Re: [Intel-gfx] [RFC PATCH 07/11] drm/i915: Expose PMU for Observation Architecture

On Thu, May 07, 2015 at 03:15:50PM +0100, Robert Bragg wrote:

+static int init_oa_buffer(struct perf_event *event) +{

• struct drm_i915_private *dev_priv =

• container_of(event->pmu, typeof(*dev_priv), oa_pmu.pmu);
  

• struct drm_i915_gem_object *bo;
• int ret;
• BUG_ON(!IS_HASWELL(dev_priv->dev));
• BUG_ON(!mutex_is_locked(&dev_priv->dev->struct_mutex));
• BUG_ON(dev_priv->oa_pmu.oa_buffer.obj);
• spin_lock_init(&dev_priv->oa_pmu.oa_buffer.flush_lock);
• /* NB: We over allocate the OA buffer due to the way raw sample data

• * gets copied from the gpu mapped circular buffer into the perf
  

• * circular buffer so that only one copy is required.
  

• *
  

• * For each perf sample (raw->size + 4) needs to be 8 byte aligned,
  

• * where the 4 corresponds to the 32bit raw->size member that's
  

• * added to the sample header that userspace sees.
  

• *
  

• * Due to the + 4 for the size member: when we copy a report to the
  

• * userspace facing perf buffer we always copy an additional 4 bytes
  

• * from the subsequent report to make up for the miss alignment, but
  

• * when a report is at the end of the gpu mapped buffer we need to
  

• * read 4 bytes past the end of the buffer.
  

• */
  

• bo = i915_gem_alloc_object(dev_priv->dev, OA_BUFFER_SIZE + PAGE_SIZE);
• if (bo == NULL) {

• DRM_ERROR("Failed to allocate OA buffer\n");
  

• ret = -ENOMEM;
  

• goto err;
  

• }
• dev_priv->oa_pmu.oa_buffer.obj = bo;
• ret = i915_gem_object_set_cache_level(bo, I915_CACHE_LLC);
• if (ret)

• goto err_unref;
  

• /* PreHSW required 512K alignment, HSW requires 16M */
• ret = i915_gem_obj_ggtt_pin(bo, SZ_16M, 0);
• if (ret)

• goto err_unref;
  

• dev_priv->oa_pmu.oa_buffer.gtt_offset = i915_gem_obj_ggtt_offset(bo);
• dev_priv->oa_pmu.oa_buffer.addr = vmap_oa_buffer(bo);

You can look forward to both i915_gem_object_create_internal() and i915_gem_object_pin_vmap()

• /* Pre-DevBDW: OABUFFER must be set with counters off,

• * before OASTATUS1, but after OASTATUS2 */
  

• I915_WRITE(GEN7_OASTATUS2, dev_priv->oa_pmu.oa_buffer.gtt_offset |

•    GEN7_OASTATUS2_GGTT); /* head */
  

• I915_WRITE(GEN7_OABUFFER, dev_priv->oa_pmu.oa_buffer.gtt_offset);
• I915_WRITE(GEN7_OASTATUS1, dev_priv->oa_pmu.oa_buffer.gtt_offset |

•    GEN7_OASTATUS1_OABUFFER_SIZE_16M); /* tail */
  

• DRM_DEBUG_DRIVER("OA Buffer initialized, gtt offset = 0x%x, vaddr = %p",

• 	 dev_priv->oa_pmu.oa_buffer.gtt_offset,
  

• 	 dev_priv->oa_pmu.oa_buffer.addr);
  

• return 0;

+err_unref:

• drm_gem_object_unreference_unlocked(&bo->base);

But what I really what to say was: mutex deadlock^^^ -Chris