Message ID | 1380243358-1861-2-git-send-email-jbarnes@virtuousgeek.org (mailing list archive) |
---|---|
State | New, archived |
Headers | show |
On Thu, Sep 26, 2013 at 05:55:58PM -0700, Jesse Barnes wrote: > We need to use the clock control reg to figure out how many CZ clks are in > 30ns and use that as the basis for our RC6 residency calculations. > > v2: use ULL everywhere for consistency (Chris) > factor out bias for clarity (Chris) I liked the NSEC_PER_MSEC as well :) > > References: https://bugs.freedesktop.org/show_bug.cgi?id=69692 > Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org> > --- > drivers/gpu/drm/i915/i915_reg.h | 3 +++ > drivers/gpu/drm/i915/i915_sysfs.c | 22 ++++++++++++++++++++-- > 2 files changed, 23 insertions(+), 2 deletions(-) > > diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h > index cf995bb..6f8d0cf 100644 > --- a/drivers/gpu/drm/i915/i915_reg.h > +++ b/drivers/gpu/drm/i915/i915_reg.h > @@ -1797,6 +1797,9 @@ > */ > #define HSW_CXT_TOTAL_SIZE (17 * PAGE_SIZE) > > +#define VLV_CLK_CTL2 0x101104 > +#define CLK_CTL2_CZCOUNT_30NS_SHIFT 28 > + > /* > * Overlay regs > */ > diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c > index 44f4c1a..8003886 100644 > --- a/drivers/gpu/drm/i915/i915_sysfs.c > +++ b/drivers/gpu/drm/i915/i915_sysfs.c > @@ -37,12 +37,30 @@ static u32 calc_residency(struct drm_device *dev, const u32 reg) > { > struct drm_i915_private *dev_priv = dev->dev_private; > u64 raw_time; /* 32b value may overflow during fixed point math */ > + u64 units = 128ULL, div = 100000ULL, bias = 100ULL; > > if (!intel_enable_rc6(dev)) > return 0; > > - raw_time = I915_READ(reg) * 128ULL; > - return DIV_ROUND_UP_ULL(raw_time, 100000); > + /* On VLV, residency time is in CZ units rather than 1.28us */ > + if (IS_VALLEYVIEW(dev)) { > + u32 clkctl2; > + > + clkctl2 = I915_READ(VLV_CLK_CTL2) >> > + CLK_CTL2_CZCOUNT_30NS_SHIFT; > + if (!clkctl2) { > + WARN(!clkctl2, "bogus CZ count value"); > + return 0; > + } > + units = DIV_ROUND_UP_ULL(30ULL * bias, (u64)clkctl2); > + if (I915_READ(VLV_COUNTER_CONTROL) & VLV_COUNT_RANGE_HIGH) > + units <<= 8; > + > + div = 1000000ULL * bias; > + } /* On VLV, residency time is in CZ units rather than 1.28us */ if (IS_VALLEVIEW9dev)) { u32 clkctl2; clkctl2 = I915_READ(VLV_CLK_CTL2) >> CLK_CTL2_CZCOUNT_30NS_SHIFT; if (!clkctl2) { WARN(!clkctl2, "bogus CZ count value"); return 0; } units = DIV_ROUND_UP_ULL(30ULL * bias, (u64)clkctl2); if (I915_READ(VLV_COUNTER_CONTROL) & VLV_COUNT_RANGE_HIGH) units <<= 8; div = NSEC_PER_MSEC * bias; } else { units = 128; div = USEC_PER_MSEC * bias; } raw_time = I915_READ(reg) * units; return DIV_ROUND_UP_ULL(raw_time, div); Either way, with or without the extra constants, Both patches, Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> -Chris
On Fri, Sep 27, 2013 at 09:15:58AM +0100, Chris Wilson wrote: > On Thu, Sep 26, 2013 at 05:55:58PM -0700, Jesse Barnes wrote: > > We need to use the clock control reg to figure out how many CZ clks are in > > 30ns and use that as the basis for our RC6 residency calculations. > > > > v2: use ULL everywhere for consistency (Chris) > > factor out bias for clarity (Chris) > > I liked the NSEC_PER_MSEC as well :) > > > > > References: https://bugs.freedesktop.org/show_bug.cgi?id=69692 > > Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org> > > --- > > drivers/gpu/drm/i915/i915_reg.h | 3 +++ > > drivers/gpu/drm/i915/i915_sysfs.c | 22 ++++++++++++++++++++-- > > 2 files changed, 23 insertions(+), 2 deletions(-) > > > > diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h > > index cf995bb..6f8d0cf 100644 > > --- a/drivers/gpu/drm/i915/i915_reg.h > > +++ b/drivers/gpu/drm/i915/i915_reg.h > > @@ -1797,6 +1797,9 @@ > > */ > > #define HSW_CXT_TOTAL_SIZE (17 * PAGE_SIZE) > > > > +#define VLV_CLK_CTL2 0x101104 > > +#define CLK_CTL2_CZCOUNT_30NS_SHIFT 28 > > + > > /* > > * Overlay regs > > */ > > diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c > > index 44f4c1a..8003886 100644 > > --- a/drivers/gpu/drm/i915/i915_sysfs.c > > +++ b/drivers/gpu/drm/i915/i915_sysfs.c > > @@ -37,12 +37,30 @@ static u32 calc_residency(struct drm_device *dev, const u32 reg) > > { > > struct drm_i915_private *dev_priv = dev->dev_private; > > u64 raw_time; /* 32b value may overflow during fixed point math */ > > + u64 units = 128ULL, div = 100000ULL, bias = 100ULL; > > > > if (!intel_enable_rc6(dev)) > > return 0; > > > > - raw_time = I915_READ(reg) * 128ULL; > > - return DIV_ROUND_UP_ULL(raw_time, 100000); > > + /* On VLV, residency time is in CZ units rather than 1.28us */ > > + if (IS_VALLEYVIEW(dev)) { > > + u32 clkctl2; > > + > > + clkctl2 = I915_READ(VLV_CLK_CTL2) >> > > + CLK_CTL2_CZCOUNT_30NS_SHIFT; > > + if (!clkctl2) { > > + WARN(!clkctl2, "bogus CZ count value"); > > + return 0; > > + } > > + units = DIV_ROUND_UP_ULL(30ULL * bias, (u64)clkctl2); > > + if (I915_READ(VLV_COUNTER_CONTROL) & VLV_COUNT_RANGE_HIGH) > > + units <<= 8; > > + > > + div = 1000000ULL * bias; > > + } > > /* On VLV, residency time is in CZ units rather than 1.28us */ > if (IS_VALLEVIEW9dev)) { > u32 clkctl2; > > clkctl2 = I915_READ(VLV_CLK_CTL2) >> > CLK_CTL2_CZCOUNT_30NS_SHIFT; > if (!clkctl2) { > WARN(!clkctl2, "bogus CZ count value"); > return 0; > } > > units = DIV_ROUND_UP_ULL(30ULL * bias, (u64)clkctl2); > if (I915_READ(VLV_COUNTER_CONTROL) & VLV_COUNT_RANGE_HIGH) > units <<= 8; > > div = NSEC_PER_MSEC * bias; > } else { > units = 128; > div = USEC_PER_MSEC * bias; > } > > raw_time = I915_READ(reg) * units; > return DIV_ROUND_UP_ULL(raw_time, div); > > Either way, with or without the extra constants, > Both patches, > Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Both merged without further bikeshedding applied. Thanks for patches&review. -Daniel
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index cf995bb..6f8d0cf 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -1797,6 +1797,9 @@ */ #define HSW_CXT_TOTAL_SIZE (17 * PAGE_SIZE) +#define VLV_CLK_CTL2 0x101104 +#define CLK_CTL2_CZCOUNT_30NS_SHIFT 28 + /* * Overlay regs */ diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c index 44f4c1a..8003886 100644 --- a/drivers/gpu/drm/i915/i915_sysfs.c +++ b/drivers/gpu/drm/i915/i915_sysfs.c @@ -37,12 +37,30 @@ static u32 calc_residency(struct drm_device *dev, const u32 reg) { struct drm_i915_private *dev_priv = dev->dev_private; u64 raw_time; /* 32b value may overflow during fixed point math */ + u64 units = 128ULL, div = 100000ULL, bias = 100ULL; if (!intel_enable_rc6(dev)) return 0; - raw_time = I915_READ(reg) * 128ULL; - return DIV_ROUND_UP_ULL(raw_time, 100000); + /* On VLV, residency time is in CZ units rather than 1.28us */ + if (IS_VALLEYVIEW(dev)) { + u32 clkctl2; + + clkctl2 = I915_READ(VLV_CLK_CTL2) >> + CLK_CTL2_CZCOUNT_30NS_SHIFT; + if (!clkctl2) { + WARN(!clkctl2, "bogus CZ count value"); + return 0; + } + units = DIV_ROUND_UP_ULL(30ULL * bias, (u64)clkctl2); + if (I915_READ(VLV_COUNTER_CONTROL) & VLV_COUNT_RANGE_HIGH) + units <<= 8; + + div = 1000000ULL * bias; + } + + raw_time = I915_READ(reg) * units; + return DIV_ROUND_UP_ULL(raw_time, div); } static ssize_t
We need to use the clock control reg to figure out how many CZ clks are in 30ns and use that as the basis for our RC6 residency calculations. v2: use ULL everywhere for consistency (Chris) factor out bias for clarity (Chris) References: https://bugs.freedesktop.org/show_bug.cgi?id=69692 Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org> --- drivers/gpu/drm/i915/i915_reg.h | 3 +++ drivers/gpu/drm/i915/i915_sysfs.c | 22 ++++++++++++++++++++-- 2 files changed, 23 insertions(+), 2 deletions(-)