diff --git a/drivers/clk/bcm/clk-raspberrypi.c b/drivers/clk/bcm/clk-raspberrypi.c
index dcc3ae5fb91650..90103d9498d0bf 100644
--- a/drivers/clk/bcm/clk-raspberrypi.c
+++ b/drivers/clk/bcm/clk-raspberrypi.c
@@ -66,7 +66,8 @@ const struct raspberrypi_clk_data *clk_hw_to_data(const struct clk_hw *hw)
 struct raspberrypi_clk_variant {
 	bool		export;
 	char		*clkdev;
-	unsigned long	min_rate;
+	u32		min_rate;
+	u32		max_rate;
 	bool		minimize;
 	bool		maximize;
 	u32		flags;
@@ -141,17 +142,17 @@ raspberrypi_clk_variants[RPI_FIRMWARE_NUM_CLK_ID] = {
 	[RPI_FIRMWARE_PIXEL_CLK_ID] = {
 		.export = true,
 		.minimize = true,
-		.flags = CLK_IS_CRITICAL,
+		.flags = CLK_IGNORE_UNUSED,
 	},
 	[RPI_FIRMWARE_HEVC_CLK_ID] = {
 		.export = true,
 		.minimize = true,
-		.flags = CLK_IS_CRITICAL,
+		.flags = CLK_IGNORE_UNUSED,
 	},
 	[RPI_FIRMWARE_ISP_CLK_ID] = {
 		.export = true,
 		.minimize = true,
-		.flags = CLK_IS_CRITICAL,
+		.flags = CLK_IGNORE_UNUSED,
 	},
 	[RPI_FIRMWARE_PIXEL_BVB_CLK_ID] = {
 		.export = true,
@@ -290,16 +291,22 @@ static int raspberrypi_fw_dumb_determine_rate(struct clk_hw *hw,
 static int raspberrypi_fw_prepare(struct clk_hw *hw)
 {
 	const struct raspberrypi_clk_data *data = clk_hw_to_data(hw);
+	struct raspberrypi_clk_variant *variant = data->variant;
 	struct raspberrypi_clk *rpi = data->rpi;
 	u32 state = RPI_FIRMWARE_STATE_ENABLE_BIT;
 	int ret;
 
 	ret = raspberrypi_clock_property(rpi->firmware, data,
 					 RPI_FIRMWARE_SET_CLOCK_STATE, &state);
-	if (ret)
+	if (ret) {
 		dev_err_ratelimited(rpi->dev,
 				    "Failed to set clock %s state to on: %d\n",
 				    clk_hw_get_name(hw), ret);
+		return ret;
+	}
+
+	if (variant->maximize)
+		ret = raspberrypi_fw_set_rate(hw, variant->max_rate, 0);
 
 	return ret;
 }
@@ -307,10 +314,19 @@ static int raspberrypi_fw_prepare(struct clk_hw *hw)
 static void raspberrypi_fw_unprepare(struct clk_hw *hw)
 {
 	const struct raspberrypi_clk_data *data = clk_hw_to_data(hw);
+	struct raspberrypi_clk_variant *variant = data->variant;
 	struct raspberrypi_clk *rpi = data->rpi;
 	u32 state = 0;
 	int ret;
 
+	/*
+	 * On current firmware versions, RPI_FIRMWARE_SET_CLOCK_STATE doesn't
+	 * actually power off the clock. To achieve meaningful power consumption
+	 * reduction, the driver needs to set the clock rate to minimum before
+	 * disabling it.
+	 */
+	raspberrypi_fw_set_rate(hw, variant->min_rate, 0);
+
 	ret = raspberrypi_clock_property(rpi->firmware, data,
 					 RPI_FIRMWARE_SET_CLOCK_STATE, &state);
 	if (ret)
@@ -335,7 +351,7 @@ static struct clk_hw *raspberrypi_clk_register(struct raspberrypi_clk *rpi,
 {
 	struct raspberrypi_clk_data *data;
 	struct clk_init_data init = {};
-	u32 min_rate, max_rate;
+	unsigned long rate;
 	int ret;
 
 	data = devm_kzalloc(rpi->dev, sizeof(*data), GFP_KERNEL);
@@ -355,18 +371,20 @@ static struct clk_hw *raspberrypi_clk_register(struct raspberrypi_clk *rpi,
 
 	data->hw.init = &init;
 
-	ret = raspberrypi_clock_property(rpi->firmware, data,
-					 RPI_FIRMWARE_GET_MIN_CLOCK_RATE,
-					 &min_rate);
-	if (ret) {
-		dev_err(rpi->dev, "Failed to get clock %d min freq: %d\n",
-			id, ret);
-		return ERR_PTR(ret);
+	if (!variant->min_rate) {
+		ret = raspberrypi_clock_property(rpi->firmware, data,
+						 RPI_FIRMWARE_GET_MIN_CLOCK_RATE,
+						 &variant->min_rate);
+		if (ret) {
+			dev_err(rpi->dev, "Failed to get clock %d min freq: %d\n",
+				id, ret);
+			return ERR_PTR(ret);
+		}
 	}
 
 	ret = raspberrypi_clock_property(rpi->firmware, data,
 					 RPI_FIRMWARE_GET_MAX_CLOCK_RATE,
-					 &max_rate);
+					 &variant->max_rate);
 	if (ret) {
 		dev_err(rpi->dev, "Failed to get clock %d max freq: %d\n",
 			id, ret);
@@ -377,7 +395,7 @@ static struct clk_hw *raspberrypi_clk_register(struct raspberrypi_clk *rpi,
 	if (ret)
 		return ERR_PTR(ret);
 
-	clk_hw_set_rate_range(&data->hw, min_rate, max_rate);
+	clk_hw_set_rate_range(&data->hw, variant->min_rate, variant->max_rate);
 
 	if (variant->clkdev) {
 		ret = devm_clk_hw_register_clkdev(rpi->dev, &data->hw,
@@ -388,20 +406,11 @@ static struct clk_hw *raspberrypi_clk_register(struct raspberrypi_clk *rpi,
 		}
 	}
 
-	if (variant->maximize)
-		variant->min_rate = max_rate;
-
-	if (variant->min_rate) {
-		unsigned long rate;
-
-		clk_hw_set_rate_range(&data->hw, variant->min_rate, max_rate);
-
-		rate = raspberrypi_fw_get_rate(&data->hw, 0);
-		if (rate < variant->min_rate) {
-			ret = raspberrypi_fw_set_rate(&data->hw, variant->min_rate, 0);
-			if (ret)
-				return ERR_PTR(ret);
-		}
+	rate = raspberrypi_fw_get_rate(&data->hw, 0);
+	if (rate < variant->min_rate) {
+		ret = raspberrypi_fw_set_rate(&data->hw, variant->min_rate, 0);
+		if (ret)
+			return ERR_PTR(ret);
 	}
 
 	return &data->hw;
diff --git a/drivers/gpu/drm/v3d/Makefile b/drivers/gpu/drm/v3d/Makefile
index fcf710926057b3..c2d6d4b9534353 100644
--- a/drivers/gpu/drm/v3d/Makefile
+++ b/drivers/gpu/drm/v3d/Makefile
@@ -14,7 +14,8 @@ v3d-y := \
 	v3d_sched.o \
 	v3d_sysfs.o \
 	v3d_submit.o \
-	v3d_gemfs.o
+	v3d_gemfs.o \
+	v3d_power.o
 
 v3d-$(CONFIG_DEBUG_FS) += v3d_debugfs.o
 
diff --git a/drivers/gpu/drm/v3d/v3d_debugfs.c b/drivers/gpu/drm/v3d/v3d_debugfs.c
index 7e789e181af0ac..d4cd4360ad21a2 100644
--- a/drivers/gpu/drm/v3d/v3d_debugfs.c
+++ b/drivers/gpu/drm/v3d/v3d_debugfs.c
@@ -96,7 +96,11 @@ static int v3d_v3d_debugfs_regs(struct seq_file *m, void *unused)
 	struct drm_debugfs_entry *entry = m->private;
 	struct drm_device *dev = entry->dev;
 	struct v3d_dev *v3d = to_v3d_dev(dev);
-	int i, core;
+	int i, core, ret;
+
+	ret = v3d_pm_runtime_get(v3d);
+	if (ret)
+		return ret;
 
 	for (i = 0; i < ARRAY_SIZE(v3d_hub_reg_defs); i++) {
 		const struct v3d_reg_def *def = &v3d_hub_reg_defs[i];
@@ -138,6 +142,8 @@ static int v3d_v3d_debugfs_regs(struct seq_file *m, void *unused)
 		}
 	}
 
+	v3d_pm_runtime_put(v3d);
+
 	return 0;
 }
 
@@ -147,7 +153,11 @@ static int v3d_v3d_debugfs_ident(struct seq_file *m, void *unused)
 	struct drm_device *dev = entry->dev;
 	struct v3d_dev *v3d = to_v3d_dev(dev);
 	u32 ident0, ident1, ident2, ident3, cores;
-	int core;
+	int core, ret;
+
+	ret = v3d_pm_runtime_get(v3d);
+	if (ret)
+		return ret;
 
 	ident0 = V3D_READ(V3D_HUB_IDENT0);
 	ident1 = V3D_READ(V3D_HUB_IDENT1);
@@ -206,6 +216,8 @@ static int v3d_v3d_debugfs_ident(struct seq_file *m, void *unused)
 		}
 	}
 
+	v3d_pm_runtime_put(v3d);
+
 	return 0;
 }
 
@@ -233,6 +245,11 @@ static int v3d_measure_clock(struct seq_file *m, void *unused)
 	uint32_t cycles;
 	int core = 0;
 	int measure_ms = 1000;
+	int ret;
+
+	ret = v3d_pm_runtime_get(v3d);
+	if (ret)
+		return ret;
 
 	if (v3d->ver >= V3D_GEN_41) {
 		int cycle_count_reg = V3D_PCTR_CYCLE_COUNT(v3d->ver);
@@ -252,6 +269,8 @@ static int v3d_measure_clock(struct seq_file *m, void *unused)
 	msleep(measure_ms);
 	cycles = V3D_CORE_READ(core, V3D_PCTR_0_PCTR0);
 
+	v3d_pm_runtime_put(v3d);
+
 	seq_printf(m, "cycles: %d (%d.%d Mhz)\n",
 		   cycles,
 		   cycles / (measure_ms * 1000),
diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c
index cf33cec1075ea4..324cba8b7d1585 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.c
+++ b/drivers/gpu/drm/v3d/v3d_drv.c
@@ -26,8 +26,6 @@
 #include <drm/drm_drv.h>
 #include <drm/drm_managed.h>
 
-#include <soc/bcm2835/raspberrypi-firmware.h>
-
 #include <uapi/drm/v3d_drm.h>
 
 #include "v3d_drv.h"
@@ -65,6 +63,7 @@ static int v3d_get_param_ioctl(struct drm_device *dev, void *data,
 		[DRM_V3D_PARAM_V3D_CORE0_IDENT1] = V3D_CTL_IDENT1,
 		[DRM_V3D_PARAM_V3D_CORE0_IDENT2] = V3D_CTL_IDENT2,
 	};
+	int ret;
 
 	if (args->pad != 0)
 		return -EINVAL;
@@ -81,12 +80,19 @@ static int v3d_get_param_ioctl(struct drm_device *dev, void *data,
 		if (args->value != 0)
 			return -EINVAL;
 
+		ret = v3d_pm_runtime_get(v3d);
+		if (ret)
+			return ret;
+
 		if (args->param >= DRM_V3D_PARAM_V3D_CORE0_IDENT0 &&
 		    args->param <= DRM_V3D_PARAM_V3D_CORE0_IDENT2) {
 			args->value = V3D_CORE_READ(0, offset);
 		} else {
 			args->value = V3D_READ(offset);
 		}
+
+		v3d_pm_runtime_put(v3d);
+
 		return 0;
 	}
 
@@ -293,36 +299,6 @@ static const struct of_device_id v3d_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, v3d_of_match);
 
-static void
-v3d_idle_sms(struct v3d_dev *v3d)
-{
-	if (v3d->ver < V3D_GEN_71)
-		return;
-
-	V3D_SMS_WRITE(V3D_SMS_TEE_CS, V3D_SMS_CLEAR_POWER_OFF);
-
-	if (wait_for((V3D_GET_FIELD(V3D_SMS_READ(V3D_SMS_TEE_CS),
-				    V3D_SMS_STATE) == V3D_SMS_IDLE), 100)) {
-		DRM_ERROR("Failed to power up SMS\n");
-	}
-
-	v3d_reset_sms(v3d);
-}
-
-static void
-v3d_power_off_sms(struct v3d_dev *v3d)
-{
-	if (v3d->ver < V3D_GEN_71)
-		return;
-
-	V3D_SMS_WRITE(V3D_SMS_TEE_CS, V3D_SMS_POWER_OFF);
-
-	if (wait_for((V3D_GET_FIELD(V3D_SMS_READ(V3D_SMS_TEE_CS),
-				    V3D_SMS_STATE) == V3D_SMS_POWER_OFF_STATE), 100)) {
-		DRM_ERROR("Failed to power off SMS\n");
-	}
-}
-
 static int
 map_regs(struct v3d_dev *v3d, void __iomem **regs, const char *name)
 {
@@ -333,8 +309,6 @@ map_regs(struct v3d_dev *v3d, void __iomem **regs, const char *name)
 static int v3d_platform_drm_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct rpi_firmware *firmware;
-	struct device_node *node;
 	struct drm_device *drm;
 	struct v3d_dev *v3d;
 	enum v3d_gen gen;
@@ -368,23 +342,66 @@ static int v3d_platform_drm_probe(struct platform_device *pdev)
 			return ret;
 	}
 
+	if (v3d->ver < V3D_GEN_41) {
+		ret = map_regs(v3d, &v3d->gca_regs, "gca");
+		if (ret)
+			return ret;
+	}
+
+	v3d->reset = devm_reset_control_get_optional_exclusive(dev, NULL);
+	if (IS_ERR(v3d->reset))
+		return dev_err_probe(dev, PTR_ERR(v3d->reset),
+				     "Failed to get reset control\n");
+
+	if (!v3d->reset) {
+		ret = map_regs(v3d, &v3d->bridge_regs, "bridge");
+		if (ret) {
+			dev_err(dev, "Failed to get bridge registers\n");
+			return ret;
+		}
+	}
+
 	v3d->clk = devm_clk_get_optional(dev, NULL);
 	if (IS_ERR(v3d->clk))
 		return dev_err_probe(dev, PTR_ERR(v3d->clk), "Failed to get V3D clock\n");
 
-	ret = clk_prepare_enable(v3d->clk);
-	if (ret) {
-		dev_err(&pdev->dev, "Couldn't enable the V3D clock\n");
+	ret = v3d_irq_init(v3d);
+	if (ret)
 		return ret;
+
+	v3d_perfmon_init(v3d);
+
+	v3d->mmu_scratch = dma_alloc_wc(dev, 4096, &v3d->mmu_scratch_paddr,
+					GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO);
+	if (!v3d->mmu_scratch) {
+		dev_err(dev, "Failed to allocate MMU scratch page\n");
+		return -ENOMEM;
 	}
 
-	v3d_idle_sms(v3d);
+	ret = v3d_gem_init(drm);
+	if (ret)
+		goto dma_free;
+
+	ret = devm_pm_runtime_enable(dev);
+	if (ret)
+		goto gem_destroy;
+
+	ret = pm_runtime_resume_and_get(dev);
+	if (ret)
+		goto gem_destroy;
+
+	/* If PM is disabled, we need to call v3d_power_resume() manually. */
+	if (!IS_ENABLED(CONFIG_PM)) {
+		ret = v3d_power_resume(dev);
+		if (ret)
+			goto gem_destroy;
+	}
 
 	mmu_debug = V3D_READ(V3D_MMU_DEBUG_INFO);
 	mask = DMA_BIT_MASK(30 + V3D_GET_FIELD(mmu_debug, V3D_MMU_PA_WIDTH));
 	ret = dma_set_mask_and_coherent(dev, mask);
 	if (ret)
-		goto clk_disable;
+		goto runtime_pm_put;
 
 	v3d->va_width = 30 + V3D_GET_FIELD(mmu_debug, V3D_MMU_VA_WIDTH);
 
@@ -402,93 +419,32 @@ static int v3d_platform_drm_probe(struct platform_device *pdev)
 	ident3 = V3D_READ(V3D_HUB_IDENT3);
 	v3d->rev = V3D_GET_FIELD(ident3, V3D_HUB_IDENT3_IPREV);
 
-	v3d_perfmon_init(v3d);
-
-	v3d->reset = devm_reset_control_get_exclusive(dev, NULL);
-	if (IS_ERR(v3d->reset)) {
-		ret = PTR_ERR(v3d->reset);
-
-		if (ret == -EPROBE_DEFER)
-			goto clk_disable;
+	v3d_init_hw_state(v3d);
 
-		v3d->reset = NULL;
-		ret = map_regs(v3d, &v3d->bridge_regs, "bridge");
-		if (ret) {
-			dev_err(dev,
-				"Failed to get reset control or bridge regs\n");
-			goto clk_disable;
-		}
-	}
-
-	node = rpi_firmware_find_node();
-	if (!node) {
-		ret = -EINVAL;
-		goto clk_disable;
-	}
-
-	firmware = rpi_firmware_get(node);
-	of_node_put(node);
-	if (!firmware) {
-		ret = -EPROBE_DEFER;
-		goto clk_disable;
-	}
-
-	v3d->clk_up_rate = rpi_firmware_clk_get_max_rate(firmware,
-							 RPI_FIRMWARE_V3D_CLK_ID);
-	rpi_firmware_put(firmware);
-
-	/* For downclocking, drop it to the minimum frequency we can get from
-	 * the CPRMAN clock generator dividing off our parent.  The divider is
-	 * 4 bits, but ask for just higher than that so that rounding doesn't
-	 * make cprman reject our rate.
-	 */
-	v3d->clk_down_rate =
-		(clk_get_rate(clk_get_parent(v3d->clk)) / (1 << 4)) + 10000;
-
-	if (v3d->ver < V3D_GEN_41) {
-		ret = map_regs(v3d, &v3d->gca_regs, "gca");
-		if (ret)
-			goto clk_disable;
-	}
-
-	v3d->mmu_scratch = dma_alloc_wc(dev, 4096, &v3d->mmu_scratch_paddr,
-					GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO);
-	if (!v3d->mmu_scratch) {
-		dev_err(dev, "Failed to allocate MMU scratch page\n");
-		ret = -ENOMEM;
-		goto clk_disable;
-	}
-
-	ret = v3d_gem_init(drm);
-	if (ret)
-		goto dma_free;
-
-	ret = v3d_irq_init(v3d);
-	if (ret)
-		goto gem_destroy;
+	pm_runtime_set_autosuspend_delay(dev, 50);
+	pm_runtime_use_autosuspend(dev);
 
 	ret = drm_dev_register(drm, 0);
 	if (ret)
-		goto irq_disable;
+		goto runtime_pm_put;
 
 	ret = v3d_sysfs_init(dev);
 	if (ret)
 		goto drm_unregister;
-	ret = clk_set_min_rate(v3d->clk, v3d->clk_down_rate);
-	WARN_ON_ONCE(ret != 0);
+
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_put_autosuspend(dev);
 
 	return 0;
 
 drm_unregister:
 	drm_dev_unregister(drm);
-irq_disable:
-	v3d_irq_disable(v3d);
+runtime_pm_put:
+	pm_runtime_put_sync_suspend(dev);
 gem_destroy:
 	v3d_gem_destroy(drm);
 dma_free:
 	dma_free_wc(dev, 4096, v3d->mmu_scratch, v3d->mmu_scratch_paddr);
-clk_disable:
-	clk_disable_unprepare(v3d->clk);
 	return ret;
 }
 
@@ -502,22 +458,27 @@ static void v3d_platform_drm_remove(struct platform_device *pdev)
 
 	drm_dev_unregister(drm);
 
-	v3d_gem_destroy(drm);
+	pm_runtime_suspend(dev);
 
-	dma_free_wc(v3d->drm.dev, 4096, v3d->mmu_scratch,
-		    v3d->mmu_scratch_paddr);
+	/* If PM is disabled, we need to call v3d_power_suspend() manually. */
+	if (!IS_ENABLED(CONFIG_PM))
+		v3d_power_suspend(dev);
 
-	v3d_power_off_sms(v3d);
+	v3d_gem_destroy(drm);
 
-	clk_disable_unprepare(v3d->clk);
+	dma_free_wc(dev, 4096, v3d->mmu_scratch, v3d->mmu_scratch_paddr);
 }
 
+static DEFINE_RUNTIME_DEV_PM_OPS(v3d_pm_ops, v3d_power_suspend,
+				 v3d_power_resume, NULL);
+
 static struct platform_driver v3d_platform_driver = {
 	.probe		= v3d_platform_drm_probe,
 	.remove		= v3d_platform_drm_remove,
 	.driver		= {
 		.name	= "v3d",
 		.of_match_table = v3d_of_match,
+		.pm = pm_ptr(&v3d_pm_ops),
 	},
 };
 
diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h
index 4ebb3dcd7ab4a8..a1da44ec656750 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.h
+++ b/drivers/gpu/drm/v3d/v3d_drv.h
@@ -3,6 +3,7 @@
 
 #include <linux/delay.h>
 #include <linux/mutex.h>
+#include <linux/pm_runtime.h>
 #include <linux/spinlock_types.h>
 #include <linux/workqueue.h>
 
@@ -134,11 +135,6 @@ struct v3d_dev {
 	void __iomem *gca_regs;
 	void __iomem *sms_regs;
 	struct clk *clk;
-	struct delayed_work clk_down_work;
-	unsigned long clk_up_rate, clk_down_rate;
-	struct mutex clk_lock;
-	u32 clk_refcount;
-	bool clk_up;
 
 	struct reset_control *reset;
 
@@ -335,6 +331,8 @@ struct v3d_job {
 
 	/* Callback for the freeing of the job on refcount going to 0. */
 	void (*free)(struct kref *ref);
+
+	bool has_pm_ref;
 };
 
 struct v3d_bin_job {
@@ -575,6 +573,7 @@ extern const struct dma_fence_ops v3d_fence_ops;
 struct dma_fence *v3d_fence_create(struct v3d_dev *v3d, enum v3d_queue q);
 
 /* v3d_gem.c */
+void v3d_init_hw_state(struct v3d_dev *v3d);
 int v3d_gem_init(struct drm_device *dev);
 void v3d_gem_destroy(struct drm_device *dev);
 void v3d_reset_sms(struct v3d_dev *v3d);
@@ -612,6 +611,20 @@ int v3d_mmu_set_page_table(struct v3d_dev *v3d);
 void v3d_mmu_insert_ptes(struct v3d_bo *bo);
 void v3d_mmu_remove_ptes(struct v3d_bo *bo);
 
+/* v3d_power.c */
+int v3d_power_suspend(struct device *dev);
+int v3d_power_resume(struct device *dev);
+
+static __always_inline int v3d_pm_runtime_get(struct v3d_dev *v3d)
+{
+	return pm_runtime_resume_and_get(v3d->drm.dev);
+}
+
+static __always_inline int v3d_pm_runtime_put(struct v3d_dev *v3d)
+{
+	return pm_runtime_put_autosuspend(v3d->drm.dev);
+}
+
 /* v3d_sched.c */
 void v3d_timestamp_query_info_free(struct v3d_timestamp_query_info *query_info,
 				   unsigned int count);
@@ -645,4 +658,3 @@ int v3d_perfmon_set_global_ioctl(struct drm_device *dev, void *data,
 /* v3d_sysfs.c */
 int v3d_sysfs_init(struct device *dev);
 void v3d_sysfs_destroy(struct device *dev);
-void v3d_submit_init(struct drm_device *dev);
diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
index 62fcd8c9cbc4be..82fda76a2daf1d 100644
--- a/drivers/gpu/drm/v3d/v3d_gem.c
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -36,13 +36,6 @@ v3d_init_core(struct v3d_dev *v3d, int core)
 	V3D_CORE_WRITE(core, V3D_CTL_L2TFLEND, ~0);
 }
 
-/* Sets invariant state for the HW. */
-static void
-v3d_init_hw_state(struct v3d_dev *v3d)
-{
-	v3d_init_core(v3d, 0);
-}
-
 static void
 v3d_idle_axi(struct v3d_dev *v3d, int core)
 {
@@ -259,6 +252,13 @@ v3d_invalidate_caches(struct v3d_dev *v3d)
 	v3d_invalidate_slices(v3d, 0);
 }
 
+/* Sets invariant state for the HW. */
+void
+v3d_init_hw_state(struct v3d_dev *v3d)
+{
+	v3d_init_core(v3d, 0);
+}
+
 int
 v3d_gem_init(struct drm_device *dev)
 {
@@ -291,8 +291,6 @@ v3d_gem_init(struct drm_device *dev)
 	if (ret)
 		return ret;
 
-	v3d_submit_init(dev);
-
 	/* Note: We don't allocate address 0.  Various bits of HW
 	 * treat 0 as special, such as the occlusion query counters
 	 * where 0 means "disabled".
@@ -309,9 +307,6 @@ v3d_gem_init(struct drm_device *dev)
 		return -ENOMEM;
 	}
 
-	v3d_init_hw_state(v3d);
-	v3d_mmu_set_page_table(v3d);
-
 	v3d_gemfs_init(v3d);
 
 	ret = v3d_sched_init(v3d);
diff --git a/drivers/gpu/drm/v3d/v3d_irq.c b/drivers/gpu/drm/v3d/v3d_irq.c
index 2a7988adcd04b8..d9fd912e86bbaa 100644
--- a/drivers/gpu/drm/v3d/v3d_irq.c
+++ b/drivers/gpu/drm/v3d/v3d_irq.c
@@ -251,17 +251,10 @@ v3d_hub_irq(int irq, void *arg)
 int
 v3d_irq_init(struct v3d_dev *v3d)
 {
-	int irq, ret, core;
+	int irq, ret;
 
 	INIT_WORK(&v3d->overflow_mem_work, v3d_overflow_mem_work);
 
-	/* Clear any pending interrupts someone might have left around
-	 * for us.
-	 */
-	for (core = 0; core < v3d->cores; core++)
-		V3D_CORE_WRITE(core, V3D_CTL_INT_CLR, V3D_CORE_IRQS(v3d->ver));
-	V3D_WRITE(V3D_HUB_INT_CLR, V3D_HUB_IRQS(v3d->ver));
-
 	irq = platform_get_irq_optional(v3d_to_pdev(v3d), 1);
 	if (irq == -EPROBE_DEFER)
 		return irq;
@@ -299,7 +292,6 @@ v3d_irq_init(struct v3d_dev *v3d)
 			goto fail;
 	}
 
-	v3d_irq_enable(v3d);
 	return 0;
 
 fail:
@@ -313,6 +305,11 @@ v3d_irq_enable(struct v3d_dev *v3d)
 {
 	int core;
 
+	/* Clear any pending interrupts someone might have left around for us. */
+	for (core = 0; core < v3d->cores; core++)
+		V3D_CORE_WRITE(core, V3D_CTL_INT_CLR, V3D_CORE_IRQS(v3d->ver));
+	V3D_WRITE(V3D_HUB_INT_CLR, V3D_HUB_IRQS(v3d->ver));
+
 	/* Enable our set of interrupts, masking out any others. */
 	for (core = 0; core < v3d->cores; core++) {
 		V3D_CORE_WRITE(core, V3D_CTL_INT_MSK_SET, ~V3D_CORE_IRQS(v3d->ver));
diff --git a/drivers/gpu/drm/v3d/v3d_mmu.c b/drivers/gpu/drm/v3d/v3d_mmu.c
index a25d25a8ae617b..01f0b7c7b864dc 100644
--- a/drivers/gpu/drm/v3d/v3d_mmu.c
+++ b/drivers/gpu/drm/v3d/v3d_mmu.c
@@ -37,7 +37,11 @@ static bool v3d_mmu_is_aligned(u32 page, u32 page_address, size_t alignment)
 
 int v3d_mmu_flush_all(struct v3d_dev *v3d)
 {
-	int ret;
+	int ret = 0;
+
+	/* Flush the PTs only if we're already awake */
+	if (!pm_runtime_get_if_active(v3d->drm.dev))
+		return 0;
 
 	V3D_WRITE(V3D_MMUC_CONTROL, V3D_MMUC_CONTROL_FLUSH |
 		  V3D_MMUC_CONTROL_ENABLE);
@@ -46,7 +50,7 @@ int v3d_mmu_flush_all(struct v3d_dev *v3d)
 			 V3D_MMUC_CONTROL_FLUSHING), 100);
 	if (ret) {
 		dev_err(v3d->drm.dev, "MMUC flush wait idle failed\n");
-		return ret;
+		goto pm_put;
 	}
 
 	V3D_WRITE(V3D_MMU_CTL, V3D_READ(V3D_MMU_CTL) |
@@ -57,6 +61,8 @@ int v3d_mmu_flush_all(struct v3d_dev *v3d)
 	if (ret)
 		dev_err(v3d->drm.dev, "MMU TLB clear wait idle failed\n");
 
+pm_put:
+	v3d_pm_runtime_put(v3d);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/v3d/v3d_perfmon.c b/drivers/gpu/drm/v3d/v3d_perfmon.c
index 9a3fe52558746e..b0873fe20347e7 100644
--- a/drivers/gpu/drm/v3d/v3d_perfmon.c
+++ b/drivers/gpu/drm/v3d/v3d_perfmon.c
@@ -235,6 +235,9 @@ void v3d_perfmon_start(struct v3d_dev *v3d, struct v3d_perfmon *perfmon)
 	if (WARN_ON_ONCE(!perfmon || v3d->active_perfmon))
 		return;
 
+	if (!pm_runtime_get_if_active(v3d->drm.dev))
+		return;
+
 	ncounters = perfmon->ncounters;
 	mask = GENMASK(ncounters - 1, 0);
 
@@ -260,6 +263,8 @@ void v3d_perfmon_start(struct v3d_dev *v3d, struct v3d_perfmon *perfmon)
 	V3D_CORE_WRITE(0, V3D_PCTR_0_OVERFLOW, mask);
 
 	v3d->active_perfmon = perfmon;
+
+	v3d_pm_runtime_put(v3d);
 }
 
 void v3d_perfmon_stop(struct v3d_dev *v3d, struct v3d_perfmon *perfmon,
@@ -271,10 +276,11 @@ void v3d_perfmon_stop(struct v3d_dev *v3d, struct v3d_perfmon *perfmon,
 		return;
 
 	mutex_lock(&perfmon->lock);
-	if (perfmon != v3d->active_perfmon) {
-		mutex_unlock(&perfmon->lock);
-		return;
-	}
+	if (perfmon != v3d->active_perfmon)
+		goto out;
+
+	if (!pm_runtime_get_if_active(v3d->drm.dev))
+		goto out_clear;
 
 	if (capture)
 		for (i = 0; i < perfmon->ncounters; i++)
@@ -282,7 +288,11 @@ void v3d_perfmon_stop(struct v3d_dev *v3d, struct v3d_perfmon *perfmon,
 
 	V3D_CORE_WRITE(0, V3D_V4_PCTR_0_EN, 0);
 
+	v3d_pm_runtime_put(v3d);
+
+out_clear:
 	v3d->active_perfmon = NULL;
+out:
 	mutex_unlock(&perfmon->lock);
 }
 
diff --git a/drivers/gpu/drm/v3d/v3d_power.c b/drivers/gpu/drm/v3d/v3d_power.c
new file mode 100644
index 00000000000000..f3d30ef5de4ea6
--- /dev/null
+++ b/drivers/gpu/drm/v3d/v3d_power.c
@@ -0,0 +1,83 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2026 Raspberry Pi */
+
+#include <linux/clk.h>
+#include <linux/reset.h>
+
+#include <drm/drm_print.h>
+
+#include "v3d_drv.h"
+#include "v3d_regs.h"
+
+static void
+v3d_resume_sms(struct v3d_dev *v3d)
+{
+	if (v3d->ver < V3D_GEN_71)
+		return;
+
+	V3D_SMS_WRITE(V3D_SMS_TEE_CS, V3D_SMS_CLEAR_POWER_OFF);
+
+	if (wait_for((V3D_GET_FIELD(V3D_SMS_READ(V3D_SMS_TEE_CS),
+				    V3D_SMS_STATE) == V3D_SMS_IDLE), 100)) {
+		drm_err(&v3d->drm, "Failed to power up SMS\n");
+	}
+
+	v3d_reset_sms(v3d);
+}
+
+static void
+v3d_suspend_sms(struct v3d_dev *v3d)
+{
+	if (v3d->ver < V3D_GEN_71)
+		return;
+
+	V3D_SMS_WRITE(V3D_SMS_TEE_CS, V3D_SMS_POWER_OFF);
+
+	if (wait_for((V3D_GET_FIELD(V3D_SMS_READ(V3D_SMS_TEE_CS),
+				    V3D_SMS_STATE) == V3D_SMS_POWER_OFF_STATE), 100)) {
+		drm_err(&v3d->drm, "Failed to power off SMS\n");
+	}
+}
+
+int v3d_power_suspend(struct device *dev)
+{
+	struct drm_device *drm = dev_get_drvdata(dev);
+	struct v3d_dev *v3d = to_v3d_dev(drm);
+
+	v3d_irq_disable(v3d);
+	v3d_suspend_sms(v3d);
+
+	if (v3d->reset)
+		reset_control_assert(v3d->reset);
+
+	clk_disable_unprepare(v3d->clk);
+
+	return 0;
+}
+
+int v3d_power_resume(struct device *dev)
+{
+	struct drm_device *drm = dev_get_drvdata(dev);
+	struct v3d_dev *v3d = to_v3d_dev(drm);
+	int ret;
+
+	ret = clk_prepare_enable(v3d->clk);
+	if (ret)
+		return ret;
+
+	if (v3d->reset) {
+		ret = reset_control_deassert(v3d->reset);
+		if (ret)
+			goto clk_disable;
+	}
+
+	v3d_resume_sms(v3d);
+	v3d_mmu_set_page_table(v3d);
+	v3d_irq_enable(v3d);
+
+	return 0;
+
+clk_disable:
+	clk_disable_unprepare(v3d->clk);
+	return ret;
+}
diff --git a/drivers/gpu/drm/v3d/v3d_submit.c b/drivers/gpu/drm/v3d/v3d_submit.c
index e6ca9312566680..614cb6e3cf81f8 100644
--- a/drivers/gpu/drm/v3d/v3d_submit.c
+++ b/drivers/gpu/drm/v3d/v3d_submit.c
@@ -5,52 +5,11 @@
  */
 
 #include <drm/drm_syncobj.h>
-#include <linux/clk.h>
 
 #include "v3d_drv.h"
 #include "v3d_regs.h"
 #include "v3d_trace.h"
 
-static void
-v3d_clock_down_work(struct work_struct *work)
-{
-	struct v3d_dev *v3d =
-		container_of(work, struct v3d_dev, clk_down_work.work);
-	int ret;
-
-	ret = clk_set_min_rate(v3d->clk, v3d->clk_down_rate);
-	v3d->clk_up = false;
-	WARN_ON_ONCE(ret != 0);
-}
-
-static void
-v3d_clock_up_get(struct v3d_dev *v3d)
-{
-	mutex_lock(&v3d->clk_lock);
-	if (v3d->clk_refcount++ == 0) {
-		cancel_delayed_work_sync(&v3d->clk_down_work);
-		if (!v3d->clk_up)  {
-			int ret;
-
-			ret = clk_set_min_rate(v3d->clk, v3d->clk_up_rate);
-			WARN_ON_ONCE(ret != 0);
-			v3d->clk_up = true;
-		}
-	}
-	mutex_unlock(&v3d->clk_lock);
-}
-
-static void
-v3d_clock_up_put(struct v3d_dev *v3d)
-{
-	mutex_lock(&v3d->clk_lock);
-	if (--v3d->clk_refcount == 0) {
-		schedule_delayed_work(&v3d->clk_down_work,
-			msecs_to_jiffies(100));
-	}
-	mutex_unlock(&v3d->clk_lock);
-}
-
 /* Takes the reservation lock on all the BOs being referenced, so that
  * we can attach fences and update the reservations after pushing the job
  * to the queue.
@@ -126,10 +85,9 @@ v3d_lookup_bos(struct drm_device *dev,
 }
 
 static void
-v3d_job_free_common(struct v3d_job *job,
-		    bool is_gpu_job)
+v3d_job_free(struct kref *ref)
 {
-	struct v3d_dev *v3d = job->v3d;
+	struct v3d_job *job = container_of(ref, struct v3d_job, refcount);
 	int i;
 
 	if (job->bo) {
@@ -141,29 +99,13 @@ v3d_job_free_common(struct v3d_job *job,
 	dma_fence_put(job->irq_fence);
 	dma_fence_put(job->done_fence);
 
-	if (is_gpu_job)
-		v3d_clock_up_put(v3d);
-
 	if (job->perfmon)
 		v3d_perfmon_put(job->perfmon);
 
-	kfree(job);
-}
-
-static void
-v3d_job_free(struct kref *ref)
-{
-	struct v3d_job *job = container_of(ref, struct v3d_job, refcount);
-
-	v3d_job_free_common(job, true);
-}
-
-static void
-v3d_cpu_job_free(struct kref *ref)
-{
-	struct v3d_job *job = container_of(ref, struct v3d_job, refcount);
+	if (job->has_pm_ref)
+		v3d_pm_runtime_put(job->v3d);
 
-	v3d_job_free_common(job, false);
+	kfree(job);
 }
 
 static void
@@ -244,13 +186,13 @@ v3d_job_init(struct v3d_dev *v3d, struct drm_file *file_priv,
 				if (copy_from_user(&in, handle++, sizeof(in))) {
 					ret = -EFAULT;
 					DRM_DEBUG("Failed to copy wait dep handle.\n");
-					goto fail_deps;
+					goto fail_job_init;
 				}
 				ret = drm_sched_job_add_syncobj_dependency(&job->base, file_priv, in.handle, 0);
 
 				// TODO: Investigate why this was filtered out for the IOCTL.
 				if (ret && ret != -ENOENT)
-					goto fail_deps;
+					goto fail_job_init;
 			}
 		}
 	} else {
@@ -258,16 +200,22 @@ v3d_job_init(struct v3d_dev *v3d, struct drm_file *file_priv,
 
 		// TODO: Investigate why this was filtered out for the IOCTL.
 		if (ret && ret != -ENOENT)
-			goto fail_deps;
+			goto fail_job_init;
+	}
+
+	/* CPU jobs don't require hardware resources */
+	if (queue != V3D_CPU) {
+		ret = v3d_pm_runtime_get(v3d);
+		if (ret)
+			goto fail_job_init;
+		job->has_pm_ref = true;
 	}
-	if (queue != V3D_CPU)
-		v3d_clock_up_get(v3d);
 
 	kref_init(&job->refcount);
 
 	return 0;
 
-fail_deps:
+fail_job_init:
 	drm_sched_job_cleanup(&job->base);
 	return ret;
 }
@@ -1379,7 +1327,7 @@ v3d_submit_cpu_ioctl(struct drm_device *dev, void *data,
 	trace_v3d_submit_cpu_ioctl(&v3d->drm, cpu_job->job_type);
 
 	ret = v3d_job_init(v3d, file_priv, &cpu_job->base,
-			   v3d_cpu_job_free, 0, &se, V3D_CPU);
+			   v3d_job_free, 0, &se, V3D_CPU);
 	if (ret) {
 		v3d_job_deallocate((void *)&cpu_job);
 		goto fail;
@@ -1467,14 +1415,3 @@ v3d_submit_cpu_ioctl(struct drm_device *dev, void *data,
 
 	return ret;
 }
-
-void v3d_submit_init(struct drm_device *dev) {
-	struct v3d_dev *v3d = to_v3d_dev(dev);
-
-	mutex_init(&v3d->clk_lock);
-	INIT_DELAYED_WORK(&v3d->clk_down_work, v3d_clock_down_work);
-
-	/* kick the clock so firmware knows we are using firmware clock interface */
-	v3d_clock_up_get(v3d);
-	v3d_clock_up_put(v3d);
-}
\ No newline at end of file
diff --git a/drivers/pmdomain/bcm/bcm2835-power.c b/drivers/pmdomain/bcm/bcm2835-power.c
index 71c23bfd64692b..3fde817ab6ae1a 100644
--- a/drivers/pmdomain/bcm/bcm2835-power.c
+++ b/drivers/pmdomain/bcm/bcm2835-power.c
@@ -166,8 +166,6 @@ static int bcm2835_asb_control(struct bcm2835_power *power, u32 reg, bool enable
 		break;
 	}
 
-	start = ktime_get_ns();
-
 	/* Enable the module's async AXI bridges. */
 	if (enable) {
 		val = readl(base + reg) & ~ASB_REQ_STOP;
@@ -176,9 +174,10 @@ static int bcm2835_asb_control(struct bcm2835_power *power, u32 reg, bool enable
 	}
 	writel(PM_PASSWORD | val, base + reg);
 
+	start = ktime_get_ns();
 	while (!!(readl(base + reg) & ASB_ACK) == enable) {
 		cpu_relax();
-		if (ktime_get_ns() - start >= 1000)
+		if (ktime_get_ns() - start >= 5000)
 			return -ETIMEDOUT;
 	}