Re: [PATCH v2 3/3] gpu: host1x: Continue CDMA execution starting with a next job

[Mikko Perttunen <cyndis@kapsi.fi>]

Reviewed-by: Mikko Perttnuen <mperttunen@nvidia.com>

On 07/08/2018 22.07, Dmitry Osipenko wrote:
> Currently gathers of a hung job are getting NOP'ed and a restarted CDMA
> executes the NOP'ed gathers. There shouldn't be a reason to not restart
> CDMA execution starting with a next job, avoiding the unnecessary churning
> with gathers NOP'ing.
> 
> Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
> ---
>   drivers/gpu/host1x/cdma.c       | 23 +++++++++++------------
>   drivers/gpu/host1x/hw/cdma_hw.c | 13 -------------
>   2 files changed, 11 insertions(+), 25 deletions(-)
> 
> diff --git a/drivers/gpu/host1x/cdma.c b/drivers/gpu/host1x/cdma.c
> index 6aa6fa1498e8..9e4f01c7f663 100644
> --- a/drivers/gpu/host1x/cdma.c
> +++ b/drivers/gpu/host1x/cdma.c
> @@ -323,7 +323,7 @@ void host1x_cdma_update_sync_queue(struct host1x_cdma *cdma,
>   {
>   	struct host1x *host1x = cdma_to_host1x(cdma);
>   	u32 restart_addr, syncpt_incrs, syncpt_val;
> -	struct host1x_job *job;
> +	struct host1x_job *job, *next_job = NULL;
>   
>   	syncpt_val = host1x_syncpt_load(cdma->timeout.syncpt);
>   
> @@ -341,8 +341,13 @@ void host1x_cdma_update_sync_queue(struct host1x_cdma *cdma,
>   		__func__);
>   
>   	list_for_each_entry(job, &cdma->sync_queue, list) {
> -		if (syncpt_val < job->syncpt_end)
> +		if (syncpt_val < job->syncpt_end) {
> +
> +			if (!list_is_last(&job->list, &cdma->sync_queue))
> +				next_job = list_next_entry(job, list);
> +
>   			goto syncpt_incr;
> +		}
>   
>   		host1x_job_dump(dev, job);
>   	}
> @@ -355,17 +360,11 @@ void host1x_cdma_update_sync_queue(struct host1x_cdma *cdma,
>   	/*
>   	 * Increment with CPU the remaining syncpts of a partially executed job.
>   	 *
> -	 * Syncpt increments must be done inline with the pushbuffer from a
> -	 * GATHER buffer to maintain the order (slots are modified to be a
> -	 * GATHER of syncpt incrs).
> -	 *
> -	 * Note: save in restart_addr the location where the timed out buffer
> -	 * started in the PB, so we can start the refetch from there (with the
> -	 * modified NOP-ed PB slots). This lets things appear to have completed
> -	 * properly for this buffer and resources are freed.
> +	 * CDMA will continue execution starting with the next job or will get
> +	 * into idle state.
>   	 */
> -	if (job)
> -		restart_addr = job->first_get;
> +	if (next_job)
> +		restart_addr = next_job->first_get;
>   	else
>   		restart_addr = cdma->last_pos;
>   
> diff --git a/drivers/gpu/host1x/hw/cdma_hw.c b/drivers/gpu/host1x/hw/cdma_hw.c
> index ce320534cbed..bc203532ae6d 100644
> --- a/drivers/gpu/host1x/hw/cdma_hw.c
> +++ b/drivers/gpu/host1x/hw/cdma_hw.c
> @@ -40,7 +40,6 @@ static void cdma_timeout_cpu_incr(struct host1x_cdma *cdma, u32 getptr,
>   				u32 syncpt_incrs, u32 syncval, u32 nr_slots)
>   {
>   	struct host1x *host1x = cdma_to_host1x(cdma);
> -	struct push_buffer *pb = &cdma->push_buffer;
>   	unsigned int i;
>   
>   	for (i = 0; i < syncpt_incrs; i++)
> @@ -48,18 +47,6 @@ static void cdma_timeout_cpu_incr(struct host1x_cdma *cdma, u32 getptr,
>   
>   	/* after CPU incr, ensure shadow is up to date */
>   	host1x_syncpt_load(cdma->timeout.syncpt);
> -
> -	/* NOP all the PB slots */
> -	while (nr_slots--) {
> -		u32 *p = (u32 *)(pb->mapped + getptr);
> -		*(p++) = HOST1X_OPCODE_NOP;
> -		*(p++) = HOST1X_OPCODE_NOP;
> -		dev_dbg(host1x->dev, "%s: NOP at %pad+%#x\n", __func__,
> -			&pb->dma, getptr);
> -		getptr = (getptr + 8) & (pb->size - 1);
> -	}
> -
> -	wmb();
>   }
>   
>   /*
>