[RFC 1/9] drm/xe: Error handling in xe_force_wake_get()

[Jani Nikula]

On Fri, 30 Aug 2024, Himal Prasad Ghimiray <himal.prasad.ghimiray at intel.com> wrote:
> If an acknowledgment timeout occurs for a domain awake request, put to
> sleep all domains awakened by the caller and decrease the reference
> count for all requested domains. This prevents xe_force_wake_get() from
> leaving an unhandled reference count in case of failure.
> While at it, add simple kernel-doc for xe_force_wake_get() and
> xe_force_wake_put() functions.
>
> Cc: Badal Nilawar <badal.nilawar at intel.com>
> Cc: Rodrigo Vivi <rodrigo.vivi at intel.com>
> Cc: Lucas De Marchi <lucas.demarchi at intel.com>
> Cc: Nirmoy Das <nirmoy.das at intel.com>
> Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray at intel.com>
> ---
>  drivers/gpu/drm/xe/xe_force_wake.c | 52 +++++++++++++++++++++++++++---
>  1 file changed, 47 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/gpu/drm/xe/xe_force_wake.c b/drivers/gpu/drm/xe/xe_force_wake.c
> index b263fff15273..8aa8d9b41052 100644
> --- a/drivers/gpu/drm/xe/xe_force_wake.c
> +++ b/drivers/gpu/drm/xe/xe_force_wake.c
> @@ -150,31 +150,73 @@ static int domain_sleep_wait(struct xe_gt *gt,
>  					 (ffs(tmp__) - 1))) && \
>  					 domain__->reg_ctl.addr)
>  
> +/**
> + * xe_force_wake_get : Increase the domain refcount; if it was 0 initially, wake the domain
> + * @fw: struct xe_force_wake
> + * @domains: forcewake domains to get refcount on
> + *
> + * Increment refcount for the force-wake domain. If the domain is
> + * asleep, awaken it and wait for acknowledgment within the specified
> + * timeout. If a timeout occurs, decrement the refcount and put the
> + * caller awaken domains to sleep.
> + *
> + * Return: 0 on success or 1 on ack timeout from domains.

Please stick to conventions on error returns, i.e. please use defined
negative error values instead of magic 1.

> + */
>  int xe_force_wake_get(struct xe_force_wake *fw,
>  		      enum xe_force_wake_domains domains)
>  {
>  	struct xe_gt *gt = fw->gt;
>  	struct xe_force_wake_domain *domain;
> -	enum xe_force_wake_domains tmp, woken = 0;
> +	enum xe_force_wake_domains tmp, awake_rqst = 0, awake_ack = 0;
>  	unsigned long flags;
>  	int ret = 0;
>  
>  	spin_lock_irqsave(&fw->lock, flags);
>  	for_each_fw_domain_masked(domain, domains, fw, tmp) {
>  		if (!domain->ref++) {
> -			woken |= BIT(domain->id);
> +			awake_rqst |= BIT(domain->id);
>  			domain_wake(gt, domain);
>  		}
>  	}
> -	for_each_fw_domain_masked(domain, woken, fw, tmp) {
> -		ret |= domain_wake_wait(gt, domain);
> +	for_each_fw_domain_masked(domain, awake_rqst, fw, tmp) {
> +		if (domain_wake_wait(gt, domain) == 0)
> +			awake_ack |= BIT(domain->id);
> +	}
> +
> +	ret = (awake_ack == awake_rqst) ? 0 : 1;
> +
> +	/*
> +	 * If @domains is XE_FORCEWAKE_ALL and an acknowledgment times out
> +	 * for any domain, decrease the reference count and put the awake
> +	 * domains to sleep. For individual domains, just decrement the
> +	 * reference count.
> +	 */
> +	if (ret) {
> +		for_each_fw_domain_masked(domain, awake_rqst, fw, tmp) {
> +			if (!--domain->ref && (awake_ack & BIT(domain->id)))
> +				domain_sleep(gt, domain);
> +		}
> +		awake_ack = 0;
>  	}
> -	fw->awake_domains |= woken;
> +
> +	fw->awake_domains |= awake_ack;
>  	spin_unlock_irqrestore(&fw->lock, flags);
>  
>  	return ret;
>  }
>  
> +/**
> + * xe_force_wake_put - Decrement the refcount and put domain to sleep if refcount becomes 0
> + * @fw: Pointer to the force wake structure
> + * @domains: forcewake domains to put reference
> + *
> + * This function reduces the reference counts for specified domains. If
> + * refcount for any of the specified domain reaches 0, it puts the domain to sleep
> + * and waits for acknowledgment for domain to sleep within specified timeout.
> + * Ensure this function is called only in case of successful xe_force_wake_get().
> + *
> + * Returns 0 in case of success or non-zero in case of timeout of ack
> + */
>  int xe_force_wake_put(struct xe_force_wake *fw,
>  		      enum xe_force_wake_domains domains)
>  {

-- 
Jani Nikula, Intel