From 06e668ac91c93eb10bd21dfcc8891493722db29a Mon Sep 17 00:00:00 2001 From: Mika Kuoppala Date: Wed, 16 Dec 2015 19:18:37 +0200 Subject: drm/i915: Apply broader WaRsDisableCoarsePowerGating for guc also commit 344df9809f45 ("drm/i915/skl: Disable coarse power gating up until F0") failed to take into account that the same workaround is used in guc when forcewake is sampled. Wrap the condition check inside a macro and use it in both places to fix the guc side scope. Cc: Dave Gordon Cc: Sagar Arun Kamble Reviewed-by: Sagar Arun Kamble Signed-off-by: Mika Kuoppala Link: http://patchwork.freedesktop.org/patch/msgid/1450286318-6854-1-git-send-email-mika.kuoppala@intel.com --- drivers/gpu/drm/i915/intel_pm.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'drivers/gpu/drm/i915/intel_pm.c') diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 8d0d6f59a72b..02fe081878ad 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -4713,9 +4713,7 @@ static void gen9_enable_rc6(struct drm_device *dev) * 3b: Enable Coarse Power Gating only when RC6 is enabled. * WaRsDisableCoarsePowerGating:skl,bxt - Render/Media PG need to be disabled with RC6. */ - if (IS_BXT_REVID(dev, 0, BXT_REVID_A1) || - ((IS_SKL_GT3(dev) || IS_SKL_GT4(dev)) && - IS_SKL_REVID(dev, 0, SKL_REVID_F0))) + if (NEEDS_WaRsDisableCoarsePowerGating(dev)) I915_WRITE(GEN9_PG_ENABLE, 0); else I915_WRITE(GEN9_PG_ENABLE, (rc6_mask & GEN6_RC_CTL_RC6_ENABLE) ? -- cgit v1.2.3 From ee91a15972cc70efa4d17b4bbdb61ff314528110 Mon Sep 17 00:00:00 2001 From: Matt Roper Date: Thu, 3 Dec 2015 11:37:39 -0800 Subject: drm/i915: Convert hsw_compute_linetime_wm to use in-flight state When watermark calculation was moved up to the atomic check phase, the code was updated to calculate based on in-flight atomic state rather than already-committed state. However the hsw_compute_linetime_wm() didn't get updated and continued to pull values out of the currently-committed CRTC state. On platforms that call this function (HSW/BDW only), this will cause problems when we go to enable the CRTC since we'll pull the current mode (off) rather than the mode we're calculating for and wind up with a divide by zero error. This was an oversight in commit: commit a28170f3389f4e42db95e595b0d86384a79de696 Author: Matt Roper Date: Thu Sep 24 15:53:16 2015 -0700 drm/i915: Calculate ILK-style watermarks during atomic check (v3) Signed-off-by: Matt Roper Link: http://patchwork.freedesktop.org/patch/msgid/1449171462-30763-5-git-send-email-matthew.d.roper@intel.com Signed-off-by: Maarten Lankhorst --- drivers/gpu/drm/i915/intel_pm.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) (limited to 'drivers/gpu/drm/i915/intel_pm.c') diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 02fe081878ad..0f22d11937b4 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -1998,14 +1998,19 @@ static void ilk_compute_wm_level(const struct drm_i915_private *dev_priv, } static uint32_t -hsw_compute_linetime_wm(struct drm_device *dev, struct drm_crtc *crtc) +hsw_compute_linetime_wm(struct drm_device *dev, + struct intel_crtc_state *cstate) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - const struct drm_display_mode *adjusted_mode = &intel_crtc->config->base.adjusted_mode; + const struct drm_display_mode *adjusted_mode = + &cstate->base.adjusted_mode; u32 linetime, ips_linetime; - if (!intel_crtc->active) + if (!cstate->base.active) + return 0; + if (WARN_ON(adjusted_mode->crtc_clock == 0)) + return 0; + if (WARN_ON(dev_priv->cdclk_freq == 0)) return 0; /* The WM are computed with base on how long it takes to fill a single @@ -2313,8 +2318,7 @@ static int ilk_compute_pipe_wm(struct intel_crtc *intel_crtc, pristate, sprstate, curstate, &pipe_wm->wm[0]); if (IS_HASWELL(dev) || IS_BROADWELL(dev)) - pipe_wm->linetime = hsw_compute_linetime_wm(dev, - &intel_crtc->base); + pipe_wm->linetime = hsw_compute_linetime_wm(dev, cstate); /* LP0 watermarks always use 1/2 DDB partitioning */ ilk_compute_wm_maximums(dev, 0, &config, INTEL_DDB_PART_1_2, &max); -- cgit v1.2.3 From 151268821e6f08956b28b6ff90fae187a5b230b8 Mon Sep 17 00:00:00 2001 From: Matt Roper Date: Thu, 3 Dec 2015 11:37:40 -0800 Subject: drm/i915: Add extra paranoia to ILK watermark calculations Our low-level watermark calculation functions don't get called when the CRTC is disabled or the relevant plane is invisible, so they should never see a zero htotal or zero bpp. However add some checks to ensure this is true so that we don't wind up dividing by zero if we make a mistake elsewhere in the driver (which the atomic watermark series has revealed we might be). References: http://lists.freedesktop.org/archives/intel-gfx/2015-October/077370.html Signed-off-by: Matt Roper Link: http://patchwork.freedesktop.org/patch/msgid/1449171462-30763-6-git-send-email-matthew.d.roper@intel.com Signed-off-by: Maarten Lankhorst --- drivers/gpu/drm/i915/intel_pm.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'drivers/gpu/drm/i915/intel_pm.c') diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 0f22d11937b4..f9cbd2e81f54 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -1672,6 +1672,9 @@ uint32_t ilk_pipe_pixel_rate(const struct intel_crtc_state *pipe_config) if (pipe_h < pfit_h) pipe_h = pfit_h; + if (WARN_ON(!pfit_w || !pfit_h)) + return pixel_rate; + pixel_rate = div_u64((uint64_t) pixel_rate * pipe_w * pipe_h, pfit_w * pfit_h); } @@ -1703,6 +1706,8 @@ static uint32_t ilk_wm_method2(uint32_t pixel_rate, uint32_t pipe_htotal, if (WARN(latency == 0, "Latency value missing\n")) return UINT_MAX; + if (WARN_ON(!pipe_htotal)) + return UINT_MAX; ret = (latency * pixel_rate) / (pipe_htotal * 10000); ret = (ret + 1) * horiz_pixels * bytes_per_pixel; @@ -1713,6 +1718,17 @@ static uint32_t ilk_wm_method2(uint32_t pixel_rate, uint32_t pipe_htotal, static uint32_t ilk_wm_fbc(uint32_t pri_val, uint32_t horiz_pixels, uint8_t bytes_per_pixel) { + /* + * Neither of these should be possible since this function shouldn't be + * called if the CRTC is off or the plane is invisible. But let's be + * extra paranoid to avoid a potential divide-by-zero if we screw up + * elsewhere in the driver. + */ + if (WARN_ON(!bytes_per_pixel)) + return 0; + if (WARN_ON(!horiz_pixels)) + return 0; + return DIV_ROUND_UP(pri_val * 64, horiz_pixels * bytes_per_pixel) + 2; } -- cgit v1.2.3 From d93c037246104e403436ffe339bcb832185d0627 Mon Sep 17 00:00:00 2001 From: Matt Roper Date: Thu, 3 Dec 2015 11:37:41 -0800 Subject: drm/i915: Sanitize watermarks after hardware state readout (v4) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Although we can do a good job of reading out hardware state, the graphics firmware may have programmed the watermarks in a creative way that doesn't match how i915 would have chosen to program them. We shouldn't trust the firmware's watermark programming, but should rather re-calculate how we think WM's should be programmed and then shove those values into the hardware. We can do this pretty easily by creating a dummy top-level state, running it through the check process to calculate all the values, and then just programming the watermarks for each CRTC. v2: Move watermark sanitization after our BIOS fb reconstruction; the watermark calculations that we do here need to look at pstate->fb, which isn't setup yet in intel_modeset_setup_hw_state(), even though we have an enabled & visible plane. v3: - Don't move 'active = optimal' watermark assignment; we just undo that change in the next patch anyway. (Ville) - Move atomic helper locking fix to separate patch. (Maarten) v4: - Grab connection_mutex before calling atomic helper to duplicate state. The connector loop inside the helper will throw a WARN if we don't hold something to protect the connector list (and the helper itself doesn't try to lock the list). - Make failure to calculate watermarks for inherited state a WARN() since it probably indicates a serious problem in either our state readout code or our watermark code for this platform. Cc: Maarten Lankhorst Cc: Ville Syrjälä Signed-off-by: Matt Roper Signed-off-by: Maarten Lankhorst --- drivers/gpu/drm/i915/i915_drv.h | 1 + drivers/gpu/drm/i915/intel_display.c | 79 ++++++++++++++++++++++++++++++++++++ drivers/gpu/drm/i915/intel_pm.c | 10 +++-- 3 files changed, 86 insertions(+), 4 deletions(-) (limited to 'drivers/gpu/drm/i915/intel_pm.c') diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index c6dd4db29cea..bde9c764b415 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -623,6 +623,7 @@ struct drm_i915_display_funcs { struct dpll *best_clock); int (*compute_pipe_wm)(struct intel_crtc *crtc, struct drm_atomic_state *state); + void (*program_watermarks)(struct intel_crtc_state *cstate); void (*update_wm)(struct drm_crtc *crtc); int (*modeset_calc_cdclk)(struct drm_atomic_state *state); void (*modeset_commit_cdclk)(struct drm_atomic_state *state); diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index c1a3969f3d4c..043adfa65203 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -15276,6 +15276,78 @@ void intel_modeset_init_hw(struct drm_device *dev) intel_enable_gt_powersave(dev); } +/* + * Calculate what we think the watermarks should be for the state we've read + * out of the hardware and then immediately program those watermarks so that + * we ensure the hardware settings match our internal state. + * + * We can calculate what we think WM's should be by creating a duplicate of the + * current state (which was constructed during hardware readout) and running it + * through the atomic check code to calculate new watermark values in the + * state object. + */ +static void sanitize_watermarks(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = to_i915(dev); + struct drm_atomic_state *state; + struct drm_crtc *crtc; + struct drm_crtc_state *cstate; + struct drm_modeset_acquire_ctx ctx; + int ret; + int i; + + /* Only supported on platforms that use atomic watermark design */ + if (!dev_priv->display.program_watermarks) + return; + + /* + * We need to hold connection_mutex before calling duplicate_state so + * that the connector loop is protected. + */ + drm_modeset_acquire_init(&ctx, 0); +retry: + ret = drm_modeset_lock(&dev->mode_config.connection_mutex, &ctx); + if (ret == -EDEADLK) { + drm_modeset_backoff(&ctx); + goto retry; + } else if (WARN_ON(ret)) { + return; + } + + state = drm_atomic_helper_duplicate_state(dev, &ctx); + if (WARN_ON(IS_ERR(state))) + return; + + ret = intel_atomic_check(dev, state); + if (ret) { + /* + * If we fail here, it means that the hardware appears to be + * programmed in a way that shouldn't be possible, given our + * understanding of watermark requirements. This might mean a + * mistake in the hardware readout code or a mistake in the + * watermark calculations for a given platform. Raise a WARN + * so that this is noticeable. + * + * If this actually happens, we'll have to just leave the + * BIOS-programmed watermarks untouched and hope for the best. + */ + WARN(true, "Could not determine valid watermarks for inherited state\n"); + return; + } + + /* Write calculated watermark values back */ + to_i915(dev)->wm.config = to_intel_atomic_state(state)->wm_config; + for_each_crtc_in_state(state, crtc, cstate, i) { + struct intel_crtc_state *cs = to_intel_crtc_state(cstate); + + dev_priv->display.program_watermarks(cs); + } + + drm_atomic_state_free(state); + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); +} + void intel_modeset_init(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -15396,6 +15468,13 @@ void intel_modeset_init(struct drm_device *dev) */ intel_find_initial_plane_obj(crtc, &plane_config); } + + /* + * Make sure hardware watermarks really match the state we read out. + * Note that we need to do this after reconstructing the BIOS fb's + * since the watermark calculation done here will use pstate->fb. + */ + sanitize_watermarks(dev); } static void intel_enable_pipe_a(struct drm_device *dev) diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index f9cbd2e81f54..db3ca41ce16b 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -3617,9 +3617,11 @@ static void skl_update_wm(struct drm_crtc *crtc) dev_priv->wm.skl_hw = *results; } -static void ilk_program_watermarks(struct drm_i915_private *dev_priv) +static void ilk_program_watermarks(struct intel_crtc_state *cstate) { - struct drm_device *dev = dev_priv->dev; + struct drm_crtc *crtc = cstate->base.crtc; + struct drm_device *dev = crtc->dev; + struct drm_i915_private *dev_priv = to_i915(dev); struct intel_pipe_wm lp_wm_1_2 = {}, lp_wm_5_6 = {}, *best_lp_wm; struct ilk_wm_maximums max; struct intel_wm_config *config = &dev_priv->wm.config; @@ -3650,7 +3652,6 @@ static void ilk_program_watermarks(struct drm_i915_private *dev_priv) static void ilk_update_wm(struct drm_crtc *crtc) { - struct drm_i915_private *dev_priv = to_i915(crtc->dev); struct intel_crtc *intel_crtc = to_intel_crtc(crtc); struct intel_crtc_state *cstate = to_intel_crtc_state(crtc->state); @@ -3670,7 +3671,7 @@ static void ilk_update_wm(struct drm_crtc *crtc) intel_crtc->wm.active.ilk = cstate->wm.optimal.ilk; - ilk_program_watermarks(dev_priv); + ilk_program_watermarks(cstate); } static void skl_pipe_wm_active_state(uint32_t val, @@ -7000,6 +7001,7 @@ void intel_init_pm(struct drm_device *dev) dev_priv->wm.spr_latency[0] && dev_priv->wm.cur_latency[0])) { dev_priv->display.update_wm = ilk_update_wm; dev_priv->display.compute_pipe_wm = ilk_compute_pipe_wm; + dev_priv->display.program_watermarks = ilk_program_watermarks; } else { DRM_DEBUG_KMS("Failed to read display plane latency. " "Disable CxSR\n"); -- cgit v1.2.3 From 396e33ae204f52abebec9e578f44c749305500f4 Mon Sep 17 00:00:00 2001 From: Matt Roper Date: Wed, 6 Jan 2016 11:34:30 -0800 Subject: drm/i915: Add two-stage ILK-style watermark programming (v10) In addition to calculating final watermarks, let's also pre-calculate a set of intermediate watermark values at atomic check time. These intermediate watermarks are a combination of the watermarks for the old state and the new state; they should satisfy the requirements of both states which means they can be programmed immediately when we commit the atomic state (without waiting for a vblank). Once the vblank does happen, we can then re-program watermarks to the more optimal final value. v2: Significant rebasing/rewriting. v3: - Move 'need_postvbl_update' flag to CRTC state (Daniel) - Don't forget to check intermediate watermark values for validity (Maarten) - Don't due async watermark optimization; just do it at the end of the atomic transaction, after waiting for vblanks. We do want it to be async eventually, but adding that now will cause more trouble for Maarten's in-progress work. (Maarten) - Don't allocate space in crtc_state for intermediate watermarks on platforms that don't need it (gen9+). - Move WaCxSRDisabledForSpriteScaling:ivb into intel_begin_crtc_commit now that ilk_update_wm is gone. v4: - Add a wm_mutex to cover updates to intel_crtc->active and the need_postvbl_update flag. Since we don't have async yet it isn't terribly important yet, but might as well add it now. - Change interface to program watermarks. Platforms will now expose .initial_watermarks() and .optimize_watermarks() functions to do watermark programming. These should lock wm_mutex, copy the appropriate state values into intel_crtc->active, and then call the internal program watermarks function. v5: - Skip intermediate watermark calculation/check during initial hardware readout since we don't trust the existing HW values (and don't have valid values of our own yet). - Don't try to call .optimize_watermarks() on platforms that don't have atomic watermarks yet. (Maarten) v6: - Rebase v7: - Further rebase v8: - A few minor indentation and line length fixes v9: - Yet another rebase since Maarten's patches reworked a bunch of the code (wm_pre, wm_post, etc.) that this was previously based on. v10: - Move wm_mutex to dev_priv to protect against racing commits against disjoint CRTC sets. (Maarten) - Drop unnecessary clearing of cstate->wm.need_postvbl_update (Maarten) Cc: Maarten Lankhorst Signed-off-by: Matt Roper Link: http://patchwork.freedesktop.org/patch/msgid/1452108870-24204-1-git-send-email-matthew.d.roper@intel.com Signed-off-by: Maarten Lankhorst --- drivers/gpu/drm/i915/i915_dma.c | 1 + drivers/gpu/drm/i915/i915_drv.h | 13 ++- drivers/gpu/drm/i915/intel_atomic.c | 1 + drivers/gpu/drm/i915/intel_display.c | 92 +++++++++++++++++++- drivers/gpu/drm/i915/intel_drv.h | 28 +++++- drivers/gpu/drm/i915/intel_pm.c | 162 ++++++++++++++++++++++++----------- 6 files changed, 241 insertions(+), 56 deletions(-) (limited to 'drivers/gpu/drm/i915/intel_pm.c') diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index 988a3806512a..44a896ce32e6 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -893,6 +893,7 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) mutex_init(&dev_priv->sb_lock); mutex_init(&dev_priv->modeset_restore_lock); mutex_init(&dev_priv->av_mutex); + mutex_init(&dev_priv->wm.wm_mutex); intel_pm_setup(dev); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index bde9c764b415..61b9d910b912 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -623,7 +623,11 @@ struct drm_i915_display_funcs { struct dpll *best_clock); int (*compute_pipe_wm)(struct intel_crtc *crtc, struct drm_atomic_state *state); - void (*program_watermarks)(struct intel_crtc_state *cstate); + int (*compute_intermediate_wm)(struct drm_device *dev, + struct intel_crtc *intel_crtc, + struct intel_crtc_state *newstate); + void (*initial_watermarks)(struct intel_crtc_state *cstate); + void (*optimize_watermarks)(struct intel_crtc_state *cstate); void (*update_wm)(struct drm_crtc *crtc); int (*modeset_calc_cdclk)(struct drm_atomic_state *state); void (*modeset_commit_cdclk)(struct drm_atomic_state *state); @@ -1927,6 +1931,13 @@ struct drm_i915_private { }; uint8_t max_level; + + /* + * Should be held around atomic WM register writing; also + * protects * intel_crtc->wm.active and + * cstate->wm.need_postvbl_update. + */ + struct mutex wm_mutex; } wm; struct i915_runtime_pm pm; diff --git a/drivers/gpu/drm/i915/intel_atomic.c b/drivers/gpu/drm/i915/intel_atomic.c index 4625f8a9ba12..9682d94af710 100644 --- a/drivers/gpu/drm/i915/intel_atomic.c +++ b/drivers/gpu/drm/i915/intel_atomic.c @@ -97,6 +97,7 @@ intel_crtc_duplicate_state(struct drm_crtc *crtc) crtc_state->disable_lp_wm = false; crtc_state->disable_cxsr = false; crtc_state->wm_changed = false; + crtc_state->wm.need_postvbl_update = false; return &crtc_state->base; } diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index ab0b406ee8ca..24b3503f94be 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -4858,7 +4858,42 @@ static void intel_pre_plane_update(struct intel_crtc *crtc) intel_set_memory_cxsr(dev_priv, false); } - if (!needs_modeset(&pipe_config->base) && pipe_config->wm_changed) + /* + * IVB workaround: must disable low power watermarks for at least + * one frame before enabling scaling. LP watermarks can be re-enabled + * when scaling is disabled. + * + * WaCxSRDisabledForSpriteScaling:ivb + */ + if (pipe_config->disable_lp_wm) { + ilk_disable_lp_wm(dev); + intel_wait_for_vblank(dev, crtc->pipe); + } + + /* + * If we're doing a modeset, we're done. No need to do any pre-vblank + * watermark programming here. + */ + if (needs_modeset(&pipe_config->base)) + return; + + /* + * For platforms that support atomic watermarks, program the + * 'intermediate' watermarks immediately. On pre-gen9 platforms, these + * will be the intermediate values that are safe for both pre- and + * post- vblank; when vblank happens, the 'active' values will be set + * to the final 'target' values and we'll do this again to get the + * optimal watermarks. For gen9+ platforms, the values we program here + * will be the final target values which will get automatically latched + * at vblank time; no further programming will be necessary. + * + * If a platform hasn't been transitioned to atomic watermarks yet, + * we'll continue to update watermarks the old way, if flags tell + * us to. + */ + if (dev_priv->display.initial_watermarks != NULL) + dev_priv->display.initial_watermarks(pipe_config); + else if (pipe_config->wm_changed) intel_update_watermarks(&crtc->base); } @@ -11918,6 +11953,11 @@ int intel_plane_atomic_calc_changes(struct drm_crtc_state *crtc_state, pipe_config->wm_changed = true; } + /* Pre-gen9 platforms need two-step watermark updates */ + if (pipe_config->wm_changed && INTEL_INFO(dev)->gen < 9 && + dev_priv->display.optimize_watermarks) + to_intel_crtc_state(crtc_state)->wm.need_postvbl_update = true; + if (visible || was_visible) intel_crtc->atomic.fb_bits |= to_intel_plane(plane)->frontbuffer_bit; @@ -12074,8 +12114,29 @@ static int intel_crtc_atomic_check(struct drm_crtc *crtc, ret = 0; if (dev_priv->display.compute_pipe_wm) { ret = dev_priv->display.compute_pipe_wm(intel_crtc, state); - if (ret) + if (ret) { + DRM_DEBUG_KMS("Target pipe watermarks are invalid\n"); + return ret; + } + } + + if (dev_priv->display.compute_intermediate_wm && + !to_intel_atomic_state(state)->skip_intermediate_wm) { + if (WARN_ON(!dev_priv->display.compute_pipe_wm)) + return 0; + + /* + * Calculate 'intermediate' watermarks that satisfy both the + * old state and the new state. We can program these + * immediately. + */ + ret = dev_priv->display.compute_intermediate_wm(crtc->dev, + intel_crtc, + pipe_config); + if (ret) { + DRM_DEBUG_KMS("No valid intermediate pipe watermarks are possible\n"); return ret; + } } if (INTEL_INFO(dev)->gen >= 9) { @@ -13530,6 +13591,7 @@ static int intel_atomic_commit(struct drm_device *dev, struct drm_i915_private *dev_priv = dev->dev_private; struct drm_crtc_state *crtc_state; struct drm_crtc *crtc; + struct intel_crtc_state *intel_cstate; int ret = 0, i; bool hw_check = intel_state->modeset; @@ -13629,6 +13691,20 @@ static int intel_atomic_commit(struct drm_device *dev, drm_atomic_helper_wait_for_vblanks(dev, state); + /* + * Now that the vblank has passed, we can go ahead and program the + * optimal watermarks on platforms that need two-step watermark + * programming. + * + * TODO: Move this (and other cleanup) to an async worker eventually. + */ + for_each_crtc_in_state(state, crtc, crtc_state, i) { + intel_cstate = to_intel_crtc_state(crtc->state); + + if (dev_priv->display.optimize_watermarks) + dev_priv->display.optimize_watermarks(intel_cstate); + } + mutex_lock(&dev->struct_mutex); drm_atomic_helper_cleanup_planes(dev, state); mutex_unlock(&dev->struct_mutex); @@ -15300,7 +15376,7 @@ static void sanitize_watermarks(struct drm_device *dev) int i; /* Only supported on platforms that use atomic watermark design */ - if (!dev_priv->display.program_watermarks) + if (!dev_priv->display.optimize_watermarks) return; /* @@ -15321,6 +15397,13 @@ retry: if (WARN_ON(IS_ERR(state))) return; + /* + * Hardware readout is the only time we don't want to calculate + * intermediate watermarks (since we don't trust the current + * watermarks). + */ + to_intel_atomic_state(state)->skip_intermediate_wm = true; + ret = intel_atomic_check(dev, state); if (ret) { /* @@ -15343,7 +15426,8 @@ retry: for_each_crtc_in_state(state, crtc, cstate, i) { struct intel_crtc_state *cs = to_intel_crtc_state(cstate); - dev_priv->display.program_watermarks(cs); + cs->wm.need_postvbl_update = true; + dev_priv->display.optimize_watermarks(cs); } drm_atomic_state_free(state); diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index a3b2025da563..b7a33f6cbbbc 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -260,6 +260,12 @@ struct intel_atomic_state { struct intel_shared_dpll_config shared_dpll[I915_NUM_PLLS]; struct intel_wm_config wm_config; + + /* + * Current watermarks can't be trusted during hardware readout, so + * don't bother calculating intermediate watermarks. + */ + bool skip_intermediate_wm; }; struct intel_plane_state { @@ -507,13 +513,29 @@ struct intel_crtc_state { struct { /* - * optimal watermarks, programmed post-vblank when this state - * is committed + * Optimal watermarks, programmed post-vblank when this state + * is committed. */ union { struct intel_pipe_wm ilk; struct skl_pipe_wm skl; } optimal; + + /* + * Intermediate watermarks; these can be programmed immediately + * since they satisfy both the current configuration we're + * switching away from and the new configuration we're switching + * to. + */ + struct intel_pipe_wm intermediate; + + /* + * Platforms with two-step watermark programming will need to + * update watermark programming post-vblank to switch from the + * safe intermediate watermarks to the optimal final + * watermarks. + */ + bool need_postvbl_update; } wm; }; @@ -600,6 +622,7 @@ struct intel_crtc { struct intel_pipe_wm ilk; struct skl_pipe_wm skl; } active; + /* allow CxSR on this pipe */ bool cxsr_allowed; } wm; @@ -1566,6 +1589,7 @@ void skl_wm_get_hw_state(struct drm_device *dev); void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv, struct skl_ddb_allocation *ddb /* out */); uint32_t ilk_pipe_pixel_rate(const struct intel_crtc_state *pipe_config); +bool ilk_disable_lp_wm(struct drm_device *dev); /* intel_sdvo.c */ bool intel_sdvo_init(struct drm_device *dev, diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index db3ca41ce16b..9df9e9a22f3c 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -2273,6 +2273,29 @@ static void skl_setup_wm_latency(struct drm_device *dev) intel_print_wm_latency(dev, "Gen9 Plane", dev_priv->wm.skl_latency); } +static bool ilk_validate_pipe_wm(struct drm_device *dev, + struct intel_pipe_wm *pipe_wm) +{ + /* LP0 watermark maximums depend on this pipe alone */ + const struct intel_wm_config config = { + .num_pipes_active = 1, + .sprites_enabled = pipe_wm->sprites_enabled, + .sprites_scaled = pipe_wm->sprites_scaled, + }; + 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); + + /* At least LP0 must be valid */ + if (!ilk_validate_wm_level(0, &max, &pipe_wm->wm[0])) { + DRM_DEBUG_KMS("LP0 watermark invalid\n"); + return false; + } + + return true; +} + /* Compute new watermarks for the pipe */ static int ilk_compute_pipe_wm(struct intel_crtc *intel_crtc, struct drm_atomic_state *state) @@ -2287,10 +2310,6 @@ static int ilk_compute_pipe_wm(struct intel_crtc *intel_crtc, struct intel_plane_state *sprstate = NULL; struct intel_plane_state *curstate = NULL; int level, max_level = ilk_wm_max_level(dev); - /* LP0 watermark maximums depend on this pipe alone */ - struct intel_wm_config config = { - .num_pipes_active = 1, - }; struct ilk_wm_maximums max; cstate = intel_atomic_get_crtc_state(state, intel_crtc); @@ -2313,21 +2332,18 @@ static int ilk_compute_pipe_wm(struct intel_crtc *intel_crtc, curstate = to_intel_plane_state(ps); } - config.sprites_enabled = sprstate->visible; - config.sprites_scaled = sprstate->visible && + pipe_wm->pipe_enabled = cstate->base.active; + pipe_wm->sprites_enabled = sprstate->visible; + pipe_wm->sprites_scaled = sprstate->visible && (drm_rect_width(&sprstate->dst) != drm_rect_width(&sprstate->src) >> 16 || drm_rect_height(&sprstate->dst) != drm_rect_height(&sprstate->src) >> 16); - pipe_wm->pipe_enabled = cstate->base.active; - pipe_wm->sprites_enabled = config.sprites_enabled; - pipe_wm->sprites_scaled = config.sprites_scaled; - /* ILK/SNB: LP2+ watermarks only w/o sprites */ if (INTEL_INFO(dev)->gen <= 6 && sprstate->visible) max_level = 1; /* ILK/SNB/IVB: LP1+ watermarks only w/o scaling */ - if (config.sprites_scaled) + if (pipe_wm->sprites_scaled) max_level = 0; ilk_compute_wm_level(dev_priv, intel_crtc, 0, cstate, @@ -2336,12 +2352,8 @@ static int ilk_compute_pipe_wm(struct intel_crtc *intel_crtc, if (IS_HASWELL(dev) || IS_BROADWELL(dev)) pipe_wm->linetime = hsw_compute_linetime_wm(dev, cstate); - /* 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 */ - if (!ilk_validate_wm_level(0, &max, &pipe_wm->wm[0])) - return -EINVAL; + if (!ilk_validate_pipe_wm(dev, pipe_wm)) + return false; ilk_compute_wm_reg_maximums(dev, 1, &max); @@ -2365,6 +2377,59 @@ static int ilk_compute_pipe_wm(struct intel_crtc *intel_crtc, return 0; } +/* + * Build a set of 'intermediate' watermark values that satisfy both the old + * state and the new state. These can be programmed to the hardware + * immediately. + */ +static int ilk_compute_intermediate_wm(struct drm_device *dev, + struct intel_crtc *intel_crtc, + struct intel_crtc_state *newstate) +{ + struct intel_pipe_wm *a = &newstate->wm.intermediate; + struct intel_pipe_wm *b = &intel_crtc->wm.active.ilk; + int level, max_level = ilk_wm_max_level(dev); + + /* + * Start with the final, target watermarks, then combine with the + * currently active watermarks to get values that are safe both before + * and after the vblank. + */ + *a = newstate->wm.optimal.ilk; + a->pipe_enabled |= b->pipe_enabled; + a->sprites_enabled |= b->sprites_enabled; + a->sprites_scaled |= b->sprites_scaled; + + for (level = 0; level <= max_level; level++) { + struct intel_wm_level *a_wm = &a->wm[level]; + const struct intel_wm_level *b_wm = &b->wm[level]; + + a_wm->enable &= b_wm->enable; + a_wm->pri_val = max(a_wm->pri_val, b_wm->pri_val); + a_wm->spr_val = max(a_wm->spr_val, b_wm->spr_val); + a_wm->cur_val = max(a_wm->cur_val, b_wm->cur_val); + a_wm->fbc_val = max(a_wm->fbc_val, b_wm->fbc_val); + } + + /* + * We need to make sure that these merged watermark values are + * actually a valid configuration themselves. If they're not, + * there's no safe way to transition from the old state to + * the new state, so we need to fail the atomic transaction. + */ + if (!ilk_validate_pipe_wm(dev, a)) + return -EINVAL; + + /* + * If our intermediate WM are identical to the final WM, then we can + * omit the post-vblank programming; only update if it's different. + */ + if (memcmp(a, &newstate->wm.optimal.ilk, sizeof(*a)) != 0) + newstate->wm.need_postvbl_update = false; + + return 0; +} + /* * Merge the watermarks from all active pipes for a specific level. */ @@ -2377,9 +2442,7 @@ static void ilk_merge_wm_level(struct drm_device *dev, ret_wm->enable = true; for_each_intel_crtc(dev, intel_crtc) { - const struct intel_crtc_state *cstate = - to_intel_crtc_state(intel_crtc->base.state); - const struct intel_pipe_wm *active = &cstate->wm.optimal.ilk; + const struct intel_pipe_wm *active = &intel_crtc->wm.active.ilk; const struct intel_wm_level *wm = &active->wm[level]; if (!active->pipe_enabled) @@ -2527,15 +2590,14 @@ static void ilk_compute_wm_results(struct drm_device *dev, /* LP0 register values */ for_each_intel_crtc(dev, intel_crtc) { - const struct intel_crtc_state *cstate = - to_intel_crtc_state(intel_crtc->base.state); enum pipe pipe = intel_crtc->pipe; - const struct intel_wm_level *r = &cstate->wm.optimal.ilk.wm[0]; + const struct intel_wm_level *r = + &intel_crtc->wm.active.ilk.wm[0]; if (WARN_ON(!r->enable)) continue; - results->wm_linetime[pipe] = cstate->wm.optimal.ilk.linetime; + results->wm_linetime[pipe] = intel_crtc->wm.active.ilk.linetime; results->wm_pipe[pipe] = (r->pri_val << WM0_PIPE_PLANE_SHIFT) | @@ -2742,7 +2804,7 @@ static void ilk_write_wm_values(struct drm_i915_private *dev_priv, dev_priv->wm.hw = *results; } -static bool ilk_disable_lp_wm(struct drm_device *dev) +bool ilk_disable_lp_wm(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -3617,11 +3679,9 @@ static void skl_update_wm(struct drm_crtc *crtc) dev_priv->wm.skl_hw = *results; } -static void ilk_program_watermarks(struct intel_crtc_state *cstate) +static void ilk_program_watermarks(struct drm_i915_private *dev_priv) { - struct drm_crtc *crtc = cstate->base.crtc; - struct drm_device *dev = crtc->dev; - struct drm_i915_private *dev_priv = to_i915(dev); + struct drm_device *dev = dev_priv->dev; struct intel_pipe_wm lp_wm_1_2 = {}, lp_wm_5_6 = {}, *best_lp_wm; struct ilk_wm_maximums max; struct intel_wm_config *config = &dev_priv->wm.config; @@ -3650,28 +3710,28 @@ static void ilk_program_watermarks(struct intel_crtc_state *cstate) ilk_write_wm_values(dev_priv, &results); } -static void ilk_update_wm(struct drm_crtc *crtc) +static void ilk_initial_watermarks(struct intel_crtc_state *cstate) { - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - struct intel_crtc_state *cstate = to_intel_crtc_state(crtc->state); - - WARN_ON(cstate->base.active != intel_crtc->active); + struct drm_i915_private *dev_priv = to_i915(cstate->base.crtc->dev); + struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc); - /* - * IVB workaround: must disable low power watermarks for at least - * one frame before enabling scaling. LP watermarks can be re-enabled - * when scaling is disabled. - * - * WaCxSRDisabledForSpriteScaling:ivb - */ - if (cstate->disable_lp_wm) { - ilk_disable_lp_wm(crtc->dev); - intel_wait_for_vblank(crtc->dev, intel_crtc->pipe); - } + mutex_lock(&dev_priv->wm.wm_mutex); + intel_crtc->wm.active.ilk = cstate->wm.intermediate; + ilk_program_watermarks(dev_priv); + mutex_unlock(&dev_priv->wm.wm_mutex); +} - intel_crtc->wm.active.ilk = cstate->wm.optimal.ilk; +static void ilk_optimize_watermarks(struct intel_crtc_state *cstate) +{ + struct drm_i915_private *dev_priv = to_i915(cstate->base.crtc->dev); + struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc); - ilk_program_watermarks(cstate); + mutex_lock(&dev_priv->wm.wm_mutex); + if (cstate->wm.need_postvbl_update) { + intel_crtc->wm.active.ilk = cstate->wm.optimal.ilk; + ilk_program_watermarks(dev_priv); + } + mutex_unlock(&dev_priv->wm.wm_mutex); } static void skl_pipe_wm_active_state(uint32_t val, @@ -6999,9 +7059,13 @@ void intel_init_pm(struct drm_device *dev) dev_priv->wm.spr_latency[1] && dev_priv->wm.cur_latency[1]) || (!IS_GEN5(dev) && dev_priv->wm.pri_latency[0] && dev_priv->wm.spr_latency[0] && dev_priv->wm.cur_latency[0])) { - dev_priv->display.update_wm = ilk_update_wm; dev_priv->display.compute_pipe_wm = ilk_compute_pipe_wm; - dev_priv->display.program_watermarks = ilk_program_watermarks; + dev_priv->display.compute_intermediate_wm = + ilk_compute_intermediate_wm; + dev_priv->display.initial_watermarks = + ilk_initial_watermarks; + dev_priv->display.optimize_watermarks = + ilk_optimize_watermarks; } else { DRM_DEBUG_KMS("Failed to read display plane latency. " "Disable CxSR\n"); -- cgit v1.2.3 From 87ad321287ae99a8932af1a19ac99849284a62bd Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Thu, 14 Jan 2016 12:53:34 +0200 Subject: drm/i915: add onoff utility function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a common function to return "on" or "off" string based on the argument, and drop the local versions of it. This is the onoff version of commit 42a8ca4cb4a48ddbf40e8edb291425e76bcdc230 Author: Jani Nikula Date: Thu Aug 27 16:23:30 2015 +0300 drm/i915: add yesno utility function Reviewed-by: Ville Syrjälä Signed-off-by: Jani Nikula Link: http://patchwork.freedesktop.org/patch/msgid/1452768814-29787-1-git-send-email-jani.nikula@intel.com --- drivers/gpu/drm/i915/i915_drv.c | 6 +++--- drivers/gpu/drm/i915/i915_drv.h | 5 +++++ drivers/gpu/drm/i915/intel_display.c | 30 ++++++++++++------------------ drivers/gpu/drm/i915/intel_dp.c | 9 ++------- drivers/gpu/drm/i915/intel_pm.c | 11 +++++------ 5 files changed, 27 insertions(+), 34 deletions(-) (limited to 'drivers/gpu/drm/i915/intel_pm.c') diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index f17a2b0c2493..975af3568521 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -1335,8 +1335,8 @@ static int vlv_wait_for_gt_wells(struct drm_i915_private *dev_priv, return 0; DRM_DEBUG_KMS("waiting for GT wells to go %s (%08x)\n", - wait_for_on ? "on" : "off", - I915_READ(VLV_GTLC_PW_STATUS)); + onoff(wait_for_on), + I915_READ(VLV_GTLC_PW_STATUS)); /* * RC6 transitioning can be delayed up to 2 msec (see @@ -1345,7 +1345,7 @@ static int vlv_wait_for_gt_wells(struct drm_i915_private *dev_priv, err = wait_for(COND, 3); if (err) DRM_ERROR("timeout waiting for GT wells to go %s\n", - wait_for_on ? "on" : "off"); + onoff(wait_for_on)); return err; #undef COND diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 104bd1809936..eb7bb97f7316 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -102,6 +102,11 @@ static inline const char *yesno(bool v) return v ? "yes" : "no"; } +static inline const char *onoff(bool v) +{ + return v ? "on" : "off"; +} + enum pipe { INVALID_PIPE = -1, PIPE_A = 0, diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index e5eb341c6ca3..aa24f79d85bf 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -1150,11 +1150,6 @@ static void intel_wait_for_pipe_off(struct intel_crtc *crtc) } } -static const char *state_string(bool enabled) -{ - return enabled ? "on" : "off"; -} - /* Only for pre-ILK configs */ void assert_pll(struct drm_i915_private *dev_priv, enum pipe pipe, bool state) @@ -1166,7 +1161,7 @@ void assert_pll(struct drm_i915_private *dev_priv, cur_state = !!(val & DPLL_VCO_ENABLE); I915_STATE_WARN(cur_state != state, "PLL state assertion failure (expected %s, current %s)\n", - state_string(state), state_string(cur_state)); + onoff(state), onoff(cur_state)); } /* XXX: the dsi pll is shared between MIPI DSI ports */ @@ -1182,7 +1177,7 @@ static void assert_dsi_pll(struct drm_i915_private *dev_priv, bool state) cur_state = val & DSI_PLL_VCO_EN; I915_STATE_WARN(cur_state != state, "DSI PLL state assertion failure (expected %s, current %s)\n", - state_string(state), state_string(cur_state)); + onoff(state), onoff(cur_state)); } #define assert_dsi_pll_enabled(d) assert_dsi_pll(d, true) #define assert_dsi_pll_disabled(d) assert_dsi_pll(d, false) @@ -1206,14 +1201,13 @@ void assert_shared_dpll(struct drm_i915_private *dev_priv, bool cur_state; struct intel_dpll_hw_state hw_state; - if (WARN (!pll, - "asserting DPLL %s with no DPLL\n", state_string(state))) + if (WARN(!pll, "asserting DPLL %s with no DPLL\n", onoff(state))) return; cur_state = pll->get_hw_state(dev_priv, pll, &hw_state); I915_STATE_WARN(cur_state != state, "%s assertion failure (expected %s, current %s)\n", - pll->name, state_string(state), state_string(cur_state)); + pll->name, onoff(state), onoff(cur_state)); } static void assert_fdi_tx(struct drm_i915_private *dev_priv, @@ -1233,7 +1227,7 @@ static void assert_fdi_tx(struct drm_i915_private *dev_priv, } I915_STATE_WARN(cur_state != state, "FDI TX state assertion failure (expected %s, current %s)\n", - state_string(state), state_string(cur_state)); + onoff(state), onoff(cur_state)); } #define assert_fdi_tx_enabled(d, p) assert_fdi_tx(d, p, true) #define assert_fdi_tx_disabled(d, p) assert_fdi_tx(d, p, false) @@ -1248,7 +1242,7 @@ static void assert_fdi_rx(struct drm_i915_private *dev_priv, cur_state = !!(val & FDI_RX_ENABLE); I915_STATE_WARN(cur_state != state, "FDI RX state assertion failure (expected %s, current %s)\n", - state_string(state), state_string(cur_state)); + onoff(state), onoff(cur_state)); } #define assert_fdi_rx_enabled(d, p) assert_fdi_rx(d, p, true) #define assert_fdi_rx_disabled(d, p) assert_fdi_rx(d, p, false) @@ -1280,7 +1274,7 @@ void assert_fdi_rx_pll(struct drm_i915_private *dev_priv, cur_state = !!(val & FDI_RX_PLL_ENABLE); I915_STATE_WARN(cur_state != state, "FDI RX PLL assertion failure (expected %s, current %s)\n", - state_string(state), state_string(cur_state)); + onoff(state), onoff(cur_state)); } void assert_panel_unlocked(struct drm_i915_private *dev_priv, @@ -1338,7 +1332,7 @@ static void assert_cursor(struct drm_i915_private *dev_priv, I915_STATE_WARN(cur_state != state, "cursor on pipe %c assertion failure (expected %s, current %s)\n", - pipe_name(pipe), state_string(state), state_string(cur_state)); + pipe_name(pipe), onoff(state), onoff(cur_state)); } #define assert_cursor_enabled(d, p) assert_cursor(d, p, true) #define assert_cursor_disabled(d, p) assert_cursor(d, p, false) @@ -1365,7 +1359,7 @@ void assert_pipe(struct drm_i915_private *dev_priv, I915_STATE_WARN(cur_state != state, "pipe %c assertion failure (expected %s, current %s)\n", - pipe_name(pipe), state_string(state), state_string(cur_state)); + pipe_name(pipe), onoff(state), onoff(cur_state)); } static void assert_plane(struct drm_i915_private *dev_priv, @@ -1378,7 +1372,7 @@ static void assert_plane(struct drm_i915_private *dev_priv, cur_state = !!(val & DISPLAY_PLANE_ENABLE); I915_STATE_WARN(cur_state != state, "plane %c assertion failure (expected %s, current %s)\n", - plane_name(plane), state_string(state), state_string(cur_state)); + plane_name(plane), onoff(state), onoff(cur_state)); } #define assert_plane_enabled(d, p) assert_plane(d, p, true) @@ -16317,7 +16311,7 @@ intel_display_print_error_state(struct drm_i915_error_state_buf *m, for_each_pipe(dev_priv, i) { err_printf(m, "Pipe [%d]:\n", i); err_printf(m, " Power: %s\n", - error->pipe[i].power_domain_on ? "on" : "off"); + onoff(error->pipe[i].power_domain_on)); err_printf(m, " SRC: %08x\n", error->pipe[i].source); err_printf(m, " STAT: %08x\n", error->pipe[i].stat); @@ -16345,7 +16339,7 @@ intel_display_print_error_state(struct drm_i915_error_state_buf *m, err_printf(m, "CPU transcoder: %c\n", transcoder_name(error->transcoder[i].cpu_transcoder)); err_printf(m, " Power: %s\n", - error->transcoder[i].power_domain_on ? "on" : "off"); + onoff(error->transcoder[i].power_domain_on)); err_printf(m, " CONF: %08x\n", error->transcoder[i].conf); err_printf(m, " HTOTAL: %08x\n", error->transcoder[i].htotal); err_printf(m, " HBLANK: %08x\n", error->transcoder[i].hblank); diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 9e02dd789b86..3999afa440bd 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -2238,11 +2238,6 @@ static void intel_edp_backlight_power(struct intel_connector *connector, _intel_edp_backlight_off(intel_dp); } -static const char *state_string(bool enabled) -{ - return enabled ? "on" : "off"; -} - static void assert_dp_port(struct intel_dp *intel_dp, bool state) { struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); @@ -2252,7 +2247,7 @@ static void assert_dp_port(struct intel_dp *intel_dp, bool state) I915_STATE_WARN(cur_state != state, "DP port %c state assertion failure (expected %s, current %s)\n", port_name(dig_port->port), - state_string(state), state_string(cur_state)); + onoff(state), onoff(cur_state)); } #define assert_dp_port_disabled(d) assert_dp_port((d), false) @@ -2262,7 +2257,7 @@ static void assert_edp_pll(struct drm_i915_private *dev_priv, bool state) I915_STATE_WARN(cur_state != state, "eDP PLL state assertion failure (expected %s, current %s)\n", - state_string(state), state_string(cur_state)); + onoff(state), onoff(cur_state)); } #define assert_edp_pll_enabled(d) assert_edp_pll((d), true) #define assert_edp_pll_disabled(d) assert_edp_pll((d), false) diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 9df9e9a22f3c..465ca76df201 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -4590,13 +4590,13 @@ static void intel_print_rc6_info(struct drm_device *dev, u32 mode) } if (HAS_RC6p(dev)) DRM_DEBUG_KMS("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"); + onoff(mode & GEN6_RC_CTL_RC6_ENABLE), + onoff(mode & GEN6_RC_CTL_RC6p_ENABLE), + onoff(mode & GEN6_RC_CTL_RC6pp_ENABLE)); else DRM_DEBUG_KMS("Enabling RC6 states: RC6 %s\n", - (mode & GEN6_RC_CTL_RC6_ENABLE) ? "on" : "off"); + onoff(mode & GEN6_RC_CTL_RC6_ENABLE)); } static int sanitize_rc6_option(const struct drm_device *dev, int enable_rc6) @@ -4774,8 +4774,7 @@ static void gen9_enable_rc6(struct drm_device *dev) /* 3a: 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"); + DRM_INFO("RC6 %s\n", onoff(rc6_mask & GEN6_RC_CTL_RC6_ENABLE)); /* WaRsUseTimeoutMode */ if (IS_SKL_REVID(dev, 0, SKL_REVID_D0) || IS_BXT_REVID(dev, 0, BXT_REVID_A1)) { -- cgit v1.2.3 From f1ecaf8f9c9924badd4c8f690e39632d31edb500 Mon Sep 17 00:00:00 2001 From: Ville Syrjälä Date: Thu, 14 Jan 2016 14:53:34 +0200 Subject: drm/i915: Start WM computation from scratch on ILK-BDW MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ilk_compute_pipe_wm() assumes as zeroed pipe_wm structure when it starts. We used to pass such a zeroed struct in, but this got broken when the pipe_wm structure got embedded in the crtc state. To fix it without too much fuzz, we need to resort to a memset(). Fixes: 4e0963c7663b ("drm/i915: Calculate pipe watermarks into CRTC state (v3)") Cc: Matt Roper Signed-off-by: Ville Syrjälä Reviewed-by: Matt Roper Link: http://patchwork.freedesktop.org/patch/msgid/1452776015-22076-1-git-send-email-ville.syrjala@linux.intel.com --- drivers/gpu/drm/i915/intel_pm.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/gpu/drm/i915/intel_pm.c') diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 465ca76df201..966c4c2c416f 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -2317,6 +2317,7 @@ static int ilk_compute_pipe_wm(struct intel_crtc *intel_crtc, return PTR_ERR(cstate); pipe_wm = &cstate->wm.optimal.ilk; + memset(pipe_wm, 0, sizeof(*pipe_wm)); for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane) { ps = drm_atomic_get_plane_state(state, -- cgit v1.2.3 From d890565c44447db08fd9d07f5b02928a07a88c7e Mon Sep 17 00:00:00 2001 From: Ville Syrjälä Date: Thu, 14 Jan 2016 14:53:35 +0200 Subject: drm/i915: Use the active wm config for merging on ILK-BDW MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ilk_program_watermarks() is supposed to merge the active watermarks from all pipes. Thus we need to use the active config too instead of some precomputed stuff. Fixes: aa363136866c ("drm/i915: Calculate watermark configuration during atomic check (v2)") Cc: Matt Roper Signed-off-by: Ville Syrjälä Reviewed-by: Matt Roper Link: http://patchwork.freedesktop.org/patch/msgid/1452776015-22076-2-git-send-email-ville.syrjala@linux.intel.com --- drivers/gpu/drm/i915/intel_pm.c | 32 ++++++++++++++++++++++++++------ 1 file changed, 26 insertions(+), 6 deletions(-) (limited to 'drivers/gpu/drm/i915/intel_pm.c') diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 966c4c2c416f..6b2b3e331a09 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -3680,23 +3680,43 @@ static void skl_update_wm(struct drm_crtc *crtc) dev_priv->wm.skl_hw = *results; } +static void ilk_compute_wm_config(struct drm_device *dev, + struct intel_wm_config *config) +{ + struct intel_crtc *crtc; + + /* Compute the currently _active_ config */ + for_each_intel_crtc(dev, crtc) { + const struct intel_pipe_wm *wm = &crtc->wm.active.ilk; + + if (!wm->pipe_enabled) + continue; + + config->sprites_enabled |= wm->sprites_enabled; + config->sprites_scaled |= wm->sprites_scaled; + config->num_pipes_active++; + } +} + static void ilk_program_watermarks(struct drm_i915_private *dev_priv) { struct drm_device *dev = dev_priv->dev; struct intel_pipe_wm lp_wm_1_2 = {}, lp_wm_5_6 = {}, *best_lp_wm; struct ilk_wm_maximums max; - struct intel_wm_config *config = &dev_priv->wm.config; + struct intel_wm_config config = {}; struct ilk_wm_values results = {}; enum intel_ddb_partitioning partitioning; - ilk_compute_wm_maximums(dev, 1, config, INTEL_DDB_PART_1_2, &max); - ilk_wm_merge(dev, config, &max, &lp_wm_1_2); + 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); /* 5/6 split only in single pipe config on IVB+ */ if (INTEL_INFO(dev)->gen >= 7 && - config->num_pipes_active == 1 && config->sprites_enabled) { - ilk_compute_wm_maximums(dev, 1, config, INTEL_DDB_PART_5_6, &max); - ilk_wm_merge(dev, config, &max, &lp_wm_5_6); + config.num_pipes_active == 1 && config.sprites_enabled) { + ilk_compute_wm_maximums(dev, 1, &config, INTEL_DDB_PART_5_6, &max); + ilk_wm_merge(dev, &config, &max, &lp_wm_5_6); best_lp_wm = ilk_find_best_result(dev, &lp_wm_1_2, &lp_wm_5_6); } else { -- cgit v1.2.3 From e2828914723a0739058c263af4f74a05a9bd85bb Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Mon, 18 Jan 2016 09:19:47 +0200 Subject: drm/i915: turn some bogus kernel-doc comments to normal comments Apparently accidental or misplaced /** kernel-doc comments, confusing the tool. Turn them to normal comments. Reviewed-by: Daniel Vetter Signed-off-by: Jani Nikula Link: http://patchwork.freedesktop.org/patch/msgid/1453101588-18008-2-git-send-email-jani.nikula@intel.com --- drivers/gpu/drm/i915/intel_pm.c | 2 +- drivers/gpu/drm/i915/intel_ringbuffer.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/gpu/drm/i915/intel_pm.c') diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 6b2b3e331a09..7e6e70054d6a 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -4138,7 +4138,7 @@ void intel_update_watermarks(struct drm_crtc *crtc) dev_priv->display.update_wm(crtc); } -/** +/* * Lock protecting IPS related data structures */ DEFINE_SPINLOCK(mchdev_lock); diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index ede57954080e..91ac8a9bd903 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -410,7 +410,7 @@ intel_write_status_page(struct intel_engine_cs *ring, ring->status_page.page_addr[reg] = value; } -/** +/* * Reads a dword out of the status page, which is written to from the command * queue by automatic updates, MI_REPORT_HEAD, MI_STORE_DATA_INDEX, or * MI_STORE_DATA_IMM. -- cgit v1.2.3 From 18afd443f7f92c3cf514af531e020c8d992e49ac Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Mon, 18 Jan 2016 09:19:48 +0200 Subject: drm/i915: add DOC: headline to RC6 kernel-doc Without the DOC:, kernel-doc confuses the documentation block for something else. Reviewed-by: Daniel Vetter Signed-off-by: Jani Nikula Link: http://patchwork.freedesktop.org/patch/msgid/1453101588-18008-3-git-send-email-jani.nikula@intel.com --- drivers/gpu/drm/i915/intel_pm.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers/gpu/drm/i915/intel_pm.c') diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 7e6e70054d6a..180555553fa2 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -32,6 +32,8 @@ #include /** + * DOC: RC6 + * * RC6 is a special power stage which allows the GPU to enter an very * low-voltage mode when idle, using down to 0V while at this stage. This * stage is entered automatically when the GPU is idle when RC6 support is -- cgit v1.2.3 From bf22045250fafbe733277e13300eaa240ba2104d Mon Sep 17 00:00:00 2001 From: Matt Roper Date: Tue, 19 Jan 2016 11:43:04 -0800 Subject: Revert "drm/i915: Add two-stage ILK-style watermark programming (v10)" This reverts commit 396e33ae204f52abebec9e578f44c749305500f4. This commit was triggering some FIFO underrun warnings on ILK-IVB platforms (but surprisingly not on HSW/BDW that share more or less the same codepaths). These underruns were caught by the continuous integration (CI) system and could be reproduced consistently when running the basic acceptance tests (BAT) on the affected platforms. Note that this revert will cause a visible regression for some end-users; the "flicker when mouse moves between monitors in X" issue that was reported before this patch was merged will now return. However regressions that are visible to CI have higher priority since they prevent proper testing of future patches on those platforms. Hopefully we'll be able to figure out the cause of the underruns quickly and remerge an improved version of this patch to fix the regression. Cc: Daniel Vetter Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=93640 Signed-off-by: Matt Roper Reviewed-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1453232584-8543-1-git-send-email-matthew.d.roper@intel.com Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_dma.c | 1 - drivers/gpu/drm/i915/i915_drv.h | 13 +-- drivers/gpu/drm/i915/intel_atomic.c | 1 - drivers/gpu/drm/i915/intel_display.c | 92 +------------------- drivers/gpu/drm/i915/intel_drv.h | 28 +----- drivers/gpu/drm/i915/intel_pm.c | 162 +++++++++++------------------------ 6 files changed, 56 insertions(+), 241 deletions(-) (limited to 'drivers/gpu/drm/i915/intel_pm.c') diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index a0f5659032fc..d70d96fe553b 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -896,7 +896,6 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) mutex_init(&dev_priv->sb_lock); mutex_init(&dev_priv->modeset_restore_lock); mutex_init(&dev_priv->av_mutex); - mutex_init(&dev_priv->wm.wm_mutex); intel_pm_setup(dev); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index af301482e6f8..d3b98c228683 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -628,11 +628,7 @@ struct drm_i915_display_funcs { struct dpll *best_clock); int (*compute_pipe_wm)(struct intel_crtc *crtc, struct drm_atomic_state *state); - int (*compute_intermediate_wm)(struct drm_device *dev, - struct intel_crtc *intel_crtc, - struct intel_crtc_state *newstate); - void (*initial_watermarks)(struct intel_crtc_state *cstate); - void (*optimize_watermarks)(struct intel_crtc_state *cstate); + void (*program_watermarks)(struct intel_crtc_state *cstate); void (*update_wm)(struct drm_crtc *crtc); int (*modeset_calc_cdclk)(struct drm_atomic_state *state); void (*modeset_commit_cdclk)(struct drm_atomic_state *state); @@ -1938,13 +1934,6 @@ struct drm_i915_private { }; uint8_t max_level; - - /* - * Should be held around atomic WM register writing; also - * protects * intel_crtc->wm.active and - * cstate->wm.need_postvbl_update. - */ - struct mutex wm_mutex; } wm; struct i915_runtime_pm pm; diff --git a/drivers/gpu/drm/i915/intel_atomic.c b/drivers/gpu/drm/i915/intel_atomic.c index 9682d94af710..4625f8a9ba12 100644 --- a/drivers/gpu/drm/i915/intel_atomic.c +++ b/drivers/gpu/drm/i915/intel_atomic.c @@ -97,7 +97,6 @@ intel_crtc_duplicate_state(struct drm_crtc *crtc) crtc_state->disable_lp_wm = false; crtc_state->disable_cxsr = false; crtc_state->wm_changed = false; - crtc_state->wm.need_postvbl_update = false; return &crtc_state->base; } diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index a851cb70479e..3260fc639b07 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -4833,42 +4833,7 @@ static void intel_pre_plane_update(struct intel_crtc *crtc) intel_set_memory_cxsr(dev_priv, false); } - /* - * IVB workaround: must disable low power watermarks for at least - * one frame before enabling scaling. LP watermarks can be re-enabled - * when scaling is disabled. - * - * WaCxSRDisabledForSpriteScaling:ivb - */ - if (pipe_config->disable_lp_wm) { - ilk_disable_lp_wm(dev); - intel_wait_for_vblank(dev, crtc->pipe); - } - - /* - * If we're doing a modeset, we're done. No need to do any pre-vblank - * watermark programming here. - */ - if (needs_modeset(&pipe_config->base)) - return; - - /* - * For platforms that support atomic watermarks, program the - * 'intermediate' watermarks immediately. On pre-gen9 platforms, these - * will be the intermediate values that are safe for both pre- and - * post- vblank; when vblank happens, the 'active' values will be set - * to the final 'target' values and we'll do this again to get the - * optimal watermarks. For gen9+ platforms, the values we program here - * will be the final target values which will get automatically latched - * at vblank time; no further programming will be necessary. - * - * If a platform hasn't been transitioned to atomic watermarks yet, - * we'll continue to update watermarks the old way, if flags tell - * us to. - */ - if (dev_priv->display.initial_watermarks != NULL) - dev_priv->display.initial_watermarks(pipe_config); - else if (pipe_config->wm_changed) + if (!needs_modeset(&pipe_config->base) && pipe_config->wm_changed) intel_update_watermarks(&crtc->base); } @@ -11914,11 +11879,6 @@ int intel_plane_atomic_calc_changes(struct drm_crtc_state *crtc_state, pipe_config->wm_changed = true; } - /* Pre-gen9 platforms need two-step watermark updates */ - if (pipe_config->wm_changed && INTEL_INFO(dev)->gen < 9 && - dev_priv->display.optimize_watermarks) - to_intel_crtc_state(crtc_state)->wm.need_postvbl_update = true; - if (visible || was_visible) intel_crtc->atomic.fb_bits |= to_intel_plane(plane)->frontbuffer_bit; @@ -12075,29 +12035,8 @@ static int intel_crtc_atomic_check(struct drm_crtc *crtc, ret = 0; if (dev_priv->display.compute_pipe_wm) { ret = dev_priv->display.compute_pipe_wm(intel_crtc, state); - if (ret) { - DRM_DEBUG_KMS("Target pipe watermarks are invalid\n"); - return ret; - } - } - - if (dev_priv->display.compute_intermediate_wm && - !to_intel_atomic_state(state)->skip_intermediate_wm) { - if (WARN_ON(!dev_priv->display.compute_pipe_wm)) - return 0; - - /* - * Calculate 'intermediate' watermarks that satisfy both the - * old state and the new state. We can program these - * immediately. - */ - ret = dev_priv->display.compute_intermediate_wm(crtc->dev, - intel_crtc, - pipe_config); - if (ret) { - DRM_DEBUG_KMS("No valid intermediate pipe watermarks are possible\n"); + if (ret) return ret; - } } if (INTEL_INFO(dev)->gen >= 9) { @@ -13562,7 +13501,6 @@ static int intel_atomic_commit(struct drm_device *dev, struct drm_i915_private *dev_priv = dev->dev_private; struct drm_crtc_state *crtc_state; struct drm_crtc *crtc; - struct intel_crtc_state *intel_cstate; int ret = 0, i; bool hw_check = intel_state->modeset; @@ -13662,20 +13600,6 @@ static int intel_atomic_commit(struct drm_device *dev, drm_atomic_helper_wait_for_vblanks(dev, state); - /* - * Now that the vblank has passed, we can go ahead and program the - * optimal watermarks on platforms that need two-step watermark - * programming. - * - * TODO: Move this (and other cleanup) to an async worker eventually. - */ - for_each_crtc_in_state(state, crtc, crtc_state, i) { - intel_cstate = to_intel_crtc_state(crtc->state); - - if (dev_priv->display.optimize_watermarks) - dev_priv->display.optimize_watermarks(intel_cstate); - } - mutex_lock(&dev->struct_mutex); drm_atomic_helper_cleanup_planes(dev, state); mutex_unlock(&dev->struct_mutex); @@ -15342,7 +15266,7 @@ static void sanitize_watermarks(struct drm_device *dev) int i; /* Only supported on platforms that use atomic watermark design */ - if (!dev_priv->display.optimize_watermarks) + if (!dev_priv->display.program_watermarks) return; /* @@ -15363,13 +15287,6 @@ retry: if (WARN_ON(IS_ERR(state))) goto fail; - /* - * Hardware readout is the only time we don't want to calculate - * intermediate watermarks (since we don't trust the current - * watermarks). - */ - to_intel_atomic_state(state)->skip_intermediate_wm = true; - ret = intel_atomic_check(dev, state); if (ret) { /* @@ -15392,8 +15309,7 @@ retry: for_each_crtc_in_state(state, crtc, cstate, i) { struct intel_crtc_state *cs = to_intel_crtc_state(cstate); - cs->wm.need_postvbl_update = true; - dev_priv->display.optimize_watermarks(cs); + dev_priv->display.program_watermarks(cs); } drm_atomic_state_free(state); diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 059b46e22c31..15917e3a3352 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -260,12 +260,6 @@ struct intel_atomic_state { struct intel_shared_dpll_config shared_dpll[I915_NUM_PLLS]; struct intel_wm_config wm_config; - - /* - * Current watermarks can't be trusted during hardware readout, so - * don't bother calculating intermediate watermarks. - */ - bool skip_intermediate_wm; }; struct intel_plane_state { @@ -513,29 +507,13 @@ struct intel_crtc_state { struct { /* - * Optimal watermarks, programmed post-vblank when this state - * is committed. + * optimal watermarks, programmed post-vblank when this state + * is committed */ union { struct intel_pipe_wm ilk; struct skl_pipe_wm skl; } optimal; - - /* - * Intermediate watermarks; these can be programmed immediately - * since they satisfy both the current configuration we're - * switching away from and the new configuration we're switching - * to. - */ - struct intel_pipe_wm intermediate; - - /* - * Platforms with two-step watermark programming will need to - * update watermark programming post-vblank to switch from the - * safe intermediate watermarks to the optimal final - * watermarks. - */ - bool need_postvbl_update; } wm; }; @@ -622,7 +600,6 @@ struct intel_crtc { struct intel_pipe_wm ilk; struct skl_pipe_wm skl; } active; - /* allow CxSR on this pipe */ bool cxsr_allowed; } wm; @@ -1583,7 +1560,6 @@ void skl_wm_get_hw_state(struct drm_device *dev); void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv, struct skl_ddb_allocation *ddb /* out */); uint32_t ilk_pipe_pixel_rate(const struct intel_crtc_state *pipe_config); -bool ilk_disable_lp_wm(struct drm_device *dev); /* intel_sdvo.c */ bool intel_sdvo_init(struct drm_device *dev, diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 180555553fa2..20bf854eae8c 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -2275,29 +2275,6 @@ static void skl_setup_wm_latency(struct drm_device *dev) intel_print_wm_latency(dev, "Gen9 Plane", dev_priv->wm.skl_latency); } -static bool ilk_validate_pipe_wm(struct drm_device *dev, - struct intel_pipe_wm *pipe_wm) -{ - /* LP0 watermark maximums depend on this pipe alone */ - const struct intel_wm_config config = { - .num_pipes_active = 1, - .sprites_enabled = pipe_wm->sprites_enabled, - .sprites_scaled = pipe_wm->sprites_scaled, - }; - 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); - - /* At least LP0 must be valid */ - if (!ilk_validate_wm_level(0, &max, &pipe_wm->wm[0])) { - DRM_DEBUG_KMS("LP0 watermark invalid\n"); - return false; - } - - return true; -} - /* Compute new watermarks for the pipe */ static int ilk_compute_pipe_wm(struct intel_crtc *intel_crtc, struct drm_atomic_state *state) @@ -2312,6 +2289,10 @@ static int ilk_compute_pipe_wm(struct intel_crtc *intel_crtc, struct intel_plane_state *sprstate = NULL; struct intel_plane_state *curstate = NULL; int level, max_level = ilk_wm_max_level(dev); + /* LP0 watermark maximums depend on this pipe alone */ + struct intel_wm_config config = { + .num_pipes_active = 1, + }; struct ilk_wm_maximums max; cstate = intel_atomic_get_crtc_state(state, intel_crtc); @@ -2335,18 +2316,21 @@ static int ilk_compute_pipe_wm(struct intel_crtc *intel_crtc, curstate = to_intel_plane_state(ps); } - pipe_wm->pipe_enabled = cstate->base.active; - pipe_wm->sprites_enabled = sprstate->visible; - pipe_wm->sprites_scaled = sprstate->visible && + config.sprites_enabled = sprstate->visible; + config.sprites_scaled = sprstate->visible && (drm_rect_width(&sprstate->dst) != drm_rect_width(&sprstate->src) >> 16 || drm_rect_height(&sprstate->dst) != drm_rect_height(&sprstate->src) >> 16); + pipe_wm->pipe_enabled = cstate->base.active; + pipe_wm->sprites_enabled = config.sprites_enabled; + pipe_wm->sprites_scaled = config.sprites_scaled; + /* ILK/SNB: LP2+ watermarks only w/o sprites */ if (INTEL_INFO(dev)->gen <= 6 && sprstate->visible) max_level = 1; /* ILK/SNB/IVB: LP1+ watermarks only w/o scaling */ - if (pipe_wm->sprites_scaled) + if (config.sprites_scaled) max_level = 0; ilk_compute_wm_level(dev_priv, intel_crtc, 0, cstate, @@ -2355,8 +2339,12 @@ static int ilk_compute_pipe_wm(struct intel_crtc *intel_crtc, if (IS_HASWELL(dev) || IS_BROADWELL(dev)) pipe_wm->linetime = hsw_compute_linetime_wm(dev, cstate); - if (!ilk_validate_pipe_wm(dev, pipe_wm)) - return false; + /* 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 */ + if (!ilk_validate_wm_level(0, &max, &pipe_wm->wm[0])) + return -EINVAL; ilk_compute_wm_reg_maximums(dev, 1, &max); @@ -2380,59 +2368,6 @@ static int ilk_compute_pipe_wm(struct intel_crtc *intel_crtc, return 0; } -/* - * Build a set of 'intermediate' watermark values that satisfy both the old - * state and the new state. These can be programmed to the hardware - * immediately. - */ -static int ilk_compute_intermediate_wm(struct drm_device *dev, - struct intel_crtc *intel_crtc, - struct intel_crtc_state *newstate) -{ - struct intel_pipe_wm *a = &newstate->wm.intermediate; - struct intel_pipe_wm *b = &intel_crtc->wm.active.ilk; - int level, max_level = ilk_wm_max_level(dev); - - /* - * Start with the final, target watermarks, then combine with the - * currently active watermarks to get values that are safe both before - * and after the vblank. - */ - *a = newstate->wm.optimal.ilk; - a->pipe_enabled |= b->pipe_enabled; - a->sprites_enabled |= b->sprites_enabled; - a->sprites_scaled |= b->sprites_scaled; - - for (level = 0; level <= max_level; level++) { - struct intel_wm_level *a_wm = &a->wm[level]; - const struct intel_wm_level *b_wm = &b->wm[level]; - - a_wm->enable &= b_wm->enable; - a_wm->pri_val = max(a_wm->pri_val, b_wm->pri_val); - a_wm->spr_val = max(a_wm->spr_val, b_wm->spr_val); - a_wm->cur_val = max(a_wm->cur_val, b_wm->cur_val); - a_wm->fbc_val = max(a_wm->fbc_val, b_wm->fbc_val); - } - - /* - * We need to make sure that these merged watermark values are - * actually a valid configuration themselves. If they're not, - * there's no safe way to transition from the old state to - * the new state, so we need to fail the atomic transaction. - */ - if (!ilk_validate_pipe_wm(dev, a)) - return -EINVAL; - - /* - * If our intermediate WM are identical to the final WM, then we can - * omit the post-vblank programming; only update if it's different. - */ - if (memcmp(a, &newstate->wm.optimal.ilk, sizeof(*a)) != 0) - newstate->wm.need_postvbl_update = false; - - return 0; -} - /* * Merge the watermarks from all active pipes for a specific level. */ @@ -2445,7 +2380,9 @@ static void ilk_merge_wm_level(struct drm_device *dev, ret_wm->enable = true; for_each_intel_crtc(dev, intel_crtc) { - const struct intel_pipe_wm *active = &intel_crtc->wm.active.ilk; + const struct intel_crtc_state *cstate = + to_intel_crtc_state(intel_crtc->base.state); + const struct intel_pipe_wm *active = &cstate->wm.optimal.ilk; const struct intel_wm_level *wm = &active->wm[level]; if (!active->pipe_enabled) @@ -2593,14 +2530,15 @@ static void ilk_compute_wm_results(struct drm_device *dev, /* LP0 register values */ for_each_intel_crtc(dev, intel_crtc) { + const struct intel_crtc_state *cstate = + to_intel_crtc_state(intel_crtc->base.state); enum pipe pipe = intel_crtc->pipe; - const struct intel_wm_level *r = - &intel_crtc->wm.active.ilk.wm[0]; + const struct intel_wm_level *r = &cstate->wm.optimal.ilk.wm[0]; if (WARN_ON(!r->enable)) continue; - results->wm_linetime[pipe] = intel_crtc->wm.active.ilk.linetime; + results->wm_linetime[pipe] = cstate->wm.optimal.ilk.linetime; results->wm_pipe[pipe] = (r->pri_val << WM0_PIPE_PLANE_SHIFT) | @@ -2807,7 +2745,7 @@ static void ilk_write_wm_values(struct drm_i915_private *dev_priv, dev_priv->wm.hw = *results; } -bool ilk_disable_lp_wm(struct drm_device *dev) +static bool ilk_disable_lp_wm(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -3700,9 +3638,11 @@ static void ilk_compute_wm_config(struct drm_device *dev, } } -static void ilk_program_watermarks(struct drm_i915_private *dev_priv) +static void ilk_program_watermarks(struct intel_crtc_state *cstate) { - struct drm_device *dev = dev_priv->dev; + struct drm_crtc *crtc = cstate->base.crtc; + struct drm_device *dev = crtc->dev; + struct drm_i915_private *dev_priv = to_i915(dev); struct intel_pipe_wm lp_wm_1_2 = {}, lp_wm_5_6 = {}, *best_lp_wm; struct ilk_wm_maximums max; struct intel_wm_config config = {}; @@ -3733,28 +3673,28 @@ static void ilk_program_watermarks(struct drm_i915_private *dev_priv) ilk_write_wm_values(dev_priv, &results); } -static void ilk_initial_watermarks(struct intel_crtc_state *cstate) +static void ilk_update_wm(struct drm_crtc *crtc) { - struct drm_i915_private *dev_priv = to_i915(cstate->base.crtc->dev); - struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc); - - mutex_lock(&dev_priv->wm.wm_mutex); - intel_crtc->wm.active.ilk = cstate->wm.intermediate; - ilk_program_watermarks(dev_priv); - mutex_unlock(&dev_priv->wm.wm_mutex); -} + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + struct intel_crtc_state *cstate = to_intel_crtc_state(crtc->state); -static void ilk_optimize_watermarks(struct intel_crtc_state *cstate) -{ - struct drm_i915_private *dev_priv = to_i915(cstate->base.crtc->dev); - struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc); + WARN_ON(cstate->base.active != intel_crtc->active); - mutex_lock(&dev_priv->wm.wm_mutex); - if (cstate->wm.need_postvbl_update) { - intel_crtc->wm.active.ilk = cstate->wm.optimal.ilk; - ilk_program_watermarks(dev_priv); + /* + * IVB workaround: must disable low power watermarks for at least + * one frame before enabling scaling. LP watermarks can be re-enabled + * when scaling is disabled. + * + * WaCxSRDisabledForSpriteScaling:ivb + */ + if (cstate->disable_lp_wm) { + ilk_disable_lp_wm(crtc->dev); + intel_wait_for_vblank(crtc->dev, intel_crtc->pipe); } - mutex_unlock(&dev_priv->wm.wm_mutex); + + intel_crtc->wm.active.ilk = cstate->wm.optimal.ilk; + + ilk_program_watermarks(cstate); } static void skl_pipe_wm_active_state(uint32_t val, @@ -7081,13 +7021,9 @@ void intel_init_pm(struct drm_device *dev) dev_priv->wm.spr_latency[1] && dev_priv->wm.cur_latency[1]) || (!IS_GEN5(dev) && dev_priv->wm.pri_latency[0] && dev_priv->wm.spr_latency[0] && dev_priv->wm.cur_latency[0])) { + dev_priv->display.update_wm = ilk_update_wm; dev_priv->display.compute_pipe_wm = ilk_compute_pipe_wm; - dev_priv->display.compute_intermediate_wm = - ilk_compute_intermediate_wm; - dev_priv->display.initial_watermarks = - ilk_initial_watermarks; - dev_priv->display.optimize_watermarks = - ilk_optimize_watermarks; + dev_priv->display.program_watermarks = ilk_program_watermarks; } else { DRM_DEBUG_KMS("Failed to read display plane latency. " "Disable CxSR\n"); -- cgit v1.2.3 From ac484963f979b6ab490183f0e09a3a17175f5758 Mon Sep 17 00:00:00 2001 From: Ville Syrjälä Date: Wed, 20 Jan 2016 21:05:26 +0200 Subject: drm/i915: Standardize on 'cpp' for bytes per pixel MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We more or less randomly call the "bytes per pixel" value 'cpp', 'bytes_per_pixel', 'pixel_size', or even 'bpp'. Let's just pick one and stick to it. I've chosen 'cpp'. Signed-off-by: Ville Syrjälä Link: http://patchwork.freedesktop.org/patch/msgid/1453316739-13296-6-git-send-email-ville.syrjala@linux.intel.com Reviewed-by: Daniel Vetter --- drivers/gpu/drm/i915/intel_display.c | 22 +++--- drivers/gpu/drm/i915/intel_pm.c | 128 +++++++++++++++++------------------ drivers/gpu/drm/i915/intel_sprite.c | 34 ++++------ 3 files changed, 87 insertions(+), 97 deletions(-) (limited to 'drivers/gpu/drm/i915/intel_pm.c') diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 97af94a12960..23cce7df74b0 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -2709,7 +2709,7 @@ static void i9xx_update_primary_plane(struct drm_plane *primary, u32 linear_offset; u32 dspcntr; i915_reg_t reg = DSPCNTR(plane); - int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0); + int cpp = drm_format_plane_cpp(fb->pixel_format, 0); int x = plane_state->src.x1 >> 16; int y = plane_state->src.y1 >> 16; @@ -2769,13 +2769,12 @@ static void i9xx_update_primary_plane(struct drm_plane *primary, if (IS_G4X(dev)) dspcntr |= DISPPLANE_TRICKLE_FEED_DISABLE; - linear_offset = y * fb->pitches[0] + x * pixel_size; + linear_offset = y * fb->pitches[0] + x * cpp; if (INTEL_INFO(dev)->gen >= 4) { intel_crtc->dspaddr_offset = intel_compute_tile_offset(dev_priv, &x, &y, - fb->modifier[0], - pixel_size, + fb->modifier[0], cpp, fb->pitches[0]); linear_offset -= intel_crtc->dspaddr_offset; } else { @@ -2792,7 +2791,7 @@ static void i9xx_update_primary_plane(struct drm_plane *primary, data and adding to linear_offset*/ linear_offset += (crtc_state->pipe_src_h - 1) * fb->pitches[0] + - (crtc_state->pipe_src_w - 1) * pixel_size; + (crtc_state->pipe_src_w - 1) * cpp; } intel_crtc->adjusted_x = x; @@ -2840,7 +2839,7 @@ static void ironlake_update_primary_plane(struct drm_plane *primary, u32 linear_offset; u32 dspcntr; i915_reg_t reg = DSPCNTR(plane); - int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0); + int cpp = drm_format_plane_cpp(fb->pixel_format, 0); int x = plane_state->src.x1 >> 16; int y = plane_state->src.y1 >> 16; @@ -2879,11 +2878,10 @@ static void ironlake_update_primary_plane(struct drm_plane *primary, if (!IS_HASWELL(dev) && !IS_BROADWELL(dev)) dspcntr |= DISPPLANE_TRICKLE_FEED_DISABLE; - linear_offset = y * fb->pitches[0] + x * pixel_size; + linear_offset = y * fb->pitches[0] + x * cpp; intel_crtc->dspaddr_offset = intel_compute_tile_offset(dev_priv, &x, &y, - fb->modifier[0], - pixel_size, + fb->modifier[0], cpp, fb->pitches[0]); linear_offset -= intel_crtc->dspaddr_offset; if (plane_state->base.rotation == BIT(DRM_ROTATE_180)) { @@ -2897,7 +2895,7 @@ static void ironlake_update_primary_plane(struct drm_plane *primary, data and adding to linear_offset*/ linear_offset += (crtc_state->pipe_src_h - 1) * fb->pitches[0] + - (crtc_state->pipe_src_w - 1) * pixel_size; + (crtc_state->pipe_src_w - 1) * cpp; } } @@ -14682,10 +14680,12 @@ u32 intel_fb_pitch_limit(struct drm_device *dev, uint64_t fb_modifier, u32 gen = INTEL_INFO(dev)->gen; if (gen >= 9) { + int cpp = drm_format_plane_cpp(pixel_format, 0); + /* "The stride in bytes must not exceed the of the size of 8K * pixels and 32K bytes." */ - return min(8192*drm_format_plane_cpp(pixel_format, 0), 32768); + return min(8192 * cpp, 32768); } else if (gen >= 5 && !IS_VALLEYVIEW(dev) && !IS_CHERRYVIEW(dev)) { return 32*1024; } else if (gen >= 4) { diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 20bf854eae8c..31bc4ea395ac 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -548,7 +548,7 @@ static const struct intel_watermark_params i845_wm_info = { * intel_calculate_wm - calculate watermark level * @clock_in_khz: pixel clock * @wm: chip FIFO params - * @pixel_size: display pixel size + * @cpp: bytes per pixel * @latency_ns: memory latency for the platform * * Calculate the watermark level (the level at which the display plane will @@ -564,8 +564,7 @@ static const struct intel_watermark_params i845_wm_info = { */ static unsigned long intel_calculate_wm(unsigned long clock_in_khz, const struct intel_watermark_params *wm, - int fifo_size, - int pixel_size, + int fifo_size, int cpp, unsigned long latency_ns) { long entries_required, wm_size; @@ -576,7 +575,7 @@ static unsigned long intel_calculate_wm(unsigned long clock_in_khz, * clocks go from a few thousand to several hundred thousand. * latency is usually a few thousand */ - entries_required = ((clock_in_khz / 1000) * pixel_size * latency_ns) / + entries_required = ((clock_in_khz / 1000) * cpp * latency_ns) / 1000; entries_required = DIV_ROUND_UP(entries_required, wm->cacheline_size); @@ -640,13 +639,13 @@ static void pineview_update_wm(struct drm_crtc *unused_crtc) crtc = single_enabled_crtc(dev); if (crtc) { const struct drm_display_mode *adjusted_mode = &to_intel_crtc(crtc)->config->base.adjusted_mode; - int pixel_size = crtc->primary->state->fb->bits_per_pixel / 8; + int cpp = drm_format_plane_cpp(crtc->primary->state->fb->pixel_format, 0); int clock = adjusted_mode->crtc_clock; /* Display SR */ wm = intel_calculate_wm(clock, &pineview_display_wm, pineview_display_wm.fifo_size, - pixel_size, latency->display_sr); + cpp, latency->display_sr); reg = I915_READ(DSPFW1); reg &= ~DSPFW_SR_MASK; reg |= FW_WM(wm, SR); @@ -656,7 +655,7 @@ static void pineview_update_wm(struct drm_crtc *unused_crtc) /* cursor SR */ wm = intel_calculate_wm(clock, &pineview_cursor_wm, pineview_display_wm.fifo_size, - pixel_size, latency->cursor_sr); + cpp, latency->cursor_sr); reg = I915_READ(DSPFW3); reg &= ~DSPFW_CURSOR_SR_MASK; reg |= FW_WM(wm, CURSOR_SR); @@ -665,7 +664,7 @@ static void pineview_update_wm(struct drm_crtc *unused_crtc) /* Display HPLL off SR */ wm = intel_calculate_wm(clock, &pineview_display_hplloff_wm, pineview_display_hplloff_wm.fifo_size, - pixel_size, latency->display_hpll_disable); + cpp, latency->display_hpll_disable); reg = I915_READ(DSPFW3); reg &= ~DSPFW_HPLL_SR_MASK; reg |= FW_WM(wm, HPLL_SR); @@ -674,7 +673,7 @@ static void pineview_update_wm(struct drm_crtc *unused_crtc) /* cursor HPLL off SR */ wm = intel_calculate_wm(clock, &pineview_cursor_hplloff_wm, pineview_display_hplloff_wm.fifo_size, - pixel_size, latency->cursor_hpll_disable); + cpp, latency->cursor_hpll_disable); reg = I915_READ(DSPFW3); reg &= ~DSPFW_HPLL_CURSOR_MASK; reg |= FW_WM(wm, HPLL_CURSOR); @@ -698,7 +697,7 @@ static bool g4x_compute_wm0(struct drm_device *dev, { struct drm_crtc *crtc; const struct drm_display_mode *adjusted_mode; - int htotal, hdisplay, clock, pixel_size; + int htotal, hdisplay, clock, cpp; int line_time_us, line_count; int entries, tlb_miss; @@ -713,10 +712,10 @@ 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->primary->state->fb->bits_per_pixel / 8; + cpp = drm_format_plane_cpp(crtc->primary->state->fb->pixel_format, 0); /* Use the small buffer method to calculate plane watermark */ - entries = ((clock * pixel_size / 1000) * display_latency_ns) / 1000; + entries = ((clock * cpp / 1000) * display_latency_ns) / 1000; tlb_miss = display->fifo_size*display->cacheline_size - hdisplay * 8; if (tlb_miss > 0) entries += tlb_miss; @@ -728,7 +727,7 @@ static bool g4x_compute_wm0(struct drm_device *dev, /* Use the large buffer method to calculate cursor watermark */ line_time_us = max(htotal * 1000 / clock, 1); line_count = (cursor_latency_ns / line_time_us + 1000) / 1000; - entries = line_count * crtc->cursor->state->crtc_w * pixel_size; + entries = line_count * crtc->cursor->state->crtc_w * cpp; tlb_miss = cursor->fifo_size*cursor->cacheline_size - hdisplay * 8; if (tlb_miss > 0) entries += tlb_miss; @@ -784,7 +783,7 @@ static bool g4x_compute_srwm(struct drm_device *dev, { struct drm_crtc *crtc; const struct drm_display_mode *adjusted_mode; - int hdisplay, htotal, pixel_size, clock; + int hdisplay, htotal, cpp, clock; unsigned long line_time_us; int line_count, line_size; int small, large; @@ -800,21 +799,21 @@ 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->primary->state->fb->bits_per_pixel / 8; + cpp = drm_format_plane_cpp(crtc->primary->state->fb->pixel_format, 0); line_time_us = max(htotal * 1000 / clock, 1); line_count = (latency_ns / line_time_us + 1000) / 1000; - line_size = hdisplay * pixel_size; + line_size = hdisplay * cpp; /* Use the minimum of the small and large buffer method for primary */ - small = ((clock * pixel_size / 1000) * latency_ns) / 1000; + small = ((clock * cpp / 1000) * latency_ns) / 1000; large = line_count * line_size; entries = DIV_ROUND_UP(min(small, large), display->cacheline_size); *display_wm = entries + display->guard_size; /* calculate the self-refresh watermark for display cursor */ - entries = line_count * pixel_size * crtc->cursor->state->crtc_w; + entries = line_count * cpp * crtc->cursor->state->crtc_w; entries = DIV_ROUND_UP(entries, cursor->cacheline_size); *cursor_wm = entries + cursor->guard_size; @@ -906,13 +905,13 @@ enum vlv_wm_level { static unsigned int vlv_wm_method2(unsigned int pixel_rate, unsigned int pipe_htotal, unsigned int horiz_pixels, - unsigned int bytes_per_pixel, + unsigned int cpp, unsigned int latency) { unsigned int ret; ret = (latency * pixel_rate) / (pipe_htotal * 10000); - ret = (ret + 1) * horiz_pixels * bytes_per_pixel; + ret = (ret + 1) * horiz_pixels * cpp; ret = DIV_ROUND_UP(ret, 64); return ret; @@ -941,7 +940,7 @@ static uint16_t vlv_compute_wm_level(struct intel_plane *plane, int level) { struct drm_i915_private *dev_priv = to_i915(plane->base.dev); - int clock, htotal, pixel_size, width, wm; + int clock, htotal, cpp, width, wm; if (dev_priv->wm.pri_latency[level] == 0) return USHRT_MAX; @@ -949,7 +948,7 @@ static uint16_t vlv_compute_wm_level(struct intel_plane *plane, if (!state->visible) return 0; - pixel_size = drm_format_plane_cpp(state->base.fb->pixel_format, 0); + cpp = drm_format_plane_cpp(state->base.fb->pixel_format, 0); clock = crtc->config->base.adjusted_mode.crtc_clock; htotal = crtc->config->base.adjusted_mode.crtc_htotal; width = crtc->config->pipe_src_w; @@ -965,7 +964,7 @@ static uint16_t vlv_compute_wm_level(struct intel_plane *plane, */ wm = 63; } else { - wm = vlv_wm_method2(clock, htotal, width, pixel_size, + wm = vlv_wm_method2(clock, htotal, width, cpp, dev_priv->wm.pri_latency[level] * 10); } @@ -1439,7 +1438,7 @@ 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->primary->state->fb->bits_per_pixel / 8; + int cpp = drm_format_plane_cpp(crtc->primary->state->fb->pixel_format, 0); unsigned long line_time_us; int entries; @@ -1447,7 +1446,7 @@ static void i965_update_wm(struct drm_crtc *unused_crtc) /* Use ns/us then divide to preserve precision */ entries = (((sr_latency_ns / line_time_us) + 1000) / 1000) * - pixel_size * hdisplay; + cpp * hdisplay; entries = DIV_ROUND_UP(entries, I915_FIFO_LINE_SIZE); srwm = I965_FIFO_SIZE - entries; if (srwm < 0) @@ -1457,7 +1456,7 @@ static void i965_update_wm(struct drm_crtc *unused_crtc) entries, srwm); entries = (((sr_latency_ns / line_time_us) + 1000) / 1000) * - pixel_size * crtc->cursor->state->crtc_w; + cpp * crtc->cursor->state->crtc_w; entries = DIV_ROUND_UP(entries, i965_cursor_wm_info.cacheline_size); cursor_sr = i965_cursor_wm_info.fifo_size - @@ -1518,7 +1517,7 @@ 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->primary->state->fb->bits_per_pixel / 8; + int cpp = drm_format_plane_cpp(crtc->primary->state->fb->pixel_format, 0); if (IS_GEN2(dev)) cpp = 4; @@ -1540,7 +1539,7 @@ 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->primary->state->fb->bits_per_pixel / 8; + int cpp = drm_format_plane_cpp(crtc->primary->state->fb->pixel_format, 0); if (IS_GEN2(dev)) cpp = 4; @@ -1586,7 +1585,7 @@ 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->primary->state->fb->bits_per_pixel / 8; + int cpp = drm_format_plane_cpp(enabled->primary->state->fb->pixel_format, 0); unsigned long line_time_us; int entries; @@ -1594,7 +1593,7 @@ static void i9xx_update_wm(struct drm_crtc *unused_crtc) /* Use ns/us then divide to preserve precision */ entries = (((sr_latency_ns / line_time_us) + 1000) / 1000) * - pixel_size * hdisplay; + cpp * hdisplay; entries = DIV_ROUND_UP(entries, wm_info->cacheline_size); DRM_DEBUG_KMS("self-refresh entries: %d\n", entries); srwm = wm_info->fifo_size - entries; @@ -1685,15 +1684,14 @@ uint32_t ilk_pipe_pixel_rate(const struct intel_crtc_state *pipe_config) } /* latency must be in 0.1us units. */ -static uint32_t ilk_wm_method1(uint32_t pixel_rate, uint8_t bytes_per_pixel, - uint32_t latency) +static uint32_t ilk_wm_method1(uint32_t pixel_rate, uint8_t cpp, uint32_t latency) { uint64_t ret; if (WARN(latency == 0, "Latency value missing\n")) return UINT_MAX; - ret = (uint64_t) pixel_rate * bytes_per_pixel * latency; + ret = (uint64_t) pixel_rate * cpp * latency; ret = DIV_ROUND_UP_ULL(ret, 64 * 10000) + 2; return ret; @@ -1701,7 +1699,7 @@ static uint32_t ilk_wm_method1(uint32_t pixel_rate, uint8_t bytes_per_pixel, /* latency must be in 0.1us units. */ static uint32_t ilk_wm_method2(uint32_t pixel_rate, uint32_t pipe_htotal, - uint32_t horiz_pixels, uint8_t bytes_per_pixel, + uint32_t horiz_pixels, uint8_t cpp, uint32_t latency) { uint32_t ret; @@ -1712,13 +1710,13 @@ static uint32_t ilk_wm_method2(uint32_t pixel_rate, uint32_t pipe_htotal, return UINT_MAX; ret = (latency * pixel_rate) / (pipe_htotal * 10000); - ret = (ret + 1) * horiz_pixels * bytes_per_pixel; + ret = (ret + 1) * horiz_pixels * cpp; ret = DIV_ROUND_UP(ret, 64) + 2; return ret; } static uint32_t ilk_wm_fbc(uint32_t pri_val, uint32_t horiz_pixels, - uint8_t bytes_per_pixel) + uint8_t cpp) { /* * Neither of these should be possible since this function shouldn't be @@ -1726,12 +1724,12 @@ static uint32_t ilk_wm_fbc(uint32_t pri_val, uint32_t horiz_pixels, * extra paranoid to avoid a potential divide-by-zero if we screw up * elsewhere in the driver. */ - if (WARN_ON(!bytes_per_pixel)) + if (WARN_ON(!cpp)) return 0; if (WARN_ON(!horiz_pixels)) return 0; - return DIV_ROUND_UP(pri_val * 64, horiz_pixels * bytes_per_pixel) + 2; + return DIV_ROUND_UP(pri_val * 64, horiz_pixels * cpp) + 2; } struct ilk_wm_maximums { @@ -1750,13 +1748,14 @@ static uint32_t ilk_compute_pri_wm(const struct intel_crtc_state *cstate, uint32_t mem_value, bool is_lp) { - int bpp = pstate->base.fb ? pstate->base.fb->bits_per_pixel / 8 : 0; + int cpp = pstate->base.fb ? + drm_format_plane_cpp(pstate->base.fb->pixel_format, 0) : 0; uint32_t method1, method2; if (!cstate->base.active || !pstate->visible) return 0; - method1 = ilk_wm_method1(ilk_pipe_pixel_rate(cstate), bpp, mem_value); + method1 = ilk_wm_method1(ilk_pipe_pixel_rate(cstate), cpp, mem_value); if (!is_lp) return method1; @@ -1764,8 +1763,7 @@ static uint32_t ilk_compute_pri_wm(const struct intel_crtc_state *cstate, method2 = ilk_wm_method2(ilk_pipe_pixel_rate(cstate), cstate->base.adjusted_mode.crtc_htotal, drm_rect_width(&pstate->dst), - bpp, - mem_value); + cpp, mem_value); return min(method1, method2); } @@ -1778,18 +1776,18 @@ static uint32_t ilk_compute_spr_wm(const struct intel_crtc_state *cstate, const struct intel_plane_state *pstate, uint32_t mem_value) { - int bpp = pstate->base.fb ? pstate->base.fb->bits_per_pixel / 8 : 0; + int cpp = pstate->base.fb ? + drm_format_plane_cpp(pstate->base.fb->pixel_format, 0) : 0; uint32_t method1, method2; if (!cstate->base.active || !pstate->visible) return 0; - method1 = ilk_wm_method1(ilk_pipe_pixel_rate(cstate), bpp, mem_value); + method1 = ilk_wm_method1(ilk_pipe_pixel_rate(cstate), cpp, mem_value); method2 = ilk_wm_method2(ilk_pipe_pixel_rate(cstate), cstate->base.adjusted_mode.crtc_htotal, drm_rect_width(&pstate->dst), - bpp, - mem_value); + cpp, mem_value); return min(method1, method2); } @@ -1801,7 +1799,8 @@ static uint32_t ilk_compute_cur_wm(const struct intel_crtc_state *cstate, const struct intel_plane_state *pstate, uint32_t mem_value) { - int bpp = pstate->base.fb ? pstate->base.fb->bits_per_pixel / 8 : 0; + int cpp = pstate->base.fb ? + drm_format_plane_cpp(pstate->base.fb->pixel_format, 0) : 0; if (!cstate->base.active || !pstate->visible) return 0; @@ -1809,8 +1808,7 @@ static uint32_t ilk_compute_cur_wm(const struct intel_crtc_state *cstate, return ilk_wm_method2(ilk_pipe_pixel_rate(cstate), cstate->base.adjusted_mode.crtc_htotal, drm_rect_width(&pstate->dst), - bpp, - mem_value); + cpp, mem_value); } /* Only for WM_LP. */ @@ -1818,12 +1816,13 @@ static uint32_t ilk_compute_fbc_wm(const struct intel_crtc_state *cstate, const struct intel_plane_state *pstate, uint32_t pri_val) { - int bpp = pstate->base.fb ? pstate->base.fb->bits_per_pixel / 8 : 0; + int cpp = pstate->base.fb ? + drm_format_plane_cpp(pstate->base.fb->pixel_format, 0) : 0; if (!cstate->base.active || !pstate->visible) return 0; - return ilk_wm_fbc(pri_val, drm_rect_width(&pstate->dst), bpp); + return ilk_wm_fbc(pri_val, drm_rect_width(&pstate->dst), cpp); } static unsigned int ilk_display_fifo_size(const struct drm_device *dev) @@ -3042,26 +3041,25 @@ static uint32_t skl_pipe_pixel_rate(const struct intel_crtc_state *config) /* * The max latency should be 257 (max the punit can code is 255 and we add 2us - * for the read latency) and bytes_per_pixel should always be <= 8, so that + * for the read latency) and cpp should always be <= 8, so that * should allow pixel_rate up to ~2 GHz which seems sufficient since max * 2xcdclk is 1350 MHz and the pixel rate should never exceed that. */ -static uint32_t skl_wm_method1(uint32_t pixel_rate, uint8_t bytes_per_pixel, - uint32_t latency) +static uint32_t skl_wm_method1(uint32_t pixel_rate, uint8_t cpp, uint32_t latency) { uint32_t wm_intermediate_val, ret; if (latency == 0) return UINT_MAX; - wm_intermediate_val = latency * pixel_rate * bytes_per_pixel / 512; + wm_intermediate_val = latency * pixel_rate * cpp / 512; ret = DIV_ROUND_UP(wm_intermediate_val, 1000); return ret; } static uint32_t skl_wm_method2(uint32_t pixel_rate, uint32_t pipe_htotal, - uint32_t horiz_pixels, uint8_t bytes_per_pixel, + uint32_t horiz_pixels, uint8_t cpp, uint64_t tiling, uint32_t latency) { uint32_t ret; @@ -3071,7 +3069,7 @@ static uint32_t skl_wm_method2(uint32_t pixel_rate, uint32_t pipe_htotal, if (latency == 0) return UINT_MAX; - plane_bytes_per_line = horiz_pixels * bytes_per_pixel; + plane_bytes_per_line = horiz_pixels * cpp; if (tiling == I915_FORMAT_MOD_Y_TILED || tiling == I915_FORMAT_MOD_Yf_TILED) { @@ -3121,23 +3119,21 @@ static bool skl_compute_plane_wm(const struct drm_i915_private *dev_priv, uint32_t plane_bytes_per_line, plane_blocks_per_line; uint32_t res_blocks, res_lines; uint32_t selected_result; - uint8_t bytes_per_pixel; + uint8_t cpp; if (latency == 0 || !cstate->base.active || !fb) return false; - bytes_per_pixel = drm_format_plane_cpp(fb->pixel_format, 0); + cpp = drm_format_plane_cpp(fb->pixel_format, 0); method1 = skl_wm_method1(skl_pipe_pixel_rate(cstate), - bytes_per_pixel, - latency); + cpp, latency); method2 = skl_wm_method2(skl_pipe_pixel_rate(cstate), cstate->base.adjusted_mode.crtc_htotal, cstate->pipe_src_w, - bytes_per_pixel, - fb->modifier[0], + cpp, fb->modifier[0], latency); - plane_bytes_per_line = cstate->pipe_src_w * bytes_per_pixel; + plane_bytes_per_line = cstate->pipe_src_w * cpp; plane_blocks_per_line = DIV_ROUND_UP(plane_bytes_per_line, 512); if (fb->modifier[0] == I915_FORMAT_MOD_Y_TILED || @@ -3145,11 +3141,11 @@ static bool skl_compute_plane_wm(const struct drm_i915_private *dev_priv, uint32_t min_scanlines = 4; uint32_t y_tile_minimum; if (intel_rotation_90_or_270(plane->state->rotation)) { - int bpp = (fb->pixel_format == DRM_FORMAT_NV12) ? + int cpp = (fb->pixel_format == DRM_FORMAT_NV12) ? drm_format_plane_cpp(fb->pixel_format, 1) : drm_format_plane_cpp(fb->pixel_format, 0); - switch (bpp) { + switch (cpp) { case 1: min_scanlines = 16; break; diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c index f1ee7db0811a..a2582c455b36 100644 --- a/drivers/gpu/drm/i915/intel_sprite.c +++ b/drivers/gpu/drm/i915/intel_sprite.c @@ -351,7 +351,7 @@ vlv_update_plane(struct drm_plane *dplane, int plane = intel_plane->plane; u32 sprctl; u32 sprsurf_offset, linear_offset; - int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0); + int cpp = drm_format_plane_cpp(fb->pixel_format, 0); const struct drm_intel_sprite_colorkey *key = &plane_state->ckey; int crtc_x = plane_state->dst.x1; int crtc_y = plane_state->dst.y1; @@ -422,10 +422,9 @@ vlv_update_plane(struct drm_plane *dplane, crtc_w--; crtc_h--; - linear_offset = y * fb->pitches[0] + x * pixel_size; + linear_offset = y * fb->pitches[0] + x * cpp; sprsurf_offset = intel_compute_tile_offset(dev_priv, &x, &y, - fb->modifier[0], - pixel_size, + fb->modifier[0], cpp, fb->pitches[0]); linear_offset -= sprsurf_offset; @@ -434,7 +433,7 @@ vlv_update_plane(struct drm_plane *dplane, x += src_w; y += src_h; - linear_offset += src_h * fb->pitches[0] + src_w * pixel_size; + linear_offset += src_h * fb->pitches[0] + src_w * cpp; } if (key->flags) { @@ -494,7 +493,7 @@ ivb_update_plane(struct drm_plane *plane, enum pipe pipe = intel_plane->pipe; u32 sprctl, sprscale = 0; u32 sprsurf_offset, linear_offset; - int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0); + int cpp = drm_format_plane_cpp(fb->pixel_format, 0); const struct drm_intel_sprite_colorkey *key = &plane_state->ckey; int crtc_x = plane_state->dst.x1; int crtc_y = plane_state->dst.y1; @@ -556,10 +555,9 @@ ivb_update_plane(struct drm_plane *plane, if (crtc_w != src_w || crtc_h != src_h) sprscale = SPRITE_SCALE_ENABLE | (src_w << 16) | src_h; - linear_offset = y * fb->pitches[0] + x * pixel_size; + linear_offset = y * fb->pitches[0] + x * cpp; sprsurf_offset = intel_compute_tile_offset(dev_priv, &x, &y, - fb->modifier[0], - pixel_size, + fb->modifier[0], cpp, fb->pitches[0]); linear_offset -= sprsurf_offset; @@ -570,8 +568,7 @@ ivb_update_plane(struct drm_plane *plane, if (!IS_HASWELL(dev) && !IS_BROADWELL(dev)) { x += src_w; y += src_h; - linear_offset += src_h * fb->pitches[0] + - src_w * pixel_size; + linear_offset += src_h * fb->pitches[0] + src_w * cpp; } } @@ -637,7 +634,7 @@ ilk_update_plane(struct drm_plane *plane, int pipe = intel_plane->pipe; u32 dvscntr, dvsscale; u32 dvssurf_offset, linear_offset; - int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0); + int cpp = drm_format_plane_cpp(fb->pixel_format, 0); const struct drm_intel_sprite_colorkey *key = &plane_state->ckey; int crtc_x = plane_state->dst.x1; int crtc_y = plane_state->dst.y1; @@ -695,10 +692,9 @@ ilk_update_plane(struct drm_plane *plane, if (crtc_w != src_w || crtc_h != src_h) dvsscale = DVS_SCALE_ENABLE | (src_w << 16) | src_h; - linear_offset = y * fb->pitches[0] + x * pixel_size; + linear_offset = y * fb->pitches[0] + x * cpp; dvssurf_offset = intel_compute_tile_offset(dev_priv, &x, &y, - fb->modifier[0], - pixel_size, + fb->modifier[0], cpp, fb->pitches[0]); linear_offset -= dvssurf_offset; @@ -707,7 +703,7 @@ ilk_update_plane(struct drm_plane *plane, x += src_w; y += src_h; - linear_offset += src_h * fb->pitches[0] + src_w * pixel_size; + linear_offset += src_h * fb->pitches[0] + src_w * cpp; } if (key->flags) { @@ -772,7 +768,6 @@ intel_check_sprite_plane(struct drm_plane *plane, int hscale, vscale; int max_scale, min_scale; bool can_scale; - int pixel_size; if (!fb) { state->visible = false; @@ -894,6 +889,7 @@ intel_check_sprite_plane(struct drm_plane *plane, /* Check size restrictions when scaling */ if (state->visible && (src_w != crtc_w || src_h != crtc_h)) { unsigned int width_bytes; + int cpp = drm_format_plane_cpp(fb->pixel_format, 0); WARN_ON(!can_scale); @@ -905,9 +901,7 @@ intel_check_sprite_plane(struct drm_plane *plane, if (src_w < 3 || src_h < 3) state->visible = false; - pixel_size = drm_format_plane_cpp(fb->pixel_format, 0); - width_bytes = ((src_x * pixel_size) & 63) + - src_w * pixel_size; + width_bytes = ((src_x * cpp) & 63) + src_w * cpp; if (INTEL_INFO(dev)->gen < 9 && (src_w > 2048 || src_h > 2048 || width_bytes > 4096 || fb->pitches[0] > 4096)) { -- cgit v1.2.3 From 9c06f6744d663205395f88d98aef87edcd3ce5bd Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Fri, 29 Jan 2016 14:52:27 +0200 Subject: drm/i915/chv: Fix error path in GPU freq helpers Atm we wouldn't catch these errors or on the error path we would end up with a division-by-zero, fix this up. Signed-off-by: Imre Deak Reviewed-by: David Weinehall Link: http://patchwork.freedesktop.org/patch/msgid/1454071949-24677-2-git-send-email-imre.deak@intel.com --- drivers/gpu/drm/i915/intel_pm.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'drivers/gpu/drm/i915/intel_pm.c') diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 31bc4ea395ac..a47b8f219357 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -7185,9 +7185,10 @@ static int chv_gpu_freq(struct drm_i915_private *dev_priv, int val) { int div, czclk_freq = DIV_ROUND_CLOSEST(dev_priv->czclk_freq, 1000); - div = vlv_gpu_freq_div(czclk_freq) / 2; + div = vlv_gpu_freq_div(czclk_freq); if (div < 0) return div; + div /= 2; return DIV_ROUND_CLOSEST(czclk_freq * val, 2 * div) / 2; } @@ -7196,9 +7197,10 @@ static int chv_freq_opcode(struct drm_i915_private *dev_priv, int val) { int mul, czclk_freq = DIV_ROUND_CLOSEST(dev_priv->czclk_freq, 1000); - mul = vlv_gpu_freq_div(czclk_freq) / 2; + mul = vlv_gpu_freq_div(czclk_freq); if (mul < 0) return mul; + mul /= 2; /* CHV needs even values */ return DIV_ROUND_CLOSEST(val * 2 * mul, czclk_freq) * 2; -- cgit v1.2.3 From b2435692dbb709d4c8ff3b2f2815c9b8423b72bb Mon Sep 17 00:00:00 2001 From: Matt Roper Date: Tue, 2 Feb 2016 22:06:51 -0800 Subject: drm/i915: Pretend cursor is always on for ILK-style WM calculations (v2) Due to our lack of two-step watermark programming, our driver has historically pretended that the cursor plane is always on for the purpose of watermark calculations; this helps avoid serious flickering when the cursor turns off/on (e.g., when the user moves the mouse pointer to a different screen). That workaround was accidentally dropped as we started working toward atomic watermark updates. Since we still aren't quite there yet with two-stage updates, we need to resurrect the workaround and treat the cursor as always active. v2: Tweak cursor width calculations slightly to more closely match the logic we used before the atomic overhaul began. (Ville) Cc: simdev11@outlook.com Cc: manfred.kitzbichler@gmail.com Cc: drm-intel-fixes@lists.freedesktop.org Reported-by: simdev11@outlook.com Reported-by: manfred.kitzbichler@gmail.com Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=93892 Fixes: 43d59eda1 ("drm/i915: Eliminate usage of plane_wm_parameters from ILK-style WM code (v2)") Signed-off-by: Matt Roper Link: http://patchwork.freedesktop.org/patch/msgid/1454479611-6804-1-git-send-email-matthew.d.roper@intel.com --- drivers/gpu/drm/i915/intel_pm.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'drivers/gpu/drm/i915/intel_pm.c') diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index a47b8f219357..3da7935c1665 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -1799,16 +1799,20 @@ static uint32_t ilk_compute_cur_wm(const struct intel_crtc_state *cstate, const struct intel_plane_state *pstate, uint32_t mem_value) { - int cpp = pstate->base.fb ? - drm_format_plane_cpp(pstate->base.fb->pixel_format, 0) : 0; + /* + * We treat the cursor plane as always-on for the purposes of watermark + * calculation. Until we have two-stage watermark programming merged, + * this is necessary to avoid flickering. + */ + int cpp = 4; + int width = pstate->visible ? pstate->base.crtc_w : 64; - if (!cstate->base.active || !pstate->visible) + if (!cstate->base.active) return 0; return ilk_wm_method2(ilk_pipe_pixel_rate(cstate), cstate->base.adjusted_mode.crtc_htotal, - drm_rect_width(&pstate->dst), - cpp, mem_value); + width, cpp, mem_value); } /* Only for WM_LP. */ -- cgit v1.2.3 From 274008e89d78ded4324c7d81d9d106f62f5d5727 Mon Sep 17 00:00:00 2001 From: Sagar Arun Kamble Date: Sat, 6 Feb 2016 00:13:29 +0530 Subject: drm/i915/bxt: Check BIOS RC6 setup before enabling RC6 RC6 setup is shared between BIOS and Driver. BIOS sets up subset of RC6 setup registers. If those are not setup Driver should not enable RC6. For implementing this, driver can check RC_CTRL0 and RC_CTRL1 values to know if BIOS has enabled HW/SW RC6. This will also enable user to control RC6 using BIOS settings alone. RC6 related instability can be avoided by disabling via BIOS settings till driver fixes it. v2: Had placed logic in gen8 function by mistake. Fixed it. Ensuring RPM is not enabled in case BIOS disabled RC6. v3: Need to disable RPM if RC6 is disabled due to BIOS settings. (Daniel) Runtime PM enabling happens before gen9_enable_rc6. Moved the updation of enable_rc6 parameter in intel_uncore_sanitize. v4: Added elaborate check for BIOS RC6 setup. Prepared check_pctx for bxt. (Imre) v5: Caching reserved stolen base and size in the driver private data. Reorganized RC6 setup check. Moved from gen9_enable_rc6 to intel_uncore_sanitize. (Imre) v6: Rebasing on the patch submitted by Imre that moves gem_init_stolen earlier in the load. v7: Removed PWRCTX_MAXCNT_VCSUNIT1 check as it applies to SKL. (Imre) v8: Fixed formatting and checkpatch issues. Fixed functional issue where RC6 ctx size check was missing. (Imre) Cc: Imre Deak Signed-off-by: Sagar Arun Kamble Signed-off-by: Imre Deak Link: http://patchwork.freedesktop.org/patch/msgid/1454697809-22113-1-git-send-email-sagar.a.kamble@intel.com --- drivers/gpu/drm/i915/i915_gem_gtt.h | 2 ++ drivers/gpu/drm/i915/i915_gem_stolen.c | 3 ++ drivers/gpu/drm/i915/i915_reg.h | 11 +++++++ drivers/gpu/drm/i915/intel_drv.h | 1 + drivers/gpu/drm/i915/intel_pm.c | 53 ++++++++++++++++++++++++++++++++-- drivers/gpu/drm/i915/intel_uncore.c | 2 ++ 6 files changed, 70 insertions(+), 2 deletions(-) (limited to 'drivers/gpu/drm/i915/intel_pm.c') diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h index f520c90e5377..66a6da2396a2 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.h +++ b/drivers/gpu/drm/i915/i915_gem_gtt.h @@ -342,6 +342,8 @@ struct i915_gtt { size_t stolen_size; /* Total size of stolen memory */ size_t stolen_usable_size; /* Total size minus BIOS reserved */ + size_t stolen_reserved_base; + size_t stolen_reserved_size; u64 mappable_end; /* End offset that we can CPU map */ struct io_mapping *mappable; /* Mapping to our CPU mappable region */ phys_addr_t mappable_base; /* PA of our GMADR */ diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c index c384dc9c8a63..ba1a00d815d3 100644 --- a/drivers/gpu/drm/i915/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/i915_gem_stolen.c @@ -458,6 +458,9 @@ int i915_gem_init_stolen(struct drm_device *dev) return 0; } + dev_priv->gtt.stolen_reserved_base = reserved_base; + dev_priv->gtt.stolen_reserved_size = reserved_size; + /* It is possible for the reserved area to end before the end of stolen * memory, so just consider the start. */ reserved_total = stolen_top - reserved_base; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 6732fc139196..188ad5de020f 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -6785,6 +6785,16 @@ enum skl_disp_power_wells { #define VLV_PMWGICZ _MMIO(0x1300a4) +#define RC6_LOCATION _MMIO(0xD40) +#define RC6_CTX_IN_DRAM (1 << 0) +#define RC6_CTX_BASE _MMIO(0xD48) +#define RC6_CTX_BASE_MASK 0xFFFFFFF0 +#define PWRCTX_MAXCNT_RCSUNIT _MMIO(0x2054) +#define PWRCTX_MAXCNT_VCSUNIT0 _MMIO(0x12054) +#define PWRCTX_MAXCNT_BCSUNIT _MMIO(0x22054) +#define PWRCTX_MAXCNT_VECSUNIT _MMIO(0x1A054) +#define PWRCTX_MAXCNT_VCSUNIT1 _MMIO(0x1C054) +#define IDLE_TIME_MASK 0xFFFFF #define FORCEWAKE _MMIO(0xA18C) #define FORCEWAKE_VLV _MMIO(0x1300b0) #define FORCEWAKE_ACK_VLV _MMIO(0x1300b4) @@ -6923,6 +6933,7 @@ enum skl_disp_power_wells { #define GEN6_RPDEUC _MMIO(0xA084) #define GEN6_RPDEUCSW _MMIO(0xA088) #define GEN6_RC_STATE _MMIO(0xA094) +#define RC6_STATE (1 << 18) #define GEN6_RC1_WAKE_RATE_LIMIT _MMIO(0xA098) #define GEN6_RC6_WAKE_RATE_LIMIT _MMIO(0xA09C) #define GEN6_RC6pp_WAKE_RATE_LIMIT _MMIO(0xA0A0) diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 93ba14a3bb76..1251a7ae4a6a 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -1566,6 +1566,7 @@ void skl_wm_get_hw_state(struct drm_device *dev); void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv, struct skl_ddb_allocation *ddb /* out */); uint32_t ilk_pipe_pixel_rate(const struct intel_crtc_state *pipe_config); +int sanitize_rc6_option(const struct drm_device *dev, int enable_rc6); /* intel_sdvo.c */ bool intel_sdvo_init(struct drm_device *dev, diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 3da7935c1665..379eabe093cb 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -4562,12 +4562,62 @@ static void intel_print_rc6_info(struct drm_device *dev, u32 mode) onoff(mode & GEN6_RC_CTL_RC6_ENABLE)); } -static int sanitize_rc6_option(const struct drm_device *dev, int enable_rc6) +static bool bxt_check_bios_rc6_setup(const struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + bool enable_rc6 = true; + unsigned long rc6_ctx_base; + + if (!(I915_READ(RC6_LOCATION) & RC6_CTX_IN_DRAM)) { + DRM_DEBUG_KMS("RC6 Base location not set properly.\n"); + enable_rc6 = false; + } + + /* + * The exact context size is not known for BXT, so assume a page size + * for this check. + */ + rc6_ctx_base = I915_READ(RC6_CTX_BASE) & RC6_CTX_BASE_MASK; + if (!((rc6_ctx_base >= dev_priv->gtt.stolen_reserved_base) && + (rc6_ctx_base + PAGE_SIZE <= dev_priv->gtt.stolen_reserved_base + + dev_priv->gtt.stolen_reserved_size))) { + DRM_DEBUG_KMS("RC6 Base address not as expected.\n"); + enable_rc6 = false; + } + + if (!(((I915_READ(PWRCTX_MAXCNT_RCSUNIT) & IDLE_TIME_MASK) > 1) && + ((I915_READ(PWRCTX_MAXCNT_VCSUNIT0) & IDLE_TIME_MASK) > 1) && + ((I915_READ(PWRCTX_MAXCNT_BCSUNIT) & IDLE_TIME_MASK) > 1) && + ((I915_READ(PWRCTX_MAXCNT_VECSUNIT) & IDLE_TIME_MASK) > 1))) { + DRM_DEBUG_KMS("Engine Idle wait time not set properly.\n"); + enable_rc6 = false; + } + + if (!(I915_READ(GEN6_RC_CONTROL) & (GEN6_RC_CTL_RC6_ENABLE | + GEN6_RC_CTL_HW_ENABLE)) && + ((I915_READ(GEN6_RC_CONTROL) & GEN6_RC_CTL_HW_ENABLE) || + !(I915_READ(GEN6_RC_STATE) & RC6_STATE))) { + DRM_DEBUG_KMS("HW/SW RC6 is not enabled by BIOS.\n"); + enable_rc6 = false; + } + + return enable_rc6; +} + +int sanitize_rc6_option(const struct drm_device *dev, int enable_rc6) { /* No RC6 before Ironlake and code is gone for ilk. */ if (INTEL_INFO(dev)->gen < 6) return 0; + if (!enable_rc6) + return 0; + + if (IS_BROXTON(dev) && !bxt_check_bios_rc6_setup(dev)) { + DRM_INFO("RC6 disabled by BIOS\n"); + return 0; + } + /* Respect the kernel parameter if it is set */ if (enable_rc6 >= 0) { int mask; @@ -6057,7 +6107,6 @@ void intel_init_gt_powersave(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - i915.enable_rc6 = sanitize_rc6_option(dev, i915.enable_rc6); /* * RPM depends on RC6 to save restore the GT HW context, so make RC6 a * requirement. diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index bfa79e5c214e..436d8f2b8682 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -400,6 +400,8 @@ void intel_uncore_early_sanitize(struct drm_device *dev, bool restore_forcewake) void intel_uncore_sanitize(struct drm_device *dev) { + i915.enable_rc6 = sanitize_rc6_option(dev, i915.enable_rc6); + /* BIOS often leaves RC6 enabled, but disable it for hw init */ intel_disable_gt_powersave(dev); } -- cgit v1.2.3 From ee504898777b7d14a6058fc1f1a93d02d974de87 Mon Sep 17 00:00:00 2001 From: Tvrtko Ursulin Date: Thu, 11 Feb 2016 10:27:30 +0000 Subject: drm/i915: Fix struct mutex vs. RPS lock inversion MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit RPS lock must be taken before the struct_mutex to avoid locking inversion. So stop grabbing it for the whole powersave initialization and instead only take it during the sections which need it. Also, struct_mutex is not needed any more since dedicated RPS lock was added in: commit 4fc688ce79772496503d22263d61b071a8fb596e Author: Jesse Barnes Date: Fri Nov 2 11:14:01 2012 -0700 drm/i915: protect RPS/RC6 related accesses (including PCU) with a new mutex Based on prototype patch by Chris Wilson and a subsequent mailing list discussion involving Ville, Imre, Chris and Daniel. v2: More details in the commit. v3: Use drm_gem_object_unreference_unlocked. (Chris Wilson) Signed-off-by: Tvrtko Ursulin Cc: Chris Wilson Cc: Ville Syrjälä Cc: Imre Deak Cc: Daniel Vetter Reviewed-by: Chris Wilson --- drivers/gpu/drm/i915/intel_display.c | 4 ---- drivers/gpu/drm/i915/intel_pm.c | 9 ++++----- 2 files changed, 4 insertions(+), 9 deletions(-) (limited to 'drivers/gpu/drm/i915/intel_pm.c') diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 0811dd136c56..4d30bca0b26b 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -15971,9 +15971,7 @@ void intel_modeset_gem_init(struct drm_device *dev) struct drm_i915_gem_object *obj; int ret; - mutex_lock(&dev->struct_mutex); intel_init_gt_powersave(dev); - mutex_unlock(&dev->struct_mutex); intel_modeset_init_hw(dev); @@ -16053,9 +16051,7 @@ void intel_modeset_cleanup(struct drm_device *dev) intel_cleanup_overlay(dev); - mutex_lock(&dev->struct_mutex); intel_cleanup_gt_powersave(dev); - mutex_unlock(&dev->struct_mutex); intel_teardown_gmbus(dev); } diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 379eabe093cb..8e869f183404 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -5229,8 +5229,6 @@ static void cherryview_setup_pctx(struct drm_device *dev) u32 pcbr; int pctx_size = 32*1024; - WARN_ON(!mutex_is_locked(&dev->struct_mutex)); - pcbr = I915_READ(VLV_PCBR); if ((pcbr >> VLV_PCBR_ADDR_SHIFT) == 0) { DRM_DEBUG_DRIVER("BIOS didn't set up PCBR, fixing up\n"); @@ -5252,7 +5250,7 @@ static void valleyview_setup_pctx(struct drm_device *dev) u32 pcbr; int pctx_size = 24*1024; - WARN_ON(!mutex_is_locked(&dev->struct_mutex)); + mutex_lock(&dev->struct_mutex); pcbr = I915_READ(VLV_PCBR); if (pcbr) { @@ -5280,7 +5278,7 @@ static void valleyview_setup_pctx(struct drm_device *dev) pctx = i915_gem_object_create_stolen(dev, pctx_size); if (!pctx) { DRM_DEBUG("not enough stolen space for PCTX, disabling\n"); - return; + goto out; } pctx_paddr = dev_priv->mm.stolen_base + pctx->stolen->start; @@ -5289,6 +5287,7 @@ static void valleyview_setup_pctx(struct drm_device *dev) out: DRM_DEBUG_DRIVER("PCBR: 0x%08x\n", I915_READ(VLV_PCBR)); dev_priv->vlv_pctx = pctx; + mutex_unlock(&dev->struct_mutex); } static void valleyview_cleanup_pctx(struct drm_device *dev) @@ -5298,7 +5297,7 @@ static void valleyview_cleanup_pctx(struct drm_device *dev) if (WARN_ON(!dev_priv->vlv_pctx)) return; - drm_gem_object_unreference(&dev_priv->vlv_pctx->base); + drm_gem_object_unreference_unlocked(&dev_priv->vlv_pctx->base); dev_priv->vlv_pctx = NULL; } -- cgit v1.2.3 From 84f1b20f095919c17d9f4a94665b96b0e677e1f4 Mon Sep 17 00:00:00 2001 From: Tvrtko Ursulin Date: Thu, 11 Feb 2016 10:27:32 +0000 Subject: drm/i915/ilk: Move register read under spinlock Code does read-modify-write but the read was outside the lock. It is fine since the caller holds struct mutex, but if we correct this we open up the opportunity for decreasing the mutex duration time since the call to ironlake_enable_drps does not need it any longer since it is covered by the mchdev_lock lock. Signed-off-by: Tvrtko Ursulin Cc: Daniel Vetter Reviewed-by: Chris Wilson Link: http://patchwork.freedesktop.org/patch/msgid/1455186452-13691-2-git-send-email-tvrtko.ursulin@linux.intel.com --- drivers/gpu/drm/i915/intel_pm.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'drivers/gpu/drm/i915/intel_pm.c') diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 8e869f183404..b63cdb23b222 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -4116,11 +4116,13 @@ bool ironlake_set_drps(struct drm_device *dev, u8 val) static void ironlake_enable_drps(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - u32 rgvmodectl = I915_READ(MEMMODECTL); + u32 rgvmodectl; u8 fmax, fmin, fstart, vstart; spin_lock_irq(&mchdev_lock); + rgvmodectl = I915_READ(MEMMODECTL); + /* Enable temp reporting */ I915_WRITE16(PMMISC, I915_READ(PMMISC) | MCPPCE_EN); I915_WRITE16(TSC1, I915_READ(TSC1) | TSE); @@ -6240,8 +6242,8 @@ void intel_enable_gt_powersave(struct drm_device *dev) return; if (IS_IRONLAKE_M(dev)) { - mutex_lock(&dev->struct_mutex); ironlake_enable_drps(dev); + mutex_lock(&dev->struct_mutex); intel_init_emon(dev); mutex_unlock(&dev->struct_mutex); } else if (INTEL_INFO(dev)->gen >= 6) { -- cgit v1.2.3 From 4d800030238878c1a98d1d3a37a3d673eea661ce Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Wed, 17 Feb 2016 16:31:29 +0200 Subject: drm/i915/skl: Ensure HW is powered during DDB HW state readout The assumption when adding the intel_display_power_is_enabled() checks was that if it returns success the power can't be turned off afterwards during the HW access, which is guaranteed by modeset locks. This isn't always true, so make sure we hold a dedicated reference for the time of the access. Spotted-by: Mika Kuoppala Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=93441 CC: Chris Wilson Signed-off-by: Imre Deak Reviewed-by: Mika Kuoppala Link: http://patchwork.freedesktop.org/patch/msgid/1455719489-3008-1-git-send-email-imre.deak@intel.com --- drivers/gpu/drm/i915/intel_pm.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'drivers/gpu/drm/i915/intel_pm.c') diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index b63cdb23b222..347d4df49a9b 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -2851,7 +2851,10 @@ void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv, memset(ddb, 0, sizeof(*ddb)); for_each_pipe(dev_priv, pipe) { - if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PIPE(pipe))) + enum intel_display_power_domain power_domain; + + power_domain = POWER_DOMAIN_PIPE(pipe); + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) continue; for_each_plane(dev_priv, pipe, plane) { @@ -2863,6 +2866,8 @@ void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv, val = I915_READ(CUR_BUF_CFG(pipe)); skl_ddb_entry_init_from_hw(&ddb->plane[pipe][PLANE_CURSOR], val); + + intel_display_power_put(dev_priv, power_domain); } } -- cgit v1.2.3