The following commit has been merged into the sched/core branch of tip: Commit-ID: 543f82fee0c531c8386f776a6050878a5bfe96f4 Gitweb: https://git.kernel.org/tip/543f82fee0c531c8386f776a6050878a5bfe96f4 Author: Peter Zijlstra <peterz@xxxxxxxxxxxxx> AuthorDate: Tue, 27 Sep 2022 21:02:34 +02:00 Committer: Peter Zijlstra <peterz@xxxxxxxxxxxxx> CommitterDate: Tue, 27 Sep 2022 22:50:22 +02:00 sched: Fix TASK_state comparisons Task state is fundamentally a bitmask; direct comparisons are probably not working as intended. Specifically the normal wait-state have a number of possible modifiers: TASK_UNINTERRUPTIBLE: TASK_WAKEKILL, TASK_NOLOAD, TASK_FREEZABLE TASK_INTERRUPTIBLE: TASK_FREEZABLE Specifically, the addition of TASK_FREEZABLE wrecked __wait_is_interruptible(). This however led to an audit of direct comparisons yielding the rest of the changes. Fixes: f5d39b020809 ("freezer,sched: Rewrite core freezer logic") Reported-by: Christian Borntraeger <borntraeger@xxxxxxxxxxxxx> Debugged-by: Christian Borntraeger <borntraeger@xxxxxxxxxxxxx> Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx> Tested-by: Christian Borntraeger <borntraeger@xxxxxxxxxxxxx> --- include/linux/wait.h | 2 +- kernel/hung_task.c | 8 ++++++-- kernel/sched/core.c | 2 +- 3 files changed, 8 insertions(+), 4 deletions(-) diff --git a/include/linux/wait.h b/include/linux/wait.h index 14ad8a0..7f5a51a 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -281,7 +281,7 @@ static inline void wake_up_pollfree(struct wait_queue_head *wq_head) #define ___wait_is_interruptible(state) \ (!__builtin_constant_p(state) || \ - state == TASK_INTERRUPTIBLE || state == TASK_KILLABLE) \ + (state & (TASK_INTERRUPTIBLE | TASK_WAKEKILL))) extern void init_wait_entry(struct wait_queue_entry *wq_entry, int flags); diff --git a/kernel/hung_task.c b/kernel/hung_task.c index f1321c0..4a8a713 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -191,6 +191,8 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout) hung_task_show_lock = false; rcu_read_lock(); for_each_process_thread(g, t) { + unsigned int state; + if (!max_count--) goto unlock; if (time_after(jiffies, last_break + HUNG_TASK_LOCK_BREAK)) { @@ -198,8 +200,10 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout) goto unlock; last_break = jiffies; } - /* use "==" to skip the TASK_KILLABLE tasks waiting on NFS */ - if (READ_ONCE(t->__state) == TASK_UNINTERRUPTIBLE) + /* skip the TASK_KILLABLE tasks -- these can be killed */ + state == READ_ONCE(t->__state); + if ((state & TASK_UNINTERRUPTIBLE) && + !(state & TASK_WAKEKILL)) check_hung_task(t, timeout); } unlock: diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 4fa4a3d..02dc1b8 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -8884,7 +8884,7 @@ state_filter_match(unsigned long state_filter, struct task_struct *p) * When looking for TASK_UNINTERRUPTIBLE skip TASK_IDLE (allows * TASK_KILLABLE). */ - if (state_filter == TASK_UNINTERRUPTIBLE && state == TASK_IDLE) + if (state_filter == TASK_UNINTERRUPTIBLE && (state & TASK_NOLOAD)) return false; return true;