Re: [PATCH v6 6/6] drm/i915/skl: Update DDB values atomically with wms/plane attrs

[Matt Roper]

On Wed, Aug 03, 2016 at 06:00:42PM +0300, Ville Syrjälä wrote:
> On Tue, Aug 02, 2016 at 06:37:37PM -0400, Lyude wrote:
> > 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()
> > 
> > Fixes: 0e8fb7ba7ca5 ("drm/i915/skl: Flush the WM configuration")
> > Fixes: 8211bd5bdf5e ("drm/i915/skl: Program the DDB allocation")
> > Signed-off-by: Lyude <cpaul@xxxxxxxxxx>
> > [omitting CC for stable, since this patch will need to be changed for
> > such backports first]
> > Cc: Ville Syrjälä <ville.syrjala@xxxxxxxxxxxxxxx>
> > Cc: Daniel Vetter <daniel.vetter@xxxxxxxxx>
> > Cc: Radhakrishna Sripada <radhakrishna.sripada@xxxxxxxxx>
> > Cc: Hans de Goede <hdegoede@xxxxxxxxxx>
> > Cc: Matt Roper <matthew.d.roper@xxxxxxxxx>
> > ---
> >  drivers/gpu/drm/i915/intel_display.c | 100 ++++++++++--
> >  drivers/gpu/drm/i915/intel_drv.h     |  10 ++
> >  drivers/gpu/drm/i915/intel_pm.c      | 288 ++++++++++++++++-------------------
> >  3 files changed, 233 insertions(+), 165 deletions(-)
> > 
> > diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
> > index 59cf513..06295f7 100644
> > --- a/drivers/gpu/drm/i915/intel_display.c
> > +++ b/drivers/gpu/drm/i915/intel_display.c
> > @@ -12897,16 +12897,23 @@ 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);
> > +		}
> >  	}
> >  }
> >  
> > @@ -13658,6 +13665,72 @@ static void intel_update_crtcs(struct drm_atomic_state *state,
> >  	}
> >  }
> >  
> > +static inline void
> > +skl_do_ddb_step(struct drm_atomic_state *state,
> > +		enum skl_ddb_step step)
> > +{
> > +	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
> > +	struct drm_crtc *crtc;
> > +	struct drm_crtc_state *old_crtc_state;
> > +	unsigned int crtc_vblank_mask; /* unused */
> > +	int i;
> > +
> > +	for_each_crtc_in_state(state, crtc, old_crtc_state, i) {
> > +		struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
> > +		struct intel_crtc_state *cstate =
> > +			to_intel_crtc_state(crtc->state);
> > +		bool vblank_wait = false;
> > +
> > +		if (cstate->wm.skl.ddb_realloc != step || !crtc->state->active)
> > +			continue;
> > +
> > +		/*
> > +		 * If we're changing the ddb allocation of this pipe to make
> > +		 * room for another pipe, we have to wait for the pipe's ddb
> > +		 * allocations to actually update by waiting for a vblank.
> > +		 * Otherwise we risk the next pipe updating before this pipe
> > +		 * finishes, resulting in the pipe fetching from ddb space for
> > +		 * the wrong pipe.
> > +		 *
> > +		 * However, if we know we don't have any more pipes to move
> > +		 * around, we can skip this wait and the new ddb allocation
> > +		 * will take effect at the start of the next vblank.
> > +		 */
> > +		switch (step) {
> > +		case SKL_DDB_STEP_NO_OVERLAP:
> > +		case SKL_DDB_STEP_OVERLAP:
> > +			if (step != intel_state->last_ddb_step)
> > +				vblank_wait = true;
> > +
> > +		/* drop through */
> > +		case SKL_DDB_STEP_FINAL:
> > +			DRM_DEBUG_KMS(
> > +			    "Updating [CRTC:%d:pipe %c] for DDB step %d\n",
> > +			    crtc->base.id, pipe_name(intel_crtc->pipe),
> > +			    step);
> > +
> > +		case SKL_DDB_STEP_NONE:
> > +			break;
> > +		}
> 
> Not sure we really need this step stuff. How about?
> 
> for_each_crtc
> 	if (crtc_needs_disabling)
> 		disable_crtc();
> 
> do {
> 	progress = false;
> 	wait_vbl_pipes=0;
> 	for_each_crtc() {
> 		if (!active || needs_modeset)
> 			continue;
> 		if (!ddb_changed)
> 			continue;
> 		if (new_ddb_overlaps_with_any_other_pipes_current_ddb)
> 			continue;
> 		commit;
> 		wait_vbl_pipes |= pipe;
> 		progress = true;
> 	}
> 	wait_vbls(wait_vbl_pipes);
> } while (progress);
> 
> for_each_crtc
> 	if (crtc_needs_enabling)
> 		enable_crtc();
> 	commit;
> }

Yeah, this approach looks nicer.  It's a bit simpler to follow code-wise
and doesn't require us to precompute any ordering during the check phase
so it's a bit more self-contained.  It should also scale properly if
future platforms decide to add more pipes.

> 
> Or if we're paranoid, we could also have an upper bound on the
> loop and assert that we never reach it.
> 
> 
> Though one thing I don't particularly like about this commit while
> changing the ddb approach is that it's going to make the update
> appear even less atomic. What I'd rather like to do for the normal
> commit path is this:
> 
> for_each_crtc
> 	if (crtc_needs_disabling)
> 		disable_planes
> for_each_crtc
> 	if (crtc_needs_disabling)
> 		disable_crtc
> for_each_crtc
> 	if (crtc_needs_enabling)
> 		enable_crtc
> for_each_crtc
> 	if (active)
> 		commit_planes;
> 
> That way everything would pop in and out as close together as possible.
> Hmm. Actually, I wonder... I'm thinking we should be able to enable all
> crtcs prior to entering the ddb commit loop, on account of no planes
> being enabled on those crtcs until we commit them. And if no planes are
> enabled, running the pipe w/o allocated ddb should be fine. So with that
> approach, I think we should be able to commit all planes within a few
> iterations of the loop, and hence within a few vblanks.

So this is pretty similar to what we do today, except that we do the
enabling/disabling of each CRTC and its planes all together, right?
Sounds reasonable to me, although I'm not sure we want to mix that
change in with the gen9-specific series Lyude is working on here.  Maybe
just do the new gen9 handler that way as part of that series and then
come back and update the non-gen9 handler to follow the new flow as a
separate patch?


Matt

> 
> > +
> > +		intel_update_crtc(crtc, state, old_crtc_state,
> > +				  &crtc_vblank_mask);
> > +
> > +		if (vblank_wait)
> > +			intel_wait_for_vblank(state->dev, intel_crtc->pipe);
> > +	}
> > +}
> > +
> > +static void skl_update_crtcs(struct drm_atomic_state *state,
> > +			     unsigned int *crtc_vblank_mask)
> > +{
> > +	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
> > +	enum skl_ddb_step step;
> > +
> > +	for (step = 0; step <= intel_state->last_ddb_step; step++)
> > +		skl_do_ddb_step(state, step);
> > +}
> > +
> >  static void intel_atomic_commit_tail(struct drm_atomic_state *state)
> >  {
> >  	struct drm_device *dev = state->dev;
> > @@ -15235,8 +15308,6 @@ 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 =
> > @@ -15326,6 +15397,11 @@ 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 1b444d3..cf5da83 100644
> > --- a/drivers/gpu/drm/i915/intel_drv.h
> > +++ b/drivers/gpu/drm/i915/intel_drv.h
> > @@ -334,6 +334,7 @@ struct intel_atomic_state {
> >  
> >  	/* Gen9+ only */
> >  	struct skl_wm_values wm_results;
> > +	int last_ddb_step;
> >  };
> >  
> >  struct intel_plane_state {
> > @@ -437,6 +438,13 @@ struct skl_pipe_wm {
> >  	uint32_t linetime;
> >  };
> >  
> > +enum skl_ddb_step {
> > +	SKL_DDB_STEP_NONE = 0,
> > +	SKL_DDB_STEP_NO_OVERLAP,
> > +	SKL_DDB_STEP_OVERLAP,
> > +	SKL_DDB_STEP_FINAL
> > +};
> > +
> >  struct intel_crtc_wm_state {
> >  	union {
> >  		struct {
> > @@ -467,6 +475,8 @@ struct intel_crtc_wm_state {
> >  			/* minimum block allocation */
> >  			uint16_t minimum_blocks[I915_MAX_PLANES];
> >  			uint16_t minimum_y_blocks[I915_MAX_PLANES];
> > +
> > +			enum skl_ddb_step ddb_realloc;
> >  		} skl;
> >  	};
> >  
> > diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
> > index 6f5beb3..636c90a 100644
> > --- a/drivers/gpu/drm/i915/intel_pm.c
> > +++ b/drivers/gpu/drm/i915/intel_pm.c
> > @@ -3816,6 +3816,11 @@ 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,
> > @@ -3832,170 +3837,51 @@ 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)
> > +static 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,
> > +skl_ddb_allocation_overlaps(struct drm_atomic_state *state,
> > +			    const struct skl_ddb_allocation *old,
> >  			    const struct skl_ddb_allocation *new,
> >  			    enum pipe pipe)
> >  {
> > -	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;
> > -}
> > -
> > -static void skl_flush_wm_values(struct drm_i915_private *dev_priv,
> > -				struct skl_wm_values *new_values)
> > -{
> > -	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;
> > -
> > -		pipe = crtc->pipe;
> > -
> > -		if (reallocated[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;
> > -		}
> > -	}
> > -
> > -	/*
> > -	 * 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;
> > +	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;
> >  
> >  		/*
> > -		 * At this point, only the pipes more space than before are
> > -		 * left to re-allocate.
> > +		 * When checking for overlaps, we don't want to:
> > +		 *  - Compare against ourselves
> > +		 *  - Compare against pipes that will be disabled in step 0
> > +		 *  - Compare against pipes that won't be enabled until step 3
> >  		 */
> > -		if (reallocated[pipe])
> > +		if (otherp == pipe || !new->pipe[otherp].end ||
> > +		    !old->pipe[otherp].end)
> >  			continue;
> >  
> > -		skl_wm_flush_pipe(dev_priv, pipe, 3);
> > +		if ((new->pipe[pipe].start >= old->pipe[otherp].start &&
> > +		     new->pipe[pipe].start < old->pipe[otherp].end) ||
> > +		    (old->pipe[otherp].start >= new->pipe[pipe].start &&
> > +		     old->pipe[otherp].start < new->pipe[pipe].end))
> > +			return true;
> >  	}
> > +
> > +	return false;
> >  }
> >  
> >  static int skl_update_pipe_wm(struct drm_crtc_state *cstate,
> > @@ -4038,8 +3924,10 @@ skl_compute_ddb(struct drm_atomic_state *state)
> >  	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 intel_crtc_state *cstate;
> >  	struct intel_crtc *intel_crtc;
> > -	struct skl_ddb_allocation *ddb = &intel_state->wm_results.ddb;
> > +	struct skl_ddb_allocation *old_ddb = &dev_priv->wm.skl_hw.ddb;
> > +	struct skl_ddb_allocation *new_ddb = &intel_state->wm_results.ddb;
> >  	uint32_t realloc_pipes = pipes_modified(state);
> >  	int ret;
> >  
> > @@ -4071,13 +3959,11 @@ skl_compute_ddb(struct drm_atomic_state *state)
> >  	}
> >  
> >  	for_each_intel_crtc_mask(dev, intel_crtc, realloc_pipes) {
> > -		struct intel_crtc_state *cstate;
> > -
> >  		cstate = intel_atomic_get_crtc_state(state, intel_crtc);
> >  		if (IS_ERR(cstate))
> >  			return PTR_ERR(cstate);
> >  
> > -		ret = skl_allocate_pipe_ddb(cstate, ddb);
> > +		ret = skl_allocate_pipe_ddb(cstate, new_ddb);
> >  		if (ret)
> >  			return ret;
> >  
> > @@ -4086,6 +3972,73 @@ skl_compute_ddb(struct drm_atomic_state *state)
> >  			return ret;
> >  	}
> >  
> > +	/*
> > +	 * 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 final sequence we want looks like this:
> > +	 *  1. Disable any pipes we're not going to be using anymore
> > +	 *  2. Reallocate all of the active pipes whose new ddb allocations
> > +	 *  won't overlap with another active pipe's ddb allocation.
> > +	 *  3. Reallocate remaining active pipes, if any.
> > +	 *  4. Enable any new pipes, if any.
> > +	 *
> > +	 * Example:
> > +	 * Initially DDB looks like this:
> > +	 *   |   B    |   C    |
> > +	 * And the final DDB should look like this:
> > +	 *   |  B  |  C  |  A  |
> > +	 *
> > +	 * 1. We're not disabling any pipes, so do nothing on this step.
> > +	 * 2. Pipe B's new allocation wouldn't overlap with pipe C, however
> > +	 * pipe C's new allocation does overlap with pipe B's current
> > +	 * allocation. Reallocate B first so the DDB looks like this:
> > +	 *   |  B  |xx|   C    |
> > +	 * 3. Now we can safely reallocate pipe C to it's new location:
> > +	 *   |  B  |  C  |xxxxx|
> > +	 * 4. Enable any remaining pipes, in this case A
> > +	 *   |  B  |  C  |  A  |
> > +	 *
> > +	 * As well, between every pipe reallocation we have to wait for a
> > +	 * vblank on the pipe so that we ensure it's new allocation has taken
> > +	 * effect by the time we start moving the next pipe. This can be
> > +	 * skipped on the last step we need to perform, which is why we keep
> > +	 * track of that information here. For example, if we've reallocated
> > +	 * all the pipes that need changing by the time we reach step 3, we can
> > +	 * finish without waiting for the pipes we changed in step 3 to update.
> > +	 */
> > +	for_each_intel_crtc_mask(dev, intel_crtc, realloc_pipes) {
> > +		enum pipe pipe = intel_crtc->pipe;
> > +		enum skl_ddb_step step;
> > +
> > +		cstate = intel_atomic_get_crtc_state(state, intel_crtc);
> > +		if (IS_ERR(cstate))
> > +			return PTR_ERR(cstate);
> > +
> > +		/* Step 1: Pipes we're disabling / haven't changed */
> > +		if (skl_ddb_allocation_equals(old_ddb, new_ddb, pipe) ||
> > +		    new_ddb->pipe[pipe].end == 0) {
> > +			step = SKL_DDB_STEP_NONE;
> > +		/* Step 2-3: Active pipes we're reallocating */
> > +		} else if (old_ddb->pipe[pipe].end != 0) {
> > +			if (skl_ddb_allocation_overlaps(state, old_ddb, new_ddb,
> > +							pipe))
> > +				step = SKL_DDB_STEP_OVERLAP;
> > +			else
> > +				step = SKL_DDB_STEP_NO_OVERLAP;
> > +		/* Step 4: Pipes we're enabling */
> > +		} else {
> > +			step = SKL_DDB_STEP_FINAL;
> > +		}
> > +
> > +		cstate->wm.skl.ddb_realloc = step;
> > +
> > +		if (step > intel_state->last_ddb_step)
> > +			intel_state->last_ddb_step = step;
> > +	}
> > +
> >  	return 0;
> >  }
> >  
> > @@ -4110,10 +4063,13 @@ skl_copy_wm_for_pipe(struct skl_wm_values *dst,
> >  static int
> >  skl_compute_wm(struct drm_atomic_state *state)
> >  {
> > +	struct drm_i915_private *dev_priv = to_i915(state->dev);
> >  	struct drm_crtc *crtc;
> >  	struct drm_crtc_state *cstate;
> >  	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
> >  	struct skl_wm_values *results = &intel_state->wm_results;
> > +	struct skl_ddb_allocation *old_ddb = &dev_priv->wm.skl_hw.ddb;
> > +	struct skl_ddb_allocation *new_ddb = &results->ddb;
> >  	struct skl_pipe_wm *pipe_wm;
> >  	bool changed = false;
> >  	int ret, i;
> > @@ -4152,7 +4108,10 @@ skl_compute_wm(struct drm_atomic_state *state)
> >  		struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
> >  		struct intel_crtc_state *intel_cstate =
> >  			to_intel_crtc_state(cstate);
> > +		enum skl_ddb_step step;
> > +		enum pipe pipe;
> >  
> > +		pipe = intel_crtc->pipe;
> >  		pipe_wm = &intel_cstate->wm.skl.optimal;
> >  		ret = skl_update_pipe_wm(cstate, &results->ddb, pipe_wm,
> >  					 &changed);
> > @@ -4167,7 +4126,18 @@ skl_compute_wm(struct drm_atomic_state *state)
> >  			continue;
> >  
> >  		intel_cstate->update_wm_pre = true;
> > +		step = intel_cstate->wm.skl.ddb_realloc;
> >  		skl_compute_wm_results(crtc->dev, pipe_wm, results, intel_crtc);
> > +
> > +		if (!skl_ddb_entry_equal(&old_ddb->pipe[pipe],
> > +					 &new_ddb->pipe[pipe])) {
> > +			DRM_DEBUG_KMS(
> > +			    "DDB changes for [CRTC:%d:pipe %c]: (%3d - %3d) -> (%3d - %3d) on step %d\n",
> > +			    intel_crtc->base.base.id, pipe_name(pipe),
> > +			    old_ddb->pipe[pipe].start, old_ddb->pipe[pipe].end,
> > +			    new_ddb->pipe[pipe].start, new_ddb->pipe[pipe].end,
> > +			    step);
> > +		}
> >  	}
> >  
> >  	return 0;
> > @@ -4191,8 +4161,20 @@ 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);
> > +	/*
> > +	 * If this pipe isn't active already, we're going to be enabling it
> > +	 * very soon. Since it's safe to update these while the pipe's shut off,
> > +	 * just do so here. Already active pipes will have their watermarks
> > +	 * updated once we update their planes.
> > +	 */
> > +	if (!intel_crtc->active) {
> > +		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);
> > +	}
> >  
> >  	/*
> >  	 * Store the new configuration (but only for the pipes that have
> > -- 
> > 2.7.4
> 
> -- 
> Ville Syrjälä
> Intel OTC

-- 
Matt Roper
Graphics Software Engineer
IoTG Platform Enabling & Development
Intel Corporation
(916) 356-2795