1 files changed, 46 insertions, 11 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index e036011137aa..1eccad4ce243 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -44,6 +44,7 @@
  * changes to accumulate
  */
 #define AMDGPU_USERPTR_RESTORE_DELAY_MS 1
+#define AMDGPU_RESERVE_MEM_LIMIT			(3UL << 29)
 
 /*
  * Align VRAM availability to 2MB to avoid fragmentation caused by 4K allocations in the tail 2MB
@@ -117,11 +118,16 @@ void amdgpu_amdkfd_gpuvm_init_mem_limits(void)
 		return;
 
 	si_meminfo(&si);
-	mem = si.freeram - si.freehigh;
+	mem = si.totalram - si.totalhigh;
 	mem *= si.mem_unit;
 
 	spin_lock_init(&kfd_mem_limit.mem_limit_lock);
-	kfd_mem_limit.max_system_mem_limit = mem - (mem >> 4);
+	kfd_mem_limit.max_system_mem_limit = mem - (mem >> 6);
+	if (kfd_mem_limit.max_system_mem_limit < 2 * AMDGPU_RESERVE_MEM_LIMIT)
+		kfd_mem_limit.max_system_mem_limit >>= 1;
+	else
+		kfd_mem_limit.max_system_mem_limit -= AMDGPU_RESERVE_MEM_LIMIT;
+
 	kfd_mem_limit.max_ttm_mem_limit = ttm_tt_pages_limit() << PAGE_SHIFT;
 	pr_debug("Kernel memory limit %lluM, TTM limit %lluM\n",
 		(kfd_mem_limit.max_system_mem_limit >> 20),
@@ -733,7 +739,7 @@ kfd_mem_dmaunmap_sg_bo(struct kgd_mem *mem,
 	enum dma_data_direction dir;
 
 	if (unlikely(!ttm->sg)) {
-		pr_err("SG Table of BO is UNEXPECTEDLY NULL");
+		pr_debug("SG Table of BO is NULL");
 		return;
 	}
 
@@ -828,6 +834,7 @@ static int kfd_mem_attach(struct amdgpu_device *adev, struct kgd_mem *mem,
 	uint64_t va = mem->va;
 	struct kfd_mem_attachment *attachment[2] = {NULL, NULL};
 	struct amdgpu_bo *bo[2] = {NULL, NULL};
+	struct amdgpu_bo_va *bo_va;
 	bool same_hive = false;
 	int i, ret;
 
@@ -866,9 +873,10 @@ static int kfd_mem_attach(struct amdgpu_device *adev, struct kgd_mem *mem,
 
 		if ((adev == bo_adev && !(mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP)) ||
 		    (amdgpu_ttm_tt_get_usermm(mem->bo->tbo.ttm) && reuse_dmamap(adev, bo_adev)) ||
-			same_hive) {
+		    (mem->domain == AMDGPU_GEM_DOMAIN_GTT && reuse_dmamap(adev, bo_adev)) ||
+		    same_hive) {
 			/* Mappings on the local GPU, or VRAM mappings in the
-			 * local hive, or userptr mapping can reuse dma map
+			 * local hive, or userptr, or GTT mapping can reuse dma map
 			 * address space share the original BO
 			 */
 			attachment[i]->type = KFD_MEM_ATT_SHARED;
@@ -914,7 +922,12 @@ static int kfd_mem_attach(struct amdgpu_device *adev, struct kgd_mem *mem,
 			pr_debug("Unable to reserve BO during memory attach");
 			goto unwind;
 		}
-		attachment[i]->bo_va = amdgpu_vm_bo_add(adev, vm, bo[i]);
+		bo_va = amdgpu_vm_bo_find(vm, bo[i]);
+		if (!bo_va)
+			bo_va = amdgpu_vm_bo_add(adev, vm, bo[i]);
+		else
+			++bo_va->ref_count;
+		attachment[i]->bo_va = bo_va;
 		amdgpu_bo_unreserve(bo[i]);
 		if (unlikely(!attachment[i]->bo_va)) {
 			ret = -ENOMEM;
@@ -938,7 +951,8 @@ unwind:
 			continue;
 		if (attachment[i]->bo_va) {
 			amdgpu_bo_reserve(bo[i], true);
-			amdgpu_vm_bo_del(adev, attachment[i]->bo_va);
+			if (--attachment[i]->bo_va->ref_count == 0)
+				amdgpu_vm_bo_del(adev, attachment[i]->bo_va);
 			amdgpu_bo_unreserve(bo[i]);
 			list_del(&attachment[i]->list);
 		}
@@ -955,7 +969,8 @@ static void kfd_mem_detach(struct kfd_mem_attachment *attachment)
 
 	pr_debug("\t remove VA 0x%llx in entry %p\n",
 			attachment->va, attachment);
-	amdgpu_vm_bo_del(attachment->adev, attachment->bo_va);
+	if (--attachment->bo_va->ref_count == 0)
+		amdgpu_vm_bo_del(attachment->adev, attachment->bo_va);
 	drm_gem_object_put(&bo->tbo.base);
 	list_del(&attachment->list);
 	kfree(attachment);
@@ -1201,8 +1216,6 @@ static void unmap_bo_from_gpuvm(struct kgd_mem *mem,
 	amdgpu_vm_clear_freed(adev, vm, &bo_va->last_pt_update);
 
 	amdgpu_sync_fence(sync, bo_va->last_pt_update);
-
-	kfd_mem_dmaunmap_attachment(mem, entry);
 }
 
 static int update_gpuvm_pte(struct kgd_mem *mem,
@@ -1257,6 +1270,7 @@ static int map_bo_to_gpuvm(struct kgd_mem *mem,
 
 update_gpuvm_pte_failed:
 	unmap_bo_from_gpuvm(mem, entry, sync);
+	kfd_mem_dmaunmap_attachment(mem, entry);
 	return ret;
 }
 
@@ -1690,6 +1704,8 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 
 	if (flags & KFD_IOC_ALLOC_MEM_FLAGS_COHERENT)
 		alloc_flags |= AMDGPU_GEM_CREATE_COHERENT;
+	if (flags & KFD_IOC_ALLOC_MEM_FLAGS_EXT_COHERENT)
+		alloc_flags |= AMDGPU_GEM_CREATE_EXT_COHERENT;
 	if (flags & KFD_IOC_ALLOC_MEM_FLAGS_UNCACHED)
 		alloc_flags |= AMDGPU_GEM_CREATE_UNCACHED;
 
@@ -1860,8 +1876,10 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
 		mem->va + bo_size * (1 + mem->aql_queue));
 
 	/* Remove from VM internal data structures */
-	list_for_each_entry_safe(entry, tmp, &mem->attachments, list)
+	list_for_each_entry_safe(entry, tmp, &mem->attachments, list) {
+		kfd_mem_dmaunmap_attachment(mem, entry);
 		kfd_mem_detach(entry);
+	}
 
 	ret = unreserve_bo_and_vms(&ctx, false, false);
 
@@ -2035,6 +2053,23 @@ out:
 	return ret;
 }
 
+void amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv)
+{
+	struct kfd_mem_attachment *entry;
+	struct amdgpu_vm *vm;
+
+	vm = drm_priv_to_vm(drm_priv);
+
+	mutex_lock(&mem->lock);
+
+	list_for_each_entry(entry, &mem->attachments, list) {
+		if (entry->bo_va->base.vm == vm)
+			kfd_mem_dmaunmap_attachment(mem, entry);
+	}
+
+	mutex_unlock(&mem->lock);
+}
+
 int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(
 		struct amdgpu_device *adev, struct kgd_mem *mem, void *drm_priv)
 {