mirror of
https://github.com/edk2-porting/linux-next.git
synced 2024-12-26 06:04:14 +08:00
d269a8b8c5
This patch effectively replaces the tsk pointer dereference (which is obviously == current), to directly use get_current() macro. This is to make the removal of setting foreign task states smoother and painfully obvious. Performance win on some archs such as x86-64 and ppc64. On a microbenchmark that calls set_task_state() vs set_current_state() and an inode rwsem pounding benchmark doing unlink: == 1. x86-64 == Avg runtime set_task_state(): 601 msecs Avg runtime set_current_state(): 552 msecs vanilla dirty Hmean unlink1-processes-2 36089.26 ( 0.00%) 38977.33 ( 8.00%) Hmean unlink1-processes-5 28555.01 ( 0.00%) 29832.55 ( 4.28%) Hmean unlink1-processes-8 37323.75 ( 0.00%) 44974.57 ( 20.50%) Hmean unlink1-processes-12 43571.88 ( 0.00%) 44283.01 ( 1.63%) Hmean unlink1-processes-21 34431.52 ( 0.00%) 38284.45 ( 11.19%) Hmean unlink1-processes-30 34813.26 ( 0.00%) 37975.17 ( 9.08%) Hmean unlink1-processes-48 37048.90 ( 0.00%) 39862.78 ( 7.59%) Hmean unlink1-processes-79 35630.01 ( 0.00%) 36855.30 ( 3.44%) Hmean unlink1-processes-110 36115.85 ( 0.00%) 39843.91 ( 10.32%) Hmean unlink1-processes-141 32546.96 ( 0.00%) 35418.52 ( 8.82%) Hmean unlink1-processes-172 34674.79 ( 0.00%) 36899.21 ( 6.42%) Hmean unlink1-processes-203 37303.11 ( 0.00%) 36393.04 ( -2.44%) Hmean unlink1-processes-224 35712.13 ( 0.00%) 36685.96 ( 2.73%) == 2. ppc64le == Avg runtime set_task_state(): 938 msecs Avg runtime set_current_state: 940 msecs vanilla dirty Hmean unlink1-processes-2 19269.19 ( 0.00%) 30704.50 ( 59.35%) Hmean unlink1-processes-5 20106.15 ( 0.00%) 21804.15 ( 8.45%) Hmean unlink1-processes-8 17496.97 ( 0.00%) 17243.28 ( -1.45%) Hmean unlink1-processes-12 14224.15 ( 0.00%) 17240.21 ( 21.20%) Hmean unlink1-processes-21 14155.66 ( 0.00%) 15681.23 ( 10.78%) Hmean unlink1-processes-30 14450.70 ( 0.00%) 15995.83 ( 10.69%) Hmean unlink1-processes-48 16945.57 ( 0.00%) 16370.42 ( -3.39%) Hmean unlink1-processes-79 15788.39 ( 0.00%) 14639.27 ( -7.28%) Hmean unlink1-processes-110 14268.48 ( 0.00%) 14377.40 ( 0.76%) Hmean unlink1-processes-141 14023.65 ( 0.00%) 16271.69 ( 16.03%) Hmean unlink1-processes-172 13417.62 ( 0.00%) 16067.55 ( 19.75%) Hmean unlink1-processes-203 15293.08 ( 0.00%) 15440.40 ( 0.96%) Hmean unlink1-processes-234 13719.32 ( 0.00%) 16190.74 ( 18.01%) Hmean unlink1-processes-265 16400.97 ( 0.00%) 16115.22 ( -1.74%) Hmean unlink1-processes-296 14388.60 ( 0.00%) 16216.13 ( 12.70%) Hmean unlink1-processes-320 15771.85 ( 0.00%) 15905.96 ( 0.85%) Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: dave@stgolabs.net Cc: mark.rutland@arm.com Link: http://lkml.kernel.org/r/1483479794-14013-4-git-send-email-dave@stgolabs.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
313 lines
6.9 KiB
C
313 lines
6.9 KiB
C
/* 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);
|
|
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;
|
|
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;
|
|
}
|
|
|
|
set_task_state(current, TASK_UNINTERRUPTIBLE);
|
|
|
|
/* set up my own style of waitqueue */
|
|
waiter.task = current;
|
|
waiter.type = RWSEM_WAITING_FOR_READ;
|
|
get_task_struct(current);
|
|
|
|
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(current, TASK_UNINTERRUPTIBLE);
|
|
}
|
|
|
|
__set_task_state(current, 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
|
|
*/
|
|
int __sched __down_write_common(struct rw_semaphore *sem, int state)
|
|
{
|
|
struct rwsem_waiter waiter;
|
|
unsigned long flags;
|
|
int ret = 0;
|
|
|
|
raw_spin_lock_irqsave(&sem->wait_lock, flags);
|
|
|
|
/* set up my own style of waitqueue */
|
|
waiter.task = current;
|
|
waiter.type = RWSEM_WAITING_FOR_WRITE;
|
|
list_add_tail(&waiter.list, &sem->wait_list);
|
|
|
|
/* wait for someone to release the lock */
|
|
for (;;) {
|
|
/*
|
|
* 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;
|
|
if (signal_pending_state(state, current)) {
|
|
ret = -EINTR;
|
|
goto out;
|
|
}
|
|
set_task_state(current, state);
|
|
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
|
|
schedule();
|
|
raw_spin_lock_irqsave(&sem->wait_lock, flags);
|
|
}
|
|
/* got the lock */
|
|
sem->count = -1;
|
|
out:
|
|
list_del(&waiter.list);
|
|
|
|
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
|
|
|
|
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) {
|
|
/* 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);
|
|
}
|
|
|