[BACKPORTED] drm/v3d: Introduce Runtime Power Management

Commit 90a64ad ("drm/v3d: Get rid of pm code") removed the last
bits of power management code that V3D had, which were actually never
hooked. Therefore, currently, the GPU clock is enabled during probe
and only disabled when removing the driver.

Implement proper power management using the kernel's Runtime PM
framework.

Signed-off-by: Maíra Canal <mcanal@igalia.com>

Author: mairacanal

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
 

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),

drivers/gpu/drm/v3d/v3d_drv.c

@@ -63,6 +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;
@@ -79,12 +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;
 	}
 
@@ -291,36 +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)
 {
@@ -404,19 +382,26 @@ static int v3d_platform_drm_probe(struct platform_device *pdev)
 	if (ret)
 		goto dma_free;
 
-	ret = clk_prepare_enable(v3d->clk);
-	if (ret) {
-		dev_err(&pdev->dev, "Couldn't enable the V3D clock\n");
+	ret = devm_pm_runtime_enable(dev);
+	if (ret)
 		goto gem_destroy;
-	}
 
-	v3d_idle_sms(v3d);
+	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;
 
 	dma_set_max_seg_size(&pdev->dev, UINT_MAX);
 
@@ -437,26 +422,27 @@ static int v3d_platform_drm_probe(struct platform_device *pdev)
 	v3d->rev = V3D_GET_FIELD(ident3, V3D_HUB_IDENT3_IPREV);
 
 	v3d_init_hw_state(v3d);
-	v3d_mmu_set_page_table(v3d);
-	v3d_irq_enable(v3d);
+
+	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;
 
+	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);
-clk_disable:
-	v3d_power_off_sms(v3d);
-	clk_disable_unprepare(v3d->clk);
+runtime_pm_put:
+	pm_runtime_put_sync_suspend(dev);
 gem_destroy:
 	v3d_gem_destroy(drm);
 dma_free:
@@ -474,21 +460,27 @@ static void v3d_platform_drm_remove(struct platform_device *pdev)
 
 	drm_dev_unregister(drm);
 
-	v3d_power_off_sms(v3d);
+	pm_runtime_suspend(dev);
 
-	clk_disable_unprepare(v3d->clk);
+	/* If PM is disabled, we need to call v3d_power_suspend() manually. */
+	if (!IS_ENABLED(CONFIG_PM))
+		v3d_power_suspend(dev);
 
 	v3d_gem_destroy(drm);
 
 	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),
 	},
 };
 

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>
 
@@ -330,6 +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 {
@@ -608,6 +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);

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;
 }
 

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,
@@ -271,18 +276,23 @@ 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++)
 			perfmon->values[i] += V3D_CORE_READ(0, V3D_PCTR_0_PCTRX(i));
 
 	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);
 }