aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--arch/arm/kernel/smp.c2
-rw-r--r--arch/arm/kvm/arm.c4
-rw-r--r--arch/arm/kvm/psci.c4
-rw-r--r--arch/powerpc/include/asm/kvm_host.h4
-rw-r--r--arch/powerpc/kernel/time.c2
-rw-r--r--arch/powerpc/kvm/book3s_hv.c20
-rw-r--r--arch/s390/include/asm/kvm_host.h2
-rw-r--r--arch/sparc/kernel/pcr.c2
-rw-r--r--arch/x86/kernel/irq_work.c2
-rw-r--r--arch/x86/kvm/lapic.c48
-rw-r--r--include/linux/kvm_host.h4
-rw-r--r--kernel/cpu.c2
-rw-r--r--kernel/irq_work.c5
-rw-r--r--kernel/sched/core.c29
-rw-r--r--kernel/time/tick-sched.c10
-rw-r--r--kernel/timer.c2
-rw-r--r--kernel/trace/trace.c2
-rw-r--r--localversion-rt2
-rw-r--r--virt/kvm/async_pf.c4
-rw-r--r--virt/kvm/kvm_main.c16
20 files changed, 110 insertions, 56 deletions
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 686f1d1eb32e..8cd3724714fe 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -463,14 +463,12 @@ void arch_send_call_function_single_ipi(int cpu)
}
#ifdef CONFIG_IRQ_WORK
-#ifndef CONFIG_PREEMPT_RT_FULL
void arch_irq_work_raise(void)
{
if (is_smp())
smp_cross_call(cpumask_of(smp_processor_id()), IPI_IRQ_WORK);
}
#endif
-#endif
static const char *ipi_types[NR_IPI] = {
#define S(x,s) [x] = s
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index f48c520c7dde..7f35063c8882 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -441,9 +441,9 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
static void vcpu_pause(struct kvm_vcpu *vcpu)
{
- wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu);
+ struct swait_head *wq = kvm_arch_vcpu_wq(vcpu);
- wait_event_interruptible(*wq, !vcpu->arch.pause);
+ swait_event_interruptible(*wq, !vcpu->arch.pause);
}
static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu)
diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index 09cf37737ee2..b26f4cb51b1e 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -66,7 +66,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
{
struct kvm *kvm = source_vcpu->kvm;
struct kvm_vcpu *vcpu = NULL, *tmp;
- wait_queue_head_t *wq;
+ struct swait_head *wq;
unsigned long cpu_id;
unsigned long context_id;
unsigned long mpidr;
@@ -123,7 +123,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
smp_mb(); /* Make sure the above is visible */
wq = kvm_arch_vcpu_wq(vcpu);
- wake_up_interruptible(wq);
+ swait_wake_interruptible(wq);
return PSCI_RET_SUCCESS;
}
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 7b3907aad2a9..5f7b79002f81 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -290,7 +290,7 @@ struct kvmppc_vcore {
u8 in_guest;
struct list_head runnable_threads;
spinlock_t lock;
- wait_queue_head_t wq;
+ struct swait_head wq;
u64 stolen_tb;
u64 preempt_tb;
struct kvm_vcpu *runner;
@@ -607,7 +607,7 @@ struct kvm_vcpu_arch {
u8 prodded;
u32 last_inst;
- wait_queue_head_t *wqp;
+ struct swait_head *wqp;
struct kvmppc_vcore *vcore;
int ret;
int trap;
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 6d37d7603a8f..5bec5fd82a7e 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -423,7 +423,7 @@ unsigned long profile_pc(struct pt_regs *regs)
EXPORT_SYMBOL(profile_pc);
#endif
-#if defined(CONFIG_IRQ_WORK) && !defined(CONFIG_PREEMPT_RT_FULL)
+#if defined(CONFIG_IRQ_WORK)
/*
* 64-bit uses a byte in the PACA, 32-bit uses a per-cpu variable...
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 7a25d9218a05..0019281510da 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -74,11 +74,11 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
{
int me;
int cpu = vcpu->cpu;
- wait_queue_head_t *wqp;
+ struct swait_head *wqp;
wqp = kvm_arch_vcpu_wq(vcpu);
- if (waitqueue_active(wqp)) {
- wake_up_interruptible(wqp);
+ if (swaitqueue_active(wqp)) {
+ swait_wake_interruptible(wqp);
++vcpu->stat.halt_wakeup;
}
@@ -583,8 +583,8 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
tvcpu->arch.prodded = 1;
smp_mb();
if (vcpu->arch.ceded) {
- if (waitqueue_active(&vcpu->wq)) {
- wake_up_interruptible(&vcpu->wq);
+ if (swaitqueue_active(&vcpu->wq)) {
+ swait_wake_interruptible(&vcpu->wq);
vcpu->stat.halt_wakeup++;
}
}
@@ -1199,7 +1199,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
if (vcore) {
INIT_LIST_HEAD(&vcore->runnable_threads);
spin_lock_init(&vcore->lock);
- init_waitqueue_head(&vcore->wq);
+ init_swait_head(&vcore->wq);
vcore->preempt_tb = TB_NIL;
vcore->lpcr = kvm->arch.lpcr;
vcore->first_vcpuid = core * threads_per_core;
@@ -1566,13 +1566,13 @@ static void kvmppc_wait_for_exec(struct kvm_vcpu *vcpu, int wait_state)
*/
static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
{
- DEFINE_WAIT(wait);
+ DEFINE_SWAITER(wait);
- prepare_to_wait(&vc->wq, &wait, TASK_INTERRUPTIBLE);
+ swait_prepare(&vc->wq, &wait, TASK_INTERRUPTIBLE);
vc->vcore_state = VCORE_SLEEPING;
spin_unlock(&vc->lock);
schedule();
- finish_wait(&vc->wq, &wait);
+ swait_finish(&vc->wq, &wait);
spin_lock(&vc->lock);
vc->vcore_state = VCORE_INACTIVE;
}
@@ -1613,7 +1613,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
kvmppc_create_dtl_entry(vcpu, vc);
kvmppc_start_thread(vcpu);
} else if (vc->vcore_state == VCORE_SLEEPING) {
- wake_up(&vc->wq);
+ swait_wake(&vc->wq);
}
}
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 892d9571fbf4..ca7b44ed9108 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -236,7 +236,7 @@ struct kvm_s390_local_interrupt {
atomic_t active;
struct kvm_s390_float_interrupt *float_int;
int timer_due; /* event indicator for waitqueue below */
- wait_queue_head_t *wq;
+ struct swait_head *wq;
atomic_t *cpuflags;
unsigned int action_bits;
};
diff --git a/arch/sparc/kernel/pcr.c b/arch/sparc/kernel/pcr.c
index 927d9c5e50f5..7e967c8018c8 100644
--- a/arch/sparc/kernel/pcr.c
+++ b/arch/sparc/kernel/pcr.c
@@ -43,12 +43,10 @@ void __irq_entry deferred_pcr_work_irq(int irq, struct pt_regs *regs)
set_irq_regs(old_regs);
}
-#ifndef CONFIG_PREEMPT_RT_FULL
void arch_irq_work_raise(void)
{
set_softint(1 << PIL_DEFERRED_PCR_WORK);
}
-#endif
const struct pcr_ops *pcr_ops;
EXPORT_SYMBOL_GPL(pcr_ops);
diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c
index 3d21f7bd7b42..1de84e3ab4e0 100644
--- a/arch/x86/kernel/irq_work.c
+++ b/arch/x86/kernel/irq_work.c
@@ -38,7 +38,6 @@ __visible void smp_trace_irq_work_interrupt(struct pt_regs *regs)
exiting_irq();
}
-#ifndef CONFIG_PREEMPT_RT_FULL
void arch_irq_work_raise(void)
{
#ifdef CONFIG_X86_LOCAL_APIC
@@ -49,4 +48,3 @@ void arch_irq_work_raise(void)
apic_wait_icr_idle();
#endif
}
-#endif
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 453e5fbbb7ae..8b25d010d5e4 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1031,8 +1031,38 @@ static void update_divide_count(struct kvm_lapic *apic)
apic->divide_count);
}
+
+static enum hrtimer_restart apic_timer_fn(struct hrtimer *data);
+
+static void apic_timer_expired(struct hrtimer *data)
+{
+ int ret, i = 0;
+ enum hrtimer_restart r;
+ struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer);
+
+ r = apic_timer_fn(data);
+
+ if (r == HRTIMER_RESTART) {
+ do {
+ ret = hrtimer_start_expires(data, HRTIMER_MODE_ABS);
+ if (ret == -ETIME)
+ hrtimer_add_expires_ns(&ktimer->timer,
+ ktimer->period);
+ i++;
+ } while (ret == -ETIME && i < 10);
+
+ if (ret == -ETIME) {
+ printk_once(KERN_ERR "%s: failed to reprogram timer\n",
+ __func__);
+ WARN_ON_ONCE(1);
+ }
+ }
+}
+
+
static void start_apic_timer(struct kvm_lapic *apic)
{
+ int ret;
ktime_t now;
atomic_set(&apic->lapic_timer.pending, 0);
@@ -1062,9 +1092,11 @@ static void start_apic_timer(struct kvm_lapic *apic)
}
}
- hrtimer_start(&apic->lapic_timer.timer,
+ ret = hrtimer_start(&apic->lapic_timer.timer,
ktime_add_ns(now, apic->lapic_timer.period),
HRTIMER_MODE_ABS);
+ if (ret == -ETIME)
+ apic_timer_expired(&apic->lapic_timer.timer);
apic_debug("%s: bus cycle is %" PRId64 "ns, now 0x%016"
PRIx64 ", "
@@ -1094,8 +1126,10 @@ static void start_apic_timer(struct kvm_lapic *apic)
ns = (tscdeadline - guest_tsc) * 1000000ULL;
do_div(ns, this_tsc_khz);
}
- hrtimer_start(&apic->lapic_timer.timer,
+ ret = hrtimer_start(&apic->lapic_timer.timer,
ktime_add_ns(now, ns), HRTIMER_MODE_ABS);
+ if (ret == -ETIME)
+ apic_timer_expired(&apic->lapic_timer.timer);
local_irq_restore(flags);
}
@@ -1533,7 +1567,7 @@ static enum hrtimer_restart apic_timer_fn(struct hrtimer *data)
struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer);
struct kvm_lapic *apic = container_of(ktimer, struct kvm_lapic, lapic_timer);
struct kvm_vcpu *vcpu = apic->vcpu;
- wait_queue_head_t *q = &vcpu->wq;
+ struct swait_head *q = &vcpu->wq;
/*
* There is a race window between reading and incrementing, but we do
@@ -1547,8 +1581,8 @@ static enum hrtimer_restart apic_timer_fn(struct hrtimer *data)
kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu);
}
- if (waitqueue_active(q))
- wake_up_interruptible(q);
+ if (swaitqueue_active(q))
+ swait_wake_interruptible(q);
if (lapic_is_periodic(apic)) {
hrtimer_add_expires_ns(&ktimer->timer, ktimer->period);
@@ -1581,6 +1615,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu)
hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
HRTIMER_MODE_ABS);
apic->lapic_timer.timer.function = apic_timer_fn;
+ apic->lapic_timer.timer.irqsafe = 1;
/*
* APIC is created enabled. This will prevent kvm_lapic_set_base from
@@ -1699,7 +1734,8 @@ void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu)
timer = &vcpu->arch.apic->lapic_timer.timer;
if (hrtimer_cancel(timer))
- hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
+ if (hrtimer_start_expires(timer, HRTIMER_MODE_ABS) == -ETIME)
+ apic_timer_expired(timer);
}
/*
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index bf933ba17529..ebac0c9ee892 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -229,7 +229,7 @@ struct kvm_vcpu {
int fpu_active;
int guest_fpu_loaded, guest_xcr0_loaded;
- wait_queue_head_t wq;
+ struct swait_head wq;
struct pid *pid;
int sigset_active;
sigset_t sigset;
@@ -662,7 +662,7 @@ static inline bool kvm_arch_has_noncoherent_dma(struct kvm *kvm)
}
#endif
-static inline wait_queue_head_t *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu)
+static inline struct swait_head *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu)
{
#ifdef __KVM_HAVE_ARCH_WQP
return vcpu->arch.wqp;
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 285e18b2c420..a3890754e407 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -242,7 +242,7 @@ static int sync_unplug_thread(void *data)
* we don't want any more work on this CPU.
*/
current->flags &= ~PF_NO_SETAFFINITY;
- do_set_cpus_allowed(current, cpu_present_mask);
+ set_cpus_allowed_ptr(current, cpu_present_mask);
migrate_me();
return 0;
}
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index 35d21f93bbe8..5f7d93d89c7f 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -16,6 +16,7 @@
#include <linux/tick.h>
#include <linux/cpu.h>
#include <linux/notifier.h>
+#include <linux/interrupt.h>
#include <asm/processor.h>
@@ -51,11 +52,7 @@ static bool irq_work_claim(struct irq_work *work)
return true;
}
-#ifdef CONFIG_PREEMPT_RT_FULL
-void arch_irq_work_raise(void)
-#else
void __weak arch_irq_work_raise(void)
-#endif
{
/*
* Lame architectures will get the timer tick callback
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 883669d3e293..71c0bb1cdeb0 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -696,17 +696,34 @@ static inline bool got_nohz_idle_kick(void)
#endif /* CONFIG_NO_HZ_COMMON */
#ifdef CONFIG_NO_HZ_FULL
+
+static int ksoftirqd_running(void)
+{
+ struct task_struct *softirqd;
+
+ if (!IS_ENABLED(CONFIG_PREEMPT_RT_FULL))
+ return 0;
+ softirqd = this_cpu_ksoftirqd();
+ if (softirqd && softirqd->on_rq)
+ return 1;
+ return 0;
+}
+
bool sched_can_stop_tick(void)
{
- struct rq *rq;
+ struct rq *rq;
- rq = this_rq();
+ rq = this_rq();
- /* Make sure rq->nr_running update is visible after the IPI */
- smp_rmb();
+ /* Make sure rq->nr_running update is visible after the IPI */
+ smp_rmb();
- /* More than one running task need preemption */
- if (rq->nr_running > 1)
+ /*
+ * More than one running task need preemption
+ *
+ * NOTE, RT: if ksoftirqd is awake, subtract it.
+ */
+ if (rq->nr_running - ksoftirqd_running() > 1)
return false;
return true;
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index ab32130964b6..57d5bb1b3919 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -180,6 +180,11 @@ static bool can_stop_full_tick(void)
return false;
}
+ if (!arch_irq_work_has_interrupt()) {
+ trace_tick_stop(0, "missing irq work interrupt\n");
+ return false;
+ }
+
/* sched_clock_tick() needs us? */
#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
/*
@@ -221,7 +226,12 @@ void __tick_nohz_full_check(void)
static void nohz_full_kick_work_func(struct irq_work *work)
{
+ unsigned long flags;
+
+ /* ksoftirqd processes sirqs with interrupts enabled */
+ local_irq_save(flags);
__tick_nohz_full_check();
+ local_irq_restore(flags);
}
static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = {
diff --git a/kernel/timer.c b/kernel/timer.c
index 34fd2dbba3e3..36b9f10bb3c7 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1450,7 +1450,7 @@ void update_process_times(int user_tick)
scheduler_tick();
run_local_timers();
rcu_check_callbacks(cpu, user_tick);
-#if defined(CONFIG_IRQ_WORK)
+#if defined(CONFIG_IRQ_WORK) && !defined(CONFIG_PREEMPT_RT_FULL)
if (in_irq())
irq_work_run();
#endif
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index b262e442d6c3..a106d356de90 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -468,7 +468,7 @@ int __trace_puts(unsigned long ip, const char *str, int size)
local_save_flags(irq_flags);
buffer = global_trace.trace_buffer.buffer;
- event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc,
+ event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc,
irq_flags, pc);
if (!event)
return 0;
diff --git a/localversion-rt b/localversion-rt
index 21988f9ad53f..8bdfb9a04683 100644
--- a/localversion-rt
+++ b/localversion-rt
@@ -1 +1 @@
--rt34
+-rt42
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index d6a3d0993d88..cd63d6993698 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -96,8 +96,8 @@ static void async_pf_execute(struct work_struct *work)
trace_kvm_async_pf_completed(addr, gva);
- if (waitqueue_active(&vcpu->wq))
- wake_up_interruptible(&vcpu->wq);
+ if (swaitqueue_active(&vcpu->wq))
+ swait_wake_interruptible(&vcpu->wq);
mmput(mm);
kvm_put_kvm(vcpu->kvm);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 024f40795aa0..fa7f9cbf1a6f 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -220,7 +220,7 @@ int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
vcpu->kvm = kvm;
vcpu->vcpu_id = id;
vcpu->pid = NULL;
- init_waitqueue_head(&vcpu->wq);
+ init_swait_head(&vcpu->wq);
kvm_async_pf_vcpu_init(vcpu);
page = alloc_page(GFP_KERNEL | __GFP_ZERO);
@@ -1694,10 +1694,10 @@ EXPORT_SYMBOL_GPL(mark_page_dirty);
*/
void kvm_vcpu_block(struct kvm_vcpu *vcpu)
{
- DEFINE_WAIT(wait);
+ DEFINE_SWAITER(wait);
for (;;) {
- prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
+ swait_prepare(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
if (kvm_arch_vcpu_runnable(vcpu)) {
kvm_make_request(KVM_REQ_UNHALT, vcpu);
@@ -1711,7 +1711,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
schedule();
}
- finish_wait(&vcpu->wq, &wait);
+ swait_finish(&vcpu->wq, &wait);
}
EXPORT_SYMBOL_GPL(kvm_vcpu_block);
@@ -1723,11 +1723,11 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
{
int me;
int cpu = vcpu->cpu;
- wait_queue_head_t *wqp;
+ struct swait_head *wqp;
wqp = kvm_arch_vcpu_wq(vcpu);
- if (waitqueue_active(wqp)) {
- wake_up_interruptible(wqp);
+ if (swaitqueue_active(wqp)) {
+ swait_wake_interruptible(wqp);
++vcpu->stat.halt_wakeup;
}
@@ -1832,7 +1832,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
continue;
if (vcpu == me)
continue;
- if (waitqueue_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu))
+ if (swaitqueue_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu))
continue;
if (!kvm_vcpu_eligible_for_directed_yield(vcpu))
continue;
generated by cgit v1.2.3 (git 2.25.1) at 2024-04-26 11:47:16 +0000