Merge branch 'timers-nohz-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timer fixes from Ingo Molnar:
 "Main changes:

  - Fix the deadlock reported by Dave Jones et al
  - Clean up and fix nohz_full interaction with arch abilities
  - nohz init code consolidation/cleanup"

* 'timers-nohz-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  nohz: nohz full depends on irq work self IPI support
  nohz: Consolidate nohz full init code
  arm64: Tell irq work about self IPI support
  arm: Tell irq work about self IPI support
  x86: Tell irq work about self IPI support
  irq_work: Force raised irq work to run on irq work interrupt
  irq_work: Introduce arch_irq_work_has_interrupt()
  nohz: Move nohz full init call to tick init

arch/alpha/include/asm/Kbuild

@@ -4,6 +4,7 @@ generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += exec.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
 generic-y += scatterlist.h

arch/arc/include/asm/Kbuild

@@ -18,6 +18,7 @@ generic-y += ioctl.h
 generic-y += ioctls.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kmap_types.h
 generic-y += kvm_para.h
 generic-y += local.h

arch/arm/include/asm/irq_work.h

@@ -0,0 +1,11 @@
+#ifndef __ASM_ARM_IRQ_WORK_H
+#define __ASM_ARM_IRQ_WORK_H
+
+#include <asm/smp_plat.h>
+
+static inline bool arch_irq_work_has_interrupt(void)
+{
+	return is_smp();
+}
+
+#endif /* _ASM_ARM_IRQ_WORK_H */

arch/arm/kernel/smp.c

@@ -499,7 +499,7 @@ void arch_send_call_function_single_ipi(int cpu)
 #ifdef CONFIG_IRQ_WORK
 void arch_irq_work_raise(void)
 {
-	if (is_smp())
+	if (arch_irq_work_has_interrupt())
 		smp_cross_call(cpumask_of(smp_processor_id()), IPI_IRQ_WORK);
 }
 #endif

arch/arm64/include/asm/Kbuild

@@ -9,8 +9,8 @@ generic-y += current.h
 generic-y += delay.h
 generic-y += div64.h
 generic-y += dma.h
-generic-y += emergency-restart.h
 generic-y += early_ioremap.h
+generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += ftrace.h
 generic-y += hash.h

arch/arm64/include/asm/irq_work.h

@@ -0,0 +1,11 @@
+#ifndef __ASM_IRQ_WORK_H
+#define __ASM_IRQ_WORK_H
+
+#include <asm/smp.h>
+
+static inline bool arch_irq_work_has_interrupt(void)
+{
+	return !!__smp_cross_call;
+}
+
+#endif /* __ASM_IRQ_WORK_H */

arch/arm64/include/asm/smp.h

@@ -48,6 +48,8 @@ extern void smp_init_cpus(void);
  */
 extern void set_smp_cross_call(void (*)(const struct cpumask *, unsigned int));
 
+extern void (*__smp_cross_call)(const struct cpumask *, unsigned int);
+
 /*
  * Called from the secondary holding pen, this is the secondary CPU entry point.
  */

arch/arm64/kernel/smp.c

@@ -470,7 +470,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	}
 }
 
-static void (*__smp_cross_call)(const struct cpumask *, unsigned int);
+void (*__smp_cross_call)(const struct cpumask *, unsigned int);
 
 void __init set_smp_cross_call(void (*fn)(const struct cpumask *, unsigned int))
 {

arch/avr32/include/asm/Kbuild

@@ -9,6 +9,7 @@ generic-y += exec.h
 generic-y += futex.h
 generic-y += hash.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h

arch/blackfin/include/asm/Kbuild

@@ -15,6 +15,7 @@ generic-y += hw_irq.h
 generic-y += ioctl.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += kvm_para.h

arch/c6x/include/asm/Kbuild

@@ -22,6 +22,7 @@ generic-y += ioctl.h
 generic-y += ioctls.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += local.h

arch/cris/include/asm/Kbuild

@@ -8,6 +8,7 @@ generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += exec.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += kvm_para.h
 generic-y += linkage.h
 generic-y += mcs_spinlock.h

arch/frv/include/asm/Kbuild

@@ -3,6 +3,7 @@ generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += exec.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
 generic-y += scatterlist.h

arch/hexagon/include/asm/Kbuild

@@ -23,6 +23,7 @@ generic-y += ioctls.h
 generic-y += iomap.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += local.h

arch/ia64/include/asm/Kbuild

@@ -2,6 +2,7 @@
 generic-y += clkdev.h
 generic-y += exec.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += kvm_para.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h

arch/m32r/include/asm/Kbuild

@@ -3,6 +3,7 @@ generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += exec.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += module.h
 generic-y += preempt.h

arch/m68k/include/asm/Kbuild

@@ -11,6 +11,7 @@ generic-y += hw_irq.h
 generic-y += ioctl.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += kvm_para.h

arch/metag/include/asm/Kbuild

@@ -19,6 +19,7 @@ generic-y += ioctl.h
 generic-y += ioctls.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += kvm_para.h

arch/microblaze/include/asm/Kbuild

@@ -5,6 +5,7 @@ generic-y += cputime.h
 generic-y += device.h
 generic-y += exec.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
 generic-y += scatterlist.h

arch/mips/include/asm/Kbuild

@@ -3,6 +3,7 @@ generic-y += cputime.h
 generic-y += current.h
 generic-y += emergency-restart.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mutex.h

arch/mn10300/include/asm/Kbuild

@@ -4,6 +4,7 @@ generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += exec.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
 generic-y += scatterlist.h

arch/openrisc/include/asm/Kbuild

@@ -31,6 +31,7 @@ generic-y += ioctl.h
 generic-y += ioctls.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += kvm_para.h

arch/parisc/include/asm/Kbuild

@@ -10,6 +10,7 @@ generic-y += exec.h
 generic-y += hash.h
 generic-y += hw_irq.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kvm_para.h
 generic-y += local.h

arch/powerpc/include/asm/Kbuild

@@ -1,6 +1,7 @@
 
 generic-y += clkdev.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
 generic-y += rwsem.h

arch/s390/include/asm/Kbuild

@@ -2,6 +2,7 @@
 
 generic-y += clkdev.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
 generic-y += scatterlist.h

arch/score/include/asm/Kbuild

@@ -6,6 +6,7 @@ generic-y += barrier.h
 generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
 generic-y += scatterlist.h

arch/sh/include/asm/Kbuild

@@ -12,6 +12,7 @@ generic-y += hash.h
 generic-y += ioctl.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kvm_para.h
 generic-y += local.h
 generic-y += local64.h

arch/sparc/include/asm/Kbuild

@@ -8,6 +8,7 @@ generic-y += emergency-restart.h
 generic-y += exec.h
 generic-y += hash.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += linkage.h
 generic-y += local.h
 generic-y += local64.h

arch/tile/include/asm/Kbuild

@@ -17,6 +17,7 @@ generic-y += ioctl.h
 generic-y += ioctls.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h

arch/um/include/asm/Kbuild

@@ -14,6 +14,7 @@ generic-y += hash.h
 generic-y += hw_irq.h
 generic-y += io.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += mcs_spinlock.h
 generic-y += mutex.h

arch/unicore32/include/asm/Kbuild

@@ -22,6 +22,7 @@ generic-y += ioctl.h
 generic-y += ioctls.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += local.h

arch/x86/include/asm/irq_work.h

@@ -0,0 +1,11 @@
+#ifndef _ASM_IRQ_WORK_H
+#define _ASM_IRQ_WORK_H
+
+#include <asm/processor.h>
+
+static inline bool arch_irq_work_has_interrupt(void)
+{
+	return cpu_has_apic;
+}
+
+#endif /* _ASM_IRQ_WORK_H */

arch/x86/kernel/irq_work.c

@@ -41,7 +41,7 @@ __visible void smp_trace_irq_work_interrupt(struct pt_regs *regs)
 void arch_irq_work_raise(void)
 {
 #ifdef CONFIG_X86_LOCAL_APIC
-	if (!cpu_has_apic)
+	if (!arch_irq_work_has_interrupt())
 		return;
 
 	apic->send_IPI_self(IRQ_WORK_VECTOR);

arch/xtensa/include/asm/Kbuild

@@ -12,6 +12,7 @@ generic-y += hardirq.h
 generic-y += hash.h
 generic-y += ioctl.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += kvm_para.h

include/asm-generic/irq_work.h

@@ -0,0 +1,10 @@
+#ifndef __ASM_IRQ_WORK_H
+#define __ASM_IRQ_WORK_H
+
+static inline bool arch_irq_work_has_interrupt(void)
+{
+	return false;
+}
+
+#endif /* __ASM_IRQ_WORK_H */
+

include/linux/irq_work.h

@@ -39,9 +39,12 @@ bool irq_work_queue_on(struct irq_work *work, int cpu);
 #endif
 
 void irq_work_run(void);
+void irq_work_tick(void);
 void irq_work_sync(struct irq_work *work);
 
 #ifdef CONFIG_IRQ_WORK
+#include <asm/irq_work.h>
+
 bool irq_work_needs_cpu(void);
 #else
 static inline bool irq_work_needs_cpu(void) { return false; }

include/linux/tick.h

@@ -181,14 +181,12 @@ static inline bool tick_nohz_full_cpu(int cpu)
 	return cpumask_test_cpu(cpu, tick_nohz_full_mask);
 }
 
-extern void tick_nohz_init(void);
 extern void __tick_nohz_full_check(void);
 extern void tick_nohz_full_kick(void);
 extern void tick_nohz_full_kick_cpu(int cpu);
 extern void tick_nohz_full_kick_all(void);
 extern void __tick_nohz_task_switch(struct task_struct *tsk);
 #else
-static inline void tick_nohz_init(void) { }
 static inline bool tick_nohz_full_enabled(void) { return false; }
 static inline bool tick_nohz_full_cpu(int cpu) { return false; }
 static inline void __tick_nohz_full_check(void) { }

init/main.c

@@ -577,7 +577,6 @@ asmlinkage __visible void __init start_kernel(void)
 		local_irq_disable();
 	idr_init_cache();
 	rcu_init();
-	tick_nohz_init();
 	context_tracking_init();
 	radix_tree_init();
 	/* init some links before init_ISA_irqs() */

kernel/irq_work.c

@@ -115,8 +115,10 @@ bool irq_work_needs_cpu(void)
 
 	raised = &__get_cpu_var(raised_list);
 	lazy = &__get_cpu_var(lazy_list);
-	if (llist_empty(raised) && llist_empty(lazy))
-		return false;
+
+	if (llist_empty(raised) || arch_irq_work_has_interrupt())
+		if (llist_empty(lazy))
+			return false;
 
 	/* All work should have been flushed before going offline */
 	WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
@@ -171,6 +173,15 @@ void irq_work_run(void)
 }
 EXPORT_SYMBOL_GPL(irq_work_run);
 
+void irq_work_tick(void)
+{
+	struct llist_head *raised = &__get_cpu_var(raised_list);
+
+	if (!llist_empty(raised) && !arch_irq_work_has_interrupt())
+		irq_work_run_list(raised);
+	irq_work_run_list(&__get_cpu_var(lazy_list));
+}
+
 /*
  * Synchronize against the irq_work @entry, ensures the entry is not
  * currently in use.

kernel/time/tick-common.c

@@ -400,4 +400,5 @@ void tick_resume(void)
 void __init tick_init(void)
 {
 	tick_broadcast_init();
+	tick_nohz_init();
 }

kernel/time/tick-internal.h

@@ -99,6 +99,13 @@ static inline int tick_broadcast_oneshot_active(void) { return 0; }
 static inline bool tick_broadcast_oneshot_available(void) { return false; }
 #endif /* !TICK_ONESHOT */
 
+/* NO_HZ_FULL internal */
+#ifdef CONFIG_NO_HZ_FULL
+extern void tick_nohz_init(void);
+# else
+static inline void tick_nohz_init(void) { }
+#endif
+
 /*
  * Broadcasting support
  */

kernel/time/tick-sched.c

@@ -295,22 +295,12 @@ void __tick_nohz_task_switch(struct task_struct *tsk)
 /* Parse the boot-time nohz CPU list from the kernel parameters. */
 static int __init tick_nohz_full_setup(char *str)
 {
-	int cpu;
-
 	alloc_bootmem_cpumask_var(&tick_nohz_full_mask);
-	alloc_bootmem_cpumask_var(&housekeeping_mask);
 	if (cpulist_parse(str, tick_nohz_full_mask) < 0) {
 		pr_warning("NOHZ: Incorrect nohz_full cpumask\n");
+		free_bootmem_cpumask_var(tick_nohz_full_mask);
 		return 1;
 	}
-
-	cpu = smp_processor_id();
-	if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) {
-		pr_warning("NO_HZ: Clearing %d from nohz_full range for timekeeping\n", cpu);
-		cpumask_clear_cpu(cpu, tick_nohz_full_mask);
-	}
-	cpumask_andnot(housekeeping_mask,
-		       cpu_possible_mask, tick_nohz_full_mask);
 	tick_nohz_full_running = true;
 
 	return 1;
@@ -349,18 +339,11 @@ static int tick_nohz_init_all(void)
 
 #ifdef CONFIG_NO_HZ_FULL_ALL
 	if (!alloc_cpumask_var(&tick_nohz_full_mask, GFP_KERNEL)) {
-		pr_err("NO_HZ: Can't allocate full dynticks cpumask\n");
-		return err;
-	}
-	if (!alloc_cpumask_var(&housekeeping_mask, GFP_KERNEL)) {
-		pr_err("NO_HZ: Can't allocate not-full dynticks cpumask\n");
+		WARN(1, "NO_HZ: Can't allocate full dynticks cpumask\n");
 		return err;
 	}
 	err = 0;
 	cpumask_setall(tick_nohz_full_mask);
-	cpumask_clear_cpu(smp_processor_id(), tick_nohz_full_mask);
-	cpumask_clear(housekeeping_mask);
-	cpumask_set_cpu(smp_processor_id(), housekeeping_mask);
 	tick_nohz_full_running = true;
 #endif
 	return err;
@@ -375,6 +358,37 @@ void __init tick_nohz_init(void)
 			return;
 	}
 
+	if (!alloc_cpumask_var(&housekeeping_mask, GFP_KERNEL)) {
+		WARN(1, "NO_HZ: Can't allocate not-full dynticks cpumask\n");
+		cpumask_clear(tick_nohz_full_mask);
+		tick_nohz_full_running = false;
+		return;
+	}
+
+	/*
+	 * Full dynticks uses irq work to drive the tick rescheduling on safe
+	 * locking contexts. But then we need irq work to raise its own
+	 * interrupts to avoid circular dependency on the tick
+	 */
+	if (!arch_irq_work_has_interrupt()) {
+		pr_warning("NO_HZ: Can't run full dynticks because arch doesn't "
+			   "support irq work self-IPIs\n");
+		cpumask_clear(tick_nohz_full_mask);
+		cpumask_copy(housekeeping_mask, cpu_possible_mask);
+		tick_nohz_full_running = false;
+		return;
+	}
+
+	cpu = smp_processor_id();
+
+	if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) {
+		pr_warning("NO_HZ: Clearing %d from nohz_full range for timekeeping\n", cpu);
+		cpumask_clear_cpu(cpu, tick_nohz_full_mask);
+	}
+
+	cpumask_andnot(housekeeping_mask,
+		       cpu_possible_mask, tick_nohz_full_mask);
+
 	for_each_cpu(cpu, tick_nohz_full_mask)
 		context_tracking_cpu_set(cpu);
 

kernel/time/timer.c

@@ -1385,7 +1385,7 @@ void update_process_times(int user_tick)
 	rcu_check_callbacks(cpu, user_tick);
 #ifdef CONFIG_IRQ_WORK
 	if (in_irq())
-		irq_work_run();
+		irq_work_tick();
 #endif
 	scheduler_tick();
 	run_posix_cpu_timers(p);