| Message ID | 1475065546-5481-4-git-send-email-tvrtko.ursulin@linux.intel.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
On Wed, Sep 28, 2016 at 01:25:46PM +0100, Tvrtko Ursulin wrote: > From: Tvrtko Ursulin <tvrtko.ursulin@intel.com> > > Once we know we need to take new forcewakes, that being > a slow operation, it does not make sense to inline that > code into every mmio accessor. > > Move it to a separate function and save some code. > > Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> > --- > drivers/gpu/drm/i915/intel_uncore.c | 25 +++++++++++++++---------- > 1 file changed, 15 insertions(+), 10 deletions(-) > > diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c > index 079102b46fd3..c887ab0947c6 100644 > --- a/drivers/gpu/drm/i915/intel_uncore.c > +++ b/drivers/gpu/drm/i915/intel_uncore.c > @@ -862,11 +862,22 @@ __gen2_read(64) > trace_i915_reg_rw(false, reg, val, sizeof(val), trace); \ > return val > > -static inline void __force_wake_auto(struct drm_i915_private *dev_priv, > - enum forcewake_domains fw_domains) noinline just to reinforce? > +static void ___force_wake_auto(struct drm_i915_private *dev_priv, > + enum forcewake_domains fw_domains) > { > struct intel_uncore_forcewake_domain *domain; > > + /* Ideally GCC would be constant-fold and eliminate this loop */ That comment no longer applies, since we are now out of line. > + for_each_fw_domain_masked(domain, fw_domains, dev_priv) > + fw_domain_arm_timer(domain); > + > + dev_priv->uncore.funcs.force_wake_get(dev_priv, fw_domains); > + dev_priv->uncore.fw_domains_active |= fw_domains; > +} > + > +static inline void __force_wake_auto(struct drm_i915_private *dev_priv, > + enum forcewake_domains fw_domains) > +{ > if (WARN_ON(!fw_domains)) > return; > > @@ -874,14 +885,8 @@ static inline void __force_wake_auto(struct drm_i915_private *dev_priv, > fw_domains &= dev_priv->uncore.fw_domains; > fw_domains &= ~dev_priv->uncore.fw_domains_active; Ok, that seems a reasonable justification (and that is what would neuter the /* Ideally... */ comment). -Chris
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index 079102b46fd3..c887ab0947c6 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -862,11 +862,22 @@ __gen2_read(64) trace_i915_reg_rw(false, reg, val, sizeof(val), trace); \ return val -static inline void __force_wake_auto(struct drm_i915_private *dev_priv, - enum forcewake_domains fw_domains) +static void ___force_wake_auto(struct drm_i915_private *dev_priv, + enum forcewake_domains fw_domains) { struct intel_uncore_forcewake_domain *domain; + /* Ideally GCC would be constant-fold and eliminate this loop */ + for_each_fw_domain_masked(domain, fw_domains, dev_priv) + fw_domain_arm_timer(domain); + + dev_priv->uncore.funcs.force_wake_get(dev_priv, fw_domains); + dev_priv->uncore.fw_domains_active |= fw_domains; +} + +static inline void __force_wake_auto(struct drm_i915_private *dev_priv, + enum forcewake_domains fw_domains) +{ if (WARN_ON(!fw_domains)) return; @@ -874,14 +885,8 @@ static inline void __force_wake_auto(struct drm_i915_private *dev_priv, fw_domains &= dev_priv->uncore.fw_domains; fw_domains &= ~dev_priv->uncore.fw_domains_active; - if (fw_domains) { - /* Ideally GCC would be constant-fold and eliminate this loop */ - for_each_fw_domain_masked(domain, fw_domains, dev_priv) - fw_domain_arm_timer(domain); - - dev_priv->uncore.funcs.force_wake_get(dev_priv, fw_domains); - dev_priv->uncore.fw_domains_active |= fw_domains; - } + if (fw_domains) + ___force_wake_auto(dev_priv, fw_domains); } #define __gen6_read(x) \