diff mbox

[v2,05/14] drm/i915: Rewrite vlv_find_best_dpll()

Message ID 1380047191-3359-6-git-send-email-ville.syrjala@linux.intel.com (mailing list archive)
State New, archived
Headers show

Commit Message

Ville Syrjälä Sept. 24, 2013, 6:26 p.m. UTC
From: Ville Syrjälä <ville.syrjala@linux.intel.com>

Rewrite vlv_find_best_dpll() to use intel_clock_t rather than
an army of local variables.

Also extract the code to calculate the derived values into
vlv_clock().

v2: Split up the earlier fixes, extract vlv_clock()

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
---
 drivers/gpu/drm/i915/intel_display.c | 72 ++++++++++++++++--------------------
 1 file changed, 31 insertions(+), 41 deletions(-)

Comments

Mika Kuoppala Sept. 26, 2013, 3:30 p.m. UTC | #1
ville.syrjala@linux.intel.com writes:

> From: Ville Syrjälä <ville.syrjala@linux.intel.com>
>
> Rewrite vlv_find_best_dpll() to use intel_clock_t rather than
> an army of local variables.
>
> Also extract the code to calculate the derived values into
> vlv_clock().
>
> v2: Split up the earlier fixes, extract vlv_clock()
>
> Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
> ---
>  drivers/gpu/drm/i915/intel_display.c | 72 ++++++++++++++++--------------------
>  1 file changed, 31 insertions(+), 41 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
> index f646fea..c5f0794 100644
> --- a/drivers/gpu/drm/i915/intel_display.c
> +++ b/drivers/gpu/drm/i915/intel_display.c
> @@ -438,6 +438,14 @@ static void i9xx_clock(int refclk, intel_clock_t *clock)
>  	clock->dot = clock->vco / clock->p;
>  }
>  
> +static void vlv_clock(int refclk, intel_clock_t *clock)
> +{
> +	clock->m = clock->m1 * clock->m2;
> +	clock->p = clock->p1 * clock->p2;
> +	clock->vco = refclk * clock->m / clock->n;
> +	clock->dot = clock->vco / clock->p;
> +}
> +
>  /**
>   * Returns whether any output on the specified pipe is of the specified type
>   */
> @@ -670,66 +678,48 @@ vlv_find_best_dpll(const intel_limit_t *limit, struct drm_crtc *crtc,
>  		   int target, int refclk, intel_clock_t *match_clock,
>  		   intel_clock_t *best_clock)
>  {
> -	u32 p1, p2, m1, m2, vco, bestn, bestm1, bestm2, bestp1, bestp2;
> -	u32 m, n, fastclk;
> -	u32 updrate, minupdate, p;
> +	intel_clock_t clock;
> +	u32 minupdate = 19200;
>  	unsigned int bestppm = 1000000;
> -	int dotclk, flag;
>  
> -	flag = 0;
> -	dotclk = target * 1000;
> -	fastclk = dotclk / (2*100);
> -	updrate = 0;
> -	minupdate = 19200;
> -	n = p = p1 = p2 = m = m1 = m2 = vco = bestn = 0;
> -	bestm1 = bestm2 = bestp1 = bestp2 = 0;
> +	target *= 5; /* fast clock */
>  
>  	/* based on hardware requirement, prefer smaller n to precision */
> -	for (n = limit->n.min; n <= ((refclk) / minupdate); n++) {
> -		updrate = refclk / n;
> -		for (p1 = limit->p1.max; p1 > limit->p1.min; p1--) {
> -			for (p2 = limit->p2.p2_fast+1; p2 > 0; p2--) {
> -				if (p2 > 10)
> -					p2 = p2 - 1;
> -				p = p1 * p2;
> +	for (clock.n = limit->n.min; clock.n <= ((refclk) / minupdate); clock.n++) {
> +		for (clock.p1 = limit->p1.max; clock.p1 > limit->p1.min; clock.p1--) {
> +			for (clock.p2 = limit->p2.p2_fast+1; clock.p2 > 0; clock.p2--) {
> +				if (clock.p2 > 10)
> +					clock.p2--;
> +				clock.p = clock.p1 * clock.p2;
>  				/* based on hardware requirement, prefer bigger m1,m2 values */

Is this comment valid as we seem to start from m1.min?

> -				for (m1 = limit->m1.min; m1 <= limit->m1.max; m1++) {
> +				for (clock.m1 = limit->m1.min; clock.m1 <= limit->m1.max; clock.m1++) {
>  					unsigned int ppm, diff;
>  
> -					m2 = DIV_ROUND_CLOSEST(fastclk * p * n, refclk * m1);
> -					m = m1 * m2;
> -					vco = updrate * m;
> +					clock.m2 = DIV_ROUND_CLOSEST(target * clock.p * clock.n,
> +								     refclk * clock.m1);
>  
> -					if (vco < limit->vco.min || vco >= limit->vco.max)
> +					vlv_clock(refclk, &clock);
> +

> +					if (clock.vco < limit->vco.min ||
> +					    clock.vco >= limit->vco.max)
>  						continue;

Can intel_PLL_is_valid() used here instead of just checking the vco?

>  
> -					diff = abs(vco / p - fastclk);
> -					ppm = div_u64(1000000ULL * diff, fastclk);
> -					if (ppm < 100 && ((p1 * p2) > (bestp1 * bestp2))) {
> +					diff = abs(clock.dot - target);
> +					ppm = div_u64(1000000ULL * diff, target);
> +
> +					if (ppm < 100 && clock.p > best_clock->p) {
>  						bestppm = 0;
> -						flag = 1;
> +						*best_clock = clock;
>  					}
> +
>  					if (bestppm >= 10 && ppm < bestppm - 10) {
>  						bestppm = ppm;
> -						flag = 1;
> -					}
> -					if (flag) {
> -						bestn = n;
> -						bestm1 = m1;
> -						bestm2 = m2;
> -						bestp1 = p1;
> -						bestp2 = p2;
> -						flag = 0;
> +						*best_clock = clock;
>  					}
>  				}
>  			}
>  		}
>  	}
> -	best_clock->n = bestn;
> -	best_clock->m1 = bestm1;
> -	best_clock->m2 = bestm2;
> -	best_clock->p1 = bestp1;
> -	best_clock->p2 = bestp2;
>  
>  	return true;
>  }
> -- 
> 1.8.1.5
>
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Mika Kuoppala Sept. 27, 2013, 11:55 a.m. UTC | #2
ville.syrjala@linux.intel.com writes:

> From: Ville Syrjälä <ville.syrjala@linux.intel.com>
>
> Rewrite vlv_find_best_dpll() to use intel_clock_t rather than
> an army of local variables.
>
> Also extract the code to calculate the derived values into
> vlv_clock().
>
> v2: Split up the earlier fixes, extract vlv_clock()
>
> Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
> ---
>  drivers/gpu/drm/i915/intel_display.c | 72 ++++++++++++++++--------------------
>  1 file changed, 31 insertions(+), 41 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
> index f646fea..c5f0794 100644
> --- a/drivers/gpu/drm/i915/intel_display.c
> +++ b/drivers/gpu/drm/i915/intel_display.c
> @@ -438,6 +438,14 @@ static void i9xx_clock(int refclk, intel_clock_t *clock)
>  	clock->dot = clock->vco / clock->p;
>  }
>  
> +static void vlv_clock(int refclk, intel_clock_t *clock)
> +{
> +	clock->m = clock->m1 * clock->m2;
> +	clock->p = clock->p1 * clock->p2;
> +	clock->vco = refclk * clock->m / clock->n;
> +	clock->dot = clock->vco / clock->p;
> +}
> +
>  /**
>   * Returns whether any output on the specified pipe is of the specified type
>   */
> @@ -670,66 +678,48 @@ vlv_find_best_dpll(const intel_limit_t *limit, struct drm_crtc *crtc,
>  		   int target, int refclk, intel_clock_t *match_clock,
>  		   intel_clock_t *best_clock)
>  {
> -	u32 p1, p2, m1, m2, vco, bestn, bestm1, bestm2, bestp1, bestp2;
> -	u32 m, n, fastclk;
> -	u32 updrate, minupdate, p;
> +	intel_clock_t clock;
> +	u32 minupdate = 19200;
>  	unsigned int bestppm = 1000000;
> -	int dotclk, flag;
>  
> -	flag = 0;
> -	dotclk = target * 1000;
> -	fastclk = dotclk / (2*100);
> -	updrate = 0;
> -	minupdate = 19200;
> -	n = p = p1 = p2 = m = m1 = m2 = vco = bestn = 0;
> -	bestm1 = bestm2 = bestp1 = bestp2 = 0;
> +	target *= 5; /* fast clock */
>  
>  	/* based on hardware requirement, prefer smaller n to precision */
> -	for (n = limit->n.min; n <= ((refclk) / minupdate); n++) {
> -		updrate = refclk / n;
> -		for (p1 = limit->p1.max; p1 > limit->p1.min; p1--) {
> -			for (p2 = limit->p2.p2_fast+1; p2 > 0; p2--) {
> -				if (p2 > 10)
> -					p2 = p2 - 1;
> -				p = p1 * p2;
> +	for (clock.n = limit->n.min; clock.n <= ((refclk) / minupdate); clock.n++) {
> +		for (clock.p1 = limit->p1.max; clock.p1 > limit->p1.min; clock.p1--) {
> +			for (clock.p2 = limit->p2.p2_fast+1; clock.p2 > 0; clock.p2--) {
> +				if (clock.p2 > 10)
> +					clock.p2--;
> +				clock.p = clock.p1 * clock.p2;
>  				/* based on hardware requirement, prefer bigger m1,m2 values */
> -				for (m1 = limit->m1.min; m1 <= limit->m1.max; m1++) {
> +				for (clock.m1 = limit->m1.min; clock.m1 <= limit->m1.max; clock.m1++) {
>  					unsigned int ppm, diff;
>  
> -					m2 = DIV_ROUND_CLOSEST(fastclk * p * n, refclk * m1);
> -					m = m1 * m2;
> -					vco = updrate * m;
> +					clock.m2 = DIV_ROUND_CLOSEST(target * clock.p * clock.n,
> +								     refclk * clock.m1);
>  
> -					if (vco < limit->vco.min || vco >= limit->vco.max)
> +					vlv_clock(refclk, &clock);
> +
> +					if (clock.vco < limit->vco.min ||
> +					    clock.vco >= limit->vco.max)
>  						continue;
>  
> -					diff = abs(vco / p - fastclk);
> -					ppm = div_u64(1000000ULL * diff, fastclk);
> -					if (ppm < 100 && ((p1 * p2) > (bestp1 * bestp2))) {
> +					diff = abs(clock.dot - target);
> +					ppm = div_u64(1000000ULL * diff, target);
> +
> +					if (ppm < 100 && clock.p > best_clock->p) {

best_clock needs to be initialized or you end up comparing against
bytes from stack on first hitting here.

>  						bestppm = 0;
> -						flag = 1;
> +						*best_clock = clock;
>  					}
> +
>  					if (bestppm >= 10 && ppm < bestppm - 10) {
>  						bestppm = ppm;
> -						flag = 1;
> -					}
> -					if (flag) {
> -						bestn = n;
> -						bestm1 = m1;
> -						bestm2 = m2;
> -						bestp1 = p1;
> -						bestp2 = p2;
> -						flag = 0;
> +						*best_clock = clock;
>  					}
>  				}
>  			}
>  		}
>  	}
> -	best_clock->n = bestn;
> -	best_clock->m1 = bestm1;
> -	best_clock->m2 = bestm2;
> -	best_clock->p1 = bestp1;
> -	best_clock->p2 = bestp2;
>  
>  	return true;
>  }
> -- 
> 1.8.1.5
>
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Ville Syrjälä Sept. 27, 2013, 1:01 p.m. UTC | #3
On Thu, Sep 26, 2013 at 06:30:55PM +0300, Mika Kuoppala wrote:
> ville.syrjala@linux.intel.com writes:
> 
> > From: Ville Syrjälä <ville.syrjala@linux.intel.com>
> >
> > Rewrite vlv_find_best_dpll() to use intel_clock_t rather than
> > an army of local variables.
> >
> > Also extract the code to calculate the derived values into
> > vlv_clock().
> >
> > v2: Split up the earlier fixes, extract vlv_clock()
> >
> > Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
> > ---
> >  drivers/gpu/drm/i915/intel_display.c | 72 ++++++++++++++++--------------------
> >  1 file changed, 31 insertions(+), 41 deletions(-)
> >
> > diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
> > index f646fea..c5f0794 100644
> > --- a/drivers/gpu/drm/i915/intel_display.c
> > +++ b/drivers/gpu/drm/i915/intel_display.c
> > @@ -438,6 +438,14 @@ static void i9xx_clock(int refclk, intel_clock_t *clock)
> >  	clock->dot = clock->vco / clock->p;
> >  }
> >  
> > +static void vlv_clock(int refclk, intel_clock_t *clock)
> > +{
> > +	clock->m = clock->m1 * clock->m2;
> > +	clock->p = clock->p1 * clock->p2;
> > +	clock->vco = refclk * clock->m / clock->n;
> > +	clock->dot = clock->vco / clock->p;
> > +}
> > +
> >  /**
> >   * Returns whether any output on the specified pipe is of the specified type
> >   */
> > @@ -670,66 +678,48 @@ vlv_find_best_dpll(const intel_limit_t *limit, struct drm_crtc *crtc,
> >  		   int target, int refclk, intel_clock_t *match_clock,
> >  		   intel_clock_t *best_clock)
> >  {
> > -	u32 p1, p2, m1, m2, vco, bestn, bestm1, bestm2, bestp1, bestp2;
> > -	u32 m, n, fastclk;
> > -	u32 updrate, minupdate, p;
> > +	intel_clock_t clock;
> > +	u32 minupdate = 19200;
> >  	unsigned int bestppm = 1000000;
> > -	int dotclk, flag;
> >  
> > -	flag = 0;
> > -	dotclk = target * 1000;
> > -	fastclk = dotclk / (2*100);
> > -	updrate = 0;
> > -	minupdate = 19200;
> > -	n = p = p1 = p2 = m = m1 = m2 = vco = bestn = 0;
> > -	bestm1 = bestm2 = bestp1 = bestp2 = 0;
> > +	target *= 5; /* fast clock */
> >  
> >  	/* based on hardware requirement, prefer smaller n to precision */
> > -	for (n = limit->n.min; n <= ((refclk) / minupdate); n++) {
> > -		updrate = refclk / n;
> > -		for (p1 = limit->p1.max; p1 > limit->p1.min; p1--) {
> > -			for (p2 = limit->p2.p2_fast+1; p2 > 0; p2--) {
> > -				if (p2 > 10)
> > -					p2 = p2 - 1;
> > -				p = p1 * p2;
> > +	for (clock.n = limit->n.min; clock.n <= ((refclk) / minupdate); clock.n++) {
> > +		for (clock.p1 = limit->p1.max; clock.p1 > limit->p1.min; clock.p1--) {
> > +			for (clock.p2 = limit->p2.p2_fast+1; clock.p2 > 0; clock.p2--) {
> > +				if (clock.p2 > 10)
> > +					clock.p2--;
> > +				clock.p = clock.p1 * clock.p2;
> >  				/* based on hardware requirement, prefer bigger m1,m2 values */
> 
> Is this comment valid as we seem to start from m1.min?

We anyway try to find the closest m2 based on m1,n,p1 and p2, and since
we start w/ large p dividers, m1*m2 will come out as something big to
compensate. Though starting with small n does mean m2 doesn't come out
as large as it could be, but I guess having a small n is considered
more important than having a large m.

The bestppm comparison we do guarantees that we prefer an earlier result
unless the new ppm is at least 10 better, and since we start with small
n and large p, it should do what we want.

Then there's ppm<100 comparison which is a bit different. It means we
favor anything that is considered good enough (ppm < 100) as long as
the p divider increases, and hence the VCO frequency increases. That
would seem to be in line with the other stated goals of big m and small n.

> 
> > -				for (m1 = limit->m1.min; m1 <= limit->m1.max; m1++) {
> > +				for (clock.m1 = limit->m1.min; clock.m1 <= limit->m1.max; clock.m1++) {
> >  					unsigned int ppm, diff;
> >  
> > -					m2 = DIV_ROUND_CLOSEST(fastclk * p * n, refclk * m1);
> > -					m = m1 * m2;
> > -					vco = updrate * m;
> > +					clock.m2 = DIV_ROUND_CLOSEST(target * clock.p * clock.n,
> > +								     refclk * clock.m1);
> >  
> > -					if (vco < limit->vco.min || vco >= limit->vco.max)
> > +					vlv_clock(refclk, &clock);
> > +
> 
> > +					if (clock.vco < limit->vco.min ||
> > +					    clock.vco >= limit->vco.max)
> >  						continue;
> 
> Can intel_PLL_is_valid() used here instead of just checking the vco?

We'd need to modify intel_PLL_is_valid() a bit to skip the m1<=m2 check,
and we'd also need to skip the 'm' and 'p' divider check, or populate
the m and p min/max with something that makes sense.

It would do the clock.dot min/max check that we're currently missing
from this function, and I guess it would allow easier debugging since it
has the INTELPllInvalid() macro for that purpose. So it would seem to be
a good idea to use it.

> 
> >  
> > -					diff = abs(vco / p - fastclk);
> > -					ppm = div_u64(1000000ULL * diff, fastclk);
> > -					if (ppm < 100 && ((p1 * p2) > (bestp1 * bestp2))) {
> > +					diff = abs(clock.dot - target);
> > +					ppm = div_u64(1000000ULL * diff, target);
> > +
> > +					if (ppm < 100 && clock.p > best_clock->p) {
> >  						bestppm = 0;
> > -						flag = 1;
> > +						*best_clock = clock;
> >  					}
> > +
> >  					if (bestppm >= 10 && ppm < bestppm - 10) {
> >  						bestppm = ppm;
> > -						flag = 1;
> > -					}
> > -					if (flag) {
> > -						bestn = n;
> > -						bestm1 = m1;
> > -						bestm2 = m2;
> > -						bestp1 = p1;
> > -						bestp2 = p2;
> > -						flag = 0;
> > +						*best_clock = clock;
> >  					}
> >  				}
> >  			}
> >  		}
> >  	}
> > -	best_clock->n = bestn;
> > -	best_clock->m1 = bestm1;
> > -	best_clock->m2 = bestm2;
> > -	best_clock->p1 = bestp1;
> > -	best_clock->p2 = bestp2;
> >  
> >  	return true;
> >  }
> > -- 
> > 1.8.1.5
> >
> > _______________________________________________
> > Intel-gfx mailing list
> > Intel-gfx@lists.freedesktop.org
> > http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Ville Syrjälä Sept. 27, 2013, 1:04 p.m. UTC | #4
On Fri, Sep 27, 2013 at 02:55:32PM +0300, Mika Kuoppala wrote:
> ville.syrjala@linux.intel.com writes:
> 
> > From: Ville Syrjälä <ville.syrjala@linux.intel.com>
> >
> > Rewrite vlv_find_best_dpll() to use intel_clock_t rather than
> > an army of local variables.
> >
> > Also extract the code to calculate the derived values into
> > vlv_clock().
> >
> > v2: Split up the earlier fixes, extract vlv_clock()
> >
> > Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
> > ---
> >  drivers/gpu/drm/i915/intel_display.c | 72 ++++++++++++++++--------------------
> >  1 file changed, 31 insertions(+), 41 deletions(-)
> >
> > diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
> > index f646fea..c5f0794 100644
> > --- a/drivers/gpu/drm/i915/intel_display.c
> > +++ b/drivers/gpu/drm/i915/intel_display.c
> > @@ -438,6 +438,14 @@ static void i9xx_clock(int refclk, intel_clock_t *clock)
> >  	clock->dot = clock->vco / clock->p;
> >  }
> >  
> > +static void vlv_clock(int refclk, intel_clock_t *clock)
> > +{
> > +	clock->m = clock->m1 * clock->m2;
> > +	clock->p = clock->p1 * clock->p2;
> > +	clock->vco = refclk * clock->m / clock->n;
> > +	clock->dot = clock->vco / clock->p;
> > +}
> > +
> >  /**
> >   * Returns whether any output on the specified pipe is of the specified type
> >   */
> > @@ -670,66 +678,48 @@ vlv_find_best_dpll(const intel_limit_t *limit, struct drm_crtc *crtc,
> >  		   int target, int refclk, intel_clock_t *match_clock,
> >  		   intel_clock_t *best_clock)
> >  {
> > -	u32 p1, p2, m1, m2, vco, bestn, bestm1, bestm2, bestp1, bestp2;
> > -	u32 m, n, fastclk;
> > -	u32 updrate, minupdate, p;
> > +	intel_clock_t clock;
> > +	u32 minupdate = 19200;
> >  	unsigned int bestppm = 1000000;
> > -	int dotclk, flag;
> >  
> > -	flag = 0;
> > -	dotclk = target * 1000;
> > -	fastclk = dotclk / (2*100);
> > -	updrate = 0;
> > -	minupdate = 19200;
> > -	n = p = p1 = p2 = m = m1 = m2 = vco = bestn = 0;
> > -	bestm1 = bestm2 = bestp1 = bestp2 = 0;
> > +	target *= 5; /* fast clock */
> >  
> >  	/* based on hardware requirement, prefer smaller n to precision */
> > -	for (n = limit->n.min; n <= ((refclk) / minupdate); n++) {
> > -		updrate = refclk / n;
> > -		for (p1 = limit->p1.max; p1 > limit->p1.min; p1--) {
> > -			for (p2 = limit->p2.p2_fast+1; p2 > 0; p2--) {
> > -				if (p2 > 10)
> > -					p2 = p2 - 1;
> > -				p = p1 * p2;
> > +	for (clock.n = limit->n.min; clock.n <= ((refclk) / minupdate); clock.n++) {
> > +		for (clock.p1 = limit->p1.max; clock.p1 > limit->p1.min; clock.p1--) {
> > +			for (clock.p2 = limit->p2.p2_fast+1; clock.p2 > 0; clock.p2--) {
> > +				if (clock.p2 > 10)
> > +					clock.p2--;
> > +				clock.p = clock.p1 * clock.p2;
> >  				/* based on hardware requirement, prefer bigger m1,m2 values */
> > -				for (m1 = limit->m1.min; m1 <= limit->m1.max; m1++) {
> > +				for (clock.m1 = limit->m1.min; clock.m1 <= limit->m1.max; clock.m1++) {
> >  					unsigned int ppm, diff;
> >  
> > -					m2 = DIV_ROUND_CLOSEST(fastclk * p * n, refclk * m1);
> > -					m = m1 * m2;
> > -					vco = updrate * m;
> > +					clock.m2 = DIV_ROUND_CLOSEST(target * clock.p * clock.n,
> > +								     refclk * clock.m1);
> >  
> > -					if (vco < limit->vco.min || vco >= limit->vco.max)
> > +					vlv_clock(refclk, &clock);
> > +
> > +					if (clock.vco < limit->vco.min ||
> > +					    clock.vco >= limit->vco.max)
> >  						continue;
> >  
> > -					diff = abs(vco / p - fastclk);
> > -					ppm = div_u64(1000000ULL * diff, fastclk);
> > -					if (ppm < 100 && ((p1 * p2) > (bestp1 * bestp2))) {
> > +					diff = abs(clock.dot - target);
> > +					ppm = div_u64(1000000ULL * diff, target);
> > +
> > +					if (ppm < 100 && clock.p > best_clock->p) {
> 
> best_clock needs to be initialized or you end up comparing against
> bytes from stack on first hitting here.

Right. v3 coming up.

> 
> >  						bestppm = 0;
> > -						flag = 1;
> > +						*best_clock = clock;
> >  					}
> > +
> >  					if (bestppm >= 10 && ppm < bestppm - 10) {
> >  						bestppm = ppm;
> > -						flag = 1;
> > -					}
> > -					if (flag) {
> > -						bestn = n;
> > -						bestm1 = m1;
> > -						bestm2 = m2;
> > -						bestp1 = p1;
> > -						bestp2 = p2;
> > -						flag = 0;
> > +						*best_clock = clock;
> >  					}
> >  				}
> >  			}
> >  		}
> >  	}
> > -	best_clock->n = bestn;
> > -	best_clock->m1 = bestm1;
> > -	best_clock->m2 = bestm2;
> > -	best_clock->p1 = bestp1;
> > -	best_clock->p2 = bestp2;
> >  
> >  	return true;
> >  }
> > -- 
> > 1.8.1.5
> >
> > _______________________________________________
> > Intel-gfx mailing list
> > Intel-gfx@lists.freedesktop.org
> > http://lists.freedesktop.org/mailman/listinfo/intel-gfx
diff mbox

Patch

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index f646fea..c5f0794 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -438,6 +438,14 @@  static void i9xx_clock(int refclk, intel_clock_t *clock)
 	clock->dot = clock->vco / clock->p;
 }
 
+static void vlv_clock(int refclk, intel_clock_t *clock)
+{
+	clock->m = clock->m1 * clock->m2;
+	clock->p = clock->p1 * clock->p2;
+	clock->vco = refclk * clock->m / clock->n;
+	clock->dot = clock->vco / clock->p;
+}
+
 /**
  * Returns whether any output on the specified pipe is of the specified type
  */
@@ -670,66 +678,48 @@  vlv_find_best_dpll(const intel_limit_t *limit, struct drm_crtc *crtc,
 		   int target, int refclk, intel_clock_t *match_clock,
 		   intel_clock_t *best_clock)
 {
-	u32 p1, p2, m1, m2, vco, bestn, bestm1, bestm2, bestp1, bestp2;
-	u32 m, n, fastclk;
-	u32 updrate, minupdate, p;
+	intel_clock_t clock;
+	u32 minupdate = 19200;
 	unsigned int bestppm = 1000000;
-	int dotclk, flag;
 
-	flag = 0;
-	dotclk = target * 1000;
-	fastclk = dotclk / (2*100);
-	updrate = 0;
-	minupdate = 19200;
-	n = p = p1 = p2 = m = m1 = m2 = vco = bestn = 0;
-	bestm1 = bestm2 = bestp1 = bestp2 = 0;
+	target *= 5; /* fast clock */
 
 	/* based on hardware requirement, prefer smaller n to precision */
-	for (n = limit->n.min; n <= ((refclk) / minupdate); n++) {
-		updrate = refclk / n;
-		for (p1 = limit->p1.max; p1 > limit->p1.min; p1--) {
-			for (p2 = limit->p2.p2_fast+1; p2 > 0; p2--) {
-				if (p2 > 10)
-					p2 = p2 - 1;
-				p = p1 * p2;
+	for (clock.n = limit->n.min; clock.n <= ((refclk) / minupdate); clock.n++) {
+		for (clock.p1 = limit->p1.max; clock.p1 > limit->p1.min; clock.p1--) {
+			for (clock.p2 = limit->p2.p2_fast+1; clock.p2 > 0; clock.p2--) {
+				if (clock.p2 > 10)
+					clock.p2--;
+				clock.p = clock.p1 * clock.p2;
 				/* based on hardware requirement, prefer bigger m1,m2 values */
-				for (m1 = limit->m1.min; m1 <= limit->m1.max; m1++) {
+				for (clock.m1 = limit->m1.min; clock.m1 <= limit->m1.max; clock.m1++) {
 					unsigned int ppm, diff;
 
-					m2 = DIV_ROUND_CLOSEST(fastclk * p * n, refclk * m1);
-					m = m1 * m2;
-					vco = updrate * m;
+					clock.m2 = DIV_ROUND_CLOSEST(target * clock.p * clock.n,
+								     refclk * clock.m1);
 
-					if (vco < limit->vco.min || vco >= limit->vco.max)
+					vlv_clock(refclk, &clock);
+
+					if (clock.vco < limit->vco.min ||
+					    clock.vco >= limit->vco.max)
 						continue;
 
-					diff = abs(vco / p - fastclk);
-					ppm = div_u64(1000000ULL * diff, fastclk);
-					if (ppm < 100 && ((p1 * p2) > (bestp1 * bestp2))) {
+					diff = abs(clock.dot - target);
+					ppm = div_u64(1000000ULL * diff, target);
+
+					if (ppm < 100 && clock.p > best_clock->p) {
 						bestppm = 0;
-						flag = 1;
+						*best_clock = clock;
 					}
+
 					if (bestppm >= 10 && ppm < bestppm - 10) {
 						bestppm = ppm;
-						flag = 1;
-					}
-					if (flag) {
-						bestn = n;
-						bestm1 = m1;
-						bestm2 = m2;
-						bestp1 = p1;
-						bestp2 = p2;
-						flag = 0;
+						*best_clock = clock;
 					}
 				}
 			}
 		}
 	}
-	best_clock->n = bestn;
-	best_clock->m1 = bestm1;
-	best_clock->m2 = bestm2;
-	best_clock->p1 = bestp1;
-	best_clock->p2 = bestp2;
 
 	return true;
 }