Resguardo inicial

linux-7.2.3/drivers/gpu/drm/panthor/Kconfig

@@ -0,0 +1,22 @@
+# SPDX-License-Identifier: GPL-2.0 or MIT
+
+config DRM_PANTHOR
+	tristate "Panthor (DRM support for ARM Mali CSF-based GPUs)"
+	depends on DRM
+	depends on ARM || ARM64 || COMPILE_TEST
+	depends on !GENERIC_ATOMIC64  # for IOMMU_IO_PGTABLE_LPAE
+	depends on MMU
+	select DEVFREQ_GOV_SIMPLE_ONDEMAND
+	select DRM_EXEC
+	select DRM_GPUVM
+	select DRM_SCHED
+	select IOMMU_IO_PGTABLE_LPAE
+	select IOMMU_SUPPORT
+	select PM_DEVFREQ
+	help
+	  DRM driver for ARM Mali CSF-based GPUs.
+
+	  This driver is for Mali (or Immortalis) Valhall Gxxx GPUs.
+
+	  Note that the Mali-G68 and Mali-G78, while Valhall architecture, will
+	  be supported with the panfrost driver as they are not CSF GPUs.

linux-7.2.3/drivers/gpu/drm/panthor/Makefile

@@ -0,0 +1,18 @@
+# SPDX-License-Identifier: GPL-2.0 or MIT
+
+panthor-y := \
+	panthor_devfreq.o \
+	panthor_device.o \
+	panthor_drv.o \
+	panthor_fw.o \
+	panthor_gem.o \
+	panthor_gpu.o \
+	panthor_heap.o \
+	panthor_hw.o \
+	panthor_mmu.o \
+	panthor_pwr.o \
+	panthor_sched.o
+
+obj-$(CONFIG_DRM_PANTHOR) += panthor.o
+
+CFLAGS_panthor_gpu.o := -I$(src)

linux-7.2.3/drivers/gpu/drm/panthor/panthor_devfreq.c

@@ -0,0 +1,334 @@
+// SPDX-License-Identifier: GPL-2.0 or MIT
+/* Copyright 2019 Collabora ltd. */
+
+#include <linux/clk.h>
+#include <linux/devfreq.h>
+#include <linux/devfreq_cooling.h>
+#include <linux/platform_device.h>
+#include <linux/pm_opp.h>
+
+#include <drm/drm_managed.h>
+#include <drm/drm_print.h>
+
+#include "panthor_devfreq.h"
+#include "panthor_device.h"
+
+/**
+ * struct panthor_devfreq - Device frequency management
+ */
+struct panthor_devfreq {
+	/** @devfreq: devfreq device. */
+	struct devfreq *devfreq;
+
+	/** @gov_data: Governor data. */
+	struct devfreq_simple_ondemand_data gov_data;
+
+	/** @busy_time: Busy time. */
+	ktime_t busy_time;
+
+	/** @idle_time: Idle time. */
+	ktime_t idle_time;
+
+	/** @time_last_update: Last update time. */
+	ktime_t time_last_update;
+
+	/** @last_busy_state: True if the GPU was busy last time we updated the state. */
+	bool last_busy_state;
+
+	/**
+	 * @lock: Lock used to protect busy_time, idle_time, time_last_update and
+	 * last_busy_state.
+	 *
+	 * These fields can be accessed concurrently by panthor_devfreq_get_dev_status()
+	 * and panthor_devfreq_record_{busy,idle}().
+	 */
+	spinlock_t lock;
+};
+
+static void panthor_devfreq_update_utilization(struct panthor_devfreq *pdevfreq)
+{
+	ktime_t now, last;
+
+	now = ktime_get();
+	last = pdevfreq->time_last_update;
+
+	if (pdevfreq->last_busy_state)
+		pdevfreq->busy_time += ktime_sub(now, last);
+	else
+		pdevfreq->idle_time += ktime_sub(now, last);
+
+	pdevfreq->time_last_update = now;
+}
+
+static int panthor_devfreq_target(struct device *dev, unsigned long *freq,
+				  u32 flags)
+{
+	struct dev_pm_opp *opp;
+	int err;
+
+	opp = devfreq_recommended_opp(dev, freq, flags);
+	if (IS_ERR(opp))
+		return PTR_ERR(opp);
+	dev_pm_opp_put(opp);
+
+	err = dev_pm_opp_set_rate(dev, *freq);
+
+	return err;
+}
+
+static void panthor_devfreq_reset(struct panthor_devfreq *pdevfreq)
+{
+	pdevfreq->busy_time = 0;
+	pdevfreq->idle_time = 0;
+	pdevfreq->time_last_update = ktime_get();
+}
+
+static int panthor_devfreq_get_dev_status(struct device *dev,
+					  struct devfreq_dev_status *status)
+{
+	struct panthor_device *ptdev = dev_get_drvdata(dev);
+	struct panthor_devfreq *pdevfreq = ptdev->devfreq;
+	unsigned long irqflags;
+
+	status->current_frequency = clk_get_rate(ptdev->clks.core);
+
+	spin_lock_irqsave(&pdevfreq->lock, irqflags);
+
+	panthor_devfreq_update_utilization(pdevfreq);
+
+	status->total_time = ktime_to_ns(ktime_add(pdevfreq->busy_time,
+						   pdevfreq->idle_time));
+
+	status->busy_time = ktime_to_ns(pdevfreq->busy_time);
+
+	panthor_devfreq_reset(pdevfreq);
+
+	spin_unlock_irqrestore(&pdevfreq->lock, irqflags);
+
+	drm_dbg(&ptdev->base, "busy %lu total %lu %lu %% freq %lu MHz\n",
+		status->busy_time, status->total_time,
+		status->busy_time / (status->total_time / 100),
+		status->current_frequency / 1000 / 1000);
+
+	return 0;
+}
+
+static int panthor_devfreq_get_cur_freq(struct device *dev, unsigned long *freq)
+{
+	struct panthor_device *ptdev = dev_get_drvdata(dev);
+
+	*freq = clk_get_rate(ptdev->clks.core);
+
+	return 0;
+}
+
+static struct devfreq_dev_profile panthor_devfreq_profile = {
+	.timer = DEVFREQ_TIMER_DELAYED,
+	.polling_ms = 50, /* ~3 frames */
+	.target = panthor_devfreq_target,
+	.get_dev_status = panthor_devfreq_get_dev_status,
+	.get_cur_freq = panthor_devfreq_get_cur_freq,
+};
+
+int panthor_devfreq_init(struct panthor_device *ptdev)
+{
+	/* There's actually 2 regulators (mali and sram), but the OPP core only
+	 * supports one.
+	 *
+	 * We assume the sram regulator is coupled with the mali one and let
+	 * the coupling logic deal with voltage updates.
+	 */
+	static const char * const reg_names[] = { "mali", NULL };
+	struct thermal_cooling_device *cooling;
+	struct device *dev = ptdev->base.dev;
+	struct panthor_devfreq *pdevfreq;
+	struct opp_table *table;
+	struct dev_pm_opp *opp;
+	unsigned long cur_freq;
+	unsigned long freq = ULONG_MAX;
+	int ret;
+
+	pdevfreq = drmm_kzalloc(&ptdev->base, sizeof(*ptdev->devfreq), GFP_KERNEL);
+	if (!pdevfreq)
+		return -ENOMEM;
+
+	ptdev->devfreq = pdevfreq;
+
+	/*
+	 * The power domain associated with the GPU may have already added an
+	 * OPP table, complete with OPPs, as part of the platform bus
+	 * initialization. If this is the case, the power domain is in charge of
+	 * also controlling the performance, with a set_performance callback.
+	 * Only add a new OPP table from DT if there isn't such a table present
+	 * already.
+	 */
+	table = dev_pm_opp_get_opp_table(dev);
+	if (IS_ERR_OR_NULL(table)) {
+		ret = devm_pm_opp_set_regulators(dev, reg_names);
+		if (ret && ret != -ENODEV) {
+			if (ret != -EPROBE_DEFER)
+				DRM_DEV_ERROR(dev, "Couldn't set OPP regulators\n");
+			return ret;
+		}
+
+		ret = devm_pm_opp_of_add_table(dev);
+		if (ret)
+			return ret;
+	} else {
+		dev_pm_opp_put_opp_table(table);
+	}
+
+	spin_lock_init(&pdevfreq->lock);
+
+	panthor_devfreq_reset(pdevfreq);
+
+	cur_freq = clk_get_rate(ptdev->clks.core);
+
+	/* Regulator coupling only takes care of synchronizing/balancing voltage
+	 * updates, but the coupled regulator needs to be enabled manually.
+	 *
+	 * We use devm_regulator_get_enable_optional() and keep the sram supply
+	 * enabled until the device is removed, just like we do for the mali
+	 * supply, which is enabled when dev_pm_opp_set_opp(dev, opp) is called,
+	 * and disabled when the opp_table is torn down, using the devm action.
+	 *
+	 * If we really care about disabling regulators on suspend, we should:
+	 * - use devm_regulator_get_optional() here
+	 * - call dev_pm_opp_set_opp(dev, NULL) before leaving this function
+	 *   (this disables the regulator passed to the OPP layer)
+	 * - call dev_pm_opp_set_opp(dev, NULL) and
+	 *   regulator_disable(ptdev->regulators.sram) in
+	 *   panthor_devfreq_suspend()
+	 * - call dev_pm_opp_set_opp(dev, default_opp) and
+	 *   regulator_enable(ptdev->regulators.sram) in
+	 *   panthor_devfreq_resume()
+	 *
+	 * But without knowing if it's beneficial or not (in term of power
+	 * consumption), or how much it slows down the suspend/resume steps,
+	 * let's just keep regulators enabled for the device lifetime.
+	 */
+	ret = devm_regulator_get_enable_optional(dev, "sram");
+	if (ret && ret != -ENODEV) {
+		if (ret != -EPROBE_DEFER)
+			DRM_DEV_ERROR(dev, "Couldn't retrieve/enable sram supply\n");
+		return ret;
+	}
+
+	opp = devfreq_recommended_opp(dev, &cur_freq, 0);
+	if (IS_ERR(opp))
+		return PTR_ERR(opp);
+
+	panthor_devfreq_profile.initial_freq = cur_freq;
+
+	/*
+	 * Set the recommend OPP this will enable and configure the regulator
+	 * 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;
+	}
+
+	/* Find the fastest defined rate  */
+	opp = dev_pm_opp_find_freq_floor(dev, &freq);
+	if (IS_ERR(opp))
+		return PTR_ERR(opp);
+	ptdev->fast_rate = freq;
+
+	dev_pm_opp_put(opp);
+
+	/*
+	 * Setup default thresholds for the simple_ondemand governor.
+	 * The values are chosen based on experiments.
+	 */
+	pdevfreq->gov_data.upthreshold = 45;
+	pdevfreq->gov_data.downdifferential = 5;
+
+	pdevfreq->devfreq = devm_devfreq_add_device(dev, &panthor_devfreq_profile,
+						    DEVFREQ_GOV_SIMPLE_ONDEMAND,
+						    &pdevfreq->gov_data);
+	if (IS_ERR(pdevfreq->devfreq)) {
+		DRM_DEV_ERROR(dev, "Couldn't initialize GPU devfreq\n");
+		ret = PTR_ERR(pdevfreq->devfreq);
+		pdevfreq->devfreq = NULL;
+		return ret;
+	}
+
+	cooling = devfreq_cooling_em_register(pdevfreq->devfreq, NULL);
+	if (IS_ERR(cooling))
+		DRM_DEV_INFO(dev, "Failed to register cooling device\n");
+
+	return 0;
+}
+
+void panthor_devfreq_resume(struct panthor_device *ptdev)
+{
+	struct panthor_devfreq *pdevfreq = ptdev->devfreq;
+
+	if (!pdevfreq->devfreq)
+		return;
+
+	panthor_devfreq_reset(pdevfreq);
+
+	drm_WARN_ON(&ptdev->base, devfreq_resume_device(pdevfreq->devfreq));
+}
+
+void panthor_devfreq_suspend(struct panthor_device *ptdev)
+{
+	struct panthor_devfreq *pdevfreq = ptdev->devfreq;
+
+	if (!pdevfreq->devfreq)
+		return;
+
+	drm_WARN_ON(&ptdev->base, devfreq_suspend_device(pdevfreq->devfreq));
+}
+
+void panthor_devfreq_record_busy(struct panthor_device *ptdev)
+{
+	struct panthor_devfreq *pdevfreq = ptdev->devfreq;
+	unsigned long irqflags;
+
+	if (!pdevfreq->devfreq)
+		return;
+
+	spin_lock_irqsave(&pdevfreq->lock, irqflags);
+
+	panthor_devfreq_update_utilization(pdevfreq);
+	pdevfreq->last_busy_state = true;
+
+	spin_unlock_irqrestore(&pdevfreq->lock, irqflags);
+}
+
+void panthor_devfreq_record_idle(struct panthor_device *ptdev)
+{
+	struct panthor_devfreq *pdevfreq = ptdev->devfreq;
+	unsigned long irqflags;
+
+	if (!pdevfreq->devfreq)
+		return;
+
+	spin_lock_irqsave(&pdevfreq->lock, irqflags);
+
+	panthor_devfreq_update_utilization(pdevfreq);
+	pdevfreq->last_busy_state = false;
+
+	spin_unlock_irqrestore(&pdevfreq->lock, irqflags);
+}
+
+unsigned long panthor_devfreq_get_freq(struct panthor_device *ptdev)
+{
+	struct panthor_devfreq *pdevfreq = ptdev->devfreq;
+	unsigned long freq = 0;
+	int ret;
+
+	if (!pdevfreq->devfreq)
+		return 0;
+
+	ret = pdevfreq->devfreq->profile->get_cur_freq(ptdev->base.dev, &freq);
+	if (ret)
+		return 0;
+
+	return freq;
+}

linux-7.2.3/drivers/gpu/drm/panthor/panthor_devfreq.h

@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 or MIT */
+/* Copyright 2019 Collabora ltd. */
+
+#ifndef __PANTHOR_DEVFREQ_H__
+#define __PANTHOR_DEVFREQ_H__
+
+struct devfreq;
+struct thermal_cooling_device;
+
+struct panthor_device;
+struct panthor_devfreq;
+
+int panthor_devfreq_init(struct panthor_device *ptdev);
+
+void panthor_devfreq_resume(struct panthor_device *ptdev);
+void panthor_devfreq_suspend(struct panthor_device *ptdev);
+
+void panthor_devfreq_record_busy(struct panthor_device *ptdev);
+void panthor_devfreq_record_idle(struct panthor_device *ptdev);
+
+unsigned long panthor_devfreq_get_freq(struct panthor_device *ptdev);
+
+#endif /* __PANTHOR_DEVFREQ_H__ */

linux-7.2.3/drivers/gpu/drm/panthor/panthor_device.c

@@ -0,0 +1,613 @@
+// SPDX-License-Identifier: GPL-2.0 or MIT
+/* Copyright 2018 Marty E. Plummer <hanetzer@startmail.com> */
+/* Copyright 2019 Linaro, Ltd, Rob Herring <robh@kernel.org> */
+/* Copyright 2023 Collabora ltd. */
+/* Copyright 2025 ARM Limited. All rights reserved. */
+
+#include <linux/clk.h>
+#include <linux/mm.h>
+#include <linux/platform_device.h>
+#include <linux/pm_domain.h>
+#include <linux/pm_runtime.h>
+#include <linux/regulator/consumer.h>
+#include <linux/reset.h>
+
+#include <drm/drm_drv.h>
+#include <drm/drm_managed.h>
+#include <drm/drm_print.h>
+
+#include "panthor_devfreq.h"
+#include "panthor_device.h"
+#include "panthor_fw.h"
+#include "panthor_fw_regs.h"
+#include "panthor_gem.h"
+#include "panthor_gpu.h"
+#include "panthor_hw.h"
+#include "panthor_mmu.h"
+#include "panthor_pwr.h"
+#include "panthor_sched.h"
+
+static int panthor_clk_init(struct panthor_device *ptdev)
+{
+	ptdev->clks.core = devm_clk_get(ptdev->base.dev, NULL);
+	if (IS_ERR(ptdev->clks.core))
+		return dev_err_probe(ptdev->base.dev,
+				     PTR_ERR(ptdev->clks.core),
+				     "get 'core' clock failed");
+
+	ptdev->clks.stacks = devm_clk_get_optional(ptdev->base.dev, "stacks");
+	if (IS_ERR(ptdev->clks.stacks))
+		return dev_err_probe(ptdev->base.dev,
+				     PTR_ERR(ptdev->clks.stacks),
+				     "get 'stacks' clock failed");
+
+	ptdev->clks.coregroup = devm_clk_get_optional(ptdev->base.dev, "coregroup");
+	if (IS_ERR(ptdev->clks.coregroup))
+		return dev_err_probe(ptdev->base.dev,
+				     PTR_ERR(ptdev->clks.coregroup),
+				     "get 'coregroup' clock failed");
+
+	drm_info(&ptdev->base, "clock rate = %lu\n", clk_get_rate(ptdev->clks.core));
+	return 0;
+}
+
+static int panthor_init_power(struct device *dev)
+{
+	struct dev_pm_domain_list  *pd_list = NULL;
+
+	if (dev->pm_domain)
+		return 0;
+
+	return devm_pm_domain_attach_list(dev, NULL, &pd_list);
+}
+
+void panthor_device_unplug(struct panthor_device *ptdev)
+{
+	/* This function can be called from two different path: the reset work
+	 * and the platform device remove callback. drm_dev_unplug() doesn't
+	 * deal with concurrent callers, so we have to protect drm_dev_unplug()
+	 * calls with our own lock, and bail out if the device is already
+	 * unplugged.
+	 */
+	mutex_lock(&ptdev->unplug.lock);
+	if (drm_dev_is_unplugged(&ptdev->base)) {
+		/* Someone beat us, release the lock and wait for the unplug
+		 * operation to be reported as done.
+		 **/
+		mutex_unlock(&ptdev->unplug.lock);
+		wait_for_completion(&ptdev->unplug.done);
+		return;
+	}
+
+	drm_WARN_ON(&ptdev->base, pm_runtime_get_sync(ptdev->base.dev) < 0);
+
+	/* Call drm_dev_unplug() so any access to HW blocks happening after
+	 * that point get rejected.
+	 */
+	drm_dev_unplug(&ptdev->base);
+
+	/* We do the rest of the unplug with the unplug lock released,
+	 * future callers will wait on ptdev->unplug.done anyway.
+	 */
+	mutex_unlock(&ptdev->unplug.lock);
+
+	/* Now, try to cleanly shutdown the GPU before the device resources
+	 * get reclaimed.
+	 */
+	panthor_sched_unplug(ptdev);
+	panthor_fw_unplug(ptdev);
+	panthor_mmu_unplug(ptdev);
+	panthor_gem_shrinker_unplug(ptdev);
+	panthor_gpu_unplug(ptdev);
+	panthor_pwr_unplug(ptdev);
+
+	pm_runtime_dont_use_autosuspend(ptdev->base.dev);
+	pm_runtime_put_sync_suspend(ptdev->base.dev);
+
+	/* If PM is disabled, we need to call the suspend handler manually. */
+	if (!IS_ENABLED(CONFIG_PM))
+		panthor_device_suspend(ptdev->base.dev);
+
+	/* Report the unplug operation as done to unblock concurrent
+	 * panthor_device_unplug() callers.
+	 */
+	complete_all(&ptdev->unplug.done);
+}
+
+static void panthor_device_reset_cleanup(struct drm_device *ddev, void *data)
+{
+	struct panthor_device *ptdev = container_of(ddev, struct panthor_device, base);
+
+	disable_work_sync(&ptdev->reset.work);
+	destroy_workqueue(ptdev->reset.wq);
+}
+
+static void panthor_device_reset_work(struct work_struct *work)
+{
+	struct panthor_device *ptdev = container_of(work, struct panthor_device, reset.work);
+	int ret = 0, cookie;
+
+	/* If the device is entering suspend, we don't reset. A slow reset will
+	 * be forced at resume time instead.
+	 */
+	if (atomic_read(&ptdev->pm.state) != PANTHOR_DEVICE_PM_STATE_ACTIVE)
+		return;
+
+	if (!drm_dev_enter(&ptdev->base, &cookie))
+		return;
+
+	panthor_sched_pre_reset(ptdev);
+	panthor_fw_pre_reset(ptdev, true);
+	panthor_mmu_pre_reset(ptdev);
+	panthor_hw_soft_reset(ptdev);
+	panthor_hw_l2_power_on(ptdev);
+	panthor_mmu_post_reset(ptdev);
+	ret = panthor_fw_post_reset(ptdev);
+	atomic_set(&ptdev->reset.pending, 0);
+	panthor_sched_post_reset(ptdev, ret != 0);
+	drm_dev_exit(cookie);
+
+	if (ret) {
+		panthor_device_unplug(ptdev);
+		drm_err(&ptdev->base, "Failed to boot MCU after reset, making device unusable.");
+	}
+}
+
+static bool panthor_device_is_initialized(struct panthor_device *ptdev)
+{
+	return !!ptdev->scheduler;
+}
+
+static void panthor_device_free_page(struct drm_device *ddev, void *data)
+{
+	__free_page(data);
+}
+
+int panthor_device_init(struct panthor_device *ptdev)
+{
+	u32 *dummy_page_virt;
+	struct resource *res;
+	struct page *p;
+	int ret;
+
+	ptdev->soc_data = of_device_get_match_data(ptdev->base.dev);
+
+	init_completion(&ptdev->unplug.done);
+	ret = drmm_mutex_init(&ptdev->base, &ptdev->unplug.lock);
+	if (ret)
+		return ret;
+
+	ret = drmm_mutex_init(&ptdev->base, &ptdev->pm.mmio_lock);
+	if (ret)
+		return ret;
+
+#ifdef CONFIG_DEBUG_FS
+	ret = drmm_mutex_init(&ptdev->base, &ptdev->gems.lock);
+	if (ret)
+		return ret;
+
+	INIT_LIST_HEAD(&ptdev->gems.node);
+#endif
+
+	atomic_set(&ptdev->pm.state, PANTHOR_DEVICE_PM_STATE_SUSPENDED);
+	p = alloc_page(GFP_KERNEL | __GFP_ZERO);
+	if (!p)
+		return -ENOMEM;
+
+	ptdev->pm.dummy_latest_flush = p;
+	dummy_page_virt = page_address(p);
+	ret = drmm_add_action_or_reset(&ptdev->base, panthor_device_free_page,
+				       ptdev->pm.dummy_latest_flush);
+	if (ret)
+		return ret;
+
+	/*
+	 * Set the dummy page holding the latest flush to 1. This will cause the
+	 * flush to avoided as we know it isn't necessary if the submission
+	 * happens while the dummy page is mapped. Zero cannot be used because
+	 * that means 'always flush'.
+	 */
+	*dummy_page_virt = 1;
+
+	INIT_WORK(&ptdev->reset.work, panthor_device_reset_work);
+	disable_work(&ptdev->reset.work);
+	ptdev->reset.wq = alloc_ordered_workqueue("panthor-reset-wq", 0);
+	if (!ptdev->reset.wq)
+		return -ENOMEM;
+
+	ret = drmm_add_action_or_reset(&ptdev->base, panthor_device_reset_cleanup, NULL);
+	if (ret)
+		return ret;
+
+	ret = panthor_clk_init(ptdev);
+	if (ret)
+		return ret;
+
+	ret = panthor_init_power(ptdev->base.dev);
+	if (ret < 0) {
+		drm_err(&ptdev->base, "init power domains failed, ret=%d", ret);
+		return ret;
+	}
+
+	ret = panthor_devfreq_init(ptdev);
+	if (ret)
+		return ret;
+
+	ptdev->iomem = devm_platform_get_and_ioremap_resource(to_platform_device(ptdev->base.dev),
+							      0, &res);
+	if (IS_ERR(ptdev->iomem))
+		return PTR_ERR(ptdev->iomem);
+
+	ptdev->phys_addr = res->start;
+
+	ret = devm_pm_runtime_enable(ptdev->base.dev);
+	if (ret)
+		return ret;
+
+	ret = pm_runtime_resume_and_get(ptdev->base.dev);
+	if (ret)
+		return ret;
+
+	/* If PM is disabled, we need to call panthor_device_resume() manually. */
+	if (!IS_ENABLED(CONFIG_PM)) {
+		ret = panthor_device_resume(ptdev->base.dev);
+		if (ret)
+			return ret;
+	}
+
+	ret = panthor_hw_init(ptdev);
+	if (ret)
+		goto err_rpm_put;
+
+	ret = panthor_pwr_init(ptdev);
+	if (ret)
+		goto err_rpm_put;
+
+	ret = panthor_gpu_init(ptdev);
+	if (ret)
+		goto err_unplug_pwr;
+
+	ret = panthor_gpu_coherency_init(ptdev);
+	if (ret)
+		goto err_unplug_gpu;
+
+	ret = panthor_gem_shrinker_init(ptdev);
+	if (ret)
+		goto err_unplug_gpu;
+
+	ret = panthor_mmu_init(ptdev);
+	if (ret)
+		goto err_unplug_shrinker;
+
+	ret = panthor_fw_init(ptdev);
+	if (ret)
+		goto err_unplug_mmu;
+
+	ret = panthor_sched_init(ptdev);
+	if (ret)
+		goto err_unplug_fw;
+
+	panthor_gem_init(ptdev);
+
+	/* Now that everything is initialized, we can enable the reset work. */
+	enable_work(&ptdev->reset.work);
+
+	/* ~3 frames */
+	pm_runtime_set_autosuspend_delay(ptdev->base.dev, 50);
+	pm_runtime_use_autosuspend(ptdev->base.dev);
+
+	ret = drm_dev_register(&ptdev->base, 0);
+	if (ret)
+		goto err_disable_autosuspend;
+
+	pm_runtime_put_autosuspend(ptdev->base.dev);
+	return 0;
+
+err_disable_autosuspend:
+	pm_runtime_dont_use_autosuspend(ptdev->base.dev);
+	panthor_sched_unplug(ptdev);
+
+err_unplug_fw:
+	panthor_fw_unplug(ptdev);
+
+err_unplug_mmu:
+	panthor_mmu_unplug(ptdev);
+
+err_unplug_shrinker:
+	panthor_gem_shrinker_unplug(ptdev);
+
+err_unplug_gpu:
+	panthor_gpu_unplug(ptdev);
+
+err_unplug_pwr:
+	panthor_pwr_unplug(ptdev);
+
+err_rpm_put:
+	pm_runtime_put_sync_suspend(ptdev->base.dev);
+	return ret;
+}
+
+#define PANTHOR_EXCEPTION(id) \
+	[DRM_PANTHOR_EXCEPTION_ ## id] = { \
+		.name = #id, \
+	}
+
+struct panthor_exception_info {
+	const char *name;
+};
+
+static const struct panthor_exception_info panthor_exception_infos[] = {
+	PANTHOR_EXCEPTION(OK),
+	PANTHOR_EXCEPTION(TERMINATED),
+	PANTHOR_EXCEPTION(KABOOM),
+	PANTHOR_EXCEPTION(EUREKA),
+	PANTHOR_EXCEPTION(ACTIVE),
+	PANTHOR_EXCEPTION(CS_RES_TERM),
+	PANTHOR_EXCEPTION(CS_CONFIG_FAULT),
+	PANTHOR_EXCEPTION(CS_UNRECOVERABLE),
+	PANTHOR_EXCEPTION(CS_ENDPOINT_FAULT),
+	PANTHOR_EXCEPTION(CS_BUS_FAULT),
+	PANTHOR_EXCEPTION(CS_INSTR_INVALID),
+	PANTHOR_EXCEPTION(CS_CALL_STACK_OVERFLOW),
+	PANTHOR_EXCEPTION(CS_INHERIT_FAULT),
+	PANTHOR_EXCEPTION(INSTR_INVALID_PC),
+	PANTHOR_EXCEPTION(INSTR_INVALID_ENC),
+	PANTHOR_EXCEPTION(INSTR_BARRIER_FAULT),
+	PANTHOR_EXCEPTION(DATA_INVALID_FAULT),
+	PANTHOR_EXCEPTION(TILE_RANGE_FAULT),
+	PANTHOR_EXCEPTION(ADDR_RANGE_FAULT),
+	PANTHOR_EXCEPTION(IMPRECISE_FAULT),
+	PANTHOR_EXCEPTION(OOM),
+	PANTHOR_EXCEPTION(CSF_FW_INTERNAL_ERROR),
+	PANTHOR_EXCEPTION(CSF_RES_EVICTION_TIMEOUT),
+	PANTHOR_EXCEPTION(GPU_BUS_FAULT),
+	PANTHOR_EXCEPTION(GPU_SHAREABILITY_FAULT),
+	PANTHOR_EXCEPTION(SYS_SHAREABILITY_FAULT),
+	PANTHOR_EXCEPTION(GPU_CACHEABILITY_FAULT),
+	PANTHOR_EXCEPTION(TRANSLATION_FAULT_0),
+	PANTHOR_EXCEPTION(TRANSLATION_FAULT_1),
+	PANTHOR_EXCEPTION(TRANSLATION_FAULT_2),
+	PANTHOR_EXCEPTION(TRANSLATION_FAULT_3),
+	PANTHOR_EXCEPTION(TRANSLATION_FAULT_4),
+	PANTHOR_EXCEPTION(PERM_FAULT_0),
+	PANTHOR_EXCEPTION(PERM_FAULT_1),
+	PANTHOR_EXCEPTION(PERM_FAULT_2),
+	PANTHOR_EXCEPTION(PERM_FAULT_3),
+	PANTHOR_EXCEPTION(ACCESS_FLAG_1),
+	PANTHOR_EXCEPTION(ACCESS_FLAG_2),
+	PANTHOR_EXCEPTION(ACCESS_FLAG_3),
+	PANTHOR_EXCEPTION(ADDR_SIZE_FAULT_IN),
+	PANTHOR_EXCEPTION(ADDR_SIZE_FAULT_OUT0),
+	PANTHOR_EXCEPTION(ADDR_SIZE_FAULT_OUT1),
+	PANTHOR_EXCEPTION(ADDR_SIZE_FAULT_OUT2),
+	PANTHOR_EXCEPTION(ADDR_SIZE_FAULT_OUT3),
+	PANTHOR_EXCEPTION(MEM_ATTR_FAULT_0),
+	PANTHOR_EXCEPTION(MEM_ATTR_FAULT_1),
+	PANTHOR_EXCEPTION(MEM_ATTR_FAULT_2),
+	PANTHOR_EXCEPTION(MEM_ATTR_FAULT_3),
+};
+
+const char *panthor_exception_name(struct panthor_device *ptdev, u32 exception_code)
+{
+	if (exception_code >= ARRAY_SIZE(panthor_exception_infos) ||
+	    !panthor_exception_infos[exception_code].name)
+		return "Unknown exception type";
+
+	return panthor_exception_infos[exception_code].name;
+}
+
+static vm_fault_t panthor_mmio_vm_fault(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct panthor_device *ptdev = vma->vm_private_data;
+	u64 offset = (u64)vma->vm_pgoff << PAGE_SHIFT;
+	unsigned long pfn;
+	pgprot_t pgprot;
+	vm_fault_t ret;
+	bool active;
+	int cookie;
+
+	if (!drm_dev_enter(&ptdev->base, &cookie))
+		return VM_FAULT_SIGBUS;
+
+	mutex_lock(&ptdev->pm.mmio_lock);
+	active = atomic_read(&ptdev->pm.state) == PANTHOR_DEVICE_PM_STATE_ACTIVE;
+
+	switch (offset) {
+	case DRM_PANTHOR_USER_FLUSH_ID_MMIO_OFFSET:
+		if (active)
+			pfn = __phys_to_pfn(ptdev->phys_addr + CSF_GPU_LATEST_FLUSH_ID);
+		else
+			pfn = page_to_pfn(ptdev->pm.dummy_latest_flush);
+		break;
+
+	default:
+		ret = VM_FAULT_SIGBUS;
+		goto out_unlock;
+	}
+
+	pgprot = vma->vm_page_prot;
+	if (active)
+		pgprot = pgprot_noncached(pgprot);
+
+	ret = vmf_insert_pfn_prot(vma, vmf->address, pfn, pgprot);
+
+out_unlock:
+	mutex_unlock(&ptdev->pm.mmio_lock);
+	drm_dev_exit(cookie);
+	return ret;
+}
+
+static const struct vm_operations_struct panthor_mmio_vm_ops = {
+	.fault = panthor_mmio_vm_fault,
+};
+
+int panthor_device_mmap_io(struct panthor_device *ptdev, struct vm_area_struct *vma)
+{
+	u64 offset = (u64)vma->vm_pgoff << PAGE_SHIFT;
+
+	if ((vma->vm_flags & VM_SHARED) == 0)
+		return -EINVAL;
+
+	switch (offset) {
+	case DRM_PANTHOR_USER_FLUSH_ID_MMIO_OFFSET:
+		if (vma->vm_end - vma->vm_start != PAGE_SIZE ||
+		    (vma->vm_flags & (VM_WRITE | VM_EXEC)))
+			return -EINVAL;
+		vm_flags_clear(vma, VM_MAYWRITE);
+
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	/* Defer actual mapping to the fault handler. */
+	vma->vm_private_data = ptdev;
+	vma->vm_ops = &panthor_mmio_vm_ops;
+	vm_flags_set(vma,
+		     VM_IO | VM_DONTCOPY | VM_DONTEXPAND |
+		     VM_NORESERVE | VM_DONTDUMP | VM_PFNMAP);
+	return 0;
+}
+
+static int panthor_device_resume_hw_components(struct panthor_device *ptdev)
+{
+	int ret;
+
+	panthor_pwr_resume(ptdev);
+	panthor_gpu_resume(ptdev);
+	panthor_mmu_resume(ptdev);
+
+	ret = panthor_fw_resume(ptdev);
+	if (!ret)
+		return 0;
+
+	panthor_mmu_suspend(ptdev);
+	panthor_gpu_suspend(ptdev);
+	panthor_pwr_suspend(ptdev);
+	return ret;
+}
+
+int panthor_device_resume(struct device *dev)
+{
+	struct panthor_device *ptdev = dev_get_drvdata(dev);
+	int ret, cookie;
+
+	if (atomic_read(&ptdev->pm.state) != PANTHOR_DEVICE_PM_STATE_SUSPENDED)
+		return -EINVAL;
+
+	atomic_set(&ptdev->pm.state, PANTHOR_DEVICE_PM_STATE_RESUMING);
+
+	ret = clk_prepare_enable(ptdev->clks.core);
+	if (ret)
+		goto err_set_suspended;
+
+	ret = clk_prepare_enable(ptdev->clks.stacks);
+	if (ret)
+		goto err_disable_core_clk;
+
+	ret = clk_prepare_enable(ptdev->clks.coregroup);
+	if (ret)
+		goto err_disable_stacks_clk;
+
+	panthor_devfreq_resume(ptdev);
+
+	if (panthor_device_is_initialized(ptdev) &&
+	    drm_dev_enter(&ptdev->base, &cookie)) {
+		/* If there was a reset pending at the time we suspended the
+		 * device, we force a slow reset.
+		 */
+		if (atomic_read(&ptdev->reset.pending)) {
+			ptdev->reset.fast = false;
+			atomic_set(&ptdev->reset.pending, 0);
+		}
+
+		ret = panthor_device_resume_hw_components(ptdev);
+		if (ret && ptdev->reset.fast) {
+			drm_err(&ptdev->base, "Fast reset failed, trying a slow reset");
+			ptdev->reset.fast = false;
+			ret = panthor_device_resume_hw_components(ptdev);
+		}
+
+		if (!ret)
+			panthor_sched_resume(ptdev);
+
+		drm_dev_exit(cookie);
+
+		if (ret)
+			goto err_suspend_devfreq;
+	}
+
+	/* Clear all IOMEM mappings pointing to this device after we've
+	 * resumed. This way the fake mappings pointing to the dummy pages
+	 * are removed and the real iomem mapping will be restored on next
+	 * access.
+	 */
+	mutex_lock(&ptdev->pm.mmio_lock);
+	unmap_mapping_range(ptdev->base.anon_inode->i_mapping,
+			    DRM_PANTHOR_USER_MMIO_OFFSET, 0, 1);
+	atomic_set(&ptdev->pm.state, PANTHOR_DEVICE_PM_STATE_ACTIVE);
+	mutex_unlock(&ptdev->pm.mmio_lock);
+	return 0;
+
+err_suspend_devfreq:
+	panthor_devfreq_suspend(ptdev);
+	clk_disable_unprepare(ptdev->clks.coregroup);
+
+err_disable_stacks_clk:
+	clk_disable_unprepare(ptdev->clks.stacks);
+
+err_disable_core_clk:
+	clk_disable_unprepare(ptdev->clks.core);
+
+err_set_suspended:
+	atomic_set(&ptdev->pm.state, PANTHOR_DEVICE_PM_STATE_SUSPENDED);
+	atomic_set(&ptdev->pm.recovery_needed, 1);
+	return ret;
+}
+
+int panthor_device_suspend(struct device *dev)
+{
+	struct panthor_device *ptdev = dev_get_drvdata(dev);
+	int cookie;
+
+	if (atomic_read(&ptdev->pm.state) != PANTHOR_DEVICE_PM_STATE_ACTIVE)
+		return -EINVAL;
+
+	/* Clear all IOMEM mappings pointing to this device before we
+	 * shutdown the power-domain and clocks. Failing to do that results
+	 * in external aborts when the process accesses the iomem region.
+	 * We change the state and call unmap_mapping_range() with the
+	 * mmio_lock held to make sure the vm_fault handler won't set up
+	 * invalid mappings.
+	 */
+	mutex_lock(&ptdev->pm.mmio_lock);
+	atomic_set(&ptdev->pm.state, PANTHOR_DEVICE_PM_STATE_SUSPENDING);
+	unmap_mapping_range(ptdev->base.anon_inode->i_mapping,
+			    DRM_PANTHOR_USER_MMIO_OFFSET, 0, 1);
+	mutex_unlock(&ptdev->pm.mmio_lock);
+
+	if (panthor_device_is_initialized(ptdev) &&
+	    drm_dev_enter(&ptdev->base, &cookie)) {
+		cancel_work_sync(&ptdev->reset.work);
+
+		/* We prepare everything as if we were resetting the GPU.
+		 * The end of the reset will happen in the resume path though.
+		 */
+		panthor_sched_suspend(ptdev);
+		panthor_fw_suspend(ptdev);
+		panthor_mmu_suspend(ptdev);
+		panthor_gpu_suspend(ptdev);
+		panthor_pwr_suspend(ptdev);
+		drm_dev_exit(cookie);
+	}
+
+	panthor_devfreq_suspend(ptdev);
+
+	clk_disable_unprepare(ptdev->clks.coregroup);
+	clk_disable_unprepare(ptdev->clks.stacks);
+	clk_disable_unprepare(ptdev->clks.core);
+	atomic_set(&ptdev->pm.state, PANTHOR_DEVICE_PM_STATE_SUSPENDED);
+	return 0;
+}

linux-7.2.3/drivers/gpu/drm/panthor/panthor_device.h

@@ -0,0 +1,706 @@
+/* SPDX-License-Identifier: GPL-2.0 or MIT */
+/* Copyright 2018 Marty E. Plummer <hanetzer@startmail.com> */
+/* Copyright 2019 Linaro, Ltd, Rob Herring <robh@kernel.org> */
+/* Copyright 2023 Collabora ltd. */
+
+#ifndef __PANTHOR_DEVICE_H__
+#define __PANTHOR_DEVICE_H__
+
+#include <linux/atomic.h>
+#include <linux/io-pgtable.h>
+#include <linux/regulator/consumer.h>
+#include <linux/pm_runtime.h>
+#include <linux/sched.h>
+#include <linux/spinlock.h>
+
+#include <drm/drm_device.h>
+#include <drm/drm_gem.h>
+#include <drm/drm_mm.h>
+#include <drm/gpu_scheduler.h>
+#include <drm/panthor_drm.h>
+
+struct panthor_csf;
+struct panthor_csf_ctx;
+struct panthor_device;
+struct panthor_gpu;
+struct panthor_group_pool;
+struct panthor_heap_pool;
+struct panthor_hw;
+struct panthor_job;
+struct panthor_mmu;
+struct panthor_fw;
+struct panthor_perfcnt;
+struct panthor_pwr;
+struct panthor_vm;
+struct panthor_vm_pool;
+
+/**
+ * struct panthor_soc_data - Panthor SoC Data
+ */
+struct panthor_soc_data {
+	/** @asn_hash_enable: True if GPU_L2_CONFIG_ASN_HASH_ENABLE must be set. */
+	bool asn_hash_enable;
+
+	/** @asn_hash: ASN_HASH values when asn_hash_enable is true. */
+	u32 asn_hash[3];
+};
+
+/**
+ * enum panthor_device_pm_state - PM state
+ */
+enum panthor_device_pm_state {
+	/** @PANTHOR_DEVICE_PM_STATE_SUSPENDED: Device is suspended. */
+	PANTHOR_DEVICE_PM_STATE_SUSPENDED = 0,
+
+	/** @PANTHOR_DEVICE_PM_STATE_RESUMING: Device is being resumed. */
+	PANTHOR_DEVICE_PM_STATE_RESUMING,
+
+	/** @PANTHOR_DEVICE_PM_STATE_ACTIVE: Device is active. */
+	PANTHOR_DEVICE_PM_STATE_ACTIVE,
+
+	/** @PANTHOR_DEVICE_PM_STATE_SUSPENDING: Device is being suspended. */
+	PANTHOR_DEVICE_PM_STATE_SUSPENDING,
+};
+
+enum panthor_irq_state {
+	/** @PANTHOR_IRQ_STATE_ACTIVE: IRQ is active and ready to process events. */
+	PANTHOR_IRQ_STATE_ACTIVE = 0,
+	/** @PANTHOR_IRQ_STATE_PROCESSING: IRQ is currently processing events. */
+	PANTHOR_IRQ_STATE_PROCESSING,
+	/** @PANTHOR_IRQ_STATE_SUSPENDED: IRQ is suspended. */
+	PANTHOR_IRQ_STATE_SUSPENDED,
+	/** @PANTHOR_IRQ_STATE_SUSPENDING: IRQ is being suspended. */
+	PANTHOR_IRQ_STATE_SUSPENDING,
+};
+
+/**
+ * struct panthor_irq - IRQ data
+ *
+ * Used to automate IRQ handling for the 3 different IRQs we have in this driver.
+ */
+struct panthor_irq {
+	/** @ptdev: Panthor device */
+	struct panthor_device *ptdev;
+
+	/** @iomem: CPU mapping of IRQ base address */
+	void __iomem *iomem;
+
+	/** @irq: IRQ number. */
+	int irq;
+
+	/** @mask: Values to write to xxx_INT_MASK if active. */
+	u32 mask;
+
+	/**
+	 * @mask_lock: protects modifications to _INT_MASK and @mask.
+	 *
+	 * In paths where _INT_MASK is updated based on a state
+	 * transition/check, it's crucial for the state update/check to be
+	 * inside the locked section, otherwise it introduces a race window
+	 * leading to potential _INT_MASK inconsistencies.
+	 */
+	spinlock_t mask_lock;
+
+	/** @state: one of &enum panthor_irq_state reflecting the current state. */
+	atomic_t state;
+};
+
+/**
+ * enum panthor_device_profiling_mode - Profiling state
+ */
+enum panthor_device_profiling_flags {
+	/** @PANTHOR_DEVICE_PROFILING_DISABLED: Profiling is disabled. */
+	PANTHOR_DEVICE_PROFILING_DISABLED = 0,
+
+	/** @PANTHOR_DEVICE_PROFILING_CYCLES: Sampling job cycles. */
+	PANTHOR_DEVICE_PROFILING_CYCLES = BIT(0),
+
+	/** @PANTHOR_DEVICE_PROFILING_TIMESTAMP: Sampling job timestamp. */
+	PANTHOR_DEVICE_PROFILING_TIMESTAMP = BIT(1),
+
+	/** @PANTHOR_DEVICE_PROFILING_ALL: Sampling everything. */
+	PANTHOR_DEVICE_PROFILING_ALL =
+	PANTHOR_DEVICE_PROFILING_CYCLES |
+	PANTHOR_DEVICE_PROFILING_TIMESTAMP,
+};
+
+/**
+ * struct panthor_device - Panthor device
+ */
+struct panthor_device {
+	/** @base: Base drm_device. */
+	struct drm_device base;
+
+	/** @soc_data: Optional SoC data. */
+	const struct panthor_soc_data *soc_data;
+
+	/** @phys_addr: Physical address of the iomem region. */
+	phys_addr_t phys_addr;
+
+	/** @iomem: CPU mapping of the IOMEM region. */
+	void __iomem *iomem;
+
+	/** @clks: GPU clocks. */
+	struct {
+		/** @core: Core clock. */
+		struct clk *core;
+
+		/** @stacks: Stacks clock. This clock is optional. */
+		struct clk *stacks;
+
+		/** @coregroup: Core group clock. This clock is optional. */
+		struct clk *coregroup;
+	} clks;
+
+	/** @coherent: True if the CPU/GPU are memory coherent. */
+	bool coherent;
+
+	/** @gpu_info: GPU information. */
+	struct drm_panthor_gpu_info gpu_info;
+
+	/** @csif_info: Command stream interface information. */
+	struct drm_panthor_csif_info csif_info;
+
+	/** @hw: GPU-specific data. */
+	struct panthor_hw *hw;
+
+	/** @pwr: Power control management data. */
+	struct panthor_pwr *pwr;
+
+	/** @gpu: GPU management data. */
+	struct panthor_gpu *gpu;
+
+	/** @fw: FW management data. */
+	struct panthor_fw *fw;
+
+	/** @mmu: MMU management data. */
+	struct panthor_mmu *mmu;
+
+	/** @scheduler: Scheduler management data. */
+	struct panthor_scheduler *scheduler;
+
+	/** @devfreq: Device frequency scaling management data. */
+	struct panthor_devfreq *devfreq;
+
+	/** @reclaim: Reclaim related stuff */
+	struct {
+		/** @reclaim.shrinker: Shrinker instance */
+		struct shrinker *shrinker;
+
+		/**
+		 * @reclaim.unused: BOs with unused pages
+		 *
+		 * Basically all buffers that got mmapped, vmapped or GPU mapped and
+		 * then unmapped. There should be no contention on these buffers,
+		 * making them ideal to reclaim.
+		 */
+		struct drm_gem_lru unused;
+
+		/**
+		 * @reclaim.mmapped: mmap()-ed buffers
+		 *
+		 * Those are relatively easy to reclaim since we don't need user
+		 * agreement, we can simply teardown the mapping and let it fault on
+		 * the next access.
+		 */
+		struct drm_gem_lru mmapped;
+
+		/**
+		 * @reclaim.gpu_mapped_shared: shared BO LRU list
+		 *
+		 * That's the most tricky BO type to reclaim, because it involves
+		 * tearing down all mappings in all VMs where this BO is mapped,
+		 * which increases the risk of contention and thus decreases the
+		 * likeliness of success.
+		 */
+		struct drm_gem_lru gpu_mapped_shared;
+
+		/**
+		 * @reclaim.vms: VM LRU list
+		 *
+		 * VMs that have reclaimable BOs only mapped to a single VM are placed
+		 * in this LRU. Reclaiming such BOs implies waiting for VM idleness
+		 * (no in-flight GPU jobs targeting this VM), meaning we can't reclaim
+		 * those if we're in a context where we can't block/sleep.
+		 */
+		struct list_head vms;
+
+		/**
+		 * @reclaim.gpu_mapped_count: Global counter of pages that are GPU mapped
+		 *
+		 * Allows us to get the number of reclaimable pages without walking
+		 * the vms and gpu_mapped_shared LRUs.
+		 */
+		long gpu_mapped_count;
+
+		/**
+		 * @reclaim.retry_count: Number of times we ran the shrinker without being
+		 * able to reclaim stuff
+		 *
+		 * Used to stop scanning GEMs when too many attempts were made
+		 * without progress.
+		 */
+		atomic_t retry_count;
+
+#ifdef CONFIG_DEBUG_FS
+		/**
+		 * @reclaim.nr_pages_reclaimed_on_last_scan: Number of pages reclaimed on the last
+		 * shrinker scan
+		 */
+		unsigned long nr_pages_reclaimed_on_last_scan;
+#endif
+	} reclaim;
+
+	/** @unplug: Device unplug related fields. */
+	struct {
+		/** @lock: Lock used to serialize unplug operations. */
+		struct mutex lock;
+
+		/**
+		 * @done: Completion object signaled when the unplug
+		 * operation is done.
+		 */
+		struct completion done;
+	} unplug;
+
+	/** @reset: Reset related fields. */
+	struct {
+		/** @wq: Ordered worqueud used to schedule reset operations. */
+		struct workqueue_struct *wq;
+
+		/** @work: Reset work. */
+		struct work_struct work;
+
+		/** @pending: Set to true if a reset is pending. */
+		atomic_t pending;
+
+		/**
+		 * @fast: True if the post_reset logic can proceed with a fast reset.
+		 *
+		 * A fast reset is just a reset where the driver doesn't reload the FW sections.
+		 *
+		 * Any time the firmware is properly suspended, a fast reset can take place.
+		 * On the other hand, if the halt operation failed, the driver will reload
+		 * all FW sections to make sure we start from a fresh state.
+		 */
+		bool fast;
+	} reset;
+
+	/** @pm: Power management related data. */
+	struct {
+		/** @state: Power state. */
+		atomic_t state;
+
+		/**
+		 * @mmio_lock: Lock protecting MMIO userspace CPU mappings.
+		 *
+		 * This is needed to ensure we map the dummy IO pages when
+		 * the device is being suspended, and the real IO pages when
+		 * the device is being resumed. We can't just do with the
+		 * state atomicity to deal with this race.
+		 */
+		struct mutex mmio_lock;
+
+		/**
+		 * @dummy_latest_flush: Dummy LATEST_FLUSH page.
+		 *
+		 * Used to replace the real LATEST_FLUSH page when the GPU
+		 * is suspended.
+		 */
+		struct page *dummy_latest_flush;
+
+		/** @recovery_needed: True when a resume attempt failed. */
+		atomic_t recovery_needed;
+	} pm;
+
+	/** @profile_mask: User-set profiling flags for job accounting. */
+	u32 profile_mask;
+
+	/** @fast_rate: Maximum device clock frequency. Set by DVFS */
+	unsigned long fast_rate;
+
+#ifdef CONFIG_DEBUG_FS
+	/** @gems: Device-wide list of GEM objects owned by at least one file. */
+	struct {
+		/** @gems.lock: Protects the device-wide list of GEM objects. */
+		struct mutex lock;
+
+		/** @node: Used to keep track of all the device's DRM objects */
+		struct list_head node;
+	} gems;
+#endif
+};
+
+struct panthor_gpu_usage {
+	u64 time;
+	u64 cycles;
+};
+
+/**
+ * struct panthor_file - Panthor file
+ */
+struct panthor_file {
+	/** @ptdev: Device attached to this file. */
+	struct panthor_device *ptdev;
+
+	/** @user_mmio: User MMIO related fields. */
+	struct {
+		/**
+		 * @offset: Offset used for user MMIO mappings.
+		 *
+		 * This offset should not be used to check the type of mapping
+		 * except in panthor_mmap(). After that point, MMIO mapping
+		 * offsets have been adjusted to match
+		 * DRM_PANTHOR_USER_MMIO_OFFSET and that macro should be used
+		 * instead.
+		 * Make sure this rule is followed at all times, because
+		 * userspace is in control of the offset, and can change the
+		 * value behind our back. Otherwise it can lead to erroneous
+		 * branching happening in kernel space.
+		 */
+		u64 offset;
+	} user_mmio;
+
+	/** @vms: VM pool attached to this file. */
+	struct panthor_vm_pool *vms;
+
+	/** @groups: Scheduling group pool attached to this file. */
+	struct panthor_group_pool *groups;
+
+	/** @stats: cycle and timestamp measures for job execution. */
+	struct panthor_gpu_usage stats;
+};
+
+int panthor_device_init(struct panthor_device *ptdev);
+void panthor_device_unplug(struct panthor_device *ptdev);
+
+/**
+ * panthor_device_schedule_reset() - Schedules a reset operation
+ */
+static inline void panthor_device_schedule_reset(struct panthor_device *ptdev)
+{
+	if (!atomic_cmpxchg(&ptdev->reset.pending, 0, 1) &&
+	    atomic_read(&ptdev->pm.state) == PANTHOR_DEVICE_PM_STATE_ACTIVE)
+		queue_work(ptdev->reset.wq, &ptdev->reset.work);
+}
+
+/**
+ * panthor_device_reset_is_pending() - Checks if a reset is pending.
+ *
+ * Return: true if a reset is pending, false otherwise.
+ */
+static inline bool panthor_device_reset_is_pending(struct panthor_device *ptdev)
+{
+	return atomic_read(&ptdev->reset.pending) != 0;
+}
+
+int panthor_device_mmap_io(struct panthor_device *ptdev,
+			   struct vm_area_struct *vma);
+
+int panthor_device_resume(struct device *dev);
+int panthor_device_suspend(struct device *dev);
+
+static inline int panthor_device_resume_and_get(struct panthor_device *ptdev)
+{
+	int ret = pm_runtime_resume_and_get(ptdev->base.dev);
+
+	/* If the resume failed, we need to clear the runtime_error, which
+	 * can done by forcing the RPM state to suspended. If multiple
+	 * threads called panthor_device_resume_and_get(), we only want
+	 * one of them to update the state, hence the cmpxchg. Note that a
+	 * thread might enter panthor_device_resume_and_get() and call
+	 * pm_runtime_resume_and_get() after another thread had attempted
+	 * to resume and failed. This means we will end up with an error
+	 * without even attempting a resume ourselves. The only risk here
+	 * is to report an error when the second resume attempt might have
+	 * succeeded. Given resume errors are not expected, this is probably
+	 * something we can live with.
+	 */
+	if (ret && atomic_cmpxchg(&ptdev->pm.recovery_needed, 1, 0) == 1)
+		pm_runtime_set_suspended(ptdev->base.dev);
+
+	return ret;
+}
+
+enum drm_panthor_exception_type {
+	DRM_PANTHOR_EXCEPTION_OK = 0x00,
+	DRM_PANTHOR_EXCEPTION_TERMINATED = 0x04,
+	DRM_PANTHOR_EXCEPTION_KABOOM = 0x05,
+	DRM_PANTHOR_EXCEPTION_EUREKA = 0x06,
+	DRM_PANTHOR_EXCEPTION_ACTIVE = 0x08,
+	DRM_PANTHOR_EXCEPTION_CS_RES_TERM = 0x0f,
+	DRM_PANTHOR_EXCEPTION_MAX_NON_FAULT = 0x3f,
+	DRM_PANTHOR_EXCEPTION_CS_CONFIG_FAULT = 0x40,
+	DRM_PANTHOR_EXCEPTION_CS_UNRECOVERABLE = 0x41,
+	DRM_PANTHOR_EXCEPTION_CS_ENDPOINT_FAULT = 0x44,
+	DRM_PANTHOR_EXCEPTION_CS_BUS_FAULT = 0x48,
+	DRM_PANTHOR_EXCEPTION_CS_INSTR_INVALID = 0x49,
+	DRM_PANTHOR_EXCEPTION_CS_CALL_STACK_OVERFLOW = 0x4a,
+	DRM_PANTHOR_EXCEPTION_CS_INHERIT_FAULT = 0x4b,
+	DRM_PANTHOR_EXCEPTION_INSTR_INVALID_PC = 0x50,
+	DRM_PANTHOR_EXCEPTION_INSTR_INVALID_ENC = 0x51,
+	DRM_PANTHOR_EXCEPTION_INSTR_BARRIER_FAULT = 0x55,
+	DRM_PANTHOR_EXCEPTION_DATA_INVALID_FAULT = 0x58,
+	DRM_PANTHOR_EXCEPTION_TILE_RANGE_FAULT = 0x59,
+	DRM_PANTHOR_EXCEPTION_ADDR_RANGE_FAULT = 0x5a,
+	DRM_PANTHOR_EXCEPTION_IMPRECISE_FAULT = 0x5b,
+	DRM_PANTHOR_EXCEPTION_OOM = 0x60,
+	DRM_PANTHOR_EXCEPTION_CSF_FW_INTERNAL_ERROR = 0x68,
+	DRM_PANTHOR_EXCEPTION_CSF_RES_EVICTION_TIMEOUT = 0x69,
+	DRM_PANTHOR_EXCEPTION_GPU_BUS_FAULT = 0x80,
+	DRM_PANTHOR_EXCEPTION_GPU_SHAREABILITY_FAULT = 0x88,
+	DRM_PANTHOR_EXCEPTION_SYS_SHAREABILITY_FAULT = 0x89,
+	DRM_PANTHOR_EXCEPTION_GPU_CACHEABILITY_FAULT = 0x8a,
+	DRM_PANTHOR_EXCEPTION_TRANSLATION_FAULT_0 = 0xc0,
+	DRM_PANTHOR_EXCEPTION_TRANSLATION_FAULT_1 = 0xc1,
+	DRM_PANTHOR_EXCEPTION_TRANSLATION_FAULT_2 = 0xc2,
+	DRM_PANTHOR_EXCEPTION_TRANSLATION_FAULT_3 = 0xc3,
+	DRM_PANTHOR_EXCEPTION_TRANSLATION_FAULT_4 = 0xc4,
+	DRM_PANTHOR_EXCEPTION_PERM_FAULT_0 = 0xc8,
+	DRM_PANTHOR_EXCEPTION_PERM_FAULT_1 = 0xc9,
+	DRM_PANTHOR_EXCEPTION_PERM_FAULT_2 = 0xca,
+	DRM_PANTHOR_EXCEPTION_PERM_FAULT_3 = 0xcb,
+	DRM_PANTHOR_EXCEPTION_ACCESS_FLAG_1 = 0xd9,
+	DRM_PANTHOR_EXCEPTION_ACCESS_FLAG_2 = 0xda,
+	DRM_PANTHOR_EXCEPTION_ACCESS_FLAG_3 = 0xdb,
+	DRM_PANTHOR_EXCEPTION_ADDR_SIZE_FAULT_IN = 0xe0,
+	DRM_PANTHOR_EXCEPTION_ADDR_SIZE_FAULT_OUT0 = 0xe4,
+	DRM_PANTHOR_EXCEPTION_ADDR_SIZE_FAULT_OUT1 = 0xe5,
+	DRM_PANTHOR_EXCEPTION_ADDR_SIZE_FAULT_OUT2 = 0xe6,
+	DRM_PANTHOR_EXCEPTION_ADDR_SIZE_FAULT_OUT3 = 0xe7,
+	DRM_PANTHOR_EXCEPTION_MEM_ATTR_FAULT_0 = 0xe8,
+	DRM_PANTHOR_EXCEPTION_MEM_ATTR_FAULT_1 = 0xe9,
+	DRM_PANTHOR_EXCEPTION_MEM_ATTR_FAULT_2 = 0xea,
+	DRM_PANTHOR_EXCEPTION_MEM_ATTR_FAULT_3 = 0xeb,
+};
+
+/**
+ * panthor_exception_is_fault() - Checks if an exception is a fault.
+ *
+ * Return: true if the exception is a fault, false otherwise.
+ */
+static inline bool
+panthor_exception_is_fault(u32 exception_code)
+{
+	return exception_code > DRM_PANTHOR_EXCEPTION_MAX_NON_FAULT;
+}
+
+const char *panthor_exception_name(struct panthor_device *ptdev,
+				   u32 exception_code);
+
+#define INT_RAWSTAT 0x0
+#define INT_CLEAR   0x4
+#define INT_MASK    0x8
+#define INT_STAT    0xc
+
+/**
+ * PANTHOR_IRQ_HANDLER() - Define interrupt handlers and the interrupt
+ * registration function.
+ *
+ * The boiler-plate to gracefully deal with shared interrupts is
+ * auto-generated. All you have to do is call PANTHOR_IRQ_HANDLER()
+ * just after the actual handler. The handler prototype is:
+ *
+ * void (*handler)(struct panthor_device *, u32 status);
+ */
+#define PANTHOR_IRQ_HANDLER(__name, __handler)							\
+static irqreturn_t panthor_ ## __name ## _irq_raw_handler(int irq, void *data)			\
+{												\
+	struct panthor_irq *pirq = data;							\
+	enum panthor_irq_state old_state;							\
+												\
+	guard(spinlock_irqsave)(&pirq->mask_lock);						\
+	old_state = atomic_cmpxchg(&pirq->state,						\
+				   PANTHOR_IRQ_STATE_ACTIVE,					\
+				   PANTHOR_IRQ_STATE_PROCESSING);				\
+	if (old_state != PANTHOR_IRQ_STATE_ACTIVE)						\
+		return IRQ_NONE;								\
+												\
+	if (!gpu_read(pirq->iomem, INT_STAT)) {							\
+		atomic_cmpxchg(&pirq->state,							\
+			       PANTHOR_IRQ_STATE_PROCESSING,					\
+			       PANTHOR_IRQ_STATE_ACTIVE);					\
+		return IRQ_NONE;								\
+	}											\
+												\
+	gpu_write(pirq->iomem, INT_MASK, 0);							\
+	return IRQ_WAKE_THREAD;									\
+}												\
+												\
+static irqreturn_t panthor_ ## __name ## _irq_threaded_handler(int irq, void *data)		\
+{												\
+	struct panthor_irq *pirq = data;							\
+	struct panthor_device *ptdev = pirq->ptdev;						\
+	irqreturn_t ret = IRQ_NONE;								\
+												\
+	while (true) {										\
+		/* It's safe to access pirq->mask without the lock held here. If a new		\
+		 * event gets added to the mask and the corresponding IRQ is pending,		\
+		 * we'll process it right away instead of adding an extra raw -> threaded	\
+		 * round trip. If an event is removed and the status bit is set, it will	\
+		 * be ignored, just like it would have been if the mask had been adjusted	\
+		 * right before the HW event kicks in. TLDR; it's all expected races we're	\
+		 * covered for.									\
+		 */										\
+		u32 status = gpu_read(pirq->iomem, INT_RAWSTAT) & pirq->mask;			\
+												\
+		if (!status)									\
+			break;									\
+												\
+		__handler(ptdev, status);							\
+		ret = IRQ_HANDLED;								\
+	}											\
+												\
+	scoped_guard(spinlock_irqsave, &pirq->mask_lock) {					\
+		enum panthor_irq_state old_state;						\
+												\
+		old_state = atomic_cmpxchg(&pirq->state,					\
+					   PANTHOR_IRQ_STATE_PROCESSING,			\
+					   PANTHOR_IRQ_STATE_ACTIVE);				\
+		if (old_state == PANTHOR_IRQ_STATE_PROCESSING)					\
+			gpu_write(pirq->iomem, INT_MASK, pirq->mask);				\
+	}											\
+												\
+	return ret;										\
+}												\
+												\
+static inline void panthor_ ## __name ## _irq_suspend(struct panthor_irq *pirq)			\
+{												\
+	scoped_guard(spinlock_irqsave, &pirq->mask_lock) {					\
+		atomic_set(&pirq->state, PANTHOR_IRQ_STATE_SUSPENDING);				\
+		gpu_write(pirq->iomem, INT_MASK, 0);						\
+	}											\
+	synchronize_irq(pirq->irq);								\
+	atomic_set(&pirq->state, PANTHOR_IRQ_STATE_SUSPENDED);					\
+}												\
+												\
+static inline void panthor_ ## __name ## _irq_resume(struct panthor_irq *pirq)			\
+{												\
+	guard(spinlock_irqsave)(&pirq->mask_lock);						\
+												\
+	atomic_set(&pirq->state, PANTHOR_IRQ_STATE_ACTIVE);					\
+	gpu_write(pirq->iomem, INT_CLEAR, pirq->mask);						\
+	gpu_write(pirq->iomem, INT_MASK, pirq->mask);						\
+}												\
+												\
+static int panthor_request_ ## __name ## _irq(struct panthor_device *ptdev,			\
+					      struct panthor_irq *pirq,				\
+					      int irq, void __iomem *iomem)			\
+{												\
+	pirq->ptdev = ptdev;									\
+	pirq->irq = irq;									\
+	pirq->mask = 0;										\
+	pirq->iomem = iomem;									\
+	spin_lock_init(&pirq->mask_lock);							\
+	atomic_set(&pirq->state, PANTHOR_IRQ_STATE_SUSPENDED);					\
+	gpu_write(pirq->iomem, INT_MASK, 0);							\
+												\
+	return devm_request_threaded_irq(ptdev->base.dev, irq,					\
+					 panthor_ ## __name ## _irq_raw_handler,		\
+					 panthor_ ## __name ## _irq_threaded_handler,		\
+					 IRQF_SHARED, KBUILD_MODNAME "-" # __name,		\
+					 pirq);							\
+}												\
+												\
+static inline void panthor_ ## __name ## _irq_enable_events(struct panthor_irq *pirq, u32 mask)	\
+{												\
+	guard(spinlock_irqsave)(&pirq->mask_lock);						\
+	pirq->mask |= mask;									\
+												\
+	/* The only situation where we need to write the new mask is if the IRQ is active.	\
+	 * If it's being processed, the mask will be restored for us in _irq_threaded_handler()	\
+	 * on the PROCESSING -> ACTIVE transition.						\
+	 * If the IRQ is suspended/suspending, the mask is restored at resume time.		\
+	 */											\
+	if (atomic_read(&pirq->state) == PANTHOR_IRQ_STATE_ACTIVE)				\
+		gpu_write(pirq->iomem, INT_MASK, pirq->mask);					\
+}												\
+												\
+static inline void panthor_ ## __name ## _irq_disable_events(struct panthor_irq *pirq, u32 mask)\
+{												\
+	guard(spinlock_irqsave)(&pirq->mask_lock);						\
+	pirq->mask &= ~mask;									\
+												\
+	/* The only situation where we need to write the new mask is if the IRQ is active.	\
+	 * If it's being processed, the mask will be restored for us in _irq_threaded_handler()	\
+	 * on the PROCESSING -> ACTIVE transition.						\
+	 * If the IRQ is suspended/suspending, the mask is restored at resume time.		\
+	 */											\
+	if (atomic_read(&pirq->state) == PANTHOR_IRQ_STATE_ACTIVE)				\
+		gpu_write(pirq->iomem, INT_MASK, pirq->mask);					\
+}
+
+extern struct workqueue_struct *panthor_cleanup_wq;
+
+static inline void gpu_write(void __iomem *iomem, u32 reg, u32 data)
+{
+	writel(data, iomem + reg);
+}
+
+static inline u32 gpu_read(void __iomem *iomem, u32 reg)
+{
+	return readl(iomem + reg);
+}
+
+static inline u32 gpu_read_relaxed(void __iomem *iomem, u32 reg)
+{
+	return readl_relaxed(iomem + reg);
+}
+
+static inline void gpu_write64(void __iomem *iomem, u32 reg, u64 data)
+{
+	gpu_write(iomem, reg, lower_32_bits(data));
+	gpu_write(iomem, reg + 4, upper_32_bits(data));
+}
+
+static inline u64 gpu_read64(void __iomem *iomem, u32 reg)
+{
+	return (gpu_read(iomem, reg) | ((u64)gpu_read(iomem, reg + 4) << 32));
+}
+
+static inline u64 gpu_read64_relaxed(void __iomem *iomem, u32 reg)
+{
+	return (gpu_read_relaxed(iomem, reg) |
+		((u64)gpu_read_relaxed(iomem, reg + 4) << 32));
+}
+
+static inline u64 gpu_read64_counter(void __iomem *iomem, u32 reg)
+{
+	u32 lo, hi1, hi2;
+	do {
+		hi1 = gpu_read(iomem, reg + 4);
+		lo = gpu_read(iomem, reg);
+		hi2 = gpu_read(iomem, reg + 4);
+	} while (hi1 != hi2);
+	return lo | ((u64)hi2 << 32);
+}
+
+#define gpu_read_poll_timeout(iomem, reg, val, cond, delay_us, timeout_us)	\
+	read_poll_timeout(gpu_read, val, cond, delay_us, timeout_us, false,	\
+			  iomem, reg)
+
+#define gpu_read_poll_timeout_atomic(iomem, reg, val, cond, delay_us,		\
+				     timeout_us)				\
+	read_poll_timeout_atomic(gpu_read, val, cond, delay_us, timeout_us,	\
+				 false, iomem, reg)
+
+#define gpu_read64_poll_timeout(iomem, reg, val, cond, delay_us, timeout_us)	\
+	read_poll_timeout(gpu_read64, val, cond, delay_us, timeout_us, false,	\
+			  iomem, reg)
+
+#define gpu_read64_poll_timeout_atomic(iomem, reg, val, cond, delay_us,		\
+				       timeout_us)				\
+	read_poll_timeout_atomic(gpu_read64, val, cond, delay_us, timeout_us,	\
+				 false, iomem, reg)
+
+#define gpu_read_relaxed_poll_timeout_atomic(iomem, reg, val, cond, delay_us,	\
+					     timeout_us)			\
+	read_poll_timeout_atomic(gpu_read_relaxed, val, cond, delay_us,		\
+				 timeout_us, false, iomem, reg)
+
+#define gpu_read64_relaxed_poll_timeout(iomem, reg, val, cond, delay_us,	\
+					timeout_us)				\
+	read_poll_timeout(gpu_read64_relaxed, val, cond, delay_us, timeout_us,	\
+			  false, iomem, reg)
+
+#endif

linux-7.2.3/drivers/gpu/drm/panthor/panthor_drv.h

@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 or MIT */
+/* Copyright 2025 Amazon.com, Inc. or its affiliates */
+
+#ifndef __PANTHOR_DRV_H__
+#define __PANTHOR_DRV_H__
+
+#include <linux/types.h>
+
+extern bool panthor_transparent_hugepage;
+
+#endif

linux-7.2.3/drivers/gpu/drm/panthor/panthor_fw.h

@@ -0,0 +1,532 @@
+/* SPDX-License-Identifier: GPL-2.0 or MIT */
+/* Copyright 2023 Collabora ltd. */
+
+#ifndef __PANTHOR_MCU_H__
+#define __PANTHOR_MCU_H__
+
+#include <linux/types.h>
+
+struct panthor_device;
+struct panthor_kernel_bo;
+
+#define MAX_CSGS				31
+#define MAX_CS_PER_CSG                          32
+
+struct panthor_fw_ringbuf_input_iface {
+	u64 insert;
+	u64 extract;
+};
+
+struct panthor_fw_ringbuf_output_iface {
+	u64 extract;
+	u32 active;
+};
+
+struct panthor_fw_cs_control_iface {
+#define CS_FEATURES_WORK_REGS(x)		(((x) & GENMASK(7, 0)) + 1)
+#define CS_FEATURES_SCOREBOARDS(x)		(((x) & GENMASK(15, 8)) >> 8)
+#define CS_FEATURES_COMPUTE			BIT(16)
+#define CS_FEATURES_FRAGMENT			BIT(17)
+#define CS_FEATURES_TILER			BIT(18)
+	u32 features;
+	u32 input_va;
+	u32 output_va;
+};
+
+struct panthor_fw_cs_input_iface {
+#define CS_STATE_MASK				GENMASK(2, 0)
+#define CS_STATE_STOP				0
+#define CS_STATE_START				1
+#define CS_EXTRACT_EVENT			BIT(4)
+#define CS_IDLE_SYNC_WAIT			BIT(8)
+#define CS_IDLE_PROTM_PENDING			BIT(9)
+#define CS_IDLE_EMPTY				BIT(10)
+#define CS_IDLE_RESOURCE_REQ			BIT(11)
+#define CS_TILER_OOM				BIT(26)
+#define CS_PROTM_PENDING			BIT(27)
+#define CS_FATAL				BIT(30)
+#define CS_FAULT				BIT(31)
+#define CS_REQ_MASK				(CS_STATE_MASK | \
+						 CS_EXTRACT_EVENT | \
+						 CS_IDLE_SYNC_WAIT | \
+						 CS_IDLE_PROTM_PENDING | \
+						 CS_IDLE_EMPTY | \
+						 CS_IDLE_RESOURCE_REQ)
+#define CS_EVT_MASK				(CS_TILER_OOM | \
+						 CS_PROTM_PENDING | \
+						 CS_FATAL | \
+						 CS_FAULT)
+	u32 req;
+
+#define CS_CONFIG_PRIORITY(x)			((x) & GENMASK(3, 0))
+#define CS_CONFIG_DOORBELL(x)			(((x) << 8) & GENMASK(15, 8))
+	u32 config;
+	u32 reserved1;
+	u32 ack_irq_mask;
+	u64 ringbuf_base;
+	u32 ringbuf_size;
+	u32 reserved2;
+	u64 heap_start;
+	u64 heap_end;
+	u64 ringbuf_input;
+	u64 ringbuf_output;
+	u32 instr_config;
+	u32 instrbuf_size;
+	u64 instrbuf_base;
+	u64 instrbuf_offset_ptr;
+};
+
+struct panthor_fw_cs_output_iface {
+	u32 ack;
+	u32 reserved1[15];
+	u64 status_cmd_ptr;
+
+#define CS_STATUS_WAIT_SB_MASK			GENMASK(15, 0)
+#define CS_STATUS_WAIT_SB_SRC_MASK		GENMASK(19, 16)
+#define CS_STATUS_WAIT_SB_SRC_NONE		(0 << 16)
+#define CS_STATUS_WAIT_SB_SRC_WAIT		(8 << 16)
+#define CS_STATUS_WAIT_SYNC_COND_LE		(0 << 24)
+#define CS_STATUS_WAIT_SYNC_COND_GT		(1 << 24)
+#define CS_STATUS_WAIT_SYNC_COND_MASK		GENMASK(27, 24)
+#define CS_STATUS_WAIT_PROGRESS			BIT(28)
+#define CS_STATUS_WAIT_PROTM			BIT(29)
+#define CS_STATUS_WAIT_SYNC_64B			BIT(30)
+#define CS_STATUS_WAIT_SYNC			BIT(31)
+	u32 status_wait;
+	u32 status_req_resource;
+	u64 status_wait_sync_ptr;
+	u32 status_wait_sync_value;
+	u32 status_scoreboards;
+
+#define CS_STATUS_BLOCKED_REASON_UNBLOCKED	0
+#define CS_STATUS_BLOCKED_REASON_SB_WAIT	1
+#define CS_STATUS_BLOCKED_REASON_PROGRESS_WAIT	2
+#define CS_STATUS_BLOCKED_REASON_SYNC_WAIT	3
+#define CS_STATUS_BLOCKED_REASON_DEFERRED	4
+#define CS_STATUS_BLOCKED_REASON_RESOURCE	5
+#define CS_STATUS_BLOCKED_REASON_FLUSH		6
+#define CS_STATUS_BLOCKED_REASON_MASK		GENMASK(3, 0)
+	u32 status_blocked_reason;
+	u32 status_wait_sync_value_hi;
+	u32 reserved2[6];
+
+#define CS_EXCEPTION_TYPE(x)			((x) & GENMASK(7, 0))
+#define CS_EXCEPTION_DATA(x)			(((x) >> 8) & GENMASK(23, 0))
+	u32 fault;
+	u32 fatal;
+	u64 fault_info;
+	u64 fatal_info;
+	u32 reserved3[10];
+	u32 heap_vt_start;
+	u32 heap_vt_end;
+	u32 reserved4;
+	u32 heap_frag_end;
+	u64 heap_address;
+};
+
+struct panthor_fw_csg_control_iface {
+	u32 features;
+	u32 input_va;
+	u32 output_va;
+	u32 suspend_size;
+	u32 protm_suspend_size;
+	u32 stream_num;
+	u32 stream_stride;
+};
+
+struct panthor_fw_csg_input_iface {
+#define CSG_STATE_MASK				GENMASK(2, 0)
+#define CSG_STATE_TERMINATE			0
+#define CSG_STATE_START				1
+#define CSG_STATE_SUSPEND			2
+#define CSG_STATE_RESUME			3
+#define CSG_ENDPOINT_CONFIG			BIT(4)
+#define CSG_STATUS_UPDATE			BIT(5)
+#define CSG_SYNC_UPDATE				BIT(28)
+#define CSG_IDLE				BIT(29)
+#define CSG_DOORBELL				BIT(30)
+#define CSG_PROGRESS_TIMER_EVENT		BIT(31)
+#define CSG_REQ_MASK				(CSG_STATE_MASK | \
+						 CSG_ENDPOINT_CONFIG | \
+						 CSG_STATUS_UPDATE)
+#define CSG_EVT_MASK				(CSG_SYNC_UPDATE | \
+						 CSG_IDLE | \
+						 CSG_PROGRESS_TIMER_EVENT)
+	u32 req;
+	u32 ack_irq_mask;
+
+	u32 doorbell_req;
+	u32 cs_irq_ack;
+	u32 reserved1[4];
+	u64 allow_compute;
+	u64 allow_fragment;
+	u32 allow_other;
+
+#define CSG_EP_REQ_COMPUTE(x)			((x) & GENMASK(7, 0))
+#define CSG_EP_REQ_FRAGMENT(x)			(((x) << 8) & GENMASK(15, 8))
+#define CSG_EP_REQ_TILER(x)			(((x) << 16) & GENMASK(19, 16))
+#define CSG_EP_REQ_EXCL_COMPUTE			BIT(20)
+#define CSG_EP_REQ_EXCL_FRAGMENT		BIT(21)
+#define CSG_EP_REQ_PRIORITY_MASK		GENMASK(31, 28)
+#define CSG_EP_REQ_PRIORITY(x)			(((x) << 28) & CSG_EP_REQ_PRIORITY_MASK)
+#define CSG_EP_REQ_PRIORITY_GET(x)		(((x) & CSG_EP_REQ_PRIORITY_MASK) >> 28)
+	u32 endpoint_req;
+	u64 endpoint_req2;
+	u64 suspend_buf;
+	u64 protm_suspend_buf;
+	u32 config;
+	u32 iter_trace_config;
+};
+
+struct panthor_fw_csg_output_iface {
+	u32 ack;
+	u32 reserved1;
+	u32 doorbell_ack;
+	u32 cs_irq_req;
+	u32 status_endpoint_current;
+	u32 status_endpoint_req;
+
+#define CSG_STATUS_STATE_IS_IDLE		BIT(0)
+	u32 status_state;
+	u32 resource_dep;
+};
+
+struct panthor_fw_global_control_iface {
+	u32 version;
+	u32 features;
+	u32 input_va;
+	u32 output_va;
+	u32 group_num;
+	u32 group_stride;
+	u32 perfcnt_size;
+	u32 instr_features;
+};
+
+struct panthor_fw_global_input_iface {
+#define GLB_HALT				BIT(0)
+#define GLB_CFG_PROGRESS_TIMER			BIT(1)
+#define GLB_CFG_ALLOC_EN			BIT(2)
+#define GLB_CFG_POWEROFF_TIMER			BIT(3)
+#define GLB_PROTM_ENTER				BIT(4)
+#define GLB_PERFCNT_EN				BIT(5)
+#define GLB_PERFCNT_SAMPLE			BIT(6)
+#define GLB_COUNTER_EN				BIT(7)
+#define GLB_PING				BIT(8)
+#define GLB_FWCFG_UPDATE			BIT(9)
+#define GLB_IDLE_EN				BIT(10)
+#define GLB_SLEEP				BIT(12)
+#define GLB_STATE_MASK				GENMASK(14, 12)
+#define   GLB_STATE_ACTIVE			0
+#define   GLB_STATE_HALT			1
+#define   GLB_STATE_SLEEP			2
+#define   GLB_STATE_SUSPEND			3
+#define   GLB_STATE(x)				(((x) << 12) & GLB_STATE_MASK)
+#define   GLB_STATE_GET(x)			(((x) & GLB_STATE_MASK) >> 12)
+#define GLB_INACTIVE_COMPUTE			BIT(20)
+#define GLB_INACTIVE_FRAGMENT			BIT(21)
+#define GLB_INACTIVE_TILER			BIT(22)
+#define GLB_PROTM_EXIT				BIT(23)
+#define GLB_PERFCNT_THRESHOLD			BIT(24)
+#define GLB_PERFCNT_OVERFLOW			BIT(25)
+#define GLB_IDLE				BIT(26)
+#define GLB_DBG_CSF				BIT(30)
+#define GLB_DBG_HOST				BIT(31)
+#define GLB_REQ_MASK				GENMASK(10, 0)
+#define GLB_EVT_MASK				GENMASK(26, 20)
+	u32 req;
+	u32 ack_irq_mask;
+	u32 doorbell_req;
+	u32 reserved1;
+	u32 progress_timer;
+
+#define GLB_TIMER_VAL(x)			((x) & GENMASK(30, 0))
+#define GLB_TIMER_SOURCE_GPU_COUNTER		BIT(31)
+	u32 poweroff_timer;
+	u64 core_en_mask;
+	u32 reserved2;
+	u32 perfcnt_as;
+	u64 perfcnt_base;
+	u32 perfcnt_extract;
+	u32 reserved3[3];
+	u32 perfcnt_config;
+	u32 perfcnt_csg_select;
+	u32 perfcnt_fw_enable;
+	u32 perfcnt_csg_enable;
+	u32 perfcnt_csf_enable;
+	u32 perfcnt_shader_enable;
+	u32 perfcnt_tiler_enable;
+	u32 perfcnt_mmu_l2_enable;
+	u32 reserved4[8];
+	u32 idle_timer;
+};
+
+enum panthor_fw_halt_status {
+	PANTHOR_FW_HALT_OK = 0,
+	PANTHOR_FW_HALT_ON_PANIC = 0x4e,
+	PANTHOR_FW_HALT_ON_WATCHDOG_EXPIRATION = 0x4f,
+};
+
+struct panthor_fw_global_output_iface {
+	u32 ack;
+	u32 reserved1;
+	u32 doorbell_ack;
+	u32 reserved2;
+	u32 halt_status;
+	u32 perfcnt_status;
+	u32 perfcnt_insert;
+};
+
+/**
+ * struct panthor_fw_cs_iface - Firmware command stream slot interface
+ */
+struct panthor_fw_cs_iface {
+	/**
+	 * @lock: Lock protecting access to the panthor_fw_cs_input_iface::req
+	 * field.
+	 *
+	 * Needed so we can update the req field concurrently from the interrupt
+	 * handler and the scheduler logic.
+	 *
+	 * TODO: Ideally we'd want to use a cmpxchg() to update the req, but FW
+	 * interface sections are mapped uncached/write-combined right now, and
+	 * using cmpxchg() on such mappings leads to SError faults. Revisit when
+	 * we have 'SHARED' GPU mappings hooked up.
+	 */
+	spinlock_t lock;
+
+	/**
+	 * @control: Command stream slot control interface.
+	 *
+	 * Used to expose command stream slot properties.
+	 *
+	 * This interface is read-only.
+	 */
+	struct panthor_fw_cs_control_iface *control;
+
+	/**
+	 * @input: Command stream slot input interface.
+	 *
+	 * Used for host updates/events.
+	 */
+	struct panthor_fw_cs_input_iface *input;
+
+	/**
+	 * @output: Command stream slot output interface.
+	 *
+	 * Used for FW updates/events.
+	 *
+	 * This interface is read-only.
+	 */
+	const struct panthor_fw_cs_output_iface *output;
+};
+
+/**
+ * struct panthor_fw_csg_iface - Firmware command stream group slot interface
+ */
+struct panthor_fw_csg_iface {
+	/**
+	 * @lock: Lock protecting access to the panthor_fw_csg_input_iface::req
+	 * field.
+	 *
+	 * Needed so we can update the req field concurrently from the interrupt
+	 * handler and the scheduler logic.
+	 *
+	 * TODO: Ideally we'd want to use a cmpxchg() to update the req, but FW
+	 * interface sections are mapped uncached/write-combined right now, and
+	 * using cmpxchg() on such mappings leads to SError faults. Revisit when
+	 * we have 'SHARED' GPU mappings hooked up.
+	 */
+	spinlock_t lock;
+
+	/**
+	 * @control: Command stream group slot control interface.
+	 *
+	 * Used to expose command stream group slot properties.
+	 *
+	 * This interface is read-only.
+	 */
+	const struct panthor_fw_csg_control_iface *control;
+
+	/**
+	 * @input: Command stream slot input interface.
+	 *
+	 * Used for host updates/events.
+	 */
+	struct panthor_fw_csg_input_iface *input;
+
+	/**
+	 * @output: Command stream group slot output interface.
+	 *
+	 * Used for FW updates/events.
+	 *
+	 * This interface is read-only.
+	 */
+	const struct panthor_fw_csg_output_iface *output;
+};
+
+/**
+ * struct panthor_fw_global_iface - Firmware global interface
+ */
+struct panthor_fw_global_iface {
+	/**
+	 * @lock: Lock protecting access to the panthor_fw_global_input_iface::req
+	 * field.
+	 *
+	 * Needed so we can update the req field concurrently from the interrupt
+	 * handler and the scheduler/FW management logic.
+	 *
+	 * TODO: Ideally we'd want to use a cmpxchg() to update the req, but FW
+	 * interface sections are mapped uncached/write-combined right now, and
+	 * using cmpxchg() on such mappings leads to SError faults. Revisit when
+	 * we have 'SHARED' GPU mappings hooked up.
+	 */
+	spinlock_t lock;
+
+	/**
+	 * @control: Command stream group slot control interface.
+	 *
+	 * Used to expose global FW properties.
+	 *
+	 * This interface is read-only.
+	 */
+	const struct panthor_fw_global_control_iface *control;
+
+	/**
+	 * @input: Global input interface.
+	 *
+	 * Used for host updates/events.
+	 */
+	struct panthor_fw_global_input_iface *input;
+
+	/**
+	 * @output: Global output interface.
+	 *
+	 * Used for FW updates/events.
+	 *
+	 * This interface is read-only.
+	 */
+	const struct panthor_fw_global_output_iface *output;
+};
+
+/**
+ * panthor_fw_toggle_reqs() - Toggle acknowledge bits to send an event to the FW
+ * @__iface: The interface to operate on.
+ * @__in_reg: Name of the register to update in the input section of the interface.
+ * @__out_reg: Name of the register to take as a reference in the output section of the
+ * interface.
+ * @__mask: Mask to apply to the update.
+ *
+ * The Host -> FW event/message passing was designed to be lockless, with each side of
+ * the channel having its writeable section. Events are signaled as a difference between
+ * the host and FW side in the req/ack registers (when a bit differs, there's an event
+ * pending, when they are the same, nothing needs attention).
+ *
+ * This helper allows one to update the req register based on the current value of the
+ * ack register managed by the FW. Toggling a specific bit will flag an event. In order
+ * for events to be re-evaluated, the interface doorbell needs to be rung.
+ *
+ * Concurrent accesses to the same req register is covered.
+ *
+ * Anything requiring atomic updates to multiple registers requires a dedicated lock.
+ */
+#define panthor_fw_toggle_reqs(__iface, __in_reg, __out_reg, __mask) \
+	do { \
+		u32 __cur_val, __new_val, __out_val; \
+		spin_lock(&(__iface)->lock); \
+		__cur_val = READ_ONCE((__iface)->input->__in_reg); \
+		__out_val = READ_ONCE((__iface)->output->__out_reg); \
+		__new_val = ((__out_val ^ (__mask)) & (__mask)) | (__cur_val & ~(__mask)); \
+		WRITE_ONCE((__iface)->input->__in_reg, __new_val); \
+		spin_unlock(&(__iface)->lock); \
+	} while (0)
+
+/**
+ * panthor_fw_update_reqs() - Update bits to reflect a configuration change
+ * @__iface: The interface to operate on.
+ * @__in_reg: Name of the register to update in the input section of the interface.
+ * @__val: Value to set.
+ * @__mask: Mask to apply to the update.
+ *
+ * Some configuration get passed through req registers that are also used to
+ * send events to the FW. Those req registers being updated from the interrupt
+ * handler, they require special helpers to update the configuration part as well.
+ *
+ * Concurrent accesses to the same req register is covered.
+ *
+ * Anything requiring atomic updates to multiple registers requires a dedicated lock.
+ */
+#define panthor_fw_update_reqs(__iface, __in_reg, __val, __mask) \
+	do { \
+		u32 __cur_val, __new_val; \
+		spin_lock(&(__iface)->lock); \
+		__cur_val = READ_ONCE((__iface)->input->__in_reg); \
+		__new_val = (__cur_val & ~(__mask)) | ((__val) & (__mask)); \
+		WRITE_ONCE((__iface)->input->__in_reg, __new_val); \
+		spin_unlock(&(__iface)->lock); \
+	} while (0)
+
+#define panthor_fw_update_reqs64(__iface, __in_reg, __val, __mask) \
+	do { \
+		u64 __cur_val, __new_val; \
+		spin_lock(&(__iface)->lock); \
+		__cur_val = READ_ONCE((__iface)->input->__in_reg); \
+		__new_val = (__cur_val & ~(__mask)) | ((__val) & (__mask)); \
+		WRITE_ONCE((__iface)->input->__in_reg, __new_val); \
+		spin_unlock(&(__iface)->lock); \
+	} while (0)
+
+struct panthor_fw_global_iface *
+panthor_fw_get_glb_iface(struct panthor_device *ptdev);
+
+struct panthor_fw_csg_iface *
+panthor_fw_get_csg_iface(struct panthor_device *ptdev, u32 csg_slot);
+
+struct panthor_fw_cs_iface *
+panthor_fw_get_cs_iface(struct panthor_device *ptdev, u32 csg_slot, u32 cs_slot);
+
+u64 panthor_fw_csg_endpoint_req_get(struct panthor_device *ptdev,
+				    struct panthor_fw_csg_iface *csg_iface);
+
+void panthor_fw_csg_endpoint_req_set(struct panthor_device *ptdev,
+				     struct panthor_fw_csg_iface *csg_iface, u64 value);
+
+void panthor_fw_csg_endpoint_req_update(struct panthor_device *ptdev,
+					struct panthor_fw_csg_iface *csg_iface, u64 value,
+					u64 mask);
+
+int panthor_fw_csg_wait_acks(struct panthor_device *ptdev, u32 csg_id, u32 req_mask,
+			     u32 *acked, u32 timeout_ms);
+
+int panthor_fw_glb_wait_acks(struct panthor_device *ptdev, u32 req_mask, u32 *acked,
+			     u32 timeout_ms);
+
+void panthor_fw_ring_doorbell(struct panthor_device *ptdev, u32 doorbell_id);
+void panthor_fw_ring_csg_doorbells(struct panthor_device *ptdev, u32 csg_slot);
+
+struct panthor_kernel_bo *
+panthor_fw_alloc_queue_iface_mem(struct panthor_device *ptdev,
+				 struct panthor_fw_ringbuf_input_iface **input,
+				 const struct panthor_fw_ringbuf_output_iface **output,
+				 u32 *input_fw_va, u32 *output_fw_va);
+struct panthor_kernel_bo *
+panthor_fw_alloc_suspend_buf_mem(struct panthor_device *ptdev, size_t size);
+
+struct panthor_vm *panthor_fw_vm(struct panthor_device *ptdev);
+
+void panthor_fw_pre_reset(struct panthor_device *ptdev, bool on_hang);
+int panthor_fw_post_reset(struct panthor_device *ptdev);
+
+static inline void panthor_fw_suspend(struct panthor_device *ptdev)
+{
+	panthor_fw_pre_reset(ptdev, false);
+}
+
+static inline int panthor_fw_resume(struct panthor_device *ptdev)
+{
+	return panthor_fw_post_reset(ptdev);
+}
+
+int panthor_fw_init(struct panthor_device *ptdev);
+void panthor_fw_unplug(struct panthor_device *ptdev);
+
+#endif

linux-7.2.3/drivers/gpu/drm/panthor/panthor_fw_regs.h

@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 or MIT */
+/* Copyright 2026 ARM Limited. All rights reserved. */
+
+#ifndef __PANTHOR_FW_REGS_H__
+#define __PANTHOR_FW_REGS_H__
+
+#define MCU_CONTROL_BASE				0x700
+
+#define MCU_CONTROL					0x0
+#define   MCU_CONTROL_ENABLE				1
+#define   MCU_CONTROL_AUTO				2
+#define   MCU_CONTROL_DISABLE				0
+
+#define MCU_STATUS					0x4
+#define   MCU_STATUS_DISABLED				0
+#define   MCU_STATUS_ENABLED				1
+#define   MCU_STATUS_HALT				2
+#define   MCU_STATUS_FATAL				3
+
+#define JOB_INT_BASE					0x1000
+#define   JOB_INT_GLOBAL_IF				BIT(31)
+#define   JOB_INT_CSG_IF(x)				BIT(x)
+
+#define CSF_GPU_LATEST_FLUSH_ID				0x10000
+
+#define CSF_DOORBELL(i)					(0x80000 + ((i) * 0x10000))
+#define CSF_GLB_DOORBELL_ID				0
+
+#endif /* __PANTHOR_FW_REGS_H__ */

linux-7.2.3/drivers/gpu/drm/panthor/panthor_gem.h

@@ -0,0 +1,332 @@
+/* SPDX-License-Identifier: GPL-2.0 or MIT */
+/* Copyright 2019 Linaro, Ltd, Rob Herring <robh@kernel.org> */
+/* Copyright 2023 Collabora ltd. */
+/* Copyright 2025 ARM Limited. All rights reserved. */
+
+#ifndef __PANTHOR_GEM_H__
+#define __PANTHOR_GEM_H__
+
+#include <drm/drm_gem.h>
+#include <drm/drm_mm.h>
+
+#include <linux/iosys-map.h>
+#include <linux/rwsem.h>
+
+struct panthor_vm;
+
+#define PANTHOR_BO_LABEL_MAXLEN	4096
+
+enum panthor_debugfs_gem_state_flags {
+	PANTHOR_DEBUGFS_GEM_STATE_IMPORTED_BIT = 0,
+	PANTHOR_DEBUGFS_GEM_STATE_EXPORTED_BIT = 1,
+	PANTHOR_DEBUGFS_GEM_STATE_EVICTED_BIT = 2,
+
+	/** @PANTHOR_DEBUGFS_GEM_STATE_FLAG_IMPORTED: GEM BO is PRIME imported. */
+	PANTHOR_DEBUGFS_GEM_STATE_FLAG_IMPORTED = BIT(PANTHOR_DEBUGFS_GEM_STATE_IMPORTED_BIT),
+
+	/** @PANTHOR_DEBUGFS_GEM_STATE_FLAG_EXPORTED: GEM BO is PRIME exported. */
+	PANTHOR_DEBUGFS_GEM_STATE_FLAG_EXPORTED = BIT(PANTHOR_DEBUGFS_GEM_STATE_EXPORTED_BIT),
+
+	/** @PANTHOR_DEBUGFS_GEM_STATE_FLAG_EVICTED: GEM BO is evicted to swap. */
+	PANTHOR_DEBUGFS_GEM_STATE_FLAG_EVICTED = BIT(PANTHOR_DEBUGFS_GEM_STATE_EVICTED_BIT),
+};
+
+enum panthor_debugfs_gem_usage_flags {
+	PANTHOR_DEBUGFS_GEM_USAGE_KERNEL_BIT = 0,
+	PANTHOR_DEBUGFS_GEM_USAGE_FW_MAPPED_BIT = 1,
+
+	/** @PANTHOR_DEBUGFS_GEM_USAGE_FLAG_KERNEL: BO is for kernel use only. */
+	PANTHOR_DEBUGFS_GEM_USAGE_FLAG_KERNEL = BIT(PANTHOR_DEBUGFS_GEM_USAGE_KERNEL_BIT),
+
+	/** @PANTHOR_DEBUGFS_GEM_USAGE_FLAG_FW_MAPPED: BO is mapped on the FW VM. */
+	PANTHOR_DEBUGFS_GEM_USAGE_FLAG_FW_MAPPED = BIT(PANTHOR_DEBUGFS_GEM_USAGE_FW_MAPPED_BIT),
+};
+
+/**
+ * struct panthor_gem_debugfs - GEM object's DebugFS list information
+ */
+struct panthor_gem_debugfs {
+	/**
+	 * @node: Node used to insert the object in the device-wide list of
+	 * GEM objects, to display information about it through a DebugFS file.
+	 */
+	struct list_head node;
+
+	/** @creator: Information about the UM process which created the GEM. */
+	struct {
+		/** @creator.process_name: Group leader name in owning thread's process */
+		char process_name[TASK_COMM_LEN];
+
+		/** @creator.tgid: PID of the thread's group leader within its process */
+		pid_t tgid;
+	} creator;
+
+	/** @flags: Combination of panthor_debugfs_gem_usage_flags flags */
+	u32 flags;
+};
+
+/**
+ * struct panthor_gem_backing - GEM memory backing related data
+ */
+struct panthor_gem_backing {
+	/** @pages: Pages requested with drm_gem_get_pages() */
+	struct page **pages;
+
+	/** @pin_count: Number of active pin requests on this GEM */
+	refcount_t pin_count;
+};
+
+/**
+ * struct panthor_gem_cpu_map - GEM CPU mapping related data
+ */
+struct panthor_gem_cpu_map {
+	/** @vaddr: Address returned by vmap() */
+	void *vaddr;
+
+	/** @vaddr_use_count: Number of active vmap() requests on this GEM */
+	refcount_t vaddr_use_count;
+
+	/** @mmap_count: Number of active mmap() requests on this GEM */
+	refcount_t mmap_count;
+};
+
+/**
+ * struct panthor_gem_dev_map - GEM device mapping related data
+ */
+struct panthor_gem_dev_map {
+	/** @sgt: Device mapped sg_table for this GEM */
+	struct sg_table *sgt;
+};
+
+/**
+ * enum panthor_gem_reclaim_state - Reclaim state of a GEM object
+ *
+ * This is defined in descending reclaimability order and some part
+ * of the code depends on that.
+ */
+enum panthor_gem_reclaim_state {
+	/**
+	 * @PANTHOR_GEM_UNUSED: GEM is currently unused
+	 *
+	 * This can happen when the GEM was previously vmap-ed, mmap-ed,
+	 * and/or GPU mapped and got unmapped. Because pages are lazily
+	 * returned to the shmem layer, we want to keep a list of such
+	 * BOs, because they should be fairly easy to reclaim (no need
+	 * to wait for GPU to be done, and no need to tear down user
+	 * mappings either).
+	 */
+	PANTHOR_GEM_UNUSED,
+
+	/**
+	 * @PANTHOR_GEM_MMAPPED: GEM is currently mmap-ed
+	 *
+	 * When a GEM has pages allocated and the mmap_count is > 0, the
+	 * GEM is placed in the mmapped list. This comes right after
+	 * unused because we can relatively easily tear down user mappings.
+	 */
+	PANTHOR_GEM_MMAPPED,
+
+	/**
+	 * @PANTHOR_GEM_GPU_MAPPED_SINGLE_VM: GEM is GPU mapped to only one VM
+	 *
+	 * When a GEM is mapped to a single VM, reclaim requests have more
+	 * chances to succeed, because we only need to synchronize against
+	 * a single GPU context. This is more annoying than reclaiming
+	 * mmap-ed pages still, because we have to wait for in-flight jobs
+	 * to land, and we might not be able to acquire all necessary locks
+	 * at reclaim time either.
+	 */
+	PANTHOR_GEM_GPU_MAPPED_SINGLE_VM,
+
+	/**
+	 * @PANTHOR_GEM_GPU_MAPPED_MULTI_VM: GEM is GPU mapped to multiple VMs
+	 *
+	 * Like PANTHOR_GEM_GPU_MAPPED_SINGLE_VM, but the synchronization across
+	 * VMs makes such BOs harder to reclaim.
+	 */
+	PANTHOR_GEM_GPU_MAPPED_MULTI_VM,
+
+	/**
+	 * @PANTHOR_GEM_UNRECLAIMABLE: GEM can't be reclaimed
+	 *
+	 * Happens when the GEM memory is pinned. It's also the state all GEM
+	 * objects start in, because no memory is allocated until explicitly
+	 * requested by a CPU or GPU map, meaning there's nothing to reclaim
+	 * until such an allocation happens.
+	 */
+	PANTHOR_GEM_UNRECLAIMABLE,
+};
+
+/**
+ * struct panthor_gem_object - Driver specific GEM object.
+ */
+struct panthor_gem_object {
+	/** @base: Inherit from drm_gem_object. */
+	struct drm_gem_object base;
+
+	/** @backing: Memory backing state */
+	struct panthor_gem_backing backing;
+
+	/** @cmap: CPU mapping state */
+	struct panthor_gem_cpu_map cmap;
+
+	/** @dmap: Device mapping state */
+	struct panthor_gem_dev_map dmap;
+
+	/** @reclaim_state: Cached reclaim state */
+	enum panthor_gem_reclaim_state reclaim_state;
+
+	/**
+	 * @reclaimed_count: How many times object has been evicted to swap.
+	 * The count saturates at %INT_MAX and will never wrap around to 0.
+	 */
+	atomic_t reclaimed_count;
+
+	/**
+	 * @exclusive_vm_root_gem: Root GEM of the exclusive VM this GEM object
+	 * is attached to.
+	 *
+	 * If @exclusive_vm_root_gem != NULL, any attempt to bind the GEM to a
+	 * different VM will fail.
+	 *
+	 * All FW memory objects have this field set to the root GEM of the MCU
+	 * VM.
+	 */
+	struct drm_gem_object *exclusive_vm_root_gem;
+
+	/** @flags: Combination of drm_panthor_bo_flags flags. */
+	u32 flags;
+
+	/**
+	 * @label: BO tagging fields. The label can be assigned within the
+	 * driver itself or through a specific IOCTL.
+	 */
+	struct {
+		/**
+		 * @label.str: Pointer to NULL-terminated string,
+		 */
+		const char *str;
+
+		/** @lock.str: Protects access to the @label.str field. */
+		struct mutex lock;
+	} label;
+
+#ifdef CONFIG_DEBUG_FS
+	struct panthor_gem_debugfs debugfs;
+#endif
+};
+
+/**
+ * struct panthor_kernel_bo - Kernel buffer object.
+ *
+ * These objects are only manipulated by the kernel driver and not
+ * directly exposed to the userspace. The GPU address of a kernel
+ * BO might be passed to userspace though.
+ */
+struct panthor_kernel_bo {
+	/**
+	 * @obj: The GEM object backing this kernel buffer object.
+	 */
+	struct drm_gem_object *obj;
+
+	/**
+	 * @vm: VM this private buffer is attached to.
+	 */
+	struct panthor_vm *vm;
+
+	/**
+	 * @va_node: VA space allocated to this GEM.
+	 */
+	struct drm_mm_node va_node;
+
+	/**
+	 * @kmap: Kernel CPU mapping of @gem.
+	 */
+	void *kmap;
+};
+
+#define to_panthor_bo(obj) container_of_const(obj, struct panthor_gem_object, base)
+
+void panthor_gem_init(struct panthor_device *ptdev);
+
+struct drm_gem_object *
+panthor_gem_prime_import_sg_table(struct drm_device *dev,
+				  struct dma_buf_attachment *attach,
+				  struct sg_table *sgt);
+int
+panthor_gem_create_with_handle(struct drm_file *file,
+			       struct drm_device *ddev,
+			       struct panthor_vm *exclusive_vm,
+			       u64 *size, u32 flags, uint32_t *handle);
+
+struct sg_table *
+panthor_gem_get_dev_sgt(struct panthor_gem_object *bo);
+int panthor_gem_pin(struct panthor_gem_object *bo);
+void panthor_gem_unpin(struct panthor_gem_object *bo);
+int panthor_gem_swapin_locked(struct panthor_gem_object *bo);
+void panthor_gem_update_reclaim_state_locked(struct panthor_gem_object *bo,
+					     enum panthor_gem_reclaim_state *old_state);
+int panthor_gem_shrinker_init(struct panthor_device *ptdev);
+void panthor_gem_shrinker_unplug(struct panthor_device *ptdev);
+
+void panthor_gem_bo_set_label(struct drm_gem_object *obj, const char *label);
+void panthor_gem_kernel_bo_set_label(struct panthor_kernel_bo *bo, const char *label);
+int panthor_gem_sync(struct drm_gem_object *obj,
+		     u32 type, u64 offset, u64 size);
+
+struct drm_gem_object *
+panthor_gem_prime_import(struct drm_device *dev,
+			 struct dma_buf *dma_buf);
+
+static inline u64
+panthor_kernel_bo_gpuva(struct panthor_kernel_bo *bo)
+{
+	return bo->va_node.start;
+}
+
+static inline size_t
+panthor_kernel_bo_size(struct panthor_kernel_bo *bo)
+{
+	return bo->obj->size;
+}
+
+static inline int
+panthor_kernel_bo_vmap(struct panthor_kernel_bo *bo)
+{
+	struct iosys_map map;
+	int ret;
+
+	if (bo->kmap)
+		return 0;
+
+	ret = drm_gem_vmap(bo->obj, &map);
+	if (ret)
+		return ret;
+
+	bo->kmap = map.vaddr;
+	return 0;
+}
+
+static inline void
+panthor_kernel_bo_vunmap(struct panthor_kernel_bo *bo)
+{
+	if (bo->kmap) {
+		struct iosys_map map = IOSYS_MAP_INIT_VADDR(bo->kmap);
+
+		drm_gem_vunmap(bo->obj, &map);
+		bo->kmap = NULL;
+	}
+}
+
+struct panthor_kernel_bo *
+panthor_kernel_bo_create(struct panthor_device *ptdev, struct panthor_vm *vm,
+			 size_t size, u32 bo_flags, u32 vm_map_flags,
+			 u64 gpu_va, const char *name);
+
+void panthor_kernel_bo_destroy(struct panthor_kernel_bo *bo);
+
+#ifdef CONFIG_DEBUG_FS
+void panthor_gem_debugfs_init(struct drm_minor *minor);
+#endif
+
+#endif /* __PANTHOR_GEM_H__ */

linux-7.2.3/drivers/gpu/drm/panthor/panthor_gpu.c

@@ -0,0 +1,483 @@
+// SPDX-License-Identifier: GPL-2.0 or MIT
+/* Copyright 2018 Marty E. Plummer <hanetzer@startmail.com> */
+/* Copyright 2019 Linaro, Ltd., Rob Herring <robh@kernel.org> */
+/* Copyright 2019 Collabora ltd. */
+
+#include <linux/bitfield.h>
+#include <linux/bitmap.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+
+#include <drm/drm_drv.h>
+#include <drm/drm_managed.h>
+#include <drm/drm_print.h>
+
+#include "panthor_device.h"
+#include "panthor_gpu.h"
+#include "panthor_gpu_regs.h"
+#include "panthor_hw.h"
+
+#define CREATE_TRACE_POINTS
+#include "panthor_trace.h"
+
+/**
+ * struct panthor_gpu - GPU block management data.
+ */
+struct panthor_gpu {
+	/** @iomem: CPU mapping of GPU_CONTROL iomem region */
+	void __iomem *iomem;
+
+	/** @irq: GPU irq. */
+	struct panthor_irq irq;
+
+	/** @reqs_lock: Lock protecting access to pending_reqs. */
+	spinlock_t reqs_lock;
+
+	/** @pending_reqs: Pending GPU requests. */
+	u32 pending_reqs;
+
+	/** @reqs_acked: GPU request wait queue. */
+	wait_queue_head_t reqs_acked;
+
+	/** @cache_flush_lock: Lock to serialize cache flushes */
+	struct mutex cache_flush_lock;
+};
+
+#define GPU_INTERRUPTS_MASK	\
+	(GPU_IRQ_FAULT | \
+	 GPU_IRQ_PROTM_FAULT | \
+	 GPU_IRQ_RESET_COMPLETED | \
+	 GPU_IRQ_CLEAN_CACHES_COMPLETED)
+
+#define GPU_POWER_INTERRUPTS_MASK	\
+	(GPU_IRQ_POWER_CHANGED | GPU_IRQ_POWER_CHANGED_ALL)
+
+static void panthor_gpu_coherency_set(struct panthor_device *ptdev)
+{
+	gpu_write(ptdev->gpu->iomem, GPU_COHERENCY_PROTOCOL,
+		  ptdev->gpu_info.selected_coherency);
+}
+
+static void panthor_gpu_l2_config_set(struct panthor_device *ptdev)
+{
+	struct panthor_gpu *gpu = ptdev->gpu;
+	const struct panthor_soc_data *data = ptdev->soc_data;
+	u32 l2_config;
+	u32 i;
+
+	if (!data || !data->asn_hash_enable)
+		return;
+
+	if (GPU_ARCH_MAJOR(ptdev->gpu_info.gpu_id) < 11) {
+		drm_err(&ptdev->base, "Custom ASN hash not supported by the device");
+		return;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(data->asn_hash); i++)
+		gpu_write(gpu->iomem, GPU_ASN_HASH(i), data->asn_hash[i]);
+
+	l2_config = gpu_read(gpu->iomem, GPU_L2_CONFIG);
+	l2_config |= GPU_L2_CONFIG_ASN_HASH_ENABLE;
+	gpu_write(gpu->iomem, GPU_L2_CONFIG, l2_config);
+}
+
+static void panthor_gpu_irq_handler(struct panthor_device *ptdev, u32 status)
+{
+	struct panthor_gpu *gpu = ptdev->gpu;
+
+	gpu_write(gpu->irq.iomem, INT_CLEAR, status);
+
+	if (tracepoint_enabled(gpu_power_status) && (status & GPU_POWER_INTERRUPTS_MASK))
+		trace_gpu_power_status(ptdev->base.dev,
+				       gpu_read64(gpu->iomem, SHADER_READY),
+				       gpu_read64(gpu->iomem, TILER_READY),
+				       gpu_read64(gpu->iomem, L2_READY));
+
+	if (status & GPU_IRQ_FAULT) {
+		u32 fault_status = gpu_read(gpu->iomem, GPU_FAULT_STATUS);
+		u64 address = gpu_read64(gpu->iomem, GPU_FAULT_ADDR);
+
+		drm_warn(&ptdev->base, "GPU Fault 0x%08x (%s) at 0x%016llx\n",
+			 fault_status, panthor_exception_name(ptdev, fault_status & 0xFF),
+			 address);
+	}
+	if (status & GPU_IRQ_PROTM_FAULT)
+		drm_warn(&ptdev->base, "GPU Fault in protected mode\n");
+
+	spin_lock(&ptdev->gpu->reqs_lock);
+	if (status & ptdev->gpu->pending_reqs) {
+		ptdev->gpu->pending_reqs &= ~status;
+		wake_up_all(&ptdev->gpu->reqs_acked);
+	}
+	spin_unlock(&ptdev->gpu->reqs_lock);
+}
+PANTHOR_IRQ_HANDLER(gpu, panthor_gpu_irq_handler);
+
+/**
+ * panthor_gpu_unplug() - Called when the GPU is unplugged.
+ * @ptdev: Device to unplug.
+ */
+void panthor_gpu_unplug(struct panthor_device *ptdev)
+{
+	unsigned long flags;
+
+	/* Make sure the IRQ handler is not running after that point. */
+	if (!IS_ENABLED(CONFIG_PM) || pm_runtime_active(ptdev->base.dev))
+		panthor_gpu_irq_suspend(&ptdev->gpu->irq);
+
+	/* Wake-up all waiters. */
+	spin_lock_irqsave(&ptdev->gpu->reqs_lock, flags);
+	ptdev->gpu->pending_reqs = 0;
+	wake_up_all(&ptdev->gpu->reqs_acked);
+	spin_unlock_irqrestore(&ptdev->gpu->reqs_lock, flags);
+}
+
+/**
+ * panthor_gpu_init() - Initialize the GPU block
+ * @ptdev: Device.
+ *
+ * Return: 0 on success, a negative error code otherwise.
+ */
+int panthor_gpu_init(struct panthor_device *ptdev)
+{
+	struct panthor_gpu *gpu;
+	u32 pa_bits;
+	int ret, irq;
+
+	gpu = drmm_kzalloc(&ptdev->base, sizeof(*gpu), GFP_KERNEL);
+	if (!gpu)
+		return -ENOMEM;
+
+	gpu->iomem = ptdev->iomem + GPU_CONTROL_BASE;
+	spin_lock_init(&gpu->reqs_lock);
+	init_waitqueue_head(&gpu->reqs_acked);
+	mutex_init(&gpu->cache_flush_lock);
+	ptdev->gpu = gpu;
+
+	dma_set_max_seg_size(ptdev->base.dev, UINT_MAX);
+	pa_bits = GPU_MMU_FEATURES_PA_BITS(ptdev->gpu_info.mmu_features);
+	ret = dma_set_mask_and_coherent(ptdev->base.dev, DMA_BIT_MASK(pa_bits));
+	if (ret)
+		return ret;
+
+	irq = platform_get_irq_byname(to_platform_device(ptdev->base.dev), "gpu");
+	if (irq < 0)
+		return irq;
+
+	ret = panthor_request_gpu_irq(ptdev, &ptdev->gpu->irq, irq,
+				      ptdev->iomem + GPU_INT_BASE);
+	if (ret)
+		return ret;
+
+	panthor_gpu_irq_enable_events(&ptdev->gpu->irq, GPU_INTERRUPTS_MASK);
+	panthor_gpu_irq_resume(&ptdev->gpu->irq);
+	return 0;
+}
+
+int panthor_gpu_power_changed_on(struct panthor_device *ptdev)
+{
+	guard(pm_runtime_active)(ptdev->base.dev);
+
+	panthor_gpu_irq_enable_events(&ptdev->gpu->irq, GPU_POWER_INTERRUPTS_MASK);
+
+	return 0;
+}
+
+void panthor_gpu_power_changed_off(struct panthor_device *ptdev)
+{
+	guard(pm_runtime_active)(ptdev->base.dev);
+
+	panthor_gpu_irq_disable_events(&ptdev->gpu->irq, GPU_POWER_INTERRUPTS_MASK);
+}
+
+/**
+ * panthor_gpu_block_power_off() - Power-off a specific block of the GPU
+ * @ptdev: Device.
+ * @blk_name: Block name.
+ * @pwroff_reg: Power-off register for this block.
+ * @pwrtrans_reg: Power transition register for this block.
+ * @mask: Sub-elements to power-off.
+ * @timeout_us: Timeout in microseconds.
+ *
+ * Return: 0 on success, a negative error code otherwise.
+ */
+int panthor_gpu_block_power_off(struct panthor_device *ptdev,
+				const char *blk_name,
+				u32 pwroff_reg, u32 pwrtrans_reg,
+				u64 mask, u32 timeout_us)
+{
+	struct panthor_gpu *gpu = ptdev->gpu;
+	u32 val;
+	int ret;
+
+	ret = gpu_read64_relaxed_poll_timeout(gpu->iomem, pwrtrans_reg, val,
+					      !(mask & val), 100, timeout_us);
+	if (ret) {
+		drm_err(&ptdev->base,
+			"timeout waiting on %s:%llx power transition", blk_name,
+			mask);
+		return ret;
+	}
+
+	gpu_write64(gpu->iomem, pwroff_reg, mask);
+
+	ret = gpu_read64_relaxed_poll_timeout(gpu->iomem, pwrtrans_reg, val,
+					      !(mask & val), 100, timeout_us);
+	if (ret) {
+		drm_err(&ptdev->base,
+			"timeout waiting on %s:%llx power transition", blk_name,
+			mask);
+		return ret;
+	}
+
+	return 0;
+}
+
+/**
+ * panthor_gpu_block_power_on() - Power-on a specific block of the GPU
+ * @ptdev: Device.
+ * @blk_name: Block name.
+ * @pwron_reg: Power-on register for this block.
+ * @pwrtrans_reg: Power transition register for this block.
+ * @rdy_reg: Power transition ready register.
+ * @mask: Sub-elements to power-on.
+ * @timeout_us: Timeout in microseconds.
+ *
+ * Return: 0 on success, a negative error code otherwise.
+ */
+int panthor_gpu_block_power_on(struct panthor_device *ptdev,
+			       const char *blk_name,
+			       u32 pwron_reg, u32 pwrtrans_reg,
+			       u32 rdy_reg, u64 mask, u32 timeout_us)
+{
+	struct panthor_gpu *gpu = ptdev->gpu;
+	u32 val;
+	int ret;
+
+	ret = gpu_read64_relaxed_poll_timeout(gpu->iomem, pwrtrans_reg, val,
+					      !(mask & val), 100, timeout_us);
+	if (ret) {
+		drm_err(&ptdev->base,
+			"timeout waiting on %s:%llx power transition", blk_name,
+			mask);
+		return ret;
+	}
+
+	gpu_write64(gpu->iomem, pwron_reg, mask);
+
+	ret = gpu_read64_relaxed_poll_timeout(gpu->iomem, rdy_reg, val,
+					      (mask & val) == val,
+					      100, timeout_us);
+	if (ret) {
+		drm_err(&ptdev->base, "timeout waiting on %s:%llx readiness",
+			blk_name, mask);
+		return ret;
+	}
+
+	return 0;
+}
+
+void panthor_gpu_l2_power_off(struct panthor_device *ptdev)
+{
+	panthor_gpu_power_off(ptdev, L2, ptdev->gpu_info.l2_present, 20000);
+}
+
+/**
+ * panthor_gpu_l2_power_on() - Power-on the L2-cache
+ * @ptdev: Device.
+ *
+ * Return: 0 on success, a negative error code otherwise.
+ */
+int panthor_gpu_l2_power_on(struct panthor_device *ptdev)
+{
+	if (ptdev->gpu_info.l2_present != 1) {
+		/*
+		 * Only support one core group now.
+		 * ~(l2_present - 1) unsets all bits in l2_present except
+		 * the bottom bit. (l2_present - 2) has all the bits in
+		 * the first core group set. AND them together to generate
+		 * a mask of cores in the first core group.
+		 */
+		u64 core_mask = ~(ptdev->gpu_info.l2_present - 1) &
+				(ptdev->gpu_info.l2_present - 2);
+		drm_info_once(&ptdev->base, "using only 1st core group (%lu cores from %lu)\n",
+			      hweight64(core_mask),
+			      hweight64(ptdev->gpu_info.shader_present));
+	}
+
+	/* Set the desired coherency mode and L2 config before the power up of L2 */
+	panthor_gpu_coherency_set(ptdev);
+	panthor_gpu_l2_config_set(ptdev);
+
+	return panthor_gpu_power_on(ptdev, L2, 1, 20000);
+}
+
+/**
+ * panthor_gpu_flush_caches() - Flush caches
+ * @ptdev: Device.
+ * @l2: L2 flush type.
+ * @lsc: LSC flush type.
+ * @other: Other flush type.
+ *
+ * Return: 0 on success, a negative error code otherwise.
+ */
+int panthor_gpu_flush_caches(struct panthor_device *ptdev,
+			     u32 l2, u32 lsc, u32 other)
+{
+	struct panthor_gpu *gpu = ptdev->gpu;
+	unsigned long flags;
+	int ret = 0;
+
+	/* Serialize cache flush operations. */
+	guard(mutex)(&ptdev->gpu->cache_flush_lock);
+
+	spin_lock_irqsave(&ptdev->gpu->reqs_lock, flags);
+	if (!(ptdev->gpu->pending_reqs & GPU_IRQ_CLEAN_CACHES_COMPLETED)) {
+		ptdev->gpu->pending_reqs |= GPU_IRQ_CLEAN_CACHES_COMPLETED;
+		gpu_write(gpu->iomem, GPU_CMD, GPU_FLUSH_CACHES(l2, lsc, other));
+	} else {
+		ret = -EIO;
+	}
+	spin_unlock_irqrestore(&ptdev->gpu->reqs_lock, flags);
+
+	if (ret)
+		return ret;
+
+	if (!wait_event_timeout(ptdev->gpu->reqs_acked,
+				!(ptdev->gpu->pending_reqs & GPU_IRQ_CLEAN_CACHES_COMPLETED),
+				msecs_to_jiffies(100))) {
+		spin_lock_irqsave(&ptdev->gpu->reqs_lock, flags);
+		if ((ptdev->gpu->pending_reqs & GPU_IRQ_CLEAN_CACHES_COMPLETED) != 0 &&
+		    !(gpu_read(gpu->irq.iomem, INT_RAWSTAT) & GPU_IRQ_CLEAN_CACHES_COMPLETED))
+			ret = -ETIMEDOUT;
+		else
+			ptdev->gpu->pending_reqs &= ~GPU_IRQ_CLEAN_CACHES_COMPLETED;
+		spin_unlock_irqrestore(&ptdev->gpu->reqs_lock, flags);
+	}
+
+	if (ret) {
+		panthor_device_schedule_reset(ptdev);
+		drm_err(&ptdev->base, "Flush caches timeout");
+	}
+
+	return ret;
+}
+
+/**
+ * panthor_gpu_soft_reset() - Issue a soft-reset
+ * @ptdev: Device.
+ *
+ * Return: 0 on success, a negative error code otherwise.
+ */
+int panthor_gpu_soft_reset(struct panthor_device *ptdev)
+{
+	struct panthor_gpu *gpu = ptdev->gpu;
+	bool timedout = false;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ptdev->gpu->reqs_lock, flags);
+	if (!drm_WARN_ON(&ptdev->base,
+			 ptdev->gpu->pending_reqs & GPU_IRQ_RESET_COMPLETED)) {
+		ptdev->gpu->pending_reqs |= GPU_IRQ_RESET_COMPLETED;
+		gpu_write(gpu->irq.iomem, INT_CLEAR, GPU_IRQ_RESET_COMPLETED);
+		gpu_write(gpu->iomem, GPU_CMD, GPU_SOFT_RESET);
+	}
+	spin_unlock_irqrestore(&ptdev->gpu->reqs_lock, flags);
+
+	if (!wait_event_timeout(ptdev->gpu->reqs_acked,
+				!(ptdev->gpu->pending_reqs & GPU_IRQ_RESET_COMPLETED),
+				msecs_to_jiffies(100))) {
+		spin_lock_irqsave(&ptdev->gpu->reqs_lock, flags);
+		if ((ptdev->gpu->pending_reqs & GPU_IRQ_RESET_COMPLETED) != 0 &&
+		    !(gpu_read(gpu->irq.iomem, INT_RAWSTAT) & GPU_IRQ_RESET_COMPLETED))
+			timedout = true;
+		else
+			ptdev->gpu->pending_reqs &= ~GPU_IRQ_RESET_COMPLETED;
+		spin_unlock_irqrestore(&ptdev->gpu->reqs_lock, flags);
+	}
+
+	if (timedout) {
+		drm_err(&ptdev->base, "Soft reset timeout");
+		return -ETIMEDOUT;
+	}
+
+	ptdev->gpu->pending_reqs = 0;
+	return 0;
+}
+
+/**
+ * panthor_gpu_suspend() - Suspend the GPU block.
+ * @ptdev: Device.
+ *
+ * Suspend the GPU irq. This should be called last in the suspend procedure,
+ * after all other blocks have been suspented.
+ */
+void panthor_gpu_suspend(struct panthor_device *ptdev)
+{
+	/* On a fast reset, simply power down the L2. */
+	if (!ptdev->reset.fast)
+		panthor_hw_soft_reset(ptdev);
+	else
+		panthor_hw_l2_power_off(ptdev);
+
+	panthor_gpu_irq_suspend(&ptdev->gpu->irq);
+}
+
+/**
+ * panthor_gpu_resume() - Resume the GPU block.
+ * @ptdev: Device.
+ *
+ * Resume the IRQ handler and power-on the L2-cache.
+ * The FW takes care of powering the other blocks.
+ */
+void panthor_gpu_resume(struct panthor_device *ptdev)
+{
+	panthor_gpu_irq_resume(&ptdev->gpu->irq);
+	panthor_hw_l2_power_on(ptdev);
+}
+
+u64 panthor_gpu_get_timestamp(struct panthor_device *ptdev)
+{
+	return gpu_read64_counter(ptdev->gpu->iomem, GPU_TIMESTAMP);
+}
+
+u64 panthor_gpu_get_timestamp_offset(struct panthor_device *ptdev)
+{
+	return gpu_read64(ptdev->gpu->iomem, GPU_TIMESTAMP_OFFSET);
+}
+
+u64 panthor_gpu_get_cycle_count(struct panthor_device *ptdev)
+{
+	return gpu_read64_counter(ptdev->gpu->iomem, GPU_CYCLE_COUNT);
+}
+
+int panthor_gpu_coherency_init(struct panthor_device *ptdev)
+{
+	BUILD_BUG_ON(GPU_COHERENCY_NONE != DRM_PANTHOR_GPU_COHERENCY_NONE);
+	BUILD_BUG_ON(GPU_COHERENCY_ACE_LITE != DRM_PANTHOR_GPU_COHERENCY_ACE_LITE);
+	BUILD_BUG_ON(GPU_COHERENCY_ACE != DRM_PANTHOR_GPU_COHERENCY_ACE);
+
+	/* Start with no coherency, and update it if the device is flagged coherent. */
+	ptdev->gpu_info.selected_coherency = GPU_COHERENCY_NONE;
+	ptdev->coherent = device_get_dma_attr(ptdev->base.dev) == DEV_DMA_COHERENT;
+
+	if (!ptdev->coherent)
+		return 0;
+
+	/* Check if the ACE-Lite coherency protocol is actually supported by the GPU.
+	 * ACE protocol has never been supported for command stream frontend GPUs.
+	 */
+	if ((gpu_read(ptdev->gpu->iomem, GPU_COHERENCY_FEATURES) &
+		      GPU_COHERENCY_PROT_BIT(ACE_LITE))) {
+		ptdev->gpu_info.selected_coherency = GPU_COHERENCY_ACE_LITE;
+		return 0;
+	}
+
+	drm_err(&ptdev->base, "Coherency not supported by the device");
+	return -ENOTSUPP;
+}

linux-7.2.3/drivers/gpu/drm/panthor/panthor_gpu.h

@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: GPL-2.0 or MIT */
+/* Copyright 2018 Marty E. Plummer <hanetzer@startmail.com> */
+/* Copyright 2019 Collabora ltd. */
+
+#ifndef __PANTHOR_GPU_H__
+#define __PANTHOR_GPU_H__
+
+#include <linux/types.h>
+
+struct panthor_device;
+
+int panthor_gpu_init(struct panthor_device *ptdev);
+void panthor_gpu_unplug(struct panthor_device *ptdev);
+void panthor_gpu_suspend(struct panthor_device *ptdev);
+void panthor_gpu_resume(struct panthor_device *ptdev);
+
+int panthor_gpu_block_power_on(struct panthor_device *ptdev,
+			       const char *blk_name,
+			       u32 pwron_reg, u32 pwrtrans_reg,
+			       u32 rdy_reg, u64 mask, u32 timeout_us);
+int panthor_gpu_block_power_off(struct panthor_device *ptdev,
+				const char *blk_name,
+				u32 pwroff_reg, u32 pwrtrans_reg,
+				u64 mask, u32 timeout_us);
+
+/**
+ * panthor_gpu_power_on() - Power on the GPU block.
+ *
+ * Return: 0 on success, a negative error code otherwise.
+ */
+#define panthor_gpu_power_on(ptdev, type, mask, timeout_us) \
+	panthor_gpu_block_power_on(ptdev, #type, \
+				  type ## _PWRON, \
+				  type ## _PWRTRANS, \
+				  type ## _READY, \
+				  mask, timeout_us)
+
+/**
+ * panthor_gpu_power_off() - Power off the GPU block.
+ *
+ * Return: 0 on success, a negative error code otherwise.
+ */
+#define panthor_gpu_power_off(ptdev, type, mask, timeout_us) \
+	panthor_gpu_block_power_off(ptdev, #type, \
+				   type ## _PWROFF, \
+				   type ## _PWRTRANS, \
+				   mask, timeout_us)
+
+void panthor_gpu_l2_power_off(struct panthor_device *ptdev);
+int panthor_gpu_l2_power_on(struct panthor_device *ptdev);
+int panthor_gpu_flush_caches(struct panthor_device *ptdev,
+			     u32 l2, u32 lsc, u32 other);
+int panthor_gpu_soft_reset(struct panthor_device *ptdev);
+void panthor_gpu_power_changed_off(struct panthor_device *ptdev);
+int panthor_gpu_power_changed_on(struct panthor_device *ptdev);
+
+u64 panthor_gpu_get_timestamp(struct panthor_device *ptdev);
+u64 panthor_gpu_get_timestamp_offset(struct panthor_device *ptdev);
+u64 panthor_gpu_get_cycle_count(struct panthor_device *ptdev);
+
+int panthor_gpu_coherency_init(struct panthor_device *ptdev);
+
+#endif

linux-7.2.3/drivers/gpu/drm/panthor/panthor_gpu_regs.h

@@ -0,0 +1,119 @@
+/* SPDX-License-Identifier: GPL-2.0 or MIT */
+/* Copyright 2026 ARM Limited. All rights reserved. */
+
+#ifndef __PANTHOR_GPU_REGS_H__
+#define __PANTHOR_GPU_REGS_H__
+
+#define GPU_CONTROL_BASE				0x0
+
+#define GPU_ID						0x0
+#define   GPU_ARCH_MAJOR(x)				((x) >> 28)
+#define   GPU_ARCH_MINOR(x)				(((x) & GENMASK(27, 24)) >> 24)
+#define   GPU_ARCH_REV(x)				(((x) & GENMASK(23, 20)) >> 20)
+#define   GPU_PROD_MAJOR(x)				(((x) & GENMASK(19, 16)) >> 16)
+#define   GPU_VER_MAJOR(x)				(((x) & GENMASK(15, 12)) >> 12)
+#define   GPU_VER_MINOR(x)				(((x) & GENMASK(11, 4)) >> 4)
+#define   GPU_VER_STATUS(x)				((x) & GENMASK(3, 0))
+
+#define GPU_L2_FEATURES					0x4
+#define  GPU_L2_FEATURES_LINE_SIZE(x)			(1 << ((x) & GENMASK(7, 0)))
+
+#define GPU_CORE_FEATURES				0x8
+
+#define GPU_TILER_FEATURES				0xC
+#define GPU_MEM_FEATURES				0x10
+#define   GROUPS_L2_COHERENT				BIT(0)
+
+#define GPU_MMU_FEATURES				0x14
+#define  GPU_MMU_FEATURES_VA_BITS(x)			((x) & GENMASK(7, 0))
+#define  GPU_MMU_FEATURES_PA_BITS(x)			(((x) >> 8) & GENMASK(7, 0))
+#define GPU_AS_PRESENT					0x18
+#define GPU_CSF_ID					0x1C
+
+#define GPU_INT_BASE					0x20
+#define   GPU_IRQ_FAULT					BIT(0)
+#define   GPU_IRQ_PROTM_FAULT				BIT(1)
+#define   GPU_IRQ_RESET_COMPLETED			BIT(8)
+#define   GPU_IRQ_POWER_CHANGED				BIT(9)
+#define   GPU_IRQ_POWER_CHANGED_ALL			BIT(10)
+#define   GPU_IRQ_CLEAN_CACHES_COMPLETED		BIT(17)
+#define   GPU_IRQ_DOORBELL_MIRROR			BIT(18)
+#define   GPU_IRQ_MCU_STATUS_CHANGED			BIT(19)
+#define GPU_CMD						0x30
+#define   GPU_CMD_DEF(type, payload)			((type) | ((payload) << 8))
+#define   GPU_SOFT_RESET				GPU_CMD_DEF(1, 1)
+#define   GPU_HARD_RESET				GPU_CMD_DEF(1, 2)
+#define   CACHE_CLEAN					BIT(0)
+#define   CACHE_INV					BIT(1)
+#define   GPU_FLUSH_CACHES(l2, lsc, oth)		\
+	  GPU_CMD_DEF(4, ((l2) << 0) | ((lsc) << 4) | ((oth) << 8))
+
+#define GPU_STATUS					0x34
+#define   GPU_STATUS_ACTIVE				BIT(0)
+#define   GPU_STATUS_PWR_ACTIVE				BIT(1)
+#define   GPU_STATUS_PAGE_FAULT				BIT(4)
+#define   GPU_STATUS_PROTM_ACTIVE			BIT(7)
+#define   GPU_STATUS_DBG_ENABLED			BIT(8)
+
+#define GPU_FAULT_STATUS				0x3C
+#define GPU_FAULT_ADDR					0x40
+#define GPU_L2_CONFIG					0x48
+#define   GPU_L2_CONFIG_ASN_HASH_ENABLE			BIT(24)
+
+#define GPU_PWR_KEY					0x50
+#define  GPU_PWR_KEY_UNLOCK				0x2968A819
+#define GPU_PWR_OVERRIDE0				0x54
+#define GPU_PWR_OVERRIDE1				0x58
+
+#define GPU_FEATURES					0x60
+#define   GPU_FEATURES_RAY_INTERSECTION			BIT(2)
+#define   GPU_FEATURES_RAY_TRAVERSAL			BIT(5)
+
+#define GPU_TIMESTAMP_OFFSET				0x88
+#define GPU_CYCLE_COUNT					0x90
+#define GPU_TIMESTAMP					0x98
+
+#define GPU_THREAD_MAX_THREADS				0xA0
+#define GPU_THREAD_MAX_WORKGROUP_SIZE			0xA4
+#define GPU_THREAD_MAX_BARRIER_SIZE			0xA8
+#define GPU_THREAD_FEATURES				0xAC
+
+#define GPU_TEXTURE_FEATURES(n)				(0xB0 + ((n) * 4))
+
+#define GPU_SHADER_PRESENT				0x100
+#define GPU_TILER_PRESENT				0x110
+#define GPU_L2_PRESENT					0x120
+
+#define SHADER_READY					0x140
+#define TILER_READY					0x150
+#define L2_READY					0x160
+
+#define SHADER_PWRON					0x180
+#define TILER_PWRON					0x190
+#define L2_PWRON					0x1A0
+
+#define SHADER_PWROFF					0x1C0
+#define TILER_PWROFF					0x1D0
+#define L2_PWROFF					0x1E0
+
+#define SHADER_PWRTRANS					0x200
+#define TILER_PWRTRANS					0x210
+#define L2_PWRTRANS					0x220
+
+#define SHADER_PWRACTIVE				0x240
+#define TILER_PWRACTIVE					0x250
+#define L2_PWRACTIVE					0x260
+
+#define GPU_REVID					0x280
+
+#define GPU_ASN_HASH(n)					(0x2C0 + ((n) * 4))
+
+#define GPU_COHERENCY_FEATURES				0x300
+#define GPU_COHERENCY_PROT_BIT(name)			BIT(GPU_COHERENCY_  ## name)
+
+#define GPU_COHERENCY_PROTOCOL				0x304
+#define   GPU_COHERENCY_ACE_LITE			0
+#define   GPU_COHERENCY_ACE				1
+#define   GPU_COHERENCY_NONE				31
+
+#endif /* __PANTHOR_GPU_REGS_H__ */

linux-7.2.3/drivers/gpu/drm/panthor/panthor_heap.c

@@ -0,0 +1,632 @@
+// SPDX-License-Identifier: GPL-2.0 or MIT
+/* Copyright 2023 Collabora ltd. */
+
+#include <linux/iosys-map.h>
+#include <linux/rwsem.h>
+
+#include <drm/drm_print.h>
+#include <drm/panthor_drm.h>
+
+#include "panthor_device.h"
+#include "panthor_gem.h"
+#include "panthor_gpu_regs.h"
+#include "panthor_heap.h"
+#include "panthor_mmu.h"
+
+/*
+ * The GPU heap context is an opaque structure used by the GPU to track the
+ * heap allocations. The driver should only touch it to initialize it (zero all
+ * fields). Because the CPU and GPU can both access this structure it is
+ * required to be GPU cache line aligned.
+ */
+#define HEAP_CONTEXT_SIZE	32
+
+/**
+ * struct panthor_heap_chunk_header - Heap chunk header
+ */
+struct panthor_heap_chunk_header {
+	/**
+	 * @next: Next heap chunk in the list.
+	 *
+	 * This is a GPU VA.
+	 */
+	u64 next;
+
+	/** @unknown: MBZ. */
+	u32 unknown[14];
+};
+
+/**
+ * struct panthor_heap_chunk - Structure used to keep track of allocated heap chunks.
+ */
+struct panthor_heap_chunk {
+	/** @node: Used to insert the heap chunk in panthor_heap::chunks. */
+	struct list_head node;
+
+	/** @bo: Buffer object backing the heap chunk. */
+	struct panthor_kernel_bo *bo;
+};
+
+/**
+ * struct panthor_heap - Structure used to manage tiler heap contexts.
+ */
+struct panthor_heap {
+	/** @chunks: List containing all heap chunks allocated so far. */
+	struct list_head chunks;
+
+	/** @lock: Lock protecting insertion in the chunks list. */
+	struct mutex lock;
+
+	/** @chunk_size: Size of each chunk. */
+	u32 chunk_size;
+
+	/** @max_chunks: Maximum number of chunks. */
+	u32 max_chunks;
+
+	/**
+	 * @target_in_flight: Number of in-flight render passes after which
+	 * we'd let the FW wait for fragment job to finish instead of allocating new chunks.
+	 */
+	u32 target_in_flight;
+
+	/** @chunk_count: Number of heap chunks currently allocated. */
+	u32 chunk_count;
+};
+
+#define MAX_HEAPS_PER_POOL    128
+
+/**
+ * struct panthor_heap_pool - Pool of heap contexts
+ *
+ * The pool is attached to a panthor_file and can't be shared across processes.
+ */
+struct panthor_heap_pool {
+	/** @refcount: Reference count. */
+	struct kref refcount;
+
+	/** @ptdev: Device. */
+	struct panthor_device *ptdev;
+
+	/** @vm: VM this pool is bound to. */
+	struct panthor_vm *vm;
+
+	/** @lock: Lock protecting access to @xa. */
+	struct rw_semaphore lock;
+
+	/** @xa: Array storing panthor_heap objects. */
+	struct xarray xa;
+
+	/** @gpu_contexts: Buffer object containing the GPU heap contexts. */
+	struct panthor_kernel_bo *gpu_contexts;
+
+	/** @size: Size of all chunks across all heaps in the pool. */
+	atomic_t size;
+};
+
+static int panthor_heap_ctx_stride(struct panthor_device *ptdev)
+{
+	u32 l2_features = ptdev->gpu_info.l2_features;
+	u32 gpu_cache_line_size = GPU_L2_FEATURES_LINE_SIZE(l2_features);
+
+	return ALIGN(HEAP_CONTEXT_SIZE, gpu_cache_line_size);
+}
+
+static int panthor_get_heap_ctx_offset(struct panthor_heap_pool *pool, int id)
+{
+	return panthor_heap_ctx_stride(pool->ptdev) * id;
+}
+
+static void *panthor_get_heap_ctx(struct panthor_heap_pool *pool, int id)
+{
+	return pool->gpu_contexts->kmap +
+	       panthor_get_heap_ctx_offset(pool, id);
+}
+
+static void panthor_free_heap_chunk(struct panthor_heap_pool *pool,
+				    struct panthor_heap *heap,
+				    struct panthor_heap_chunk *chunk)
+{
+	mutex_lock(&heap->lock);
+	list_del(&chunk->node);
+	heap->chunk_count--;
+	mutex_unlock(&heap->lock);
+
+	atomic_sub(heap->chunk_size, &pool->size);
+
+	panthor_kernel_bo_destroy(chunk->bo);
+	kfree(chunk);
+}
+
+static int panthor_alloc_heap_chunk(struct panthor_heap_pool *pool,
+				    struct panthor_heap *heap,
+				    bool initial_chunk)
+{
+	struct panthor_heap_chunk *chunk;
+	struct panthor_heap_chunk_header *hdr;
+	int ret;
+
+	chunk = kmalloc_obj(*chunk);
+	if (!chunk)
+		return -ENOMEM;
+
+	chunk->bo = panthor_kernel_bo_create(pool->ptdev, pool->vm, heap->chunk_size,
+					     DRM_PANTHOR_BO_NO_MMAP,
+					     DRM_PANTHOR_VM_BIND_OP_MAP_NOEXEC,
+					     PANTHOR_VM_KERNEL_AUTO_VA,
+					     "Tiler heap chunk");
+	if (IS_ERR(chunk->bo)) {
+		ret = PTR_ERR(chunk->bo);
+		goto err_free_chunk;
+	}
+
+	ret = panthor_kernel_bo_vmap(chunk->bo);
+	if (ret)
+		goto err_destroy_bo;
+
+	hdr = chunk->bo->kmap;
+	memset(hdr, 0, sizeof(*hdr));
+
+	if (initial_chunk && !list_empty(&heap->chunks)) {
+		struct panthor_heap_chunk *prev_chunk;
+		u64 prev_gpuva;
+
+		prev_chunk = list_first_entry(&heap->chunks,
+					      struct panthor_heap_chunk,
+					      node);
+
+		prev_gpuva = panthor_kernel_bo_gpuva(prev_chunk->bo);
+		hdr->next = (prev_gpuva & GENMASK_ULL(63, 12)) |
+			    (heap->chunk_size >> 12);
+	}
+
+	panthor_kernel_bo_vunmap(chunk->bo);
+
+	mutex_lock(&heap->lock);
+	list_add(&chunk->node, &heap->chunks);
+	heap->chunk_count++;
+	mutex_unlock(&heap->lock);
+
+	atomic_add(heap->chunk_size, &pool->size);
+
+	return 0;
+
+err_destroy_bo:
+	panthor_kernel_bo_destroy(chunk->bo);
+
+err_free_chunk:
+	kfree(chunk);
+
+	return ret;
+}
+
+static void panthor_free_heap_chunks(struct panthor_heap_pool *pool,
+				     struct panthor_heap *heap)
+{
+	struct panthor_heap_chunk *chunk, *tmp;
+
+	list_for_each_entry_safe(chunk, tmp, &heap->chunks, node)
+		panthor_free_heap_chunk(pool, heap, chunk);
+}
+
+static int panthor_alloc_heap_chunks(struct panthor_heap_pool *pool,
+				     struct panthor_heap *heap,
+				     u32 chunk_count)
+{
+	int ret;
+	u32 i;
+
+	for (i = 0; i < chunk_count; i++) {
+		ret = panthor_alloc_heap_chunk(pool, heap, true);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int
+panthor_heap_destroy_locked(struct panthor_heap_pool *pool, u32 handle)
+{
+	struct panthor_heap *heap;
+
+	heap = xa_erase(&pool->xa, handle);
+	if (!heap)
+		return -EINVAL;
+
+	panthor_free_heap_chunks(pool, heap);
+	mutex_destroy(&heap->lock);
+	kfree(heap);
+	return 0;
+}
+
+/**
+ * panthor_heap_destroy() - Destroy a heap context
+ * @pool: Pool this context belongs to.
+ * @handle: Handle returned by panthor_heap_create().
+ */
+int panthor_heap_destroy(struct panthor_heap_pool *pool, u32 handle)
+{
+	int ret;
+
+	down_write(&pool->lock);
+	ret = panthor_heap_destroy_locked(pool, handle);
+	up_write(&pool->lock);
+
+	return ret;
+}
+
+/**
+ * panthor_heap_create() - Create a heap context
+ * @pool: Pool to instantiate the heap context from.
+ * @initial_chunk_count: Number of chunk allocated at initialization time.
+ * Must be at least 1.
+ * @chunk_size: The size of each chunk. Must be page-aligned and lie in the
+ * [128k:8M] range.
+ * @max_chunks: Maximum number of chunks that can be allocated.
+ * @target_in_flight: Maximum number of in-flight render passes.
+ * @heap_ctx_gpu_va: Pointer holding the GPU address of the allocated heap
+ * context.
+ * @first_chunk_gpu_va: Pointer holding the GPU address of the first chunk
+ * assigned to the heap context.
+ *
+ * Return: a positive handle on success, a negative error otherwise.
+ */
+int panthor_heap_create(struct panthor_heap_pool *pool,
+			u32 initial_chunk_count,
+			u32 chunk_size,
+			u32 max_chunks,
+			u32 target_in_flight,
+			u64 *heap_ctx_gpu_va,
+			u64 *first_chunk_gpu_va)
+{
+	struct panthor_heap *heap;
+	struct panthor_heap_chunk *first_chunk;
+	struct panthor_vm *vm;
+	int ret = 0;
+	u32 id;
+
+	if (initial_chunk_count == 0)
+		return -EINVAL;
+
+	if (initial_chunk_count > max_chunks)
+		return -EINVAL;
+
+	if (!IS_ALIGNED(chunk_size, PAGE_SIZE) ||
+	    chunk_size < SZ_128K || chunk_size > SZ_8M)
+		return -EINVAL;
+
+	down_read(&pool->lock);
+	vm = panthor_vm_get(pool->vm);
+	up_read(&pool->lock);
+
+	/* The pool has been destroyed, we can't create a new heap. */
+	if (!vm)
+		return -EINVAL;
+
+	heap = kzalloc_obj(*heap);
+	if (!heap) {
+		ret = -ENOMEM;
+		goto err_put_vm;
+	}
+
+	mutex_init(&heap->lock);
+	INIT_LIST_HEAD(&heap->chunks);
+	heap->chunk_size = chunk_size;
+	heap->max_chunks = max_chunks;
+	heap->target_in_flight = target_in_flight;
+
+	ret = panthor_alloc_heap_chunks(pool, heap, initial_chunk_count);
+	if (ret)
+		goto err_free_heap;
+
+	first_chunk = list_first_entry(&heap->chunks,
+				       struct panthor_heap_chunk,
+				       node);
+	*first_chunk_gpu_va = panthor_kernel_bo_gpuva(first_chunk->bo);
+
+	down_write(&pool->lock);
+	/* The pool has been destroyed, we can't create a new heap. */
+	if (!pool->vm) {
+		ret = -EINVAL;
+	} else {
+		ret = xa_alloc(&pool->xa, &id, heap,
+			       XA_LIMIT(0, MAX_HEAPS_PER_POOL - 1), GFP_KERNEL);
+		if (!ret) {
+			void *gpu_ctx = panthor_get_heap_ctx(pool, id);
+
+			memset(gpu_ctx, 0, panthor_heap_ctx_stride(pool->ptdev));
+			*heap_ctx_gpu_va = panthor_kernel_bo_gpuva(pool->gpu_contexts) +
+					   panthor_get_heap_ctx_offset(pool, id);
+		}
+	}
+	up_write(&pool->lock);
+
+	if (ret)
+		goto err_free_heap;
+
+	panthor_vm_put(vm);
+	return id;
+
+err_free_heap:
+	panthor_free_heap_chunks(pool, heap);
+	mutex_destroy(&heap->lock);
+	kfree(heap);
+
+err_put_vm:
+	panthor_vm_put(vm);
+	return ret;
+}
+
+/**
+ * panthor_heap_return_chunk() - Return an unused heap chunk
+ * @pool: The pool this heap belongs to.
+ * @heap_gpu_va: The GPU address of the heap context.
+ * @chunk_gpu_va: The chunk VA to return.
+ *
+ * This function is used when a chunk allocated with panthor_heap_grow()
+ * couldn't be linked to the heap context through the FW interface because
+ * the group requesting the allocation was scheduled out in the meantime.
+ */
+int panthor_heap_return_chunk(struct panthor_heap_pool *pool,
+			      u64 heap_gpu_va,
+			      u64 chunk_gpu_va)
+{
+	u64 offset = heap_gpu_va - panthor_kernel_bo_gpuva(pool->gpu_contexts);
+	u32 heap_id = (u32)offset / panthor_heap_ctx_stride(pool->ptdev);
+	struct panthor_heap_chunk *chunk, *tmp, *removed = NULL;
+	struct panthor_heap *heap;
+	int ret;
+
+	if (offset > U32_MAX || heap_id >= MAX_HEAPS_PER_POOL)
+		return -EINVAL;
+
+	down_read(&pool->lock);
+	heap = xa_load(&pool->xa, heap_id);
+	if (!heap) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	chunk_gpu_va &= GENMASK_ULL(63, 12);
+
+	mutex_lock(&heap->lock);
+	list_for_each_entry_safe(chunk, tmp, &heap->chunks, node) {
+		if (panthor_kernel_bo_gpuva(chunk->bo) == chunk_gpu_va) {
+			removed = chunk;
+			list_del(&chunk->node);
+			heap->chunk_count--;
+			atomic_sub(heap->chunk_size, &pool->size);
+			break;
+		}
+	}
+	mutex_unlock(&heap->lock);
+
+	if (removed) {
+		panthor_kernel_bo_destroy(chunk->bo);
+		kfree(chunk);
+		ret = 0;
+	} else {
+		ret = -EINVAL;
+	}
+
+out_unlock:
+	up_read(&pool->lock);
+	return ret;
+}
+
+/**
+ * panthor_heap_grow() - Make a heap context grow.
+ * @pool: The pool this heap belongs to.
+ * @heap_gpu_va: The GPU address of the heap context.
+ * @renderpasses_in_flight: Number of render passes currently in-flight.
+ * @pending_frag_count: Number of fragment jobs waiting for execution/completion.
+ * @new_chunk_gpu_va: Pointer used to return the chunk VA.
+ *
+ * Return:
+ * - 0 if a new heap was allocated
+ * - -ENOMEM if the tiler context reached the maximum number of chunks
+ *   or if too many render passes are in-flight
+ *   or if the allocation failed
+ * - -EINVAL if any of the arguments passed to panthor_heap_grow() is invalid
+ */
+int panthor_heap_grow(struct panthor_heap_pool *pool,
+		      u64 heap_gpu_va,
+		      u32 renderpasses_in_flight,
+		      u32 pending_frag_count,
+		      u64 *new_chunk_gpu_va)
+{
+	u64 offset = heap_gpu_va - panthor_kernel_bo_gpuva(pool->gpu_contexts);
+	u32 heap_id = (u32)offset / panthor_heap_ctx_stride(pool->ptdev);
+	struct panthor_heap_chunk *chunk;
+	struct panthor_heap *heap;
+	int ret;
+
+	if (offset > U32_MAX || heap_id >= MAX_HEAPS_PER_POOL)
+		return -EINVAL;
+
+	down_read(&pool->lock);
+	heap = xa_load(&pool->xa, heap_id);
+	if (!heap) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	/* If we reached the target in-flight render passes, or if we
+	 * reached the maximum number of chunks, let the FW figure another way to
+	 * find some memory (wait for render passes to finish, or call the exception
+	 * handler provided by the userspace driver, if any).
+	 */
+	if (renderpasses_in_flight > heap->target_in_flight ||
+	    heap->chunk_count >= heap->max_chunks) {
+		ret = -ENOMEM;
+		goto out_unlock;
+	}
+
+	/* FIXME: panthor_alloc_heap_chunk() triggers a kernel BO creation,
+	 * which goes through the blocking allocation path. Ultimately, we
+	 * want a non-blocking allocation, so we can immediately report to the
+	 * FW when the system is running out of memory. In that case, the FW
+	 * can call a user-provided exception handler, which might try to free
+	 * some tiler memory by issuing an intermediate fragment job. If the
+	 * exception handler can't do anything, it will flag the queue as
+	 * faulty so the job that triggered this tiler chunk allocation and all
+	 * further jobs in this queue fail immediately instead of having to
+	 * wait for the job timeout.
+	 */
+	ret = panthor_alloc_heap_chunk(pool, heap, false);
+	if (ret)
+		goto out_unlock;
+
+	chunk = list_first_entry(&heap->chunks,
+				 struct panthor_heap_chunk,
+				 node);
+	*new_chunk_gpu_va = (panthor_kernel_bo_gpuva(chunk->bo) & GENMASK_ULL(63, 12)) |
+			    (heap->chunk_size >> 12);
+	ret = 0;
+
+out_unlock:
+	up_read(&pool->lock);
+	return ret;
+}
+
+static void panthor_heap_pool_release(struct kref *refcount)
+{
+	struct panthor_heap_pool *pool =
+		container_of(refcount, struct panthor_heap_pool, refcount);
+
+	xa_destroy(&pool->xa);
+	kfree(pool);
+}
+
+/**
+ * panthor_heap_pool_put() - Release a heap pool reference
+ * @pool: Pool to release the reference on. Can be NULL.
+ */
+void panthor_heap_pool_put(struct panthor_heap_pool *pool)
+{
+	if (pool)
+		kref_put(&pool->refcount, panthor_heap_pool_release);
+}
+
+/**
+ * panthor_heap_pool_get() - Get a heap pool reference
+ * @pool: Pool to get the reference on. Can be NULL.
+ *
+ * Return: @pool.
+ */
+struct panthor_heap_pool *
+panthor_heap_pool_get(struct panthor_heap_pool *pool)
+{
+	if (pool)
+		kref_get(&pool->refcount);
+
+	return pool;
+}
+
+/**
+ * panthor_heap_pool_create() - Create a heap pool
+ * @ptdev: Device.
+ * @vm: The VM this heap pool will be attached to.
+ *
+ * Heap pools might contain up to 128 heap contexts, and are per-VM.
+ *
+ * Return: A valid pointer on success, a negative error code otherwise.
+ */
+struct panthor_heap_pool *
+panthor_heap_pool_create(struct panthor_device *ptdev, struct panthor_vm *vm)
+{
+	size_t bosize = ALIGN(MAX_HEAPS_PER_POOL *
+			      panthor_heap_ctx_stride(ptdev),
+			      4096);
+	struct panthor_heap_pool *pool;
+	int ret = 0;
+
+	pool = kzalloc_obj(*pool);
+	if (!pool)
+		return ERR_PTR(-ENOMEM);
+
+	/* We want a weak ref here: the heap pool belongs to the VM, so we're
+	 * sure that, as long as the heap pool exists, the VM exists too.
+	 */
+	pool->vm = vm;
+	pool->ptdev = ptdev;
+	init_rwsem(&pool->lock);
+	xa_init_flags(&pool->xa, XA_FLAGS_ALLOC);
+	kref_init(&pool->refcount);
+
+	pool->gpu_contexts = panthor_kernel_bo_create(ptdev, vm, bosize,
+						      DRM_PANTHOR_BO_NO_MMAP,
+						      DRM_PANTHOR_VM_BIND_OP_MAP_NOEXEC,
+						      PANTHOR_VM_KERNEL_AUTO_VA,
+						      "Heap pool");
+	if (IS_ERR(pool->gpu_contexts)) {
+		ret = PTR_ERR(pool->gpu_contexts);
+		goto err_destroy_pool;
+	}
+
+	ret = panthor_kernel_bo_vmap(pool->gpu_contexts);
+	if (ret)
+		goto err_destroy_pool;
+
+	atomic_add(pool->gpu_contexts->obj->size, &pool->size);
+
+	return pool;
+
+err_destroy_pool:
+	panthor_heap_pool_destroy(pool);
+	return ERR_PTR(ret);
+}
+
+/**
+ * panthor_heap_pool_destroy() - Destroy a heap pool.
+ * @pool: Pool to destroy.
+ *
+ * This function destroys all heap contexts and their resources. Thus
+ * preventing any use of the heap context or the chunk attached to them
+ * after that point.
+ *
+ * If the GPU still has access to some heap contexts, a fault should be
+ * triggered, which should flag the command stream groups using these
+ * context as faulty.
+ *
+ * The heap pool object is only released when all references to this pool
+ * are released.
+ */
+void panthor_heap_pool_destroy(struct panthor_heap_pool *pool)
+{
+	struct panthor_heap *heap;
+	unsigned long i;
+
+	if (!pool)
+		return;
+
+	down_write(&pool->lock);
+	xa_for_each(&pool->xa, i, heap)
+		drm_WARN_ON(&pool->ptdev->base, panthor_heap_destroy_locked(pool, i));
+
+	if (!IS_ERR_OR_NULL(pool->gpu_contexts)) {
+		atomic_sub(pool->gpu_contexts->obj->size, &pool->size);
+		panthor_kernel_bo_destroy(pool->gpu_contexts);
+	}
+
+	/* Reflects the fact the pool has been destroyed. */
+	pool->vm = NULL;
+	up_write(&pool->lock);
+
+	panthor_heap_pool_put(pool);
+}
+
+/**
+ * panthor_heap_pool_size() - Get a heap pool's total size
+ * @pool: Pool whose total chunks size to return
+ *
+ * Returns the aggregated size of all chunks for all heaps in the pool
+ *
+ */
+size_t panthor_heap_pool_size(struct panthor_heap_pool *pool)
+{
+	if (!pool)
+		return 0;
+
+	return atomic_read(&pool->size);
+}

linux-7.2.3/drivers/gpu/drm/panthor/panthor_heap.h

@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 or MIT */
+/* Copyright 2023 Collabora ltd. */
+
+#ifndef __PANTHOR_HEAP_H__
+#define __PANTHOR_HEAP_H__
+
+#include <linux/types.h>
+
+struct panthor_device;
+struct panthor_heap_pool;
+struct panthor_vm;
+
+int panthor_heap_create(struct panthor_heap_pool *pool,
+			u32 initial_chunk_count,
+			u32 chunk_size,
+			u32 max_chunks,
+			u32 target_in_flight,
+			u64 *heap_ctx_gpu_va,
+			u64 *first_chunk_gpu_va);
+int panthor_heap_destroy(struct panthor_heap_pool *pool, u32 handle);
+
+struct panthor_heap_pool *
+panthor_heap_pool_create(struct panthor_device *ptdev, struct panthor_vm *vm);
+void panthor_heap_pool_destroy(struct panthor_heap_pool *pool);
+
+struct panthor_heap_pool *
+panthor_heap_pool_get(struct panthor_heap_pool *pool);
+void panthor_heap_pool_put(struct panthor_heap_pool *pool);
+
+size_t panthor_heap_pool_size(struct panthor_heap_pool *pool);
+
+int panthor_heap_grow(struct panthor_heap_pool *pool,
+		      u64 heap_gpu_va,
+		      u32 renderpasses_in_flight,
+		      u32 pending_frag_count,
+		      u64 *new_chunk_gpu_va);
+int panthor_heap_return_chunk(struct panthor_heap_pool *pool,
+			      u64 heap_gpu_va,
+			      u64 chunk_gpu_va);
+
+#endif

linux-7.2.3/drivers/gpu/drm/panthor/panthor_hw.c

@@ -0,0 +1,318 @@
+// SPDX-License-Identifier: GPL-2.0 or MIT
+/* Copyright 2025 ARM Limited. All rights reserved. */
+
+#include <linux/nvmem-consumer.h>
+#include <linux/platform_device.h>
+
+#include <drm/drm_print.h>
+
+#include "panthor_device.h"
+#include "panthor_gpu.h"
+#include "panthor_gpu_regs.h"
+#include "panthor_hw.h"
+#include "panthor_pwr.h"
+#include "panthor_pwr_regs.h"
+
+#define GPU_PROD_ID_MAKE(arch_major, prod_major) \
+	(((arch_major) << 24) | (prod_major))
+
+/** struct panthor_hw_entry - HW arch major to panthor_hw binding entry */
+struct panthor_hw_entry {
+	/** @arch_min: Minimum supported architecture major value (inclusive) */
+	u8 arch_min;
+
+	/** @arch_max: Maximum supported architecture major value (inclusive) */
+	u8 arch_max;
+
+	/** @hwdev: Pointer to panthor_hw structure */
+	struct panthor_hw *hwdev;
+};
+
+static struct panthor_hw panthor_hw_arch_v10 = {
+	.ops = {
+		.soft_reset = panthor_gpu_soft_reset,
+		.l2_power_off = panthor_gpu_l2_power_off,
+		.l2_power_on = panthor_gpu_l2_power_on,
+		.power_changed_off = panthor_gpu_power_changed_off,
+		.power_changed_on = panthor_gpu_power_changed_on,
+	},
+};
+
+static struct panthor_hw panthor_hw_arch_v14 = {
+	.ops = {
+		.soft_reset = panthor_pwr_reset_soft,
+		.l2_power_off = panthor_pwr_l2_power_off,
+		.l2_power_on = panthor_pwr_l2_power_on,
+	},
+};
+
+static struct panthor_hw_entry panthor_hw_match[] = {
+	{
+		.arch_min = 10,
+		.arch_max = 13,
+		.hwdev = &panthor_hw_arch_v10,
+	},
+	{
+		.arch_min = 14,
+		.arch_max = 14,
+		.hwdev = &panthor_hw_arch_v14,
+	},
+};
+
+static int panthor_hw_set_power_tracing(struct device *dev, void *data)
+{
+	struct panthor_device *ptdev = dev_get_drvdata(dev);
+
+	if (!ptdev)
+		return -ENODEV;
+
+	if (!ptdev->hw)
+		return 0;
+
+	if (data) {
+		if (ptdev->hw->ops.power_changed_on)
+			return ptdev->hw->ops.power_changed_on(ptdev);
+	} else {
+		if (ptdev->hw->ops.power_changed_off)
+			ptdev->hw->ops.power_changed_off(ptdev);
+	}
+
+	return 0;
+}
+
+int panthor_hw_power_status_register(void)
+{
+	struct device_driver *drv;
+	int ret;
+
+	drv = driver_find("panthor", &platform_bus_type);
+	if (!drv)
+		return -ENODEV;
+
+	ret = driver_for_each_device(drv, NULL, (void *)true,
+				     panthor_hw_set_power_tracing);
+
+	return ret;
+}
+
+void panthor_hw_power_status_unregister(void)
+{
+	struct device_driver *drv;
+	int ret;
+
+	drv = driver_find("panthor", &platform_bus_type);
+	if (!drv)
+		return;
+
+	ret = driver_for_each_device(drv, NULL, NULL, panthor_hw_set_power_tracing);
+
+	/*
+	 * Ideally, it'd be possible to ask driver_for_each_device to hand us
+	 * another "start" to keep going after the failing device, but it
+	 * doesn't do that. Minor inconvenience in what is probably a bad day
+	 * on the computer already though.
+	 */
+	if (ret)
+		pr_warn("Couldn't mask power IRQ for at least one device: %pe\n",
+			ERR_PTR(ret));
+}
+
+static char *get_gpu_model_name(struct panthor_device *ptdev)
+{
+	const u32 gpu_id = ptdev->gpu_info.gpu_id;
+	const u32 product_id = GPU_PROD_ID_MAKE(GPU_ARCH_MAJOR(gpu_id),
+						GPU_PROD_MAJOR(gpu_id));
+	const bool ray_intersection = !!(ptdev->gpu_info.gpu_features &
+					 GPU_FEATURES_RAY_INTERSECTION);
+	const u8 shader_core_count = hweight64(ptdev->gpu_info.shader_present);
+
+	switch (product_id) {
+	case GPU_PROD_ID_MAKE(10, 2):
+		return "Mali-G710";
+	case GPU_PROD_ID_MAKE(10, 3):
+		return "Mali-G510";
+	case GPU_PROD_ID_MAKE(10, 4):
+		return "Mali-G310";
+	case GPU_PROD_ID_MAKE(10, 7):
+		return "Mali-G610";
+	case GPU_PROD_ID_MAKE(11, 2):
+		if (shader_core_count > 10 && ray_intersection)
+			return "Mali-G715-Immortalis";
+		else if (shader_core_count >= 7)
+			return "Mali-G715";
+
+		fallthrough;
+	case GPU_PROD_ID_MAKE(11, 3):
+		return "Mali-G615";
+	case GPU_PROD_ID_MAKE(12, 0):
+		if (shader_core_count >= 10 && ray_intersection)
+			return "Mali-G720-Immortalis";
+		else if (shader_core_count >= 6)
+			return "Mali-G720";
+
+		fallthrough;
+	case GPU_PROD_ID_MAKE(12, 1):
+		return "Mali-G620";
+	case GPU_PROD_ID_MAKE(13, 0):
+		if (shader_core_count >= 10 && ray_intersection)
+			return "Mali-G925-Immortalis";
+		else if (shader_core_count >= 6)
+			return "Mali-G725";
+
+		fallthrough;
+	case GPU_PROD_ID_MAKE(13, 1):
+		return "Mali-G625";
+	case GPU_PROD_ID_MAKE(14, 0):
+		return "Mali-G1-Ultra";
+	case GPU_PROD_ID_MAKE(14, 1):
+		return "Mali-G1-Premium";
+	case GPU_PROD_ID_MAKE(14, 3):
+		return "Mali-G1-Pro";
+	}
+
+	return "(Unknown Mali GPU)";
+}
+
+static int overload_shader_present(struct panthor_device *ptdev)
+{
+	u64 contents;
+	int ret;
+
+	ret = nvmem_cell_read_variable_le_u64(ptdev->base.dev, "shader-present",
+					      &contents);
+	if (!ret)
+		ptdev->gpu_info.shader_present = contents;
+	else if (ret == -ENOENT)
+		return 0;
+	else
+		return dev_err_probe(ptdev->base.dev, ret,
+				     "Failed to read shader-present nvmem cell\n");
+
+	return 0;
+}
+
+static int panthor_gpu_info_init(struct panthor_device *ptdev)
+{
+	unsigned int i;
+
+	void __iomem *gpu_iomem = ptdev->iomem + GPU_CONTROL_BASE;
+
+	ptdev->gpu_info.csf_id = gpu_read(gpu_iomem, GPU_CSF_ID);
+	ptdev->gpu_info.gpu_rev = gpu_read(gpu_iomem, GPU_REVID);
+	ptdev->gpu_info.core_features = gpu_read(gpu_iomem, GPU_CORE_FEATURES);
+	ptdev->gpu_info.l2_features = gpu_read(gpu_iomem, GPU_L2_FEATURES);
+	ptdev->gpu_info.tiler_features = gpu_read(gpu_iomem, GPU_TILER_FEATURES);
+	ptdev->gpu_info.mem_features = gpu_read(gpu_iomem, GPU_MEM_FEATURES);
+	ptdev->gpu_info.mmu_features = gpu_read(gpu_iomem, GPU_MMU_FEATURES);
+	ptdev->gpu_info.thread_features = gpu_read(gpu_iomem, GPU_THREAD_FEATURES);
+	ptdev->gpu_info.max_threads = gpu_read(gpu_iomem, GPU_THREAD_MAX_THREADS);
+	ptdev->gpu_info.thread_max_workgroup_size =
+		gpu_read(gpu_iomem, GPU_THREAD_MAX_WORKGROUP_SIZE);
+	ptdev->gpu_info.thread_max_barrier_size =
+		gpu_read(gpu_iomem, GPU_THREAD_MAX_BARRIER_SIZE);
+	ptdev->gpu_info.coherency_features = gpu_read(gpu_iomem, GPU_COHERENCY_FEATURES);
+	for (i = 0; i < 4; i++)
+		ptdev->gpu_info.texture_features[i] =
+			gpu_read(gpu_iomem, GPU_TEXTURE_FEATURES(i));
+
+	ptdev->gpu_info.as_present = gpu_read(gpu_iomem, GPU_AS_PRESENT);
+
+	/* Introduced in arch 11.x */
+	ptdev->gpu_info.gpu_features = gpu_read64(gpu_iomem, GPU_FEATURES);
+
+	if (panthor_hw_has_pwr_ctrl(ptdev)) {
+		void __iomem *pwr_iomem = gpu_iomem + PWR_CONTROL_BASE;
+
+		/* Introduced in arch 14.x */
+		ptdev->gpu_info.l2_present = gpu_read64(pwr_iomem, PWR_L2_PRESENT);
+		ptdev->gpu_info.tiler_present = gpu_read64(pwr_iomem, PWR_TILER_PRESENT);
+		ptdev->gpu_info.shader_present = gpu_read64(pwr_iomem, PWR_SHADER_PRESENT);
+	} else {
+		ptdev->gpu_info.shader_present = gpu_read64(gpu_iomem, GPU_SHADER_PRESENT);
+		ptdev->gpu_info.tiler_present = gpu_read64(gpu_iomem, GPU_TILER_PRESENT);
+		ptdev->gpu_info.l2_present = gpu_read64(gpu_iomem, GPU_L2_PRESENT);
+	}
+
+	return overload_shader_present(ptdev);
+}
+
+static int panthor_hw_info_init(struct panthor_device *ptdev)
+{
+	u32 major, minor, status;
+	int ret;
+
+	ret = panthor_gpu_info_init(ptdev);
+	if (ret)
+		return ret;
+
+	major = GPU_VER_MAJOR(ptdev->gpu_info.gpu_id);
+	minor = GPU_VER_MINOR(ptdev->gpu_info.gpu_id);
+	status = GPU_VER_STATUS(ptdev->gpu_info.gpu_id);
+
+	drm_info(&ptdev->base,
+		 "%s id 0x%x major 0x%x minor 0x%x status 0x%x",
+		 get_gpu_model_name(ptdev), ptdev->gpu_info.gpu_id >> 16,
+		 major, minor, status);
+
+	drm_info(&ptdev->base,
+		 "Features: L2:%#x Tiler:%#x Mem:%#x MMU:%#x AS:%#x",
+		 ptdev->gpu_info.l2_features,
+		 ptdev->gpu_info.tiler_features,
+		 ptdev->gpu_info.mem_features,
+		 ptdev->gpu_info.mmu_features,
+		 ptdev->gpu_info.as_present);
+
+	drm_info(&ptdev->base,
+		 "shader_present=0x%0llx l2_present=0x%0llx tiler_present=0x%0llx",
+		 ptdev->gpu_info.shader_present, ptdev->gpu_info.l2_present,
+		 ptdev->gpu_info.tiler_present);
+
+	return 0;
+}
+
+static int panthor_hw_bind_device(struct panthor_device *ptdev)
+{
+	struct panthor_hw *hdev = NULL;
+	const u32 arch_major = GPU_ARCH_MAJOR(ptdev->gpu_info.gpu_id);
+	int i = 0;
+
+	for (i = 0; i < ARRAY_SIZE(panthor_hw_match); i++) {
+		struct panthor_hw_entry *entry = &panthor_hw_match[i];
+
+		if (arch_major >= entry->arch_min && arch_major <= entry->arch_max) {
+			hdev = entry->hwdev;
+			break;
+		}
+	}
+
+	if (!hdev)
+		return -EOPNOTSUPP;
+
+	ptdev->hw = hdev;
+
+	return 0;
+}
+
+static int panthor_hw_gpu_id_init(struct panthor_device *ptdev)
+{
+	ptdev->gpu_info.gpu_id = gpu_read(ptdev->iomem, GPU_ID);
+	if (!ptdev->gpu_info.gpu_id)
+		return -ENXIO;
+
+	return 0;
+}
+
+int panthor_hw_init(struct panthor_device *ptdev)
+{
+	int ret = 0;
+
+	ret = panthor_hw_gpu_id_init(ptdev);
+	if (ret)
+		return ret;
+
+	ret = panthor_hw_bind_device(ptdev);
+	if (ret)
+		return ret;
+
+	return panthor_hw_info_init(ptdev);
+}

linux-7.2.3/drivers/gpu/drm/panthor/panthor_hw.h

@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0 or MIT */
+/* Copyright 2025 ARM Limited. All rights reserved. */
+
+#ifndef __PANTHOR_HW_H__
+#define __PANTHOR_HW_H__
+
+#include "panthor_device.h"
+#include "panthor_gpu_regs.h"
+
+/**
+ * struct panthor_hw_ops - HW operations that are specific to a GPU
+ */
+struct panthor_hw_ops {
+	/** @soft_reset: Soft reset function pointer */
+	int (*soft_reset)(struct panthor_device *ptdev);
+
+	/** @l2_power_off: L2 power off function pointer */
+	void (*l2_power_off)(struct panthor_device *ptdev);
+
+	/** @l2_power_on: L2 power on function pointer */
+	int (*l2_power_on)(struct panthor_device *ptdev);
+
+	/** @power_changed_on: Start listening to power change IRQs */
+	int (*power_changed_on)(struct panthor_device *ptdev);
+
+	/** @power_changed_off: Stop listening to power change IRQs */
+	void (*power_changed_off)(struct panthor_device *ptdev);
+};
+
+/**
+ * struct panthor_hw - GPU specific register mapping and functions
+ */
+struct panthor_hw {
+	/** @features: Bitmap containing panthor_hw_feature */
+
+	/** @ops: Panthor HW specific operations */
+	struct panthor_hw_ops ops;
+};
+
+int panthor_hw_init(struct panthor_device *ptdev);
+int panthor_hw_power_status_register(void);
+void panthor_hw_power_status_unregister(void);
+
+static inline int panthor_hw_soft_reset(struct panthor_device *ptdev)
+{
+	return ptdev->hw->ops.soft_reset(ptdev);
+}
+
+static inline int panthor_hw_l2_power_on(struct panthor_device *ptdev)
+{
+	return ptdev->hw->ops.l2_power_on(ptdev);
+}
+
+static inline void panthor_hw_l2_power_off(struct panthor_device *ptdev)
+{
+	ptdev->hw->ops.l2_power_off(ptdev);
+}
+
+static inline bool panthor_hw_has_pwr_ctrl(struct panthor_device *ptdev)
+{
+	return GPU_ARCH_MAJOR(ptdev->gpu_info.gpu_id) >= 14;
+}
+
+#endif /* __PANTHOR_HW_H__ */

linux-7.2.3/drivers/gpu/drm/panthor/panthor_mmu.h

@@ -0,0 +1,114 @@
+/* SPDX-License-Identifier: GPL-2.0 or MIT */
+/* Copyright 2019 Linaro, Ltd, Rob Herring <robh@kernel.org> */
+/* Copyright 2023 Collabora ltd. */
+/* Copyright 2025 ARM Limited. All rights reserved. */
+
+#ifndef __PANTHOR_MMU_H__
+#define __PANTHOR_MMU_H__
+
+#include <linux/dma-resv.h>
+
+struct drm_exec;
+struct drm_sched_job;
+struct drm_memory_stats;
+struct panthor_gem_object;
+struct panthor_heap_pool;
+struct panthor_vm;
+struct panthor_vma;
+struct panthor_mmu;
+
+int panthor_mmu_init(struct panthor_device *ptdev);
+void panthor_mmu_unplug(struct panthor_device *ptdev);
+void panthor_mmu_pre_reset(struct panthor_device *ptdev);
+void panthor_mmu_post_reset(struct panthor_device *ptdev);
+void panthor_mmu_suspend(struct panthor_device *ptdev);
+void panthor_mmu_resume(struct panthor_device *ptdev);
+
+int panthor_vm_map_bo_range(struct panthor_vm *vm, struct panthor_gem_object *bo,
+			    u64 offset, u64 size, u64 va, u32 flags);
+int panthor_vm_unmap_range(struct panthor_vm *vm, u64 va, u64 size);
+struct panthor_gem_object *
+panthor_vm_get_bo_for_va(struct panthor_vm *vm, u64 va, u64 *bo_offset);
+
+int panthor_vm_active(struct panthor_vm *vm);
+void panthor_vm_idle(struct panthor_vm *vm);
+u32 panthor_vm_page_size(struct panthor_vm *vm);
+int panthor_vm_as(struct panthor_vm *vm);
+
+struct panthor_heap_pool *
+panthor_vm_get_heap_pool(struct panthor_vm *vm, bool create);
+
+void panthor_vm_heaps_sizes(struct panthor_file *pfile, struct drm_memory_stats *stats);
+
+struct panthor_vm *panthor_vm_get(struct panthor_vm *vm);
+void panthor_vm_put(struct panthor_vm *vm);
+struct panthor_vm *panthor_vm_create(struct panthor_device *ptdev, bool for_mcu,
+				     u64 kernel_va_start, u64 kernel_va_size,
+				     u64 kernel_auto_va_start,
+				     u64 kernel_auto_va_size);
+
+void panthor_vm_update_bo_reclaim_lru_locked(struct panthor_gem_object *bo);
+int panthor_vm_evict_bo_mappings_locked(struct panthor_gem_object *bo);
+unsigned long
+panthor_mmu_reclaim_priv_bos(struct panthor_device *ptdev,
+			     unsigned int nr_to_scan, unsigned long *remaining,
+			     bool (*shrink)(struct drm_gem_object *,
+					    struct ww_acquire_ctx *));
+int panthor_vm_prepare_mapped_bos_resvs(struct drm_exec *exec,
+					struct panthor_vm *vm,
+					u32 slot_count);
+int panthor_vm_add_bos_resvs_deps_to_job(struct panthor_vm *vm,
+					 struct drm_sched_job *job);
+void panthor_vm_add_job_fence_to_bos_resvs(struct panthor_vm *vm,
+					   struct drm_sched_job *job);
+
+struct dma_resv *panthor_vm_resv(struct panthor_vm *vm);
+struct drm_gem_object *panthor_vm_root_gem(struct panthor_vm *vm);
+
+void panthor_vm_pool_destroy(struct panthor_file *pfile);
+int panthor_vm_pool_create(struct panthor_file *pfile);
+int panthor_vm_pool_create_vm(struct panthor_device *ptdev,
+			      struct panthor_vm_pool *pool,
+			      struct drm_panthor_vm_create *args);
+int panthor_vm_pool_destroy_vm(struct panthor_vm_pool *pool, u32 handle);
+struct panthor_vm *panthor_vm_pool_get_vm(struct panthor_vm_pool *pool, u32 handle);
+
+bool panthor_vm_has_unhandled_faults(struct panthor_vm *vm);
+bool panthor_vm_is_unusable(struct panthor_vm *vm);
+
+/*
+ * PANTHOR_VM_KERNEL_AUTO_VA: Use this magic address when you want the GEM
+ * logic to auto-allocate the virtual address in the reserved kernel VA range.
+ */
+#define PANTHOR_VM_KERNEL_AUTO_VA		~0ull
+
+int panthor_vm_alloc_va(struct panthor_vm *vm, u64 va, u64 size,
+			struct drm_mm_node *va_node);
+void panthor_vm_free_va(struct panthor_vm *vm, struct drm_mm_node *va_node);
+
+int panthor_vm_bind_exec_sync_op(struct drm_file *file,
+				 struct panthor_vm *vm,
+				 struct drm_panthor_vm_bind_op *op);
+
+struct drm_sched_job *
+panthor_vm_bind_job_create(struct drm_file *file,
+			   struct panthor_vm *vm,
+			   const struct drm_panthor_vm_bind_op *op);
+void panthor_vm_bind_job_put(struct drm_sched_job *job);
+int panthor_vm_bind_job_prepare_resvs(struct drm_exec *exec,
+				      struct drm_sched_job *job);
+void panthor_vm_bind_job_update_resvs(struct drm_exec *exec, struct drm_sched_job *job);
+
+void panthor_vm_update_resvs(struct panthor_vm *vm, struct drm_exec *exec,
+			     struct dma_fence *fence,
+			     enum dma_resv_usage private_usage,
+			     enum dma_resv_usage extobj_usage);
+
+int panthor_mmu_pt_cache_init(void);
+void panthor_mmu_pt_cache_fini(void);
+
+#ifdef CONFIG_DEBUG_FS
+void panthor_mmu_debugfs_init(struct drm_minor *minor);
+#endif
+
+#endif

linux-7.2.3/drivers/gpu/drm/panthor/panthor_mmu_regs.h

@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0 or MIT */
+/* Copyright 2026 ARM Limited. All rights reserved. */
+
+#ifndef __PANTHOR_MMU_REGS_H__
+#define __PANTHOR_MMU_REGS_H__
+
+/* MMU regs */
+
+#define MMU_INT_BASE					0x2000
+
+/* AS_COMMAND register commands */
+
+#define MMU_AS_BASE					0x2400
+
+#define MMU_AS_SHIFT					6
+#define MMU_AS(as)					((as) << MMU_AS_SHIFT)
+
+#define AS_TRANSTAB(as)					(MMU_AS(as) + 0x0)
+#define AS_MEMATTR(as)					(MMU_AS(as) + 0x8)
+#define   AS_MEMATTR_AARCH64_INNER_ALLOC_IMPL		(2 << 2)
+#define   AS_MEMATTR_AARCH64_INNER_ALLOC_EXPL(w, r)	((3 << 2) | \
+							 ((w) ? BIT(0) : 0) | \
+							 ((r) ? BIT(1) : 0))
+#define   AS_MEMATTR_AARCH64_SH_MIDGARD_INNER		(0 << 4)
+#define   AS_MEMATTR_AARCH64_SH_CPU_INNER		(1 << 4)
+#define   AS_MEMATTR_AARCH64_SH_CPU_INNER_SHADER_COH	(2 << 4)
+#define   AS_MEMATTR_AARCH64_SHARED			(0 << 6)
+#define   AS_MEMATTR_AARCH64_INNER_OUTER_NC		(1 << 6)
+#define   AS_MEMATTR_AARCH64_INNER_OUTER_WB		(2 << 6)
+#define   AS_MEMATTR_AARCH64_FAULT			(3 << 6)
+#define AS_LOCKADDR(as)					(MMU_AS(as) + 0x10)
+#define AS_COMMAND(as)					(MMU_AS(as) + 0x18)
+#define   AS_COMMAND_NOP				0
+#define   AS_COMMAND_UPDATE				1
+#define   AS_COMMAND_LOCK				2
+#define   AS_COMMAND_UNLOCK				3
+#define   AS_COMMAND_FLUSH_PT				4
+#define   AS_COMMAND_FLUSH_MEM				5
+#define   AS_LOCK_REGION_MIN_SIZE			(1ULL << 15)
+#define AS_FAULTSTATUS(as)				(MMU_AS(as) + 0x1C)
+#define  AS_FAULTSTATUS_ACCESS_TYPE_MASK		(0x3 << 8)
+#define  AS_FAULTSTATUS_ACCESS_TYPE_ATOMIC		(0x0 << 8)
+#define  AS_FAULTSTATUS_ACCESS_TYPE_EX			(0x1 << 8)
+#define  AS_FAULTSTATUS_ACCESS_TYPE_READ		(0x2 << 8)
+#define  AS_FAULTSTATUS_ACCESS_TYPE_WRITE		(0x3 << 8)
+#define AS_FAULTADDRESS(as)				(MMU_AS(as) + 0x20)
+#define AS_STATUS(as)					(MMU_AS(as) + 0x28)
+#define   AS_STATUS_AS_ACTIVE				BIT(0)
+#define AS_TRANSCFG(as)					(MMU_AS(as) + 0x30)
+#define   AS_TRANSCFG_ADRMODE_UNMAPPED			(1 << 0)
+#define   AS_TRANSCFG_ADRMODE_IDENTITY			(2 << 0)
+#define   AS_TRANSCFG_ADRMODE_AARCH64_4K		(6 << 0)
+#define   AS_TRANSCFG_ADRMODE_AARCH64_64K		(8 << 0)
+#define   AS_TRANSCFG_INA_BITS(x)			((x) << 6)
+#define   AS_TRANSCFG_OUTA_BITS(x)			((x) << 14)
+#define   AS_TRANSCFG_SL_CONCAT				BIT(22)
+#define   AS_TRANSCFG_PTW_MEMATTR_NC			(1 << 24)
+#define   AS_TRANSCFG_PTW_MEMATTR_WB			(2 << 24)
+#define   AS_TRANSCFG_PTW_SH_NS				(0 << 28)
+#define   AS_TRANSCFG_PTW_SH_OS				(2 << 28)
+#define   AS_TRANSCFG_PTW_SH_IS				(3 << 28)
+#define   AS_TRANSCFG_PTW_RA				BIT(30)
+#define   AS_TRANSCFG_DISABLE_HIER_AP			BIT(33)
+#define   AS_TRANSCFG_DISABLE_AF_FAULT			BIT(34)
+#define   AS_TRANSCFG_WXN				BIT(35)
+#define   AS_TRANSCFG_XREADABLE				BIT(36)
+#define AS_FAULTEXTRA(as)				(MMU_AS(as) + 0x38)
+
+#endif /* __PANTHOR_MMU_REGS_H__ */

linux-7.2.3/drivers/gpu/drm/panthor/panthor_pwr.c

@@ -0,0 +1,578 @@
+// SPDX-License-Identifier: GPL-2.0 or MIT
+/* Copyright 2025 ARM Limited. All rights reserved. */
+
+#include <linux/platform_device.h>
+#include <linux/interrupt.h>
+#include <linux/cleanup.h>
+#include <linux/iopoll.h>
+#include <linux/wait.h>
+
+#include <drm/drm_managed.h>
+#include <drm/drm_print.h>
+
+#include "panthor_device.h"
+#include "panthor_gpu_regs.h"
+#include "panthor_hw.h"
+#include "panthor_pwr.h"
+#include "panthor_pwr_regs.h"
+
+#define PWR_INTERRUPTS_MASK \
+	(PWR_IRQ_POWER_CHANGED_SINGLE | \
+	 PWR_IRQ_POWER_CHANGED_ALL | \
+	 PWR_IRQ_DELEGATION_CHANGED | \
+	 PWR_IRQ_RESET_COMPLETED | \
+	 PWR_IRQ_RETRACT_COMPLETED | \
+	 PWR_IRQ_INSPECT_COMPLETED | \
+	 PWR_IRQ_COMMAND_NOT_ALLOWED | \
+	 PWR_IRQ_COMMAND_INVALID)
+
+#define PWR_ALL_CORES_MASK		GENMASK_U64(63, 0)
+
+#define PWR_DOMAIN_MAX_BITS		16
+
+#define PWR_TRANSITION_TIMEOUT_US	(2ULL * USEC_PER_SEC)
+
+#define PWR_RETRACT_TIMEOUT_US		(2ULL * USEC_PER_MSEC)
+
+#define PWR_RESET_TIMEOUT_MS		500
+
+/**
+ * struct panthor_pwr - PWR_CONTROL block management data.
+ */
+struct panthor_pwr {
+	/** @iomem: CPU mapping of PWR_CONTROL iomem region */
+	void __iomem *iomem;
+
+	/** @irq: PWR irq. */
+	struct panthor_irq irq;
+
+	/** @reqs_lock: Lock protecting access to pending_reqs. */
+	spinlock_t reqs_lock;
+
+	/** @pending_reqs: Pending PWR requests. */
+	u32 pending_reqs;
+
+	/** @reqs_acked: PWR request wait queue. */
+	wait_queue_head_t reqs_acked;
+};
+
+static void panthor_pwr_irq_handler(struct panthor_device *ptdev, u32 status)
+{
+	struct panthor_pwr *pwr = ptdev->pwr;
+
+	spin_lock(&ptdev->pwr->reqs_lock);
+	gpu_write(pwr->irq.iomem, INT_CLEAR, status);
+
+	if (unlikely(status & PWR_IRQ_COMMAND_NOT_ALLOWED))
+		drm_err(&ptdev->base, "PWR_IRQ: COMMAND_NOT_ALLOWED");
+
+	if (unlikely(status & PWR_IRQ_COMMAND_INVALID))
+		drm_err(&ptdev->base, "PWR_IRQ: COMMAND_INVALID");
+
+	if (status & ptdev->pwr->pending_reqs) {
+		ptdev->pwr->pending_reqs &= ~status;
+		wake_up_all(&ptdev->pwr->reqs_acked);
+	}
+	spin_unlock(&ptdev->pwr->reqs_lock);
+}
+PANTHOR_IRQ_HANDLER(pwr, panthor_pwr_irq_handler);
+
+static void panthor_pwr_write_command(struct panthor_device *ptdev, u32 command, u64 args)
+{
+	struct panthor_pwr *pwr = ptdev->pwr;
+
+	if (args)
+		gpu_write64(pwr->iomem, PWR_CMDARG, args);
+
+	gpu_write(pwr->iomem, PWR_COMMAND, command);
+}
+
+static bool reset_irq_raised(struct panthor_device *ptdev)
+{
+	struct panthor_pwr *pwr = ptdev->pwr;
+
+	return gpu_read(pwr->irq.iomem, INT_RAWSTAT) & PWR_IRQ_RESET_COMPLETED;
+}
+
+static bool reset_pending(struct panthor_device *ptdev)
+{
+	return (ptdev->pwr->pending_reqs & PWR_IRQ_RESET_COMPLETED);
+}
+
+static int panthor_pwr_reset(struct panthor_device *ptdev, u32 reset_cmd)
+{
+	struct panthor_pwr *pwr = ptdev->pwr;
+
+	scoped_guard(spinlock_irqsave, &ptdev->pwr->reqs_lock) {
+		if (reset_pending(ptdev)) {
+			drm_WARN(&ptdev->base, 1, "Reset already pending");
+		} else {
+			ptdev->pwr->pending_reqs |= PWR_IRQ_RESET_COMPLETED;
+			gpu_write(pwr->irq.iomem, INT_CLEAR, PWR_IRQ_RESET_COMPLETED);
+			panthor_pwr_write_command(ptdev, reset_cmd, 0);
+		}
+	}
+
+	if (!wait_event_timeout(ptdev->pwr->reqs_acked, !reset_pending(ptdev),
+				msecs_to_jiffies(PWR_RESET_TIMEOUT_MS))) {
+		guard(spinlock_irqsave)(&ptdev->pwr->reqs_lock);
+
+		if (reset_pending(ptdev) && !reset_irq_raised(ptdev)) {
+			drm_err(&ptdev->base, "RESET timed out (0x%x)", reset_cmd);
+			return -ETIMEDOUT;
+		}
+
+		ptdev->pwr->pending_reqs &= ~PWR_IRQ_RESET_COMPLETED;
+	}
+
+	return 0;
+}
+
+static const char *get_domain_name(u8 domain)
+{
+	switch (domain) {
+	case PWR_COMMAND_DOMAIN_L2:
+		return "L2";
+	case PWR_COMMAND_DOMAIN_TILER:
+		return "Tiler";
+	case PWR_COMMAND_DOMAIN_SHADER:
+		return "Shader";
+	case PWR_COMMAND_DOMAIN_BASE:
+		return "Base";
+	case PWR_COMMAND_DOMAIN_STACK:
+		return "Stack";
+	}
+	return "Unknown";
+}
+
+static u32 get_domain_base(u8 domain)
+{
+	switch (domain) {
+	case PWR_COMMAND_DOMAIN_L2:
+		return PWR_L2_PRESENT;
+	case PWR_COMMAND_DOMAIN_TILER:
+		return PWR_TILER_PRESENT;
+	case PWR_COMMAND_DOMAIN_SHADER:
+		return PWR_SHADER_PRESENT;
+	case PWR_COMMAND_DOMAIN_BASE:
+		return PWR_BASE_PRESENT;
+	case PWR_COMMAND_DOMAIN_STACK:
+		return PWR_STACK_PRESENT;
+	}
+	return 0;
+}
+
+static u32 get_domain_ready_reg(u32 domain)
+{
+	return get_domain_base(domain) + (PWR_L2_READY - PWR_L2_PRESENT);
+}
+
+static u32 get_domain_pwrtrans_reg(u32 domain)
+{
+	return get_domain_base(domain) + (PWR_L2_PWRTRANS - PWR_L2_PRESENT);
+}
+
+static bool is_valid_domain(u32 domain)
+{
+	return get_domain_base(domain) != 0;
+}
+
+static bool has_rtu(struct panthor_device *ptdev)
+{
+	return ptdev->gpu_info.gpu_features & GPU_FEATURES_RAY_TRAVERSAL;
+}
+
+static u8 get_domain_subdomain(struct panthor_device *ptdev, u32 domain)
+{
+	if (domain == PWR_COMMAND_DOMAIN_SHADER && has_rtu(ptdev))
+		return PWR_COMMAND_SUBDOMAIN_RTU;
+
+	return 0;
+}
+
+static int panthor_pwr_domain_wait_transition(struct panthor_device *ptdev, u32 domain,
+					      u32 timeout_us)
+{
+	struct panthor_pwr *pwr = ptdev->pwr;
+	u32 pwrtrans_reg = get_domain_pwrtrans_reg(domain);
+	u64 val;
+	int ret = 0;
+
+	ret = gpu_read64_poll_timeout(pwr->iomem, pwrtrans_reg, val, !(PWR_ALL_CORES_MASK & val), 100,
+				      timeout_us);
+	if (ret) {
+		drm_err(&ptdev->base, "%s domain power in transition, pwrtrans(0x%llx)",
+			get_domain_name(domain), val);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void panthor_pwr_debug_info_show(struct panthor_device *ptdev)
+{
+	struct panthor_pwr *pwr = ptdev->pwr;
+
+	drm_info(&ptdev->base, "GPU_FEATURES:    0x%016llx", ptdev->gpu_info.gpu_features);
+	drm_info(&ptdev->base, "PWR_STATUS:      0x%016llx", gpu_read64(pwr->iomem, PWR_STATUS));
+	drm_info(&ptdev->base, "L2_PRESENT:      0x%016llx", gpu_read64(pwr->iomem, PWR_L2_PRESENT));
+	drm_info(&ptdev->base, "L2_PWRTRANS:     0x%016llx", gpu_read64(pwr->iomem, PWR_L2_PWRTRANS));
+	drm_info(&ptdev->base, "L2_READY:        0x%016llx", gpu_read64(pwr->iomem, PWR_L2_READY));
+	drm_info(&ptdev->base, "TILER_PRESENT:   0x%016llx", gpu_read64(pwr->iomem, PWR_TILER_PRESENT));
+	drm_info(&ptdev->base, "TILER_PWRTRANS:  0x%016llx", gpu_read64(pwr->iomem, PWR_TILER_PWRTRANS));
+	drm_info(&ptdev->base, "TILER_READY:     0x%016llx", gpu_read64(pwr->iomem, PWR_TILER_READY));
+	drm_info(&ptdev->base, "SHADER_PRESENT:  0x%016llx", gpu_read64(pwr->iomem, PWR_SHADER_PRESENT));
+	drm_info(&ptdev->base, "SHADER_PWRTRANS: 0x%016llx", gpu_read64(pwr->iomem, PWR_SHADER_PWRTRANS));
+	drm_info(&ptdev->base, "SHADER_READY:    0x%016llx", gpu_read64(pwr->iomem, PWR_SHADER_READY));
+}
+
+static int panthor_pwr_domain_transition(struct panthor_device *ptdev, u32 cmd, u32 domain,
+					 u64 mask, u32 timeout_us)
+{
+	struct panthor_pwr *pwr = ptdev->pwr;
+	u32 ready_reg = get_domain_ready_reg(domain);
+	u32 pwr_cmd = PWR_COMMAND_DEF(cmd, domain, get_domain_subdomain(ptdev, domain));
+	u64 expected_val = 0;
+	u64 val;
+	int ret = 0;
+
+	if (drm_WARN_ON(&ptdev->base, !is_valid_domain(domain)))
+		return -EINVAL;
+
+	switch (cmd) {
+	case PWR_COMMAND_POWER_DOWN:
+		expected_val = 0;
+		break;
+	case PWR_COMMAND_POWER_UP:
+		expected_val = mask;
+		break;
+	default:
+		drm_err(&ptdev->base, "Invalid power domain transition command (0x%x)", cmd);
+		return -EINVAL;
+	}
+
+	ret = panthor_pwr_domain_wait_transition(ptdev, domain, timeout_us);
+	if (ret)
+		return ret;
+
+	/* domain already in target state, return early */
+	if ((gpu_read64(pwr->iomem, ready_reg) & mask) == expected_val)
+		return 0;
+
+	panthor_pwr_write_command(ptdev, pwr_cmd, mask);
+
+	ret = gpu_read64_poll_timeout(pwr->iomem, ready_reg, val, (mask & val) == expected_val,
+				      100, timeout_us);
+	if (ret) {
+		drm_err(&ptdev->base,
+			"timeout waiting on %s power domain transition, cmd(0x%x), arg(0x%llx)",
+			get_domain_name(domain), pwr_cmd, mask);
+		panthor_pwr_debug_info_show(ptdev);
+		return ret;
+	}
+
+	return 0;
+}
+
+#define panthor_pwr_domain_power_off(__ptdev, __domain, __mask, __timeout_us)            \
+	panthor_pwr_domain_transition(__ptdev, PWR_COMMAND_POWER_DOWN, __domain, __mask, \
+				      __timeout_us)
+
+#define panthor_pwr_domain_power_on(__ptdev, __domain, __mask, __timeout_us) \
+	panthor_pwr_domain_transition(__ptdev, PWR_COMMAND_POWER_UP, __domain, __mask, __timeout_us)
+
+/**
+ * retract_domain() - Retract control of a domain from MCU
+ * @ptdev: Device.
+ * @domain: Domain to retract the control
+ *
+ * Retracting L2 domain is not expected since it won't be delegated.
+ *
+ * Return: 0 on success or retracted already.
+ *         -EPERM if domain is L2.
+ *         A negative error code otherwise.
+ */
+static int retract_domain(struct panthor_device *ptdev, u32 domain)
+{
+	struct panthor_pwr *pwr = ptdev->pwr;
+	const u32 pwr_cmd = PWR_COMMAND_DEF(PWR_COMMAND_RETRACT, domain, 0);
+	const u64 pwr_status = gpu_read64(pwr->iomem, PWR_STATUS);
+	const u64 delegated_mask = PWR_STATUS_DOMAIN_DELEGATED(domain);
+	const u64 allow_mask = PWR_STATUS_DOMAIN_ALLOWED(domain);
+	u64 val;
+	int ret;
+
+	if (drm_WARN_ON(&ptdev->base, domain == PWR_COMMAND_DOMAIN_L2))
+		return -EPERM;
+
+	ret = gpu_read64_poll_timeout(pwr->iomem, PWR_STATUS, val,
+				      !(PWR_STATUS_RETRACT_PENDING & val), 0,
+				      PWR_RETRACT_TIMEOUT_US);
+	if (ret) {
+		drm_err(&ptdev->base, "%s domain retract pending", get_domain_name(domain));
+		return ret;
+	}
+
+	if (!(pwr_status & delegated_mask)) {
+		drm_dbg(&ptdev->base, "%s domain already retracted", get_domain_name(domain));
+		return 0;
+	}
+
+	panthor_pwr_write_command(ptdev, pwr_cmd, 0);
+
+	/*
+	 * On successful retraction
+	 * allow-flag will be set with delegated-flag being cleared.
+	 */
+	ret = gpu_read64_poll_timeout(pwr->iomem, PWR_STATUS, val,
+				      ((delegated_mask | allow_mask) & val) == allow_mask, 10,
+				      PWR_TRANSITION_TIMEOUT_US);
+	if (ret) {
+		drm_err(&ptdev->base, "Retracting %s domain timeout, cmd(0x%x)",
+			get_domain_name(domain), pwr_cmd);
+		return ret;
+	}
+
+	return 0;
+}
+
+/**
+ * delegate_domain() - Delegate control of a domain to MCU
+ * @ptdev: Device.
+ * @domain: Domain to delegate the control
+ *
+ * Delegating L2 domain is prohibited.
+ *
+ * Return:
+ * *       0 on success or delegated already.
+ * *       -EPERM if domain is L2.
+ * *       A negative error code otherwise.
+ */
+static int delegate_domain(struct panthor_device *ptdev, u32 domain)
+{
+	struct panthor_pwr *pwr = ptdev->pwr;
+	const u32 pwr_cmd = PWR_COMMAND_DEF(PWR_COMMAND_DELEGATE, domain, 0);
+	const u64 pwr_status = gpu_read64(pwr->iomem, PWR_STATUS);
+	const u64 allow_mask = PWR_STATUS_DOMAIN_ALLOWED(domain);
+	const u64 delegated_mask = PWR_STATUS_DOMAIN_DELEGATED(domain);
+	u64 val;
+	int ret;
+
+	if (drm_WARN_ON(&ptdev->base, domain == PWR_COMMAND_DOMAIN_L2))
+		return -EPERM;
+
+	/* Already delegated, exit early */
+	if (pwr_status & delegated_mask)
+		return 0;
+
+	/* Check if the command is allowed before delegating. */
+	if (!(pwr_status & allow_mask)) {
+		drm_warn(&ptdev->base, "Delegating %s domain not allowed", get_domain_name(domain));
+		return -EPERM;
+	}
+
+	ret = panthor_pwr_domain_wait_transition(ptdev, domain, PWR_TRANSITION_TIMEOUT_US);
+	if (ret)
+		return ret;
+
+	panthor_pwr_write_command(ptdev, pwr_cmd, 0);
+
+	/*
+	 * On successful delegation
+	 * allow-flag will be cleared with delegated-flag being set.
+	 */
+	ret = gpu_read64_poll_timeout(pwr->iomem, PWR_STATUS, val,
+				      ((delegated_mask | allow_mask) & val) == delegated_mask,
+				      10, PWR_TRANSITION_TIMEOUT_US);
+	if (ret) {
+		drm_err(&ptdev->base, "Delegating %s domain timeout, cmd(0x%x)",
+			get_domain_name(domain), pwr_cmd);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int panthor_pwr_delegate_domains(struct panthor_device *ptdev)
+{
+	int ret;
+
+	if (!ptdev->pwr)
+		return 0;
+
+	ret = delegate_domain(ptdev, PWR_COMMAND_DOMAIN_SHADER);
+	if (ret)
+		return ret;
+
+	ret = delegate_domain(ptdev, PWR_COMMAND_DOMAIN_TILER);
+	if (ret)
+		goto err_retract_shader;
+
+	return 0;
+
+err_retract_shader:
+	retract_domain(ptdev, PWR_COMMAND_DOMAIN_SHADER);
+
+	return ret;
+}
+
+/**
+ * panthor_pwr_domain_force_off - Forcefully power down a domain.
+ * @ptdev: Device.
+ * @domain: Domain to forcefully power down.
+ *
+ * This function will attempt to retract and power off the requested power
+ * domain. However, if retraction fails, the operation is aborted. If power off
+ * fails, the domain will remain retracted and under the host control.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+static int panthor_pwr_domain_force_off(struct panthor_device *ptdev, u32 domain)
+{
+	struct panthor_pwr *pwr = ptdev->pwr;
+	const u64 domain_ready = gpu_read64(pwr->iomem, get_domain_ready_reg(domain));
+	int ret;
+
+	/* Domain already powered down, early exit. */
+	if (!domain_ready)
+		return 0;
+
+	/* Domain has to be in host control to issue power off command. */
+	ret = retract_domain(ptdev, domain);
+	if (ret)
+		return ret;
+
+	return panthor_pwr_domain_power_off(ptdev, domain, domain_ready, PWR_TRANSITION_TIMEOUT_US);
+}
+
+void panthor_pwr_unplug(struct panthor_device *ptdev)
+{
+	unsigned long flags;
+
+	if (!ptdev->pwr)
+		return;
+
+	/* Make sure the IRQ handler is not running after that point. */
+	if (!IS_ENABLED(CONFIG_PM) || pm_runtime_active(ptdev->base.dev))
+		panthor_pwr_irq_suspend(&ptdev->pwr->irq);
+
+	/* Wake-up all waiters. */
+	spin_lock_irqsave(&ptdev->pwr->reqs_lock, flags);
+	ptdev->pwr->pending_reqs = 0;
+	wake_up_all(&ptdev->pwr->reqs_acked);
+	spin_unlock_irqrestore(&ptdev->pwr->reqs_lock, flags);
+}
+
+int panthor_pwr_init(struct panthor_device *ptdev)
+{
+	struct panthor_pwr *pwr;
+	int err, irq;
+
+	if (!panthor_hw_has_pwr_ctrl(ptdev))
+		return 0;
+
+	pwr = drmm_kzalloc(&ptdev->base, sizeof(*pwr), GFP_KERNEL);
+	if (!pwr)
+		return -ENOMEM;
+
+	pwr->iomem = ptdev->iomem + PWR_CONTROL_BASE;
+	spin_lock_init(&pwr->reqs_lock);
+	init_waitqueue_head(&pwr->reqs_acked);
+	ptdev->pwr = pwr;
+
+	irq = platform_get_irq_byname(to_platform_device(ptdev->base.dev), "gpu");
+	if (irq < 0)
+		return irq;
+
+	err = panthor_request_pwr_irq(ptdev, &pwr->irq, irq,
+				      pwr->iomem + PWR_INT_BASE);
+	if (err)
+		return err;
+
+	panthor_pwr_irq_enable_events(&pwr->irq, PWR_INTERRUPTS_MASK);
+	panthor_pwr_irq_resume(&pwr->irq);
+	return 0;
+}
+
+int panthor_pwr_reset_soft(struct panthor_device *ptdev)
+{
+	struct panthor_pwr *pwr = ptdev->pwr;
+
+	if (!(gpu_read64(pwr->iomem, PWR_STATUS) & PWR_STATUS_ALLOW_SOFT_RESET)) {
+		drm_err(&ptdev->base, "RESET_SOFT not allowed");
+		return -EOPNOTSUPP;
+	}
+
+	return panthor_pwr_reset(ptdev, PWR_COMMAND_RESET_SOFT);
+}
+
+void panthor_pwr_l2_power_off(struct panthor_device *ptdev)
+{
+	struct panthor_pwr *pwr = ptdev->pwr;
+	const u64 l2_allow_mask = PWR_STATUS_DOMAIN_ALLOWED(PWR_COMMAND_DOMAIN_L2);
+	const u64 pwr_status = gpu_read64(pwr->iomem, PWR_STATUS);
+
+	/* Abort if L2 power off constraints are not satisfied */
+	if (!(pwr_status & l2_allow_mask)) {
+		drm_warn(&ptdev->base, "Power off L2 domain not allowed");
+		return;
+	}
+
+	/* It is expected that when halting the MCU, it would power down its
+	 * delegated domains. However, an unresponsive or hung MCU may not do
+	 * so, which is why we need to check and retract the domains back into
+	 * host control to be powered down in the right order before powering
+	 * down the L2.
+	 */
+	if (panthor_pwr_domain_force_off(ptdev, PWR_COMMAND_DOMAIN_TILER))
+		return;
+
+	if (panthor_pwr_domain_force_off(ptdev, PWR_COMMAND_DOMAIN_SHADER))
+		return;
+
+	panthor_pwr_domain_power_off(ptdev, PWR_COMMAND_DOMAIN_L2, ptdev->gpu_info.l2_present,
+				     PWR_TRANSITION_TIMEOUT_US);
+}
+
+int panthor_pwr_l2_power_on(struct panthor_device *ptdev)
+{
+	struct panthor_pwr *pwr = ptdev->pwr;
+	const u32 pwr_status = gpu_read64(pwr->iomem, PWR_STATUS);
+	const u32 l2_allow_mask = PWR_STATUS_DOMAIN_ALLOWED(PWR_COMMAND_DOMAIN_L2);
+	int ret;
+
+	if ((pwr_status & l2_allow_mask) == 0) {
+		drm_warn(&ptdev->base, "Power on L2 domain not allowed");
+		return -EPERM;
+	}
+
+	ret = panthor_pwr_domain_power_on(ptdev, PWR_COMMAND_DOMAIN_L2, ptdev->gpu_info.l2_present,
+					  PWR_TRANSITION_TIMEOUT_US);
+	if (ret)
+		return ret;
+
+	/* Delegate control of the shader and tiler power domains to the MCU as
+	 * it can better manage which shader/tiler cores need to be powered up
+	 * or can be powered down based on currently running jobs.
+	 *
+	 * If the shader and tiler domains are already delegated to the MCU,
+	 * this call would just return early.
+	 */
+	return panthor_pwr_delegate_domains(ptdev);
+}
+
+void panthor_pwr_suspend(struct panthor_device *ptdev)
+{
+	if (!ptdev->pwr)
+		return;
+
+	panthor_pwr_irq_suspend(&ptdev->pwr->irq);
+}
+
+void panthor_pwr_resume(struct panthor_device *ptdev)
+{
+	if (!ptdev->pwr)
+		return;
+
+	panthor_pwr_irq_resume(&ptdev->pwr->irq);
+}

linux-7.2.3/drivers/gpu/drm/panthor/panthor_pwr.h

@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 or MIT */
+/* Copyright 2025 ARM Limited. All rights reserved. */
+
+#ifndef __PANTHOR_PWR_H__
+#define __PANTHOR_PWR_H__
+
+struct panthor_device;
+
+void panthor_pwr_unplug(struct panthor_device *ptdev);
+
+int panthor_pwr_init(struct panthor_device *ptdev);
+
+int panthor_pwr_reset_soft(struct panthor_device *ptdev);
+
+void panthor_pwr_l2_power_off(struct panthor_device *ptdev);
+
+int panthor_pwr_l2_power_on(struct panthor_device *ptdev);
+
+void panthor_pwr_suspend(struct panthor_device *ptdev);
+
+void panthor_pwr_resume(struct panthor_device *ptdev);
+
+#endif /* __PANTHOR_PWR_H__ */

linux-7.2.3/drivers/gpu/drm/panthor/panthor_pwr_regs.h

@@ -0,0 +1,79 @@
+/* SPDX-License-Identifier: GPL-2.0 or MIT */
+/* Copyright 2026 ARM Limited. All rights reserved. */
+
+#ifndef __PANTHOR_PWR_REGS_H__
+#define __PANTHOR_PWR_REGS_H__
+
+#define PWR_CONTROL_BASE				0x800
+
+#define PWR_INT_BASE					0x0
+#define   PWR_IRQ_POWER_CHANGED_SINGLE			BIT(0)
+#define   PWR_IRQ_POWER_CHANGED_ALL			BIT(1)
+#define   PWR_IRQ_DELEGATION_CHANGED			BIT(2)
+#define   PWR_IRQ_RESET_COMPLETED			BIT(3)
+#define   PWR_IRQ_RETRACT_COMPLETED			BIT(4)
+#define   PWR_IRQ_INSPECT_COMPLETED			BIT(5)
+#define   PWR_IRQ_COMMAND_NOT_ALLOWED			BIT(30)
+#define   PWR_IRQ_COMMAND_INVALID			BIT(31)
+
+#define PWR_STATUS					0x20
+#define   PWR_STATUS_ALLOW_L2				BIT_U64(0)
+#define   PWR_STATUS_ALLOW_TILER			BIT_U64(1)
+#define   PWR_STATUS_ALLOW_SHADER			BIT_U64(8)
+#define   PWR_STATUS_ALLOW_BASE				BIT_U64(14)
+#define   PWR_STATUS_ALLOW_STACK			BIT_U64(15)
+#define   PWR_STATUS_DOMAIN_ALLOWED(x)			BIT_U64(x)
+#define   PWR_STATUS_DELEGATED_L2			BIT_U64(16)
+#define   PWR_STATUS_DELEGATED_TILER			BIT_U64(17)
+#define   PWR_STATUS_DELEGATED_SHADER			BIT_U64(24)
+#define   PWR_STATUS_DELEGATED_BASE			BIT_U64(30)
+#define   PWR_STATUS_DELEGATED_STACK			BIT_U64(31)
+#define   PWR_STATUS_DELEGATED_SHIFT			16
+#define   PWR_STATUS_DOMAIN_DELEGATED(x)		BIT_U64((x) + PWR_STATUS_DELEGATED_SHIFT)
+#define   PWR_STATUS_ALLOW_SOFT_RESET			BIT_U64(33)
+#define   PWR_STATUS_ALLOW_FAST_RESET			BIT_U64(34)
+#define   PWR_STATUS_POWER_PENDING			BIT_U64(41)
+#define   PWR_STATUS_RESET_PENDING			BIT_U64(42)
+#define   PWR_STATUS_RETRACT_PENDING			BIT_U64(43)
+#define   PWR_STATUS_INSPECT_PENDING			BIT_U64(44)
+
+#define PWR_COMMAND					0x28
+#define   PWR_COMMAND_POWER_UP				0x10
+#define   PWR_COMMAND_POWER_DOWN			0x11
+#define   PWR_COMMAND_DELEGATE				0x20
+#define   PWR_COMMAND_RETRACT				0x21
+#define   PWR_COMMAND_RESET_SOFT			0x31
+#define   PWR_COMMAND_RESET_FAST			0x32
+#define   PWR_COMMAND_INSPECT				0xF0
+#define   PWR_COMMAND_DOMAIN_L2				0
+#define   PWR_COMMAND_DOMAIN_TILER			1
+#define   PWR_COMMAND_DOMAIN_SHADER			8
+#define   PWR_COMMAND_DOMAIN_BASE			14
+#define   PWR_COMMAND_DOMAIN_STACK			15
+#define   PWR_COMMAND_SUBDOMAIN_RTU			BIT(0)
+#define   PWR_COMMAND_DEF(cmd, domain, subdomain)	\
+	(((subdomain) << 16) | ((domain) << 8) | (cmd))
+
+#define PWR_CMDARG					0x30
+
+#define PWR_L2_PRESENT					0x100
+#define PWR_L2_READY					0x108
+#define PWR_L2_PWRTRANS					0x110
+#define PWR_L2_PWRACTIVE				0x118
+#define PWR_TILER_PRESENT				0x140
+#define PWR_TILER_READY					0x148
+#define PWR_TILER_PWRTRANS				0x150
+#define PWR_TILER_PWRACTIVE				0x158
+#define PWR_SHADER_PRESENT				0x200
+#define PWR_SHADER_READY				0x208
+#define PWR_SHADER_PWRTRANS				0x210
+#define PWR_SHADER_PWRACTIVE				0x218
+#define PWR_BASE_PRESENT				0x380
+#define PWR_BASE_READY					0x388
+#define PWR_BASE_PWRTRANS				0x390
+#define PWR_BASE_PWRACTIVE				0x398
+#define PWR_STACK_PRESENT				0x3c0
+#define PWR_STACK_READY					0x3c8
+#define PWR_STACK_PWRTRANS				0x3d0
+
+#endif /* __PANTHOR_PWR_REGS_H__ */

linux-7.2.3/drivers/gpu/drm/panthor/panthor_sched.h

@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 or MIT */
+/* Copyright 2023 Collabora ltd. */
+
+#ifndef __PANTHOR_SCHED_H__
+#define __PANTHOR_SCHED_H__
+
+struct drm_exec;
+struct dma_fence;
+struct drm_file;
+struct drm_gem_object;
+struct drm_sched_job;
+struct drm_memory_stats;
+struct drm_panthor_group_create;
+struct drm_panthor_queue_create;
+struct drm_panthor_group_get_state;
+struct drm_panthor_queue_submit;
+struct panthor_device;
+struct panthor_file;
+struct panthor_group_pool;
+struct panthor_job;
+
+int panthor_group_create(struct panthor_file *pfile,
+			 const struct drm_panthor_group_create *group_args,
+			 const struct drm_panthor_queue_create *queue_args,
+			 u64 drm_client_id);
+int panthor_group_destroy(struct panthor_file *pfile, u32 group_handle);
+int panthor_group_get_state(struct panthor_file *pfile,
+			    struct drm_panthor_group_get_state *get_state);
+
+struct drm_sched_job *
+panthor_job_create(struct panthor_file *pfile,
+		   u16 group_handle,
+		   const struct drm_panthor_queue_submit *qsubmit,
+		   u64 drm_client_id);
+struct drm_sched_job *panthor_job_get(struct drm_sched_job *job);
+struct panthor_vm *panthor_job_vm(struct drm_sched_job *sched_job);
+void panthor_job_put(struct drm_sched_job *job);
+void panthor_job_update_resvs(struct drm_exec *exec, struct drm_sched_job *job);
+
+int panthor_group_pool_create(struct panthor_file *pfile);
+void panthor_group_pool_destroy(struct panthor_file *pfile);
+void panthor_fdinfo_gather_group_mem_info(struct panthor_file *pfile,
+					  struct drm_memory_stats *stats);
+
+int panthor_sched_init(struct panthor_device *ptdev);
+void panthor_sched_unplug(struct panthor_device *ptdev);
+void panthor_sched_pre_reset(struct panthor_device *ptdev);
+void panthor_sched_post_reset(struct panthor_device *ptdev, bool reset_failed);
+void panthor_sched_suspend(struct panthor_device *ptdev);
+void panthor_sched_resume(struct panthor_device *ptdev);
+
+void panthor_sched_report_mmu_fault(struct panthor_device *ptdev);
+void panthor_sched_prepare_for_vm_destruction(struct panthor_device *ptdev);
+void panthor_sched_report_fw_events(struct panthor_device *ptdev, u32 events);
+
+void panthor_fdinfo_gather_group_samples(struct panthor_file *pfile);
+
+#endif

linux-7.2.3/drivers/gpu/drm/panthor/panthor_trace.h

@@ -0,0 +1,86 @@
+/* SPDX-License-Identifier: GPL-2.0 or MIT */
+/* Copyright 2025 Collabora ltd. */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM panthor
+
+#if !defined(__PANTHOR_TRACE_H__) || defined(TRACE_HEADER_MULTI_READ)
+#define __PANTHOR_TRACE_H__
+
+#include <linux/tracepoint.h>
+#include <linux/types.h>
+
+#include "panthor_hw.h"
+
+/**
+ * gpu_power_status - called whenever parts of GPU hardware are turned on or off
+ * @dev: pointer to the &struct device, for printing the device name
+ * @shader_bitmap: bitmap where a high bit indicates the shader core at a given
+ *                 bit index is on, and a low bit indicates a shader core is
+ *                 either powered off or absent
+ * @tiler_bitmap: bitmap where a high bit indicates the tiler unit at a given
+ *                bit index is on, and a low bit indicates a tiler unit is
+ *                either powered off or absent
+ * @l2_bitmap: bitmap where a high bit indicates the L2 cache at a given bit
+ *             index is on, and a low bit indicates the L2 cache is either
+ *             powered off or absent
+ */
+TRACE_EVENT_FN(gpu_power_status,
+	TP_PROTO(const struct device *dev, u64 shader_bitmap, u64 tiler_bitmap,
+		 u64 l2_bitmap),
+	TP_ARGS(dev, shader_bitmap, tiler_bitmap, l2_bitmap),
+	TP_STRUCT__entry(
+		__string(dev_name, dev_name(dev))
+		__field(u64, shader_bitmap)
+		__field(u64, tiler_bitmap)
+		__field(u64, l2_bitmap)
+	),
+	TP_fast_assign(
+		__assign_str(dev_name);
+		__entry->shader_bitmap	= shader_bitmap;
+		__entry->tiler_bitmap	= tiler_bitmap;
+		__entry->l2_bitmap	= l2_bitmap;
+	),
+	TP_printk("%s: shader_bitmap=0x%llx tiler_bitmap=0x%llx l2_bitmap=0x%llx",
+		  __get_str(dev_name), __entry->shader_bitmap, __entry->tiler_bitmap,
+		  __entry->l2_bitmap
+	),
+	panthor_hw_power_status_register, panthor_hw_power_status_unregister
+);
+
+/**
+ * gpu_job_irq - called after a job interrupt from firmware completes
+ * @dev: pointer to the &struct device, for printing the device name
+ * @events: bitmask of BIT(CSG id) | BIT(31) for a global event
+ * @duration_ns: Nanoseconds between job IRQ handler entry and exit
+ *
+ * The panthor_job_irq_handler() function instrumented by this tracepoint exits
+ * once it has queued the firmware interrupts for processing, not when the
+ * firmware interrupts are fully processed. This tracepoint allows for debugging
+ * issues with delays in the workqueue's processing of events.
+ */
+TRACE_EVENT(gpu_job_irq,
+	TP_PROTO(const struct device *dev, u32 events, u32 duration_ns),
+	TP_ARGS(dev, events, duration_ns),
+	TP_STRUCT__entry(
+		__string(dev_name, dev_name(dev))
+		__field(u32, events)
+		__field(u32, duration_ns)
+	),
+	TP_fast_assign(
+		__assign_str(dev_name);
+		__entry->events		= events;
+		__entry->duration_ns	= duration_ns;
+	),
+	TP_printk("%s: events=0x%x duration_ns=%d", __get_str(dev_name),
+		  __entry->events, __entry->duration_ns)
+);
+
+#endif /* __PANTHOR_TRACE_H__ */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE panthor_trace
+
+#include <trace/define_trace.h>