All of lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH RT 0/5] Linux 3.10.75-rt81-rc1
@ 2015-05-14 14:02 Steven Rostedt
  2015-05-14 14:02 ` [PATCH RT 1/5] kernel/irq_work: fix no_hz deadlock Steven Rostedt
                   ` (5 more replies)
  0 siblings, 6 replies; 9+ messages in thread
From: Steven Rostedt @ 2015-05-14 14:02 UTC (permalink / raw)
  To: linux-kernel, linux-rt-users
  Cc: Thomas Gleixner, Carsten Emde, Sebastian Andrzej Siewior,
	John Kacur, Paul Gortmaker


Dear RT Folks,

This is the RT stable review cycle of patch 3.10.75-rt81-rc1.

Please scream at me if I messed something up. Please test the patches too.

The -rc release will be uploaded to kernel.org and will be deleted when
the final release is out. This is just a review release (or release candidate).

The pre-releases will not be pushed to the git repository, only the
final release is.

If all goes well, this patch will be converted to the next main release
on 5/18/2015.

Enjoy,

-- Steve


To build 3.10.75-rt81-rc1 directly, the following patches should be applied:

  http://www.kernel.org/pub/linux/kernel/v3.x/linux-3.10.tar.xz

  http://www.kernel.org/pub/linux/kernel/v3.x/patch-3.10.75.xz

  http://www.kernel.org/pub/linux/kernel/projects/rt/3.10/patch-3.10.75-rt81-rc1.patch.xz

You can also build from 3.10.75-rt80 by applying the incremental patch:

http://www.kernel.org/pub/linux/kernel/projects/rt/3.10/incr/patch-3.10.75-rt80-rt81-rc1.patch.xz


Changes from 3.10.75-rt80:

---


Marcelo Tosatti (2):
      KVM: lapic: mark LAPIC timer handler as irqsafe
      KVM: use simple waitqueue for vcpu->wq

Mike Galbraith (1):
      hotplug: Use set_cpus_allowed_ptr() in sync_unplug_thread()

Sebastian Andrzej Siewior (1):
      kernel/irq_work: fix no_hz deadlock

Steven Rostedt (Red Hat) (1):
      Linux 3.10.75-rt81-rc1

----
 arch/arm/kvm/arm.c                  |  4 ++--
 arch/arm/kvm/psci.c                 |  4 ++--
 arch/powerpc/include/asm/kvm_host.h |  4 ++--
 arch/powerpc/kernel/time.c          |  2 +-
 arch/powerpc/kvm/book3s_hv.c        | 20 ++++++++--------
 arch/s390/include/asm/kvm_host.h    |  2 +-
 arch/sparc/kernel/pcr.c             |  2 --
 arch/x86/kernel/irq_work.c          |  2 --
 arch/x86/kvm/lapic.c                | 48 ++++++++++++++++++++++++++++++++-----
 include/linux/kvm_host.h            |  4 ++--
 kernel/cpu.c                        |  2 +-
 kernel/irq_work.c                   |  5 +---
 kernel/time/tick-sched.c            |  5 ++++
 kernel/timer.c                      |  2 +-
 localversion-rt                     |  2 +-
 virt/kvm/async_pf.c                 |  4 ++--
 virt/kvm/kvm_main.c                 | 16 ++++++-------
 17 files changed, 81 insertions(+), 47 deletions(-)

^ permalink raw reply	[flat|nested] 9+ messages in thread
* [PATCH RT 1/5] kernel/irq_work: fix no_hz deadlock
  2015-05-14 14:02 [PATCH RT 0/5] Linux 3.10.75-rt81-rc1 Steven Rostedt
@ 2015-05-14 14:02 ` Steven Rostedt
  2015-05-14 14:02 ` [PATCH RT 2/5] KVM: lapic: mark LAPIC timer handler as irqsafe Steven Rostedt
                   ` (4 subsequent siblings)
  5 siblings, 0 replies; 9+ messages in thread
From: Steven Rostedt @ 2015-05-14 14:02 UTC (permalink / raw)
  To: linux-kernel, linux-rt-users
  Cc: Thomas Gleixner, Carsten Emde, Sebastian Andrzej Siewior,
	John Kacur, Paul Gortmaker, stable-rt

[-- Attachment #1: 0001-kernel-irq_work-fix-no_hz-deadlock.patch --]
[-- Type: text/plain, Size: 4242 bytes --]

3.10.75-rt81-rc1 stable review patch.
If anyone has any objections, please let me know.

------------------

From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

Invoking NO_HZ's irq_work callback from timer irq is not working very
well if the callback decides to invoke hrtimer_cancel():

|hrtimer_try_to_cancel+0x55/0x5f
|hrtimer_cancel+0x16/0x28
|tick_nohz_restart+0x17/0x72
|__tick_nohz_full_check+0x8e/0x93
|nohz_full_kick_work_func+0xe/0x10
|irq_work_run_list+0x39/0x57
|irq_work_tick+0x60/0x67
|update_process_times+0x57/0x67
|tick_sched_handle+0x4a/0x59
|tick_sched_timer+0x3b/0x64
|__run_hrtimer+0x7a/0x149
|hrtimer_interrupt+0x1cc/0x2c5

and here we deadlock while waiting for the lock which we are holding.
To fix this I'm doing the same thing that upstream is doing: is the
irq_work dedicated IRQ and use it only for what is marked as "hirq"
which should only be the FULL_NO_HZ related work.

Cc: stable-rt@vger.kernel.org
Reported-by: Carsten Emde <C.Emde@osadl.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
[ Added check for in_irq() before calling irq_work_run() ]
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 arch/powerpc/kernel/time.c | 2 +-
 arch/sparc/kernel/pcr.c    | 2 --
 arch/x86/kernel/irq_work.c | 2 --
 kernel/irq_work.c          | 5 +----
 kernel/time/tick-sched.c   | 5 +++++
 kernel/timer.c             | 2 +-
 6 files changed, 8 insertions(+), 10 deletions(-)

diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index fe66ccabb744..03c314694e58 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/sparc/kernel/pcr.c b/arch/sparc/kernel/pcr.c
index dbb51a6441a6..269af58497aa 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 129b8bb73de2..ca8f703a1e70 100644
--- a/arch/x86/kernel/irq_work.c
+++ b/arch/x86/kernel/irq_work.c
@@ -18,7 +18,6 @@ void smp_irq_work_interrupt(struct pt_regs *regs)
 	irq_exit();
 }
 
-#ifndef CONFIG_PREEMPT_RT_FULL
 void arch_irq_work_raise(void)
 {
 #ifdef CONFIG_X86_LOCAL_APIC
@@ -29,4 +28,3 @@ void arch_irq_work_raise(void)
 	apic_wait_icr_idle();
 #endif
 }
-#endif
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/time/tick-sched.c b/kernel/time/tick-sched.c
index aedf4c21e2c1..b280dba280b3 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -174,6 +174,11 @@ 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
 	/*
diff --git a/kernel/timer.c b/kernel/timer.c
index a2bfef4a8f23..4254253f2267 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
-- 
2.1.4



^ permalink raw reply related	[flat|nested] 9+ messages in thread
* [PATCH RT 2/5] KVM: lapic: mark LAPIC timer handler as irqsafe
  2015-05-14 14:02 [PATCH RT 0/5] Linux 3.10.75-rt81-rc1 Steven Rostedt
  2015-05-14 14:02 ` [PATCH RT 1/5] kernel/irq_work: fix no_hz deadlock Steven Rostedt
@ 2015-05-14 14:02 ` Steven Rostedt
  2015-05-14 14:02 ` [PATCH RT 3/5] KVM: use simple waitqueue for vcpu->wq Steven Rostedt
                   ` (3 subsequent siblings)
  5 siblings, 0 replies; 9+ messages in thread
From: Steven Rostedt @ 2015-05-14 14:02 UTC (permalink / raw)
  To: linux-kernel, linux-rt-users
  Cc: Thomas Gleixner, Carsten Emde, Sebastian Andrzej Siewior,
	John Kacur, Paul Gortmaker, stable-rt, Marcelo Tosatti

[-- Attachment #1: 0002-KVM-lapic-mark-LAPIC-timer-handler-as-irqsafe.patch --]
[-- Type: text/plain, Size: 3262 bytes --]

3.10.75-rt81-rc1 stable review patch.
If anyone has any objections, please let me know.

------------------

From: Marcelo Tosatti <mtosatti@redhat.com>

Since lapic timer handler only wakes up a simple waitqueue,
it can be executed from hardirq context.

Also handle the case where hrtimer_start_expires fails due to -ETIME,
by injecting the interrupt to the guest immediately.

Reduces average cyclictest latency by 3us.

Cc: stable-rt@vger.kernel.org
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 arch/x86/kvm/lapic.c | 42 +++++++++++++++++++++++++++++++++++++++---
 1 file changed, 39 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 681e4e251f00..4500d312f8d9 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1045,8 +1045,38 @@ 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);
 
@@ -1076,9 +1106,11 @@ 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 ", "
@@ -1108,8 +1140,10 @@ 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);
 	}
@@ -1595,6 +1629,7 @@ 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
@@ -1713,7 +1748,8 @@ 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);
 }
 
 /*
-- 
2.1.4



^ permalink raw reply related	[flat|nested] 9+ messages in thread
* [PATCH RT 3/5] KVM: use simple waitqueue for vcpu->wq
  2015-05-14 14:02 [PATCH RT 0/5] Linux 3.10.75-rt81-rc1 Steven Rostedt
  2015-05-14 14:02 ` [PATCH RT 1/5] kernel/irq_work: fix no_hz deadlock Steven Rostedt
  2015-05-14 14:02 ` [PATCH RT 2/5] KVM: lapic: mark LAPIC timer handler as irqsafe Steven Rostedt
@ 2015-05-14 14:02 ` Steven Rostedt
  2015-05-14 14:02 ` [PATCH RT 4/5] hotplug: Use set_cpus_allowed_ptr() in sync_unplug_thread() Steven Rostedt
                   ` (2 subsequent siblings)
  5 siblings, 0 replies; 9+ messages in thread
From: Steven Rostedt @ 2015-05-14 14:02 UTC (permalink / raw)
  To: linux-kernel, linux-rt-users
  Cc: Thomas Gleixner, Carsten Emde, Sebastian Andrzej Siewior,
	John Kacur, Paul Gortmaker, stable-rt, Marcelo Tosatti

[-- Attachment #1: 0003-KVM-use-simple-waitqueue-for-vcpu-wq.patch --]
[-- Type: text/plain, Size: 9568 bytes --]

3.10.75-rt81-rc1 stable review patch.
If anyone has any objections, please let me know.

------------------

From: Marcelo Tosatti <mtosatti@redhat.com>

The problem:

On -RT, an emulated LAPIC timer instances has the following path:

1) hard interrupt
2) ksoftirqd is scheduled
3) ksoftirqd wakes up vcpu thread
4) vcpu thread is scheduled

This extra context switch introduces unnecessary latency in the
LAPIC path for a KVM guest.

The solution:

Allow waking up vcpu thread from hardirq context,
thus avoiding the need for ksoftirqd to be scheduled.

Normal waitqueues make use of spinlocks, which on -RT
are sleepable locks. Therefore, waking up a waitqueue
waiter involves locking a sleeping lock, which
is not allowed from hard interrupt context.

cyclictest command line:

This patch reduces the average latency in my tests from 14us to 11us.

Cc: stable-rt@vger.kernel.org
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 arch/arm/kvm/arm.c                  |  4 ++--
 arch/arm/kvm/psci.c                 |  4 ++--
 arch/powerpc/include/asm/kvm_host.h |  4 ++--
 arch/powerpc/kvm/book3s_hv.c        | 20 ++++++++++----------
 arch/s390/include/asm/kvm_host.h    |  2 +-
 arch/x86/kvm/lapic.c                |  6 +++---
 include/linux/kvm_host.h            |  4 ++--
 virt/kvm/async_pf.c                 |  4 ++--
 virt/kvm/kvm_main.c                 | 16 ++++++++--------
 9 files changed, 32 insertions(+), 32 deletions(-)

diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index ef1703b9587b..6837ef09934c 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -487,9 +487,9 @@ 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 7ee5bb7a3667..6da25764094f 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -35,7 +35,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 {
 	struct kvm *kvm = source_vcpu->kvm;
 	struct kvm_vcpu *vcpu;
-	wait_queue_head_t *wq;
+	struct swait_head *wq;
 	unsigned long cpu_id;
 	phys_addr_t target_pc;
 
@@ -66,7 +66,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 	vcpu->arch.pause = false;
 	smp_mb();		/* Make sure the above is visible */
 
-	wake_up_interruptible(wq);
+	swait_wake_interruptible(wq);
 
 	return KVM_PSCI_RET_SUCCESS;
 }
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index af326cde7cb6..286e65ad2fa1 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -294,7 +294,7 @@ 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;
@@ -566,7 +566,7 @@ 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/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 102ad8a255f3..47193e4ae46f 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -70,11 +70,11 @@ void kvmppc_fast_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;
 	}
 
@@ -534,8 +534,8 @@ 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++;
 			}
 		}
@@ -942,7 +942,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 		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;
 		}
 		kvm->arch.vcores[core] = vcore;
@@ -1315,13 +1315,13 @@ 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;
 }
@@ -1363,7 +1363,7 @@ 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 16bd5d169cdb..1a492e2f1075 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -219,7 +219,7 @@ 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/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 4500d312f8d9..dce9273a3361 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1581,7 +1581,7 @@ 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
@@ -1595,8 +1595,8 @@ 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);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 8db53cfaccdb..be9bcd06c571 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -220,7 +220,7 @@ 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;
@@ -655,7 +655,7 @@ static inline void kvm_arch_free_vm(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/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index ea475cd03511..59a9f1eada67 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -85,8 +85,8 @@ static void async_pf_execute(struct work_struct *work)
 
 	trace_kvm_async_pf_completed(addr, page, gva);
 
-	if (waitqueue_active(&vcpu->wq))
-		wake_up_interruptible(&vcpu->wq);
+	if (swaitqueue_active(&vcpu->wq))
+		swait_wake_interruptible(&vcpu->wq);
 
 	mmdrop(mm);
 	kvm_put_kvm(vcpu->kvm);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index a17f190be58e..71a1f09cd94b 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -233,7 +233,7 @@ 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);
@@ -1672,10 +1672,10 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
  */
 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);
@@ -1689,7 +1689,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 		schedule();
 	}
 
-	finish_wait(&vcpu->wq, &wait);
+	swait_finish(&vcpu->wq, &wait);
 }
 
 #ifndef CONFIG_S390
@@ -1700,11 +1700,11 @@ 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;
 	}
 
@@ -1816,7 +1816,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 				continue;
 			if (vcpu == me)
 				continue;
-			if (waitqueue_active(&vcpu->wq))
+			if (swaitqueue_active(&vcpu->wq))
 				continue;
 			if (!kvm_vcpu_eligible_for_directed_yield(vcpu))
 				continue;
-- 
2.1.4



^ permalink raw reply related	[flat|nested] 9+ messages in thread
* [PATCH RT 4/5] hotplug: Use set_cpus_allowed_ptr() in sync_unplug_thread()
  2015-05-14 14:02 [PATCH RT 0/5] Linux 3.10.75-rt81-rc1 Steven Rostedt
                   ` (2 preceding siblings ...)
  2015-05-14 14:02 ` [PATCH RT 3/5] KVM: use simple waitqueue for vcpu->wq Steven Rostedt
@ 2015-05-14 14:02 ` Steven Rostedt
  2015-05-14 14:02 ` [PATCH RT 5/5] Linux 3.10.75-rt81-rc1 Steven Rostedt
  2015-05-20  3:01 ` [PATCH RT] rt, nohz_full: fix nohz_full for PREEMPT_RT_FULL Steven Rostedt
  5 siblings, 0 replies; 9+ messages in thread
From: Steven Rostedt @ 2015-05-14 14:02 UTC (permalink / raw)
  To: linux-kernel, linux-rt-users
  Cc: Thomas Gleixner, Carsten Emde, Sebastian Andrzej Siewior,
	John Kacur, Paul Gortmaker, Mike Galbraith, stable-rt

[-- Attachment #1: 0004-hotplug-Use-set_cpus_allowed_ptr-in-sync_unplug_thre.patch --]
[-- Type: text/plain, Size: 2131 bytes --]

3.10.75-rt81-rc1 stable review patch.
If anyone has any objections, please let me know.

------------------

From: Mike Galbraith <umgwanakikbuti@gmail.com>

do_set_cpus_allowed() is not safe vs ->sched_class change.

crash> bt
PID: 11676  TASK: ffff88026f979da0  CPU: 22  COMMAND: "sync_unplug/22"
 #0 [ffff880274d25bc8] machine_kexec at ffffffff8103b41c
 #1 [ffff880274d25c18] crash_kexec at ffffffff810d881a
 #2 [ffff880274d25cd8] oops_end at ffffffff81525818
 #3 [ffff880274d25cf8] do_invalid_op at ffffffff81003096
 #4 [ffff880274d25d90] invalid_op at ffffffff8152d3de
    [exception RIP: set_cpus_allowed_rt+18]
    RIP: ffffffff8109e012  RSP: ffff880274d25e48  RFLAGS: 00010202
    RAX: ffffffff8109e000  RBX: ffff88026f979da0  RCX: ffff8802770cb6e8
    RDX: 0000000000000000  RSI: ffffffff81add700  RDI: ffff88026f979da0
    RBP: ffff880274d25e78   R8: ffffffff816112e0   R9: 0000000000000001
    R10: 0000000000000001  R11: 0000000000011940  R12: ffff88026f979da0
    R13: ffff8802770cb6d0  R14: ffff880274d25fd8  R15: 0000000000000000
    ORIG_RAX: ffffffffffffffff  CS: 0010  SS: 0018
 #5 [ffff880274d25e60] do_set_cpus_allowed at ffffffff8108e65f
 #6 [ffff880274d25e80] sync_unplug_thread at ffffffff81058c08
 #7 [ffff880274d25ed8] kthread at ffffffff8107cad6
 #8 [ffff880274d25f50] ret_from_fork at ffffffff8152bbbc
crash> task_struct ffff88026f979da0 | grep class
  sched_class = 0xffffffff816111e0 <fair_sched_class+64>,

Signed-off-by: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: stable-rt@vger.kernel.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/cpu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/cpu.c b/kernel/cpu.c
index b460d99bc761..50ae129671f0 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -234,7 +234,7 @@ 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;
 }
-- 
2.1.4



^ permalink raw reply related	[flat|nested] 9+ messages in thread
* [PATCH RT 5/5] Linux 3.10.75-rt81-rc1
  2015-05-14 14:02 [PATCH RT 0/5] Linux 3.10.75-rt81-rc1 Steven Rostedt
                   ` (3 preceding siblings ...)
  2015-05-14 14:02 ` [PATCH RT 4/5] hotplug: Use set_cpus_allowed_ptr() in sync_unplug_thread() Steven Rostedt
@ 2015-05-14 14:02 ` Steven Rostedt
  2015-05-20  3:01 ` [PATCH RT] rt, nohz_full: fix nohz_full for PREEMPT_RT_FULL Steven Rostedt
  5 siblings, 0 replies; 9+ messages in thread
From: Steven Rostedt @ 2015-05-14 14:02 UTC (permalink / raw)
  To: linux-kernel, linux-rt-users
  Cc: Thomas Gleixner, Carsten Emde, Sebastian Andrzej Siewior,
	John Kacur, Paul Gortmaker

[-- Attachment #1: 0005-Linux-3.10.75-rt81-rc1.patch --]
[-- Type: text/plain, Size: 414 bytes --]

3.10.75-rt81-rc1 stable review patch.
If anyone has any objections, please let me know.

------------------

From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>

---
 localversion-rt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/localversion-rt b/localversion-rt
index 5ba2c2091cf9..738174cbcc3e 100644
--- a/localversion-rt
+++ b/localversion-rt
@@ -1 +1 @@
--rt80
+-rt81-rc1
-- 
2.1.4



^ permalink raw reply related	[flat|nested] 9+ messages in thread
* [PATCH RT] rt, nohz_full: fix nohz_full for PREEMPT_RT_FULL
  2015-05-14 14:02 [PATCH RT 0/5] Linux 3.10.75-rt81-rc1 Steven Rostedt
                   ` (4 preceding siblings ...)
  2015-05-14 14:02 ` [PATCH RT 5/5] Linux 3.10.75-rt81-rc1 Steven Rostedt
@ 2015-05-20  3:01 ` Steven Rostedt
  5 siblings, 0 replies; 9+ messages in thread
From: Steven Rostedt @ 2015-05-20  3:01 UTC (permalink / raw)
  To: linux-kernel, linux-rt-users
  Cc: Thomas Gleixner, Carsten Emde, Sebastian Andrzej Siewior,
	John Kacur, Paul Gortmaker, Mike Galbraith, Muli Baron

I'm adding this patch to the next 3.10-rt release.

-- Steve

>From 26a6945bebcccd8900370b76de2b94bbb0b4678f Mon Sep 17 00:00:00 2001
From: Mike Galbraith <umgwanakikbuti@gmail.com>
Date: Sat, 11 Apr 2015 15:15:59 +0200
Subject: [PATCH] rt, nohz_full: fix nohz_full for PREEMPT_RT_FULL

A task being ticked and trying to shut the tick down will fail due
to having just awakened ksoftirqd, subtract it from nr_running.

Signed-off-by: Mike Galbraith <umgwanakikbuti@gmail.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/sched/core.c      | 29 +++++++++++++++++++++++------
 kernel/time/tick-sched.c |  5 +++++
 2 files changed, 28 insertions(+), 6 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f6d5587cc529..23e289ae4270 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -694,17 +694,34 @@ 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 b280dba280b3..d2e137953d44 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -214,7 +214,12 @@ 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) = {
-- 
2.1.4


^ permalink raw reply related	[flat|nested] 9+ messages in thread
* [PATCH RT 1/5] kernel/irq_work: fix no_hz deadlock
  2015-05-14 14:01 [PATCH RT 0/5] Linux 3.12.40-rt56-rc1 Steven Rostedt
@ 2015-05-14 14:01 ` Steven Rostedt
  0 siblings, 0 replies; 9+ messages in thread
From: Steven Rostedt @ 2015-05-14 14:01 UTC (permalink / raw)
  To: linux-kernel, linux-rt-users
  Cc: Thomas Gleixner, Carsten Emde, Sebastian Andrzej Siewior,
	John Kacur, Paul Gortmaker, stable-rt

[-- Attachment #1: 0001-kernel-irq_work-fix-no_hz-deadlock.patch --]
[-- Type: text/plain, Size: 4261 bytes --]

3.12.40-rt56-rc1 stable review patch.
If anyone has any objections, please let me know.

------------------

From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

Invoking NO_HZ's irq_work callback from timer irq is not working very
well if the callback decides to invoke hrtimer_cancel():

|hrtimer_try_to_cancel+0x55/0x5f
|hrtimer_cancel+0x16/0x28
|tick_nohz_restart+0x17/0x72
|__tick_nohz_full_check+0x8e/0x93
|nohz_full_kick_work_func+0xe/0x10
|irq_work_run_list+0x39/0x57
|irq_work_tick+0x60/0x67
|update_process_times+0x57/0x67
|tick_sched_handle+0x4a/0x59
|tick_sched_timer+0x3b/0x64
|__run_hrtimer+0x7a/0x149
|hrtimer_interrupt+0x1cc/0x2c5

and here we deadlock while waiting for the lock which we are holding.
To fix this I'm doing the same thing that upstream is doing: is the
irq_work dedicated IRQ and use it only for what is marked as "hirq"
which should only be the FULL_NO_HZ related work.

Cc: stable-rt@vger.kernel.org
Reported-by: Carsten Emde <C.Emde@osadl.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
[ Added check for in_irq() before calling irq_work_run() ]
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 arch/powerpc/kernel/time.c | 2 +-
 arch/sparc/kernel/pcr.c    | 2 --
 arch/x86/kernel/irq_work.c | 2 --
 kernel/irq_work.c          | 5 +----
 kernel/time/tick-sched.c   | 5 +++++
 kernel/timer.c             | 2 +-
 6 files changed, 8 insertions(+), 10 deletions(-)

diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 03cbe6f231dc..945505e6ae9e 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/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/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/time/tick-sched.c b/kernel/time/tick-sched.c
index 7e5c94b245e8..2cfd4c740042 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -175,6 +175,11 @@ 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
 	/*
diff --git a/kernel/timer.c b/kernel/timer.c
index 2d9ba1b9f698..286ca044f767 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
-- 
2.1.4



^ permalink raw reply related	[flat|nested] 9+ messages in thread
* [PATCH RT 1/5] kernel/irq_work: fix no_hz deadlock
  2015-05-14 13:59 [PATCH RT 0/5] Linux 3.14.39-rt38-rc1 Steven Rostedt
@ 2015-05-14 13:59 ` Steven Rostedt
  0 siblings, 0 replies; 9+ messages in thread
From: Steven Rostedt @ 2015-05-14 13:59 UTC (permalink / raw)
  To: linux-kernel, linux-rt-users
  Cc: Thomas Gleixner, Carsten Emde, Sebastian Andrzej Siewior,
	John Kacur, Paul Gortmaker, stable-rt

[-- Attachment #1: 0001-kernel-irq_work-fix-no_hz-deadlock.patch --]
[-- Type: text/plain, Size: 4784 bytes --]

3.14.39-rt38-rc1 stable review patch.
If anyone has any objections, please let me know.

------------------

From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

Invoking NO_HZ's irq_work callback from timer irq is not working very
well if the callback decides to invoke hrtimer_cancel():

|hrtimer_try_to_cancel+0x55/0x5f
|hrtimer_cancel+0x16/0x28
|tick_nohz_restart+0x17/0x72
|__tick_nohz_full_check+0x8e/0x93
|nohz_full_kick_work_func+0xe/0x10
|irq_work_run_list+0x39/0x57
|irq_work_tick+0x60/0x67
|update_process_times+0x57/0x67
|tick_sched_handle+0x4a/0x59
|tick_sched_timer+0x3b/0x64
|__run_hrtimer+0x7a/0x149
|hrtimer_interrupt+0x1cc/0x2c5

and here we deadlock while waiting for the lock which we are holding.
To fix this I'm doing the same thing that upstream is doing: is the
irq_work dedicated IRQ and use it only for what is marked as "hirq"
which should only be the FULL_NO_HZ related work.

Cc: stable-rt@vger.kernel.org
Reported-by: Carsten Emde <C.Emde@osadl.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
[ Added back in_irq() check for non PREEMPT_RT configs ]
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 arch/arm/kernel/smp.c      | 2 --
 arch/powerpc/kernel/time.c | 2 +-
 arch/sparc/kernel/pcr.c    | 2 --
 arch/x86/kernel/irq_work.c | 2 --
 kernel/irq_work.c          | 5 +----
 kernel/time/tick-sched.c   | 5 +++++
 kernel/timer.c             | 2 +-
 7 files changed, 8 insertions(+), 12 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/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/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/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/time/tick-sched.c b/kernel/time/tick-sched.c
index ab32130964b6..6c97081f67f9 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
 	/*
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
-- 
2.1.4



^ permalink raw reply related	[flat|nested] 9+ messages in thread
end of thread, other threads:[~2015-05-20  3:01 UTC | newest]

Thread overview: 9+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2015-05-14 14:02 [PATCH RT 0/5] Linux 3.10.75-rt81-rc1 Steven Rostedt
2015-05-14 14:02 ` [PATCH RT 1/5] kernel/irq_work: fix no_hz deadlock Steven Rostedt
2015-05-14 14:02 ` [PATCH RT 2/5] KVM: lapic: mark LAPIC timer handler as irqsafe Steven Rostedt
2015-05-14 14:02 ` [PATCH RT 3/5] KVM: use simple waitqueue for vcpu->wq Steven Rostedt
2015-05-14 14:02 ` [PATCH RT 4/5] hotplug: Use set_cpus_allowed_ptr() in sync_unplug_thread() Steven Rostedt
2015-05-14 14:02 ` [PATCH RT 5/5] Linux 3.10.75-rt81-rc1 Steven Rostedt
2015-05-20  3:01 ` [PATCH RT] rt, nohz_full: fix nohz_full for PREEMPT_RT_FULL Steven Rostedt
  -- strict thread matches above, loose matches on Subject: below --
2015-05-14 14:01 [PATCH RT 0/5] Linux 3.12.40-rt56-rc1 Steven Rostedt
2015-05-14 14:01 ` [PATCH RT 1/5] kernel/irq_work: fix no_hz deadlock Steven Rostedt
2015-05-14 13:59 [PATCH RT 0/5] Linux 3.14.39-rt38-rc1 Steven Rostedt
2015-05-14 13:59 ` [PATCH RT 1/5] kernel/irq_work: fix no_hz deadlock Steven Rostedt

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.