From ebd6884167eac94bae9f92793fcd84069d9e4415 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 14 Jul 2025 19:45:31 +0200 Subject: [PATCH] PM: sleep: Update power.completion for all devices on errors After commit aa7a9275ab81 ("PM: sleep: Suspend async parents after suspending children"), the following scenario is possible: 1. Device A is async and it depends on device B that is sync. 2. Async suspend is scheduled for A before the processing of B is started. 3. A is waiting for B. 4. In the meantime, an unrelated device fails to suspend and returns an error. 5. The processing of B doesn't start at all and its power.completion is not updated. 6. A is still waiting for B when async_synchronize_full() is called. 7. Deadlock ensues. To prevent this from happening, update power.completion for all devices on errors in all suspend phases, but do not do it directly for devices that are already being processed or are waiting for the processing to start because in those cases it may be necessary to wait for the processing to actually complete before updating power.completion for the device. Fixes: aa7a9275ab81 ("PM: sleep: Suspend async parents after suspending children") Fixes: 443046d1ad66 ("PM: sleep: Make suspend of devices more asynchronous") Closes: https://lore.kernel.org/linux-pm/e13740a0-88f3-4a6f-920f-15805071a7d6@linaro.org/ Reported-and-tested-by: Tudor Ambarus Signed-off-by: Rafael J. Wysocki Reviewed-by: Ulf Hansson Link: https://patch.msgid.link/6191258.lOV4Wx5bFT@rjwysocki.net --- drivers/base/power/main.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index a6ab666ef48ae..7a50af416cac8 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -1280,6 +1280,22 @@ static void dpm_async_suspend_parent(struct device *dev, async_func_t func) dpm_async_with_cleanup(dev->parent, func); } +static void dpm_async_suspend_complete_all(struct list_head *device_list) +{ + struct device *dev; + + guard(mutex)(&async_wip_mtx); + + list_for_each_entry_reverse(dev, device_list, power.entry) { + /* + * In case the device is being waited for and async processing + * has not started for it yet, let the waiters make progress. + */ + if (!dev->power.work_in_progress) + complete_all(&dev->power.completion); + } +} + /** * resume_event - Return a "resume" message for given "suspend" sleep state. * @sleep_state: PM message representing a sleep state. @@ -1456,6 +1472,7 @@ static int dpm_noirq_suspend_devices(pm_message_t state) mutex_lock(&dpm_list_mtx); if (error || async_error) { + dpm_async_suspend_complete_all(&dpm_late_early_list); /* * Move all devices to the target list to resume them * properly. @@ -1658,6 +1675,7 @@ int dpm_suspend_late(pm_message_t state) mutex_lock(&dpm_list_mtx); if (error || async_error) { + dpm_async_suspend_complete_all(&dpm_suspended_list); /* * Move all devices to the target list to resume them * properly. @@ -1951,6 +1969,7 @@ int dpm_suspend(pm_message_t state) mutex_lock(&dpm_list_mtx); if (error || async_error) { + dpm_async_suspend_complete_all(&dpm_prepared_list); /* * Move all devices to the target list to resume them * properly. -- 2.47.2