* 'sched/for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
sched: hrtick_enabled() should use cpu_active()
sched, x86: clean up hrtick implementation
sched: fix build error, provide partition_sched_domains() unconditionally
sched: fix warning in inc_rt_tasks() to not declare variable 'rq' if it's not needed
cpu hotplug: Make cpu_active_map synchronization dependency clear
cpu hotplug, sched: Introduce cpu_active_map and redo sched domain managment (take 2)
sched: rework of "prioritize non-migratable tasks over migratable ones"
sched: reduce stack size in isolated_cpu_setup()
Revert parts of "ftrace: do not trace scheduler functions"
Fixed up conflicts in include/asm-x86/thread_info.h (due to the
TIF_SINGLESTEP unification vs TIF_HRTICK_RESCHED removal) and
kernel/sched_fair.c (due to cpu_active_map vs for_each_cpu_mask_nr()
introduction).
badframe:
if (show_unhandled_signals && printk_ratelimit()) {
- printk(KERN_INFO "%s%s[%d] bad frame in sigreturn frame:"
+ printk("%s%s[%d] bad frame in sigreturn frame:"
"%p ip:%lx sp:%lx oeax:%lx",
task_pid_nr(current) > 1 ? KERN_INFO : KERN_EMERG,
current->comm, task_pid_nr(current), frame, regs->ip,
void
do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
{
- /* Pending single-step? */
- if (thread_info_flags & _TIF_SINGLESTEP) {
- regs->flags |= X86_EFLAGS_TF;
- clear_thread_flag(TIF_SINGLESTEP);
- }
-
/* deal with pending signal delivery */
if (thread_info_flags & _TIF_SIGPENDING)
do_signal(regs);
- if (thread_info_flags & _TIF_HRTICK_RESCHED)
- hrtick_resched();
-
clear_thread_flag(TIF_IRET);
}
void do_notify_resume(struct pt_regs *regs, void *unused,
__u32 thread_info_flags)
{
- /* Pending single-step? */
- if (thread_info_flags & _TIF_SINGLESTEP) {
- regs->flags |= X86_EFLAGS_TF;
- clear_thread_flag(TIF_SINGLESTEP);
- }
-
#ifdef CONFIG_X86_MCE
/* notify userspace of pending MCEs */
if (thread_info_flags & _TIF_MCE_NOTIFY)
/* deal with pending signal delivery */
if (thread_info_flags & _TIF_SIGPENDING)
do_signal(regs);
-
- if (thread_info_flags & _TIF_HRTICK_RESCHED)
- hrtick_resched();
}
void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
#define TIF_NEED_RESCHED 3 /* rescheduling necessary */
#define TIF_SINGLESTEP 4 /* reenable singlestep on user return*/
#define TIF_IRET 5 /* force IRET */
-#ifdef CONFIG_X86_32
#define TIF_SYSCALL_EMU 6 /* syscall emulation active */
-#endif
#define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */
#define TIF_SECCOMP 8 /* secure computing */
#define TIF_MCE_NOTIFY 10 /* notify userspace of an MCE */
- #define TIF_HRTICK_RESCHED 11 /* reprogram hrtick timer */
#define TIF_NOTSC 16 /* TSC is not accessible in userland */
#define TIF_IA32 17 /* 32bit process */
#define TIF_FORK 18 /* ret_from_fork */
#define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP)
#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
#define _TIF_IRET (1 << TIF_IRET)
-#ifdef CONFIG_X86_32
#define _TIF_SYSCALL_EMU (1 << TIF_SYSCALL_EMU)
-#else
-#define _TIF_SYSCALL_EMU 0
-#endif
#define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT)
#define _TIF_SECCOMP (1 << TIF_SECCOMP)
#define _TIF_MCE_NOTIFY (1 << TIF_MCE_NOTIFY)
- #define _TIF_HRTICK_RESCHED (1 << TIF_HRTICK_RESCHED)
#define _TIF_NOTSC (1 << TIF_NOTSC)
#define _TIF_IA32 (1 << TIF_IA32)
#define _TIF_FORK (1 << TIF_FORK)
#define _TIF_DS_AREA_MSR (1 << TIF_DS_AREA_MSR)
#define _TIF_BTS_TRACE_TS (1 << TIF_BTS_TRACE_TS)
+/* work to do in syscall_trace_enter() */
+#define _TIF_WORK_SYSCALL_ENTRY \
+ (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | \
+ _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | _TIF_SINGLESTEP)
+
+/* work to do in syscall_trace_leave() */
+#define _TIF_WORK_SYSCALL_EXIT \
+ (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP)
+
/* work to do on interrupt/exception return */
#define _TIF_WORK_MASK \
(0x0000FFFF & \
- ~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP| \
- _TIF_SECCOMP|_TIF_SYSCALL_EMU))
+ ~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT| \
+ _TIF_SINGLESTEP|_TIF_SECCOMP|_TIF_SYSCALL_EMU))
/* work to do on any return to user space */
#define _TIF_ALLWORK_MASK (0x0000FFFF & ~_TIF_SECCOMP)
/* Only used for 64 bit */
#define _TIF_DO_NOTIFY_MASK \
- (_TIF_SIGPENDING|_TIF_MCE_NOTIFY|_TIF_HRTICK_RESCHED)
- (_TIF_SIGPENDING|_TIF_SINGLESTEP|_TIF_MCE_NOTIFY)
++ (_TIF_SIGPENDING|_TIF_MCE_NOTIFY)
/* flags to check in __switch_to() */
#define _TIF_WORK_CTXSW \
* For details of cpus_onto(), see bitmap_onto in lib/bitmap.c.
* For details of cpus_fold(), see bitmap_fold in lib/bitmap.c.
*
+ * . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
+ * Note: The alternate operations with the suffix "_nr" are used
+ * to limit the range of the loop to nr_cpu_ids instead of
+ * NR_CPUS when NR_CPUS > 64 for performance reasons.
+ * If NR_CPUS is <= 64 then most assembler bitmask
+ * operators execute faster with a constant range, so
+ * the operator will continue to use NR_CPUS.
+ *
+ * Another consideration is that nr_cpu_ids is initialized
+ * to NR_CPUS and isn't lowered until the possible cpus are
+ * discovered (including any disabled cpus). So early uses
+ * will span the entire range of NR_CPUS.
+ * . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
+ *
* The available cpumask operations are:
*
* void cpu_set(cpu, mask) turn on bit 'cpu' in mask
* int cpus_empty(mask) Is mask empty (no bits sets)?
* int cpus_full(mask) Is mask full (all bits sets)?
* int cpus_weight(mask) Hamming weigh - number of set bits
+ * int cpus_weight_nr(mask) Same using nr_cpu_ids instead of NR_CPUS
*
* void cpus_shift_right(dst, src, n) Shift right
* void cpus_shift_left(dst, src, n) Shift left
*
* int first_cpu(mask) Number lowest set bit, or NR_CPUS
* int next_cpu(cpu, mask) Next cpu past 'cpu', or NR_CPUS
+ * int next_cpu_nr(cpu, mask) Next cpu past 'cpu', or nr_cpu_ids
*
* cpumask_t cpumask_of_cpu(cpu) Return cpumask with bit 'cpu' set
+ *ifdef CONFIG_HAS_CPUMASK_OF_CPU
+ * cpumask_of_cpu_ptr_declare(v) Declares cpumask_t *v
+ * cpumask_of_cpu_ptr_next(v, cpu) Sets v = &cpumask_of_cpu_map[cpu]
+ * cpumask_of_cpu_ptr(v, cpu) Combines above two operations
+ *else
+ * cpumask_of_cpu_ptr_declare(v) Declares cpumask_t _v and *v = &_v
+ * cpumask_of_cpu_ptr_next(v, cpu) Sets _v = cpumask_of_cpu(cpu)
+ * cpumask_of_cpu_ptr(v, cpu) Combines above two operations
+ *endif
* CPU_MASK_ALL Initializer - all bits set
* CPU_MASK_NONE Initializer - no bits set
* unsigned long *cpus_addr(mask) Array of unsigned long's in mask
*
+ * CPUMASK_ALLOC kmalloc's a structure that is a composite of many cpumask_t
+ * variables, and CPUMASK_PTR provides pointers to each field.
+ *
+ * The structure should be defined something like this:
+ * struct my_cpumasks {
+ * cpumask_t mask1;
+ * cpumask_t mask2;
+ * };
+ *
+ * Usage is then:
+ * CPUMASK_ALLOC(my_cpumasks);
+ * CPUMASK_PTR(mask1, my_cpumasks);
+ * CPUMASK_PTR(mask2, my_cpumasks);
+ *
+ * --- DO NOT reference cpumask_t pointers until this check ---
+ * if (my_cpumasks == NULL)
+ * "kmalloc failed"...
+ *
+ * References are now pointers to the cpumask_t variables (*mask1, ...)
+ *
+ *if NR_CPUS > BITS_PER_LONG
+ * CPUMASK_ALLOC(m) Declares and allocates struct m *m =
+ * kmalloc(sizeof(*m), GFP_KERNEL)
+ * CPUMASK_FREE(m) Macro for kfree(m)
+ *else
+ * CPUMASK_ALLOC(m) Declares struct m _m, *m = &_m
+ * CPUMASK_FREE(m) Nop
+ *endif
+ * CPUMASK_PTR(v, m) Declares cpumask_t *v = &(m->v)
+ * ------------------------------------------------------------------------
+ *
* int cpumask_scnprintf(buf, len, mask) Format cpumask for printing
* int cpumask_parse_user(ubuf, ulen, mask) Parse ascii string as cpumask
* int cpulist_scnprintf(buf, len, mask) Format cpumask as list for printing
* void cpus_onto(dst, orig, relmap) *dst = orig relative to relmap
* void cpus_fold(dst, orig, sz) dst bits = orig bits mod sz
*
- * for_each_cpu_mask(cpu, mask) for-loop cpu over mask
+ * for_each_cpu_mask(cpu, mask) for-loop cpu over mask using NR_CPUS
+ * for_each_cpu_mask_nr(cpu, mask) for-loop cpu over mask using nr_cpu_ids
*
* int num_online_cpus() Number of online CPUs
* int num_possible_cpus() Number of all possible CPUs
bitmap_shift_left(dstp->bits, srcp->bits, n, nbits);
}
-#ifdef CONFIG_SMP
-int __first_cpu(const cpumask_t *srcp);
-#define first_cpu(src) __first_cpu(&(src))
-int __next_cpu(int n, const cpumask_t *srcp);
-#define next_cpu(n, src) __next_cpu((n), &(src))
-#else
-#define first_cpu(src) ({ (void)(src); 0; })
-#define next_cpu(n, src) ({ (void)(src); 1; })
-#endif
#ifdef CONFIG_HAVE_CPUMASK_OF_CPU_MAP
extern cpumask_t *cpumask_of_cpu_map;
-#define cpumask_of_cpu(cpu) (cpumask_of_cpu_map[cpu])
-
+#define cpumask_of_cpu(cpu) (cpumask_of_cpu_map[cpu])
+#define cpumask_of_cpu_ptr(v, cpu) \
+ const cpumask_t *v = &cpumask_of_cpu(cpu)
+#define cpumask_of_cpu_ptr_declare(v) \
+ const cpumask_t *v
+#define cpumask_of_cpu_ptr_next(v, cpu) \
+ v = &cpumask_of_cpu(cpu)
#else
#define cpumask_of_cpu(cpu) \
-(*({ \
+({ \
typeof(_unused_cpumask_arg_) m; \
if (sizeof(m) == sizeof(unsigned long)) { \
m.bits[0] = 1UL<<(cpu); \
cpus_clear(m); \
cpu_set((cpu), m); \
} \
- &m; \
-}))
+ m; \
+})
+#define cpumask_of_cpu_ptr(v, cpu) \
+ cpumask_t _##v = cpumask_of_cpu(cpu); \
+ const cpumask_t *v = &_##v
+#define cpumask_of_cpu_ptr_declare(v) \
+ cpumask_t _##v; \
+ const cpumask_t *v = &_##v
+#define cpumask_of_cpu_ptr_next(v, cpu) \
+ _##v = cpumask_of_cpu(cpu)
#endif
#define CPU_MASK_LAST_WORD BITMAP_LAST_WORD_MASK(NR_CPUS)
#define cpus_addr(src) ((src).bits)
+#if NR_CPUS > BITS_PER_LONG
+#define CPUMASK_ALLOC(m) struct m *m = kmalloc(sizeof(*m), GFP_KERNEL)
+#define CPUMASK_FREE(m) kfree(m)
+#else
+#define CPUMASK_ALLOC(m) struct m _m, *m = &_m
+#define CPUMASK_FREE(m)
+#endif
+#define CPUMASK_PTR(v, m) cpumask_t *v = &(m->v)
+
#define cpumask_scnprintf(buf, len, src) \
__cpumask_scnprintf((buf), (len), &(src), NR_CPUS)
static inline int __cpumask_scnprintf(char *buf, int len,
bitmap_fold(dstp->bits, origp->bits, sz, nbits);
}
-#if NR_CPUS > 1
-#define for_each_cpu_mask(cpu, mask) \
- for ((cpu) = first_cpu(mask); \
- (cpu) < NR_CPUS; \
- (cpu) = next_cpu((cpu), (mask)))
-#else /* NR_CPUS == 1 */
-#define for_each_cpu_mask(cpu, mask) \
+#if NR_CPUS == 1
+
+#define nr_cpu_ids 1
+#define first_cpu(src) ({ (void)(src); 0; })
+#define next_cpu(n, src) ({ (void)(src); 1; })
+#define any_online_cpu(mask) 0
+#define for_each_cpu_mask(cpu, mask) \
for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask)
-#endif /* NR_CPUS */
+
+#else /* NR_CPUS > 1 */
+
+extern int nr_cpu_ids;
+int __first_cpu(const cpumask_t *srcp);
+int __next_cpu(int n, const cpumask_t *srcp);
+int __any_online_cpu(const cpumask_t *mask);
+
+#define first_cpu(src) __first_cpu(&(src))
+#define next_cpu(n, src) __next_cpu((n), &(src))
+#define any_online_cpu(mask) __any_online_cpu(&(mask))
+#define for_each_cpu_mask(cpu, mask) \
+ for ((cpu) = -1; \
+ (cpu) = next_cpu((cpu), (mask)), \
+ (cpu) < NR_CPUS; )
+#endif
+
+#if NR_CPUS <= 64
#define next_cpu_nr(n, src) next_cpu(n, src)
#define cpus_weight_nr(cpumask) cpus_weight(cpumask)
#define for_each_cpu_mask_nr(cpu, mask) for_each_cpu_mask(cpu, mask)
+#else /* NR_CPUS > 64 */
+
+int __next_cpu_nr(int n, const cpumask_t *srcp);
+#define next_cpu_nr(n, src) __next_cpu_nr((n), &(src))
+#define cpus_weight_nr(cpumask) __cpus_weight(&(cpumask), nr_cpu_ids)
+#define for_each_cpu_mask_nr(cpu, mask) \
+ for ((cpu) = -1; \
+ (cpu) = next_cpu_nr((cpu), (mask)), \
+ (cpu) < nr_cpu_ids; )
+
+#endif /* NR_CPUS > 64 */
+
/*
* The following particular system cpumasks and operations manage
- * possible, present and online cpus. Each of them is a fixed size
+ * possible, present, active and online cpus. Each of them is a fixed size
* bitmap of size NR_CPUS.
*
* #ifdef CONFIG_HOTPLUG_CPU
* cpu_possible_map - has bit 'cpu' set iff cpu is populatable
* cpu_present_map - has bit 'cpu' set iff cpu is populated
* cpu_online_map - has bit 'cpu' set iff cpu available to scheduler
+ * cpu_active_map - has bit 'cpu' set iff cpu available to migration
* #else
* cpu_possible_map - has bit 'cpu' set iff cpu is populated
* cpu_present_map - copy of cpu_possible_map
extern cpumask_t cpu_possible_map;
extern cpumask_t cpu_online_map;
extern cpumask_t cpu_present_map;
+ extern cpumask_t cpu_active_map;
#if NR_CPUS > 1
-#define num_online_cpus() cpus_weight(cpu_online_map)
-#define num_possible_cpus() cpus_weight(cpu_possible_map)
-#define num_present_cpus() cpus_weight(cpu_present_map)
+#define num_online_cpus() cpus_weight_nr(cpu_online_map)
+#define num_possible_cpus() cpus_weight_nr(cpu_possible_map)
+#define num_present_cpus() cpus_weight_nr(cpu_present_map)
#define cpu_online(cpu) cpu_isset((cpu), cpu_online_map)
#define cpu_possible(cpu) cpu_isset((cpu), cpu_possible_map)
#define cpu_present(cpu) cpu_isset((cpu), cpu_present_map)
+ #define cpu_active(cpu) cpu_isset((cpu), cpu_active_map)
#else
#define num_online_cpus() 1
#define num_possible_cpus() 1
#define cpu_online(cpu) ((cpu) == 0)
#define cpu_possible(cpu) ((cpu) == 0)
#define cpu_present(cpu) ((cpu) == 0)
+ #define cpu_active(cpu) ((cpu) == 0)
#endif
#define cpu_is_offline(cpu) unlikely(!cpu_online(cpu))
-#ifdef CONFIG_SMP
-extern int nr_cpu_ids;
-#define any_online_cpu(mask) __any_online_cpu(&(mask))
-int __any_online_cpu(const cpumask_t *mask);
-#else
-#define nr_cpu_ids 1
-#define any_online_cpu(mask) 0
-#endif
-
-#define for_each_possible_cpu(cpu) for_each_cpu_mask((cpu), cpu_possible_map)
-#define for_each_online_cpu(cpu) for_each_cpu_mask((cpu), cpu_online_map)
-#define for_each_present_cpu(cpu) for_each_cpu_mask((cpu), cpu_present_map)
+#define for_each_possible_cpu(cpu) for_each_cpu_mask_nr((cpu), cpu_possible_map)
+#define for_each_online_cpu(cpu) for_each_cpu_mask_nr((cpu), cpu_online_map)
+#define for_each_present_cpu(cpu) for_each_cpu_mask_nr((cpu), cpu_present_map)
#endif /* __LINUX_CPUMASK_H */
extern void spawn_softlockup_task(void);
extern void touch_softlockup_watchdog(void);
extern void touch_all_softlockup_watchdogs(void);
-extern unsigned long softlockup_thresh;
+extern unsigned int softlockup_panic;
extern unsigned long sysctl_hung_task_check_count;
extern unsigned long sysctl_hung_task_timeout_secs;
extern unsigned long sysctl_hung_task_warnings;
+extern int softlockup_thresh;
#else
static inline void softlockup_tick(void)
{
struct sched_domain_attr *dattr_new);
extern int arch_reinit_sched_domains(void);
- #endif /* CONFIG_SMP */
+ #else /* CONFIG_SMP */
+
+ struct sched_domain_attr;
+
+ static inline void
+ partition_sched_domains(int ndoms_new, cpumask_t *doms_new,
+ struct sched_domain_attr *dattr_new)
+ {
+ }
+ #endif /* !CONFIG_SMP */
struct io_context; /* See blkdev.h */
#define NGROUPS_SMALL 32
{
unsigned int cpu;
+ /*
+ * Set up the current CPU as possible to migrate to.
+ * The other ones will be done by cpu_up/cpu_down()
+ */
+ cpu = smp_processor_id();
+ cpu_set(cpu, cpu_active_map);
+
/* FIXME: This should be done in userspace --RR */
for_each_present_cpu(cpu) {
if (num_online_cpus() >= setup_max_cpus)
#ifdef CONFIG_BLK_DEV_INITRD
if (initrd_start && !initrd_below_start_ok &&
- initrd_start < min_low_pfn << PAGE_SHIFT) {
+ page_to_pfn(virt_to_page(initrd_start)) < min_low_pfn) {
printk(KERN_CRIT "initrd overwritten (0x%08lx < 0x%08lx) - "
- "disabling it.\n",initrd_start,min_low_pfn << PAGE_SHIFT);
+ "disabling it.\n",
+ page_to_pfn(virt_to_page(initrd_start)), min_low_pfn);
initrd_start = 0;
}
#endif
cpu_hotplug.refcount = 0;
}
+ cpumask_t cpu_active_map;
+
#ifdef CONFIG_HOTPLUG_CPU
void get_online_cpus(void)
int err = 0;
cpu_maps_update_begin();
- if (cpu_hotplug_disabled)
+
+ if (cpu_hotplug_disabled) {
err = -EBUSY;
- else
- err = _cpu_down(cpu, 0);
+ goto out;
+ }
+
+ cpu_clear(cpu, cpu_active_map);
+
+ /*
+ * Make sure the all cpus did the reschedule and are not
+ * using stale version of the cpu_active_map.
+ * This is not strictly necessary becuase stop_machine()
+ * that we run down the line already provides the required
+ * synchronization. But it's really a side effect and we do not
+ * want to depend on the innards of the stop_machine here.
+ */
+ synchronize_sched();
+ err = _cpu_down(cpu, 0);
+
+ if (cpu_online(cpu))
+ cpu_set(cpu, cpu_active_map);
+
+ out:
cpu_maps_update_done();
return err;
}
}
cpu_maps_update_begin();
- if (cpu_hotplug_disabled)
+
+ if (cpu_hotplug_disabled) {
err = -EBUSY;
- else
- err = _cpu_up(cpu, 0);
+ goto out;
+ }
+
+ err = _cpu_up(cpu, 0);
+
+ if (cpu_online(cpu))
+ cpu_set(cpu, cpu_active_map);
+ out:
cpu_maps_update_done();
return err;
}
goto out;
printk("Enabling non-boot CPUs ...\n");
- for_each_cpu_mask(cpu, frozen_cpus) {
+ for_each_cpu_mask_nr(cpu, frozen_cpus) {
error = _cpu_up(cpu, 1);
if (!error) {
printk("CPU%d is up\n", cpu);
* partition_sched_domains().
*/
- static void rebuild_sched_domains(void)
+ void rebuild_sched_domains(void)
{
struct kfifo *q; /* queue of cpusets to be scanned */
struct cpuset *cp; /* scans q */
if (apn == b->pn) {
cpus_or(*dp, *dp, b->cpus_allowed);
b->pn = -1;
- update_domain_attr(dattr, b);
+ if (dattr)
+ update_domain_attr(dattr
+ + nslot, b);
}
}
nslot++;
#endif
#ifdef CONFIG_SCHED_HRTICK
- unsigned long hrtick_flags;
- ktime_t hrtick_expire;
+ #ifdef CONFIG_SMP
+ int hrtick_csd_pending;
+ struct call_single_data hrtick_csd;
+ #endif
struct hrtimer hrtick_timer;
#endif
return rq;
}
- static void __resched_task(struct task_struct *p, int tif_bit);
-
- static inline void resched_task(struct task_struct *p)
- {
- __resched_task(p, TIF_NEED_RESCHED);
- }
-
#ifdef CONFIG_SCHED_HRTICK
/*
* Use HR-timers to deliver accurate preemption points.
* When we get rescheduled we reprogram the hrtick_timer outside of the
* rq->lock.
*/
- static inline void resched_hrt(struct task_struct *p)
- {
- __resched_task(p, TIF_HRTICK_RESCHED);
- }
-
- static inline void resched_rq(struct rq *rq)
- {
- unsigned long flags;
-
- spin_lock_irqsave(&rq->lock, flags);
- resched_task(rq->curr);
- spin_unlock_irqrestore(&rq->lock, flags);
- }
-
- enum {
- HRTICK_SET, /* re-programm hrtick_timer */
- HRTICK_RESET, /* not a new slice */
- HRTICK_BLOCK, /* stop hrtick operations */
- };
/*
* Use hrtick when:
{
if (!sched_feat(HRTICK))
return 0;
- if (unlikely(test_bit(HRTICK_BLOCK, &rq->hrtick_flags)))
+ if (!cpu_active(cpu_of(rq)))
return 0;
return hrtimer_is_hres_active(&rq->hrtick_timer);
}
- /*
- * Called to set the hrtick timer state.
- *
- * called with rq->lock held and irqs disabled
- */
- static void hrtick_start(struct rq *rq, u64 delay, int reset)
- {
- assert_spin_locked(&rq->lock);
-
- /*
- * preempt at: now + delay
- */
- rq->hrtick_expire =
- ktime_add_ns(rq->hrtick_timer.base->get_time(), delay);
- /*
- * indicate we need to program the timer
- */
- __set_bit(HRTICK_SET, &rq->hrtick_flags);
- if (reset)
- __set_bit(HRTICK_RESET, &rq->hrtick_flags);
-
- /*
- * New slices are called from the schedule path and don't need a
- * forced reschedule.
- */
- if (reset)
- resched_hrt(rq->curr);
- }
-
static void hrtick_clear(struct rq *rq)
{
if (hrtimer_active(&rq->hrtick_timer))
hrtimer_cancel(&rq->hrtick_timer);
}
- /*
- * Update the timer from the possible pending state.
- */
- static void hrtick_set(struct rq *rq)
- {
- ktime_t time;
- int set, reset;
- unsigned long flags;
-
- WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
-
- spin_lock_irqsave(&rq->lock, flags);
- set = __test_and_clear_bit(HRTICK_SET, &rq->hrtick_flags);
- reset = __test_and_clear_bit(HRTICK_RESET, &rq->hrtick_flags);
- time = rq->hrtick_expire;
- clear_thread_flag(TIF_HRTICK_RESCHED);
- spin_unlock_irqrestore(&rq->lock, flags);
-
- if (set) {
- hrtimer_start(&rq->hrtick_timer, time, HRTIMER_MODE_ABS);
- if (reset && !hrtimer_active(&rq->hrtick_timer))
- resched_rq(rq);
- } else
- hrtick_clear(rq);
- }
-
/*
* High-resolution timer tick.
* Runs from hardirq context with interrupts disabled.
}
#ifdef CONFIG_SMP
- static void hotplug_hrtick_disable(int cpu)
+ /*
+ * called from hardirq (IPI) context
+ */
+ static void __hrtick_start(void *arg)
{
- struct rq *rq = cpu_rq(cpu);
- unsigned long flags;
-
- spin_lock_irqsave(&rq->lock, flags);
- rq->hrtick_flags = 0;
- __set_bit(HRTICK_BLOCK, &rq->hrtick_flags);
- spin_unlock_irqrestore(&rq->lock, flags);
+ struct rq *rq = arg;
- hrtick_clear(rq);
+ spin_lock(&rq->lock);
+ hrtimer_restart(&rq->hrtick_timer);
+ rq->hrtick_csd_pending = 0;
+ spin_unlock(&rq->lock);
}
- static void hotplug_hrtick_enable(int cpu)
+ /*
+ * Called to set the hrtick timer state.
+ *
+ * called with rq->lock held and irqs disabled
+ */
+ static void hrtick_start(struct rq *rq, u64 delay)
{
- struct rq *rq = cpu_rq(cpu);
- unsigned long flags;
+ struct hrtimer *timer = &rq->hrtick_timer;
+ ktime_t time = ktime_add_ns(timer->base->get_time(), delay);
- spin_lock_irqsave(&rq->lock, flags);
- __clear_bit(HRTICK_BLOCK, &rq->hrtick_flags);
- spin_unlock_irqrestore(&rq->lock, flags);
+ timer->expires = time;
+
+ if (rq == this_rq()) {
+ hrtimer_restart(timer);
+ } else if (!rq->hrtick_csd_pending) {
+ __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd);
+ rq->hrtick_csd_pending = 1;
+ }
}
static int
case CPU_DOWN_PREPARE_FROZEN:
case CPU_DEAD:
case CPU_DEAD_FROZEN:
- hotplug_hrtick_disable(cpu);
- return NOTIFY_OK;
-
- case CPU_UP_PREPARE:
- case CPU_UP_PREPARE_FROZEN:
- case CPU_DOWN_FAILED:
- case CPU_DOWN_FAILED_FROZEN:
- case CPU_ONLINE:
- case CPU_ONLINE_FROZEN:
- hotplug_hrtick_enable(cpu);
+ hrtick_clear(cpu_rq(cpu));
return NOTIFY_OK;
}
{
hotcpu_notifier(hotplug_hrtick, 0);
}
- #endif /* CONFIG_SMP */
+ #else
+ /*
+ * Called to set the hrtick timer state.
+ *
+ * called with rq->lock held and irqs disabled
+ */
+ static void hrtick_start(struct rq *rq, u64 delay)
+ {
+ hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay), HRTIMER_MODE_REL);
+ }
- static void init_rq_hrtick(struct rq *rq)
+ static void init_hrtick(void)
{
- rq->hrtick_flags = 0;
- hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
- rq->hrtick_timer.function = hrtick;
- rq->hrtick_timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ;
}
+ #endif /* CONFIG_SMP */
- void hrtick_resched(void)
+ static void init_rq_hrtick(struct rq *rq)
{
- struct rq *rq;
- unsigned long flags;
+ #ifdef CONFIG_SMP
+ rq->hrtick_csd_pending = 0;
- if (!test_thread_flag(TIF_HRTICK_RESCHED))
- return;
+ rq->hrtick_csd.flags = 0;
+ rq->hrtick_csd.func = __hrtick_start;
+ rq->hrtick_csd.info = rq;
+ #endif
- local_irq_save(flags);
- rq = cpu_rq(smp_processor_id());
- hrtick_set(rq);
- local_irq_restore(flags);
+ hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ rq->hrtick_timer.function = hrtick;
+ rq->hrtick_timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ;
}
#else
static inline void hrtick_clear(struct rq *rq)
{
}
- static inline void hrtick_set(struct rq *rq)
- {
- }
-
static inline void init_rq_hrtick(struct rq *rq)
{
}
- void hrtick_resched(void)
- {
- }
-
static inline void init_hrtick(void)
{
}
#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG)
#endif
- static void __resched_task(struct task_struct *p, int tif_bit)
+ static void resched_task(struct task_struct *p)
{
int cpu;
assert_spin_locked(&task_rq(p)->lock);
- if (unlikely(test_tsk_thread_flag(p, tif_bit)))
+ if (unlikely(test_tsk_thread_flag(p, TIF_NEED_RESCHED)))
return;
- set_tsk_thread_flag(p, tif_bit);
+ set_tsk_thread_flag(p, TIF_NEED_RESCHED);
cpu = task_cpu(p);
if (cpu == smp_processor_id())
#endif /* CONFIG_NO_HZ */
#else /* !CONFIG_SMP */
- static void __resched_task(struct task_struct *p, int tif_bit)
+ static void resched_task(struct task_struct *p)
{
assert_spin_locked(&task_rq(p)->lock);
- set_tsk_thread_flag(p, tif_bit);
+ set_tsk_need_resched(p);
}
#endif /* CONFIG_SMP */
/* Tally up the load of all CPUs in the group */
avg_load = 0;
- for_each_cpu_mask(i, group->cpumask) {
+ for_each_cpu_mask_nr(i, group->cpumask) {
/* Bias balancing toward cpus of our domain */
if (local_group)
load = source_load(i, load_idx);
/* Traverse only the allowed CPUs */
cpus_and(*tmp, group->cpumask, p->cpus_allowed);
- for_each_cpu_mask(i, *tmp) {
+ for_each_cpu_mask_nr(i, *tmp) {
load = weighted_cpuload(i);
if (load < min_load || (load == min_load && i == this_cpu)) {
rq = task_rq_lock(p, &flags);
if (!cpu_isset(dest_cpu, p->cpus_allowed)
- || unlikely(cpu_is_offline(dest_cpu)))
+ || unlikely(!cpu_active(dest_cpu)))
goto out;
/* force the process onto the specified CPU */
max_cpu_load = 0;
min_cpu_load = ~0UL;
- for_each_cpu_mask(i, group->cpumask) {
+ for_each_cpu_mask_nr(i, group->cpumask) {
struct rq *rq;
if (!cpu_isset(i, *cpus))
unsigned long max_load = 0;
int i;
- for_each_cpu_mask(i, group->cpumask) {
+ for_each_cpu_mask_nr(i, group->cpumask) {
unsigned long wl;
if (!cpu_isset(i, *cpus))
/*
* If we are going offline and still the leader, give up!
*/
- if (cpu_is_offline(cpu) &&
+ if (!cpu_active(cpu) &&
atomic_read(&nohz.load_balancer) == cpu) {
if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu)
BUG();
int balance_cpu;
cpu_clear(this_cpu, cpus);
- for_each_cpu_mask(balance_cpu, cpus) {
+ for_each_cpu_mask_nr(balance_cpu, cpus) {
/*
* If this cpu gets work to do, stop the load balancing
* work being done for other cpus. Next load
struct task_struct *prev, *next;
unsigned long *switch_count;
struct rq *rq;
- int cpu, hrtick = sched_feat(HRTICK);
+ int cpu;
need_resched:
preempt_disable();
schedule_debug(prev);
- if (hrtick)
+ if (sched_feat(HRTICK))
hrtick_clear(rq);
/*
} else
spin_unlock_irq(&rq->lock);
- if (hrtick)
- hrtick_set(rq);
-
if (unlikely(reacquire_kernel_lock(current) < 0))
goto need_resched_nonpreemptible;
struct rq *rq_dest, *rq_src;
int ret = 0, on_rq;
- if (unlikely(cpu_is_offline(dest_cpu)))
+ if (unlikely(!cpu_active(dest_cpu)))
return ret;
rq_src = cpu_rq(src_cpu);
/* Setup the mask of cpus configured for isolated domains */
static int __init isolated_cpu_setup(char *str)
{
- int ints[NR_CPUS], i;
+ static int __initdata ints[NR_CPUS];
+ int i;
str = get_options(str, ARRAY_SIZE(ints), ints);
cpus_clear(cpu_isolated_map);
cpus_clear(*covered);
- for_each_cpu_mask(i, *span) {
+ for_each_cpu_mask_nr(i, *span) {
struct sched_group *sg;
int group = group_fn(i, cpu_map, &sg, tmpmask);
int j;
cpus_clear(sg->cpumask);
sg->__cpu_power = 0;
- for_each_cpu_mask(j, *span) {
+ for_each_cpu_mask_nr(j, *span) {
if (group_fn(j, cpu_map, NULL, tmpmask) != group)
continue;
if (!sg)
return;
do {
- for_each_cpu_mask(j, sg->cpumask) {
+ for_each_cpu_mask_nr(j, sg->cpumask) {
struct sched_domain *sd;
sd = &per_cpu(phys_domains, j);
{
int cpu, i;
- for_each_cpu_mask(cpu, *cpu_map) {
+ for_each_cpu_mask_nr(cpu, *cpu_map) {
struct sched_group **sched_group_nodes
= sched_group_nodes_bycpu[cpu];
/*
* Set up domains for cpus specified by the cpu_map.
*/
- for_each_cpu_mask(i, *cpu_map) {
+ for_each_cpu_mask_nr(i, *cpu_map) {
struct sched_domain *sd = NULL, *p;
SCHED_CPUMASK_VAR(nodemask, allmasks);
#ifdef CONFIG_SCHED_SMT
/* Set up CPU (sibling) groups */
- for_each_cpu_mask(i, *cpu_map) {
+ for_each_cpu_mask_nr(i, *cpu_map) {
SCHED_CPUMASK_VAR(this_sibling_map, allmasks);
SCHED_CPUMASK_VAR(send_covered, allmasks);
#ifdef CONFIG_SCHED_MC
/* Set up multi-core groups */
- for_each_cpu_mask(i, *cpu_map) {
+ for_each_cpu_mask_nr(i, *cpu_map) {
SCHED_CPUMASK_VAR(this_core_map, allmasks);
SCHED_CPUMASK_VAR(send_covered, allmasks);
goto error;
}
sched_group_nodes[i] = sg;
- for_each_cpu_mask(j, *nodemask) {
+ for_each_cpu_mask_nr(j, *nodemask) {
struct sched_domain *sd;
sd = &per_cpu(node_domains, j);
/* Calculate CPU power for physical packages and nodes */
#ifdef CONFIG_SCHED_SMT
- for_each_cpu_mask(i, *cpu_map) {
+ for_each_cpu_mask_nr(i, *cpu_map) {
struct sched_domain *sd = &per_cpu(cpu_domains, i);
init_sched_groups_power(i, sd);
}
#endif
#ifdef CONFIG_SCHED_MC
- for_each_cpu_mask(i, *cpu_map) {
+ for_each_cpu_mask_nr(i, *cpu_map) {
struct sched_domain *sd = &per_cpu(core_domains, i);
init_sched_groups_power(i, sd);
}
#endif
- for_each_cpu_mask(i, *cpu_map) {
+ for_each_cpu_mask_nr(i, *cpu_map) {
struct sched_domain *sd = &per_cpu(phys_domains, i);
init_sched_groups_power(i, sd);
#endif
/* Attach the domains */
- for_each_cpu_mask(i, *cpu_map) {
+ for_each_cpu_mask_nr(i, *cpu_map) {
struct sched_domain *sd;
#ifdef CONFIG_SCHED_SMT
sd = &per_cpu(cpu_domains, i);
{
}
- /*
- * Free current domain masks.
- * Called after all cpus are attached to NULL domain.
- */
- static void free_sched_domains(void)
- {
- ndoms_cur = 0;
- if (doms_cur != &fallback_doms)
- kfree(doms_cur);
- doms_cur = &fallback_doms;
- }
-
/*
* Set up scheduler domains and groups. Callers must hold the hotplug lock.
* For now this just excludes isolated cpus, but could be used to
unregister_sched_domain_sysctl();
- for_each_cpu_mask(i, *cpu_map)
+ for_each_cpu_mask_nr(i, *cpu_map)
cpu_attach_domain(NULL, &def_root_domain, i);
synchronize_sched();
arch_destroy_sched_domains(cpu_map, &tmpmask);
* ownership of it and will kfree it when done with it. If the caller
* failed the kmalloc call, then it can pass in doms_new == NULL,
* and partition_sched_domains() will fallback to the single partition
- * 'fallback_doms'.
+ * 'fallback_doms', it also forces the domains to be rebuilt.
*
* Call with hotplug lock held
*/
/* always unregister in case we don't destroy any domains */
unregister_sched_domain_sysctl();
- if (doms_new == NULL) {
- ndoms_new = 1;
- doms_new = &fallback_doms;
- cpus_andnot(doms_new[0], cpu_online_map, cpu_isolated_map);
- dattr_new = NULL;
- }
+ if (doms_new == NULL)
+ ndoms_new = 0;
/* Destroy deleted domains */
for (i = 0; i < ndoms_cur; i++) {
;
}
+ if (doms_new == NULL) {
+ ndoms_cur = 0;
+ ndoms_new = 1;
+ doms_new = &fallback_doms;
+ cpus_andnot(doms_new[0], cpu_online_map, cpu_isolated_map);
+ dattr_new = NULL;
+ }
+
/* Build new domains */
for (i = 0; i < ndoms_new; i++) {
for (j = 0; j < ndoms_cur; j++) {
#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
int arch_reinit_sched_domains(void)
{
- int err;
-
get_online_cpus();
- mutex_lock(&sched_domains_mutex);
- detach_destroy_domains(&cpu_online_map);
- free_sched_domains();
- err = arch_init_sched_domains(&cpu_online_map);
- mutex_unlock(&sched_domains_mutex);
+ rebuild_sched_domains();
put_online_cpus();
-
- return err;
+ return 0;
}
static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt)
}
#ifdef CONFIG_SCHED_MC
-static ssize_t sched_mc_power_savings_show(struct sys_device *dev, char *page)
+static ssize_t sched_mc_power_savings_show(struct sys_device *dev,
+ struct sysdev_attribute *attr, char *page)
{
return sprintf(page, "%u\n", sched_mc_power_savings);
}
static ssize_t sched_mc_power_savings_store(struct sys_device *dev,
+ struct sysdev_attribute *attr,
const char *buf, size_t count)
{
return sched_power_savings_store(buf, count, 0);
#endif
#ifdef CONFIG_SCHED_SMT
-static ssize_t sched_smt_power_savings_show(struct sys_device *dev, char *page)
+static ssize_t sched_smt_power_savings_show(struct sys_device *dev,
+ struct sysdev_attribute *attr, char *page)
{
return sprintf(page, "%u\n", sched_smt_power_savings);
}
static ssize_t sched_smt_power_savings_store(struct sys_device *dev,
+ struct sysdev_attribute *attr,
const char *buf, size_t count)
{
return sched_power_savings_store(buf, count, 1);
}
#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
+ #ifndef CONFIG_CPUSETS
/*
- * Force a reinitialization of the sched domains hierarchy. The domains
- * and groups cannot be updated in place without racing with the balancing
- * code, so we temporarily attach all running cpus to the NULL domain
- * which will prevent rebalancing while the sched domains are recalculated.
+ * Add online and remove offline CPUs from the scheduler domains.
+ * When cpusets are enabled they take over this function.
*/
static int update_sched_domains(struct notifier_block *nfb,
unsigned long action, void *hcpu)
+ {
+ switch (action) {
+ case CPU_ONLINE:
+ case CPU_ONLINE_FROZEN:
+ case CPU_DEAD:
+ case CPU_DEAD_FROZEN:
+ partition_sched_domains(0, NULL, NULL);
+ return NOTIFY_OK;
+
+ default:
+ return NOTIFY_DONE;
+ }
+ }
+ #endif
+
+ static int update_runtime(struct notifier_block *nfb,
+ unsigned long action, void *hcpu)
{
int cpu = (int)(long)hcpu;
case CPU_DOWN_PREPARE:
case CPU_DOWN_PREPARE_FROZEN:
disable_runtime(cpu_rq(cpu));
- /* fall-through */
- case CPU_UP_PREPARE:
- case CPU_UP_PREPARE_FROZEN:
- detach_destroy_domains(&cpu_online_map);
- free_sched_domains();
return NOTIFY_OK;
-
case CPU_DOWN_FAILED:
case CPU_DOWN_FAILED_FROZEN:
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
enable_runtime(cpu_rq(cpu));
- /* fall-through */
- case CPU_UP_CANCELED:
- case CPU_UP_CANCELED_FROZEN:
- case CPU_DEAD:
- case CPU_DEAD_FROZEN:
- /*
- * Fall through and re-initialise the domains.
- */
- break;
+ return NOTIFY_OK;
+
default:
return NOTIFY_DONE;
}
-
- #ifndef CONFIG_CPUSETS
- /*
- * Create default domain partitioning if cpusets are disabled.
- * Otherwise we let cpusets rebuild the domains based on the
- * current setup.
- */
-
- /* The hotplug lock is already held by cpu_up/cpu_down */
- arch_init_sched_domains(&cpu_online_map);
- #endif
-
- return NOTIFY_OK;
}
void __init sched_init_smp(void)
cpu_set(smp_processor_id(), non_isolated_cpus);
mutex_unlock(&sched_domains_mutex);
put_online_cpus();
+
+ #ifndef CONFIG_CPUSETS
/* XXX: Theoretical race here - CPU may be hotplugged now */
hotcpu_notifier(update_sched_domains, 0);
+ #endif
+
+ /* RT runtime code needs to handle some hotplug events */
+ hotcpu_notifier(update_runtime, 0);
+
init_hrtick();
/* Move init over to a non-isolated CPU */
#ifdef CONFIG_SCHED_HRTICK
static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
{
- int requeue = rq->curr == p;
struct sched_entity *se = &p->se;
struct cfs_rq *cfs_rq = cfs_rq_of(se);
* Don't schedule slices shorter than 10000ns, that just
* doesn't make sense. Rely on vruntime for fairness.
*/
- if (!requeue)
+ if (rq->curr != p)
delta = max(10000LL, delta);
- hrtick_start(rq, delta, requeue);
+ hrtick_start(rq, delta);
}
}
#else /* !CONFIG_SCHED_HRTICK */
* not idle and an idle cpu is available. The span of cpus to
* search starts with cpus closest then further out as needed,
* so we always favor a closer, idle cpu.
+ * Domains may include CPUs that are not usable for migration,
+ * hence we need to mask them out (cpu_active_map)
*
* Returns the CPU we should wake onto.
*/
|| ((sd->flags & SD_WAKE_IDLE_FAR)
&& !task_hot(p, task_rq(p)->clock, sd))) {
cpus_and(tmp, sd->span, p->cpus_allowed);
- for_each_cpu_mask(i, tmp) {
+ cpus_and(tmp, tmp, cpu_active_map);
+ for_each_cpu_mask_nr(i, tmp) {
if (idle_cpu(i)) {
if (i != task_cpu(p)) {
schedstat_inc(p,
spin_lock(&rt_b->rt_runtime_lock);
rt_period = ktime_to_ns(rt_b->rt_period);
- for_each_cpu_mask(i, rd->span) {
+ for_each_cpu_mask_nr(i, rd->span) {
struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i);
s64 diff;
rt_rq->rt_nr_running++;
#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
if (rt_se_prio(rt_se) < rt_rq->highest_prio) {
+ #ifdef CONFIG_SMP
struct rq *rq = rq_of_rt_rq(rt_rq);
+ #endif
rt_rq->highest_prio = rt_se_prio(rt_se);
#ifdef CONFIG_SMP
if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running))
return;
- if (rt_se->nr_cpus_allowed == 1)
- list_add(&rt_se->run_list, queue);
- else
- list_add_tail(&rt_se->run_list, queue);
-
+ list_add_tail(&rt_se->run_list, queue);
__set_bit(rt_se_prio(rt_se), array->bitmap);
inc_rt_tasks(rt_se, rt_rq);
* Put task to the end of the run list without the overhead of dequeue
* followed by enqueue.
*/
- static
- void requeue_rt_entity(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se)
+ static void
+ requeue_rt_entity(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se, int head)
{
- struct rt_prio_array *array = &rt_rq->active;
-
if (on_rt_rq(rt_se)) {
- list_del_init(&rt_se->run_list);
- list_add_tail(&rt_se->run_list,
- array->queue + rt_se_prio(rt_se));
+ struct rt_prio_array *array = &rt_rq->active;
+ struct list_head *queue = array->queue + rt_se_prio(rt_se);
+
+ if (head)
+ list_move(&rt_se->run_list, queue);
+ else
+ list_move_tail(&rt_se->run_list, queue);
}
}
- static void requeue_task_rt(struct rq *rq, struct task_struct *p)
+ static void requeue_task_rt(struct rq *rq, struct task_struct *p, int head)
{
struct sched_rt_entity *rt_se = &p->rt;
struct rt_rq *rt_rq;
for_each_sched_rt_entity(rt_se) {
rt_rq = rt_rq_of_se(rt_se);
- requeue_rt_entity(rt_rq, rt_se);
+ requeue_rt_entity(rt_rq, rt_se, head);
}
}
static void yield_task_rt(struct rq *rq)
{
- requeue_task_rt(rq, rq->curr);
+ requeue_task_rt(rq, rq->curr, 0);
}
#ifdef CONFIG_SMP
*/
return task_cpu(p);
}
+
+ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
+ {
+ cpumask_t mask;
+
+ if (rq->curr->rt.nr_cpus_allowed == 1)
+ return;
+
+ if (p->rt.nr_cpus_allowed != 1
+ && cpupri_find(&rq->rd->cpupri, p, &mask))
+ return;
+
+ if (!cpupri_find(&rq->rd->cpupri, rq->curr, &mask))
+ return;
+
+ /*
+ * There appears to be other cpus that can accept
+ * current and none to run 'p', so lets reschedule
+ * to try and push current away:
+ */
+ requeue_task_rt(rq, p, 1);
+ resched_task(rq->curr);
+ }
+
#endif /* CONFIG_SMP */
/*
* to move current somewhere else, making room for our non-migratable
* task.
*/
- if((p->prio == rq->curr->prio)
- && p->rt.nr_cpus_allowed == 1
- && rq->curr->rt.nr_cpus_allowed != 1) {
- cpumask_t mask;
-
- if (cpupri_find(&rq->rd->cpupri, rq->curr, &mask))
- /*
- * There appears to be other cpus that can accept
- * current, so lets reschedule to try and push it away
- */
- resched_task(rq->curr);
- }
+ if (p->prio == rq->curr->prio && !need_resched())
+ check_preempt_equal_prio(rq, p);
#endif
}
if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask))
return -1; /* No targets found */
+ /*
+ * Only consider CPUs that are usable for migration.
+ * I guess we might want to change cpupri_find() to ignore those
+ * in the first place.
+ */
+ cpus_and(*lowest_mask, *lowest_mask, cpu_active_map);
+
/*
* At this point we have built a mask of cpus representing the
* lowest priority tasks in the system. Now we want to elect
next = pick_next_task_rt(this_rq);
- for_each_cpu_mask(cpu, this_rq->rd->rto_mask) {
+ for_each_cpu_mask_nr(cpu, this_rq->rd->rto_mask) {
if (this_cpu == cpu)
continue;
* on the queue:
*/
if (p->rt.run_list.prev != p->rt.run_list.next) {
- requeue_task_rt(rq, p);
+ requeue_task_rt(rq, p, 0);
set_tsk_need_resched(p);
}
}