1 files changed, 188 insertions, 16 deletions

diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c
index ffbbe9d527d3..e8a46c8bad8a 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.c
+++ b/drivers/gpu/drm/v3d/v3d_drv.c
@@ -17,12 +17,15 @@
 #include <linux/dma-mapping.h>
 #include <linux/io.h>
 #include <linux/module.h>
+#include <linux/of.h>
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
+#include <linux/sched/clock.h>
 #include <linux/reset.h>
 
 #include <drm/drm_drv.h>
 #include <drm/drm_managed.h>
+#include <drm/drm_print.h>
 #include <uapi/drm/v3d_drm.h>
 
 #include "v3d_drv.h"
@@ -30,14 +33,21 @@
 
 #define DRIVER_NAME "v3d"
 #define DRIVER_DESC "Broadcom V3D graphics"
-#define DRIVER_DATE "20180419"
 #define DRIVER_MAJOR 1
 #define DRIVER_MINOR 0
 #define DRIVER_PATCHLEVEL 0
 
+/* Only expose the `super_pages` modparam if THP is enabled. */
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+bool super_pages = true;
+module_param_named(super_pages, super_pages, bool, 0400);
+MODULE_PARM_DESC(super_pages, "Enable/Disable Super Pages support.");
+#endif
+
 static int v3d_get_param_ioctl(struct drm_device *dev, void *data,
 			       struct drm_file *file_priv)
 {
+	struct v3d_file_priv *v3d_priv = file_priv->driver_priv;
 	struct v3d_dev *v3d = to_v3d_dev(dev);
 	struct drm_v3d_get_param *args = data;
 	static const u32 reg_map[] = {
@@ -85,11 +95,30 @@ static int v3d_get_param_ioctl(struct drm_device *dev, void *data,
 		args->value = 1;
 		return 0;
 	case DRM_V3D_PARAM_SUPPORTS_PERFMON:
-		args->value = (v3d->ver >= 40);
+		args->value = (v3d->ver >= V3D_GEN_41);
 		return 0;
 	case DRM_V3D_PARAM_SUPPORTS_MULTISYNC_EXT:
 		args->value = 1;
 		return 0;
+	case DRM_V3D_PARAM_SUPPORTS_CPU_QUEUE:
+		args->value = 1;
+		return 0;
+	case DRM_V3D_PARAM_MAX_PERF_COUNTERS:
+		args->value = v3d->perfmon_info.max_counters;
+		return 0;
+	case DRM_V3D_PARAM_SUPPORTS_SUPER_PAGES:
+		args->value = !!v3d->gemfs;
+		return 0;
+	case DRM_V3D_PARAM_GLOBAL_RESET_COUNTER:
+		mutex_lock(&v3d->reset_lock);
+		args->value = v3d->reset_counter;
+		mutex_unlock(&v3d->reset_lock);
+		return 0;
+	case DRM_V3D_PARAM_CONTEXT_RESET_COUNTER:
+		mutex_lock(&v3d->reset_lock);
+		args->value = v3d_priv->reset_counter;
+		mutex_unlock(&v3d->reset_lock);
+		return 0;
 	default:
 		DRM_DEBUG("Unknown parameter %d\n", args->param);
 		return -EINVAL;
@@ -115,6 +144,9 @@ v3d_open(struct drm_device *dev, struct drm_file *file)
 		drm_sched_entity_init(&v3d_priv->sched_entity[i],
 				      DRM_SCHED_PRIORITY_NORMAL, &sched,
 				      1, NULL);
+
+		memset(&v3d_priv->stats[i], 0, sizeof(v3d_priv->stats[i]));
+		seqcount_init(&v3d_priv->stats[i].lock);
 	}
 
 	v3d_perfmon_open_file(v3d_priv);
@@ -126,17 +158,75 @@ v3d_open(struct drm_device *dev, struct drm_file *file)
 static void
 v3d_postclose(struct drm_device *dev, struct drm_file *file)
 {
+	struct v3d_dev *v3d = to_v3d_dev(dev);
 	struct v3d_file_priv *v3d_priv = file->driver_priv;
+	unsigned long irqflags;
 	enum v3d_queue q;
 
-	for (q = 0; q < V3D_MAX_QUEUES; q++)
+	for (q = 0; q < V3D_MAX_QUEUES; q++) {
+		struct v3d_queue_state *queue = &v3d->queue[q];
+		struct v3d_job *job = queue->active_job;
+
 		drm_sched_entity_destroy(&v3d_priv->sched_entity[q]);
 
+		if (job && job->base.entity == &v3d_priv->sched_entity[q]) {
+			spin_lock_irqsave(&queue->queue_lock, irqflags);
+			job->file_priv = NULL;
+			spin_unlock_irqrestore(&queue->queue_lock, irqflags);
+		}
+	}
+
 	v3d_perfmon_close_file(v3d_priv);
 	kfree(v3d_priv);
 }
 
-DEFINE_DRM_GEM_FOPS(v3d_drm_fops);
+void v3d_get_stats(const struct v3d_stats *stats, u64 timestamp,
+		   u64 *active_runtime, u64 *jobs_completed)
+{
+	unsigned int seq;
+
+	do {
+		seq = read_seqcount_begin(&stats->lock);
+		*active_runtime = stats->enabled_ns;
+		if (stats->start_ns)
+			*active_runtime += timestamp - stats->start_ns;
+		*jobs_completed = stats->jobs_completed;
+	} while (read_seqcount_retry(&stats->lock, seq));
+}
+
+static void v3d_show_fdinfo(struct drm_printer *p, struct drm_file *file)
+{
+	struct v3d_file_priv *file_priv = file->driver_priv;
+	u64 timestamp = local_clock();
+	enum v3d_queue queue;
+
+	for (queue = 0; queue < V3D_MAX_QUEUES; queue++) {
+		struct v3d_stats *stats = &file_priv->stats[queue];
+		u64 active_runtime, jobs_completed;
+
+		v3d_get_stats(stats, timestamp, &active_runtime, &jobs_completed);
+
+		/* Note that, in case of a GPU reset, the time spent during an
+		 * attempt of executing the job is not computed in the runtime.
+		 */
+		drm_printf(p, "drm-engine-%s: \t%llu ns\n",
+			   v3d_queue_to_string(queue), active_runtime);
+
+		/* Note that we only count jobs that completed. Therefore, jobs
+		 * that were resubmitted due to a GPU reset are not computed.
+		 */
+		drm_printf(p, "v3d-jobs-%s: \t%llu jobs\n",
+			   v3d_queue_to_string(queue), jobs_completed);
+	}
+
+	drm_show_memory_stats(p, file);
+}
+
+static const struct file_operations v3d_drm_fops = {
+	.owner = THIS_MODULE,
+	DRM_GEM_FOPS,
+	.show_fdinfo = drm_show_fdinfo,
+};
 
 /* DRM_AUTH is required on SUBMIT_CL for now, while we don't have GMP
  * protection between clients.  Note that render nodes would be
@@ -156,6 +246,9 @@ static const struct drm_ioctl_desc v3d_drm_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(V3D_PERFMON_CREATE, v3d_perfmon_create_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(V3D_PERFMON_DESTROY, v3d_perfmon_destroy_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(V3D_PERFMON_GET_VALUES, v3d_perfmon_get_values_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(V3D_SUBMIT_CPU, v3d_submit_cpu_ioctl, DRM_RENDER_ALLOW | DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(V3D_PERFMON_GET_COUNTER, v3d_perfmon_get_counter_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(V3D_PERFMON_SET_GLOBAL, v3d_perfmon_set_global_ioctl, DRM_RENDER_ALLOW),
 };
 
 static const struct drm_driver v3d_drm_driver = {
@@ -176,23 +269,54 @@ static const struct drm_driver v3d_drm_driver = {
 	.ioctls = v3d_drm_ioctls,
 	.num_ioctls = ARRAY_SIZE(v3d_drm_ioctls),
 	.fops = &v3d_drm_fops,
+	.show_fdinfo = v3d_show_fdinfo,
 
 	.name = DRIVER_NAME,
 	.desc = DRIVER_DESC,
-	.date = DRIVER_DATE,
 	.major = DRIVER_MAJOR,
 	.minor = DRIVER_MINOR,
 	.patchlevel = DRIVER_PATCHLEVEL,
 };
 
 static const struct of_device_id v3d_of_match[] = {
-	{ .compatible = "brcm,2711-v3d" },
-	{ .compatible = "brcm,7268-v3d" },
-	{ .compatible = "brcm,7278-v3d" },
+	{ .compatible = "brcm,2711-v3d", .data = (void *)V3D_GEN_42 },
+	{ .compatible = "brcm,2712-v3d", .data = (void *)V3D_GEN_71 },
+	{ .compatible = "brcm,7268-v3d", .data = (void *)V3D_GEN_33 },
+	{ .compatible = "brcm,7278-v3d", .data = (void *)V3D_GEN_41 },
 	{},
 };
 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)
 {
@@ -205,9 +329,10 @@ static int v3d_platform_drm_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct drm_device *drm;
 	struct v3d_dev *v3d;
+	enum v3d_gen gen;
 	int ret;
 	u32 mmu_debug;
-	u32 ident1;
+	u32 ident1, ident3;
 	u64 mask;
 
 	v3d = devm_drm_dev_alloc(dev, &v3d_drm_driver, struct v3d_dev, drm);
@@ -218,6 +343,9 @@ static int v3d_platform_drm_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, drm);
 
+	gen = (uintptr_t)of_device_get_match_data(dev);
+	v3d->ver = gen;
+
 	ret = map_regs(v3d, &v3d->hub_regs, "hub");
 	if (ret)
 		return ret;
@@ -226,47 +354,76 @@ static int v3d_platform_drm_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	if (v3d->ver >= V3D_GEN_71) {
+		ret = map_regs(v3d, &v3d->sms_regs, "sms");
+		if (ret)
+			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");
+		return ret;
+	}
+
+	v3d_idle_sms(v3d);
+
 	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)
-		return ret;
+		goto clk_disable;
 
 	v3d->va_width = 30 + V3D_GET_FIELD(mmu_debug, V3D_MMU_VA_WIDTH);
 
 	ident1 = V3D_READ(V3D_HUB_IDENT1);
 	v3d->ver = (V3D_GET_FIELD(ident1, V3D_HUB_IDENT1_TVER) * 10 +
 		    V3D_GET_FIELD(ident1, V3D_HUB_IDENT1_REV));
+	/* Make sure that the V3D tech version retrieved from the HW is equal
+	 * to the one advertised by the device tree.
+	 */
+	WARN_ON(v3d->ver != gen);
+
 	v3d->cores = V3D_GET_FIELD(ident1, V3D_HUB_IDENT1_NCORES);
 	WARN_ON(v3d->cores > 1); /* multicore not yet implemented */
 
+	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)
-			return ret;
+			goto clk_disable;
 
 		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");
-			return ret;
+			goto clk_disable;
 		}
 	}
 
-	if (v3d->ver < 41) {
+	if (v3d->ver < V3D_GEN_41) {
 		ret = map_regs(v3d, &v3d->gca_regs, "gca");
 		if (ret)
-			return 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");
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto clk_disable;
 	}
 
 	ret = v3d_gem_init(drm);
@@ -281,14 +438,22 @@ static int v3d_platform_drm_probe(struct platform_device *pdev)
 	if (ret)
 		goto irq_disable;
 
+	ret = v3d_sysfs_init(dev);
+	if (ret)
+		goto drm_unregister;
+
 	return 0;
 
+drm_unregister:
+	drm_dev_unregister(drm);
 irq_disable:
 	v3d_irq_disable(v3d);
 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;
 }
 
@@ -296,6 +461,9 @@ static void v3d_platform_drm_remove(struct platform_device *pdev)
 {
 	struct drm_device *drm = platform_get_drvdata(pdev);
 	struct v3d_dev *v3d = to_v3d_dev(drm);
+	struct device *dev = &pdev->dev;
+
+	v3d_sysfs_destroy(dev);
 
 	drm_dev_unregister(drm);
 
@@ -303,11 +471,15 @@ static void v3d_platform_drm_remove(struct platform_device *pdev)
 
 	dma_free_wc(v3d->drm.dev, 4096, v3d->mmu_scratch,
 		    v3d->mmu_scratch_paddr);
+
+	v3d_power_off_sms(v3d);
+
+	clk_disable_unprepare(v3d->clk);
 }
 
 static struct platform_driver v3d_platform_driver = {
 	.probe		= v3d_platform_drm_probe,
-	.remove_new	= v3d_platform_drm_remove,
+	.remove		= v3d_platform_drm_remove,
 	.driver		= {
 		.name	= "v3d",
 		.of_match_table = v3d_of_match,