diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2014-01-20 10:42:08 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2014-01-20 10:42:08 -0800 |
commit | a0fa1dd3cdbccec9597fe53b6177a9aa6e20f2f8 (patch) | |
tree | b249854573815eedf377e554f0ea516f86411841 /kernel/locking | |
parent | 9326657abe1a83ed4b4f396b923ca1217fd50cba (diff) | |
parent | eaad45132c564ce377e6dce05e78e08e456d5315 (diff) | |
download | linux-a0fa1dd3cdbccec9597fe53b6177a9aa6e20f2f8.tar.gz linux-a0fa1dd3cdbccec9597fe53b6177a9aa6e20f2f8.tar.bz2 linux-a0fa1dd3cdbccec9597fe53b6177a9aa6e20f2f8.zip |
Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler changes from Ingo Molnar:
- Add the initial implementation of SCHED_DEADLINE support: a real-time
scheduling policy where tasks that meet their deadlines and
periodically execute their instances in less than their runtime quota
see real-time scheduling and won't miss any of their deadlines.
Tasks that go over their quota get delayed (Available to privileged
users for now)
- Clean up and fix preempt_enable_no_resched() abuse all around the
tree
- Do sched_clock() performance optimizations on x86 and elsewhere
- Fix and improve auto-NUMA balancing
- Fix and clean up the idle loop
- Apply various cleanups and fixes
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (60 commits)
sched: Fix __sched_setscheduler() nice test
sched: Move SCHED_RESET_ON_FORK into attr::sched_flags
sched: Fix up attr::sched_priority warning
sched: Fix up scheduler syscall LTP fails
sched: Preserve the nice level over sched_setscheduler() and sched_setparam() calls
sched/core: Fix htmldocs warnings
sched/deadline: No need to check p if dl_se is valid
sched/deadline: Remove unused variables
sched/deadline: Fix sparse static warnings
m68k: Fix build warning in mac_via.h
sched, thermal: Clean up preempt_enable_no_resched() abuse
sched, net: Fixup busy_loop_us_clock()
sched, net: Clean up preempt_enable_no_resched() abuse
sched/preempt: Fix up missed PREEMPT_NEED_RESCHED folding
sched/preempt, locking: Rework local_bh_{dis,en}able()
sched/clock, x86: Avoid a runtime condition in native_sched_clock()
sched/clock: Fix up clear_sched_clock_stable()
sched/clock, x86: Use a static_key for sched_clock_stable
sched/clock: Remove local_irq_disable() from the clocks
sched/clock, x86: Rewrite cyc2ns() to avoid the need to disable IRQs
...
Diffstat (limited to 'kernel/locking')
-rw-r--r-- | kernel/locking/rtmutex-debug.c | 8 | ||||
-rw-r--r-- | kernel/locking/rtmutex.c | 166 | ||||
-rw-r--r-- | kernel/locking/rtmutex_common.h | 23 |
3 files changed, 149 insertions, 48 deletions
diff --git a/kernel/locking/rtmutex-debug.c b/kernel/locking/rtmutex-debug.c index 13b243a323fa..49b2ed3dced8 100644 --- a/kernel/locking/rtmutex-debug.c +++ b/kernel/locking/rtmutex-debug.c @@ -24,7 +24,7 @@ #include <linux/kallsyms.h> #include <linux/syscalls.h> #include <linux/interrupt.h> -#include <linux/plist.h> +#include <linux/rbtree.h> #include <linux/fs.h> #include <linux/debug_locks.h> @@ -57,7 +57,7 @@ static void printk_lock(struct rt_mutex *lock, int print_owner) void rt_mutex_debug_task_free(struct task_struct *task) { - DEBUG_LOCKS_WARN_ON(!plist_head_empty(&task->pi_waiters)); + DEBUG_LOCKS_WARN_ON(!RB_EMPTY_ROOT(&task->pi_waiters)); DEBUG_LOCKS_WARN_ON(task->pi_blocked_on); } @@ -154,16 +154,12 @@ void debug_rt_mutex_proxy_unlock(struct rt_mutex *lock) void debug_rt_mutex_init_waiter(struct rt_mutex_waiter *waiter) { memset(waiter, 0x11, sizeof(*waiter)); - plist_node_init(&waiter->list_entry, MAX_PRIO); - plist_node_init(&waiter->pi_list_entry, MAX_PRIO); waiter->deadlock_task_pid = NULL; } void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter) { put_pid(waiter->deadlock_task_pid); - DEBUG_LOCKS_WARN_ON(!plist_node_empty(&waiter->list_entry)); - DEBUG_LOCKS_WARN_ON(!plist_node_empty(&waiter->pi_list_entry)); memset(waiter, 0x22, sizeof(*waiter)); } diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 0dd6aec1cb6a..2e960a2bab81 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -14,6 +14,7 @@ #include <linux/export.h> #include <linux/sched.h> #include <linux/sched/rt.h> +#include <linux/sched/deadline.h> #include <linux/timer.h> #include "rtmutex_common.h" @@ -91,10 +92,107 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock) } #endif +static inline int +rt_mutex_waiter_less(struct rt_mutex_waiter *left, + struct rt_mutex_waiter *right) +{ + if (left->prio < right->prio) + return 1; + + /* + * If both waiters have dl_prio(), we check the deadlines of the + * associated tasks. + * If left waiter has a dl_prio(), and we didn't return 1 above, + * then right waiter has a dl_prio() too. + */ + if (dl_prio(left->prio)) + return (left->task->dl.deadline < right->task->dl.deadline); + + return 0; +} + +static void +rt_mutex_enqueue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter) +{ + struct rb_node **link = &lock->waiters.rb_node; + struct rb_node *parent = NULL; + struct rt_mutex_waiter *entry; + int leftmost = 1; + + while (*link) { + parent = *link; + entry = rb_entry(parent, struct rt_mutex_waiter, tree_entry); + if (rt_mutex_waiter_less(waiter, entry)) { + link = &parent->rb_left; + } else { + link = &parent->rb_right; + leftmost = 0; + } + } + + if (leftmost) + lock->waiters_leftmost = &waiter->tree_entry; + + rb_link_node(&waiter->tree_entry, parent, link); + rb_insert_color(&waiter->tree_entry, &lock->waiters); +} + +static void +rt_mutex_dequeue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter) +{ + if (RB_EMPTY_NODE(&waiter->tree_entry)) + return; + + if (lock->waiters_leftmost == &waiter->tree_entry) + lock->waiters_leftmost = rb_next(&waiter->tree_entry); + + rb_erase(&waiter->tree_entry, &lock->waiters); + RB_CLEAR_NODE(&waiter->tree_entry); +} + +static void +rt_mutex_enqueue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter) +{ + struct rb_node **link = &task->pi_waiters.rb_node; + struct rb_node *parent = NULL; + struct rt_mutex_waiter *entry; + int leftmost = 1; + + while (*link) { + parent = *link; + entry = rb_entry(parent, struct rt_mutex_waiter, pi_tree_entry); + if (rt_mutex_waiter_less(waiter, entry)) { + link = &parent->rb_left; + } else { + link = &parent->rb_right; + leftmost = 0; + } + } + + if (leftmost) + task->pi_waiters_leftmost = &waiter->pi_tree_entry; + + rb_link_node(&waiter->pi_tree_entry, parent, link); + rb_insert_color(&waiter->pi_tree_entry, &task->pi_waiters); +} + +static void +rt_mutex_dequeue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter) +{ + if (RB_EMPTY_NODE(&waiter->pi_tree_entry)) + return; + + if (task->pi_waiters_leftmost == &waiter->pi_tree_entry) + task->pi_waiters_leftmost = rb_next(&waiter->pi_tree_entry); + + rb_erase(&waiter->pi_tree_entry, &task->pi_waiters); + RB_CLEAR_NODE(&waiter->pi_tree_entry); +} + /* - * Calculate task priority from the waiter list priority + * Calculate task priority from the waiter tree priority * - * Return task->normal_prio when the waiter list is empty or when + * Return task->normal_prio when the waiter tree is empty or when * the waiter is not allowed to do priority boosting */ int rt_mutex_getprio(struct task_struct *task) @@ -102,10 +200,18 @@ int rt_mutex_getprio(struct task_struct *task) if (likely(!task_has_pi_waiters(task))) return task->normal_prio; - return min(task_top_pi_waiter(task)->pi_list_entry.prio, + return min(task_top_pi_waiter(task)->prio, task->normal_prio); } +struct task_struct *rt_mutex_get_top_task(struct task_struct *task) +{ + if (likely(!task_has_pi_waiters(task))) + return NULL; + + return task_top_pi_waiter(task)->task; +} + /* * Adjust the priority of a task, after its pi_waiters got modified. * @@ -115,7 +221,7 @@ static void __rt_mutex_adjust_prio(struct task_struct *task) { int prio = rt_mutex_getprio(task); - if (task->prio != prio) + if (task->prio != prio || dl_prio(prio)) rt_mutex_setprio(task, prio); } @@ -233,7 +339,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, * When deadlock detection is off then we check, if further * priority adjustment is necessary. */ - if (!detect_deadlock && waiter->list_entry.prio == task->prio) + if (!detect_deadlock && waiter->prio == task->prio) goto out_unlock_pi; lock = waiter->lock; @@ -254,9 +360,9 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, top_waiter = rt_mutex_top_waiter(lock); /* Requeue the waiter */ - plist_del(&waiter->list_entry, &lock->wait_list); - waiter->list_entry.prio = task->prio; - plist_add(&waiter->list_entry, &lock->wait_list); + rt_mutex_dequeue(lock, waiter); + waiter->prio = task->prio; + rt_mutex_enqueue(lock, waiter); /* Release the task */ raw_spin_unlock_irqrestore(&task->pi_lock, flags); @@ -280,17 +386,15 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, if (waiter == rt_mutex_top_waiter(lock)) { /* Boost the owner */ - plist_del(&top_waiter->pi_list_entry, &task->pi_waiters); - waiter->pi_list_entry.prio = waiter->list_entry.prio; - plist_add(&waiter->pi_list_entry, &task->pi_waiters); + rt_mutex_dequeue_pi(task, top_waiter); + rt_mutex_enqueue_pi(task, waiter); __rt_mutex_adjust_prio(task); } else if (top_waiter == waiter) { /* Deboost the owner */ - plist_del(&waiter->pi_list_entry, &task->pi_waiters); + rt_mutex_dequeue_pi(task, waiter); waiter = rt_mutex_top_waiter(lock); - waiter->pi_list_entry.prio = waiter->list_entry.prio; - plist_add(&waiter->pi_list_entry, &task->pi_waiters); + rt_mutex_enqueue_pi(task, waiter); __rt_mutex_adjust_prio(task); } @@ -355,7 +459,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, * 3) it is top waiter */ if (rt_mutex_has_waiters(lock)) { - if (task->prio >= rt_mutex_top_waiter(lock)->list_entry.prio) { + if (task->prio >= rt_mutex_top_waiter(lock)->prio) { if (!waiter || waiter != rt_mutex_top_waiter(lock)) return 0; } @@ -369,7 +473,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, /* remove the queued waiter. */ if (waiter) { - plist_del(&waiter->list_entry, &lock->wait_list); + rt_mutex_dequeue(lock, waiter); task->pi_blocked_on = NULL; } @@ -379,8 +483,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, */ if (rt_mutex_has_waiters(lock)) { top = rt_mutex_top_waiter(lock); - top->pi_list_entry.prio = top->list_entry.prio; - plist_add(&top->pi_list_entry, &task->pi_waiters); + rt_mutex_enqueue_pi(task, top); } raw_spin_unlock_irqrestore(&task->pi_lock, flags); } @@ -416,13 +519,12 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, __rt_mutex_adjust_prio(task); waiter->task = task; waiter->lock = lock; - plist_node_init(&waiter->list_entry, task->prio); - plist_node_init(&waiter->pi_list_entry, task->prio); + waiter->prio = task->prio; /* Get the top priority waiter on the lock */ if (rt_mutex_has_waiters(lock)) top_waiter = rt_mutex_top_waiter(lock); - plist_add(&waiter->list_entry, &lock->wait_list); + rt_mutex_enqueue(lock, waiter); task->pi_blocked_on = waiter; @@ -433,8 +535,8 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, if (waiter == rt_mutex_top_waiter(lock)) { raw_spin_lock_irqsave(&owner->pi_lock, flags); - plist_del(&top_waiter->pi_list_entry, &owner->pi_waiters); - plist_add(&waiter->pi_list_entry, &owner->pi_waiters); + rt_mutex_dequeue_pi(owner, top_waiter); + rt_mutex_enqueue_pi(owner, waiter); __rt_mutex_adjust_prio(owner); if (owner->pi_blocked_on) @@ -486,7 +588,7 @@ static void wakeup_next_waiter(struct rt_mutex *lock) * boosted mode and go back to normal after releasing * lock->wait_lock. */ - plist_del(&waiter->pi_list_entry, ¤t->pi_waiters); + rt_mutex_dequeue_pi(current, waiter); rt_mutex_set_owner(lock, NULL); @@ -510,7 +612,7 @@ static void remove_waiter(struct rt_mutex *lock, int chain_walk = 0; raw_spin_lock_irqsave(¤t->pi_lock, flags); - plist_del(&waiter->list_entry, &lock->wait_list); + rt_mutex_dequeue(lock, waiter); current->pi_blocked_on = NULL; raw_spin_unlock_irqrestore(¤t->pi_lock, flags); @@ -521,13 +623,13 @@ static void remove_waiter(struct rt_mutex *lock, raw_spin_lock_irqsave(&owner->pi_lock, flags); - plist_del(&waiter->pi_list_entry, &owner->pi_waiters); + rt_mutex_dequeue_pi(owner, waiter); if (rt_mutex_has_waiters(lock)) { struct rt_mutex_waiter *next; next = rt_mutex_top_waiter(lock); - plist_add(&next->pi_list_entry, &owner->pi_waiters); + rt_mutex_enqueue_pi(owner, next); } __rt_mutex_adjust_prio(owner); @@ -537,8 +639,6 @@ static void remove_waiter(struct rt_mutex *lock, raw_spin_unlock_irqrestore(&owner->pi_lock, flags); } - WARN_ON(!plist_node_empty(&waiter->pi_list_entry)); - if (!chain_walk) return; @@ -565,7 +665,8 @@ void rt_mutex_adjust_pi(struct task_struct *task) raw_spin_lock_irqsave(&task->pi_lock, flags); waiter = task->pi_blocked_on; - if (!waiter || waiter->list_entry.prio == task->prio) { + if (!waiter || (waiter->prio == task->prio && + !dl_prio(task->prio))) { raw_spin_unlock_irqrestore(&task->pi_lock, flags); return; } @@ -638,6 +739,8 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, int ret = 0; debug_rt_mutex_init_waiter(&waiter); + RB_CLEAR_NODE(&waiter.pi_tree_entry); + RB_CLEAR_NODE(&waiter.tree_entry); raw_spin_lock(&lock->wait_lock); @@ -904,7 +1007,8 @@ void __rt_mutex_init(struct rt_mutex *lock, const char *name) { lock->owner = NULL; raw_spin_lock_init(&lock->wait_lock); - plist_head_init(&lock->wait_list); + lock->waiters = RB_ROOT; + lock->waiters_leftmost = NULL; debug_rt_mutex_init(lock, name); } diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h index 53a66c85261b..7431a9c86f35 100644 --- a/kernel/locking/rtmutex_common.h +++ b/kernel/locking/rtmutex_common.h @@ -40,13 +40,13 @@ extern void schedule_rt_mutex_test(struct rt_mutex *lock); * This is the control structure for tasks blocked on a rt_mutex, * which is allocated on the kernel stack on of the blocked task. * - * @list_entry: pi node to enqueue into the mutex waiters list - * @pi_list_entry: pi node to enqueue into the mutex owner waiters list + * @tree_entry: pi node to enqueue into the mutex waiters tree + * @pi_tree_entry: pi node to enqueue into the mutex owner waiters tree * @task: task reference to the blocked task */ struct rt_mutex_waiter { - struct plist_node list_entry; - struct plist_node pi_list_entry; + struct rb_node tree_entry; + struct rb_node pi_tree_entry; struct task_struct *task; struct rt_mutex *lock; #ifdef CONFIG_DEBUG_RT_MUTEXES @@ -54,14 +54,15 @@ struct rt_mutex_waiter { struct pid *deadlock_task_pid; struct rt_mutex *deadlock_lock; #endif + int prio; }; /* - * Various helpers to access the waiters-plist: + * Various helpers to access the waiters-tree: */ static inline int rt_mutex_has_waiters(struct rt_mutex *lock) { - return !plist_head_empty(&lock->wait_list); + return !RB_EMPTY_ROOT(&lock->waiters); } static inline struct rt_mutex_waiter * @@ -69,8 +70,8 @@ rt_mutex_top_waiter(struct rt_mutex *lock) { struct rt_mutex_waiter *w; - w = plist_first_entry(&lock->wait_list, struct rt_mutex_waiter, - list_entry); + w = rb_entry(lock->waiters_leftmost, struct rt_mutex_waiter, + tree_entry); BUG_ON(w->lock != lock); return w; @@ -78,14 +79,14 @@ rt_mutex_top_waiter(struct rt_mutex *lock) static inline int task_has_pi_waiters(struct task_struct *p) { - return !plist_head_empty(&p->pi_waiters); + return !RB_EMPTY_ROOT(&p->pi_waiters); } static inline struct rt_mutex_waiter * task_top_pi_waiter(struct task_struct *p) { - return plist_first_entry(&p->pi_waiters, struct rt_mutex_waiter, - pi_list_entry); + return rb_entry(p->pi_waiters_leftmost, struct rt_mutex_waiter, + pi_tree_entry); } /* |