drm/i915: Extend the async flip VT-d w/a to skl/bxt

Looks like skl/bxt/derivatives also need the plane stride
stretch w/a when using async flips and VT-d is enabled, or
else we get corruption on screen. To my surprise this was
even documented in bspec, but only as a note on the
CHICHKEN_PIPESL register description rather than on the
w/a list.

So very much the same thing as on HSW/BDW, except the bits
moved yet again.

Cc: stable@vger.kernel.org
Cc: Karthik B S <karthik.b.s@intel.com>
Fixes: 55ea1cb1 ("drm/i915: Enable async flips in i915")
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210930190943.17547-1-ville.syrjala@linux.intel.comReviewed-by: Matt Roper <matthew.d.roper@intel.com>
(cherry picked from commit d08df3b0)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>

drivers/gpu/drm/i915/i915_reg.h

@@ -8193,6 +8193,11 @@ enum {
 #define  HSW_SPR_STRETCH_MAX_X1		REG_FIELD_PREP(HSW_SPR_STRETCH_MAX_MASK, 3)
 #define  HSW_FBCQ_DIS			(1 << 22)
 #define  BDW_DPRS_MASK_VBLANK_SRD	(1 << 0)
+#define  SKL_PLANE1_STRETCH_MAX_MASK	REG_GENMASK(1, 0)
+#define  SKL_PLANE1_STRETCH_MAX_X8	REG_FIELD_PREP(SKL_PLANE1_STRETCH_MAX_MASK, 0)
+#define  SKL_PLANE1_STRETCH_MAX_X4	REG_FIELD_PREP(SKL_PLANE1_STRETCH_MAX_MASK, 1)
+#define  SKL_PLANE1_STRETCH_MAX_X2	REG_FIELD_PREP(SKL_PLANE1_STRETCH_MAX_MASK, 2)
+#define  SKL_PLANE1_STRETCH_MAX_X1	REG_FIELD_PREP(SKL_PLANE1_STRETCH_MAX_MASK, 3)
 #define CHICKEN_PIPESL_1(pipe) _MMIO_PIPE(pipe, _CHICKEN_PIPESL_1_A, _CHICKEN_PIPESL_1_B)
 
 #define _CHICKEN_TRANS_A	0x420c0

drivers/gpu/drm/i915/intel_pm.c

@@ -76,6 +76,8 @@ struct intel_wm_config {
 
 static void gen9_init_clock_gating(struct drm_i915_private *dev_priv)
 {
+	enum pipe pipe;
+
 	if (HAS_LLC(dev_priv)) {
 		/*
 		 * WaCompressedResourceDisplayNewHashMode:skl,kbl
@@ -89,6 +91,16 @@ static void gen9_init_clock_gating(struct drm_i915_private *dev_priv)
 			   SKL_DE_COMPRESSED_HASH_MODE);
 	}
 
+	for_each_pipe(dev_priv, pipe) {
+		/*
+		 * "Plane N strech max must be programmed to 11b (x1)
+		 *  when Async flips are enabled on that plane."
+		 */
+		if (!IS_GEMINILAKE(dev_priv) && intel_vtd_active())
+			intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe),
+					 SKL_PLANE1_STRETCH_MAX_MASK, SKL_PLANE1_STRETCH_MAX_X1);
+	}
+
 	/* See Bspec note for PSR2_CTL bit 31, Wa#828:skl,bxt,kbl,cfl */
 	intel_uncore_write(&dev_priv->uncore, CHICKEN_PAR1_1,
 		   intel_uncore_read(&dev_priv->uncore, CHICKEN_PAR1_1) | SKL_EDP_PSR_FIX_RDWRAP);