diff options
author | Boris Brezillon <boris.brezillon@collabora.com> | 2024-10-30 16:27:08 +0100 |
---|---|---|
committer | Boris Brezillon <boris.brezillon@collabora.com> | 2024-10-30 16:27:08 +0100 |
commit | e360704e0e4acb5163ecf3cac0cbe83fdd1f2fda (patch) | |
tree | 2791761d240e633efa5cde272e58999d2d9fce10 | |
parent | c3646d06846448fb2437680bb420c243a833c653 (diff) |
2024y-10m-30d-15h-25m-59s UTC: drm-tip rerere cache update
git version 2.46.2
-rw-r--r-- | rr-cache/9d16c377d811118cc2433a0be1ca2947fd8fbcb0/postimage | 284 | ||||
-rw-r--r-- | rr-cache/9d16c377d811118cc2433a0be1ca2947fd8fbcb0/preimage | 303 |
2 files changed, 587 insertions, 0 deletions
diff --git a/rr-cache/9d16c377d811118cc2433a0be1ca2947fd8fbcb0/postimage b/rr-cache/9d16c377d811118cc2433a0be1ca2947fd8fbcb0/postimage new file mode 100644 index 000000000000..f5d08d955834 --- /dev/null +++ b/rr-cache/9d16c377d811118cc2433a0be1ca2947fd8fbcb0/postimage @@ -0,0 +1,284 @@ +// 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 "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; + + opp = devfreq_recommended_opp(dev, freq, flags); + if (IS_ERR(opp)) + return PTR_ERR(opp); + dev_pm_opp_put(opp); + + return dev_pm_opp_set_rate(dev, *freq); +} + +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 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, +}; + +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 dev_pm_opp *opp; + unsigned long cur_freq; + int ret; + + pdevfreq = drmm_kzalloc(&ptdev->base, sizeof(*ptdev->devfreq), GFP_KERNEL); + if (!pdevfreq) + return -ENOMEM; + + ptdev->devfreq = pdevfreq; + + ret = devm_pm_opp_set_regulators(dev, reg_names); + if (ret) { + 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; + + 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; + } + + 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; +} + +int panthor_devfreq_resume(struct panthor_device *ptdev) +{ + struct panthor_devfreq *pdevfreq = ptdev->devfreq; + + if (!pdevfreq->devfreq) + return 0; + + panthor_devfreq_reset(pdevfreq); + + return devfreq_resume_device(pdevfreq->devfreq); +} + +int panthor_devfreq_suspend(struct panthor_device *ptdev) +{ + struct panthor_devfreq *pdevfreq = ptdev->devfreq; + + if (!pdevfreq->devfreq) + return 0; + + return 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); +} diff --git a/rr-cache/9d16c377d811118cc2433a0be1ca2947fd8fbcb0/preimage b/rr-cache/9d16c377d811118cc2433a0be1ca2947fd8fbcb0/preimage new file mode 100644 index 000000000000..10367779454a --- /dev/null +++ b/rr-cache/9d16c377d811118cc2433a0be1ca2947fd8fbcb0/preimage @@ -0,0 +1,303 @@ +// 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 "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; + + opp = devfreq_recommended_opp(dev, freq, flags); + if (IS_ERR(opp)) + return PTR_ERR(opp); + dev_pm_opp_put(opp); + + return dev_pm_opp_set_rate(dev, *freq); +} + +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 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, +}; + +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 dev_pm_opp *opp; + unsigned long cur_freq; + int ret; + + pdevfreq = drmm_kzalloc(&ptdev->base, sizeof(*ptdev->devfreq), GFP_KERNEL); + if (!pdevfreq) + return -ENOMEM; + + ptdev->devfreq = pdevfreq; + + ret = devm_pm_opp_set_regulators(dev, reg_names); + if (ret) { + 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; + + spin_lock_init(&pdevfreq->lock); + + panthor_devfreq_reset(pdevfreq); + + cur_freq = clk_get_rate(ptdev->clks.core); + +<<<<<<< +======= + opp = devfreq_recommended_opp(dev, &cur_freq, 0); + if (IS_ERR(opp)) + return PTR_ERR(opp); + + panthor_devfreq_profile.initial_freq = cur_freq; + +>>>>>>> + /* 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; + ptdev->current_frequency = 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; +} + +int panthor_devfreq_resume(struct panthor_device *ptdev) +{ + struct panthor_devfreq *pdevfreq = ptdev->devfreq; + + if (!pdevfreq->devfreq) + return 0; + + panthor_devfreq_reset(pdevfreq); + + return devfreq_resume_device(pdevfreq->devfreq); +} + +int panthor_devfreq_suspend(struct panthor_device *ptdev) +{ + struct panthor_devfreq *pdevfreq = ptdev->devfreq; + + if (!pdevfreq->devfreq) + return 0; + + return 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); +} |