[Intel-gfx] [PATCH 3/5] drm/i915/error: report ctx id & desc for each request in the queue

[Mika Kuoppala]

Arun Siluvery <arun.siluvery at linux.intel.com> writes:

> From: Dave Gordon <david.s.gordon at intel.com>
>
> Also decode and output CSB entries, in time order
>

Traditionally we have had the decoding burden in
igt/tools/intel_error_decode.

Is there reason not to follow that pattern?
-Mika


> For: VIZ-2021
> Signed-off-by: Dave Gordon <david.s.gordon at intel.com>
> ---
>  drivers/gpu/drm/i915/i915_drv.h       |  1 +
>  drivers/gpu/drm/i915/i915_gpu_error.c | 37 +++++++++++++++++++++++++++--------
>  2 files changed, 30 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index 8b510fb..239aaed 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -568,6 +568,7 @@ struct drm_i915_error_state {
>  		} *req_ringbuffer, *hw_ringbuffer, *batchbuffer, *wa_batchbuffer, *ctx, *hws_page;
>  
>  		struct drm_i915_error_request {
> +			uint64_t ctx_desc;
>  			long jiffies;
>  			u32 seqno;
>  			u32 tail;
> diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
> index 5c8ec63..a88160c 100644
> --- a/drivers/gpu/drm/i915/i915_gpu_error.c
> +++ b/drivers/gpu/drm/i915/i915_gpu_error.c
> @@ -311,9 +311,25 @@ static void i915_ring_error_state(struct drm_i915_error_state_buf *m,
>  	err_printf(m, "  EXECLIST_CSB_WR: 0x%08x\n", ring->execlist_csb_write_pointer);
>  	err_printf(m, "  EXECLIST_CSB_RD: 0x%08x\n", ring->execlist_csb_read_pointer);
>  
> -	for (i = 0; i < 6; i++) {
> -		err_printf(m, "  EXECLIST_CSB[%d]: 0x%08x\n", i, ring->execlist_csb[i]);
> -		err_printf(m, "  EXECLIST_CTX[%d]: 0x%08x\n", i, ring->execlist_ctx[i]);
> +#define GEN8_CTX_STATUS_IDLE_ACTIVE	(1 << 0)
> +#define GEN8_CTX_STATUS_PREEMPTED	(1 << 1)
> +#define GEN8_CTX_STATUS_ELEMENT_SWITCH	(1 << 2)
> +#define GEN8_CTX_STATUS_ACTIVE_IDLE	(1 << 3)
> +#define GEN8_CTX_STATUS_COMPLETE	(1 << 4)
> +#define GEN8_CTX_STATUS_LITE_RESTORE	(1 << 15)
> +
> +	for (i = 1; i <= 6; ++i) {
> +		int n = (ring->execlist_csb_write_pointer + i) % 6;
> +		u32 csb = ring->execlist_csb[n];
> +		err_printf(m, "  EXECLIST_CTX/CSB[%d]:  0x%08x  0x%08x  ",
> +			n, ring->execlist_ctx[n], csb);
> +		err_printf(m, "%s %s %s %s %s %s\n",
> +			csb & GEN8_CTX_STATUS_IDLE_ACTIVE	? "I->A" : "    ",
> +			csb & GEN8_CTX_STATUS_PREEMPTED		? "PRMT" : "    ",
> +			csb & GEN8_CTX_STATUS_ELEMENT_SWITCH	? "ELSW" : "    ",
> +			csb & GEN8_CTX_STATUS_ACTIVE_IDLE	? "A->I" : "    ",
> +			csb & GEN8_CTX_STATUS_COMPLETE		? "DONE" : "    ",
> +			csb & GEN8_CTX_STATUS_LITE_RESTORE	? "LITE" : "    ");
>  	}
>  }
>  
> @@ -468,10 +484,13 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
>  				   dev_priv->ring[i].name,
>  				   error->ring[i].num_requests);
>  			for (j = 0; j < error->ring[i].num_requests; j++) {
> -				err_printf(m, "  seqno 0x%08x, emitted %ld, tail 0x%08x\n",
> -					   error->ring[i].requests[j].seqno,
> -					   error->ring[i].requests[j].jiffies,
> -					   error->ring[i].requests[j].tail);
> +				struct drm_i915_error_request *erq;
> +				erq = &error->ring[i].requests[j];
> +				err_printf(m, "  seqno 0x%08x, tail 0x%08x, "
> +					"emitted %ld, ctx_desc 0x%08x_%08x\n",
> +					erq->seqno, erq->tail, erq->jiffies,
> +					upper_32_bits(erq->ctx_desc),
> +					lower_32_bits(erq->ctx_desc));
>  			}
>  		}
>  
> @@ -1130,6 +1149,7 @@ static void i915_gem_record_rings(struct drm_device *dev,
>  
>  		count = 0;
>  		list_for_each_entry(request, &ring->request_list, list) {
> +			struct intel_context *ctx = request->ctx;
>  			struct drm_i915_error_request *erq;
>  
>  			if (count >= error->ring[i].num_requests) {
> @@ -1152,8 +1172,9 @@ static void i915_gem_record_rings(struct drm_device *dev,
>  			}
>  
>  			erq = &error->ring[i].requests[count++];
> -			erq->seqno = request->seqno;
> +			erq->ctx_desc = intel_lr_context_descriptor(ctx, ring);
>  			erq->jiffies = request->emitted_jiffies;
> +			erq->seqno = request->seqno;
>  			erq->tail = request->postfix;
>  		}
>  	}
> -- 
> 1.9.1