NVIDIA Tegra power management patches for 5.16

index 04b4691a8aac..3057beabd370 100644
@@ -2348,12 +2348,12 @@ static void _opp_detach_genpd(struct opp_table *opp_table)
  * "required-opps" are added in DT.
  */
 struct opp_table *dev_pm_opp_attach_genpd(struct device *dev,
-		const char **names, struct device ***virt_devs)
+		const char * const *names, struct device ***virt_devs)
 {
 	struct opp_table *opp_table;
 	struct device *virt_dev;
 	int index = 0, ret = -EINVAL;
-	const char **name = names;
+	const char * const *name = names;
 
 	opp_table = _add_opp_table(dev, false);
 	if (IS_ERR(opp_table))

@@ -2457,7 +2457,7 @@ static void devm_pm_opp_detach_genpd(void *data)
  *
  * Return: 0 on success and errorno otherwise.
  */
-int devm_pm_opp_attach_genpd(struct device *dev, const char **names,
+int devm_pm_opp_attach_genpd(struct device *dev, const char * const *names,
 			     struct device ***virt_devs)
 {
 	struct opp_table *opp_table;

index a95d6fdd20b6..879c138c7b8e 100644
@@ -156,9 +156,9 @@ int devm_pm_opp_set_clkname(struct device *dev, const char *name);
 struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data));
 void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table);
 int devm_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data));
-struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char **names, struct device ***virt_devs);
+struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char * const *names, struct device ***virt_devs);
 void dev_pm_opp_detach_genpd(struct opp_table *opp_table);
-int devm_pm_opp_attach_genpd(struct device *dev, const char **names, struct device ***virt_devs);
+int devm_pm_opp_attach_genpd(struct device *dev, const char * const *names, struct device ***virt_devs);
 struct dev_pm_opp *dev_pm_opp_xlate_required_opp(struct opp_table *src_table, struct opp_table *dst_table, struct dev_pm_opp *src_opp);
 int dev_pm_opp_xlate_performance_state(struct opp_table *src_table, struct opp_table *dst_table, unsigned int pstate);
 int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq);

@@ -376,7 +376,7 @@ static inline int devm_pm_opp_set_clkname(struct device *dev, const char *name)
 	return -EOPNOTSUPP;
 }
 
-static inline struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char **names, struct device ***virt_devs)
+static inline struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char * const *names, struct device ***virt_devs)
 {
 	return ERR_PTR(-EOPNOTSUPP);
 }

@@ -384,7 +384,7 @@ static inline struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, cons
 static inline void dev_pm_opp_detach_genpd(struct opp_table *opp_table) {}
 
 static inline int devm_pm_opp_attach_genpd(struct device *dev,
-					   const char **names,
+					   const char * const *names,
 					   struct device ***virt_devs)
 {
 	return -EOPNOTSUPP;

index af41ad80ec21..5b4a042f60fb 100644
@@ -39,4 +39,28 @@ devm_tegra_core_dev_init_opp_table(struct device *dev,
 }
 #endif
 
+/*
+ * This function should be invoked with the enabled runtime PM of the device
+ * in order to initialize performance state properly. Most of Tegra devices
+ * are assumed to be suspended at a probe time and GENPD require RPM to be
+ * enabled to set up the rpm-resume state, otherwise device is active and
+ * performance state is applied immediately. Note that it will initialize
+ * OPP bandwidth if it's wired in a device-tree for this device, which is
+ * undesirable for a suspended device.
+ */
+static inline int
+devm_tegra_core_dev_init_opp_table_common(struct device *dev)
+{
+	struct tegra_core_opp_params opp_params = {};
+	int err;
+
+	opp_params.init_state = true;
+
+	err = devm_tegra_core_dev_init_opp_table(dev, &opp_params);
+	if (err != -ENODEV)
+		return err;
+
+	return 0;
+}
+
 #endif /* __SOC_TEGRA_COMMON_H__ */

index 50091c4ec948..fb8faf7b226a 100644
@@ -360,6 +360,7 @@ struct tegra_pmc_soc {
 	unsigned int num_pmc_clks;
 	bool has_blink_output;
 	bool has_usb_sleepwalk;
+	bool supports_core_domain;
 };
 
 /**

@@ -3041,6 +3042,7 @@ static void tegra20_pmc_setup_irq_polarity(struct tegra_pmc *pmc,
 }
 
 static const struct tegra_pmc_soc tegra20_pmc_soc = {
+	.supports_core_domain = false,
 	.num_powergates = ARRAY_SIZE(tegra20_powergates),
 	.powergates = tegra20_powergates,
 	.num_cpu_powergates = 0,

@@ -3101,6 +3103,7 @@ static const char * const tegra30_reset_sources[] = {
 };
 
 static const struct tegra_pmc_soc tegra30_pmc_soc = {
+	.supports_core_domain = false,
 	.num_powergates = ARRAY_SIZE(tegra30_powergates),
 	.powergates = tegra30_powergates,
 	.num_cpu_powergates = ARRAY_SIZE(tegra30_cpu_powergates),

@@ -3157,6 +3160,7 @@ static const u8 tegra114_cpu_powergates[] = {
 };
 
 static const struct tegra_pmc_soc tegra114_pmc_soc = {
+	.supports_core_domain = false,
 	.num_powergates = ARRAY_SIZE(tegra114_powergates),
 	.powergates = tegra114_powergates,
 	.num_cpu_powergates = ARRAY_SIZE(tegra114_cpu_powergates),

@@ -3273,6 +3277,7 @@ static const struct pinctrl_pin_desc tegra124_pin_descs[] = {
 };
 
 static const struct tegra_pmc_soc tegra124_pmc_soc = {
+	.supports_core_domain = false,
 	.num_powergates = ARRAY_SIZE(tegra124_powergates),
 	.powergates = tegra124_powergates,
 	.num_cpu_powergates = ARRAY_SIZE(tegra124_cpu_powergates),

@@ -3398,6 +3403,7 @@ static const struct tegra_wake_event tegra210_wake_events[] = {
 };
 
 static const struct tegra_pmc_soc tegra210_pmc_soc = {
+	.supports_core_domain = false,
 	.num_powergates = ARRAY_SIZE(tegra210_powergates),
 	.powergates = tegra210_powergates,
 	.num_cpu_powergates = ARRAY_SIZE(tegra210_cpu_powergates),

@@ -3555,6 +3561,7 @@ static const struct tegra_wake_event tegra186_wake_events[] = {
 };
 
 static const struct tegra_pmc_soc tegra186_pmc_soc = {
+	.supports_core_domain = false,
 	.num_powergates = 0,
 	.powergates = NULL,
 	.num_cpu_powergates = 0,

@@ -3689,6 +3696,7 @@ static const struct tegra_wake_event tegra194_wake_events[] = {
 };
 
 static const struct tegra_pmc_soc tegra194_pmc_soc = {
+	.supports_core_domain = false,
 	.num_powergates = 0,
 	.powergates = NULL,
 	.num_cpu_powergates = 0,

@@ -3757,6 +3765,7 @@ static const char * const tegra234_reset_sources[] = {
 };
 
 static const struct tegra_pmc_soc tegra234_pmc_soc = {
+	.supports_core_domain = false,
 	.num_powergates = 0,
 	.powergates = NULL,
 	.num_cpu_powergates = 0,

@@ -3803,6 +3812,14 @@ static void tegra_pmc_sync_state(struct device *dev)
 {
 	int err;
 
+	/*
+	 * Newer device-trees have power domains, but we need to prepare all
+	 * device drivers with runtime PM and OPP support first, otherwise
+	 * state syncing is unsafe.
+	 */
+	if (!pmc->soc->supports_core_domain)
+		return;
+
 	/*
 	 * Older device-trees don't have core PD, and thus, there are
 	 * no dependencies that will block the state syncing. We shouldn't

index cd33e99249c3..a42d4f98c078 100644
@@ -111,9 +111,7 @@ int devm_tegra_core_dev_init_opp_table(struct device *dev,
 	 */
 	err = devm_pm_opp_of_add_table(dev);
 	if (err) {
-		if (err == -ENODEV)
-			dev_err_once(dev, "OPP table not found, please update device-tree\n");
-		else
+		if (err != -ENODEV)
 			dev_err(dev, "failed to add OPP table: %d\n", err);
 
 		return err;

222 lines not on this page · raw message

index eaa079c177c3..100b5d9b7e26 100644
@@ -1914,7 +1914,7 @@ static struct clk *_tegra_clk_register_pll(struct tegra_clk_pll *pll,
 	/* Data in .init is copied by clk_register(), so stack variable OK */
 	pll->hw.init = &init;
 
-	return clk_register(NULL, &pll->hw);
+	return tegra_clk_dev_register(&pll->hw);
 }
 
 struct clk *tegra_clk_register_pll(const char *name, const char *parent_name,

index 6099c6e9acd4..a98a420398fa 100644
@@ -226,7 +226,7 @@ struct clk *tegra_clk_register_super_mux(const char *name,
 	/* Data in .init is copied by clk_register(), so stack variable OK */
 	super->hw.init = &init;
 
-	clk = clk_register(NULL, &super->hw);
+	clk = tegra_clk_dev_register(&super->hw);
 	if (IS_ERR(clk))
 		kfree(super);
 

127 lines not on this page · raw message

185 lines not on this page · raw message

113 lines not on this page · raw message

index 0c3ba0ccce1a..5d80d8b79b8e 100644
@@ -927,4 +927,6 @@ struct clk *tegra20_clk_register_emc(void __iomem *ioaddr, bool low_jitter);
 struct clk *tegra210_clk_register_emc(struct device_node *np,
 				      void __iomem *regs);
 
+struct clk *tegra_clk_dev_register(struct clk_hw *hw);
+
 #endif /* TEGRA_CLK_H */

index 8a14880c61bb..18d9c8d206e3 100644
@@ -7,6 +7,7 @@
  */
 
 #include <linux/debugfs.h>
+#include <linux/pm_runtime.h>
 #include <linux/seq_file.h>
 #include <linux/uaccess.h>
 

@@ -52,6 +53,11 @@ static int show_channel(struct host1x_channel *ch, void *data, bool show_fifo)
 {
 	struct host1x *m = dev_get_drvdata(ch->dev->parent);
 	struct output *o = data;
+	int err;
+
+	err = pm_runtime_resume_and_get(m->dev);
+	if (err < 0)
+		return err;
 
 	mutex_lock(&ch->cdma.lock);
 	mutex_lock(&debug_lock);

@@ -64,6 +70,8 @@ static int show_channel(struct host1x_channel *ch, void *data, bool show_fifo)
 	mutex_unlock(&debug_lock);
 	mutex_unlock(&ch->cdma.lock);
 
+	pm_runtime_put(m->dev);
+
 	return 0;
 }
 

@@ -71,9 +79,14 @@ static void show_syncpts(struct host1x *m, struct output *o)
 {
 	struct list_head *pos;
 	unsigned int i;
+	int err;
 
 	host1x_debug_output(o, "---- syncpts ----\n");
 
+	err = pm_runtime_resume_and_get(m->dev);
+	if (err < 0)
+		return;
+
 	for (i = 0; i < host1x_syncpt_nb_pts(m); i++) {
 		u32 max = host1x_syncpt_read_max(m->syncpt + i);
 		u32 min = host1x_syncpt_load(m->syncpt + i);

@@ -101,6 +114,8 @@ static void show_syncpts(struct host1x *m, struct output *o)
 					    base_val);
 	}
 
+	pm_runtime_put(m->dev);
+
 	host1x_debug_output(o, "\n");
 }
 

226 lines not on this page · raw message

index fa6d4bc46e98..41a7a63514c4 100644
@@ -118,7 +118,8 @@ struct host1x {
 	struct host1x_syncpt_base *bases;
 	struct device *dev;
 	struct clk *clk;
-	struct reset_control *rst;
+	struct reset_control_bulk_data resets[2];
+	unsigned int nresets;
 
 	struct iommu_group *group;
 	struct iommu_domain *domain;

68 lines not on this page · raw message

index 45b6be927ec4..965ba21818b1 100644
@@ -297,14 +297,11 @@ int host1x_intr_init(struct host1x *host, unsigned int irq_sync)
 			 "host1x_sp_%02u", id);
 	}
 
-	host1x_intr_start(host);
-
 	return 0;
 }
 
 void host1x_intr_deinit(struct host1x *host)
 {
-	host1x_intr_stop(host);
 }
 
 void host1x_intr_start(struct host1x *host)

index d198a10848c6..e08e331e46ae 100644
@@ -143,6 +143,8 @@ void host1x_syncpt_restore(struct host1x *host)
 	for (i = 0; i < host1x_syncpt_nb_bases(host); i++)
 		host1x_hw_syncpt_restore_wait_base(host, sp_base + i);
 
+	host1x_hw_syncpt_enable_protection(host);
+
 	wmb();
 }
 

@@ -366,9 +368,6 @@ int host1x_syncpt_init(struct host1x *host)
 	host->syncpt = syncpt;
 	host->bases = bases;
 
-	host1x_syncpt_restore(host);
-	host1x_hw_syncpt_enable_protection(host);
-
 	/* Allocate sync point to use for clearing waits for expired fences */
 	host->nop_sp = host1x_syncpt_alloc(host, 0, "reserved-nop");
 	if (!host->nop_sp)

index 4cd212bb570d..2a9a3a8d5931 100644
@@ -75,6 +75,14 @@ struct host1x_channel *host1x_channel_get_index(struct host1x *host,
 	return ch;
 }
 
+void host1x_channel_stop(struct host1x_channel *channel)
+{
+	struct host1x *host = dev_get_drvdata(channel->dev->parent);
+
+	host1x_hw_cdma_stop(host, &channel->cdma);
+}
+EXPORT_SYMBOL(host1x_channel_stop);
+
 static void release_channel(struct kref *kref)
 {
 	struct host1x_channel *channel =

index 7bccf589aba7..66473b5be0af 100644
@@ -181,6 +181,7 @@ struct host1x_job;
 
 struct host1x_channel *host1x_channel_request(struct host1x_client *client);
 struct host1x_channel *host1x_channel_get(struct host1x_channel *channel);
+void host1x_channel_stop(struct host1x_channel *channel);
 void host1x_channel_put(struct host1x_channel *channel);
 int host1x_job_submit(struct host1x_job *job);
 

index a29d64f87563..d4047a14e2b6 100644
@@ -11,9 +11,12 @@
 #include <linux/interconnect.h>
 #include <linux/module.h>
 #include <linux/of_device.h>
+#include <linux/pm_domain.h>
+#include <linux/pm_opp.h>
 #include <linux/pm_runtime.h>
 #include <linux/reset.h>
 
+#include <soc/tegra/common.h>
 #include <soc/tegra/pmc.h>
 
 #include <drm/drm_atomic.h>

@@ -1762,6 +1765,47 @@ int tegra_dc_state_setup_clock(struct tegra_dc *dc,
 	return 0;
 }
 
+static void tegra_dc_update_voltage_state(struct tegra_dc *dc,
+					  struct tegra_dc_state *state)
+{
+	unsigned long rate, pstate;
+	struct dev_pm_opp *opp;
+	int err;
+
+	if (!dc->has_opp_table)
+		return;
+
+	/* calculate actual pixel clock rate which depends on internal divider */
+	rate = DIV_ROUND_UP(clk_get_rate(dc->clk) * 2, state->div + 2);
+
+	/* find suitable OPP for the rate */
+	opp = dev_pm_opp_find_freq_ceil(dc->dev, &rate);
+
+	if (opp == ERR_PTR(-ERANGE))
+		opp = dev_pm_opp_find_freq_floor(dc->dev, &rate);
+
+	if (IS_ERR(opp)) {
+		dev_err(dc->dev, "failed to find OPP for %luHz: %pe\n",
+			rate, opp);
+		return;
+	}
+
+	pstate = dev_pm_opp_get_required_pstate(opp, 0);
+	dev_pm_opp_put(opp);
+
+	/*
+	 * The minimum core voltage depends on the pixel clock rate (which
+	 * depends on internal clock divider of the CRTC) and not on the
+	 * rate of the display controller clock. This is why we're not using
+	 * dev_pm_opp_set_rate() API and instead controlling the power domain
+	 * directly.
+	 */
+	err = dev_pm_genpd_set_performance_state(dc->dev, pstate);
+	if (err)
+		dev_err(dc->dev, "failed to set power domain state to %lu: %d\n",
+			pstate, err);
+}
+
 static void tegra_dc_commit_state(struct tegra_dc *dc,
 				  struct tegra_dc_state *state)
 {

@@ -1801,6 +1845,8 @@ static void tegra_dc_commit_state(struct tegra_dc *dc,
 		value = SHIFT_CLK_DIVIDER(state->div) | PIXEL_CLK_DIVIDER_PCD1;
 		tegra_dc_writel(dc, value, DC_DISP_DISP_CLOCK_CONTROL);
 	}
+
+	tegra_dc_update_voltage_state(dc, state);
 }
 
 static void tegra_dc_stop(struct tegra_dc *dc)

@@ -1991,6 +2037,13 @@ static void tegra_crtc_atomic_disable(struct drm_crtc *crtc,
 	err = host1x_client_suspend(&dc->client);
 	if (err < 0)
 		dev_err(dc->dev, "failed to suspend: %d\n", err);
+
+	if (dc->has_opp_table) {
+		err = dev_pm_genpd_set_performance_state(dc->dev, 0);
+		if (err)
+			dev_err(dc->dev,
+				"failed to clear power domain state: %d\n", err);
+	}
 }
 
 static void tegra_crtc_atomic_enable(struct drm_crtc *crtc,

@@ -2973,6 +3026,23 @@ static int tegra_dc_couple(struct tegra_dc *dc)
 	return 0;
 }
 
+static int tegra_dc_init_opp_table(struct tegra_dc *dc)
+{
+	struct tegra_core_opp_params opp_params = {};
+	int err;
+
+	err = devm_tegra_core_dev_init_opp_table(dc->dev, &opp_params);
+	if (err && err != -ENODEV)
+		return err;
+
+	if (err)
+		dc->has_opp_table = false;
+	else
+		dc->has_opp_table = true;
+
+	return 0;
+}
+
 static int tegra_dc_probe(struct platform_device *pdev)
 {
 	u64 dma_mask = dma_get_mask(pdev->dev.parent);

@@ -3038,6 +3108,10 @@ static int tegra_dc_probe(struct platform_device *pdev)
 		tegra_powergate_power_off(dc->powergate);
 	}
 
+	err = tegra_dc_init_opp_table(dc);
+	if (err < 0)
+		return err;
+
 	dc->regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(dc->regs))
 		return PTR_ERR(dc->regs);

index 40378308d527..871cfb0cd31c 100644
@@ -100,6 +100,8 @@ struct tegra_dc {
 	struct drm_info_list *debugfs_files;
 
 	const struct tegra_dc_soc_info *soc;
+
+	bool has_opp_table;
 };
 
 static inline struct tegra_dc *

index e5d2a4026028..9a87d351a828 100644
@@ -11,10 +11,13 @@
 #include <linux/math64.h>
 #include <linux/module.h>
 #include <linux/of_device.h>
+#include <linux/pm_opp.h>
 #include <linux/pm_runtime.h>
 #include <linux/regulator/consumer.h>
 #include <linux/reset.h>
 
+#include <soc/tegra/common.h>
+
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_crtc.h>
 #include <drm/drm_debugfs.h>

@@ -1195,7 +1198,7 @@ static void tegra_hdmi_encoder_enable(struct drm_encoder *encoder)
 	h_back_porch = mode->htotal - mode->hsync_end;
 	h_front_porch = mode->hsync_start - mode->hdisplay;
 
-	err = clk_set_rate(hdmi->clk, hdmi->pixel_clock);
+	err = dev_pm_opp_set_rate(hdmi->dev, hdmi->pixel_clock);
 	if (err < 0) {
 		dev_err(hdmi->dev, "failed to set HDMI clock frequency: %d\n",
 			err);

@@ -1732,7 +1735,14 @@ static int tegra_hdmi_probe(struct platform_device *pdev)
 	}
 
 	platform_set_drvdata(pdev, hdmi);
-	pm_runtime_enable(&pdev->dev);
+
+	err = devm_pm_runtime_enable(&pdev->dev);
+	if (err)
+		return err;
+
+	err = devm_tegra_core_dev_init_opp_table_common(&pdev->dev);
+	if (err)
+		return err;
 
 	INIT_LIST_HEAD(&hdmi->client.list);
 	hdmi->client.ops = &hdmi_client_ops;

@@ -1753,8 +1763,6 @@ static int tegra_hdmi_remove(struct platform_device *pdev)
 	struct tegra_hdmi *hdmi = platform_get_drvdata(pdev);
 	int err;
 
-	pm_runtime_disable(&pdev->dev);
-
 	err = host1x_client_unregister(&hdmi->client);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to unregister host1x client: %d\n",

index de288cba3905..13df8f118f75 100644
@@ -7,11 +7,21 @@
 #include <linux/iommu.h>
 #include <linux/module.h>
 #include <linux/of_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/reset.h>
+
+#include <soc/tegra/common.h>
 
 #include "drm.h"
 #include "gem.h"
 #include "gr2d.h"
 
+enum {
+	RST_MC,
+	RST_GR2D,
+	RST_GR2D_MAX,
+};
+
 struct gr2d_soc {
 	unsigned int version;
 };

@@ -21,6 +31,9 @@ struct gr2d {
 	struct host1x_channel *channel;
 	struct clk *clk;
 
+	struct reset_control_bulk_data resets[RST_GR2D_MAX];
+	unsigned int nresets;
+
 	const struct gr2d_soc *soc;
 
 	DECLARE_BITMAP(addr_regs, GR2D_NUM_REGS);

@@ -101,16 +114,24 @@ static int gr2d_open_channel(struct tegra_drm_client *client,
 			     struct tegra_drm_context *context)
 {
 	struct gr2d *gr2d = to_gr2d(client);
+	int err;
 
 	context->channel = host1x_channel_get(gr2d->channel);
 	if (!context->channel)
 		return -ENOMEM;
 
+	err = pm_runtime_resume_and_get(client->base.dev);
+	if (err) {
+		host1x_channel_put(context->channel);
+		return err;
+	}
+
 	return 0;
 }
 
 static void gr2d_close_channel(struct tegra_drm_context *context)
 {
+	pm_runtime_put_sync(context->client->base.dev);
 	host1x_channel_put(context->channel);
 }
 

@@ -190,6 +211,27 @@ static const u32 gr2d_addr_regs[] = {
 	GR2D_VA_BASE_ADDR_SB,
 };
 
+static int gr2d_get_resets(struct device *dev, struct gr2d *gr2d)
+{
+	int err;
+
+	gr2d->resets[RST_MC].id = "mc";
+	gr2d->resets[RST_GR2D].id = "2d";
+	gr2d->nresets = RST_GR2D_MAX;
+
+	err = devm_reset_control_bulk_get_optional_exclusive_released(
+				dev, gr2d->nresets, gr2d->resets);
+	if (err) {
+		dev_err(dev, "failed to get reset: %d\n", err);
+		return err;
+	}
+
+	if (WARN_ON(!gr2d->resets[RST_GR2D].rstc))
+		return -ENOENT;
+
+	return 0;
+}
+
 static int gr2d_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;

@@ -202,6 +244,8 @@ static int gr2d_probe(struct platform_device *pdev)
 	if (!gr2d)
 		return -ENOMEM;
 
+	platform_set_drvdata(pdev, gr2d);
+
 	gr2d->soc = of_device_get_match_data(dev);
 
 	syncpts = devm_kzalloc(dev, sizeof(*syncpts), GFP_KERNEL);

@@ -214,11 +258,9 @@ static int gr2d_probe(struct platform_device *pdev)
 		return PTR_ERR(gr2d->clk);
 	}
 
-	err = clk_prepare_enable(gr2d->clk);
-	if (err) {
-		dev_err(dev, "cannot turn on clock\n");
+	err = gr2d_get_resets(dev, gr2d);
+	if (err)
 		return err;
-	}
 
 	INIT_LIST_HEAD(&gr2d->client.base.list);
 	gr2d->client.base.ops = &gr2d_client_ops;

@@ -231,20 +273,31 @@ static int gr2d_probe(struct platform_device *pdev)
 	gr2d->client.version = gr2d->soc->version;
 	gr2d->client.ops = &gr2d_ops;
 
+	pm_runtime_enable(dev);
+	pm_runtime_use_autosuspend(dev);
+	pm_runtime_set_autosuspend_delay(dev, 200);
+
+	err = devm_tegra_core_dev_init_opp_table_common(dev);
+	if (err)
+		goto disable_rpm;
+
 	err = host1x_client_register(&gr2d->client.base);
 	if (err < 0) {
 		dev_err(dev, "failed to register host1x client: %d\n", err);
-		clk_disable_unprepare(gr2d->clk);
-		return err;
+		goto disable_rpm;
 	}
 
 	/* initialize address register map */
 	for (i = 0; i < ARRAY_SIZE(gr2d_addr_regs); i++)
 		set_bit(gr2d_addr_regs[i], gr2d->addr_regs);
 
-	platform_set_drvdata(pdev, gr2d);
-
 	return 0;
+
+disable_rpm:
+	pm_runtime_dont_use_autosuspend(dev);
+	pm_runtime_disable(dev);
+
+	return err;
 }
 
 static int gr2d_remove(struct platform_device *pdev)

@@ -259,15 +312,101 @@ static int gr2d_remove(struct platform_device *pdev)
 		return err;
 	}
 
+	pm_runtime_dont_use_autosuspend(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
+
+	return 0;
+}
+
+static int __maybe_unused gr2d_runtime_suspend(struct device *dev)
+{
+	struct gr2d *gr2d = dev_get_drvdata(dev);
+	int err;
+
+	host1x_channel_stop(gr2d->channel);
+	reset_control_bulk_release(gr2d->nresets, gr2d->resets);
+
+	/*
+	 * GR2D module shouldn't be reset while hardware is idling, otherwise
+	 * host1x's cmdproc will stuck on trying to access any G2 register
+	 * after reset. GR2D module could be either hot-reset or reset after
+	 * power-gating of the HEG partition. Hence we will put in reset only
+	 * the memory client part of the module, the HEG GENPD will take care
+	 * of resetting GR2D module across power-gating.
+	 *
+	 * On Tegra20 there is no HEG partition, but it's okay to have
+	 * undetermined h/w state since userspace is expected to reprogram
+	 * the state on each job submission anyways.
+	 */
+	err = reset_control_acquire(gr2d->resets[RST_MC].rstc);
+	if (err) {
+		dev_err(dev, "failed to acquire MC reset: %d\n", err);
+		goto acquire_reset;
+	}
+
+	err = reset_control_assert(gr2d->resets[RST_MC].rstc);
+	reset_control_release(gr2d->resets[RST_MC].rstc);
+	if (err) {
+		dev_err(dev, "failed to assert MC reset: %d\n", err);
+		goto acquire_reset;
+	}
+
 	clk_disable_unprepare(gr2d->clk);
 
 	return 0;
+
+acquire_reset:
+	reset_control_bulk_acquire(gr2d->nresets, gr2d->resets);
+	reset_control_bulk_deassert(gr2d->nresets, gr2d->resets);
+
+	return err;
 }
 
+static int __maybe_unused gr2d_runtime_resume(struct device *dev)
+{
+	struct gr2d *gr2d = dev_get_drvdata(dev);
+	int err;
+
+	err = reset_control_bulk_acquire(gr2d->nresets, gr2d->resets);
+	if (err) {
+		dev_err(dev, "failed to acquire reset: %d\n", err);
+		return err;
+	}
+
+	err = clk_prepare_enable(gr2d->clk);
+	if (err) {
+		dev_err(dev, "failed to enable clock: %d\n", err);
+		goto release_reset;
+	}
+
+	/* this is a reset array which deasserts both 2D MC and 2D itself */
+	err = reset_control_bulk_deassert(gr2d->nresets, gr2d->resets);
+	if (err) {
+		dev_err(dev, "failed to deassert reset: %d\n", err);
+		goto disable_clk;
+	}
+
+	return 0;
+
+disable_clk:
+	clk_disable_unprepare(gr2d->clk);
+release_reset:
+	reset_control_bulk_release(gr2d->nresets, gr2d->resets);
+
+	return err;
+}
+
+static const struct dev_pm_ops tegra_gr2d_pm = {
+	SET_RUNTIME_PM_OPS(gr2d_runtime_suspend, gr2d_runtime_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
+};
+
 struct platform_driver tegra_gr2d_driver = {
 	.driver = {
 		.name = "tegra-gr2d",
 		.of_match_table = gr2d_match,
+		.pm = &tegra_gr2d_pm,
 	},
 	.probe = gr2d_probe,
 	.remove = gr2d_remove,

index 24442ade0da3..5879402ae55e 100644
@@ -5,32 +5,47 @@
  */
 
 #include <linux/clk.h>
+#include <linux/delay.h>
 #include <linux/host1x.h>
 #include <linux/iommu.h>
 #include <linux/module.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
+#include <linux/pm_domain.h>
+#include <linux/pm_opp.h>
+#include <linux/pm_runtime.h>
 #include <linux/reset.h>
 
+#include <soc/tegra/common.h>
 #include <soc/tegra/pmc.h>
 
 #include "drm.h"
 #include "gem.h"
 #include "gr3d.h"
 
+enum {
+	RST_MC,
+	RST_GR3D,
+	RST_MC2,
+	RST_GR3D2,
+	RST_GR3D_MAX,
+};
+
 struct gr3d_soc {
 	unsigned int version;
+	unsigned int num_clocks;
+	unsigned int num_resets;
 };
 
 struct gr3d {
 	struct tegra_drm_client client;
 	struct host1x_channel *channel;
-	struct clk *clk_secondary;
-	struct clk *clk;
-	struct reset_control *rst_secondary;
-	struct reset_control *rst;
 
 	const struct gr3d_soc *soc;
+	struct clk_bulk_data *clocks;
+	unsigned int nclocks;
+	struct reset_control_bulk_data resets[RST_GR3D_MAX];
+	unsigned int nresets;
 
 	DECLARE_BITMAP(addr_regs, GR3D_NUM_REGS);
 };

@@ -109,16 +124,24 @@ static int gr3d_open_channel(struct tegra_drm_client *client,
 			     struct tegra_drm_context *context)
 {
 	struct gr3d *gr3d = to_gr3d(client);
+	int err;
 
 	context->channel = host1x_channel_get(gr3d->channel);
 	if (!context->channel)
 		return -ENOMEM;
 
+	err = pm_runtime_resume_and_get(client->base.dev);
+	if (err) {
+		host1x_channel_put(context->channel);
+		return err;
+	}
+
 	return 0;
 }
 
 static void gr3d_close_channel(struct tegra_drm_context *context)
 {
+	pm_runtime_put_sync(context->client->base.dev);
 	host1x_channel_put(context->channel);
 }
 

@@ -155,14 +178,20 @@ static const struct tegra_drm_client_ops gr3d_ops = {
 
 static const struct gr3d_soc tegra20_gr3d_soc = {
 	.version = 0x20,
+	.num_clocks = 1,
+	.num_resets = 2,
 };
 
 static const struct gr3d_soc tegra30_gr3d_soc = {
 	.version = 0x30,
+	.num_clocks = 2,
+	.num_resets = 4,
 };
 
 static const struct gr3d_soc tegra114_gr3d_soc = {
 	.version = 0x35,
+	.num_clocks = 1,
+	.num_resets = 2,
 };
 
 static const struct of_device_id tegra_gr3d_match[] = {

@@ -278,69 +307,240 @@ static const u32 gr3d_addr_regs[] = {
 	GR3D_GLOBAL_SAMP23SURFADDR(15),
 };
 
-static int gr3d_probe(struct platform_device *pdev)
+static int gr3d_power_up_legacy_domain(struct device *dev, const char *name,
+				       unsigned int id)
 {
-	struct device_node *np = pdev->dev.of_node;
-	struct host1x_syncpt **syncpts;
-	struct gr3d *gr3d;
+	struct gr3d *gr3d = dev_get_drvdata(dev);
+	struct reset_control *reset;
+	struct clk *clk;
 	unsigned int i;
 	int err;
 
-	gr3d = devm_kzalloc(&pdev->dev, sizeof(*gr3d), GFP_KERNEL);
-	if (!gr3d)
-		return -ENOMEM;
-
-	gr3d->soc = of_device_get_match_data(&pdev->dev);
+	/*
+	 * Tegra20 device-tree doesn't specify 3d clock name and there is only
+	 * one clock for Tegra20. Tegra30+ device-trees always specified names
+	 * for the clocks.
+	 */
+	if (gr3d->nclocks == 1) {
+		if (id == TEGRA_POWERGATE_3D1)
+			return 0;
+
+		clk = gr3d->clocks[0].clk;
+	} else {
+		for (i = 0; i < gr3d->nclocks; i++) {
+			if (WARN_ON(!gr3d->clocks[i].id))
+				continue;
+
+			if (!strcmp(gr3d->clocks[i].id, name)) {
+				clk = gr3d->clocks[i].clk;
+				break;
+			}
+		}
 
-	syncpts = devm_kzalloc(&pdev->dev, sizeof(*syncpts), GFP_KERNEL);
-	if (!syncpts)
-		return -ENOMEM;
+		if (WARN_ON(i == gr3d->nclocks))
+			return -EINVAL;
+	}
 
-	gr3d->clk = devm_clk_get(&pdev->dev, NULL);
-	if (IS_ERR(gr3d->clk)) {
-		dev_err(&pdev->dev, "cannot get clock\n");
-		return PTR_ERR(gr3d->clk);
+	/*
+	 * We use array of resets, which includes MC resets, and MC
+	 * reset shouldn't be asserted while hardware is gated because
+	 * MC flushing will fail for gated hardware. Hence for legacy
+	 * PD we request the individual reset separately.
+	 */
+	reset = reset_control_get_exclusive_released(dev, name);
+	if (IS_ERR(reset))
+		return PTR_ERR(reset);
+
+	err = reset_control_acquire(reset);
+	if (err) {
+		dev_err(dev, "failed to acquire %s reset: %d\n", name, err);
+	} else {
+		err = tegra_powergate_sequence_power_up(id, clk, reset);
+		reset_control_release(reset);
 	}
 
-	gr3d->rst = devm_reset_control_get(&pdev->dev, "3d");
-	if (IS_ERR(gr3d->rst)) {
-		dev_err(&pdev->dev, "cannot get reset\n");
-		return PTR_ERR(gr3d->rst);
+	reset_control_put(reset);
+	if (err)
+		return err;
+
+	/*
+	 * tegra_powergate_sequence_power_up() leaves clocks enabled
+	 * while GENPD not, hence keep clock-enable balanced.
+	 */
+	clk_disable_unprepare(clk);
+
+	return 0;
+}
+
+static void gr3d_del_link(void *link)
+{
+	device_link_del(link);
+}
+
+static int gr3d_init_power(struct device *dev, struct gr3d *gr3d)
+{
+	static const char * const opp_genpd_names[] = { "3d0", "3d1", NULL };
+	const u32 link_flags = DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME;
+	struct device **opp_virt_devs, *pd_dev;
+	struct device_link *link;
+	unsigned int i;
+	int err;
+
+	err = of_count_phandle_with_args(dev->of_node, "power-domains",
+					 "#power-domain-cells");
+	if (err < 0) {
+		if (err != -ENOENT)
+			return err;
+
+		/*
+		 * Older device-trees don't use GENPD. In this case we should
+		 * toggle power domain manually.
+		 */
+		err = gr3d_power_up_legacy_domain(dev, "3d",
+						  TEGRA_POWERGATE_3D);
+		if (err)
+			return err;
+
+		err = gr3d_power_up_legacy_domain(dev, "3d2",
+						  TEGRA_POWERGATE_3D1);
+		if (err)
+			return err;
+
+		return 0;
 	}
 
-	if (of_device_is_compatible(np, "nvidia,tegra30-gr3d")) {
-		gr3d->clk_secondary = devm_clk_get(&pdev->dev, "3d2");
-		if (IS_ERR(gr3d->clk_secondary)) {
-			dev_err(&pdev->dev, "cannot get secondary clock\n");
-			return PTR_ERR(gr3d->clk_secondary);
+	/*
+	 * The PM domain core automatically attaches a single power domain,
+	 * otherwise it skips attaching completely. We have a single domain
+	 * on Tegra20 and two domains on Tegra30+.
+	 */
+	if (dev->pm_domain)
+		return 0;
+
+	err = devm_pm_opp_attach_genpd(dev, opp_genpd_names, &opp_virt_devs);
+	if (err)
+		return err;
+
+	for (i = 0; opp_genpd_names[i]; i++) {
+		pd_dev = opp_virt_devs[i];
+		if (!pd_dev) {
+			dev_err(dev, "failed to get %s power domain\n",
+				opp_genpd_names[i]);
+			return -EINVAL;
 		}
 
-		gr3d->rst_secondary = devm_reset_control_get(&pdev->dev,
-								"3d2");
-		if (IS_ERR(gr3d->rst_secondary)) {
-			dev_err(&pdev->dev, "cannot get secondary reset\n");
-			return PTR_ERR(gr3d->rst_secondary);
+		link = device_link_add(dev, pd_dev, link_flags);
+		if (!link) {
+			dev_err(dev, "failed to link to %s\n", dev_name(pd_dev));
+			return -EINVAL;
 		}
+
+		err = devm_add_action_or_reset(dev, gr3d_del_link, link);
+		if (err)
+			return err;
 	}
 
-	err = tegra_powergate_sequence_power_up(TEGRA_POWERGATE_3D, gr3d->clk,
-						gr3d->rst);
+	return 0;
+}
+
+static int gr3d_set_opp(struct dev_pm_set_opp_data *data)
+{
+	struct gr3d *gr3d = dev_get_drvdata(data->dev);
+	unsigned int i;
+	int err;
+
+	for (i = 0; i < gr3d->nclocks; i++) {
+		err = clk_set_rate(gr3d->clocks[i].clk, data->new_opp.rate);
+		if (err) {
+			dev_err(data->dev, "failed to set %s rate to %lu: %d\n",
+				gr3d->clocks[i].id, data->new_opp.rate, err);
+			goto restore;
+		}
+	}
+
+	return 0;
+
+restore:
+	while (i--)
+		clk_set_rate(gr3d->clocks[i].clk, data->old_opp.rate);
+
+	return err;
+}
+
+static int gr3d_get_clocks(struct device *dev, struct gr3d *gr3d)
+{
+	int err;
+
+	err = devm_clk_bulk_get_all(dev, &gr3d->clocks);
 	if (err < 0) {
-		dev_err(&pdev->dev, "failed to power up 3D unit\n");
+		dev_err(dev, "failed to get clock: %d\n", err);
 		return err;
 	}
+	gr3d->nclocks = err;
 
-	if (gr3d->clk_secondary) {
-		err = tegra_powergate_sequence_power_up(TEGRA_POWERGATE_3D1,
-							gr3d->clk_secondary,
-							gr3d->rst_secondary);
-		if (err < 0) {
-			dev_err(&pdev->dev,
-				"failed to power up secondary 3D unit\n");
-			return err;
-		}
+	if (gr3d->nclocks != gr3d->soc->num_clocks) {
+		dev_err(dev, "invalid number of clocks: %u\n", gr3d->nclocks);
+		return -ENOENT;
 	}
 
+	return 0;
+}
+
+static int gr3d_get_resets(struct device *dev, struct gr3d *gr3d)
+{
+	int err;
+
+	gr3d->resets[RST_MC].id = "mc";
+	gr3d->resets[RST_MC2].id = "mc2";
+	gr3d->resets[RST_GR3D].id = "3d";
+	gr3d->resets[RST_GR3D2].id = "3d2";
+	gr3d->nresets = gr3d->soc->num_resets;
+
+	err = devm_reset_control_bulk_get_optional_exclusive_released(
+				dev, gr3d->nresets, gr3d->resets);
+	if (err) {
+		dev_err(dev, "failed to get reset: %d\n", err);
+		return err;
+	}
+
+	if (WARN_ON(!gr3d->resets[RST_GR3D].rstc) ||
+	    WARN_ON(!gr3d->resets[RST_GR3D2].rstc && gr3d->nresets == 4))
+		return -ENOENT;
+
+	return 0;
+}
+
+static int gr3d_probe(struct platform_device *pdev)
+{
+	struct host1x_syncpt **syncpts;
+	struct gr3d *gr3d;
+	unsigned int i;
+	int err;
+
+	gr3d = devm_kzalloc(&pdev->dev, sizeof(*gr3d), GFP_KERNEL);
+	if (!gr3d)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, gr3d);
+
+	gr3d->soc = of_device_get_match_data(&pdev->dev);
+
+	syncpts = devm_kzalloc(&pdev->dev, sizeof(*syncpts), GFP_KERNEL);
+	if (!syncpts)
+		return -ENOMEM;
+
+	err = gr3d_get_clocks(&pdev->dev, gr3d);
+	if (err)
+		return err;
+
+	err = gr3d_get_resets(&pdev->dev, gr3d);
+	if (err)
+		return err;
+
+	err = gr3d_init_power(&pdev->dev, gr3d);
+	if (err)
+		return err;
+
 	INIT_LIST_HEAD(&gr3d->client.base.list);
 	gr3d->client.base.ops = &gr3d_client_ops;
 	gr3d->client.base.dev = &pdev->dev;

@@ -352,20 +552,36 @@ static int gr3d_probe(struct platform_device *pdev)
 	gr3d->client.version = gr3d->soc->version;
 	gr3d->client.ops = &gr3d_ops;
 
+	pm_runtime_enable(&pdev->dev);
+	pm_runtime_use_autosuspend(&pdev->dev);
+	pm_runtime_set_autosuspend_delay(&pdev->dev, 200);
+
+	err = devm_pm_opp_register_set_opp_helper(&pdev->dev, gr3d_set_opp);
+	if (err)
+		goto disable_rpm;
+
+	err = devm_tegra_core_dev_init_opp_table_common(&pdev->dev);
+	if (err)
+		goto disable_rpm;
+
 	err = host1x_client_register(&gr3d->client.base);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to register host1x client: %d\n",
 			err);
-		return err;
+		goto disable_rpm;
 	}
 
 	/* initialize address register map */
 	for (i = 0; i < ARRAY_SIZE(gr3d_addr_regs); i++)
 		set_bit(gr3d_addr_regs[i], gr3d->addr_regs);
 
-	platform_set_drvdata(pdev, gr3d);
-
 	return 0;
+
+disable_rpm:
+	pm_runtime_dont_use_autosuspend(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
+
+	return err;
 }
 
 static int gr3d_remove(struct platform_device *pdev)

@@ -380,23 +596,83 @@ static int gr3d_remove(struct platform_device *pdev)
 		return err;
 	}
 
-	if (gr3d->clk_secondary) {
-		reset_control_assert(gr3d->rst_secondary);
-		tegra_powergate_power_off(TEGRA_POWERGATE_3D1);
-		clk_disable_unprepare(gr3d->clk_secondary);
+	pm_runtime_dont_use_autosuspend(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
+
+	return 0;
+}
+
+static int __maybe_unused gr3d_runtime_suspend(struct device *dev)
+{
+	struct gr3d *gr3d = dev_get_drvdata(dev);
+	int err;
+
+	host1x_channel_stop(gr3d->channel);
+
+	err = reset_control_bulk_assert(gr3d->nresets, gr3d->resets);
+	if (err) {
+		dev_err(dev, "failed to assert reset: %d\n", err);
+		return err;
+	}
+
+	usleep_range(10, 20);
+
+	/*
+	 * Older device-trees don't specify MC resets and power-gating can't
+	 * be done safely in that case. Hence we will keep the power ungated
+	 * for older DTBs. For newer DTBs, GENPD will perform the power-gating.
+	 */
+
+	clk_bulk_disable_unprepare(gr3d->nclocks, gr3d->clocks);
+	reset_control_bulk_release(gr3d->nresets, gr3d->resets);
+
+	return 0;
+}
+
+static int __maybe_unused gr3d_runtime_resume(struct device *dev)
+{
+	struct gr3d *gr3d = dev_get_drvdata(dev);
+	int err;
+
+	err = reset_control_bulk_acquire(gr3d->nresets, gr3d->resets);
+	if (err) {
+		dev_err(dev, "failed to acquire reset: %d\n", err);
+		return err;
+	}
+
+	err = clk_bulk_prepare_enable(gr3d->nclocks, gr3d->clocks);
+	if (err) {
+		dev_err(dev, "failed to enable clock: %d\n", err);
+		goto release_reset;
 	}
 
-	reset_control_assert(gr3d->rst);
-	tegra_powergate_power_off(TEGRA_POWERGATE_3D);
-	clk_disable_unprepare(gr3d->clk);
+	err = reset_control_bulk_deassert(gr3d->nresets, gr3d->resets);
+	if (err) {
+		dev_err(dev, "failed to deassert reset: %d\n", err);
+		goto disable_clk;
+	}
 
 	return 0;
+
+disable_clk:
+	clk_bulk_disable_unprepare(gr3d->nclocks, gr3d->clocks);
+release_reset:
+	reset_control_bulk_release(gr3d->nresets, gr3d->resets);
+
+	return err;
 }
 
+static const struct dev_pm_ops tegra_gr3d_pm = {
+	SET_RUNTIME_PM_OPS(gr3d_runtime_suspend, gr3d_runtime_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
+};
+
 struct platform_driver tegra_gr3d_driver = {
 	.driver = {
 		.name = "tegra-gr3d",
 		.of_match_table = tegra_gr3d_match,
+		.pm = &tegra_gr3d_pm,
 	},
 	.probe = gr3d_probe,
 	.remove = gr3d_remove,

index c02010ff2b7f..359dd77f8b85 100644
@@ -315,6 +315,8 @@ static int vic_runtime_suspend(struct device *dev)
 	struct vic *vic = dev_get_drvdata(dev);
 	int err;
 
+	host1x_channel_stop(vic->channel);
+
 	err = reset_control_assert(vic->rst);
 	if (err < 0)
 		return err;

@@ -517,6 +519,8 @@ static int vic_remove(struct platform_device *pdev)
 
 static const struct dev_pm_ops vic_pm_ops = {
 	SET_RUNTIME_PM_OPS(vic_runtime_suspend, vic_runtime_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 };
 
 struct platform_driver tegra_vic_driver = {

index 60361141ac04..3142ef7ebe42 100644
@@ -7,6 +7,7 @@
 #include <linux/io.h>
 #include <linux/module.h>
 #include <linux/of_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/reset.h>
 
 #include <linux/usb.h>

@@ -15,6 +16,8 @@
 #include <linux/usb/of.h>
 #include <linux/usb/phy.h>
 
+#include <soc/tegra/common.h>
+
 #include "../host/ehci.h"
 
 #include "ci.h"

@@ -278,6 +281,8 @@ static int tegra_usb_probe(struct platform_device *pdev)
 	if (!usb)
 		return -ENOMEM;
 
+	platform_set_drvdata(pdev, usb);
+
 	soc = of_device_get_match_data(&pdev->dev);
 	if (!soc) {
 		dev_err(&pdev->dev, "failed to match OF data\n");

@@ -296,11 +301,17 @@ static int tegra_usb_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	err = clk_prepare_enable(usb->clk);
-	if (err < 0) {
-		dev_err(&pdev->dev, "failed to enable clock: %d\n", err);
+	err = devm_pm_runtime_enable(&pdev->dev);
+	if (err)
+		return err;
+
+	err = devm_tegra_core_dev_init_opp_table_common(&pdev->dev);
+	if (err)
+		return err;
+
+	err = pm_runtime_resume_and_get(&pdev->dev);
+	if (err)
 		return err;
-	}
 
 	if (device_property_present(&pdev->dev, "nvidia,needs-double-reset"))
 		usb->needs_double_reset = true;

@@ -320,8 +331,6 @@ static int tegra_usb_probe(struct platform_device *pdev)
 	if (err)
 		goto fail_power_off;
 
-	platform_set_drvdata(pdev, usb);
-
 	/* setup and register ChipIdea HDRC device */
 	usb->soc = soc;
 	usb->data.name = "tegra-usb";

@@ -350,7 +359,8 @@ static int tegra_usb_probe(struct platform_device *pdev)
 phy_shutdown:
 	usb_phy_shutdown(usb->phy);
 fail_power_off:
-	clk_disable_unprepare(usb->clk);
+	pm_runtime_put(&pdev->dev);
+
 	return err;
 }
 

@@ -360,15 +370,44 @@ static int tegra_usb_remove(struct platform_device *pdev)
 
 	ci_hdrc_remove_device(usb->dev);
 	usb_phy_shutdown(usb->phy);
+	pm_runtime_put(&pdev->dev);
+
+	return 0;
+}
+
+static int __maybe_unused tegra_usb_runtime_resume(struct device *dev)
+{
+	struct tegra_usb *usb = dev_get_drvdata(dev);
+	int err;
+
+	err = clk_prepare_enable(usb->clk);
+	if (err < 0) {
+		dev_err(dev, "failed to enable clock: %d\n", err);
+		return err;
+	}
+
+	return 0;
+}
+
+static int __maybe_unused tegra_usb_runtime_suspend(struct device *dev)
+{
+	struct tegra_usb *usb = dev_get_drvdata(dev);
+
 	clk_disable_unprepare(usb->clk);
 
 	return 0;
 }
 
+static const struct dev_pm_ops tegra_usb_pm = {
+	SET_RUNTIME_PM_OPS(tegra_usb_runtime_suspend, tegra_usb_runtime_resume,
+			   NULL)
+};
+
 static struct platform_driver tegra_usb_driver = {
 	.driver = {
 		.name = "tegra-usb",
 		.of_match_table = tegra_usb_of_match,
+		.pm = &tegra_usb_pm,
 	},
 	.probe = tegra_usb_probe,
 	.remove = tegra_usb_remove,

index a6570789f7af..72ef8a8c236b 100644
@@ -13,8 +13,11 @@
 #include <linux/io.h>
 #include <linux/module.h>
 #include <linux/of_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/reset.h>
 
+#include <soc/tegra/common.h>
+
 #define TEGRA_GMI_CONFIG		0x00
 #define TEGRA_GMI_CONFIG_GO		BIT(31)
 #define TEGRA_GMI_BUS_WIDTH_32BIT	BIT(30)

@@ -54,9 +57,9 @@ static int tegra_gmi_enable(struct tegra_gmi *gmi)
 {
 	int err;
 
-	err = clk_prepare_enable(gmi->clk);
-	if (err < 0) {
-		dev_err(gmi->dev, "failed to enable clock: %d\n", err);
+	err = pm_runtime_resume_and_get(gmi->dev);
+	if (err) {
+		pm_runtime_disable(gmi->dev);
 		return err;
 	}
 

@@ -83,7 +86,8 @@ static void tegra_gmi_disable(struct tegra_gmi *gmi)
 	writel(config, gmi->base + TEGRA_GMI_CONFIG);
 
 	reset_control_assert(gmi->rst);
-	clk_disable_unprepare(gmi->clk);
+
+	pm_runtime_put(gmi->dev);
 }
 
 static int tegra_gmi_parse_dt(struct tegra_gmi *gmi)

@@ -213,6 +217,7 @@ static int tegra_gmi_probe(struct platform_device *pdev)
 	if (!gmi)
 		return -ENOMEM;
 
+	platform_set_drvdata(pdev, gmi);
 	gmi->dev = dev;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);

@@ -232,6 +237,14 @@ static int tegra_gmi_probe(struct platform_device *pdev)
 		return PTR_ERR(gmi->rst);
 	}
 
+	err = devm_pm_runtime_enable(gmi->dev);
+	if (err)
+		return err;
+
+	err = devm_tegra_core_dev_init_opp_table_common(&pdev->dev);
+	if (err)
+		return err;
+
 	err = tegra_gmi_parse_dt(gmi);
 	if (err)
 		return err;

@@ -247,8 +260,6 @@ static int tegra_gmi_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	platform_set_drvdata(pdev, gmi);
-
 	return 0;
 }
 

@@ -262,6 +273,34 @@ static int tegra_gmi_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static int __maybe_unused tegra_gmi_runtime_resume(struct device *dev)
+{
+	struct tegra_gmi *gmi = dev_get_drvdata(dev);
+	int err;
+
+	err = clk_prepare_enable(gmi->clk);
+	if (err < 0) {
+		dev_err(gmi->dev, "failed to enable clock: %d\n", err);
+		return err;
+	}
+
+	return 0;
+}
+
+static int __maybe_unused tegra_gmi_runtime_suspend(struct device *dev)
+{
+	struct tegra_gmi *gmi = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(gmi->clk);
+
+	return 0;
+}
+
+static const struct dev_pm_ops tegra_gmi_pm = {
+	SET_RUNTIME_PM_OPS(tegra_gmi_runtime_suspend, tegra_gmi_runtime_resume,
+			   NULL)
+};
+
 static const struct of_device_id tegra_gmi_id_table[] = {
 	{ .compatible = "nvidia,tegra20-gmi", },
 	{ .compatible = "nvidia,tegra30-gmi", },

@@ -275,6 +314,7 @@ static struct platform_driver tegra_gmi_driver = {
 	.driver = {
 		.name		= "tegra-gmi",
 		.of_match_table	= tegra_gmi_id_table,
+		.pm = &tegra_gmi_pm,
 	},
 };
 module_platform_driver(tegra_gmi_driver);

index 11a10b575ace..afb5ecde007e 100644
@@ -42,12 +42,16 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
+#include <linux/pm_opp.h>
 #include <linux/pwm.h>
 #include <linux/platform_device.h>
 #include <linux/pinctrl/consumer.h>
+#include <linux/pm_runtime.h>
 #include <linux/slab.h>
 #include <linux/reset.h>
 
+#include <soc/tegra/common.h>
+
 #define PWM_ENABLE	(1 << 31)
 #define PWM_DUTY_WIDTH	8
 #define PWM_DUTY_SHIFT	16

@@ -145,7 +149,7 @@ static int tegra_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
 		required_clk_rate =
 			(NSEC_PER_SEC / period_ns) << PWM_DUTY_WIDTH;
 
-		err = clk_set_rate(pc->clk, required_clk_rate);
+		err = dev_pm_opp_set_rate(pc->dev, required_clk_rate);
 		if (err < 0)
 			return -EINVAL;
 

@@ -181,8 +185,8 @@ static int tegra_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
 	 * before writing the register. Otherwise, keep it enabled.
 	 */
 	if (!pwm_is_enabled(pwm)) {
-		err = clk_prepare_enable(pc->clk);
-		if (err < 0)
+		err = pm_runtime_resume_and_get(pc->dev);
+		if (err)
 			return err;
 	} else
 		val |= PWM_ENABLE;

@@ -193,7 +197,7 @@ static int tegra_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
 	 * If the PWM is not enabled, turn the clock off again to save power.
 	 */
 	if (!pwm_is_enabled(pwm))
-		clk_disable_unprepare(pc->clk);
+		pm_runtime_put(pc->dev);
 
 	return 0;
 }

@@ -204,8 +208,8 @@ static int tegra_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm)
 	int rc = 0;
 	u32 val;
 
-	rc = clk_prepare_enable(pc->clk);
-	if (rc < 0)
+	rc = pm_runtime_resume_and_get(pc->dev);
+	if (rc)
 		return rc;
 
 	val = pwm_readl(pc, pwm->hwpwm);

@@ -224,7 +228,7 @@ static void tegra_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm)
 	val &= ~PWM_ENABLE;
 	pwm_writel(pc, pwm->hwpwm, val);
 
-	clk_disable_unprepare(pc->clk);
+	pm_runtime_put_sync(pc->dev);
 }
 
 static const struct pwm_ops tegra_pwm_ops = {

@@ -256,11 +260,23 @@ static int tegra_pwm_probe(struct platform_device *pdev)
 	if (IS_ERR(pwm->clk))
 		return PTR_ERR(pwm->clk);
 
+	ret = devm_pm_runtime_enable(&pdev->dev);
+	if (ret)
+		return ret;
+
+	ret = devm_tegra_core_dev_init_opp_table_common(&pdev->dev);
+	if (ret)
+		return ret;
+
+	ret = pm_runtime_resume_and_get(&pdev->dev);
+	if (ret)
+		return ret;
+
 	/* Set maximum frequency of the IP */
-	ret = clk_set_rate(pwm->clk, pwm->soc->max_frequency);
+	ret = dev_pm_opp_set_rate(pwm->dev, pwm->soc->max_frequency);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "Failed to set max frequency: %d\n", ret);
-		return ret;
+		goto put_pm;
 	}
 
 	/*

@@ -278,7 +294,7 @@ static int tegra_pwm_probe(struct platform_device *pdev)
 	if (IS_ERR(pwm->rst)) {
 		ret = PTR_ERR(pwm->rst);
 		dev_err(&pdev->dev, "Reset control is not found: %d\n", ret);
-		return ret;
+		goto put_pm;
 	}
 
 	reset_control_deassert(pwm->rst);

@@ -291,34 +307,67 @@ static int tegra_pwm_probe(struct platform_device *pdev)
 	if (ret < 0) {
 		dev_err(&pdev->dev, "pwmchip_add() failed: %d\n", ret);
 		reset_control_assert(pwm->rst);
-		return ret;
+		goto put_pm;
 	}
 
+	pm_runtime_put(&pdev->dev);
+
 	return 0;
+put_pm:
+	pm_runtime_put(&pdev->dev);
+	return ret;
 }
 
 static int tegra_pwm_remove(struct platform_device *pdev)
 {
 	struct tegra_pwm_chip *pc = platform_get_drvdata(pdev);
+	int err;
 
 	pwmchip_remove(&pc->chip);
 
+	err = pm_runtime_resume_and_get(pc->dev);
+	if (err)
+		return err;
+
 	reset_control_assert(pc->rst);
+	pm_runtime_put(pc->dev);
 
 	return 0;
 }
 
-#ifdef CONFIG_PM_SLEEP
-static int tegra_pwm_suspend(struct device *dev)
+static int __maybe_unused tegra_pwm_runtime_suspend(struct device *dev)
 {
-	return pinctrl_pm_select_sleep_state(dev);
+	struct tegra_pwm_chip *pc = dev_get_drvdata(dev);
+	int err;
+
+	clk_disable_unprepare(pc->clk);
+
+	err = pinctrl_pm_select_sleep_state(dev);
+	if (err) {
+		clk_prepare_enable(pc->clk);
+		return err;
+	}
+
+	return 0;
 }
 
-static int tegra_pwm_resume(struct device *dev)
+static int __maybe_unused tegra_pwm_runtime_resume(struct device *dev)
 {
-	return pinctrl_pm_select_default_state(dev);
+	struct tegra_pwm_chip *pc = dev_get_drvdata(dev);
+	int err;
+
+	err = pinctrl_pm_select_default_state(dev);
+	if (err)
+		return err;
+
+	err = clk_prepare_enable(pc->clk);
+	if (err) {
+		pinctrl_pm_select_sleep_state(dev);
+		return err;
+	}
+
+	return 0;
 }
-#endif
 
 static const struct tegra_pwm_soc tegra20_pwm_soc = {
 	.num_channels = 4,

@@ -344,7 +393,10 @@ static const struct of_device_id tegra_pwm_of_match[] = {
 MODULE_DEVICE_TABLE(of, tegra_pwm_of_match);
 
 static const struct dev_pm_ops tegra_pwm_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(tegra_pwm_suspend, tegra_pwm_resume)
+	SET_RUNTIME_PM_OPS(tegra_pwm_runtime_suspend, tegra_pwm_runtime_resume,
+			   NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 };
 
 static struct platform_driver tegra_pwm_driver = {

index a5001875876b..6cf3712bf0a6 100644
@@ -15,6 +15,8 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/pinctrl/consumer.h>
+#include <linux/pm_opp.h>
+#include <linux/pm_runtime.h>
 #include <linux/regulator/consumer.h>
 #include <linux/reset.h>
 #include <linux/mmc/card.h>

@@ -24,6 +26,8 @@
 #include <linux/gpio/consumer.h>
 #include <linux/ktime.h>
 
+#include <soc/tegra/common.h>
+
 #include "sdhci-pltfm.h"
 #include "cqhci.h"
 

@@ -760,7 +764,9 @@ static void tegra_sdhci_set_clock(struct sdhci_host *host, unsigned int clock)
 {
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	struct sdhci_tegra *tegra_host = sdhci_pltfm_priv(pltfm_host);
+	struct device *dev = mmc_dev(host->mmc);
 	unsigned long host_clk;
+	int err;
 
 	if (!clock)
 		return sdhci_set_clock(host, clock);

@@ -778,7 +784,12 @@ static void tegra_sdhci_set_clock(struct sdhci_host *host, unsigned int clock)
 	 * from clk_get_rate() is used.
 	 */
 	host_clk = tegra_host->ddr_signaling ? clock * 2 : clock;
-	clk_set_rate(pltfm_host->clk, host_clk);
+
+	err = dev_pm_opp_set_rate(dev, host_clk);
+	if (err)
+		dev_err(dev, "failed to set clk rate to %luHz: %d\n",
+			host_clk, err);
+
 	tegra_host->curr_clk_rate = host_clk;
 	if (tegra_host->ddr_signaling)
 		host->max_clk = host_clk;

@@ -1705,7 +1716,6 @@ static int sdhci_tegra_probe(struct platform_device *pdev)
 				   "failed to get clock\n");
 		goto err_clk_get;
 	}
-	clk_prepare_enable(clk);
 	pltfm_host->clk = clk;
 
 	tegra_host->rst = devm_reset_control_get_exclusive(&pdev->dev,

@@ -1716,15 +1726,25 @@ static int sdhci_tegra_probe(struct platform_device *pdev)
 		goto err_rst_get;
 	}
 
+	pm_runtime_enable(&pdev->dev);
+
+	rc = devm_tegra_core_dev_init_opp_table_common(&pdev->dev);
+	if (rc)
+		goto err_pm_get;
+
+	rc = pm_runtime_resume_and_get(&pdev->dev);
+	if (rc)
+		goto err_pm_get;
+
 	rc = reset_control_assert(tegra_host->rst);
 	if (rc)
-		goto err_rst_get;
+		goto err_rst_assert;
 
 	usleep_range(2000, 4000);
 
 	rc = reset_control_deassert(tegra_host->rst);
 	if (rc)
-		goto err_rst_get;
+		goto err_rst_assert;
 
 	usleep_range(2000, 4000);
 

@@ -1736,8 +1756,11 @@ static int sdhci_tegra_probe(struct platform_device *pdev)
 
 err_add_host:
 	reset_control_assert(tegra_host->rst);
+err_rst_assert:
+	pm_runtime_put(&pdev->dev);
+err_pm_get:
+	pm_runtime_disable(&pdev->dev);
 err_rst_get:
-	clk_disable_unprepare(pltfm_host->clk);
 err_clk_get:
 	clk_disable_unprepare(tegra_host->tmclk);
 err_power_req:

@@ -1756,19 +1779,38 @@ static int sdhci_tegra_remove(struct platform_device *pdev)
 
 	reset_control_assert(tegra_host->rst);
 	usleep_range(2000, 4000);
-	clk_disable_unprepare(pltfm_host->clk);
-	clk_disable_unprepare(tegra_host->tmclk);
 
+	pm_runtime_put(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
+
+	clk_disable_unprepare(tegra_host->tmclk);
 	sdhci_pltfm_free(pdev);
 
 	return 0;
 }
 
-#ifdef CONFIG_PM_SLEEP
-static int __maybe_unused sdhci_tegra_suspend(struct device *dev)
+static int __maybe_unused sdhci_tegra_runtime_suspend(struct device *dev)
 {
 	struct sdhci_host *host = dev_get_drvdata(dev);
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+
+	clk_disable_unprepare(pltfm_host->clk);
+
+	return 0;
+}
+
+static int __maybe_unused sdhci_tegra_runtime_resume(struct device *dev)
+{
+	struct sdhci_host *host = dev_get_drvdata(dev);
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+
+	return clk_prepare_enable(pltfm_host->clk);
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int sdhci_tegra_suspend(struct device *dev)
+{
+	struct sdhci_host *host = dev_get_drvdata(dev);
 	int ret;
 
 	if (host->mmc->caps2 & MMC_CAP2_CQE) {

@@ -1783,17 +1825,22 @@ static int __maybe_unused sdhci_tegra_suspend(struct device *dev)
 		return ret;
 	}
 
-	clk_disable_unprepare(pltfm_host->clk);
+	ret = pm_runtime_force_suspend(dev);
+	if (ret) {
+		sdhci_resume_host(host);
+		cqhci_resume(host->mmc);
+		return ret;
+	}
+
 	return 0;
 }
 
-static int __maybe_unused sdhci_tegra_resume(struct device *dev)
+static int sdhci_tegra_resume(struct device *dev)
 {
 	struct sdhci_host *host = dev_get_drvdata(dev);
-	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	int ret;
 
-	ret = clk_prepare_enable(pltfm_host->clk);
+	ret = pm_runtime_force_resume(dev);
 	if (ret)
 		return ret;
 

@@ -1812,13 +1859,16 @@ static int __maybe_unused sdhci_tegra_resume(struct device *dev)
 suspend_host:
 	sdhci_suspend_host(host);
 disable_clk:
-	clk_disable_unprepare(pltfm_host->clk);
+	pm_runtime_force_suspend(dev);
 	return ret;
 }
 #endif
 
-static SIMPLE_DEV_PM_OPS(sdhci_tegra_dev_pm_ops, sdhci_tegra_suspend,
-			 sdhci_tegra_resume);
+static const struct dev_pm_ops sdhci_tegra_dev_pm_ops = {
+	SET_RUNTIME_PM_OPS(sdhci_tegra_runtime_suspend, sdhci_tegra_runtime_resume,
+			   NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(sdhci_tegra_suspend, sdhci_tegra_resume)
+};
 
 static struct platform_driver sdhci_tegra_driver = {
 	.driver		= {

index fbf67722a049..2cce38c58a26 100644
@@ -17,8 +17,11 @@
 #include <linux/mtd/rawnand.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/reset.h>
 
+#include <soc/tegra/common.h>
+
 #define COMMAND					0x00
 #define   COMMAND_GO				BIT(31)
 #define   COMMAND_CLE				BIT(30)

@@ -1152,6 +1155,7 @@ static int tegra_nand_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	ctrl->dev = &pdev->dev;
+	platform_set_drvdata(pdev, ctrl);
 	nand_controller_init(&ctrl->controller);
 	ctrl->controller.ops = &tegra_nand_controller_ops;
 

@@ -1168,14 +1172,22 @@ static int tegra_nand_probe(struct platform_device *pdev)
 	if (IS_ERR(ctrl->clk))
 		return PTR_ERR(ctrl->clk);
 
-	err = clk_prepare_enable(ctrl->clk);
+	err = devm_pm_runtime_enable(&pdev->dev);
+	if (err)
+		return err;
+
+	err = devm_tegra_core_dev_init_opp_table_common(&pdev->dev);
+	if (err)
+		return err;
+
+	err = pm_runtime_resume_and_get(&pdev->dev);
 	if (err)
 		return err;
 
 	err = reset_control_reset(rst);
 	if (err) {
 		dev_err(ctrl->dev, "Failed to reset HW: %d\n", err);
-		goto err_disable_clk;
+		goto err_put_pm;
 	}
 
 	writel_relaxed(HWSTATUS_CMD_DEFAULT, ctrl->regs + HWSTATUS_CMD);

@@ -1190,21 +1202,19 @@ static int tegra_nand_probe(struct platform_device *pdev)
 			       dev_name(&pdev->dev), ctrl);
 	if (err) {
 		dev_err(ctrl->dev, "Failed to get IRQ: %d\n", err);
-		goto err_disable_clk;
+		goto err_put_pm;
 	}
 
 	writel_relaxed(DMA_MST_CTRL_IS_DONE, ctrl->regs + DMA_MST_CTRL);
 
 	err = tegra_nand_chips_init(ctrl->dev, ctrl);
 	if (err)
-		goto err_disable_clk;
-
-	platform_set_drvdata(pdev, ctrl);
+		goto err_put_pm;
 
 	return 0;
 
-err_disable_clk:
-	clk_disable_unprepare(ctrl->clk);
+err_put_pm:
+	pm_runtime_put(ctrl->dev);
 	return err;
 }
 

@@ -1221,11 +1231,39 @@ static int tegra_nand_remove(struct platform_device *pdev)
 
 	nand_cleanup(chip);
 
+	pm_runtime_put(ctrl->dev);
+
+	return 0;
+}
+
+static int __maybe_unused tegra_nand_runtime_resume(struct device *dev)
+{
+	struct tegra_nand_controller *ctrl = dev_get_drvdata(dev);
+	int err;
+
+	err = clk_prepare_enable(ctrl->clk);
+	if (err) {
+		dev_err(dev, "Failed to enable clock: %d\n", err);
+		return err;
+	}
+
+	return 0;
+}
+
+static int __maybe_unused tegra_nand_runtime_suspend(struct device *dev)
+{
+	struct tegra_nand_controller *ctrl = dev_get_drvdata(dev);
+
 	clk_disable_unprepare(ctrl->clk);
 
 	return 0;
 }
 
+static const struct dev_pm_ops tegra_nand_pm = {
+	SET_RUNTIME_PM_OPS(tegra_nand_runtime_suspend, tegra_nand_runtime_resume,
+			   NULL)
+};
+
 static const struct of_device_id tegra_nand_of_match[] = {
 	{ .compatible = "nvidia,tegra20-nand" },
 	{ /* sentinel */ }

@@ -1236,6 +1274,7 @@ static struct platform_driver tegra_nand_driver = {
 	.driver = {
 		.name = "tegra-nand",
 		.of_match_table = tegra_nand_of_match,
+		.pm = &tegra_nand_pm,
 	},
 	.probe = tegra_nand_probe,
 	.remove = tegra_nand_remove,

index 8ce840c7ecc8..1a92978d2120 100644
@@ -18,12 +18,15 @@
 #include <linux/kthread.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm_opp.h>
 #include <linux/pm_runtime.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/reset.h>
 #include <linux/spi/spi.h>
 
+#include <soc/tegra/common.h>
+
 #define SLINK_COMMAND			0x000
 #define SLINK_BIT_LENGTH(x)		(((x) & 0x1f) << 0)
 #define SLINK_WORD_SIZE(x)		(((x) & 0x1f) << 5)

@@ -680,7 +683,7 @@ static int tegra_slink_start_transfer_one(struct spi_device *spi,
 	bits_per_word = t->bits_per_word;
 	speed = t->speed_hz;
 	if (speed != tspi->cur_speed) {
-		clk_set_rate(tspi->clk, speed * 4);
+		dev_pm_opp_set_rate(tspi->dev, speed * 4);
 		tspi->cur_speed = speed;
 	}
 

@@ -1082,6 +1085,11 @@ static int tegra_slink_probe(struct platform_device *pdev)
 	init_completion(&tspi->xfer_completion);
 
 	pm_runtime_enable(&pdev->dev);
+
+	ret = devm_tegra_core_dev_init_opp_table_common(&pdev->dev);
+	if (ret)
+		goto exit_pm_disable;
+
 	ret = pm_runtime_resume_and_get(&pdev->dev);
 	if (ret) {
 		dev_err(&pdev->dev, "pm runtime get failed, e = %d\n", ret);

index ed4c1250b303..bb3079a2c0b5 100644
@@ -20,6 +20,7 @@
 #include <linux/slab.h>
 #include <linux/uaccess.h>
 
+#include <soc/tegra/common.h>
 #include <soc/tegra/pmc.h>
 
 #include "uapi.h"

@@ -920,13 +921,17 @@ static __maybe_unused int tegra_vde_runtime_suspend(struct device *dev)
 	struct tegra_vde *vde = dev_get_drvdata(dev);
 	int err;
 
-	err = tegra_powergate_power_off(TEGRA_POWERGATE_VDEC);
-	if (err) {
-		dev_err(dev, "Failed to power down HW: %d\n", err);
-		return err;
+	if (!dev->pm_domain) {
+		err = tegra_powergate_power_off(TEGRA_POWERGATE_VDEC);
+		if (err) {
+			dev_err(dev, "Failed to power down HW: %d\n", err);
+			return err;
+		}
 	}
 
 	clk_disable_unprepare(vde->clk);
+	reset_control_release(vde->rst);
+	reset_control_release(vde->rst_mc);
 
 	return 0;
 }

@@ -936,14 +941,41 @@ static __maybe_unused int tegra_vde_runtime_resume(struct device *dev)
 	struct tegra_vde *vde = dev_get_drvdata(dev);
 	int err;
 
-	err = tegra_powergate_sequence_power_up(TEGRA_POWERGATE_VDEC,
-						vde->clk, vde->rst);
+	err = reset_control_acquire(vde->rst_mc);
 	if (err) {
-		dev_err(dev, "Failed to power up HW : %d\n", err);
+		dev_err(dev, "Failed to acquire mc reset: %d\n", err);
 		return err;
 	}
 
+	err = reset_control_acquire(vde->rst);
+	if (err) {
+		dev_err(dev, "Failed to acquire reset: %d\n", err);
+		goto release_mc_reset;
+	}
+
+	if (!dev->pm_domain) {
+		err = tegra_powergate_sequence_power_up(TEGRA_POWERGATE_VDEC,
+							vde->clk, vde->rst);
+		if (err) {
+			dev_err(dev, "Failed to power up HW : %d\n", err);
+			goto release_reset;
+		}
+	}
+
+	err = clk_prepare_enable(vde->clk);
+	if (err) {
+		dev_err(dev, "Failed to enable clock: %d\n", err);
+		goto release_reset;
+	}
+
 	return 0;
+
+release_reset:
+	reset_control_release(vde->rst);
+release_mc_reset:
+	reset_control_release(vde->rst_mc);
+
+	return err;
 }
 
 static int tegra_vde_probe(struct platform_device *pdev)

@@ -1001,14 +1033,14 @@ static int tegra_vde_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	vde->rst = devm_reset_control_get(dev, NULL);
+	vde->rst = devm_reset_control_get_exclusive_released(dev, NULL);
 	if (IS_ERR(vde->rst)) {
 		err = PTR_ERR(vde->rst);
 		dev_err(dev, "Could not get VDE reset %d\n", err);
 		return err;
 	}
 
-	vde->rst_mc = devm_reset_control_get_optional(dev, "mc");
+	vde->rst_mc = devm_reset_control_get_optional_exclusive_released(dev, "mc");
 	if (IS_ERR(vde->rst_mc)) {
 		err = PTR_ERR(vde->rst_mc);
 		dev_err(dev, "Could not get MC reset %d\n", err);

@@ -1066,6 +1098,10 @@ static int tegra_vde_probe(struct platform_device *pdev)
 	pm_runtime_use_autosuspend(dev);
 	pm_runtime_set_autosuspend_delay(dev, 300);
 
+	err = devm_tegra_core_dev_init_opp_table_common(dev);
+	if (err)
+		goto err_pm_runtime;
+
 	/*
 	 * VDE partition may be left ON after bootloader, hence let's
 	 * power-cycle it in order to put hardware into a predictable lower

@@ -1133,8 +1169,7 @@ static void tegra_vde_shutdown(struct platform_device *pdev)
 	 * On some devices bootloader isn't ready to a power-gated VDE on
 	 * a warm-reboot, machine will hang in that case.
 	 */
-	if (pm_runtime_status_suspended(&pdev->dev))
-		tegra_vde_runtime_resume(&pdev->dev);
+	pm_runtime_get_sync(&pdev->dev);
 }
 
 static __maybe_unused int tegra_vde_pm_suspend(struct device *dev)

index f2151815db58..cc032729a143 100644
@@ -14,6 +14,7 @@
 #include <linux/of_address.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
+#include <linux/reset.h>
 #include <linux/slab.h>
 #include <linux/sys_soc.h>
 

@@ -243,6 +244,30 @@ static int tegra_fuse_probe(struct platform_device *pdev)
 		goto restore;
 	}
 
+	fuse->rst = devm_reset_control_get_optional(&pdev->dev, "fuse");
+	if (IS_ERR(fuse->rst)) {
+		err = PTR_ERR(fuse->rst);
+		dev_err(&pdev->dev, "failed to get FUSE reset: %pe\n",
+			fuse->rst);
+		goto restore;
+	}
+
+	/*
+	 * FUSE clock is enabled at a boot time, hence this resume/suspend
+	 * disables the clock besides the h/w resetting.
+	 */
+	err = pm_runtime_resume_and_get(&pdev->dev);
+	if (err)
+		goto restore;
+
+	err = reset_control_reset(fuse->rst);
+	pm_runtime_put(&pdev->dev);
+
+	if (err < 0) {
+		dev_err(&pdev->dev, "failed to reset FUSE: %d\n", err);
+		goto restore;
+	}
+
 	/* release the early I/O memory mapping */
 	iounmap(base);
 

index de58feba0435..1b719d85bd04 100644
@@ -43,6 +43,7 @@ struct tegra_fuse {
 	void __iomem *base;
 	phys_addr_t phys;
 	struct clk *clk;
+	struct reset_control *rst;
 
 	u32 (*read_early)(struct tegra_fuse *fuse, unsigned int offset);
 	u32 (*read)(struct tegra_fuse *fuse, unsigned int offset);

index cc032729a143..fe4f935ce73a 100644
@@ -182,6 +182,12 @@ static const struct nvmem_cell_info tegra_fuse_cells[] = {
 	},
 };
 
+static void tegra_fuse_restore(void *base)
+{
+	fuse->clk = NULL;
+	fuse->base = base;
+}
+
 static int tegra_fuse_probe(struct platform_device *pdev)
 {
 	void __iomem *base = fuse->base;

@@ -189,13 +195,16 @@ static int tegra_fuse_probe(struct platform_device *pdev)
 	struct resource *res;
 	int err;
 
+	err = devm_add_action(&pdev->dev, tegra_fuse_restore, base);
+	if (err)
+		return err;
+
 	/* take over the memory region from the early initialization */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	fuse->phys = res->start;
 	fuse->base = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(fuse->base)) {
 		err = PTR_ERR(fuse->base);
-		fuse->base = base;
 		return err;
 	}
 

@@ -205,19 +214,20 @@ static int tegra_fuse_probe(struct platform_device *pdev)
 			dev_err(&pdev->dev, "failed to get FUSE clock: %ld",
 				PTR_ERR(fuse->clk));
 
-		fuse->base = base;
 		return PTR_ERR(fuse->clk);
 	}
 
 	platform_set_drvdata(pdev, fuse);
 	fuse->dev = &pdev->dev;
 
-	pm_runtime_enable(&pdev->dev);
+	err = devm_pm_runtime_enable(&pdev->dev);
+	if (err)
+		return err;
 
 	if (fuse->soc->probe) {
 		err = fuse->soc->probe(fuse);
 		if (err < 0)
-			goto restore;
+			return err;
 	}
 
 	memset(&nvmem, 0, sizeof(nvmem));

@@ -241,7 +251,7 @@ static int tegra_fuse_probe(struct platform_device *pdev)
 		err = PTR_ERR(fuse->nvmem);
 		dev_err(&pdev->dev, "failed to register NVMEM device: %d\n",
 			err);
-		goto restore;
+		return err;
 	}
 
 	fuse->rst = devm_reset_control_get_optional(&pdev->dev, "fuse");

@@ -249,7 +259,7 @@ static int tegra_fuse_probe(struct platform_device *pdev)
 		err = PTR_ERR(fuse->rst);
 		dev_err(&pdev->dev, "failed to get FUSE reset: %pe\n",
 			fuse->rst);
-		goto restore;
+		return err;
 	}
 
 	/*

@@ -258,26 +268,20 @@ static int tegra_fuse_probe(struct platform_device *pdev)
 	 */
 	err = pm_runtime_resume_and_get(&pdev->dev);
 	if (err)
-		goto restore;
+		return err;
 
 	err = reset_control_reset(fuse->rst);
 	pm_runtime_put(&pdev->dev);
 
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to reset FUSE: %d\n", err);
-		goto restore;
+		return err;
 	}
 
 	/* release the early I/O memory mapping */
 	iounmap(base);
 
 	return 0;
-
-restore:
-	fuse->clk = NULL;
-	fuse->base = base;
-	pm_runtime_disable(&pdev->dev);
-	return err;
 }
 
 static int __maybe_unused tegra_fuse_runtime_resume(struct device *dev)

index 8ec9fc5e5e4b..12503f563e36 100644
@@ -94,9 +94,28 @@ static bool dma_filter(struct dma_chan *chan, void *filter_param)
 	return of_device_is_compatible(np, "nvidia,tegra20-apbdma");
 }
 
+static void tegra20_fuse_release_channel(void *data)
+{
+	struct tegra_fuse *fuse = data;
+
+	dma_release_channel(fuse->apbdma.chan);
+	fuse->apbdma.chan = NULL;
+}
+
+static void tegra20_fuse_free_coherent(void *data)
+{
+	struct tegra_fuse *fuse = data;
+
+	dma_free_coherent(fuse->dev, sizeof(u32), fuse->apbdma.virt,
+			  fuse->apbdma.phys);
+	fuse->apbdma.virt = NULL;
+	fuse->apbdma.phys = 0x0;
+}
+
 static int tegra20_fuse_probe(struct tegra_fuse *fuse)
 {
 	dma_cap_mask_t mask;
+	int err;
 
 	dma_cap_zero(mask);
 	dma_cap_set(DMA_SLAVE, mask);

@@ -105,13 +124,21 @@ static int tegra20_fuse_probe(struct tegra_fuse *fuse)
 	if (!fuse->apbdma.chan)
 		return -EPROBE_DEFER;
 
+	err = devm_add_action_or_reset(fuse->dev, tegra20_fuse_release_channel,
+				       fuse);
+	if (err)
+		return err;
+
 	fuse->apbdma.virt = dma_alloc_coherent(fuse->dev, sizeof(u32),
 					       &fuse->apbdma.phys,
 					       GFP_KERNEL);
-	if (!fuse->apbdma.virt) {
-		dma_release_channel(fuse->apbdma.chan);
+	if (!fuse->apbdma.virt)
 		return -ENOMEM;
-	}
+
+	err = devm_add_action_or_reset(fuse->dev, tegra20_fuse_free_coherent,
+				       fuse);
+	if (err)
+		return err;
 
 	fuse->apbdma.config.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
 	fuse->apbdma.config.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;

index b8ce9fd0650d..6a2f90ab9d3e 100644
@@ -16,7 +16,9 @@
 #include <linux/regulator/coupler.h>
 #include <linux/regulator/driver.h>
 #include <linux/regulator/machine.h>
+#include <linux/suspend.h>
 
+#include <soc/tegra/fuse.h>
 #include <soc/tegra/pmc.h>
 
 struct tegra_regulator_coupler {

@@ -25,9 +27,12 @@ struct tegra_regulator_coupler {
 	struct regulator_dev *cpu_rdev;
 	struct regulator_dev *rtc_rdev;
 	struct notifier_block reboot_notifier;
+	struct notifier_block suspend_notifier;
 	int core_min_uV, cpu_min_uV;
 	bool sys_reboot_mode_req;
 	bool sys_reboot_mode;
+	bool sys_suspend_mode_req;
+	bool sys_suspend_mode;
 };
 
 static inline struct tegra_regulator_coupler *

@@ -105,6 +110,28 @@ static int tegra20_core_rtc_max_spread(struct regulator_dev *core_rdev,
 	return 150000;
 }
 
+static int tegra20_cpu_nominal_uV(void)
+{
+	switch (tegra_sku_info.soc_speedo_id) {
+	case 0:
+		return 1100000;
+	case 1:
+		return 1025000;
+	default:
+		return 1125000;
+	}
+}
+
+static int tegra20_core_nominal_uV(void)
+{
+	switch (tegra_sku_info.soc_speedo_id) {
+	default:
+		return 1225000;
+	case 2:
+		return 1300000;
+	}
+}
+
 static int tegra20_core_rtc_update(struct tegra_regulator_coupler *tegra,
 				   struct regulator_dev *core_rdev,
 				   struct regulator_dev *rtc_rdev,

@@ -144,6 +171,11 @@ static int tegra20_core_rtc_update(struct tegra_regulator_coupler *tegra,
 	if (err)
 		return err;
 
+	/* prepare voltage level for suspend */
+	if (tegra->sys_suspend_mode)
+		core_min_uV = clamp(tegra20_core_nominal_uV(),
+				    core_min_uV, core_max_uV);
+
 	core_uV = regulator_get_voltage_rdev(core_rdev);
 	if (core_uV < 0)
 		return core_uV;

@@ -279,6 +311,11 @@ static int tegra20_cpu_voltage_update(struct tegra_regulator_coupler *tegra,
 	if (tegra->sys_reboot_mode)
 		cpu_min_uV = max(cpu_min_uV, tegra->cpu_min_uV);
 
+	/* prepare voltage level for suspend */
+	if (tegra->sys_suspend_mode)
+		cpu_min_uV = clamp(tegra20_cpu_nominal_uV(),
+				   cpu_min_uV, cpu_max_uV);
+
 	if (cpu_min_uV > cpu_uV) {
 		err = tegra20_core_rtc_update(tegra, core_rdev, rtc_rdev,
 					      cpu_uV, cpu_min_uV);

@@ -320,6 +357,7 @@ static int tegra20_regulator_balance_voltage(struct regulator_coupler *coupler,
 	}
 
 	tegra->sys_reboot_mode = READ_ONCE(tegra->sys_reboot_mode_req);
+	tegra->sys_suspend_mode = READ_ONCE(tegra->sys_suspend_mode_req);
 
 	if (rdev == cpu_rdev)
 		return tegra20_cpu_voltage_update(tegra, cpu_rdev,

@@ -334,6 +372,63 @@ static int tegra20_regulator_balance_voltage(struct regulator_coupler *coupler,
 	return -EPERM;
 }
 
+static int tegra20_regulator_prepare_suspend(struct tegra_regulator_coupler *tegra,
+					     bool sys_suspend_mode)
+{
+	int err;
+
+	if (!tegra->core_rdev || !tegra->rtc_rdev || !tegra->cpu_rdev)
+		return 0;
+
+	/*
+	 * All power domains are enabled early during resume from suspend
+	 * by GENPD core.  Domains like VENC may require a higher voltage
+	 * when enabled during resume from suspend.  This also prepares
+	 * hardware for resuming from LP0.
+	 */
+
+	WRITE_ONCE(tegra->sys_suspend_mode_req, sys_suspend_mode);
+
+	err = regulator_sync_voltage_rdev(tegra->cpu_rdev);
+	if (err)
+		return err;
+
+	err = regulator_sync_voltage_rdev(tegra->core_rdev);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int tegra20_regulator_suspend(struct notifier_block *notifier,
+				     unsigned long mode, void *arg)
+{
+	struct tegra_regulator_coupler *tegra;
+	int ret = 0;
+
+	tegra = container_of(notifier, struct tegra_regulator_coupler,
+			     suspend_notifier);
+
+	switch (mode) {
+	case PM_HIBERNATION_PREPARE:
+	case PM_RESTORE_PREPARE:
+	case PM_SUSPEND_PREPARE:
+		ret = tegra20_regulator_prepare_suspend(tegra, true);
+		break;
+
+	case PM_POST_HIBERNATION:
+	case PM_POST_RESTORE:
+	case PM_POST_SUSPEND:
+		ret = tegra20_regulator_prepare_suspend(tegra, false);
+		break;
+	}
+
+	if (ret)
+		pr_err("failed to prepare regulators: %d\n", ret);
+
+	return notifier_from_errno(ret);
+}
+
 static int tegra20_regulator_prepare_reboot(struct tegra_regulator_coupler *tegra,
 					    bool sys_reboot_mode)
 {

@@ -444,6 +539,7 @@ static struct tegra_regulator_coupler tegra20_coupler = {
 		.balance_voltage = tegra20_regulator_balance_voltage,
 	},
 	.reboot_notifier.notifier_call = tegra20_regulator_reboot,
+	.suspend_notifier.notifier_call = tegra20_regulator_suspend,
 };
 
 static int __init tegra_regulator_coupler_init(void)

@@ -456,6 +552,9 @@ static int __init tegra_regulator_coupler_init(void)
 	err = register_reboot_notifier(&tegra20_coupler.reboot_notifier);
 	WARN_ON(err);
 
+	err = register_pm_notifier(&tegra20_coupler.suspend_notifier);
+	WARN_ON(err);
+
 	return regulator_coupler_register(&tegra20_coupler.coupler);
 }
 arch_initcall(tegra_regulator_coupler_init);

177 lines not on this page · raw message

index fb8faf7b226a..5e1fc873bf8f 100644
@@ -1353,7 +1353,7 @@ static int tegra_pmc_core_pd_add(struct tegra_pmc *pmc, struct device_node *np)
 	if (!genpd)
 		return -ENOMEM;
 
-	genpd->name = np->name;
+	genpd->name = "core";
 	genpd->set_performance_state = tegra_pmc_core_pd_set_performance_state;
 	genpd->opp_to_performance_state = tegra_pmc_core_pd_opp_to_performance_state;
 

index 5e1fc873bf8f..74de84a014e9 100644
@@ -3042,7 +3042,7 @@ static void tegra20_pmc_setup_irq_polarity(struct tegra_pmc *pmc,
 }
 
 static const struct tegra_pmc_soc tegra20_pmc_soc = {
-	.supports_core_domain = false,
+	.supports_core_domain = true,
 	.num_powergates = ARRAY_SIZE(tegra20_powergates),
 	.powergates = tegra20_powergates,
 	.num_cpu_powergates = 0,

@@ -3103,7 +3103,7 @@ static const char * const tegra30_reset_sources[] = {
 };
 
 static const struct tegra_pmc_soc tegra30_pmc_soc = {
-	.supports_core_domain = false,
+	.supports_core_domain = true,
 	.num_powergates = ARRAY_SIZE(tegra30_powergates),
 	.powergates = tegra30_powergates,
 	.num_cpu_powergates = ARRAY_SIZE(tegra30_cpu_powergates),