Re: [PATCH 16/17] coresight: perf: Remove reset_buffer call back for sinks

[Mathieu Poirier]

On Thu, Oct 19, 2017 at 06:15:52PM +0100, Suzuki K Poulose wrote:
> Right now we issue an update_buffer() and reset_buffer() call backs
> in succession when we stop tracing an event. The update_buffer is
> supposed to check the status of the buffer and make sure the ring buffer
> is updated with the trace data. And we store information about the
> size of the data collected only to be consumed by the reset_buffer
> callback which always follows the update_buffer. This patch gets
> rid of the reset_buffer callback altogether and performs the actions
> in update_buffer, making it return the size collected.
> 
> This removes some not-so pretty hack (storing the new head in the
> size field for snapshot mode) and cleans it up a little bit.

The idea in splitting the update and reset operation was to seamlessly support
sinks that generate an interrupt when their buffer gets full.  Those are coming
and when we do need to support them we'll find ourselves splitting the update
and reset operation again.   

See comment below.

> 
> Cc: Mathieu Poirier <mathieu.poirier@xxxxxxxxxx>
> Signed-off-by: Suzuki K Poulose <suzuki.poulose@xxxxxxx>
> ---
>  drivers/hwtracing/coresight/coresight-etb10.c    | 56 +++++------------------
>  drivers/hwtracing/coresight/coresight-etm-perf.c |  9 +---
>  drivers/hwtracing/coresight/coresight-tmc-etf.c  | 58 +++++-------------------
>  include/linux/coresight.h                        |  5 +-
>  4 files changed, 26 insertions(+), 102 deletions(-)
> 
> diff --git a/drivers/hwtracing/coresight/coresight-etb10.c b/drivers/hwtracing/coresight/coresight-etb10.c
> index 757f556975f7..75c5699000b0 100644
> --- a/drivers/hwtracing/coresight/coresight-etb10.c
> +++ b/drivers/hwtracing/coresight/coresight-etb10.c
> @@ -323,37 +323,7 @@ static int etb_set_buffer(struct coresight_device *csdev,
>  	return ret;
>  }
>  
> -static unsigned long etb_reset_buffer(struct coresight_device *csdev,
> -				      struct perf_output_handle *handle,
> -				      void *sink_config)
> -{
> -	unsigned long size = 0;
> -	struct cs_buffers *buf = sink_config;
> -
> -	if (buf) {
> -		/*
> -		 * In snapshot mode ->data_size holds the new address of the
> -		 * ring buffer's head.  The size itself is the whole address
> -		 * range since we want the latest information.
> -		 */
> -		if (buf->snapshot)
> -			handle->head = local_xchg(&buf->data_size,
> -						  buf->nr_pages << PAGE_SHIFT);
> -
> -		/*
> -		 * Tell the tracer PMU how much we got in this run and if
> -		 * something went wrong along the way.  Nobody else can use
> -		 * this cs_buffers instance until we are done.  As such
> -		 * resetting parameters here and squaring off with the ring
> -		 * buffer API in the tracer PMU is fine.
> -		 */
> -		size = local_xchg(&buf->data_size, 0);
> -	}
> -
> -	return size;
> -}
> -
> -static void etb_update_buffer(struct coresight_device *csdev,
> +static unsigned long etb_update_buffer(struct coresight_device *csdev,
>  			      struct perf_output_handle *handle,
>  			      void *sink_config)
>  {
> @@ -362,13 +332,13 @@ static void etb_update_buffer(struct coresight_device *csdev,
>  	u8 *buf_ptr;
>  	const u32 *barrier;
>  	u32 read_ptr, write_ptr, capacity;
> -	u32 status, read_data, to_read;
> -	unsigned long offset;
> +	u32 status, read_data;
> +	unsigned long offset, to_read;
>  	struct cs_buffers *buf = sink_config;
>  	struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
>  
>  	if (!buf)
> -		return;
> +		return 0;
>  
>  	capacity = drvdata->buffer_depth * ETB_FRAME_SIZE_WORDS;
>  
> @@ -473,18 +443,17 @@ static void etb_update_buffer(struct coresight_device *csdev,
>  	writel_relaxed(0x0, drvdata->base + ETB_RAM_WRITE_POINTER);
>  
>  	/*
> -	 * In snapshot mode all we have to do is communicate to
> -	 * perf_aux_output_end() the address of the current head.  In full
> -	 * trace mode the same function expects a size to move rb->aux_head
> -	 * forward.
> +	 * In snapshot mode we have to update the handle->head to point
> +	 * to the new location.
>  	 */
> -	if (buf->snapshot)
> -		local_set(&buf->data_size, (cur * PAGE_SIZE) + offset);
> -	else
> -		local_add(to_read, &buf->data_size);
> -
> +	if (buf->snapshot) {
> +		handle->head = (cur * PAGE_SIZE) + offset;
> +		to_read = buf->nr_pages << PAGE_SHIFT;
> +	}
>  	etb_enable_hw(drvdata);
>  	CS_LOCK(drvdata->base);
> +
> +	return to_read;
>  }
>  
>  static const struct coresight_ops_sink etb_sink_ops = {
> @@ -493,7 +462,6 @@ static const struct coresight_ops_sink etb_sink_ops = {
>  	.alloc_buffer	= etb_alloc_buffer,
>  	.free_buffer	= etb_free_buffer,
>  	.set_buffer	= etb_set_buffer,
> -	.reset_buffer	= etb_reset_buffer,
>  	.update_buffer	= etb_update_buffer,
>  };
>  
> diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c
> index 8a0ad77574e7..e5f9567c87c4 100644
> --- a/drivers/hwtracing/coresight/coresight-etm-perf.c
> +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c
> @@ -342,15 +342,8 @@ static void etm_event_stop(struct perf_event *event, int mode)
>  		if (!sink_ops(sink)->update_buffer)
>  			return;
>  
> -		sink_ops(sink)->update_buffer(sink, handle,
> +		size = sink_ops(sink)->update_buffer(sink, handle,
>  					      event_data->snk_config);
> -
> -		if (!sink_ops(sink)->reset_buffer)
> -			return;
> -
> -		size = sink_ops(sink)->reset_buffer(sink, handle,
> -						    event_data->snk_config);

For the current sink we support, i.e those that don't generate interrupts when
their buffer is full, I'm in agreement with your work.  I suggest you don't
touch the current implementation of etm_event_stop() and move everything you've
done to the reset operation.  The end result is the same and we don't have to
rework (again) etm_event_stop() when we need to support IPs that do send
interrupts.

> -
>  		perf_aux_output_end(handle, size);
>  	}
>  
> diff --git a/drivers/hwtracing/coresight/coresight-tmc-etf.c b/drivers/hwtracing/coresight/coresight-tmc-etf.c
> index aa4e8f03ef49..073198e7b46e 100644
> --- a/drivers/hwtracing/coresight/coresight-tmc-etf.c
> +++ b/drivers/hwtracing/coresight/coresight-tmc-etf.c
> @@ -358,36 +358,7 @@ static int tmc_set_etf_buffer(struct coresight_device *csdev,
>  	return ret;
>  }
>  
> -static unsigned long tmc_reset_etf_buffer(struct coresight_device *csdev,
> -					  struct perf_output_handle *handle,
> -					  void *sink_config)
> -{
> -	long size = 0;
> -	struct cs_buffers *buf = sink_config;
> -
> -	if (buf) {
> -		/*
> -		 * In snapshot mode ->data_size holds the new address of the
> -		 * ring buffer's head.  The size itself is the whole address
> -		 * range since we want the latest information.
> -		 */
> -		if (buf->snapshot)
> -			handle->head = local_xchg(&buf->data_size,
> -						  buf->nr_pages << PAGE_SHIFT);
> -		/*
> -		 * Tell the tracer PMU how much we got in this run and if
> -		 * something went wrong along the way.  Nobody else can use
> -		 * this cs_buffers instance until we are done.  As such
> -		 * resetting parameters here and squaring off with the ring
> -		 * buffer API in the tracer PMU is fine.
> -		 */
> -		size = local_xchg(&buf->data_size, 0);
> -	}
> -
> -	return size;
> -}
> -
> -static void tmc_update_etf_buffer(struct coresight_device *csdev,
> +static unsigned long tmc_update_etf_buffer(struct coresight_device *csdev,
>  				  struct perf_output_handle *handle,
>  				  void *sink_config)
>  {
> @@ -396,17 +367,17 @@ static void tmc_update_etf_buffer(struct coresight_device *csdev,
>  	const u32 *barrier;
>  	u32 *buf_ptr;
>  	u64 read_ptr, write_ptr;
> -	u32 status, to_read;
> -	unsigned long offset;
> +	u32 status;
> +	unsigned long offset, to_read;
>  	struct cs_buffers *buf = sink_config;
>  	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
>  
>  	if (!buf)
> -		return;
> +		return 0;
>  
>  	/* This shouldn't happen */
>  	if (WARN_ON_ONCE(drvdata->mode != CS_MODE_PERF))
> -		return;
> +		return 0;
>  
>  	CS_UNLOCK(drvdata->base);
>  
> @@ -495,18 +466,14 @@ static void tmc_update_etf_buffer(struct coresight_device *csdev,
>  		}
>  	}
>  
> -	/*
> -	 * In snapshot mode all we have to do is communicate to
> -	 * perf_aux_output_end() the address of the current head.  In full
> -	 * trace mode the same function expects a size to move rb->aux_head
> -	 * forward.
> -	 */
> -	if (buf->snapshot)
> -		local_set(&buf->data_size, (cur * PAGE_SIZE) + offset);
> -	else
> -		local_add(to_read, &buf->data_size);
> -
> +	/* In snapshot mode we have to update the head */
> +	if (buf->snapshot) {
> +		handle->head = (cur * PAGE_SIZE) + offset;
> +		to_read = buf->nr_pages << PAGE_SHIFT;
> +	}
>  	CS_LOCK(drvdata->base);
> +
> +	return to_read;
>  }
>  
>  static const struct coresight_ops_sink tmc_etf_sink_ops = {
> @@ -515,7 +482,6 @@ static const struct coresight_ops_sink tmc_etf_sink_ops = {
>  	.alloc_buffer	= tmc_alloc_etf_buffer,
>  	.free_buffer	= tmc_free_etf_buffer,
>  	.set_buffer	= tmc_set_etf_buffer,
> -	.reset_buffer	= tmc_reset_etf_buffer,
>  	.update_buffer	= tmc_update_etf_buffer,
>  };
>  
> diff --git a/include/linux/coresight.h b/include/linux/coresight.h
> index d950dad5056a..5c9e5fe2bf32 100644
> --- a/include/linux/coresight.h
> +++ b/include/linux/coresight.h
> @@ -199,10 +199,7 @@ struct coresight_ops_sink {
>  	int (*set_buffer)(struct coresight_device *csdev,
>  			  struct perf_output_handle *handle,
>  			  void *sink_config);
> -	unsigned long (*reset_buffer)(struct coresight_device *csdev,
> -				      struct perf_output_handle *handle,
> -				      void *sink_config);
> -	void (*update_buffer)(struct coresight_device *csdev,
> +	unsigned long (*update_buffer)(struct coresight_device *csdev,
>  			      struct perf_output_handle *handle,
>  			      void *sink_config);
>  };
> -- 
> 2.13.6
>