[PATCH v2] drm/amdgpu: check whether smu is idle in sriov case

[Lazar, Lijo]

On 7/7/2023 3:47 PM, Danijel Slivka wrote:
> Why:
> If the reg mmMP1_SMN_C2PMSG_90 is being programed to 0x0 before
> guest initialization, then modprobe amdgpu will fail at smu hw_init.
> (the default mmMP1_SMN_C2PMSG_90 at a clean guest environment is 0x1).
> 
A response to the FW  message doesn't mean SMU is idle. Probably, this 
is only a check that FW is ready.

Instead of introducing a new ppt function, move this implementation to 
check_fw_status(). For VF case, test message may be sent to ascertain 
that FW is ready.

Thanks,
Lijo

> How to fix:
> this patch is to check whether smu is idle by sending a test
> message to smu. If smu is idle, it will respond.
> 
> Signed-off-by: Danijel Slivka <danijel.slivka at amd.com>
> Signed-off-by: Nikola Prica <nikola.prica at amd.com>
> Signed-off-by: Jingwen Chen <Jingwen.Chen2 at amd.com>
> Signed-off-by: pengzhou <PengJu.Zhou at amd.com>
> ---
>   drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c     |  8 ++++
>   drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h |  7 ++++
>   .../gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c   |  1 +
>   drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c        | 40 +++++++++++++++++++
>   drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h        |  2 +
>   5 files changed, 58 insertions(+)
> 
> diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
> index ce41a8309582..63ea4cd32ece 100644
> --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
> +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
> @@ -1443,6 +1443,14 @@ static int smu_start_smc_engine(struct smu_context *smu)
>   		}
>   	}
>   
> +	if (amdgpu_sriov_vf(adev) && smu->ppt_funcs->wait_smu_idle) {
> +		ret = smu->ppt_funcs->wait_smu_idle(smu);
> +		if (ret) {
> +			dev_err(adev->dev, "SMU is not idle\n");
> +			return ret;
> +		}
> +	}
> +
>   	/*
>   	 * Send msg GetDriverIfVersion to check if the return value is equal
>   	 * with DRIVER_IF_VERSION of smc header.
> diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
> index 6e2069dcb6b9..1bf87ad30d93 100644
> --- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
> +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
> @@ -926,6 +926,13 @@ struct pptable_funcs {
>   	 */
>   	int (*check_fw_status)(struct smu_context *smu);
>   
> +	/**
> +	 * @wait_smu_idle: wait for SMU idle status.
> +	 *
> +	 * Return: Zero if check passes, negative errno on failure.
> +	 */
> +	int (*wait_smu_idle)(struct smu_context *smu);
> +
>   	/**
>   	 * @set_mp1_state: put SMU into a correct state for comming
>   	 *                 resume from runpm or gpu reset.
> diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
> index c94d825a871b..3745e4f96433 100644
> --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
> +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
> @@ -3503,6 +3503,7 @@ static const struct pptable_funcs navi10_ppt_funcs = {
>   	.init_power = smu_v11_0_init_power,
>   	.fini_power = smu_v11_0_fini_power,
>   	.check_fw_status = smu_v11_0_check_fw_status,
> +	.wait_smu_idle = smu_cmn_wait_smu_idle,
>   	.setup_pptable = navi10_setup_pptable,
>   	.get_vbios_bootup_values = smu_v11_0_get_vbios_bootup_values,
>   	.check_fw_version = smu_v11_0_check_fw_version,
> diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
> index 3ecb900e6ecd..e3c972984b2b 100644
> --- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
> +++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
> @@ -313,6 +313,46 @@ int smu_cmn_wait_for_response(struct smu_context *smu)
>   	return res;
>   }
>   
> +/**
> + * smu_cmn_wait_smu_idle -- wait for smu to become idle
> + * @smu: pointer to an SMU context
> + *
> + * Send SMU_MSG_TestMessage to check whether SMU is idle.
> + * If SMU is idle, it will respond.
> + * The returned parameter will be the param you pass + 1.
> + *
> + * Return 0 on success, -errno on error, indicating the execution
> + * status and result of the message being waited for. See
> + * __smu_cmn_reg2errno() for details of the -errno.
> + */
> +int smu_cmn_wait_smu_idle(struct smu_context *smu)
> +{
> +	u32 reg;
> +	u32 param = 0xff00011;
> +	uint32_t read_arg;
> +	int res, index;
> +
> +	index = smu_cmn_to_asic_specific_index(smu,
> +					       CMN2ASIC_MAPPING_MSG,
> +					       SMU_MSG_TestMessage);
> +
> +	__smu_cmn_send_msg(smu, index, param);
> +	reg = __smu_cmn_poll_stat(smu);
> +	res = __smu_cmn_reg2errno(smu, reg);
> +
> +	if (unlikely(smu->adev->pm.smu_debug_mask & SMU_DEBUG_HALT_ON_ERROR) &&
> +	    res && (res != -ETIME)) {
> +		amdgpu_device_halt(smu->adev);
> +		WARN_ON(1);
> +	}
> +
> +	smu_cmn_read_arg(smu, &read_arg);
> +	if (read_arg == param + 1)
> +		return 0;
> +	return res;
> +}
> +
> +
>   /**
>    * smu_cmn_send_smc_msg_with_param -- send a message with parameter
>    * @smu: pointer to an SMU context
> diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
> index d7cd358a53bd..65da886d6a8c 100644
> --- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
> +++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
> @@ -50,6 +50,8 @@ int smu_cmn_send_debug_smc_msg_with_param(struct smu_context *smu,
>   
>   int smu_cmn_wait_for_response(struct smu_context *smu);
>   
> +int smu_cmn_wait_smu_idle(struct smu_context *smu);
> +
>   int smu_cmn_to_asic_specific_index(struct smu_context *smu,
>   				   enum smu_cmn2asic_mapping_type type,
>   				   uint32_t index);