diff options
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 111 |
1 files changed, 41 insertions, 70 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 581c7ae41102..08997092e7f7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -115,21 +115,12 @@ void amdgpu_amdkfd_reserve_system_mem(uint64_t size) * compromise that should work in most cases without reserving too * much memory for page tables unnecessarily (factor 16K, >> 14). */ -#define ESTIMATE_PT_SIZE(mem_size) max(((mem_size) >> 14), AMDGPU_VM_RESERVED_VRAM) - -static size_t amdgpu_amdkfd_acc_size(uint64_t size) -{ - size >>= PAGE_SHIFT; - size *= sizeof(dma_addr_t) + sizeof(void *); - return __roundup_pow_of_two(sizeof(struct amdgpu_bo)) + - __roundup_pow_of_two(sizeof(struct ttm_tt)) + - PAGE_ALIGN(size); -} +#define ESTIMATE_PT_SIZE(mem_size) max(((mem_size) >> 14), AMDGPU_VM_RESERVED_VRAM) /** * amdgpu_amdkfd_reserve_mem_limit() - Decrease available memory by size - * of buffer including any reserved for control structures + * of buffer. * * @adev: Device to which allocated BO belongs to * @size: Size of buffer, in bytes, encapsulated by B0. This should be @@ -143,19 +134,16 @@ static int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev, { uint64_t reserved_for_pt = ESTIMATE_PT_SIZE(amdgpu_amdkfd_total_mem_size); - size_t acc_size, system_mem_needed, ttm_mem_needed, vram_needed; + size_t system_mem_needed, ttm_mem_needed, vram_needed; int ret = 0; - acc_size = amdgpu_amdkfd_acc_size(size); - + system_mem_needed = 0; + ttm_mem_needed = 0; vram_needed = 0; if (alloc_flag & KFD_IOC_ALLOC_MEM_FLAGS_GTT) { - system_mem_needed = acc_size + size; - ttm_mem_needed = acc_size + size; + system_mem_needed = size; + ttm_mem_needed = size; } else if (alloc_flag & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) { - system_mem_needed = acc_size; - ttm_mem_needed = acc_size; - /* * Conservatively round up the allocation requirement to 2 MB * to avoid fragmentation caused by 4K allocations in the tail @@ -163,14 +151,10 @@ static int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev, */ vram_needed = ALIGN(size, VRAM_ALLOCATION_ALIGN); } else if (alloc_flag & KFD_IOC_ALLOC_MEM_FLAGS_USERPTR) { - system_mem_needed = acc_size + size; - ttm_mem_needed = acc_size; - } else if (alloc_flag & - (KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL | - KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP)) { - system_mem_needed = acc_size; - ttm_mem_needed = acc_size; - } else { + system_mem_needed = size; + } else if (!(alloc_flag & + (KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL | + KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP))) { pr_err("%s: Invalid BO type %#x\n", __func__, alloc_flag); return -ENOMEM; } @@ -208,28 +192,18 @@ release: static void unreserve_mem_limit(struct amdgpu_device *adev, uint64_t size, u32 alloc_flag) { - size_t acc_size; - - acc_size = amdgpu_amdkfd_acc_size(size); - spin_lock(&kfd_mem_limit.mem_limit_lock); if (alloc_flag & KFD_IOC_ALLOC_MEM_FLAGS_GTT) { - kfd_mem_limit.system_mem_used -= (acc_size + size); - kfd_mem_limit.ttm_mem_used -= (acc_size + size); + kfd_mem_limit.system_mem_used -= size; + kfd_mem_limit.ttm_mem_used -= size; } else if (alloc_flag & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) { - kfd_mem_limit.system_mem_used -= acc_size; - kfd_mem_limit.ttm_mem_used -= acc_size; adev->kfd.vram_used -= ALIGN(size, VRAM_ALLOCATION_ALIGN); } else if (alloc_flag & KFD_IOC_ALLOC_MEM_FLAGS_USERPTR) { - kfd_mem_limit.system_mem_used -= (acc_size + size); - kfd_mem_limit.ttm_mem_used -= acc_size; - } else if (alloc_flag & - (KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL | - KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP)) { - kfd_mem_limit.system_mem_used -= acc_size; - kfd_mem_limit.ttm_mem_used -= acc_size; - } else { + kfd_mem_limit.system_mem_used -= size; + } else if (!(alloc_flag & + (KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL | + KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP))) { pr_err("%s: Invalid BO type %#x\n", __func__, alloc_flag); goto release; } @@ -436,45 +410,42 @@ static uint64_t get_pte_flags(struct amdgpu_device *adev, struct kgd_mem *mem) switch (adev->asic_type) { case CHIP_ARCTURUS: - if (mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) { - if (bo_adev == adev) - mapping_flags |= coherent ? - AMDGPU_VM_MTYPE_CC : AMDGPU_VM_MTYPE_RW; - else - mapping_flags |= coherent ? - AMDGPU_VM_MTYPE_UC : AMDGPU_VM_MTYPE_NC; - } else { - mapping_flags |= coherent ? - AMDGPU_VM_MTYPE_UC : AMDGPU_VM_MTYPE_NC; - } - break; case CHIP_ALDEBARAN: - if (coherent && uncached) { - if (adev->gmc.xgmi.connected_to_cpu || - !(mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM)) - snoop = true; - mapping_flags |= AMDGPU_VM_MTYPE_UC; - } else if (mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) { + if (mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) { if (bo_adev == adev) { - mapping_flags |= coherent ? - AMDGPU_VM_MTYPE_CC : AMDGPU_VM_MTYPE_RW; - if (adev->gmc.xgmi.connected_to_cpu) + if (uncached) + mapping_flags |= AMDGPU_VM_MTYPE_UC; + else if (coherent) + mapping_flags |= AMDGPU_VM_MTYPE_CC; + else + mapping_flags |= AMDGPU_VM_MTYPE_RW; + if (adev->asic_type == CHIP_ALDEBARAN && + adev->gmc.xgmi.connected_to_cpu) snoop = true; } else { - mapping_flags |= coherent ? - AMDGPU_VM_MTYPE_UC : AMDGPU_VM_MTYPE_NC; + if (uncached || coherent) + mapping_flags |= AMDGPU_VM_MTYPE_UC; + else + mapping_flags |= AMDGPU_VM_MTYPE_NC; if (amdgpu_xgmi_same_hive(adev, bo_adev)) snoop = true; } } else { + if (uncached || coherent) + mapping_flags |= AMDGPU_VM_MTYPE_UC; + else + mapping_flags |= AMDGPU_VM_MTYPE_NC; snoop = true; - mapping_flags |= coherent ? - AMDGPU_VM_MTYPE_UC : AMDGPU_VM_MTYPE_NC; } break; default: - mapping_flags |= coherent ? - AMDGPU_VM_MTYPE_UC : AMDGPU_VM_MTYPE_NC; + if (uncached || coherent) + mapping_flags |= AMDGPU_VM_MTYPE_UC; + else + mapping_flags |= AMDGPU_VM_MTYPE_NC; + + if (!(mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM)) + snoop = true; } pte_flags = amdgpu_gem_va_map_flags(adev, mapping_flags); |