drm/i915/skl: Update DDB values atomically with wms/plane attrs

Now that we can hook into update_crtcs and control the order in which we
update CRTCs at each modeset, we can finish the final step of fixing
Skylake's watermark handling by performing DDB updates at the same time
as plane updates and watermark updates.

The first major change in this patch is skl_update_crtcs(), which
handles ensuring that we order each CRTC update in our atomic commits
properly so that they honor the DDB flush order.

The second major change in this patch is the order in which we flush the
pipes. While the previous order may have worked, it can't be used in
this approach since it no longer will do the right thing. For example,
using the old ddb flush order:

We have pipes A, B, and C enabled, and we're disabling C. Initial ddb
allocation looks like this:

|   A   |   B   |xxxxxxx|

Since we're performing the ddb updates after performing any CRTC
disablements in intel_atomic_commit_tail(), the space to the right of
pipe B is unallocated.

1. Flush pipes with new allocation contained into old space. None
   apply, so we skip this
2. Flush pipes having their allocation reduced, but overlapping with a
   previous allocation. None apply, so we also skip this
3. Flush pipes that got more space allocated. This applies to A and B,
   giving us the following update order: A, B

This is wrong, since updating pipe A first will cause it to overlap with
B and potentially burst into flames. Our new order (see the code
comments for details) would update the pipes in the proper order: B, A.

As well, we calculate the order for each DDB update during the check
phase, and reference it later in the commit phase when we hit
skl_update_crtcs().

This long overdue patch fixes the rest of the underruns on Skylake.

Changes since v1:
 - Add skl_ddb_entry_write() for cursor into skl_write_cursor_wm()
Changes since v2:
 - Use the method for updating CRTCs that Ville suggested
 - In skl_update_wm(), only copy the watermarks for the crtc that was
   passed to us
Changes since v3:
 - Small comment fix in skl_ddb_allocation_overlaps()
Changes since v4:
 - Remove the second loop in intel_update_crtcs() and use Ville's
   suggestion for updating the ddb allocations in the right order
 - Get rid of the second loop and just use the ddb state as it updates
   to determine what order to update everything in (thanks for the
   suggestion Ville)
 - Simplify skl_ddb_allocation_overlaps()
 - Split actual overlap checking into it's own helper

Fixes: 0e8fb7ba7ca5 ("drm/i915/skl: Flush the WM configuration")
Fixes: 8211bd5bdf5e ("drm/i915/skl: Program the DDB allocation")
[omitting CC for stable, since this patch will need to be changed for
such backports first]

Testcase: kms_cursor_legacy
Testcase: plane-all-modeset-transition
Signed-off-by: Lyude <cpaul@redhat.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Daniel Vetter <daniel.vetter@intel.com>
Cc: Radhakrishna Sripada <radhakrishna.sripada@intel.com>
Cc: Hans de Goede <hdegoede@redhat.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1471961565-28540-2-git-send-email-cpaul@redhat.com

3 files changed, 132 insertions, 168 deletions

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 30372f9fcf66..a388ed547f73 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -13458,16 +13458,23 @@ static void verify_wm_state(struct drm_crtc *crtc,
 			  hw_entry->start, hw_entry->end);
 	}
 
-	/* cursor */
-	hw_entry = &hw_ddb.plane[pipe][PLANE_CURSOR];
-	sw_entry = &sw_ddb->plane[pipe][PLANE_CURSOR];
-
-	if (!skl_ddb_entry_equal(hw_entry, sw_entry)) {
-		DRM_ERROR("mismatch in DDB state pipe %c cursor "
-			  "(expected (%u,%u), found (%u,%u))\n",
-			  pipe_name(pipe),
-			  sw_entry->start, sw_entry->end,
-			  hw_entry->start, hw_entry->end);
+	/*
+	 * cursor
+	 * If the cursor plane isn't active, we may not have updated it's ddb
+	 * allocation. In that case since the ddb allocation will be updated
+	 * once the plane becomes visible, we can skip this check
+	 */
+	if (intel_crtc->cursor_addr) {
+		hw_entry = &hw_ddb.plane[pipe][PLANE_CURSOR];
+		sw_entry = &sw_ddb->plane[pipe][PLANE_CURSOR];
+
+		if (!skl_ddb_entry_equal(hw_entry, sw_entry)) {
+			DRM_ERROR("mismatch in DDB state pipe %c cursor "
+				  "(expected (%u,%u), found (%u,%u))\n",
+				  pipe_name(pipe),
+				  sw_entry->start, sw_entry->end,
+				  hw_entry->start, hw_entry->end);
+		}
 	}
 }
 
@@ -14219,6 +14226,65 @@ static void intel_update_crtcs(struct drm_atomic_state *state,
 	}
 }
 
+static void skl_update_crtcs(struct drm_atomic_state *state,
+			     unsigned int *crtc_vblank_mask)
+{
+	struct drm_device *dev = state->dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *old_crtc_state;
+	struct skl_ddb_allocation *new_ddb = &intel_state->wm_results.ddb;
+	struct skl_ddb_allocation *cur_ddb = &dev_priv->wm.skl_hw.ddb;
+	unsigned int updated = 0;
+	bool progress;
+	enum pipe pipe;
+
+	/*
+	 * Whenever the number of active pipes changes, we need to make sure we
+	 * update the pipes in the right order so that their ddb allocations
+	 * never overlap with eachother inbetween CRTC updates. Otherwise we'll
+	 * cause pipe underruns and other bad stuff.
+	 */
+	do {
+		int i;
+		progress = false;
+
+		for_each_crtc_in_state(state, crtc, old_crtc_state, i) {
+			bool vbl_wait = false;
+			unsigned int cmask = drm_crtc_mask(crtc);
+			pipe = to_intel_crtc(crtc)->pipe;
+
+			if (updated & cmask || !crtc->state->active)
+				continue;
+			if (skl_ddb_allocation_overlaps(state, cur_ddb, new_ddb,
+							pipe))
+				continue;
+
+			updated |= cmask;
+
+			/*
+			 * If this is an already active pipe, it's DDB changed,
+			 * and this isn't the last pipe that needs updating
+			 * then we need to wait for a vblank to pass for the
+			 * new ddb allocation to take effect.
+			 */
+			if (!skl_ddb_allocation_equals(cur_ddb, new_ddb, pipe) &&
+			    !crtc->state->active_changed &&
+			    intel_state->wm_results.dirty_pipes != updated)
+				vbl_wait = true;
+
+			intel_update_crtc(crtc, state, old_crtc_state,
+					  crtc_vblank_mask);
+
+			if (vbl_wait)
+				intel_wait_for_vblank(dev, pipe);
+
+			progress = true;
+		}
+	} while (progress);
+}
+
 static void intel_atomic_commit_tail(struct drm_atomic_state *state)
 {
 	struct drm_device *dev = state->dev;
@@ -15851,8 +15917,6 @@ void intel_init_display_hooks(struct drm_i915_private *dev_priv)
 		dev_priv->display.crtc_disable = i9xx_crtc_disable;
 	}
 
-	dev_priv->display.update_crtcs = intel_update_crtcs;
-
 	/* Returns the core display clock speed */
 	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv))
 		dev_priv->display.get_display_clock_speed =
@@ -15942,6 +16006,11 @@ void intel_init_display_hooks(struct drm_i915_private *dev_priv)
 			skl_modeset_calc_cdclk;
 	}
 
+	if (dev_priv->info.gen >= 9)
+		dev_priv->display.update_crtcs = skl_update_crtcs;
+	else
+		dev_priv->display.update_crtcs = intel_update_crtcs;
+
 	switch (INTEL_INFO(dev_priv)->gen) {
 	case 2:
 		dev_priv->display.queue_flip = intel_gen2_queue_flip;
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index f241a47b6e3a..debbc1b5b0f9 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1745,6 +1745,13 @@ void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv,
 bool skl_can_enable_sagv(struct drm_atomic_state *state);
 int skl_enable_sagv(struct drm_i915_private *dev_priv);
 int skl_disable_sagv(struct drm_i915_private *dev_priv);
+bool skl_ddb_allocation_equals(const struct skl_ddb_allocation *old,
+			       const struct skl_ddb_allocation *new,
+			       enum pipe pipe);
+bool skl_ddb_allocation_overlaps(struct drm_atomic_state *state,
+				 const struct skl_ddb_allocation *old,
+				 const struct skl_ddb_allocation *new,
+				 enum pipe pipe);
 void skl_write_cursor_wm(struct intel_crtc *intel_crtc,
 			 const struct skl_wm_values *wm);
 void skl_write_plane_wm(struct intel_crtc *intel_crtc,
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 2f4438d4af55..729d952174d8 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3851,6 +3851,11 @@ void skl_write_plane_wm(struct intel_crtc *intel_crtc,
 			   wm->plane[pipe][plane][level]);
 	}
 	I915_WRITE(PLANE_WM_TRANS(pipe, plane), wm->plane_trans[pipe][plane]);
+
+	skl_ddb_entry_write(dev_priv, PLANE_BUF_CFG(pipe, plane),
+			    &wm->ddb.plane[pipe][plane]);
+	skl_ddb_entry_write(dev_priv, PLANE_NV12_BUF_CFG(pipe, plane),
+			    &wm->ddb.y_plane[pipe][plane]);
 }
 
 void skl_write_cursor_wm(struct intel_crtc *intel_crtc,
@@ -3867,170 +3872,46 @@ void skl_write_cursor_wm(struct intel_crtc *intel_crtc,
 			   wm->plane[pipe][PLANE_CURSOR][level]);
 	}
 	I915_WRITE(CUR_WM_TRANS(pipe), wm->plane_trans[pipe][PLANE_CURSOR]);
-}
-
-static void skl_write_wm_values(struct drm_i915_private *dev_priv,
-				const struct skl_wm_values *new)
-{
-	struct drm_device *dev = &dev_priv->drm;
-	struct intel_crtc *crtc;
-
-	for_each_intel_crtc(dev, crtc) {
-		int i;
-		enum pipe pipe = crtc->pipe;
-
-		if ((new->dirty_pipes & drm_crtc_mask(&crtc->base)) == 0)
-			continue;
-		if (!crtc->active)
-			continue;
-
-		for (i = 0; i < intel_num_planes(crtc); i++) {
-			skl_ddb_entry_write(dev_priv,
-					    PLANE_BUF_CFG(pipe, i),
-					    &new->ddb.plane[pipe][i]);
-			skl_ddb_entry_write(dev_priv,
-					    PLANE_NV12_BUF_CFG(pipe, i),
-					    &new->ddb.y_plane[pipe][i]);
-		}
 
-		skl_ddb_entry_write(dev_priv, CUR_BUF_CFG(pipe),
-				    &new->ddb.plane[pipe][PLANE_CURSOR]);
-	}
+	skl_ddb_entry_write(dev_priv, CUR_BUF_CFG(pipe),
+			    &wm->ddb.plane[pipe][PLANE_CURSOR]);
 }
 
-/*
- * When setting up a new DDB allocation arrangement, we need to correctly
- * sequence the times at which the new allocations for the pipes are taken into
- * account or we'll have pipes fetching from space previously allocated to
- * another pipe.
- *
- * Roughly the sequence looks like:
- *  1. re-allocate the pipe(s) with the allocation being reduced and not
- *     overlapping with a previous light-up pipe (another way to put it is:
- *     pipes with their new allocation strickly included into their old ones).
- *  2. re-allocate the other pipes that get their allocation reduced
- *  3. allocate the pipes having their allocation increased
- *
- * Steps 1. and 2. are here to take care of the following case:
- * - Initially DDB looks like this:
- *     |   B    |   C    |
- * - enable pipe A.
- * - pipe B has a reduced DDB allocation that overlaps with the old pipe C
- *   allocation
- *     |  A  |  B  |  C  |
- *
- * We need to sequence the re-allocation: C, B, A (and not B, C, A).
- */
-
-static void
-skl_wm_flush_pipe(struct drm_i915_private *dev_priv, enum pipe pipe, int pass)
+bool skl_ddb_allocation_equals(const struct skl_ddb_allocation *old,
+			       const struct skl_ddb_allocation *new,
+			       enum pipe pipe)
 {
-	int plane;
-
-	DRM_DEBUG_KMS("flush pipe %c (pass %d)\n", pipe_name(pipe), pass);
-
-	for_each_plane(dev_priv, pipe, plane) {
-		I915_WRITE(PLANE_SURF(pipe, plane),
-			   I915_READ(PLANE_SURF(pipe, plane)));
-	}
-	I915_WRITE(CURBASE(pipe), I915_READ(CURBASE(pipe)));
+	return new->pipe[pipe].start == old->pipe[pipe].start &&
+	       new->pipe[pipe].end == old->pipe[pipe].end;
 }
 
-static bool
-skl_ddb_allocation_included(const struct skl_ddb_allocation *old,
-			    const struct skl_ddb_allocation *new,
-			    enum pipe pipe)
+static inline bool skl_ddb_entries_overlap(const struct skl_ddb_entry *a,
+					   const struct skl_ddb_entry *b)
 {
-	uint16_t old_size, new_size;
-
-	old_size = skl_ddb_entry_size(&old->pipe[pipe]);
-	new_size = skl_ddb_entry_size(&new->pipe[pipe]);
-
-	return old_size != new_size &&
-	       new->pipe[pipe].start >= old->pipe[pipe].start &&
-	       new->pipe[pipe].end <= old->pipe[pipe].end;
+	return a->start < b->end && b->start < a->end;
 }
 
-static void skl_flush_wm_values(struct drm_i915_private *dev_priv,
-				struct skl_wm_values *new_values)
+bool skl_ddb_allocation_overlaps(struct drm_atomic_state *state,
+				 const struct skl_ddb_allocation *old,
+				 const struct skl_ddb_allocation *new,
+				 enum pipe pipe)
 {
-	struct drm_device *dev = &dev_priv->drm;
-	struct skl_ddb_allocation *cur_ddb, *new_ddb;
-	bool reallocated[I915_MAX_PIPES] = {};
-	struct intel_crtc *crtc;
-	enum pipe pipe;
-
-	new_ddb = &new_values->ddb;
-	cur_ddb = &dev_priv->wm.skl_hw.ddb;
-
-	/*
-	 * First pass: flush the pipes with the new allocation contained into
-	 * the old space.
-	 *
-	 * We'll wait for the vblank on those pipes to ensure we can safely
-	 * re-allocate the freed space without this pipe fetching from it.
-	 */
-	for_each_intel_crtc(dev, crtc) {
-		if (!crtc->active)
-			continue;
-
-		pipe = crtc->pipe;
-
-		if (!skl_ddb_allocation_included(cur_ddb, new_ddb, pipe))
-			continue;
-
-		skl_wm_flush_pipe(dev_priv, pipe, 1);
-		intel_wait_for_vblank(dev, pipe);
-
-		reallocated[pipe] = true;
-	}
-
-
-	/*
-	 * Second pass: flush the pipes that are having their allocation
-	 * reduced, but overlapping with a previous allocation.
-	 *
-	 * Here as well we need to wait for the vblank to make sure the freed
-	 * space is not used anymore.
-	 */
-	for_each_intel_crtc(dev, crtc) {
-		if (!crtc->active)
-			continue;
+	struct drm_device *dev = state->dev;
+	struct intel_crtc *intel_crtc;
+	enum pipe otherp;
 
-		pipe = crtc->pipe;
+	for_each_intel_crtc(dev, intel_crtc) {
+		otherp = intel_crtc->pipe;
 
-		if (reallocated[pipe])
+		if (otherp == pipe)
 			continue;
 
-		if (skl_ddb_entry_size(&new_ddb->pipe[pipe]) <
-		    skl_ddb_entry_size(&cur_ddb->pipe[pipe])) {
-			skl_wm_flush_pipe(dev_priv, pipe, 2);
-			intel_wait_for_vblank(dev, pipe);
-			reallocated[pipe] = true;
-		}
+		if (skl_ddb_entries_overlap(&new->pipe[pipe],
+					    &old->pipe[otherp]))
+			return true;
 	}
 
-	/*
-	 * Third pass: flush the pipes that got more space allocated.
-	 *
-	 * We don't need to actively wait for the update here, next vblank
-	 * will just get more DDB space with the correct WM values.
-	 */
-	for_each_intel_crtc(dev, crtc) {
-		if (!crtc->active)
-			continue;
-
-		pipe = crtc->pipe;
-
-		/*
-		 * At this point, only the pipes more space than before are
-		 * left to re-allocate.
-		 */
-		if (reallocated[pipe])
-			continue;
-
-		skl_wm_flush_pipe(dev_priv, pipe, 3);
-	}
+	return false;
 }
 
 static int skl_update_pipe_wm(struct drm_crtc_state *cstate,
@@ -4232,7 +4113,7 @@ static void skl_update_wm(struct drm_crtc *crtc)
 	struct skl_wm_values *hw_vals = &dev_priv->wm.skl_hw;
 	struct intel_crtc_state *cstate = to_intel_crtc_state(crtc->state);
 	struct skl_pipe_wm *pipe_wm = &cstate->wm.skl.optimal;
-	int pipe;
+	enum pipe pipe = intel_crtc->pipe;
 
 	if ((results->dirty_pipes & drm_crtc_mask(crtc)) == 0)
 		return;
@@ -4241,15 +4122,22 @@ static void skl_update_wm(struct drm_crtc *crtc)
 
 	mutex_lock(&dev_priv->wm.wm_mutex);
 
-	skl_write_wm_values(dev_priv, results);
-	skl_flush_wm_values(dev_priv, results);
-
 	/*
-	 * Store the new configuration (but only for the pipes that have
-	 * changed; the other values weren't recomputed).
+	 * If this pipe isn't active already, we're going to be enabling it
+	 * very soon. Since it's safe to update a pipe's ddb allocation while
+	 * the pipe's shut off, just do so here. Already active pipes will have
+	 * their watermarks updated once we update their planes.
 	 */
-	for_each_pipe_masked(dev_priv, pipe, results->dirty_pipes)
-		skl_copy_wm_for_pipe(hw_vals, results, pipe);
+	if (crtc->state->active_changed) {
+		int plane;
+
+		for (plane = 0; plane < intel_num_planes(intel_crtc); plane++)
+			skl_write_plane_wm(intel_crtc, results, plane);
+
+		skl_write_cursor_wm(intel_crtc, results);
+	}
+
+	skl_copy_wm_for_pipe(hw_vals, results, pipe);
 
 	mutex_unlock(&dev_priv->wm.wm_mutex);
 }