[Intel-gfx] [PATCH v2] drm/i915/bdw: BDW Software Turbo
Daisy Sun
daisy.sun at intel.com
Thu Jul 10 03:00:48 CEST 2014
BDW supports GT C0 residency reporting in constant time unit. Driver calculates
GT utilization based on C0 residency and adjusts RP frequency up/down
accordingly.
Signed-off-by: Daisy Sun <daisy.sun at intel.com>
[torourke: rebased on latest and resolved conflict]
Signed-off-by: Tom O'Rourke <Tom.O'Rourke at intel.com>
---
drivers/gpu/drm/i915/i915_drv.h | 17 ++
drivers/gpu/drm/i915/i915_irq.c | 10 ++
drivers/gpu/drm/i915/i915_reg.h | 4 +
drivers/gpu/drm/i915/intel_display.c | 2 +
drivers/gpu/drm/i915/intel_drv.h | 1 +
drivers/gpu/drm/i915/intel_pm.c | 148 ++++++++++++++---
6 files changed, 162 insertions(+), 20 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 272aa7a..eef8366 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -820,6 +820,19 @@ struct i915_suspend_saved_registers {
u32 savePCH_PORT_HOTPLUG;
};
+struct intel_rps_bdw_cal {
+ u32 it_threshold_pct; /* interrupt, in percentage */
+ u32 eval_interval; /* evaluation interval, in us */
+ u32 last_ts;
+ u32 last_c0;
+ bool is_up;
+};
+
+struct intel_rps_bdw_turbo {
+ struct intel_rps_bdw_cal up;
+ struct intel_rps_bdw_cal down;
+};
+
struct intel_gen6_power_mgmt {
/* work and pm_iir are protected by dev_priv->irq_lock */
struct work_struct work;
@@ -850,6 +863,9 @@ struct intel_gen6_power_mgmt {
bool enabled;
struct delayed_work delayed_resume_work;
+ bool is_bdw_sw_turbo; /* Switch of BDW software turbo */
+ struct intel_rps_bdw_turbo sw_turbo; /* Calculate RP interrupt timing */
+
/*
* Protects RPS/RC6 register access and PCU communication.
* Must be taken after struct_mutex if nested.
@@ -2509,6 +2525,7 @@ extern void intel_disable_fbc(struct drm_device *dev);
extern bool ironlake_set_drps(struct drm_device *dev, u8 val);
extern void intel_init_pch_refclk(struct drm_device *dev);
extern void gen6_set_rps(struct drm_device *dev, u8 val);
+extern void bdw_software_turbo(struct drm_device *dev);
extern void valleyview_set_rps(struct drm_device *dev, u8 val);
extern int valleyview_rps_max_freq(struct drm_i915_private *dev_priv);
extern int valleyview_rps_min_freq(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 2b3d852..e077269 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1558,6 +1558,16 @@ static void i9xx_pipe_crc_irq_handler(struct drm_device *dev, enum pipe pipe)
res1, res2);
}
+void gen8_flip_interrupt(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+
+ if (!dev_priv->rps.is_bdw_sw_turbo)
+ return;
+
+ bdw_software_turbo(dev);
+}
+
/* The RPS events need forcewake, so we add them to a work queue and mask their
* IMR bits until the work is done. Other interrupts can be processed without
* the work queue. */
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 0b88508..ec08cd9 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -5041,6 +5041,10 @@ enum punit_power_well {
#define GEN8_UCGCTL6 0x9430
#define GEN8_SDEUNIT_CLOCK_GATE_DISABLE (1<<14)
+#define TIMESTAMP_CTR 0x44070
+#define FREQ_1_28_US(us) (((us) * 100) >> 7)
+#define MCHBAR_PCU_C0 (MCHBAR_MIRROR_BASE_SNB + 0x5960)
+
#define GEN6_RPNSWREQ 0xA008
#define GEN6_TURBO_DISABLE (1<<31)
#define GEN6_FREQUENCY(x) ((x)<<25)
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index b57210c..8e39ea7 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -8893,6 +8893,8 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
unsigned long flags;
int ret;
+ gen8_flip_interrupt(dev);
+
/* Can't change pixel format via MI display flips. */
if (fb->pixel_format != crtc->primary->fb->pixel_format)
return -EINVAL;
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index b885df1..15010d3 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -929,6 +929,7 @@ void ironlake_teardown_rc6(struct drm_device *dev);
void gen6_update_ring_freq(struct drm_device *dev);
void gen6_rps_idle(struct drm_i915_private *dev_priv);
void gen6_rps_boost(struct drm_i915_private *dev_priv);
+void gen8_flip_interrupt(struct drm_device *dev);
void intel_aux_display_runtime_get(struct drm_i915_private *dev_priv);
void intel_aux_display_runtime_put(struct drm_i915_private *dev_priv);
void intel_runtime_pm_get(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 75c1c76..9327cd7 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2963,6 +2963,9 @@ static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
{
int new_power;
+ if (dev_priv->rps.is_bdw_sw_turbo)
+ return;
+
new_power = dev_priv->rps.power;
switch (dev_priv->rps.power) {
case LOW_POWER:
@@ -3308,12 +3311,87 @@ static void parse_rp_state_cap(struct drm_i915_private *dev_priv, u32 rp_state_c
dev_priv->rps.min_freq_softlimit = dev_priv->rps.min_freq;
}
+static void bdw_sw_calculate_freq(struct drm_device *dev,
+ struct intel_rps_bdw_cal *c, u32 *cur_time, u32 *c0)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ u64 busy = 0;
+ u32 busyness_pct = 0;
+ u32 elapsed_time = 0;
+ u16 new_freq = 0;
+
+ if (!c || !cur_time || !c0)
+ return;
+
+ if (0 == c->last_c0)
+ goto out;
+
+ /* Check Evaluation interval */
+ elapsed_time = *cur_time - c->last_ts;
+ if (elapsed_time < c->eval_interval)
+ return;
+
+ mutex_lock(&dev_priv->rps.hw_lock);
+
+ /*
+ * c0 unit in 32*1.28 usec, elapsed_time unit in 1 usec.
+ * Whole busyness_pct calculation should be
+ * busy = ((u64)(*c0 - c->last_c0) << 5 << 7) / 100;
+ * busyness_pct = (u32)(busy * 100 / elapsed_time);
+ * The final formula is to simplify CPU calculation
+ */
+ busy = (u64)(*c0 - c->last_c0) << 12;
+ do_div(busy, elapsed_time);
+ busyness_pct = (u32)busy;
+
+ if (c->is_up && busyness_pct >= c->it_threshold_pct)
+ new_freq = (u16)dev_priv->rps.cur_freq + 3;
+ if (!c->is_up && busyness_pct <= c->it_threshold_pct)
+ new_freq = (u16)dev_priv->rps.cur_freq - 1;
+
+ /* Adjust to new frequency busyness and compare with threshold */
+ if (0 != new_freq) {
+ if (new_freq > dev_priv->rps.max_freq_softlimit)
+ new_freq = dev_priv->rps.max_freq_softlimit;
+ else if (new_freq < dev_priv->rps.min_freq_softlimit)
+ new_freq = dev_priv->rps.min_freq_softlimit;
+
+ gen6_set_rps(dev, new_freq);
+ }
+
+ mutex_unlock(&dev_priv->rps.hw_lock);
+
+out:
+ c->last_c0 = *c0;
+ c->last_ts = *cur_time;
+}
+
+void bdw_software_turbo(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+
+ u32 current_time = I915_READ(TIMESTAMP_CTR); /* unit in usec */
+ u32 current_c0 = I915_READ(MCHBAR_PCU_C0); /* unit in 32*1.28 usec */
+
+ bdw_sw_calculate_freq(dev, &dev_priv->rps.sw_turbo.up,
+ ¤t_time, ¤t_c0);
+ bdw_sw_calculate_freq(dev, &dev_priv->rps.sw_turbo.down,
+ ¤t_time, ¤t_c0);
+}
+
+
static void gen8_enable_rps(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_ring_buffer *ring;
uint32_t rc6_mask = 0, rp_state_cap;
+ uint32_t threshold_up_pct, threshold_down_pct;
+ uint32_t ei_up, ei_down; /* up and down evaluation interval */
+ u32 rp_ctl_flag;
int unused;
+
+ /* Use software Turbo for BDW */
+ dev_priv->rps.is_bdw_sw_turbo = IS_BROADWELL(dev);
/* 1a: Software RC state - RC0 */
I915_WRITE(GEN6_RC_STATE, 0);
@@ -3350,35 +3428,62 @@ static void gen8_enable_rps(struct drm_device *dev)
HSW_FREQUENCY(dev_priv->rps.rp1_freq));
I915_WRITE(GEN6_RC_VIDEO_FREQ,
HSW_FREQUENCY(dev_priv->rps.rp1_freq));
- /* NB: Docs say 1s, and 1000000 - which aren't equivalent */
- I915_WRITE(GEN6_RP_DOWN_TIMEOUT, 100000000 / 128); /* 1 second timeout */
+ ei_up = 84480; /* 84.48ms */
+ ei_down = 448000;
+ threshold_up_pct = 90; /* x percent busy */
+ threshold_down_pct = 70;
+
+ if (dev_priv->rps.is_bdw_sw_turbo) {
+ dev_priv->rps.sw_turbo.up.it_threshold_pct = threshold_up_pct;
+ dev_priv->rps.sw_turbo.up.eval_interval = ei_up;
+ dev_priv->rps.sw_turbo.up.is_up = true;
+ dev_priv->rps.sw_turbo.up.last_ts = 0;
+ dev_priv->rps.sw_turbo.up.last_c0 = 0;
+
+ dev_priv->rps.sw_turbo.down.it_threshold_pct = threshold_down_pct;
+ dev_priv->rps.sw_turbo.down.eval_interval = ei_down;
+ dev_priv->rps.sw_turbo.down.is_up = false;
+ dev_priv->rps.sw_turbo.down.last_ts = 0;
+ dev_priv->rps.sw_turbo.down.last_c0 = 0;
+ } else {
+ /* NB: Docs say 1s, and 1000000 - which aren't equivalent
+ * 1 second timeout*/
+ I915_WRITE(GEN6_RP_DOWN_TIMEOUT, FREQ_1_28_US(1000000));
- /* Docs recommend 900MHz, and 300 MHz respectively */
- I915_WRITE(GEN6_RP_INTERRUPT_LIMITS,
- dev_priv->rps.max_freq_softlimit << 24 |
- dev_priv->rps.min_freq_softlimit << 16);
+ /* Docs recommend 900MHz, and 300 MHz respectively */
+ I915_WRITE(GEN6_RP_INTERRUPT_LIMITS,
+ 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%*/
- I915_WRITE(GEN6_RP_UP_EI, 66000); /* 84.48ms, XXX: random? */
- I915_WRITE(GEN6_RP_DOWN_EI, 350000); /* 448ms, XXX: random? */
+ I915_WRITE(GEN6_RP_UP_THRESHOLD,
+ FREQ_1_28_US(ei_up * threshold_up_pct / 100));
+ I915_WRITE(GEN6_RP_DOWN_THRESHOLD,
+ FREQ_1_28_US(ei_down * threshold_down_pct / 100));
+ I915_WRITE(GEN6_RP_UP_EI,
+ FREQ_1_28_US(ei_up));
+ I915_WRITE(GEN6_RP_DOWN_EI,
+ FREQ_1_28_US(ei_down));
- I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10);
+ I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10);
+ }
/* 5: Enable RPS */
- I915_WRITE(GEN6_RP_CONTROL,
- GEN6_RP_MEDIA_TURBO |
- GEN6_RP_MEDIA_HW_NORMAL_MODE |
- GEN6_RP_MEDIA_IS_GFX |
- GEN6_RP_ENABLE |
- GEN6_RP_UP_BUSY_AVG |
- GEN6_RP_DOWN_IDLE_AVG);
+ rp_ctl_flag = GEN6_RP_MEDIA_TURBO |
+ GEN6_RP_MEDIA_HW_NORMAL_MODE |
+ GEN6_RP_MEDIA_IS_GFX |
+ GEN6_RP_UP_BUSY_AVG |
+ GEN6_RP_DOWN_IDLE_AVG;
+ if (!dev_priv->rps.is_bdw_sw_turbo)
+ rp_ctl_flag |= GEN6_RP_ENABLE;
+
+ I915_WRITE(GEN6_RP_CONTROL, rp_ctl_flag);
/* 6: Ring frequency + overclocking (our driver does this later */
gen6_set_rps(dev, (I915_READ(GEN6_GT_PERF_STATUS) & 0xff00) >> 8);
-
- gen6_enable_rps_interrupts(dev);
+
+ if (!dev_priv->rps.is_bdw_sw_turbo)
+ gen6_enable_rps_interrupts(dev);
gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
}
@@ -4529,8 +4634,11 @@ static void intel_gen6_powersave_work(struct work_struct *work)
container_of(work, struct drm_i915_private,
rps.delayed_resume_work.work);
struct drm_device *dev = dev_priv->dev;
+
+ dev_priv->rps.is_bdw_sw_turbo = false;
mutex_lock(&dev_priv->rps.hw_lock);
+
if (IS_VALLEYVIEW(dev)) {
valleyview_enable_rps(dev);
--
1.9.1
More information about the Intel-gfx
mailing list