diff options
Diffstat (limited to 'drivers/gpu/drm/i915/intel_pm.c')
| -rw-r--r-- | drivers/gpu/drm/i915/intel_pm.c | 1824 |
1 files changed, 1337 insertions, 487 deletions
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index e1fc35a7265..d1e53abec1b 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -92,12 +92,12 @@ static void i8xx_enable_fbc(struct drm_crtc *crtc) { struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct drm_framebuffer *fb = crtc->fb; + struct drm_framebuffer *fb = crtc->primary->fb; struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb); struct drm_i915_gem_object *obj = intel_fb->obj; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); int cfb_pitch; - int plane, i; + int i; u32 fbc_ctl; cfb_pitch = dev_priv->fbc.size / FBC_LL_SIZE; @@ -109,7 +109,6 @@ static void i8xx_enable_fbc(struct drm_crtc *crtc) cfb_pitch = (cfb_pitch / 32) - 1; else cfb_pitch = (cfb_pitch / 64) - 1; - plane = intel_crtc->plane == 0 ? FBC_CTL_PLANEA : FBC_CTL_PLANEB; /* Clear old tags */ for (i = 0; i < (FBC_LL_SIZE / 32) + 1; i++) @@ -120,7 +119,7 @@ static void i8xx_enable_fbc(struct drm_crtc *crtc) /* Set it up... */ fbc_ctl2 = FBC_CTL_FENCE_DBL | FBC_CTL_IDLE_IMM | FBC_CTL_CPU_FENCE; - fbc_ctl2 |= plane; + fbc_ctl2 |= FBC_CTL_PLANE(intel_crtc->plane); I915_WRITE(FBC_CONTROL2, fbc_ctl2); I915_WRITE(FBC_FENCE_OFF, crtc->y); } @@ -135,7 +134,7 @@ static void i8xx_enable_fbc(struct drm_crtc *crtc) fbc_ctl |= obj->fence_reg; I915_WRITE(FBC_CONTROL, fbc_ctl); - DRM_DEBUG_KMS("enabled FBC, pitch %d, yoff %d, plane %c, ", + DRM_DEBUG_KMS("enabled FBC, pitch %d, yoff %d, plane %c\n", cfb_pitch, crtc->y, plane_name(intel_crtc->plane)); } @@ -150,21 +149,23 @@ static void g4x_enable_fbc(struct drm_crtc *crtc) { struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct drm_framebuffer *fb = crtc->fb; + struct drm_framebuffer *fb = crtc->primary->fb; struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb); struct drm_i915_gem_object *obj = intel_fb->obj; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - int plane = intel_crtc->plane == 0 ? DPFC_CTL_PLANEA : DPFC_CTL_PLANEB; u32 dpfc_ctl; - dpfc_ctl = plane | DPFC_SR_EN | DPFC_CTL_LIMIT_1X; + dpfc_ctl = DPFC_CTL_PLANE(intel_crtc->plane) | DPFC_SR_EN; + if (drm_format_plane_cpp(fb->pixel_format, 0) == 2) + dpfc_ctl |= DPFC_CTL_LIMIT_2X; + else + dpfc_ctl |= DPFC_CTL_LIMIT_1X; dpfc_ctl |= DPFC_CTL_FENCE_EN | obj->fence_reg; - I915_WRITE(DPFC_CHICKEN, DPFC_HT_MODIFY); I915_WRITE(DPFC_FENCE_YOFF, crtc->y); /* enable it... */ - I915_WRITE(DPFC_CONTROL, I915_READ(DPFC_CONTROL) | DPFC_CTL_EN); + I915_WRITE(DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN); DRM_DEBUG_KMS("enabled fbc on plane %c\n", plane_name(intel_crtc->plane)); } @@ -220,22 +221,20 @@ static void ironlake_enable_fbc(struct drm_crtc *crtc) { struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct drm_framebuffer *fb = crtc->fb; + struct drm_framebuffer *fb = crtc->primary->fb; struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb); struct drm_i915_gem_object *obj = intel_fb->obj; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - int plane = intel_crtc->plane == 0 ? DPFC_CTL_PLANEA : DPFC_CTL_PLANEB; u32 dpfc_ctl; - dpfc_ctl = I915_READ(ILK_DPFC_CONTROL); - dpfc_ctl &= DPFC_RESERVED; - dpfc_ctl |= (plane | DPFC_CTL_LIMIT_1X); - /* Set persistent mode for front-buffer rendering, ala X. */ - dpfc_ctl |= DPFC_CTL_PERSISTENT_MODE; + dpfc_ctl = DPFC_CTL_PLANE(intel_crtc->plane); + if (drm_format_plane_cpp(fb->pixel_format, 0) == 2) + dpfc_ctl |= DPFC_CTL_LIMIT_2X; + else + dpfc_ctl |= DPFC_CTL_LIMIT_1X; dpfc_ctl |= DPFC_CTL_FENCE_EN; if (IS_GEN5(dev)) dpfc_ctl |= obj->fence_reg; - I915_WRITE(ILK_DPFC_CHICKEN, DPFC_HT_MODIFY); I915_WRITE(ILK_DPFC_FENCE_YOFF, crtc->y); I915_WRITE(ILK_FBC_RT_BASE, i915_gem_obj_ggtt_offset(obj) | ILK_FBC_RT_VALID); @@ -278,24 +277,31 @@ static void gen7_enable_fbc(struct drm_crtc *crtc) { struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct drm_framebuffer *fb = crtc->fb; + struct drm_framebuffer *fb = crtc->primary->fb; struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb); struct drm_i915_gem_object *obj = intel_fb->obj; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + u32 dpfc_ctl; - I915_WRITE(IVB_FBC_RT_BASE, i915_gem_obj_ggtt_offset(obj)); + dpfc_ctl = IVB_DPFC_CTL_PLANE(intel_crtc->plane); + if (drm_format_plane_cpp(fb->pixel_format, 0) == 2) + dpfc_ctl |= DPFC_CTL_LIMIT_2X; + else + dpfc_ctl |= DPFC_CTL_LIMIT_1X; + dpfc_ctl |= IVB_DPFC_CTL_FENCE_EN; - I915_WRITE(ILK_DPFC_CONTROL, DPFC_CTL_EN | DPFC_CTL_LIMIT_1X | - IVB_DPFC_CTL_FENCE_EN | - intel_crtc->plane << IVB_DPFC_CTL_PLANE_SHIFT); + I915_WRITE(ILK_DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN); if (IS_IVYBRIDGE(dev)) { /* WaFbcAsynchFlipDisableFbcQueue:ivb */ - I915_WRITE(ILK_DISPLAY_CHICKEN1, ILK_FBCQ_DIS); + I915_WRITE(ILK_DISPLAY_CHICKEN1, + I915_READ(ILK_DISPLAY_CHICKEN1) | + ILK_FBCQ_DIS); } else { - /* WaFbcAsynchFlipDisableFbcQueue:hsw */ - I915_WRITE(HSW_PIPE_SLICE_CHICKEN_1(intel_crtc->pipe), - HSW_BYPASS_FBC_QUEUE); + /* WaFbcAsynchFlipDisableFbcQueue:hsw,bdw */ + I915_WRITE(CHICKEN_PIPESL_1(intel_crtc->pipe), + I915_READ(CHICKEN_PIPESL_1(intel_crtc->pipe)) | + HSW_FBCQ_DIS); } I915_WRITE(SNB_DPFC_CTL_SA, @@ -330,11 +336,11 @@ static void intel_fbc_work_fn(struct work_struct *__work) /* Double check that we haven't switched fb without cancelling * the prior work. */ - if (work->crtc->fb == work->fb) { + if (work->crtc->primary->fb == work->fb) { dev_priv->display.enable_fbc(work->crtc); dev_priv->fbc.plane = to_intel_crtc(work->crtc)->plane; - dev_priv->fbc.fb_id = work->crtc->fb->base.id; + dev_priv->fbc.fb_id = work->crtc->primary->fb->base.id; dev_priv->fbc.y = work->crtc->y; } @@ -387,7 +393,7 @@ static void intel_enable_fbc(struct drm_crtc *crtc) } work->crtc = crtc; - work->fb = crtc->fb; + work->fb = crtc->primary->fb; INIT_DELAYED_WORK(&work->work, intel_fbc_work_fn); dev_priv->fbc.fbc_work = work; @@ -466,7 +472,7 @@ void intel_update_fbc(struct drm_device *dev) return; } - if (!i915_powersave) { + if (!i915.powersave) { if (set_no_fbc_reason(dev_priv, FBC_MODULE_PARAM)) DRM_DEBUG_KMS("fbc disabled per module param\n"); return; @@ -481,7 +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) { @@ -493,25 +499,25 @@ void intel_update_fbc(struct drm_device *dev) } } - if (!crtc || crtc->fb == NULL) { + if (!crtc || crtc->primary->fb == NULL) { if (set_no_fbc_reason(dev_priv, FBC_NO_OUTPUT)) DRM_DEBUG_KMS("no output, disabling\n"); goto out_disable; } intel_crtc = to_intel_crtc(crtc); - fb = crtc->fb; + fb = crtc->primary->fb; intel_fb = to_intel_framebuffer(fb); obj = intel_fb->obj; adjusted_mode = &intel_crtc->config.adjusted_mode; - if (i915_enable_fbc < 0 && + if (i915.enable_fbc < 0 && INTEL_INFO(dev)->gen <= 7 && !IS_HASWELL(dev)) { if (set_no_fbc_reason(dev_priv, FBC_CHIP_DEFAULT)) DRM_DEBUG_KMS("disabled per chip default\n"); goto out_disable; } - if (!i915_enable_fbc) { + if (!i915.enable_fbc) { if (set_no_fbc_reason(dev_priv, FBC_MODULE_PARAM)) DRM_DEBUG_KMS("fbc disabled per module param\n"); goto out_disable; @@ -537,7 +543,7 @@ void intel_update_fbc(struct drm_device *dev) DRM_DEBUG_KMS("mode too large for compression, disabling\n"); goto out_disable; } - if ((INTEL_INFO(dev)->gen < 4 || IS_HASWELL(dev)) && + if ((INTEL_INFO(dev)->gen < 4 || HAS_DDI(dev)) && intel_crtc->plane != PLANE_A) { if (set_no_fbc_reason(dev_priv, FBC_BAD_PLANE)) DRM_DEBUG_KMS("plane not A, disabling compression\n"); @@ -617,7 +623,7 @@ out_disable: static void i915_pineview_get_mem_freq(struct drm_device *dev) { - drm_i915_private_t *dev_priv = dev->dev_private; + struct drm_i915_private *dev_priv = dev->dev_private; u32 tmp; tmp = I915_READ(CLKCFG); @@ -656,7 +662,7 @@ static void i915_pineview_get_mem_freq(struct drm_device *dev) static void i915_ironlake_get_mem_freq(struct drm_device *dev) { - drm_i915_private_t *dev_priv = dev->dev_private; + struct drm_i915_private *dev_priv = dev->dev_private; u16 ddrpll, csipll; ddrpll = I915_READ16(DDRMPLL1); @@ -1004,7 +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; @@ -1035,7 +1041,7 @@ static void pineview_update_wm(struct drm_crtc *unused_crtc) crtc = single_enabled_crtc(dev); if (crtc) { const struct drm_display_mode *adjusted_mode; - int pixel_size = crtc->fb->bits_per_pixel / 8; + int pixel_size = crtc->primary->fb->bits_per_pixel / 8; int clock; adjusted_mode = &to_intel_crtc(crtc)->config.adjusted_mode; @@ -1115,7 +1121,7 @@ static bool g4x_compute_wm0(struct drm_device *dev, clock = adjusted_mode->crtc_clock; htotal = adjusted_mode->crtc_htotal; hdisplay = to_intel_crtc(crtc)->config.pipe_src_w; - pixel_size = crtc->fb->bits_per_pixel / 8; + pixel_size = crtc->primary->fb->bits_per_pixel / 8; /* Use the small buffer method to calculate plane watermark */ entries = ((clock * pixel_size / 1000) * display_latency_ns) / 1000; @@ -1128,9 +1134,9 @@ static bool g4x_compute_wm0(struct drm_device *dev, *plane_wm = display->max_wm; /* Use the large buffer method to calculate cursor watermark */ - line_time_us = ((htotal * 1000) / clock); + line_time_us = max(htotal * 1000 / clock, 1); line_count = (cursor_latency_ns / line_time_us + 1000) / 1000; - entries = line_count * 64 * pixel_size; + entries = line_count * to_intel_crtc(crtc)->cursor_width * pixel_size; tlb_miss = cursor->fifo_size*cursor->cacheline_size - hdisplay * 8; if (tlb_miss > 0) entries += tlb_miss; @@ -1202,9 +1208,9 @@ static bool g4x_compute_srwm(struct drm_device *dev, clock = adjusted_mode->crtc_clock; htotal = adjusted_mode->crtc_htotal; hdisplay = to_intel_crtc(crtc)->config.pipe_src_w; - pixel_size = crtc->fb->bits_per_pixel / 8; + pixel_size = crtc->primary->fb->bits_per_pixel / 8; - line_time_us = (htotal * 1000) / clock; + line_time_us = max(htotal * 1000 / clock, 1); line_count = (latency_ns / line_time_us + 1000) / 1000; line_size = hdisplay * pixel_size; @@ -1216,7 +1222,7 @@ static bool g4x_compute_srwm(struct drm_device *dev, *display_wm = entries + display->guard_size; /* calculate the self-refresh watermark for display cursor */ - entries = line_count * pixel_size * 64; + entries = line_count * pixel_size * to_intel_crtc(crtc)->cursor_width; entries = DIV_ROUND_UP(entries, cursor->cacheline_size); *cursor_wm = entries + cursor->guard_size; @@ -1241,7 +1247,7 @@ static bool vlv_compute_drain_latency(struct drm_device *dev, return false; clock = to_intel_crtc(crtc)->config.adjusted_mode.crtc_clock; - pixel_size = crtc->fb->bits_per_pixel / 8; /* BPP */ + pixel_size = crtc->primary->fb->bits_per_pixel / 8; /* BPP */ entries = (clock / 1000) * pixel_size; *plane_prec_mult = (entries > 256) ? @@ -1433,11 +1439,11 @@ static void i965_update_wm(struct drm_crtc *unused_crtc) int clock = adjusted_mode->crtc_clock; int htotal = adjusted_mode->crtc_htotal; int hdisplay = to_intel_crtc(crtc)->config.pipe_src_w; - int pixel_size = crtc->fb->bits_per_pixel / 8; + int pixel_size = crtc->primary->fb->bits_per_pixel / 8; unsigned long line_time_us; int entries; - line_time_us = ((htotal * 1000) / clock); + line_time_us = max(htotal * 1000 / clock, 1); /* Use ns/us then divide to preserve precision */ entries = (((sr_latency_ns / line_time_us) + 1000) / 1000) * @@ -1451,7 +1457,7 @@ static void i965_update_wm(struct drm_crtc *unused_crtc) entries, srwm); entries = (((sr_latency_ns / line_time_us) + 1000) / 1000) * - pixel_size * 64; + pixel_size * to_intel_crtc(crtc)->cursor_width; entries = DIV_ROUND_UP(entries, i965_cursor_wm_info.cacheline_size); cursor_sr = i965_cursor_wm_info.fifo_size - @@ -1506,7 +1512,7 @@ static void i9xx_update_wm(struct drm_crtc *unused_crtc) crtc = intel_get_crtc_for_plane(dev, 0); if (intel_crtc_active(crtc)) { const struct drm_display_mode *adjusted_mode; - int cpp = crtc->fb->bits_per_pixel / 8; + int cpp = crtc->primary->fb->bits_per_pixel / 8; if (IS_GEN2(dev)) cpp = 4; @@ -1522,7 +1528,7 @@ static void i9xx_update_wm(struct drm_crtc *unused_crtc) crtc = intel_get_crtc_for_plane(dev, 1); if (intel_crtc_active(crtc)) { const struct drm_display_mode *adjusted_mode; - int cpp = crtc->fb->bits_per_pixel / 8; + int cpp = crtc->primary->fb->bits_per_pixel / 8; if (IS_GEN2(dev)) cpp = 4; @@ -1539,6 +1545,16 @@ static void i9xx_update_wm(struct drm_crtc *unused_crtc) DRM_DEBUG_KMS("FIFO watermarks - A: %d, B: %d\n", planea_wm, planeb_wm); + if (IS_I915GM(dev) && enabled) { + struct intel_framebuffer *fb; + + fb = to_intel_framebuffer(enabled->primary->fb); + + /* self-refresh seems busted with untiled */ + if (fb->obj->tiling_mode == I915_TILING_NONE) + enabled = NULL; + } + /* * Overlay gets an aggressive default since video jitter is bad. */ @@ -1559,11 +1575,11 @@ static void i9xx_update_wm(struct drm_crtc *unused_crtc) int clock = adjusted_mode->crtc_clock; int htotal = adjusted_mode->crtc_htotal; int hdisplay = to_intel_crtc(enabled)->config.pipe_src_w; - int pixel_size = enabled->fb->bits_per_pixel / 8; + int pixel_size = enabled->primary->fb->bits_per_pixel / 8; unsigned long line_time_us; int entries; - line_time_us = (htotal * 1000) / clock; + line_time_us = max(htotal * 1000 / clock, 1); /* Use ns/us then divide to preserve precision */ entries = (((sr_latency_ns / line_time_us) + 1000) / 1000) * @@ -1815,6 +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, @@ -1823,7 +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) @@ -1854,19 +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 */ @@ -1879,23 +1916,10 @@ 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(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(struct drm_device *dev, +static void ilk_compute_wm_maximums(const struct drm_device *dev, int level, const struct intel_wm_config *config, enum intel_ddb_partitioning ddb_partitioning, @@ -1904,7 +1928,17 @@ static void ilk_compute_wm_maximums(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, @@ -1948,7 +1982,7 @@ static bool ilk_validate_wm_level(int level, return ret; } -static void ilk_compute_wm_level(struct drm_i915_private *dev_priv, +static void ilk_compute_wm_level(const struct drm_i915_private *dev_priv, int level, const struct ilk_pipe_wm_parameters *p, struct intel_wm_level *result) @@ -2043,7 +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)) @@ -2079,7 +2113,44 @@ static void intel_print_wm_latency(struct drm_device *dev, } } -static void intel_setup_wm_latency(struct drm_device *dev) +static bool ilk_increase_wm_latency(struct drm_i915_private *dev_priv, + uint16_t wm[5], uint16_t min) +{ + int level, max_level = ilk_wm_max_level(dev_priv->dev); + + if (wm[0] >= min) + return false; + + wm[0] = max(wm[0], min); + for (level = 1; level <= max_level; level++) + wm[level] = max_t(uint16_t, wm[level], DIV_ROUND_UP(min, 5)); + + return true; +} + +static void snb_wm_latency_quirk(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + bool changed; + + /* + * The BIOS provided WM memory latency values are often + * inadequate for high resolution displays. Adjust them. + */ + changed = ilk_increase_wm_latency(dev_priv, dev_priv->wm.pri_latency, 12) | + ilk_increase_wm_latency(dev_priv, dev_priv->wm.spr_latency, 12) | + ilk_increase_wm_latency(dev_priv, dev_priv->wm.cur_latency, 12); + + if (!changed) + return; + + DRM_DEBUG_KMS("WM latency values increased to avoid potential underruns\n"); + intel_print_wm_latency(dev, "Primary", dev_priv->wm.pri_latency); + intel_print_wm_latency(dev, "Sprite", dev_priv->wm.spr_latency); + intel_print_wm_latency(dev, "Cursor", dev_priv->wm.cur_latency); +} + +static void ilk_setup_wm_latency(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -2096,41 +2167,58 @@ static void intel_setup_wm_latency(struct drm_device *dev) intel_print_wm_latency(dev, "Primary", dev_priv->wm.pri_latency); intel_print_wm_latency(dev, "Sprite", dev_priv->wm.spr_latency); intel_print_wm_latency(dev, "Cursor", dev_priv->wm.cur_latency); + + if (IS_GEN6(dev)) + snb_wm_latency_quirk(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->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 = 64; - /* TODO: for now, assume primary and cursor planes are always enabled. */ - p->pri.enabled = true; - p->cur.enabled = true; - } - - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) - config->num_pipes_active += intel_crtc_active(crtc); + if (!intel_crtc_active(crtc)) + return; - list_for_each_entry(plane, &dev->mode_config.plane_list, head) { + 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; + + /* Compute the currently _active_ config */ + for_each_intel_crtc(dev, intel_crtc) { + const struct intel_pipe_wm *wm = &intel_crtc->wm.active; - config->sprites_enabled |= intel_plane->wm.enabled; - config->sprites_scaled |= intel_plane->wm.scaled; + if (!wm->pipe_enabled) + continue; + + config->sprites_enabled |= wm->sprites_enabled; + config->sprites_scaled |= wm->sprites_scaled; + config->num_pipes_active++; } } @@ -2140,7 +2228,7 @@ static bool intel_compute_pipe_wm(struct drm_crtc *crtc, struct intel_pipe_wm *pipe_wm) { struct drm_device *dev = crtc->dev; - struct drm_i915_private *dev_priv = dev->dev_private; + const struct drm_i915_private *dev_priv = dev->dev_private; int level, max_level = ilk_wm_max_level(dev); /* LP0 watermark maximums depend on this pipe alone */ struct intel_wm_config config = { @@ -2150,8 +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) @@ -2161,15 +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; } /* @@ -2181,20 +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; } /* @@ -2206,6 +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)) && @@ -2221,15 +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; } } @@ -2284,14 +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; @@ -2299,6 +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; @@ -2307,7 +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]; @@ -2542,7 +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); @@ -2551,6 +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); @@ -2617,7 +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]; /* @@ -2650,7 +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); @@ -2658,8 +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) ? @@ -2738,7 +2877,7 @@ intel_alloc_context_page(struct drm_device *dev) return NULL; } - ret = i915_gem_obj_ggtt_pin(ctx, 4096, true, false); + ret = i915_gem_obj_ggtt_pin(ctx, 4096, 0); if (ret) { DRM_ERROR("failed to pin power context: %d\n", ret); goto err_unref; @@ -2753,7 +2892,7 @@ intel_alloc_context_page(struct drm_device *dev) return ctx; err_unpin: - i915_gem_object_unpin(ctx); + i915_gem_object_ggtt_unpin(ctx); err_unref: drm_gem_object_unreference(&ctx->base); return NULL; @@ -2901,9 +3040,9 @@ 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; } @@ -2915,26 +3054,26 @@ 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; @@ -3000,41 +3139,104 @@ static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val) dev_priv->rps.last_adj = 0; } +static u32 gen6_rps_pm_mask(struct drm_i915_private *dev_priv, u8 val) +{ + u32 mask = 0; + + if (val > dev_priv->rps.min_freq_softlimit) + mask |= GEN6_PM_RP_DOWN_THRESHOLD | GEN6_PM_RP_DOWN_TIMEOUT; + if (val < dev_priv->rps.max_freq_softlimit) + mask |= GEN6_PM_RP_UP_THRESHOLD; + + /* IVB and SNB hard hangs on looping batchbuffer + * if GEN6_PM_UP_EI_EXPIRED is masked. + */ + 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; +} + +/* gen6_set_rps is called to update the frequency request, but should also be + * called when the range (min_delay and max_delay) is modified so that we can + * update the GEN6_RP_INTERRUPT_LIMITS register accordingly. */ 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) - return; - - gen6_set_rps_thresholds(dev_priv, val); + /* min/max delay may still have been modified so be sure to + * write the limits value. + */ + if (val != dev_priv->rps.cur_freq) { + gen6_set_rps_thresholds(dev_priv, val); - if (IS_HASWELL(dev)) - I915_WRITE(GEN6_RPNSWREQ, - HSW_FREQUENCY(val)); - else - I915_WRITE(GEN6_RPNSWREQ, - GEN6_FREQUENCY(val) | - GEN6_OFFSET(0) | - GEN6_AGGRESSIVE_TURBO); + if (IS_HASWELL(dev) || IS_BROADWELL(dev)) + I915_WRITE(GEN6_RPNSWREQ, + HSW_FREQUENCY(val)); + else + I915_WRITE(GEN6_RPNSWREQ, + GEN6_FREQUENCY(val) | + GEN6_OFFSET(0) | + GEN6_AGGRESSIVE_TURBO); + } /* Make sure we continue to get interrupts * until we hit the minimum or maximum frequencies. */ - I915_WRITE(GEN6_RP_INTERRUPT_LIMITS, - gen6_rps_limits(dev_priv, val)); + I915_WRITE(GEN6_RP_INTERRUPT_LIMITS, gen6_rps_limits(dev_priv, val)); + I915_WRITE(GEN6_PMINTRMSK, gen6_rps_pm_mask(dev_priv, val)); POSTING_READ(GEN6_RPNSWREQ); - dev_priv->rps.cur_delay = val; - + dev_priv->rps.cur_freq = val; trace_intel_gpu_freq_change(val * 50); } +/* vlv_set_rps_idle: Set the frequency to Rpn if Gfx clocks are down + * + * * If Gfx is Idle, then + * 1. Mask Turbo interrupts + * 2. Bring up Gfx clock + * 3. Change the freq to Rpn and wait till P-Unit updates freq + * 4. Clear the Force GFX CLK ON bit so that Gfx can down + * 5. Unmask Turbo interrupts +*/ +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_freq <= dev_priv->rps.min_freq_softlimit) + return; + + /* Mask turbo interrupt so that they will not come in between */ + I915_WRITE(GEN6_PMINTRMSK, 0xffffffff); + + vlv_force_gfx_clock(dev_priv, true); + + 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_freq_softlimit); + + if (wait_for(((vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS)) + & GENFREQSTATUS) == 0, 5)) + DRM_ERROR("timed out waiting for Punit\n"); + + vlv_force_gfx_clock(dev_priv, false); + + I915_WRITE(GEN6_PMINTRMSK, + gen6_rps_pm_mask(dev_priv, dev_priv->rps.cur_freq)); +} + void gen6_rps_idle(struct drm_i915_private *dev_priv) { struct drm_device *dev = dev_priv->dev; @@ -3042,9 +3244,9 @@ void gen6_rps_idle(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.min_delay); + 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); @@ -3057,9 +3259,9 @@ 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); @@ -3070,30 +3272,50 @@ 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) - return; - - vlv_punit_write(dev_priv, PUNIT_REG_GPU_FREQ_REQ, val); + if (val != dev_priv->rps.cur_freq) + vlv_punit_write(dev_priv, PUNIT_REG_GPU_FREQ_REQ, val); - dev_priv->rps.cur_delay = val; + I915_WRITE(GEN6_PMINTRMSK, gen6_rps_pm_mask(dev_priv, val)); + dev_priv->rps.cur_freq = 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; I915_WRITE(GEN6_PMINTRMSK, 0xffffffff); - I915_WRITE(GEN6_PMIER, I915_READ(GEN6_PMIER) & ~GEN6_PM_RPS_EVENTS); + I915_WRITE(GEN6_PMIER, I915_READ(GEN6_PMIER) & + ~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 (PMIMR) to mask PM interrupts. The only risk is in leaving @@ -3103,7 +3325,7 @@ static void gen6_disable_rps_interrupts(struct drm_device *dev) dev_priv->rps.pm_iir = 0; spin_unlock_irq(&dev_priv->irq_lock); - I915_WRITE(GEN6_PMIIR, GEN6_PM_RPS_EVENTS); + I915_WRITE(GEN6_PMIIR, dev_priv->pm_rps_events); } static void gen6_disable_rps(struct drm_device *dev) @@ -3113,7 +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) @@ -3123,78 +3348,111 @@ static void valleyview_disable_rps(struct drm_device *dev) I915_WRITE(GEN6_RC_CONTROL, 0); gen6_disable_rps_interrupts(dev); - - if (dev_priv->vlv_pctx) { - drm_gem_object_unreference(&dev_priv->vlv_pctx->base); - dev_priv->vlv_pctx = NULL; - } } static void intel_print_rc6_info(struct drm_device *dev, u32 mode) { - if (IS_GEN6(dev)) - DRM_DEBUG_DRIVER("Sandybridge: deep RC6 disabled\n"); - - if (IS_HASWELL(dev)) - DRM_DEBUG_DRIVER("Haswell: only RC6 available\n"); - + 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"); + (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) return 0; - if (IS_HASWELL(dev)) - return INTEL_RC6_ENABLE; + if (IS_IVYBRIDGE(dev)) + return (INTEL_RC6_ENABLE | INTEL_RC6p_ENABLE); - /* snb/ivb have more than one rc6 state. */ - if (INTEL_INFO(dev)->gen == 6) - return INTEL_RC6_ENABLE; + return INTEL_RC6_ENABLE; +} + +int intel_enable_rc6(const struct drm_device *dev) +{ + return i915.enable_rc6; +} - return (INTEL_RC6_ENABLE | INTEL_RC6p_ENABLE); +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; - u32 enabled_intrs; spin_lock_irq(&dev_priv->irq_lock); WARN_ON(dev_priv->rps.pm_iir); - snb_enable_pm_irq(dev_priv, GEN6_PM_RPS_EVENTS); - I915_WRITE(GEN6_PMIIR, GEN6_PM_RPS_EVENTS); + snb_enable_pm_irq(dev_priv, dev_priv->pm_rps_events); + I915_WRITE(GEN6_PMIIR, dev_priv->pm_rps_events); spin_unlock_irq(&dev_priv->irq_lock); +} - /* only unmask PM interrupts we need. Mask all others. */ - enabled_intrs = GEN6_PM_RPS_EVENTS; +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; - /* IVB and SNB hard hangs on looping batchbuffer - * if GEN6_PM_UP_EI_EXPIRED is masked. - */ - if (INTEL_INFO(dev)->gen <= 7 && !IS_HASWELL(dev)) - enabled_intrs |= GEN6_PM_RP_UP_EI_EXPIRED; + /* 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; - I915_WRITE(GEN6_PMINTRMSK, ~enabled_intrs); + 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; @@ -3209,6 +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); @@ -3222,21 +3481,23 @@ static void gen8_enable_rps(struct drm_device *dev) /* 3: Enable RC6 */ if (intel_enable_rc6(dev) & INTEL_RC6_ENABLE) rc6_mask = GEN6_RC_CTL_RC6_ENABLE; - DRM_INFO("RC6 %s\n", (rc6_mask & GEN6_RC_CTL_RC6_ENABLE) ? "on" : "off"); + intel_print_rc6_info(dev, rc6_mask); I915_WRITE(GEN6_RC_CONTROL, GEN6_RC_CTL_HW_ENABLE | - GEN6_RC_CTL_EI_MODE(1) | - rc6_mask); + GEN6_RC_CTL_EI_MODE(1) | + 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 */ /* 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%*/ @@ -3245,11 +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); @@ -3258,7 +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); } @@ -3266,10 +3531,10 @@ 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, rc6_mask = 0; + u32 rc6vids, pcu_mbox = 0, rc6_mask = 0; u32 gtfifodbg; int rc6_mode; int i, ret; @@ -3295,13 +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); - /* In units of 50MHz */ - dev_priv->rps.hw_max = dev_priv->rps.max_delay = rp_state_cap & 0xff; - dev_priv->rps.min_delay = (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; + parse_rp_state_cap(dev_priv, rp_state_cap); /* disable the counters and set deterministic thresholds */ I915_WRITE(GEN6_RC_CONTROL, 0); @@ -3350,21 +3609,19 @@ static void gen6_enable_rps(struct drm_device *dev) I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10); ret = sandybridge_pcode_write(dev_priv, GEN6_PCODE_WRITE_MIN_FREQ_TABLE, 0); - if (!ret) { - pcu_mbox = 0; - 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, - (pcu_mbox & 0xff) * 50); - dev_priv->rps.hw_max = pcu_mbox & 0xff; - } - } else { + if (ret) DRM_DEBUG_DRIVER("Failed to set the min frequency\n"); + + 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_freq_softlimit & 0xff) * 50, + (pcu_mbox & 0xff) * 50); + 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); @@ -3385,7 +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; @@ -3420,9 +3677,9 @@ 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) { @@ -3455,6 +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; @@ -3485,6 +3754,15 @@ int valleyview_rps_min_freq(struct drm_i915_private *dev_priv) return vlv_punit_read(dev_priv, PUNIT_REG_GPU_LFM) & 0xff; } +/* Check that the pctx buffer wasn't move under us. */ +static void valleyview_check_pctx(struct drm_i915_private *dev_priv) +{ + unsigned long pctx_addr = I915_READ(VLV_PCBR) & ~4095; + + WARN_ON(pctx_addr != dev_priv->mm.stolen_base + + dev_priv->vlv_pctx->stolen->start); +} + static void valleyview_setup_pctx(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -3529,15 +3807,67 @@ out: dev_priv->vlv_pctx = pctx; } +static void valleyview_cleanup_pctx(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + if (WARN_ON(!dev_priv->vlv_pctx)) + return; + + drm_gem_object_unreference(&dev_priv->vlv_pctx->base); + 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; WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock)); + valleyview_check_pctx(dev_priv); + if ((gtfifodbg = I915_READ(GTFIFODBG))) { DRM_DEBUG_DRIVER("GT fifo had a previous error %x\n", gtfifodbg); @@ -3588,32 +3918,16 @@ 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); - - dev_priv->rps.max_delay = valleyview_rps_max_freq(dev_priv); - dev_priv->rps.hw_max = dev_priv->rps.max_delay; - DRM_DEBUG_DRIVER("max GPU freq: %d MHz (%u)\n", - vlv_gpu_freq(dev_priv, dev_priv->rps.max_delay), - dev_priv->rps.max_delay); - - dev_priv->rps.rpe_delay = 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); - - dev_priv->rps.min_delay = 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_delay), - dev_priv->rps.min_delay); + vlv_gpu_freq(dev_priv, dev_priv->rps.cur_freq), + dev_priv->rps.cur_freq); 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); gen6_enable_rps_interrupts(dev); @@ -3625,13 +3939,13 @@ void ironlake_teardown_rc6(struct drm_device *dev) struct drm_i915_private *dev_priv = dev->dev_private; if (dev_priv->ips.renderctx) { - i915_gem_object_unpin(dev_priv->ips.renderctx); + i915_gem_object_ggtt_unpin(dev_priv->ips.renderctx); drm_gem_object_unreference(&dev_priv->ips.renderctx->base); dev_priv->ips.renderctx = NULL; } if (dev_priv->ips.pwrctx) { - i915_gem_object_unpin(dev_priv->ips.pwrctx); + i915_gem_object_ggtt_unpin(dev_priv->ips.pwrctx); drm_gem_object_unreference(&dev_priv->ips.pwrctx->base); dev_priv->ips.pwrctx = NULL; } @@ -3677,7 +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; @@ -3735,7 +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) @@ -3823,9 +4137,10 @@ static unsigned long __i915_chipset_val(struct drm_i915_private *dev_priv) unsigned long i915_chipset_val(struct drm_i915_private *dev_priv) { + struct drm_device *dev = dev_priv->dev; unsigned long val; - if (dev_priv->info->gen != 5) + if (INTEL_INFO(dev)->gen != 5) return 0; spin_lock_irq(&mchdev_lock); @@ -3854,6 +4169,7 @@ unsigned long i915_mch_val(struct drm_i915_private *dev_priv) static u16 pvid_to_extvid(struct drm_i915_private *dev_priv, u8 pxvid) { + struct drm_device *dev = dev_priv->dev; static const struct v_table { u16 vd; /* in .1 mil */ u16 vm; /* in .1 mil */ @@ -3987,7 +4303,7 @@ static u16 pvid_to_extvid(struct drm_i915_private *dev_priv, u8 pxvid) { 16000, 14875, }, { 16125, 15000, }, }; - if (dev_priv->info->is_mobile) + if (INTEL_INFO(dev)->is_mobile) return v_table[pxvid].vm; else return v_table[pxvid].vd; @@ -4030,7 +4346,9 @@ static void __i915_update_gfx_val(struct drm_i915_private *dev_priv) void i915_update_gfx_val(struct drm_i915_private *dev_priv) { - if (dev_priv->info->gen != 5) + struct drm_device *dev = dev_priv->dev; + + if (INTEL_INFO(dev)->gen != 5) return; spin_lock_irq(&mchdev_lock); @@ -4047,7 +4365,7 @@ 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); @@ -4079,9 +4397,10 @@ static unsigned long __i915_gfx_val(struct drm_i915_private *dev_priv) unsigned long i915_gfx_val(struct drm_i915_private *dev_priv) { + struct drm_device *dev = dev_priv->dev; unsigned long val; - if (dev_priv->info->gen != 5) + if (INTEL_INFO(dev)->gen != 5) return 0; spin_lock_irq(&mchdev_lock); @@ -4184,7 +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; @@ -4270,6 +4589,7 @@ void intel_gpu_ips_teardown(void) i915_mch_dev = NULL; spin_unlock_irq(&mchdev_lock); } + static void intel_init_emon(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -4341,6 +4661,20 @@ static void intel_init_emon(struct drm_device *dev) dev_priv->ips.corr = (lcfuse & LCFUSE_HIV_MASK); } +void intel_init_gt_powersave(struct drm_device *dev) +{ + i915.enable_rc6 = sanitize_rc6_option(dev, i915.enable_rc6); + + if (IS_VALLEYVIEW(dev)) + valleyview_init_gt_powersave(dev); +} + +void intel_cleanup_gt_powersave(struct drm_device *dev) +{ + if (IS_VALLEYVIEW(dev)) + valleyview_cleanup_gt_powersave(dev); +} + void intel_disable_gt_powersave(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -4351,8 +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)) @@ -4377,13 +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) @@ -4391,22 +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)) { - if (IS_VALLEYVIEW(dev)) - valleyview_setup_pctx(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; @@ -4512,6 +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); @@ -4587,6 +4944,20 @@ 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. + * + * 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(GEN6_GT_MODE, + GEN6_WIZ_HASHING_MASK | GEN6_WIZ_HASHING_16x4); + ilk_init_lp_watermarks(dev); I915_WRITE(CACHE_MODE_0, @@ -4607,17 +4978,24 @@ static void gen6_init_clock_gating(struct drm_device *dev) * According to the spec, bit 11 (RCCUNIT) must also be set, * but we didn't debug actual testcases to find it out. * - * Also apply WaDisableVDSUnitClockGating:snb and - * WaDisableRCPBUnitClockGating:snb. + * WaDisableRCCUnitClockGating:snb + * WaDisableRCPBUnitClockGating:snb */ I915_WRITE(GEN6_UCGCTL2, - GEN7_VDSUNIT_CLOCK_GATE_DISABLE | GEN6_RCPBUNIT_CLOCK_GATE_DISABLE | GEN6_RCCUNIT_CLOCK_GATE_DISABLE); - /* Bspec says we need to always set all mask bits. */ - I915_WRITE(_3D_CHICKEN3, (0xFFFF << 16) | - _3D_CHICKEN3_SF_DISABLE_FASTCLIP_CULL); + /* WaStripsFansDisableFastClipPerformanceFix:snb */ + I915_WRITE(_3D_CHICKEN3, + _MASKED_BIT_ENABLE(_3D_CHICKEN3_SF_DISABLE_FASTCLIP_CULL)); + + /* + * Bspec says: + * "This bit must be set if 3DSTATE_CLIP clip mode is set to normal and + * 3DSTATE_SF number of SF output attributes is more than 16." + */ + I915_WRITE(_3D_CHICKEN3, + _MASKED_BIT_ENABLE(_3D_CHICKEN3_SF_DISABLE_PIPELINED_ATTR_FETCH)); /* * According to the spec the following bits should be @@ -4643,11 +5021,6 @@ static void gen6_init_clock_gating(struct drm_device *dev) g4x_disable_trickle_feed(dev); - /* The default value should be 0x200 according to docs, but the two - * platforms I checked have a 0 for this. (Maybe BIOS overrides?) */ - I915_WRITE(GEN6_GT_MODE, _MASKED_BIT_DISABLE(0xffff)); - I915_WRITE(GEN6_GT_MODE, _MASKED_BIT_ENABLE(GEN6_GT_MODE_HI)); - cpt_init_clock_gating(dev); gen6_check_mch_setup(dev); @@ -4657,14 +5030,17 @@ static void gen7_setup_fixed_func_scheduler(struct drm_i915_private *dev_priv) { uint32_t reg = I915_READ(GEN7_FF_THREAD_MODE); + /* + * WaVSThreadDispatchOverride:ivb,vlv + * + * This actually overrides the dispatch + * mode for all thread types. + */ reg &= ~GEN7_FF_SCHED_MASK; reg |= GEN7_FF_TS_SCHED_HW; reg |= GEN7_FF_VS_SCHED_HW; reg |= GEN7_FF_DS_SCHED_HW; - if (IS_HASWELL(dev_priv->dev)) - reg &= ~GEN7_FF_VS_REF_CNT_FFME; - I915_WRITE(GEN7_FF_THREAD_MODE, reg); } @@ -4702,7 +5078,7 @@ static void lpt_suspend_hw(struct drm_device *dev) static void gen8_init_clock_gating(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - enum pipe i; + enum pipe pipe; I915_WRITE(WM3_LP_ILK, 0); I915_WRITE(WM2_LP_ILK, 0); @@ -4711,8 +5087,19 @@ static void gen8_init_clock_gating(struct drm_device *dev) /* FIXME(BDW): Check all the w/a, some might only apply to * pre-production hw. */ - WARN(!i915_preliminary_hw_support, - "GEN8_CENTROID_PIXEL_OPT_DIS not be needed for production\n"); + /* 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, @@ -4728,6 +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); @@ -4736,10 +5127,10 @@ static void gen8_init_clock_gating(struct drm_device *dev) I915_READ(CHICKEN_PAR1_1) | DPA_MASK_VBLANK_SRD); /* WaPsrDPRSUnmaskVBlankInSRD:bdw */ - for_each_pipe(i) { - I915_WRITE(CHICKEN_PIPESL_1(i), - I915_READ(CHICKEN_PIPESL_1(i) | - DPRS_MASK_VBLANK_SRD)); + for_each_pipe(pipe) { + I915_WRITE(CHICKEN_PIPESL_1(pipe), + I915_READ(CHICKEN_PIPESL_1(pipe)) | + BDW_DPRS_MASK_VBLANK_SRD); } /* Use Force Non-Coherent whenever executing a 3D context. This is a @@ -4755,6 +5146,28 @@ static void gen8_init_clock_gating(struct drm_device *dev) 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)); + + /* WaDisableSDEUnitClockGating:bdw */ + 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)); } static void haswell_init_clock_gating(struct drm_device *dev) @@ -4763,21 +5176,6 @@ static void haswell_init_clock_gating(struct drm_device *dev) ilk_init_lp_watermarks(dev); - /* According to the spec, bit 13 (RCZUNIT) must be set on IVB. - * This implements the WaDisableRCZUnitClockGating:hsw workaround. - */ - I915_WRITE(GEN6_UCGCTL2, GEN6_RCZUNIT_CLOCK_GATE_DISABLE); - - /* Apply the WaDisableRHWOOptimizationForRenderHang:hsw workaround. */ - I915_WRITE(GEN7_COMMON_SLICE_CHICKEN1, - GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC); - - /* WaApplyL3ControlAndL3ChickenMode:hsw */ - I915_WRITE(GEN7_L3CNTLREG1, - GEN7_WA_FOR_GEN7_L3_CONTROL); - I915_WRITE(GEN7_L3_CHICKEN_MODE_REGISTER, - GEN7_WA_L3_CHICKEN_MODE); - /* L3 caching of data atomics doesn't work -- disable it. */ I915_WRITE(HSW_SCRATCH1, HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE); I915_WRITE(HSW_ROW_CHICKEN3, @@ -4789,12 +5187,31 @@ static void haswell_init_clock_gating(struct drm_device *dev) GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB); /* WaVSRefCountFullforceMissDisable:hsw */ - gen7_setup_fixed_func_scheduler(dev_priv); + 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)); /* WaDisable4x2SubspanOptimization:hsw */ I915_WRITE(CACHE_MODE_1, _MASKED_BIT_ENABLE(PIXEL_SUBSPAN_COLLECT_OPT_DISABLE)); + /* + * 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); + /* WaSwitchSolVfFArbitrationPriority:hsw */ I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL); @@ -4827,9 +5244,9 @@ static void ivybridge_init_clock_gating(struct drm_device *dev) if (IS_IVB_GT1(dev)) I915_WRITE(GEN7_HALF_SLICE_CHICKEN1, _MASKED_BIT_ENABLE(GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE)); - else - I915_WRITE(GEN7_HALF_SLICE_CHICKEN1_GT2, - _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, @@ -4843,31 +5260,24 @@ static void ivybridge_init_clock_gating(struct drm_device *dev) if (IS_IVB_GT1(dev)) I915_WRITE(GEN7_ROW_CHICKEN2, _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE)); - else + else { + /* must write both registers */ + I915_WRITE(GEN7_ROW_CHICKEN2, + _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE)); I915_WRITE(GEN7_ROW_CHICKEN2_GT2, _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE)); - + } /* WaForceL3Serialization:ivb */ I915_WRITE(GEN7_L3SQCREG4, I915_READ(GEN7_L3SQCREG4) & ~L3SQ_URB_READ_CAM_MATCH_DISABLE); - /* According to the BSpec vol1g, bit 12 (RCPBUNIT) clock - * gating disable must be set. Failure to set it results in - * flickering pixels due to Z write ordering failures after - * some amount of runtime in the Mesa "fire" demo, and Unigine - * Sanctuary and Tropics, and apparently anything else with - * alpha test or pixel discard. - * - * According to the spec, bit 11 (RCCUNIT) must also be set, - * but we didn't debug actual testcases to find it out. - * + /* * According to the spec, bit 13 (RCZUNIT) must be set on IVB. * This implements the WaDisableRCZUnitClockGating:ivb workaround. */ I915_WRITE(GEN6_UCGCTL2, - GEN6_RCZUNIT_CLOCK_GATE_DISABLE | - GEN6_RCCUNIT_CLOCK_GATE_DISABLE); + GEN6_RCZUNIT_CLOCK_GATE_DISABLE); /* This is required by WaCatErrorRejectionIssue:ivb */ I915_WRITE(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG, @@ -4876,13 +5286,29 @@ static void ivybridge_init_clock_gating(struct drm_device *dev) g4x_disable_trickle_feed(dev); - /* WaVSRefCountFullforceMissDisable:ivb */ gen7_setup_fixed_func_scheduler(dev_priv); + if (0) { /* causes HiZ corruption on ivb:gt1 */ + /* enable HiZ Raw Stall Optimization */ + I915_WRITE(CACHE_MODE_0_GEN7, + _MASKED_BIT_DISABLE(HIZ_RAW_STALL_OPT_DISABLE)); + } + /* WaDisable4x2SubspanOptimization:ivb */ I915_WRITE(CACHE_MODE_1, _MASKED_BIT_ENABLE(PIXEL_SUBSPAN_COLLECT_OPT_DISABLE)); + /* + * 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); + snpcr = I915_READ(GEN6_MBCUNIT_SNPCR); snpcr &= ~GEN6_MBC_SNPCR_MASK; snpcr |= GEN6_MBC_SNPCR_MED; @@ -4904,13 +5330,11 @@ static void valleyview_init_clock_gating(struct drm_device *dev) mutex_unlock(&dev_priv->rps.hw_lock); switch ((val >> 6) & 3) { case 0: - dev_priv->mem_freq = 800; - break; case 1: - dev_priv->mem_freq = 1066; + dev_priv->mem_freq = 800; break; case 2: - dev_priv->mem_freq = 1333; + dev_priv->mem_freq = 1066; break; case 3: dev_priv->mem_freq = 1333; @@ -4918,6 +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 */ @@ -4929,18 +5357,14 @@ static void valleyview_init_clock_gating(struct drm_device *dev) CHICKEN3_DGMG_REQ_OUT_FIX_DISABLE | CHICKEN3_DGMG_DONE_FIX_DISABLE); + /* WaPsdDispatchEnable:vlv */ /* WaDisablePSDDualDispatchEnable:vlv */ I915_WRITE(GEN7_HALF_SLICE_CHICKEN1, _MASKED_BIT_ENABLE(GEN7_MAX_PS_THREAD_DEP | GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE)); - /* Apply the WaDisableRHWOOptimizationForRenderHang:vlv workaround. */ - I915_WRITE(GEN7_COMMON_SLICE_CHICKEN1, - GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC); - - /* WaApplyL3ControlAndL3ChickenMode:vlv */ - I915_WRITE(GEN7_L3CNTLREG1, I915_READ(GEN7_L3CNTLREG1) | GEN7_L3AGDIS); - I915_WRITE(GEN7_L3_CHICKEN_MODE_REGISTER, GEN7_WA_L3_CHICKEN_MODE); + /* 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) & @@ -4955,51 +5379,95 @@ static void valleyview_init_clock_gating(struct drm_device *dev) I915_READ(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) | GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB); - /* According to the BSpec vol1g, bit 12 (RCPBUNIT) clock - * gating disable must be set. Failure to set it results in - * flickering pixels due to Z write ordering failures after - * some amount of runtime in the Mesa "fire" demo, and Unigine - * Sanctuary and Tropics, and apparently anything else with - * alpha test or pixel discard. - * - * According to the spec, bit 11 (RCCUNIT) must also be set, - * but we didn't debug actual testcases to find it out. - * + gen7_setup_fixed_func_scheduler(dev_priv); + + /* * According to the spec, bit 13 (RCZUNIT) must be set on IVB. * This implements the WaDisableRCZUnitClockGating:vlv workaround. - * - * Also apply WaDisableVDSUnitClockGating:vlv and - * WaDisableRCPBUnitClockGating:vlv. */ I915_WRITE(GEN6_UCGCTL2, - GEN7_VDSUNIT_CLOCK_GATE_DISABLE | - GEN7_TDLUNIT_CLOCK_GATE_DISABLE | - GEN6_RCZUNIT_CLOCK_GATE_DISABLE | - GEN6_RCPBUNIT_CLOCK_GATE_DISABLE | - GEN6_RCCUNIT_CLOCK_GATE_DISABLE); + GEN6_RCZUNIT_CLOCK_GATE_DISABLE); - 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); + /* + * BSpec says this must be set, even though + * WaDisable4x2SubspanOptimization isn't listed for VLV. + */ I915_WRITE(CACHE_MODE_1, _MASKED_BIT_ENABLE(PIXEL_SUBSPAN_COLLECT_OPT_DISABLE)); /* + * WaIncreaseL3CreditsForVLVB0:vlv + * This is the hardware default actually. + */ + I915_WRITE(GEN7_L3SQCREG1, VLV_B0_WA_L3SQCREG1_VALUE); + + /* * WaDisableVLVClockGating_VBIIssue:vlv * Disable clock gating on th GCFG unit to prevent a delay * in the reporting of vblank events. */ - I915_WRITE(VLV_GUNIT_CLOCK_GATE, 0xffffffff); + 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; - /* Conservative clock gating settings for now */ - I915_WRITE(0x9400, 0xffffffff); - I915_WRITE(0x9404, 0xffffffff); - I915_WRITE(0x9408, 0xffffffff); - I915_WRITE(0x940c, 0xffffffff); - I915_WRITE(0x9410, 0xffffffff); - I915_WRITE(0x9414, 0xffffffff); - I915_WRITE(0x9418, 0xffffffff); + 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) @@ -5023,6 +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); } @@ -5037,6 +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) @@ -5051,6 +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) @@ -5067,6 +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) @@ -5074,6 +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) @@ -5114,35 +5601,49 @@ void intel_suspend_hw(struct drm_device *dev) * enable it, so check if it's enabled and also check if we've requested it to * be enabled. */ -static bool hsw_power_well_enabled(struct drm_device *dev, +static bool hsw_power_well_enabled(struct drm_i915_private *dev_priv, struct i915_power_well *power_well) { - struct drm_i915_private *dev_priv = dev->dev_private; - return I915_READ(HSW_PWR_WELL_DRIVER) == (HSW_PWR_WELL_ENABLE_REQUEST | HSW_PWR_WELL_STATE_ENABLED); } -bool intel_display_power_enabled_sw(struct drm_device *dev, +bool intel_display_power_enabled_sw(struct drm_i915_private *dev_priv, enum intel_display_power_domain domain) { - struct drm_i915_private *dev_priv = dev->dev_private; 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_device *dev, +bool intel_display_power_enabled(struct drm_i915_private *dev_priv, enum intel_display_power_domain domain) { - struct drm_i915_private *dev_priv = dev->dev_private; 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; @@ -5152,7 +5653,7 @@ bool intel_display_power_enabled(struct drm_device *dev, if (power_well->always_on) continue; - if (!power_well->is_enabled(dev, power_well)) { + if (!power_well->ops->is_enabled(dev_priv, power_well)) { is_enabled = false; break; } @@ -5162,6 +5663,12 @@ bool intel_display_power_enabled(struct drm_device *dev, return is_enabled; } +/* + * Starting with Haswell, we have a "Power Down Well" that can be turned off + * when not needed anymore. We have 4 registers that can request the power well + * to be enabled, and it will only be disabled if none of the registers is + * requesting it to be enabled. + */ static void hsw_power_well_post_enable(struct drm_i915_private *dev_priv) { struct drm_device *dev = dev_priv->dev; @@ -5198,35 +5705,12 @@ static void hsw_power_well_post_enable(struct drm_i915_private *dev_priv) } } -static void hsw_power_well_post_disable(struct drm_i915_private *dev_priv) -{ - struct drm_device *dev = dev_priv->dev; - enum pipe p; - 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(p) - if (p != PIPE_A) - dev->vblank[p].last = 0; - spin_unlock_irqrestore(&dev->vbl_lock, irqflags); -} - -static void hsw_set_power_well(struct drm_device *dev, +static void hsw_set_power_well(struct drm_i915_private *dev_priv, struct i915_power_well *power_well, bool enable) { - struct drm_i915_private *dev_priv = dev->dev_private; bool is_enabled, enable_requested; uint32_t tmp; - WARN_ON(dev_priv->pc8.enabled); - tmp = I915_READ(HSW_PWR_WELL_DRIVER); is_enabled = tmp & HSW_PWR_WELL_STATE_ENABLED; enable_requested = tmp & HSW_PWR_WELL_ENABLE_REQUEST; @@ -5249,61 +5733,267 @@ static void hsw_set_power_well(struct drm_device *dev, 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); } } } -static void __intel_power_well_get(struct drm_device *dev, +static void hsw_power_well_sync_hw(struct drm_i915_private *dev_priv, struct i915_power_well *power_well) { - struct drm_i915_private *dev_priv = dev->dev_private; + hsw_set_power_well(dev_priv, power_well, power_well->count > 0); + + /* + * We're taking over the BIOS, so clear any requests made by it since + * the driver is in charge now. + */ + if (I915_READ(HSW_PWR_WELL_BIOS) & HSW_PWR_WELL_ENABLE_REQUEST) + I915_WRITE(HSW_PWR_WELL_BIOS, 0); +} + +static void hsw_power_well_enable(struct drm_i915_private *dev_priv, + struct i915_power_well *power_well) +{ + hsw_set_power_well(dev_priv, power_well, true); +} + +static void hsw_power_well_disable(struct drm_i915_private *dev_priv, + struct i915_power_well *power_well) +{ + hsw_set_power_well(dev_priv, power_well, false); +} + +static void i9xx_always_on_power_well_noop(struct drm_i915_private *dev_priv, + struct i915_power_well *power_well) +{ +} + +static bool i9xx_always_on_power_well_enabled(struct drm_i915_private *dev_priv, + struct i915_power_well *power_well) +{ + return true; +} - if (!power_well->count++ && power_well->set) { - hsw_disable_package_c8(dev_priv); - power_well->set(dev, power_well, true); +void __vlv_set_power_well(struct drm_i915_private *dev_priv, + enum punit_power_well power_well_id, bool enable) +{ + 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) : + PUNIT_PWRGT_PWR_GATE(power_well_id); + + mutex_lock(&dev_priv->rps.hw_lock); + +#define COND \ + ((vlv_punit_read(dev_priv, PUNIT_REG_PWRGT_STATUS) & mask) == state) + + if (COND) + goto out; + + ctrl = vlv_punit_read(dev_priv, PUNIT_REG_PWRGT_CTRL); + ctrl &= ~mask; + ctrl |= state; + vlv_punit_write(dev_priv, PUNIT_REG_PWRGT_CTRL, ctrl); + + if (wait_for(COND, 100)) + DRM_ERROR("timout setting power well state %08x (%08x)\n", + state, + vlv_punit_read(dev_priv, PUNIT_REG_PWRGT_CTRL)); + +#undef COND + +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 __intel_power_well_put(struct drm_device *dev, +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, struct i915_power_well *power_well) { - struct drm_i915_private *dev_priv = dev->dev_private; + vlv_set_power_well(dev_priv, power_well, power_well->count > 0); +} + +static void vlv_power_well_enable(struct drm_i915_private *dev_priv, + struct i915_power_well *power_well) +{ + vlv_set_power_well(dev_priv, power_well, true); +} + +static void vlv_power_well_disable(struct drm_i915_private *dev_priv, + struct i915_power_well *power_well) +{ + vlv_set_power_well(dev_priv, power_well, false); +} - WARN_ON(!power_well->count); +static bool vlv_power_well_enabled(struct drm_i915_private *dev_priv, + struct i915_power_well *power_well) +{ + int power_well_id = power_well->data; + bool enabled = false; + u32 mask; + u32 state; + u32 ctrl; - if (!--power_well->count && power_well->set && - i915_disable_power_well) { - power_well->set(dev, power_well, false); - hsw_enable_package_c8(dev_priv); + mask = PUNIT_PWRGT_MASK(power_well_id); + ctrl = PUNIT_PWRGT_PWR_ON(power_well_id); + + mutex_lock(&dev_priv->rps.hw_lock); + + state = vlv_punit_read(dev_priv, PUNIT_REG_PWRGT_STATUS) & mask; + /* + * We only ever set the power-on and power-gate states, anything + * else is unexpected. + */ + WARN_ON(state != PUNIT_PWRGT_PWR_ON(power_well_id) && + state != PUNIT_PWRGT_PWR_GATE(power_well_id)); + if (state == ctrl) + enabled = true; + + /* + * A transient state at this point would mean some unexpected party + * is poking at the power controls too. + */ + ctrl = vlv_punit_read(dev_priv, PUNIT_REG_PWRGT_CTRL) & mask; + WARN_ON(ctrl != state); + + mutex_unlock(&dev_priv->rps.hw_lock); + + return enabled; +} + +static void vlv_display_power_well_enable(struct drm_i915_private *dev_priv, + struct i915_power_well *power_well) +{ + WARN_ON_ONCE(power_well->data != PUNIT_POWER_WELL_DISP2D); + + vlv_set_power_well(dev_priv, power_well, true); + + spin_lock_irq(&dev_priv->irq_lock); + valleyview_enable_display_irqs(dev_priv); + spin_unlock_irq(&dev_priv->irq_lock); + + /* + * During driver initialization/resume we can avoid restoring the + * part of the HW/SW state that will be inited anyway explicitly. + */ + if (dev_priv->power_domains.initializing) + return; + + intel_hpd_init(dev_priv->dev); + + i915_redisable_vga_power_on(dev_priv->dev); +} + +static void vlv_display_power_well_disable(struct drm_i915_private *dev_priv, + struct i915_power_well *power_well) +{ + WARN_ON_ONCE(power_well->data != PUNIT_POWER_WELL_DISP2D); + + spin_lock_irq(&dev_priv->irq_lock); + valleyview_disable_display_irqs(dev_priv); + spin_unlock_irq(&dev_priv->irq_lock); + + vlv_set_power_well(dev_priv, power_well, false); +} + +static void check_power_well_state(struct drm_i915_private *dev_priv, + struct i915_power_well *power_well) +{ + bool enabled = power_well->ops->is_enabled(dev_priv, power_well); + + if (power_well->always_on || !i915.disable_power_well) { + if (!enabled) + goto mismatch; + + return; } + + if (enabled != (power_well->count > 0)) + goto mismatch; + + return; + +mismatch: + WARN(1, "state mismatch for '%s' (always_on %d hw state %d use-count %d disable_power_well %d\n", + power_well->name, power_well->always_on, enabled, + power_well->count, i915.disable_power_well); } -void intel_display_power_get(struct drm_device *dev, +void intel_display_power_get(struct drm_i915_private *dev_priv, enum intel_display_power_domain domain) { - struct drm_i915_private *dev_priv = dev->dev_private; struct i915_power_domains *power_domains; struct i915_power_well *power_well; int i; + intel_runtime_pm_get(dev_priv); + power_domains = &dev_priv->power_domains; mutex_lock(&power_domains->lock); - for_each_power_well(i, power_well, BIT(domain), power_domains) - __intel_power_well_get(dev, power_well); + for_each_power_well(i, power_well, BIT(domain), power_domains) { + if (!power_well->count++) { + DRM_DEBUG_KMS("enabling %s\n", power_well->name); + power_well->ops->enable(dev_priv, power_well); + } + + check_power_well_state(dev_priv, power_well); + } power_domains->domain_use_count[domain]++; mutex_unlock(&power_domains->lock); } -void intel_display_power_put(struct drm_device *dev, +void intel_display_power_put(struct drm_i915_private *dev_priv, enum intel_display_power_domain domain) { - struct drm_i915_private *dev_priv = dev->dev_private; struct i915_power_domains *power_domains; struct i915_power_well *power_well; int i; @@ -5315,10 +6005,20 @@ void intel_display_power_put(struct drm_device *dev, WARN_ON(!power_domains->domain_use_count[domain]); power_domains->domain_use_count[domain]--; - for_each_power_well_rev(i, power_well, BIT(domain), power_domains) - __intel_power_well_put(dev, power_well); + for_each_power_well_rev(i, power_well, BIT(domain), power_domains) { + WARN_ON(!power_well->count); + + if (!--power_well->count && i915.disable_power_well) { + DRM_DEBUG_KMS("disabling %s\n", power_well->name); + power_well->ops->disable(dev_priv, power_well); + } + + check_power_well_state(dev_priv, power_well); + } mutex_unlock(&power_domains->lock); + + intel_runtime_pm_put(dev_priv); } static struct i915_power_domains *hsw_pwr; @@ -5333,7 +6033,7 @@ void i915_request_power_well(void) dev_priv = container_of(hsw_pwr, struct drm_i915_private, power_domains); - intel_display_power_get(dev_priv->dev, POWER_DOMAIN_AUDIO); + intel_display_power_get(dev_priv, POWER_DOMAIN_AUDIO); } EXPORT_SYMBOL_GPL(i915_request_power_well); @@ -5347,29 +6047,99 @@ void i915_release_power_well(void) dev_priv = container_of(hsw_pwr, struct drm_i915_private, power_domains); - intel_display_power_put(dev_priv->dev, POWER_DOMAIN_AUDIO); + intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO); } EXPORT_SYMBOL_GPL(i915_release_power_well); +#define POWER_DOMAIN_MASK (BIT(POWER_DOMAIN_NUM) - 1) + +#define HSW_ALWAYS_ON_POWER_DOMAINS ( \ + BIT(POWER_DOMAIN_PIPE_A) | \ + BIT(POWER_DOMAIN_TRANSCODER_EDP) | \ + BIT(POWER_DOMAIN_PORT_DDI_A_2_LANES) | \ + BIT(POWER_DOMAIN_PORT_DDI_A_4_LANES) | \ + BIT(POWER_DOMAIN_PORT_DDI_B_2_LANES) | \ + BIT(POWER_DOMAIN_PORT_DDI_B_4_LANES) | \ + BIT(POWER_DOMAIN_PORT_DDI_C_2_LANES) | \ + BIT(POWER_DOMAIN_PORT_DDI_C_4_LANES) | \ + BIT(POWER_DOMAIN_PORT_DDI_D_2_LANES) | \ + BIT(POWER_DOMAIN_PORT_DDI_D_4_LANES) | \ + BIT(POWER_DOMAIN_PORT_CRT) | \ + BIT(POWER_DOMAIN_INIT)) +#define HSW_DISPLAY_POWER_DOMAINS ( \ + (POWER_DOMAIN_MASK & ~HSW_ALWAYS_ON_POWER_DOMAINS) | \ + BIT(POWER_DOMAIN_INIT)) + +#define BDW_ALWAYS_ON_POWER_DOMAINS ( \ + HSW_ALWAYS_ON_POWER_DOMAINS | \ + BIT(POWER_DOMAIN_PIPE_A_PANEL_FITTER)) +#define BDW_DISPLAY_POWER_DOMAINS ( \ + (POWER_DOMAIN_MASK & ~BDW_ALWAYS_ON_POWER_DOMAINS) | \ + BIT(POWER_DOMAIN_INIT)) + +#define VLV_ALWAYS_ON_POWER_DOMAINS BIT(POWER_DOMAIN_INIT) +#define VLV_DISPLAY_POWER_DOMAINS POWER_DOMAIN_MASK + +#define VLV_DPIO_CMN_BC_POWER_DOMAINS ( \ + BIT(POWER_DOMAIN_PORT_DDI_B_2_LANES) | \ + BIT(POWER_DOMAIN_PORT_DDI_B_4_LANES) | \ + BIT(POWER_DOMAIN_PORT_DDI_C_2_LANES) | \ + BIT(POWER_DOMAIN_PORT_DDI_C_4_LANES) | \ + BIT(POWER_DOMAIN_PORT_CRT) | \ + BIT(POWER_DOMAIN_INIT)) + +#define VLV_DPIO_TX_B_LANES_01_POWER_DOMAINS ( \ + BIT(POWER_DOMAIN_PORT_DDI_B_2_LANES) | \ + BIT(POWER_DOMAIN_PORT_DDI_B_4_LANES) | \ + BIT(POWER_DOMAIN_INIT)) + +#define VLV_DPIO_TX_B_LANES_23_POWER_DOMAINS ( \ + BIT(POWER_DOMAIN_PORT_DDI_B_4_LANES) | \ + BIT(POWER_DOMAIN_INIT)) + +#define VLV_DPIO_TX_C_LANES_01_POWER_DOMAINS ( \ + BIT(POWER_DOMAIN_PORT_DDI_C_2_LANES) | \ + BIT(POWER_DOMAIN_PORT_DDI_C_4_LANES) | \ + BIT(POWER_DOMAIN_INIT)) + +#define VLV_DPIO_TX_C_LANES_23_POWER_DOMAINS ( \ + BIT(POWER_DOMAIN_PORT_DDI_C_4_LANES) | \ + BIT(POWER_DOMAIN_INIT)) + +static const struct i915_power_well_ops i9xx_always_on_power_well_ops = { + .sync_hw = i9xx_always_on_power_well_noop, + .enable = i9xx_always_on_power_well_noop, + .disable = i9xx_always_on_power_well_noop, + .is_enabled = i9xx_always_on_power_well_enabled, +}; + static struct i915_power_well i9xx_always_on_power_well[] = { { .name = "always-on", .always_on = 1, .domains = POWER_DOMAIN_MASK, + .ops = &i9xx_always_on_power_well_ops, }, }; +static const struct i915_power_well_ops hsw_power_well_ops = { + .sync_hw = hsw_power_well_sync_hw, + .enable = hsw_power_well_enable, + .disable = hsw_power_well_disable, + .is_enabled = hsw_power_well_enabled, +}; + static struct i915_power_well hsw_power_wells[] = { { .name = "always-on", .always_on = 1, .domains = HSW_ALWAYS_ON_POWER_DOMAINS, + .ops = &i9xx_always_on_power_well_ops, }, { .name = "display", - .domains = POWER_DOMAIN_MASK & ~HSW_ALWAYS_ON_POWER_DOMAINS, - .is_enabled = hsw_power_well_enabled, - .set = hsw_set_power_well, + .domains = HSW_DISPLAY_POWER_DOMAINS, + .ops = &hsw_power_well_ops, }, }; @@ -5378,12 +6148,83 @@ static struct i915_power_well bdw_power_wells[] = { .name = "always-on", .always_on = 1, .domains = BDW_ALWAYS_ON_POWER_DOMAINS, + .ops = &i9xx_always_on_power_well_ops, + }, + { + .name = "display", + .domains = BDW_DISPLAY_POWER_DOMAINS, + .ops = &hsw_power_well_ops, + }, +}; + +static const struct i915_power_well_ops vlv_display_power_well_ops = { + .sync_hw = vlv_power_well_sync_hw, + .enable = vlv_display_power_well_enable, + .disable = vlv_display_power_well_disable, + .is_enabled = vlv_power_well_enabled, +}; + +static const struct i915_power_well_ops vlv_dpio_power_well_ops = { + .sync_hw = vlv_power_well_sync_hw, + .enable = vlv_power_well_enable, + .disable = vlv_power_well_disable, + .is_enabled = vlv_power_well_enabled, +}; + +static struct i915_power_well vlv_power_wells[] = { + { + .name = "always-on", + .always_on = 1, + .domains = VLV_ALWAYS_ON_POWER_DOMAINS, + .ops = &i9xx_always_on_power_well_ops, }, { .name = "display", - .domains = POWER_DOMAIN_MASK & ~BDW_ALWAYS_ON_POWER_DOMAINS, - .is_enabled = hsw_power_well_enabled, - .set = hsw_set_power_well, + .domains = VLV_DISPLAY_POWER_DOMAINS, + .data = PUNIT_POWER_WELL_DISP2D, + .ops = &vlv_display_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 | + VLV_DPIO_TX_C_LANES_01_POWER_DOMAINS | + VLV_DPIO_TX_C_LANES_23_POWER_DOMAINS, + .ops = &vlv_dpio_power_well_ops, + .data = PUNIT_POWER_WELL_DPIO_TX_B_LANES_01, + }, + { + .name = "dpio-tx-b-23", + .domains = VLV_DPIO_TX_B_LANES_01_POWER_DOMAINS | + VLV_DPIO_TX_B_LANES_23_POWER_DOMAINS | + VLV_DPIO_TX_C_LANES_01_POWER_DOMAINS | + VLV_DPIO_TX_C_LANES_23_POWER_DOMAINS, + .ops = &vlv_dpio_power_well_ops, + .data = PUNIT_POWER_WELL_DPIO_TX_B_LANES_23, + }, + { + .name = "dpio-tx-c-01", + .domains = VLV_DPIO_TX_B_LANES_01_POWER_DOMAINS | + VLV_DPIO_TX_B_LANES_23_POWER_DOMAINS | + VLV_DPIO_TX_C_LANES_01_POWER_DOMAINS | + VLV_DPIO_TX_C_LANES_23_POWER_DOMAINS, + .ops = &vlv_dpio_power_well_ops, + .data = PUNIT_POWER_WELL_DPIO_TX_C_LANES_01, + }, + { + .name = "dpio-tx-c-23", + .domains = VLV_DPIO_TX_B_LANES_01_POWER_DOMAINS | + VLV_DPIO_TX_B_LANES_23_POWER_DOMAINS | + VLV_DPIO_TX_C_LANES_01_POWER_DOMAINS | + VLV_DPIO_TX_C_LANES_23_POWER_DOMAINS, + .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, }, }; @@ -5392,9 +6233,8 @@ static struct i915_power_well bdw_power_wells[] = { (power_domains)->power_well_count = ARRAY_SIZE(__power_wells); \ }) -int intel_power_domains_init(struct drm_device *dev) +int intel_power_domains_init(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = dev->dev_private; struct i915_power_domains *power_domains = &dev_priv->power_domains; mutex_init(&power_domains->lock); @@ -5403,12 +6243,14 @@ int intel_power_domains_init(struct drm_device *dev) * The enabling order will be from lower to higher indexed wells, * the disabling order is reversed. */ - if (IS_HASWELL(dev)) { + if (IS_HASWELL(dev_priv->dev)) { set_power_wells(power_domains, hsw_power_wells); hsw_pwr = power_domains; - } else if (IS_BROADWELL(dev)) { + } else if (IS_BROADWELL(dev_priv->dev)) { set_power_wells(power_domains, bdw_power_wells); hsw_pwr = power_domains; + } else if (IS_VALLEYVIEW(dev_priv->dev)) { + set_power_wells(power_domains, vlv_power_wells); } else { set_power_wells(power_domains, i9xx_always_on_power_well); } @@ -5416,58 +6258,42 @@ int intel_power_domains_init(struct drm_device *dev) return 0; } -void intel_power_domains_remove(struct drm_device *dev) +void intel_power_domains_remove(struct drm_i915_private *dev_priv) { hsw_pwr = NULL; } -static void intel_power_domains_resume(struct drm_device *dev) +static void intel_power_domains_resume(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = dev->dev_private; struct i915_power_domains *power_domains = &dev_priv->power_domains; struct i915_power_well *power_well; int i; mutex_lock(&power_domains->lock); - for_each_power_well(i, power_well, POWER_DOMAIN_MASK, power_domains) { - if (power_well->set) - power_well->set(dev, power_well, power_well->count > 0); - } + for_each_power_well(i, power_well, POWER_DOMAIN_MASK, power_domains) + power_well->ops->sync_hw(dev_priv, power_well); mutex_unlock(&power_domains->lock); } -/* - * Starting with Haswell, we have a "Power Down Well" that can be turned off - * when not needed anymore. We have 4 registers that can request the power well - * to be enabled, and it will only be disabled if none of the registers is - * requesting it to be enabled. - */ -void intel_power_domains_init_hw(struct drm_device *dev) +void intel_power_domains_init_hw(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = dev->dev_private; + 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, true); - intel_power_domains_resume(dev); - - if (!(IS_HASWELL(dev) || IS_BROADWELL(dev))) - return; - - /* We're taking over the BIOS, so clear any requests made by it since - * the driver is in charge now. */ - if (I915_READ(HSW_PWR_WELL_BIOS) & HSW_PWR_WELL_ENABLE_REQUEST) - I915_WRITE(HSW_PWR_WELL_BIOS, 0); + intel_display_set_init_power(dev_priv, true); + intel_power_domains_resume(dev_priv); + power_domains->initializing = false; } -/* Disables PC8 so we can use the GMBUS and DP AUX interrupts. */ void intel_aux_display_runtime_get(struct drm_i915_private *dev_priv) { - hsw_disable_package_c8(dev_priv); + intel_runtime_pm_get(dev_priv); } void intel_aux_display_runtime_put(struct drm_i915_private *dev_priv) { - hsw_enable_package_c8(dev_priv); + intel_runtime_pm_put(dev_priv); } void intel_runtime_pm_get(struct drm_i915_private *dev_priv) @@ -5482,6 +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; @@ -5499,16 +6337,25 @@ void intel_init_runtime_pm(struct drm_i915_private *dev_priv) struct drm_device *dev = dev_priv->dev; struct device *device = &dev->pdev->dev; - dev_priv->pm.suspended = false; - if (!HAS_RUNTIME_PM(dev)) return; 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); + + pm_runtime_put_autosuspend(device); } void intel_fini_runtime_pm(struct drm_i915_private *dev_priv) @@ -5519,6 +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); @@ -5560,7 +6410,7 @@ void intel_init_pm(struct drm_device *dev) /* For FIFO watermark updates */ if (HAS_PCH_SPLIT(dev)) { - intel_setup_wm_latency(dev); + ilk_setup_wm_latency(dev); if ((IS_GEN5(dev) && dev_priv->wm.pri_latency[1] && dev_priv->wm.spr_latency[1] && dev_priv->wm.cur_latency[1]) || @@ -5583,6 +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 = @@ -5731,13 +6585,9 @@ void intel_pm_setup(struct drm_device *dev) mutex_init(&dev_priv->rps.hw_lock); - mutex_init(&dev_priv->pc8.lock); - dev_priv->pc8.requirements_met = false; - dev_priv->pc8.gpu_idle = false; - dev_priv->pc8.irqs_disabled = false; - dev_priv->pc8.enabled = false; - dev_priv->pc8.disable_count = 2; /* requirements_met + gpu_idle */ - INIT_DELAYED_WORK(&dev_priv->pc8.enable_work, hsw_enable_pc8_work); INIT_DELAYED_WORK(&dev_priv->rps.delayed_resume_work, intel_gen6_powersave_work); + + dev_priv->pm.suspended = false; + dev_priv->pm.irqs_disabled = false; } |