtc.c +++ b/drivers/gpu/drm/nouveau/dispnv04/crtc.c @@ -845,7 +845,7 @@ nv04_crtc_do_mode_set_base(struct drm_crtc *crtc, fb = nouveau_framebuffer(crtc->primary->fb); }
- nv_crtc->fb.offset = fb->nvbo->bo.offset; + nv_crtc->fb.offset = fb->nvbo->offset;
if (nv_crtc->lut.depth != drm_fb->format->depth) { nv_crtc->lut.depth = drm_fb->format->depth; @@ -1013,7 +1013,7 @@ nv04_crtc_cursor_set(struct drm_crtc *crtc, struct drm_file *file_priv, nv04_cursor_upload(dev, cursor, nv_crtc->cursor.nvbo);
nouveau_bo_unmap(cursor); - nv_crtc->cursor.offset = nv_crtc->cursor.nvbo->bo.offset; + nv_crtc->cursor.offset = nv_crtc->cursor.nvbo->offset; nv_crtc->cursor.set_offset(nv_crtc, nv_crtc->cursor.offset); nv_crtc->cursor.show(nv_crtc, true); out: @@ -1191,7 +1191,7 @@ nv04_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb, /* Initialize a page flip struct */ *s = (struct nv04_page_flip_state) { { }, event, crtc, fb->format->cpp[0] * 8, fb->pitches[0], - new_bo->bo.offset }; + new_bo->offset };
/* Keep vblanks on during flip, for the target crtc of this flip */ drm_crtc_vblank_get(crtc); diff --git a/drivers/gpu/drm/nouveau/dispnv04/disp.c b/drivers/gpu/drm/nouveau/dispnv04/disp.c index 44ee82d0c9b6..89a4ddfcc55f 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv04/disp.c @@ -151,7 +151,7 @@ nv04_display_init(struct drm_device *dev, bool resume, bool runtime) continue;
if (nv_crtc->cursor.set_offset) - nv_crtc->cursor.set_offset(nv_crtc, nv_crtc->cursor.nvbo->bo.offset); + nv_crtc->cursor.set_offset(nv_crtc, nv_crtc->cursor.nvbo->offset); nv_crtc->cursor.set_pos(nv_crtc, nv_crtc->cursor_saved_x, nv_crtc->cursor_saved_y); } diff --git a/drivers/gpu/drm/nouveau/dispnv04/overlay.c b/drivers/gpu/drm/nouveau/dispnv04/overlay.c index a3a0a73ae8ab..9529bd9053e7 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/overlay.c +++ b/drivers/gpu/drm/nouveau/dispnv04/overlay.c @@ -150,7 +150,7 @@ nv10_update_plane(struct drm_plane *plane, struct drm_crtc *crtc, nvif_mask(dev, NV_PCRTC_ENGINE_CTRL + soff2, NV_CRTC_FSEL_OVERLAY, 0);
nvif_wr32(dev, NV_PVIDEO_BASE(flip), 0); - nvif_wr32(dev, NV_PVIDEO_OFFSET_BUFF(flip), nv_fb->nvbo->bo.offset); + nvif_wr32(dev, NV_PVIDEO_OFFSET_BUFF(flip), nv_fb->nvbo->offset); nvif_wr32(dev, NV_PVIDEO_SIZE_IN(flip), src_h << 16 | src_w); nvif_wr32(dev, NV_PVIDEO_POINT_IN(flip), src_y << 16 | src_x); nvif_wr32(dev, NV_PVIDEO_DS_DX(flip), (src_w << 20) / crtc_w); @@ -172,7 +172,7 @@ nv10_update_plane(struct drm_plane *plane, struct drm_crtc *crtc, if (format & NV_PVIDEO_FORMAT_PLANAR) { nvif_wr32(dev, NV_PVIDEO_UVPLANE_BASE(flip), 0); nvif_wr32(dev, NV_PVIDEO_UVPLANE_OFFSET_BUFF(flip), - nv_fb->nvbo->bo.offset + fb->offsets[1]); + nv_fb->nvbo->offset + fb->offsets[1]); } nvif_wr32(dev, NV_PVIDEO_FORMAT(flip), format | fb->pitches[0]); nvif_wr32(dev, NV_PVIDEO_STOP, 0); @@ -396,7 +396,7 @@ nv04_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
for (i = 0; i < 2; i++) { nvif_wr32(dev, NV_PVIDEO_BUFF0_START_ADDRESS + 4 * i, - nv_fb->nvbo->bo.offset); + nv_fb->nvbo->offset); nvif_wr32(dev, NV_PVIDEO_BUFF0_PITCH_LENGTH + 4 * i, fb->pitches[0]); nvif_wr32(dev, NV_PVIDEO_BUFF0_OFFSET + 4 * i, 0); diff --git a/drivers/gpu/drm/nouveau/dispnv50/base507c.c b/drivers/gpu/drm/nouveau/dispnv50/base507c.c index 00a85f1e1a4a..67829f04b2c7 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/base507c.c +++ b/drivers/gpu/drm/nouveau/dispnv50/base507c.c @@ -274,7 +274,7 @@ base507c_new_(const struct nv50_wndw_func *func, const u32 *format,
ret = nv50_dmac_create(&drm->client.device, &disp->disp->object, &oclass, head, &args, sizeof(args), - disp->sync->bo.offset, &wndw->wndw); + disp->sync->offset, &wndw->wndw); if (ret) { NV_ERROR(drm, "base%04x allocation failed: %d\n", oclass, ret); return ret; diff --git a/drivers/gpu/drm/nouveau/dispnv50/core507d.c b/drivers/gpu/drm/nouveau/dispnv50/core507d.c index e7fcfa6e6467..793dcb2ea196 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/core507d.c +++ b/drivers/gpu/drm/nouveau/dispnv50/core507d.c @@ -99,7 +99,7 @@ core507d_new_(const struct nv50_core_func *func, struct nouveau_drm *drm,
ret = nv50_dmac_create(&drm->client.device, &disp->disp->object, &oclass, 0, &args, sizeof(args), - disp->sync->bo.offset, &core->chan); + disp->sync->offset, &core->chan); if (ret) { NV_ERROR(drm, "core%04x allocation failed: %d\n", oclass, ret); return ret; diff --git a/drivers/gpu/drm/nouveau/dispnv50/ovly507e.c b/drivers/gpu/drm/nouveau/dispnv50/ovly507e.c index 8ccd96113bad..4cce1078140a 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/ovly507e.c +++ b/drivers/gpu/drm/nouveau/dispnv50/ovly507e.c @@ -186,7 +186,7 @@ ovly507e_new_(const struct nv50_wndw_func *func, const u32 *format,
ret = nv50_dmac_create(&drm->client.device, &disp->disp->object, &oclass, 0, &args, sizeof(args), - disp->sync->bo.offset, &wndw->wndw); + disp->sync->offset, &wndw->wndw); if (ret) { NV_ERROR(drm, "ovly%04x allocation failed: %d\n", oclass, ret); return ret; diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c index 890315291b01..e90ffa4a5230 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c +++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c @@ -509,7 +509,7 @@ nv50_wndw_prepare_fb(struct drm_plane *plane, struct drm_plane_state *state) }
asyw->state.fence = dma_resv_get_excl_rcu(fb->nvbo->bo.base.resv); - asyw->image.offset[0] = fb->nvbo->bo.offset; + asyw->image.offset[0] = fb->nvbo->offset;
if (wndw->func->prepare) { asyh = nv50_head_atom_get(asyw->state.state, asyw->state.crtc); diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndwc37e.c b/drivers/gpu/drm/nouveau/dispnv50/wndwc37e.c index b92dc3461bbd..bb84e4d54a33 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndwc37e.c +++ b/drivers/gpu/drm/nouveau/dispnv50/wndwc37e.c @@ -298,7 +298,7 @@ wndwc37e_new_(const struct nv50_wndw_func *func, struct nouveau_drm *drm,
ret = nv50_dmac_create(&drm->client.device, &disp->disp->object, &oclass, 0, &args, sizeof(args), - disp->sync->bo.offset, &wndw->wndw); + disp->sync->offset, &wndw->wndw); if (ret) { NV_ERROR(drm, "qndw%04x allocation failed: %d\n", oclass, ret); return ret; diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c index e2bae1424502..c32a8ca67f82 100644 --- a/drivers/gpu/drm/nouveau/nouveau_abi16.c +++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c @@ -558,13 +558,13 @@ nouveau_abi16_ioctl_notifierobj_alloc(ABI16_IOCTL_ARGS) if (drm->agp.bridge) { args.target = NV_DMA_V0_TARGET_AGP; args.access = NV_DMA_V0_ACCESS_RDWR; - args.start += drm->agp.base + chan->ntfy->bo.offset; - args.limit += drm->agp.base + chan->ntfy->bo.offset; + args.start += drm->agp.base + chan->ntfy->offset; + args.limit += drm->agp.base + chan->ntfy->offset; } else { args.target = NV_DMA_V0_TARGET_VM; args.access = NV_DMA_V0_ACCESS_RDWR; - args.start += chan->ntfy->bo.offset; - args.limit += chan->ntfy->bo.offset; + args.start += chan->ntfy->offset; + args.limit += chan->ntfy->offset; }
client->route = NVDRM_OBJECT_ABI16; diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 2b4b21b02e40..b7a9b9e85355 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -1317,6 +1317,14 @@ nouveau_bo_move_ntfy(struct ttm_buffer_object *bo, bool evict, nouveau_vma_unmap(vma); } } + + if(new_reg) { + if (new_reg->mm_node) + nvbo->offset = (new_reg->start << PAGE_SHIFT); + else + nvbo->offset = 0; + } + }
static int diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.h b/drivers/gpu/drm/nouveau/nouveau_bo.h index 38f9d8350963..e944b4aa5547 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.h +++ b/drivers/gpu/drm/nouveau/nouveau_bo.h @@ -24,6 +24,9 @@ struct nouveau_bo { int pbbo_index; bool validate_mapped;
+ /* GPU address space is independent of CPU word size */ + uint64_t offset; + struct list_head vma_list;
unsigned contig:1; diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.c b/drivers/gpu/drm/nouveau/nouveau_chan.c index d9381a053169..3d71dfcb2fde 100644 --- a/drivers/gpu/drm/nouveau/nouveau_chan.c +++ b/drivers/gpu/drm/nouveau/nouveau_chan.c @@ -162,7 +162,7 @@ nouveau_channel_prep(struct nouveau_drm *drm, struct nvif_device *device, * pushbuf lives in, this is because the GEM code requires that * we be able to call out to other (indirect) push buffers */ - chan->push.addr = chan->push.buffer->bo.offset; + chan->push.addr = chan->push.buffer->offset;
if (device->info.family >= NV_DEVICE_INFO_V0_TESLA) { ret = nouveau_vma_new(chan->push.buffer, chan->vmm, diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 0ad5d87b5a8e..475ed53b99f1 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -89,7 +89,7 @@ static unsigned long nouveau_dmem_page_addr(struct page *page) struct nouveau_dmem_chunk *chunk = page->zone_device_data; unsigned long idx = page_to_pfn(page) - chunk->pfn_first;
- return (idx << PAGE_SHIFT) + chunk->bo->bo.offset; + return (idx << PAGE_SHIFT) + chunk->bo->offset; }
static void nouveau_dmem_page_free(struct page *page) diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c index 0c5cdda3c336..508b118c0953 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c +++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c @@ -393,7 +393,7 @@ nouveau_fbcon_create(struct drm_fb_helper *helper,
/* To allow resizeing without swapping buffers */ NV_INFO(drm, "allocated %dx%d fb: 0x%llx, bo %p\n", - fb->base.width, fb->base.height, fb->nvbo->bo.offset, nvbo); + fb->base.width, fb->base.height, fb->nvbo->offset, nvbo);
vga_switcheroo_client_fb_set(dev->pdev, info); return 0; diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index f5ece1f94973..cadff37eade8 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -232,7 +232,7 @@ nouveau_gem_info(struct drm_file *file_priv, struct drm_gem_object *gem, rep->domain = NOUVEAU_GEM_DOMAIN_GART; else rep->domain = NOUVEAU_GEM_DOMAIN_VRAM; - rep->offset = nvbo->bo.offset; + rep->offset = nvbo->offset; if (vmm->vmm.object.oclass >= NVIF_CLASS_VMM_NV50) { vma = nouveau_vma_find(nvbo, vmm); if (!vma) @@ -516,7 +516,7 @@ validate_list(struct nouveau_channel *chan, struct nouveau_cli *cli, }
if (drm->client.device.info.family < NV_DEVICE_INFO_V0_TESLA) { - if (nvbo->bo.offset == b->presumed.offset && + if (nvbo->offset == b->presumed.offset && ((nvbo->bo.mem.mem_type == TTM_PL_VRAM && b->presumed.domain & NOUVEAU_GEM_DOMAIN_VRAM) || (nvbo->bo.mem.mem_type == TTM_PL_TT && @@ -527,7 +527,7 @@ validate_list(struct nouveau_channel *chan, struct nouveau_cli *cli, b->presumed.domain = NOUVEAU_GEM_DOMAIN_GART; else b->presumed.domain = NOUVEAU_GEM_DOMAIN_VRAM; - b->presumed.offset = nvbo->bo.offset; + b->presumed.offset = nvbo->offset; b->presumed.valid = 0; relocs++; } @@ -805,7 +805,7 @@ nouveau_gem_ioctl_pushbuf(struct drm_device *dev, void *data, struct nouveau_bo *nvbo = (void *)(unsigned long) bo[push[i].bo_index].user_priv;
- OUT_RING(chan, (nvbo->bo.offset + push[i].offset) | 2); + OUT_RING(chan, (nvbo->offset + push[i].offset) | 2); OUT_RING(chan, 0); } } else { @@ -840,7 +840,7 @@ nouveau_gem_ioctl_pushbuf(struct drm_device *dev, void *data, }
OUT_RING(chan, 0x20000000 | - (nvbo->bo.offset + push[i].offset)); + (nvbo->offset + push[i].offset)); OUT_RING(chan, 0); for (j = 0; j < NOUVEAU_DMA_SKIPS; j++) OUT_RING(chan, 0);
Am 05.03.20 um 14:29 schrieb Nirmoy Das:
Store ttm bo->offset in struct nouveau_bo instead.
Signed-off-by: Nirmoy Das nirmoy.das@amd.com
Looks like this is the only patch without an rb or at least acked-by. Can anybody comment or at least throw a quick tested-by on it?
With that done I would say I would pick this series up for inclusion into drm-misc-next.
Regards, Christian.
drivers/gpu/drm/nouveau/dispnv04/crtc.c | 6 +++--- drivers/gpu/drm/nouveau/dispnv04/disp.c | 2 +- drivers/gpu/drm/nouveau/dispnv04/overlay.c | 6 +++--- drivers/gpu/drm/nouveau/dispnv50/base507c.c | 2 +- drivers/gpu/drm/nouveau/dispnv50/core507d.c | 2 +- drivers/gpu/drm/nouveau/dispnv50/ovly507e.c | 2 +- drivers/gpu/drm/nouveau/dispnv50/wndw.c | 2 +- drivers/gpu/drm/nouveau/dispnv50/wndwc37e.c | 2 +- drivers/gpu/drm/nouveau/nouveau_abi16.c | 8 ++++---- drivers/gpu/drm/nouveau/nouveau_bo.c | 8 ++++++++ drivers/gpu/drm/nouveau/nouveau_bo.h | 3 +++ drivers/gpu/drm/nouveau/nouveau_chan.c | 2 +- drivers/gpu/drm/nouveau/nouveau_dmem.c | 2 +- drivers/gpu/drm/nouveau/nouveau_fbcon.c | 2 +- drivers/gpu/drm/nouveau/nouveau_gem.c | 10 +++++----- 15 files changed, 35 insertions(+), 24 deletions(-)
diff --git a/drivers/gpu/drm/nouveau/dispnv04/crtc.c b/drivers/gpu/drm/nouveau/dispnv04/crtc.c index 1f08de4241e0..d06a93f2b38a 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/crtc.c +++ b/drivers/gpu/drm/nouveau/dispnv04/crtc.c @@ -845,7 +845,7 @@ nv04_crtc_do_mode_set_base(struct drm_crtc *crtc, fb = nouveau_framebuffer(crtc->primary->fb); }
- nv_crtc->fb.offset = fb->nvbo->bo.offset;
nv_crtc->fb.offset = fb->nvbo->offset;
if (nv_crtc->lut.depth != drm_fb->format->depth) { nv_crtc->lut.depth = drm_fb->format->depth;
@@ -1013,7 +1013,7 @@ nv04_crtc_cursor_set(struct drm_crtc *crtc, struct drm_file *file_priv, nv04_cursor_upload(dev, cursor, nv_crtc->cursor.nvbo);
nouveau_bo_unmap(cursor);
- nv_crtc->cursor.offset = nv_crtc->cursor.nvbo->bo.offset;
- nv_crtc->cursor.offset = nv_crtc->cursor.nvbo->offset; nv_crtc->cursor.set_offset(nv_crtc, nv_crtc->cursor.offset); nv_crtc->cursor.show(nv_crtc, true); out:
@@ -1191,7 +1191,7 @@ nv04_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb, /* Initialize a page flip struct */ *s = (struct nv04_page_flip_state) { { }, event, crtc, fb->format->cpp[0] * 8, fb->pitches[0],
new_bo->bo.offset };
new_bo->offset };/* Keep vblanks on during flip, for the target crtc of this flip */ drm_crtc_vblank_get(crtc);
diff --git a/drivers/gpu/drm/nouveau/dispnv04/disp.c b/drivers/gpu/drm/nouveau/dispnv04/disp.c index 44ee82d0c9b6..89a4ddfcc55f 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv04/disp.c @@ -151,7 +151,7 @@ nv04_display_init(struct drm_device *dev, bool resume, bool runtime) continue;
if (nv_crtc->cursor.set_offset)
nv_crtc->cursor.set_offset(nv_crtc, nv_crtc->cursor.nvbo->bo.offset);
nv_crtc->cursor.set_offset(nv_crtc, nv_crtc->cursor.nvbo->offset);diff --git a/drivers/gpu/drm/nouveau/dispnv04/overlay.c b/drivers/gpu/drm/nouveau/dispnv04/overlay.c index a3a0a73ae8ab..9529bd9053e7 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/overlay.c +++ b/drivers/gpu/drm/nouveau/dispnv04/overlay.c @@ -150,7 +150,7 @@ nv10_update_plane(struct drm_plane *plane, struct drm_crtc *crtc, nvif_mask(dev, NV_PCRTC_ENGINE_CTRL + soff2, NV_CRTC_FSEL_OVERLAY, 0);
nvif_wr32(dev, NV_PVIDEO_BASE(flip), 0);
- nvif_wr32(dev, NV_PVIDEO_OFFSET_BUFF(flip), nv_fb->nvbo->bo.offset);
- nvif_wr32(dev, NV_PVIDEO_OFFSET_BUFF(flip), nv_fb->nvbo->offset); nvif_wr32(dev, NV_PVIDEO_SIZE_IN(flip), src_h << 16 | src_w); nvif_wr32(dev, NV_PVIDEO_POINT_IN(flip), src_y << 16 | src_x); nvif_wr32(dev, NV_PVIDEO_DS_DX(flip), (src_w << 20) / crtc_w);
@@ -172,7 +172,7 @@ nv10_update_plane(struct drm_plane *plane, struct drm_crtc *crtc, if (format & NV_PVIDEO_FORMAT_PLANAR) { nvif_wr32(dev, NV_PVIDEO_UVPLANE_BASE(flip), 0); nvif_wr32(dev, NV_PVIDEO_UVPLANE_OFFSET_BUFF(flip),
nv_fb->nvbo->bo.offset + fb->offsets[1]);
nv_fb->nvbo->offset + fb->offsets[1]);@@ -396,7 +396,7 @@ nv04_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
for (i = 0; i < 2; i++) { nvif_wr32(dev, NV_PVIDEO_BUFF0_START_ADDRESS + 4 * i,
nv_fb->nvbo->bo.offset);
nv_fb->nvbo->offset);diff --git a/drivers/gpu/drm/nouveau/dispnv50/base507c.c b/drivers/gpu/drm/nouveau/dispnv50/base507c.c index 00a85f1e1a4a..67829f04b2c7 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/base507c.c +++ b/drivers/gpu/drm/nouveau/dispnv50/base507c.c @@ -274,7 +274,7 @@ base507c_new_(const struct nv50_wndw_func *func, const u32 *format,
ret = nv50_dmac_create(&drm->client.device, &disp->disp->object, &oclass, head, &args, sizeof(args),
disp->sync->bo.offset, &wndw->wndw);
disp->sync->offset, &wndw->wndw);diff --git a/drivers/gpu/drm/nouveau/dispnv50/core507d.c b/drivers/gpu/drm/nouveau/dispnv50/core507d.c index e7fcfa6e6467..793dcb2ea196 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/core507d.c +++ b/drivers/gpu/drm/nouveau/dispnv50/core507d.c @@ -99,7 +99,7 @@ core507d_new_(const struct nv50_core_func *func, struct nouveau_drm *drm,
ret = nv50_dmac_create(&drm->client.device, &disp->disp->object, &oclass, 0, &args, sizeof(args),
disp->sync->bo.offset, &core->chan);
disp->sync->offset, &core->chan);diff --git a/drivers/gpu/drm/nouveau/dispnv50/ovly507e.c b/drivers/gpu/drm/nouveau/dispnv50/ovly507e.c index 8ccd96113bad..4cce1078140a 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/ovly507e.c +++ b/drivers/gpu/drm/nouveau/dispnv50/ovly507e.c @@ -186,7 +186,7 @@ ovly507e_new_(const struct nv50_wndw_func *func, const u32 *format,
ret = nv50_dmac_create(&drm->client.device, &disp->disp->object, &oclass, 0, &args, sizeof(args),
disp->sync->bo.offset, &wndw->wndw);
disp->sync->offset, &wndw->wndw);diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c index 890315291b01..e90ffa4a5230 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c +++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c @@ -509,7 +509,7 @@ nv50_wndw_prepare_fb(struct drm_plane *plane, struct drm_plane_state *state) }
asyw->state.fence = dma_resv_get_excl_rcu(fb->nvbo->bo.base.resv);
- asyw->image.offset[0] = fb->nvbo->bo.offset;
asyw->image.offset[0] = fb->nvbo->offset;
if (wndw->func->prepare) { asyh = nv50_head_atom_get(asyw->state.state, asyw->state.crtc);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndwc37e.c b/drivers/gpu/drm/nouveau/dispnv50/wndwc37e.c index b92dc3461bbd..bb84e4d54a33 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndwc37e.c +++ b/drivers/gpu/drm/nouveau/dispnv50/wndwc37e.c @@ -298,7 +298,7 @@ wndwc37e_new_(const struct nv50_wndw_func *func, struct nouveau_drm *drm,
ret = nv50_dmac_create(&drm->client.device, &disp->disp->object, &oclass, 0, &args, sizeof(args),
disp->sync->bo.offset, &wndw->wndw);
disp->sync->offset, &wndw->wndw);diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c index e2bae1424502..c32a8ca67f82 100644 --- a/drivers/gpu/drm/nouveau/nouveau_abi16.c +++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c @@ -558,13 +558,13 @@ nouveau_abi16_ioctl_notifierobj_alloc(ABI16_IOCTL_ARGS) if (drm->agp.bridge) { args.target = NV_DMA_V0_TARGET_AGP; args.access = NV_DMA_V0_ACCESS_RDWR;
args.start += drm->agp.base + chan->ntfy->bo.offset;args.limit += drm->agp.base + chan->ntfy->bo.offset;
args.start += drm->agp.base + chan->ntfy->offset;args.limit += drm->agp.base + chan->ntfy->offset;
args.start += chan->ntfy->bo.offset;args.limit += chan->ntfy->bo.offset;
args.start += chan->ntfy->offset;args.limit += chan->ntfy->offset;}
client->route = NVDRM_OBJECT_ABI16;
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 2b4b21b02e40..b7a9b9e85355 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -1317,6 +1317,14 @@ nouveau_bo_move_ntfy(struct ttm_buffer_object *bo, bool evict, nouveau_vma_unmap(vma); } }
if(new_reg) {
if (new_reg->mm_node)nvbo->offset = (new_reg->start << PAGE_SHIFT);elsenvbo->offset = 0;}
}
static int
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.h b/drivers/gpu/drm/nouveau/nouveau_bo.h index 38f9d8350963..e944b4aa5547 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.h +++ b/drivers/gpu/drm/nouveau/nouveau_bo.h @@ -24,6 +24,9 @@ struct nouveau_bo { int pbbo_index; bool validate_mapped;
/* GPU address space is independent of CPU word size */
uint64_t offset;
struct list_head vma_list;
unsigned contig:1;
diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.c b/drivers/gpu/drm/nouveau/nouveau_chan.c index d9381a053169..3d71dfcb2fde 100644 --- a/drivers/gpu/drm/nouveau/nouveau_chan.c +++ b/drivers/gpu/drm/nouveau/nouveau_chan.c @@ -162,7 +162,7 @@ nouveau_channel_prep(struct nouveau_drm *drm, struct nvif_device *device, * pushbuf lives in, this is because the GEM code requires that * we be able to call out to other (indirect) push buffers */
- chan->push.addr = chan->push.buffer->bo.offset;
chan->push.addr = chan->push.buffer->offset;
if (device->info.family >= NV_DEVICE_INFO_V0_TESLA) { ret = nouveau_vma_new(chan->push.buffer, chan->vmm,
diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 0ad5d87b5a8e..475ed53b99f1 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -89,7 +89,7 @@ static unsigned long nouveau_dmem_page_addr(struct page *page) struct nouveau_dmem_chunk *chunk = page->zone_device_data; unsigned long idx = page_to_pfn(page) - chunk->pfn_first;
- return (idx << PAGE_SHIFT) + chunk->bo->bo.offset;
return (idx << PAGE_SHIFT) + chunk->bo->offset; }
static void nouveau_dmem_page_free(struct page *page)
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c index 0c5cdda3c336..508b118c0953 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c +++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c @@ -393,7 +393,7 @@ nouveau_fbcon_create(struct drm_fb_helper *helper,
/* To allow resizeing without swapping buffers */ NV_INFO(drm, "allocated %dx%d fb: 0x%llx, bo %p\n",
fb->base.width, fb->base.height, fb->nvbo->bo.offset, nvbo);
fb->base.width, fb->base.height, fb->nvbo->offset, nvbo);vga_switcheroo_client_fb_set(dev->pdev, info); return 0;
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index f5ece1f94973..cadff37eade8 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -232,7 +232,7 @@ nouveau_gem_info(struct drm_file *file_priv, struct drm_gem_object *gem, rep->domain = NOUVEAU_GEM_DOMAIN_GART; else rep->domain = NOUVEAU_GEM_DOMAIN_VRAM;
- rep->offset = nvbo->bo.offset;
- rep->offset = nvbo->offset; if (vmm->vmm.object.oclass >= NVIF_CLASS_VMM_NV50) { vma = nouveau_vma_find(nvbo, vmm); if (!vma)
@@ -516,7 +516,7 @@ validate_list(struct nouveau_channel *chan, struct nouveau_cli *cli, }
if (drm->client.device.info.family < NV_DEVICE_INFO_V0_TESLA) {
if (nvbo->bo.offset == b->presumed.offset &&
if (nvbo->offset == b->presumed.offset && ((nvbo->bo.mem.mem_type == TTM_PL_VRAM && b->presumed.domain & NOUVEAU_GEM_DOMAIN_VRAM) || (nvbo->bo.mem.mem_type == TTM_PL_TT &&@@ -527,7 +527,7 @@ validate_list(struct nouveau_channel *chan, struct nouveau_cli *cli, b->presumed.domain = NOUVEAU_GEM_DOMAIN_GART; else b->presumed.domain = NOUVEAU_GEM_DOMAIN_VRAM;
b->presumed.offset = nvbo->bo.offset;
b->presumed.offset = nvbo->offset; b->presumed.valid = 0; relocs++;@@ -805,7 +805,7 @@ nouveau_gem_ioctl_pushbuf(struct drm_device *dev, void *data, struct nouveau_bo *nvbo = (void *)(unsigned long) bo[push[i].bo_index].user_priv;
OUT_RING(chan, (nvbo->bo.offset + push[i].offset) | 2);
OUT_RING(chan, (nvbo->offset + push[i].offset) | 2); OUT_RING(chan, 0);@@ -840,7 +840,7 @@ nouveau_gem_ioctl_pushbuf(struct drm_device *dev, void *data, }
OUT_RING(chan, 0x20000000 |
(nvbo->bo.offset + push[i].offset));
(nvbo->offset + push[i].offset)); OUT_RING(chan, 0); for (j = 0; j < NOUVEAU_DMA_SKIPS; j++) OUT_RING(chan, 0);
On 2020-03-05 08:29, Nirmoy Das wrote:
Store ttm bo->offset in struct nouveau_bo instead.
Signed-off-by: Nirmoy Das nirmoy.das@amd.com
drivers/gpu/drm/nouveau/dispnv04/crtc.c | 6 +++--- drivers/gpu/drm/nouveau/dispnv04/disp.c | 2 +- drivers/gpu/drm/nouveau/dispnv04/overlay.c | 6 +++--- drivers/gpu/drm/nouveau/dispnv50/base507c.c | 2 +- drivers/gpu/drm/nouveau/dispnv50/core507d.c | 2 +- drivers/gpu/drm/nouveau/dispnv50/ovly507e.c | 2 +- drivers/gpu/drm/nouveau/dispnv50/wndw.c | 2 +- drivers/gpu/drm/nouveau/dispnv50/wndwc37e.c | 2 +- drivers/gpu/drm/nouveau/nouveau_abi16.c | 8 ++++---- drivers/gpu/drm/nouveau/nouveau_bo.c | 8 ++++++++ drivers/gpu/drm/nouveau/nouveau_bo.h | 3 +++ drivers/gpu/drm/nouveau/nouveau_chan.c | 2 +- drivers/gpu/drm/nouveau/nouveau_dmem.c | 2 +- drivers/gpu/drm/nouveau/nouveau_fbcon.c | 2 +- drivers/gpu/drm/nouveau/nouveau_gem.c | 10 +++++----- 15 files changed, 35 insertions(+), 24 deletions(-)
diff --git a/drivers/gpu/drm/nouveau/dispnv04/crtc.c b/drivers/gpu/drm/nouveau/dispnv04/crtc.c index 1f08de4241e0..d06a93f2b38a 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/crtc.c +++ b/drivers/gpu/drm/nouveau/dispnv04/crtc.c @@ -845,7 +845,7 @@ nv04_crtc_do_mode_set_base(struct drm_crtc *crtc, fb = nouveau_framebuffer(crtc->primary->fb); }
- nv_crtc->fb.offset = fb->nvbo->bo.offset;
nv_crtc->fb.offset = fb->nvbo->offset;
if (nv_crtc->lut.depth != drm_fb->format->depth) { nv_crtc->lut.depth = drm_fb->format->depth;
@@ -1013,7 +1013,7 @@ nv04_crtc_cursor_set(struct drm_crtc *crtc, struct drm_file *file_priv, nv04_cursor_upload(dev, cursor, nv_crtc->cursor.nvbo);
nouveau_bo_unmap(cursor);
- nv_crtc->cursor.offset = nv_crtc->cursor.nvbo->bo.offset;
- nv_crtc->cursor.offset = nv_crtc->cursor.nvbo->offset; nv_crtc->cursor.set_offset(nv_crtc, nv_crtc->cursor.offset); nv_crtc->cursor.show(nv_crtc, true);
out: @@ -1191,7 +1191,7 @@ nv04_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb, /* Initialize a page flip struct */ *s = (struct nv04_page_flip_state) { { }, event, crtc, fb->format->cpp[0] * 8, fb->pitches[0],
new_bo->bo.offset };
new_bo->offset };/* Keep vblanks on during flip, for the target crtc of this flip */ drm_crtc_vblank_get(crtc);
diff --git a/drivers/gpu/drm/nouveau/dispnv04/disp.c b/drivers/gpu/drm/nouveau/dispnv04/disp.c index 44ee82d0c9b6..89a4ddfcc55f 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv04/disp.c @@ -151,7 +151,7 @@ nv04_display_init(struct drm_device *dev, bool resume, bool runtime) continue;
if (nv_crtc->cursor.set_offset)
nv_crtc->cursor.set_offset(nv_crtc, nv_crtc->cursor.nvbo->bo.offset);
nv_crtc->cursor.set_offset(nv_crtc, nv_crtc->cursor.nvbo->offset);diff --git a/drivers/gpu/drm/nouveau/dispnv04/overlay.c b/drivers/gpu/drm/nouveau/dispnv04/overlay.c index a3a0a73ae8ab..9529bd9053e7 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/overlay.c +++ b/drivers/gpu/drm/nouveau/dispnv04/overlay.c @@ -150,7 +150,7 @@ nv10_update_plane(struct drm_plane *plane, struct drm_crtc *crtc, nvif_mask(dev, NV_PCRTC_ENGINE_CTRL + soff2, NV_CRTC_FSEL_OVERLAY, 0);
nvif_wr32(dev, NV_PVIDEO_BASE(flip), 0);
- nvif_wr32(dev, NV_PVIDEO_OFFSET_BUFF(flip), nv_fb->nvbo->bo.offset);
- nvif_wr32(dev, NV_PVIDEO_OFFSET_BUFF(flip), nv_fb->nvbo->offset); nvif_wr32(dev, NV_PVIDEO_SIZE_IN(flip), src_h << 16 | src_w); nvif_wr32(dev, NV_PVIDEO_POINT_IN(flip), src_y << 16 | src_x); nvif_wr32(dev, NV_PVIDEO_DS_DX(flip), (src_w << 20) / crtc_w);
@@ -172,7 +172,7 @@ nv10_update_plane(struct drm_plane *plane, struct drm_crtc *crtc, if (format & NV_PVIDEO_FORMAT_PLANAR) { nvif_wr32(dev, NV_PVIDEO_UVPLANE_BASE(flip), 0); nvif_wr32(dev, NV_PVIDEO_UVPLANE_OFFSET_BUFF(flip),
nv_fb->nvbo->bo.offset + fb->offsets[1]);
nv_fb->nvbo->offset + fb->offsets[1]);@@ -396,7 +396,7 @@ nv04_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
for (i = 0; i < 2; i++) { nvif_wr32(dev, NV_PVIDEO_BUFF0_START_ADDRESS + 4 * i,
nv_fb->nvbo->bo.offset);
nv_fb->nvbo->offset);diff --git a/drivers/gpu/drm/nouveau/dispnv50/base507c.c b/drivers/gpu/drm/nouveau/dispnv50/base507c.c index 00a85f1e1a4a..67829f04b2c7 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/base507c.c +++ b/drivers/gpu/drm/nouveau/dispnv50/base507c.c @@ -274,7 +274,7 @@ base507c_new_(const struct nv50_wndw_func *func, const u32 *format,
ret = nv50_dmac_create(&drm->client.device, &disp->disp->object, &oclass, head, &args, sizeof(args),
disp->sync->bo.offset, &wndw->wndw);
disp->sync->offset, &wndw->wndw);diff --git a/drivers/gpu/drm/nouveau/dispnv50/core507d.c b/drivers/gpu/drm/nouveau/dispnv50/core507d.c index e7fcfa6e6467..793dcb2ea196 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/core507d.c +++ b/drivers/gpu/drm/nouveau/dispnv50/core507d.c @@ -99,7 +99,7 @@ core507d_new_(const struct nv50_core_func *func, struct nouveau_drm *drm,
ret = nv50_dmac_create(&drm->client.device, &disp->disp->object, &oclass, 0, &args, sizeof(args),
disp->sync->bo.offset, &core->chan);
disp->sync->offset, &core->chan);diff --git a/drivers/gpu/drm/nouveau/dispnv50/ovly507e.c b/drivers/gpu/drm/nouveau/dispnv50/ovly507e.c index 8ccd96113bad..4cce1078140a 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/ovly507e.c +++ b/drivers/gpu/drm/nouveau/dispnv50/ovly507e.c @@ -186,7 +186,7 @@ ovly507e_new_(const struct nv50_wndw_func *func, const u32 *format,
ret = nv50_dmac_create(&drm->client.device, &disp->disp->object, &oclass, 0, &args, sizeof(args),
disp->sync->bo.offset, &wndw->wndw);
disp->sync->offset, &wndw->wndw);diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c index 890315291b01..e90ffa4a5230 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c +++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c @@ -509,7 +509,7 @@ nv50_wndw_prepare_fb(struct drm_plane *plane, struct drm_plane_state *state) }
asyw->state.fence = dma_resv_get_excl_rcu(fb->nvbo->bo.base.resv);
- asyw->image.offset[0] = fb->nvbo->bo.offset;
asyw->image.offset[0] = fb->nvbo->offset;
if (wndw->func->prepare) { asyh = nv50_head_atom_get(asyw->state.state, asyw->state.crtc);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndwc37e.c b/drivers/gpu/drm/nouveau/dispnv50/wndwc37e.c index b92dc3461bbd..bb84e4d54a33 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndwc37e.c +++ b/drivers/gpu/drm/nouveau/dispnv50/wndwc37e.c @@ -298,7 +298,7 @@ wndwc37e_new_(const struct nv50_wndw_func *func, struct nouveau_drm *drm,
ret = nv50_dmac_create(&drm->client.device, &disp->disp->object, &oclass, 0, &args, sizeof(args),
disp->sync->bo.offset, &wndw->wndw);
disp->sync->offset, &wndw->wndw);diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c index e2bae1424502..c32a8ca67f82 100644 --- a/drivers/gpu/drm/nouveau/nouveau_abi16.c +++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c @@ -558,13 +558,13 @@ nouveau_abi16_ioctl_notifierobj_alloc(ABI16_IOCTL_ARGS) if (drm->agp.bridge) { args.target = NV_DMA_V0_TARGET_AGP; args.access = NV_DMA_V0_ACCESS_RDWR;
args.start += drm->agp.base + chan->ntfy->bo.offset;args.limit += drm->agp.base + chan->ntfy->bo.offset;
args.start += drm->agp.base + chan->ntfy->offset;args.limit += drm->agp.base + chan->ntfy->offset;
args.start += chan->ntfy->bo.offset;args.limit += chan->ntfy->bo.offset;
args.start += chan->ntfy->offset;args.limit += chan->ntfy->offset;}
client->route = NVDRM_OBJECT_ABI16;
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 2b4b21b02e40..b7a9b9e85355 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -1317,6 +1317,14 @@ nouveau_bo_move_ntfy(struct ttm_buffer_object *bo, bool evict, nouveau_vma_unmap(vma); } }
- if(new_reg) {
if (new_reg->mm_node)nvbo->offset = (new_reg->start << PAGE_SHIFT);elsenvbo->offset = 0;- }
The outer "if" has no space according to LKCS, but the inner one does. Add a space after the "if" and before the "(" in the outer "if" according to LKCS.
Regards, Luben
}
static int diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.h b/drivers/gpu/drm/nouveau/nouveau_bo.h index 38f9d8350963..e944b4aa5547 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.h +++ b/drivers/gpu/drm/nouveau/nouveau_bo.h @@ -24,6 +24,9 @@ struct nouveau_bo { int pbbo_index; bool validate_mapped;
/* GPU address space is independent of CPU word size */
uint64_t offset;
struct list_head vma_list;
unsigned contig:1;
diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.c b/drivers/gpu/drm/nouveau/nouveau_chan.c index d9381a053169..3d71dfcb2fde 100644 --- a/drivers/gpu/drm/nouveau/nouveau_chan.c +++ b/drivers/gpu/drm/nouveau/nouveau_chan.c @@ -162,7 +162,7 @@ nouveau_channel_prep(struct nouveau_drm *drm, struct nvif_device *device, * pushbuf lives in, this is because the GEM code requires that * we be able to call out to other (indirect) push buffers */
- chan->push.addr = chan->push.buffer->bo.offset;
chan->push.addr = chan->push.buffer->offset;
if (device->info.family >= NV_DEVICE_INFO_V0_TESLA) { ret = nouveau_vma_new(chan->push.buffer, chan->vmm,
diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 0ad5d87b5a8e..475ed53b99f1 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -89,7 +89,7 @@ static unsigned long nouveau_dmem_page_addr(struct page *page) struct nouveau_dmem_chunk *chunk = page->zone_device_data; unsigned long idx = page_to_pfn(page) - chunk->pfn_first;
- return (idx << PAGE_SHIFT) + chunk->bo->bo.offset;
- return (idx << PAGE_SHIFT) + chunk->bo->offset;
}
static void nouveau_dmem_page_free(struct page *page) diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c index 0c5cdda3c336..508b118c0953 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c +++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c @@ -393,7 +393,7 @@ nouveau_fbcon_create(struct drm_fb_helper *helper,
/* To allow resizeing without swapping buffers */ NV_INFO(drm, "allocated %dx%d fb: 0x%llx, bo %p\n",
fb->base.width, fb->base.height, fb->nvbo->bo.offset, nvbo);
fb->base.width, fb->base.height, fb->nvbo->offset, nvbo);vga_switcheroo_client_fb_set(dev->pdev, info); return 0;
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index f5ece1f94973..cadff37eade8 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -232,7 +232,7 @@ nouveau_gem_info(struct drm_file *file_priv, struct drm_gem_object *gem, rep->domain = NOUVEAU_GEM_DOMAIN_GART; else rep->domain = NOUVEAU_GEM_DOMAIN_VRAM;
- rep->offset = nvbo->bo.offset;
- rep->offset = nvbo->offset; if (vmm->vmm.object.oclass >= NVIF_CLASS_VMM_NV50) { vma = nouveau_vma_find(nvbo, vmm); if (!vma)
@@ -516,7 +516,7 @@ validate_list(struct nouveau_channel *chan, struct nouveau_cli *cli, }
if (drm->client.device.info.family < NV_DEVICE_INFO_V0_TESLA) {
if (nvbo->bo.offset == b->presumed.offset &&
if (nvbo->offset == b->presumed.offset && ((nvbo->bo.mem.mem_type == TTM_PL_VRAM && b->presumed.domain & NOUVEAU_GEM_DOMAIN_VRAM) || (nvbo->bo.mem.mem_type == TTM_PL_TT &&@@ -527,7 +527,7 @@ validate_list(struct nouveau_channel *chan, struct nouveau_cli *cli, b->presumed.domain = NOUVEAU_GEM_DOMAIN_GART; else b->presumed.domain = NOUVEAU_GEM_DOMAIN_VRAM;
b->presumed.offset = nvbo->bo.offset;
b->presumed.offset = nvbo->offset; b->presumed.valid = 0; relocs++;@@ -805,7 +805,7 @@ nouveau_gem_ioctl_pushbuf(struct drm_device *dev, void *data, struct nouveau_bo *nvbo = (void *)(unsigned long) bo[push[i].bo_index].user_priv;
OUT_RING(chan, (nvbo->bo.offset + push[i].offset) | 2);
OUT_RING(chan, (nvbo->offset + push[i].offset) | 2); OUT_RING(chan, 0);@@ -840,7 +840,7 @@ nouveau_gem_ioctl_pushbuf(struct drm_device *dev, void *data, }
OUT_RING(chan, 0x20000000 |
(nvbo->bo.offset + push[i].offset));
(nvbo->offset + push[i].offset)); OUT_RING(chan, 0); for (j = 0; j < NOUVEAU_DMA_SKIPS; j++) OUT_RING(chan, 0);
This patch removes slot->gpu_offset which is not required as VRAM and PRIV slot are in separate PCI bar.
This patch also removes unused qxl_bo_gpu_offset()
Signed-off-by: Nirmoy Das nirmoy.das@amd.com Acked-by: Christian König christian.koenig@amd.com Acked-by: Gerd Hoffmann kraxel@redhat.com --- drivers/gpu/drm/qxl/qxl_drv.h | 6 ++---- drivers/gpu/drm/qxl/qxl_kms.c | 5 ++--- drivers/gpu/drm/qxl/qxl_object.h | 5 ----- drivers/gpu/drm/qxl/qxl_ttm.c | 9 --------- 4 files changed, 4 insertions(+), 21 deletions(-)
diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h index 27e45a2d6b52..df581f0e6699 100644 --- a/drivers/gpu/drm/qxl/qxl_drv.h +++ b/drivers/gpu/drm/qxl/qxl_drv.h @@ -134,7 +134,6 @@ struct qxl_memslot { uint64_t start_phys_addr; uint64_t size; uint64_t high_bits; - uint64_t gpu_offset; };
enum { @@ -311,10 +310,9 @@ qxl_bo_physical_address(struct qxl_device *qdev, struct qxl_bo *bo, (bo->tbo.mem.mem_type == TTM_PL_VRAM) ? &qdev->main_slot : &qdev->surfaces_slot;
- WARN_ON_ONCE((bo->tbo.offset & slot->gpu_offset) != slot->gpu_offset); + /* TODO - need to hold one of the locks to read bo->tbo.mem.start */
- /* TODO - need to hold one of the locks to read tbo.offset */ - return slot->high_bits | (bo->tbo.offset - slot->gpu_offset + offset); + return slot->high_bits | ((bo->tbo.mem.start << PAGE_SHIFT) + offset); }
/* qxl_display.c */ diff --git a/drivers/gpu/drm/qxl/qxl_kms.c b/drivers/gpu/drm/qxl/qxl_kms.c index 70b20ee4741a..7a5bf544f34d 100644 --- a/drivers/gpu/drm/qxl/qxl_kms.c +++ b/drivers/gpu/drm/qxl/qxl_kms.c @@ -86,11 +86,10 @@ static void setup_slot(struct qxl_device *qdev, high_bits <<= (64 - (qdev->rom->slot_gen_bits + qdev->rom->slot_id_bits)); slot->high_bits = high_bits;
- DRM_INFO("slot %d (%s): base 0x%08lx, size 0x%08lx, gpu_offset 0x%lx\n", + DRM_INFO("slot %d (%s): base 0x%08lx, size 0x%08lx\n", slot->index, slot->name, (unsigned long)slot->start_phys_addr, - (unsigned long)slot->size, - (unsigned long)slot->gpu_offset); + (unsigned long)slot->size); }
void qxl_reinit_memslots(struct qxl_device *qdev) diff --git a/drivers/gpu/drm/qxl/qxl_object.h b/drivers/gpu/drm/qxl/qxl_object.h index 8ae54ba7857c..21fa81048f4f 100644 --- a/drivers/gpu/drm/qxl/qxl_object.h +++ b/drivers/gpu/drm/qxl/qxl_object.h @@ -48,11 +48,6 @@ static inline void qxl_bo_unreserve(struct qxl_bo *bo) ttm_bo_unreserve(&bo->tbo); }
-static inline u64 qxl_bo_gpu_offset(struct qxl_bo *bo) -{ - return bo->tbo.offset; -} - static inline unsigned long qxl_bo_size(struct qxl_bo *bo) { return bo->tbo.num_pages << PAGE_SHIFT; diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c index 62a5e424971b..635d000e7934 100644 --- a/drivers/gpu/drm/qxl/qxl_ttm.c +++ b/drivers/gpu/drm/qxl/qxl_ttm.c @@ -51,11 +51,6 @@ static struct qxl_device *qxl_get_qdev(struct ttm_bo_device *bdev) static int qxl_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, struct ttm_mem_type_manager *man) { - struct qxl_device *qdev = qxl_get_qdev(bdev); - unsigned int gpu_offset_shift = - 64 - (qdev->rom->slot_gen_bits + qdev->rom->slot_id_bits + 8); - struct qxl_memslot *slot; - switch (type) { case TTM_PL_SYSTEM: /* System memory */ @@ -66,11 +61,7 @@ static int qxl_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, case TTM_PL_VRAM: case TTM_PL_PRIV: /* "On-card" video ram */ - slot = (type == TTM_PL_VRAM) ? - &qdev->main_slot : &qdev->surfaces_slot; - slot->gpu_offset = (uint64_t)type << gpu_offset_shift; man->func = &ttm_bo_manager_func; - man->gpu_offset = slot->gpu_offset; man->flags = TTM_MEMTYPE_FLAG_FIXED | TTM_MEMTYPE_FLAG_MAPPABLE; man->available_caching = TTM_PL_MASK_CACHING; -- 2.25.0
Calculate GEM VRAM bo's offset within vram-helper without depending on bo->offset.
Signed-off-by: Nirmoy Das nirmoy.das@amd.com Reviewed-by: Daniel Vetter daniel.vetter@ffwll.ch --- drivers/gpu/drm/drm_gem_vram_helper.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c index 92a11bb42365..2749c2d25ac4 100644 --- a/drivers/gpu/drm/drm_gem_vram_helper.c +++ b/drivers/gpu/drm/drm_gem_vram_helper.c @@ -198,6 +198,13 @@ u64 drm_gem_vram_mmap_offset(struct drm_gem_vram_object *gbo) } EXPORT_SYMBOL(drm_gem_vram_mmap_offset);
+static s64 drm_gem_vram_pg_offset(struct drm_gem_vram_object *gbo) +{ + if (WARN_ON_ONCE(!gbo->bo.mem.mm_node)) + return 0; + return gbo->bo.mem.start; +} + /** * drm_gem_vram_offset() - \ Returns a GEM VRAM object's offset in video memory @@ -214,7 +221,7 @@ s64 drm_gem_vram_offset(struct drm_gem_vram_object *gbo) { if (WARN_ON_ONCE(!gbo->pin_count)) return (s64)-ENODEV; - return gbo->bo.offset; + return drm_gem_vram_pg_offset(gbo) << PAGE_SHIFT; } EXPORT_SYMBOL(drm_gem_vram_offset);
-- 2.25.0
On Thu, Mar 05, 2020 at 02:29:08PM +0100, Nirmoy Das wrote:
Calculate GEM VRAM bo's offset within vram-helper without depending on bo->offset.
Signed-off-by: Nirmoy Das nirmoy.das@amd.com Reviewed-by: Daniel Vetter daniel.vetter@ffwll.ch
drivers/gpu/drm/drm_gem_vram_helper.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c index 92a11bb42365..2749c2d25ac4 100644 --- a/drivers/gpu/drm/drm_gem_vram_helper.c +++ b/drivers/gpu/drm/drm_gem_vram_helper.c @@ -198,6 +198,13 @@ u64 drm_gem_vram_mmap_offset(struct drm_gem_vram_object *gbo) } EXPORT_SYMBOL(drm_gem_vram_mmap_offset);
+static s64 drm_gem_vram_pg_offset(struct drm_gem_vram_object *gbo) +{
- if (WARN_ON_ONCE(!gbo->bo.mem.mm_node))
return 0;
returns 0 on error.
- return gbo->bo.mem.start;
+}
/**
- drm_gem_vram_offset() - \
Returns a GEM VRAM object's offset in video memory @@ -214,7 +221,7 @@ s64 drm_gem_vram_offset(struct drm_gem_vram_object *gbo) { if (WARN_ON_ONCE(!gbo->pin_count)) return (s64)-ENODEV;
returns -errno on error.
- return gbo->bo.offset;
- return drm_gem_vram_pg_offset(gbo) << PAGE_SHIFT;
And given that one calls the other behavior on error should better be consistent ...
cheers, Gerd
Hi
Am 05.03.20 um 15:07 schrieb Gerd Hoffmann:
On Thu, Mar 05, 2020 at 02:29:08PM +0100, Nirmoy Das wrote:
Calculate GEM VRAM bo's offset within vram-helper without depending on bo->offset.
Signed-off-by: Nirmoy Das nirmoy.das@amd.com Reviewed-by: Daniel Vetter daniel.vetter@ffwll.ch
drivers/gpu/drm/drm_gem_vram_helper.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c index 92a11bb42365..2749c2d25ac4 100644 --- a/drivers/gpu/drm/drm_gem_vram_helper.c +++ b/drivers/gpu/drm/drm_gem_vram_helper.c @@ -198,6 +198,13 @@ u64 drm_gem_vram_mmap_offset(struct drm_gem_vram_object *gbo) } EXPORT_SYMBOL(drm_gem_vram_mmap_offset);
+static s64 drm_gem_vram_pg_offset(struct drm_gem_vram_object *gbo) +{
- if (WARN_ON_ONCE(!gbo->bo.mem.mm_node))
return 0;returns 0 on error.
- return gbo->bo.mem.start;
+}
/**
- drm_gem_vram_offset() - \
Returns a GEM VRAM object's offset in video memory @@ -214,7 +221,7 @@ s64 drm_gem_vram_offset(struct drm_gem_vram_object *gbo) { if (WARN_ON_ONCE(!gbo->pin_count)) return (s64)-ENODEV;
returns -errno on error.
- return gbo->bo.offset;
- return drm_gem_vram_pg_offset(gbo) << PAGE_SHIFT;
And given that one calls the other behavior on error should better be consistent ...
It is expected that the offset is valid if pin_count is positive. Anything else would be a massive ref-counting bug. And that's been the behavior of the old code as well.
But I agree that the current patch is inconsistent. I suggest changing the return type of drm_gem_vram_pg_offset() to u64.
Best regards Thomas
cheers, Gerd
dri-devel mailing list dri-devel@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/dri-devel
On 3/5/20 3:07 PM, Gerd Hoffmann wrote:
On Thu, Mar 05, 2020 at 02:29:08PM +0100, Nirmoy Das wrote:
Calculate GEM VRAM bo's offset within vram-helper without depending on bo->offset.
Signed-off-by: Nirmoy Das nirmoy.das@amd.com Reviewed-by: Daniel Vetter daniel.vetter@ffwll.ch
drivers/gpu/drm/drm_gem_vram_helper.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c index 92a11bb42365..2749c2d25ac4 100644 --- a/drivers/gpu/drm/drm_gem_vram_helper.c +++ b/drivers/gpu/drm/drm_gem_vram_helper.c @@ -198,6 +198,13 @@ u64 drm_gem_vram_mmap_offset(struct drm_gem_vram_object *gbo) } EXPORT_SYMBOL(drm_gem_vram_mmap_offset);
+static s64 drm_gem_vram_pg_offset(struct drm_gem_vram_object *gbo) +{
- if (WARN_ON_ONCE(!gbo->bo.mem.mm_node))
return 0;returns 0 on error.
I am not sure if we should call this an error. This patch series removes below offset calculation from ttm_bo.c.
- if (bo->mem.mm_node) - bo->offset = (bo->mem.start << PAGE_SHIFT) + - bdev->man[bo->mem.mem_type].gpu_offset; - else - bo->offset = 0; -
Most of the driver sets "bo->mem.mm_node". Thomas suggested to use this "return 0" in case some driver depends on bo->offset = 0.
- return gbo->bo.mem.start;
+}
- /**
Returns a GEM VRAM object's offset in video memory
- drm_gem_vram_offset() - \
@@ -214,7 +221,7 @@ s64 drm_gem_vram_offset(struct drm_gem_vram_object *gbo) { if (WARN_ON_ONCE(!gbo->pin_count)) return (s64)-ENODEV;
returns -errno on error.
- return gbo->bo.offset;
- return drm_gem_vram_pg_offset(gbo) << PAGE_SHIFT;
And given that one calls the other behavior on error should better be consistent ...
cheers, Gerd
Regards,
Nirmoy
Am 05.03.20 um 15:35 schrieb Nirmoy:
On 3/5/20 3:07 PM, Gerd Hoffmann wrote:
On Thu, Mar 05, 2020 at 02:29:08PM +0100, Nirmoy Das wrote:
Calculate GEM VRAM bo's offset within vram-helper without depending on bo->offset.
Signed-off-by: Nirmoy Dasnirmoy.das@amd.com Reviewed-by: Daniel Vetterdaniel.vetter@ffwll.ch
drivers/gpu/drm/drm_gem_vram_helper.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c index 92a11bb42365..2749c2d25ac4 100644 --- a/drivers/gpu/drm/drm_gem_vram_helper.c +++ b/drivers/gpu/drm/drm_gem_vram_helper.c @@ -198,6 +198,13 @@ u64 drm_gem_vram_mmap_offset(struct drm_gem_vram_object *gbo) } EXPORT_SYMBOL(drm_gem_vram_mmap_offset);
+static s64 drm_gem_vram_pg_offset(struct drm_gem_vram_object *gbo) +{
- if (WARN_ON_ONCE(!gbo->bo.mem.mm_node))
return 0;returns 0 on error.
I am not sure if we should call this an error. This patch series removes below offset calculation from ttm_bo.c.
- if (bo->mem.mm_node)
bo->offset = (bo->mem.start << PAGE_SHIFT) +bdev->man[bo->mem.mem_type].gpu_offset;- else
bo->offset = 0;Most of the driver sets "bo->mem.mm_node". Thomas suggested to use this "return 0" in case some driver depends on bo->offset = 0.
We should probably add a code comment here to explain why we do this.
Something like "Keep TTM behavior for now, remove when drivers are audited".
Regards, Christian.
- return gbo->bo.mem.start;
+}
- /**
Returns a GEM VRAM object's offset in video memory
- drm_gem_vram_offset() - \
@@ -214,7 +221,7 @@ s64 drm_gem_vram_offset(struct drm_gem_vram_object *gbo) { if (WARN_ON_ONCE(!gbo->pin_count)) return (s64)-ENODEV;
returns -errno on error.
- return gbo->bo.offset;
- return drm_gem_vram_pg_offset(gbo) << PAGE_SHIFT;
And given that one calls the other behavior on error should better be consistent ...
cheers, Gerd
Regards,
Nirmoy
amd-gfx mailing list amd-gfx@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/amd-gfx
Switch over to GEM VRAM's implementation to retrieve bo->offset.
Signed-off-by: Nirmoy Das nirmoy.das@amd.com Reviewed-by: Daniel Vetter daniel.vetter@ffwll.ch --- drivers/gpu/drm/bochs/bochs_kms.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/bochs/bochs_kms.c b/drivers/gpu/drm/bochs/bochs_kms.c index 8066d7d370d5..18d2ec34534d 100644 --- a/drivers/gpu/drm/bochs/bochs_kms.c +++ b/drivers/gpu/drm/bochs/bochs_kms.c @@ -29,16 +29,21 @@ static void bochs_plane_update(struct bochs_device *bochs, struct drm_plane_state *state) { struct drm_gem_vram_object *gbo; + s64 gpu_addr;
if (!state->fb || !bochs->stride) return;
gbo = drm_gem_vram_of_gem(state->fb->obj[0]); + gpu_addr = drm_gem_vram_offset(gbo); + if (WARN_ON_ONCE(gpu_addr < 0)) + return; /* Bug: we didn't pin the BO to VRAM in prepare_fb. */ + bochs_hw_setbase(bochs, state->crtc_x, state->crtc_y, state->fb->pitches[0], - state->fb->offsets[0] + gbo->bo.offset); + state->fb->offsets[0] + gpu_addr); bochs_hw_setformat(bochs, state->fb->format); }
-- 2.25.0
GPU address handling is device specific and should be handle by its device driver.
Signed-off-by: Nirmoy Das nirmoy.das@amd.com --- drivers/gpu/drm/ttm/ttm_bo.c | 7 ------- include/drm/ttm/ttm_bo_api.h | 2 -- include/drm/ttm/ttm_bo_driver.h | 1 - 3 files changed, 10 deletions(-)
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 6d1e91be9c78..9f24fb287d71 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -85,7 +85,6 @@ static void ttm_mem_type_debug(struct ttm_bo_device *bdev, struct drm_printer *p drm_printf(p, " has_type: %d\n", man->has_type); drm_printf(p, " use_type: %d\n", man->use_type); drm_printf(p, " flags: 0x%08X\n", man->flags); - drm_printf(p, " gpu_offset: 0x%08llX\n", man->gpu_offset); drm_printf(p, " size: %llu\n", man->size); drm_printf(p, " available_caching: 0x%08X\n", man->available_caching); drm_printf(p, " default_caching: 0x%08X\n", man->default_caching); @@ -345,12 +344,6 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo, moved: bo->evicted = false;
- if (bo->mem.mm_node) - bo->offset = (bo->mem.start << PAGE_SHIFT) + - bdev->man[bo->mem.mem_type].gpu_offset; - else - bo->offset = 0; - ctx->bytes_moved += bo->num_pages << PAGE_SHIFT; return 0;
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index b9bc1b00142e..d6f39ee5bf5d 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -213,8 +213,6 @@ struct ttm_buffer_object { * either of these locks held. */
- uint64_t offset; /* GPU address space is independent of CPU word size */ - struct sg_table *sg; };
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index c9e0fd09f4b2..c8ce6c181abe 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -177,7 +177,6 @@ struct ttm_mem_type_manager { bool has_type; bool use_type; uint32_t flags; - uint64_t gpu_offset; /* GPU address space is independent of CPU word size */ uint64_t size; uint32_t available_caching; uint32_t default_caching;
Am 05.03.20 um 14:29 schrieb Nirmoy Das:
GPU address handling is device specific and should be handle by its device driver.
Signed-off-by: Nirmoy Das nirmoy.das@amd.com
Reviewed-by: Christian König christian.koenig@amd.com
drivers/gpu/drm/ttm/ttm_bo.c | 7 ------- include/drm/ttm/ttm_bo_api.h | 2 -- include/drm/ttm/ttm_bo_driver.h | 1 - 3 files changed, 10 deletions(-)
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 6d1e91be9c78..9f24fb287d71 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -85,7 +85,6 @@ static void ttm_mem_type_debug(struct ttm_bo_device *bdev, struct drm_printer *p drm_printf(p, " has_type: %d\n", man->has_type); drm_printf(p, " use_type: %d\n", man->use_type); drm_printf(p, " flags: 0x%08X\n", man->flags);
- drm_printf(p, " gpu_offset: 0x%08llX\n", man->gpu_offset); drm_printf(p, " size: %llu\n", man->size); drm_printf(p, " available_caching: 0x%08X\n", man->available_caching); drm_printf(p, " default_caching: 0x%08X\n", man->default_caching);
@@ -345,12 +344,6 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo, moved: bo->evicted = false;
- if (bo->mem.mm_node)
bo->offset = (bo->mem.start << PAGE_SHIFT) +bdev->man[bo->mem.mem_type].gpu_offset;- else
bo->offset = 0;- ctx->bytes_moved += bo->num_pages << PAGE_SHIFT; return 0;
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index b9bc1b00142e..d6f39ee5bf5d 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -213,8 +213,6 @@ struct ttm_buffer_object { * either of these locks held. */
- uint64_t offset; /* GPU address space is independent of CPU word size */
- struct sg_table *sg; };
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index c9e0fd09f4b2..c8ce6c181abe 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -177,7 +177,6 @@ struct ttm_mem_type_manager { bool has_type; bool use_type; uint32_t flags;
- uint64_t gpu_offset; /* GPU address space is independent of CPU word size */ uint64_t size; uint32_t available_caching; uint32_t default_caching;
dri-devel@lists.freedesktop.org
-
Christian König -
Christian König -
Gerd Hoffmann -
Ho, Kenny -
Luben Tuikov -
Nirmoy -
Nirmoy Das -
Thomas Zimmermann