On 10/06/2019 18:25, Kenneth Graunke wrote:
On Monday, June 10, 2019 1:19:14 AM PDT Lionel Landwerlin wrote:We got the wrong offsets (could they have changed?). New values were computed off an error state by looking up the register offset in the context image as written by the HW. Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@xxxxxxxxx> Fixes: 1de401c08fa805 ("drm/i915/perf: enable perf support on ICL") --- drivers/gpu/drm/i915/i915_perf.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 4a767087de27..6c85191fc6c9 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -3612,9 +3612,13 @@ void i915_perf_init(struct drm_i915_private *dev_priv) dev_priv->perf.oa.ops.enable_metric_set = gen8_enable_metric_set; dev_priv->perf.oa.ops.disable_metric_set = gen10_disable_metric_set;- dev_priv->perf.oa.ctx_oactxctrl_offset = 0x128;- dev_priv->perf.oa.ctx_flexeu0_offset = 0x3de; - + if (IS_GEN(dev_priv, 10)) { + dev_priv->perf.oa.ctx_oactxctrl_offset = 0x128; + dev_priv->perf.oa.ctx_flexeu0_offset = 0x3de; + } else { + dev_priv->perf.oa.ctx_oactxctrl_offset = 0x124; + dev_priv->perf.oa.ctx_flexeu0_offset = 0x78e; + } dev_priv->perf.oa.gen8_valid_ctx_bit = (1<<16); } }Sounds believable. Acked-by: Kenneth Graunke <kenneth@xxxxxxxxxxxxx>
Thanks Ken. This was confirmed to fix the issue seen in performance queries. Is a Acked-by enough to land this? Could someone else maybe review? Thanks a lot, -Lionel _______________________________________________ Intel-gfx mailing list Intel-gfx@xxxxxxxxxxxxxxxxxxxxx https://lists.freedesktop.org/mailman/listinfo/intel-gfx
