From 3f884a10ab41efe2d495bf8ec8d443d70c500a60 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 22 Aug 2022 13:18:21 +0200 Subject: sched/wait: Add wait_event_state() Allows waiting with a custom @state. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Ingo Molnar Link: https://lore.kernel.org/r/20220822114648.989212021@infradead.org --- include/linux/wait.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux/wait.h') diff --git a/include/linux/wait.h b/include/linux/wait.h index 58cfbf81447c..b926eb9f3e26 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -932,6 +932,34 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_entry_t *); __ret; \ }) +#define __wait_event_state(wq, condition, state) \ + ___wait_event(wq, condition, state, 0, 0, schedule()) + +/** + * wait_event_state - sleep until a condition gets true + * @wq_head: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * @state: state to sleep in + * + * The process is put to sleep (@state) until the @condition evaluates to true + * or a signal is received (when allowed by @state). The @condition is checked + * each time the waitqueue @wq_head is woken up. + * + * wake_up() has to be called after changing any variable that could + * change the result of the wait condition. + * + * The function will return -ERESTARTSYS if it was interrupted by a signal + * (when allowed by @state) and 0 if @condition evaluated to true. + */ +#define wait_event_state(wq_head, condition, state) \ +({ \ + int __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __wait_event_state(wq_head, condition, state); \ + __ret; \ +}) + #define __wait_event_killable_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_KILLABLE, 0, timeout, \ -- cgit v1.2.3 From f5d39b020809146cc28e6e73369bf8065e0310aa Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 22 Aug 2022 13:18:22 +0200 Subject: freezer,sched: Rewrite core freezer logic Rewrite the core freezer to behave better wrt thawing and be simpler in general. By replacing PF_FROZEN with TASK_FROZEN, a special block state, it is ensured frozen tasks stay frozen until thawed and don't randomly wake up early, as is currently possible. As such, it does away with PF_FROZEN and PF_FREEZER_SKIP, freeing up two PF_flags (yay!). Specifically; the current scheme works a little like: freezer_do_not_count(); schedule(); freezer_count(); And either the task is blocked, or it lands in try_to_freezer() through freezer_count(). Now, when it is blocked, the freezer considers it frozen and continues. However, on thawing, once pm_freezing is cleared, freezer_count() stops working, and any random/spurious wakeup will let a task run before its time. That is, thawing tries to thaw things in explicit order; kernel threads and workqueues before doing bringing SMP back before userspace etc.. However due to the above mentioned races it is entirely possible for userspace tasks to thaw (by accident) before SMP is back. This can be a fatal problem in asymmetric ISA architectures (eg ARMv9) where the userspace task requires a special CPU to run. As said; replace this with a special task state TASK_FROZEN and add the following state transitions: TASK_FREEZABLE -> TASK_FROZEN __TASK_STOPPED -> TASK_FROZEN __TASK_TRACED -> TASK_FROZEN The new TASK_FREEZABLE can be set on any state part of TASK_NORMAL (IOW. TASK_INTERRUPTIBLE and TASK_UNINTERRUPTIBLE) -- any such state is already required to deal with spurious wakeups and the freezer causes one such when thawing the task (since the original state is lost). The special __TASK_{STOPPED,TRACED} states *can* be restored since their canonical state is in ->jobctl. With this, frozen tasks need an explicit TASK_FROZEN wakeup and are free of undue (early / spurious) wakeups. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Ingo Molnar Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20220822114649.055452969@infradead.org --- include/linux/wait.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux/wait.h') diff --git a/include/linux/wait.h b/include/linux/wait.h index b926eb9f3e26..14ad8a0e9fac 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -361,8 +361,8 @@ do { \ } while (0) #define __wait_event_freezable(wq_head, condition) \ - ___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0, \ - freezable_schedule()) + ___wait_event(wq_head, condition, (TASK_INTERRUPTIBLE|TASK_FREEZABLE), \ + 0, 0, schedule()) /** * wait_event_freezable - sleep (or freeze) until a condition gets true @@ -420,8 +420,8 @@ do { \ #define __wait_event_freezable_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ - TASK_INTERRUPTIBLE, 0, timeout, \ - __ret = freezable_schedule_timeout(__ret)) + (TASK_INTERRUPTIBLE|TASK_FREEZABLE), 0, timeout, \ + __ret = schedule_timeout(__ret)) /* * like wait_event_timeout() -- except it uses TASK_INTERRUPTIBLE to avoid @@ -642,8 +642,8 @@ do { \ #define __wait_event_freezable_exclusive(wq, condition) \ - ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0, \ - freezable_schedule()) + ___wait_event(wq, condition, (TASK_INTERRUPTIBLE|TASK_FREEZABLE), 1, 0,\ + schedule()) #define wait_event_freezable_exclusive(wq, condition) \ ({ \ -- cgit v1.2.3 From 5aec788aeb8eb74282b75ac1b317beb0fbb69a42 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 27 Sep 2022 21:02:34 +0200 Subject: 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 Debugged-by: Christian Borntraeger Signed-off-by: Peter Zijlstra (Intel) Tested-by: Christian Borntraeger --- include/linux/wait.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/wait.h') diff --git a/include/linux/wait.h b/include/linux/wait.h index 14ad8a0e9fac..7f5a51aae0a7 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); -- cgit v1.2.3