[PATCH] drm/amdgpu: fix modprobe failure of the 2nd GPU when GDDR6 training enabled

[Christian König]

Am 08.01.20 um 13:36 schrieb Tianci Yin:
> From: "Tianci.Yin" <tianci.yin at amd.com>
>
> [why]
> In dual GPUs scenario, stolen_size is assigned to zero on the 2nd GPU,
> then the bottom region of VRAM was allocated as GTT, unfortunately
> a small region of bottom VRAM was encroached by UMC firmware during
> GDDR6 BIST training, this cause pagefault.

What I'm missing here is why is the stolen size zero on the 2nd GPU?

Maybe we need to read the stolen size after posting the GPU instead?

Regards,
Christian.

>
> [how]
> Forcing stolen_size to 3MB, then the bottom region of VRAM was
> allocated as stolen memory, GTT corruption avoid.
> The stolen memory of the 2nd GPU will be free in late_init phase,
> no memory wasted.
>
> Change-Id: Icd0ad7de41333282949bb1e3e676c6c307ddd081
> Signed-off-by: Tianci.Yin <tianci.yin at amd.com>
> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h |  6 ++++++
>   drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c  | 21 +++++++++++++++++++++
>   2 files changed, 27 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
> index c91dd602d5f1..440b793316df 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
> @@ -60,6 +60,11 @@
>    */
>   #define AMDGPU_GMC_FAULT_TIMEOUT	5000ULL
>   
> +/*
> + * Default stolen memory size, 1024 * 768 * 4
> + */
> +#define AMDGPU_STOLEN_VGA_DEFAULT_SIZE	0x300000
> +
>   struct firmware;
>   
>   /*
> @@ -192,6 +197,7 @@ struct amdgpu_gmc {
>   	uint32_t                srbm_soft_reset;
>   	bool			prt_warning;
>   	uint64_t		stolen_size;
> +	bool			stolen_temp_reserved;
>   	/* apertures */
>   	u64			shared_aperture_start;
>   	u64			shared_aperture_end;
> diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
> index 7dc8c068c62a..0c96b67d6ca7 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
> @@ -566,6 +566,11 @@ static int gmc_v10_0_late_init(void *handle)
>   	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
>   	int r;
>   
> +	if (adev->gmc.stolen_temp_reserved) {
> +		amdgpu_bo_late_init(adev);
> +		adev->gmc.stolen_temp_reserved = false;
> +	}
> +
>   	r = amdgpu_gmc_allocate_vm_inv_eng(adev);
>   	if (r)
>   		return r;
> @@ -756,6 +761,22 @@ static int gmc_v10_0_sw_init(void *handle)
>   		return r;
>   
>   	adev->gmc.stolen_size = gmc_v10_0_get_vbios_fb_size(adev);
> +	/*
> +	 * In dual GPUs scenario, stolen_size is assigned to zero on the 2nd GPU,
> +	 * then the bottom region of VRAM was allocated as GTT, unfortunately
> +	 * a small region of bottom VRAM was encroached by UMC firmware during
> +	 * GDDR6 BIST training, this cause pagefault.
> +	 * The page fault can be fixed by forcing stolen_size to 3MB, then the bottom
> +	 * region of VRAM was allocated as stolen memory, GTT corruption avoid.
> +	 * The stolen memory of the 2nd GPU will be free in late_init phase,
> +	 * no memory wasted.
> +	 */
> +	if (adev->fw_vram_usage.mem_train_support &&
> +		adev->gmc.stolen_size == 0) {
> +		adev->gmc.stolen_size = AMDGPU_STOLEN_VGA_DEFAULT_SIZE;
> +		adev->gmc.stolen_temp_reserved = true;
> +	} else
> +		adev->gmc.stolen_temp_reserved = false;
>   
>   	/* Memory manager */
>   	r = amdgpu_bo_init(adev);