void uncore_pmu_start_hrtimer(struct intel_uncore_box *box)
{
- __hrtimer_start_range_ns(&box->hrtimer,
- ns_to_ktime(box->hrtimer_duration), 0,
- HRTIMER_MODE_REL_PINNED, 0);
+ hrtimer_start(&box->hrtimer, ns_to_ktime(box->hrtimer_duration),
+ HRTIMER_MODE_REL_PINNED);
}
void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box)
bitmap_zero(used_mask, UNCORE_PMC_IDX_MAX);
for (i = 0, wmin = UNCORE_PMC_IDX_MAX, wmax = 0; i < n; i++) {
- hwc = &box->event_list[i]->hw;
c = uncore_get_event_constraint(box, box->event_list[i]);
- hwc->constraint = c;
+ box->event_constraint[i] = c;
wmin = min(wmin, c->weight);
wmax = max(wmax, c->weight);
}
/* fastpath, try to reuse previous register */
for (i = 0; i < n; i++) {
hwc = &box->event_list[i]->hw;
- c = hwc->constraint;
+ c = box->event_constraint[i];
/* never assigned */
if (hwc->idx == -1)
}
/* slow path */
if (i != n)
- ret = perf_assign_events(box->event_list, n,
- wmin, wmax, assign);
+ ret = perf_assign_events(box->event_constraint, n,
+ wmin, wmax, n, assign);
if (!assign || ret) {
for (i = 0; i < n; i++)
box->phys_id = phys_id;
box->pci_dev = pdev;
box->pmu = pmu;
+ uncore_box_init(box);
pci_set_drvdata(pdev, box);
raw_spin_lock(&uncore_box_lock);
case 69: /* Haswell Celeron */
ret = hsw_uncore_pci_init();
break;
+ case 61: /* Broadwell */
+ ret = bdw_uncore_pci_init();
+ break;
default:
return 0;
}
pmu = &type->pmus[j];
box = *per_cpu_ptr(pmu->box, cpu);
/* called by uncore_cpu_init? */
- if (box && box->phys_id >= 0)
+ if (box && box->phys_id >= 0) {
+ uncore_box_init(box);
continue;
+ }
for_each_online_cpu(k) {
exist = *per_cpu_ptr(pmu->box, k);
}
}
- if (box)
+ if (box) {
box->phys_id = phys_id;
+ uncore_box_init(box);
+ }
}
}
return 0;
}
/**
- * dentry_rcuwalk_barrier - invalidate in-progress rcu-walk lookups
+ * dentry_rcuwalk_invalidate - invalidate in-progress rcu-walk lookups
* @dentry: the target dentry
* After this call, in-progress rcu-walk path lookup will fail. This
* should be called after unhashing, and after changing d_inode (if
* the dentry has not already been unhashed).
*/
- static inline void dentry_rcuwalk_barrier(struct dentry *dentry)
+ static inline void dentry_rcuwalk_invalidate(struct dentry *dentry)
{
- assert_spin_locked(&dentry->d_lock);
- /* Go through a barrier */
- write_seqcount_barrier(&dentry->d_seq);
+ lockdep_assert_held(&dentry->d_lock);
+ /* Go through am invalidation barrier */
+ write_seqcount_invalidate(&dentry->d_seq);
}
/*
struct inode *inode = dentry->d_inode;
__d_clear_type_and_inode(dentry);
hlist_del_init(&dentry->d_u.d_alias);
- dentry_rcuwalk_barrier(dentry);
+ dentry_rcuwalk_invalidate(dentry);
spin_unlock(&dentry->d_lock);
spin_unlock(&inode->i_lock);
if (!inode->i_nlink)
__hlist_bl_del(&dentry->d_hash);
dentry->d_hash.pprev = NULL;
hlist_bl_unlock(b);
- dentry_rcuwalk_barrier(dentry);
+ dentry_rcuwalk_invalidate(dentry);
}
}
EXPORT_SYMBOL(__d_drop);
/* might go back up the wrong parent if we have had a rename. */
if (need_seqretry(&rename_lock, seq))
goto rename_retry;
- next = child->d_child.next;
- while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)) {
+ /* go into the first sibling still alive */
+ do {
+ next = child->d_child.next;
if (next == &this_parent->d_subdirs)
goto ascend;
child = list_entry(next, struct dentry, d_child);
- next = next->next;
- }
+ } while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED));
rcu_read_unlock();
goto resume;
}
if (inode)
hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
__d_set_inode_and_type(dentry, inode, add_flags);
- dentry_rcuwalk_barrier(dentry);
+ dentry_rcuwalk_invalidate(dentry);
spin_unlock(&dentry->d_lock);
fsnotify_d_instantiate(dentry, inode);
}
int idx; /* index in shared_regs->regs[] */
};
-struct event_constraint;
-
/**
* struct hw_perf_event - performance event hardware details:
*/
struct hw_perf_event_extra extra_reg;
struct hw_perf_event_extra branch_reg;
-
- struct event_constraint *constraint;
};
struct { /* software */
struct hrtimer hrtimer;
};
struct { /* intel_cqm */
int cqm_state;
- int cqm_rmid;
+ u32 cqm_rmid;
struct list_head cqm_events_entry;
struct list_head cqm_groups_entry;
struct list_head cqm_group_entry;
struct perf_event_context *task_ctx;
int active_oncpu;
int exclusive;
+
+ raw_spinlock_t hrtimer_lock;
struct hrtimer hrtimer;
ktime_t hrtimer_interval;
+ unsigned int hrtimer_active;
+
struct pmu *unique_pmu;
struct perf_cgroup *cgrp;
};
struct perf_sample_data *data,
struct pt_regs *regs);
+extern void perf_event_output(struct perf_event *event,
+ struct perf_sample_data *data,
+ struct pt_regs *regs);
+
+extern void
+perf_event_header__init_id(struct perf_event_header *header,
+ struct perf_sample_data *data,
+ struct perf_event *event);
+extern void
+perf_event__output_id_sample(struct perf_event *event,
+ struct perf_output_handle *handle,
+ struct perf_sample_data *sample);
+
+extern void
+perf_log_lost_samples(struct perf_event *event, u64 lost);
+
static inline bool is_sampling_event(struct perf_event *event)
{
return event->attr.sample_period != 0;
extern struct static_key_deferred perf_sched_events;
+static __always_inline bool
+perf_sw_migrate_enabled(void)
+{
+ if (static_key_false(&perf_swevent_enabled[PERF_COUNT_SW_CPU_MIGRATIONS]))
+ return true;
+ return false;
+}
+
+static inline void perf_event_task_migrate(struct task_struct *task)
+{
+ if (perf_sw_migrate_enabled())
+ task->sched_migrated = 1;
+}
+
static inline void perf_event_task_sched_in(struct task_struct *prev,
struct task_struct *task)
{
if (static_key_false(&perf_sched_events.key))
__perf_event_task_sched_in(prev, task);
+
+ if (perf_sw_migrate_enabled() && task->sched_migrated) {
+ struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]);
+
+ perf_fetch_caller_regs(regs);
+ ___perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, regs, 0);
+ task->sched_migrated = 0;
+ }
}
static inline void perf_event_task_sched_out(struct task_struct *prev,
static inline void *
perf_get_aux(struct perf_output_handle *handle) { return NULL; }
static inline void
+perf_event_task_migrate(struct task_struct *task) { }
+static inline void
perf_event_task_sched_in(struct task_struct *prev,
struct task_struct *task) { }
static inline void
#include <linux/debugobjects.h>
#include <linux/bug.h>
#include <linux/compiler.h>
+ #include <linux/ktime.h>
+
#include <asm/barrier.h>
extern int rcu_expedited; /* for sysctl */
void rcu_bh_qs(void);
void rcu_check_callbacks(int user);
struct notifier_block;
-void rcu_idle_enter(void);
-void rcu_idle_exit(void);
-void rcu_irq_enter(void);
-void rcu_irq_exit(void);
int rcu_cpu_notify(struct notifier_block *self,
unsigned long action, void *hcpu);
#define rcu_note_voluntary_context_switch(t) \
do { \
rcu_all_qs(); \
- if (ACCESS_ONCE((t)->rcu_tasks_holdout)) \
- ACCESS_ONCE((t)->rcu_tasks_holdout) = false; \
+ if (READ_ONCE((t)->rcu_tasks_holdout)) \
+ WRITE_ONCE((t)->rcu_tasks_holdout, false); \
} while (0)
#else /* #ifdef CONFIG_TASKS_RCU */
#define TASKS_RCU(x) do { } while (0)
#define __rcu_access_pointer(p, space) \
({ \
- typeof(*p) *_________p1 = (typeof(*p) *__force)ACCESS_ONCE(p); \
+ typeof(*p) *_________p1 = (typeof(*p) *__force)READ_ONCE(p); \
rcu_dereference_sparse(p, space); \
((typeof(*p) __force __kernel *)(_________p1)); \
})
((typeof(*p) __force __kernel *)(p)); \
})
-#define __rcu_access_index(p, space) \
-({ \
- typeof(p) _________p1 = ACCESS_ONCE(p); \
- rcu_dereference_sparse(p, space); \
- (_________p1); \
-})
-#define __rcu_dereference_index_check(p, c) \
-({ \
- /* Dependency order vs. p above. */ \
- typeof(p) _________p1 = lockless_dereference(p); \
- rcu_lockdep_assert(c, \
- "suspicious rcu_dereference_index_check() usage"); \
- (_________p1); \
-})
-
/**
* RCU_INITIALIZER() - statically initialize an RCU-protected global variable
* @v: The value to statically initialize with.
*/
#define lockless_dereference(p) \
({ \
- typeof(p) _________p1 = ACCESS_ONCE(p); \
+ typeof(p) _________p1 = READ_ONCE(p); \
smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
(_________p1); \
})
* @p: The pointer to read
*
* Return the value of the specified RCU-protected pointer, but omit the
- * smp_read_barrier_depends() and keep the ACCESS_ONCE(). This is useful
+ * smp_read_barrier_depends() and keep the READ_ONCE(). This is useful
* when the value of this pointer is accessed, but the pointer is not
* dereferenced, for example, when testing an RCU-protected pointer against
* NULL. Although rcu_access_pointer() may also be used in cases where
*/
#define rcu_dereference_raw_notrace(p) __rcu_dereference_check((p), 1, __rcu)
-/**
- * rcu_access_index() - fetch RCU index with no dereferencing
- * @p: The index to read
- *
- * Return the value of the specified RCU-protected index, but omit the
- * smp_read_barrier_depends() and keep the ACCESS_ONCE(). This is useful
- * when the value of this index is accessed, but the index is not
- * dereferenced, for example, when testing an RCU-protected index against
- * -1. Although rcu_access_index() may also be used in cases where
- * update-side locks prevent the value of the index from changing, you
- * should instead use rcu_dereference_index_protected() for this use case.
- */
-#define rcu_access_index(p) __rcu_access_index((p), __rcu)
-
-/**
- * rcu_dereference_index_check() - rcu_dereference for indices with debug checking
- * @p: The pointer to read, prior to dereferencing
- * @c: The conditions under which the dereference will take place
- *
- * Similar to rcu_dereference_check(), but omits the sparse checking.
- * This allows rcu_dereference_index_check() to be used on integers,
- * which can then be used as array indices. Attempting to use
- * rcu_dereference_check() on an integer will give compiler warnings
- * because the sparse address-space mechanism relies on dereferencing
- * the RCU-protected pointer. Dereferencing integers is not something
- * that even gcc will put up with.
- *
- * Note that this function does not implicitly check for RCU read-side
- * critical sections. If this function gains lots of uses, it might
- * make sense to provide versions for each flavor of RCU, but it does
- * not make sense as of early 2010.
- */
-#define rcu_dereference_index_check(p, c) \
- __rcu_dereference_index_check((p), (c))
-
/**
* rcu_dereference_protected() - fetch RCU pointer when updates prevented
* @p: The pointer to read, prior to dereferencing
* @c: The conditions under which the dereference will take place
*
* Return the value of the specified RCU-protected pointer, but omit
- * both the smp_read_barrier_depends() and the ACCESS_ONCE(). This
+ * both the smp_read_barrier_depends() and the READ_ONCE(). This
* is useful in cases where update-side locks prevent the value of the
* pointer from changing. Please note that this primitive does -not-
* prevent the compiler from repeating this reference or combining it
#define kfree_rcu(ptr, rcu_head) \
__kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head))
-#if defined(CONFIG_TINY_RCU) || defined(CONFIG_RCU_NOCB_CPU_ALL)
+#ifdef CONFIG_TINY_RCU
- static inline int rcu_needs_cpu(unsigned long *delta_jiffies)
+ static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt)
{
- *delta_jiffies = ULONG_MAX;
+ *nextevt = KTIME_MAX;
return 0;
}
-#endif /* #if defined(CONFIG_TINY_RCU) || defined(CONFIG_RCU_NOCB_CPU_ALL) */
+#endif /* #ifdef CONFIG_TINY_RCU */
#if defined(CONFIG_RCU_NOCB_CPU_ALL)
static inline bool rcu_is_nocb_cpu(int cpu) { return true; }
#define __LINUX_RCUTREE_H
void rcu_note_context_switch(void);
- int rcu_needs_cpu(unsigned long *delta_jiffies);
-#ifndef CONFIG_RCU_NOCB_CPU_ALL
+ int rcu_needs_cpu(u64 basem, u64 *nextevt);
-#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
void rcu_cpu_stall_reset(void);
/*
void rcu_bh_force_quiescent_state(void);
void rcu_sched_force_quiescent_state(void);
+void rcu_idle_enter(void);
+void rcu_idle_exit(void);
+void rcu_irq_enter(void);
+void rcu_irq_exit(void);
+
void exit_rcu(void);
void rcu_scheduler_starting(void);
#include <linux/errno.h>
#include <linux/nodemask.h>
#include <linux/mm_types.h>
-#include <linux/preempt_mask.h>
+#include <linux/preempt.h>
#include <asm/page.h>
#include <asm/ptrace.h>
struct perf_event_context;
struct blk_plug;
struct filename;
+struct nameidata;
#define VMACACHE_BITS 2
#define VMACACHE_SIZE (1U << VMACACHE_BITS)
extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load);
extern void calc_global_load(unsigned long ticks);
+
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
extern void update_cpu_load_nohz(void);
+#else
+static inline void update_cpu_load_nohz(void) { }
+#endif
extern unsigned long get_parent_ip(unsigned long addr);
#define TASK_WAKEKILL 128
#define TASK_WAKING 256
#define TASK_PARKED 512
-#define TASK_STATE_MAX 1024
+#define TASK_NOLOAD 1024
+#define TASK_STATE_MAX 2048
-#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWP"
+#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWPN"
extern char ___assert_task_state[1 - 2*!!(
sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)];
#define TASK_STOPPED (TASK_WAKEKILL | __TASK_STOPPED)
#define TASK_TRACED (TASK_WAKEKILL | __TASK_TRACED)
+#define TASK_IDLE (TASK_UNINTERRUPTIBLE | TASK_NOLOAD)
+
/* Convenience macros for the sake of wake_up */
#define TASK_NORMAL (TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE)
#define TASK_ALL (TASK_NORMAL | __TASK_STOPPED | __TASK_TRACED)
((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
#define task_contributes_to_load(task) \
((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
- (task->flags & PF_FROZEN) == 0)
+ (task->flags & PF_FROZEN) == 0 && \
+ (task->state & TASK_NOLOAD) == 0)
#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
#define set_task_state(tsk, state_value) \
do { \
(tsk)->task_state_change = _THIS_IP_; \
- set_mb((tsk)->state, (state_value)); \
+ smp_store_mb((tsk)->state, (state_value)); \
} while (0)
/*
#define set_current_state(state_value) \
do { \
current->task_state_change = _THIS_IP_; \
- set_mb(current->state, (state_value)); \
+ smp_store_mb(current->state, (state_value)); \
} while (0)
#else
#define __set_task_state(tsk, state_value) \
do { (tsk)->state = (state_value); } while (0)
#define set_task_state(tsk, state_value) \
- set_mb((tsk)->state, (state_value))
+ smp_store_mb((tsk)->state, (state_value))
/*
* set_current_state() includes a barrier so that the write of current->state
#define __set_current_state(state_value) \
do { current->state = (state_value); } while (0)
#define set_current_state(state_value) \
- set_mb(current->state, (state_value))
+ smp_store_mb(current->state, (state_value))
#endif
#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
extern void nohz_balance_enter_idle(int cpu);
extern void set_cpu_sd_state_idle(void);
- extern int get_nohz_timer_target(int pinned);
+ extern int get_nohz_timer_target(void);
#else
static inline void nohz_balance_enter_idle(int cpu) { }
static inline void set_cpu_sd_state_idle(void) { }
- static inline int get_nohz_timer_target(int pinned)
- {
- return smp_processor_id();
- }
#endif
/*
.sum_exec_runtime = 0, \
}
+/*
+ * This is the atomic variant of task_cputime, which can be used for
+ * storing and updating task_cputime statistics without locking.
+ */
+struct task_cputime_atomic {
+ atomic64_t utime;
+ atomic64_t stime;
+ atomic64_t sum_exec_runtime;
+};
+
+#define INIT_CPUTIME_ATOMIC \
+ (struct task_cputime_atomic) { \
+ .utime = ATOMIC64_INIT(0), \
+ .stime = ATOMIC64_INIT(0), \
+ .sum_exec_runtime = ATOMIC64_INIT(0), \
+ }
+
#ifdef CONFIG_PREEMPT_COUNT
#define PREEMPT_DISABLED (1 + PREEMPT_ENABLED)
#else
/**
* struct thread_group_cputimer - thread group interval timer counts
- * @cputime: thread group interval timers.
+ * @cputime_atomic: atomic thread group interval timers.
* @running: non-zero when there are timers running and
* @cputime receives updates.
- * @lock: lock for fields in this struct.
*
* This structure contains the version of task_cputime, above, that is
* used for thread group CPU timer calculations.
*/
struct thread_group_cputimer {
- struct task_cputime cputime;
+ struct task_cputime_atomic cputime_atomic;
int running;
- raw_spinlock_t lock;
};
#include <linux/rwsem.h>
#define SCHED_CAPACITY_SHIFT 10
#define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT)
+/*
+ * Wake-queues are lists of tasks with a pending wakeup, whose
+ * callers have already marked the task as woken internally,
+ * and can thus carry on. A common use case is being able to
+ * do the wakeups once the corresponding user lock as been
+ * released.
+ *
+ * We hold reference to each task in the list across the wakeup,
+ * thus guaranteeing that the memory is still valid by the time
+ * the actual wakeups are performed in wake_up_q().
+ *
+ * One per task suffices, because there's never a need for a task to be
+ * in two wake queues simultaneously; it is forbidden to abandon a task
+ * in a wake queue (a call to wake_up_q() _must_ follow), so if a task is
+ * already in a wake queue, the wakeup will happen soon and the second
+ * waker can just skip it.
+ *
+ * The WAKE_Q macro declares and initializes the list head.
+ * wake_up_q() does NOT reinitialize the list; it's expected to be
+ * called near the end of a function, where the fact that the queue is
+ * not used again will be easy to see by inspection.
+ *
+ * Note that this can cause spurious wakeups. schedule() callers
+ * must ensure the call is done inside a loop, confirming that the
+ * wakeup condition has in fact occurred.
+ */
+struct wake_q_node {
+ struct wake_q_node *next;
+};
+
+struct wake_q_head {
+ struct wake_q_node *first;
+ struct wake_q_node **lastp;
+};
+
+#define WAKE_Q_TAIL ((struct wake_q_node *) 0x01)
+
+#define WAKE_Q(name) \
+ struct wake_q_head name = { WAKE_Q_TAIL, &name.first }
+
+extern void wake_q_add(struct wake_q_head *head,
+ struct task_struct *task);
+extern void wake_up_q(struct wake_q_head *head);
+
/*
* sched-domains (multiprocessor balancing) declarations:
*/
int rcu_read_lock_nesting;
union rcu_special rcu_read_unlock_special;
struct list_head rcu_node_entry;
-#endif /* #ifdef CONFIG_PREEMPT_RCU */
-#ifdef CONFIG_PREEMPT_RCU
struct rcu_node *rcu_blocked_node;
#endif /* #ifdef CONFIG_PREEMPT_RCU */
#ifdef CONFIG_TASKS_RCU
#endif
struct mm_struct *mm, *active_mm;
-#ifdef CONFIG_COMPAT_BRK
- unsigned brk_randomized:1;
-#endif
/* per-thread vma caching */
u32 vmacache_seqnum;
struct vm_area_struct *vmacache[VMACACHE_SIZE];
int exit_state;
int exit_code, exit_signal;
int pdeath_signal; /* The signal sent when the parent dies */
- unsigned int jobctl; /* JOBCTL_*, siglock protected */
+ unsigned long jobctl; /* JOBCTL_*, siglock protected */
/* Used for emulating ABI behavior of previous Linux versions */
unsigned int personality;
/* Revert to default priority/policy when forking */
unsigned sched_reset_on_fork:1;
unsigned sched_contributes_to_load:1;
+ unsigned sched_migrated:1;
#ifdef CONFIG_MEMCG_KMEM
unsigned memcg_kmem_skip_account:1;
#endif
+#ifdef CONFIG_COMPAT_BRK
+ unsigned brk_randomized:1;
+#endif
unsigned long atomic_flags; /* Flags needing atomic access. */
it with task_lock())
- initialized normally by setup_new_exec */
/* file system info */
- int link_count, total_link_count;
+ struct nameidata *nameidata;
#ifdef CONFIG_SYSVIPC
/* ipc stuff */
struct sysv_sem sysvsem;
/* Protection of the PI data structures: */
raw_spinlock_t pi_lock;
+ struct wake_q_node wake_q;
+
#ifdef CONFIG_RT_MUTEXES
/* PI waiters blocked on a rt_mutex held by this task */
struct rb_root pi_waiters;
#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
unsigned long task_state_change;
#endif
+ int pagefault_disabled;
};
/* Future-safe accessor for struct task_struct's cpus_allowed. */
#define JOBCTL_TRAPPING_BIT 21 /* switching to TRACED */
#define JOBCTL_LISTENING_BIT 22 /* ptracer is listening for events */
-#define JOBCTL_STOP_DEQUEUED (1 << JOBCTL_STOP_DEQUEUED_BIT)
-#define JOBCTL_STOP_PENDING (1 << JOBCTL_STOP_PENDING_BIT)
-#define JOBCTL_STOP_CONSUME (1 << JOBCTL_STOP_CONSUME_BIT)
-#define JOBCTL_TRAP_STOP (1 << JOBCTL_TRAP_STOP_BIT)
-#define JOBCTL_TRAP_NOTIFY (1 << JOBCTL_TRAP_NOTIFY_BIT)
-#define JOBCTL_TRAPPING (1 << JOBCTL_TRAPPING_BIT)
-#define JOBCTL_LISTENING (1 << JOBCTL_LISTENING_BIT)
+#define JOBCTL_STOP_DEQUEUED (1UL << JOBCTL_STOP_DEQUEUED_BIT)
+#define JOBCTL_STOP_PENDING (1UL << JOBCTL_STOP_PENDING_BIT)
+#define JOBCTL_STOP_CONSUME (1UL << JOBCTL_STOP_CONSUME_BIT)
+#define JOBCTL_TRAP_STOP (1UL << JOBCTL_TRAP_STOP_BIT)
+#define JOBCTL_TRAP_NOTIFY (1UL << JOBCTL_TRAP_NOTIFY_BIT)
+#define JOBCTL_TRAPPING (1UL << JOBCTL_TRAPPING_BIT)
+#define JOBCTL_LISTENING (1UL << JOBCTL_LISTENING_BIT)
#define JOBCTL_TRAP_MASK (JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
#define JOBCTL_PENDING_MASK (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)
extern bool task_set_jobctl_pending(struct task_struct *task,
- unsigned int mask);
+ unsigned long mask);
extern void task_clear_jobctl_trapping(struct task_struct *task);
extern void task_clear_jobctl_pending(struct task_struct *task,
- unsigned int mask);
+ unsigned long mask);
static inline void rcu_copy_process(struct task_struct *p)
{
void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times);
void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times);
-static inline void thread_group_cputime_init(struct signal_struct *sig)
-{
- raw_spin_lock_init(&sig->cputimer.lock);
-}
-
/*
* Reevaluate whether the task has signals pending delivery.
* Wake the task if so.
static inline unsigned long task_rlimit(const struct task_struct *tsk,
unsigned int limit)
{
- return ACCESS_ONCE(tsk->signal->rlim[limit].rlim_cur);
+ return READ_ONCE(tsk->signal->rlim[limit].rlim_cur);
}
static inline unsigned long task_rlimit_max(const struct task_struct *tsk,
unsigned int limit)
{
- return ACCESS_ONCE(tsk->signal->rlim[limit].rlim_max);
+ return READ_ONCE(tsk->signal->rlim[limit].rlim_max);
}
static inline unsigned long rlimit(unsigned int limit)
static struct workqueue_struct *perf_wq;
+ typedef int (*remote_function_f)(void *);
+
struct remote_function_call {
struct task_struct *p;
- int (*func)(void *info);
+ remote_function_f func;
void *info;
int ret;
};
* -EAGAIN - when the process moved away
*/
static int
- task_function_call(struct task_struct *p, int (*func) (void *info), void *info)
+ task_function_call(struct task_struct *p, remote_function_f func, void *info)
{
struct remote_function_call data = {
.p = p,
*
* returns: @func return value or -ENXIO when the cpu is offline
*/
- static int cpu_function_call(int cpu, int (*func) (void *info), void *info)
+ static int cpu_function_call(int cpu, remote_function_f func, void *info)
{
struct remote_function_call data = {
.p = NULL,
/*
* function must be called with interrupts disbled
*/
- static enum hrtimer_restart perf_cpu_hrtimer_handler(struct hrtimer *hr)
+ static enum hrtimer_restart perf_mux_hrtimer_handler(struct hrtimer *hr)
{
struct perf_cpu_context *cpuctx;
- enum hrtimer_restart ret = HRTIMER_NORESTART;
int rotations = 0;
WARN_ON(!irqs_disabled());
cpuctx = container_of(hr, struct perf_cpu_context, hrtimer);
-
rotations = perf_rotate_context(cpuctx);
- /*
- * arm timer if needed
- */
- if (rotations) {
+ raw_spin_lock(&cpuctx->hrtimer_lock);
+ if (rotations)
hrtimer_forward_now(hr, cpuctx->hrtimer_interval);
- ret = HRTIMER_RESTART;
- }
-
- return ret;
- }
-
- /* CPU is going down */
- void perf_cpu_hrtimer_cancel(int cpu)
- {
- struct perf_cpu_context *cpuctx;
- struct pmu *pmu;
- unsigned long flags;
-
- if (WARN_ON(cpu != smp_processor_id()))
- return;
-
- local_irq_save(flags);
-
- rcu_read_lock();
-
- list_for_each_entry_rcu(pmu, &pmus, entry) {
- cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
-
- if (pmu->task_ctx_nr == perf_sw_context)
- continue;
-
- hrtimer_cancel(&cpuctx->hrtimer);
- }
-
- rcu_read_unlock();
+ else
+ cpuctx->hrtimer_active = 0;
+ raw_spin_unlock(&cpuctx->hrtimer_lock);
- local_irq_restore(flags);
+ return rotations ? HRTIMER_RESTART : HRTIMER_NORESTART;
}
- static void __perf_cpu_hrtimer_init(struct perf_cpu_context *cpuctx, int cpu)
+ static void __perf_mux_hrtimer_init(struct perf_cpu_context *cpuctx, int cpu)
{
- struct hrtimer *hr = &cpuctx->hrtimer;
+ struct hrtimer *timer = &cpuctx->hrtimer;
struct pmu *pmu = cpuctx->ctx.pmu;
- int timer;
+ u64 interval;
/* no multiplexing needed for SW PMU */
if (pmu->task_ctx_nr == perf_sw_context)
* check default is sane, if not set then force to
* default interval (1/tick)
*/
- timer = pmu->hrtimer_interval_ms;
- if (timer < 1)
- timer = pmu->hrtimer_interval_ms = PERF_CPU_HRTIMER;
+ interval = pmu->hrtimer_interval_ms;
+ if (interval < 1)
+ interval = pmu->hrtimer_interval_ms = PERF_CPU_HRTIMER;
- cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * timer);
+ cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * interval);
- hrtimer_init(hr, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
- hr->function = perf_cpu_hrtimer_handler;
+ raw_spin_lock_init(&cpuctx->hrtimer_lock);
+ hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
+ timer->function = perf_mux_hrtimer_handler;
}
- static void perf_cpu_hrtimer_restart(struct perf_cpu_context *cpuctx)
+ static int perf_mux_hrtimer_restart(struct perf_cpu_context *cpuctx)
{
- struct hrtimer *hr = &cpuctx->hrtimer;
+ struct hrtimer *timer = &cpuctx->hrtimer;
struct pmu *pmu = cpuctx->ctx.pmu;
+ unsigned long flags;
/* not for SW PMU */
if (pmu->task_ctx_nr == perf_sw_context)
- return;
+ return 0;
- if (hrtimer_active(hr))
- return;
+ raw_spin_lock_irqsave(&cpuctx->hrtimer_lock, flags);
+ if (!cpuctx->hrtimer_active) {
+ cpuctx->hrtimer_active = 1;
+ hrtimer_forward_now(timer, cpuctx->hrtimer_interval);
+ hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED);
+ }
+ raw_spin_unlock_irqrestore(&cpuctx->hrtimer_lock, flags);
- if (!hrtimer_callback_running(hr))
- __hrtimer_start_range_ns(hr, cpuctx->hrtimer_interval,
- 0, HRTIMER_MODE_REL_PINNED, 0);
+ return 0;
}
void perf_pmu_disable(struct pmu *pmu)
if (event_sched_in(group_event, cpuctx, ctx)) {
pmu->cancel_txn(pmu);
- perf_cpu_hrtimer_restart(cpuctx);
+ perf_mux_hrtimer_restart(cpuctx);
return -EAGAIN;
}
pmu->cancel_txn(pmu);
- perf_cpu_hrtimer_restart(cpuctx);
+ perf_mux_hrtimer_restart(cpuctx);
return -EAGAIN;
}
*/
if (leader != event) {
group_sched_out(leader, cpuctx, ctx);
- perf_cpu_hrtimer_restart(cpuctx);
+ perf_mux_hrtimer_restart(cpuctx);
}
if (leader->attr.pinned) {
update_group_times(leader);
if (event->ns)
put_pid_ns(event->ns);
perf_event_free_filter(event);
- perf_event_free_bpf_prog(event);
kfree(event);
}
put_callchain_buffers();
}
+ perf_event_free_bpf_prog(event);
+
if (event->destroy)
event->destroy(event);
WARN_ON_ONCE(event->rcu_pending);
old_rb = event->rb;
- event->rcu_batches = get_state_synchronize_rcu();
- event->rcu_pending = 1;
-
spin_lock_irqsave(&old_rb->event_lock, flags);
list_del_rcu(&event->rb_entry);
spin_unlock_irqrestore(&old_rb->event_lock, flags);
- }
- if (event->rcu_pending && rb) {
- cond_synchronize_rcu(event->rcu_batches);
- event->rcu_pending = 0;
+ event->rcu_batches = get_state_synchronize_rcu();
+ event->rcu_pending = 1;
}
if (rb) {
+ if (event->rcu_pending) {
+ cond_synchronize_rcu(event->rcu_batches);
+ event->rcu_pending = 0;
+ }
+
spin_lock_irqsave(&rb->event_lock, flags);
list_add_rcu(&event->rb_entry, &rb->event_list);
spin_unlock_irqrestore(&rb->event_lock, flags);
}
}
-static void perf_event_output(struct perf_event *event,
- struct perf_sample_data *data,
- struct pt_regs *regs)
+void perf_event_output(struct perf_event *event,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
{
struct perf_output_handle handle;
struct perf_event_header header;
perf_output_end(&handle);
}
+/*
+ * Lost/dropped samples logging
+ */
+void perf_log_lost_samples(struct perf_event *event, u64 lost)
+{
+ struct perf_output_handle handle;
+ struct perf_sample_data sample;
+ int ret;
+
+ struct {
+ struct perf_event_header header;
+ u64 lost;
+ } lost_samples_event = {
+ .header = {
+ .type = PERF_RECORD_LOST_SAMPLES,
+ .misc = 0,
+ .size = sizeof(lost_samples_event),
+ },
+ .lost = lost,
+ };
+
+ perf_event_header__init_id(&lost_samples_event.header, &sample, event);
+
+ ret = perf_output_begin(&handle, event,
+ lost_samples_event.header.size);
+ if (ret)
+ return;
+
+ perf_output_put(&handle, lost_samples_event);
+ perf_event__output_id_sample(event, &handle, &sample);
+ perf_output_end(&handle);
+}
+
/*
* IRQ throttle logging
*/
} else {
period = max_t(u64, 10000, hwc->sample_period);
}
- __hrtimer_start_range_ns(&hwc->hrtimer,
- ns_to_ktime(period), 0,
- HRTIMER_MODE_REL_PINNED, 0);
+ hrtimer_start(&hwc->hrtimer, ns_to_ktime(period),
+ HRTIMER_MODE_REL_PINNED);
}
static void perf_swevent_cancel_hrtimer(struct perf_event *event)
return snprintf(page, PAGE_SIZE-1, "%d\n", pmu->hrtimer_interval_ms);
}
+ static DEFINE_MUTEX(mux_interval_mutex);
+
static ssize_t
perf_event_mux_interval_ms_store(struct device *dev,
struct device_attribute *attr,
if (timer == pmu->hrtimer_interval_ms)
return count;
+ mutex_lock(&mux_interval_mutex);
pmu->hrtimer_interval_ms = timer;
/* update all cpuctx for this PMU */
- for_each_possible_cpu(cpu) {
+ get_online_cpus();
+ for_each_online_cpu(cpu) {
struct perf_cpu_context *cpuctx;
cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * timer);
- if (hrtimer_active(&cpuctx->hrtimer))
- hrtimer_forward_now(&cpuctx->hrtimer, cpuctx->hrtimer_interval);
+ cpu_function_call(cpu,
+ (remote_function_f)perf_mux_hrtimer_restart, cpuctx);
}
+ put_online_cpus();
+ mutex_unlock(&mux_interval_mutex);
return count;
}
lockdep_set_class(&cpuctx->ctx.lock, &cpuctx_lock);
cpuctx->ctx.pmu = pmu;
- __perf_cpu_hrtimer_init(cpuctx, cpu);
+ __perf_mux_hrtimer_init(cpuctx, cpu);
cpuctx->unique_pmu = pmu;
}
/*
* The hash bucket lock must be held when this is called.
- * Afterwards, the futex_q must not be accessed.
+ * Afterwards, the futex_q must not be accessed. Callers
+ * must ensure to later call wake_up_q() for the actual
+ * wakeups to occur.
*/
-static void wake_futex(struct futex_q *q)
+static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q)
{
struct task_struct *p = q->task;
return;
/*
- * We set q->lock_ptr = NULL _before_ we wake up the task. If
- * a non-futex wake up happens on another CPU then the task
- * might exit and p would dereference a non-existing task
- * struct. Prevent this by holding a reference on p across the
- * wake up.
+ * Queue the task for later wakeup for after we've released
+ * the hb->lock. wake_q_add() grabs reference to p.
*/
- get_task_struct(p);
-
+ wake_q_add(wake_q, p);
__unqueue_futex(q);
/*
* The waiting task can free the futex_q as soon as
*/
smp_wmb();
q->lock_ptr = NULL;
-
- wake_up_state(p, TASK_NORMAL);
- put_task_struct(p);
}
static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
struct futex_q *this, *next;
union futex_key key = FUTEX_KEY_INIT;
int ret;
+ WAKE_Q(wake_q);
if (!bitset)
return -EINVAL;
if (!(this->bitset & bitset))
continue;
- wake_futex(this);
+ mark_wake_futex(&wake_q, this);
if (++ret >= nr_wake)
break;
}
}
spin_unlock(&hb->lock);
+ wake_up_q(&wake_q);
out_put_key:
put_futex_key(&key);
out:
struct futex_hash_bucket *hb1, *hb2;
struct futex_q *this, *next;
int ret, op_ret;
+ WAKE_Q(wake_q);
retry:
ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, VERIFY_READ);
ret = -EINVAL;
goto out_unlock;
}
- wake_futex(this);
+ mark_wake_futex(&wake_q, this);
if (++ret >= nr_wake)
break;
}
ret = -EINVAL;
goto out_unlock;
}
- wake_futex(this);
+ mark_wake_futex(&wake_q, this);
if (++op_ret >= nr_wake2)
break;
}
out_unlock:
double_unlock_hb(hb1, hb2);
+ wake_up_q(&wake_q);
out_put_keys:
put_futex_key(&key2);
out_put_key1:
struct futex_pi_state *pi_state = NULL;
struct futex_hash_bucket *hb1, *hb2;
struct futex_q *this, *next;
+ WAKE_Q(wake_q);
if (requeue_pi) {
/*
* woken by futex_unlock_pi().
*/
if (++task_count <= nr_wake && !requeue_pi) {
- wake_futex(this);
+ mark_wake_futex(&wake_q, this);
continue;
}
out_unlock:
free_pi_state(pi_state);
double_unlock_hb(hb1, hb2);
+ wake_up_q(&wake_q);
hb_waiters_dec(hb2);
/*
{
/*
* The task state is guaranteed to be set before another task can
- * wake it. set_current_state() is implemented using set_mb() and
+ * wake it. set_current_state() is implemented using smp_store_mb() and
* queue_me() calls spin_unlock() upon completion, both serializing
* access to the hash list and forcing another memory barrier.
*/
queue_me(q, hb);
/* Arm the timer */
- if (timeout) {
+ if (timeout)
hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS);
- if (!hrtimer_active(&timeout->timer))
- timeout->task = NULL;
- }
/*
* If we have been removed from the hash list, then another task
}
/*
- * We can speed up the acquire/release, if the architecture
- * supports cmpxchg and if there's no debugging state to be set up
+ * We can speed up the acquire/release, if there's no debugging state to be
+ * set up.
*/
-#if defined(__HAVE_ARCH_CMPXCHG) && !defined(CONFIG_DEBUG_RT_MUTEXES)
+#ifndef CONFIG_DEBUG_RT_MUTEXES
# define rt_mutex_cmpxchg(l,c,n) (cmpxchg(&l->owner, c, n) == c)
static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
{
set_current_state(state);
/* Setup the timer, when timeout != NULL */
- if (unlikely(timeout)) {
+ if (unlikely(timeout))
hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS);
- if (!hrtimer_active(&timeout->timer))
- timeout->task = NULL;
- }
ret = task_blocks_on_rt_mutex(lock, &waiter, current, chwalk);
*
* @lock: the rt_mutex to be locked
*
+ * This function can only be called in thread context. It's safe to
+ * call it from atomic regions, but not from hard interrupt or soft
+ * interrupt context.
+ *
* Returns 1 on success and 0 on contention
*/
int __sched rt_mutex_trylock(struct rt_mutex *lock)
{
+ if (WARN_ON(in_irq() || in_nmi() || in_serving_softirq()))
+ return 0;
+
return rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock);
}
EXPORT_SYMBOL_GPL(rt_mutex_trylock);
DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
DEFINE_PER_CPU(char, rcu_cpu_has_work);
-#endif /* #ifdef CONFIG_RCU_BOOST */
+#else /* #ifdef CONFIG_RCU_BOOST */
+
+/*
+ * Some architectures do not define rt_mutexes, but if !CONFIG_RCU_BOOST,
+ * all uses are in dead code. Provide a definition to keep the compiler
+ * happy, but add WARN_ON_ONCE() to complain if used in the wrong place.
+ * This probably needs to be excluded from -rt builds.
+ */
+#define rt_mutex_owner(a) ({ WARN_ON_ONCE(1); NULL; })
+
+#endif /* #else #ifdef CONFIG_RCU_BOOST */
#ifdef CONFIG_RCU_NOCB_CPU
static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */
{
if (IS_ENABLED(CONFIG_RCU_TRACE))
pr_info("\tRCU debugfs-based tracing is enabled.\n");
- if ((IS_ENABLED(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 64) ||
- (!IS_ENABLED(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 32))
+ if ((IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 64) ||
+ (!IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 32))
pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d\n",
- CONFIG_RCU_FANOUT);
- if (IS_ENABLED(CONFIG_RCU_FANOUT_EXACT))
+ RCU_FANOUT);
+ if (rcu_fanout_exact)
pr_info("\tHierarchical RCU autobalancing is disabled.\n");
if (IS_ENABLED(CONFIG_RCU_FAST_NO_HZ))
pr_info("\tRCU dyntick-idle grace-period acceleration is enabled.\n");
pr_info("\tAdditional per-CPU info printed with stalls.\n");
if (NUM_RCU_LVL_4 != 0)
pr_info("\tFour-level hierarchy is enabled.\n");
- if (CONFIG_RCU_FANOUT_LEAF != 16)
+ if (RCU_FANOUT_LEAF != 16)
pr_info("\tBuild-time adjustment of leaf fanout to %d.\n",
- CONFIG_RCU_FANOUT_LEAF);
- if (rcu_fanout_leaf != CONFIG_RCU_FANOUT_LEAF)
+ RCU_FANOUT_LEAF);
+ if (rcu_fanout_leaf != RCU_FANOUT_LEAF)
pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf);
if (nr_cpu_ids != NR_CPUS)
pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids);
#ifdef CONFIG_PREEMPT_RCU
RCU_STATE_INITIALIZER(rcu_preempt, 'p', call_rcu);
-static struct rcu_state *rcu_state_p = &rcu_preempt_state;
+static struct rcu_state *const rcu_state_p = &rcu_preempt_state;
+static struct rcu_data __percpu *const rcu_data_p = &rcu_preempt_data;
static int rcu_preempted_readers_exp(struct rcu_node *rnp);
static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
*/
static void rcu_preempt_qs(void)
{
- if (!__this_cpu_read(rcu_preempt_data.passed_quiesce)) {
+ if (!__this_cpu_read(rcu_data_p->passed_quiesce)) {
trace_rcu_grace_period(TPS("rcu_preempt"),
- __this_cpu_read(rcu_preempt_data.gpnum),
+ __this_cpu_read(rcu_data_p->gpnum),
TPS("cpuqs"));
- __this_cpu_write(rcu_preempt_data.passed_quiesce, 1);
+ __this_cpu_write(rcu_data_p->passed_quiesce, 1);
barrier(); /* Coordinate with rcu_preempt_check_callbacks(). */
current->rcu_read_unlock_special.b.need_qs = false;
}
!t->rcu_read_unlock_special.b.blocked) {
/* Possibly blocking in an RCU read-side critical section. */
- rdp = this_cpu_ptr(rcu_preempt_state.rda);
+ rdp = this_cpu_ptr(rcu_state_p->rda);
rnp = rdp->mynode;
raw_spin_lock_irqsave(&rnp->lock, flags);
smp_mb__after_unlock_lock();
if ((rnp->qsmask & rdp->grpmask) && rnp->gp_tasks != NULL) {
list_add(&t->rcu_node_entry, rnp->gp_tasks->prev);
rnp->gp_tasks = &t->rcu_node_entry;
-#ifdef CONFIG_RCU_BOOST
- if (rnp->boost_tasks != NULL)
+ if (IS_ENABLED(CONFIG_RCU_BOOST) &&
+ rnp->boost_tasks != NULL)
rnp->boost_tasks = rnp->gp_tasks;
-#endif /* #ifdef CONFIG_RCU_BOOST */
} else {
list_add(&t->rcu_node_entry, &rnp->blkd_tasks);
if (rnp->qsmask & rdp->grpmask)
bool empty_exp_now;
unsigned long flags;
struct list_head *np;
-#ifdef CONFIG_RCU_BOOST
bool drop_boost_mutex = false;
-#endif /* #ifdef CONFIG_RCU_BOOST */
struct rcu_node *rnp;
union rcu_special special;
t->rcu_read_unlock_special.b.blocked = false;
/*
- * Remove this task from the list it blocked on. The
- * task can migrate while we acquire the lock, but at
- * most one time. So at most two passes through loop.
+ * Remove this task from the list it blocked on. The task
+ * now remains queued on the rcu_node corresponding to
+ * the CPU it first blocked on, so the first attempt to
+ * acquire the task's rcu_node's ->lock will succeed.
+ * Keep the loop and add a WARN_ON() out of sheer paranoia.
*/
for (;;) {
rnp = t->rcu_blocked_node;
smp_mb__after_unlock_lock();
if (rnp == t->rcu_blocked_node)
break;
+ WARN_ON_ONCE(1);
raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
}
empty_norm = !rcu_preempt_blocked_readers_cgp(rnp);
rnp->gp_tasks = np;
if (&t->rcu_node_entry == rnp->exp_tasks)
rnp->exp_tasks = np;
-#ifdef CONFIG_RCU_BOOST
- if (&t->rcu_node_entry == rnp->boost_tasks)
- rnp->boost_tasks = np;
- /* Snapshot ->boost_mtx ownership with rcu_node lock held. */
- drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx) == t;
-#endif /* #ifdef CONFIG_RCU_BOOST */
+ if (IS_ENABLED(CONFIG_RCU_BOOST)) {
+ if (&t->rcu_node_entry == rnp->boost_tasks)
+ rnp->boost_tasks = np;
+ /* Snapshot ->boost_mtx ownership w/rnp->lock held. */
+ drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx) == t;
+ }
/*
* If this was the last task on the current list, and if
rnp->grplo,
rnp->grphi,
!!rnp->gp_tasks);
- rcu_report_unblock_qs_rnp(&rcu_preempt_state,
- rnp, flags);
+ rcu_report_unblock_qs_rnp(rcu_state_p, rnp, flags);
} else {
raw_spin_unlock_irqrestore(&rnp->lock, flags);
}
-#ifdef CONFIG_RCU_BOOST
/* Unboost if we were boosted. */
- if (drop_boost_mutex)
+ if (IS_ENABLED(CONFIG_RCU_BOOST) && drop_boost_mutex)
rt_mutex_unlock(&rnp->boost_mtx);
-#endif /* #ifdef CONFIG_RCU_BOOST */
/*
* If this was the last task on the expedited lists,
* then we need to report up the rcu_node hierarchy.
*/
if (!empty_exp && empty_exp_now)
- rcu_report_exp_rnp(&rcu_preempt_state, rnp, true);
+ rcu_report_exp_rnp(rcu_state_p, rnp, true);
} else {
local_irq_restore(flags);
}
raw_spin_unlock_irqrestore(&rnp->lock, flags);
return;
}
- t = list_entry(rnp->gp_tasks,
+ t = list_entry(rnp->gp_tasks->prev,
struct task_struct, rcu_node_entry);
list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry)
sched_show_task(t);
if (!rcu_preempt_blocked_readers_cgp(rnp))
return 0;
rcu_print_task_stall_begin(rnp);
- t = list_entry(rnp->gp_tasks,
+ t = list_entry(rnp->gp_tasks->prev,
struct task_struct, rcu_node_entry);
list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
pr_cont(" P%d", t->pid);
return;
}
if (t->rcu_read_lock_nesting > 0 &&
- __this_cpu_read(rcu_preempt_data.qs_pending) &&
- !__this_cpu_read(rcu_preempt_data.passed_quiesce))
+ __this_cpu_read(rcu_data_p->qs_pending) &&
+ !__this_cpu_read(rcu_data_p->passed_quiesce))
t->rcu_read_unlock_special.b.need_qs = true;
}
static void rcu_preempt_do_callbacks(void)
{
- rcu_do_batch(&rcu_preempt_state, this_cpu_ptr(&rcu_preempt_data));
+ rcu_do_batch(rcu_state_p, this_cpu_ptr(rcu_data_p));
}
#endif /* #ifdef CONFIG_RCU_BOOST */
*/
void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
{
- __call_rcu(head, func, &rcu_preempt_state, -1, 0);
+ __call_rcu(head, func, rcu_state_p, -1, 0);
}
EXPORT_SYMBOL_GPL(call_rcu);
static int sync_rcu_preempt_exp_done(struct rcu_node *rnp)
{
return !rcu_preempted_readers_exp(rnp) &&
- ACCESS_ONCE(rnp->expmask) == 0;
+ READ_ONCE(rnp->expmask) == 0;
}
/*
void synchronize_rcu_expedited(void)
{
struct rcu_node *rnp;
- struct rcu_state *rsp = &rcu_preempt_state;
+ struct rcu_state *rsp = rcu_state_p;
unsigned long snap;
int trycount = 0;
smp_mb(); /* Caller's modifications seen first by other CPUs. */
- snap = ACCESS_ONCE(sync_rcu_preempt_exp_count) + 1;
+ snap = READ_ONCE(sync_rcu_preempt_exp_count) + 1;
smp_mb(); /* Above access cannot bleed into critical section. */
/*
*/
while (!mutex_trylock(&sync_rcu_preempt_exp_mutex)) {
if (ULONG_CMP_LT(snap,
- ACCESS_ONCE(sync_rcu_preempt_exp_count))) {
+ READ_ONCE(sync_rcu_preempt_exp_count))) {
put_online_cpus();
goto mb_ret; /* Others did our work for us. */
}
return;
}
}
- if (ULONG_CMP_LT(snap, ACCESS_ONCE(sync_rcu_preempt_exp_count))) {
+ if (ULONG_CMP_LT(snap, READ_ONCE(sync_rcu_preempt_exp_count))) {
put_online_cpus();
goto unlock_mb_ret; /* Others did our work for us. */
}
/* Clean up and exit. */
smp_mb(); /* ensure expedited GP seen before counter increment. */
- ACCESS_ONCE(sync_rcu_preempt_exp_count) =
- sync_rcu_preempt_exp_count + 1;
+ WRITE_ONCE(sync_rcu_preempt_exp_count, sync_rcu_preempt_exp_count + 1);
unlock_mb_ret:
mutex_unlock(&sync_rcu_preempt_exp_mutex);
mb_ret:
*/
void rcu_barrier(void)
{
- _rcu_barrier(&rcu_preempt_state);
+ _rcu_barrier(rcu_state_p);
}
EXPORT_SYMBOL_GPL(rcu_barrier);
*/
static void __init __rcu_init_preempt(void)
{
- rcu_init_one(&rcu_preempt_state, &rcu_preempt_data);
+ rcu_init_one(rcu_state_p, rcu_data_p);
}
/*
#else /* #ifdef CONFIG_PREEMPT_RCU */
-static struct rcu_state *rcu_state_p = &rcu_sched_state;
+static struct rcu_state *const rcu_state_p = &rcu_sched_state;
+static struct rcu_data __percpu *const rcu_data_p = &rcu_sched_data;
/*
* Tell them what RCU they are running.
struct task_struct *t;
struct list_head *tb;
- if (ACCESS_ONCE(rnp->exp_tasks) == NULL &&
- ACCESS_ONCE(rnp->boost_tasks) == NULL)
+ if (READ_ONCE(rnp->exp_tasks) == NULL &&
+ READ_ONCE(rnp->boost_tasks) == NULL)
return 0; /* Nothing left to boost. */
raw_spin_lock_irqsave(&rnp->lock, flags);
rt_mutex_lock(&rnp->boost_mtx);
rt_mutex_unlock(&rnp->boost_mtx); /* Then keep lockdep happy. */
- return ACCESS_ONCE(rnp->exp_tasks) != NULL ||
- ACCESS_ONCE(rnp->boost_tasks) != NULL;
+ return READ_ONCE(rnp->exp_tasks) != NULL ||
+ READ_ONCE(rnp->boost_tasks) != NULL;
}
/*
struct sched_param sp;
struct task_struct *t;
- if (&rcu_preempt_state != rsp)
+ if (rcu_state_p != rsp)
return 0;
if (!rcu_scheduler_fully_active || rcu_rnp_online_cpus(rnp) == 0)
* Because we not have RCU_FAST_NO_HZ, just check whether this CPU needs
* any flavor of RCU.
*/
- int rcu_needs_cpu(unsigned long *delta_jiffies)
-#ifndef CONFIG_RCU_NOCB_CPU_ALL
+ int rcu_needs_cpu(u64 basemono, u64 *nextevt)
{
- *delta_jiffies = ULONG_MAX;
+ *nextevt = KTIME_MAX;
- return rcu_cpu_has_callbacks(NULL);
+ return IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL)
+ ? 0 : rcu_cpu_has_callbacks(NULL);
}
-#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
/*
* Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up
static int rcu_idle_lazy_gp_delay = RCU_IDLE_LAZY_GP_DELAY;
module_param(rcu_idle_lazy_gp_delay, int, 0644);
- extern int tick_nohz_active;
-
/*
* Try to advance callbacks for all flavors of RCU on the current CPU, but
* only if it has been awhile since the last time we did so. Afterwards,
* callbacks not yet ready to invoke.
*/
if ((rdp->completed != rnp->completed ||
- unlikely(ACCESS_ONCE(rdp->gpwrap))) &&
+ unlikely(READ_ONCE(rdp->gpwrap))) &&
rdp->nxttail[RCU_DONE_TAIL] != rdp->nxttail[RCU_NEXT_TAIL])
note_gp_changes(rsp, rdp);
*
* The caller must have disabled interrupts.
*/
- int rcu_needs_cpu(unsigned long *dj)
-#ifndef CONFIG_RCU_NOCB_CPU_ALL
+ int rcu_needs_cpu(u64 basemono, u64 *nextevt)
{
struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+ unsigned long dj;
- *dj = ULONG_MAX;
+ if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL)) {
++ *nextevt = KTIME_MAX;
+ return 0;
+ }
+
/* Snapshot to detect later posting of non-lazy callback. */
rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted;
/* If no callbacks, RCU doesn't need the CPU. */
if (!rcu_cpu_has_callbacks(&rdtp->all_lazy)) {
- *dj = ULONG_MAX;
+ *nextevt = KTIME_MAX;
return 0;
}
/* Request timer delay depending on laziness, and round. */
if (!rdtp->all_lazy) {
- *dj = round_up(rcu_idle_gp_delay + jiffies,
+ dj = round_up(rcu_idle_gp_delay + jiffies,
rcu_idle_gp_delay) - jiffies;
} else {
- *dj = round_jiffies(rcu_idle_lazy_gp_delay + jiffies) - jiffies;
+ dj = round_jiffies(rcu_idle_lazy_gp_delay + jiffies) - jiffies;
}
+ *nextevt = basemono + dj * TICK_NSEC;
return 0;
}
-#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
/*
* Prepare a CPU for idle from an RCU perspective. The first major task
*/
static void rcu_prepare_for_idle(void)
{
-#ifndef CONFIG_RCU_NOCB_CPU_ALL
bool needwake;
struct rcu_data *rdp;
struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
struct rcu_state *rsp;
int tne;
+ if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL))
+ return;
+
/* Handle nohz enablement switches conservatively. */
- tne = ACCESS_ONCE(tick_nohz_active);
+ tne = READ_ONCE(tick_nohz_active);
if (tne != rdtp->tick_nohz_enabled_snap) {
if (rcu_cpu_has_callbacks(NULL))
invoke_rcu_core(); /* force nohz to see update. */
if (needwake)
rcu_gp_kthread_wake(rsp);
}
-#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
}
/*
*/
static void rcu_cleanup_after_idle(void)
{
-#ifndef CONFIG_RCU_NOCB_CPU_ALL
- if (rcu_is_nocb_cpu(smp_processor_id()))
+ if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL) ||
+ rcu_is_nocb_cpu(smp_processor_id()))
return;
if (rcu_try_advance_all_cbs())
invoke_rcu_core();
-#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
}
/*
atomic_read(&rdtp->dynticks) & 0xfff,
rdtp->dynticks_nesting, rdtp->dynticks_nmi_nesting,
rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu),
- ACCESS_ONCE(rsp->n_force_qs) - rsp->n_force_qs_gpstart,
+ READ_ONCE(rsp->n_force_qs) - rsp->n_force_qs_gpstart,
fast_no_hz);
}
{
struct rcu_data *rdp_leader = rdp->nocb_leader;
- if (!ACCESS_ONCE(rdp_leader->nocb_kthread))
+ if (!READ_ONCE(rdp_leader->nocb_kthread))
return;
- if (ACCESS_ONCE(rdp_leader->nocb_leader_sleep) || force) {
+ if (READ_ONCE(rdp_leader->nocb_leader_sleep) || force) {
/* Prior smp_mb__after_atomic() orders against prior enqueue. */
- ACCESS_ONCE(rdp_leader->nocb_leader_sleep) = false;
+ WRITE_ONCE(rdp_leader->nocb_leader_sleep, false);
wake_up(&rdp_leader->nocb_wq);
}
}
ret = atomic_long_read(&rdp->nocb_q_count);
#ifdef CONFIG_PROVE_RCU
- rhp = ACCESS_ONCE(rdp->nocb_head);
+ rhp = READ_ONCE(rdp->nocb_head);
if (!rhp)
- rhp = ACCESS_ONCE(rdp->nocb_gp_head);
+ rhp = READ_ONCE(rdp->nocb_gp_head);
if (!rhp)
- rhp = ACCESS_ONCE(rdp->nocb_follower_head);
+ rhp = READ_ONCE(rdp->nocb_follower_head);
/* Having no rcuo kthread but CBs after scheduler starts is bad! */
- if (!ACCESS_ONCE(rdp->nocb_kthread) && rhp &&
+ if (!READ_ONCE(rdp->nocb_kthread) && rhp &&
rcu_scheduler_fully_active) {
/* RCU callback enqueued before CPU first came online??? */
pr_err("RCU: Never-onlined no-CBs CPU %d has CB %p\n",
atomic_long_add(rhcount, &rdp->nocb_q_count);
/* rcu_barrier() relies on ->nocb_q_count add before xchg. */
old_rhpp = xchg(&rdp->nocb_tail, rhtp);
- ACCESS_ONCE(*old_rhpp) = rhp;
+ WRITE_ONCE(*old_rhpp, rhp);
atomic_long_add(rhcount_lazy, &rdp->nocb_q_count_lazy);
smp_mb__after_atomic(); /* Store *old_rhpp before _wake test. */
/* If we are not being polled and there is a kthread, awaken it ... */
- t = ACCESS_ONCE(rdp->nocb_kthread);
+ t = READ_ONCE(rdp->nocb_kthread);
if (rcu_nocb_poll || !t) {
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
TPS("WakeNotPoll"));
for (;;) {
wait_event_interruptible(
rnp->nocb_gp_wq[c & 0x1],
- (d = ULONG_CMP_GE(ACCESS_ONCE(rnp->completed), c)));
+ (d = ULONG_CMP_GE(READ_ONCE(rnp->completed), c)));
if (likely(d))
break;
WARN_ON(signal_pending(current));
if (!rcu_nocb_poll) {
trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, "Sleep");
wait_event_interruptible(my_rdp->nocb_wq,
- !ACCESS_ONCE(my_rdp->nocb_leader_sleep));
+ !READ_ONCE(my_rdp->nocb_leader_sleep));
/* Memory barrier handled by smp_mb() calls below and repoll. */
} else if (firsttime) {
firsttime = false; /* Don't drown trace log with "Poll"! */
*/
gotcbs = false;
for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) {
- rdp->nocb_gp_head = ACCESS_ONCE(rdp->nocb_head);
+ rdp->nocb_gp_head = READ_ONCE(rdp->nocb_head);
if (!rdp->nocb_gp_head)
continue; /* No CBs here, try next follower. */
/* Move callbacks to wait-for-GP list, which is empty. */
- ACCESS_ONCE(rdp->nocb_head) = NULL;
+ WRITE_ONCE(rdp->nocb_head, NULL);
rdp->nocb_gp_tail = xchg(&rdp->nocb_tail, &rdp->nocb_head);
gotcbs = true;
}
my_rdp->nocb_leader_sleep = true;
smp_mb(); /* Ensure _sleep true before scan. */
for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower)
- if (ACCESS_ONCE(rdp->nocb_head)) {
+ if (READ_ONCE(rdp->nocb_head)) {
/* Found CB, so short-circuit next wait. */
my_rdp->nocb_leader_sleep = false;
break;
/* Each pass through the following loop wakes a follower, if needed. */
for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) {
- if (ACCESS_ONCE(rdp->nocb_head))
+ if (READ_ONCE(rdp->nocb_head))
my_rdp->nocb_leader_sleep = false;/* No need to sleep.*/
if (!rdp->nocb_gp_head)
continue; /* No CBs, so no need to wake follower. */
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
"FollowerSleep");
wait_event_interruptible(rdp->nocb_wq,
- ACCESS_ONCE(rdp->nocb_follower_head));
+ READ_ONCE(rdp->nocb_follower_head));
} else if (firsttime) {
/* Don't drown trace log with "Poll"! */
firsttime = false;
nocb_follower_wait(rdp);
/* Pull the ready-to-invoke callbacks onto local list. */
- list = ACCESS_ONCE(rdp->nocb_follower_head);
+ list = READ_ONCE(rdp->nocb_follower_head);
BUG_ON(!list);
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, "WokeNonEmpty");
- ACCESS_ONCE(rdp->nocb_follower_head) = NULL;
+ WRITE_ONCE(rdp->nocb_follower_head, NULL);
tail = xchg(&rdp->nocb_follower_tail, &rdp->nocb_follower_head);
/* Each pass through the following loop invokes a callback. */
/* Is a deferred wakeup of rcu_nocb_kthread() required? */
static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
{
- return ACCESS_ONCE(rdp->nocb_defer_wakeup);
+ return READ_ONCE(rdp->nocb_defer_wakeup);
}
/* Do a deferred wakeup of rcu_nocb_kthread(). */
if (!rcu_nocb_need_deferred_wakeup(rdp))
return;
- ndw = ACCESS_ONCE(rdp->nocb_defer_wakeup);
- ACCESS_ONCE(rdp->nocb_defer_wakeup) = RCU_NOGP_WAKE_NOT;
+ ndw = READ_ONCE(rdp->nocb_defer_wakeup);
+ WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOGP_WAKE_NOT);
wake_nocb_leader(rdp, ndw == RCU_NOGP_WAKE_FORCE);
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWake"));
}
t = kthread_run(rcu_nocb_kthread, rdp_spawn,
"rcuo%c/%d", rsp->abbr, cpu);
BUG_ON(IS_ERR(t));
- ACCESS_ONCE(rdp_spawn->nocb_kthread) = t;
+ WRITE_ONCE(rdp_spawn->nocb_kthread, t);
}
/*
/* Record start of fully idle period. */
j = jiffies;
- ACCESS_ONCE(rdtp->dynticks_idle_jiffies) = j;
+ WRITE_ONCE(rdtp->dynticks_idle_jiffies, j);
smp_mb__before_atomic();
atomic_inc(&rdtp->dynticks_idle);
smp_mb__after_atomic();
*/
void rcu_sysidle_force_exit(void)
{
- int oldstate = ACCESS_ONCE(full_sysidle_state);
+ int oldstate = READ_ONCE(full_sysidle_state);
int newoldstate;
/*
smp_mb(); /* Read counters before timestamps. */
/* Pick up timestamps. */
- j = ACCESS_ONCE(rdtp->dynticks_idle_jiffies);
+ j = READ_ONCE(rdtp->dynticks_idle_jiffies);
/* If this CPU entered idle more recently, update maxj timestamp. */
if (ULONG_CMP_LT(*maxj, j))
*maxj = j;
static void rcu_sysidle(unsigned long j)
{
/* Check the current state. */
- switch (ACCESS_ONCE(full_sysidle_state)) {
+ switch (READ_ONCE(full_sysidle_state)) {
case RCU_SYSIDLE_NOT:
/* First time all are idle, so note a short idle period. */
- ACCESS_ONCE(full_sysidle_state) = RCU_SYSIDLE_SHORT;
+ WRITE_ONCE(full_sysidle_state, RCU_SYSIDLE_SHORT);
break;
case RCU_SYSIDLE_SHORT:
{
smp_mb();
if (full_sysidle_state > RCU_SYSIDLE_SHORT)
- ACCESS_ONCE(full_sysidle_state) = RCU_SYSIDLE_NOT;
+ WRITE_ONCE(full_sysidle_state, RCU_SYSIDLE_NOT);
}
/*
smp_mb(); /* grace period precedes setting inuse. */
rshp = container_of(rhp, struct rcu_sysidle_head, rh);
- ACCESS_ONCE(rshp->inuse) = 0;
+ WRITE_ONCE(rshp->inuse, 0);
}
/*
bool rcu_sys_is_idle(void)
{
static struct rcu_sysidle_head rsh;
- int rss = ACCESS_ONCE(full_sysidle_state);
+ int rss = READ_ONCE(full_sysidle_state);
if (WARN_ON_ONCE(smp_processor_id() != tick_do_timer_cpu))
return false;
}
rcu_sysidle_report(rcu_state_p, isidle, maxj, false);
oldrss = rss;
- rss = ACCESS_ONCE(full_sysidle_state);
+ rss = READ_ONCE(full_sysidle_state);
}
}
#ifdef CONFIG_NO_HZ_FULL
if (tick_nohz_full_cpu(smp_processor_id()) &&
(!rcu_gp_in_progress(rsp) ||
- ULONG_CMP_LT(jiffies, ACCESS_ONCE(rsp->gp_start) + HZ)))
- return 1;
+ ULONG_CMP_LT(jiffies, READ_ONCE(rsp->gp_start) + HZ)))
+ return true;
#endif /* #ifdef CONFIG_NO_HZ_FULL */
- return 0;
+ return false;
}
/*
static void rcu_dynticks_task_enter(void)
{
#if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL)
- ACCESS_ONCE(current->rcu_tasks_idle_cpu) = smp_processor_id();
+ WRITE_ONCE(current->rcu_tasks_idle_cpu, smp_processor_id());
#endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */
}
static void rcu_dynticks_task_exit(void)
{
#if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL)
- ACCESS_ONCE(current->rcu_tasks_idle_cpu) = -1;
+ WRITE_ONCE(current->rcu_tasks_idle_cpu, -1);
#endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */
}
#define CREATE_TRACE_POINTS
#include <trace/events/sched.h>
- void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period)
- {
- unsigned long delta;
- ktime_t soft, hard, now;
-
- for (;;) {
- if (hrtimer_active(period_timer))
- break;
-
- now = hrtimer_cb_get_time(period_timer);
- hrtimer_forward(period_timer, now, period);
-
- soft = hrtimer_get_softexpires(period_timer);
- hard = hrtimer_get_expires(period_timer);
- delta = ktime_to_ns(ktime_sub(hard, soft));
- __hrtimer_start_range_ns(period_timer, soft, delta,
- HRTIMER_MODE_ABS_PINNED, 0);
- }
- }
-
DEFINE_MUTEX(sched_domains_mutex);
DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
#ifdef CONFIG_SMP
- static int __hrtick_restart(struct rq *rq)
+ static void __hrtick_restart(struct rq *rq)
{
struct hrtimer *timer = &rq->hrtick_timer;
- ktime_t time = hrtimer_get_softexpires(timer);
- return __hrtimer_start_range_ns(timer, time, 0, HRTIMER_MODE_ABS_PINNED, 0);
+ hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED);
}
/*
* doesn't make sense. Rely on vruntime for fairness.
*/
delay = max_t(u64, delay, 10000LL);
- __hrtimer_start_range_ns(&rq->hrtick_timer, ns_to_ktime(delay), 0,
- HRTIMER_MODE_REL_PINNED, 0);
+ hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay),
+ HRTIMER_MODE_REL_PINNED);
}
static inline void init_hrtick(void)
static bool set_nr_if_polling(struct task_struct *p)
{
struct thread_info *ti = task_thread_info(p);
- typeof(ti->flags) old, val = ACCESS_ONCE(ti->flags);
+ typeof(ti->flags) old, val = READ_ONCE(ti->flags);
for (;;) {
if (!(val & _TIF_POLLING_NRFLAG))
#endif
#endif
+void wake_q_add(struct wake_q_head *head, struct task_struct *task)
+{
+ struct wake_q_node *node = &task->wake_q;
+
+ /*
+ * Atomically grab the task, if ->wake_q is !nil already it means
+ * its already queued (either by us or someone else) and will get the
+ * wakeup due to that.
+ *
+ * This cmpxchg() implies a full barrier, which pairs with the write
+ * barrier implied by the wakeup in wake_up_list().
+ */
+ if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL))
+ return;
+
+ get_task_struct(task);
+
+ /*
+ * The head is context local, there can be no concurrency.
+ */
+ *head->lastp = node;
+ head->lastp = &node->next;
+}
+
+void wake_up_q(struct wake_q_head *head)
+{
+ struct wake_q_node *node = head->first;
+
+ while (node != WAKE_Q_TAIL) {
+ struct task_struct *task;
+
+ task = container_of(node, struct task_struct, wake_q);
+ BUG_ON(!task);
+ /* task can safely be re-inserted now */
+ node = node->next;
+ task->wake_q.next = NULL;
+
+ /*
+ * wake_up_process() implies a wmb() to pair with the queueing
+ * in wake_q_add() so as not to miss wakeups.
+ */
+ wake_up_process(task);
+ put_task_struct(task);
+ }
+}
+
/*
* resched_curr - mark rq's current task 'to be rescheduled now'.
*
* selecting an idle cpu will add more delays to the timers than intended
* (as that cpu's timer base may not be uptodate wrt jiffies etc).
*/
- int get_nohz_timer_target(int pinned)
+ int get_nohz_timer_target(void)
{
- int cpu = smp_processor_id();
- int i;
+ int i, cpu = smp_processor_id();
struct sched_domain *sd;
- if (pinned || !get_sysctl_timer_migration() || !idle_cpu(cpu))
+ if (!idle_cpu(cpu))
return cpu;
rcu_read_lock();
if (p->sched_class->migrate_task_rq)
p->sched_class->migrate_task_rq(p, new_cpu);
p->se.nr_migrations++;
- perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0);
+ perf_event_task_migrate(p);
}
__set_task_cpu(p, new_cpu);
#ifdef CONFIG_PREEMPT_NOTIFIERS
+static struct static_key preempt_notifier_key = STATIC_KEY_INIT_FALSE;
+
/**
* preempt_notifier_register - tell me when current is being preempted & rescheduled
* @notifier: notifier struct to register
*/
void preempt_notifier_register(struct preempt_notifier *notifier)
{
+ static_key_slow_inc(&preempt_notifier_key);
hlist_add_head(¬ifier->link, ¤t->preempt_notifiers);
}
EXPORT_SYMBOL_GPL(preempt_notifier_register);
* preempt_notifier_unregister - no longer interested in preemption notifications
* @notifier: notifier struct to unregister
*
- * This is safe to call from within a preemption notifier.
+ * This is *not* safe to call from within a preemption notifier.
*/
void preempt_notifier_unregister(struct preempt_notifier *notifier)
{
hlist_del(¬ifier->link);
+ static_key_slow_dec(&preempt_notifier_key);
}
EXPORT_SYMBOL_GPL(preempt_notifier_unregister);
-static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
+static void __fire_sched_in_preempt_notifiers(struct task_struct *curr)
{
struct preempt_notifier *notifier;
notifier->ops->sched_in(notifier, raw_smp_processor_id());
}
+static __always_inline void fire_sched_in_preempt_notifiers(struct task_struct *curr)
+{
+ if (static_key_false(&preempt_notifier_key))
+ __fire_sched_in_preempt_notifiers(curr);
+}
+
static void
-fire_sched_out_preempt_notifiers(struct task_struct *curr,
- struct task_struct *next)
+__fire_sched_out_preempt_notifiers(struct task_struct *curr,
+ struct task_struct *next)
{
struct preempt_notifier *notifier;
notifier->ops->sched_out(notifier, next);
}
+static __always_inline void
+fire_sched_out_preempt_notifiers(struct task_struct *curr,
+ struct task_struct *next)
+{
+ if (static_key_false(&preempt_notifier_key))
+ __fire_sched_out_preempt_notifiers(curr, next);
+}
+
#else /* !CONFIG_PREEMPT_NOTIFIERS */
-static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
+static inline void fire_sched_in_preempt_notifiers(struct task_struct *curr)
{
}
-static void
+static inline void
fire_sched_out_preempt_notifiers(struct task_struct *curr,
struct task_struct *next)
{
void get_iowait_load(unsigned long *nr_waiters, unsigned long *load)
{
- struct rq *this = this_rq();
- *nr_waiters = atomic_read(&this->nr_iowait);
- *load = this->cpu_load[0];
+ struct rq *rq = this_rq();
+ *nr_waiters = atomic_read(&rq->nr_iowait);
+ *load = rq->load.weight;
}
#ifdef CONFIG_SMP
update_rq_clock(rq);
curr->sched_class->task_tick(rq, curr, 0);
update_cpu_load_active(rq);
+ calc_global_load_tick(rq);
raw_spin_unlock(&rq->lock);
perf_event_task_tick();
u64 scheduler_tick_max_deferment(void)
{
struct rq *rq = this_rq();
- unsigned long next, now = ACCESS_ONCE(jiffies);
+ unsigned long next, now = READ_ONCE(jiffies);
next = rq->last_sched_tick + HZ;
* - return from syscall or exception to user-space
* - return from interrupt-handler to user-space
*
- * WARNING: all callers must re-check need_resched() afterward and reschedule
- * accordingly in case an event triggered the need for rescheduling (such as
- * an interrupt waking up a task) while preemption was disabled in __schedule().
+ * WARNING: must be called with preemption disabled!
*/
static void __sched __schedule(void)
{
struct rq *rq;
int cpu;
- preempt_disable();
cpu = smp_processor_id();
rq = cpu_rq(cpu);
rcu_note_context_switch();
raw_spin_unlock_irq(&rq->lock);
post_schedule(rq);
-
- sched_preempt_enable_no_resched();
}
static inline void sched_submit_work(struct task_struct *tsk)
sched_submit_work(tsk);
do {
+ preempt_disable();
__schedule();
+ sched_preempt_enable_no_resched();
} while (need_resched());
}
EXPORT_SYMBOL(schedule);
static void __sched notrace preempt_schedule_common(void)
{
do {
- __preempt_count_add(PREEMPT_ACTIVE);
+ preempt_active_enter();
__schedule();
- __preempt_count_sub(PREEMPT_ACTIVE);
+ preempt_active_exit();
/*
* Check again in case we missed a preemption opportunity
* between schedule and now.
*/
- barrier();
} while (need_resched());
}
NOKPROBE_SYMBOL(preempt_schedule);
EXPORT_SYMBOL(preempt_schedule);
-#ifdef CONFIG_CONTEXT_TRACKING
/**
- * preempt_schedule_context - preempt_schedule called by tracing
+ * preempt_schedule_notrace - preempt_schedule called by tracing
*
* The tracing infrastructure uses preempt_enable_notrace to prevent
* recursion and tracing preempt enabling caused by the tracing
* instead of preempt_schedule() to exit user context if needed before
* calling the scheduler.
*/
-asmlinkage __visible void __sched notrace preempt_schedule_context(void)
+asmlinkage __visible void __sched notrace preempt_schedule_notrace(void)
{
enum ctx_state prev_ctx;
return;
do {
- __preempt_count_add(PREEMPT_ACTIVE);
+ /*
+ * Use raw __prempt_count() ops that don't call function.
+ * We can't call functions before disabling preemption which
+ * disarm preemption tracing recursions.
+ */
+ __preempt_count_add(PREEMPT_ACTIVE + PREEMPT_DISABLE_OFFSET);
+ barrier();
/*
* Needs preempt disabled in case user_exit() is traced
* and the tracer calls preempt_enable_notrace() causing
__schedule();
exception_exit(prev_ctx);
- __preempt_count_sub(PREEMPT_ACTIVE);
barrier();
+ __preempt_count_sub(PREEMPT_ACTIVE + PREEMPT_DISABLE_OFFSET);
} while (need_resched());
}
-EXPORT_SYMBOL_GPL(preempt_schedule_context);
-#endif /* CONFIG_CONTEXT_TRACKING */
+EXPORT_SYMBOL_GPL(preempt_schedule_notrace);
#endif /* CONFIG_PREEMPT */
prev_state = exception_enter();
do {
- __preempt_count_add(PREEMPT_ACTIVE);
+ preempt_active_enter();
local_irq_enable();
__schedule();
local_irq_disable();
- __preempt_count_sub(PREEMPT_ACTIVE);
-
- /*
- * Check again in case we missed a preemption opportunity
- * between schedule and now.
- */
- barrier();
+ preempt_active_exit();
} while (need_resched());
exception_exit(prev_state);
if (!dl_prio(p->normal_prio) ||
(pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) {
p->dl.dl_boosted = 1;
- p->dl.dl_throttled = 0;
enqueue_flag = ENQUEUE_REPLENISH;
} else
p->dl.dl_boosted = 0;
long ret;
current->in_iowait = 1;
- if (old_iowait)
- blk_schedule_flush_plug(current);
- else
- blk_flush_plug(current);
+ blk_schedule_flush_plug(current);
delayacct_blkio_start();
rq = raw_rq();
.priority = CPU_PRI_MIGRATION,
};
-static void __cpuinit set_cpu_rq_start_time(void)
+static void set_cpu_rq_start_time(void)
{
int cpu = smp_processor_id();
struct rq *rq = cpu_rq(cpu);
}
#endif /* CONFIG_SMP */
- const_debug unsigned int sysctl_timer_migration = 1;
-
int in_sched_functions(unsigned long addr)
{
return in_lock_functions(addr) ||
return rt_runtime_us;
}
-static int sched_group_set_rt_period(struct task_group *tg, long rt_period_us)
+static int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us)
{
u64 rt_runtime, rt_period;
- rt_period = (u64)rt_period_us * NSEC_PER_USEC;
+ rt_period = rt_period_us * NSEC_PER_USEC;
rt_runtime = tg->rt_bandwidth.rt_runtime;
return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
__refill_cfs_bandwidth_runtime(cfs_b);
/* restart the period timer (if active) to handle new period expiry */
- if (runtime_enabled && cfs_b->timer_active) {
- /* force a reprogram */
- __start_cfs_bandwidth(cfs_b, true);
- }
+ if (runtime_enabled)
+ start_cfs_bandwidth(cfs_b);
raw_spin_unlock_irq(&cfs_b->lock);
for_each_online_cpu(i) {
struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
struct rq *rq = rq_of_dl_rq(dl_rq);
ktime_t now, act;
- ktime_t soft, hard;
- unsigned long range;
s64 delta;
if (boosted)
if (ktime_us_delta(act, now) < 0)
return 0;
- hrtimer_set_expires(&dl_se->dl_timer, act);
+ hrtimer_start(&dl_se->dl_timer, act, HRTIMER_MODE_ABS);
- soft = hrtimer_get_softexpires(&dl_se->dl_timer);
- hard = hrtimer_get_expires(&dl_se->dl_timer);
- range = ktime_to_ns(ktime_sub(hard, soft));
- __hrtimer_start_range_ns(&dl_se->dl_timer, soft,
- range, HRTIMER_MODE_ABS, 0);
-
- return hrtimer_active(&dl_se->dl_timer);
+ return 1;
}
/*
}
static
-int dl_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se)
+int dl_runtime_exceeded(struct sched_dl_entity *dl_se)
{
return (dl_se->runtime <= 0);
}
sched_rt_avg_update(rq, delta_exec);
dl_se->runtime -= dl_se->dl_yielded ? 0 : delta_exec;
- if (dl_runtime_exceeded(rq, dl_se)) {
+ if (dl_runtime_exceeded(dl_se)) {
dl_se->dl_throttled = 1;
__dequeue_task_dl(rq, curr, 0);
if (unlikely(!start_dl_timer(dl_se, curr->dl.dl_boosted)))
rq = cpu_rq(cpu);
rcu_read_lock();
- curr = ACCESS_ONCE(rq->curr); /* unlocked access */
+ curr = READ_ONCE(rq->curr); /* unlocked access */
/*
* If we are dealing with a -deadline task, we must
(p->nr_cpus_allowed > 1)) {
int target = find_later_rq(p);
- if (target != -1)
+ if (target != -1 &&
+ dl_time_before(p->dl.deadline,
+ cpu_rq(target)->dl.earliest_dl.curr))
cpu = target;
}
rcu_read_unlock();
return NULL;
}
+/*
+ * Return the earliest pushable rq's task, which is suitable to be executed
+ * on the CPU, NULL otherwise:
+ */
+static struct task_struct *pick_earliest_pushable_dl_task(struct rq *rq, int cpu)
+{
+ struct rb_node *next_node = rq->dl.pushable_dl_tasks_leftmost;
+ struct task_struct *p = NULL;
+
+ if (!has_pushable_dl_tasks(rq))
+ return NULL;
+
+next_node:
+ if (next_node) {
+ p = rb_entry(next_node, struct task_struct, pushable_dl_tasks);
+
+ if (pick_dl_task(rq, p, cpu))
+ return p;
+
+ next_node = rb_next(next_node);
+ goto next_node;
+ }
+
+ return NULL;
+}
+
static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask_dl);
static int find_later_rq(struct task_struct *task)
later_rq = cpu_rq(cpu);
+ if (!dl_time_before(task->dl.deadline,
+ later_rq->dl.earliest_dl.curr)) {
+ /*
+ * Target rq has tasks of equal or earlier deadline,
+ * retrying does not release any lock and is unlikely
+ * to yield a different result.
+ */
+ later_rq = NULL;
+ break;
+ }
+
/* Retry if something changed. */
if (double_lock_balance(rq, later_rq)) {
if (unlikely(task_rq(task) != rq ||
if (src_rq->dl.dl_nr_running <= 1)
goto skip;
- p = pick_next_earliest_dl_task(src_rq, this_cpu);
+ p = pick_earliest_pushable_dl_task(src_rq, this_cpu);
/*
* We found a task to be pulled if:
cpudl_clear_freecpu(&rq->rd->cpudl, rq->cpu);
}
-void init_sched_dl_class(void)
+void __init init_sched_dl_class(void)
{
unsigned int i;
p->prio);
#ifdef CONFIG_SCHEDSTATS
SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
- SPLIT_NS(p->se.vruntime),
+ SPLIT_NS(p->se.statistics.wait_sum),
SPLIT_NS(p->se.sum_exec_runtime),
SPLIT_NS(p->se.statistics.sum_sleep_runtime));
#else
- SEQ_printf(m, "%15Ld %15Ld %15Ld.%06ld %15Ld.%06ld %15Ld.%06ld",
- 0LL, 0LL, 0LL, 0L, 0LL, 0L, 0LL, 0L);
+ SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
+ 0LL, 0L,
+ SPLIT_NS(p->se.sum_exec_runtime),
+ 0LL, 0L);
#endif
#ifdef CONFIG_NUMA_BALANCING
SEQ_printf(m, " %d", task_node(p));
SEQ_printf(m,
"\nrunnable tasks:\n"
" task PID tree-key switches prio"
- " exec-runtime sum-exec sum-sleep\n"
+ " wait-time sum-exec sum-sleep\n"
"------------------------------------------------------"
"----------------------------------------------------\n");
#endif
#endif
#ifdef CONFIG_CFS_BANDWIDTH
- SEQ_printf(m, " .%-30s: %d\n", "tg->cfs_bandwidth.timer_active",
- cfs_rq->tg->cfs_bandwidth.timer_active);
SEQ_printf(m, " .%-30s: %d\n", "throttled",
cfs_rq->throttled);
SEQ_printf(m, " .%-30s: %d\n", "throttle_count",
nr_switches = p->nvcsw + p->nivcsw;
#ifdef CONFIG_SCHEDSTATS
+ PN(se.statistics.sum_sleep_runtime);
PN(se.statistics.wait_start);
PN(se.statistics.sleep_start);
PN(se.statistics.block_start);
*
* This idea comes from the SD scheduler of Con Kolivas:
*/
-static int get_update_sysctl_factor(void)
+static unsigned int get_update_sysctl_factor(void)
{
- unsigned int cpus = min_t(int, num_online_cpus(), 8);
+ unsigned int cpus = min_t(unsigned int, num_online_cpus(), 8);
unsigned int factor;
switch (sysctl_sched_tunable_scaling) {
loff_t *ppos)
{
int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
- int factor = get_update_sysctl_factor();
+ unsigned int factor = get_update_sysctl_factor();
if (ret || !write)
return ret;
static unsigned int task_scan_min(struct task_struct *p)
{
- unsigned int scan_size = ACCESS_ONCE(sysctl_numa_balancing_scan_size);
+ unsigned int scan_size = READ_ONCE(sysctl_numa_balancing_scan_size);
unsigned int scan, floor;
unsigned int windows = 1;
static bool load_too_imbalanced(long src_load, long dst_load,
struct task_numa_env *env)
{
+ long imb, old_imb;
+ long orig_src_load, orig_dst_load;
long src_capacity, dst_capacity;
- long orig_src_load;
- long load_a, load_b;
- long moved_load;
- long imb;
/*
* The load is corrected for the CPU capacity available on each node.
dst_capacity = env->dst_stats.compute_capacity;
/* We care about the slope of the imbalance, not the direction. */
- load_a = dst_load;
- load_b = src_load;
- if (load_a < load_b)
- swap(load_a, load_b);
+ if (dst_load < src_load)
+ swap(dst_load, src_load);
/* Is the difference below the threshold? */
- imb = load_a * src_capacity * 100 -
- load_b * dst_capacity * env->imbalance_pct;
+ imb = dst_load * src_capacity * 100 -
+ src_load * dst_capacity * env->imbalance_pct;
if (imb <= 0)
return false;
/*
* The imbalance is above the allowed threshold.
- * Allow a move that brings us closer to a balanced situation,
- * without moving things past the point of balance.
+ * Compare it with the old imbalance.
*/
orig_src_load = env->src_stats.load;
+ orig_dst_load = env->dst_stats.load;
- /*
- * In a task swap, there will be one load moving from src to dst,
- * and another moving back. This is the net sum of both moves.
- * A simple task move will always have a positive value.
- * Allow the move if it brings the system closer to a balanced
- * situation, without crossing over the balance point.
- */
- moved_load = orig_src_load - src_load;
+ if (orig_dst_load < orig_src_load)
+ swap(orig_dst_load, orig_src_load);
- if (moved_load > 0)
- /* Moving src -> dst. Did we overshoot balance? */
- return src_load * dst_capacity < dst_load * src_capacity;
- else
- /* Moving dst -> src. Did we overshoot balance? */
- return dst_load * src_capacity < src_load * dst_capacity;
+ old_imb = orig_dst_load * src_capacity * 100 -
+ orig_src_load * dst_capacity * env->imbalance_pct;
+
+ /* Would this change make things worse? */
+ return (imb > old_imb);
}
/*
}
}
+/* Only move tasks to a NUMA node less busy than the current node. */
+static bool numa_has_capacity(struct task_numa_env *env)
+{
+ struct numa_stats *src = &env->src_stats;
+ struct numa_stats *dst = &env->dst_stats;
+
+ if (src->has_free_capacity && !dst->has_free_capacity)
+ return false;
+
+ /*
+ * Only consider a task move if the source has a higher load
+ * than the destination, corrected for CPU capacity on each node.
+ *
+ * src->load dst->load
+ * --------------------- vs ---------------------
+ * src->compute_capacity dst->compute_capacity
+ */
+ if (src->load * dst->compute_capacity >
+ dst->load * src->compute_capacity)
+ return true;
+
+ return false;
+}
+
static int task_numa_migrate(struct task_struct *p)
{
struct task_numa_env env = {
update_numa_stats(&env.dst_stats, env.dst_nid);
/* Try to find a spot on the preferred nid. */
- task_numa_find_cpu(&env, taskimp, groupimp);
+ if (numa_has_capacity(&env))
+ task_numa_find_cpu(&env, taskimp, groupimp);
/*
* Look at other nodes in these cases:
env.dist = dist;
env.dst_nid = nid;
update_numa_stats(&env.dst_stats, env.dst_nid);
- task_numa_find_cpu(&env, taskimp, groupimp);
+ if (numa_has_capacity(&env))
+ task_numa_find_cpu(&env, taskimp, groupimp);
}
}
u64 runtime, period;
spinlock_t *group_lock = NULL;
- seq = ACCESS_ONCE(p->mm->numa_scan_seq);
+ /*
+ * The p->mm->numa_scan_seq field gets updated without
+ * exclusive access. Use READ_ONCE() here to ensure
+ * that the field is read in a single access:
+ */
+ seq = READ_ONCE(p->mm->numa_scan_seq);
if (p->numa_scan_seq == seq)
return;
p->numa_scan_seq = seq;
}
rcu_read_lock();
- tsk = ACCESS_ONCE(cpu_rq(cpu)->curr);
+ tsk = READ_ONCE(cpu_rq(cpu)->curr);
if (!cpupid_match_pid(tsk, cpupid))
goto no_join;
static void reset_ptenuma_scan(struct task_struct *p)
{
- ACCESS_ONCE(p->mm->numa_scan_seq)++;
+ /*
+ * We only did a read acquisition of the mmap sem, so
+ * p->mm->numa_scan_seq is written to without exclusive access
+ * and the update is not guaranteed to be atomic. That's not
+ * much of an issue though, since this is just used for
+ * statistical sampling. Use READ_ONCE/WRITE_ONCE, which are not
+ * expensive, to avoid any form of compiler optimizations:
+ */
+ WRITE_ONCE(p->mm->numa_scan_seq, READ_ONCE(p->mm->numa_scan_seq) + 1);
p->mm->numa_scan_offset = 0;
}
}
for (; vma; vma = vma->vm_next) {
if (!vma_migratable(vma) || !vma_policy_mof(vma) ||
- is_vm_hugetlb_page(vma)) {
+ is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_MIXEDMAP)) {
continue;
}
if (cfs_b->quota == RUNTIME_INF)
amount = min_amount;
else {
- /*
- * If the bandwidth pool has become inactive, then at least one
- * period must have elapsed since the last consumption.
- * Refresh the global state and ensure bandwidth timer becomes
- * active.
- */
- if (!cfs_b->timer_active) {
- __refill_cfs_bandwidth_runtime(cfs_b);
- __start_cfs_bandwidth(cfs_b, false);
- }
+ start_cfs_bandwidth(cfs_b);
if (cfs_b->runtime > 0) {
amount = min(cfs_b->runtime, min_amount);
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
struct sched_entity *se;
long task_delta, dequeue = 1;
+ bool empty;
se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))];
cfs_rq->throttled = 1;
cfs_rq->throttled_clock = rq_clock(rq);
raw_spin_lock(&cfs_b->lock);
+ empty = list_empty(&cfs_rq->throttled_list);
+
/*
* Add to the _head_ of the list, so that an already-started
* distribute_cfs_runtime will not see us
*/
list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
- if (!cfs_b->timer_active)
- __start_cfs_bandwidth(cfs_b, false);
+
+ /*
+ * If we're the first throttled task, make sure the bandwidth
+ * timer is running.
+ */
+ if (empty)
+ start_cfs_bandwidth(cfs_b);
+
raw_spin_unlock(&cfs_b->lock);
}
if (cfs_b->idle && !throttled)
goto out_deactivate;
- /*
- * if we have relooped after returning idle once, we need to update our
- * status as actually running, so that other cpus doing
- * __start_cfs_bandwidth will stop trying to cancel us.
- */
- cfs_b->timer_active = 1;
-
__refill_cfs_bandwidth_runtime(cfs_b);
if (!throttled) {
return 0;
out_deactivate:
- cfs_b->timer_active = 0;
return 1;
}
* Are we near the end of the current quota period?
*
* Requires cfs_b->lock for hrtimer_expires_remaining to be safe against the
- * hrtimer base being cleared by __hrtimer_start_range_ns. In the case of
+ * hrtimer base being cleared by hrtimer_start. In the case of
* migrate_hrtimers, base is never cleared, so we are fine.
*/
static int runtime_refresh_within(struct cfs_bandwidth *cfs_b, u64 min_expire)
if (runtime_refresh_within(cfs_b, min_left))
return;
- start_bandwidth_timer(&cfs_b->slack_timer,
- ns_to_ktime(cfs_bandwidth_slack_period));
+ hrtimer_start(&cfs_b->slack_timer,
+ ns_to_ktime(cfs_bandwidth_slack_period),
+ HRTIMER_MODE_REL);
}
/* we know any runtime found here is valid as update_curr() precedes return */
{
struct cfs_bandwidth *cfs_b =
container_of(timer, struct cfs_bandwidth, slack_timer);
+
do_sched_cfs_slack_timer(cfs_b);
return HRTIMER_NORESTART;
{
struct cfs_bandwidth *cfs_b =
container_of(timer, struct cfs_bandwidth, period_timer);
- ktime_t now;
int overrun;
int idle = 0;
raw_spin_lock(&cfs_b->lock);
for (;;) {
- now = hrtimer_cb_get_time(timer);
- overrun = hrtimer_forward(timer, now, cfs_b->period);
-
+ overrun = hrtimer_forward_now(timer, cfs_b->period);
if (!overrun)
break;
idle = do_sched_cfs_period_timer(cfs_b, overrun);
}
+ if (idle)
+ cfs_b->period_active = 0;
raw_spin_unlock(&cfs_b->lock);
return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
cfs_b->period = ns_to_ktime(default_cfs_period());
INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq);
- hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
cfs_b->period_timer.function = sched_cfs_period_timer;
hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
cfs_b->slack_timer.function = sched_cfs_slack_timer;
INIT_LIST_HEAD(&cfs_rq->throttled_list);
}
- /* requires cfs_b->lock, may release to reprogram timer */
- void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b, bool force)
+ void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
{
- /*
- * The timer may be active because we're trying to set a new bandwidth
- * period or because we're racing with the tear-down path
- * (timer_active==0 becomes visible before the hrtimer call-back
- * terminates). In either case we ensure that it's re-programmed
- */
- while (unlikely(hrtimer_active(&cfs_b->period_timer)) &&
- hrtimer_try_to_cancel(&cfs_b->period_timer) < 0) {
- /* bounce the lock to allow do_sched_cfs_period_timer to run */
- raw_spin_unlock(&cfs_b->lock);
- cpu_relax();
- raw_spin_lock(&cfs_b->lock);
- /* if someone else restarted the timer then we're done */
- if (!force && cfs_b->timer_active)
- return;
- }
+ lockdep_assert_held(&cfs_b->lock);
- cfs_b->timer_active = 1;
- start_bandwidth_timer(&cfs_b->period_timer, cfs_b->period);
+ if (!cfs_b->period_active) {
+ cfs_b->period_active = 1;
+ hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period);
+ hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED);
+ }
}
static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
}
#ifdef CONFIG_SMP
+
+/*
+ * per rq 'load' arrray crap; XXX kill this.
+ */
+
+/*
+ * The exact cpuload at various idx values, calculated at every tick would be
+ * load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load
+ *
+ * If a cpu misses updates for n-1 ticks (as it was idle) and update gets called
+ * on nth tick when cpu may be busy, then we have:
+ * load = ((2^idx - 1) / 2^idx)^(n-1) * load
+ * load = (2^idx - 1) / 2^idx) * load + 1 / 2^idx * cur_load
+ *
+ * decay_load_missed() below does efficient calculation of
+ * load = ((2^idx - 1) / 2^idx)^(n-1) * load
+ * avoiding 0..n-1 loop doing load = ((2^idx - 1) / 2^idx) * load
+ *
+ * The calculation is approximated on a 128 point scale.
+ * degrade_zero_ticks is the number of ticks after which load at any
+ * particular idx is approximated to be zero.
+ * degrade_factor is a precomputed table, a row for each load idx.
+ * Each column corresponds to degradation factor for a power of two ticks,
+ * based on 128 point scale.
+ * Example:
+ * row 2, col 3 (=12) says that the degradation at load idx 2 after
+ * 8 ticks is 12/128 (which is an approximation of exact factor 3^8/4^8).
+ *
+ * With this power of 2 load factors, we can degrade the load n times
+ * by looking at 1 bits in n and doing as many mult/shift instead of
+ * n mult/shifts needed by the exact degradation.
+ */
+#define DEGRADE_SHIFT 7
+static const unsigned char
+ degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128};
+static const unsigned char
+ degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = {
+ {0, 0, 0, 0, 0, 0, 0, 0},
+ {64, 32, 8, 0, 0, 0, 0, 0},
+ {96, 72, 40, 12, 1, 0, 0},
+ {112, 98, 75, 43, 15, 1, 0},
+ {120, 112, 98, 76, 45, 16, 2} };
+
+/*
+ * Update cpu_load for any missed ticks, due to tickless idle. The backlog
+ * would be when CPU is idle and so we just decay the old load without
+ * adding any new load.
+ */
+static unsigned long
+decay_load_missed(unsigned long load, unsigned long missed_updates, int idx)
+{
+ int j = 0;
+
+ if (!missed_updates)
+ return load;
+
+ if (missed_updates >= degrade_zero_ticks[idx])
+ return 0;
+
+ if (idx == 1)
+ return load >> missed_updates;
+
+ while (missed_updates) {
+ if (missed_updates % 2)
+ load = (load * degrade_factor[idx][j]) >> DEGRADE_SHIFT;
+
+ missed_updates >>= 1;
+ j++;
+ }
+ return load;
+}
+
+/*
+ * Update rq->cpu_load[] statistics. This function is usually called every
+ * scheduler tick (TICK_NSEC). With tickless idle this will not be called
+ * every tick. We fix it up based on jiffies.
+ */
+static void __update_cpu_load(struct rq *this_rq, unsigned long this_load,
+ unsigned long pending_updates)
+{
+ int i, scale;
+
+ this_rq->nr_load_updates++;
+
+ /* Update our load: */
+ this_rq->cpu_load[0] = this_load; /* Fasttrack for idx 0 */
+ for (i = 1, scale = 2; i < CPU_LOAD_IDX_MAX; i++, scale += scale) {
+ unsigned long old_load, new_load;
+
+ /* scale is effectively 1 << i now, and >> i divides by scale */
+
+ old_load = this_rq->cpu_load[i];
+ old_load = decay_load_missed(old_load, pending_updates - 1, i);
+ new_load = this_load;
+ /*
+ * Round up the averaging division if load is increasing. This
+ * prevents us from getting stuck on 9 if the load is 10, for
+ * example.
+ */
+ if (new_load > old_load)
+ new_load += scale - 1;
+
+ this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i;
+ }
+
+ sched_avg_update(this_rq);
+}
+
+#ifdef CONFIG_NO_HZ_COMMON
+/*
+ * There is no sane way to deal with nohz on smp when using jiffies because the
+ * cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading
+ * causing off-by-one errors in observed deltas; {0,2} instead of {1,1}.
+ *
+ * Therefore we cannot use the delta approach from the regular tick since that
+ * would seriously skew the load calculation. However we'll make do for those
+ * updates happening while idle (nohz_idle_balance) or coming out of idle
+ * (tick_nohz_idle_exit).
+ *
+ * This means we might still be one tick off for nohz periods.
+ */
+
+/*
+ * Called from nohz_idle_balance() to update the load ratings before doing the
+ * idle balance.
+ */
+static void update_idle_cpu_load(struct rq *this_rq)
+{
+ unsigned long curr_jiffies = READ_ONCE(jiffies);
+ unsigned long load = this_rq->cfs.runnable_load_avg;
+ unsigned long pending_updates;
+
+ /*
+ * bail if there's load or we're actually up-to-date.
+ */
+ if (load || curr_jiffies == this_rq->last_load_update_tick)
+ return;
+
+ pending_updates = curr_jiffies - this_rq->last_load_update_tick;
+ this_rq->last_load_update_tick = curr_jiffies;
+
+ __update_cpu_load(this_rq, load, pending_updates);
+}
+
+/*
+ * Called from tick_nohz_idle_exit() -- try and fix up the ticks we missed.
+ */
+void update_cpu_load_nohz(void)
+{
+ struct rq *this_rq = this_rq();
+ unsigned long curr_jiffies = READ_ONCE(jiffies);
+ unsigned long pending_updates;
+
+ if (curr_jiffies == this_rq->last_load_update_tick)
+ return;
+
+ raw_spin_lock(&this_rq->lock);
+ pending_updates = curr_jiffies - this_rq->last_load_update_tick;
+ if (pending_updates) {
+ this_rq->last_load_update_tick = curr_jiffies;
+ /*
+ * We were idle, this means load 0, the current load might be
+ * !0 due to remote wakeups and the sort.
+ */
+ __update_cpu_load(this_rq, 0, pending_updates);
+ }
+ raw_spin_unlock(&this_rq->lock);
+}
+#endif /* CONFIG_NO_HZ */
+
+/*
+ * Called from scheduler_tick()
+ */
+void update_cpu_load_active(struct rq *this_rq)
+{
+ unsigned long load = this_rq->cfs.runnable_load_avg;
+ /*
+ * See the mess around update_idle_cpu_load() / update_cpu_load_nohz().
+ */
+ this_rq->last_load_update_tick = jiffies;
+ __update_cpu_load(this_rq, load, 1);
+}
+
/* Used instead of source_load when we know the type == 0 */
static unsigned long weighted_cpuload(const int cpu)
{
static unsigned long cpu_avg_load_per_task(int cpu)
{
struct rq *rq = cpu_rq(cpu);
- unsigned long nr_running = ACCESS_ONCE(rq->cfs.h_nr_running);
+ unsigned long nr_running = READ_ONCE(rq->cfs.h_nr_running);
unsigned long load_avg = rq->cfs.runnable_load_avg;
if (nr_running)
* entity, update_curr() will update its vruntime, otherwise
* forget we've ever seen it.
*/
- if (curr && curr->on_rq)
- update_curr(cfs_rq);
- else
- curr = NULL;
+ if (curr) {
+ if (curr->on_rq)
+ update_curr(cfs_rq);
+ else
+ curr = NULL;
- /*
- * This call to check_cfs_rq_runtime() will do the throttle and
- * dequeue its entity in the parent(s). Therefore the 'simple'
- * nr_running test will indeed be correct.
- */
- if (unlikely(check_cfs_rq_runtime(cfs_rq)))
- goto simple;
+ /*
+ * This call to check_cfs_rq_runtime() will do the
+ * throttle and dequeue its entity in the parent(s).
+ * Therefore the 'simple' nr_running test will indeed
+ * be correct.
+ */
+ if (unlikely(check_cfs_rq_runtime(cfs_rq)))
+ goto simple;
+ }
se = pick_next_entity(cfs_rq, curr);
cfs_rq = group_cfs_rq(se);
}
#ifdef CONFIG_NUMA_BALANCING
-/* Returns true if the destination node has incurred more faults */
+/*
+ * Returns true if the destination node is the preferred node.
+ * Needs to match fbq_classify_rq(): if there is a runnable task
+ * that is not on its preferred node, we should identify it.
+ */
static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env)
{
struct numa_group *numa_group = rcu_dereference(p->numa_group);
+ unsigned long src_faults, dst_faults;
int src_nid, dst_nid;
if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults ||
if (src_nid == dst_nid)
return false;
- if (numa_group) {
- /* Task is already in the group's interleave set. */
- if (node_isset(src_nid, numa_group->active_nodes))
- return false;
-
- /* Task is moving into the group's interleave set. */
- if (node_isset(dst_nid, numa_group->active_nodes))
- return true;
-
- return group_faults(p, dst_nid) > group_faults(p, src_nid);
- }
-
/* Encourage migration to the preferred node. */
if (dst_nid == p->numa_preferred_nid)
return true;
- return task_faults(p, dst_nid) > task_faults(p, src_nid);
+ /* Migrating away from the preferred node is bad. */
+ if (src_nid == p->numa_preferred_nid)
+ return false;
+
+ if (numa_group) {
+ src_faults = group_faults(p, src_nid);
+ dst_faults = group_faults(p, dst_nid);
+ } else {
+ src_faults = task_faults(p, src_nid);
+ dst_faults = task_faults(p, dst_nid);
+ }
+
+ return dst_faults > src_faults;
}
static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
{
struct numa_group *numa_group = rcu_dereference(p->numa_group);
+ unsigned long src_faults, dst_faults;
int src_nid, dst_nid;
if (!sched_feat(NUMA) || !sched_feat(NUMA_RESIST_LOWER))
if (src_nid == dst_nid)
return false;
- if (numa_group) {
- /* Task is moving within/into the group's interleave set. */
- if (node_isset(dst_nid, numa_group->active_nodes))
- return false;
+ /* Migrating away from the preferred node is bad. */
+ if (src_nid == p->numa_preferred_nid)
+ return true;
- /* Task is moving out of the group's interleave set. */
- if (node_isset(src_nid, numa_group->active_nodes))
- return true;
+ /* Encourage migration to the preferred node. */
+ if (dst_nid == p->numa_preferred_nid)
+ return false;
- return group_faults(p, dst_nid) < group_faults(p, src_nid);
+ if (numa_group) {
+ src_faults = group_faults(p, src_nid);
+ dst_faults = group_faults(p, dst_nid);
+ } else {
+ src_faults = task_faults(p, src_nid);
+ dst_faults = task_faults(p, dst_nid);
}
- /* Migrating away from the preferred node is always bad. */
- if (src_nid == p->numa_preferred_nid)
- return true;
-
- return task_faults(p, dst_nid) < task_faults(p, src_nid);
+ return dst_faults < src_faults;
}
#else
* Since we're reading these variables without serialization make sure
* we read them once before doing sanity checks on them.
*/
- age_stamp = ACCESS_ONCE(rq->age_stamp);
- avg = ACCESS_ONCE(rq->rt_avg);
+ age_stamp = READ_ONCE(rq->age_stamp);
+ avg = READ_ONCE(rq->rt_avg);
delta = __rq_clock_broken(rq) - age_stamp;
if (unlikely(delta < 0))
{
struct rt_bandwidth *rt_b =
container_of(timer, struct rt_bandwidth, rt_period_timer);
- ktime_t now;
- int overrun;
int idle = 0;
+ int overrun;
+ raw_spin_lock(&rt_b->rt_runtime_lock);
for (;;) {
- now = hrtimer_cb_get_time(timer);
- overrun = hrtimer_forward(timer, now, rt_b->rt_period);
-
+ overrun = hrtimer_forward_now(timer, rt_b->rt_period);
if (!overrun)
break;
+ raw_spin_unlock(&rt_b->rt_runtime_lock);
idle = do_sched_rt_period_timer(rt_b, overrun);
+ raw_spin_lock(&rt_b->rt_runtime_lock);
}
+ if (idle)
+ rt_b->rt_period_active = 0;
+ raw_spin_unlock(&rt_b->rt_runtime_lock);
return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
}
if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
return;
- if (hrtimer_active(&rt_b->rt_period_timer))
- return;
-
raw_spin_lock(&rt_b->rt_runtime_lock);
- start_bandwidth_timer(&rt_b->rt_period_timer, rt_b->rt_period);
+ if (!rt_b->rt_period_active) {
+ rt_b->rt_period_active = 1;
+ hrtimer_forward_now(&rt_b->rt_period_timer, rt_b->rt_period);
+ hrtimer_start_expires(&rt_b->rt_period_timer, HRTIMER_MODE_ABS_PINNED);
+ }
raw_spin_unlock(&rt_b->rt_runtime_lock);
}
rq = cpu_rq(cpu);
rcu_read_lock();
- curr = ACCESS_ONCE(rq->curr); /* unlocked access */
+ curr = READ_ONCE(rq->curr); /* unlocked access */
/*
* If the current task on @p's runqueue is an RT task, then
extern unsigned long calc_load_update;
extern atomic_long_t calc_load_tasks;
+extern void calc_global_load_tick(struct rq *this_rq);
extern long calc_load_fold_active(struct rq *this_rq);
+
+#ifdef CONFIG_SMP
extern void update_cpu_load_active(struct rq *this_rq);
+#else
+static inline void update_cpu_load_active(struct rq *this_rq) { }
+#endif
/*
* Helpers for converting nanosecond timing to jiffy resolution
ktime_t rt_period;
u64 rt_runtime;
struct hrtimer rt_period_timer;
+ unsigned int rt_period_active;
};
void __dl_clear_params(struct task_struct *p);
s64 hierarchical_quota;
u64 runtime_expires;
- int idle, timer_active;
+ int idle, period_active;
struct hrtimer period_timer, slack_timer;
struct list_head throttled_cfs_rq;
extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b);
- extern void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b, bool force);
+ extern void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
extern void unthrottle_cfs_rq(struct cfs_rq *cfs_rq);
extern void free_rt_sched_group(struct task_group *tg);
static inline u64 __rq_clock_broken(struct rq *rq)
{
- return ACCESS_ONCE(rq->clock);
+ return READ_ONCE(rq->clock);
}
static inline u64 rq_clock(struct rq *rq)
extern void init_sched_dl_class(void);
extern void init_sched_rt_class(void);
extern void init_sched_fair_class(void);
-extern void init_sched_dl_class(void);
extern void resched_curr(struct rq *rq);
extern void resched_cpu(int cpu);
unsigned long to_ratio(u64 period, u64 runtime);
-extern void update_idle_cpu_load(struct rq *this_rq);
-
extern void init_task_runnable_average(struct task_struct *p);
static inline void add_nr_running(struct rq *rq, unsigned count)
static inline void sched_avg_update(struct rq *rq) { }
#endif
- extern void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period);
-
/*
* __task_rq_lock - lock the rq @p resides on.
*/
*/
DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
{
-
.lock = __RAW_SPIN_LOCK_UNLOCKED(hrtimer_bases.lock),
+ .seq = SEQCNT_ZERO(hrtimer_bases.seq),
.clock_base =
{
{
.index = HRTIMER_BASE_MONOTONIC,
.clockid = CLOCK_MONOTONIC,
.get_time = &ktime_get,
- .resolution = KTIME_LOW_RES,
},
{
.index = HRTIMER_BASE_REALTIME,
.clockid = CLOCK_REALTIME,
.get_time = &ktime_get_real,
- .resolution = KTIME_LOW_RES,
},
{
.index = HRTIMER_BASE_BOOTTIME,
.clockid = CLOCK_BOOTTIME,
.get_time = &ktime_get_boottime,
- .resolution = KTIME_LOW_RES,
},
{
.index = HRTIMER_BASE_TAI,
.clockid = CLOCK_TAI,
.get_time = &ktime_get_clocktai,
- .resolution = KTIME_LOW_RES,
},
}
};
return hrtimer_clock_to_base_table[clock_id];
}
-
- /*
- * Get the coarse grained time at the softirq based on xtime and
- * wall_to_monotonic.
- */
- static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
- {
- ktime_t xtim, mono, boot, tai;
- ktime_t off_real, off_boot, off_tai;
-
- mono = ktime_get_update_offsets_tick(&off_real, &off_boot, &off_tai);
- boot = ktime_add(mono, off_boot);
- xtim = ktime_add(mono, off_real);
- tai = ktime_add(mono, off_tai);
-
- base->clock_base[HRTIMER_BASE_REALTIME].softirq_time = xtim;
- base->clock_base[HRTIMER_BASE_MONOTONIC].softirq_time = mono;
- base->clock_base[HRTIMER_BASE_BOOTTIME].softirq_time = boot;
- base->clock_base[HRTIMER_BASE_TAI].softirq_time = tai;
- }
-
/*
* Functions and macros which are different for UP/SMP systems are kept in a
* single place
*/
#ifdef CONFIG_SMP
+ /*
+ * We require the migration_base for lock_hrtimer_base()/switch_hrtimer_base()
+ * such that hrtimer_callback_running() can unconditionally dereference
+ * timer->base->cpu_base
+ */
+ static struct hrtimer_cpu_base migration_cpu_base = {
+ .seq = SEQCNT_ZERO(migration_cpu_base),
+ .clock_base = { { .cpu_base = &migration_cpu_base, }, },
+ };
+
+ #define migration_base migration_cpu_base.clock_base[0]
+
/*
* We are using hashed locking: holding per_cpu(hrtimer_bases)[n].lock
* means that all timers which are tied to this base via timer->base are
* be found on the lists/queues.
*
* When the timer's base is locked, and the timer removed from list, it is
- * possible to set timer->base = NULL and drop the lock: the timer remains
- * locked.
+ * possible to set timer->base = &migration_base and drop the lock: the timer
+ * remains locked.
*/
static
struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
for (;;) {
base = timer->base;
- if (likely(base != NULL)) {
+ if (likely(base != &migration_base)) {
raw_spin_lock_irqsave(&base->cpu_base->lock, *flags);
if (likely(base == timer->base))
return base;
#endif
}
+ #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+ static inline
+ struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base,
+ int pinned)
+ {
+ if (pinned || !base->migration_enabled)
+ return this_cpu_ptr(&hrtimer_bases);
+ return &per_cpu(hrtimer_bases, get_nohz_timer_target());
+ }
+ #else
+ static inline
+ struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base,
+ int pinned)
+ {
+ return this_cpu_ptr(&hrtimer_bases);
+ }
+ #endif
+
/*
* Switch the timer base to the current CPU when possible.
*/
switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base,
int pinned)
{
+ struct hrtimer_cpu_base *new_cpu_base, *this_base;
struct hrtimer_clock_base *new_base;
- struct hrtimer_cpu_base *new_cpu_base;
- int this_cpu = smp_processor_id();
- int cpu = get_nohz_timer_target(pinned);
int basenum = base->index;
+ this_base = this_cpu_ptr(&hrtimer_bases);
+ new_cpu_base = get_target_base(this_base, pinned);
again:
- new_cpu_base = &per_cpu(hrtimer_bases, cpu);
new_base = &new_cpu_base->clock_base[basenum];
if (base != new_base) {
if (unlikely(hrtimer_callback_running(timer)))
return base;
- /* See the comment in lock_timer_base() */
- timer->base = NULL;
+ /* See the comment in lock_hrtimer_base() */
+ timer->base = &migration_base;
raw_spin_unlock(&base->cpu_base->lock);
raw_spin_lock(&new_base->cpu_base->lock);
- if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) {
- cpu = this_cpu;
+ if (new_cpu_base != this_base &&
+ hrtimer_check_target(timer, new_base)) {
raw_spin_unlock(&new_base->cpu_base->lock);
raw_spin_lock(&base->cpu_base->lock);
+ new_cpu_base = this_base;
timer->base = base;
goto again;
}
timer->base = new_base;
} else {
- if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) {
- cpu = this_cpu;
+ if (new_cpu_base != this_base &&
+ hrtimer_check_target(timer, new_base)) {
+ new_cpu_base = this_base;
goto again;
}
}
/*
* Divide a ktime value by a nanosecond value
*/
-u64 __ktime_divns(const ktime_t kt, s64 div)
+s64 __ktime_divns(const ktime_t kt, s64 div)
{
- u64 dclc;
int sft = 0;
+ s64 dclc;
+ u64 tmp;
dclc = ktime_to_ns(kt);
+ tmp = dclc < 0 ? -dclc : dclc;
+
/* Make sure the divisor is less than 2^32: */
while (div >> 32) {
sft++;
div >>= 1;
}
- dclc >>= sft;
- do_div(dclc, (unsigned long) div);
-
- return dclc;
+ tmp >>= sft;
+ do_div(tmp, (unsigned long) div);
+ return dclc < 0 ? -tmp : tmp;
}
EXPORT_SYMBOL_GPL(__ktime_divns);
#endif /* BITS_PER_LONG >= 64 */
}
#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS)
+ static inline void hrtimer_update_next_timer(struct hrtimer_cpu_base *cpu_base,
+ struct hrtimer *timer)
+ {
+ #ifdef CONFIG_HIGH_RES_TIMERS
+ cpu_base->next_timer = timer;
+ #endif
+ }
+
static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base)
{
struct hrtimer_clock_base *base = cpu_base->clock_base;
ktime_t expires, expires_next = { .tv64 = KTIME_MAX };
- int i;
+ unsigned int active = cpu_base->active_bases;
- for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
+ hrtimer_update_next_timer(cpu_base, NULL);
+ for (; active; base++, active >>= 1) {
struct timerqueue_node *next;
struct hrtimer *timer;
- next = timerqueue_getnext(&base->active);
- if (!next)
+ if (!(active & 0x01))
continue;
+ next = timerqueue_getnext(&base->active);
timer = container_of(next, struct hrtimer, node);
expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
- if (expires.tv64 < expires_next.tv64)
+ if (expires.tv64 < expires_next.tv64) {
expires_next = expires;
+ hrtimer_update_next_timer(cpu_base, timer);
+ }
}
/*
* clock_was_set() might have changed base->offset of any of
}
#endif
+ static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
+ {
+ ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset;
+ ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset;
+ ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset;
+
+ return ktime_get_update_offsets_now(&base->clock_was_set_seq,
+ offs_real, offs_boot, offs_tai);
+ }
+
/* High resolution timer related functions */
#ifdef CONFIG_HIGH_RES_TIMERS
* High resolution timer enabled ?
*/
static int hrtimer_hres_enabled __read_mostly = 1;
+ unsigned int hrtimer_resolution __read_mostly = LOW_RES_NSEC;
+ EXPORT_SYMBOL_GPL(hrtimer_resolution);
/*
* Enable / Disable high resolution mode
/*
* Is the high resolution mode active ?
*/
+ static inline int __hrtimer_hres_active(struct hrtimer_cpu_base *cpu_base)
+ {
+ return cpu_base->hres_active;
+ }
+
static inline int hrtimer_hres_active(void)
{
- return __this_cpu_read(hrtimer_bases.hres_active);
+ return __hrtimer_hres_active(this_cpu_ptr(&hrtimer_bases));
}
/*
static void
hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
{
- ktime_t expires_next = __hrtimer_get_next_event(cpu_base);
+ ktime_t expires_next;
+
+ if (!cpu_base->hres_active)
+ return;
+
+ expires_next = __hrtimer_get_next_event(cpu_base);
if (skip_equal && expires_next.tv64 == cpu_base->expires_next.tv64)
return;
if (cpu_base->hang_detected)
return;
- if (cpu_base->expires_next.tv64 != KTIME_MAX)
- tick_program_event(cpu_base->expires_next, 1);
+ tick_program_event(cpu_base->expires_next, 1);
}
/*
- * Shared reprogramming for clock_realtime and clock_monotonic
- *
* When a timer is enqueued and expires earlier than the already enqueued
* timers, we have to check, whether it expires earlier than the timer for
* which the clock event device was armed.
*
- * Note, that in case the state has HRTIMER_STATE_CALLBACK set, no reprogramming
- * and no expiry check happens. The timer gets enqueued into the rbtree. The
- * reprogramming and expiry check is done in the hrtimer_interrupt or in the
- * softirq.
- *
* Called with interrupts disabled and base->cpu_base.lock held
*/
- static int hrtimer_reprogram(struct hrtimer *timer,
- struct hrtimer_clock_base *base)
+ static void hrtimer_reprogram(struct hrtimer *timer,
+ struct hrtimer_clock_base *base)
{
struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
- int res;
WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0);
/*
- * When the callback is running, we do not reprogram the clock event
- * device. The timer callback is either running on a different CPU or
- * the callback is executed in the hrtimer_interrupt context. The
- * reprogramming is handled either by the softirq, which called the
- * callback or at the end of the hrtimer_interrupt.
+ * If the timer is not on the current cpu, we cannot reprogram
+ * the other cpus clock event device.
*/
- if (hrtimer_callback_running(timer))
- return 0;
+ if (base->cpu_base != cpu_base)
+ return;
+
+ /*
+ * If the hrtimer interrupt is running, then it will
+ * reevaluate the clock bases and reprogram the clock event
+ * device. The callbacks are always executed in hard interrupt
+ * context so we don't need an extra check for a running
+ * callback.
+ */
+ if (cpu_base->in_hrtirq)
+ return;
/*
* CLOCK_REALTIME timer might be requested with an absolute
- * expiry time which is less than base->offset. Nothing wrong
- * about that, just avoid to call into the tick code, which
- * has now objections against negative expiry values.
+ * expiry time which is less than base->offset. Set it to 0.
*/
if (expires.tv64 < 0)
- return -ETIME;
+ expires.tv64 = 0;
if (expires.tv64 >= cpu_base->expires_next.tv64)
- return 0;
+ return;
- /*
- * When the target cpu of the timer is currently executing
- * hrtimer_interrupt(), then we do not touch the clock event
- * device. hrtimer_interrupt() will reevaluate all clock bases
- * before reprogramming the device.
- */
- if (cpu_base->in_hrtirq)
- return 0;
+ /* Update the pointer to the next expiring timer */
+ cpu_base->next_timer = timer;
/*
* If a hang was detected in the last timer interrupt then we
* to make progress.
*/
if (cpu_base->hang_detected)
- return 0;
+ return;
/*
- * Clockevents returns -ETIME, when the event was in the past.
+ * Program the timer hardware. We enforce the expiry for
+ * events which are already in the past.
*/
- res = tick_program_event(expires, 0);
- if (!IS_ERR_VALUE(res))
- cpu_base->expires_next = expires;
- return res;
+ cpu_base->expires_next = expires;
+ tick_program_event(expires, 1);
}
/*
base->hres_active = 0;
}
- static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
- {
- ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset;
- ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset;
- ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset;
-
- return ktime_get_update_offsets_now(offs_real, offs_boot, offs_tai);
- }
-
/*
* Retrigger next event is called after clock was set
*
{
struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases);
- if (!hrtimer_hres_active())
+ if (!base->hres_active)
return;
raw_spin_lock(&base->lock);
*/
static int hrtimer_switch_to_hres(void)
{
- int i, cpu = smp_processor_id();
- struct hrtimer_cpu_base *base = &per_cpu(hrtimer_bases, cpu);
- unsigned long flags;
-
- if (base->hres_active)
- return 1;
-
- local_irq_save(flags);
+ struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases);
if (tick_init_highres()) {
- local_irq_restore(flags);
printk(KERN_WARNING "Could not switch to high resolution "
- "mode on CPU %d\n", cpu);
+ "mode on CPU %d\n", base->cpu);
return 0;
}
base->hres_active = 1;
- for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++)
- base->clock_base[i].resolution = KTIME_HIGH_RES;
+ hrtimer_resolution = HIGH_RES_NSEC;
tick_setup_sched_timer();
/* "Retrigger" the interrupt to get things going */
retrigger_next_event(NULL);
- local_irq_restore(flags);
return 1;
}
#else
+ static inline int __hrtimer_hres_active(struct hrtimer_cpu_base *b) { return 0; }
static inline int hrtimer_hres_active(void) { return 0; }
static inline int hrtimer_is_hres_enabled(void) { return 0; }
static inline int hrtimer_switch_to_hres(void) { return 0; }
*
* Forward the timer expiry so it will expire in the future.
* Returns the number of overruns.
+ *
+ * Can be safely called from the callback function of @timer. If
+ * called from other contexts @timer must neither be enqueued nor
+ * running the callback and the caller needs to take care of
+ * serialization.
+ *
+ * Note: This only updates the timer expiry value and does not requeue
+ * the timer.
*/
u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
{
if (delta.tv64 < 0)
return 0;
- if (interval.tv64 < timer->base->resolution.tv64)
- interval.tv64 = timer->base->resolution.tv64;
+ if (WARN_ON(timer->state & HRTIMER_STATE_ENQUEUED))
+ return 0;
+
+ if (interval.tv64 < hrtimer_resolution)
+ interval.tv64 = hrtimer_resolution;
if (unlikely(delta.tv64 >= interval.tv64)) {
s64 incr = ktime_to_ns(interval);
{
debug_activate(timer);
- timerqueue_add(&base->active, &timer->node);
base->cpu_base->active_bases |= 1 << base->index;
- /*
- * HRTIMER_STATE_ENQUEUED is or'ed to the current state to preserve the
- * state of a possibly running callback.
- */
- timer->state |= HRTIMER_STATE_ENQUEUED;
+ timer->state = HRTIMER_STATE_ENQUEUED;
- return (&timer->node == base->active.next);
+ return timerqueue_add(&base->active, &timer->node);
}
/*
struct hrtimer_clock_base *base,
unsigned long newstate, int reprogram)
{
- struct timerqueue_node *next_timer;
- if (!(timer->state & HRTIMER_STATE_ENQUEUED))
- goto out;
+ struct hrtimer_cpu_base *cpu_base = base->cpu_base;
+ unsigned int state = timer->state;
+
+ timer->state = newstate;
+ if (!(state & HRTIMER_STATE_ENQUEUED))
+ return;
+
+ if (!timerqueue_del(&base->active, &timer->node))
+ cpu_base->active_bases &= ~(1 << base->index);
- next_timer = timerqueue_getnext(&base->active);
- timerqueue_del(&base->active, &timer->node);
- if (&timer->node == next_timer) {
#ifdef CONFIG_HIGH_RES_TIMERS
- /* Reprogram the clock event device. if enabled */
- if (reprogram && hrtimer_hres_active()) {
- ktime_t expires;
-
- expires = ktime_sub(hrtimer_get_expires(timer),
- base->offset);
- if (base->cpu_base->expires_next.tv64 == expires.tv64)
- hrtimer_force_reprogram(base->cpu_base, 1);
- }
+ /*
+ * Note: If reprogram is false we do not update
+ * cpu_base->next_timer. This happens when we remove the first
+ * timer on a remote cpu. No harm as we never dereference
+ * cpu_base->next_timer. So the worst thing what can happen is
+ * an superflous call to hrtimer_force_reprogram() on the
+ * remote cpu later on if the same timer gets enqueued again.
+ */
+ if (reprogram && timer == cpu_base->next_timer)
+ hrtimer_force_reprogram(cpu_base, 1);
#endif
- }
- if (!timerqueue_getnext(&base->active))
- base->cpu_base->active_bases &= ~(1 << base->index);
- out:
- timer->state = newstate;
}
/*
* remove hrtimer, called with base lock held
*/
static inline int
- remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
+ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool restart)
{
if (hrtimer_is_queued(timer)) {
- unsigned long state;
+ unsigned long state = timer->state;
int reprogram;
/*
debug_deactivate(timer);
timer_stats_hrtimer_clear_start_info(timer);
reprogram = base->cpu_base == this_cpu_ptr(&hrtimer_bases);
- /*
- * We must preserve the CALLBACK state flag here,
- * otherwise we could move the timer base in
- * switch_hrtimer_base.
- */
- state = timer->state & HRTIMER_STATE_CALLBACK;
+
+ if (!restart)
+ state = HRTIMER_STATE_INACTIVE;
+
__remove_hrtimer(timer, base, state, reprogram);
return 1;
}
return 0;
}
- int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
- unsigned long delta_ns, const enum hrtimer_mode mode,
- int wakeup)
+ /**
+ * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU
+ * @timer: the timer to be added
+ * @tim: expiry time
+ * @delta_ns: "slack" range for the timer
+ * @mode: expiry mode: absolute (HRTIMER_MODE_ABS) or
+ * relative (HRTIMER_MODE_REL)
+ */
+ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
+ unsigned long delta_ns, const enum hrtimer_mode mode)
{
struct hrtimer_clock_base *base, *new_base;
unsigned long flags;
- int ret, leftmost;
+ int leftmost;
base = lock_hrtimer_base(timer, &flags);
/* Remove an active timer from the queue: */
- ret = remove_hrtimer(timer, base);
+ remove_hrtimer(timer, base, true);
if (mode & HRTIMER_MODE_REL) {
tim = ktime_add_safe(tim, base->get_time());
* timeouts. This will go away with the GTOD framework.
*/
#ifdef CONFIG_TIME_LOW_RES
- tim = ktime_add_safe(tim, base->resolution);
+ tim = ktime_add_safe(tim, ktime_set(0, hrtimer_resolution));
#endif
}
timer_stats_hrtimer_set_start_info(timer);
leftmost = enqueue_hrtimer(timer, new_base);
-
- if (!leftmost) {
- unlock_hrtimer_base(timer, &flags);
- return ret;
- }
+ if (!leftmost)
+ goto unlock;
if (!hrtimer_is_hres_active(timer)) {
/*
* Kick to reschedule the next tick to handle the new timer
* on dynticks target.
*/
- wake_up_nohz_cpu(new_base->cpu_base->cpu);
- } else if (new_base->cpu_base == this_cpu_ptr(&hrtimer_bases) &&
- hrtimer_reprogram(timer, new_base)) {
- /*
- * Only allow reprogramming if the new base is on this CPU.
- * (it might still be on another CPU if the timer was pending)
- *
- * XXX send_remote_softirq() ?
- */
- if (wakeup) {
- /*
- * We need to drop cpu_base->lock to avoid a
- * lock ordering issue vs. rq->lock.
- */
- raw_spin_unlock(&new_base->cpu_base->lock);
- raise_softirq_irqoff(HRTIMER_SOFTIRQ);
- local_irq_restore(flags);
- return ret;
- } else {
- __raise_softirq_irqoff(HRTIMER_SOFTIRQ);
- }
+ if (new_base->cpu_base->nohz_active)
+ wake_up_nohz_cpu(new_base->cpu_base->cpu);
+ } else {
+ hrtimer_reprogram(timer, new_base);
}
-
+ unlock:
unlock_hrtimer_base(timer, &flags);
-
- return ret;
- }
- EXPORT_SYMBOL_GPL(__hrtimer_start_range_ns);
-
- /**
- * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU
- * @timer: the timer to be added
- * @tim: expiry time
- * @delta_ns: "slack" range for the timer
- * @mode: expiry mode: absolute (HRTIMER_MODE_ABS) or
- * relative (HRTIMER_MODE_REL)
- *
- * Returns:
- * 0 on success
- * 1 when the timer was active
- */
- int hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
- unsigned long delta_ns, const enum hrtimer_mode mode)
- {
- return __hrtimer_start_range_ns(timer, tim, delta_ns, mode, 1);
}
EXPORT_SYMBOL_GPL(hrtimer_start_range_ns);
- /**
- * hrtimer_start - (re)start an hrtimer on the current CPU
- * @timer: the timer to be added
- * @tim: expiry time
- * @mode: expiry mode: absolute (HRTIMER_MODE_ABS) or
- * relative (HRTIMER_MODE_REL)
- *
- * Returns:
- * 0 on success
- * 1 when the timer was active
- */
- int
- hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
- {
- return __hrtimer_start_range_ns(timer, tim, 0, mode, 1);
- }
- EXPORT_SYMBOL_GPL(hrtimer_start);
-
-
/**
* hrtimer_try_to_cancel - try to deactivate a timer
* @timer: hrtimer to stop
unsigned long flags;
int ret = -1;
+ /*
+ * Check lockless first. If the timer is not active (neither
+ * enqueued nor running the callback, nothing to do here. The
+ * base lock does not serialize against a concurrent enqueue,
+ * so we can avoid taking it.
+ */
+ if (!hrtimer_active(timer))
+ return 0;
+
base = lock_hrtimer_base(timer, &flags);
if (!hrtimer_callback_running(timer))
- ret = remove_hrtimer(timer, base);
+ ret = remove_hrtimer(timer, base, false);
unlock_hrtimer_base(timer, &flags);
/**
* hrtimer_get_next_event - get the time until next expiry event
*
- * Returns the delta to the next expiry event or KTIME_MAX if no timer
- * is pending.
+ * Returns the next expiry time or KTIME_MAX if no timer is pending.
*/
- ktime_t hrtimer_get_next_event(void)
+ u64 hrtimer_get_next_event(void)
{
struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
- ktime_t mindelta = { .tv64 = KTIME_MAX };
+ u64 expires = KTIME_MAX;
unsigned long flags;
raw_spin_lock_irqsave(&cpu_base->lock, flags);
- if (!hrtimer_hres_active())
- mindelta = ktime_sub(__hrtimer_get_next_event(cpu_base),
- ktime_get());
+ if (!__hrtimer_hres_active(cpu_base))
+ expires = __hrtimer_get_next_event(cpu_base).tv64;
raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
- if (mindelta.tv64 < 0)
- mindelta.tv64 = 0;
- return mindelta;
+ return expires;
}
#endif
}
EXPORT_SYMBOL_GPL(hrtimer_init);
- /**
- * hrtimer_get_res - get the timer resolution for a clock
- * @which_clock: which clock to query
- * @tp: pointer to timespec variable to store the resolution
+ /*
+ * A timer is active, when it is enqueued into the rbtree or the
+ * callback function is running or it's in the state of being migrated
+ * to another cpu.
*
- * Store the resolution of the clock selected by @which_clock in the
- * variable pointed to by @tp.
+ * It is important for this function to not return a false negative.
*/
- int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp)
+ bool hrtimer_active(const struct hrtimer *timer)
{
struct hrtimer_cpu_base *cpu_base;
- int base = hrtimer_clockid_to_base(which_clock);
+ unsigned int seq;
- cpu_base = raw_cpu_ptr(&hrtimer_bases);
- *tp = ktime_to_timespec(cpu_base->clock_base[base].resolution);
+ do {
+ cpu_base = READ_ONCE(timer->base->cpu_base);
+ seq = raw_read_seqcount_begin(&cpu_base->seq);
- return 0;
+ if (timer->state != HRTIMER_STATE_INACTIVE ||
+ cpu_base->running == timer)
+ return true;
+
+ } while (read_seqcount_retry(&cpu_base->seq, seq) ||
+ cpu_base != READ_ONCE(timer->base->cpu_base));
+
+ return false;
}
- EXPORT_SYMBOL_GPL(hrtimer_get_res);
+ EXPORT_SYMBOL_GPL(hrtimer_active);
- static void __run_hrtimer(struct hrtimer *timer, ktime_t *now)
+ /*
+ * The write_seqcount_barrier()s in __run_hrtimer() split the thing into 3
+ * distinct sections:
+ *
+ * - queued: the timer is queued
+ * - callback: the timer is being ran
+ * - post: the timer is inactive or (re)queued
+ *
+ * On the read side we ensure we observe timer->state and cpu_base->running
+ * from the same section, if anything changed while we looked at it, we retry.
+ * This includes timer->base changing because sequence numbers alone are
+ * insufficient for that.
+ *
+ * The sequence numbers are required because otherwise we could still observe
+ * a false negative if the read side got smeared over multiple consequtive
+ * __run_hrtimer() invocations.
+ */
+
+ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
+ struct hrtimer_clock_base *base,
+ struct hrtimer *timer, ktime_t *now)
{
- struct hrtimer_clock_base *base = timer->base;
- struct hrtimer_cpu_base *cpu_base = base->cpu_base;
enum hrtimer_restart (*fn)(struct hrtimer *);
int restart;
- WARN_ON(!irqs_disabled());
+ lockdep_assert_held(&cpu_base->lock);
debug_deactivate(timer);
- __remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0);
+ cpu_base->running = timer;
+
+ /*
+ * Separate the ->running assignment from the ->state assignment.
+ *
+ * As with a regular write barrier, this ensures the read side in
+ * hrtimer_active() cannot observe cpu_base->running == NULL &&
+ * timer->state == INACTIVE.
+ */
+ raw_write_seqcount_barrier(&cpu_base->seq);
+
+ __remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE, 0);
timer_stats_account_hrtimer(timer);
fn = timer->function;
raw_spin_lock(&cpu_base->lock);
/*
- * Note: We clear the CALLBACK bit after enqueue_hrtimer and
+ * Note: We clear the running state after enqueue_hrtimer and
* we do not reprogramm the event hardware. Happens either in
* hrtimer_start_range_ns() or in hrtimer_interrupt()
+ *
+ * Note: Because we dropped the cpu_base->lock above,
+ * hrtimer_start_range_ns() can have popped in and enqueued the timer
+ * for us already.
*/
- if (restart != HRTIMER_NORESTART) {
- BUG_ON(timer->state != HRTIMER_STATE_CALLBACK);
+ if (restart != HRTIMER_NORESTART &&
+ !(timer->state & HRTIMER_STATE_ENQUEUED))
enqueue_hrtimer(timer, base);
- }
- WARN_ON_ONCE(!(timer->state & HRTIMER_STATE_CALLBACK));
+ /*
+ * Separate the ->running assignment from the ->state assignment.
+ *
+ * As with a regular write barrier, this ensures the read side in
+ * hrtimer_active() cannot observe cpu_base->running == NULL &&
+ * timer->state == INACTIVE.
+ */
+ raw_write_seqcount_barrier(&cpu_base->seq);
- timer->state &= ~HRTIMER_STATE_CALLBACK;
+ WARN_ON_ONCE(cpu_base->running != timer);
+ cpu_base->running = NULL;
}
- #ifdef CONFIG_HIGH_RES_TIMERS
-
- /*
- * High resolution timer interrupt
- * Called with interrupts disabled
- */
- void hrtimer_interrupt(struct clock_event_device *dev)
+ static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now)
{
- struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
- ktime_t expires_next, now, entry_time, delta;
- int i, retries = 0;
-
- BUG_ON(!cpu_base->hres_active);
- cpu_base->nr_events++;
- dev->next_event.tv64 = KTIME_MAX;
-
- raw_spin_lock(&cpu_base->lock);
- entry_time = now = hrtimer_update_base(cpu_base);
- retry:
- cpu_base->in_hrtirq = 1;
- /*
- * We set expires_next to KTIME_MAX here with cpu_base->lock
- * held to prevent that a timer is enqueued in our queue via
- * the migration code. This does not affect enqueueing of
- * timers which run their callback and need to be requeued on
- * this CPU.
- */
- cpu_base->expires_next.tv64 = KTIME_MAX;
+ struct hrtimer_clock_base *base = cpu_base->clock_base;
+ unsigned int active = cpu_base->active_bases;
- for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
- struct hrtimer_clock_base *base;
+ for (; active; base++, active >>= 1) {
struct timerqueue_node *node;
ktime_t basenow;
- if (!(cpu_base->active_bases & (1 << i)))
+ if (!(active & 0x01))
continue;
- base = cpu_base->clock_base + i;
basenow = ktime_add(now, base->offset);
while ((node = timerqueue_getnext(&base->active))) {
if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer))
break;
- __run_hrtimer(timer, &basenow);
+ __run_hrtimer(cpu_base, base, timer, &basenow);
}
}
+ }
+
+ #ifdef CONFIG_HIGH_RES_TIMERS
+
+ /*
+ * High resolution timer interrupt
+ * Called with interrupts disabled
+ */
+ void hrtimer_interrupt(struct clock_event_device *dev)
+ {
+ struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
+ ktime_t expires_next, now, entry_time, delta;
+ int retries = 0;
+
+ BUG_ON(!cpu_base->hres_active);
+ cpu_base->nr_events++;
+ dev->next_event.tv64 = KTIME_MAX;
+
+ raw_spin_lock(&cpu_base->lock);
+ entry_time = now = hrtimer_update_base(cpu_base);
+ retry:
+ cpu_base->in_hrtirq = 1;
+ /*
+ * We set expires_next to KTIME_MAX here with cpu_base->lock
+ * held to prevent that a timer is enqueued in our queue via
+ * the migration code. This does not affect enqueueing of
+ * timers which run their callback and need to be requeued on
+ * this CPU.
+ */
+ cpu_base->expires_next.tv64 = KTIME_MAX;
+
+ __hrtimer_run_queues(cpu_base, now);
+
/* Reevaluate the clock bases for the next expiry */
expires_next = __hrtimer_get_next_event(cpu_base);
/*
raw_spin_unlock(&cpu_base->lock);
/* Reprogramming necessary ? */
- if (expires_next.tv64 == KTIME_MAX ||
- !tick_program_event(expires_next, 0)) {
+ if (!tick_program_event(expires_next, 0)) {
cpu_base->hang_detected = 0;
return;
}
cpu_base->hang_detected = 1;
raw_spin_unlock(&cpu_base->lock);
delta = ktime_sub(now, entry_time);
- if (delta.tv64 > cpu_base->max_hang_time.tv64)
- cpu_base->max_hang_time = delta;
+ if ((unsigned int)delta.tv64 > cpu_base->max_hang_time)
+ cpu_base->max_hang_time = (unsigned int) delta.tv64;
/*
* Limit it to a sensible value as we enforce a longer
* delay. Give the CPU at least 100ms to catch up.
* local version of hrtimer_peek_ahead_timers() called with interrupts
* disabled.
*/
- static void __hrtimer_peek_ahead_timers(void)
+ static inline void __hrtimer_peek_ahead_timers(void)
{
struct tick_device *td;
hrtimer_interrupt(td->evtdev);
}
- /**
- * hrtimer_peek_ahead_timers -- run soft-expired timers now
- *
- * hrtimer_peek_ahead_timers will peek at the timer queue of
- * the current cpu and check if there are any timers for which
- * the soft expires time has passed. If any such timers exist,
- * they are run immediately and then removed from the timer queue.
- *
- */
- void hrtimer_peek_ahead_timers(void)
- {
- unsigned long flags;
-
- local_irq_save(flags);
- __hrtimer_peek_ahead_timers();
- local_irq_restore(flags);
- }
-
- static void run_hrtimer_softirq(struct softirq_action *h)
- {
- hrtimer_peek_ahead_timers();
- }
-
#else /* CONFIG_HIGH_RES_TIMERS */
static inline void __hrtimer_peek_ahead_timers(void) { }
#endif /* !CONFIG_HIGH_RES_TIMERS */
/*
- * Called from timer softirq every jiffy, expire hrtimers:
- *
- * For HRT its the fall back code to run the softirq in the timer
- * softirq context in case the hrtimer initialization failed or has
- * not been done yet.
+ * Called from run_local_timers in hardirq context every jiffy
*/
- void hrtimer_run_pending(void)
+ void hrtimer_run_queues(void)
{
- if (hrtimer_hres_active())
+ struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
+ ktime_t now;
+
+ if (__hrtimer_hres_active(cpu_base))
return;
/*
- * This _is_ ugly: We have to check in the softirq context,
- * whether we can switch to highres and / or nohz mode. The
- * clocksource switch happens in the timer interrupt with
- * xtime_lock held. Notification from there only sets the
- * check bit in the tick_oneshot code, otherwise we might
- * deadlock vs. xtime_lock.
+ * This _is_ ugly: We have to check periodically, whether we
+ * can switch to highres and / or nohz mode. The clocksource
+ * switch happens with xtime_lock held. Notification from
+ * there only sets the check bit in the tick_oneshot code,
+ * otherwise we might deadlock vs. xtime_lock.
*/
- if (tick_check_oneshot_change(!hrtimer_is_hres_enabled()))
+ if (tick_check_oneshot_change(!hrtimer_is_hres_enabled())) {
hrtimer_switch_to_hres();
- }
-
- /*
- * Called from hardirq context every jiffy
- */
- void hrtimer_run_queues(void)
- {
- struct timerqueue_node *node;
- struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
- struct hrtimer_clock_base *base;
- int index, gettime = 1;
-
- if (hrtimer_hres_active())
return;
-
- for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) {
- base = &cpu_base->clock_base[index];
- if (!timerqueue_getnext(&base->active))
- continue;
-
- if (gettime) {
- hrtimer_get_softirq_time(cpu_base);
- gettime = 0;
- }
-
- raw_spin_lock(&cpu_base->lock);
-
- while ((node = timerqueue_getnext(&base->active))) {
- struct hrtimer *timer;
-
- timer = container_of(node, struct hrtimer, node);
- if (base->softirq_time.tv64 <=
- hrtimer_get_expires_tv64(timer))
- break;
-
- __run_hrtimer(timer, &base->softirq_time);
- }
- raw_spin_unlock(&cpu_base->lock);
}
+
+ raw_spin_lock(&cpu_base->lock);
+ now = hrtimer_update_base(cpu_base);
+ __hrtimer_run_queues(cpu_base, now);
+ raw_spin_unlock(&cpu_base->lock);
}
/*
do {
set_current_state(TASK_INTERRUPTIBLE);
hrtimer_start_expires(&t->timer, mode);
- if (!hrtimer_active(&t->timer))
- t->task = NULL;
if (likely(t->task))
freezable_schedule();
debug_deactivate(timer);
/*
- * Mark it as STATE_MIGRATE not INACTIVE otherwise the
+ * Mark it as ENQUEUED not INACTIVE otherwise the
* timer could be seen as !active and just vanish away
* under us on another CPU
*/
- __remove_hrtimer(timer, old_base, HRTIMER_STATE_MIGRATE, 0);
+ __remove_hrtimer(timer, old_base, HRTIMER_STATE_ENQUEUED, 0);
timer->base = new_base;
/*
* Enqueue the timers on the new cpu. This does not
* event device.
*/
enqueue_hrtimer(timer, new_base);
-
- /* Clear the migration state bit */
- timer->state &= ~HRTIMER_STATE_MIGRATE;
}
}
hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE,
(void *)(long)smp_processor_id());
register_cpu_notifier(&hrtimers_nb);
- #ifdef CONFIG_HIGH_RES_TIMERS
- open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq);
- #endif
}
/**
hrtimer_init_sleeper(&t, current);
hrtimer_start_expires(&t.timer, mode);
- if (!hrtimer_active(&t.timer))
- t.task = NULL;
if (likely(t.task))
schedule();
if (dev->flags & IFF_UP)
dev_deactivate(dev);
- if (new && new->ops->attach) {
- new->ops->attach(new);
- num_q = 0;
- }
+ if (new && new->ops->attach)
+ goto skip;
for (i = 0; i < num_q; i++) {
struct netdev_queue *dev_queue = dev_ingress_queue(dev);
qdisc_destroy(old);
}
+skip:
if (!ingress) {
notify_and_destroy(net, skb, n, classid,
dev->qdisc, new);
if (new && !new->ops->attach)
atomic_inc(&new->refcnt);
dev->qdisc = new ? : &noop_qdisc;
+
+ if (new && new->ops->attach)
+ new->ops->attach(new);
} else {
notify_and_destroy(net, skb, n, classid, old, new);
}
#ifdef CONFIG_PROC_FS
static int psched_show(struct seq_file *seq, void *v)
{
- struct timespec ts;
-
- hrtimer_get_res(CLOCK_MONOTONIC, &ts);
seq_printf(seq, "%08x %08x %08x %08x\n",
(u32)NSEC_PER_USEC, (u32)PSCHED_TICKS2NS(1),
1000000,
- (u32)NSEC_PER_SEC/(u32)ktime_to_ns(timespec_to_ktime(ts)));
+ (u32)NSEC_PER_SEC / hrtimer_resolution);
return 0;
}