| Message ID | 20220901091527.1992208-1-dmitry.baryshkov@linaro.org |
|---|---|
| Headers | show |
| Series | drm/msm/dp: several fixes for the IRQ handling | expand |
On 01/09/2022 12:20, Johan Hovold wrote: > On Thu, Sep 01, 2022 at 12:15:24PM +0300, Dmitry Baryshkov wrote: >> Johan Hovold has reported that returning a probe deferral from the >> msm_dp_modeset_init() can cause issues because the IRQ is not freed >> properly. This (compile-tested only) series tries to fix the issue by >> moving devm_request_irq() to the probe callback. > > Please try to reproduce the issue yourself before posting untested RFCs. > We're all short on time. I do not have a working DP setup. Thus it's either this, or nothing.
On Thu, Sep 01, 2022 at 12:15:24PM +0300, Dmitry Baryshkov wrote: > Johan Hovold has reported that returning a probe deferral from the > msm_dp_modeset_init() can cause issues because the IRQ is not freed > properly. This (compile-tested only) series tries to fix the issue by > moving devm_request_irq() to the probe callback. > This series fixes the probe deferral issue on Lenovo Thinkpad X13s. But I didn't look close enough to verify if all other resource deallocation are just fine. Thanks for the quick series, Dmitry! Regards, Mani > Dmitry Baryshkov (3): > drm/msm/dp: fold disable_irq into devm_request_irq > drm/msm/dp: switch to using platform_get_irq() > drm/msm/dp: move dp_request_irq() call to dp_display_probe() > > drivers/gpu/drm/msm/dp/dp_display.c | 19 +++++++++---------- > 1 file changed, 9 insertions(+), 10 deletions(-) > > -- > 2.35.1 >
On Thu, Sep 01, 2022 at 12:15:24PM +0300, Dmitry Baryshkov wrote: > Johan Hovold has reported that returning a probe deferral from the > msm_dp_modeset_init() can cause issues because the IRQ is not freed > properly. This (compile-tested only) series tries to fix the issue by > moving devm_request_irq() to the probe callback. For reference, here's an analysis of the underlying problem and a series of fixes that addresses this: https://lore.kernel.org/all/20220913085320.8577-1-johan+linaro@kernel.org/ Note that moving the irq request to probe also fixes the immediate issue, but that can now be done as a follow-on cleanup (optimisation) instead. > Dmitry Baryshkov (3): > drm/msm/dp: fold disable_irq into devm_request_irq > drm/msm/dp: switch to using platform_get_irq() > drm/msm/dp: move dp_request_irq() call to dp_display_probe() > > drivers/gpu/drm/msm/dp/dp_display.c | 19 +++++++++---------- > 1 file changed, 9 insertions(+), 10 deletions(-) Johan