From 8f48de49795ca52f70c96558ccc6a0c174504779 Mon Sep 17 00:00:00 2001 From: Lionel Landwerlin Date: Wed, 10 Jul 2019 11:55:24 +0100 Subject: [PATCH] drm/i915/perf: add missing delay for OA muxes configuration This was dropped from the original patch series, we weren't sure whether it was needed at the time. More recent tests show it's definitely needed to have acurate performance data. Signed-off-by: Lionel Landwerlin Fixes: 19f81df2859eb1 ("drm/i915/perf: Add OA unit support for Gen 8+") Acked-by: Chris Wilson [ickle: combine duplicate code and comments] Signed-off-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/20190710105524.23017-1-chris@chris-wilson.co.uk (cherry picked from commit 14bfcd3e0daeb0f757a02aac85fd03e0933ab37e) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_perf.c | 49 ++++++++++++++++++-------------- 1 file changed, 28 insertions(+), 21 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 629511ea9a18..5140017f9a39 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -1567,28 +1567,10 @@ static void config_oa_regs(struct drm_i915_private *dev_priv, } } -static int hsw_enable_metric_set(struct i915_perf_stream *stream) +static void delay_after_mux(void) { - struct drm_i915_private *dev_priv = stream->dev_priv; - const struct i915_oa_config *oa_config = stream->oa_config; - - /* PRM: - * - * OA unit is using “crclk” for its functionality. When trunk - * level clock gating takes place, OA clock would be gated, - * unable to count the events from non-render clock domain. - * Render clock gating must be disabled when OA is enabled to - * count the events from non-render domain. Unit level clock - * gating for RCS should also be disabled. - */ - I915_WRITE(GEN7_MISCCPCTL, (I915_READ(GEN7_MISCCPCTL) & - ~GEN7_DOP_CLOCK_GATE_ENABLE)); - I915_WRITE(GEN6_UCGCTL1, (I915_READ(GEN6_UCGCTL1) | - GEN6_CSUNIT_CLOCK_GATE_DISABLE)); - - config_oa_regs(dev_priv, oa_config->mux_regs, oa_config->mux_regs_len); - - /* It apparently takes a fairly long time for a new MUX + /* + * It apparently takes a fairly long time for a new MUX * configuration to be be applied after these register writes. * This delay duration was derived empirically based on the * render_basic config but hopefully it covers the maximum @@ -1610,6 +1592,30 @@ static int hsw_enable_metric_set(struct i915_perf_stream *stream) * a delay at this location would mitigate any invalid reports. */ usleep_range(15000, 20000); +} + +static int hsw_enable_metric_set(struct i915_perf_stream *stream) +{ + struct drm_i915_private *dev_priv = stream->dev_priv; + const struct i915_oa_config *oa_config = stream->oa_config; + + /* + * PRM: + * + * OA unit is using “crclk” for its functionality. When trunk + * level clock gating takes place, OA clock would be gated, + * unable to count the events from non-render clock domain. + * Render clock gating must be disabled when OA is enabled to + * count the events from non-render domain. Unit level clock + * gating for RCS should also be disabled. + */ + I915_WRITE(GEN7_MISCCPCTL, (I915_READ(GEN7_MISCCPCTL) & + ~GEN7_DOP_CLOCK_GATE_ENABLE)); + I915_WRITE(GEN6_UCGCTL1, (I915_READ(GEN6_UCGCTL1) | + GEN6_CSUNIT_CLOCK_GATE_DISABLE)); + + config_oa_regs(dev_priv, oa_config->mux_regs, oa_config->mux_regs_len); + delay_after_mux(); config_oa_regs(dev_priv, oa_config->b_counter_regs, oa_config->b_counter_regs_len); @@ -1835,6 +1841,7 @@ static int gen8_enable_metric_set(struct i915_perf_stream *stream) return ret; config_oa_regs(dev_priv, oa_config->mux_regs, oa_config->mux_regs_len); + delay_after_mux(); config_oa_regs(dev_priv, oa_config->b_counter_regs, oa_config->b_counter_regs_len);