kernel/locking: Compute 'current' directly
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>
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 9b34961..4c7d043 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -622,7 +622,6 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
struct lockdep_map *nest_lock, unsigned long ip,
struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx)
{
- struct task_struct *task = current;
struct mutex_waiter waiter;
unsigned long flags;
bool first = false;
@@ -656,18 +655,18 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
goto skip_wait;
debug_mutex_lock_common(lock, &waiter);
- debug_mutex_add_waiter(lock, &waiter, task);
+ debug_mutex_add_waiter(lock, &waiter, current);
/* add waiting tasks to the end of the waitqueue (FIFO): */
list_add_tail(&waiter.list, &lock->wait_list);
- waiter.task = task;
+ waiter.task = current;
if (__mutex_waiter_is_first(lock, &waiter))
__mutex_set_flag(lock, MUTEX_FLAG_WAITERS);
lock_contended(&lock->dep_map, ip);
- set_task_state(task, state);
+ set_task_state(current, state);
for (;;) {
/*
* Once we hold wait_lock, we're serialized against
@@ -683,7 +682,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
* wait_lock. This ensures the lock cancellation is ordered
* against mutex_unlock() and wake-ups do not go missing.
*/
- if (unlikely(signal_pending_state(state, task))) {
+ if (unlikely(signal_pending_state(state, current))) {
ret = -EINTR;
goto err;
}
@@ -702,7 +701,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
__mutex_set_flag(lock, MUTEX_FLAG_HANDOFF);
}
- set_task_state(task, state);
+ set_task_state(current, state);
/*
* Here we order against unlock; we must either see it change
* state back to RUNNING and fall through the next schedule(),
@@ -716,9 +715,9 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
}
spin_lock_mutex(&lock->wait_lock, flags);
acquired:
- __set_task_state(task, TASK_RUNNING);
+ __set_task_state(current, TASK_RUNNING);
- mutex_remove_waiter(lock, &waiter, task);
+ mutex_remove_waiter(lock, &waiter, current);
if (likely(list_empty(&lock->wait_list)))
__mutex_clear_flag(lock, MUTEX_FLAGS);
@@ -736,8 +735,8 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
return 0;
err:
- __set_task_state(task, TASK_RUNNING);
- mutex_remove_waiter(lock, &waiter, task);
+ __set_task_state(current, TASK_RUNNING);
+ mutex_remove_waiter(lock, &waiter, current);
spin_unlock_mutex(&lock->wait_lock, flags);
debug_mutex_free_waiter(&waiter);
mutex_release(&lock->dep_map, 1, ip);
