Re: [PATCH 4/4] remoteproc: k3-r5: support for graceful stop of remote cores

[Mathieu Poirier <mathieu.poirier@linaro.org>]

On Fri, Jun 21, 2024 at 05:00:58PM +0200, Richard Genoud wrote:
> Introduce software IPC handshake between the K3-R5 remote proc driver
> and the R5 MCU to gracefully stop/reset the remote core.
> 
> Upon a stop request, K3-R5 remote proc driver sends a RP_MBOX_SHUTDOWN
> mailbox message to the remote R5 core.
> The remote core is expected to:
> - relinquish all the resources acquired through Device Manager (DM)
> - disable its interrupts
> - send back a mailbox acknowledgment RP_MBOX_SHUDOWN_ACK
> - enter WFI state.
> 
> Meanwhile, the K3-R5 remote proc driver does:
> - wait for the RP_MBOX_SHUTDOWN_ACK from the remote core
> - wait for the remote proc to enter WFI state
> - reset the remote core through device manager
> 
> Based on work from: Hari Nagalla <hnagalla@ti.com>
>

Why is this needed now and what happens to system with a new kernel driver and
an older K3R5 firmware?

Thanks,
Mathieu

> Signed-off-by: Richard Genoud <richard.genoud@bootlin.com>
> ---
>  drivers/remoteproc/omap_remoteproc.h     |  9 +++++-
>  drivers/remoteproc/ti_k3_r5_remoteproc.c | 40 ++++++++++++++++++++++++
>  2 files changed, 48 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/remoteproc/omap_remoteproc.h b/drivers/remoteproc/omap_remoteproc.h
> index 828e13256c02..c008f11fa2a4 100644
> --- a/drivers/remoteproc/omap_remoteproc.h
> +++ b/drivers/remoteproc/omap_remoteproc.h
> @@ -42,6 +42,11 @@
>   * @RP_MBOX_SUSPEND_CANCEL: a cancel suspend response from a remote processor
>   * on a suspend request
>   *
> + * @RP_MBOX_SHUTDOWN: shutdown request for the remote processor
> + *
> + * @RP_MBOX_SHUTDOWN_ACK: successful response from remote processor for a
> + * shutdown request. The remote processor should be in WFI state short after.
> + *
>   * Introduce new message definitions if any here.
>   *
>   * @RP_MBOX_END_MSG: Indicates end of known/defined messages from remote core
> @@ -59,7 +64,9 @@ enum omap_rp_mbox_messages {
>  	RP_MBOX_SUSPEND_SYSTEM	= 0xFFFFFF11,
>  	RP_MBOX_SUSPEND_ACK	= 0xFFFFFF12,
>  	RP_MBOX_SUSPEND_CANCEL	= 0xFFFFFF13,
> -	RP_MBOX_END_MSG		= 0xFFFFFF14,
> +	RP_MBOX_SHUTDOWN	= 0xFFFFFF14,
> +	RP_MBOX_SHUTDOWN_ACK	= 0xFFFFFF15,
> +	RP_MBOX_END_MSG		= 0xFFFFFF16,
>  };
>  
>  #endif /* _OMAP_RPMSG_H */
> diff --git a/drivers/remoteproc/ti_k3_r5_remoteproc.c b/drivers/remoteproc/ti_k3_r5_remoteproc.c
> index a2ead87952c7..918a15e1dd9a 100644
> --- a/drivers/remoteproc/ti_k3_r5_remoteproc.c
> +++ b/drivers/remoteproc/ti_k3_r5_remoteproc.c
> @@ -21,6 +21,7 @@
>  #include <linux/pm_runtime.h>
>  #include <linux/remoteproc.h>
>  #include <linux/suspend.h>
> +#include <linux/iopoll.h>
>  #include <linux/reset.h>
>  #include <linux/slab.h>
>  
> @@ -172,8 +173,23 @@ struct k3_r5_rproc {
>  	struct k3_r5_core *core;
>  	struct k3_r5_mem *rmem;
>  	int num_rmems;
> +	struct completion shutdown_complete;
>  };
>  
> +/*
> + * This will return true if the remote core is in Wait For Interrupt state.
> + */
> +static bool k3_r5_is_core_in_wfi(struct k3_r5_core *core)
> +{
> +	int ret;
> +	u64 boot_vec;
> +	u32 cfg, ctrl, stat;
> +
> +	ret = ti_sci_proc_get_status(core->tsp, &boot_vec, &cfg, &ctrl, &stat);
> +
> +	return !ret ? !!(stat & PROC_BOOT_STATUS_FLAG_R5_WFI) : false;
> +}
> +
>  /**
>   * k3_r5_rproc_mbox_callback() - inbound mailbox message handler
>   * @client: mailbox client pointer used for requesting the mailbox channel
> @@ -209,6 +225,10 @@ static void k3_r5_rproc_mbox_callback(struct mbox_client *client, void *data)
>  	case RP_MBOX_ECHO_REPLY:
>  		dev_info(dev, "received echo reply from %s\n", name);
>  		break;
> +	case RP_MBOX_SHUTDOWN_ACK:
> +		dev_dbg(dev, "received shutdown_ack from %s\n", name);
> +		complete(&kproc->shutdown_complete);
> +		break;
>  	default:
>  		/* silently handle all other valid messages */
>  		if (msg >= RP_MBOX_READY && msg < RP_MBOX_END_MSG)
> @@ -634,6 +654,7 @@ static int k3_r5_rproc_stop(struct rproc *rproc)
>  	struct k3_r5_cluster *cluster = kproc->cluster;
>  	struct device *dev = kproc->dev;
>  	struct k3_r5_core *core1, *core = kproc->core;
> +	bool wfi;
>  	int ret;
>  
>  
> @@ -650,6 +671,24 @@ static int k3_r5_rproc_stop(struct rproc *rproc)
>  		}
>  	}
>  
> +	/* Send SHUTDOWN message to remote proc */
> +	reinit_completion(&kproc->shutdown_complete);
> +	ret = mbox_send_message(kproc->mbox, (void *)RP_MBOX_SHUTDOWN);
> +	if (ret < 0) {
> +		dev_err(dev, "Sending SHUTDOWN message failed: %d. Halting core anyway.\n", ret);
> +	} else {
> +		ret = wait_for_completion_timeout(&kproc->shutdown_complete,
> +						  msecs_to_jiffies(1000));
> +		if (ret == 0) {
> +			dev_err(dev, "Timeout waiting SHUTDOWN_ACK message. Halting core anyway.\n");
> +		} else {
> +			ret = readx_poll_timeout(k3_r5_is_core_in_wfi, core,
> +						 wfi, wfi, 200, 2000);
> +			if (ret)
> +				dev_err(dev, "Timeout waiting for remote proc to be in WFI state. Halting core anyway.\n");
> +		}
> +	}
> +
>  	/* halt all applicable cores */
>  	if (cluster->mode == CLUSTER_MODE_LOCKSTEP) {
>  		list_for_each_entry(core, &cluster->cores, elem) {
> @@ -1410,6 +1449,7 @@ static int k3_r5_cluster_rproc_init(struct platform_device *pdev)
>  			goto err_config;
>  		}
>  
> +		init_completion(&kproc->shutdown_complete);
>  init_rmem:
>  		k3_r5_adjust_tcm_sizes(kproc);
>