aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/irq/handle.c2
-rw-r--r--kernel/irq/msi.c6
-rw-r--r--kernel/kmod.c8
-rw-r--r--kernel/memremap.c14
-rw-r--r--kernel/module.c8
-rw-r--r--kernel/sched/core.c22
-rw-r--r--kernel/sched/deadline.c17
-rw-r--r--kernel/sched/fair.c9
-rw-r--r--kernel/sched/idle.c2
-rw-r--r--kernel/sched/sched.h5
-rw-r--r--kernel/time/timekeeping.c2
-rw-r--r--kernel/trace/trace_stack.c11
-rw-r--r--kernel/workqueue.c8
13 files changed, 78 insertions, 36 deletions
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index de41a68fc038..e25a83b67cce 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -22,7 +22,6 @@
/**
* handle_bad_irq - handle spurious and unhandled irqs
- * @irq: the interrupt number
* @desc: description of the interrupt
*
* Handles spurious and unhandled IRQ's. It also prints a debugmessage.
@@ -35,6 +34,7 @@ void handle_bad_irq(struct irq_desc *desc)
kstat_incr_irqs_this_cpu(desc);
ack_bad_irq(irq);
}
+EXPORT_SYMBOL_GPL(handle_bad_irq);
/*
* Special, empty irq handler:
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 7e6512b9dc1f..be9149f62eb8 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -228,11 +228,7 @@ static void msi_domain_update_chip_ops(struct msi_domain_info *info)
{
struct irq_chip *chip = info->chip;
- BUG_ON(!chip);
- if (!chip->irq_mask)
- chip->irq_mask = pci_msi_mask_irq;
- if (!chip->irq_unmask)
- chip->irq_unmask = pci_msi_unmask_irq;
+ BUG_ON(!chip || !chip->irq_mask || !chip->irq_unmask);
if (!chip->irq_set_affinity)
chip->irq_set_affinity = msi_domain_set_affinity;
}
diff --git a/kernel/kmod.c b/kernel/kmod.c
index da98d0593de2..0277d1216f80 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -327,9 +327,13 @@ static void call_usermodehelper_exec_work(struct work_struct *work)
call_usermodehelper_exec_sync(sub_info);
} else {
pid_t pid;
-
+ /*
+ * Use CLONE_PARENT to reparent it to kthreadd; we do not
+ * want to pollute current->children, and we need a parent
+ * that always ignores SIGCHLD to ensure auto-reaping.
+ */
pid = kernel_thread(call_usermodehelper_exec_async, sub_info,
- SIGCHLD);
+ CLONE_PARENT | SIGCHLD);
if (pid < 0) {
sub_info->retval = pid;
umh_complete(sub_info);
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 72b0c66628b6..9d6b55587eaa 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -24,6 +24,16 @@ __weak void __iomem *ioremap_cache(resource_size_t offset, unsigned long size)
}
#endif
+static void *try_ram_remap(resource_size_t offset, size_t size)
+{
+ struct page *page = pfn_to_page(offset >> PAGE_SHIFT);
+
+ /* In the simple case just return the existing linear address */
+ if (!PageHighMem(page))
+ return __va(offset);
+ return NULL; /* fallback to ioremap_cache */
+}
+
/**
* memremap() - remap an iomem_resource as cacheable memory
* @offset: iomem resource start address
@@ -66,8 +76,8 @@ void *memremap(resource_size_t offset, size_t size, unsigned long flags)
* the requested range is potentially in "System RAM"
*/
if (is_ram == REGION_INTERSECTS)
- addr = __va(offset);
- else
+ addr = try_ram_remap(offset, size);
+ if (!addr)
addr = ioremap_cache(offset, size);
}
diff --git a/kernel/module.c b/kernel/module.c
index b86b7bf1be38..8f051a106676 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1063,11 +1063,15 @@ void symbol_put_addr(void *addr)
if (core_kernel_text(a))
return;
- /* module_text_address is safe here: we're supposed to have reference
- * to module from symbol_get, so it can't go away. */
+ /*
+ * Even though we hold a reference on the module; we still need to
+ * disable preemption in order to safely traverse the data structure.
+ */
+ preempt_disable();
modaddr = __module_text_address(a);
BUG_ON(!modaddr);
module_put(modaddr);
+ preempt_enable();
}
EXPORT_SYMBOL_GPL(symbol_put_addr);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 615953141951..bcd214e4b4d6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2366,8 +2366,15 @@ void wake_up_new_task(struct task_struct *p)
trace_sched_wakeup_new(p);
check_preempt_curr(rq, p, WF_FORK);
#ifdef CONFIG_SMP
- if (p->sched_class->task_woken)
+ if (p->sched_class->task_woken) {
+ /*
+ * Nothing relies on rq->lock after this, so its fine to
+ * drop it.
+ */
+ lockdep_unpin_lock(&rq->lock);
p->sched_class->task_woken(rq, p);
+ lockdep_pin_lock(&rq->lock);
+ }
#endif
task_rq_unlock(rq, p, &flags);
}
@@ -2517,11 +2524,11 @@ static struct rq *finish_task_switch(struct task_struct *prev)
* If a task dies, then it sets TASK_DEAD in tsk->state and calls
* schedule one last time. The schedule call will never return, and
* the scheduled task must drop that reference.
- * The test for TASK_DEAD must occur while the runqueue locks are
- * still held, otherwise prev could be scheduled on another cpu, die
- * there before we look at prev->state, and then the reference would
- * be dropped twice.
- * Manfred Spraul <manfred@colorfullife.com>
+ *
+ * We must observe prev->state before clearing prev->on_cpu (in
+ * finish_lock_switch), otherwise a concurrent wakeup can get prev
+ * running on another CPU and we could rave with its RUNNING -> DEAD
+ * transition, resulting in a double drop.
*/
prev_state = prev->state;
vtime_task_switch(prev);
@@ -7238,9 +7245,6 @@ void __init sched_init_smp(void)
alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL);
alloc_cpumask_var(&fallback_doms, GFP_KERNEL);
- /* nohz_full won't take effect without isolating the cpus. */
- tick_nohz_full_add_cpus_to(cpu_isolated_map);
-
sched_init_numa();
/*
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index fc8f01083527..8b0a15e285f9 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -668,8 +668,15 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
* Queueing this task back might have overloaded rq, check if we need
* to kick someone away.
*/
- if (has_pushable_dl_tasks(rq))
+ if (has_pushable_dl_tasks(rq)) {
+ /*
+ * Nothing relies on rq->lock after this, so its safe to drop
+ * rq->lock.
+ */
+ lockdep_unpin_lock(&rq->lock);
push_dl_task(rq);
+ lockdep_pin_lock(&rq->lock);
+ }
#endif
unlock:
@@ -1066,8 +1073,9 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
int target = find_later_rq(p);
if (target != -1 &&
- dl_time_before(p->dl.deadline,
- cpu_rq(target)->dl.earliest_dl.curr))
+ (dl_time_before(p->dl.deadline,
+ cpu_rq(target)->dl.earliest_dl.curr) ||
+ (cpu_rq(target)->dl.dl_nr_running == 0)))
cpu = target;
}
rcu_read_unlock();
@@ -1417,7 +1425,8 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
later_rq = cpu_rq(cpu);
- if (!dl_time_before(task->dl.deadline,
+ if (later_rq->dl.dl_nr_running &&
+ !dl_time_before(task->dl.deadline,
later_rq->dl.earliest_dl.curr)) {
/*
* Target rq has tasks of equal or earlier deadline,
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6e2e3483b1ec..9a5e60fe721a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2363,7 +2363,7 @@ static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq)
*/
tg_weight = atomic_long_read(&tg->load_avg);
tg_weight -= cfs_rq->tg_load_avg_contrib;
- tg_weight += cfs_rq_load_avg(cfs_rq);
+ tg_weight += cfs_rq->load.weight;
return tg_weight;
}
@@ -2373,7 +2373,7 @@ static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
long tg_weight, load, shares;
tg_weight = calc_tg_weight(tg, cfs_rq);
- load = cfs_rq_load_avg(cfs_rq);
+ load = cfs_rq->load.weight;
shares = (tg->shares * load);
if (tg_weight)
@@ -2664,13 +2664,14 @@ static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);
/* Group cfs_rq's load_avg is used for task_h_load and update_cfs_share */
static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
{
- int decayed;
struct sched_avg *sa = &cfs_rq->avg;
+ int decayed, removed = 0;
if (atomic_long_read(&cfs_rq->removed_load_avg)) {
long r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0);
sa->load_avg = max_t(long, sa->load_avg - r, 0);
sa->load_sum = max_t(s64, sa->load_sum - r * LOAD_AVG_MAX, 0);
+ removed = 1;
}
if (atomic_long_read(&cfs_rq->removed_util_avg)) {
@@ -2688,7 +2689,7 @@ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
cfs_rq->load_last_update_time_copy = sa->last_update_time;
#endif
- return decayed;
+ return decayed || removed;
}
/* Update task and its cfs_rq load average */
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 8f177c73ae19..4a2ef5a02fd3 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -57,9 +57,11 @@ static inline int cpu_idle_poll(void)
rcu_idle_enter();
trace_cpu_idle_rcuidle(0, smp_processor_id());
local_irq_enable();
+ stop_critical_timings();
while (!tif_need_resched() &&
(cpu_idle_force_poll || tick_check_broadcast_expired()))
cpu_relax();
+ start_critical_timings();
trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
rcu_idle_exit();
return 1;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 68cda117574c..6d2a119c7ad9 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1078,9 +1078,10 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
* After ->on_cpu is cleared, the task can be moved to a different CPU.
* We must ensure this doesn't happen until the switch is completely
* finished.
+ *
+ * Pairs with the control dependency and rmb in try_to_wake_up().
*/
- smp_wmb();
- prev->on_cpu = 0;
+ smp_store_release(&prev->on_cpu, 0);
#endif
#ifdef CONFIG_DEBUG_SPINLOCK
/* this is a valid case when another task releases the spinlock */
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 3739ac6aa473..44d2cc0436f4 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1251,7 +1251,7 @@ void __init timekeeping_init(void)
set_normalized_timespec64(&tmp, -boot.tv_sec, -boot.tv_nsec);
tk_set_wall_to_mono(tk, tmp);
- timekeeping_update(tk, TK_MIRROR);
+ timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
write_seqcount_end(&tk_core.seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index b746399ab59c..8abf1ba18085 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -85,9 +85,19 @@ check_stack(unsigned long ip, unsigned long *stack)
if (!object_is_on_stack(stack))
return;
+ /* Can't do this from NMI context (can cause deadlocks) */
+ if (in_nmi())
+ return;
+
local_irq_save(flags);
arch_spin_lock(&max_stack_lock);
+ /*
+ * RCU may not be watching, make it see us.
+ * The stack trace code uses rcu_sched.
+ */
+ rcu_irq_enter();
+
/* In case another CPU set the tracer_frame on us */
if (unlikely(!frame_size))
this_size -= tracer_frame;
@@ -169,6 +179,7 @@ check_stack(unsigned long ip, unsigned long *stack)
}
out:
+ rcu_irq_exit();
arch_spin_unlock(&max_stack_lock);
local_irq_restore(flags);
}
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index ca71582fcfab..bcb14cafe007 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1458,13 +1458,13 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq,
timer_stats_timer_set_start_info(&dwork->timer);
dwork->wq = wq;
+ /* timer isn't guaranteed to run in this cpu, record earlier */
+ if (cpu == WORK_CPU_UNBOUND)
+ cpu = raw_smp_processor_id();
dwork->cpu = cpu;
timer->expires = jiffies + delay;
- if (unlikely(cpu != WORK_CPU_UNBOUND))
- add_timer_on(timer, cpu);
- else
- add_timer(timer);
+ add_timer_on(timer, cpu);
}
/**
Powered by cgit, Gruvboxed by Blaster4385.