diff options
Diffstat (limited to 'drivers/gpu/drm/i915/i915_pmu.c')
| -rw-r--r-- | drivers/gpu/drm/i915/i915_pmu.c | 93 |
1 files changed, 45 insertions, 48 deletions
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index b745c49a5af6..8fe46ee920a0 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -6,9 +6,12 @@ #include <linux/irq.h> #include <linux/pm_runtime.h> -#include "i915_pmu.h" -#include "intel_ringbuffer.h" + +#include "gt/intel_engine.h" + #include "i915_drv.h" +#include "i915_pmu.h" +#include "intel_pm.h" /* Frequency for the sampling timer for events which need it. */ #define FREQUENCY 200 @@ -102,7 +105,7 @@ static bool pmu_needs_timer(struct drm_i915_private *i915, bool gpu_active) * * Use RCS as proxy for all engines. */ - else if (intel_engine_supports_stats(i915->engine[RCS])) + else if (intel_engine_supports_stats(i915->engine[RCS0])) enable &= ~BIT(I915_SAMPLE_BUSY); /* @@ -149,14 +152,6 @@ void i915_pmu_gt_unparked(struct drm_i915_private *i915) spin_unlock_irq(&i915->pmu.lock); } -static bool grab_forcewake(struct drm_i915_private *i915, bool fw) -{ - if (!fw) - intel_uncore_forcewake_get(i915, FORCEWAKE_ALL); - - return true; -} - static void add_sample(struct i915_pmu_sample *sample, u32 val) { @@ -169,51 +164,50 @@ engines_sample(struct drm_i915_private *dev_priv, unsigned int period_ns) struct intel_engine_cs *engine; enum intel_engine_id id; intel_wakeref_t wakeref; - bool fw = false; + unsigned long flags; if ((dev_priv->pmu.enable & ENGINE_SAMPLE_MASK) == 0) return; - if (!dev_priv->gt.awake) - return; - - wakeref = intel_runtime_pm_get_if_in_use(dev_priv); + wakeref = 0; + if (READ_ONCE(dev_priv->gt.awake)) + wakeref = intel_runtime_pm_get_if_in_use(&dev_priv->runtime_pm); if (!wakeref) return; + spin_lock_irqsave(&dev_priv->uncore.lock, flags); for_each_engine(engine, dev_priv, id) { - u32 current_seqno = intel_engine_get_seqno(engine); - u32 last_seqno = intel_engine_last_submit(engine); + struct intel_engine_pmu *pmu = &engine->pmu; + bool busy; u32 val; - val = !i915_seqno_passed(current_seqno, last_seqno); - - if (val) - add_sample(&engine->pmu.sample[I915_SAMPLE_BUSY], - period_ns); - - if (val && (engine->pmu.enable & - (BIT(I915_SAMPLE_WAIT) | BIT(I915_SAMPLE_SEMA)))) { - fw = grab_forcewake(dev_priv, fw); - - val = I915_READ_FW(RING_CTL(engine->mmio_base)); - } else { - val = 0; - } + val = I915_READ_FW(RING_CTL(engine->mmio_base)); + if (val == 0) /* powerwell off => engine idle */ + continue; if (val & RING_WAIT) - add_sample(&engine->pmu.sample[I915_SAMPLE_WAIT], - period_ns); - + add_sample(&pmu->sample[I915_SAMPLE_WAIT], period_ns); if (val & RING_WAIT_SEMAPHORE) - add_sample(&engine->pmu.sample[I915_SAMPLE_SEMA], - period_ns); - } + add_sample(&pmu->sample[I915_SAMPLE_SEMA], period_ns); - if (fw) - intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); + /* + * While waiting on a semaphore or event, MI_MODE reports the + * ring as idle. However, previously using the seqno, and with + * execlists sampling, we account for the ring waiting as the + * engine being busy. Therefore, we record the sample as being + * busy if either waiting or !idle. + */ + busy = val & (RING_WAIT_SEMAPHORE | RING_WAIT); + if (!busy) { + val = I915_READ_FW(RING_MI_MODE(engine->mmio_base)); + busy = !(val & MODE_IDLE); + } + if (busy) + add_sample(&pmu->sample[I915_SAMPLE_BUSY], period_ns); + } + spin_unlock_irqrestore(&dev_priv->uncore.lock, flags); - intel_runtime_pm_put(dev_priv, wakeref); + intel_runtime_pm_put(&dev_priv->runtime_pm, wakeref); } static void @@ -233,9 +227,12 @@ frequency_sample(struct drm_i915_private *dev_priv, unsigned int period_ns) if (dev_priv->gt.awake) { intel_wakeref_t wakeref; - with_intel_runtime_pm_if_in_use(dev_priv, wakeref) - val = intel_get_cagf(dev_priv, - I915_READ_NOTRACE(GEN6_RPSTAT1)); + with_intel_runtime_pm_if_in_use(&dev_priv->runtime_pm, + wakeref) { + val = intel_uncore_read_notrace(&dev_priv->uncore, + GEN6_RPSTAT1); + val = intel_get_cagf(dev_priv, val); + } } add_sample_mult(&dev_priv->pmu.sample[__I915_SAMPLE_FREQ_ACT], @@ -447,14 +444,15 @@ static u64 __get_rc6(struct drm_i915_private *i915) static u64 get_rc6(struct drm_i915_private *i915) { #if IS_ENABLED(CONFIG_PM) + struct intel_runtime_pm *rpm = &i915->runtime_pm; intel_wakeref_t wakeref; unsigned long flags; u64 val; - wakeref = intel_runtime_pm_get_if_in_use(i915); + wakeref = intel_runtime_pm_get_if_in_use(rpm); if (wakeref) { val = __get_rc6(i915); - intel_runtime_pm_put(i915, wakeref); + intel_runtime_pm_put(rpm, wakeref); /* * If we are coming back from being runtime suspended we must @@ -473,8 +471,7 @@ static u64 get_rc6(struct drm_i915_private *i915) spin_unlock_irqrestore(&i915->pmu.lock, flags); } else { - struct pci_dev *pdev = i915->drm.pdev; - struct device *kdev = &pdev->dev; + struct device *kdev = rpm->kdev; /* * We are runtime suspended. |