* i915.i915_enable_fbc parameter
*/
+static void gen9_init_clock_gating(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+
+ /*
+ * WaDisableSDEUnitClockGating:skl
+ * This seems to be a pre-production w/a.
+ */
+ I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
+ GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
+
+ /*
+ * WaDisableDgMirrorFixInHalfSliceChicken5:skl
+ * This is a pre-production w/a.
+ */
+ I915_WRITE(GEN9_HALF_SLICE_CHICKEN5,
+ I915_READ(GEN9_HALF_SLICE_CHICKEN5) &
+ ~GEN9_DG_MIRROR_FIX_ENABLE);
+
+ /* Wa4x4STCOptimizationDisable:skl */
+ I915_WRITE(CACHE_MODE_1,
+ _MASKED_BIT_ENABLE(GEN8_4x4_STC_OPTIMIZATION_DISABLE));
+}
+
static void i8xx_disable_fbc(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
* A value of 5us seems to be a good balance; safe for very low end
* platforms but not overly aggressive on lower latency configs.
*/
-static const int latency_ns = 5000;
+static const int pessimal_latency_ns = 5000;
static int i9xx_get_fifo_size(struct drm_device *dev, int plane)
{
.guard_size = 2,
.cacheline_size = I915_FIFO_LINE_SIZE,
};
-static const struct intel_watermark_params i830_wm_info = {
+static const struct intel_watermark_params i830_a_wm_info = {
.fifo_size = I855GM_FIFO_SIZE,
.max_wm = I915_MAX_WM,
.default_wm = 1,
.guard_size = 2,
.cacheline_size = I830_FIFO_LINE_SIZE,
};
+static const struct intel_watermark_params i830_bc_wm_info = {
+ .fifo_size = I855GM_FIFO_SIZE,
+ .max_wm = I915_MAX_WM/2,
+ .default_wm = 1,
+ .guard_size = 2,
+ .cacheline_size = I830_FIFO_LINE_SIZE,
+};
static const struct intel_watermark_params i845_wm_info = {
.fifo_size = I830_FIFO_SIZE,
.max_wm = I915_MAX_WM,
vlv_update_drain_latency(crtc);
if (g4x_compute_wm0(dev, PIPE_A,
- &valleyview_wm_info, latency_ns,
- &valleyview_cursor_wm_info, latency_ns,
+ &valleyview_wm_info, pessimal_latency_ns,
+ &valleyview_cursor_wm_info, pessimal_latency_ns,
&planea_wm, &cursora_wm))
enabled |= 1 << PIPE_A;
if (g4x_compute_wm0(dev, PIPE_B,
- &valleyview_wm_info, latency_ns,
- &valleyview_cursor_wm_info, latency_ns,
+ &valleyview_wm_info, pessimal_latency_ns,
+ &valleyview_cursor_wm_info, pessimal_latency_ns,
&planeb_wm, &cursorb_wm))
enabled |= 1 << PIPE_B;
vlv_update_drain_latency(crtc);
if (g4x_compute_wm0(dev, PIPE_A,
- &valleyview_wm_info, latency_ns,
- &valleyview_cursor_wm_info, latency_ns,
+ &valleyview_wm_info, pessimal_latency_ns,
+ &valleyview_cursor_wm_info, pessimal_latency_ns,
&planea_wm, &cursora_wm))
enabled |= 1 << PIPE_A;
if (g4x_compute_wm0(dev, PIPE_B,
- &valleyview_wm_info, latency_ns,
- &valleyview_cursor_wm_info, latency_ns,
+ &valleyview_wm_info, pessimal_latency_ns,
+ &valleyview_cursor_wm_info, pessimal_latency_ns,
&planeb_wm, &cursorb_wm))
enabled |= 1 << PIPE_B;
if (g4x_compute_wm0(dev, PIPE_C,
- &valleyview_wm_info, latency_ns,
- &valleyview_cursor_wm_info, latency_ns,
+ &valleyview_wm_info, pessimal_latency_ns,
+ &valleyview_cursor_wm_info, pessimal_latency_ns,
&planec_wm, &cursorc_wm))
enabled |= 1 << PIPE_C;
bool cxsr_enabled;
if (g4x_compute_wm0(dev, PIPE_A,
- &g4x_wm_info, latency_ns,
- &g4x_cursor_wm_info, latency_ns,
+ &g4x_wm_info, pessimal_latency_ns,
+ &g4x_cursor_wm_info, pessimal_latency_ns,
&planea_wm, &cursora_wm))
enabled |= 1 << PIPE_A;
if (g4x_compute_wm0(dev, PIPE_B,
- &g4x_wm_info, latency_ns,
- &g4x_cursor_wm_info, latency_ns,
+ &g4x_wm_info, pessimal_latency_ns,
+ &g4x_cursor_wm_info, pessimal_latency_ns,
&planeb_wm, &cursorb_wm))
enabled |= 1 << PIPE_B;
else if (!IS_GEN2(dev))
wm_info = &i915_wm_info;
else
- wm_info = &i830_wm_info;
+ wm_info = &i830_a_wm_info;
fifo_size = dev_priv->display.get_fifo_size(dev, 0);
crtc = intel_get_crtc_for_plane(dev, 0);
adjusted_mode = &to_intel_crtc(crtc)->config.adjusted_mode;
planea_wm = intel_calculate_wm(adjusted_mode->crtc_clock,
wm_info, fifo_size, cpp,
- latency_ns);
+ pessimal_latency_ns);
enabled = crtc;
- } else
+ } else {
planea_wm = fifo_size - wm_info->guard_size;
+ if (planea_wm > (long)wm_info->max_wm)
+ planea_wm = wm_info->max_wm;
+ }
+
+ if (IS_GEN2(dev))
+ wm_info = &i830_bc_wm_info;
fifo_size = dev_priv->display.get_fifo_size(dev, 1);
crtc = intel_get_crtc_for_plane(dev, 1);
adjusted_mode = &to_intel_crtc(crtc)->config.adjusted_mode;
planeb_wm = intel_calculate_wm(adjusted_mode->crtc_clock,
wm_info, fifo_size, cpp,
- latency_ns);
+ pessimal_latency_ns);
if (enabled == NULL)
enabled = crtc;
else
enabled = NULL;
- } else
+ } else {
planeb_wm = fifo_size - wm_info->guard_size;
+ if (planeb_wm > (long)wm_info->max_wm)
+ planeb_wm = wm_info->max_wm;
+ }
DRM_DEBUG_KMS("FIFO watermarks - A: %d, B: %d\n", planea_wm, planeb_wm);
planea_wm = intel_calculate_wm(adjusted_mode->crtc_clock,
&i845_wm_info,
dev_priv->display.get_fifo_size(dev, 0),
- 4, latency_ns);
+ 4, pessimal_latency_ns);
fwater_lo = I915_READ(FW_BLC) & ~0xfff;
fwater_lo |= (3<<8) | planea_wm;
else
return 2;
}
-
static void intel_print_wm_latency(struct drm_device *dev,
const char *name,
const uint16_t wm[5])
{
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:
valleyview_set_rps(dev_priv->dev, dev_priv->rps.min_freq_softlimit);
else if (IS_VALLEYVIEW(dev))
vlv_set_rps_idle(dev_priv);
- else
+ else if (!dev_priv->rps.is_bdw_sw_turbo
+ || atomic_read(&dev_priv->rps.sw_turbo.flip_received)){
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);
if (dev_priv->rps.enabled) {
if (IS_VALLEYVIEW(dev))
valleyview_set_rps(dev_priv->dev, dev_priv->rps.max_freq_softlimit);
- else
+ else if (!dev_priv->rps.is_bdw_sw_turbo
+ || atomic_read(&dev_priv->rps.sw_turbo.flip_received)){
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);
dev_priv->rps.cur_freq,
vlv_gpu_freq(dev_priv, val), val);
+ if (WARN_ONCE(IS_CHERRYVIEW(dev) && (val & 1),
+ "Odd GPU freq value\n"))
+ val &= ~1;
+
if (val != dev_priv->rps.cur_freq)
vlv_punit_write(dev_priv, PUNIT_REG_GPU_FREQ_REQ, val);
static void gen8_disable_rps_interrupts(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
+ if (IS_BROADWELL(dev) && dev_priv->rps.is_bdw_sw_turbo){
+ if (atomic_read(&dev_priv->rps.sw_turbo.flip_received))
+ del_timer(&dev_priv->rps.sw_turbo.flip_timer);
+ dev_priv-> rps.is_bdw_sw_turbo = false;
+ } else {
+ I915_WRITE(GEN6_PMINTRMSK, ~GEN8_PMINTR_REDIRECT_TO_NON_DISP);
+ I915_WRITE(GEN8_GT_IER(2), I915_READ(GEN8_GT_IER(2)) &
+ ~dev_priv->pm_rps_events);
+ /* Complete PM interrupt masking here doesn't race with the rps work
+ * item again unmasking PM interrupts because that is using a different
+ * register (GEN8_GT_IMR(2)) to mask PM interrupts. The only risk is in
+ * leaving stale bits in GEN8_GT_IIR(2) and GEN8_GT_IMR(2) which
+ * gen8_enable_rps will clean up. */
- I915_WRITE(GEN6_PMINTRMSK, ~GEN8_PMINTR_REDIRECT_TO_NON_DISP);
- I915_WRITE(GEN8_GT_IER(2), I915_READ(GEN8_GT_IER(2)) &
- ~dev_priv->pm_rps_events);
- /* Complete PM interrupt masking here doesn't race with the rps work
- * item again unmasking PM interrupts because that is using a different
- * register (GEN8_GT_IMR(2)) to mask PM interrupts. The only risk is in
- * leaving stale bits in GEN8_GT_IIR(2) and GEN8_GT_IMR(2) which
- * gen8_enable_rps will clean up. */
+ spin_lock_irq(&dev_priv->irq_lock);
+ dev_priv->rps.pm_iir = 0;
+ spin_unlock_irq(&dev_priv->irq_lock);
- spin_lock_irq(&dev_priv->irq_lock);
- dev_priv->rps.pm_iir = 0;
- spin_unlock_irq(&dev_priv->irq_lock);
-
- I915_WRITE(GEN8_GT_IIR(2), dev_priv->pm_rps_events);
+ I915_WRITE(GEN8_GT_IIR(2), dev_priv->pm_rps_events);
+ }
}
static void gen6_disable_rps_interrupts(struct drm_device *dev)
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;
+}
+
+static void gen8_set_frequency_RP0(struct work_struct *work)
+{
+ struct intel_rps_bdw_turbo *p_bdw_turbo =
+ container_of(work, struct intel_rps_bdw_turbo, work_max_freq);
+ struct intel_gen6_power_mgmt *p_power_mgmt =
+ container_of(p_bdw_turbo, struct intel_gen6_power_mgmt, sw_turbo);
+ struct drm_i915_private *dev_priv =
+ container_of(p_power_mgmt, struct drm_i915_private, rps);
+
+ mutex_lock(&dev_priv->rps.hw_lock);
+ gen6_set_rps(dev_priv->dev, dev_priv->rps.rp0_freq);
+ mutex_unlock(&dev_priv->rps.hw_lock);
+}
+
+static void flip_active_timeout_handler(unsigned long var)
+{
+ struct drm_i915_private *dev_priv = (struct drm_i915_private *) var;
+
+ del_timer(&dev_priv->rps.sw_turbo.flip_timer);
+ atomic_set(&dev_priv->rps.sw_turbo.flip_received, false);
+
+ queue_work(dev_priv->wq, &dev_priv->rps.sw_turbo.work_max_freq);
+}
+
+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_engine_cs *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);
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;
+
+ /* Start the timer to track if flip comes*/
+ dev_priv->rps.sw_turbo.timeout = 200*1000; /* in us */
+
+ init_timer(&dev_priv->rps.sw_turbo.flip_timer);
+ dev_priv->rps.sw_turbo.flip_timer.function = flip_active_timeout_handler;
+ dev_priv->rps.sw_turbo.flip_timer.data = (unsigned long) dev_priv;
+ dev_priv->rps.sw_turbo.flip_timer.expires =
+ usecs_to_jiffies(dev_priv->rps.sw_turbo.timeout) + jiffies;
+ add_timer(&dev_priv->rps.sw_turbo.flip_timer);
+ INIT_WORK(&dev_priv->rps.sw_turbo.work_max_freq, gen8_set_frequency_RP0);
+
+ atomic_set(&dev_priv->rps.sw_turbo.flip_received, true);
+ } 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);
-
- /* 6: Ring frequency + overclocking (our driver does this later */
-
+ 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);
-
- gen8_enable_rps_interrupts(dev);
+ if (!dev_priv->rps.is_bdw_sw_turbo)
+ gen8_enable_rps_interrupts(dev);
gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
}
static void valleyview_init_gt_powersave(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
+ u32 val;
valleyview_setup_pctx(dev);
mutex_lock(&dev_priv->rps.hw_lock);
+ val = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
+ switch ((val >> 6) & 3) {
+ case 0:
+ case 1:
+ dev_priv->mem_freq = 800;
+ break;
+ case 2:
+ dev_priv->mem_freq = 1066;
+ break;
+ case 3:
+ dev_priv->mem_freq = 1333;
+ break;
+ }
+ DRM_DEBUG_DRIVER("DDR speed: %d MHz", dev_priv->mem_freq);
+
dev_priv->rps.max_freq = valleyview_rps_max_freq(dev_priv);
dev_priv->rps.rp0_freq = dev_priv->rps.max_freq;
DRM_DEBUG_DRIVER("max GPU freq: %d MHz (%u)\n",
static void cherryview_init_gt_powersave(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
+ u32 val;
cherryview_setup_pctx(dev);
mutex_lock(&dev_priv->rps.hw_lock);
+ val = vlv_punit_read(dev_priv, CCK_FUSE_REG);
+ switch ((val >> 2) & 0x7) {
+ case 0:
+ case 1:
+ dev_priv->rps.cz_freq = 200;
+ dev_priv->mem_freq = 1600;
+ break;
+ case 2:
+ dev_priv->rps.cz_freq = 267;
+ dev_priv->mem_freq = 1600;
+ break;
+ case 3:
+ dev_priv->rps.cz_freq = 333;
+ dev_priv->mem_freq = 2000;
+ break;
+ case 4:
+ dev_priv->rps.cz_freq = 320;
+ dev_priv->mem_freq = 1600;
+ break;
+ case 5:
+ dev_priv->rps.cz_freq = 400;
+ dev_priv->mem_freq = 1600;
+ break;
+ }
+ DRM_DEBUG_DRIVER("DDR speed: %d MHz", dev_priv->mem_freq);
+
dev_priv->rps.max_freq = cherryview_rps_max_freq(dev_priv);
dev_priv->rps.rp0_freq = dev_priv->rps.max_freq;
DRM_DEBUG_DRIVER("max GPU freq: %d MHz (%u)\n",
vlv_gpu_freq(dev_priv, dev_priv->rps.min_freq),
dev_priv->rps.min_freq);
+ WARN_ONCE((dev_priv->rps.max_freq |
+ dev_priv->rps.efficient_freq |
+ dev_priv->rps.rp1_freq |
+ dev_priv->rps.min_freq) & 1,
+ "Odd GPU freq values\n");
+
/* Preserve min/max settings in case of re-init */
if (dev_priv->rps.max_freq_softlimit == 0)
dev_priv->rps.max_freq_softlimit = dev_priv->rps.max_freq;
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_CHERRYVIEW(dev)) {
/* FIXME(BDW): Check all the w/a, some might only apply to
* pre-production hw. */
- /* WaDisablePartialInstShootdown:bdw */
- I915_WRITE(GEN8_ROW_CHICKEN,
- _MASKED_BIT_ENABLE(PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE));
-
- /* WaDisableThreadStallDopClockGating:bdw */
- /* FIXME: Unclear whether we really need this on production bdw. */
- I915_WRITE(GEN8_ROW_CHICKEN,
- _MASKED_BIT_ENABLE(STALL_DOP_GATING_DISABLE));
- /*
- * This GEN8_CENTROID_PIXEL_OPT_DIS W/A is only needed for
- * pre-production hardware
- */
- I915_WRITE(HALF_SLICE_CHICKEN3,
- _MASKED_BIT_ENABLE(GEN8_CENTROID_PIXEL_OPT_DIS));
- I915_WRITE(HALF_SLICE_CHICKEN3,
- _MASKED_BIT_ENABLE(GEN8_SAMPLER_POWER_BYPASS_DIS));
I915_WRITE(GAMTARBMODE, _MASKED_BIT_ENABLE(ARB_MODE_BWGTLB_DISABLE));
I915_WRITE(_3D_CHICKEN3,
_MASKED_BIT_ENABLE(_3D_CHICKEN_SDE_LIMIT_FIFO_POLY_DEPTH(2)));
- I915_WRITE(COMMON_SLICE_CHICKEN2,
- _MASKED_BIT_ENABLE(GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE));
-
- I915_WRITE(GEN7_HALF_SLICE_CHICKEN1,
- _MASKED_BIT_ENABLE(GEN7_SINGLE_SUBSCAN_DISPATCH_ENABLE));
-
- /* WaDisableDopClockGating:bdw May not be needed for production */
- I915_WRITE(GEN7_ROW_CHICKEN2,
- _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
/* WaSwitchSolVfFArbitrationPriority:bdw */
I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL);
BDW_DPRS_MASK_VBLANK_SRD);
}
- /* Use Force Non-Coherent whenever executing a 3D context. This is a
- * workaround for for a possible hang in the unlikely event a TLB
- * invalidation occurs during a PSD flush.
- */
- I915_WRITE(HDC_CHICKEN0,
- I915_READ(HDC_CHICKEN0) |
- _MASKED_BIT_ENABLE(HDC_FORCE_NON_COHERENT));
-
/* WaVSRefCountFullforceMissDisable:bdw */
/* WaDSRefCountFullforceMissDisable:bdw */
I915_WRITE(GEN7_FF_THREAD_MODE,
I915_READ(GEN7_FF_THREAD_MODE) &
~(GEN8_FF_DS_REF_CNT_FFME | GEN7_FF_VS_REF_CNT_FFME));
- /*
- * BSpec recommends 8x4 when MSAA is used,
- * however in practice 16x4 seems fastest.
- *
- * Note that PS/WM thread counts depend on the WIZ hashing
- * disable bit, which we don't touch here, but it's good
- * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
- */
- I915_WRITE(GEN7_GT_MODE,
- GEN6_WIZ_HASHING_MASK | GEN6_WIZ_HASHING_16x4);
-
I915_WRITE(GEN6_RC_SLEEP_PSMI_CONTROL,
_MASKED_BIT_ENABLE(GEN8_RC_SEMA_IDLE_MSG_DISABLE));
I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
- /* Wa4x4STCOptimizationDisable:bdw */
- I915_WRITE(CACHE_MODE_1,
- _MASKED_BIT_ENABLE(GEN8_4x4_STC_OPTIMIZATION_DISABLE));
-
lpt_init_clock_gating(dev);
}
static void valleyview_init_clock_gating(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
- u32 val;
-
- mutex_lock(&dev_priv->rps.hw_lock);
- val = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
- mutex_unlock(&dev_priv->rps.hw_lock);
- switch ((val >> 6) & 3) {
- case 0:
- case 1:
- dev_priv->mem_freq = 800;
- break;
- case 2:
- dev_priv->mem_freq = 1066;
- break;
- case 3:
- dev_priv->mem_freq = 1333;
- break;
- }
- DRM_DEBUG_DRIVER("DDR speed: %d MHz", dev_priv->mem_freq);
I915_WRITE(DSPCLK_GATE_D, VRHUNIT_CLOCK_GATE_DISABLE);
static void cherryview_init_clock_gating(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
- u32 val;
-
- mutex_lock(&dev_priv->rps.hw_lock);
- val = vlv_punit_read(dev_priv, CCK_FUSE_REG);
- mutex_unlock(&dev_priv->rps.hw_lock);
- switch ((val >> 2) & 0x7) {
- case 0:
- case 1:
- dev_priv->rps.cz_freq = CHV_CZ_CLOCK_FREQ_MODE_200;
- dev_priv->mem_freq = 1600;
- break;
- case 2:
- dev_priv->rps.cz_freq = CHV_CZ_CLOCK_FREQ_MODE_267;
- dev_priv->mem_freq = 1600;
- break;
- case 3:
- dev_priv->rps.cz_freq = CHV_CZ_CLOCK_FREQ_MODE_333;
- dev_priv->mem_freq = 2000;
- break;
- case 4:
- dev_priv->rps.cz_freq = CHV_CZ_CLOCK_FREQ_MODE_320;
- dev_priv->mem_freq = 1600;
- break;
- case 5:
- dev_priv->rps.cz_freq = CHV_CZ_CLOCK_FREQ_MODE_400;
- dev_priv->mem_freq = 1600;
- break;
- }
- DRM_DEBUG_DRIVER("DDR speed: %d MHz", dev_priv->mem_freq);
I915_WRITE(DSPCLK_GATE_D, VRHUNIT_CLOCK_GATE_DISABLE);
I915_WRITE(MI_ARB_VLV, MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE);
- /* WaDisablePartialInstShootdown:chv */
- I915_WRITE(GEN8_ROW_CHICKEN,
- _MASKED_BIT_ENABLE(PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE));
-
- /* WaDisableThreadStallDopClockGating:chv */
- I915_WRITE(GEN8_ROW_CHICKEN,
- _MASKED_BIT_ENABLE(STALL_DOP_GATING_DISABLE));
-
/* WaVSRefCountFullforceMissDisable:chv */
/* WaDSRefCountFullforceMissDisable:chv */
I915_WRITE(GEN7_FF_THREAD_MODE,
I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
- /* WaDisableSamplerPowerBypass:chv (pre-production hw) */
- I915_WRITE(HALF_SLICE_CHICKEN3,
- _MASKED_BIT_ENABLE(GEN8_SAMPLER_POWER_BYPASS_DIS));
-
/* WaDisableGunitClockGating:chv (pre-production hw) */
I915_WRITE(VLV_GUNIT_CLOCK_GATE, I915_READ(VLV_GUNIT_CLOCK_GATE) |
GINT_DIS);
_MASKED_BIT_ENABLE(GEN8_FF_DOP_CLOCK_GATE_DISABLE));
/* WaDisableDopClockGating:chv (pre-production hw) */
- I915_WRITE(GEN7_ROW_CHICKEN2,
- _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
I915_WRITE(GEN6_UCGCTL1, I915_READ(GEN6_UCGCTL1) |
GEN6_EU_TCUNIT_CLOCK_GATE_DISABLE);
}
/* On GEN3 we really need to make sure the ARB C3 LP bit is set */
I915_WRITE(MI_ARB_STATE, _MASKED_BIT_ENABLE(MI_ARB_C3_LP_WRITE_ENABLE));
+
+ I915_WRITE(MI_ARB_STATE,
+ _MASKED_BIT_ENABLE(MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE));
}
static void i85x_init_clock_gating(struct drm_device *dev)
/* interrupts should cause a wake up from C3 */
I915_WRITE(MI_STATE, _MASKED_BIT_ENABLE(MI_AGPBUSY_INT_EN) |
_MASKED_BIT_DISABLE(MI_AGPBUSY_830_MODE));
+
+ I915_WRITE(MEM_MODE,
+ _MASKED_BIT_ENABLE(MEM_DISPLAY_TRICKLE_FEED_DISABLE));
}
static void i830_init_clock_gating(struct drm_device *dev)
struct drm_i915_private *dev_priv = dev->dev_private;
I915_WRITE(DSPCLK_GATE_D, OVRUNIT_CLOCK_GATE_DISABLE);
+
+ I915_WRITE(MEM_MODE,
+ _MASKED_BIT_ENABLE(MEM_DISPLAY_A_TRICKLE_FEED_DISABLE) |
+ _MASKED_BIT_ENABLE(MEM_DISPLAY_B_TRICKLE_FEED_DISABLE));
}
void intel_init_clock_gating(struct drm_device *dev)
outb(inb(VGA_MSR_READ), VGA_MSR_WRITE);
vga_put(dev->pdev, VGA_RSRC_LEGACY_IO);
- if (IS_BROADWELL(dev))
+ if (IS_BROADWELL(dev) || (INTEL_INFO(dev)->gen >= 9))
gen8_irq_power_well_post_enable(dev_priv);
}
spin_unlock_irq(&dev_priv->irq_lock);
vlv_set_power_well(dev_priv, power_well, false);
+
+ vlv_power_sequencer_reset(dev_priv);
}
static void vlv_dpio_cmn_power_well_enable(struct drm_i915_private *dev_priv,
dev_priv->display.init_clock_gating = haswell_init_clock_gating;
else if (INTEL_INFO(dev)->gen == 8)
dev_priv->display.init_clock_gating = broadwell_init_clock_gating;
+ else if (INTEL_INFO(dev)->gen == 9)
+ dev_priv->display.init_clock_gating = gen9_init_clock_gating;
} else if (IS_CHERRYVIEW(dev)) {
dev_priv->display.update_wm = cherryview_update_wm;
dev_priv->display.update_sprite_wm = valleyview_update_sprite_wm;
return -1;
}
+ /* CHV needs even values */
opcode = (DIV_ROUND_CLOSEST((val * 2 * mul), dev_priv->rps.cz_freq) * 2);
return opcode;
projects / firefly-linux-kernel-4.4.55.git / blobdiff