[Intel-gfx] [PATCH 04/12] drm/i915: Rename and comment all the RPS *stuff*
Ben Widawsky
benjamin.widawsky at intel.com
Thu Mar 20 02:31:11 CET 2014
The names of the struct members for RPS are stupid. Every time I need to
do anything in this code I have to spend a significant amount of time to
remember what it all means. By renaming the variables (and adding the
comments) I hope to clear up the situation. Indeed doing this make some
upcoming patches more readable.
I've avoided ILK because it's possible that the naming used for Ironlake
matches what is in the docs. I believe the ILK power docs were never
published, and I am too lazy to dig them up.
v2: leave rp0, and rp1 in the names. It is useful to have these limits
available at times. min_freq and max_freq (which may be equal to rp0, or
rp1 depending on the platform) represent the actual HW min and max.
Cc: Chris Wilson <chris at chris-wilson.co.uk>
Signed-off-by: Ben Widawsky <ben at bwidawsk.net>
---
drivers/gpu/drm/i915/i915_debugfs.c | 26 ++++----
drivers/gpu/drm/i915/i915_drv.h | 26 +++++---
drivers/gpu/drm/i915/i915_irq.c | 25 ++++----
drivers/gpu/drm/i915/i915_sysfs.c | 32 +++++-----
drivers/gpu/drm/i915/intel_pm.c | 118 ++++++++++++++++++------------------
5 files changed, 120 insertions(+), 107 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 6037913..d1e0a36 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1026,7 +1026,7 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused)
max_freq * GT_FREQUENCY_MULTIPLIER);
seq_printf(m, "Max overclocked frequency: %dMHz\n",
- dev_priv->rps.hw_max * GT_FREQUENCY_MULTIPLIER);
+ dev_priv->rps.max_freq * GT_FREQUENCY_MULTIPLIER);
} else if (IS_VALLEYVIEW(dev)) {
u32 freq_sts, val;
@@ -1498,8 +1498,8 @@ static int i915_ring_freq_table(struct seq_file *m, void *unused)
seq_puts(m, "GPU freq (MHz)\tEffective CPU freq (MHz)\tEffective Ring freq (MHz)\n");
- for (gpu_freq = dev_priv->rps.min_delay;
- gpu_freq <= dev_priv->rps.max_delay;
+ for (gpu_freq = dev_priv->rps.min_freq_softlimit;
+ gpu_freq <= dev_priv->rps.max_freq_softlimit;
gpu_freq++) {
ia_freq = gpu_freq;
sandybridge_pcode_read(dev_priv,
@@ -3449,9 +3449,9 @@ i915_max_freq_get(void *data, u64 *val)
return ret;
if (IS_VALLEYVIEW(dev))
- *val = vlv_gpu_freq(dev_priv, dev_priv->rps.max_delay);
+ *val = vlv_gpu_freq(dev_priv, dev_priv->rps.max_freq_softlimit);
else
- *val = dev_priv->rps.max_delay * GT_FREQUENCY_MULTIPLIER;
+ *val = dev_priv->rps.max_freq_softlimit * GT_FREQUENCY_MULTIPLIER;
mutex_unlock(&dev_priv->rps.hw_lock);
return 0;
@@ -3488,16 +3488,16 @@ i915_max_freq_set(void *data, u64 val)
do_div(val, GT_FREQUENCY_MULTIPLIER);
rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
- hw_max = dev_priv->rps.hw_max;
+ hw_max = dev_priv->rps.max_freq;
hw_min = (rp_state_cap >> 16) & 0xff;
}
- if (val < hw_min || val > hw_max || val < dev_priv->rps.min_delay) {
+ if (val < hw_min || val > hw_max || val < dev_priv->rps.min_freq_softlimit) {
mutex_unlock(&dev_priv->rps.hw_lock);
return -EINVAL;
}
- dev_priv->rps.max_delay = val;
+ dev_priv->rps.max_freq_softlimit = val;
if (IS_VALLEYVIEW(dev))
valleyview_set_rps(dev, val);
@@ -3530,9 +3530,9 @@ i915_min_freq_get(void *data, u64 *val)
return ret;
if (IS_VALLEYVIEW(dev))
- *val = vlv_gpu_freq(dev_priv, dev_priv->rps.min_delay);
+ *val = vlv_gpu_freq(dev_priv, dev_priv->rps.min_freq_softlimit);
else
- *val = dev_priv->rps.min_delay * GT_FREQUENCY_MULTIPLIER;
+ *val = dev_priv->rps.min_freq_softlimit * GT_FREQUENCY_MULTIPLIER;
mutex_unlock(&dev_priv->rps.hw_lock);
return 0;
@@ -3569,16 +3569,16 @@ i915_min_freq_set(void *data, u64 val)
do_div(val, GT_FREQUENCY_MULTIPLIER);
rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
- hw_max = dev_priv->rps.hw_max;
+ hw_max = dev_priv->rps.max_freq;
hw_min = (rp_state_cap >> 16) & 0xff;
}
- if (val < hw_min || val > hw_max || val > dev_priv->rps.max_delay) {
+ if (val < hw_min || val > hw_max || val > dev_priv->rps.max_freq_softlimit) {
mutex_unlock(&dev_priv->rps.hw_lock);
return -EINVAL;
}
- dev_priv->rps.min_delay = val;
+ dev_priv->rps.min_freq_softlimit = val;
if (IS_VALLEYVIEW(dev))
valleyview_set_rps(dev, val);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 241f5e1..c5c5760 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -980,14 +980,24 @@ struct intel_gen6_power_mgmt {
struct work_struct work;
u32 pm_iir;
- u8 cur_delay;
- u8 min_delay;
- u8 max_delay;
- u8 rpe_delay;
- u8 rp1_delay;
- u8 rp0_delay;
- u8 hw_max;
- u8 min_freq;
+ /* Frequencies are stored in potentially platform dependent multiples.
+ * In other words, *_freq needs to be multiplied by X to be interesting.
+ * Soft limits are those which are used for the dynamic reclocking done
+ * by the driver (raise frequencies under heavy loads, and lower for
+ * lighter loads). Hard limits are those imposed by the hardware.
+ *
+ * A distinction is made for overclocking, which is never enabled by
+ * default, and is considered to be above the hard limit if it's
+ * possible at all.
+ */
+ u8 cur_freq; /* Current frequency (cached, may not == HW) */
+ u8 min_freq_softlimit; /* Minimum frequency permitted by the driver */
+ u8 max_freq_softlimit; /* Max frequency permitted by the driver */
+ u8 max_freq; /* Maximum frequency, RP0 if not overclocking */
+ u8 min_freq; /* AKA RPn. Minimum frequency */
+ u8 efficient_freq; /* AKA RPe. Pre-determined balanced frequency */
+ u8 rp1_freq; /* "less than" RP0 power/freqency */
+ u8 rp0_freq; /* Non-overclocked max frequency. */
bool rp_up_masked;
bool rp_down_masked;
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 888f08c..4b4aeb3 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1088,7 +1088,7 @@ void gen6_set_pm_mask(struct drm_i915_private *dev_priv,
u32 pm_iir, int new_delay)
{
if (pm_iir & GEN6_PM_RP_UP_THRESHOLD) {
- if (new_delay >= dev_priv->rps.max_delay) {
+ if (new_delay >= dev_priv->rps.max_freq_softlimit) {
/* Mask UP THRESHOLD Interrupts */
I915_WRITE(GEN6_PMINTRMSK,
I915_READ(GEN6_PMINTRMSK) |
@@ -1103,7 +1103,7 @@ void gen6_set_pm_mask(struct drm_i915_private *dev_priv,
dev_priv->rps.rp_down_masked = false;
}
} else if (pm_iir & GEN6_PM_RP_DOWN_THRESHOLD) {
- if (new_delay <= dev_priv->rps.min_delay) {
+ if (new_delay <= dev_priv->rps.min_freq_softlimit) {
/* Mask DOWN THRESHOLD Interrupts */
I915_WRITE(GEN6_PMINTRMSK,
I915_READ(GEN6_PMINTRMSK) |
@@ -1149,38 +1149,39 @@ static void gen6_pm_rps_work(struct work_struct *work)
adj *= 2;
else
adj = 1;
- new_delay = dev_priv->rps.cur_delay + adj;
+ new_delay = dev_priv->rps.cur_freq + adj;
/*
* For better performance, jump directly
* to RPe if we're below it.
*/
- if (new_delay < dev_priv->rps.rpe_delay)
- new_delay = dev_priv->rps.rpe_delay;
+ if (new_delay < dev_priv->rps.efficient_freq)
+ new_delay = dev_priv->rps.efficient_freq;
} else if (pm_iir & GEN6_PM_RP_DOWN_TIMEOUT) {
- if (dev_priv->rps.cur_delay > dev_priv->rps.rpe_delay)
- new_delay = dev_priv->rps.rpe_delay;
+ if (dev_priv->rps.cur_freq > dev_priv->rps.efficient_freq)
+ new_delay = dev_priv->rps.efficient_freq;
else
- new_delay = dev_priv->rps.min_delay;
+ new_delay = dev_priv->rps.min_freq_softlimit;
adj = 0;
} else if (pm_iir & GEN6_PM_RP_DOWN_THRESHOLD) {
if (adj < 0)
adj *= 2;
else
adj = -1;
- new_delay = dev_priv->rps.cur_delay + adj;
+ new_delay = dev_priv->rps.cur_freq + adj;
} else { /* unknown event */
- new_delay = dev_priv->rps.cur_delay;
+ new_delay = dev_priv->rps.cur_freq;
}
/* sysfs frequency interfaces may have snuck in while servicing the
* interrupt
*/
new_delay = clamp_t(int, new_delay,
- dev_priv->rps.min_delay, dev_priv->rps.max_delay);
+ dev_priv->rps.min_freq_softlimit,
+ dev_priv->rps.max_freq_softlimit);
gen6_set_pm_mask(dev_priv, pm_iir, new_delay);
- dev_priv->rps.last_adj = new_delay - dev_priv->rps.cur_delay;
+ dev_priv->rps.last_adj = new_delay - dev_priv->rps.cur_freq;
if (IS_VALLEYVIEW(dev_priv->dev))
valleyview_set_rps(dev_priv->dev, new_delay);
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index e9ffefb..e3fa8cd 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -269,7 +269,7 @@ static ssize_t gt_cur_freq_mhz_show(struct device *kdev,
freq = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
ret = vlv_gpu_freq(dev_priv, (freq >> 8) & 0xff);
} else {
- ret = dev_priv->rps.cur_delay * GT_FREQUENCY_MULTIPLIER;
+ ret = dev_priv->rps.cur_freq * GT_FREQUENCY_MULTIPLIER;
}
mutex_unlock(&dev_priv->rps.hw_lock);
@@ -284,7 +284,7 @@ static ssize_t vlv_rpe_freq_mhz_show(struct device *kdev,
struct drm_i915_private *dev_priv = dev->dev_private;
return snprintf(buf, PAGE_SIZE, "%d\n",
- vlv_gpu_freq(dev_priv, dev_priv->rps.rpe_delay));
+ vlv_gpu_freq(dev_priv, dev_priv->rps.efficient_freq));
}
static ssize_t gt_max_freq_mhz_show(struct device *kdev, struct device_attribute *attr, char *buf)
@@ -298,9 +298,9 @@ static ssize_t gt_max_freq_mhz_show(struct device *kdev, struct device_attribute
mutex_lock(&dev_priv->rps.hw_lock);
if (IS_VALLEYVIEW(dev_priv->dev))
- ret = vlv_gpu_freq(dev_priv, dev_priv->rps.max_delay);
+ ret = vlv_gpu_freq(dev_priv, dev_priv->rps.max_freq_softlimit);
else
- ret = dev_priv->rps.max_delay * GT_FREQUENCY_MULTIPLIER;
+ ret = dev_priv->rps.max_freq_softlimit * GT_FREQUENCY_MULTIPLIER;
mutex_unlock(&dev_priv->rps.hw_lock);
return snprintf(buf, PAGE_SIZE, "%d\n", ret);
@@ -334,13 +334,13 @@ static ssize_t gt_max_freq_mhz_store(struct device *kdev,
val /= GT_FREQUENCY_MULTIPLIER;
rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
- hw_max = dev_priv->rps.hw_max;
+ hw_max = dev_priv->rps.max_freq;
non_oc_max = (rp_state_cap & 0xff);
hw_min = ((rp_state_cap & 0xff0000) >> 16);
}
if (val < hw_min || val > hw_max ||
- val < dev_priv->rps.min_delay) {
+ val < dev_priv->rps.min_freq_softlimit) {
mutex_unlock(&dev_priv->rps.hw_lock);
return -EINVAL;
}
@@ -349,9 +349,9 @@ static ssize_t gt_max_freq_mhz_store(struct device *kdev,
DRM_DEBUG("User requested overclocking to %d\n",
val * GT_FREQUENCY_MULTIPLIER);
- dev_priv->rps.max_delay = val;
+ dev_priv->rps.max_freq_softlimit = val;
- if (dev_priv->rps.cur_delay > val) {
+ if (dev_priv->rps.cur_freq > val) {
if (IS_VALLEYVIEW(dev))
valleyview_set_rps(dev, val);
else
@@ -360,7 +360,7 @@ static ssize_t gt_max_freq_mhz_store(struct device *kdev,
/* We still need gen6_set_rps to process the new max_delay and
* update the interrupt limits even though frequency request is
* unchanged. */
- gen6_set_rps(dev, dev_priv->rps.cur_delay);
+ gen6_set_rps(dev, dev_priv->rps.cur_freq);
}
mutex_unlock(&dev_priv->rps.hw_lock);
@@ -379,9 +379,9 @@ static ssize_t gt_min_freq_mhz_show(struct device *kdev, struct device_attribute
mutex_lock(&dev_priv->rps.hw_lock);
if (IS_VALLEYVIEW(dev_priv->dev))
- ret = vlv_gpu_freq(dev_priv, dev_priv->rps.min_delay);
+ ret = vlv_gpu_freq(dev_priv, dev_priv->rps.min_freq_softlimit);
else
- ret = dev_priv->rps.min_delay * GT_FREQUENCY_MULTIPLIER;
+ ret = dev_priv->rps.min_freq_softlimit * GT_FREQUENCY_MULTIPLIER;
mutex_unlock(&dev_priv->rps.hw_lock);
return snprintf(buf, PAGE_SIZE, "%d\n", ret);
@@ -414,18 +414,18 @@ static ssize_t gt_min_freq_mhz_store(struct device *kdev,
val /= GT_FREQUENCY_MULTIPLIER;
rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
- hw_max = dev_priv->rps.hw_max;
+ hw_max = dev_priv->rps.max_freq;
hw_min = ((rp_state_cap & 0xff0000) >> 16);
}
- if (val < hw_min || val > hw_max || val > dev_priv->rps.max_delay) {
+ if (val < hw_min || val > hw_max || val > dev_priv->rps.max_freq_softlimit) {
mutex_unlock(&dev_priv->rps.hw_lock);
return -EINVAL;
}
- dev_priv->rps.min_delay = val;
+ dev_priv->rps.min_freq_softlimit = val;
- if (dev_priv->rps.cur_delay < val) {
+ if (dev_priv->rps.cur_freq < val) {
if (IS_VALLEYVIEW(dev))
valleyview_set_rps(dev, val);
else
@@ -434,7 +434,7 @@ static ssize_t gt_min_freq_mhz_store(struct device *kdev,
/* We still need gen6_set_rps to process the new min_delay and
* update the interrupt limits even though frequency request is
* unchanged. */
- gen6_set_rps(dev, dev_priv->rps.cur_delay);
+ gen6_set_rps(dev, dev_priv->rps.cur_freq);
}
mutex_unlock(&dev_priv->rps.hw_lock);
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index dd631d1..3db7c40 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2907,9 +2907,9 @@ static u32 gen6_rps_limits(struct drm_i915_private *dev_priv, u8 val)
* the hw runs at the minimal clock before selecting the desired
* frequency, if the down threshold expires in that window we will not
* receive a down interrupt. */
- limits = dev_priv->rps.max_delay << 24;
- if (val <= dev_priv->rps.min_delay)
- limits |= dev_priv->rps.min_delay << 16;
+ limits = dev_priv->rps.max_freq_softlimit << 24;
+ if (val <= dev_priv->rps.min_freq_softlimit)
+ limits |= dev_priv->rps.min_freq_softlimit << 16;
return limits;
}
@@ -2921,26 +2921,26 @@ static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
new_power = dev_priv->rps.power;
switch (dev_priv->rps.power) {
case LOW_POWER:
- if (val > dev_priv->rps.rpe_delay + 1 && val > dev_priv->rps.cur_delay)
+ if (val > dev_priv->rps.efficient_freq + 1 && val > dev_priv->rps.cur_freq)
new_power = BETWEEN;
break;
case BETWEEN:
- if (val <= dev_priv->rps.rpe_delay && val < dev_priv->rps.cur_delay)
+ if (val <= dev_priv->rps.efficient_freq && val < dev_priv->rps.cur_freq)
new_power = LOW_POWER;
- else if (val >= dev_priv->rps.rp0_delay && val > dev_priv->rps.cur_delay)
+ else if (val >= dev_priv->rps.rp0_freq && val > dev_priv->rps.cur_freq)
new_power = HIGH_POWER;
break;
case HIGH_POWER:
- if (val < (dev_priv->rps.rp1_delay + dev_priv->rps.rp0_delay) >> 1 && val < dev_priv->rps.cur_delay)
+ if (val < (dev_priv->rps.rp1_freq + dev_priv->rps.rp0_freq) >> 1 && val < dev_priv->rps.cur_freq)
new_power = BETWEEN;
break;
}
/* Max/min bins are special */
- if (val == dev_priv->rps.min_delay)
+ if (val == dev_priv->rps.min_freq_softlimit)
new_power = LOW_POWER;
- if (val == dev_priv->rps.max_delay)
+ if (val == dev_priv->rps.max_freq_softlimit)
new_power = HIGH_POWER;
if (new_power == dev_priv->rps.power)
return;
@@ -3014,10 +3014,10 @@ void gen6_set_rps(struct drm_device *dev, u8 val)
struct drm_i915_private *dev_priv = dev->dev_private;
WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
- WARN_ON(val > dev_priv->rps.max_delay);
- WARN_ON(val < dev_priv->rps.min_delay);
+ WARN_ON(val > dev_priv->rps.max_freq_softlimit);
+ WARN_ON(val < dev_priv->rps.min_freq_softlimit);
- if (val == dev_priv->rps.cur_delay) {
+ if (val == dev_priv->rps.cur_freq) {
/* min/max delay may still have been modified so be sure to
* write the limits value */
I915_WRITE(GEN6_RP_INTERRUPT_LIMITS,
@@ -3045,7 +3045,7 @@ void gen6_set_rps(struct drm_device *dev, u8 val)
POSTING_READ(GEN6_RPNSWREQ);
- dev_priv->rps.cur_delay = val;
+ dev_priv->rps.cur_freq = val;
trace_intel_gpu_freq_change(val * 50);
}
@@ -3065,7 +3065,7 @@ static void vlv_set_rps_idle(struct drm_i915_private *dev_priv)
* When we are idle. Drop to min voltage state.
*/
- if (dev_priv->rps.cur_delay <= dev_priv->rps.min_delay)
+ if (dev_priv->rps.cur_freq <= dev_priv->rps.min_freq_softlimit)
return;
/* Mask turbo interrupt so that they will not come in between */
@@ -3082,10 +3082,10 @@ static void vlv_set_rps_idle(struct drm_i915_private *dev_priv)
return;
}
- dev_priv->rps.cur_delay = dev_priv->rps.min_delay;
+ dev_priv->rps.cur_freq = dev_priv->rps.min_freq_softlimit;
vlv_punit_write(dev_priv, PUNIT_REG_GPU_FREQ_REQ,
- dev_priv->rps.min_delay);
+ dev_priv->rps.min_freq_softlimit);
if (wait_for(((vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS))
& GENFREQSTATUS) == 0, 5))
@@ -3099,7 +3099,7 @@ static void vlv_set_rps_idle(struct drm_i915_private *dev_priv)
/* Unmask Up interrupts */
dev_priv->rps.rp_up_masked = true;
gen6_set_pm_mask(dev_priv, GEN6_PM_RP_DOWN_THRESHOLD,
- dev_priv->rps.min_delay);
+ dev_priv->rps.min_freq_softlimit);
}
void gen6_rps_idle(struct drm_i915_private *dev_priv)
@@ -3111,7 +3111,7 @@ void gen6_rps_idle(struct drm_i915_private *dev_priv)
if (IS_VALLEYVIEW(dev))
vlv_set_rps_idle(dev_priv);
else
- gen6_set_rps(dev_priv->dev, dev_priv->rps.min_delay);
+ gen6_set_rps(dev_priv->dev, dev_priv->rps.min_freq_softlimit);
dev_priv->rps.last_adj = 0;
}
mutex_unlock(&dev_priv->rps.hw_lock);
@@ -3124,9 +3124,9 @@ void gen6_rps_boost(struct drm_i915_private *dev_priv)
mutex_lock(&dev_priv->rps.hw_lock);
if (dev_priv->rps.enabled) {
if (IS_VALLEYVIEW(dev))
- valleyview_set_rps(dev_priv->dev, dev_priv->rps.max_delay);
+ valleyview_set_rps(dev_priv->dev, dev_priv->rps.max_freq_softlimit);
else
- gen6_set_rps(dev_priv->dev, dev_priv->rps.max_delay);
+ gen6_set_rps(dev_priv->dev, dev_priv->rps.max_freq_softlimit);
dev_priv->rps.last_adj = 0;
}
mutex_unlock(&dev_priv->rps.hw_lock);
@@ -3137,20 +3137,20 @@ void valleyview_set_rps(struct drm_device *dev, u8 val)
struct drm_i915_private *dev_priv = dev->dev_private;
WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
- WARN_ON(val > dev_priv->rps.max_delay);
- WARN_ON(val < dev_priv->rps.min_delay);
+ WARN_ON(val > dev_priv->rps.max_freq_softlimit);
+ WARN_ON(val < dev_priv->rps.min_freq_softlimit);
DRM_DEBUG_DRIVER("GPU freq request from %d MHz (%u) to %d MHz (%u)\n",
- vlv_gpu_freq(dev_priv, dev_priv->rps.cur_delay),
- dev_priv->rps.cur_delay,
+ vlv_gpu_freq(dev_priv, dev_priv->rps.cur_freq),
+ dev_priv->rps.cur_freq,
vlv_gpu_freq(dev_priv, val), val);
- if (val == dev_priv->rps.cur_delay)
+ if (val == dev_priv->rps.cur_freq)
return;
vlv_punit_write(dev_priv, PUNIT_REG_GPU_FREQ_REQ, val);
- dev_priv->rps.cur_delay = val;
+ dev_priv->rps.cur_freq = val;
trace_intel_gpu_freq_change(vlv_gpu_freq(dev_priv, val));
}
@@ -3292,8 +3292,8 @@ static void gen8_enable_rps(struct drm_device *dev)
/* Docs recommend 900MHz, and 300 MHz respectively */
I915_WRITE(GEN6_RP_INTERRUPT_LIMITS,
- dev_priv->rps.max_delay << 24 |
- dev_priv->rps.min_delay << 16);
+ dev_priv->rps.max_freq_softlimit << 24 |
+ dev_priv->rps.min_freq_softlimit << 16);
I915_WRITE(GEN6_RP_UP_THRESHOLD, 7600000 / 128); /* 76ms busyness per EI, 90% */
I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 31300000 / 128); /* 313ms busyness per EI, 70%*/
@@ -3352,20 +3352,22 @@ static void gen6_enable_rps(struct drm_device *dev)
rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
gt_perf_status = I915_READ(GEN6_GT_PERF_STATUS);
- /* In units of 50MHz */
- dev_priv->rps.hw_max = hw_max = rp_state_cap & 0xff;
+ /* All of these values are in units of 50MHz */
+ dev_priv->rps.cur_freq = 0;
+ /* hw_max = RP0 until we check for overclocking */
+ dev_priv->rps.max_freq = hw_max = rp_state_cap & 0xff;
+ /* static values from HW: RP0 < RPe < RP1 < RPn (min_freq) */
+ dev_priv->rps.rp1_freq = (rp_state_cap >> 8) & 0xff;
+ dev_priv->rps.rp0_freq = (rp_state_cap >> 0) & 0xff;
+ dev_priv->rps.efficient_freq = dev_priv->rps.rp1_freq;
dev_priv->rps.min_freq = hw_min = (rp_state_cap >> 16) & 0xff;
- dev_priv->rps.rp1_delay = (rp_state_cap >> 8) & 0xff;
- dev_priv->rps.rp0_delay = (rp_state_cap >> 0) & 0xff;
- dev_priv->rps.rpe_delay = dev_priv->rps.rp1_delay;
- dev_priv->rps.cur_delay = 0;
/* Preserve min/max settings in case of re-init */
- if (dev_priv->rps.max_delay == 0)
- dev_priv->rps.max_delay = hw_max;
+ if (dev_priv->rps.max_freq_softlimit == 0)
+ dev_priv->rps.max_freq_softlimit = hw_max;
- if (dev_priv->rps.min_delay == 0)
- dev_priv->rps.min_delay = hw_min;
+ if (dev_priv->rps.min_freq_softlimit == 0)
+ dev_priv->rps.min_freq_softlimit = hw_min;
/* disable the counters and set deterministic thresholds */
I915_WRITE(GEN6_RC_CONTROL, 0);
@@ -3420,13 +3422,13 @@ static void gen6_enable_rps(struct drm_device *dev)
ret = sandybridge_pcode_read(dev_priv, GEN6_READ_OC_PARAMS, &pcu_mbox);
if (!ret && (pcu_mbox & (1<<31))) { /* OC supported */
DRM_DEBUG_DRIVER("Overclocking supported. Max: %dMHz, Overclock max: %dMHz\n",
- (dev_priv->rps.max_delay & 0xff) * 50,
+ (dev_priv->rps.max_freq_softlimit & 0xff) * 50,
(pcu_mbox & 0xff) * 50);
- dev_priv->rps.hw_max = pcu_mbox & 0xff;
+ dev_priv->rps.max_freq = pcu_mbox & 0xff;
}
dev_priv->rps.power = HIGH_POWER; /* force a reset */
- gen6_set_rps(dev_priv->dev, dev_priv->rps.min_delay);
+ gen6_set_rps(dev_priv->dev, dev_priv->rps.min_freq_softlimit);
gen6_enable_rps_interrupts(dev);
@@ -3482,9 +3484,9 @@ void gen6_update_ring_freq(struct drm_device *dev)
* to use for memory access. We do this by specifying the IA frequency
* the PCU should use as a reference to determine the ring frequency.
*/
- for (gpu_freq = dev_priv->rps.max_delay; gpu_freq >= dev_priv->rps.min_delay;
+ for (gpu_freq = dev_priv->rps.max_freq_softlimit; gpu_freq >= dev_priv->rps.min_freq_softlimit;
gpu_freq--) {
- int diff = dev_priv->rps.max_delay - gpu_freq;
+ int diff = dev_priv->rps.max_freq_softlimit - gpu_freq;
unsigned int ia_freq = 0, ring_freq = 0;
if (INTEL_INFO(dev)->gen >= 8) {
@@ -3650,20 +3652,20 @@ static void valleyview_enable_rps(struct drm_device *dev)
DRM_DEBUG_DRIVER("GPLL enabled? %s\n", val & 0x10 ? "yes" : "no");
DRM_DEBUG_DRIVER("GPU status: 0x%08x\n", val);
- dev_priv->rps.cur_delay = (val >> 8) & 0xff;
+ dev_priv->rps.cur_freq = (val >> 8) & 0xff;
DRM_DEBUG_DRIVER("current GPU freq: %d MHz (%u)\n",
- vlv_gpu_freq(dev_priv, dev_priv->rps.cur_delay),
- dev_priv->rps.cur_delay);
+ vlv_gpu_freq(dev_priv, dev_priv->rps.cur_freq),
+ dev_priv->rps.cur_freq);
- dev_priv->rps.hw_max = hw_max = valleyview_rps_max_freq(dev_priv);
+ dev_priv->rps.max_freq = hw_max = valleyview_rps_max_freq(dev_priv);
DRM_DEBUG_DRIVER("max GPU freq: %d MHz (%u)\n",
vlv_gpu_freq(dev_priv, hw_max),
hw_max);
- dev_priv->rps.rpe_delay = valleyview_rps_rpe_freq(dev_priv);
+ dev_priv->rps.efficient_freq = valleyview_rps_rpe_freq(dev_priv);
DRM_DEBUG_DRIVER("RPe GPU freq: %d MHz (%u)\n",
- vlv_gpu_freq(dev_priv, dev_priv->rps.rpe_delay),
- dev_priv->rps.rpe_delay);
+ vlv_gpu_freq(dev_priv, dev_priv->rps.efficient_freq),
+ dev_priv->rps.efficient_freq);
hw_min = valleyview_rps_min_freq(dev_priv);
DRM_DEBUG_DRIVER("min GPU freq: %d MHz (%u)\n",
@@ -3671,17 +3673,17 @@ static void valleyview_enable_rps(struct drm_device *dev)
hw_min);
/* Preserve min/max settings in case of re-init */
- if (dev_priv->rps.max_delay == 0)
- dev_priv->rps.max_delay = hw_max;
+ if (dev_priv->rps.max_freq_softlimit == 0)
+ dev_priv->rps.max_freq_softlimit = hw_max;
- if (dev_priv->rps.min_delay == 0)
- dev_priv->rps.min_delay = hw_min;
+ if (dev_priv->rps.min_freq_softlimit == 0)
+ dev_priv->rps.min_freq_softlimit = hw_min;
DRM_DEBUG_DRIVER("setting GPU freq to %d MHz (%u)\n",
- vlv_gpu_freq(dev_priv, dev_priv->rps.rpe_delay),
- dev_priv->rps.rpe_delay);
+ vlv_gpu_freq(dev_priv, dev_priv->rps.efficient_freq),
+ dev_priv->rps.efficient_freq);
- valleyview_set_rps(dev_priv->dev, dev_priv->rps.rpe_delay);
+ valleyview_set_rps(dev_priv->dev, dev_priv->rps.efficient_freq);
dev_priv->rps.rp_up_masked = false;
dev_priv->rps.rp_down_masked = false;
@@ -4122,7 +4124,7 @@ static unsigned long __i915_gfx_val(struct drm_i915_private *dev_priv)
assert_spin_locked(&mchdev_lock);
- pxvid = I915_READ(PXVFREQ_BASE + (dev_priv->rps.cur_delay * 4));
+ pxvid = I915_READ(PXVFREQ_BASE + (dev_priv->rps.cur_freq * 4));
pxvid = (pxvid >> 24) & 0x7f;
ext_v = pvid_to_extvid(dev_priv, pxvid);
--
1.9.0
More information about the Intel-gfx
mailing list