12 files changed, 149 insertions, 73 deletions

diff --git a/drivers/gpu/drm/panfrost/Makefile b/drivers/gpu/drm/panfrost/Makefile
index 2c01c1e7523e..7da2b3f02ed9 100644
--- a/drivers/gpu/drm/panfrost/Makefile
+++ b/drivers/gpu/drm/panfrost/Makefile
@@ -12,6 +12,4 @@ panfrost-y := \
 	panfrost_perfcnt.o \
 	panfrost_dump.o
 
-panfrost-$(CONFIG_DEBUG_FS) += panfrost_debugfs.o
-
 obj-$(CONFIG_DRM_PANFROST) += panfrost.o
diff --git a/drivers/gpu/drm/panfrost/panfrost_debugfs.c b/drivers/gpu/drm/panfrost/panfrost_debugfs.c
deleted file mode 100644
index 72d4286a6bf7..000000000000
--- a/drivers/gpu/drm/panfrost/panfrost_debugfs.c
+++ /dev/null
@@ -1,21 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Copyright 2023 Collabora ltd. */
-/* Copyright 2023 Amazon.com, Inc. or its affiliates. */
-
-#include <linux/debugfs.h>
-#include <linux/platform_device.h>
-#include <drm/drm_debugfs.h>
-#include <drm/drm_file.h>
-#include <drm/panfrost_drm.h>
-
-#include "panfrost_device.h"
-#include "panfrost_gpu.h"
-#include "panfrost_debugfs.h"
-
-void panfrost_debugfs_init(struct drm_minor *minor)
-{
-	struct drm_device *dev = minor->dev;
-	struct panfrost_device *pfdev = platform_get_drvdata(to_platform_device(dev->dev));
-
-	debugfs_create_atomic_t("profile", 0600, minor->debugfs_root, &pfdev->profile_mode);
-}
diff --git a/drivers/gpu/drm/panfrost/panfrost_debugfs.h b/drivers/gpu/drm/panfrost/panfrost_debugfs.h
deleted file mode 100644
index c5af5f35877f..000000000000
--- a/drivers/gpu/drm/panfrost/panfrost_debugfs.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright 2023 Collabora ltd.
- * Copyright 2023 Amazon.com, Inc. or its affiliates.
- */
-
-#ifndef PANFROST_DEBUGFS_H
-#define PANFROST_DEBUGFS_H
-
-#ifdef CONFIG_DEBUG_FS
-void panfrost_debugfs_init(struct drm_minor *minor);
-#endif
-
-#endif  /* PANFROST_DEBUGFS_H */
diff --git a/drivers/gpu/drm/panfrost/panfrost_devfreq.c b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
index 2d30da38c2c3..3385fd3ef41a 100644
--- a/drivers/gpu/drm/panfrost/panfrost_devfreq.c
+++ b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
@@ -38,7 +38,7 @@ static int panfrost_devfreq_target(struct device *dev, unsigned long *freq,
 		return PTR_ERR(opp);
 	dev_pm_opp_put(opp);
 
-	err =  dev_pm_opp_set_rate(dev, *freq);
+	err = dev_pm_opp_set_rate(dev, *freq);
 	if (!err)
 		ptdev->pfdevfreq.current_frequency = *freq;
 
@@ -182,6 +182,7 @@ int panfrost_devfreq_init(struct panfrost_device *pfdev)
 	 * if any and will avoid a switch off by regulator_late_cleanup()
 	 */
 	ret = dev_pm_opp_set_opp(dev, opp);
+	dev_pm_opp_put(opp);
 	if (ret) {
 		DRM_DEV_ERROR(dev, "Couldn't set recommended OPP\n");
 		return ret;
diff --git a/drivers/gpu/drm/panfrost/panfrost_device.h b/drivers/gpu/drm/panfrost/panfrost_device.h
index 62f7e3527385..cffcb0ac7c11 100644
--- a/drivers/gpu/drm/panfrost/panfrost_device.h
+++ b/drivers/gpu/drm/panfrost/panfrost_device.h
@@ -130,7 +130,7 @@ struct panfrost_device {
 	struct list_head scheduled_jobs;
 
 	struct panfrost_perfcnt *perfcnt;
-	atomic_t profile_mode;
+	bool profile_mode;
 
 	struct mutex sched_lock;
 
diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c
index a926d71e8131..0f3935556ac7 100644
--- a/drivers/gpu/drm/panfrost/panfrost_drv.c
+++ b/drivers/gpu/drm/panfrost/panfrost_drv.c
@@ -3,6 +3,10 @@
 /* Copyright 2019 Linaro, Ltd., Rob Herring <robh@kernel.org> */
 /* Copyright 2019 Collabora ltd. */
 
+#ifdef CONFIG_ARM_ARCH_TIMER
+#include <asm/arch_timer.h>
+#endif
+
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/pagemap.h>
@@ -20,15 +24,34 @@
 #include "panfrost_job.h"
 #include "panfrost_gpu.h"
 #include "panfrost_perfcnt.h"
-#include "panfrost_debugfs.h"
+
+#define JOB_REQUIREMENTS (PANFROST_JD_REQ_FS | PANFROST_JD_REQ_CYCLE_COUNT)
 
 static bool unstable_ioctls;
 module_param_unsafe(unstable_ioctls, bool, 0600);
 
+static int panfrost_ioctl_query_timestamp(struct panfrost_device *pfdev,
+					  u64 *arg)
+{
+	int ret;
+
+	ret = pm_runtime_resume_and_get(pfdev->dev);
+	if (ret)
+		return ret;
+
+	panfrost_cycle_counter_get(pfdev);
+	*arg = panfrost_timestamp_read(pfdev);
+	panfrost_cycle_counter_put(pfdev);
+
+	pm_runtime_put(pfdev->dev);
+	return 0;
+}
+
 static int panfrost_ioctl_get_param(struct drm_device *ddev, void *data, struct drm_file *file)
 {
 	struct drm_panfrost_get_param *param = data;
 	struct panfrost_device *pfdev = ddev->dev_private;
+	int ret;
 
 	if (param->pad != 0)
 		return -EINVAL;
@@ -70,6 +93,21 @@ static int panfrost_ioctl_get_param(struct drm_device *ddev, void *data, struct
 		PANFROST_FEATURE_ARRAY(JS_FEATURES, js_features, 15);
 		PANFROST_FEATURE(NR_CORE_GROUPS, nr_core_groups);
 		PANFROST_FEATURE(THREAD_TLS_ALLOC, thread_tls_alloc);
+
+	case DRM_PANFROST_PARAM_SYSTEM_TIMESTAMP:
+		ret = panfrost_ioctl_query_timestamp(pfdev, &param->value);
+		if (ret)
+			return ret;
+		break;
+
+	case DRM_PANFROST_PARAM_SYSTEM_TIMESTAMP_FREQUENCY:
+#ifdef CONFIG_ARM_ARCH_TIMER
+		param->value = arch_timer_get_cntfrq();
+#else
+		param->value = 0;
+#endif
+		break;
+
 	default:
 		return -EINVAL;
 	}
@@ -246,7 +284,7 @@ static int panfrost_ioctl_submit(struct drm_device *dev, void *data,
 	if (!args->jc)
 		return -EINVAL;
 
-	if (args->requirements && args->requirements != PANFROST_JD_REQ_FS)
+	if (args->requirements & ~JOB_REQUIREMENTS)
 		return -EINVAL;
 
 	if (args->out_sync > 0) {
@@ -551,10 +589,12 @@ static void panfrost_gpu_show_fdinfo(struct panfrost_device *pfdev,
 	BUILD_BUG_ON(ARRAY_SIZE(engine_names) != NUM_JOB_SLOTS);
 
 	for (i = 0; i < NUM_JOB_SLOTS - 1; i++) {
-		drm_printf(p, "drm-engine-%s:\t%llu ns\n",
-			   engine_names[i], panfrost_priv->engine_usage.elapsed_ns[i]);
-		drm_printf(p, "drm-cycles-%s:\t%llu\n",
-			   engine_names[i], panfrost_priv->engine_usage.cycles[i]);
+		if (pfdev->profile_mode) {
+			drm_printf(p, "drm-engine-%s:\t%llu ns\n",
+				   engine_names[i], panfrost_priv->engine_usage.elapsed_ns[i]);
+			drm_printf(p, "drm-cycles-%s:\t%llu\n",
+				   engine_names[i], panfrost_priv->engine_usage.cycles[i]);
+		}
 		drm_printf(p, "drm-maxfreq-%s:\t%lu Hz\n",
 			   engine_names[i], pfdev->pfdevfreq.fast_rate);
 		drm_printf(p, "drm-curfreq-%s:\t%lu Hz\n",
@@ -583,6 +623,8 @@ static const struct file_operations panfrost_drm_driver_fops = {
  * - 1.0 - initial interface
  * - 1.1 - adds HEAP and NOEXEC flags for CREATE_BO
  * - 1.2 - adds AFBC_FEATURES query
+ * - 1.3 - adds JD_REQ_CYCLE_COUNT job requirement for SUBMIT
+ *       - adds SYSTEM_TIMESTAMP and SYSTEM_TIMESTAMP_FREQUENCY queries
  */
 static const struct drm_driver panfrost_drm_driver = {
 	.driver_features	= DRIVER_RENDER | DRIVER_GEM | DRIVER_SYNCOBJ,
@@ -594,16 +636,11 @@ static const struct drm_driver panfrost_drm_driver = {
 	.fops			= &panfrost_drm_driver_fops,
 	.name			= "panfrost",
 	.desc			= "panfrost DRM",
-	.date			= "20180908",
 	.major			= 1,
-	.minor			= 2,
+	.minor			= 3,
 
 	.gem_create_object	= panfrost_gem_create_object,
 	.gem_prime_import_sg_table = panfrost_gem_prime_import_sg_table,
-
-#ifdef CONFIG_DEBUG_FS
-	.debugfs_init		= panfrost_debugfs_init,
-#endif
 };
 
 static int panfrost_probe(struct platform_device *pdev)
@@ -692,6 +729,40 @@ static void panfrost_remove(struct platform_device *pdev)
 	drm_dev_put(ddev);
 }
 
+static ssize_t profiling_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	struct panfrost_device *pfdev = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%d\n", pfdev->profile_mode);
+}
+
+static ssize_t profiling_store(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf, size_t len)
+{
+	struct panfrost_device *pfdev = dev_get_drvdata(dev);
+	bool value;
+	int err;
+
+	err = kstrtobool(buf, &value);
+	if (err)
+		return err;
+
+	pfdev->profile_mode = value;
+
+	return len;
+}
+
+static DEVICE_ATTR_RW(profiling);
+
+static struct attribute *panfrost_attrs[] = {
+	&dev_attr_profiling.attr,
+	NULL,
+};
+
+ATTRIBUTE_GROUPS(panfrost);
+
 /*
  * The OPP core wants the supply names to be NULL terminated, but we need the
  * correct num_supplies value for regulator core. Hence, we NULL terminate here
@@ -746,6 +817,15 @@ static const struct panfrost_compatible mediatek_mt8186_data = {
 	.pm_features = BIT(GPU_PM_CLK_DIS) | BIT(GPU_PM_VREG_OFF),
 };
 
+/* MT8188 uses the same power domains and power supplies as MT8183 */
+static const struct panfrost_compatible mediatek_mt8188_data = {
+	.num_supplies = ARRAY_SIZE(mediatek_mt8183_b_supplies) - 1,
+	.supply_names = mediatek_mt8183_b_supplies,
+	.num_pm_domains = ARRAY_SIZE(mediatek_mt8183_pm_domains),
+	.pm_domain_names = mediatek_mt8183_pm_domains,
+	.pm_features = BIT(GPU_PM_CLK_DIS) | BIT(GPU_PM_VREG_OFF),
+};
+
 static const char * const mediatek_mt8192_supplies[] = { "mali", NULL };
 static const char * const mediatek_mt8192_pm_domains[] = { "core0", "core1", "core2",
 							   "core3", "core4" };
@@ -777,6 +857,7 @@ static const struct of_device_id dt_match[] = {
 	{ .compatible = "mediatek,mt8183-mali", .data = &mediatek_mt8183_data },
 	{ .compatible = "mediatek,mt8183b-mali", .data = &mediatek_mt8183_b_data },
 	{ .compatible = "mediatek,mt8186-mali", .data = &mediatek_mt8186_data },
+	{ .compatible = "mediatek,mt8188-mali", .data = &mediatek_mt8188_data },
 	{ .compatible = "mediatek,mt8192-mali", .data = &mediatek_mt8192_data },
 	{}
 };
@@ -784,11 +865,12 @@ MODULE_DEVICE_TABLE(of, dt_match);
 
 static struct platform_driver panfrost_driver = {
 	.probe		= panfrost_probe,
-	.remove_new	= panfrost_remove,
+	.remove		= panfrost_remove,
 	.driver		= {
 		.name	= "panfrost",
 		.pm	= pm_ptr(&panfrost_pm_ops),
 		.of_match_table = dt_match,
+		.dev_groups = panfrost_groups,
 	},
 };
 module_platform_driver(panfrost_driver);
@@ -796,3 +878,4 @@ module_platform_driver(panfrost_driver);
 MODULE_AUTHOR("Panfrost Project Developers");
 MODULE_DESCRIPTION("Panfrost DRM Driver");
 MODULE_LICENSE("GPL v2");
+MODULE_SOFTDEP("pre: governor_simpleondemand");
diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.c b/drivers/gpu/drm/panfrost/panfrost_gem.c
index d47b40b82b0b..8e0ff3efede7 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gem.c
@@ -192,7 +192,7 @@ static int panfrost_gem_pin(struct drm_gem_object *obj)
 	if (bo->is_heap)
 		return -EINVAL;
 
-	return drm_gem_shmem_pin(&bo->base);
+	return drm_gem_shmem_pin_locked(&bo->base);
 }
 
 static enum drm_gem_object_status panfrost_gem_status(struct drm_gem_object *obj)
diff --git a/drivers/gpu/drm/panfrost/panfrost_gpu.c b/drivers/gpu/drm/panfrost/panfrost_gpu.c
index 9063ce254642..174e190ba40f 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gpu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gpu.c
@@ -177,7 +177,6 @@ static void panfrost_gpu_init_quirks(struct panfrost_device *pfdev)
 struct panfrost_model {
 	const char *name;
 	u32 id;
-	u32 id_mask;
 	u64 features;
 	u64 issues;
 	struct {
@@ -237,6 +236,10 @@ static const struct panfrost_model gpu_models[] = {
 	 */
 	GPU_MODEL(g57, 0x9003,
 		GPU_REV(g57, 0, 0)),
+
+	/* MediaTek MT8188 Mali-G57 MC3 */
+	GPU_MODEL(g57, 0x9093,
+		GPU_REV(g57, 0, 0)),
 };
 
 static void panfrost_gpu_init_features(struct panfrost_device *pfdev)
@@ -380,6 +383,18 @@ unsigned long long panfrost_cycle_counter_read(struct panfrost_device *pfdev)
 	return ((u64)hi << 32) | lo;
 }
 
+unsigned long long panfrost_timestamp_read(struct panfrost_device *pfdev)
+{
+	u32 hi, lo;
+
+	do {
+		hi = gpu_read(pfdev, GPU_TIMESTAMP_HI);
+		lo = gpu_read(pfdev, GPU_TIMESTAMP_LO);
+	} while (hi != gpu_read(pfdev, GPU_TIMESTAMP_HI));
+
+	return ((u64)hi << 32) | lo;
+}
+
 static u64 panfrost_get_core_mask(struct panfrost_device *pfdev)
 {
 	u64 core_mask;
@@ -441,19 +456,19 @@ void panfrost_gpu_power_off(struct panfrost_device *pfdev)
 
 	gpu_write(pfdev, SHADER_PWROFF_LO, pfdev->features.shader_present);
 	ret = readl_relaxed_poll_timeout(pfdev->iomem + SHADER_PWRTRANS_LO,
-					 val, !val, 1, 1000);
+					 val, !val, 1, 2000);
 	if (ret)
 		dev_err(pfdev->dev, "shader power transition timeout");
 
 	gpu_write(pfdev, TILER_PWROFF_LO, pfdev->features.tiler_present);
 	ret = readl_relaxed_poll_timeout(pfdev->iomem + TILER_PWRTRANS_LO,
-					 val, !val, 1, 1000);
+					 val, !val, 1, 2000);
 	if (ret)
 		dev_err(pfdev->dev, "tiler power transition timeout");
 
 	gpu_write(pfdev, L2_PWROFF_LO, pfdev->features.l2_present);
 	ret = readl_poll_timeout(pfdev->iomem + L2_PWRTRANS_LO,
-				 val, !val, 0, 1000);
+				 val, !val, 0, 2000);
 	if (ret)
 		dev_err(pfdev->dev, "l2 power transition timeout");
 }
diff --git a/drivers/gpu/drm/panfrost/panfrost_gpu.h b/drivers/gpu/drm/panfrost/panfrost_gpu.h
index d841b86504ea..b4fef11211d5 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gpu.h
+++ b/drivers/gpu/drm/panfrost/panfrost_gpu.h
@@ -20,6 +20,7 @@ void panfrost_gpu_suspend_irq(struct panfrost_device *pfdev);
 void panfrost_cycle_counter_get(struct panfrost_device *pfdev);
 void panfrost_cycle_counter_put(struct panfrost_device *pfdev);
 unsigned long long panfrost_cycle_counter_read(struct panfrost_device *pfdev);
+unsigned long long panfrost_timestamp_read(struct panfrost_device *pfdev);
 
 void panfrost_gpu_amlogic_quirk(struct panfrost_device *pfdev);
 
diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c
index 0c2dbf6ef2a5..9b8e82fb8bc4 100644
--- a/drivers/gpu/drm/panfrost/panfrost_job.c
+++ b/drivers/gpu/drm/panfrost/panfrost_job.c
@@ -159,16 +159,17 @@ panfrost_dequeue_job(struct panfrost_device *pfdev, int slot)
 	struct panfrost_job *job = pfdev->jobs[slot][0];
 
 	WARN_ON(!job);
-	if (job->is_profiled) {
-		if (job->engine_usage) {
-			job->engine_usage->elapsed_ns[slot] +=
-				ktime_to_ns(ktime_sub(ktime_get(), job->start_time));
-			job->engine_usage->cycles[slot] +=
-				panfrost_cycle_counter_read(pfdev) - job->start_cycles;
-		}
-		panfrost_cycle_counter_put(job->pfdev);
+
+	if (job->is_profiled && job->engine_usage) {
+		job->engine_usage->elapsed_ns[slot] +=
+			ktime_to_ns(ktime_sub(ktime_get(), job->start_time));
+		job->engine_usage->cycles[slot] +=
+			panfrost_cycle_counter_read(pfdev) - job->start_cycles;
 	}
 
+	if (job->requirements & PANFROST_JD_REQ_CYCLE_COUNT || job->is_profiled)
+		panfrost_cycle_counter_put(pfdev);
+
 	pfdev->jobs[slot][0] = pfdev->jobs[slot][1];
 	pfdev->jobs[slot][1] = NULL;
 
@@ -243,9 +244,13 @@ static void panfrost_job_hw_submit(struct panfrost_job *job, int js)
 	subslot = panfrost_enqueue_job(pfdev, js, job);
 	/* Don't queue the job if a reset is in progress */
 	if (!atomic_read(&pfdev->reset.pending)) {
-		if (atomic_read(&pfdev->profile_mode)) {
+		job->is_profiled = pfdev->profile_mode;
+
+		if (job->requirements & PANFROST_JD_REQ_CYCLE_COUNT ||
+		    job->is_profiled)
 			panfrost_cycle_counter_get(pfdev);
-			job->is_profiled = true;
+
+		if (job->is_profiled) {
 			job->start_time = ktime_get();
 			job->start_cycles = panfrost_cycle_counter_read(pfdev);
 		}
@@ -693,7 +698,8 @@ panfrost_reset(struct panfrost_device *pfdev,
 	spin_lock(&pfdev->js->job_lock);
 	for (i = 0; i < NUM_JOB_SLOTS; i++) {
 		for (j = 0; j < ARRAY_SIZE(pfdev->jobs[0]) && pfdev->jobs[i][j]; j++) {
-			if (pfdev->jobs[i][j]->is_profiled)
+			if (pfdev->jobs[i][j]->requirements & PANFROST_JD_REQ_CYCLE_COUNT ||
+			    pfdev->jobs[i][j]->is_profiled)
 				panfrost_cycle_counter_put(pfdev->jobs[i][j]->pfdev);
 			pm_runtime_put_noidle(pfdev->dev);
 			panfrost_devfreq_record_idle(&pfdev->pfdevfreq);
@@ -727,7 +733,7 @@ panfrost_reset(struct panfrost_device *pfdev,
 
 	/* Restart the schedulers */
 	for (i = 0; i < NUM_JOB_SLOTS; i++)
-		drm_sched_start(&pfdev->js->queue[i].sched, true);
+		drm_sched_start(&pfdev->js->queue[i].sched, 0);
 
 	/* Re-enable job interrupts now that everything has been restarted. */
 	job_write(pfdev, JOB_INT_MASK,
diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index f38385fe76bb..b91019cd5acb 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -502,11 +502,18 @@ static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as,
 	mapping_set_unevictable(mapping);
 
 	for (i = page_offset; i < page_offset + NUM_FAULT_PAGES; i++) {
+		/* Can happen if the last fault only partially filled this
+		 * section of the pages array before failing. In that case
+		 * we skip already filled pages.
+		 */
+		if (pages[i])
+			continue;
+
 		pages[i] = shmem_read_mapping_page(mapping, i);
 		if (IS_ERR(pages[i])) {
 			ret = PTR_ERR(pages[i]);
 			pages[i] = NULL;
-			goto err_pages;
+			goto err_unlock;
 		}
 	}
 
@@ -514,7 +521,7 @@ static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as,
 	ret = sg_alloc_table_from_pages(sgt, pages + page_offset,
 					NUM_FAULT_PAGES, 0, SZ_2M, GFP_KERNEL);
 	if (ret)
-		goto err_pages;
+		goto err_unlock;
 
 	ret = dma_map_sgtable(pfdev->dev, sgt, DMA_BIDIRECTIONAL, 0);
 	if (ret)
@@ -537,8 +544,6 @@ out:
 
 err_map:
 	sg_free_table(sgt);
-err_pages:
-	drm_gem_shmem_put_pages(&bo->base);
 err_unlock:
 	dma_resv_unlock(obj->resv);
 err_bo:
diff --git a/drivers/gpu/drm/panfrost/panfrost_regs.h b/drivers/gpu/drm/panfrost/panfrost_regs.h
index c25743b05c55..c7bba476ab3f 100644
--- a/drivers/gpu/drm/panfrost/panfrost_regs.h
+++ b/drivers/gpu/drm/panfrost/panfrost_regs.h
@@ -78,6 +78,8 @@
 
 #define GPU_CYCLE_COUNT_LO		0x90
 #define GPU_CYCLE_COUNT_HI		0x94
+#define GPU_TIMESTAMP_LO		0x98
+#define GPU_TIMESTAMP_HI		0x9C
 
 #define GPU_THREAD_MAX_THREADS		0x0A0	/* (RO) Maximum number of threads per core */
 #define GPU_THREAD_MAX_WORKGROUP_SIZE	0x0A4	/* (RO) Maximum workgroup size */