On Mi, 2026-07-29 at 03:54 +0100, Adrián Larumbe wrote:
> During device probe(), failure to do a PM get() will leave the usage_count
> set to 0, which is the value assigned at device creation time. That means
> when the autosuspend delay expires, runtime suspend callback won't be
> invoked, so the device will remain powered on forever.
>
> On top of that, failure to call PM put() during device unplug means
> Panfrost device's PM usage_count increases monotonically for every new
> module reload.
>
> The combined outcome of both of the above was that devfreq OPP transition
> notifications would be printed all the time, even when no jobs are being
> submitted. This quickly fills the kernel ring buffer with junk.
>
> Even direr than that was the fact MMU interrupts are only enabled when
> the device is reset, so after device probe() the very first job targeting
> the tiler heap BO would always time out, because the driver's PM runtime
> resume callback would not be invoked.
>
> Fix all that by moving all GPU enabling and disabling into RPM resume and
> suspend callbacks, and making sure we resume the device right before
> touching any HW registers. This is done in imitation of the Panthor model.
>
> Signed-off-by: Adrián Larumbe <[email protected]>
> Fixes: 635430797d3f ("drm/panfrost: Rework runtime PM initialization")
> Fixes: 876b15d2c88d ("drm/panfrost: Fix module unload")
> ---
> drivers/gpu/drm/panfrost/panfrost_device.c | 375
> +++++++++++++++++------------
> drivers/gpu/drm/panfrost/panfrost_device.h | 9 +
> drivers/gpu/drm/panfrost/panfrost_drv.c | 10 +-
> drivers/gpu/drm/panfrost/panfrost_gpu.c | 7 +-
> drivers/gpu/drm/panfrost/panfrost_job.c | 7 +-
> 5 files changed, 237 insertions(+), 171 deletions(-)
>
> diff --git a/drivers/gpu/drm/panfrost/panfrost_device.c
> b/drivers/gpu/drm/panfrost/panfrost_device.c
> index 03905495aee2..a9d29d9ee22b 100644
> --- a/drivers/gpu/drm/panfrost/panfrost_device.c
> +++ b/drivers/gpu/drm/panfrost/panfrost_device.c
> @@ -34,6 +34,40 @@ static void panfrost_reset_fini(struct panfrost_device
> *pfdev)
> reset_control_assert(pfdev->rstc);
> }
>
> +static int panfrost_clk_enable(struct panfrost_device *pfdev)
> +{
> + int err;
> +
> + err = clk_enable(pfdev->clock);
> + if (err)
> + return err;
> +
> + err = clk_enable(pfdev->bus_clock);
> + if (err)
> + goto disable_clock;
> +
> + err = clk_enable(pfdev->bus_ace_clock);
> + if (err)
> + goto disable_bus_clock;
> +
> + return 0;
> +
> +disable_bus_clock:
> + clk_disable(pfdev->bus_clock);
> +disable_clock:
> + clk_disable(pfdev->clock);
> +
> + return err;
> +}
> +
> +static void panfrost_clk_disable(struct panfrost_device *pfdev)
> +{
> + clk_disable(pfdev->bus_ace_clock);
> + clk_disable(pfdev->bus_clock);
> + clk_disable(pfdev->clock);
> + reset_control_assert(pfdev->rstc);
> +}
This asymmetry is weird. Why assert the reset control in
panfrost_clock_disable() but not deassert it in panfrost_clk_enable()?
It's also unexpected to have a function called _clk_disable do
something else.
> +
> static int panfrost_clk_init(struct panfrost_device *pfdev)
> {
> int err;
> @@ -48,7 +82,7 @@ static int panfrost_clk_init(struct panfrost_device *pfdev)
> rate = clk_get_rate(pfdev->clock);
> dev_info(pfdev->base.dev, "clock rate = %lu\n", rate);
>
> - err = clk_prepare_enable(pfdev->clock);
> + err = clk_prepare(pfdev->clock);
> if (err)
> return err;
>
> @@ -57,44 +91,55 @@ static int panfrost_clk_init(struct panfrost_device
> *pfdev)
[...]
> static void panfrost_clk_fini(struct panfrost_device *pfdev)
> {
> - clk_disable_unprepare(pfdev->bus_ace_clock);
> - clk_disable_unprepare(pfdev->bus_clock);
> - clk_disable_unprepare(pfdev->clock);
> + if (!(pfdev->comp->pm_features & BIT(GPU_PM_RT)))
> + panfrost_clk_disable(pfdev);
So here you are effectively adding a reset_control_assert() that wasn't
there before. That seems to be intentional because you are removing the
call to panfrost_reset_fini() in panfrost_device_fini().
It's confusing though, panfrost_clk_fini() now cleans up things that
panfrost_clk_init() didn't set up.
> +
> + clk_unprepare(pfdev->bus_ace_clock);
> + clk_unprepare(pfdev->bus_clock);
> + clk_unprepare(pfdev->clock);
> }
>
> static int panfrost_regulator_init(struct panfrost_device *pfdev)
> @@ -212,6 +257,133 @@ static int panfrost_pm_domain_init(struct
> panfrost_device *pfdev)
> return err;
> }
>
> +static int panfrost_device_runtime_resume(struct device *dev)
> +{
> + struct panfrost_device *pfdev = dev_get_drvdata(dev);
> + int ret;
> +
> + if (pfdev->comp->pm_features & BIT(GPU_PM_RT)) {
> + ret = reset_control_deassert(pfdev->rstc);
> + if (ret)
> + return ret;
> +
> + ret = panfrost_clk_enable(pfdev);
> + if (ret)
> + goto err_clk;
Here we clearly deassert the reset and enable the clocks ...
> + }
> +
> + panfrost_device_reset(pfdev, true);
> + panfrost_devfreq_resume(pfdev);
> +
> + return 0;
> +
> +err_clk:
> + if (pfdev->comp->pm_features & BIT(GPU_PM_RT))
> + reset_control_assert(pfdev->rstc);
> + return ret;
> +}
> +
> +static int panfrost_device_runtime_suspend(struct device *dev)
> +{
> + struct panfrost_device *pfdev = dev_get_drvdata(dev);
> +
> + if (!panfrost_jm_is_idle(pfdev))
> + return -EBUSY;
> +
> + panfrost_devfreq_suspend(pfdev);
> + panfrost_jm_suspend_irq(pfdev);
> + panfrost_mmu_suspend_irq(pfdev);
> + panfrost_gpu_suspend_irq(pfdev);
> + panfrost_gpu_power_off(pfdev);
> +
> + if (pfdev->comp->pm_features & BIT(GPU_PM_RT))
> + panfrost_clk_disable(pfdev);
... and here we don't seem to assert the reset, but secretly do.
> +
> + return 0;
> +}
> +
> +static int panfrost_device_resume(struct device *dev)
> +{
> + struct panfrost_device *pfdev = dev_get_drvdata(dev);
> + int ret;
> +
> + if (pfdev->comp->pm_features & BIT(GPU_PM_VREG_OFF)) {
> + unsigned long freq = pfdev->pfdevfreq.fast_rate;
> + struct dev_pm_opp *opp;
> +
> + opp = dev_pm_opp_find_freq_ceil(dev, &freq);
> + if (IS_ERR(opp))
> + return PTR_ERR(opp);
> + dev_pm_opp_set_opp(dev, opp);
> + dev_pm_opp_put(opp);
> + }
> +
> + if (pfdev->comp->pm_features & BIT(GPU_PM_CLK_DIS)) {
> + ret = clk_enable(pfdev->clock);
> + if (ret)
> + goto err_clk;
> +
> + if (pfdev->bus_clock) {
Unnecessary check, clk_enable() handles NULL pointers.
> + ret = clk_enable(pfdev->bus_clock);
> + if (ret)
> + goto err_bus_clk;
> + }
> + }
> +
> + ret = pm_runtime_force_resume(dev);
> + if (ret)
> + goto err_resume;
> +
> + return 0;
> +
> +err_resume:
> + if (pfdev->comp->pm_features & BIT(GPU_PM_CLK_DIS) && pfdev->bus_clock)
Unnecessary check.
> + clk_disable(pfdev->bus_clock);
> +err_bus_clk:
> + if (pfdev->comp->pm_features & BIT(GPU_PM_CLK_DIS))
> + clk_disable(pfdev->clock);
> +err_clk:
> + if (pfdev->comp->pm_features & BIT(GPU_PM_VREG_OFF))
> + dev_pm_opp_set_opp(dev, NULL);
> + return ret;
> +}
> +
> +static int panfrost_device_suspend(struct device *dev)
> +{
> + struct panfrost_device *pfdev = dev_get_drvdata(dev);
> + int ret;
> +
> + ret = pm_runtime_force_suspend(dev);
> + if (ret)
> + return ret;
> +
> + if (pfdev->comp->pm_features & BIT(GPU_PM_CLK_DIS)) {
> + if (pfdev->bus_clock)
Unnecessary check.
> + clk_disable(pfdev->bus_clock);
> +
> + clk_disable(pfdev->clock);
> + }
> +
> + if (pfdev->comp->pm_features & BIT(GPU_PM_VREG_OFF))
> + dev_pm_opp_set_opp(dev, NULL);
> +
> + return 0;
> +}
> +
> +EXPORT_GPL_DEV_PM_OPS(panfrost_pm_ops) = {
> + RUNTIME_PM_OPS(panfrost_device_runtime_suspend,
> panfrost_device_runtime_resume, NULL)
> + SYSTEM_SLEEP_PM_OPS(panfrost_device_suspend, panfrost_device_resume)
> +};
> +
> +void panfrost_try_suspend_device(struct panfrost_device *pfdev)
> +{
> + pm_runtime_put_sync_suspend(pfdev->base.dev);
> +
> + /* If PM is disabled, we need to call the suspend handler manually. */
> + if (!IS_ENABLED(CONFIG_PM))
> + panfrost_device_runtime_suspend(pfdev->base.dev);
> +}
> +
> int panfrost_device_init(struct panfrost_device *pfdev)
> {
> int err;
> @@ -265,10 +437,25 @@ int panfrost_device_init(struct panfrost_device *pfdev)
> goto out_regulator;
> }
>
> - err = panfrost_gpu_init(pfdev);
> + err = devm_pm_runtime_enable(pfdev->base.dev);
> if (err)
> goto out_regulator;
>
> + err = pm_runtime_resume_and_get(pfdev->base.dev);
> + if (err)
> + goto out_regulator;
> +
> + /* If PM is disabled, we need to call panfrost_device_runtime_resume()
> manually. */
> + if (!IS_ENABLED(CONFIG_PM)) {
> + err = panfrost_device_runtime_resume(pfdev->base.dev);
> + if (err)
> + goto out_regulator;
> + }
> +
> + err = panfrost_gpu_init(pfdev);
> + if (err)
> + goto out_rpm_put;
> +
> err = panfrost_mmu_init(pfdev);
> if (err)
> goto out_gpu;
> @@ -295,6 +482,8 @@ int panfrost_device_init(struct panfrost_device *pfdev)
> panfrost_mmu_fini(pfdev);
> out_gpu:
> panfrost_gpu_fini(pfdev);
> +out_rpm_put:
> + panfrost_try_suspend_device(pfdev);
> out_regulator:
> panfrost_regulator_fini(pfdev);
> out_devfreq:
Directly below this:
panfrost_devfreq_fini(pfdev);
out_clk:
panfrost_clk_fini(pfdev);
out_reset:
panfrost_reset_fini(pfdev);
_reset_fini is still called right after _clk_fini asserted the reset
control.
> @@ -313,12 +502,10 @@ void panfrost_device_fini(struct panfrost_device *pfdev)
> panfrost_gem_shrinker_fini(pfdev);
> panfrost_perfcnt_fini(pfdev);
> panfrost_jm_fini(pfdev);
> - panfrost_mmu_fini(pfdev);
> - panfrost_gpu_fini(pfdev);
> - panfrost_devfreq_fini(pfdev);
> + panfrost_try_suspend_device(pfdev);
> panfrost_regulator_fini(pfdev);
> + panfrost_devfreq_fini(pfdev);
> panfrost_clk_fini(pfdev);
> - panfrost_reset_fini(pfdev);
Here _reset_fini is dropped because _clk_fini already asserted the
reset.
regards
Philipp
