From: "Christian König" <ckoenig.leichtzumerken-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
To: Chunming Zhou <david1.zhou-5C7GfCeVMHo@public.gmane.org>,
amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org
Cc: Felix.Kuehling-5C7GfCeVMHo@public.gmane.org,
christian.koenig-5C7GfCeVMHo@public.gmane.org
Subject: Re: [PATCH 2/2] drm/amdgpu: use amdgpu_bo_param for amdgpu_bo_create v2
Date: Tue, 17 Apr 2018 12:12:42 +0200 [thread overview]
Message-ID: <d12a673e-1f6a-4e24-353a-ad540440af9a@gmail.com> (raw)
In-Reply-To: <20180417055406.19902-2-david1.zhou-5C7GfCeVMHo@public.gmane.org>
Am 17.04.2018 um 07:54 schrieb Chunming Zhou:
> After that, we can easily add new parameter when need.
>
> v2:
> a) rebase.
> b) Initialize struct amdgpu_bo_param, future new
> member could only be used in some one case, but all member
> should have its own initial value.
>
> Change-Id: I6e80039c3801f163129ecc605d931483fdbc91db
> Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
> Reviewed-by: Huang Rui <ray.huang@amd.com> (v1)
> Reviewed-by: Christian König <christian.koenig@amd.com> (v1)
Reviewed-by: Christian König <christian.koenig@amd.com>
> Cc: christian.koenig@amd.com
> Cc: Felix.Kuehling@amd.com
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 12 +++--
> drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 11 ++++-
> drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c | 15 ++++--
> drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c | 17 ++++---
> drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 11 ++++-
> drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 58 ++++++++++++------------
> drivers/gpu/drm/amd/amdgpu/amdgpu_object.h | 6 +--
> drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c | 12 +++--
> drivers/gpu/drm/amd/amdgpu/amdgpu_test.c | 18 +++++---
> drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 15 ++++--
> drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 26 ++++++++---
> 11 files changed, 130 insertions(+), 71 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
> index 4d36203ffb11..887702c59488 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
> @@ -217,13 +217,19 @@ int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
> {
> struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
> struct amdgpu_bo *bo = NULL;
> + struct amdgpu_bo_param bp;
> int r;
> uint64_t gpu_addr_tmp = 0;
> void *cpu_ptr_tmp = NULL;
>
> - r = amdgpu_bo_create(adev, size, PAGE_SIZE, AMDGPU_GEM_DOMAIN_GTT,
> - AMDGPU_GEM_CREATE_CPU_GTT_USWC, ttm_bo_type_kernel,
> - NULL, &bo);
> + memset(&bp, 0, sizeof(bp));
> + bp.size = size;
> + bp.byte_align = PAGE_SIZE;
> + bp.domain = AMDGPU_GEM_DOMAIN_GTT;
> + bp.flags = AMDGPU_GEM_CREATE_CPU_GTT_USWC;
> + bp.type = ttm_bo_type_kernel;
> + bp.resv = NULL;
> + r = amdgpu_bo_create(adev, &bp, &bo);
> if (r) {
> dev_err(adev->dev,
> "failed to allocate BO for amdkfd (%d)\n", r);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
> index 1d6e1479da38..c1b0cdb401dc 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
> @@ -1004,6 +1004,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
> struct amdgpu_device *adev = get_amdgpu_device(kgd);
> struct amdgpu_vm *avm = (struct amdgpu_vm *)vm;
> struct amdgpu_bo *bo;
> + struct amdgpu_bo_param bp;
> int byte_align;
> u32 alloc_domain;
> u64 alloc_flags;
> @@ -1069,8 +1070,14 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
> pr_debug("\tcreate BO VA 0x%llx size 0x%llx domain %s\n",
> va, size, domain_string(alloc_domain));
>
> - ret = amdgpu_bo_create(adev, size, byte_align,
> - alloc_domain, alloc_flags, ttm_bo_type_device, NULL, &bo);
> + memset(&bp, 0, sizeof(bp));
> + bp.size = size;
> + bp.byte_align = byte_align;
> + bp.domain = alloc_domain;
> + bp.flags = alloc_flags;
> + bp.type = ttm_bo_type_device;
> + bp.resv = NULL;
> + ret = amdgpu_bo_create(adev, &bp, &bo);
> if (ret) {
> pr_debug("Failed to create BO on domain %s. ret %d\n",
> domain_string(alloc_domain), ret);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
> index 02b849be083b..19cfff31f2e1 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
> @@ -75,13 +75,20 @@ static void amdgpu_benchmark_move(struct amdgpu_device *adev, unsigned size,
> {
> struct amdgpu_bo *dobj = NULL;
> struct amdgpu_bo *sobj = NULL;
> + struct amdgpu_bo_param bp;
> uint64_t saddr, daddr;
> int r, n;
> int time;
>
> + memset(&bp, 0, sizeof(bp));
> + bp.size = size;
> + bp.byte_align = PAGE_SIZE;
> + bp.domain = sdomain;
> + bp.flags = 0;
> + bp.type = ttm_bo_type_kernel;
> + bp.resv = NULL;
> n = AMDGPU_BENCHMARK_ITERATIONS;
> - r = amdgpu_bo_create(adev, size, PAGE_SIZE,sdomain, 0,
> - ttm_bo_type_kernel, NULL, &sobj);
> + r = amdgpu_bo_create(adev, &bp, &sobj);
> if (r) {
> goto out_cleanup;
> }
> @@ -93,8 +100,8 @@ static void amdgpu_benchmark_move(struct amdgpu_device *adev, unsigned size,
> if (r) {
> goto out_cleanup;
> }
> - r = amdgpu_bo_create(adev, size, PAGE_SIZE, ddomain, 0,
> - ttm_bo_type_kernel, NULL, &dobj);
> + bp.domain = ddomain;
> + r = amdgpu_bo_create(adev, &bp, &dobj);
> if (r) {
> goto out_cleanup;
> }
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
> index cf0f186c6092..17d6b9fb6d77 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
> @@ -113,12 +113,17 @@ int amdgpu_gart_table_vram_alloc(struct amdgpu_device *adev)
> int r;
>
> if (adev->gart.robj == NULL) {
> - r = amdgpu_bo_create(adev, adev->gart.table_size, PAGE_SIZE,
> - AMDGPU_GEM_DOMAIN_VRAM,
> - AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
> - AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS,
> - ttm_bo_type_kernel, NULL,
> - &adev->gart.robj);
> + struct amdgpu_bo_param bp;
> +
> + memset(&bp, 0, sizeof(bp));
> + bp.size = adev->gart.table_size;
> + bp.byte_align = PAGE_SIZE;
> + bp.domain = AMDGPU_GEM_DOMAIN_VRAM;
> + bp.flags = AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
> + AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
> + bp.type = ttm_bo_type_kernel;
> + bp.resv = NULL;
> + r = amdgpu_bo_create(adev, &bp, &adev->gart.robj);
> if (r) {
> return r;
> }
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
> index 46b9ea4e6103..1200c5ba37da 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
> @@ -48,17 +48,24 @@ int amdgpu_gem_object_create(struct amdgpu_device *adev, unsigned long size,
> struct drm_gem_object **obj)
> {
> struct amdgpu_bo *bo;
> + struct amdgpu_bo_param bp;
> int r;
>
> + memset(&bp, 0, sizeof(bp));
> *obj = NULL;
> /* At least align on page size */
> if (alignment < PAGE_SIZE) {
> alignment = PAGE_SIZE;
> }
>
> + bp.size = size;
> + bp.byte_align = alignment;
> + bp.type = type;
> + bp.resv = resv;
> retry:
> - r = amdgpu_bo_create(adev, size, alignment, initial_domain,
> - flags, type, resv, &bo);
> + bp.flags = flags;
> + bp.domain = initial_domain;
> + r = amdgpu_bo_create(adev, &bp, &bo);
> if (r) {
> if (r != -ERESTARTSYS) {
> if (flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) {
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> index b33a7fdea7f2..cac65e32a0b9 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> @@ -191,14 +191,21 @@ int amdgpu_bo_create_reserved(struct amdgpu_device *adev,
> u32 domain, struct amdgpu_bo **bo_ptr,
> u64 *gpu_addr, void **cpu_addr)
> {
> + struct amdgpu_bo_param bp;
> bool free = false;
> int r;
>
> + memset(&bp, 0, sizeof(bp));
> + bp.size = size;
> + bp.byte_align = align;
> + bp.domain = domain;
> + bp.flags = AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
> + AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
> + bp.type = ttm_bo_type_kernel;
> + bp.resv = NULL;
> +
> if (!*bo_ptr) {
> - r = amdgpu_bo_create(adev, size, align, domain,
> - AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
> - AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS,
> - ttm_bo_type_kernel, NULL, bo_ptr);
> + r = amdgpu_bo_create(adev, &bp, bo_ptr);
> if (r) {
> dev_err(adev->dev, "(%d) failed to allocate kernel bo\n",
> r);
> @@ -470,20 +477,21 @@ static int amdgpu_bo_create_shadow(struct amdgpu_device *adev,
> unsigned long size, int byte_align,
> struct amdgpu_bo *bo)
> {
> - struct amdgpu_bo_param bp = {
> - .size = size,
> - .byte_align = byte_align,
> - .domain = AMDGPU_GEM_DOMAIN_GTT,
> - .flags = AMDGPU_GEM_CREATE_CPU_GTT_USWC |
> - AMDGPU_GEM_CREATE_SHADOW,
> - .type = ttm_bo_type_kernel,
> - .resv = bo->tbo.resv
> - };
> + struct amdgpu_bo_param bp;
> int r;
>
> if (bo->shadow)
> return 0;
>
> + memset(&bp, 0, sizeof(bp));
> + bp.size = size;
> + bp.byte_align = byte_align;
> + bp.domain = AMDGPU_GEM_DOMAIN_GTT;
> + bp.flags = AMDGPU_GEM_CREATE_CPU_GTT_USWC |
> + AMDGPU_GEM_CREATE_SHADOW;
> + bp.type = ttm_bo_type_kernel;
> + bp.resv = bo->tbo.resv;
> +
> r = amdgpu_bo_do_create(adev, &bp, &bo->shadow);
> if (!r) {
> bo->shadow->parent = amdgpu_bo_ref(bo);
> @@ -495,34 +503,26 @@ static int amdgpu_bo_create_shadow(struct amdgpu_device *adev,
> return r;
> }
>
> -int amdgpu_bo_create(struct amdgpu_device *adev, unsigned long size,
> - int byte_align, u32 domain,
> - u64 flags, enum ttm_bo_type type,
> - struct reservation_object *resv,
> +int amdgpu_bo_create(struct amdgpu_device *adev,
> + struct amdgpu_bo_param *bp,
> struct amdgpu_bo **bo_ptr)
> {
> - struct amdgpu_bo_param bp = {
> - .size = size,
> - .byte_align = byte_align,
> - .domain = domain,
> - .flags = flags & ~AMDGPU_GEM_CREATE_SHADOW,
> - .type = type,
> - .resv = resv
> - };
> + u64 flags = bp->flags;
> int r;
>
> - r = amdgpu_bo_do_create(adev, &bp, bo_ptr);
> + bp->flags = bp->flags & ~AMDGPU_GEM_CREATE_SHADOW;
> + r = amdgpu_bo_do_create(adev, bp, bo_ptr);
> if (r)
> return r;
>
> if ((flags & AMDGPU_GEM_CREATE_SHADOW) && amdgpu_need_backup(adev)) {
> - if (!resv)
> + if (!bp->resv)
> WARN_ON(reservation_object_lock((*bo_ptr)->tbo.resv,
> NULL));
>
> - r = amdgpu_bo_create_shadow(adev, size, byte_align, (*bo_ptr));
> + r = amdgpu_bo_create_shadow(adev, bp->size, bp->byte_align, (*bo_ptr));
>
> - if (!resv)
> + if (!bp->resv)
> reservation_object_unlock((*bo_ptr)->tbo.resv);
>
> if (r)
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
> index 4bb6f0a8d799..e9a21d991e77 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
> @@ -233,10 +233,8 @@ static inline bool amdgpu_bo_explicit_sync(struct amdgpu_bo *bo)
> return bo->flags & AMDGPU_GEM_CREATE_EXPLICIT_SYNC;
> }
>
> -int amdgpu_bo_create(struct amdgpu_device *adev, unsigned long size,
> - int byte_align, u32 domain,
> - u64 flags, enum ttm_bo_type type,
> - struct reservation_object *resv,
> +int amdgpu_bo_create(struct amdgpu_device *adev,
> + struct amdgpu_bo_param *bp,
> struct amdgpu_bo **bo_ptr);
> int amdgpu_bo_create_reserved(struct amdgpu_device *adev,
> unsigned long size, int align,
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
> index 4b584cb75bf4..713417b6d15d 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
> @@ -102,12 +102,18 @@ amdgpu_gem_prime_import_sg_table(struct drm_device *dev,
> struct reservation_object *resv = attach->dmabuf->resv;
> struct amdgpu_device *adev = dev->dev_private;
> struct amdgpu_bo *bo;
> + struct amdgpu_bo_param bp;
> int ret;
>
> + memset(&bp, 0, sizeof(bp));
> + bp.size = attach->dmabuf->size;
> + bp.byte_align = PAGE_SIZE;
> + bp.domain = AMDGPU_GEM_DOMAIN_CPU;
> + bp.flags = 0;
> + bp.type = ttm_bo_type_sg;
> + bp.resv = resv;
> ww_mutex_lock(&resv->lock, NULL);
> - ret = amdgpu_bo_create(adev, attach->dmabuf->size, PAGE_SIZE,
> - AMDGPU_GEM_DOMAIN_CPU, 0, ttm_bo_type_sg,
> - resv, &bo);
> + ret = amdgpu_bo_create(adev, &bp, &bo);
> if (ret)
> goto error;
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
> index 2dbe87591f81..d167e8ab76d3 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
> @@ -33,6 +33,7 @@ static void amdgpu_do_test_moves(struct amdgpu_device *adev)
> struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring;
> struct amdgpu_bo *vram_obj = NULL;
> struct amdgpu_bo **gtt_obj = NULL;
> + struct amdgpu_bo_param bp;
> uint64_t gart_addr, vram_addr;
> unsigned n, size;
> int i, r;
> @@ -58,9 +59,15 @@ static void amdgpu_do_test_moves(struct amdgpu_device *adev)
> r = 1;
> goto out_cleanup;
> }
> -
> - r = amdgpu_bo_create(adev, size, PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM, 0,
> - ttm_bo_type_kernel, NULL, &vram_obj);
> + memset(&bp, 0, sizeof(bp));
> + bp.size = size;
> + bp.byte_align = PAGE_SIZE;
> + bp.domain = AMDGPU_GEM_DOMAIN_VRAM;
> + bp.flags = 0;
> + bp.type = ttm_bo_type_kernel;
> + bp.resv = NULL;
> +
> + r = amdgpu_bo_create(adev, &bp, &vram_obj);
> if (r) {
> DRM_ERROR("Failed to create VRAM object\n");
> goto out_cleanup;
> @@ -79,9 +86,8 @@ static void amdgpu_do_test_moves(struct amdgpu_device *adev)
> void **vram_start, **vram_end;
> struct dma_fence *fence = NULL;
>
> - r = amdgpu_bo_create(adev, size, PAGE_SIZE,
> - AMDGPU_GEM_DOMAIN_GTT, 0,
> - ttm_bo_type_kernel, NULL, gtt_obj + i);
> + bp.domain = AMDGPU_GEM_DOMAIN_GTT;
> + r = amdgpu_bo_create(adev, &bp, gtt_obj + i);
> if (r) {
> DRM_ERROR("Failed to create GTT object %d\n", i);
> goto out_lclean;
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> index 29efaac6e3ed..dfd22db13fb1 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> @@ -1316,6 +1316,7 @@ static void amdgpu_ttm_fw_reserve_vram_fini(struct amdgpu_device *adev)
> static int amdgpu_ttm_fw_reserve_vram_init(struct amdgpu_device *adev)
> {
> struct ttm_operation_ctx ctx = { false, false };
> + struct amdgpu_bo_param bp;
> int r = 0;
> int i;
> u64 vram_size = adev->gmc.visible_vram_size;
> @@ -1323,17 +1324,21 @@ static int amdgpu_ttm_fw_reserve_vram_init(struct amdgpu_device *adev)
> u64 size = adev->fw_vram_usage.size;
> struct amdgpu_bo *bo;
>
> + memset(&bp, 0, sizeof(bp));
> + bp.size = adev->fw_vram_usage.size;
> + bp.byte_align = PAGE_SIZE;
> + bp.domain = AMDGPU_GEM_DOMAIN_VRAM;
> + bp.flags = AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
> + AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
> + bp.type = ttm_bo_type_kernel;
> + bp.resv = NULL;
> adev->fw_vram_usage.va = NULL;
> adev->fw_vram_usage.reserved_bo = NULL;
>
> if (adev->fw_vram_usage.size > 0 &&
> adev->fw_vram_usage.size <= vram_size) {
>
> - r = amdgpu_bo_create(adev, adev->fw_vram_usage.size, PAGE_SIZE,
> - AMDGPU_GEM_DOMAIN_VRAM,
> - AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
> - AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS,
> - ttm_bo_type_kernel, NULL,
> + r = amdgpu_bo_create(adev, &bp,
> &adev->fw_vram_usage.reserved_bo);
> if (r)
> goto error_create;
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> index f0fbc331aa30..9ec7c1041df2 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> @@ -412,11 +412,16 @@ static int amdgpu_vm_alloc_levels(struct amdgpu_device *adev,
> struct amdgpu_bo *pt;
>
> if (!entry->base.bo) {
> - r = amdgpu_bo_create(adev,
> - amdgpu_vm_bo_size(adev, level),
> - AMDGPU_GPU_PAGE_SIZE,
> - AMDGPU_GEM_DOMAIN_VRAM, flags,
> - ttm_bo_type_kernel, resv, &pt);
> + struct amdgpu_bo_param bp;
> +
> + memset(&bp, 0, sizeof(bp));
> + bp.size = amdgpu_vm_bo_size(adev, level);
> + bp.byte_align = AMDGPU_GPU_PAGE_SIZE;
> + bp.domain = AMDGPU_GEM_DOMAIN_VRAM;
> + bp.flags = flags;
> + bp.type = ttm_bo_type_kernel;
> + bp.resv = resv;
> + r = amdgpu_bo_create(adev, &bp, &pt);
> if (r)
> return r;
>
> @@ -2368,6 +2373,7 @@ void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint32_t vm_size,
> int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
> int vm_context, unsigned int pasid)
> {
> + struct amdgpu_bo_param bp;
> const unsigned align = min(AMDGPU_VM_PTB_ALIGN_SIZE,
> AMDGPU_VM_PTE_COUNT(adev) * 8);
> unsigned ring_instance;
> @@ -2422,8 +2428,14 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
> flags |= AMDGPU_GEM_CREATE_SHADOW;
>
> size = amdgpu_vm_bo_size(adev, adev->vm_manager.root_level);
> - r = amdgpu_bo_create(adev, size, align, AMDGPU_GEM_DOMAIN_VRAM, flags,
> - ttm_bo_type_kernel, NULL, &vm->root.base.bo);
> + memset(&bp, 0, sizeof(bp));
> + bp.size = size;
> + bp.byte_align = align;
> + bp.domain = AMDGPU_GEM_DOMAIN_VRAM;
> + bp.flags = flags;
> + bp.type = ttm_bo_type_kernel;
> + bp.resv = NULL;
> + r = amdgpu_bo_create(adev, &bp, &vm->root.base.bo);
> if (r)
> goto error_free_sched_entity;
>
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
next prev parent reply other threads:[~2018-04-17 10:12 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-04-17 5:54 [PATCH 1/2] drm/amdgpu: add amdgpu_bo_param Chunming Zhou
[not found] ` <20180417055406.19902-1-david1.zhou-5C7GfCeVMHo@public.gmane.org>
2018-04-17 5:54 ` [PATCH 2/2] drm/amdgpu: use amdgpu_bo_param for amdgpu_bo_create v2 Chunming Zhou
[not found] ` <20180417055406.19902-2-david1.zhou-5C7GfCeVMHo@public.gmane.org>
2018-04-17 10:12 ` Christian König [this message]
2018-04-17 6:12 ` [PATCH 1/2] drm/amdgpu: add amdgpu_bo_param Zhang, Jerry (Junwei)
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=d12a673e-1f6a-4e24-353a-ad540440af9a@gmail.com \
--to=ckoenig.leichtzumerken-re5jqeeqqe8avxtiumwx3w@public.gmane.org \
--cc=Felix.Kuehling-5C7GfCeVMHo@public.gmane.org \
--cc=amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org \
--cc=christian.koenig-5C7GfCeVMHo@public.gmane.org \
--cc=david1.zhou-5C7GfCeVMHo@public.gmane.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox