diff options
Diffstat (limited to 'drivers/gpu/drm/i915/intel_pm.c')
| -rw-r--r-- | drivers/gpu/drm/i915/intel_pm.c | 770 |
1 files changed, 560 insertions, 210 deletions
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index d93dcf683e8c..d1e53abec1b5 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -487,7 +487,7 @@ void intel_update_fbc(struct drm_device *dev) * - new fb is too large to fit in compressed buffer * - going to an unsupported config (interlace, pixel multiply, etc.) */ - list_for_each_entry(tmp_crtc, &dev->mode_config.crtc_list, head) { + for_each_crtc(dev, tmp_crtc) { if (intel_crtc_active(tmp_crtc) && to_intel_crtc(tmp_crtc)->primary_enabled) { if (crtc) { @@ -1010,7 +1010,7 @@ static struct drm_crtc *single_enabled_crtc(struct drm_device *dev) { struct drm_crtc *crtc, *enabled = NULL; - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + for_each_crtc(dev, crtc) { if (intel_crtc_active(crtc)) { if (enabled) return NULL; @@ -1831,6 +1831,40 @@ static unsigned int ilk_display_fifo_size(const struct drm_device *dev) return 512; } +static unsigned int ilk_plane_wm_reg_max(const struct drm_device *dev, + int level, bool is_sprite) +{ + if (INTEL_INFO(dev)->gen >= 8) + /* BDW primary/sprite plane watermarks */ + return level == 0 ? 255 : 2047; + else if (INTEL_INFO(dev)->gen >= 7) + /* IVB/HSW primary/sprite plane watermarks */ + return level == 0 ? 127 : 1023; + else if (!is_sprite) + /* ILK/SNB primary plane watermarks */ + return level == 0 ? 127 : 511; + else + /* ILK/SNB sprite plane watermarks */ + return level == 0 ? 63 : 255; +} + +static unsigned int ilk_cursor_wm_reg_max(const struct drm_device *dev, + int level) +{ + if (INTEL_INFO(dev)->gen >= 7) + return level == 0 ? 63 : 255; + else + return level == 0 ? 31 : 63; +} + +static unsigned int ilk_fbc_wm_reg_max(const struct drm_device *dev) +{ + if (INTEL_INFO(dev)->gen >= 8) + return 31; + else + return 15; +} + /* Calculate the maximum primary/sprite plane watermark */ static unsigned int ilk_plane_wm_max(const struct drm_device *dev, int level, @@ -1839,7 +1873,6 @@ static unsigned int ilk_plane_wm_max(const struct drm_device *dev, bool is_sprite) { unsigned int fifo_size = ilk_display_fifo_size(dev); - unsigned int max; /* if sprites aren't enabled, sprites get nothing */ if (is_sprite && !config->sprites_enabled) @@ -1870,19 +1903,7 @@ static unsigned int ilk_plane_wm_max(const struct drm_device *dev, } /* clamp to max that the registers can hold */ - if (INTEL_INFO(dev)->gen >= 8) - max = level == 0 ? 255 : 2047; - else if (INTEL_INFO(dev)->gen >= 7) - /* IVB/HSW primary/sprite plane watermarks */ - max = level == 0 ? 127 : 1023; - else if (!is_sprite) - /* ILK/SNB primary plane watermarks */ - max = level == 0 ? 127 : 511; - else - /* ILK/SNB sprite plane watermarks */ - max = level == 0 ? 63 : 255; - - return min(fifo_size, max); + return min(fifo_size, ilk_plane_wm_reg_max(dev, level, is_sprite)); } /* Calculate the maximum cursor plane watermark */ @@ -1895,20 +1916,7 @@ static unsigned int ilk_cursor_wm_max(const struct drm_device *dev, return 64; /* otherwise just report max that registers can hold */ - if (INTEL_INFO(dev)->gen >= 7) - return level == 0 ? 63 : 255; - else - return level == 0 ? 31 : 63; -} - -/* Calculate the maximum FBC watermark */ -static unsigned int ilk_fbc_wm_max(const struct drm_device *dev) -{ - /* max that registers can hold */ - if (INTEL_INFO(dev)->gen >= 8) - return 31; - else - return 15; + return ilk_cursor_wm_reg_max(dev, level); } static void ilk_compute_wm_maximums(const struct drm_device *dev, @@ -1920,7 +1928,17 @@ static void ilk_compute_wm_maximums(const struct drm_device *dev, max->pri = ilk_plane_wm_max(dev, level, config, ddb_partitioning, false); max->spr = ilk_plane_wm_max(dev, level, config, ddb_partitioning, true); max->cur = ilk_cursor_wm_max(dev, level, config); - max->fbc = ilk_fbc_wm_max(dev); + max->fbc = ilk_fbc_wm_reg_max(dev); +} + +static void ilk_compute_wm_reg_maximums(struct drm_device *dev, + int level, + struct ilk_wm_maximums *max) +{ + max->pri = ilk_plane_wm_reg_max(dev, level, false); + max->spr = ilk_plane_wm_reg_max(dev, level, true); + max->cur = ilk_cursor_wm_reg_max(dev, level); + max->fbc = ilk_fbc_wm_reg_max(dev); } static bool ilk_validate_wm_level(int level, @@ -2059,7 +2077,7 @@ static void intel_fixup_cur_wm_latency(struct drm_device *dev, uint16_t wm[5]) wm[3] *= 2; } -static int ilk_wm_max_level(const struct drm_device *dev) +int ilk_wm_max_level(const struct drm_device *dev) { /* how many WM levels are we expecting */ if (IS_HASWELL(dev) || IS_BROADWELL(dev)) @@ -2155,38 +2173,52 @@ static void ilk_setup_wm_latency(struct drm_device *dev) } static void ilk_compute_wm_parameters(struct drm_crtc *crtc, - struct ilk_pipe_wm_parameters *p, - struct intel_wm_config *config) + struct ilk_pipe_wm_parameters *p) { struct drm_device *dev = crtc->dev; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); enum pipe pipe = intel_crtc->pipe; struct drm_plane *plane; - p->active = intel_crtc_active(crtc); - if (p->active) { - p->pipe_htotal = intel_crtc->config.adjusted_mode.crtc_htotal; - p->pixel_rate = ilk_pipe_pixel_rate(dev, crtc); - p->pri.bytes_per_pixel = crtc->primary->fb->bits_per_pixel / 8; - p->cur.bytes_per_pixel = 4; - p->pri.horiz_pixels = intel_crtc->config.pipe_src_w; - p->cur.horiz_pixels = intel_crtc->cursor_width; - /* TODO: for now, assume primary and cursor planes are always enabled. */ - p->pri.enabled = true; - p->cur.enabled = true; - } + if (!intel_crtc_active(crtc)) + return; - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) - config->num_pipes_active += intel_crtc_active(crtc); + p->active = true; + p->pipe_htotal = intel_crtc->config.adjusted_mode.crtc_htotal; + p->pixel_rate = ilk_pipe_pixel_rate(dev, crtc); + p->pri.bytes_per_pixel = crtc->primary->fb->bits_per_pixel / 8; + p->cur.bytes_per_pixel = 4; + p->pri.horiz_pixels = intel_crtc->config.pipe_src_w; + p->cur.horiz_pixels = intel_crtc->cursor_width; + /* TODO: for now, assume primary and cursor planes are always enabled. */ + p->pri.enabled = true; + p->cur.enabled = true; drm_for_each_legacy_plane(plane, &dev->mode_config.plane_list) { struct intel_plane *intel_plane = to_intel_plane(plane); - if (intel_plane->pipe == pipe) + if (intel_plane->pipe == pipe) { p->spr = intel_plane->wm; + break; + } + } +} + +static void ilk_compute_wm_config(struct drm_device *dev, + struct intel_wm_config *config) +{ + struct intel_crtc *intel_crtc; - config->sprites_enabled |= intel_plane->wm.enabled; - config->sprites_scaled |= intel_plane->wm.scaled; + /* Compute the currently _active_ config */ + for_each_intel_crtc(dev, intel_crtc) { + const struct intel_pipe_wm *wm = &intel_crtc->wm.active; + + if (!wm->pipe_enabled) + continue; + + config->sprites_enabled |= wm->sprites_enabled; + config->sprites_scaled |= wm->sprites_scaled; + config->num_pipes_active++; } } @@ -2206,8 +2238,9 @@ static bool intel_compute_pipe_wm(struct drm_crtc *crtc, }; struct ilk_wm_maximums max; - /* LP0 watermarks always use 1/2 DDB partitioning */ - ilk_compute_wm_maximums(dev, 0, &config, INTEL_DDB_PART_1_2, &max); + pipe_wm->pipe_enabled = params->active; + pipe_wm->sprites_enabled = params->spr.enabled; + pipe_wm->sprites_scaled = params->spr.scaled; /* ILK/SNB: LP2+ watermarks only w/o sprites */ if (INTEL_INFO(dev)->gen <= 6 && params->spr.enabled) @@ -2217,15 +2250,37 @@ static bool intel_compute_pipe_wm(struct drm_crtc *crtc, if (params->spr.scaled) max_level = 0; - for (level = 0; level <= max_level; level++) - ilk_compute_wm_level(dev_priv, level, params, - &pipe_wm->wm[level]); + ilk_compute_wm_level(dev_priv, 0, params, &pipe_wm->wm[0]); if (IS_HASWELL(dev) || IS_BROADWELL(dev)) pipe_wm->linetime = hsw_compute_linetime_wm(dev, crtc); + /* LP0 watermarks always use 1/2 DDB partitioning */ + ilk_compute_wm_maximums(dev, 0, &config, INTEL_DDB_PART_1_2, &max); + /* At least LP0 must be valid */ - return ilk_validate_wm_level(0, &max, &pipe_wm->wm[0]); + if (!ilk_validate_wm_level(0, &max, &pipe_wm->wm[0])) + return false; + + ilk_compute_wm_reg_maximums(dev, 1, &max); + + for (level = 1; level <= max_level; level++) { + struct intel_wm_level wm = {}; + + ilk_compute_wm_level(dev_priv, level, params, &wm); + + /* + * Disable any watermark level that exceeds the + * register maximums since such watermarks are + * always invalid. + */ + if (!ilk_validate_wm_level(level, &max, &wm)) + break; + + pipe_wm->wm[level] = wm; + } + + return true; } /* @@ -2237,20 +2292,28 @@ static void ilk_merge_wm_level(struct drm_device *dev, { const struct intel_crtc *intel_crtc; - list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list, base.head) { - const struct intel_wm_level *wm = - &intel_crtc->wm.active.wm[level]; + ret_wm->enable = true; + + for_each_intel_crtc(dev, intel_crtc) { + const struct intel_pipe_wm *active = &intel_crtc->wm.active; + const struct intel_wm_level *wm = &active->wm[level]; + + if (!active->pipe_enabled) + continue; + /* + * The watermark values may have been used in the past, + * so we must maintain them in the registers for some + * time even if the level is now disabled. + */ if (!wm->enable) - return; + ret_wm->enable = false; ret_wm->pri_val = max(ret_wm->pri_val, wm->pri_val); ret_wm->spr_val = max(ret_wm->spr_val, wm->spr_val); ret_wm->cur_val = max(ret_wm->cur_val, wm->cur_val); ret_wm->fbc_val = max(ret_wm->fbc_val, wm->fbc_val); } - - ret_wm->enable = true; } /* @@ -2262,6 +2325,7 @@ static void ilk_wm_merge(struct drm_device *dev, struct intel_pipe_wm *merged) { int level, max_level = ilk_wm_max_level(dev); + int last_enabled_level = max_level; /* ILK/SNB/IVB: LP1+ watermarks only w/ single pipe */ if ((INTEL_INFO(dev)->gen <= 6 || IS_IVYBRIDGE(dev)) && @@ -2277,15 +2341,19 @@ static void ilk_wm_merge(struct drm_device *dev, ilk_merge_wm_level(dev, level, wm); - if (!ilk_validate_wm_level(level, max, wm)) - break; + if (level > last_enabled_level) + wm->enable = false; + else if (!ilk_validate_wm_level(level, max, wm)) + /* make sure all following levels get disabled */ + last_enabled_level = level - 1; /* * The spec says it is preferred to disable * FBC WMs instead of disabling a WM level. */ if (wm->fbc_val > max->fbc) { - merged->fbc_wm_enabled = false; + if (wm->enable) + merged->fbc_wm_enabled = false; wm->fbc_val = 0; } } @@ -2340,14 +2408,19 @@ static void ilk_compute_wm_results(struct drm_device *dev, level = ilk_wm_lp_to_level(wm_lp, merged); r = &merged->wm[level]; - if (!r->enable) - break; - results->wm_lp[wm_lp - 1] = WM3_LP_EN | + /* + * Maintain the watermark values even if the level is + * disabled. Doing otherwise could cause underruns. + */ + results->wm_lp[wm_lp - 1] = (ilk_wm_lp_latency(dev, level) << WM1_LP_LATENCY_SHIFT) | (r->pri_val << WM1_LP_SR_SHIFT) | r->cur_val; + if (r->enable) + results->wm_lp[wm_lp - 1] |= WM1_LP_SR_EN; + if (INTEL_INFO(dev)->gen >= 8) results->wm_lp[wm_lp - 1] |= r->fbc_val << WM1_LP_FBC_SHIFT_BDW; @@ -2355,6 +2428,10 @@ static void ilk_compute_wm_results(struct drm_device *dev, results->wm_lp[wm_lp - 1] |= r->fbc_val << WM1_LP_FBC_SHIFT; + /* + * Always set WM1S_LP_EN when spr_val != 0, even if the + * level is disabled. Doing otherwise could cause underruns. + */ if (INTEL_INFO(dev)->gen <= 6 && r->spr_val) { WARN_ON(wm_lp != 1); results->wm_lp_spr[wm_lp - 1] = WM1S_LP_EN | r->spr_val; @@ -2363,7 +2440,7 @@ static void ilk_compute_wm_results(struct drm_device *dev, } /* LP0 register values */ - list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list, base.head) { + for_each_intel_crtc(dev, intel_crtc) { enum pipe pipe = intel_crtc->pipe; const struct intel_wm_level *r = &intel_crtc->wm.active.wm[0]; @@ -2598,7 +2675,7 @@ static void ilk_update_wm(struct drm_crtc *crtc) struct intel_pipe_wm lp_wm_1_2 = {}, lp_wm_5_6 = {}, *best_lp_wm; struct intel_wm_config config = {}; - ilk_compute_wm_parameters(crtc, ¶ms, &config); + ilk_compute_wm_parameters(crtc, ¶ms); intel_compute_pipe_wm(crtc, ¶ms, &pipe_wm); @@ -2607,6 +2684,8 @@ static void ilk_update_wm(struct drm_crtc *crtc) intel_crtc->wm.active = pipe_wm; + ilk_compute_wm_config(dev, &config); + ilk_compute_wm_maximums(dev, 1, &config, INTEL_DDB_PART_1_2, &max); ilk_wm_merge(dev, &config, &max, &lp_wm_1_2); @@ -2673,7 +2752,9 @@ static void ilk_pipe_wm_get_hw_state(struct drm_crtc *crtc) if (IS_HASWELL(dev) || IS_BROADWELL(dev)) hw->wm_linetime[pipe] = I915_READ(PIPE_WM_LINETIME(pipe)); - if (intel_crtc_active(crtc)) { + active->pipe_enabled = intel_crtc_active(crtc); + + if (active->pipe_enabled) { u32 tmp = hw->wm_pipe[pipe]; /* @@ -2706,7 +2787,7 @@ void ilk_wm_get_hw_state(struct drm_device *dev) struct ilk_wm_values *hw = &dev_priv->wm.hw; struct drm_crtc *crtc; - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) + for_each_crtc(dev, crtc) ilk_pipe_wm_get_hw_state(crtc); hw->wm_lp[0] = I915_READ(WM1_LP_ILK); @@ -2714,8 +2795,10 @@ void ilk_wm_get_hw_state(struct drm_device *dev) hw->wm_lp[2] = I915_READ(WM3_LP_ILK); hw->wm_lp_spr[0] = I915_READ(WM1S_LP_ILK); - hw->wm_lp_spr[1] = I915_READ(WM2S_LP_IVB); - hw->wm_lp_spr[2] = I915_READ(WM3S_LP_IVB); + if (INTEL_INFO(dev)->gen >= 7) { + hw->wm_lp_spr[1] = I915_READ(WM2S_LP_IVB); + hw->wm_lp_spr[2] = I915_READ(WM3S_LP_IVB); + } if (IS_HASWELL(dev) || IS_BROADWELL(dev)) hw->partitioning = (I915_READ(WM_MISC) & WM_MISC_DATA_PARTITION_5_6) ? @@ -3071,6 +3154,9 @@ static u32 gen6_rps_pm_mask(struct drm_i915_private *dev_priv, u8 val) if (INTEL_INFO(dev_priv->dev)->gen <= 7 && !IS_HASWELL(dev_priv->dev)) mask |= GEN6_PM_RP_UP_EI_EXPIRED; + if (IS_GEN8(dev_priv->dev)) + mask |= GEN8_PMINTR_REDIRECT_TO_NON_DISP; + return ~mask; } @@ -3091,7 +3177,7 @@ void gen6_set_rps(struct drm_device *dev, u8 val) if (val != dev_priv->rps.cur_freq) { gen6_set_rps_thresholds(dev_priv, val); - if (IS_HASWELL(dev)) + if (IS_HASWELL(dev) || IS_BROADWELL(dev)) I915_WRITE(GEN6_RPNSWREQ, HSW_FREQUENCY(val)); else @@ -3134,16 +3220,7 @@ static void vlv_set_rps_idle(struct drm_i915_private *dev_priv) /* Mask turbo interrupt so that they will not come in between */ I915_WRITE(GEN6_PMINTRMSK, 0xffffffff); - /* Bring up the Gfx clock */ - I915_WRITE(VLV_GTLC_SURVIVABILITY_REG, - I915_READ(VLV_GTLC_SURVIVABILITY_REG) | - VLV_GFX_CLK_FORCE_ON_BIT); - - if (wait_for(((VLV_GFX_CLK_STATUS_BIT & - I915_READ(VLV_GTLC_SURVIVABILITY_REG)) != 0), 5)) { - DRM_ERROR("GFX_CLK_ON request timed out\n"); - return; - } + vlv_force_gfx_clock(dev_priv, true); dev_priv->rps.cur_freq = dev_priv->rps.min_freq_softlimit; @@ -3154,10 +3231,7 @@ static void vlv_set_rps_idle(struct drm_i915_private *dev_priv) & GENFREQSTATUS) == 0, 5)) DRM_ERROR("timed out waiting for Punit\n"); - /* Release the Gfx clock */ - I915_WRITE(VLV_GTLC_SURVIVABILITY_REG, - I915_READ(VLV_GTLC_SURVIVABILITY_REG) & - ~VLV_GFX_CLK_FORCE_ON_BIT); + vlv_force_gfx_clock(dev_priv, false); I915_WRITE(GEN6_PMINTRMSK, gen6_rps_pm_mask(dev_priv, dev_priv->rps.cur_freq)); @@ -3215,6 +3289,26 @@ void valleyview_set_rps(struct drm_device *dev, u8 val) trace_intel_gpu_freq_change(vlv_gpu_freq(dev_priv, val)); } +static void gen8_disable_rps_interrupts(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + 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); + + I915_WRITE(GEN8_GT_IIR(2), dev_priv->pm_rps_events); +} + static void gen6_disable_rps_interrupts(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -3241,7 +3335,10 @@ static void gen6_disable_rps(struct drm_device *dev) I915_WRITE(GEN6_RC_CONTROL, 0); I915_WRITE(GEN6_RPNSWREQ, 1 << 31); - gen6_disable_rps_interrupts(dev); + if (IS_BROADWELL(dev)) + gen8_disable_rps_interrupts(dev); + else + gen6_disable_rps_interrupts(dev); } static void valleyview_disable_rps(struct drm_device *dev) @@ -3255,21 +3352,44 @@ static void valleyview_disable_rps(struct drm_device *dev) static void intel_print_rc6_info(struct drm_device *dev, u32 mode) { + if (IS_VALLEYVIEW(dev)) { + if (mode & (GEN7_RC_CTL_TO_MODE | GEN6_RC_CTL_EI_MODE(1))) + mode = GEN6_RC_CTL_RC6_ENABLE; + else + mode = 0; + } DRM_INFO("Enabling RC6 states: RC6 %s, RC6p %s, RC6pp %s\n", (mode & GEN6_RC_CTL_RC6_ENABLE) ? "on" : "off", (mode & GEN6_RC_CTL_RC6p_ENABLE) ? "on" : "off", (mode & GEN6_RC_CTL_RC6pp_ENABLE) ? "on" : "off"); } -int intel_enable_rc6(const struct drm_device *dev) +static int sanitize_rc6_option(const struct drm_device *dev, int enable_rc6) { /* No RC6 before Ironlake */ if (INTEL_INFO(dev)->gen < 5) return 0; + /* RC6 is only on Ironlake mobile not on desktop */ + if (INTEL_INFO(dev)->gen == 5 && !IS_IRONLAKE_M(dev)) + return 0; + /* Respect the kernel parameter if it is set */ - if (i915.enable_rc6 >= 0) - return i915.enable_rc6; + if (enable_rc6 >= 0) { + int mask; + + if (INTEL_INFO(dev)->gen == 6 || IS_IVYBRIDGE(dev)) + mask = INTEL_RC6_ENABLE | INTEL_RC6p_ENABLE | + INTEL_RC6pp_ENABLE; + else + mask = INTEL_RC6_ENABLE; + + if ((enable_rc6 & mask) != enable_rc6) + DRM_INFO("Adjusting RC6 mask to %d (requested %d, valid %d)\n", + enable_rc6 & mask, enable_rc6, mask); + + return enable_rc6 & mask; + } /* Disable RC6 on Ironlake */ if (INTEL_INFO(dev)->gen == 5) @@ -3281,6 +3401,22 @@ int intel_enable_rc6(const struct drm_device *dev) return INTEL_RC6_ENABLE; } +int intel_enable_rc6(const struct drm_device *dev) +{ + return i915.enable_rc6; +} + +static void gen8_enable_rps_interrupts(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + spin_lock_irq(&dev_priv->irq_lock); + WARN_ON(dev_priv->rps.pm_iir); + bdw_enable_pm_irq(dev_priv, dev_priv->pm_rps_events); + I915_WRITE(GEN8_GT_IIR(2), dev_priv->pm_rps_events); + spin_unlock_irq(&dev_priv->irq_lock); +} + static void gen6_enable_rps_interrupts(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -3292,10 +3428,31 @@ static void gen6_enable_rps_interrupts(struct drm_device *dev) spin_unlock_irq(&dev_priv->irq_lock); } +static void parse_rp_state_cap(struct drm_i915_private *dev_priv, u32 rp_state_cap) +{ + /* All of these values are in units of 50MHz */ + dev_priv->rps.cur_freq = 0; + /* 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.min_freq = (rp_state_cap >> 16) & 0xff; + /* XXX: only BYT has a special efficient freq */ + dev_priv->rps.efficient_freq = dev_priv->rps.rp1_freq; + /* hw_max = RP0 until we check for overclocking */ + dev_priv->rps.max_freq = dev_priv->rps.rp0_freq; + + /* 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; + + if (dev_priv->rps.min_freq_softlimit == 0) + dev_priv->rps.min_freq_softlimit = dev_priv->rps.min_freq; +} + static void gen8_enable_rps(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; uint32_t rc6_mask = 0, rp_state_cap; int unused; @@ -3310,6 +3467,7 @@ static void gen8_enable_rps(struct drm_device *dev) I915_WRITE(GEN6_RC_CONTROL, 0); rp_state_cap = I915_READ(GEN6_RP_STATE_CAP); + parse_rp_state_cap(dev_priv, rp_state_cap); /* 2b: Program RC6 thresholds.*/ I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16); @@ -3329,8 +3487,10 @@ static void gen8_enable_rps(struct drm_device *dev) rc6_mask); /* 4 Program defaults and thresholds for RPS*/ - I915_WRITE(GEN6_RPNSWREQ, HSW_FREQUENCY(10)); /* Request 500 MHz */ - I915_WRITE(GEN6_RC_VIDEO_FREQ, HSW_FREQUENCY(12)); /* Request 600 MHz */ + I915_WRITE(GEN6_RPNSWREQ, + 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 */ @@ -3346,11 +3506,15 @@ static void gen8_enable_rps(struct drm_device *dev) I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10); + /* WaDisablePwrmtrEvent:chv (pre-production hw) */ + I915_WRITE(0xA80C, I915_READ(0xA80C) & 0x00ffffff); + I915_WRITE(0xA810, I915_READ(0xA810) & 0xffffff00); + /* 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_MEDIA_IS_GFX | /* WaSetMaskForGfxBusyness:chv (pre-production hw ?) */ GEN6_RP_ENABLE | GEN6_RP_UP_BUSY_AVG | GEN6_RP_DOWN_IDLE_AVG); @@ -3359,7 +3523,7 @@ static void gen8_enable_rps(struct drm_device *dev) gen6_set_rps(dev, (I915_READ(GEN6_GT_PERF_STATUS) & 0xff00) >> 8); - gen6_enable_rps_interrupts(dev); + gen8_enable_rps_interrupts(dev); gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL); } @@ -3367,7 +3531,7 @@ static void gen8_enable_rps(struct drm_device *dev) static void gen6_enable_rps(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; u32 rp_state_cap; u32 gt_perf_status; u32 rc6vids, pcu_mbox = 0, rc6_mask = 0; @@ -3396,23 +3560,7 @@ 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); - /* All of these values are in units of 50MHz */ - dev_priv->rps.cur_freq = 0; - /* 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.min_freq = (rp_state_cap >> 16) & 0xff; - /* XXX: only BYT has a special efficient freq */ - dev_priv->rps.efficient_freq = dev_priv->rps.rp1_freq; - /* hw_max = RP0 until we check for overclocking */ - dev_priv->rps.max_freq = dev_priv->rps.rp0_freq; - - /* 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; - - if (dev_priv->rps.min_freq_softlimit == 0) - dev_priv->rps.min_freq_softlimit = dev_priv->rps.min_freq; + parse_rp_state_cap(dev_priv, rp_state_cap); /* disable the counters and set deterministic thresholds */ I915_WRITE(GEN6_RC_CONTROL, 0); @@ -3494,7 +3642,7 @@ static void gen6_enable_rps(struct drm_device *dev) gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL); } -void gen6_update_ring_freq(struct drm_device *dev) +static void __gen6_update_ring_freq(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; int min_freq = 15; @@ -3564,6 +3712,18 @@ void gen6_update_ring_freq(struct drm_device *dev) } } +void gen6_update_ring_freq(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + if (INTEL_INFO(dev)->gen < 6 || IS_VALLEYVIEW(dev)) + return; + + mutex_lock(&dev_priv->rps.hw_lock); + __gen6_update_ring_freq(dev); + mutex_unlock(&dev_priv->rps.hw_lock); +} + int valleyview_rps_max_freq(struct drm_i915_private *dev_priv) { u32 val, rp0; @@ -3658,10 +3818,49 @@ static void valleyview_cleanup_pctx(struct drm_device *dev) dev_priv->vlv_pctx = NULL; } +static void valleyview_init_gt_powersave(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + valleyview_setup_pctx(dev); + + mutex_lock(&dev_priv->rps.hw_lock); + + 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", + vlv_gpu_freq(dev_priv, dev_priv->rps.max_freq), + dev_priv->rps.max_freq); + + 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.efficient_freq), + dev_priv->rps.efficient_freq); + + dev_priv->rps.min_freq = valleyview_rps_min_freq(dev_priv); + DRM_DEBUG_DRIVER("min GPU freq: %d MHz (%u)\n", + vlv_gpu_freq(dev_priv, dev_priv->rps.min_freq), + dev_priv->rps.min_freq); + + /* 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; + + if (dev_priv->rps.min_freq_softlimit == 0) + dev_priv->rps.min_freq_softlimit = dev_priv->rps.min_freq; + + mutex_unlock(&dev_priv->rps.hw_lock); +} + +static void valleyview_cleanup_gt_powersave(struct drm_device *dev) +{ + valleyview_cleanup_pctx(dev); +} + static void valleyview_enable_rps(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; u32 gtfifodbg, val, rc6_mode = 0; int i; @@ -3724,29 +3923,6 @@ static void valleyview_enable_rps(struct drm_device *dev) vlv_gpu_freq(dev_priv, dev_priv->rps.cur_freq), dev_priv->rps.cur_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", - vlv_gpu_freq(dev_priv, dev_priv->rps.max_freq), - dev_priv->rps.max_freq); - - 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.efficient_freq), - dev_priv->rps.efficient_freq); - - dev_priv->rps.min_freq = valleyview_rps_min_freq(dev_priv); - DRM_DEBUG_DRIVER("min GPU freq: %d MHz (%u)\n", - vlv_gpu_freq(dev_priv, dev_priv->rps.min_freq), - dev_priv->rps.min_freq); - - /* 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; - - if (dev_priv->rps.min_freq_softlimit == 0) - dev_priv->rps.min_freq_softlimit = dev_priv->rps.min_freq; - DRM_DEBUG_DRIVER("setting GPU freq to %d MHz (%u)\n", vlv_gpu_freq(dev_priv, dev_priv->rps.efficient_freq), dev_priv->rps.efficient_freq); @@ -3815,7 +3991,7 @@ static int ironlake_setup_rc6(struct drm_device *dev) static void ironlake_enable_rc6(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = &dev_priv->ring[RCS]; + struct intel_engine_cs *ring = &dev_priv->ring[RCS]; bool was_interruptible; int ret; @@ -3873,7 +4049,7 @@ static void ironlake_enable_rc6(struct drm_device *dev) I915_WRITE(PWRCTXA, i915_gem_obj_ggtt_offset(dev_priv->ips.pwrctx) | PWRCTX_EN); I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) & ~RCX_SW_EXIT); - intel_print_rc6_info(dev, INTEL_RC6_ENABLE); + intel_print_rc6_info(dev, GEN6_RC_CTL_RC6_ENABLE); } static unsigned long intel_pxfreq(u32 vidfreq) @@ -4327,7 +4503,7 @@ EXPORT_SYMBOL_GPL(i915_gpu_lower); bool i915_gpu_busy(void) { struct drm_i915_private *dev_priv; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; bool ret = false; int i; @@ -4487,14 +4663,16 @@ static void intel_init_emon(struct drm_device *dev) void intel_init_gt_powersave(struct drm_device *dev) { + i915.enable_rc6 = sanitize_rc6_option(dev, i915.enable_rc6); + if (IS_VALLEYVIEW(dev)) - valleyview_setup_pctx(dev); + valleyview_init_gt_powersave(dev); } void intel_cleanup_gt_powersave(struct drm_device *dev) { if (IS_VALLEYVIEW(dev)) - valleyview_cleanup_pctx(dev); + valleyview_cleanup_gt_powersave(dev); } void intel_disable_gt_powersave(struct drm_device *dev) @@ -4507,8 +4685,10 @@ void intel_disable_gt_powersave(struct drm_device *dev) if (IS_IRONLAKE_M(dev)) { ironlake_disable_drps(dev); ironlake_disable_rc6(dev); - } else if (INTEL_INFO(dev)->gen >= 6) { - cancel_delayed_work_sync(&dev_priv->rps.delayed_resume_work); + } else if (IS_GEN6(dev) || IS_GEN7(dev) || IS_BROADWELL(dev)) { + if (cancel_delayed_work_sync(&dev_priv->rps.delayed_resume_work)) + intel_runtime_pm_put(dev_priv); + cancel_work_sync(&dev_priv->rps.work); mutex_lock(&dev_priv->rps.hw_lock); if (IS_VALLEYVIEW(dev)) @@ -4533,13 +4713,15 @@ static void intel_gen6_powersave_work(struct work_struct *work) valleyview_enable_rps(dev); } else if (IS_BROADWELL(dev)) { gen8_enable_rps(dev); - gen6_update_ring_freq(dev); + __gen6_update_ring_freq(dev); } else { gen6_enable_rps(dev); - gen6_update_ring_freq(dev); + __gen6_update_ring_freq(dev); } dev_priv->rps.enabled = true; mutex_unlock(&dev_priv->rps.hw_lock); + + intel_runtime_pm_put(dev_priv); } void intel_enable_gt_powersave(struct drm_device *dev) @@ -4547,20 +4729,38 @@ void intel_enable_gt_powersave(struct drm_device *dev) struct drm_i915_private *dev_priv = dev->dev_private; if (IS_IRONLAKE_M(dev)) { + mutex_lock(&dev->struct_mutex); ironlake_enable_drps(dev); ironlake_enable_rc6(dev); intel_init_emon(dev); - } else if (IS_GEN6(dev) || IS_GEN7(dev)) { + mutex_unlock(&dev->struct_mutex); + } else if (IS_GEN6(dev) || IS_GEN7(dev) || IS_BROADWELL(dev)) { /* * PCU communication is slow and this doesn't need to be * done at any specific time, so do this out of our fast path * to make resume and init faster. + * + * We depend on the HW RC6 power context save/restore + * mechanism when entering D3 through runtime PM suspend. So + * disable RPM until RPS/RC6 is properly setup. We can only + * get here via the driver load/system resume/runtime resume + * paths, so the _noresume version is enough (and in case of + * runtime resume it's necessary). */ - schedule_delayed_work(&dev_priv->rps.delayed_resume_work, - round_jiffies_up_relative(HZ)); + if (schedule_delayed_work(&dev_priv->rps.delayed_resume_work, + round_jiffies_up_relative(HZ))) + intel_runtime_pm_get_noresume(dev_priv); } } +void intel_reset_gt_powersave(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + dev_priv->rps.enabled = false; + intel_enable_gt_powersave(dev); +} + static void ibx_init_clock_gating(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -4666,6 +4866,9 @@ static void ironlake_init_clock_gating(struct drm_device *dev) I915_WRITE(CACHE_MODE_0, _MASKED_BIT_ENABLE(CM0_PIPELINED_RENDER_FLUSH_DISABLE)); + /* WaDisable_RenderCache_OperationalFlush:ilk */ + I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE)); + g4x_disable_trickle_feed(dev); ibx_init_clock_gating(dev); @@ -4741,6 +4944,9 @@ static void gen6_init_clock_gating(struct drm_device *dev) I915_WRITE(GEN6_GT_MODE, _MASKED_BIT_ENABLE(GEN6_TD_FOUR_ROW_DISPATCH_DISABLE)); + /* WaDisable_RenderCache_OperationalFlush:snb */ + I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE)); + /* * BSpec recoomends 8x4 when MSAA is used, * however in practice 16x4 seems fastest. @@ -4909,6 +5115,10 @@ static void gen8_init_clock_gating(struct drm_device *dev) 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); @@ -4980,6 +5190,9 @@ static void haswell_init_clock_gating(struct drm_device *dev) I915_WRITE(GEN7_FF_THREAD_MODE, I915_READ(GEN7_FF_THREAD_MODE) & ~GEN7_FF_VS_REF_CNT_FFME); + /* WaDisable_RenderCache_OperationalFlush:hsw */ + I915_WRITE(CACHE_MODE_0_GEN7, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE)); + /* enable HiZ Raw Stall Optimization */ I915_WRITE(CACHE_MODE_0_GEN7, _MASKED_BIT_DISABLE(HIZ_RAW_STALL_OPT_DISABLE)); @@ -5032,6 +5245,9 @@ static void ivybridge_init_clock_gating(struct drm_device *dev) I915_WRITE(GEN7_HALF_SLICE_CHICKEN1, _MASKED_BIT_ENABLE(GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE)); + /* WaDisable_RenderCache_OperationalFlush:ivb */ + I915_WRITE(CACHE_MODE_0_GEN7, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE)); + /* Apply the WaDisableRHWOOptimizationForRenderHang:ivb workaround. */ I915_WRITE(GEN7_COMMON_SLICE_CHICKEN1, GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC); @@ -5126,6 +5342,10 @@ static void valleyview_init_clock_gating(struct drm_device *dev) } DRM_DEBUG_DRIVER("DDR speed: %d MHz", dev_priv->mem_freq); + dev_priv->vlv_cdclk_freq = valleyview_cur_cdclk(dev_priv); + DRM_DEBUG_DRIVER("Current CD clock rate: %d MHz", + dev_priv->vlv_cdclk_freq); + I915_WRITE(DSPCLK_GATE_D, VRHUNIT_CLOCK_GATE_DISABLE); /* WaDisableEarlyCull:vlv */ @@ -5143,6 +5363,9 @@ static void valleyview_init_clock_gating(struct drm_device *dev) _MASKED_BIT_ENABLE(GEN7_MAX_PS_THREAD_DEP | GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE)); + /* WaDisable_RenderCache_OperationalFlush:vlv */ + I915_WRITE(CACHE_MODE_0_GEN7, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE)); + /* WaForceL3Serialization:vlv */ I915_WRITE(GEN7_L3SQCREG4, I915_READ(GEN7_L3SQCREG4) & ~L3SQ_URB_READ_CAM_MATCH_DISABLE); @@ -5165,8 +5388,11 @@ static void valleyview_init_clock_gating(struct drm_device *dev) I915_WRITE(GEN6_UCGCTL2, GEN6_RCZUNIT_CLOCK_GATE_DISABLE); - /* WaDisableL3Bank2xClockGate:vlv */ - I915_WRITE(GEN7_UCGCTL4, GEN7_L3BANK2X_CLOCK_GATE_DISABLE); + /* WaDisableL3Bank2xClockGate:vlv + * Disabling L3 clock gating- MMIO 940c[25] = 1 + * Set bit 25, to disable L3_BANK_2x_CLK_GATING */ + I915_WRITE(GEN7_UCGCTL4, + I915_READ(GEN7_UCGCTL4) | GEN7_L3BANK2X_CLOCK_GATE_DISABLE); I915_WRITE(MI_ARB_VLV, MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE); @@ -5191,6 +5417,59 @@ static void valleyview_init_clock_gating(struct drm_device *dev) I915_WRITE(VLV_GUNIT_CLOCK_GATE, GCFG_DIS); } +static void cherryview_init_clock_gating(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + 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_READ(GEN7_FF_THREAD_MODE) & + ~(GEN8_FF_DS_REF_CNT_FFME | GEN7_FF_VS_REF_CNT_FFME)); + + /* WaDisableSemaphoreAndSyncFlipWait:chv */ + I915_WRITE(GEN6_RC_SLEEP_PSMI_CONTROL, + _MASKED_BIT_ENABLE(GEN8_RC_SEMA_IDLE_MSG_DISABLE)); + + /* WaDisableCSUnitClockGating:chv */ + I915_WRITE(GEN6_UCGCTL1, I915_READ(GEN6_UCGCTL1) | + GEN6_CSUNIT_CLOCK_GATE_DISABLE); + + /* WaDisableSDEUnitClockGating:chv */ + 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); + + /* WaDisableFfDopClockGating:chv (pre-production hw) */ + I915_WRITE(GEN6_RC_SLEEP_PSMI_CONTROL, + _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); +} + static void g4x_init_clock_gating(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -5212,6 +5491,9 @@ static void g4x_init_clock_gating(struct drm_device *dev) I915_WRITE(CACHE_MODE_0, _MASKED_BIT_ENABLE(CM0_PIPELINED_RENDER_FLUSH_DISABLE)); + /* WaDisable_RenderCache_OperationalFlush:g4x */ + I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE)); + g4x_disable_trickle_feed(dev); } @@ -5226,6 +5508,9 @@ static void crestline_init_clock_gating(struct drm_device *dev) I915_WRITE16(DEUC, 0); I915_WRITE(MI_ARB_STATE, _MASKED_BIT_ENABLE(MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE)); + + /* WaDisable_RenderCache_OperationalFlush:gen4 */ + I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE)); } static void broadwater_init_clock_gating(struct drm_device *dev) @@ -5240,6 +5525,9 @@ static void broadwater_init_clock_gating(struct drm_device *dev) I915_WRITE(RENCLK_GATE_D2, 0); I915_WRITE(MI_ARB_STATE, _MASKED_BIT_ENABLE(MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE)); + + /* WaDisable_RenderCache_OperationalFlush:gen4 */ + I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE)); } static void gen3_init_clock_gating(struct drm_device *dev) @@ -5256,6 +5544,12 @@ static void gen3_init_clock_gating(struct drm_device *dev) /* IIR "flip pending" means done if this bit is set */ I915_WRITE(ECOSKPD, _MASKED_BIT_DISABLE(ECO_FLIP_DONE)); + + /* interrupts should cause a wake up from C3 */ + I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_AGPBUSY_INT_EN)); + + /* 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)); } static void i85x_init_clock_gating(struct drm_device *dev) @@ -5263,6 +5557,10 @@ static void i85x_init_clock_gating(struct drm_device *dev) struct drm_i915_private *dev_priv = dev->dev_private; I915_WRITE(RENCLK_GATE_D1, SV_CLOCK_GATE_DISABLE); + + /* 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)); } static void i830_init_clock_gating(struct drm_device *dev) @@ -5314,10 +5612,25 @@ bool intel_display_power_enabled_sw(struct drm_i915_private *dev_priv, enum intel_display_power_domain domain) { struct i915_power_domains *power_domains; + struct i915_power_well *power_well; + bool is_enabled; + int i; + + if (dev_priv->pm.suspended) + return false; power_domains = &dev_priv->power_domains; + is_enabled = true; + for_each_power_well_rev(i, power_well, BIT(domain), power_domains) { + if (power_well->always_on) + continue; - return power_domains->domain_use_count[domain]; + if (!power_well->count) { + is_enabled = false; + break; + } + } + return is_enabled; } bool intel_display_power_enabled(struct drm_i915_private *dev_priv, @@ -5392,33 +5705,6 @@ static void hsw_power_well_post_enable(struct drm_i915_private *dev_priv) } } -static void reset_vblank_counter(struct drm_device *dev, enum pipe pipe) -{ - assert_spin_locked(&dev->vbl_lock); - - dev->vblank[pipe].last = 0; -} - -static void hsw_power_well_post_disable(struct drm_i915_private *dev_priv) -{ - struct drm_device *dev = dev_priv->dev; - enum pipe pipe; - unsigned long irqflags; - - /* - * After this, the registers on the pipes that are part of the power - * well will become zero, so we have to adjust our counters according to - * that. - * - * FIXME: Should we do this in general in drm_vblank_post_modeset? - */ - spin_lock_irqsave(&dev->vbl_lock, irqflags); - for_each_pipe(pipe) - if (pipe != PIPE_A) - reset_vblank_counter(dev, pipe); - spin_unlock_irqrestore(&dev->vbl_lock, irqflags); -} - static void hsw_set_power_well(struct drm_i915_private *dev_priv, struct i915_power_well *power_well, bool enable) { @@ -5447,8 +5733,6 @@ static void hsw_set_power_well(struct drm_i915_private *dev_priv, I915_WRITE(HSW_PWR_WELL_DRIVER, 0); POSTING_READ(HSW_PWR_WELL_DRIVER); DRM_DEBUG_KMS("Requesting to disable the power well\n"); - - hsw_power_well_post_disable(dev_priv); } } } @@ -5489,13 +5773,34 @@ static bool i9xx_always_on_power_well_enabled(struct drm_i915_private *dev_priv, return true; } -static void vlv_set_power_well(struct drm_i915_private *dev_priv, - struct i915_power_well *power_well, bool enable) +void __vlv_set_power_well(struct drm_i915_private *dev_priv, + enum punit_power_well power_well_id, bool enable) { - enum punit_power_well power_well_id = power_well->data; + struct drm_device *dev = dev_priv->dev; u32 mask; u32 state; u32 ctrl; + enum pipe pipe; + + if (power_well_id == PUNIT_POWER_WELL_DPIO_CMN_BC) { + if (enable) { + /* + * Enable the CRI clock source so we can get at the + * display and the reference clock for VGA + * hotplug / manual detection. + */ + I915_WRITE(DPLL(PIPE_B), I915_READ(DPLL(PIPE_B)) | + DPLL_REFA_CLK_ENABLE_VLV | + DPLL_INTEGRATED_CRI_CLK_VLV); + udelay(1); /* >10ns for cmnreset, >0ns for sidereset */ + } else { + for_each_pipe(pipe) + assert_pll_disabled(dev_priv, pipe); + /* Assert common reset */ + I915_WRITE(DPIO_CTL, I915_READ(DPIO_CTL) & + ~DPIO_CMNRST); + } + } mask = PUNIT_PWRGT_MASK(power_well_id); state = enable ? PUNIT_PWRGT_PWR_ON(power_well_id) : @@ -5523,6 +5828,28 @@ static void vlv_set_power_well(struct drm_i915_private *dev_priv, out: mutex_unlock(&dev_priv->rps.hw_lock); + + /* + * From VLV2A0_DP_eDP_DPIO_driver_vbios_notes_10.docx - + * 6. De-assert cmn_reset/side_reset. Same as VLV X0. + * a. GUnit 0x2110 bit[0] set to 1 (def 0) + * b. The other bits such as sfr settings / modesel may all + * be set to 0. + * + * This should only be done on init and resume from S3 with + * both PLLs disabled, or we risk losing DPIO and PLL + * synchronization. + */ + if (power_well_id == PUNIT_POWER_WELL_DPIO_CMN_BC && enable) + I915_WRITE(DPIO_CTL, I915_READ(DPIO_CTL) | DPIO_CMNRST); +} + +static void vlv_set_power_well(struct drm_i915_private *dev_priv, + struct i915_power_well *power_well, bool enable) +{ + enum punit_power_well power_well_id = power_well->data; + + __vlv_set_power_well(dev_priv, power_well_id, enable); } static void vlv_power_well_sync_hw(struct drm_i915_private *dev_priv, @@ -5591,11 +5918,13 @@ static void vlv_display_power_well_enable(struct drm_i915_private *dev_priv, spin_unlock_irq(&dev_priv->irq_lock); /* - * During driver initialization we need to defer enabling hotplug - * processing until fbdev is set up. + * During driver initialization/resume we can avoid restoring the + * part of the HW/SW state that will be inited anyway explicitly. */ - if (dev_priv->enable_hotplug_processing) - intel_hpd_init(dev_priv->dev); + if (dev_priv->power_domains.initializing) + return; + + intel_hpd_init(dev_priv->dev); i915_redisable_vga_power_on(dev_priv->dev); } @@ -5603,23 +5932,12 @@ static void vlv_display_power_well_enable(struct drm_i915_private *dev_priv, static void vlv_display_power_well_disable(struct drm_i915_private *dev_priv, struct i915_power_well *power_well) { - struct drm_device *dev = dev_priv->dev; - enum pipe pipe; - WARN_ON_ONCE(power_well->data != PUNIT_POWER_WELL_DISP2D); spin_lock_irq(&dev_priv->irq_lock); - for_each_pipe(pipe) - __intel_set_cpu_fifo_underrun_reporting(dev, pipe, false); - valleyview_disable_display_irqs(dev_priv); spin_unlock_irq(&dev_priv->irq_lock); - spin_lock_irq(&dev->vbl_lock); - for_each_pipe(pipe) - reset_vblank_counter(dev, pipe); - spin_unlock_irq(&dev->vbl_lock); - vlv_set_power_well(dev_priv, power_well, false); } @@ -5867,12 +6185,6 @@ static struct i915_power_well vlv_power_wells[] = { .ops = &vlv_display_power_well_ops, }, { - .name = "dpio-common", - .domains = VLV_DPIO_CMN_BC_POWER_DOMAINS, - .data = PUNIT_POWER_WELL_DPIO_CMN_BC, - .ops = &vlv_dpio_power_well_ops, - }, - { .name = "dpio-tx-b-01", .domains = VLV_DPIO_TX_B_LANES_01_POWER_DOMAINS | VLV_DPIO_TX_B_LANES_23_POWER_DOMAINS | @@ -5908,6 +6220,12 @@ static struct i915_power_well vlv_power_wells[] = { .ops = &vlv_dpio_power_well_ops, .data = PUNIT_POWER_WELL_DPIO_TX_C_LANES_23, }, + { + .name = "dpio-common", + .domains = VLV_DPIO_CMN_BC_POWER_DOMAINS, + .data = PUNIT_POWER_WELL_DPIO_CMN_BC, + .ops = &vlv_dpio_power_well_ops, + }, }; #define set_power_wells(power_domains, __power_wells) ({ \ @@ -5959,9 +6277,13 @@ static void intel_power_domains_resume(struct drm_i915_private *dev_priv) void intel_power_domains_init_hw(struct drm_i915_private *dev_priv) { + struct i915_power_domains *power_domains = &dev_priv->power_domains; + + power_domains->initializing = true; /* For now, we need the power well to be always enabled. */ intel_display_set_init_power(dev_priv, true); intel_power_domains_resume(dev_priv); + power_domains->initializing = false; } void intel_aux_display_runtime_get(struct drm_i915_private *dev_priv) @@ -5986,6 +6308,18 @@ void intel_runtime_pm_get(struct drm_i915_private *dev_priv) WARN(dev_priv->pm.suspended, "Device still suspended.\n"); } +void intel_runtime_pm_get_noresume(struct drm_i915_private *dev_priv) +{ + struct drm_device *dev = dev_priv->dev; + struct device *device = &dev->pdev->dev; + + if (!HAS_RUNTIME_PM(dev)) + return; + + WARN(dev_priv->pm.suspended, "Getting nosync-ref while suspended.\n"); + pm_runtime_get_noresume(device); +} + void intel_runtime_pm_put(struct drm_i915_private *dev_priv) { struct drm_device *dev = dev_priv->dev; @@ -6008,6 +6342,15 @@ void intel_init_runtime_pm(struct drm_i915_private *dev_priv) pm_runtime_set_active(device); + /* + * RPM depends on RC6 to save restore the GT HW context, so make RC6 a + * requirement. + */ + if (!intel_enable_rc6(dev)) { + DRM_INFO("RC6 disabled, disabling runtime PM support\n"); + return; + } + pm_runtime_set_autosuspend_delay(device, 10000); /* 10s */ pm_runtime_mark_last_busy(device); pm_runtime_use_autosuspend(device); @@ -6023,6 +6366,9 @@ void intel_fini_runtime_pm(struct drm_i915_private *dev_priv) if (!HAS_RUNTIME_PM(dev)) return; + if (!intel_enable_rc6(dev)) + return; + /* Make sure we're not suspended first. */ pm_runtime_get_sync(device); pm_runtime_disable(device); @@ -6087,6 +6433,10 @@ void intel_init_pm(struct drm_device *dev) dev_priv->display.init_clock_gating = haswell_init_clock_gating; else if (INTEL_INFO(dev)->gen == 8) dev_priv->display.init_clock_gating = gen8_init_clock_gating; + } else if (IS_CHERRYVIEW(dev)) { + dev_priv->display.update_wm = valleyview_update_wm; + dev_priv->display.init_clock_gating = + cherryview_init_clock_gating; } else if (IS_VALLEYVIEW(dev)) { dev_priv->display.update_wm = valleyview_update_wm; dev_priv->display.init_clock_gating = |