On Mon, 09 Nov 2026, Ville Syrjala <[email protected]> wrote: > From: Ville Syrjälä <[email protected]> > > We already have GEN8_GT_IRQS to teel whether any of the GT > interrupts need processing. If none of the relevant bits are > set skip the whole gen8_gt_irq_handler(), as a micro optimization. > We already do the equivalent for the display irqs, so why not > do it for GT irqs as well. > > Originally gen8_gt_irq_handler() was a static inline, so this > probably wouldn't have made sense. But these days it's a proper > function call every time. > > Signed-off-by: Ville Syrjälä <[email protected]>
With the typo fixed, Reviewed-by: Jani Nikula <[email protected]> > --- > drivers/gpu/drm/i915/i915_irq.c | 3 ++- > 1 file changed, 2 insertions(+), 1 deletion(-) > > diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c > index 0762017d9089..448c4730d178 100644 > --- a/drivers/gpu/drm/i915/i915_irq.c > +++ b/drivers/gpu/drm/i915/i915_irq.c > @@ -455,7 +455,8 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg) > } > > /* Find, queue (onto bottom-halves), then clear each source */ > - gen8_gt_irq_handler(to_gt(dev_priv), master_ctl); > + if (master_ctl & GEN8_GT_IRQS) > + gen8_gt_irq_handler(to_gt(dev_priv), master_ctl); > > /* IRQs are synced during runtime_suspend, we don't require a wakeref */ > if (master_ctl & ~GEN8_GT_IRQS) { -- Jani Nikula, Intel
