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

5 files changed, 55 insertions, 22 deletions

diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index e6bcbe756663..385b85aded19 100644
--- a/kernel/irq_work.c
+++ b/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.
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 0a0608edeb26..052b4b53c3d6 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -400,4 +400,5 @@ void tick_resume(void)
 void __init tick_init(void)
 {
         tick_broadcast_init();
+        tick_nohz_init();
 }
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index c19c1d84b6f3..366aeb4f2c66 100644
--- a/kernel/time/tick-internal.h
+++ b/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
  */
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index f654a8a298fa..5a9ff243588c 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -295,22 +295,12 @@ out:
 /* 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);
 
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index aca5dfe2fa3d..9bbb8344ed3b 100644
--- a/kernel/time/timer.c
+++ b/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);