drm/i915: Add GT support for multiple types of multicast steering

Although most of our multicast registers are replicated per-subslice, we
also have a small number of multicast registers that are replicated
per-l3 bank instead.  For both types of multicast registers we need to
make sure we steer reads of these registers to a valid instance.
Ideally we'd like to find a specific instance ID that would steer reads
of either type of multicast register to a valid instance (i.e., not
fused off and not powered down), but sometimes the combination of
part-specific fusing and the additional restrictions imposed by Render
Power Gating make it impossible to find any overlap between the set of
valid subslices and valid l3 banks.  This problem will become even more
noticeable on our upcoming platforms since they will be adding
additional types of multicast registers with new types of replication
and rules for finding valid instances for reads.

To handle this we'll continue to pick a suitable subslice instance at
driver startup and program this as the default (sliceid,subsliceid)
setting in the steering control register (0xFDC).  In cases where we
need to read another type of multicast GT register, but the default
subslice steering would not correspond to a valid instance, we'll
explicitly re-steer the single read to a valid value, perform the read,
and then reset the steering to it's "subslice" default.

This patch adds the general functionality to prepare for this explicit
steering of other multicast register types.  We'll plug L3 bank steering
into this in the next patch, and then add additional types of multicast
registers when the support for our next upcoming platform arrives.

v2:
 - Use entry->end==0 as table terminator.  (Rodrigo)
 - Grab forcewake in wa_list_verify() now that we're using accessors
   that assume forcewake is already held.

v3:
 - Fix loop condition when iterating over steering range tables.
   (Rodrigo)

Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210617211425.1943662-3-matthew.d.roper@intel.com

1 files changed, 27 insertions, 12 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 977a76e648e0..93c74d4cae02 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -1248,8 +1248,9 @@ wa_verify(const struct i915_wa *wa, u32 cur, const char *name, const char *from)
 }
 
 static void
-wa_list_apply(struct intel_uncore *uncore, const struct i915_wa_list *wal)
+wa_list_apply(struct intel_gt *gt, const struct i915_wa_list *wal)
 {
+	struct intel_uncore *uncore = gt->uncore;
 	enum forcewake_domains fw;
 	unsigned long flags;
 	struct i915_wa *wa;
@@ -1264,13 +1265,16 @@ wa_list_apply(struct intel_uncore *uncore, const struct i915_wa_list *wal)
 	intel_uncore_forcewake_get__locked(uncore, fw);
 
 	for (i = 0, wa = wal->list; i < wal->count; i++, wa++) {
-		if (wa->clr)
-			intel_uncore_rmw_fw(uncore, wa->reg, wa->clr, wa->set);
-		else
-			intel_uncore_write_fw(uncore, wa->reg, wa->set);
+		u32 val, old = 0;
+
+		/* open-coded rmw due to steering */
+		old = wa->clr ? intel_gt_read_register_fw(gt, wa->reg) : 0;
+		val = (old & ~wa->clr) | wa->set;
+		if (val != old || !wa->clr)
+			intel_uncore_write_fw(uncore, wa->reg, val);
+
 		if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
-			wa_verify(wa,
-				  intel_uncore_read_fw(uncore, wa->reg),
+			wa_verify(wa, intel_gt_read_register_fw(gt, wa->reg),
 				  wal->name, "application");
 	}
 
@@ -1280,28 +1284,39 @@ wa_list_apply(struct intel_uncore *uncore, const struct i915_wa_list *wal)
 
 void intel_gt_apply_workarounds(struct intel_gt *gt)
 {
-	wa_list_apply(gt->uncore, &gt->i915->gt_wa_list);
+	wa_list_apply(gt, &gt->i915->gt_wa_list);
 }
 
-static bool wa_list_verify(struct intel_uncore *uncore,
+static bool wa_list_verify(struct intel_gt *gt,
 			   const struct i915_wa_list *wal,
 			   const char *from)
 {
+	struct intel_uncore *uncore = gt->uncore;
 	struct i915_wa *wa;
+	enum forcewake_domains fw;
+	unsigned long flags;
 	unsigned int i;
 	bool ok = true;
 
+	fw = wal_get_fw_for_rmw(uncore, wal);
+
+	spin_lock_irqsave(&uncore->lock, flags);
+	intel_uncore_forcewake_get__locked(uncore, fw);
+
 	for (i = 0, wa = wal->list; i < wal->count; i++, wa++)
 		ok &= wa_verify(wa,
-				intel_uncore_read(uncore, wa->reg),
+				intel_gt_read_register_fw(gt, wa->reg),
 				wal->name, from);
 
+	intel_uncore_forcewake_put__locked(uncore, fw);
+	spin_unlock_irqrestore(&uncore->lock, flags);
+
 	return ok;
 }
 
 bool intel_gt_verify_workarounds(struct intel_gt *gt, const char *from)
 {
-	return wa_list_verify(gt->uncore, &gt->i915->gt_wa_list, from);
+	return wa_list_verify(gt, &gt->i915->gt_wa_list, from);
 }
 
 __maybe_unused
@@ -2084,7 +2099,7 @@ void intel_engine_init_workarounds(struct intel_engine_cs *engine)
 
 void intel_engine_apply_workarounds(struct intel_engine_cs *engine)
 {
-	wa_list_apply(engine->uncore, &engine->wa_list);
+	wa_list_apply(engine->gt, &engine->wa_list);
 }
 
 struct mcr_range {