Eric Lee / smarc-ti-linux-kernel

Download as
Browse Code ยป

Commit 99e5ada9407cc19d7c4c05ce2165f20dc46fc093

Authored by Frederic Weisbecker
1 parent 5811d9963e
Exists in master and in 20 other branches dlt-processor-sdk-linux-03.00.00.04, newt-ti-linux-3.12.y, processor-sdk-linux-01.00.00, processor-sdk-linux-02.00.01, smarc-ti-linux-3.12.10, smarc-ti-linux-3.12.y, smarc-ti-linux-3.14.y, smarc-ti-linux-3.15.y, smarc-ti-lsk-linux-4.1.y, smarct3x-processor-sdk-04.01.00.06, smarct3x-processor-sdk-linux-02.00.01, smarct3x-processor-sdk-linux-03.00.00.04, smarct4x-800-processor-sdk-linux-02.00.01, smarct4x-processor-sdk-04.01.00.06, smarct4x-processor-sdk-linux-02.00.01, smarct4x-processor-sdk-linux-03.00.00.04, ti-linux-3.12.y, ti-linux-3.14.y, ti-linux-3.15.y, ti-lsk-linux-4.1.y

nohz: Re-evaluate the tick for the new task after a context switch 

When a task is scheduled in, it may have some properties
of its own that could make the CPU reconsider the need for
the tick: posix cpu timers, perf events, ...

So notify the full dynticks subsystem when a task gets
scheduled in and re-check the tick dependency at this
stage. This is done through a self IPI to avoid messing
up with any current lock scenario.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Geoff Levand <geoff@infradead.org>
Cc: Gilad Ben Yossef <gilad@benyossef.com>
Cc: Hakan Akkan <hakanakkan@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Kevin Hilman <khilman@linaro.org>
Cc: Li Zhong <zhong@linux.vnet.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>

Showing 3 changed files with 24 additions and 0 deletions Side-by-side Diff

include/linux/tick.h
Diff comments   View file @ 99e5ada
... ... @@ -163,12 +163,14 @@
163 163 extern void tick_nohz_full_check(void);
164 164 extern void tick_nohz_full_kick(void);
165 165 extern void tick_nohz_full_kick_all(void);
  166 +extern void tick_nohz_task_switch(struct task_struct *tsk);
166 167 #else
167 168 static inline void tick_nohz_init(void) { }
168 169 static inline int tick_nohz_full_cpu(int cpu) { return 0; }
169 170 static inline void tick_nohz_full_check(void) { }
170 171 static inline void tick_nohz_full_kick(void) { }
171 172 static inline void tick_nohz_full_kick_all(void) { }
  173 +static inline void tick_nohz_task_switch(struct task_struct *tsk) { }
172 174 #endif
173 175  
174 176  
... ... @@ -1896,6 +1896,8 @@
1896 1896 kprobe_flush_task(prev);
1897 1897 put_task_struct(prev);
1898 1898 }
  1899 +
  1900 + tick_nohz_task_switch(current);
1899 1901 }
1900 1902  
1901 1903 #ifdef CONFIG_SMP
kernel/time/tick-sched.c
Diff comments   View file @ 99e5ada
... ... @@ -232,6 +232,26 @@
232 232 preempt_enable();
233 233 }
234 234  
  235 +/*
  236 + * Re-evaluate the need for the tick as we switch the current task.
  237 + * It might need the tick due to per task/process properties:
  238 + * perf events, posix cpu timers, ...
  239 + */
  240 +void tick_nohz_task_switch(struct task_struct *tsk)
  241 +{
  242 + unsigned long flags;
  243 +
  244 + if (!tick_nohz_full_cpu(smp_processor_id()))
  245 + return;
  246 +
  247 + local_irq_save(flags);
  248 +
  249 + if (tick_nohz_tick_stopped() && !can_stop_full_tick())
  250 + tick_nohz_full_kick();
  251 +
  252 + local_irq_restore(flags);
  253 +}
  254 +
235 255 int tick_nohz_full_cpu(int cpu)
236 256 {
237 257 if (!have_nohz_full_mask)