Re: [PATCH v4 05/14] drm/amdgpu: Split amdgpu_device_fini into early and late

[Christian König <ckoenig.leichtzumerken@xxxxxxxxx>]

Am 18.01.21 um 22:01 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@xxxxxxx>

The fence and irq changes look sane to me, no idea for the rest.

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

> ---
>   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 +-
>   16 files changed, 78 insertions(+), 35 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> index f77443c..478a7d8 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> @@ -1060,7 +1060,9 @@ static inline struct amdgpu_device *amdgpu_ttm_adev(struct ttm_bo_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,
> @@ -1273,6 +1275,8 @@ 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 348ac67..90c8353 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> @@ -3579,14 +3579,12 @@ 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
>   	 * */
> @@ -3603,11 +3601,24 @@ 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;
> @@ -3636,14 +3647,13 @@ 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 72efd57..9c0cd00 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> @@ -1238,14 +1238,10 @@ 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
> @@ -1569,6 +1565,7 @@ 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 d56f402..e19b74c 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 bea57e8..2f1cfc5 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 ac527e5..392a732 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 b16b327..fee95d3 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)
> @@ -1153,6 +1154,15 @@ 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 c136bd4..87eaf13 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 7112137..accb243 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 d374571..183d44a 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 da37f8a..ee824d7 100644
> --- a/drivers/gpu/drm/amd/amdgpu/cz_ih.c
> +++ b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
> @@ -290,7 +290,7 @@ 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 37d8b6c..b24f6fb 100644
> --- a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
> +++ b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
> @@ -290,7 +290,7 @@ 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 7ba229e..c191410 100644
> --- a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
> +++ b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
> @@ -716,7 +716,7 @@ 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.ih2);
>   	amdgpu_ih_ring_fini(adev, &adev->irq.ih1);
>   	amdgpu_ih_ring_fini(adev, &adev->irq.ih);
> diff --git a/drivers/gpu/drm/amd/amdgpu/si_ih.c b/drivers/gpu/drm/amd/amdgpu/si_ih.c
> index 51880f6..751307f 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 ce33199..729aaaa 100644
> --- a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
> +++ b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
> @@ -301,7 +301,7 @@ 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 e5ae31e..a342406 100644
> --- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
> +++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
> @@ -627,7 +627,7 @@ 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.ih2);
>   	amdgpu_ih_ring_fini(adev, &adev->irq.ih1);
>   	amdgpu_ih_ring_fini(adev, &adev->irq.ih);

_______________________________________________
amd-gfx mailing list
amd-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/amd-gfx