Re: [PATCH] accel/ivpu: Don't enter d0i3 during FLR

[Jeffrey Hugo <quic_jhugo@xxxxxxxxxxx>]

On 10/3/2023 12:42 AM, Stanislaw Gruszka wrote:
> From: Jacek Lawrynowicz <jacek.lawrynowicz@xxxxxxxxxxxxxxx>
>
> Fix a bug on some platforms where FLR causes complete system
> hang when CPU is low power states (C8 or above).

Why does FLR cause a complete system hang?  Why does avoiding d0i3 fix 
the issue?  Feels like there could be a lot more detail here.

> Fixes: 852be13f3bd3 ("accel/ivpu: Add PM support")
> Cc: stable@xxxxxxxxxxxxxxx
> Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@xxxxxxxxxxxxxxx>
> Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@xxxxxxxxxxxxxxx>
> Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@xxxxxxxxxxxxxxx>
> ---
>   drivers/accel/ivpu/ivpu_drv.c     | 11 ++++++++---
>   drivers/accel/ivpu/ivpu_drv.h     |  1 +
>   drivers/accel/ivpu/ivpu_hw.h      |  8 ++++++++
>   drivers/accel/ivpu/ivpu_hw_37xx.c |  1 +
>   drivers/accel/ivpu/ivpu_hw_40xx.c |  1 +
>   drivers/accel/ivpu/ivpu_pm.c      |  3 ++-
>   6 files changed, 21 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
> index 3f4efa07ce7c..1eb232e903e8 100644
> --- a/drivers/accel/ivpu/ivpu_drv.c
> +++ b/drivers/accel/ivpu/ivpu_drv.c
> @@ -367,14 +367,19 @@ int ivpu_boot(struct ivpu_device *vdev)
>   	return 0;
>   }
>   
> -int ivpu_shutdown(struct ivpu_device *vdev)
> +void ivpu_prepare_for_reset(struct ivpu_device *vdev)
>   {
> -	int ret;
> -
>   	ivpu_hw_irq_disable(vdev);
>   	disable_irq(vdev->irq);
>   	ivpu_ipc_disable(vdev);
>   	ivpu_mmu_disable(vdev);
> +}
> +
> +int ivpu_shutdown(struct ivpu_device *vdev)
> +{
> +	int ret;
> +
> +	ivpu_prepare_for_reset(vdev);
>   
>   	ret = ivpu_hw_power_down(vdev);
>   	if (ret)
> diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h
> index 98380c1db9fa..a3b45032e6cf 100644
> --- a/drivers/accel/ivpu/ivpu_drv.h
> +++ b/drivers/accel/ivpu/ivpu_drv.h
> @@ -158,6 +158,7 @@ void ivpu_file_priv_put(struct ivpu_file_priv **link);
>   
>   int ivpu_boot(struct ivpu_device *vdev);
>   int ivpu_shutdown(struct ivpu_device *vdev);
> +void ivpu_prepare_for_reset(struct ivpu_device *vdev);
>   
>   static inline u8 ivpu_revision(struct ivpu_device *vdev)
>   {
> diff --git a/drivers/accel/ivpu/ivpu_hw.h b/drivers/accel/ivpu/ivpu_hw.h
> index ab341237bcf9..1079e06255ba 100644
> --- a/drivers/accel/ivpu/ivpu_hw.h
> +++ b/drivers/accel/ivpu/ivpu_hw.h
> @@ -13,6 +13,7 @@ struct ivpu_hw_ops {
>   	int (*power_up)(struct ivpu_device *vdev);
>   	int (*boot_fw)(struct ivpu_device *vdev);
>   	int (*power_down)(struct ivpu_device *vdev);
> +	int (*reset)(struct ivpu_device *vdev);
>   	bool (*is_idle)(struct ivpu_device *vdev);
>   	void (*wdt_disable)(struct ivpu_device *vdev);
>   	void (*diagnose_failure)(struct ivpu_device *vdev);
> @@ -91,6 +92,13 @@ static inline int ivpu_hw_power_down(struct ivpu_device *vdev)
>   	return vdev->hw->ops->power_down(vdev);
>   };
>   
> +static inline int ivpu_hw_reset(struct ivpu_device *vdev)
> +{
> +	ivpu_dbg(vdev, PM, "HW reset\n");
> +
> +	return vdev->hw->ops->reset(vdev);
> +};
> +
>   static inline void ivpu_hw_wdt_disable(struct ivpu_device *vdev)
>   {
>   	vdev->hw->ops->wdt_disable(vdev);
> diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c
> index edd4d860f135..1e842739e937 100644
> --- a/drivers/accel/ivpu/ivpu_hw_37xx.c
> +++ b/drivers/accel/ivpu/ivpu_hw_37xx.c
> @@ -1036,6 +1036,7 @@ const struct ivpu_hw_ops ivpu_hw_37xx_ops = {
>   	.power_up = ivpu_hw_37xx_power_up,
>   	.is_idle = ivpu_hw_37xx_is_idle,
>   	.power_down = ivpu_hw_37xx_power_down,
> +	.reset = ivpu_hw_37xx_reset,
>   	.boot_fw = ivpu_hw_37xx_boot_fw,
>   	.wdt_disable = ivpu_hw_37xx_wdt_disable,
>   	.diagnose_failure = ivpu_hw_37xx_diagnose_failure,
> diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c
> index a48cd36f9931..d7b8ec0410af 100644
> --- a/drivers/accel/ivpu/ivpu_hw_40xx.c
> +++ b/drivers/accel/ivpu/ivpu_hw_40xx.c
> @@ -1186,6 +1186,7 @@ const struct ivpu_hw_ops ivpu_hw_40xx_ops = {
>   	.power_up = ivpu_hw_40xx_power_up,
>   	.is_idle = ivpu_hw_40xx_is_idle,
>   	.power_down = ivpu_hw_40xx_power_down,
> +	.reset = ivpu_hw_40xx_reset,
>   	.boot_fw = ivpu_hw_40xx_boot_fw,
>   	.wdt_disable = ivpu_hw_40xx_wdt_disable,
>   	.diagnose_failure = ivpu_hw_40xx_diagnose_failure,
> diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
> index 28a0d1111e12..da46f95b008a 100644
> --- a/drivers/accel/ivpu/ivpu_pm.c
> +++ b/drivers/accel/ivpu/ivpu_pm.c
> @@ -261,7 +261,8 @@ void ivpu_pm_reset_prepare_cb(struct pci_dev *pdev)
>   	ivpu_dbg(vdev, PM, "Pre-reset..\n");
>   	atomic_inc(&vdev->pm->reset_counter);
>   	atomic_set(&vdev->pm->in_reset, 1);
> -	ivpu_shutdown(vdev);
> +	ivpu_prepare_for_reset(vdev);
> +	ivpu_hw_reset(vdev);
>   	ivpu_pm_prepare_cold_boot(vdev);
>   	ivpu_jobs_abort_all(vdev);
>   	ivpu_dbg(vdev, PM, "Pre-reset done.\n");