OpenCloudOS-Kernel/kernel/locking/rwsem-spinlock.c

317 lines
6.9 KiB
C
Raw Normal View History

/* rwsem-spinlock.c: R/W semaphores: contention handling functions for
* generic spinlock implementation
*
* Copyright (c) 2001 David Howells (dhowells@redhat.com).
* - Derived partially from idea by Andrea Arcangeli <andrea@suse.de>
* - Derived also from comments by Linus
*/
#include <linux/rwsem.h>
#include <linux/sched.h>
#include <linux/export.h>
enum rwsem_waiter_type {
RWSEM_WAITING_FOR_WRITE,
RWSEM_WAITING_FOR_READ
};
struct rwsem_waiter {
struct list_head list;
struct task_struct *task;
enum rwsem_waiter_type type;
};
int rwsem_is_locked(struct rw_semaphore *sem)
{
int ret = 1;
unsigned long flags;
if (raw_spin_trylock_irqsave(&sem->wait_lock, flags)) {
ret = (sem->count != 0);
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
}
return ret;
}
EXPORT_SYMBOL(rwsem_is_locked);
/*
* initialise the semaphore
*/
void __init_rwsem(struct rw_semaphore *sem, const char *name,
struct lock_class_key *key)
{
#ifdef CONFIG_DEBUG_LOCK_ALLOC
/*
* Make sure we are not reinitializing a held semaphore:
*/
debug_check_no_locks_freed((void *)sem, sizeof(*sem));
lockdep_init_map(&sem->dep_map, name, key, 0);
#endif
sem->count = 0;
raw_spin_lock_init(&sem->wait_lock);
INIT_LIST_HEAD(&sem->wait_list);
}
EXPORT_SYMBOL(__init_rwsem);
/*
* handle the lock release when processes blocked on it that can now run
* - if we come here, then:
* - the 'active count' _reached_ zero
* - the 'waiting count' is non-zero
* - the spinlock must be held by the caller
* - woken process blocks are discarded from the list after having task zeroed
* - writers are only woken if wakewrite is non-zero
*/
static inline struct rw_semaphore *
__rwsem_do_wake(struct rw_semaphore *sem, int wakewrite)
{
struct rwsem_waiter *waiter;
struct task_struct *tsk;
int woken;
waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
if (waiter->type == RWSEM_WAITING_FOR_WRITE) {
if (wakewrite)
/* Wake up a writer. Note that we do not grant it the
* lock - it will have to acquire it when it runs. */
wake_up_process(waiter->task);
goto out;
}
/* grant an infinite number of read locks to the front of the queue */
woken = 0;
do {
struct list_head *next = waiter->list.next;
list_del(&waiter->list);
tsk = waiter->task;
/*
* Make sure we do not wakeup the next reader before
* setting the nil condition to grant the next reader;
* otherwise we could miss the wakeup on the other
* side and end up sleeping again. See the pairing
* in rwsem_down_read_failed().
*/
smp_mb();
waiter->task = NULL;
wake_up_process(tsk);
put_task_struct(tsk);
woken++;
if (next == &sem->wait_list)
break;
waiter = list_entry(next, struct rwsem_waiter, list);
} while (waiter->type != RWSEM_WAITING_FOR_WRITE);
sem->count += woken;
out:
return sem;
}
/*
* wake a single writer
*/
static inline struct rw_semaphore *
__rwsem_wake_one_writer(struct rw_semaphore *sem)
{
struct rwsem_waiter *waiter;
waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
rwsem-spinlock: Implement writer lock-stealing for better scalability We (Linux Kernel Performance project) found a regression introduced by commit: 5a505085f043 mm/rmap: Convert the struct anon_vma::mutex to an rwsem which converted all anon_vma::mutex locks rwsem write locks. The semantics are the same, but the behavioral difference is quite huge in some cases. After investigating it we found the root cause: mutexes support lock stealing while rwsems don't. Here is the link for the detailed regression report: https://lkml.org/lkml/2013/1/29/84 Ingo suggested adding write lock stealing to rwsems: "I think we should allow lock-steal between rwsem writers - that will not hurt fairness as most rwsem fairness concerns relate to reader vs. writer fairness" And here is the rwsem-spinlock version. With this patch, we got a double performance increase in one test box with following aim7 workfile: FILESIZE: 1M POOLSIZE: 10M 10 fork_test /usr/bin/time output w/o patch /usr/bin/time_output with patch -- Percent of CPU this job got: 369% Percent of CPU this job got: 537% Voluntary context switches: 640595016 Voluntary context switches: 157915561 We got a 45% increase in CPU usage and saved about 3/4 voluntary context switches. Reported-by: LKP project <lkp@linux.intel.com> Suggested-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com> Cc: Alex Shi <alex.shi@intel.com> Cc: David Howells <dhowells@redhat.com> Cc: Michel Lespinasse <walken@google.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Anton Blanchard <anton@samba.org> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: paul.gortmaker@windriver.com Link: http://lkml.kernel.org/r/1359716356-23865-1-git-send-email-yuanhan.liu@linux.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-02-01 18:59:16 +08:00
wake_up_process(waiter->task);
return sem;
}
/*
* get a read lock on the semaphore
*/
void __sched __down_read(struct rw_semaphore *sem)
{
struct rwsem_waiter waiter;
struct task_struct *tsk;
unsigned long flags;
raw_spin_lock_irqsave(&sem->wait_lock, flags);
if (sem->count >= 0 && list_empty(&sem->wait_list)) {
/* granted */
sem->count++;
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
goto out;
}
tsk = current;
set_task_state(tsk, TASK_UNINTERRUPTIBLE);
/* set up my own style of waitqueue */
waiter.task = tsk;
waiter.type = RWSEM_WAITING_FOR_READ;
get_task_struct(tsk);
list_add_tail(&waiter.list, &sem->wait_list);
/* we don't need to touch the semaphore struct anymore */
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
/* wait to be given the lock */
for (;;) {
if (!waiter.task)
break;
schedule();
set_task_state(tsk, TASK_UNINTERRUPTIBLE);
}
__set_task_state(tsk, TASK_RUNNING);
out:
;
}
/*
* trylock for reading -- returns 1 if successful, 0 if contention
*/
int __down_read_trylock(struct rw_semaphore *sem)
{
unsigned long flags;
int ret = 0;
raw_spin_lock_irqsave(&sem->wait_lock, flags);
if (sem->count >= 0 && list_empty(&sem->wait_list)) {
/* granted */
sem->count++;
ret = 1;
}
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
return ret;
}
/*
* get a write lock on the semaphore
*/
locking/rwsem: Introduce basis for down_write_killable() Introduce a generic implementation necessary for down_write_killable(). This is a trivial extension of the already existing down_write() call which can be interrupted by SIGKILL. This patch doesn't provide down_write_killable() yet because arches have to provide the necessary pieces before. rwsem_down_write_failed() which is a generic slow path for the write lock is extended to take a task state and renamed to __rwsem_down_write_failed_common(). The return value is either a valid semaphore pointer or ERR_PTR(-EINTR). rwsem_down_write_failed_killable() is exported as a new way to wait for the lock and be killable. For rwsem-spinlock implementation the current __down_write() it updated in a similar way as __rwsem_down_write_failed_common() except it doesn't need new exports just visible __down_write_killable(). Architectures which are not using the generic rwsem implementation are supposed to provide their __down_write_killable() implementation and use rwsem_down_write_failed_killable() for the slow path. Signed-off-by: Michal Hocko <mhocko@suse.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Chris Zankel <chris@zankel.net> Cc: David S. Miller <davem@davemloft.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Cc: Signed-off-by: Jason Low <jason.low2@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: linux-alpha@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-ia64@vger.kernel.org Cc: linux-s390@vger.kernel.org Cc: linux-sh@vger.kernel.org Cc: linux-xtensa@linux-xtensa.org Cc: sparclinux@vger.kernel.org Link: http://lkml.kernel.org/r/1460041951-22347-7-git-send-email-mhocko@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-04-07 23:12:26 +08:00
int __sched __down_write_common(struct rw_semaphore *sem, int state)
{
struct rwsem_waiter waiter;
struct task_struct *tsk;
unsigned long flags;
locking/rwsem: Introduce basis for down_write_killable() Introduce a generic implementation necessary for down_write_killable(). This is a trivial extension of the already existing down_write() call which can be interrupted by SIGKILL. This patch doesn't provide down_write_killable() yet because arches have to provide the necessary pieces before. rwsem_down_write_failed() which is a generic slow path for the write lock is extended to take a task state and renamed to __rwsem_down_write_failed_common(). The return value is either a valid semaphore pointer or ERR_PTR(-EINTR). rwsem_down_write_failed_killable() is exported as a new way to wait for the lock and be killable. For rwsem-spinlock implementation the current __down_write() it updated in a similar way as __rwsem_down_write_failed_common() except it doesn't need new exports just visible __down_write_killable(). Architectures which are not using the generic rwsem implementation are supposed to provide their __down_write_killable() implementation and use rwsem_down_write_failed_killable() for the slow path. Signed-off-by: Michal Hocko <mhocko@suse.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Chris Zankel <chris@zankel.net> Cc: David S. Miller <davem@davemloft.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Cc: Signed-off-by: Jason Low <jason.low2@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: linux-alpha@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-ia64@vger.kernel.org Cc: linux-s390@vger.kernel.org Cc: linux-sh@vger.kernel.org Cc: linux-xtensa@linux-xtensa.org Cc: sparclinux@vger.kernel.org Link: http://lkml.kernel.org/r/1460041951-22347-7-git-send-email-mhocko@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-04-07 23:12:26 +08:00
int ret = 0;
raw_spin_lock_irqsave(&sem->wait_lock, flags);
/* set up my own style of waitqueue */
rwsem-spinlock: Implement writer lock-stealing for better scalability We (Linux Kernel Performance project) found a regression introduced by commit: 5a505085f043 mm/rmap: Convert the struct anon_vma::mutex to an rwsem which converted all anon_vma::mutex locks rwsem write locks. The semantics are the same, but the behavioral difference is quite huge in some cases. After investigating it we found the root cause: mutexes support lock stealing while rwsems don't. Here is the link for the detailed regression report: https://lkml.org/lkml/2013/1/29/84 Ingo suggested adding write lock stealing to rwsems: "I think we should allow lock-steal between rwsem writers - that will not hurt fairness as most rwsem fairness concerns relate to reader vs. writer fairness" And here is the rwsem-spinlock version. With this patch, we got a double performance increase in one test box with following aim7 workfile: FILESIZE: 1M POOLSIZE: 10M 10 fork_test /usr/bin/time output w/o patch /usr/bin/time_output with patch -- Percent of CPU this job got: 369% Percent of CPU this job got: 537% Voluntary context switches: 640595016 Voluntary context switches: 157915561 We got a 45% increase in CPU usage and saved about 3/4 voluntary context switches. Reported-by: LKP project <lkp@linux.intel.com> Suggested-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com> Cc: Alex Shi <alex.shi@intel.com> Cc: David Howells <dhowells@redhat.com> Cc: Michel Lespinasse <walken@google.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Anton Blanchard <anton@samba.org> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: paul.gortmaker@windriver.com Link: http://lkml.kernel.org/r/1359716356-23865-1-git-send-email-yuanhan.liu@linux.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-02-01 18:59:16 +08:00
tsk = current;
waiter.task = tsk;
waiter.type = RWSEM_WAITING_FOR_WRITE;
list_add_tail(&waiter.list, &sem->wait_list);
rwsem-spinlock: Implement writer lock-stealing for better scalability We (Linux Kernel Performance project) found a regression introduced by commit: 5a505085f043 mm/rmap: Convert the struct anon_vma::mutex to an rwsem which converted all anon_vma::mutex locks rwsem write locks. The semantics are the same, but the behavioral difference is quite huge in some cases. After investigating it we found the root cause: mutexes support lock stealing while rwsems don't. Here is the link for the detailed regression report: https://lkml.org/lkml/2013/1/29/84 Ingo suggested adding write lock stealing to rwsems: "I think we should allow lock-steal between rwsem writers - that will not hurt fairness as most rwsem fairness concerns relate to reader vs. writer fairness" And here is the rwsem-spinlock version. With this patch, we got a double performance increase in one test box with following aim7 workfile: FILESIZE: 1M POOLSIZE: 10M 10 fork_test /usr/bin/time output w/o patch /usr/bin/time_output with patch -- Percent of CPU this job got: 369% Percent of CPU this job got: 537% Voluntary context switches: 640595016 Voluntary context switches: 157915561 We got a 45% increase in CPU usage and saved about 3/4 voluntary context switches. Reported-by: LKP project <lkp@linux.intel.com> Suggested-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com> Cc: Alex Shi <alex.shi@intel.com> Cc: David Howells <dhowells@redhat.com> Cc: Michel Lespinasse <walken@google.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Anton Blanchard <anton@samba.org> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: paul.gortmaker@windriver.com Link: http://lkml.kernel.org/r/1359716356-23865-1-git-send-email-yuanhan.liu@linux.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-02-01 18:59:16 +08:00
/* wait for someone to release the lock */
for (;;) {
rwsem-spinlock: Implement writer lock-stealing for better scalability We (Linux Kernel Performance project) found a regression introduced by commit: 5a505085f043 mm/rmap: Convert the struct anon_vma::mutex to an rwsem which converted all anon_vma::mutex locks rwsem write locks. The semantics are the same, but the behavioral difference is quite huge in some cases. After investigating it we found the root cause: mutexes support lock stealing while rwsems don't. Here is the link for the detailed regression report: https://lkml.org/lkml/2013/1/29/84 Ingo suggested adding write lock stealing to rwsems: "I think we should allow lock-steal between rwsem writers - that will not hurt fairness as most rwsem fairness concerns relate to reader vs. writer fairness" And here is the rwsem-spinlock version. With this patch, we got a double performance increase in one test box with following aim7 workfile: FILESIZE: 1M POOLSIZE: 10M 10 fork_test /usr/bin/time output w/o patch /usr/bin/time_output with patch -- Percent of CPU this job got: 369% Percent of CPU this job got: 537% Voluntary context switches: 640595016 Voluntary context switches: 157915561 We got a 45% increase in CPU usage and saved about 3/4 voluntary context switches. Reported-by: LKP project <lkp@linux.intel.com> Suggested-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com> Cc: Alex Shi <alex.shi@intel.com> Cc: David Howells <dhowells@redhat.com> Cc: Michel Lespinasse <walken@google.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Anton Blanchard <anton@samba.org> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: paul.gortmaker@windriver.com Link: http://lkml.kernel.org/r/1359716356-23865-1-git-send-email-yuanhan.liu@linux.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-02-01 18:59:16 +08:00
/*
* That is the key to support write lock stealing: allows the
* task already on CPU to get the lock soon rather than put
* itself into sleep and waiting for system woke it or someone
* else in the head of the wait list up.
*/
if (sem->count == 0)
break;
locking/rwsem: Introduce basis for down_write_killable() Introduce a generic implementation necessary for down_write_killable(). This is a trivial extension of the already existing down_write() call which can be interrupted by SIGKILL. This patch doesn't provide down_write_killable() yet because arches have to provide the necessary pieces before. rwsem_down_write_failed() which is a generic slow path for the write lock is extended to take a task state and renamed to __rwsem_down_write_failed_common(). The return value is either a valid semaphore pointer or ERR_PTR(-EINTR). rwsem_down_write_failed_killable() is exported as a new way to wait for the lock and be killable. For rwsem-spinlock implementation the current __down_write() it updated in a similar way as __rwsem_down_write_failed_common() except it doesn't need new exports just visible __down_write_killable(). Architectures which are not using the generic rwsem implementation are supposed to provide their __down_write_killable() implementation and use rwsem_down_write_failed_killable() for the slow path. Signed-off-by: Michal Hocko <mhocko@suse.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Chris Zankel <chris@zankel.net> Cc: David S. Miller <davem@davemloft.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Cc: Signed-off-by: Jason Low <jason.low2@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: linux-alpha@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-ia64@vger.kernel.org Cc: linux-s390@vger.kernel.org Cc: linux-sh@vger.kernel.org Cc: linux-xtensa@linux-xtensa.org Cc: sparclinux@vger.kernel.org Link: http://lkml.kernel.org/r/1460041951-22347-7-git-send-email-mhocko@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-04-07 23:12:26 +08:00
if (signal_pending_state(state, current)) {
ret = -EINTR;
goto out;
}
set_task_state(tsk, state);
rwsem-spinlock: Implement writer lock-stealing for better scalability We (Linux Kernel Performance project) found a regression introduced by commit: 5a505085f043 mm/rmap: Convert the struct anon_vma::mutex to an rwsem which converted all anon_vma::mutex locks rwsem write locks. The semantics are the same, but the behavioral difference is quite huge in some cases. After investigating it we found the root cause: mutexes support lock stealing while rwsems don't. Here is the link for the detailed regression report: https://lkml.org/lkml/2013/1/29/84 Ingo suggested adding write lock stealing to rwsems: "I think we should allow lock-steal between rwsem writers - that will not hurt fairness as most rwsem fairness concerns relate to reader vs. writer fairness" And here is the rwsem-spinlock version. With this patch, we got a double performance increase in one test box with following aim7 workfile: FILESIZE: 1M POOLSIZE: 10M 10 fork_test /usr/bin/time output w/o patch /usr/bin/time_output with patch -- Percent of CPU this job got: 369% Percent of CPU this job got: 537% Voluntary context switches: 640595016 Voluntary context switches: 157915561 We got a 45% increase in CPU usage and saved about 3/4 voluntary context switches. Reported-by: LKP project <lkp@linux.intel.com> Suggested-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com> Cc: Alex Shi <alex.shi@intel.com> Cc: David Howells <dhowells@redhat.com> Cc: Michel Lespinasse <walken@google.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Anton Blanchard <anton@samba.org> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: paul.gortmaker@windriver.com Link: http://lkml.kernel.org/r/1359716356-23865-1-git-send-email-yuanhan.liu@linux.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-02-01 18:59:16 +08:00
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
schedule();
raw_spin_lock_irqsave(&sem->wait_lock, flags);
}
rwsem-spinlock: Implement writer lock-stealing for better scalability We (Linux Kernel Performance project) found a regression introduced by commit: 5a505085f043 mm/rmap: Convert the struct anon_vma::mutex to an rwsem which converted all anon_vma::mutex locks rwsem write locks. The semantics are the same, but the behavioral difference is quite huge in some cases. After investigating it we found the root cause: mutexes support lock stealing while rwsems don't. Here is the link for the detailed regression report: https://lkml.org/lkml/2013/1/29/84 Ingo suggested adding write lock stealing to rwsems: "I think we should allow lock-steal between rwsem writers - that will not hurt fairness as most rwsem fairness concerns relate to reader vs. writer fairness" And here is the rwsem-spinlock version. With this patch, we got a double performance increase in one test box with following aim7 workfile: FILESIZE: 1M POOLSIZE: 10M 10 fork_test /usr/bin/time output w/o patch /usr/bin/time_output with patch -- Percent of CPU this job got: 369% Percent of CPU this job got: 537% Voluntary context switches: 640595016 Voluntary context switches: 157915561 We got a 45% increase in CPU usage and saved about 3/4 voluntary context switches. Reported-by: LKP project <lkp@linux.intel.com> Suggested-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com> Cc: Alex Shi <alex.shi@intel.com> Cc: David Howells <dhowells@redhat.com> Cc: Michel Lespinasse <walken@google.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Anton Blanchard <anton@samba.org> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: paul.gortmaker@windriver.com Link: http://lkml.kernel.org/r/1359716356-23865-1-git-send-email-yuanhan.liu@linux.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-02-01 18:59:16 +08:00
/* got the lock */
sem->count = -1;
locking/rwsem: Introduce basis for down_write_killable() Introduce a generic implementation necessary for down_write_killable(). This is a trivial extension of the already existing down_write() call which can be interrupted by SIGKILL. This patch doesn't provide down_write_killable() yet because arches have to provide the necessary pieces before. rwsem_down_write_failed() which is a generic slow path for the write lock is extended to take a task state and renamed to __rwsem_down_write_failed_common(). The return value is either a valid semaphore pointer or ERR_PTR(-EINTR). rwsem_down_write_failed_killable() is exported as a new way to wait for the lock and be killable. For rwsem-spinlock implementation the current __down_write() it updated in a similar way as __rwsem_down_write_failed_common() except it doesn't need new exports just visible __down_write_killable(). Architectures which are not using the generic rwsem implementation are supposed to provide their __down_write_killable() implementation and use rwsem_down_write_failed_killable() for the slow path. Signed-off-by: Michal Hocko <mhocko@suse.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Chris Zankel <chris@zankel.net> Cc: David S. Miller <davem@davemloft.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Cc: Signed-off-by: Jason Low <jason.low2@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: linux-alpha@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-ia64@vger.kernel.org Cc: linux-s390@vger.kernel.org Cc: linux-sh@vger.kernel.org Cc: linux-xtensa@linux-xtensa.org Cc: sparclinux@vger.kernel.org Link: http://lkml.kernel.org/r/1460041951-22347-7-git-send-email-mhocko@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-04-07 23:12:26 +08:00
out:
rwsem-spinlock: Implement writer lock-stealing for better scalability We (Linux Kernel Performance project) found a regression introduced by commit: 5a505085f043 mm/rmap: Convert the struct anon_vma::mutex to an rwsem which converted all anon_vma::mutex locks rwsem write locks. The semantics are the same, but the behavioral difference is quite huge in some cases. After investigating it we found the root cause: mutexes support lock stealing while rwsems don't. Here is the link for the detailed regression report: https://lkml.org/lkml/2013/1/29/84 Ingo suggested adding write lock stealing to rwsems: "I think we should allow lock-steal between rwsem writers - that will not hurt fairness as most rwsem fairness concerns relate to reader vs. writer fairness" And here is the rwsem-spinlock version. With this patch, we got a double performance increase in one test box with following aim7 workfile: FILESIZE: 1M POOLSIZE: 10M 10 fork_test /usr/bin/time output w/o patch /usr/bin/time_output with patch -- Percent of CPU this job got: 369% Percent of CPU this job got: 537% Voluntary context switches: 640595016 Voluntary context switches: 157915561 We got a 45% increase in CPU usage and saved about 3/4 voluntary context switches. Reported-by: LKP project <lkp@linux.intel.com> Suggested-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com> Cc: Alex Shi <alex.shi@intel.com> Cc: David Howells <dhowells@redhat.com> Cc: Michel Lespinasse <walken@google.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Anton Blanchard <anton@samba.org> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: paul.gortmaker@windriver.com Link: http://lkml.kernel.org/r/1359716356-23865-1-git-send-email-yuanhan.liu@linux.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-02-01 18:59:16 +08:00
list_del(&waiter.list);
rwsem-spinlock: Implement writer lock-stealing for better scalability We (Linux Kernel Performance project) found a regression introduced by commit: 5a505085f043 mm/rmap: Convert the struct anon_vma::mutex to an rwsem which converted all anon_vma::mutex locks rwsem write locks. The semantics are the same, but the behavioral difference is quite huge in some cases. After investigating it we found the root cause: mutexes support lock stealing while rwsems don't. Here is the link for the detailed regression report: https://lkml.org/lkml/2013/1/29/84 Ingo suggested adding write lock stealing to rwsems: "I think we should allow lock-steal between rwsem writers - that will not hurt fairness as most rwsem fairness concerns relate to reader vs. writer fairness" And here is the rwsem-spinlock version. With this patch, we got a double performance increase in one test box with following aim7 workfile: FILESIZE: 1M POOLSIZE: 10M 10 fork_test /usr/bin/time output w/o patch /usr/bin/time_output with patch -- Percent of CPU this job got: 369% Percent of CPU this job got: 537% Voluntary context switches: 640595016 Voluntary context switches: 157915561 We got a 45% increase in CPU usage and saved about 3/4 voluntary context switches. Reported-by: LKP project <lkp@linux.intel.com> Suggested-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com> Cc: Alex Shi <alex.shi@intel.com> Cc: David Howells <dhowells@redhat.com> Cc: Michel Lespinasse <walken@google.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Anton Blanchard <anton@samba.org> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: paul.gortmaker@windriver.com Link: http://lkml.kernel.org/r/1359716356-23865-1-git-send-email-yuanhan.liu@linux.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-02-01 18:59:16 +08:00
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
locking/rwsem: Introduce basis for down_write_killable() Introduce a generic implementation necessary for down_write_killable(). This is a trivial extension of the already existing down_write() call which can be interrupted by SIGKILL. This patch doesn't provide down_write_killable() yet because arches have to provide the necessary pieces before. rwsem_down_write_failed() which is a generic slow path for the write lock is extended to take a task state and renamed to __rwsem_down_write_failed_common(). The return value is either a valid semaphore pointer or ERR_PTR(-EINTR). rwsem_down_write_failed_killable() is exported as a new way to wait for the lock and be killable. For rwsem-spinlock implementation the current __down_write() it updated in a similar way as __rwsem_down_write_failed_common() except it doesn't need new exports just visible __down_write_killable(). Architectures which are not using the generic rwsem implementation are supposed to provide their __down_write_killable() implementation and use rwsem_down_write_failed_killable() for the slow path. Signed-off-by: Michal Hocko <mhocko@suse.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Chris Zankel <chris@zankel.net> Cc: David S. Miller <davem@davemloft.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Cc: Signed-off-by: Jason Low <jason.low2@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: linux-alpha@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-ia64@vger.kernel.org Cc: linux-s390@vger.kernel.org Cc: linux-sh@vger.kernel.org Cc: linux-xtensa@linux-xtensa.org Cc: sparclinux@vger.kernel.org Link: http://lkml.kernel.org/r/1460041951-22347-7-git-send-email-mhocko@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-04-07 23:12:26 +08:00
return ret;
}
void __sched __down_write(struct rw_semaphore *sem)
{
__down_write_common(sem, TASK_UNINTERRUPTIBLE);
}
int __sched __down_write_killable(struct rw_semaphore *sem)
{
return __down_write_common(sem, TASK_KILLABLE);
}
/*
* trylock for writing -- returns 1 if successful, 0 if contention
*/
int __down_write_trylock(struct rw_semaphore *sem)
{
unsigned long flags;
int ret = 0;
raw_spin_lock_irqsave(&sem->wait_lock, flags);
if (sem->count == 0) {
rwsem-spinlock: Implement writer lock-stealing for better scalability We (Linux Kernel Performance project) found a regression introduced by commit: 5a505085f043 mm/rmap: Convert the struct anon_vma::mutex to an rwsem which converted all anon_vma::mutex locks rwsem write locks. The semantics are the same, but the behavioral difference is quite huge in some cases. After investigating it we found the root cause: mutexes support lock stealing while rwsems don't. Here is the link for the detailed regression report: https://lkml.org/lkml/2013/1/29/84 Ingo suggested adding write lock stealing to rwsems: "I think we should allow lock-steal between rwsem writers - that will not hurt fairness as most rwsem fairness concerns relate to reader vs. writer fairness" And here is the rwsem-spinlock version. With this patch, we got a double performance increase in one test box with following aim7 workfile: FILESIZE: 1M POOLSIZE: 10M 10 fork_test /usr/bin/time output w/o patch /usr/bin/time_output with patch -- Percent of CPU this job got: 369% Percent of CPU this job got: 537% Voluntary context switches: 640595016 Voluntary context switches: 157915561 We got a 45% increase in CPU usage and saved about 3/4 voluntary context switches. Reported-by: LKP project <lkp@linux.intel.com> Suggested-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com> Cc: Alex Shi <alex.shi@intel.com> Cc: David Howells <dhowells@redhat.com> Cc: Michel Lespinasse <walken@google.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Anton Blanchard <anton@samba.org> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: paul.gortmaker@windriver.com Link: http://lkml.kernel.org/r/1359716356-23865-1-git-send-email-yuanhan.liu@linux.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-02-01 18:59:16 +08:00
/* got the lock */
sem->count = -1;
ret = 1;
}
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
return ret;
}
/*
* release a read lock on the semaphore
*/
void __up_read(struct rw_semaphore *sem)
{
unsigned long flags;
raw_spin_lock_irqsave(&sem->wait_lock, flags);
if (--sem->count == 0 && !list_empty(&sem->wait_list))
sem = __rwsem_wake_one_writer(sem);
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
}
/*
* release a write lock on the semaphore
*/
void __up_write(struct rw_semaphore *sem)
{
unsigned long flags;
raw_spin_lock_irqsave(&sem->wait_lock, flags);
sem->count = 0;
if (!list_empty(&sem->wait_list))
sem = __rwsem_do_wake(sem, 1);
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
}
/*
* downgrade a write lock into a read lock
* - just wake up any readers at the front of the queue
*/
void __downgrade_write(struct rw_semaphore *sem)
{
unsigned long flags;
raw_spin_lock_irqsave(&sem->wait_lock, flags);
sem->count = 1;
if (!list_empty(&sem->wait_list))
sem = __rwsem_do_wake(sem, 0);
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
}