diff mbox series

[v5,03/27] drm/amdgpu: Split amdgpu_device_fini into early and late

Message ID 20210428151207.1212258-4-andrey.grodzovsky@amd.com (mailing list archive)
State New, archived
Headers show
Series RFC Support hot device unplug in amdgpu | expand

Commit Message

Andrey Grodzovsky April 28, 2021, 3:11 p.m. UTC
Some of the stuff in amdgpu_device_fini such as HW interrupts
disable and pending fences finilization must be done right away on
pci_remove while most of the stuff which relates to finilizing and
releasing driver data structures can be kept until
drm_driver.release hook is called, i.e. when the last device
reference is dropped.

v4: Change functions prefix early->hw and late->sw

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h        |  6 ++++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 26 +++++++++++++++-------
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c    |  7 ++----
 drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c  | 15 ++++++++++++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c    | 26 +++++++++++++---------
 drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h    |  3 ++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c    | 12 +++++++++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c    |  1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h   |  3 ++-
 drivers/gpu/drm/amd/amdgpu/cik_ih.c        |  2 +-
 drivers/gpu/drm/amd/amdgpu/cz_ih.c         |  2 +-
 drivers/gpu/drm/amd/amdgpu/iceland_ih.c    |  2 +-
 drivers/gpu/drm/amd/amdgpu/navi10_ih.c     |  2 +-
 drivers/gpu/drm/amd/amdgpu/si_ih.c         |  2 +-
 drivers/gpu/drm/amd/amdgpu/tonga_ih.c      |  2 +-
 drivers/gpu/drm/amd/amdgpu/vega10_ih.c     |  2 +-
 drivers/gpu/drm/amd/amdgpu/vega20_ih.c     |  2 +-
 17 files changed, 79 insertions(+), 36 deletions(-)

Comments

Christian König April 29, 2021, 7:04 a.m. UTC | #1
Am 28.04.21 um 17:11 schrieb Andrey Grodzovsky:
> Some of the stuff in amdgpu_device_fini such as HW interrupts
> disable and pending fences finilization must be done right away on
> pci_remove while most of the stuff which relates to finilizing and
> releasing driver data structures can be kept until
> drm_driver.release hook is called, i.e. when the last device
> reference is dropped.
>
> v4: Change functions prefix early->hw and late->sw
>
> Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>

Acked-by: Christian König <christian.koenig@amd.com>

But Alex should acknowledge this as well since it is general driver design.

Christian.

> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu.h        |  6 ++++-
>   drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 26 +++++++++++++++-------
>   drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c    |  7 ++----
>   drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c  | 15 ++++++++++++-
>   drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c    | 26 +++++++++++++---------
>   drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h    |  3 ++-
>   drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c    | 12 +++++++++-
>   drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c    |  1 +
>   drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h   |  3 ++-
>   drivers/gpu/drm/amd/amdgpu/cik_ih.c        |  2 +-
>   drivers/gpu/drm/amd/amdgpu/cz_ih.c         |  2 +-
>   drivers/gpu/drm/amd/amdgpu/iceland_ih.c    |  2 +-
>   drivers/gpu/drm/amd/amdgpu/navi10_ih.c     |  2 +-
>   drivers/gpu/drm/amd/amdgpu/si_ih.c         |  2 +-
>   drivers/gpu/drm/amd/amdgpu/tonga_ih.c      |  2 +-
>   drivers/gpu/drm/amd/amdgpu/vega10_ih.c     |  2 +-
>   drivers/gpu/drm/amd/amdgpu/vega20_ih.c     |  2 +-
>   17 files changed, 79 insertions(+), 36 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> index 1af2fa1591fd..fddb82897e5d 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> @@ -1073,7 +1073,9 @@ static inline struct amdgpu_device *amdgpu_ttm_adev(struct ttm_device *bdev)
>   
>   int amdgpu_device_init(struct amdgpu_device *adev,
>   		       uint32_t flags);
> -void amdgpu_device_fini(struct amdgpu_device *adev);
> +void amdgpu_device_fini_hw(struct amdgpu_device *adev);
> +void amdgpu_device_fini_sw(struct amdgpu_device *adev);
> +
>   int amdgpu_gpu_wait_for_idle(struct amdgpu_device *adev);
>   
>   void amdgpu_device_vram_access(struct amdgpu_device *adev, loff_t pos,
> @@ -1289,6 +1291,8 @@ void amdgpu_driver_lastclose_kms(struct drm_device *dev);
>   int amdgpu_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv);
>   void amdgpu_driver_postclose_kms(struct drm_device *dev,
>   				 struct drm_file *file_priv);
> +void amdgpu_driver_release_kms(struct drm_device *dev);
> +
>   int amdgpu_device_ip_suspend(struct amdgpu_device *adev);
>   int amdgpu_device_suspend(struct drm_device *dev, bool fbcon);
>   int amdgpu_device_resume(struct drm_device *dev, bool fbcon);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> index 6447cd6ca5a8..8d22b79fc1cd 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> @@ -3590,14 +3590,12 @@ int amdgpu_device_init(struct amdgpu_device *adev,
>    * Tear down the driver info (all asics).
>    * Called at driver shutdown.
>    */
> -void amdgpu_device_fini(struct amdgpu_device *adev)
> +void amdgpu_device_fini_hw(struct amdgpu_device *adev)
>   {
>   	dev_info(adev->dev, "amdgpu: finishing device.\n");
>   	flush_delayed_work(&adev->delayed_init_work);
>   	adev->shutdown = true;
>   
> -	kfree(adev->pci_state);
> -
>   	/* make sure IB test finished before entering exclusive mode
>   	 * to avoid preemption on IB test
>   	 * */
> @@ -3614,11 +3612,24 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
>   		else
>   			drm_atomic_helper_shutdown(adev_to_drm(adev));
>   	}
> -	amdgpu_fence_driver_fini(adev);
> +	amdgpu_fence_driver_fini_hw(adev);
> +
>   	if (adev->pm_sysfs_en)
>   		amdgpu_pm_sysfs_fini(adev);
> +	if (adev->ucode_sysfs_en)
> +		amdgpu_ucode_sysfs_fini(adev);
> +	sysfs_remove_files(&adev->dev->kobj, amdgpu_dev_attributes);
> +
> +
>   	amdgpu_fbdev_fini(adev);
> +
> +	amdgpu_irq_fini_hw(adev);
> +}
> +
> +void amdgpu_device_fini_sw(struct amdgpu_device *adev)
> +{
>   	amdgpu_device_ip_fini(adev);
> +	amdgpu_fence_driver_fini_sw(adev);
>   	release_firmware(adev->firmware.gpu_info_fw);
>   	adev->firmware.gpu_info_fw = NULL;
>   	adev->accel_working = false;
> @@ -3647,14 +3658,13 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
>   	adev->rmmio = NULL;
>   	amdgpu_device_doorbell_fini(adev);
>   
> -	if (adev->ucode_sysfs_en)
> -		amdgpu_ucode_sysfs_fini(adev);
> -
> -	sysfs_remove_files(&adev->dev->kobj, amdgpu_dev_attributes);
>   	if (IS_ENABLED(CONFIG_PERF_EVENTS))
>   		amdgpu_pmu_fini(adev);
>   	if (adev->mman.discovery_bin)
>   		amdgpu_discovery_fini(adev);
> +
> +	kfree(adev->pci_state);
> +
>   }
>   
>   
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> index 671ec1002230..54cb5ee2f563 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> @@ -1249,14 +1249,10 @@ amdgpu_pci_remove(struct pci_dev *pdev)
>   {
>   	struct drm_device *dev = pci_get_drvdata(pdev);
>   
> -#ifdef MODULE
> -	if (THIS_MODULE->state != MODULE_STATE_GOING)
> -#endif
> -		DRM_ERROR("Hotplug removal is not supported\n");
>   	drm_dev_unplug(dev);
>   	amdgpu_driver_unload_kms(dev);
> +
>   	pci_disable_device(pdev);
> -	pci_set_drvdata(pdev, NULL);
>   }
>   
>   static void
> @@ -1587,6 +1583,7 @@ static const struct drm_driver amdgpu_kms_driver = {
>   	.dumb_create = amdgpu_mode_dumb_create,
>   	.dumb_map_offset = amdgpu_mode_dumb_mmap,
>   	.fops = &amdgpu_driver_kms_fops,
> +	.release = &amdgpu_driver_release_kms,
>   
>   	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
>   	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
> index 8e0a5650d383..34d51e962799 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
> @@ -523,7 +523,7 @@ int amdgpu_fence_driver_init(struct amdgpu_device *adev)
>    *
>    * Tear down the fence driver for all possible rings (all asics).
>    */
> -void amdgpu_fence_driver_fini(struct amdgpu_device *adev)
> +void amdgpu_fence_driver_fini_hw(struct amdgpu_device *adev)
>   {
>   	unsigned i, j;
>   	int r;
> @@ -544,6 +544,19 @@ void amdgpu_fence_driver_fini(struct amdgpu_device *adev)
>   		if (!ring->no_scheduler)
>   			drm_sched_fini(&ring->sched);
>   		del_timer_sync(&ring->fence_drv.fallback_timer);
> +	}
> +}
> +
> +void amdgpu_fence_driver_fini_sw(struct amdgpu_device *adev)
> +{
> +	unsigned int i, j;
> +
> +	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
> +		struct amdgpu_ring *ring = adev->rings[i];
> +
> +		if (!ring || !ring->fence_drv.initialized)
> +			continue;
> +
>   		for (j = 0; j <= ring->fence_drv.num_fences_mask; ++j)
>   			dma_fence_put(ring->fence_drv.fences[j]);
>   		kfree(ring->fence_drv.fences);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
> index afbbec82a289..63e815c27585 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
> @@ -49,6 +49,7 @@
>   #include <drm/drm_irq.h>
>   #include <drm/drm_vblank.h>
>   #include <drm/amdgpu_drm.h>
> +#include <drm/drm_drv.h>
>   #include "amdgpu.h"
>   #include "amdgpu_ih.h"
>   #include "atom.h"
> @@ -313,6 +314,20 @@ int amdgpu_irq_init(struct amdgpu_device *adev)
>   	return 0;
>   }
>   
> +
> +void amdgpu_irq_fini_hw(struct amdgpu_device *adev)
> +{
> +	if (adev->irq.installed) {
> +		drm_irq_uninstall(&adev->ddev);
> +		adev->irq.installed = false;
> +		if (adev->irq.msi_enabled)
> +			pci_free_irq_vectors(adev->pdev);
> +
> +		if (!amdgpu_device_has_dc_support(adev))
> +			flush_work(&adev->hotplug_work);
> +	}
> +}
> +
>   /**
>    * amdgpu_irq_fini - shut down interrupt handling
>    *
> @@ -322,19 +337,10 @@ int amdgpu_irq_init(struct amdgpu_device *adev)
>    * functionality, shuts down vblank, hotplug and reset interrupt handling,
>    * turns off interrupts from all sources (all ASICs).
>    */
> -void amdgpu_irq_fini(struct amdgpu_device *adev)
> +void amdgpu_irq_fini_sw(struct amdgpu_device *adev)
>   {
>   	unsigned i, j;
>   
> -	if (adev->irq.installed) {
> -		drm_irq_uninstall(adev_to_drm(adev));
> -		adev->irq.installed = false;
> -		if (adev->irq.msi_enabled)
> -			pci_free_irq_vectors(adev->pdev);
> -		if (!amdgpu_device_has_dc_support(adev))
> -			flush_work(&adev->hotplug_work);
> -	}
> -
>   	for (i = 0; i < AMDGPU_IRQ_CLIENTID_MAX; ++i) {
>   		if (!adev->irq.client[i].sources)
>   			continue;
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h
> index ac527e5deae6..392a7324e2b1 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h
> @@ -104,7 +104,8 @@ void amdgpu_irq_disable_all(struct amdgpu_device *adev);
>   irqreturn_t amdgpu_irq_handler(int irq, void *arg);
>   
>   int amdgpu_irq_init(struct amdgpu_device *adev);
> -void amdgpu_irq_fini(struct amdgpu_device *adev);
> +void amdgpu_irq_fini_sw(struct amdgpu_device *adev);
> +void amdgpu_irq_fini_hw(struct amdgpu_device *adev);
>   int amdgpu_irq_add_id(struct amdgpu_device *adev,
>   		      unsigned client_id, unsigned src_id,
>   		      struct amdgpu_irq_src *source);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
> index 64beb3399604..1af3fba7bfd4 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
> @@ -29,6 +29,7 @@
>   #include "amdgpu.h"
>   #include <drm/drm_debugfs.h>
>   #include <drm/amdgpu_drm.h>
> +#include <drm/drm_drv.h>
>   #include "amdgpu_uvd.h"
>   #include "amdgpu_vce.h"
>   #include "atom.h"
> @@ -93,7 +94,7 @@ void amdgpu_driver_unload_kms(struct drm_device *dev)
>   	}
>   
>   	amdgpu_acpi_fini(adev);
> -	amdgpu_device_fini(adev);
> +	amdgpu_device_fini_hw(adev);
>   }
>   
>   void amdgpu_register_gpu_instance(struct amdgpu_device *adev)
> @@ -1151,6 +1152,15 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev,
>   	pm_runtime_put_autosuspend(dev->dev);
>   }
>   
> +
> +void amdgpu_driver_release_kms(struct drm_device *dev)
> +{
> +	struct amdgpu_device *adev = drm_to_adev(dev);
> +
> +	amdgpu_device_fini_sw(adev);
> +	pci_set_drvdata(adev->pdev, NULL);
> +}
> +
>   /*
>    * VBlank related functions.
>    */
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
> index 1fb2a91ad30a..c0a16eac4923 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
> @@ -2142,6 +2142,7 @@ int amdgpu_ras_pre_fini(struct amdgpu_device *adev)
>   	if (!con)
>   		return 0;
>   
> +
>   	/* Need disable ras on all IPs here before ip [hw/sw]fini */
>   	amdgpu_ras_disable_all_features(adev, 0);
>   	amdgpu_ras_recovery_fini(adev);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
> index 56acec1075ac..0f195f7bf797 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
> @@ -107,7 +107,8 @@ struct amdgpu_fence_driver {
>   };
>   
>   int amdgpu_fence_driver_init(struct amdgpu_device *adev);
> -void amdgpu_fence_driver_fini(struct amdgpu_device *adev);
> +void amdgpu_fence_driver_fini_hw(struct amdgpu_device *adev);
> +void amdgpu_fence_driver_fini_sw(struct amdgpu_device *adev);
>   void amdgpu_fence_driver_force_completion(struct amdgpu_ring *ring);
>   
>   int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
> diff --git a/drivers/gpu/drm/amd/amdgpu/cik_ih.c b/drivers/gpu/drm/amd/amdgpu/cik_ih.c
> index d3745711d55f..183d44a6583c 100644
> --- a/drivers/gpu/drm/amd/amdgpu/cik_ih.c
> +++ b/drivers/gpu/drm/amd/amdgpu/cik_ih.c
> @@ -309,7 +309,7 @@ static int cik_ih_sw_fini(void *handle)
>   {
>   	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
>   
> -	amdgpu_irq_fini(adev);
> +	amdgpu_irq_fini_sw(adev);
>   	amdgpu_ih_ring_fini(adev, &adev->irq.ih);
>   	amdgpu_irq_remove_domain(adev);
>   
> diff --git a/drivers/gpu/drm/amd/amdgpu/cz_ih.c b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
> index 307c01301c87..d32743949003 100644
> --- a/drivers/gpu/drm/amd/amdgpu/cz_ih.c
> +++ b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
> @@ -301,7 +301,7 @@ static int cz_ih_sw_fini(void *handle)
>   {
>   	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
>   
> -	amdgpu_irq_fini(adev);
> +	amdgpu_irq_fini_sw(adev);
>   	amdgpu_ih_ring_fini(adev, &adev->irq.ih);
>   	amdgpu_irq_remove_domain(adev);
>   
> diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
> index cc957471f31e..da96c6013477 100644
> --- a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
> +++ b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
> @@ -300,7 +300,7 @@ static int iceland_ih_sw_fini(void *handle)
>   {
>   	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
>   
> -	amdgpu_irq_fini(adev);
> +	amdgpu_irq_fini_sw(adev);
>   	amdgpu_ih_ring_fini(adev, &adev->irq.ih);
>   	amdgpu_irq_remove_domain(adev);
>   
> diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
> index f4e4040bbd25..5eea4550b856 100644
> --- a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
> +++ b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
> @@ -569,7 +569,7 @@ static int navi10_ih_sw_fini(void *handle)
>   {
>   	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
>   
> -	amdgpu_irq_fini(adev);
> +	amdgpu_irq_fini_sw(adev);
>   	amdgpu_ih_ring_fini(adev, &adev->irq.ih_soft);
>   	amdgpu_ih_ring_fini(adev, &adev->irq.ih2);
>   	amdgpu_ih_ring_fini(adev, &adev->irq.ih1);
> diff --git a/drivers/gpu/drm/amd/amdgpu/si_ih.c b/drivers/gpu/drm/amd/amdgpu/si_ih.c
> index 51880f6ef634..751307f3252c 100644
> --- a/drivers/gpu/drm/amd/amdgpu/si_ih.c
> +++ b/drivers/gpu/drm/amd/amdgpu/si_ih.c
> @@ -175,7 +175,7 @@ static int si_ih_sw_fini(void *handle)
>   {
>   	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
>   
> -	amdgpu_irq_fini(adev);
> +	amdgpu_irq_fini_sw(adev);
>   	amdgpu_ih_ring_fini(adev, &adev->irq.ih);
>   
>   	return 0;
> diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
> index 249fcbee7871..973d80ec7f6c 100644
> --- a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
> +++ b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
> @@ -312,7 +312,7 @@ static int tonga_ih_sw_fini(void *handle)
>   {
>   	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
>   
> -	amdgpu_irq_fini(adev);
> +	amdgpu_irq_fini_sw(adev);
>   	amdgpu_ih_ring_fini(adev, &adev->irq.ih);
>   	amdgpu_irq_remove_domain(adev);
>   
> diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
> index 88626d83e07b..2d0094c276ca 100644
> --- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
> +++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
> @@ -523,7 +523,7 @@ static int vega10_ih_sw_fini(void *handle)
>   {
>   	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
>   
> -	amdgpu_irq_fini(adev);
> +	amdgpu_irq_fini_sw(adev);
>   	amdgpu_ih_ring_fini(adev, &adev->irq.ih_soft);
>   	amdgpu_ih_ring_fini(adev, &adev->irq.ih2);
>   	amdgpu_ih_ring_fini(adev, &adev->irq.ih1);
> diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
> index 5a3c867d5881..9059b21b079f 100644
> --- a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
> +++ b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
> @@ -558,7 +558,7 @@ static int vega20_ih_sw_fini(void *handle)
>   {
>   	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
>   
> -	amdgpu_irq_fini(adev);
> +	amdgpu_irq_fini_sw(adev);
>   	amdgpu_ih_ring_fini(adev, &adev->irq.ih_soft);
>   	amdgpu_ih_ring_fini(adev, &adev->irq.ih2);
>   	amdgpu_ih_ring_fini(adev, &adev->irq.ih1);
Alex Deucher April 30, 2021, 3:10 a.m. UTC | #2
On Thu, Apr 29, 2021 at 3:04 AM Christian König
<ckoenig.leichtzumerken@gmail.com> wrote:
>
>
>
> Am 28.04.21 um 17:11 schrieb Andrey Grodzovsky:
> > Some of the stuff in amdgpu_device_fini such as HW interrupts
> > disable and pending fences finilization must be done right away on
> > pci_remove while most of the stuff which relates to finilizing and
> > releasing driver data structures can be kept until
> > drm_driver.release hook is called, i.e. when the last device
> > reference is dropped.
> >
> > v4: Change functions prefix early->hw and late->sw
> >
> > Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
>
> Acked-by: Christian König <christian.koenig@amd.com>
>
> But Alex should acknowledge this as well since it is general driver design.

Looks good to me as well.
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>

>
> Christian.
>
> > ---
> >   drivers/gpu/drm/amd/amdgpu/amdgpu.h        |  6 ++++-
> >   drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 26 +++++++++++++++-------
> >   drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c    |  7 ++----
> >   drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c  | 15 ++++++++++++-
> >   drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c    | 26 +++++++++++++---------
> >   drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h    |  3 ++-
> >   drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c    | 12 +++++++++-
> >   drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c    |  1 +
> >   drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h   |  3 ++-
> >   drivers/gpu/drm/amd/amdgpu/cik_ih.c        |  2 +-
> >   drivers/gpu/drm/amd/amdgpu/cz_ih.c         |  2 +-
> >   drivers/gpu/drm/amd/amdgpu/iceland_ih.c    |  2 +-
> >   drivers/gpu/drm/amd/amdgpu/navi10_ih.c     |  2 +-
> >   drivers/gpu/drm/amd/amdgpu/si_ih.c         |  2 +-
> >   drivers/gpu/drm/amd/amdgpu/tonga_ih.c      |  2 +-
> >   drivers/gpu/drm/amd/amdgpu/vega10_ih.c     |  2 +-
> >   drivers/gpu/drm/amd/amdgpu/vega20_ih.c     |  2 +-
> >   17 files changed, 79 insertions(+), 36 deletions(-)
> >
> > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> > index 1af2fa1591fd..fddb82897e5d 100644
> > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> > @@ -1073,7 +1073,9 @@ static inline struct amdgpu_device *amdgpu_ttm_adev(struct ttm_device *bdev)
> >
> >   int amdgpu_device_init(struct amdgpu_device *adev,
> >                      uint32_t flags);
> > -void amdgpu_device_fini(struct amdgpu_device *adev);
> > +void amdgpu_device_fini_hw(struct amdgpu_device *adev);
> > +void amdgpu_device_fini_sw(struct amdgpu_device *adev);
> > +
> >   int amdgpu_gpu_wait_for_idle(struct amdgpu_device *adev);
> >
> >   void amdgpu_device_vram_access(struct amdgpu_device *adev, loff_t pos,
> > @@ -1289,6 +1291,8 @@ void amdgpu_driver_lastclose_kms(struct drm_device *dev);
> >   int amdgpu_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv);
> >   void amdgpu_driver_postclose_kms(struct drm_device *dev,
> >                                struct drm_file *file_priv);
> > +void amdgpu_driver_release_kms(struct drm_device *dev);
> > +
> >   int amdgpu_device_ip_suspend(struct amdgpu_device *adev);
> >   int amdgpu_device_suspend(struct drm_device *dev, bool fbcon);
> >   int amdgpu_device_resume(struct drm_device *dev, bool fbcon);
> > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> > index 6447cd6ca5a8..8d22b79fc1cd 100644
> > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> > @@ -3590,14 +3590,12 @@ int amdgpu_device_init(struct amdgpu_device *adev,
> >    * Tear down the driver info (all asics).
> >    * Called at driver shutdown.
> >    */
> > -void amdgpu_device_fini(struct amdgpu_device *adev)
> > +void amdgpu_device_fini_hw(struct amdgpu_device *adev)
> >   {
> >       dev_info(adev->dev, "amdgpu: finishing device.\n");
> >       flush_delayed_work(&adev->delayed_init_work);
> >       adev->shutdown = true;
> >
> > -     kfree(adev->pci_state);
> > -
> >       /* make sure IB test finished before entering exclusive mode
> >        * to avoid preemption on IB test
> >        * */
> > @@ -3614,11 +3612,24 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
> >               else
> >                       drm_atomic_helper_shutdown(adev_to_drm(adev));
> >       }
> > -     amdgpu_fence_driver_fini(adev);
> > +     amdgpu_fence_driver_fini_hw(adev);
> > +
> >       if (adev->pm_sysfs_en)
> >               amdgpu_pm_sysfs_fini(adev);
> > +     if (adev->ucode_sysfs_en)
> > +             amdgpu_ucode_sysfs_fini(adev);
> > +     sysfs_remove_files(&adev->dev->kobj, amdgpu_dev_attributes);
> > +
> > +
> >       amdgpu_fbdev_fini(adev);
> > +
> > +     amdgpu_irq_fini_hw(adev);
> > +}
> > +
> > +void amdgpu_device_fini_sw(struct amdgpu_device *adev)
> > +{
> >       amdgpu_device_ip_fini(adev);
> > +     amdgpu_fence_driver_fini_sw(adev);
> >       release_firmware(adev->firmware.gpu_info_fw);
> >       adev->firmware.gpu_info_fw = NULL;
> >       adev->accel_working = false;
> > @@ -3647,14 +3658,13 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
> >       adev->rmmio = NULL;
> >       amdgpu_device_doorbell_fini(adev);
> >
> > -     if (adev->ucode_sysfs_en)
> > -             amdgpu_ucode_sysfs_fini(adev);
> > -
> > -     sysfs_remove_files(&adev->dev->kobj, amdgpu_dev_attributes);
> >       if (IS_ENABLED(CONFIG_PERF_EVENTS))
> >               amdgpu_pmu_fini(adev);
> >       if (adev->mman.discovery_bin)
> >               amdgpu_discovery_fini(adev);
> > +
> > +     kfree(adev->pci_state);
> > +
> >   }
> >
> >
> > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> > index 671ec1002230..54cb5ee2f563 100644
> > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> > @@ -1249,14 +1249,10 @@ amdgpu_pci_remove(struct pci_dev *pdev)
> >   {
> >       struct drm_device *dev = pci_get_drvdata(pdev);
> >
> > -#ifdef MODULE
> > -     if (THIS_MODULE->state != MODULE_STATE_GOING)
> > -#endif
> > -             DRM_ERROR("Hotplug removal is not supported\n");
> >       drm_dev_unplug(dev);
> >       amdgpu_driver_unload_kms(dev);
> > +
> >       pci_disable_device(pdev);
> > -     pci_set_drvdata(pdev, NULL);
> >   }
> >
> >   static void
> > @@ -1587,6 +1583,7 @@ static const struct drm_driver amdgpu_kms_driver = {
> >       .dumb_create = amdgpu_mode_dumb_create,
> >       .dumb_map_offset = amdgpu_mode_dumb_mmap,
> >       .fops = &amdgpu_driver_kms_fops,
> > +     .release = &amdgpu_driver_release_kms,
> >
> >       .prime_handle_to_fd = drm_gem_prime_handle_to_fd,
> >       .prime_fd_to_handle = drm_gem_prime_fd_to_handle,
> > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
> > index 8e0a5650d383..34d51e962799 100644
> > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
> > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
> > @@ -523,7 +523,7 @@ int amdgpu_fence_driver_init(struct amdgpu_device *adev)
> >    *
> >    * Tear down the fence driver for all possible rings (all asics).
> >    */
> > -void amdgpu_fence_driver_fini(struct amdgpu_device *adev)
> > +void amdgpu_fence_driver_fini_hw(struct amdgpu_device *adev)
> >   {
> >       unsigned i, j;
> >       int r;
> > @@ -544,6 +544,19 @@ void amdgpu_fence_driver_fini(struct amdgpu_device *adev)
> >               if (!ring->no_scheduler)
> >                       drm_sched_fini(&ring->sched);
> >               del_timer_sync(&ring->fence_drv.fallback_timer);
> > +     }
> > +}
> > +
> > +void amdgpu_fence_driver_fini_sw(struct amdgpu_device *adev)
> > +{
> > +     unsigned int i, j;
> > +
> > +     for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
> > +             struct amdgpu_ring *ring = adev->rings[i];
> > +
> > +             if (!ring || !ring->fence_drv.initialized)
> > +                     continue;
> > +
> >               for (j = 0; j <= ring->fence_drv.num_fences_mask; ++j)
> >                       dma_fence_put(ring->fence_drv.fences[j]);
> >               kfree(ring->fence_drv.fences);
> > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
> > index afbbec82a289..63e815c27585 100644
> > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
> > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
> > @@ -49,6 +49,7 @@
> >   #include <drm/drm_irq.h>
> >   #include <drm/drm_vblank.h>
> >   #include <drm/amdgpu_drm.h>
> > +#include <drm/drm_drv.h>
> >   #include "amdgpu.h"
> >   #include "amdgpu_ih.h"
> >   #include "atom.h"
> > @@ -313,6 +314,20 @@ int amdgpu_irq_init(struct amdgpu_device *adev)
> >       return 0;
> >   }
> >
> > +
> > +void amdgpu_irq_fini_hw(struct amdgpu_device *adev)
> > +{
> > +     if (adev->irq.installed) {
> > +             drm_irq_uninstall(&adev->ddev);
> > +             adev->irq.installed = false;
> > +             if (adev->irq.msi_enabled)
> > +                     pci_free_irq_vectors(adev->pdev);
> > +
> > +             if (!amdgpu_device_has_dc_support(adev))
> > +                     flush_work(&adev->hotplug_work);
> > +     }
> > +}
> > +
> >   /**
> >    * amdgpu_irq_fini - shut down interrupt handling
> >    *
> > @@ -322,19 +337,10 @@ int amdgpu_irq_init(struct amdgpu_device *adev)
> >    * functionality, shuts down vblank, hotplug and reset interrupt handling,
> >    * turns off interrupts from all sources (all ASICs).
> >    */
> > -void amdgpu_irq_fini(struct amdgpu_device *adev)
> > +void amdgpu_irq_fini_sw(struct amdgpu_device *adev)
> >   {
> >       unsigned i, j;
> >
> > -     if (adev->irq.installed) {
> > -             drm_irq_uninstall(adev_to_drm(adev));
> > -             adev->irq.installed = false;
> > -             if (adev->irq.msi_enabled)
> > -                     pci_free_irq_vectors(adev->pdev);
> > -             if (!amdgpu_device_has_dc_support(adev))
> > -                     flush_work(&adev->hotplug_work);
> > -     }
> > -
> >       for (i = 0; i < AMDGPU_IRQ_CLIENTID_MAX; ++i) {
> >               if (!adev->irq.client[i].sources)
> >                       continue;
> > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h
> > index ac527e5deae6..392a7324e2b1 100644
> > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h
> > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h
> > @@ -104,7 +104,8 @@ void amdgpu_irq_disable_all(struct amdgpu_device *adev);
> >   irqreturn_t amdgpu_irq_handler(int irq, void *arg);
> >
> >   int amdgpu_irq_init(struct amdgpu_device *adev);
> > -void amdgpu_irq_fini(struct amdgpu_device *adev);
> > +void amdgpu_irq_fini_sw(struct amdgpu_device *adev);
> > +void amdgpu_irq_fini_hw(struct amdgpu_device *adev);
> >   int amdgpu_irq_add_id(struct amdgpu_device *adev,
> >                     unsigned client_id, unsigned src_id,
> >                     struct amdgpu_irq_src *source);
> > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
> > index 64beb3399604..1af3fba7bfd4 100644
> > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
> > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
> > @@ -29,6 +29,7 @@
> >   #include "amdgpu.h"
> >   #include <drm/drm_debugfs.h>
> >   #include <drm/amdgpu_drm.h>
> > +#include <drm/drm_drv.h>
> >   #include "amdgpu_uvd.h"
> >   #include "amdgpu_vce.h"
> >   #include "atom.h"
> > @@ -93,7 +94,7 @@ void amdgpu_driver_unload_kms(struct drm_device *dev)
> >       }
> >
> >       amdgpu_acpi_fini(adev);
> > -     amdgpu_device_fini(adev);
> > +     amdgpu_device_fini_hw(adev);
> >   }
> >
> >   void amdgpu_register_gpu_instance(struct amdgpu_device *adev)
> > @@ -1151,6 +1152,15 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev,
> >       pm_runtime_put_autosuspend(dev->dev);
> >   }
> >
> > +
> > +void amdgpu_driver_release_kms(struct drm_device *dev)
> > +{
> > +     struct amdgpu_device *adev = drm_to_adev(dev);
> > +
> > +     amdgpu_device_fini_sw(adev);
> > +     pci_set_drvdata(adev->pdev, NULL);
> > +}
> > +
> >   /*
> >    * VBlank related functions.
> >    */
> > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
> > index 1fb2a91ad30a..c0a16eac4923 100644
> > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
> > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
> > @@ -2142,6 +2142,7 @@ int amdgpu_ras_pre_fini(struct amdgpu_device *adev)
> >       if (!con)
> >               return 0;
> >
> > +
> >       /* Need disable ras on all IPs here before ip [hw/sw]fini */
> >       amdgpu_ras_disable_all_features(adev, 0);
> >       amdgpu_ras_recovery_fini(adev);
> > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
> > index 56acec1075ac..0f195f7bf797 100644
> > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
> > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
> > @@ -107,7 +107,8 @@ struct amdgpu_fence_driver {
> >   };
> >
> >   int amdgpu_fence_driver_init(struct amdgpu_device *adev);
> > -void amdgpu_fence_driver_fini(struct amdgpu_device *adev);
> > +void amdgpu_fence_driver_fini_hw(struct amdgpu_device *adev);
> > +void amdgpu_fence_driver_fini_sw(struct amdgpu_device *adev);
> >   void amdgpu_fence_driver_force_completion(struct amdgpu_ring *ring);
> >
> >   int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
> > diff --git a/drivers/gpu/drm/amd/amdgpu/cik_ih.c b/drivers/gpu/drm/amd/amdgpu/cik_ih.c
> > index d3745711d55f..183d44a6583c 100644
> > --- a/drivers/gpu/drm/amd/amdgpu/cik_ih.c
> > +++ b/drivers/gpu/drm/amd/amdgpu/cik_ih.c
> > @@ -309,7 +309,7 @@ static int cik_ih_sw_fini(void *handle)
> >   {
> >       struct amdgpu_device *adev = (struct amdgpu_device *)handle;
> >
> > -     amdgpu_irq_fini(adev);
> > +     amdgpu_irq_fini_sw(adev);
> >       amdgpu_ih_ring_fini(adev, &adev->irq.ih);
> >       amdgpu_irq_remove_domain(adev);
> >
> > diff --git a/drivers/gpu/drm/amd/amdgpu/cz_ih.c b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
> > index 307c01301c87..d32743949003 100644
> > --- a/drivers/gpu/drm/amd/amdgpu/cz_ih.c
> > +++ b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
> > @@ -301,7 +301,7 @@ static int cz_ih_sw_fini(void *handle)
> >   {
> >       struct amdgpu_device *adev = (struct amdgpu_device *)handle;
> >
> > -     amdgpu_irq_fini(adev);
> > +     amdgpu_irq_fini_sw(adev);
> >       amdgpu_ih_ring_fini(adev, &adev->irq.ih);
> >       amdgpu_irq_remove_domain(adev);
> >
> > diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
> > index cc957471f31e..da96c6013477 100644
> > --- a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
> > +++ b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
> > @@ -300,7 +300,7 @@ static int iceland_ih_sw_fini(void *handle)
> >   {
> >       struct amdgpu_device *adev = (struct amdgpu_device *)handle;
> >
> > -     amdgpu_irq_fini(adev);
> > +     amdgpu_irq_fini_sw(adev);
> >       amdgpu_ih_ring_fini(adev, &adev->irq.ih);
> >       amdgpu_irq_remove_domain(adev);
> >
> > diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
> > index f4e4040bbd25..5eea4550b856 100644
> > --- a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
> > +++ b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
> > @@ -569,7 +569,7 @@ static int navi10_ih_sw_fini(void *handle)
> >   {
> >       struct amdgpu_device *adev = (struct amdgpu_device *)handle;
> >
> > -     amdgpu_irq_fini(adev);
> > +     amdgpu_irq_fini_sw(adev);
> >       amdgpu_ih_ring_fini(adev, &adev->irq.ih_soft);
> >       amdgpu_ih_ring_fini(adev, &adev->irq.ih2);
> >       amdgpu_ih_ring_fini(adev, &adev->irq.ih1);
> > diff --git a/drivers/gpu/drm/amd/amdgpu/si_ih.c b/drivers/gpu/drm/amd/amdgpu/si_ih.c
> > index 51880f6ef634..751307f3252c 100644
> > --- a/drivers/gpu/drm/amd/amdgpu/si_ih.c
> > +++ b/drivers/gpu/drm/amd/amdgpu/si_ih.c
> > @@ -175,7 +175,7 @@ static int si_ih_sw_fini(void *handle)
> >   {
> >       struct amdgpu_device *adev = (struct amdgpu_device *)handle;
> >
> > -     amdgpu_irq_fini(adev);
> > +     amdgpu_irq_fini_sw(adev);
> >       amdgpu_ih_ring_fini(adev, &adev->irq.ih);
> >
> >       return 0;
> > diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
> > index 249fcbee7871..973d80ec7f6c 100644
> > --- a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
> > +++ b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
> > @@ -312,7 +312,7 @@ static int tonga_ih_sw_fini(void *handle)
> >   {
> >       struct amdgpu_device *adev = (struct amdgpu_device *)handle;
> >
> > -     amdgpu_irq_fini(adev);
> > +     amdgpu_irq_fini_sw(adev);
> >       amdgpu_ih_ring_fini(adev, &adev->irq.ih);
> >       amdgpu_irq_remove_domain(adev);
> >
> > diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
> > index 88626d83e07b..2d0094c276ca 100644
> > --- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
> > +++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
> > @@ -523,7 +523,7 @@ static int vega10_ih_sw_fini(void *handle)
> >   {
> >       struct amdgpu_device *adev = (struct amdgpu_device *)handle;
> >
> > -     amdgpu_irq_fini(adev);
> > +     amdgpu_irq_fini_sw(adev);
> >       amdgpu_ih_ring_fini(adev, &adev->irq.ih_soft);
> >       amdgpu_ih_ring_fini(adev, &adev->irq.ih2);
> >       amdgpu_ih_ring_fini(adev, &adev->irq.ih1);
> > diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
> > index 5a3c867d5881..9059b21b079f 100644
> > --- a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
> > +++ b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
> > @@ -558,7 +558,7 @@ static int vega20_ih_sw_fini(void *handle)
> >   {
> >       struct amdgpu_device *adev = (struct amdgpu_device *)handle;
> >
> > -     amdgpu_irq_fini(adev);
> > +     amdgpu_irq_fini_sw(adev);
> >       amdgpu_ih_ring_fini(adev, &adev->irq.ih_soft);
> >       amdgpu_ih_ring_fini(adev, &adev->irq.ih2);
> >       amdgpu_ih_ring_fini(adev, &adev->irq.ih1);
>
> _______________________________________________
> amd-gfx mailing list
> amd-gfx@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/amd-gfx
Lazar, Lijo April 30, 2021, 5:19 a.m. UTC | #3
[AMD Official Use Only - Internal Distribution Only]

sysfs cleanup is a sw cleanup to me but done inside hw fini. sw/hw separation is not strictly followed, or name it like stage1/stage2 fini.

Thanks,
Lijo
Andrey Grodzovsky April 30, 2021, 5:39 a.m. UTC | #4
On 2021-04-30 1:19 a.m., Lazar, Lijo wrote:
> [AMD Official Use Only - Internal Distribution Only]
> 
> 
> sysfs cleanup is a sw cleanup to me but done inside hw fini. sw/hw 
> separation is not strictly followed, or name it like stage1/stage2 fini.

The thing is that it was called early_fini and late_fini before and then
according to Daniel's requirest it was changed to fini_hw and fini_sw

Andrey

> 
> Thanks,
> Lijo
> ------------------------------------------------------------------------
> *From:* amd-gfx <amd-gfx-bounces@lists.freedesktop.org> on behalf of 
> Andrey Grodzovsky <andrey.grodzovsky@amd.com>
> *Sent:* Wednesday, April 28, 2021 8:41:43 PM
> *To:* dri-devel@lists.freedesktop.org <dri-devel@lists.freedesktop.org>; 
> amd-gfx@lists.freedesktop.org <amd-gfx@lists.freedesktop.org>; 
> linux-pci@vger.kernel.org <linux-pci@vger.kernel.org>; 
> ckoenig.leichtzumerken@gmail.com <ckoenig.leichtzumerken@gmail.com>; 
> daniel.vetter@ffwll.ch <daniel.vetter@ffwll.ch>; Wentland, Harry 
> <Harry.Wentland@amd.com>
> *Cc:* Grodzovsky, Andrey <Andrey.Grodzovsky@amd.com>; 
> gregkh@linuxfoundation.org <gregkh@linuxfoundation.org>; Kuehling, Felix 
> <Felix.Kuehling@amd.com>; ppaalanen@gmail.com <ppaalanen@gmail.com>; 
> helgaas@kernel.org <helgaas@kernel.org>; Deucher, Alexander 
> <Alexander.Deucher@amd.com>
> *Subject:* [PATCH v5 03/27] drm/amdgpu: Split amdgpu_device_fini into 
> early and late
> Some of the stuff in amdgpu_device_fini such as HW interrupts
> disable and pending fences finilization must be done right away on
> pci_remove while most of the stuff which relates to finilizing and
> releasing driver data structures can be kept until
> drm_driver.release hook is called, i.e. when the last device
> reference is dropped.
> 
> v4: Change functions prefix early->hw and late->sw
> 
> Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu.h        |  6 ++++-
>   drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 26 +++++++++++++++-------
>   drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c    |  7 ++----
>   drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c  | 15 ++++++++++++-
>   drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c    | 26 +++++++++++++---------
>   drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h    |  3 ++-
>   drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c    | 12 +++++++++-
>   drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c    |  1 +
>   drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h   |  3 ++-
>   drivers/gpu/drm/amd/amdgpu/cik_ih.c        |  2 +-
>   drivers/gpu/drm/amd/amdgpu/cz_ih.c         |  2 +-
>   drivers/gpu/drm/amd/amdgpu/iceland_ih.c    |  2 +-
>   drivers/gpu/drm/amd/amdgpu/navi10_ih.c     |  2 +-
>   drivers/gpu/drm/amd/amdgpu/si_ih.c         |  2 +-
>   drivers/gpu/drm/amd/amdgpu/tonga_ih.c      |  2 +-
>   drivers/gpu/drm/amd/amdgpu/vega10_ih.c     |  2 +-
>   drivers/gpu/drm/amd/amdgpu/vega20_ih.c     |  2 +-
>   17 files changed, 79 insertions(+), 36 deletions(-)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h 
> b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> index 1af2fa1591fd..fddb82897e5d 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> @@ -1073,7 +1073,9 @@ static inline struct amdgpu_device 
> *amdgpu_ttm_adev(struct ttm_device *bdev)
> 
>   int amdgpu_device_init(struct amdgpu_device *adev,
>                          uint32_t flags);
> -void amdgpu_device_fini(struct amdgpu_device *adev);
> +void amdgpu_device_fini_hw(struct amdgpu_device *adev);
> +void amdgpu_device_fini_sw(struct amdgpu_device *adev);
> +
>   int amdgpu_gpu_wait_for_idle(struct amdgpu_device *adev);
> 
>   void amdgpu_device_vram_access(struct amdgpu_device *adev, loff_t pos,
> @@ -1289,6 +1291,8 @@ void amdgpu_driver_lastclose_kms(struct drm_device 
> *dev);
>   int amdgpu_driver_open_kms(struct drm_device *dev, struct drm_file 
> *file_priv);
>   void amdgpu_driver_postclose_kms(struct drm_device *dev,
>                                    struct drm_file *file_priv);
> +void amdgpu_driver_release_kms(struct drm_device *dev);
> +
>   int amdgpu_device_ip_suspend(struct amdgpu_device *adev);
>   int amdgpu_device_suspend(struct drm_device *dev, bool fbcon);
>   int amdgpu_device_resume(struct drm_device *dev, bool fbcon);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c 
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> index 6447cd6ca5a8..8d22b79fc1cd 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> @@ -3590,14 +3590,12 @@ int amdgpu_device_init(struct amdgpu_device *adev,
>    * Tear down the driver info (all asics).
>    * Called at driver shutdown.
>    */
> -void amdgpu_device_fini(struct amdgpu_device *adev)
> +void amdgpu_device_fini_hw(struct amdgpu_device *adev)
>   {
>           dev_info(adev->dev, "amdgpu: finishing device.\n");
>           flush_delayed_work(&adev->delayed_init_work);
>           adev->shutdown = true;
> 
> -       kfree(adev->pci_state);
> -
>           /* make sure IB test finished before entering exclusive mode
>            * to avoid preemption on IB test
>            * */
> @@ -3614,11 +3612,24 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
>                   else
>                           drm_atomic_helper_shutdown(adev_to_drm(adev));
>           }
> -       amdgpu_fence_driver_fini(adev);
> +       amdgpu_fence_driver_fini_hw(adev);
> +
>           if (adev->pm_sysfs_en)
>                   amdgpu_pm_sysfs_fini(adev);
> +       if (adev->ucode_sysfs_en)
> +               amdgpu_ucode_sysfs_fini(adev);
> +       sysfs_remove_files(&adev->dev->kobj, amdgpu_dev_attributes);
> +
> +
>           amdgpu_fbdev_fini(adev);
> +
> +       amdgpu_irq_fini_hw(adev);
> +}
> +
> +void amdgpu_device_fini_sw(struct amdgpu_device *adev)
> +{
>           amdgpu_device_ip_fini(adev);
> +       amdgpu_fence_driver_fini_sw(adev);
>           release_firmware(adev->firmware.gpu_info_fw);
>           adev->firmware.gpu_info_fw = NULL;
>           adev->accel_working = false;
> @@ -3647,14 +3658,13 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
>           adev->rmmio = NULL;
>           amdgpu_device_doorbell_fini(adev);
> 
> -       if (adev->ucode_sysfs_en)
> -               amdgpu_ucode_sysfs_fini(adev);
> -
> -       sysfs_remove_files(&adev->dev->kobj, amdgpu_dev_attributes);
>           if (IS_ENABLED(CONFIG_PERF_EVENTS))
>                   amdgpu_pmu_fini(adev);
>           if (adev->mman.discovery_bin)
>                   amdgpu_discovery_fini(adev);
> +
> +       kfree(adev->pci_state);
> +
>   }
> 
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c 
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> index 671ec1002230..54cb5ee2f563 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> @@ -1249,14 +1249,10 @@ amdgpu_pci_remove(struct pci_dev *pdev)
>   {
>           struct drm_device *dev = pci_get_drvdata(pdev);
> 
> -#ifdef MODULE
> -       if (THIS_MODULE->state != MODULE_STATE_GOING)
> -#endif
> -               DRM_ERROR("Hotplug removal is not supported\n");
>           drm_dev_unplug(dev);
>           amdgpu_driver_unload_kms(dev);
> +
>           pci_disable_device(pdev);
> -       pci_set_drvdata(pdev, NULL);
>   }
> 
>   static void
> @@ -1587,6 +1583,7 @@ static const struct drm_driver amdgpu_kms_driver = {
>           .dumb_create = amdgpu_mode_dumb_create,
>           .dumb_map_offset = amdgpu_mode_dumb_mmap,
>           .fops = &amdgpu_driver_kms_fops,
> +       .release = &amdgpu_driver_release_kms,
> 
>           .prime_handle_to_fd = drm_gem_prime_handle_to_fd,
>           .prime_fd_to_handle = drm_gem_prime_fd_to_handle,
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c 
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
> index 8e0a5650d383..34d51e962799 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
> @@ -523,7 +523,7 @@ int amdgpu_fence_driver_init(struct amdgpu_device *adev)
>    *
>    * Tear down the fence driver for all possible rings (all asics).
>    */
> -void amdgpu_fence_driver_fini(struct amdgpu_device *adev)
> +void amdgpu_fence_driver_fini_hw(struct amdgpu_device *adev)
>   {
>           unsigned i, j;
>           int r;
> @@ -544,6 +544,19 @@ void amdgpu_fence_driver_fini(struct amdgpu_device 
> *adev)
>                   if (!ring->no_scheduler)
>                           drm_sched_fini(&ring->sched);
>                   del_timer_sync(&ring->fence_drv.fallback_timer);
> +       }
> +}
> +
> +void amdgpu_fence_driver_fini_sw(struct amdgpu_device *adev)
> +{
> +       unsigned int i, j;
> +
> +       for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
> +               struct amdgpu_ring *ring = adev->rings[i];
> +
> +               if (!ring || !ring->fence_drv.initialized)
> +                       continue;
> +
>                   for (j = 0; j <= ring->fence_drv.num_fences_mask; ++j)
>                           dma_fence_put(ring->fence_drv.fences[j]);
>                   kfree(ring->fence_drv.fences);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c 
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
> index afbbec82a289..63e815c27585 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
> @@ -49,6 +49,7 @@
>   #include <drm/drm_irq.h>
>   #include <drm/drm_vblank.h>
>   #include <drm/amdgpu_drm.h>
> +#include <drm/drm_drv.h>
>   #include "amdgpu.h"
>   #include "amdgpu_ih.h"
>   #include "atom.h"
> @@ -313,6 +314,20 @@ int amdgpu_irq_init(struct amdgpu_device *adev)
>           return 0;
>   }
> 
> +
> +void amdgpu_irq_fini_hw(struct amdgpu_device *adev)
> +{
> +       if (adev->irq.installed) {
> +               drm_irq_uninstall(&adev->ddev);
> +               adev->irq.installed = false;
> +               if (adev->irq.msi_enabled)
> +                       pci_free_irq_vectors(adev->pdev);
> +
> +               if (!amdgpu_device_has_dc_support(adev))
> +                       flush_work(&adev->hotplug_work);
> +       }
> +}
> +
>   /**
>    * amdgpu_irq_fini - shut down interrupt handling
>    *
> @@ -322,19 +337,10 @@ int amdgpu_irq_init(struct amdgpu_device *adev)
>    * functionality, shuts down vblank, hotplug and reset interrupt handling,
>    * turns off interrupts from all sources (all ASICs).
>    */
> -void amdgpu_irq_fini(struct amdgpu_device *adev)
> +void amdgpu_irq_fini_sw(struct amdgpu_device *adev)
>   {
>           unsigned i, j;
> 
> -       if (adev->irq.installed) {
> -               drm_irq_uninstall(adev_to_drm(adev));
> -               adev->irq.installed = false;
> -               if (adev->irq.msi_enabled)
> -                       pci_free_irq_vectors(adev->pdev);
> -               if (!amdgpu_device_has_dc_support(adev))
> -                       flush_work(&adev->hotplug_work);
> -       }
> -
>           for (i = 0; i < AMDGPU_IRQ_CLIENTID_MAX; ++i) {
>                   if (!adev->irq.client[i].sources)
>                           continue;
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h 
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h
> index ac527e5deae6..392a7324e2b1 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h
> @@ -104,7 +104,8 @@ void amdgpu_irq_disable_all(struct amdgpu_device *adev);
>   irqreturn_t amdgpu_irq_handler(int irq, void *arg);
> 
>   int amdgpu_irq_init(struct amdgpu_device *adev);
> -void amdgpu_irq_fini(struct amdgpu_device *adev);
> +void amdgpu_irq_fini_sw(struct amdgpu_device *adev);
> +void amdgpu_irq_fini_hw(struct amdgpu_device *adev);
>   int amdgpu_irq_add_id(struct amdgpu_device *adev,
>                         unsigned client_id, unsigned src_id,
>                         struct amdgpu_irq_src *source);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c 
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
> index 64beb3399604..1af3fba7bfd4 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
> @@ -29,6 +29,7 @@
>   #include "amdgpu.h"
>   #include <drm/drm_debugfs.h>
>   #include <drm/amdgpu_drm.h>
> +#include <drm/drm_drv.h>
>   #include "amdgpu_uvd.h"
>   #include "amdgpu_vce.h"
>   #include "atom.h"
> @@ -93,7 +94,7 @@ void amdgpu_driver_unload_kms(struct drm_device *dev)
>           }
> 
>           amdgpu_acpi_fini(adev);
> -       amdgpu_device_fini(adev);
> +       amdgpu_device_fini_hw(adev);
>   }
> 
>   void amdgpu_register_gpu_instance(struct amdgpu_device *adev)
> @@ -1151,6 +1152,15 @@ void amdgpu_driver_postclose_kms(struct 
> drm_device *dev,
>           pm_runtime_put_autosuspend(dev->dev);
>   }
> 
> +
> +void amdgpu_driver_release_kms(struct drm_device *dev)
> +{
> +       struct amdgpu_device *adev = drm_to_adev(dev);
> +
> +       amdgpu_device_fini_sw(adev);
> +       pci_set_drvdata(adev->pdev, NULL);
> +}
> +
>   /*
>    * VBlank related functions.
>    */
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c 
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
> index 1fb2a91ad30a..c0a16eac4923 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
> @@ -2142,6 +2142,7 @@ int amdgpu_ras_pre_fini(struct amdgpu_device *adev)
>           if (!con)
>                   return 0;
> 
> +
>           /* Need disable ras on all IPs here before ip [hw/sw]fini */
>           amdgpu_ras_disable_all_features(adev, 0);
>           amdgpu_ras_recovery_fini(adev);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h 
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
> index 56acec1075ac..0f195f7bf797 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
> @@ -107,7 +107,8 @@ struct amdgpu_fence_driver {
>   };
> 
>   int amdgpu_fence_driver_init(struct amdgpu_device *adev);
> -void amdgpu_fence_driver_fini(struct amdgpu_device *adev);
> +void amdgpu_fence_driver_fini_hw(struct amdgpu_device *adev);
> +void amdgpu_fence_driver_fini_sw(struct amdgpu_device *adev);
>   void amdgpu_fence_driver_force_completion(struct amdgpu_ring *ring);
> 
>   int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
> diff --git a/drivers/gpu/drm/amd/amdgpu/cik_ih.c 
> b/drivers/gpu/drm/amd/amdgpu/cik_ih.c
> index d3745711d55f..183d44a6583c 100644
> --- a/drivers/gpu/drm/amd/amdgpu/cik_ih.c
> +++ b/drivers/gpu/drm/amd/amdgpu/cik_ih.c
> @@ -309,7 +309,7 @@ static int cik_ih_sw_fini(void *handle)
>   {
>           struct amdgpu_device *adev = (struct amdgpu_device *)handle;
> 
> -       amdgpu_irq_fini(adev);
> +       amdgpu_irq_fini_sw(adev);
>           amdgpu_ih_ring_fini(adev, &adev->irq.ih);
>           amdgpu_irq_remove_domain(adev);
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/cz_ih.c 
> b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
> index 307c01301c87..d32743949003 100644
> --- a/drivers/gpu/drm/amd/amdgpu/cz_ih.c
> +++ b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
> @@ -301,7 +301,7 @@ static int cz_ih_sw_fini(void *handle)
>   {
>           struct amdgpu_device *adev = (struct amdgpu_device *)handle;
> 
> -       amdgpu_irq_fini(adev);
> +       amdgpu_irq_fini_sw(adev);
>           amdgpu_ih_ring_fini(adev, &adev->irq.ih);
>           amdgpu_irq_remove_domain(adev);
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c 
> b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
> index cc957471f31e..da96c6013477 100644
> --- a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
> +++ b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
> @@ -300,7 +300,7 @@ static int iceland_ih_sw_fini(void *handle)
>   {
>           struct amdgpu_device *adev = (struct amdgpu_device *)handle;
> 
> -       amdgpu_irq_fini(adev);
> +       amdgpu_irq_fini_sw(adev);
>           amdgpu_ih_ring_fini(adev, &adev->irq.ih);
>           amdgpu_irq_remove_domain(adev);
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c 
> b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
> index f4e4040bbd25..5eea4550b856 100644
> --- a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
> +++ b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
> @@ -569,7 +569,7 @@ static int navi10_ih_sw_fini(void *handle)
>   {
>           struct amdgpu_device *adev = (struct amdgpu_device *)handle;
> 
> -       amdgpu_irq_fini(adev);
> +       amdgpu_irq_fini_sw(adev);
>           amdgpu_ih_ring_fini(adev, &adev->irq.ih_soft);
>           amdgpu_ih_ring_fini(adev, &adev->irq.ih2);
>           amdgpu_ih_ring_fini(adev, &adev->irq.ih1);
> diff --git a/drivers/gpu/drm/amd/amdgpu/si_ih.c 
> b/drivers/gpu/drm/amd/amdgpu/si_ih.c
> index 51880f6ef634..751307f3252c 100644
> --- a/drivers/gpu/drm/amd/amdgpu/si_ih.c
> +++ b/drivers/gpu/drm/amd/amdgpu/si_ih.c
> @@ -175,7 +175,7 @@ static int si_ih_sw_fini(void *handle)
>   {
>           struct amdgpu_device *adev = (struct amdgpu_device *)handle;
> 
> -       amdgpu_irq_fini(adev);
> +       amdgpu_irq_fini_sw(adev);
>           amdgpu_ih_ring_fini(adev, &adev->irq.ih);
> 
>           return 0;
> diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c 
> b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
> index 249fcbee7871..973d80ec7f6c 100644
> --- a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
> +++ b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
> @@ -312,7 +312,7 @@ static int tonga_ih_sw_fini(void *handle)
>   {
>           struct amdgpu_device *adev = (struct amdgpu_device *)handle;
> 
> -       amdgpu_irq_fini(adev);
> +       amdgpu_irq_fini_sw(adev);
>           amdgpu_ih_ring_fini(adev, &adev->irq.ih);
>           amdgpu_irq_remove_domain(adev);
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c 
> b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
> index 88626d83e07b..2d0094c276ca 100644
> --- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
> +++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
> @@ -523,7 +523,7 @@ static int vega10_ih_sw_fini(void *handle)
>   {
>           struct amdgpu_device *adev = (struct amdgpu_device *)handle;
> 
> -       amdgpu_irq_fini(adev);
> +       amdgpu_irq_fini_sw(adev);
>           amdgpu_ih_ring_fini(adev, &adev->irq.ih_soft);
>           amdgpu_ih_ring_fini(adev, &adev->irq.ih2);
>           amdgpu_ih_ring_fini(adev, &adev->irq.ih1);
> diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c 
> b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
> index 5a3c867d5881..9059b21b079f 100644
> --- a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
> +++ b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
> @@ -558,7 +558,7 @@ static int vega20_ih_sw_fini(void *handle)
>   {
>           struct amdgpu_device *adev = (struct amdgpu_device *)handle;
> 
> -       amdgpu_irq_fini(adev);
> +       amdgpu_irq_fini_sw(adev);
>           amdgpu_ih_ring_fini(adev, &adev->irq.ih_soft);
>           amdgpu_ih_ring_fini(adev, &adev->irq.ih2);
>           amdgpu_ih_ring_fini(adev, &adev->irq.ih1);
> -- 
> 2.25.1
> 
> _______________________________________________
> amd-gfx mailing list
> amd-gfx@lists.freedesktop.org
> https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Flists.freedesktop.org%2Fmailman%2Flistinfo%2Famd-gfx&amp;data=04%7C01%7Clijo.lazar%40amd.com%7C71f92dcef6d04dfea28308d90a5818c9%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637552195764790324%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&amp;sdata=fzGS6ZXYffGH0DE%2BEM4jxyB8yDGpYO%2FmT%2FKAtgig1Tw%3D&amp;reserved=0 
> <https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Flists.freedesktop.org%2Fmailman%2Flistinfo%2Famd-gfx&amp;data=04%7C01%7Clijo.lazar%40amd.com%7C71f92dcef6d04dfea28308d90a5818c9%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637552195764790324%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&amp;sdata=fzGS6ZXYffGH0DE%2BEM4jxyB8yDGpYO%2FmT%2FKAtgig1Tw%3D&amp;reserved=0>
Lazar, Lijo April 30, 2021, 5:49 a.m. UTC | #5
[AMD Official Use Only - Internal Distribution Only]

That looks better to me :) As more things get added, I don't know how long you will be able to hold sw/hw cleanup separate and the name could confuse eventually.

Thanks,
Lijo
diff mbox series

Patch

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 1af2fa1591fd..fddb82897e5d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1073,7 +1073,9 @@  static inline struct amdgpu_device *amdgpu_ttm_adev(struct ttm_device *bdev)
 
 int amdgpu_device_init(struct amdgpu_device *adev,
 		       uint32_t flags);
-void amdgpu_device_fini(struct amdgpu_device *adev);
+void amdgpu_device_fini_hw(struct amdgpu_device *adev);
+void amdgpu_device_fini_sw(struct amdgpu_device *adev);
+
 int amdgpu_gpu_wait_for_idle(struct amdgpu_device *adev);
 
 void amdgpu_device_vram_access(struct amdgpu_device *adev, loff_t pos,
@@ -1289,6 +1291,8 @@  void amdgpu_driver_lastclose_kms(struct drm_device *dev);
 int amdgpu_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv);
 void amdgpu_driver_postclose_kms(struct drm_device *dev,
 				 struct drm_file *file_priv);
+void amdgpu_driver_release_kms(struct drm_device *dev);
+
 int amdgpu_device_ip_suspend(struct amdgpu_device *adev);
 int amdgpu_device_suspend(struct drm_device *dev, bool fbcon);
 int amdgpu_device_resume(struct drm_device *dev, bool fbcon);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 6447cd6ca5a8..8d22b79fc1cd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3590,14 +3590,12 @@  int amdgpu_device_init(struct amdgpu_device *adev,
  * Tear down the driver info (all asics).
  * Called at driver shutdown.
  */
-void amdgpu_device_fini(struct amdgpu_device *adev)
+void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 {
 	dev_info(adev->dev, "amdgpu: finishing device.\n");
 	flush_delayed_work(&adev->delayed_init_work);
 	adev->shutdown = true;
 
-	kfree(adev->pci_state);
-
 	/* make sure IB test finished before entering exclusive mode
 	 * to avoid preemption on IB test
 	 * */
@@ -3614,11 +3612,24 @@  void amdgpu_device_fini(struct amdgpu_device *adev)
 		else
 			drm_atomic_helper_shutdown(adev_to_drm(adev));
 	}
-	amdgpu_fence_driver_fini(adev);
+	amdgpu_fence_driver_fini_hw(adev);
+
 	if (adev->pm_sysfs_en)
 		amdgpu_pm_sysfs_fini(adev);
+	if (adev->ucode_sysfs_en)
+		amdgpu_ucode_sysfs_fini(adev);
+	sysfs_remove_files(&adev->dev->kobj, amdgpu_dev_attributes);
+
+
 	amdgpu_fbdev_fini(adev);
+
+	amdgpu_irq_fini_hw(adev);
+}
+
+void amdgpu_device_fini_sw(struct amdgpu_device *adev)
+{
 	amdgpu_device_ip_fini(adev);
+	amdgpu_fence_driver_fini_sw(adev);
 	release_firmware(adev->firmware.gpu_info_fw);
 	adev->firmware.gpu_info_fw = NULL;
 	adev->accel_working = false;
@@ -3647,14 +3658,13 @@  void amdgpu_device_fini(struct amdgpu_device *adev)
 	adev->rmmio = NULL;
 	amdgpu_device_doorbell_fini(adev);
 
-	if (adev->ucode_sysfs_en)
-		amdgpu_ucode_sysfs_fini(adev);
-
-	sysfs_remove_files(&adev->dev->kobj, amdgpu_dev_attributes);
 	if (IS_ENABLED(CONFIG_PERF_EVENTS))
 		amdgpu_pmu_fini(adev);
 	if (adev->mman.discovery_bin)
 		amdgpu_discovery_fini(adev);
+
+	kfree(adev->pci_state);
+
 }
 
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 671ec1002230..54cb5ee2f563 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1249,14 +1249,10 @@  amdgpu_pci_remove(struct pci_dev *pdev)
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
 
-#ifdef MODULE
-	if (THIS_MODULE->state != MODULE_STATE_GOING)
-#endif
-		DRM_ERROR("Hotplug removal is not supported\n");
 	drm_dev_unplug(dev);
 	amdgpu_driver_unload_kms(dev);
+
 	pci_disable_device(pdev);
-	pci_set_drvdata(pdev, NULL);
 }
 
 static void
@@ -1587,6 +1583,7 @@  static const struct drm_driver amdgpu_kms_driver = {
 	.dumb_create = amdgpu_mode_dumb_create,
 	.dumb_map_offset = amdgpu_mode_dumb_mmap,
 	.fops = &amdgpu_driver_kms_fops,
+	.release = &amdgpu_driver_release_kms,
 
 	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
 	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 8e0a5650d383..34d51e962799 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -523,7 +523,7 @@  int amdgpu_fence_driver_init(struct amdgpu_device *adev)
  *
  * Tear down the fence driver for all possible rings (all asics).
  */
-void amdgpu_fence_driver_fini(struct amdgpu_device *adev)
+void amdgpu_fence_driver_fini_hw(struct amdgpu_device *adev)
 {
 	unsigned i, j;
 	int r;
@@ -544,6 +544,19 @@  void amdgpu_fence_driver_fini(struct amdgpu_device *adev)
 		if (!ring->no_scheduler)
 			drm_sched_fini(&ring->sched);
 		del_timer_sync(&ring->fence_drv.fallback_timer);
+	}
+}
+
+void amdgpu_fence_driver_fini_sw(struct amdgpu_device *adev)
+{
+	unsigned int i, j;
+
+	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
+		struct amdgpu_ring *ring = adev->rings[i];
+
+		if (!ring || !ring->fence_drv.initialized)
+			continue;
+
 		for (j = 0; j <= ring->fence_drv.num_fences_mask; ++j)
 			dma_fence_put(ring->fence_drv.fences[j]);
 		kfree(ring->fence_drv.fences);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
index afbbec82a289..63e815c27585 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
@@ -49,6 +49,7 @@ 
 #include <drm/drm_irq.h>
 #include <drm/drm_vblank.h>
 #include <drm/amdgpu_drm.h>
+#include <drm/drm_drv.h>
 #include "amdgpu.h"
 #include "amdgpu_ih.h"
 #include "atom.h"
@@ -313,6 +314,20 @@  int amdgpu_irq_init(struct amdgpu_device *adev)
 	return 0;
 }
 
+
+void amdgpu_irq_fini_hw(struct amdgpu_device *adev)
+{
+	if (adev->irq.installed) {
+		drm_irq_uninstall(&adev->ddev);
+		adev->irq.installed = false;
+		if (adev->irq.msi_enabled)
+			pci_free_irq_vectors(adev->pdev);
+
+		if (!amdgpu_device_has_dc_support(adev))
+			flush_work(&adev->hotplug_work);
+	}
+}
+
 /**
  * amdgpu_irq_fini - shut down interrupt handling
  *
@@ -322,19 +337,10 @@  int amdgpu_irq_init(struct amdgpu_device *adev)
  * functionality, shuts down vblank, hotplug and reset interrupt handling,
  * turns off interrupts from all sources (all ASICs).
  */
-void amdgpu_irq_fini(struct amdgpu_device *adev)
+void amdgpu_irq_fini_sw(struct amdgpu_device *adev)
 {
 	unsigned i, j;
 
-	if (adev->irq.installed) {
-		drm_irq_uninstall(adev_to_drm(adev));
-		adev->irq.installed = false;
-		if (adev->irq.msi_enabled)
-			pci_free_irq_vectors(adev->pdev);
-		if (!amdgpu_device_has_dc_support(adev))
-			flush_work(&adev->hotplug_work);
-	}
-
 	for (i = 0; i < AMDGPU_IRQ_CLIENTID_MAX; ++i) {
 		if (!adev->irq.client[i].sources)
 			continue;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h
index ac527e5deae6..392a7324e2b1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h
@@ -104,7 +104,8 @@  void amdgpu_irq_disable_all(struct amdgpu_device *adev);
 irqreturn_t amdgpu_irq_handler(int irq, void *arg);
 
 int amdgpu_irq_init(struct amdgpu_device *adev);
-void amdgpu_irq_fini(struct amdgpu_device *adev);
+void amdgpu_irq_fini_sw(struct amdgpu_device *adev);
+void amdgpu_irq_fini_hw(struct amdgpu_device *adev);
 int amdgpu_irq_add_id(struct amdgpu_device *adev,
 		      unsigned client_id, unsigned src_id,
 		      struct amdgpu_irq_src *source);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 64beb3399604..1af3fba7bfd4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -29,6 +29,7 @@ 
 #include "amdgpu.h"
 #include <drm/drm_debugfs.h>
 #include <drm/amdgpu_drm.h>
+#include <drm/drm_drv.h>
 #include "amdgpu_uvd.h"
 #include "amdgpu_vce.h"
 #include "atom.h"
@@ -93,7 +94,7 @@  void amdgpu_driver_unload_kms(struct drm_device *dev)
 	}
 
 	amdgpu_acpi_fini(adev);
-	amdgpu_device_fini(adev);
+	amdgpu_device_fini_hw(adev);
 }
 
 void amdgpu_register_gpu_instance(struct amdgpu_device *adev)
@@ -1151,6 +1152,15 @@  void amdgpu_driver_postclose_kms(struct drm_device *dev,
 	pm_runtime_put_autosuspend(dev->dev);
 }
 
+
+void amdgpu_driver_release_kms(struct drm_device *dev)
+{
+	struct amdgpu_device *adev = drm_to_adev(dev);
+
+	amdgpu_device_fini_sw(adev);
+	pci_set_drvdata(adev->pdev, NULL);
+}
+
 /*
  * VBlank related functions.
  */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 1fb2a91ad30a..c0a16eac4923 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -2142,6 +2142,7 @@  int amdgpu_ras_pre_fini(struct amdgpu_device *adev)
 	if (!con)
 		return 0;
 
+
 	/* Need disable ras on all IPs here before ip [hw/sw]fini */
 	amdgpu_ras_disable_all_features(adev, 0);
 	amdgpu_ras_recovery_fini(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index 56acec1075ac..0f195f7bf797 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -107,7 +107,8 @@  struct amdgpu_fence_driver {
 };
 
 int amdgpu_fence_driver_init(struct amdgpu_device *adev);
-void amdgpu_fence_driver_fini(struct amdgpu_device *adev);
+void amdgpu_fence_driver_fini_hw(struct amdgpu_device *adev);
+void amdgpu_fence_driver_fini_sw(struct amdgpu_device *adev);
 void amdgpu_fence_driver_force_completion(struct amdgpu_ring *ring);
 
 int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_ih.c b/drivers/gpu/drm/amd/amdgpu/cik_ih.c
index d3745711d55f..183d44a6583c 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_ih.c
@@ -309,7 +309,7 @@  static int cik_ih_sw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	amdgpu_irq_fini(adev);
+	amdgpu_irq_fini_sw(adev);
 	amdgpu_ih_ring_fini(adev, &adev->irq.ih);
 	amdgpu_irq_remove_domain(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/cz_ih.c b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
index 307c01301c87..d32743949003 100644
--- a/drivers/gpu/drm/amd/amdgpu/cz_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
@@ -301,7 +301,7 @@  static int cz_ih_sw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	amdgpu_irq_fini(adev);
+	amdgpu_irq_fini_sw(adev);
 	amdgpu_ih_ring_fini(adev, &adev->irq.ih);
 	amdgpu_irq_remove_domain(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
index cc957471f31e..da96c6013477 100644
--- a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
@@ -300,7 +300,7 @@  static int iceland_ih_sw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	amdgpu_irq_fini(adev);
+	amdgpu_irq_fini_sw(adev);
 	amdgpu_ih_ring_fini(adev, &adev->irq.ih);
 	amdgpu_irq_remove_domain(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
index f4e4040bbd25..5eea4550b856 100644
--- a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
@@ -569,7 +569,7 @@  static int navi10_ih_sw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	amdgpu_irq_fini(adev);
+	amdgpu_irq_fini_sw(adev);
 	amdgpu_ih_ring_fini(adev, &adev->irq.ih_soft);
 	amdgpu_ih_ring_fini(adev, &adev->irq.ih2);
 	amdgpu_ih_ring_fini(adev, &adev->irq.ih1);
diff --git a/drivers/gpu/drm/amd/amdgpu/si_ih.c b/drivers/gpu/drm/amd/amdgpu/si_ih.c
index 51880f6ef634..751307f3252c 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_ih.c
@@ -175,7 +175,7 @@  static int si_ih_sw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	amdgpu_irq_fini(adev);
+	amdgpu_irq_fini_sw(adev);
 	amdgpu_ih_ring_fini(adev, &adev->irq.ih);
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
index 249fcbee7871..973d80ec7f6c 100644
--- a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
@@ -312,7 +312,7 @@  static int tonga_ih_sw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	amdgpu_irq_fini(adev);
+	amdgpu_irq_fini_sw(adev);
 	amdgpu_ih_ring_fini(adev, &adev->irq.ih);
 	amdgpu_irq_remove_domain(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
index 88626d83e07b..2d0094c276ca 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
@@ -523,7 +523,7 @@  static int vega10_ih_sw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	amdgpu_irq_fini(adev);
+	amdgpu_irq_fini_sw(adev);
 	amdgpu_ih_ring_fini(adev, &adev->irq.ih_soft);
 	amdgpu_ih_ring_fini(adev, &adev->irq.ih2);
 	amdgpu_ih_ring_fini(adev, &adev->irq.ih1);
diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
index 5a3c867d5881..9059b21b079f 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
@@ -558,7 +558,7 @@  static int vega20_ih_sw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	amdgpu_irq_fini(adev);
+	amdgpu_irq_fini_sw(adev);
 	amdgpu_ih_ring_fini(adev, &adev->irq.ih_soft);
 	amdgpu_ih_ring_fini(adev, &adev->irq.ih2);
 	amdgpu_ih_ring_fini(adev, &adev->irq.ih1);