Re: [PATCH] drm/amdgpu: Add early fini callback

Andrey Grodzovsky <andrey.grodzovsky@xxxxxxx> · Wed, 19 May 2021 23:58:17 -0400

On 2021-05-19 11:29 p.m., Felix Kuehling wrote:
Am 2021-05-19 um 11:20 p.m. schrieb Andrey Grodzovsky:
Use it to call disply code dependent on device->drv_data
before it's set to NULL on device unplug

v5:
Move HW finilization into this callback to prevent MMIO accesses
post cpi remove.

v7:
Split kfd suspend from device exit to expdite HW related
stuff to amdgpu_pci_remove

v8:
Squash previous KFD commit into this commit to avoid compile break.

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@xxxxxxx>
Acked-by: Christian König <christian.koenig@xxxxxxx>
See one cosmetic comment inline. With that fixed the patch is

Reviewed-by: Felix Kuehling <Felix.Kuehling@xxxxxxx>


Thanks for quick response, updated.
Since this was last commit to review I also pushed the series to
drm-misc-next.

Andrey



---
  drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c    |  2 +-
  drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h    |  2 +-
  drivers/gpu/drm/amd/amdgpu/amdgpu_device.c    | 59 +++++++++++++------
  drivers/gpu/drm/amd/amdkfd/kfd_device.c       |  3 +-
  .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 12 +++-
  drivers/gpu/drm/amd/include/amd_shared.h      |  2 +
  6 files changed, 56 insertions(+), 24 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 5f6696a3c778..2b06dee9a0ce 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -170,7 +170,7 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
  	}
  }
  
-void amdgpu_amdkfd_device_fini(struct amdgpu_device *adev)
+void amdgpu_amdkfd_device_fini_sw(struct amdgpu_device *adev)
  {
  	if (adev->kfd.dev) {
  		kgd2kfd_device_exit(adev->kfd.dev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 5ffb07b02810..d8a537e8aea5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -127,7 +127,7 @@ void amdgpu_amdkfd_interrupt(struct amdgpu_device *adev,
  			const void *ih_ring_entry);
  void amdgpu_amdkfd_device_probe(struct amdgpu_device *adev);
  void amdgpu_amdkfd_device_init(struct amdgpu_device *adev);
-void amdgpu_amdkfd_device_fini(struct amdgpu_device *adev);
+void amdgpu_amdkfd_device_fini_sw(struct amdgpu_device *adev);
  int amdgpu_amdkfd_submit_ib(struct kgd_dev *kgd, enum kgd_engine_type engine,
  				uint32_t vmid, uint64_t gpu_addr,
  				uint32_t *ib_cmd, uint32_t ib_len);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 8bee95ad32d9..bc75e35dd8d8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2558,34 +2558,26 @@ static int amdgpu_device_ip_late_init(struct amdgpu_device *adev)
  	return 0;
  }
  
-/**
- * amdgpu_device_ip_fini - run fini for hardware IPs
- *
- * @adev: amdgpu_device pointer
- *
- * Main teardown pass for hardware IPs.  The list of all the hardware
- * IPs that make up the asic is walked and the hw_fini and sw_fini callbacks
- * are run.  hw_fini tears down the hardware associated with each IP
- * and sw_fini tears down any software state associated with each IP.
- * Returns 0 on success, negative error code on failure.
- */
-static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
+static int amdgpu_device_ip_fini_early(struct amdgpu_device *adev)
  {
  	int i, r;
  
-	if (amdgpu_sriov_vf(adev) && adev->virt.ras_init_done)
-		amdgpu_virt_release_ras_err_handler_data(adev);
+	for (i = 0; i < adev->num_ip_blocks; i++) {
+		if (!adev->ip_blocks[i].version->funcs->early_fini)
+			continue;
  
-	amdgpu_ras_pre_fini(adev);
+		r = adev->ip_blocks[i].version->funcs->early_fini((void *)adev);
+		if (r) {
+			DRM_DEBUG("early_fini of IP block <%s> failed %d\n",
+				  adev->ip_blocks[i].version->funcs->name, r);
+		}
+	}
  
-	if (adev->gmc.xgmi.num_physical_nodes > 1)
-		amdgpu_xgmi_remove_device(adev);
+	amdgpu_amdkfd_suspend(adev, false);
  
  	amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE);
  	amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE);
  
-	amdgpu_amdkfd_device_fini(adev);
-
  	/* need to disable SMC first */
  	for (i = 0; i < adev->num_ip_blocks; i++) {
  		if (!adev->ip_blocks[i].status.hw)
@@ -2616,6 +2608,33 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
  		adev->ip_blocks[i].status.hw = false;
  	}
  
+	return 0;
+}
+
+/**
+ * amdgpu_device_ip_fini - run fini for hardware IPs
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Main teardown pass for hardware IPs.  The list of all the hardware
+ * IPs that make up the asic is walked and the hw_fini and sw_fini callbacks
+ * are run.  hw_fini tears down the hardware associated with each IP
+ * and sw_fini tears down any software state associated with each IP.
+ * Returns 0 on success, negative error code on failure.
+ */
+static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
+{
+	int i, r;
+
+	if (amdgpu_sriov_vf(adev) && adev->virt.ras_init_done)
+		amdgpu_virt_release_ras_err_handler_data(adev);
+
+	amdgpu_ras_pre_fini(adev);
+
+	if (adev->gmc.xgmi.num_physical_nodes > 1)
+		amdgpu_xgmi_remove_device(adev);
+
+	amdgpu_amdkfd_device_fini_sw(adev);
  
  	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
  		if (!adev->ip_blocks[i].status.sw)
@@ -3681,6 +3700,8 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
  	amdgpu_fbdev_fini(adev);
  
  	amdgpu_irq_fini_hw(adev);
+
+	amdgpu_device_ip_fini_early(adev);
  }
  
  void amdgpu_device_fini_sw(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 357b9bf62a1c..ab6d2a43c9a3 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -858,10 +858,11 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
  	return kfd->init_complete;
  }
  
+
+
  void kgd2kfd_device_exit(struct kfd_dev *kfd)
Unnecessary whitespace change.

Regards,
   Felix


  {
  	if (kfd->init_complete) {
-		kgd2kfd_suspend(kfd, false);
  		device_queue_manager_uninit(kfd->dqm);
  		kfd_interrupt_exit(kfd);
  		kfd_topology_remove_device(kfd);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 9ca517b65854..f7112865269a 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1251,6 +1251,15 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
  	return -EINVAL;
  }
  
+static int amdgpu_dm_early_fini(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	amdgpu_dm_audio_fini(adev);
+
+	return 0;
+}
+
  static void amdgpu_dm_fini(struct amdgpu_device *adev)
  {
  	int i;
@@ -1259,8 +1268,6 @@ static void amdgpu_dm_fini(struct amdgpu_device *adev)
  		drm_encoder_cleanup(&adev->dm.mst_encoders[i].base);
  	}
  
-	amdgpu_dm_audio_fini(adev);
-
  	amdgpu_dm_destroy_drm_device(&adev->dm);
  
  #if defined(CONFIG_DRM_AMD_SECURE_DISPLAY)
@@ -2298,6 +2305,7 @@ static const struct amd_ip_funcs amdgpu_dm_funcs = {
  	.late_init = dm_late_init,
  	.sw_init = dm_sw_init,
  	.sw_fini = dm_sw_fini,
+	.early_fini = amdgpu_dm_early_fini,
  	.hw_init = dm_hw_init,
  	.hw_fini = dm_hw_fini,
  	.suspend = dm_suspend,
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index 43ed6291b2b8..1ad56da486e4 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -240,6 +240,7 @@ enum amd_dpm_forced_level;
   * @late_init: sets up late driver/hw state (post hw_init) - Optional
   * @sw_init: sets up driver state, does not configure hw
   * @sw_fini: tears down driver state, does not configure hw
+ * @early_fini: tears down stuff before dev detached from driver
   * @hw_init: sets up the hw state
   * @hw_fini: tears down the hw state
   * @late_fini: final cleanup
@@ -268,6 +269,7 @@ struct amd_ip_funcs {
  	int (*late_init)(void *handle);
  	int (*sw_init)(void *handle);
  	int (*sw_fini)(void *handle);
+	int (*early_fini)(void *handle);
  	int (*hw_init)(void *handle);
  	int (*hw_fini)(void *handle);
  	void (*late_fini)(void *handle);






