linux/kernel/sched/wait.c

440 lines
13 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Generic waiting primitives.
*
* (C) 2004 Nadia Yvette Chambers, Oracle
*/
#include "sched.h"
void __init_waitqueue_head(struct wait_queue_head *wq_head, const char *name, struct lock_class_key *key)
{
spin_lock_init(&wq_head->lock);
lockdep_set_class_and_name(&wq_head->lock, key, name);
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming So I've noticed a number of instances where it was not obvious from the code whether ->task_list was for a wait-queue head or a wait-queue entry. Furthermore, there's a number of wait-queue users where the lists are not for 'tasks' but other entities (poll tables, etc.), in which case the 'task_list' name is actively confusing. To clear this all up, name the wait-queue head and entry list structure fields unambiguously: struct wait_queue_head::task_list => ::head struct wait_queue_entry::task_list => ::entry For example, this code: rqw->wait.task_list.next != &wait->task_list ... is was pretty unclear (to me) what it's doing, while now it's written this way: rqw->wait.head.next != &wait->entry ... which makes it pretty clear that we are iterating a list until we see the head. Other examples are: list_for_each_entry_safe(pos, next, &x->task_list, task_list) { list_for_each_entry(wq, &fence->wait.task_list, task_list) { ... where it's unclear (to me) what we are iterating, and during review it's hard to tell whether it's trying to walk a wait-queue entry (which would be a bug), while now it's written as: list_for_each_entry_safe(pos, next, &x->head, entry) { list_for_each_entry(wq, &fence->wait.head, entry) { Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-20 12:06:46 +02:00
INIT_LIST_HEAD(&wq_head->head);
}
EXPORT_SYMBOL(__init_waitqueue_head);
void add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
{
unsigned long flags;
sched/wait: Standardize internal naming of wait-queue entries So the various wait-queue entry variables in include/linux/wait.h and kernel/sched/wait.c are named in a colorfully inconsistent way: wait_queue_entry_t *wait wait_queue_entry_t *__wait (even in plain C code!) wait_queue_entry_t *q (!) wait_queue_entry_t *new (making anyone who knows C++ cringe) wait_queue_entry_t *old I think part of the reason for the inconsistency is the constant apparent confusion about what a wait queue 'head' versus 'entry' is. ( Some of the documentation talks about a 'wait descriptor', which is the wait-queue entry itself - further adding to the confusion. ) The most common name is 'wait', but that in itself is somewhat ambiguous as well, as it does not really make it clear whether it's a wait-queue entry or head. To improve all this name the wait-queue entry structure parameters and variables consistently and push through this naming into all the wait.h and wait.c code: struct wait_queue_entry *wq_entry The 'wq_' prefix makes it easy to grep for, and we also use the opportunity to move away from the typedef to a plain 'struct' naming: in the kernel we typically reserve typedefs for cases where a C structure is really small and somewhat opaque - such as pte_t. wait-queue entries are neither small nor opaque, so use the more standard 'struct xxx_entry' list management code nomenclature instead. ( We don't touch external users, and we preserve the typedef as well for actual wait-queue users, to reduce unnecessary churn. ) Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-03-05 10:33:16 +01:00
wq_entry->flags &= ~WQ_FLAG_EXCLUSIVE;
spin_lock_irqsave(&wq_head->lock, flags);
__add_wait_queue(wq_head, wq_entry);
spin_unlock_irqrestore(&wq_head->lock, flags);
}
EXPORT_SYMBOL(add_wait_queue);
void add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
{
unsigned long flags;
sched/wait: Standardize internal naming of wait-queue entries So the various wait-queue entry variables in include/linux/wait.h and kernel/sched/wait.c are named in a colorfully inconsistent way: wait_queue_entry_t *wait wait_queue_entry_t *__wait (even in plain C code!) wait_queue_entry_t *q (!) wait_queue_entry_t *new (making anyone who knows C++ cringe) wait_queue_entry_t *old I think part of the reason for the inconsistency is the constant apparent confusion about what a wait queue 'head' versus 'entry' is. ( Some of the documentation talks about a 'wait descriptor', which is the wait-queue entry itself - further adding to the confusion. ) The most common name is 'wait', but that in itself is somewhat ambiguous as well, as it does not really make it clear whether it's a wait-queue entry or head. To improve all this name the wait-queue entry structure parameters and variables consistently and push through this naming into all the wait.h and wait.c code: struct wait_queue_entry *wq_entry The 'wq_' prefix makes it easy to grep for, and we also use the opportunity to move away from the typedef to a plain 'struct' naming: in the kernel we typically reserve typedefs for cases where a C structure is really small and somewhat opaque - such as pte_t. wait-queue entries are neither small nor opaque, so use the more standard 'struct xxx_entry' list management code nomenclature instead. ( We don't touch external users, and we preserve the typedef as well for actual wait-queue users, to reduce unnecessary churn. ) Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-03-05 10:33:16 +01:00
wq_entry->flags |= WQ_FLAG_EXCLUSIVE;
spin_lock_irqsave(&wq_head->lock, flags);
__add_wait_queue_entry_tail(wq_head, wq_entry);
spin_unlock_irqrestore(&wq_head->lock, flags);
}
EXPORT_SYMBOL(add_wait_queue_exclusive);
void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
{
unsigned long flags;
spin_lock_irqsave(&wq_head->lock, flags);
__remove_wait_queue(wq_head, wq_entry);
spin_unlock_irqrestore(&wq_head->lock, flags);
}
EXPORT_SYMBOL(remove_wait_queue);
sched/wait: Break up long wake list walk We encountered workloads that have very long wake up list on large systems. A waker takes a long time to traverse the entire wake list and execute all the wake functions. We saw page wait list that are up to 3700+ entries long in tests of large 4 and 8 socket systems. It took 0.8 sec to traverse such list during wake up. Any other CPU that contends for the list spin lock will spin for a long time. It is a result of the numa balancing migration of hot pages that are shared by many threads. Multiple CPUs waking are queued up behind the lock, and the last one queued has to wait until all CPUs did all the wakeups. The page wait list is traversed with interrupt disabled, which caused various problems. This was the original cause that triggered the NMI watch dog timer in: https://patchwork.kernel.org/patch/9800303/ . Only extending the NMI watch dog timer there helped. This patch bookmarks the waker's scan position in wake list and break the wake up walk, to allow access to the list before the waker resume its walk down the rest of the wait list. It lowers the interrupt and rescheduling latency. This patch also provides a performance boost when combined with the next patch to break up page wakeup list walk. We saw 22% improvement in the will-it-scale file pread2 test on a Xeon Phi system running 256 threads. [ v2: Merged in Linus' changes to remove the bookmark_wake_function, and simply access to flags. ] Reported-by: Kan Liang <kan.liang@intel.com> Tested-by: Kan Liang <kan.liang@intel.com> Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-08-25 18:13:54 +02:00
/*
* Scan threshold to break wait queue walk.
* This allows a waker to take a break from holding the
* wait queue lock during the wait queue walk.
*/
#define WAITQUEUE_WALK_BREAK_CNT 64
/*
* The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just
* wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve
* number) then we wake all the non-exclusive tasks and one exclusive task.
*
* There are circumstances in which we can try to wake a task which has already
* started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
* zero in this (rare) case, and we handle it by continuing to scan the queue.
*/
sched/wait: Break up long wake list walk We encountered workloads that have very long wake up list on large systems. A waker takes a long time to traverse the entire wake list and execute all the wake functions. We saw page wait list that are up to 3700+ entries long in tests of large 4 and 8 socket systems. It took 0.8 sec to traverse such list during wake up. Any other CPU that contends for the list spin lock will spin for a long time. It is a result of the numa balancing migration of hot pages that are shared by many threads. Multiple CPUs waking are queued up behind the lock, and the last one queued has to wait until all CPUs did all the wakeups. The page wait list is traversed with interrupt disabled, which caused various problems. This was the original cause that triggered the NMI watch dog timer in: https://patchwork.kernel.org/patch/9800303/ . Only extending the NMI watch dog timer there helped. This patch bookmarks the waker's scan position in wake list and break the wake up walk, to allow access to the list before the waker resume its walk down the rest of the wait list. It lowers the interrupt and rescheduling latency. This patch also provides a performance boost when combined with the next patch to break up page wakeup list walk. We saw 22% improvement in the will-it-scale file pread2 test on a Xeon Phi system running 256 threads. [ v2: Merged in Linus' changes to remove the bookmark_wake_function, and simply access to flags. ] Reported-by: Kan Liang <kan.liang@intel.com> Tested-by: Kan Liang <kan.liang@intel.com> Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-08-25 18:13:54 +02:00
static int __wake_up_common(struct wait_queue_head *wq_head, unsigned int mode,
int nr_exclusive, int wake_flags, void *key,
wait_queue_entry_t *bookmark)
{
wait_queue_entry_t *curr, *next;
sched/wait: Break up long wake list walk We encountered workloads that have very long wake up list on large systems. A waker takes a long time to traverse the entire wake list and execute all the wake functions. We saw page wait list that are up to 3700+ entries long in tests of large 4 and 8 socket systems. It took 0.8 sec to traverse such list during wake up. Any other CPU that contends for the list spin lock will spin for a long time. It is a result of the numa balancing migration of hot pages that are shared by many threads. Multiple CPUs waking are queued up behind the lock, and the last one queued has to wait until all CPUs did all the wakeups. The page wait list is traversed with interrupt disabled, which caused various problems. This was the original cause that triggered the NMI watch dog timer in: https://patchwork.kernel.org/patch/9800303/ . Only extending the NMI watch dog timer there helped. This patch bookmarks the waker's scan position in wake list and break the wake up walk, to allow access to the list before the waker resume its walk down the rest of the wait list. It lowers the interrupt and rescheduling latency. This patch also provides a performance boost when combined with the next patch to break up page wakeup list walk. We saw 22% improvement in the will-it-scale file pread2 test on a Xeon Phi system running 256 threads. [ v2: Merged in Linus' changes to remove the bookmark_wake_function, and simply access to flags. ] Reported-by: Kan Liang <kan.liang@intel.com> Tested-by: Kan Liang <kan.liang@intel.com> Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-08-25 18:13:54 +02:00
int cnt = 0;
lockdep_assert_held(&wq_head->lock);
sched/wait: Break up long wake list walk We encountered workloads that have very long wake up list on large systems. A waker takes a long time to traverse the entire wake list and execute all the wake functions. We saw page wait list that are up to 3700+ entries long in tests of large 4 and 8 socket systems. It took 0.8 sec to traverse such list during wake up. Any other CPU that contends for the list spin lock will spin for a long time. It is a result of the numa balancing migration of hot pages that are shared by many threads. Multiple CPUs waking are queued up behind the lock, and the last one queued has to wait until all CPUs did all the wakeups. The page wait list is traversed with interrupt disabled, which caused various problems. This was the original cause that triggered the NMI watch dog timer in: https://patchwork.kernel.org/patch/9800303/ . Only extending the NMI watch dog timer there helped. This patch bookmarks the waker's scan position in wake list and break the wake up walk, to allow access to the list before the waker resume its walk down the rest of the wait list. It lowers the interrupt and rescheduling latency. This patch also provides a performance boost when combined with the next patch to break up page wakeup list walk. We saw 22% improvement in the will-it-scale file pread2 test on a Xeon Phi system running 256 threads. [ v2: Merged in Linus' changes to remove the bookmark_wake_function, and simply access to flags. ] Reported-by: Kan Liang <kan.liang@intel.com> Tested-by: Kan Liang <kan.liang@intel.com> Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-08-25 18:13:54 +02:00
if (bookmark && (bookmark->flags & WQ_FLAG_BOOKMARK)) {
curr = list_next_entry(bookmark, entry);
sched/wait: Break up long wake list walk We encountered workloads that have very long wake up list on large systems. A waker takes a long time to traverse the entire wake list and execute all the wake functions. We saw page wait list that are up to 3700+ entries long in tests of large 4 and 8 socket systems. It took 0.8 sec to traverse such list during wake up. Any other CPU that contends for the list spin lock will spin for a long time. It is a result of the numa balancing migration of hot pages that are shared by many threads. Multiple CPUs waking are queued up behind the lock, and the last one queued has to wait until all CPUs did all the wakeups. The page wait list is traversed with interrupt disabled, which caused various problems. This was the original cause that triggered the NMI watch dog timer in: https://patchwork.kernel.org/patch/9800303/ . Only extending the NMI watch dog timer there helped. This patch bookmarks the waker's scan position in wake list and break the wake up walk, to allow access to the list before the waker resume its walk down the rest of the wait list. It lowers the interrupt and rescheduling latency. This patch also provides a performance boost when combined with the next patch to break up page wakeup list walk. We saw 22% improvement in the will-it-scale file pread2 test on a Xeon Phi system running 256 threads. [ v2: Merged in Linus' changes to remove the bookmark_wake_function, and simply access to flags. ] Reported-by: Kan Liang <kan.liang@intel.com> Tested-by: Kan Liang <kan.liang@intel.com> Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-08-25 18:13:54 +02:00
list_del(&bookmark->entry);
bookmark->flags = 0;
} else
curr = list_first_entry(&wq_head->head, wait_queue_entry_t, entry);
if (&curr->entry == &wq_head->head)
return nr_exclusive;
list_for_each_entry_safe_from(curr, next, &wq_head->head, entry) {
unsigned flags = curr->flags;
sched/wait: Break up long wake list walk We encountered workloads that have very long wake up list on large systems. A waker takes a long time to traverse the entire wake list and execute all the wake functions. We saw page wait list that are up to 3700+ entries long in tests of large 4 and 8 socket systems. It took 0.8 sec to traverse such list during wake up. Any other CPU that contends for the list spin lock will spin for a long time. It is a result of the numa balancing migration of hot pages that are shared by many threads. Multiple CPUs waking are queued up behind the lock, and the last one queued has to wait until all CPUs did all the wakeups. The page wait list is traversed with interrupt disabled, which caused various problems. This was the original cause that triggered the NMI watch dog timer in: https://patchwork.kernel.org/patch/9800303/ . Only extending the NMI watch dog timer there helped. This patch bookmarks the waker's scan position in wake list and break the wake up walk, to allow access to the list before the waker resume its walk down the rest of the wait list. It lowers the interrupt and rescheduling latency. This patch also provides a performance boost when combined with the next patch to break up page wakeup list walk. We saw 22% improvement in the will-it-scale file pread2 test on a Xeon Phi system running 256 threads. [ v2: Merged in Linus' changes to remove the bookmark_wake_function, and simply access to flags. ] Reported-by: Kan Liang <kan.liang@intel.com> Tested-by: Kan Liang <kan.liang@intel.com> Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-08-25 18:13:54 +02:00
int ret;
if (flags & WQ_FLAG_BOOKMARK)
continue;
ret = curr->func(curr, mode, wake_flags, key);
Minor page waitqueue cleanups Tim Chen and Kan Liang have been battling a customer load that shows extremely long page wakeup lists. The cause seems to be constant NUMA migration of a hot page that is shared across a lot of threads, but the actual root cause for the exact behavior has not been found. Tim has a patch that batches the wait list traversal at wakeup time, so that we at least don't get long uninterruptible cases where we traverse and wake up thousands of processes and get nasty latency spikes. That is likely 4.14 material, but we're still discussing the page waitqueue specific parts of it. In the meantime, I've tried to look at making the page wait queues less expensive, and failing miserably. If you have thousands of threads waiting for the same page, it will be painful. We'll need to try to figure out the NUMA balancing issue some day, in addition to avoiding the excessive spinlock hold times. That said, having tried to rewrite the page wait queues, I can at least fix up some of the braindamage in the current situation. In particular: (a) we don't want to continue walking the page wait list if the bit we're waiting for already got set again (which seems to be one of the patterns of the bad load). That makes no progress and just causes pointless cache pollution chasing the pointers. (b) we don't want to put the non-locking waiters always on the front of the queue, and the locking waiters always on the back. Not only is that unfair, it means that we wake up thousands of reading threads that will just end up being blocked by the writer later anyway. Also add a comment about the layout of 'struct wait_page_key' - there is an external user of it in the cachefiles code that means that it has to match the layout of 'struct wait_bit_key' in the two first members. It so happens to match, because 'struct page *' and 'unsigned long *' end up having the same values simply because the page flags are the first member in struct page. Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Christopher Lameter <cl@linux.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-08-27 22:55:12 +02:00
if (ret < 0)
break;
if (ret && (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive)
break;
sched/wait: Break up long wake list walk We encountered workloads that have very long wake up list on large systems. A waker takes a long time to traverse the entire wake list and execute all the wake functions. We saw page wait list that are up to 3700+ entries long in tests of large 4 and 8 socket systems. It took 0.8 sec to traverse such list during wake up. Any other CPU that contends for the list spin lock will spin for a long time. It is a result of the numa balancing migration of hot pages that are shared by many threads. Multiple CPUs waking are queued up behind the lock, and the last one queued has to wait until all CPUs did all the wakeups. The page wait list is traversed with interrupt disabled, which caused various problems. This was the original cause that triggered the NMI watch dog timer in: https://patchwork.kernel.org/patch/9800303/ . Only extending the NMI watch dog timer there helped. This patch bookmarks the waker's scan position in wake list and break the wake up walk, to allow access to the list before the waker resume its walk down the rest of the wait list. It lowers the interrupt and rescheduling latency. This patch also provides a performance boost when combined with the next patch to break up page wakeup list walk. We saw 22% improvement in the will-it-scale file pread2 test on a Xeon Phi system running 256 threads. [ v2: Merged in Linus' changes to remove the bookmark_wake_function, and simply access to flags. ] Reported-by: Kan Liang <kan.liang@intel.com> Tested-by: Kan Liang <kan.liang@intel.com> Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-08-25 18:13:54 +02:00
if (bookmark && (++cnt > WAITQUEUE_WALK_BREAK_CNT) &&
(&next->entry != &wq_head->head)) {
bookmark->flags = WQ_FLAG_BOOKMARK;
list_add_tail(&bookmark->entry, &next->entry);
break;
}
}
sched/wait: Break up long wake list walk We encountered workloads that have very long wake up list on large systems. A waker takes a long time to traverse the entire wake list and execute all the wake functions. We saw page wait list that are up to 3700+ entries long in tests of large 4 and 8 socket systems. It took 0.8 sec to traverse such list during wake up. Any other CPU that contends for the list spin lock will spin for a long time. It is a result of the numa balancing migration of hot pages that are shared by many threads. Multiple CPUs waking are queued up behind the lock, and the last one queued has to wait until all CPUs did all the wakeups. The page wait list is traversed with interrupt disabled, which caused various problems. This was the original cause that triggered the NMI watch dog timer in: https://patchwork.kernel.org/patch/9800303/ . Only extending the NMI watch dog timer there helped. This patch bookmarks the waker's scan position in wake list and break the wake up walk, to allow access to the list before the waker resume its walk down the rest of the wait list. It lowers the interrupt and rescheduling latency. This patch also provides a performance boost when combined with the next patch to break up page wakeup list walk. We saw 22% improvement in the will-it-scale file pread2 test on a Xeon Phi system running 256 threads. [ v2: Merged in Linus' changes to remove the bookmark_wake_function, and simply access to flags. ] Reported-by: Kan Liang <kan.liang@intel.com> Tested-by: Kan Liang <kan.liang@intel.com> Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-08-25 18:13:54 +02:00
return nr_exclusive;
}
static void __wake_up_common_lock(struct wait_queue_head *wq_head, unsigned int mode,
int nr_exclusive, int wake_flags, void *key)
{
unsigned long flags;
wait_queue_entry_t bookmark;
bookmark.flags = 0;
bookmark.private = NULL;
bookmark.func = NULL;
INIT_LIST_HEAD(&bookmark.entry);
do {
sched/wait: Break up long wake list walk We encountered workloads that have very long wake up list on large systems. A waker takes a long time to traverse the entire wake list and execute all the wake functions. We saw page wait list that are up to 3700+ entries long in tests of large 4 and 8 socket systems. It took 0.8 sec to traverse such list during wake up. Any other CPU that contends for the list spin lock will spin for a long time. It is a result of the numa balancing migration of hot pages that are shared by many threads. Multiple CPUs waking are queued up behind the lock, and the last one queued has to wait until all CPUs did all the wakeups. The page wait list is traversed with interrupt disabled, which caused various problems. This was the original cause that triggered the NMI watch dog timer in: https://patchwork.kernel.org/patch/9800303/ . Only extending the NMI watch dog timer there helped. This patch bookmarks the waker's scan position in wake list and break the wake up walk, to allow access to the list before the waker resume its walk down the rest of the wait list. It lowers the interrupt and rescheduling latency. This patch also provides a performance boost when combined with the next patch to break up page wakeup list walk. We saw 22% improvement in the will-it-scale file pread2 test on a Xeon Phi system running 256 threads. [ v2: Merged in Linus' changes to remove the bookmark_wake_function, and simply access to flags. ] Reported-by: Kan Liang <kan.liang@intel.com> Tested-by: Kan Liang <kan.liang@intel.com> Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-08-25 18:13:54 +02:00
spin_lock_irqsave(&wq_head->lock, flags);
nr_exclusive = __wake_up_common(wq_head, mode, nr_exclusive,
wake_flags, key, &bookmark);
spin_unlock_irqrestore(&wq_head->lock, flags);
} while (bookmark.flags & WQ_FLAG_BOOKMARK);
}
/**
* __wake_up - wake up threads blocked on a waitqueue.
* @wq_head: the waitqueue
* @mode: which threads
* @nr_exclusive: how many wake-one or wake-many threads to wake up
* @key: is directly passed to the wakeup function
*
* If this function wakes up a task, it executes a full memory barrier before
* accessing the task state.
*/
void __wake_up(struct wait_queue_head *wq_head, unsigned int mode,
int nr_exclusive, void *key)
{
sched/wait: Break up long wake list walk We encountered workloads that have very long wake up list on large systems. A waker takes a long time to traverse the entire wake list and execute all the wake functions. We saw page wait list that are up to 3700+ entries long in tests of large 4 and 8 socket systems. It took 0.8 sec to traverse such list during wake up. Any other CPU that contends for the list spin lock will spin for a long time. It is a result of the numa balancing migration of hot pages that are shared by many threads. Multiple CPUs waking are queued up behind the lock, and the last one queued has to wait until all CPUs did all the wakeups. The page wait list is traversed with interrupt disabled, which caused various problems. This was the original cause that triggered the NMI watch dog timer in: https://patchwork.kernel.org/patch/9800303/ . Only extending the NMI watch dog timer there helped. This patch bookmarks the waker's scan position in wake list and break the wake up walk, to allow access to the list before the waker resume its walk down the rest of the wait list. It lowers the interrupt and rescheduling latency. This patch also provides a performance boost when combined with the next patch to break up page wakeup list walk. We saw 22% improvement in the will-it-scale file pread2 test on a Xeon Phi system running 256 threads. [ v2: Merged in Linus' changes to remove the bookmark_wake_function, and simply access to flags. ] Reported-by: Kan Liang <kan.liang@intel.com> Tested-by: Kan Liang <kan.liang@intel.com> Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-08-25 18:13:54 +02:00
__wake_up_common_lock(wq_head, mode, nr_exclusive, 0, key);
}
EXPORT_SYMBOL(__wake_up);
/*
* Same as __wake_up but called with the spinlock in wait_queue_head_t held.
*/
void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr)
{
sched/wait: Break up long wake list walk We encountered workloads that have very long wake up list on large systems. A waker takes a long time to traverse the entire wake list and execute all the wake functions. We saw page wait list that are up to 3700+ entries long in tests of large 4 and 8 socket systems. It took 0.8 sec to traverse such list during wake up. Any other CPU that contends for the list spin lock will spin for a long time. It is a result of the numa balancing migration of hot pages that are shared by many threads. Multiple CPUs waking are queued up behind the lock, and the last one queued has to wait until all CPUs did all the wakeups. The page wait list is traversed with interrupt disabled, which caused various problems. This was the original cause that triggered the NMI watch dog timer in: https://patchwork.kernel.org/patch/9800303/ . Only extending the NMI watch dog timer there helped. This patch bookmarks the waker's scan position in wake list and break the wake up walk, to allow access to the list before the waker resume its walk down the rest of the wait list. It lowers the interrupt and rescheduling latency. This patch also provides a performance boost when combined with the next patch to break up page wakeup list walk. We saw 22% improvement in the will-it-scale file pread2 test on a Xeon Phi system running 256 threads. [ v2: Merged in Linus' changes to remove the bookmark_wake_function, and simply access to flags. ] Reported-by: Kan Liang <kan.liang@intel.com> Tested-by: Kan Liang <kan.liang@intel.com> Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-08-25 18:13:54 +02:00
__wake_up_common(wq_head, mode, nr, 0, NULL, NULL);
}
EXPORT_SYMBOL_GPL(__wake_up_locked);
void __wake_up_locked_key(struct wait_queue_head *wq_head, unsigned int mode, void *key)
{
sched/wait: Break up long wake list walk We encountered workloads that have very long wake up list on large systems. A waker takes a long time to traverse the entire wake list and execute all the wake functions. We saw page wait list that are up to 3700+ entries long in tests of large 4 and 8 socket systems. It took 0.8 sec to traverse such list during wake up. Any other CPU that contends for the list spin lock will spin for a long time. It is a result of the numa balancing migration of hot pages that are shared by many threads. Multiple CPUs waking are queued up behind the lock, and the last one queued has to wait until all CPUs did all the wakeups. The page wait list is traversed with interrupt disabled, which caused various problems. This was the original cause that triggered the NMI watch dog timer in: https://patchwork.kernel.org/patch/9800303/ . Only extending the NMI watch dog timer there helped. This patch bookmarks the waker's scan position in wake list and break the wake up walk, to allow access to the list before the waker resume its walk down the rest of the wait list. It lowers the interrupt and rescheduling latency. This patch also provides a performance boost when combined with the next patch to break up page wakeup list walk. We saw 22% improvement in the will-it-scale file pread2 test on a Xeon Phi system running 256 threads. [ v2: Merged in Linus' changes to remove the bookmark_wake_function, and simply access to flags. ] Reported-by: Kan Liang <kan.liang@intel.com> Tested-by: Kan Liang <kan.liang@intel.com> Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-08-25 18:13:54 +02:00
__wake_up_common(wq_head, mode, 1, 0, key, NULL);
}
EXPORT_SYMBOL_GPL(__wake_up_locked_key);
void __wake_up_locked_key_bookmark(struct wait_queue_head *wq_head,
unsigned int mode, void *key, wait_queue_entry_t *bookmark)
{
__wake_up_common(wq_head, mode, 1, 0, key, bookmark);
}
EXPORT_SYMBOL_GPL(__wake_up_locked_key_bookmark);
/**
* __wake_up_sync_key - wake up threads blocked on a waitqueue.
* @wq_head: the waitqueue
* @mode: which threads
* @nr_exclusive: how many wake-one or wake-many threads to wake up
* @key: opaque value to be passed to wakeup targets
*
* The sync wakeup differs that the waker knows that it will schedule
* away soon, so while the target thread will be woken up, it will not
* be migrated to another CPU - ie. the two threads are 'synchronized'
* with each other. This can prevent needless bouncing between CPUs.
*
* On UP it can prevent extra preemption.
*
* If this function wakes up a task, it executes a full memory barrier before
* accessing the task state.
*/
void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode,
int nr_exclusive, void *key)
{
int wake_flags = 1; /* XXX WF_SYNC */
if (unlikely(!wq_head))
return;
if (unlikely(nr_exclusive != 1))
wake_flags = 0;
sched/wait: Break up long wake list walk We encountered workloads that have very long wake up list on large systems. A waker takes a long time to traverse the entire wake list and execute all the wake functions. We saw page wait list that are up to 3700+ entries long in tests of large 4 and 8 socket systems. It took 0.8 sec to traverse such list during wake up. Any other CPU that contends for the list spin lock will spin for a long time. It is a result of the numa balancing migration of hot pages that are shared by many threads. Multiple CPUs waking are queued up behind the lock, and the last one queued has to wait until all CPUs did all the wakeups. The page wait list is traversed with interrupt disabled, which caused various problems. This was the original cause that triggered the NMI watch dog timer in: https://patchwork.kernel.org/patch/9800303/ . Only extending the NMI watch dog timer there helped. This patch bookmarks the waker's scan position in wake list and break the wake up walk, to allow access to the list before the waker resume its walk down the rest of the wait list. It lowers the interrupt and rescheduling latency. This patch also provides a performance boost when combined with the next patch to break up page wakeup list walk. We saw 22% improvement in the will-it-scale file pread2 test on a Xeon Phi system running 256 threads. [ v2: Merged in Linus' changes to remove the bookmark_wake_function, and simply access to flags. ] Reported-by: Kan Liang <kan.liang@intel.com> Tested-by: Kan Liang <kan.liang@intel.com> Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-08-25 18:13:54 +02:00
__wake_up_common_lock(wq_head, mode, nr_exclusive, wake_flags, key);
}
EXPORT_SYMBOL_GPL(__wake_up_sync_key);
/*
* __wake_up_sync - see __wake_up_sync_key()
*/
void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode, int nr_exclusive)
{
__wake_up_sync_key(wq_head, mode, nr_exclusive, NULL);
}
EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */
/*
* Note: we use "set_current_state()" _after_ the wait-queue add,
* because we need a memory barrier there on SMP, so that any
* wake-function that tests for the wait-queue being active
* will be guaranteed to see waitqueue addition _or_ subsequent
* tests in this thread will see the wakeup having taken place.
*
* The spin_unlock() itself is semi-permeable and only protects
* one way (it only protects stuff inside the critical region and
* stops them from bleeding out - it would still allow subsequent
* loads to move into the critical region).
*/
void
prepare_to_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state)
{
unsigned long flags;
sched/wait: Standardize internal naming of wait-queue entries So the various wait-queue entry variables in include/linux/wait.h and kernel/sched/wait.c are named in a colorfully inconsistent way: wait_queue_entry_t *wait wait_queue_entry_t *__wait (even in plain C code!) wait_queue_entry_t *q (!) wait_queue_entry_t *new (making anyone who knows C++ cringe) wait_queue_entry_t *old I think part of the reason for the inconsistency is the constant apparent confusion about what a wait queue 'head' versus 'entry' is. ( Some of the documentation talks about a 'wait descriptor', which is the wait-queue entry itself - further adding to the confusion. ) The most common name is 'wait', but that in itself is somewhat ambiguous as well, as it does not really make it clear whether it's a wait-queue entry or head. To improve all this name the wait-queue entry structure parameters and variables consistently and push through this naming into all the wait.h and wait.c code: struct wait_queue_entry *wq_entry The 'wq_' prefix makes it easy to grep for, and we also use the opportunity to move away from the typedef to a plain 'struct' naming: in the kernel we typically reserve typedefs for cases where a C structure is really small and somewhat opaque - such as pte_t. wait-queue entries are neither small nor opaque, so use the more standard 'struct xxx_entry' list management code nomenclature instead. ( We don't touch external users, and we preserve the typedef as well for actual wait-queue users, to reduce unnecessary churn. ) Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-03-05 10:33:16 +01:00
wq_entry->flags &= ~WQ_FLAG_EXCLUSIVE;
spin_lock_irqsave(&wq_head->lock, flags);
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming So I've noticed a number of instances where it was not obvious from the code whether ->task_list was for a wait-queue head or a wait-queue entry. Furthermore, there's a number of wait-queue users where the lists are not for 'tasks' but other entities (poll tables, etc.), in which case the 'task_list' name is actively confusing. To clear this all up, name the wait-queue head and entry list structure fields unambiguously: struct wait_queue_head::task_list => ::head struct wait_queue_entry::task_list => ::entry For example, this code: rqw->wait.task_list.next != &wait->task_list ... is was pretty unclear (to me) what it's doing, while now it's written this way: rqw->wait.head.next != &wait->entry ... which makes it pretty clear that we are iterating a list until we see the head. Other examples are: list_for_each_entry_safe(pos, next, &x->task_list, task_list) { list_for_each_entry(wq, &fence->wait.task_list, task_list) { ... where it's unclear (to me) what we are iterating, and during review it's hard to tell whether it's trying to walk a wait-queue entry (which would be a bug), while now it's written as: list_for_each_entry_safe(pos, next, &x->head, entry) { list_for_each_entry(wq, &fence->wait.head, entry) { Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-20 12:06:46 +02:00
if (list_empty(&wq_entry->entry))
__add_wait_queue(wq_head, wq_entry);
set_current_state(state);
spin_unlock_irqrestore(&wq_head->lock, flags);
}
EXPORT_SYMBOL(prepare_to_wait);
void
prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state)
{
unsigned long flags;
sched/wait: Standardize internal naming of wait-queue entries So the various wait-queue entry variables in include/linux/wait.h and kernel/sched/wait.c are named in a colorfully inconsistent way: wait_queue_entry_t *wait wait_queue_entry_t *__wait (even in plain C code!) wait_queue_entry_t *q (!) wait_queue_entry_t *new (making anyone who knows C++ cringe) wait_queue_entry_t *old I think part of the reason for the inconsistency is the constant apparent confusion about what a wait queue 'head' versus 'entry' is. ( Some of the documentation talks about a 'wait descriptor', which is the wait-queue entry itself - further adding to the confusion. ) The most common name is 'wait', but that in itself is somewhat ambiguous as well, as it does not really make it clear whether it's a wait-queue entry or head. To improve all this name the wait-queue entry structure parameters and variables consistently and push through this naming into all the wait.h and wait.c code: struct wait_queue_entry *wq_entry The 'wq_' prefix makes it easy to grep for, and we also use the opportunity to move away from the typedef to a plain 'struct' naming: in the kernel we typically reserve typedefs for cases where a C structure is really small and somewhat opaque - such as pte_t. wait-queue entries are neither small nor opaque, so use the more standard 'struct xxx_entry' list management code nomenclature instead. ( We don't touch external users, and we preserve the typedef as well for actual wait-queue users, to reduce unnecessary churn. ) Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-03-05 10:33:16 +01:00
wq_entry->flags |= WQ_FLAG_EXCLUSIVE;
spin_lock_irqsave(&wq_head->lock, flags);
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming So I've noticed a number of instances where it was not obvious from the code whether ->task_list was for a wait-queue head or a wait-queue entry. Furthermore, there's a number of wait-queue users where the lists are not for 'tasks' but other entities (poll tables, etc.), in which case the 'task_list' name is actively confusing. To clear this all up, name the wait-queue head and entry list structure fields unambiguously: struct wait_queue_head::task_list => ::head struct wait_queue_entry::task_list => ::entry For example, this code: rqw->wait.task_list.next != &wait->task_list ... is was pretty unclear (to me) what it's doing, while now it's written this way: rqw->wait.head.next != &wait->entry ... which makes it pretty clear that we are iterating a list until we see the head. Other examples are: list_for_each_entry_safe(pos, next, &x->task_list, task_list) { list_for_each_entry(wq, &fence->wait.task_list, task_list) { ... where it's unclear (to me) what we are iterating, and during review it's hard to tell whether it's trying to walk a wait-queue entry (which would be a bug), while now it's written as: list_for_each_entry_safe(pos, next, &x->head, entry) { list_for_each_entry(wq, &fence->wait.head, entry) { Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-20 12:06:46 +02:00
if (list_empty(&wq_entry->entry))
__add_wait_queue_entry_tail(wq_head, wq_entry);
set_current_state(state);
spin_unlock_irqrestore(&wq_head->lock, flags);
}
EXPORT_SYMBOL(prepare_to_wait_exclusive);
sched/wait: Standardize internal naming of wait-queue entries So the various wait-queue entry variables in include/linux/wait.h and kernel/sched/wait.c are named in a colorfully inconsistent way: wait_queue_entry_t *wait wait_queue_entry_t *__wait (even in plain C code!) wait_queue_entry_t *q (!) wait_queue_entry_t *new (making anyone who knows C++ cringe) wait_queue_entry_t *old I think part of the reason for the inconsistency is the constant apparent confusion about what a wait queue 'head' versus 'entry' is. ( Some of the documentation talks about a 'wait descriptor', which is the wait-queue entry itself - further adding to the confusion. ) The most common name is 'wait', but that in itself is somewhat ambiguous as well, as it does not really make it clear whether it's a wait-queue entry or head. To improve all this name the wait-queue entry structure parameters and variables consistently and push through this naming into all the wait.h and wait.c code: struct wait_queue_entry *wq_entry The 'wq_' prefix makes it easy to grep for, and we also use the opportunity to move away from the typedef to a plain 'struct' naming: in the kernel we typically reserve typedefs for cases where a C structure is really small and somewhat opaque - such as pte_t. wait-queue entries are neither small nor opaque, so use the more standard 'struct xxx_entry' list management code nomenclature instead. ( We don't touch external users, and we preserve the typedef as well for actual wait-queue users, to reduce unnecessary churn. ) Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-03-05 10:33:16 +01:00
void init_wait_entry(struct wait_queue_entry *wq_entry, int flags)
{
sched/wait: Standardize internal naming of wait-queue entries So the various wait-queue entry variables in include/linux/wait.h and kernel/sched/wait.c are named in a colorfully inconsistent way: wait_queue_entry_t *wait wait_queue_entry_t *__wait (even in plain C code!) wait_queue_entry_t *q (!) wait_queue_entry_t *new (making anyone who knows C++ cringe) wait_queue_entry_t *old I think part of the reason for the inconsistency is the constant apparent confusion about what a wait queue 'head' versus 'entry' is. ( Some of the documentation talks about a 'wait descriptor', which is the wait-queue entry itself - further adding to the confusion. ) The most common name is 'wait', but that in itself is somewhat ambiguous as well, as it does not really make it clear whether it's a wait-queue entry or head. To improve all this name the wait-queue entry structure parameters and variables consistently and push through this naming into all the wait.h and wait.c code: struct wait_queue_entry *wq_entry The 'wq_' prefix makes it easy to grep for, and we also use the opportunity to move away from the typedef to a plain 'struct' naming: in the kernel we typically reserve typedefs for cases where a C structure is really small and somewhat opaque - such as pte_t. wait-queue entries are neither small nor opaque, so use the more standard 'struct xxx_entry' list management code nomenclature instead. ( We don't touch external users, and we preserve the typedef as well for actual wait-queue users, to reduce unnecessary churn. ) Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-03-05 10:33:16 +01:00
wq_entry->flags = flags;
wq_entry->private = current;
wq_entry->func = autoremove_wake_function;
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming So I've noticed a number of instances where it was not obvious from the code whether ->task_list was for a wait-queue head or a wait-queue entry. Furthermore, there's a number of wait-queue users where the lists are not for 'tasks' but other entities (poll tables, etc.), in which case the 'task_list' name is actively confusing. To clear this all up, name the wait-queue head and entry list structure fields unambiguously: struct wait_queue_head::task_list => ::head struct wait_queue_entry::task_list => ::entry For example, this code: rqw->wait.task_list.next != &wait->task_list ... is was pretty unclear (to me) what it's doing, while now it's written this way: rqw->wait.head.next != &wait->entry ... which makes it pretty clear that we are iterating a list until we see the head. Other examples are: list_for_each_entry_safe(pos, next, &x->task_list, task_list) { list_for_each_entry(wq, &fence->wait.task_list, task_list) { ... where it's unclear (to me) what we are iterating, and during review it's hard to tell whether it's trying to walk a wait-queue entry (which would be a bug), while now it's written as: list_for_each_entry_safe(pos, next, &x->head, entry) { list_for_each_entry(wq, &fence->wait.head, entry) { Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-20 12:06:46 +02:00
INIT_LIST_HEAD(&wq_entry->entry);
}
EXPORT_SYMBOL(init_wait_entry);
long prepare_to_wait_event(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state)
{
unsigned long flags;
long ret = 0;
spin_lock_irqsave(&wq_head->lock, flags);
if (signal_pending_state(state, current)) {
/*
* Exclusive waiter must not fail if it was selected by wakeup,
* it should "consume" the condition we were waiting for.
*
* The caller will recheck the condition and return success if
* we were already woken up, we can not miss the event because
* wakeup locks/unlocks the same wq_head->lock.
*
* But we need to ensure that set-condition + wakeup after that
* can't see us, it should wake up another exclusive waiter if
* we fail.
*/
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming So I've noticed a number of instances where it was not obvious from the code whether ->task_list was for a wait-queue head or a wait-queue entry. Furthermore, there's a number of wait-queue users where the lists are not for 'tasks' but other entities (poll tables, etc.), in which case the 'task_list' name is actively confusing. To clear this all up, name the wait-queue head and entry list structure fields unambiguously: struct wait_queue_head::task_list => ::head struct wait_queue_entry::task_list => ::entry For example, this code: rqw->wait.task_list.next != &wait->task_list ... is was pretty unclear (to me) what it's doing, while now it's written this way: rqw->wait.head.next != &wait->entry ... which makes it pretty clear that we are iterating a list until we see the head. Other examples are: list_for_each_entry_safe(pos, next, &x->task_list, task_list) { list_for_each_entry(wq, &fence->wait.task_list, task_list) { ... where it's unclear (to me) what we are iterating, and during review it's hard to tell whether it's trying to walk a wait-queue entry (which would be a bug), while now it's written as: list_for_each_entry_safe(pos, next, &x->head, entry) { list_for_each_entry(wq, &fence->wait.head, entry) { Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-20 12:06:46 +02:00
list_del_init(&wq_entry->entry);
ret = -ERESTARTSYS;
} else {
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming So I've noticed a number of instances where it was not obvious from the code whether ->task_list was for a wait-queue head or a wait-queue entry. Furthermore, there's a number of wait-queue users where the lists are not for 'tasks' but other entities (poll tables, etc.), in which case the 'task_list' name is actively confusing. To clear this all up, name the wait-queue head and entry list structure fields unambiguously: struct wait_queue_head::task_list => ::head struct wait_queue_entry::task_list => ::entry For example, this code: rqw->wait.task_list.next != &wait->task_list ... is was pretty unclear (to me) what it's doing, while now it's written this way: rqw->wait.head.next != &wait->entry ... which makes it pretty clear that we are iterating a list until we see the head. Other examples are: list_for_each_entry_safe(pos, next, &x->task_list, task_list) { list_for_each_entry(wq, &fence->wait.task_list, task_list) { ... where it's unclear (to me) what we are iterating, and during review it's hard to tell whether it's trying to walk a wait-queue entry (which would be a bug), while now it's written as: list_for_each_entry_safe(pos, next, &x->head, entry) { list_for_each_entry(wq, &fence->wait.head, entry) { Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-20 12:06:46 +02:00
if (list_empty(&wq_entry->entry)) {
sched/wait: Standardize internal naming of wait-queue entries So the various wait-queue entry variables in include/linux/wait.h and kernel/sched/wait.c are named in a colorfully inconsistent way: wait_queue_entry_t *wait wait_queue_entry_t *__wait (even in plain C code!) wait_queue_entry_t *q (!) wait_queue_entry_t *new (making anyone who knows C++ cringe) wait_queue_entry_t *old I think part of the reason for the inconsistency is the constant apparent confusion about what a wait queue 'head' versus 'entry' is. ( Some of the documentation talks about a 'wait descriptor', which is the wait-queue entry itself - further adding to the confusion. ) The most common name is 'wait', but that in itself is somewhat ambiguous as well, as it does not really make it clear whether it's a wait-queue entry or head. To improve all this name the wait-queue entry structure parameters and variables consistently and push through this naming into all the wait.h and wait.c code: struct wait_queue_entry *wq_entry The 'wq_' prefix makes it easy to grep for, and we also use the opportunity to move away from the typedef to a plain 'struct' naming: in the kernel we typically reserve typedefs for cases where a C structure is really small and somewhat opaque - such as pte_t. wait-queue entries are neither small nor opaque, so use the more standard 'struct xxx_entry' list management code nomenclature instead. ( We don't touch external users, and we preserve the typedef as well for actual wait-queue users, to reduce unnecessary churn. ) Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-03-05 10:33:16 +01:00
if (wq_entry->flags & WQ_FLAG_EXCLUSIVE)
__add_wait_queue_entry_tail(wq_head, wq_entry);
else
__add_wait_queue(wq_head, wq_entry);
}
set_current_state(state);
}
spin_unlock_irqrestore(&wq_head->lock, flags);
return ret;
}
EXPORT_SYMBOL(prepare_to_wait_event);
/*
* Note! These two wait functions are entered with the
* wait-queue lock held (and interrupts off in the _irq
* case), so there is no race with testing the wakeup
* condition in the caller before they add the wait
* entry to the wake queue.
*/
int do_wait_intr(wait_queue_head_t *wq, wait_queue_entry_t *wait)
{
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming So I've noticed a number of instances where it was not obvious from the code whether ->task_list was for a wait-queue head or a wait-queue entry. Furthermore, there's a number of wait-queue users where the lists are not for 'tasks' but other entities (poll tables, etc.), in which case the 'task_list' name is actively confusing. To clear this all up, name the wait-queue head and entry list structure fields unambiguously: struct wait_queue_head::task_list => ::head struct wait_queue_entry::task_list => ::entry For example, this code: rqw->wait.task_list.next != &wait->task_list ... is was pretty unclear (to me) what it's doing, while now it's written this way: rqw->wait.head.next != &wait->entry ... which makes it pretty clear that we are iterating a list until we see the head. Other examples are: list_for_each_entry_safe(pos, next, &x->task_list, task_list) { list_for_each_entry(wq, &fence->wait.task_list, task_list) { ... where it's unclear (to me) what we are iterating, and during review it's hard to tell whether it's trying to walk a wait-queue entry (which would be a bug), while now it's written as: list_for_each_entry_safe(pos, next, &x->head, entry) { list_for_each_entry(wq, &fence->wait.head, entry) { Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-20 12:06:46 +02:00
if (likely(list_empty(&wait->entry)))
__add_wait_queue_entry_tail(wq, wait);
set_current_state(TASK_INTERRUPTIBLE);
if (signal_pending(current))
return -ERESTARTSYS;
spin_unlock(&wq->lock);
schedule();
spin_lock(&wq->lock);
return 0;
}
EXPORT_SYMBOL(do_wait_intr);
int do_wait_intr_irq(wait_queue_head_t *wq, wait_queue_entry_t *wait)
{
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming So I've noticed a number of instances where it was not obvious from the code whether ->task_list was for a wait-queue head or a wait-queue entry. Furthermore, there's a number of wait-queue users where the lists are not for 'tasks' but other entities (poll tables, etc.), in which case the 'task_list' name is actively confusing. To clear this all up, name the wait-queue head and entry list structure fields unambiguously: struct wait_queue_head::task_list => ::head struct wait_queue_entry::task_list => ::entry For example, this code: rqw->wait.task_list.next != &wait->task_list ... is was pretty unclear (to me) what it's doing, while now it's written this way: rqw->wait.head.next != &wait->entry ... which makes it pretty clear that we are iterating a list until we see the head. Other examples are: list_for_each_entry_safe(pos, next, &x->task_list, task_list) { list_for_each_entry(wq, &fence->wait.task_list, task_list) { ... where it's unclear (to me) what we are iterating, and during review it's hard to tell whether it's trying to walk a wait-queue entry (which would be a bug), while now it's written as: list_for_each_entry_safe(pos, next, &x->head, entry) { list_for_each_entry(wq, &fence->wait.head, entry) { Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-20 12:06:46 +02:00
if (likely(list_empty(&wait->entry)))
__add_wait_queue_entry_tail(wq, wait);
set_current_state(TASK_INTERRUPTIBLE);
if (signal_pending(current))
return -ERESTARTSYS;
spin_unlock_irq(&wq->lock);
schedule();
spin_lock_irq(&wq->lock);
return 0;
}
EXPORT_SYMBOL(do_wait_intr_irq);
/**
wait: prevent exclusive waiter starvation With exclusive waiters, every process woken up through the wait queue must ensure that the next waiter down the line is woken when it has finished. Interruptible waiters don't do that when aborting due to a signal. And if an aborting waiter is concurrently woken up through the waitqueue, noone will ever wake up the next waiter. This has been observed with __wait_on_bit_lock() used by lock_page_killable(): the first contender on the queue was aborting when the actual lock holder woke it up concurrently. The aborted contender didn't acquire the lock and therefor never did an unlock followed by waking up the next waiter. Add abort_exclusive_wait() which removes the process' wait descriptor from the waitqueue, iff still queued, or wakes up the next waiter otherwise. It does so under the waitqueue lock. Racing with a wake up means the aborting process is either already woken (removed from the queue) and will wake up the next waiter, or it will remove itself from the queue and the concurrent wake up will apply to the next waiter after it. Use abort_exclusive_wait() in __wait_event_interruptible_exclusive() and __wait_on_bit_lock() when they were interrupted by other means than a wake up through the queue. [akpm@linux-foundation.org: coding-style fixes] Reported-by: Chris Mason <chris.mason@oracle.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Mentored-by: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Chuck Lever <cel@citi.umich.edu> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Ingo Molnar <mingo@elte.hu> Cc: <stable@kernel.org> ["after some testing"] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-02-05 00:12:14 +01:00
* finish_wait - clean up after waiting in a queue
* @wq_head: waitqueue waited on
sched/wait: Standardize internal naming of wait-queue entries So the various wait-queue entry variables in include/linux/wait.h and kernel/sched/wait.c are named in a colorfully inconsistent way: wait_queue_entry_t *wait wait_queue_entry_t *__wait (even in plain C code!) wait_queue_entry_t *q (!) wait_queue_entry_t *new (making anyone who knows C++ cringe) wait_queue_entry_t *old I think part of the reason for the inconsistency is the constant apparent confusion about what a wait queue 'head' versus 'entry' is. ( Some of the documentation talks about a 'wait descriptor', which is the wait-queue entry itself - further adding to the confusion. ) The most common name is 'wait', but that in itself is somewhat ambiguous as well, as it does not really make it clear whether it's a wait-queue entry or head. To improve all this name the wait-queue entry structure parameters and variables consistently and push through this naming into all the wait.h and wait.c code: struct wait_queue_entry *wq_entry The 'wq_' prefix makes it easy to grep for, and we also use the opportunity to move away from the typedef to a plain 'struct' naming: in the kernel we typically reserve typedefs for cases where a C structure is really small and somewhat opaque - such as pte_t. wait-queue entries are neither small nor opaque, so use the more standard 'struct xxx_entry' list management code nomenclature instead. ( We don't touch external users, and we preserve the typedef as well for actual wait-queue users, to reduce unnecessary churn. ) Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-03-05 10:33:16 +01:00
* @wq_entry: wait descriptor
wait: prevent exclusive waiter starvation With exclusive waiters, every process woken up through the wait queue must ensure that the next waiter down the line is woken when it has finished. Interruptible waiters don't do that when aborting due to a signal. And if an aborting waiter is concurrently woken up through the waitqueue, noone will ever wake up the next waiter. This has been observed with __wait_on_bit_lock() used by lock_page_killable(): the first contender on the queue was aborting when the actual lock holder woke it up concurrently. The aborted contender didn't acquire the lock and therefor never did an unlock followed by waking up the next waiter. Add abort_exclusive_wait() which removes the process' wait descriptor from the waitqueue, iff still queued, or wakes up the next waiter otherwise. It does so under the waitqueue lock. Racing with a wake up means the aborting process is either already woken (removed from the queue) and will wake up the next waiter, or it will remove itself from the queue and the concurrent wake up will apply to the next waiter after it. Use abort_exclusive_wait() in __wait_event_interruptible_exclusive() and __wait_on_bit_lock() when they were interrupted by other means than a wake up through the queue. [akpm@linux-foundation.org: coding-style fixes] Reported-by: Chris Mason <chris.mason@oracle.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Mentored-by: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Chuck Lever <cel@citi.umich.edu> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Ingo Molnar <mingo@elte.hu> Cc: <stable@kernel.org> ["after some testing"] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-02-05 00:12:14 +01:00
*
* Sets current thread back to running state and removes
* the wait descriptor from the given waitqueue if still
* queued.
*/
void finish_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
{
unsigned long flags;
__set_current_state(TASK_RUNNING);
/*
* We can check for list emptiness outside the lock
* IFF:
* - we use the "careful" check that verifies both
* the next and prev pointers, so that there cannot
* be any half-pending updates in progress on other
* CPU's that we haven't seen yet (and that might
* still change the stack area.
* and
* - all other users take the lock (ie we can only
* have _one_ other CPU that looks at or modifies
* the list).
*/
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming So I've noticed a number of instances where it was not obvious from the code whether ->task_list was for a wait-queue head or a wait-queue entry. Furthermore, there's a number of wait-queue users where the lists are not for 'tasks' but other entities (poll tables, etc.), in which case the 'task_list' name is actively confusing. To clear this all up, name the wait-queue head and entry list structure fields unambiguously: struct wait_queue_head::task_list => ::head struct wait_queue_entry::task_list => ::entry For example, this code: rqw->wait.task_list.next != &wait->task_list ... is was pretty unclear (to me) what it's doing, while now it's written this way: rqw->wait.head.next != &wait->entry ... which makes it pretty clear that we are iterating a list until we see the head. Other examples are: list_for_each_entry_safe(pos, next, &x->task_list, task_list) { list_for_each_entry(wq, &fence->wait.task_list, task_list) { ... where it's unclear (to me) what we are iterating, and during review it's hard to tell whether it's trying to walk a wait-queue entry (which would be a bug), while now it's written as: list_for_each_entry_safe(pos, next, &x->head, entry) { list_for_each_entry(wq, &fence->wait.head, entry) { Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-20 12:06:46 +02:00
if (!list_empty_careful(&wq_entry->entry)) {
spin_lock_irqsave(&wq_head->lock, flags);
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming So I've noticed a number of instances where it was not obvious from the code whether ->task_list was for a wait-queue head or a wait-queue entry. Furthermore, there's a number of wait-queue users where the lists are not for 'tasks' but other entities (poll tables, etc.), in which case the 'task_list' name is actively confusing. To clear this all up, name the wait-queue head and entry list structure fields unambiguously: struct wait_queue_head::task_list => ::head struct wait_queue_entry::task_list => ::entry For example, this code: rqw->wait.task_list.next != &wait->task_list ... is was pretty unclear (to me) what it's doing, while now it's written this way: rqw->wait.head.next != &wait->entry ... which makes it pretty clear that we are iterating a list until we see the head. Other examples are: list_for_each_entry_safe(pos, next, &x->task_list, task_list) { list_for_each_entry(wq, &fence->wait.task_list, task_list) { ... where it's unclear (to me) what we are iterating, and during review it's hard to tell whether it's trying to walk a wait-queue entry (which would be a bug), while now it's written as: list_for_each_entry_safe(pos, next, &x->head, entry) { list_for_each_entry(wq, &fence->wait.head, entry) { Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-20 12:06:46 +02:00
list_del_init(&wq_entry->entry);
spin_unlock_irqrestore(&wq_head->lock, flags);
}
}
EXPORT_SYMBOL(finish_wait);
sched/wait: Standardize internal naming of wait-queue entries So the various wait-queue entry variables in include/linux/wait.h and kernel/sched/wait.c are named in a colorfully inconsistent way: wait_queue_entry_t *wait wait_queue_entry_t *__wait (even in plain C code!) wait_queue_entry_t *q (!) wait_queue_entry_t *new (making anyone who knows C++ cringe) wait_queue_entry_t *old I think part of the reason for the inconsistency is the constant apparent confusion about what a wait queue 'head' versus 'entry' is. ( Some of the documentation talks about a 'wait descriptor', which is the wait-queue entry itself - further adding to the confusion. ) The most common name is 'wait', but that in itself is somewhat ambiguous as well, as it does not really make it clear whether it's a wait-queue entry or head. To improve all this name the wait-queue entry structure parameters and variables consistently and push through this naming into all the wait.h and wait.c code: struct wait_queue_entry *wq_entry The 'wq_' prefix makes it easy to grep for, and we also use the opportunity to move away from the typedef to a plain 'struct' naming: in the kernel we typically reserve typedefs for cases where a C structure is really small and somewhat opaque - such as pte_t. wait-queue entries are neither small nor opaque, so use the more standard 'struct xxx_entry' list management code nomenclature instead. ( We don't touch external users, and we preserve the typedef as well for actual wait-queue users, to reduce unnecessary churn. ) Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-03-05 10:33:16 +01:00
int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key)
{
sched/wait: Standardize internal naming of wait-queue entries So the various wait-queue entry variables in include/linux/wait.h and kernel/sched/wait.c are named in a colorfully inconsistent way: wait_queue_entry_t *wait wait_queue_entry_t *__wait (even in plain C code!) wait_queue_entry_t *q (!) wait_queue_entry_t *new (making anyone who knows C++ cringe) wait_queue_entry_t *old I think part of the reason for the inconsistency is the constant apparent confusion about what a wait queue 'head' versus 'entry' is. ( Some of the documentation talks about a 'wait descriptor', which is the wait-queue entry itself - further adding to the confusion. ) The most common name is 'wait', but that in itself is somewhat ambiguous as well, as it does not really make it clear whether it's a wait-queue entry or head. To improve all this name the wait-queue entry structure parameters and variables consistently and push through this naming into all the wait.h and wait.c code: struct wait_queue_entry *wq_entry The 'wq_' prefix makes it easy to grep for, and we also use the opportunity to move away from the typedef to a plain 'struct' naming: in the kernel we typically reserve typedefs for cases where a C structure is really small and somewhat opaque - such as pte_t. wait-queue entries are neither small nor opaque, so use the more standard 'struct xxx_entry' list management code nomenclature instead. ( We don't touch external users, and we preserve the typedef as well for actual wait-queue users, to reduce unnecessary churn. ) Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-03-05 10:33:16 +01:00
int ret = default_wake_function(wq_entry, mode, sync, key);
if (ret)
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming So I've noticed a number of instances where it was not obvious from the code whether ->task_list was for a wait-queue head or a wait-queue entry. Furthermore, there's a number of wait-queue users where the lists are not for 'tasks' but other entities (poll tables, etc.), in which case the 'task_list' name is actively confusing. To clear this all up, name the wait-queue head and entry list structure fields unambiguously: struct wait_queue_head::task_list => ::head struct wait_queue_entry::task_list => ::entry For example, this code: rqw->wait.task_list.next != &wait->task_list ... is was pretty unclear (to me) what it's doing, while now it's written this way: rqw->wait.head.next != &wait->entry ... which makes it pretty clear that we are iterating a list until we see the head. Other examples are: list_for_each_entry_safe(pos, next, &x->task_list, task_list) { list_for_each_entry(wq, &fence->wait.task_list, task_list) { ... where it's unclear (to me) what we are iterating, and during review it's hard to tell whether it's trying to walk a wait-queue entry (which would be a bug), while now it's written as: list_for_each_entry_safe(pos, next, &x->head, entry) { list_for_each_entry(wq, &fence->wait.head, entry) { Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-20 12:06:46 +02:00
list_del_init(&wq_entry->entry);
return ret;
}
EXPORT_SYMBOL(autoremove_wake_function);
static inline bool is_kthread_should_stop(void)
{
return (current->flags & PF_KTHREAD) && kthread_should_stop();
}
/*
* DEFINE_WAIT_FUNC(wait, woken_wake_func);
*
* add_wait_queue(&wq_head, &wait);
* for (;;) {
* if (condition)
* break;
*
sched/core: Use smp_mb() in wake_woken_function() wake_woken_function() synchronizes with wait_woken() as follows: [wait_woken] [wake_woken_function] entry->flags &= ~wq_flag_woken; condition = true; smp_mb(); smp_wmb(); if (condition) wq_entry->flags |= wq_flag_woken; break; This commit replaces the above smp_wmb() with an smp_mb() in order to guarantee that either wait_woken() sees the wait condition being true or the store to wq_entry->flags in woken_wake_function() follows the store in wait_woken() in the coherence order (so that the former can eventually be observed by wait_woken()). The commit also fixes a comment associated to set_current_state() in wait_woken(): the comment pairs the barrier in set_current_state() to the above smp_wmb(), while the actual pairing involves the barrier in set_current_state() and the barrier executed by the try_to_wake_up() in wake_woken_function(). Signed-off-by: Andrea Parri <andrea.parri@amarulasolutions.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: akiyks@gmail.com Cc: boqun.feng@gmail.com Cc: dhowells@redhat.com Cc: j.alglave@ucl.ac.uk Cc: linux-arch@vger.kernel.org Cc: luc.maranget@inria.fr Cc: npiggin@gmail.com Cc: parri.andrea@gmail.com Cc: stern@rowland.harvard.edu Cc: will.deacon@arm.com Link: http://lkml.kernel.org/r/20180716180605.16115-10-paulmck@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-07-16 20:06:01 +02:00
* // in wait_woken() // in woken_wake_function()
*
sched/core: Use smp_mb() in wake_woken_function() wake_woken_function() synchronizes with wait_woken() as follows: [wait_woken] [wake_woken_function] entry->flags &= ~wq_flag_woken; condition = true; smp_mb(); smp_wmb(); if (condition) wq_entry->flags |= wq_flag_woken; break; This commit replaces the above smp_wmb() with an smp_mb() in order to guarantee that either wait_woken() sees the wait condition being true or the store to wq_entry->flags in woken_wake_function() follows the store in wait_woken() in the coherence order (so that the former can eventually be observed by wait_woken()). The commit also fixes a comment associated to set_current_state() in wait_woken(): the comment pairs the barrier in set_current_state() to the above smp_wmb(), while the actual pairing involves the barrier in set_current_state() and the barrier executed by the try_to_wake_up() in wake_woken_function(). Signed-off-by: Andrea Parri <andrea.parri@amarulasolutions.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: akiyks@gmail.com Cc: boqun.feng@gmail.com Cc: dhowells@redhat.com Cc: j.alglave@ucl.ac.uk Cc: linux-arch@vger.kernel.org Cc: luc.maranget@inria.fr Cc: npiggin@gmail.com Cc: parri.andrea@gmail.com Cc: stern@rowland.harvard.edu Cc: will.deacon@arm.com Link: http://lkml.kernel.org/r/20180716180605.16115-10-paulmck@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-07-16 20:06:01 +02:00
* p->state = mode; wq_entry->flags |= WQ_FLAG_WOKEN;
* smp_mb(); // A try_to_wake_up():
* if (!(wq_entry->flags & WQ_FLAG_WOKEN)) <full barrier>
* schedule() if (p->state & mode)
* p->state = TASK_RUNNING; p->state = TASK_RUNNING;
* wq_entry->flags &= ~WQ_FLAG_WOKEN; ~~~~~~~~~~~~~~~~~~
* smp_mb(); // B condition = true;
* } smp_mb(); // C
* remove_wait_queue(&wq_head, &wait); wq_entry->flags |= WQ_FLAG_WOKEN;
*/
sched/wait: Standardize internal naming of wait-queue entries So the various wait-queue entry variables in include/linux/wait.h and kernel/sched/wait.c are named in a colorfully inconsistent way: wait_queue_entry_t *wait wait_queue_entry_t *__wait (even in plain C code!) wait_queue_entry_t *q (!) wait_queue_entry_t *new (making anyone who knows C++ cringe) wait_queue_entry_t *old I think part of the reason for the inconsistency is the constant apparent confusion about what a wait queue 'head' versus 'entry' is. ( Some of the documentation talks about a 'wait descriptor', which is the wait-queue entry itself - further adding to the confusion. ) The most common name is 'wait', but that in itself is somewhat ambiguous as well, as it does not really make it clear whether it's a wait-queue entry or head. To improve all this name the wait-queue entry structure parameters and variables consistently and push through this naming into all the wait.h and wait.c code: struct wait_queue_entry *wq_entry The 'wq_' prefix makes it easy to grep for, and we also use the opportunity to move away from the typedef to a plain 'struct' naming: in the kernel we typically reserve typedefs for cases where a C structure is really small and somewhat opaque - such as pte_t. wait-queue entries are neither small nor opaque, so use the more standard 'struct xxx_entry' list management code nomenclature instead. ( We don't touch external users, and we preserve the typedef as well for actual wait-queue users, to reduce unnecessary churn. ) Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-03-05 10:33:16 +01:00
long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout)
{
/*
sched/core: Use smp_mb() in wake_woken_function() wake_woken_function() synchronizes with wait_woken() as follows: [wait_woken] [wake_woken_function] entry->flags &= ~wq_flag_woken; condition = true; smp_mb(); smp_wmb(); if (condition) wq_entry->flags |= wq_flag_woken; break; This commit replaces the above smp_wmb() with an smp_mb() in order to guarantee that either wait_woken() sees the wait condition being true or the store to wq_entry->flags in woken_wake_function() follows the store in wait_woken() in the coherence order (so that the former can eventually be observed by wait_woken()). The commit also fixes a comment associated to set_current_state() in wait_woken(): the comment pairs the barrier in set_current_state() to the above smp_wmb(), while the actual pairing involves the barrier in set_current_state() and the barrier executed by the try_to_wake_up() in wake_woken_function(). Signed-off-by: Andrea Parri <andrea.parri@amarulasolutions.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: akiyks@gmail.com Cc: boqun.feng@gmail.com Cc: dhowells@redhat.com Cc: j.alglave@ucl.ac.uk Cc: linux-arch@vger.kernel.org Cc: luc.maranget@inria.fr Cc: npiggin@gmail.com Cc: parri.andrea@gmail.com Cc: stern@rowland.harvard.edu Cc: will.deacon@arm.com Link: http://lkml.kernel.org/r/20180716180605.16115-10-paulmck@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-07-16 20:06:01 +02:00
* The below executes an smp_mb(), which matches with the full barrier
* executed by the try_to_wake_up() in woken_wake_function() such that
* either we see the store to wq_entry->flags in woken_wake_function()
* or woken_wake_function() sees our store to current->state.
*/
sched/core: Use smp_mb() in wake_woken_function() wake_woken_function() synchronizes with wait_woken() as follows: [wait_woken] [wake_woken_function] entry->flags &= ~wq_flag_woken; condition = true; smp_mb(); smp_wmb(); if (condition) wq_entry->flags |= wq_flag_woken; break; This commit replaces the above smp_wmb() with an smp_mb() in order to guarantee that either wait_woken() sees the wait condition being true or the store to wq_entry->flags in woken_wake_function() follows the store in wait_woken() in the coherence order (so that the former can eventually be observed by wait_woken()). The commit also fixes a comment associated to set_current_state() in wait_woken(): the comment pairs the barrier in set_current_state() to the above smp_wmb(), while the actual pairing involves the barrier in set_current_state() and the barrier executed by the try_to_wake_up() in wake_woken_function(). Signed-off-by: Andrea Parri <andrea.parri@amarulasolutions.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: akiyks@gmail.com Cc: boqun.feng@gmail.com Cc: dhowells@redhat.com Cc: j.alglave@ucl.ac.uk Cc: linux-arch@vger.kernel.org Cc: luc.maranget@inria.fr Cc: npiggin@gmail.com Cc: parri.andrea@gmail.com Cc: stern@rowland.harvard.edu Cc: will.deacon@arm.com Link: http://lkml.kernel.org/r/20180716180605.16115-10-paulmck@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-07-16 20:06:01 +02:00
set_current_state(mode); /* A */
sched/wait: Standardize internal naming of wait-queue entries So the various wait-queue entry variables in include/linux/wait.h and kernel/sched/wait.c are named in a colorfully inconsistent way: wait_queue_entry_t *wait wait_queue_entry_t *__wait (even in plain C code!) wait_queue_entry_t *q (!) wait_queue_entry_t *new (making anyone who knows C++ cringe) wait_queue_entry_t *old I think part of the reason for the inconsistency is the constant apparent confusion about what a wait queue 'head' versus 'entry' is. ( Some of the documentation talks about a 'wait descriptor', which is the wait-queue entry itself - further adding to the confusion. ) The most common name is 'wait', but that in itself is somewhat ambiguous as well, as it does not really make it clear whether it's a wait-queue entry or head. To improve all this name the wait-queue entry structure parameters and variables consistently and push through this naming into all the wait.h and wait.c code: struct wait_queue_entry *wq_entry The 'wq_' prefix makes it easy to grep for, and we also use the opportunity to move away from the typedef to a plain 'struct' naming: in the kernel we typically reserve typedefs for cases where a C structure is really small and somewhat opaque - such as pte_t. wait-queue entries are neither small nor opaque, so use the more standard 'struct xxx_entry' list management code nomenclature instead. ( We don't touch external users, and we preserve the typedef as well for actual wait-queue users, to reduce unnecessary churn. ) Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-03-05 10:33:16 +01:00
if (!(wq_entry->flags & WQ_FLAG_WOKEN) && !is_kthread_should_stop())
timeout = schedule_timeout(timeout);
__set_current_state(TASK_RUNNING);
/*
sched/core: Use smp_mb() in wake_woken_function() wake_woken_function() synchronizes with wait_woken() as follows: [wait_woken] [wake_woken_function] entry->flags &= ~wq_flag_woken; condition = true; smp_mb(); smp_wmb(); if (condition) wq_entry->flags |= wq_flag_woken; break; This commit replaces the above smp_wmb() with an smp_mb() in order to guarantee that either wait_woken() sees the wait condition being true or the store to wq_entry->flags in woken_wake_function() follows the store in wait_woken() in the coherence order (so that the former can eventually be observed by wait_woken()). The commit also fixes a comment associated to set_current_state() in wait_woken(): the comment pairs the barrier in set_current_state() to the above smp_wmb(), while the actual pairing involves the barrier in set_current_state() and the barrier executed by the try_to_wake_up() in wake_woken_function(). Signed-off-by: Andrea Parri <andrea.parri@amarulasolutions.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: akiyks@gmail.com Cc: boqun.feng@gmail.com Cc: dhowells@redhat.com Cc: j.alglave@ucl.ac.uk Cc: linux-arch@vger.kernel.org Cc: luc.maranget@inria.fr Cc: npiggin@gmail.com Cc: parri.andrea@gmail.com Cc: stern@rowland.harvard.edu Cc: will.deacon@arm.com Link: http://lkml.kernel.org/r/20180716180605.16115-10-paulmck@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-07-16 20:06:01 +02:00
* The below executes an smp_mb(), which matches with the smp_mb() (C)
* in woken_wake_function() such that either we see the wait condition
* being true or the store to wq_entry->flags in woken_wake_function()
* follows ours in the coherence order.
*/
sched/wait: Standardize internal naming of wait-queue entries So the various wait-queue entry variables in include/linux/wait.h and kernel/sched/wait.c are named in a colorfully inconsistent way: wait_queue_entry_t *wait wait_queue_entry_t *__wait (even in plain C code!) wait_queue_entry_t *q (!) wait_queue_entry_t *new (making anyone who knows C++ cringe) wait_queue_entry_t *old I think part of the reason for the inconsistency is the constant apparent confusion about what a wait queue 'head' versus 'entry' is. ( Some of the documentation talks about a 'wait descriptor', which is the wait-queue entry itself - further adding to the confusion. ) The most common name is 'wait', but that in itself is somewhat ambiguous as well, as it does not really make it clear whether it's a wait-queue entry or head. To improve all this name the wait-queue entry structure parameters and variables consistently and push through this naming into all the wait.h and wait.c code: struct wait_queue_entry *wq_entry The 'wq_' prefix makes it easy to grep for, and we also use the opportunity to move away from the typedef to a plain 'struct' naming: in the kernel we typically reserve typedefs for cases where a C structure is really small and somewhat opaque - such as pte_t. wait-queue entries are neither small nor opaque, so use the more standard 'struct xxx_entry' list management code nomenclature instead. ( We don't touch external users, and we preserve the typedef as well for actual wait-queue users, to reduce unnecessary churn. ) Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-03-05 10:33:16 +01:00
smp_store_mb(wq_entry->flags, wq_entry->flags & ~WQ_FLAG_WOKEN); /* B */
return timeout;
}
EXPORT_SYMBOL(wait_woken);
sched/wait: Standardize internal naming of wait-queue entries So the various wait-queue entry variables in include/linux/wait.h and kernel/sched/wait.c are named in a colorfully inconsistent way: wait_queue_entry_t *wait wait_queue_entry_t *__wait (even in plain C code!) wait_queue_entry_t *q (!) wait_queue_entry_t *new (making anyone who knows C++ cringe) wait_queue_entry_t *old I think part of the reason for the inconsistency is the constant apparent confusion about what a wait queue 'head' versus 'entry' is. ( Some of the documentation talks about a 'wait descriptor', which is the wait-queue entry itself - further adding to the confusion. ) The most common name is 'wait', but that in itself is somewhat ambiguous as well, as it does not really make it clear whether it's a wait-queue entry or head. To improve all this name the wait-queue entry structure parameters and variables consistently and push through this naming into all the wait.h and wait.c code: struct wait_queue_entry *wq_entry The 'wq_' prefix makes it easy to grep for, and we also use the opportunity to move away from the typedef to a plain 'struct' naming: in the kernel we typically reserve typedefs for cases where a C structure is really small and somewhat opaque - such as pte_t. wait-queue entries are neither small nor opaque, so use the more standard 'struct xxx_entry' list management code nomenclature instead. ( We don't touch external users, and we preserve the typedef as well for actual wait-queue users, to reduce unnecessary churn. ) Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-03-05 10:33:16 +01:00
int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key)
{
sched/core: Use smp_mb() in wake_woken_function() wake_woken_function() synchronizes with wait_woken() as follows: [wait_woken] [wake_woken_function] entry->flags &= ~wq_flag_woken; condition = true; smp_mb(); smp_wmb(); if (condition) wq_entry->flags |= wq_flag_woken; break; This commit replaces the above smp_wmb() with an smp_mb() in order to guarantee that either wait_woken() sees the wait condition being true or the store to wq_entry->flags in woken_wake_function() follows the store in wait_woken() in the coherence order (so that the former can eventually be observed by wait_woken()). The commit also fixes a comment associated to set_current_state() in wait_woken(): the comment pairs the barrier in set_current_state() to the above smp_wmb(), while the actual pairing involves the barrier in set_current_state() and the barrier executed by the try_to_wake_up() in wake_woken_function(). Signed-off-by: Andrea Parri <andrea.parri@amarulasolutions.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: akiyks@gmail.com Cc: boqun.feng@gmail.com Cc: dhowells@redhat.com Cc: j.alglave@ucl.ac.uk Cc: linux-arch@vger.kernel.org Cc: luc.maranget@inria.fr Cc: npiggin@gmail.com Cc: parri.andrea@gmail.com Cc: stern@rowland.harvard.edu Cc: will.deacon@arm.com Link: http://lkml.kernel.org/r/20180716180605.16115-10-paulmck@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-07-16 20:06:01 +02:00
/* Pairs with the smp_store_mb() in wait_woken(). */
smp_mb(); /* C */
sched/wait: Standardize internal naming of wait-queue entries So the various wait-queue entry variables in include/linux/wait.h and kernel/sched/wait.c are named in a colorfully inconsistent way: wait_queue_entry_t *wait wait_queue_entry_t *__wait (even in plain C code!) wait_queue_entry_t *q (!) wait_queue_entry_t *new (making anyone who knows C++ cringe) wait_queue_entry_t *old I think part of the reason for the inconsistency is the constant apparent confusion about what a wait queue 'head' versus 'entry' is. ( Some of the documentation talks about a 'wait descriptor', which is the wait-queue entry itself - further adding to the confusion. ) The most common name is 'wait', but that in itself is somewhat ambiguous as well, as it does not really make it clear whether it's a wait-queue entry or head. To improve all this name the wait-queue entry structure parameters and variables consistently and push through this naming into all the wait.h and wait.c code: struct wait_queue_entry *wq_entry The 'wq_' prefix makes it easy to grep for, and we also use the opportunity to move away from the typedef to a plain 'struct' naming: in the kernel we typically reserve typedefs for cases where a C structure is really small and somewhat opaque - such as pte_t. wait-queue entries are neither small nor opaque, so use the more standard 'struct xxx_entry' list management code nomenclature instead. ( We don't touch external users, and we preserve the typedef as well for actual wait-queue users, to reduce unnecessary churn. ) Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-03-05 10:33:16 +01:00
wq_entry->flags |= WQ_FLAG_WOKEN;
sched/wait: Standardize internal naming of wait-queue entries So the various wait-queue entry variables in include/linux/wait.h and kernel/sched/wait.c are named in a colorfully inconsistent way: wait_queue_entry_t *wait wait_queue_entry_t *__wait (even in plain C code!) wait_queue_entry_t *q (!) wait_queue_entry_t *new (making anyone who knows C++ cringe) wait_queue_entry_t *old I think part of the reason for the inconsistency is the constant apparent confusion about what a wait queue 'head' versus 'entry' is. ( Some of the documentation talks about a 'wait descriptor', which is the wait-queue entry itself - further adding to the confusion. ) The most common name is 'wait', but that in itself is somewhat ambiguous as well, as it does not really make it clear whether it's a wait-queue entry or head. To improve all this name the wait-queue entry structure parameters and variables consistently and push through this naming into all the wait.h and wait.c code: struct wait_queue_entry *wq_entry The 'wq_' prefix makes it easy to grep for, and we also use the opportunity to move away from the typedef to a plain 'struct' naming: in the kernel we typically reserve typedefs for cases where a C structure is really small and somewhat opaque - such as pte_t. wait-queue entries are neither small nor opaque, so use the more standard 'struct xxx_entry' list management code nomenclature instead. ( We don't touch external users, and we preserve the typedef as well for actual wait-queue users, to reduce unnecessary churn. ) Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-03-05 10:33:16 +01:00
return default_wake_function(wq_entry, mode, sync, key);
}
EXPORT_SYMBOL(woken_wake_function);