drm/i915/gen9: Fix PCODE polling during CDCLK change notification

commit 848496e5
Author: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date:   Wed Jul 13 16:32:03 2016 +0300

    drm/i915: Wait up to 3ms for the pcu to ack the cdclk change request on SKL

increased the timeout to match the spec, but we still see a timeout on
at least one SKL. A CDCLK change request following the failed one will
succeed nevertheless.

I could reproduce this problem easily by running kms_pipe_crc_basic in a
loop. In all failure cases _wait_for() was pre-empted for >3ms and so in
the worst case - when the pre-emption happened right after calculating
timeout__ in _wait_for() - we called skl_cdclk_wait_for_pcu_ready() only
once which failed and so _wait_for() timed out. As opposed to this the
spec says to keep retrying the request for at most a 3ms period.

To fix this send the first request explicitly to guarantee that there is
3ms between the first and last request. Though this matches the spec, I
noticed that in rare cases this can still time out if we sent only a few
requests (in the worst case 2) _and_ PCODE is busy for some reason even
after a previous request and a 3ms delay. To work around this retry the
polling with pre-emption disabled to maximize the number of requests.
Also increase the timeout to 10ms to account for interrupts that could
reduce the number of requests. With this change I couldn't trigger
the problem.

v2:
- Use 1ms poll period instead of 10us. (Chris)
v3:
- Poll with pre-emption disabled to increase the number of request
  attempts. (Ville, Chris)
- Factor out a helper to poll, it's also needed by the next patch.
v4:
- Pass reply_mask, reply to skl_pcode_request(), instead of assuming the
  reply is generic. (Ville)
v5:
- List the request specific timeout values as code comment. (Ville)
v6:
- Try the poll first with preemption enabled.
- Add code comment about first request being queued by PCODE. (Art)
- Add timeout_base_ms argument. (Ville)
v7:
- Clarify code comment about first queued request. (Chris)

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Art Runyan <arthur.j.runyan@intel.com>
Cc: <stable@vger.kernel.org> # v4.2- : 3b2c1710 : drm/i915: Wait up to 3ms
Cc: <stable@vger.kernel.org> # v4.2-
Fixes: 5d96d8af ("drm/i915/skl: Deinit/init the display at suspend/resume")
Reference: https://bugs.freedesktop.org/show_bug.cgi?id=97929
Testcase: igt/kms_pipe_crc_basic/suspend-read-crc-pipe-B
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/1480955258-26311-1-git-send-email-imre.deak@intel.com

drivers/gpu/drm/i915/i915_drv.h

@@ -3705,6 +3705,8 @@ extern void intel_display_print_error_state(struct drm_i915_error_state_buf *e,
 
 int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u32 mbox, u32 *val);
 int sandybridge_pcode_write(struct drm_i915_private *dev_priv, u32 mbox, u32 val);
+int skl_pcode_request(struct drm_i915_private *dev_priv, u32 mbox, u32 request,
+		      u32 reply_mask, u32 reply, int timeout_base_ms);
 
 /* intel_sideband.c */
 u32 vlv_punit_read(struct drm_i915_private *dev_priv, u32 addr);

drivers/gpu/drm/i915/intel_display.c

@@ -6271,35 +6271,24 @@ skl_dpll0_disable(struct drm_i915_private *dev_priv)
 	dev_priv->cdclk_pll.vco = 0;
 }
 
-static bool skl_cdclk_pcu_ready(struct drm_i915_private *dev_priv)
-{
-	int ret;
-	u32 val;
-
-	/* inform PCU we want to change CDCLK */
-	val = SKL_CDCLK_PREPARE_FOR_CHANGE;
-	mutex_lock(&dev_priv->rps.hw_lock);
-	ret = sandybridge_pcode_read(dev_priv, SKL_PCODE_CDCLK_CONTROL, &val);
-	mutex_unlock(&dev_priv->rps.hw_lock);
-
-	return ret == 0 && (val & SKL_CDCLK_READY_FOR_CHANGE);
-}
-
-static bool skl_cdclk_wait_for_pcu_ready(struct drm_i915_private *dev_priv)
-{
-	return _wait_for(skl_cdclk_pcu_ready(dev_priv), 3000, 10) == 0;
-}
-
 static void skl_set_cdclk(struct drm_i915_private *dev_priv, int cdclk, int vco)
 {
 	u32 freq_select, pcu_ack;
+	int ret;
 
 	WARN_ON((cdclk == 24000) != (vco == 0));
 
 	DRM_DEBUG_DRIVER("Changing CDCLK to %d kHz (VCO %d kHz)\n", cdclk, vco);
 
-	if (!skl_cdclk_wait_for_pcu_ready(dev_priv)) {
-		DRM_ERROR("failed to inform PCU about cdclk change\n");
+	mutex_lock(&dev_priv->rps.hw_lock);
+	ret = skl_pcode_request(dev_priv, SKL_PCODE_CDCLK_CONTROL,
+				SKL_CDCLK_PREPARE_FOR_CHANGE,
+				SKL_CDCLK_READY_FOR_CHANGE,
+				SKL_CDCLK_READY_FOR_CHANGE, 3);
+	mutex_unlock(&dev_priv->rps.hw_lock);
+	if (ret) {
+		DRM_ERROR("Failed to inform PCU about cdclk change (%d)\n",
+			  ret);
 		return;
 	}
 

drivers/gpu/drm/i915/intel_pm.c

@@ -7896,6 +7896,81 @@ int sandybridge_pcode_write(struct drm_i915_private *dev_priv,
 	return 0;
 }
 
+static bool skl_pcode_try_request(struct drm_i915_private *dev_priv, u32 mbox,
+				  u32 request, u32 reply_mask, u32 reply,
+				  u32 *status)
+{
+	u32 val = request;
+
+	*status = sandybridge_pcode_read(dev_priv, mbox, &val);
+
+	return *status || ((val & reply_mask) == reply);
+}
+
+/**
+ * skl_pcode_request - send PCODE request until acknowledgment
+ * @dev_priv: device private
+ * @mbox: PCODE mailbox ID the request is targeted for
+ * @request: request ID
+ * @reply_mask: mask used to check for request acknowledgment
+ * @reply: value used to check for request acknowledgment
+ * @timeout_base_ms: timeout for polling with preemption enabled
+ *
+ * Keep resending the @request to @mbox until PCODE acknowledges it, PCODE
+ * reports an error or an overall timeout of @timeout_base_ms+10 ms expires.
+ * The request is acknowledged once the PCODE reply dword equals @reply after
+ * applying @reply_mask. Polling is first attempted with preemption enabled
+ * for @timeout_base_ms and if this times out for another 10 ms with
+ * preemption disabled.
+ *
+ * Returns 0 on success, %-ETIMEDOUT in case of a timeout, <0 in case of some
+ * other error as reported by PCODE.
+ */
+int skl_pcode_request(struct drm_i915_private *dev_priv, u32 mbox, u32 request,
+		      u32 reply_mask, u32 reply, int timeout_base_ms)
+{
+	u32 status;
+	int ret;
+
+	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
+
+#define COND skl_pcode_try_request(dev_priv, mbox, request, reply_mask, reply, \
+				   &status)
+
+	/*
+	 * Prime the PCODE by doing a request first. Normally it guarantees
+	 * that a subsequent request, at most @timeout_base_ms later, succeeds.
+	 * _wait_for() doesn't guarantee when its passed condition is evaluated
+	 * first, so send the first request explicitly.
+	 */
+	if (COND) {
+		ret = 0;
+		goto out;
+	}
+	ret = _wait_for(COND, timeout_base_ms * 1000, 10);
+	if (!ret)
+		goto out;
+
+	/*
+	 * The above can time out if the number of requests was low (2 in the
+	 * worst case) _and_ PCODE was busy for some reason even after a
+	 * (queued) request and @timeout_base_ms delay. As a workaround retry
+	 * the poll with preemption disabled to maximize the number of
+	 * requests. Increase the timeout from @timeout_base_ms to 10ms to
+	 * account for interrupts that could reduce the number of these
+	 * requests.
+	 */
+	DRM_DEBUG_KMS("PCODE timeout, retrying with preemption disabled\n");
+	WARN_ON_ONCE(timeout_base_ms > 3);
+	preempt_disable();
+	ret = wait_for_atomic(COND, 10);
+	preempt_enable();
+
+out:
+	return ret ? ret : status;
+#undef COND
+}
+
 static int byt_gpu_freq(struct drm_i915_private *dev_priv, int val)
 {
 	/*