drm/i915/gt: Add intel_gt_mcr_wait_for_reg_fw()

Xe_HP has some MCR registers that need to be polled for completion of
operations like TLB invalidation.  Those registers are in the GAM range,
which rolls up the status from each unit into the 'primary' instance's
value.  This makes it useful to have a dedicated 'wait for register'
function that handles this on MCR registers, similar to the
__intel_wait_for_register_fw() function we already have for regular
registers.
Signed-off-by: NMatt Roper <matthew.d.roper@intel.com>
Reviewed-by: NBalasubramani Vivekanandan <balasubramani.vivekanandan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221014230239.1023689-8-matthew.d.roper@intel.com

drivers/gpu/drm/i915/gt/intel_gt_mcr.c

@@ -568,3 +568,58 @@ void intel_gt_mcr_get_ss_steering(struct intel_gt *gt, unsigned int dss,
 		return;
 	}
 }
+
+/**
+ * intel_gt_mcr_wait_for_reg_fw - wait until MCR register matches expected state
+ * @gt: GT structure
+ * @reg: the register to read
+ * @mask: mask to apply to register value
+ * @value: value to wait for
+ * @fast_timeout_us: fast timeout in microsecond for atomic/tight wait
+ * @slow_timeout_ms: slow timeout in millisecond
+ *
+ * This routine waits until the target register @reg contains the expected
+ * @value after applying the @mask, i.e. it waits until ::
+ *
+ *     (intel_gt_mcr_read_any_fw(gt, reg) & mask) == value
+ *
+ * Otherwise, the wait will timeout after @slow_timeout_ms milliseconds.
+ * For atomic context @slow_timeout_ms must be zero and @fast_timeout_us
+ * must be not larger than 20,0000 microseconds.
+ *
+ * This function is basically an MCR-friendly version of
+ * __intel_wait_for_register_fw().  Generally this function will only be used
+ * on GAM registers which are a bit special --- although they're MCR registers,
+ * reads (e.g., waiting for status updates) are always directed to the primary
+ * instance.
+ *
+ * Note that this routine assumes the caller holds forcewake asserted, it is
+ * not suitable for very long waits.
+ *
+ * Return: 0 if the register matches the desired condition, or -ETIMEDOUT.
+ */
+int intel_gt_mcr_wait_for_reg_fw(struct intel_gt *gt,
+				 i915_reg_t reg,
+				 u32 mask,
+				 u32 value,
+				 unsigned int fast_timeout_us,
+				 unsigned int slow_timeout_ms)
+{
+	u32 reg_value = 0;
+#define done (((reg_value = intel_gt_mcr_read_any_fw(gt, reg)) & mask) == value)
+	int ret;
+
+	/* Catch any overuse of this function */
+	might_sleep_if(slow_timeout_ms);
+	GEM_BUG_ON(fast_timeout_us > 20000);
+	GEM_BUG_ON(!fast_timeout_us && !slow_timeout_ms);
+
+	ret = -ETIMEDOUT;
+	if (fast_timeout_us && fast_timeout_us <= 20000)
+		ret = _wait_for_atomic(done, fast_timeout_us, 0);
+	if (ret && slow_timeout_ms)
+		ret = wait_for(done, slow_timeout_ms);
+
+	return ret;
+#undef done
+}

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

@@ -37,6 +37,13 @@ void intel_gt_mcr_report_steering(struct drm_printer *p, struct intel_gt *gt,
 void intel_gt_mcr_get_ss_steering(struct intel_gt *gt, unsigned int dss,
 				  unsigned int *group, unsigned int *instance);
 
+int intel_gt_mcr_wait_for_reg_fw(struct intel_gt *gt,
+				 i915_reg_t reg,
+				 u32 mask,
+				 u32 value,
+				 unsigned int fast_timeout_us,
+				 unsigned int slow_timeout_ms);
+
 /*
  * Helper for for_each_ss_steering loop.  On pre-Xe_HP platforms, subslice
  * presence is determined by using the group/instance as direct lookups in the