drm/i915: Replace pcu_lock with sb_lock

We now have two locks for sideband access. The general one covering
sideband access across all generation, sb_lock, and a specific one
covering sideband access via the punit on vlv/chv. After lifting the
sb_lock around the punit into the callers, the pcu_lock is now redudant
and can be separated from its other use to regulate RPS (essentially
giving RPS a lock all of its own).

v2: Extract a couple of minor bug fixes.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Sagar Arun Kamble <sagar.a.kamble@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190426081725.31217-4-chris@chris-wilson.co.uk

10 files changed, 81 insertions, 168 deletions

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index f8472db460bb..9545556898e6 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1046,8 +1046,6 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 	} else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
 		u32 rpmodectl, freq_sts;
 
-		mutex_lock(&dev_priv->pcu_lock);
-
 		rpmodectl = I915_READ(GEN6_RP_CONTROL);
 		seq_printf(m, "Video Turbo Mode: %s\n",
 			   yesno(rpmodectl & GEN6_RP_MEDIA_TURBO));
@@ -1082,7 +1080,6 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 		seq_printf(m,
 			   "efficient (RPe) frequency: %d MHz\n",
 			   intel_gpu_freq(dev_priv, rps->efficient_freq));
-		mutex_unlock(&dev_priv->pcu_lock);
 	} else if (INTEL_GEN(dev_priv) >= 6) {
 		u32 rp_state_limits;
 		u32 gt_perf_status;
@@ -1487,12 +1484,9 @@ static int gen6_drpc_info(struct seq_file *m)
 		gen9_powergate_status = I915_READ(GEN9_PWRGT_DOMAIN_STATUS);
 	}
 
-	if (INTEL_GEN(dev_priv) <= 7) {
-		mutex_lock(&dev_priv->pcu_lock);
+	if (INTEL_GEN(dev_priv) <= 7)
 		sandybridge_pcode_read(dev_priv, GEN6_PCODE_READ_RC6VIDS,
 				       &rc6vids);
-		mutex_unlock(&dev_priv->pcu_lock);
-	}
 
 	seq_printf(m, "RC1e Enabled: %s\n",
 		   yesno(rcctl1 & GEN6_RC_CTL_RC1e_ENABLE));
@@ -1756,17 +1750,10 @@ static int i915_ring_freq_table(struct seq_file *m, void *unused)
 	unsigned int max_gpu_freq, min_gpu_freq;
 	intel_wakeref_t wakeref;
 	int gpu_freq, ia_freq;
-	int ret;
 
 	if (!HAS_LLC(dev_priv))
 		return -ENODEV;
 
-	wakeref = intel_runtime_pm_get(dev_priv);
-
-	ret = mutex_lock_interruptible(&dev_priv->pcu_lock);
-	if (ret)
-		goto out;
-
 	min_gpu_freq = rps->min_freq;
 	max_gpu_freq = rps->max_freq;
 	if (IS_GEN9_BC(dev_priv) || INTEL_GEN(dev_priv) >= 10) {
@@ -1777,6 +1764,7 @@ static int i915_ring_freq_table(struct seq_file *m, void *unused)
 
 	seq_puts(m, "GPU freq (MHz)\tEffective CPU freq (MHz)\tEffective Ring freq (MHz)\n");
 
+	wakeref = intel_runtime_pm_get(dev_priv);
 	for (gpu_freq = min_gpu_freq; gpu_freq <= max_gpu_freq; gpu_freq++) {
 		ia_freq = gpu_freq;
 		sandybridge_pcode_read(dev_priv,
@@ -1790,12 +1778,9 @@ static int i915_ring_freq_table(struct seq_file *m, void *unused)
 			   ((ia_freq >> 0) & 0xff) * 100,
 			   ((ia_freq >> 8) & 0xff) * 100);
 	}
-
-	mutex_unlock(&dev_priv->pcu_lock);
-
-out:
 	intel_runtime_pm_put(dev_priv, wakeref);
-	return ret;
+
+	return 0;
 }
 
 static int i915_opregion(struct seq_file *m, void *unused)
@@ -2032,13 +2017,11 @@ static int i915_rps_boost_info(struct seq_file *m, void *data)
 
 	with_intel_runtime_pm_if_in_use(dev_priv, wakeref) {
 		if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
-			mutex_lock(&dev_priv->pcu_lock);
 			vlv_punit_get(dev_priv);
 			act_freq = vlv_punit_read(dev_priv,
 						  PUNIT_REG_GPU_FREQ_STS);
 			vlv_punit_put(dev_priv);
 			act_freq = (act_freq >> 8) & 0xff;
-			mutex_unlock(&dev_priv->pcu_lock);
 		} else {
 			act_freq = intel_get_cagf(dev_priv,
 						  I915_READ(GEN6_RPSTAT1));
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index b2215fb7f562..ca1b35d8faca 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -648,6 +648,8 @@ struct intel_rps_ei {
 };
 
 struct intel_rps {
+	struct mutex lock; /* protects enabling and the worker */
+
 	/*
 	 * work, interrupts_enabled and pm_iir are protected by
 	 * dev_priv->irq_lock
@@ -1710,14 +1712,6 @@ struct drm_i915_private {
 	 */
 	u32 edram_size_mb;
 
-	/*
-	 * Protects RPS/RC6 register access and PCU communication.
-	 * Must be taken after struct_mutex if nested. Note that
-	 * this lock may be held for long periods of time when
-	 * talking to hw - so only take it when talking to hw!
-	 */
-	struct mutex pcu_lock;
-
 	/* gen6+ GT PM state */
 	struct intel_gen6_power_mgmt gt_pm;
 
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index b92cfd69134b..15f5415a0aa2 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1301,7 +1301,7 @@ static void gen6_pm_rps_work(struct work_struct *work)
 	if ((pm_iir & dev_priv->pm_rps_events) == 0 && !client_boost)
 		goto out;
 
-	mutex_lock(&dev_priv->pcu_lock);
+	mutex_lock(&rps->lock);
 
 	pm_iir |= vlv_wa_c0_ei(dev_priv, pm_iir);
 
@@ -1367,7 +1367,7 @@ static void gen6_pm_rps_work(struct work_struct *work)
 		rps->last_adj = 0;
 	}
 
-	mutex_unlock(&dev_priv->pcu_lock);
+	mutex_unlock(&rps->lock);
 
 out:
 	/* Make sure not to corrupt PMIMR state used by ringbuffer on GEN6 */
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index bfabb3de4808..0952d6a70e1f 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -263,7 +263,6 @@ static ssize_t gt_act_freq_mhz_show(struct device *kdev,
 
 	wakeref = intel_runtime_pm_get(dev_priv);
 
-	mutex_lock(&dev_priv->pcu_lock);
 	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
 		vlv_punit_get(dev_priv);
 		freq = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
@@ -273,7 +272,6 @@ static ssize_t gt_act_freq_mhz_show(struct device *kdev,
 	} else {
 		freq = intel_get_cagf(dev_priv, I915_READ(GEN6_RPSTAT1));
 	}
-	mutex_unlock(&dev_priv->pcu_lock);
 
 	intel_runtime_pm_put(dev_priv, wakeref);
 
@@ -318,12 +316,12 @@ static ssize_t gt_boost_freq_mhz_store(struct device *kdev,
 	if (val < rps->min_freq || val > rps->max_freq)
 		return -EINVAL;
 
-	mutex_lock(&dev_priv->pcu_lock);
+	mutex_lock(&rps->lock);
 	if (val != rps->boost_freq) {
 		rps->boost_freq = val;
 		boost = atomic_read(&rps->num_waiters);
 	}
-	mutex_unlock(&dev_priv->pcu_lock);
+	mutex_unlock(&rps->lock);
 	if (boost)
 		schedule_work(&rps->work);
 
@@ -364,17 +362,14 @@ static ssize_t gt_max_freq_mhz_store(struct device *kdev,
 		return ret;
 
 	wakeref = intel_runtime_pm_get(dev_priv);
-
-	mutex_lock(&dev_priv->pcu_lock);
+	mutex_lock(&rps->lock);
 
 	val = intel_freq_opcode(dev_priv, val);
-
 	if (val < rps->min_freq ||
 	    val > rps->max_freq ||
 	    val < rps->min_freq_softlimit) {
-		mutex_unlock(&dev_priv->pcu_lock);
-		intel_runtime_pm_put(dev_priv, wakeref);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto unlock;
 	}
 
 	if (val > rps->rp0_freq)
@@ -392,8 +387,8 @@ static ssize_t gt_max_freq_mhz_store(struct device *kdev,
 	 * frequency request may be unchanged. */
 	ret = intel_set_rps(dev_priv, val);
 
-	mutex_unlock(&dev_priv->pcu_lock);
-
+unlock:
+	mutex_unlock(&rps->lock);
 	intel_runtime_pm_put(dev_priv, wakeref);
 
 	return ret ?: count;
@@ -423,17 +418,14 @@ static ssize_t gt_min_freq_mhz_store(struct device *kdev,
 		return ret;
 
 	wakeref = intel_runtime_pm_get(dev_priv);
-
-	mutex_lock(&dev_priv->pcu_lock);
+	mutex_lock(&rps->lock);
 
 	val = intel_freq_opcode(dev_priv, val);
-
 	if (val < rps->min_freq ||
 	    val > rps->max_freq ||
 	    val > rps->max_freq_softlimit) {
-		mutex_unlock(&dev_priv->pcu_lock);
-		intel_runtime_pm_put(dev_priv, wakeref);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto unlock;
 	}
 
 	rps->min_freq_softlimit = val;
@@ -447,8 +439,8 @@ static ssize_t gt_min_freq_mhz_store(struct device *kdev,
 	 * frequency request may be unchanged. */
 	ret = intel_set_rps(dev_priv, val);
 
-	mutex_unlock(&dev_priv->pcu_lock);
-
+unlock:
+	mutex_unlock(&rps->lock);
 	intel_runtime_pm_put(dev_priv, wakeref);
 
 	return ret ?: count;
diff --git a/drivers/gpu/drm/i915/intel_cdclk.c b/drivers/gpu/drm/i915/intel_cdclk.c
index 9dd22203a7e8..2bc5d3227a24 100644
--- a/drivers/gpu/drm/i915/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/intel_cdclk.c
@@ -464,7 +464,6 @@ static void vlv_get_cdclk(struct drm_i915_private *dev_priv,
 {
 	u32 val;
 
-	mutex_lock(&dev_priv->pcu_lock);
 	vlv_iosf_sb_get(dev_priv,
 			BIT(VLV_IOSF_SB_CCK) | BIT(VLV_IOSF_SB_PUNIT));
 
@@ -477,7 +476,6 @@ static void vlv_get_cdclk(struct drm_i915_private *dev_priv,
 
 	vlv_iosf_sb_put(dev_priv,
 			BIT(VLV_IOSF_SB_CCK) | BIT(VLV_IOSF_SB_PUNIT));
-	mutex_unlock(&dev_priv->pcu_lock);
 
 	if (IS_VALLEYVIEW(dev_priv))
 		cdclk_state->voltage_level = (val & DSPFREQGUAR_MASK) >>
@@ -556,7 +554,6 @@ static void vlv_set_cdclk(struct drm_i915_private *dev_priv,
 			BIT(VLV_IOSF_SB_BUNIT) |
 			BIT(VLV_IOSF_SB_PUNIT));
 
-	mutex_lock(&dev_priv->pcu_lock);
 	val = vlv_punit_read(dev_priv, PUNIT_REG_DSPSSPM);
 	val &= ~DSPFREQGUAR_MASK;
 	val |= (cmd << DSPFREQGUAR_SHIFT);
@@ -566,7 +563,6 @@ static void vlv_set_cdclk(struct drm_i915_private *dev_priv,
 		     50)) {
 		DRM_ERROR("timed out waiting for CDclk change\n");
 	}
-	mutex_unlock(&dev_priv->pcu_lock);
 
 	if (cdclk == 400000) {
 		u32 divider;
@@ -639,7 +635,6 @@ static void chv_set_cdclk(struct drm_i915_private *dev_priv,
 	 */
 	wakeref = intel_display_power_get(dev_priv, POWER_DOMAIN_PIPE_A);
 
-	mutex_lock(&dev_priv->pcu_lock);
 	vlv_punit_get(dev_priv);
 	val = vlv_punit_read(dev_priv, PUNIT_REG_DSPSSPM);
 	val &= ~DSPFREQGUAR_MASK_CHV;
@@ -652,7 +647,6 @@ static void chv_set_cdclk(struct drm_i915_private *dev_priv,
 	}
 
 	vlv_punit_put(dev_priv);
-	mutex_unlock(&dev_priv->pcu_lock);
 
 	intel_update_cdclk(dev_priv);
 
@@ -731,10 +725,8 @@ static void bdw_set_cdclk(struct drm_i915_private *dev_priv,
 		 "trying to change cdclk frequency with cdclk not enabled\n"))
 		return;
 
-	mutex_lock(&dev_priv->pcu_lock);
 	ret = sandybridge_pcode_write(dev_priv,
 				      BDW_PCODE_DISPLAY_FREQ_CHANGE_REQ, 0x0);
-	mutex_unlock(&dev_priv->pcu_lock);
 	if (ret) {
 		DRM_ERROR("failed to inform pcode about cdclk change\n");
 		return;
@@ -783,10 +775,8 @@ static void bdw_set_cdclk(struct drm_i915_private *dev_priv,
 			LCPLL_CD_SOURCE_FCLK_DONE) == 0, 1))
 		DRM_ERROR("Switching back to LCPLL failed\n");
 
-	mutex_lock(&dev_priv->pcu_lock);
 	sandybridge_pcode_write(dev_priv, HSW_PCODE_DE_WRITE_FREQ_REQ,
 				cdclk_state->voltage_level);
-	mutex_unlock(&dev_priv->pcu_lock);
 
 	I915_WRITE(CDCLK_FREQ, DIV_ROUND_CLOSEST(cdclk, 1000) - 1);
 
@@ -1025,12 +1015,10 @@ static void skl_set_cdclk(struct drm_i915_private *dev_priv,
 	 */
 	WARN_ON_ONCE(IS_SKYLAKE(dev_priv) && vco == 8640000);
 
-	mutex_lock(&dev_priv->pcu_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->pcu_lock);
 	if (ret) {
 		DRM_ERROR("Failed to inform PCU about cdclk change (%d)\n",
 			  ret);
@@ -1094,10 +1082,8 @@ static void skl_set_cdclk(struct drm_i915_private *dev_priv,
 	POSTING_READ(CDCLK_CTL);
 
 	/* inform PCU of the change */
-	mutex_lock(&dev_priv->pcu_lock);
 	sandybridge_pcode_write(dev_priv, SKL_PCODE_CDCLK_CONTROL,
 				cdclk_state->voltage_level);
-	mutex_unlock(&dev_priv->pcu_lock);
 
 	intel_update_cdclk(dev_priv);
 }
@@ -1394,12 +1380,9 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv,
 	 * requires us to wait up to 150usec, but that leads to timeouts;
 	 * the 2ms used here is based on experiment.
 	 */
-	mutex_lock(&dev_priv->pcu_lock);
 	ret = sandybridge_pcode_write_timeout(dev_priv,
 					      HSW_PCODE_DE_WRITE_FREQ_REQ,
 					      0x80000000, 150, 2);
-	mutex_unlock(&dev_priv->pcu_lock);
-
 	if (ret) {
 		DRM_ERROR("PCode CDCLK freq change notify failed (err %d, freq %d)\n",
 			  ret, cdclk);
@@ -1429,7 +1412,6 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv,
 	if (pipe != INVALID_PIPE)
 		intel_wait_for_vblank(dev_priv, pipe);
 
-	mutex_lock(&dev_priv->pcu_lock);
 	/*
 	 * The timeout isn't specified, the 2ms used here is based on
 	 * experiment.
@@ -1439,8 +1421,6 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv,
 	ret = sandybridge_pcode_write_timeout(dev_priv,
 					      HSW_PCODE_DE_WRITE_FREQ_REQ,
 					      cdclk_state->voltage_level, 150, 2);
-	mutex_unlock(&dev_priv->pcu_lock);
-
 	if (ret) {
 		DRM_ERROR("PCode CDCLK freq set failed, (err %d, freq %d)\n",
 			  ret, cdclk);
@@ -1663,12 +1643,10 @@ static void cnl_set_cdclk(struct drm_i915_private *dev_priv,
 	u32 val, divider;
 	int ret;
 
-	mutex_lock(&dev_priv->pcu_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->pcu_lock);
 	if (ret) {
 		DRM_ERROR("Failed to inform PCU about cdclk change (%d)\n",
 			  ret);
@@ -1707,10 +1685,8 @@ static void cnl_set_cdclk(struct drm_i915_private *dev_priv,
 		intel_wait_for_vblank(dev_priv, pipe);
 
 	/* inform PCU of the change */
-	mutex_lock(&dev_priv->pcu_lock);
 	sandybridge_pcode_write(dev_priv, SKL_PCODE_CDCLK_CONTROL,
 				cdclk_state->voltage_level);
-	mutex_unlock(&dev_priv->pcu_lock);
 
 	intel_update_cdclk(dev_priv);
 
@@ -1849,12 +1825,10 @@ static void icl_set_cdclk(struct drm_i915_private *dev_priv,
 	unsigned int vco = cdclk_state->vco;
 	int ret;
 
-	mutex_lock(&dev_priv->pcu_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->pcu_lock);
 	if (ret) {
 		DRM_ERROR("Failed to inform PCU about cdclk change (%d)\n",
 			  ret);
@@ -1876,10 +1850,8 @@ static void icl_set_cdclk(struct drm_i915_private *dev_priv,
 	I915_WRITE(CDCLK_CTL, ICL_CDCLK_CD2X_PIPE_NONE |
 			      skl_cdclk_decimal(cdclk));
 
-	mutex_lock(&dev_priv->pcu_lock);
 	sandybridge_pcode_write(dev_priv, SKL_PCODE_CDCLK_CONTROL,
 				cdclk_state->voltage_level);
-	mutex_unlock(&dev_priv->pcu_lock);
 
 	intel_update_cdclk(dev_priv);
 
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 8eef0e732ac9..3cd8273b7186 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -5331,10 +5331,8 @@ void hsw_enable_ips(const struct intel_crtc_state *crtc_state)
 	WARN_ON(!(crtc_state->active_planes & ~BIT(PLANE_CURSOR)));
 
 	if (IS_BROADWELL(dev_priv)) {
-		mutex_lock(&dev_priv->pcu_lock);
 		WARN_ON(sandybridge_pcode_write(dev_priv, DISPLAY_IPS_CONTROL,
 						IPS_ENABLE | IPS_PCODE_CONTROL));
-		mutex_unlock(&dev_priv->pcu_lock);
 		/* Quoting Art Runyan: "its not safe to expect any particular
 		 * value in IPS_CTL bit 31 after enabling IPS through the
 		 * mailbox." Moreover, the mailbox may return a bogus state,
@@ -5364,9 +5362,7 @@ void hsw_disable_ips(const struct intel_crtc_state *crtc_state)
 		return;
 
 	if (IS_BROADWELL(dev_priv)) {
-		mutex_lock(&dev_priv->pcu_lock);
 		WARN_ON(sandybridge_pcode_write(dev_priv, DISPLAY_IPS_CONTROL, 0));
-		mutex_unlock(&dev_priv->pcu_lock);
 		/*
 		 * Wait for PCODE to finish disabling IPS. The BSpec specified
 		 * 42ms timeout value leads to occasional timeouts so use 100ms
@@ -9506,11 +9502,9 @@ static u32 hsw_read_dcomp(struct drm_i915_private *dev_priv)
 static void hsw_write_dcomp(struct drm_i915_private *dev_priv, u32 val)
 {
 	if (IS_HASWELL(dev_priv)) {
-		mutex_lock(&dev_priv->pcu_lock);
 		if (sandybridge_pcode_write(dev_priv, GEN6_PCODE_WRITE_D_COMP,
 					    val))
 			DRM_DEBUG_KMS("Failed to write to D_COMP\n");
-		mutex_unlock(&dev_priv->pcu_lock);
 	} else {
 		I915_WRITE(D_COMP_BDW, val);
 		POSTING_READ(D_COMP_BDW);
diff --git a/drivers/gpu/drm/i915/intel_hdcp.c b/drivers/gpu/drm/i915/intel_hdcp.c
index 99b007169c49..2476e867981d 100644
--- a/drivers/gpu/drm/i915/intel_hdcp.c
+++ b/drivers/gpu/drm/i915/intel_hdcp.c
@@ -213,10 +213,8 @@ static int intel_hdcp_load_keys(struct drm_i915_private *dev_priv)
 	 * from other platforms. So GEN9_BC uses the GT Driver Mailbox i/f.
 	 */
 	if (IS_GEN9_BC(dev_priv)) {
-		mutex_lock(&dev_priv->pcu_lock);
 		ret = sandybridge_pcode_write(dev_priv,
 					      SKL_PCODE_LOAD_HDCP_KEYS, 1);
-		mutex_unlock(&dev_priv->pcu_lock);
 		if (ret) {
 			DRM_ERROR("Failed to initiate HDCP key load (%d)\n",
 			          ret);
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 9db39ea9bd83..5d4a793a1988 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -317,7 +317,6 @@ static void chv_set_memory_dvfs(struct drm_i915_private *dev_priv, bool enable)
 {
 	u32 val;
 
-	mutex_lock(&dev_priv->pcu_lock);
 	vlv_punit_get(dev_priv);
 
 	val = vlv_punit_read(dev_priv, PUNIT_REG_DDR_SETUP2);
@@ -334,14 +333,12 @@ static void chv_set_memory_dvfs(struct drm_i915_private *dev_priv, bool enable)
 		DRM_ERROR("timed out waiting for Punit DDR DVFS request\n");
 
 	vlv_punit_put(dev_priv);
-	mutex_unlock(&dev_priv->pcu_lock);
 }
 
 static void chv_set_memory_pm5(struct drm_i915_private *dev_priv, bool enable)
 {
 	u32 val;
 
-	mutex_lock(&dev_priv->pcu_lock);
 	vlv_punit_get(dev_priv);
 
 	val = vlv_punit_read(dev_priv, PUNIT_REG_DSPSSPM);
@@ -352,7 +349,6 @@ static void chv_set_memory_pm5(struct drm_i915_private *dev_priv, bool enable)
 	vlv_punit_write(dev_priv, PUNIT_REG_DSPSSPM, val);
 
 	vlv_punit_put(dev_priv);
-	mutex_unlock(&dev_priv->pcu_lock);
 }
 
 #define FW_WM(value, plane) \
@@ -2821,11 +2817,9 @@ static void intel_read_wm_latency(struct drm_i915_private *dev_priv,
 
 		/* read the first set of memory latencies[0:3] */
 		val = 0; /* data0 to be programmed to 0 for first set */
-		mutex_lock(&dev_priv->pcu_lock);
 		ret = sandybridge_pcode_read(dev_priv,
 					     GEN9_PCODE_READ_MEM_LATENCY,
 					     &val);
-		mutex_unlock(&dev_priv->pcu_lock);
 
 		if (ret) {
 			DRM_ERROR("SKL Mailbox read error = %d\n", ret);
@@ -2842,11 +2836,9 @@ static void intel_read_wm_latency(struct drm_i915_private *dev_priv,
 
 		/* read the second set of memory latencies[4:7] */
 		val = 1; /* data0 to be programmed to 1 for second set */
-		mutex_lock(&dev_priv->pcu_lock);
 		ret = sandybridge_pcode_read(dev_priv,
 					     GEN9_PCODE_READ_MEM_LATENCY,
 					     &val);
-		mutex_unlock(&dev_priv->pcu_lock);
 		if (ret) {
 			DRM_ERROR("SKL Mailbox read error = %d\n", ret);
 			return;
@@ -3681,13 +3673,10 @@ intel_enable_sagv(struct drm_i915_private *dev_priv)
 		return 0;
 
 	DRM_DEBUG_KMS("Enabling SAGV\n");
-	mutex_lock(&dev_priv->pcu_lock);
-
 	ret = sandybridge_pcode_write(dev_priv, GEN9_PCODE_SAGV_CONTROL,
 				      GEN9_SAGV_ENABLE);
 
 	/* We don't need to wait for SAGV when enabling */
-	mutex_unlock(&dev_priv->pcu_lock);
 
 	/*
 	 * Some skl systems, pre-release machines in particular,
@@ -3718,15 +3707,11 @@ intel_disable_sagv(struct drm_i915_private *dev_priv)
 		return 0;
 
 	DRM_DEBUG_KMS("Disabling SAGV\n");
-	mutex_lock(&dev_priv->pcu_lock);
-
 	/* bspec says to keep retrying for at least 1 ms */
 	ret = skl_pcode_request(dev_priv, GEN9_PCODE_SAGV_CONTROL,
 				GEN9_SAGV_DISABLE,
 				GEN9_SAGV_IS_DISABLED, GEN9_SAGV_IS_DISABLED,
 				1);
-	mutex_unlock(&dev_priv->pcu_lock);
-
 	/*
 	 * Some skl systems, pre-release machines in particular,
 	 * don't actually have SAGV.
@@ -6143,7 +6128,6 @@ void vlv_wm_get_hw_state(struct drm_i915_private *dev_priv)
 	wm->level = VLV_WM_LEVEL_PM2;
 
 	if (IS_CHERRYVIEW(dev_priv)) {
-		mutex_lock(&dev_priv->pcu_lock);
 		vlv_punit_get(dev_priv);
 
 		val = vlv_punit_read(dev_priv, PUNIT_REG_DSPSSPM);
@@ -6175,7 +6159,6 @@ void vlv_wm_get_hw_state(struct drm_i915_private *dev_priv)
 		}
 
 		vlv_punit_put(dev_priv);
-		mutex_unlock(&dev_priv->pcu_lock);
 	}
 
 	for_each_intel_crtc(&dev_priv->drm, crtc) {
@@ -6804,7 +6787,7 @@ void gen6_rps_busy(struct drm_i915_private *dev_priv)
 {
 	struct intel_rps *rps = &dev_priv->gt_pm.rps;
 
-	mutex_lock(&dev_priv->pcu_lock);
+	mutex_lock(&rps->lock);
 	if (rps->enabled) {
 		u8 freq;
 
@@ -6827,7 +6810,7 @@ void gen6_rps_busy(struct drm_i915_private *dev_priv)
 					rps->max_freq_softlimit)))
 			DRM_DEBUG_DRIVER("Failed to set idle frequency\n");
 	}
-	mutex_unlock(&dev_priv->pcu_lock);
+	mutex_unlock(&rps->lock);
 }
 
 void gen6_rps_idle(struct drm_i915_private *dev_priv)
@@ -6841,7 +6824,7 @@ void gen6_rps_idle(struct drm_i915_private *dev_priv)
 	 */
 	gen6_disable_rps_interrupts(dev_priv);
 
-	mutex_lock(&dev_priv->pcu_lock);
+	mutex_lock(&rps->lock);
 	if (rps->enabled) {
 		if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
 			vlv_set_rps_idle(dev_priv);
@@ -6851,7 +6834,7 @@ void gen6_rps_idle(struct drm_i915_private *dev_priv)
 		I915_WRITE(GEN6_PMINTRMSK,
 			   gen6_sanitize_rps_pm_mask(dev_priv, ~0));
 	}
-	mutex_unlock(&dev_priv->pcu_lock);
+	mutex_unlock(&rps->lock);
 }
 
 void gen6_rps_boost(struct i915_request *rq)
@@ -6891,7 +6874,7 @@ int intel_set_rps(struct drm_i915_private *dev_priv, u8 val)
 	struct intel_rps *rps = &dev_priv->gt_pm.rps;
 	int err;
 
-	lockdep_assert_held(&dev_priv->pcu_lock);
+	lockdep_assert_held(&rps->lock);
 	GEM_BUG_ON(val > rps->max_freq);
 	GEM_BUG_ON(val < rps->min_freq);
 
@@ -7464,7 +7447,7 @@ static void gen6_update_ring_freq(struct drm_i915_private *dev_priv)
 	unsigned int max_gpu_freq, min_gpu_freq;
 	struct cpufreq_policy *policy;
 
-	WARN_ON(!mutex_is_locked(&dev_priv->pcu_lock));
+	lockdep_assert_held(&rps->lock);
 
 	if (rps->max_freq <= rps->min_freq)
 		return;
@@ -8549,8 +8532,6 @@ void intel_init_gt_powersave(struct drm_i915_private *dev_priv)
 		pm_runtime_get(&dev_priv->drm.pdev->dev);
 	}
 
-	mutex_lock(&dev_priv->pcu_lock);
-
 	/* Initialize RPS limits (for userspace) */
 	if (IS_CHERRYVIEW(dev_priv))
 		cherryview_init_gt_powersave(dev_priv);
@@ -8581,8 +8562,6 @@ void intel_init_gt_powersave(struct drm_i915_private *dev_priv)
 	rps->boost_freq = rps->max_freq;
 	rps->idle_freq = rps->min_freq;
 	rps->cur_freq = rps->idle_freq;
-
-	mutex_unlock(&dev_priv->pcu_lock);
 }
 
 void intel_cleanup_gt_powersave(struct drm_i915_private *dev_priv)
@@ -8608,7 +8587,7 @@ void intel_sanitize_gt_powersave(struct drm_i915_private *dev_priv)
 
 static inline void intel_disable_llc_pstate(struct drm_i915_private *i915)
 {
-	lockdep_assert_held(&i915->pcu_lock);
+	lockdep_assert_held(&i915->gt_pm.rps.lock);
 
 	if (!i915->gt_pm.llc_pstate.enabled)
 		return;
@@ -8620,7 +8599,7 @@ static inline void intel_disable_llc_pstate(struct drm_i915_private *i915)
 
 static void intel_disable_rc6(struct drm_i915_private *dev_priv)
 {
-	lockdep_assert_held(&dev_priv->pcu_lock);
+	lockdep_assert_held(&dev_priv->gt_pm.rps.lock);
 
 	if (!dev_priv->gt_pm.rc6.enabled)
 		return;
@@ -8639,7 +8618,7 @@ static void intel_disable_rc6(struct drm_i915_private *dev_priv)
 
 static void intel_disable_rps(struct drm_i915_private *dev_priv)
 {
-	lockdep_assert_held(&dev_priv->pcu_lock);
+	lockdep_assert_held(&dev_priv->gt_pm.rps.lock);
 
 	if (!dev_priv->gt_pm.rps.enabled)
 		return;
@@ -8660,19 +8639,19 @@ static void intel_disable_rps(struct drm_i915_private *dev_priv)
 
 void intel_disable_gt_powersave(struct drm_i915_private *dev_priv)
 {
-	mutex_lock(&dev_priv->pcu_lock);
+	mutex_lock(&dev_priv->gt_pm.rps.lock);
 
 	intel_disable_rc6(dev_priv);
 	intel_disable_rps(dev_priv);
 	if (HAS_LLC(dev_priv))
 		intel_disable_llc_pstate(dev_priv);
 
-	mutex_unlock(&dev_priv->pcu_lock);
+	mutex_unlock(&dev_priv->gt_pm.rps.lock);
 }
 
 static inline void intel_enable_llc_pstate(struct drm_i915_private *i915)
 {
-	lockdep_assert_held(&i915->pcu_lock);
+	lockdep_assert_held(&i915->gt_pm.rps.lock);
 
 	if (i915->gt_pm.llc_pstate.enabled)
 		return;
@@ -8684,7 +8663,7 @@ static inline void intel_enable_llc_pstate(struct drm_i915_private *i915)
 
 static void intel_enable_rc6(struct drm_i915_private *dev_priv)
 {
-	lockdep_assert_held(&dev_priv->pcu_lock);
+	lockdep_assert_held(&dev_priv->gt_pm.rps.lock);
 
 	if (dev_priv->gt_pm.rc6.enabled)
 		return;
@@ -8709,7 +8688,7 @@ static void intel_enable_rps(struct drm_i915_private *dev_priv)
 {
 	struct intel_rps *rps = &dev_priv->gt_pm.rps;
 
-	lockdep_assert_held(&dev_priv->pcu_lock);
+	lockdep_assert_held(&rps->lock);
 
 	if (rps->enabled)
 		return;
@@ -8744,7 +8723,7 @@ void intel_enable_gt_powersave(struct drm_i915_private *dev_priv)
 	if (intel_vgpu_active(dev_priv))
 		return;
 
-	mutex_lock(&dev_priv->pcu_lock);
+	mutex_lock(&dev_priv->gt_pm.rps.lock);
 
 	if (HAS_RC6(dev_priv))
 		intel_enable_rc6(dev_priv);
@@ -8753,7 +8732,7 @@ void intel_enable_gt_powersave(struct drm_i915_private *dev_priv)
 	if (HAS_LLC(dev_priv))
 		intel_enable_llc_pstate(dev_priv);
 
-	mutex_unlock(&dev_priv->pcu_lock);
+	mutex_unlock(&dev_priv->gt_pm.rps.lock);
 }
 
 static void ibx_init_clock_gating(struct drm_i915_private *dev_priv)
@@ -9769,22 +9748,20 @@ static inline int gen7_check_mailbox_status(struct drm_i915_private *dev_priv)
 	}
 }
 
-int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u32 mbox, u32 *val)
+static int
+__sandybridge_pcode_read(struct drm_i915_private *dev_priv, u32 mbox, u32 *val)
 {
 	int status;
 
-	WARN_ON(!mutex_is_locked(&dev_priv->pcu_lock));
+	lockdep_assert_held(&dev_priv->sb_lock);
 
 	/* GEN6_PCODE_* are outside of the forcewake domain, we can
 	 * use te fw I915_READ variants to reduce the amount of work
 	 * required when reading/writing.
 	 */
 
-	if (I915_READ_FW(GEN6_PCODE_MAILBOX) & GEN6_PCODE_READY) {
-		DRM_DEBUG_DRIVER("warning: pcode (read from mbox %x) mailbox access failed for %ps\n",
-				 mbox, __builtin_return_address(0));
+	if (I915_READ_FW(GEN6_PCODE_MAILBOX) & GEN6_PCODE_READY)
 		return -EAGAIN;
-	}
 
 	I915_WRITE_FW(GEN6_PCODE_DATA, *val);
 	I915_WRITE_FW(GEN6_PCODE_DATA1, 0);
@@ -9792,11 +9769,8 @@ int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u32 mbox, u32 *val
 
 	if (__intel_wait_for_register_fw(&dev_priv->uncore,
 					 GEN6_PCODE_MAILBOX, GEN6_PCODE_READY, 0,
-					 500, 0, NULL)) {
-		DRM_ERROR("timeout waiting for pcode read (from mbox %x) to finish for %ps\n",
-			  mbox, __builtin_return_address(0));
+					 500, 0, NULL))
 		return -ETIMEDOUT;
-	}
 
 	*val = I915_READ_FW(GEN6_PCODE_DATA);
 	I915_WRITE_FW(GEN6_PCODE_DATA, 0);
@@ -9806,33 +9780,40 @@ int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u32 mbox, u32 *val
 	else
 		status = gen6_check_mailbox_status(dev_priv);
 
+	return status;
+}
+
+int
+sandybridge_pcode_read(struct drm_i915_private *dev_priv, u32 mbox, u32 *val)
+{
+	int status;
+
+	mutex_lock(&dev_priv->sb_lock);
+	status = __sandybridge_pcode_read(dev_priv, mbox, val);
+	mutex_unlock(&dev_priv->sb_lock);
+
 	if (status) {
 		DRM_DEBUG_DRIVER("warning: pcode (read from mbox %x) mailbox access failed for %ps: %d\n",
 				 mbox, __builtin_return_address(0), status);
-		return status;
 	}
 
-	return 0;
+	return status;
 }
 
-int sandybridge_pcode_write_timeout(struct drm_i915_private *dev_priv,
-				    u32 mbox, u32 val,
-				    int fast_timeout_us, int slow_timeout_ms)
+static int __sandybridge_pcode_write_timeout(struct drm_i915_private *dev_priv,
+					     u32 mbox, u32 val,
+					     int fast_timeout_us,
+					     int slow_timeout_ms)
 {
 	int status;
 
-	WARN_ON(!mutex_is_locked(&dev_priv->pcu_lock));
-
 	/* GEN6_PCODE_* are outside of the forcewake domain, we can
 	 * use te fw I915_READ variants to reduce the amount of work
 	 * required when reading/writing.
 	 */
 
-	if (I915_READ_FW(GEN6_PCODE_MAILBOX) & GEN6_PCODE_READY) {
-		DRM_DEBUG_DRIVER("warning: pcode (write of 0x%08x to mbox %x) mailbox access failed for %ps\n",
-				 val, mbox, __builtin_return_address(0));
+	if (I915_READ_FW(GEN6_PCODE_MAILBOX) & GEN6_PCODE_READY)
 		return -EAGAIN;
-	}
 
 	I915_WRITE_FW(GEN6_PCODE_DATA, val);
 	I915_WRITE_FW(GEN6_PCODE_DATA1, 0);
@@ -9841,11 +9822,8 @@ int sandybridge_pcode_write_timeout(struct drm_i915_private *dev_priv,
 	if (__intel_wait_for_register_fw(&dev_priv->uncore,
 					 GEN6_PCODE_MAILBOX, GEN6_PCODE_READY, 0,
 					 fast_timeout_us, slow_timeout_ms,
-					 NULL)) {
-		DRM_ERROR("timeout waiting for pcode write of 0x%08x to mbox %x to finish for %ps\n",
-			  val, mbox, __builtin_return_address(0));
+					 NULL))
 		return -ETIMEDOUT;
-	}
 
 	I915_WRITE_FW(GEN6_PCODE_DATA, 0);
 
@@ -9854,13 +9832,28 @@ int sandybridge_pcode_write_timeout(struct drm_i915_private *dev_priv,
 	else
 		status = gen6_check_mailbox_status(dev_priv);
 
+	return status;
+}
+
+int sandybridge_pcode_write_timeout(struct drm_i915_private *dev_priv,
+				    u32 mbox, u32 val,
+				    int fast_timeout_us,
+				    int slow_timeout_ms)
+{
+	int status;
+
+	mutex_lock(&dev_priv->sb_lock);
+	status = __sandybridge_pcode_write_timeout(dev_priv, mbox, val,
+						   fast_timeout_us,
+						   slow_timeout_ms);
+	mutex_unlock(&dev_priv->sb_lock);
+
 	if (status) {
 		DRM_DEBUG_DRIVER("warning: pcode (write of 0x%08x to mbox %x) mailbox access failed for %ps: %d\n",
 				 val, mbox, __builtin_return_address(0), status);
-		return status;
 	}
 
-	return 0;
+	return status;
 }
 
 static bool skl_pcode_try_request(struct drm_i915_private *dev_priv, u32 mbox,
@@ -9869,7 +9862,7 @@ static bool skl_pcode_try_request(struct drm_i915_private *dev_priv, u32 mbox,
 {
 	u32 val = request;
 
-	*status = sandybridge_pcode_read(dev_priv, mbox, &val);
+	*status = __sandybridge_pcode_read(dev_priv, mbox, &val);
 
 	return *status || ((val & reply_mask) == reply);
 }
@@ -9899,7 +9892,7 @@ int skl_pcode_request(struct drm_i915_private *dev_priv, u32 mbox, u32 request,
 	u32 status;
 	int ret;
 
-	WARN_ON(!mutex_is_locked(&dev_priv->pcu_lock));
+	mutex_lock(&dev_priv->sb_lock);
 
 #define COND skl_pcode_try_request(dev_priv, mbox, request, reply_mask, reply, \
 				   &status)
@@ -9935,6 +9928,7 @@ int skl_pcode_request(struct drm_i915_private *dev_priv, u32 mbox, u32 request,
 	preempt_enable();
 
 out:
+	mutex_unlock(&dev_priv->sb_lock);
 	return ret ? ret : status;
 #undef COND
 }
@@ -10004,7 +9998,7 @@ int intel_freq_opcode(struct drm_i915_private *dev_priv, int val)
 
 void intel_pm_setup(struct drm_i915_private *dev_priv)
 {
-	mutex_init(&dev_priv->pcu_lock);
+	mutex_init(&dev_priv->gt_pm.rps.lock);
 	mutex_init(&dev_priv->gt_pm.rps.power.mutex);
 
 	atomic_set(&dev_priv->gt_pm.rps.num_waiters, 0);
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index ac8bc5baef40..a80ff35f6c81 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -1211,7 +1211,6 @@ static void vlv_set_power_well(struct drm_i915_private *dev_priv,
 	state = enable ? PUNIT_PWRGT_PWR_ON(pw_idx) :
 			 PUNIT_PWRGT_PWR_GATE(pw_idx);
 
-	mutex_lock(&dev_priv->pcu_lock);
 	vlv_punit_get(dev_priv);
 
 #define COND \
@@ -1234,7 +1233,6 @@ static void vlv_set_power_well(struct drm_i915_private *dev_priv,
 
 out:
 	vlv_punit_put(dev_priv);
-	mutex_unlock(&dev_priv->pcu_lock);
 }
 
 static void vlv_power_well_enable(struct drm_i915_private *dev_priv,
@@ -1261,7 +1259,6 @@ static bool vlv_power_well_enabled(struct drm_i915_private *dev_priv,
 	mask = PUNIT_PWRGT_MASK(pw_idx);
 	ctrl = PUNIT_PWRGT_PWR_ON(pw_idx);
 
-	mutex_lock(&dev_priv->pcu_lock);
 	vlv_punit_get(dev_priv);
 
 	state = vlv_punit_read(dev_priv, PUNIT_REG_PWRGT_STATUS) & mask;
@@ -1282,7 +1279,6 @@ static bool vlv_power_well_enabled(struct drm_i915_private *dev_priv,
 	WARN_ON(ctrl != state);
 
 	vlv_punit_put(dev_priv);
-	mutex_unlock(&dev_priv->pcu_lock);
 
 	return enabled;
 }
@@ -1768,7 +1764,6 @@ static bool chv_pipe_power_well_enabled(struct drm_i915_private *dev_priv,
 	bool enabled;
 	u32 state, ctrl;
 
-	mutex_lock(&dev_priv->pcu_lock);
 	vlv_punit_get(dev_priv);
 
 	state = vlv_punit_read(dev_priv, PUNIT_REG_DSPSSPM) & DP_SSS_MASK(pipe);
@@ -1787,7 +1782,6 @@ static bool chv_pipe_power_well_enabled(struct drm_i915_private *dev_priv,
 	WARN_ON(ctrl << 16 != state);
 
 	vlv_punit_put(dev_priv);
-	mutex_unlock(&dev_priv->pcu_lock);
 
 	return enabled;
 }
@@ -1802,7 +1796,6 @@ static void chv_set_pipe_power_well(struct drm_i915_private *dev_priv,
 
 	state = enable ? DP_SSS_PWR_ON(pipe) : DP_SSS_PWR_GATE(pipe);
 
-	mutex_lock(&dev_priv->pcu_lock);
 	vlv_punit_get(dev_priv);
 
 #define COND \
@@ -1825,7 +1818,6 @@ static void chv_set_pipe_power_well(struct drm_i915_private *dev_priv,
 
 out:
 	vlv_punit_put(dev_priv);
-	mutex_unlock(&dev_priv->pcu_lock);
 }
 
 static void chv_pipe_power_well_enable(struct drm_i915_private *dev_priv,
@@ -4019,11 +4011,9 @@ static bool vlv_punit_is_power_gated(struct drm_i915_private *dev_priv, u32 reg0
 {
 	bool ret;
 
-	mutex_lock(&dev_priv->pcu_lock);
 	vlv_punit_get(dev_priv);
 	ret = (vlv_punit_read(dev_priv, reg0) & SSPM0_SSC_MASK) == SSPM0_SSC_PWR_GATE;
 	vlv_punit_put(dev_priv);
-	mutex_unlock(&dev_priv->pcu_lock);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/intel_sideband.c b/drivers/gpu/drm/i915/intel_sideband.c
index 7c33925f52f9..457b8cad5494 100644
--- a/drivers/gpu/drm/i915/intel_sideband.c
+++ b/drivers/gpu/drm/i915/intel_sideband.c
@@ -143,8 +143,6 @@ u32 vlv_punit_read(struct drm_i915_private *i915, u32 addr)
 {
 	u32 val = 0;
 
-	lockdep_assert_held(&i915->pcu_lock);
-
 	vlv_sideband_rw(i915, PCI_DEVFN(0, 0), IOSF_PORT_PUNIT,
 			SB_CRRDDA_NP, addr, &val);
 
@@ -153,8 +151,6 @@ u32 vlv_punit_read(struct drm_i915_private *i915, u32 addr)
 
 int vlv_punit_write(struct drm_i915_private *i915, u32 addr, u32 val)
 {
-	lockdep_assert_held(&i915->pcu_lock);
-
 	return vlv_sideband_rw(i915, PCI_DEVFN(0, 0), IOSF_PORT_PUNIT,
 			       SB_CRWRDA_NP, addr, &val);
 }