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

…inux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "The main changes in this (fairly busy) cycle were:

   - There was a class of scheduler bugs related to forgetting to update
     the rq-clock timestamp which can cause weird and hard to debug
     problems, so there's a new debug facility for this: which uncovered
     a whole lot of bugs which convinced us that we want to keep the
     debug facility.

     (Peter Zijlstra, Matt Fleming)

   - Various cputime related updates: eliminate cputime and use u64
     nanoseconds directly, simplify and improve the arch interfaces,
     implement delayed accounting more widely, etc. - (Frederic
     Weisbecker)

   - Move code around for better structure plus cleanups (Ingo Molnar)

   - Move IO schedule accounting deeper into the scheduler plus related
     changes to improve the situation (Tejun Heo)

   - ... plus a round of sched/rt and sched/deadline fixes, plus other
     fixes, updats and cleanups"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (85 commits)
  sched/core: Remove unlikely() annotation from sched_move_task()
  sched/autogroup: Rename auto_group.[ch] to autogroup.[ch]
  sched/topology: Split out scheduler topology code from core.c into topology.c
  sched/core: Remove unnecessary #include headers
  sched/rq_clock: Consolidate the ordering of the rq_clock methods
  delayacct: Include <uapi/linux/taskstats.h>
  sched/core: Clean up comments
  sched/rt: Show the 'sched_rr_timeslice' SCHED_RR timeslice tuning knob in milliseconds
  sched/clock: Add dummy clear_sched_clock_stable() stub function
  sched/cputime: Remove generic asm headers
  sched/cputime: Remove unused nsec_to_cputime()
  s390, sched/cputime: Remove unused cputime definitions
  powerpc, sched/cputime: Remove unused cputime definitions
  s390, sched/cputime: Make arch_cpu_idle_time() to return nsecs
  ia64, sched/cputime: Remove unused cputime definitions
  ia64: Convert vtime to use nsec units directly
  ia64, sched/cputime: Move the nsecs based cputime headers to the last arch using it
  sched/cputime: Remove jiffies based cputime
  sched/cputime, vtime: Return nsecs instead of cputime_t to account
  sched/cputime: Complete nsec conversion of tick based accounting
  ...

Documentation/scheduler/sched-deadline.txt

@@ -408,6 +408,11 @@ CONTENTS
   * the new scheduling related syscalls that manipulate it, i.e.,
     sched_setattr() and sched_getattr() are implemented.
 
+ For debugging purposes, the leftover runtime and absolute deadline of a
+ SCHED_DEADLINE task can be retrieved through /proc/<pid>/sched (entries
+ dl.runtime and dl.deadline, both values in ns). A programmatic way to
+ retrieve these values from production code is under discussion.
+
 
 4.3 Default behavior
 ---------------------
@@ -476,6 +481,7 @@ CONTENTS
 
  Still missing:
 
+  - programmatic way to retrieve current runtime and absolute deadline
   - refinements to deadline inheritance, especially regarding the possibility
     of retaining bandwidth isolation among non-interacting tasks. This is
     being studied from both theoretical and practical points of view, and

Documentation/scheduler/sched-rt-group.txt

@@ -158,11 +158,11 @@ as its prone to starvation without deadline scheduling.
 Consider two sibling groups A and B; both have 50% bandwidth, but A's
 period is twice the length of B's.
 
-* group A: period=100000us, runtime=10000us
-	- this runs for 0.01s once every 0.1s
+* group A: period=100000us, runtime=50000us
+	- this runs for 0.05s once every 0.1s
 
-* group B: period= 50000us, runtime=10000us
-	- this runs for 0.01s twice every 0.1s (or once every 0.05 sec).
+* group B: period= 50000us, runtime=25000us
+	- this runs for 0.025s twice every 0.1s (or once every 0.05 sec).
 
 This means that currently a while (1) loop in A will run for the full period of
 B and can starve B's tasks (assuming they are of lower priority) for a whole

arch/alpha/include/asm/Kbuild

@@ -1,7 +1,6 @@
 
 
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += exec.h
 generic-y += export.h
 generic-y += irq_work.h

arch/alpha/kernel/osf_sys.c

@@ -1145,7 +1145,7 @@ struct rusage32 {
 SYSCALL_DEFINE2(osf_getrusage, int, who, struct rusage32 __user *, ru)
 {
 	struct rusage32 r;
-	cputime_t utime, stime;
+	u64 utime, stime;
 	unsigned long utime_jiffies, stime_jiffies;
 
 	if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN)
@@ -1155,16 +1155,16 @@ SYSCALL_DEFINE2(osf_getrusage, int, who, struct rusage32 __user *, ru)
 	switch (who) {
 	case RUSAGE_SELF:
 		task_cputime(current, &utime, &stime);
-		utime_jiffies = cputime_to_jiffies(utime);
-		stime_jiffies = cputime_to_jiffies(stime);
+		utime_jiffies = nsecs_to_jiffies(utime);
+		stime_jiffies = nsecs_to_jiffies(stime);
 		jiffies_to_timeval32(utime_jiffies, &r.ru_utime);
 		jiffies_to_timeval32(stime_jiffies, &r.ru_stime);
 		r.ru_minflt = current->min_flt;
 		r.ru_majflt = current->maj_flt;
 		break;
 	case RUSAGE_CHILDREN:
-		utime_jiffies = cputime_to_jiffies(current->signal->cutime);
-		stime_jiffies = cputime_to_jiffies(current->signal->cstime);
+		utime_jiffies = nsecs_to_jiffies(current->signal->cutime);
+		stime_jiffies = nsecs_to_jiffies(current->signal->cstime);
 		jiffies_to_timeval32(utime_jiffies, &r.ru_utime);
 		jiffies_to_timeval32(stime_jiffies, &r.ru_stime);
 		r.ru_minflt = current->signal->cmin_flt;

arch/arc/include/asm/Kbuild

@@ -2,7 +2,6 @@ generic-y += auxvec.h
 generic-y += bitsperlong.h
 generic-y += bugs.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += device.h
 generic-y += div64.h
 generic-y += emergency-restart.h

arch/arm/include/asm/Kbuild

@@ -2,7 +2,6 @@
 
 generic-y += bitsperlong.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += current.h
 generic-y += early_ioremap.h
 generic-y += emergency-restart.h

arch/arm64/include/asm/Kbuild

@@ -1,6 +1,5 @@
 generic-y += bugs.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += delay.h
 generic-y += div64.h
 generic-y += dma.h

arch/avr32/include/asm/Kbuild

@@ -1,6 +1,5 @@
 
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += delay.h
 generic-y += device.h
 generic-y += div64.h

arch/blackfin/include/asm/Kbuild

@@ -2,7 +2,6 @@
 generic-y += auxvec.h
 generic-y += bitsperlong.h
 generic-y += bugs.h
-generic-y += cputime.h
 generic-y += current.h
 generic-y += device.h
 generic-y += div64.h

arch/c6x/include/asm/Kbuild

@@ -5,7 +5,6 @@ generic-y += barrier.h
 generic-y += bitsperlong.h
 generic-y += bugs.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += current.h
 generic-y += device.h
 generic-y += div64.h

arch/cris/include/asm/Kbuild

@@ -4,7 +4,6 @@ generic-y += barrier.h
 generic-y += bitsperlong.h
 generic-y += clkdev.h
 generic-y += cmpxchg.h
-generic-y += cputime.h
 generic-y += device.h
 generic-y += div64.h
 generic-y += errno.h

arch/frv/include/asm/Kbuild

@@ -1,6 +1,5 @@
 
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += exec.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h

arch/h8300/include/asm/Kbuild

@@ -5,7 +5,6 @@ generic-y += bugs.h
 generic-y += cacheflush.h
 generic-y += checksum.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += current.h
 generic-y += delay.h
 generic-y += device.h

arch/hexagon/include/asm/Kbuild

@@ -6,7 +6,6 @@ generic-y += barrier.h
 generic-y += bug.h
 generic-y += bugs.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += current.h
 generic-y += device.h
 generic-y += div64.h

arch/ia64/include/asm/cputime.h

@@ -18,11 +18,7 @@
 #ifndef __IA64_CPUTIME_H
 #define __IA64_CPUTIME_H
 
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-# include <asm-generic/cputime.h>
-#else
-# include <asm/processor.h>
-# include <asm-generic/cputime_nsecs.h>
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 extern void arch_vtime_task_switch(struct task_struct *tsk);
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 

arch/ia64/include/asm/thread_info.h

@@ -27,6 +27,12 @@ struct thread_info {
 	mm_segment_t addr_limit;	/* user-level address space limit */
 	int preempt_count;		/* 0=premptable, <0=BUG; will also serve as bh-counter */
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+	__u64 utime;
+	__u64 stime;
+	__u64 gtime;
+	__u64 hardirq_time;
+	__u64 softirq_time;
+	__u64 idle_time;
 	__u64 ac_stamp;
 	__u64 ac_leave;
 	__u64 ac_stime;

arch/ia64/kernel/head.S

@@ -1031,7 +1031,7 @@ GLOBAL_ENTRY(ia64_native_sched_clock)
 END(ia64_native_sched_clock)
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-GLOBAL_ENTRY(cycle_to_cputime)
+GLOBAL_ENTRY(cycle_to_nsec)
 	alloc r16=ar.pfs,1,0,0,0
 	addl r8=THIS_CPU(ia64_cpu_info) + IA64_CPUINFO_NSEC_PER_CYC_OFFSET,r0
 	;;
@@ -1047,7 +1047,7 @@ GLOBAL_ENTRY(cycle_to_cputime)
 	;;
 	shrp r8=r9,r8,IA64_NSEC_PER_CYC_SHIFT
 	br.ret.sptk.many rp
-END(cycle_to_cputime)
+END(cycle_to_nsec)
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 
 #ifdef CONFIG_IA64_BRL_EMU

arch/ia64/kernel/setup.c

@@ -619,6 +619,8 @@ setup_arch (char **cmdline_p)
 	check_sal_cache_flush();
 #endif
 	paging_init();
+
+	clear_sched_clock_stable();
 }
 
 /*

arch/ia64/kernel/time.c

@@ -21,6 +21,7 @@
 #include <linux/timex.h>
 #include <linux/timekeeper_internal.h>
 #include <linux/platform_device.h>
+#include <linux/cputime.h>
 
 #include <asm/machvec.h>
 #include <asm/delay.h>
@@ -59,18 +60,43 @@ static struct clocksource *itc_clocksource;
 
 #include <linux/kernel_stat.h>
 
-extern cputime_t cycle_to_cputime(u64 cyc);
+extern u64 cycle_to_nsec(u64 cyc);
 
-void vtime_account_user(struct task_struct *tsk)
+void vtime_flush(struct task_struct *tsk)
 {
-	cputime_t delta_utime;
 	struct thread_info *ti = task_thread_info(tsk);
+	u64 delta;
 
-	if (ti->ac_utime) {
-		delta_utime = cycle_to_cputime(ti->ac_utime);
-		account_user_time(tsk, delta_utime);
-		ti->ac_utime = 0;
+	if (ti->utime)
+		account_user_time(tsk, cycle_to_nsec(ti->utime));
+
+	if (ti->gtime)
+		account_guest_time(tsk, cycle_to_nsec(ti->gtime));
+
+	if (ti->idle_time)
+		account_idle_time(cycle_to_nsec(ti->idle_time));
+
+	if (ti->stime) {
+		delta = cycle_to_nsec(ti->stime);
+		account_system_index_time(tsk, delta, CPUTIME_SYSTEM);
+	}
+
+	if (ti->hardirq_time) {
+		delta = cycle_to_nsec(ti->hardirq_time);
+		account_system_index_time(tsk, delta, CPUTIME_IRQ);
+	}
+
+	if (ti->softirq_time) {
+		delta = cycle_to_nsec(ti->softirq_time));
+		account_system_index_time(tsk, delta, CPUTIME_SOFTIRQ);
 	}
+
+	ti->utime = 0;
+	ti->gtime = 0;
+	ti->idle_time = 0;
+	ti->stime = 0;
+	ti->hardirq_time = 0;
+	ti->softirq_time = 0;
 }
 
 /*
@@ -83,42 +109,49 @@ void arch_vtime_task_switch(struct task_struct *prev)
 	struct thread_info *pi = task_thread_info(prev);
 	struct thread_info *ni = task_thread_info(current);
 
-	pi->ac_stamp = ni->ac_stamp;
+	ni->ac_stamp = pi->ac_stamp;
 	ni->ac_stime = ni->ac_utime = 0;
 }
 
 /*
  * Account time for a transition between system, hard irq or soft irq state.
  * Note that this function is called with interrupts enabled.
  */
-static cputime_t vtime_delta(struct task_struct *tsk)
+static __u64 vtime_delta(struct task_struct *tsk)
 {
 	struct thread_info *ti = task_thread_info(tsk);
-	cputime_t delta_stime;
-	__u64 now;
+	__u64 now, delta_stime;
 
 	WARN_ON_ONCE(!irqs_disabled());
 
 	now = ia64_get_itc();
-
-	delta_stime = cycle_to_cputime(ti->ac_stime + (now - ti->ac_stamp));
-	ti->ac_stime = 0;
+	delta_stime = now - ti->ac_stamp;
 	ti->ac_stamp = now;
 
 	return delta_stime;
 }
 
 void vtime_account_system(struct task_struct *tsk)
 {
-	cputime_t delta = vtime_delta(tsk);
-
-	account_system_time(tsk, 0, delta);
+	struct thread_info *ti = task_thread_info(tsk);
+	__u64 stime = vtime_delta(tsk);
+
+	if ((tsk->flags & PF_VCPU) && !irq_count())
+		ti->gtime += stime;
+	else if (hardirq_count())
+		ti->hardirq_time += stime;
+	else if (in_serving_softirq())
+		ti->softirq_time += stime;
+	else
+		ti->stime += stime;
 }
 EXPORT_SYMBOL_GPL(vtime_account_system);
 
 void vtime_account_idle(struct task_struct *tsk)
 {
-	account_idle_time(vtime_delta(tsk));
+	struct thread_info *ti = task_thread_info(tsk);
+
+	ti->idle_time += vtime_delta(tsk);
 }
 
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */

arch/m32r/include/asm/Kbuild

@@ -1,6 +1,5 @@
 
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += exec.h
 generic-y += irq_work.h
 generic-y += kvm_para.h

arch/m68k/include/asm/Kbuild

@@ -1,7 +1,6 @@
 generic-y += barrier.h
 generic-y += bitsperlong.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += device.h
 generic-y += emergency-restart.h
 generic-y += errno.h

arch/metag/include/asm/Kbuild

@@ -2,7 +2,6 @@ generic-y += auxvec.h
 generic-y += bitsperlong.h
 generic-y += bugs.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += current.h
 generic-y += device.h
 generic-y += dma.h

arch/microblaze/include/asm/Kbuild

@@ -1,7 +1,6 @@
 
 generic-y += barrier.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += device.h
 generic-y += exec.h
 generic-y += irq_work.h

arch/mips/include/asm/Kbuild

@@ -1,7 +1,6 @@
 # MIPS headers
 generic-(CONFIG_GENERIC_CSUM) += checksum.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += current.h
 generic-y += dma-contiguous.h
 generic-y += emergency-restart.h

arch/mips/kernel/binfmt_elfn32.c

@@ -99,15 +99,7 @@ jiffies_to_compat_timeval(unsigned long jiffies, struct compat_timeval *value)
 #undef TASK_SIZE
 #define TASK_SIZE TASK_SIZE32
 
-#undef cputime_to_timeval
-#define cputime_to_timeval cputime_to_compat_timeval
-static __inline__ void
-cputime_to_compat_timeval(const cputime_t cputime, struct compat_timeval *value)
-{
-	unsigned long jiffies = cputime_to_jiffies(cputime);
-
-	value->tv_usec = (jiffies % HZ) * (1000000L / HZ);
-	value->tv_sec = jiffies / HZ;
-}
+#undef ns_to_timeval
+#define ns_to_timeval ns_to_compat_timeval
 
 #include "../../../fs/binfmt_elf.c"

arch/mips/kernel/binfmt_elfo32.c

@@ -102,15 +102,7 @@ jiffies_to_compat_timeval(unsigned long jiffies, struct compat_timeval *value)
 #undef TASK_SIZE
 #define TASK_SIZE TASK_SIZE32
 
-#undef cputime_to_timeval
-#define cputime_to_timeval cputime_to_compat_timeval
-static __inline__ void
-cputime_to_compat_timeval(const cputime_t cputime, struct compat_timeval *value)
-{
-	unsigned long jiffies = cputime_to_jiffies(cputime);
-
-	value->tv_usec = (jiffies % HZ) * (1000000L / HZ);
-	value->tv_sec = jiffies / HZ;
-}
+#undef ns_to_timeval
+#define ns_to_timeval ns_to_compat_timeval
 
 #include "../../../fs/binfmt_elf.c"