[PATCH] ath10k: Don't always treat modem stop events as crashes

[Matthias Kaehlcke]

On Sun, Sep 05, 2021 at 02:04:00PM -0700, Stephen Boyd wrote:
> When rebooting on sc7180 Trogdor devices I see the following crash from
> the wifi driver.
> 
>  ath10k_snoc 18800000.wifi: firmware crashed! (guid 83493570-29a2-4e98-a83e-70048c47669c)
> 
> This is because a modem stop event looks just like a firmware crash to
> the driver, the qmi connection is closed in both cases. Use the qcom ssr
> notifier block to stop treating the qmi connection close event as a
> firmware crash signal when the modem hasn't actually crashed. See
> ath10k_qmi_event_server_exit() for more details.
> 
> This silences the crash message seen during every reboot.
> 
> Fixes: 3f14b73c3843 ("ath10k: Enable MSA region dump support for WCN3990")
> Cc: Govind Singh <govinds at codeaurora.org>
> Cc: Youghandhar Chintala <youghand at codeaurora.org>
> Cc: Abhishek Kumar <kuabhs at chromium.org>
> Signed-off-by: Stephen Boyd <swboyd at chromium.org>
> ---
>  drivers/net/wireless/ath/ath10k/snoc.c | 75 ++++++++++++++++++++++++++
>  drivers/net/wireless/ath/ath10k/snoc.h |  4 ++
>  2 files changed, 79 insertions(+)
> 
> diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c
> index ea00fbb15601..fc4970e063f8 100644
> --- a/drivers/net/wireless/ath/ath10k/snoc.c
> +++ b/drivers/net/wireless/ath/ath10k/snoc.c
> @@ -12,6 +12,7 @@
>  #include <linux/platform_device.h>
>  #include <linux/property.h>
>  #include <linux/regulator/consumer.h>
> +#include <linux/remoteproc/qcom_rproc.h>
>  #include <linux/of_address.h>
>  #include <linux/iommu.h>
>  
> @@ -1477,6 +1478,70 @@ void ath10k_snoc_fw_crashed_dump(struct ath10k *ar)
>  	mutex_unlock(&ar->dump_mutex);
>  }
>  
> +static int ath10k_snoc_modem_notify(struct notifier_block *nb, unsigned long action,
> +				    void *data)
> +{
> +	struct ath10k_snoc *ar_snoc = container_of(nb, struct ath10k_snoc, nb);
> +	struct ath10k *ar = ar_snoc->ar;
> +	struct qcom_ssr_notify_data *notify_data = data;
> +
> +	switch (action) {
> +	case QCOM_SSR_BEFORE_POWERUP:
> +		ath10k_dbg(ar, ATH10K_DBG_SNOC, "received modem starting event\n");
> +		clear_bit(ATH10K_SNOC_FLAG_UNREGISTERING, &ar_snoc->flags);
> +		break;
> +
> +	case QCOM_SSR_AFTER_POWERUP:
> +		ath10k_dbg(ar, ATH10K_DBG_SNOC, "received modem running event\n");
> +		break;
> +
> +	case QCOM_SSR_BEFORE_SHUTDOWN:
> +		ath10k_dbg(ar, ATH10K_DBG_SNOC, "received modem %s event\n",
> +			   notify_data->crashed ? "crashed" : "stopping");
> +		if (!notify_data->crashed)
> +			set_bit(ATH10K_SNOC_FLAG_UNREGISTERING, &ar_snoc->flags);
> +		else
> +			clear_bit(ATH10K_SNOC_FLAG_UNREGISTERING, &ar_snoc->flags);
> +		break;
> +
> +	case QCOM_SSR_AFTER_SHUTDOWN:
> +		ath10k_dbg(ar, ATH10K_DBG_SNOC, "received modem offline event\n");
> +		break;
> +
> +	default:
> +		ath10k_err(ar, "received unrecognized event %lu\n", action);
> +		break;
> +	}
> +
> +	return NOTIFY_OK;
> +}
> +
> +static int ath10k_modem_init(struct ath10k *ar)
> +{
> +	struct ath10k_snoc *ar_snoc = ath10k_snoc_priv(ar);
> +	void *notifier;
> +
> +	ar_snoc->nb.notifier_call = ath10k_snoc_modem_notify;
> +
> +	notifier = qcom_register_ssr_notifier("mpss", &ar_snoc->nb);
> +	if (IS_ERR(notifier))
> +		return PTR_ERR(notifier);
> +
> +	ar_snoc->notifier = notifier;
> +
> +	return 0;
> +}
> +
> +static void ath10k_modem_deinit(struct ath10k *ar)
> +{
> +	int ret;
> +	struct ath10k_snoc *ar_snoc = ath10k_snoc_priv(ar);
> +
> +	ret = qcom_unregister_ssr_notifier(ar_snoc->notifier, &ar_snoc->nb);
> +	if (ret)
> +		ath10k_err(ar, "error %d unregistering notifier\n", ret);
> +}
> +
>  static int ath10k_setup_msa_resources(struct ath10k *ar, u32 msa_size)
>  {
>  	struct device *dev = ar->dev;
> @@ -1740,10 +1805,19 @@ static int ath10k_snoc_probe(struct platform_device *pdev)
>  		goto err_fw_deinit;
>  	}
>  
> +	ret = ath10k_modem_init(ar);
> +	if (ret) {
> +		ath10k_err(ar, "failed to initialize modem notifier: %d\n", ret);

nit: ath10k_modem_init() encapsulates/hides the setup of the notifier,
the error message should be inside the function, as for _deinit()

Reviewed-by: Matthias Kaehlcke <mka at chromium.org>