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

Pull scheduler changes from Ingo Molnar:
 "Main changes:

   - scheduler side full-dynticks (user-space execution is undisturbed
     and receives no timer IRQs) preparation changes that convert the
     cputime accounting code to be full-dynticks ready, from Frederic
     Weisbecker.

   - Initial sched.h split-up changes, by Clark Williams

   - select_idle_sibling() performance improvement by Mike Galbraith:

        " 1 tbench pair (worst case) in a 10 core + SMT package:

          pre   15.22 MB/sec 1 procs
          post 252.01 MB/sec 1 procs "

  - sched_rr_get_interval() ABI fix/change.  We think this detail is not
    used by apps (so it's not an ABI in practice), but lets keep it
    under observation.

  - misc RT scheduling cleanups, optimizations"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (24 commits)
  sched/rt: Add <linux/sched/rt.h> header to <linux/init_task.h>
  cputime: Remove irqsave from seqlock readers
  sched, powerpc: Fix sched.h split-up build failure
  cputime: Restore CPU_ACCOUNTING config defaults for PPC64
  sched/rt: Move rt specific bits into new header file
  sched/rt: Add a tuning knob to allow changing SCHED_RR timeslice
  sched: Move sched.h sysctl bits into separate header
  sched: Fix signedness bug in yield_to()
  sched: Fix select_idle_sibling() bouncing cow syndrome
  sched/rt: Further simplify pick_rt_task()
  sched/rt: Do not account zero delta_exec in update_curr_rt()
  cputime: Safely read cputime of full dynticks CPUs
  kvm: Prepare to add generic guest entry/exit callbacks
  cputime: Use accessors to read task cputime stats
  cputime: Allow dynamic switch between tick/virtual based cputime accounting
  cputime: Generic on-demand virtual cputime accounting
  cputime: Move default nsecs_to_cputime() to jiffies based cputime file
  cputime: Librarize per nsecs resolution cputime definitions
  cputime: Avoid multiplication overflow on utime scaling
  context_tracking: Export context state for generic vtime
  ...

Fix up conflict in kernel/context_tracking.c due to comment additions.

2 files changed, 25 insertions, 2 deletions

diff --git a/init/Kconfig b/init/Kconfig
index dcb68ac42b78..7000d9657402 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -322,10 +322,13 @@ source "kernel/time/Kconfig"
 
 menu "CPU/Task time and stats accounting"
 
+config VIRT_CPU_ACCOUNTING
+        bool
+
 choice
         prompt "Cputime accounting"
         default TICK_CPU_ACCOUNTING if !PPC64
-        default VIRT_CPU_ACCOUNTING if PPC64
+        default VIRT_CPU_ACCOUNTING_NATIVE if PPC64
 
 # Kind of a stub config for the pure tick based cputime accounting
 config TICK_CPU_ACCOUNTING
@@ -338,9 +341,10 @@ config TICK_CPU_ACCOUNTING
 
           If unsure, say Y.
 
-config VIRT_CPU_ACCOUNTING
+config VIRT_CPU_ACCOUNTING_NATIVE
         bool "Deterministic task and CPU time accounting"
         depends on HAVE_VIRT_CPU_ACCOUNTING
+        select VIRT_CPU_ACCOUNTING
         help
           Select this option to enable more accurate task and CPU time
           accounting.  This is done by reading a CPU counter on each
@@ -350,6 +354,23 @@ config VIRT_CPU_ACCOUNTING
           this also enables accounting of stolen time on logically-partitioned
           systems.
 
+config VIRT_CPU_ACCOUNTING_GEN
+        bool "Full dynticks CPU time accounting"
+        depends on HAVE_CONTEXT_TRACKING && 64BIT
+        select VIRT_CPU_ACCOUNTING
+        select CONTEXT_TRACKING
+        help
+          Select this option to enable task and CPU time accounting on full
+          dynticks systems. This accounting is implemented by watching every
+          kernel-user boundaries using the context tracking subsystem.
+          The accounting is thus performed at the expense of some significant
+          overhead.
+
+          For now this is only useful if you are working on the full
+          dynticks subsystem development.
+
+          If unsure, say N.
+
 config IRQ_TIME_ACCOUNTING
         bool "Fine granularity task level IRQ time accounting"
         depends on HAVE_IRQ_TIME_ACCOUNTING
diff --git a/init/init_task.c b/init/init_task.c
index 8b2f3996b035..ba0a7f362d9e 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -2,6 +2,8 @@
 #include <linux/export.h>
 #include <linux/mqueue.h>
 #include <linux/sched.h>
+#include <linux/sched/sysctl.h>
+#include <linux/sched/rt.h>
 #include <linux/init.h>
 #include <linux/fs.h>
 #include <linux/mm.h>