drm/amdgpu: change vm->task_info handling

This patch changes the handling and lifecycle of vm->task_info object.
The major changes are:
- vm->task_info is a dynamically allocated ptr now, and its uasge is
  reference counted.
- introducing two new helper funcs for task_info lifecycle management
    - amdgpu_vm_get_task_info: reference counts up task_info before
      returning this info
    - amdgpu_vm_put_task_info: reference counts down task_info
- last put to task_info() frees task_info from the vm.

This patch also does logistical changes required for existing usage
of vm->task_info.

V2: Do not block all the prints when task_info not found (Felix)

V3: Fixed review comments from Felix
   - Fix wrong indentation
   - No debug message for -ENOMEM
   - Add NULL check for task_info
   - Do not duplicate the debug messages (ti vs no ti)
   - Get first reference of task_info in vm_init(), put last
     in vm_fini()

V4: Fixed review comments from Felix
   - fix double reference increment in create_task_info
   - change amdgpu_vm_get_task_info_pasid
   - additional changes in amdgpu_gem.c while porting

Cc: Christian Koenig <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Shashank Sharma <shashank.sharma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 14 insertions, 10 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index db89d13bd80d..d933e19e0cf5 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -105,7 +105,7 @@ static int gmc_v10_0_process_interrupt(struct amdgpu_device *adev,
 	struct amdgpu_vmhub *hub = &adev->vmhub[vmhub_index];
 	bool retry_fault = !!(entry->src_data[1] & 0x80);
 	bool write_fault = !!(entry->src_data[1] & 0x20);
-	struct amdgpu_task_info task_info;
+	struct amdgpu_task_info *task_info;
 	uint32_t status = 0;
 	u64 addr;
 
@@ -157,18 +157,22 @@ static int gmc_v10_0_process_interrupt(struct amdgpu_device *adev,
 	if (!printk_ratelimit())
 		return 0;
 
-	memset(&task_info, 0, sizeof(struct amdgpu_task_info));
-	amdgpu_vm_get_task_info(adev, entry->pasid, &task_info);
-
 	dev_err(adev->dev,
-		"[%s] page fault (src_id:%u ring:%u vmid:%u pasid:%u, for process %s pid %d thread %s pid %d)\n",
+		"[%s] page fault (src_id:%u ring:%u vmid:%u pasid:%u)\n",
 		entry->vmid_src ? "mmhub" : "gfxhub",
-		entry->src_id, entry->ring_id, entry->vmid,
-		entry->pasid, task_info.process_name, task_info.tgid,
-		task_info.task_name, task_info.pid);
+		entry->src_id, entry->ring_id, entry->vmid, entry->pasid);
+	task_info = amdgpu_vm_get_task_info_pasid(adev, entry->pasid);
+	if (task_info) {
+		dev_err(adev->dev,
+			" in process %s pid %d thread %s pid %d\n",
+			task_info->process_name, task_info->tgid,
+			task_info->task_name, task_info->pid);
+		amdgpu_vm_put_task_info(task_info);
+	}
+
 	dev_err(adev->dev, "  in page starting at address 0x%016llx from client 0x%x (%s)\n",
-		addr, entry->client_id,
-		soc15_ih_clientid_name[entry->client_id]);
+			addr, entry->client_id,
+			soc15_ih_clientid_name[entry->client_id]);
 
 	if (!amdgpu_sriov_vf(adev))
 		hub->vmhub_funcs->print_l2_protection_fault_status(adev,