drm/i915: Add support for steered register writes

Upcoming patches will need to steer writes to multicast registers as
well as reading them.

Although the setting of the 'multicast' bit should only really matter
for write operations (reads always operate in a unicast manner and give
us the result from one specific instance), Wa_22013088509 suggests that
we leave the multicast bit enabled when performing read operations, so
we follow suit here.

Cc: Harish Chegondi <harish.chegondi@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220314234203.799268-4-matthew.d.roper@intel.com

drivers/gpu/drm/i915/gt/intel_gt_regs.h

@@ -46,6 +46,7 @@
 #define   GEN8_MCR_SLICE_MASK			GEN8_MCR_SLICE(3)
 #define   GEN8_MCR_SUBSLICE(subslice)		(((subslice) & 3) << 24)
 #define   GEN8_MCR_SUBSLICE_MASK		GEN8_MCR_SUBSLICE(3)
+#define   GEN11_MCR_MULTICAST			REG_BIT(31)
 #define   GEN11_MCR_SLICE(slice)		(((slice) & 0xf) << 27)
 #define   GEN11_MCR_SLICE_MASK			GEN11_MCR_SLICE(0xf)
 #define   GEN11_MCR_SUBSLICE(subslice)		(((subslice) & 0x7) << 24)

drivers/gpu/drm/i915/intel_uncore.c

@@ -2464,17 +2464,46 @@ intel_uncore_forcewake_for_reg(struct intel_uncore *uncore,
 	return fw_domains;
 }
 
-u32 intel_uncore_read_with_mcr_steering_fw(struct intel_uncore *uncore,
-					   i915_reg_t reg,
-					   int slice, int subslice)
+/**
+ * uncore_rw_with_mcr_steering_fw - Access a register after programming
+ *				    the MCR selector register.
+ * @uncore: pointer to struct intel_uncore
+ * @reg: register being accessed
+ * @rw_flag: FW_REG_READ for read access or FW_REG_WRITE for write access
+ * @slice: slice number (ignored for multi-cast write)
+ * @subslice: sub-slice number (ignored for multi-cast write)
+ * @value: register value to be written (ignored for read)
+ *
+ * Return: 0 for write access. register value for read access.
+ *
+ * Caller needs to make sure the relevant forcewake wells are up.
+ */
+static u32 uncore_rw_with_mcr_steering_fw(struct intel_uncore *uncore,
+					  i915_reg_t reg, u8 rw_flag,
+					  int slice, int subslice, u32 value)
 {
-	u32 mcr_mask, mcr_ss, mcr, old_mcr, val;
+	u32 mcr_mask, mcr_ss, mcr, old_mcr, val = 0;
 
 	lockdep_assert_held(&uncore->lock);
 
 	if (GRAPHICS_VER(uncore->i915) >= 11) {
 		mcr_mask = GEN11_MCR_SLICE_MASK | GEN11_MCR_SUBSLICE_MASK;
 		mcr_ss = GEN11_MCR_SLICE(slice) | GEN11_MCR_SUBSLICE(subslice);
+
+		/*
+		 * Wa_22013088509
+		 *
+		 * The setting of the multicast/unicast bit usually wouldn't
+		 * matter for read operations (which always return the value
+		 * from a single register instance regardless of how that bit
+		 * is set), but some platforms have a workaround requiring us
+		 * to remain in multicast mode for reads.  There's no real
+		 * downside to this, so we'll just go ahead and do so on all
+		 * platforms; we'll only clear the multicast bit from the mask
+		 * when exlicitly doing a write operation.
+		 */
+		if (rw_flag == FW_REG_WRITE)
+			mcr_mask |= GEN11_MCR_MULTICAST;
 	} else {
 		mcr_mask = GEN8_MCR_SLICE_MASK | GEN8_MCR_SUBSLICE_MASK;
 		mcr_ss = GEN8_MCR_SLICE(slice) | GEN8_MCR_SUBSLICE(subslice);
@@ -2486,7 +2515,10 @@ u32 intel_uncore_read_with_mcr_steering_fw(struct intel_uncore *uncore,
 	mcr |= mcr_ss;
 	intel_uncore_write_fw(uncore, GEN8_MCR_SELECTOR, mcr);
 
-	val = intel_uncore_read_fw(uncore, reg);
+	if (rw_flag == FW_REG_READ)
+		val = intel_uncore_read_fw(uncore, reg);
+	else
+		intel_uncore_write_fw(uncore, reg, value);
 
 	mcr &= ~mcr_mask;
 	mcr |= old_mcr & mcr_mask;
@@ -2496,14 +2528,16 @@ u32 intel_uncore_read_with_mcr_steering_fw(struct intel_uncore *uncore,
 	return val;
 }
 
-u32 intel_uncore_read_with_mcr_steering(struct intel_uncore *uncore,
-					i915_reg_t reg, int slice, int subslice)
+static u32 uncore_rw_with_mcr_steering(struct intel_uncore *uncore,
+				       i915_reg_t reg, u8 rw_flag,
+				       int slice, int subslice,
+				       u32 value)
 {
 	enum forcewake_domains fw_domains;
 	u32 val;
 
 	fw_domains = intel_uncore_forcewake_for_reg(uncore, reg,
-						    FW_REG_READ);
+						    rw_flag);
 	fw_domains |= intel_uncore_forcewake_for_reg(uncore,
 						     GEN8_MCR_SELECTOR,
 						     FW_REG_READ | FW_REG_WRITE);
@@ -2511,7 +2545,8 @@ u32 intel_uncore_read_with_mcr_steering(struct intel_uncore *uncore,
 	spin_lock_irq(&uncore->lock);
 	intel_uncore_forcewake_get__locked(uncore, fw_domains);
 
-	val = intel_uncore_read_with_mcr_steering_fw(uncore, reg, slice, subslice);
+	val = uncore_rw_with_mcr_steering_fw(uncore, reg, rw_flag,
+					     slice, subslice, value);
 
 	intel_uncore_forcewake_put__locked(uncore, fw_domains);
 	spin_unlock_irq(&uncore->lock);
@@ -2519,6 +2554,28 @@ u32 intel_uncore_read_with_mcr_steering(struct intel_uncore *uncore,
 	return val;
 }
 
+u32 intel_uncore_read_with_mcr_steering_fw(struct intel_uncore *uncore,
+					   i915_reg_t reg, int slice, int subslice)
+{
+	return uncore_rw_with_mcr_steering_fw(uncore, reg, FW_REG_READ,
+					      slice, subslice, 0);
+}
+
+u32 intel_uncore_read_with_mcr_steering(struct intel_uncore *uncore,
+					i915_reg_t reg, int slice, int subslice)
+{
+	return uncore_rw_with_mcr_steering(uncore, reg, FW_REG_READ,
+					   slice, subslice, 0);
+}
+
+void intel_uncore_write_with_mcr_steering(struct intel_uncore *uncore,
+					  i915_reg_t reg, u32 value,
+					  int slice, int subslice)
+{
+	uncore_rw_with_mcr_steering(uncore, reg, FW_REG_WRITE,
+				    slice, subslice, value);
+}
+
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftests/mock_uncore.c"
 #include "selftests/intel_uncore.c"

drivers/gpu/drm/i915/intel_uncore.h

@@ -214,7 +214,9 @@ u32 intel_uncore_read_with_mcr_steering_fw(struct intel_uncore *uncore,
 					   int slice, int subslice);
 u32 intel_uncore_read_with_mcr_steering(struct intel_uncore *uncore,
 					i915_reg_t reg,	int slice, int subslice);
-
+void intel_uncore_write_with_mcr_steering(struct intel_uncore *uncore,
+					  i915_reg_t reg, u32 value,
+					  int slice, int subslice);
 void
 intel_uncore_mmio_debug_init_early(struct intel_uncore_mmio_debug *mmio_debug);
 void intel_uncore_init_early(struct intel_uncore *uncore,