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

…inux/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.

arch/alpha/kernel/osf_sys.c

@@ -1139,15 +1139,17 @@ struct rusage32 {
 SYSCALL_DEFINE2(osf_getrusage, int, who, struct rusage32 __user *, ru)
 {
 	struct rusage32 r;
+	cputime_t utime, stime;
 
 	if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN)
 		return -EINVAL;
 
 	memset(&r, 0, sizeof(r));
 	switch (who) {
 	case RUSAGE_SELF:
-		jiffies_to_timeval32(current->utime, &r.ru_utime);
-		jiffies_to_timeval32(current->stime, &r.ru_stime);
+		task_cputime(current, &utime, &stime);
+		jiffies_to_timeval32(utime, &r.ru_utime);
+		jiffies_to_timeval32(stime, &r.ru_stime);
 		r.ru_minflt = current->min_flt;
 		r.ru_majflt = current->maj_flt;
 		break;

arch/ia64/include/asm/cputime.h

@@ -11,99 +11,19 @@
  * as published by the Free Software Foundation; either version
  * 2 of the License, or (at your option) any later version.
  *
- * If we have CONFIG_VIRT_CPU_ACCOUNTING, we measure cpu time in nsec.
+ * If we have CONFIG_VIRT_CPU_ACCOUNTING_NATIVE, we measure cpu time in nsec.
  * Otherwise we measure cpu time in jiffies using the generic definitions.
  */
 
 #ifndef __IA64_CPUTIME_H
 #define __IA64_CPUTIME_H
 
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
-#include <asm-generic/cputime.h>
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+# include <asm-generic/cputime.h>
 #else
-
-#include <linux/time.h>
-#include <linux/jiffies.h>
-#include <asm/processor.h>
-
-typedef u64 __nocast cputime_t;
-typedef u64 __nocast cputime64_t;
-
-#define cputime_one_jiffy		jiffies_to_cputime(1)
-
-/*
- * Convert cputime <-> jiffies (HZ)
- */
-#define cputime_to_jiffies(__ct)	\
-	((__force u64)(__ct) / (NSEC_PER_SEC / HZ))
-#define jiffies_to_cputime(__jif)	\
-	(__force cputime_t)((__jif) * (NSEC_PER_SEC / HZ))
-#define cputime64_to_jiffies64(__ct)	\
-	((__force u64)(__ct) / (NSEC_PER_SEC / HZ))
-#define jiffies64_to_cputime64(__jif)	\
-	(__force cputime64_t)((__jif) * (NSEC_PER_SEC / HZ))
-
-/*
- * Convert cputime <-> microseconds
- */
-#define cputime_to_usecs(__ct)		\
-	((__force u64)(__ct) / NSEC_PER_USEC)
-#define usecs_to_cputime(__usecs)	\
-	(__force cputime_t)((__usecs) * NSEC_PER_USEC)
-#define usecs_to_cputime64(__usecs)	\
-	(__force cputime64_t)((__usecs) * NSEC_PER_USEC)
-
-/*
- * Convert cputime <-> seconds
- */
-#define cputime_to_secs(__ct)		\
-	((__force u64)(__ct) / NSEC_PER_SEC)
-#define secs_to_cputime(__secs)		\
-	(__force cputime_t)((__secs) * NSEC_PER_SEC)
-
-/*
- * Convert cputime <-> timespec (nsec)
- */
-static inline cputime_t timespec_to_cputime(const struct timespec *val)
-{
-	u64 ret = val->tv_sec * NSEC_PER_SEC + val->tv_nsec;
-	return (__force cputime_t) ret;
-}
-static inline void cputime_to_timespec(const cputime_t ct, struct timespec *val)
-{
-	val->tv_sec  = (__force u64) ct / NSEC_PER_SEC;
-	val->tv_nsec = (__force u64) ct % NSEC_PER_SEC;
-}
-
-/*
- * Convert cputime <-> timeval (msec)
- */
-static inline cputime_t timeval_to_cputime(struct timeval *val)
-{
-	u64 ret = val->tv_sec * NSEC_PER_SEC + val->tv_usec * NSEC_PER_USEC;
-	return (__force cputime_t) ret;
-}
-static inline void cputime_to_timeval(const cputime_t ct, struct timeval *val)
-{
-	val->tv_sec = (__force u64) ct / NSEC_PER_SEC;
-	val->tv_usec = ((__force u64) ct % NSEC_PER_SEC) / NSEC_PER_USEC;
-}
-
-/*
- * Convert cputime <-> clock (USER_HZ)
- */
-#define cputime_to_clock_t(__ct)	\
-	((__force u64)(__ct) / (NSEC_PER_SEC / USER_HZ))
-#define clock_t_to_cputime(__x)		\
-	(__force cputime_t)((__x) * (NSEC_PER_SEC / USER_HZ))
-
-/*
- * Convert cputime64 to clock.
- */
-#define cputime64_to_clock_t(__ct)	\
-	cputime_to_clock_t((__force cputime_t)__ct)
-
+# include <asm/processor.h>
+# include <asm-generic/cputime_nsecs.h>
 extern void arch_vtime_task_switch(struct task_struct *tsk);
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 
-#endif /* CONFIG_VIRT_CPU_ACCOUNTING */
 #endif /* __IA64_CPUTIME_H */

arch/ia64/include/asm/thread_info.h

@@ -31,7 +31,7 @@ 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 */
 	struct restart_block restart_block;
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	__u64 ac_stamp;
 	__u64 ac_leave;
 	__u64 ac_stime;
@@ -69,7 +69,7 @@ struct thread_info {
 #define task_stack_page(tsk)	((void *)(tsk))
 
 #define __HAVE_THREAD_FUNCTIONS
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 #define setup_thread_stack(p, org)			\
 	*task_thread_info(p) = *task_thread_info(org);	\
 	task_thread_info(p)->ac_stime = 0;		\

arch/ia64/include/asm/xen/minstate.h

@@ -1,5 +1,5 @@
 
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 /* read ar.itc in advance, and use it before leaving bank 0 */
 #define XEN_ACCOUNT_GET_STAMP		\
 	MOV_FROM_ITC(pUStk, p6, r20, r2);

arch/ia64/kernel/asm-offsets.c

@@ -41,7 +41,7 @@ void foo(void)
 	DEFINE(TI_FLAGS, offsetof(struct thread_info, flags));
 	DEFINE(TI_CPU, offsetof(struct thread_info, cpu));
 	DEFINE(TI_PRE_COUNT, offsetof(struct thread_info, preempt_count));
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	DEFINE(TI_AC_STAMP, offsetof(struct thread_info, ac_stamp));
 	DEFINE(TI_AC_LEAVE, offsetof(struct thread_info, ac_leave));
 	DEFINE(TI_AC_STIME, offsetof(struct thread_info, ac_stime));

arch/ia64/kernel/entry.S

@@ -724,7 +724,7 @@ GLOBAL_ENTRY(__paravirt_leave_syscall)
 #endif
 .global __paravirt_work_processed_syscall;
 __paravirt_work_processed_syscall:
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	adds r2=PT(LOADRS)+16,r12
 	MOV_FROM_ITC(pUStk, p9, r22, r19)	// fetch time at leave
 	adds r18=TI_FLAGS+IA64_TASK_SIZE,r13
@@ -762,7 +762,7 @@ __paravirt_work_processed_syscall:
 
 	ld8 r29=[r2],16		// M0|1 load cr.ipsr
 	ld8 r28=[r3],16		// M0|1 load cr.iip
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 (pUStk) add r14=TI_AC_LEAVE+IA64_TASK_SIZE,r13
 	;;
 	ld8 r30=[r2],16		// M0|1 load cr.ifs
@@ -793,7 +793,7 @@ __paravirt_work_processed_syscall:
 	ld8.fill r1=[r3],16			// M0|1 load r1
 (pUStk) mov r17=1				// A
 	;;
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 (pUStk) st1 [r15]=r17				// M2|3
 #else
 (pUStk) st1 [r14]=r17				// M2|3
@@ -813,7 +813,7 @@ __paravirt_work_processed_syscall:
 	shr.u r18=r19,16		// I0|1 get byte size of existing "dirty" partition
 	COVER				// B    add current frame into dirty partition & set cr.ifs
 	;;
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	mov r19=ar.bsp			// M2   get new backing store pointer
 	st8 [r14]=r22			// M	save time at leave
 	mov f10=f0			// F    clear f10
@@ -948,7 +948,7 @@ GLOBAL_ENTRY(__paravirt_leave_kernel)
 	adds r16=PT(CR_IPSR)+16,r12
 	adds r17=PT(CR_IIP)+16,r12
 
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	.pred.rel.mutex pUStk,pKStk
 	MOV_FROM_PSR(pKStk, r22, r29)	// M2 read PSR now that interrupts are disabled
 	MOV_FROM_ITC(pUStk, p9, r22, r29)	// M  fetch time at leave
@@ -981,23 +981,23 @@ GLOBAL_ENTRY(__paravirt_leave_kernel)
 	;;
 	ld8.fill r12=[r16],16
 	ld8.fill r13=[r17],16
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 (pUStk)	adds r3=TI_AC_LEAVE+IA64_TASK_SIZE,r18
 #else
 (pUStk)	adds r18=IA64_TASK_THREAD_ON_USTACK_OFFSET,r18
 #endif
 	;;
 	ld8 r20=[r16],16	// ar.fpsr
 	ld8.fill r15=[r17],16
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 (pUStk)	adds r18=IA64_TASK_THREAD_ON_USTACK_OFFSET,r18	// deferred
 #endif
 	;;
 	ld8.fill r14=[r16],16
 	ld8.fill r2=[r17]
 (pUStk)	mov r17=1
 	;;
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	//  mmi_ :  ld8 st1 shr;;         mmi_ : st8 st1 shr;;
 	//  mib  :  mov add br        ->  mib  : ld8 add br
 	//  bbb_ :  br  nop cover;;       mbb_ : mov br  cover;;

arch/ia64/kernel/fsys.S

@@ -529,7 +529,7 @@ GLOBAL_ENTRY(paravirt_fsys_bubble_down)
 	nop.i 0
 	;;
 	mov ar.rsc=0				// M2   set enforced lazy mode, pl 0, LE, loadrs=0
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	MOV_FROM_ITC(p0, p6, r30, r23)		// M    get cycle for accounting
 #else
 	nop.m 0
@@ -555,7 +555,7 @@ GLOBAL_ENTRY(paravirt_fsys_bubble_down)
 	cmp.ne pKStk,pUStk=r0,r0		// A    set pKStk <- 0, pUStk <- 1
 	br.call.sptk.many b7=ia64_syscall_setup	// B
 	;;
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	// mov.m r30=ar.itc is called in advance
 	add r16=TI_AC_STAMP+IA64_TASK_SIZE,r2
 	add r17=TI_AC_LEAVE+IA64_TASK_SIZE,r2

arch/ia64/kernel/head.S

@@ -1073,7 +1073,7 @@ END(ia64_native_sched_clock)
 sched_clock = ia64_native_sched_clock
 #endif
 
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 GLOBAL_ENTRY(cycle_to_cputime)
 	alloc r16=ar.pfs,1,0,0,0
 	addl r8=THIS_CPU(ia64_cpu_info) + IA64_CPUINFO_NSEC_PER_CYC_OFFSET,r0
@@ -1091,7 +1091,7 @@ GLOBAL_ENTRY(cycle_to_cputime)
 	shrp r8=r9,r8,IA64_NSEC_PER_CYC_SHIFT
 	br.ret.sptk.many rp
 END(cycle_to_cputime)
-#endif /* CONFIG_VIRT_CPU_ACCOUNTING */
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 
 #ifdef CONFIG_IA64_BRL_EMU
 

arch/ia64/kernel/ivt.S

@@ -784,7 +784,7 @@ ENTRY(break_fault)
 
 (p8)	adds r28=16,r28				// A    switch cr.iip to next bundle
 (p9)	adds r8=1,r8				// A    increment ei to next slot
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	;;
 	mov b6=r30				// I0   setup syscall handler branch reg early
 #else
@@ -801,7 +801,7 @@ ENTRY(break_fault)
 	//
 ///////////////////////////////////////////////////////////////////////
 	st1 [r16]=r0				// M2|3 clear current->thread.on_ustack flag
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	MOV_FROM_ITC(p0, p14, r30, r18)		// M    get cycle for accounting
 #else
 	mov b6=r30				// I0   setup syscall handler branch reg early
@@ -817,7 +817,7 @@ ENTRY(break_fault)
 	cmp.eq p14,p0=r9,r0			// A    are syscalls being traced/audited?
 	br.call.sptk.many b7=ia64_syscall_setup	// B
 1:
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	// mov.m r30=ar.itc is called in advance, and r13 is current
 	add r16=TI_AC_STAMP+IA64_TASK_SIZE,r13	// A
 	add r17=TI_AC_LEAVE+IA64_TASK_SIZE,r13	// A
@@ -1043,7 +1043,7 @@ END(ia64_syscall_setup)
 	DBG_FAULT(16)
 	FAULT(16)
 
-#if defined(CONFIG_VIRT_CPU_ACCOUNTING) && defined(__IA64_ASM_PARAVIRTUALIZED_NATIVE)
+#if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) && defined(__IA64_ASM_PARAVIRTUALIZED_NATIVE)
 	/*
 	 * There is no particular reason for this code to be here, other than
 	 * that there happens to be space here that would go unused otherwise.

arch/ia64/kernel/minstate.h

@@ -4,7 +4,7 @@
 #include "entry.h"
 #include "paravirt_inst.h"
 
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 /* read ar.itc in advance, and use it before leaving bank 0 */
 #define ACCOUNT_GET_STAMP				\
 (pUStk) mov.m r20=ar.itc;

arch/ia64/kernel/time.c

@@ -77,7 +77,7 @@ static struct clocksource clocksource_itc = {
 };
 static struct clocksource *itc_clocksource;
 
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 
 #include <linux/kernel_stat.h>
 
@@ -136,13 +136,14 @@ void vtime_account_system(struct task_struct *tsk)
 
 	account_system_time(tsk, 0, delta, delta);
 }
+EXPORT_SYMBOL_GPL(vtime_account_system);
 
 void vtime_account_idle(struct task_struct *tsk)
 {
 	account_idle_time(vtime_delta(tsk));
 }
 
-#endif /* CONFIG_VIRT_CPU_ACCOUNTING */
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 
 static irqreturn_t
 timer_interrupt (int irq, void *dev_id)

arch/powerpc/configs/chroma_defconfig

@@ -1,6 +1,6 @@
 CONFIG_PPC64=y
 CONFIG_PPC_BOOK3E_64=y
-# CONFIG_VIRT_CPU_ACCOUNTING is not set
+# CONFIG_VIRT_CPU_ACCOUNTING_NATIVE is not set
 CONFIG_SMP=y
 CONFIG_NR_CPUS=256
 CONFIG_EXPERIMENTAL=y

arch/powerpc/configs/corenet64_smp_defconfig

@@ -1,6 +1,6 @@
 CONFIG_PPC64=y
 CONFIG_PPC_BOOK3E_64=y
-# CONFIG_VIRT_CPU_ACCOUNTING is not set
+# CONFIG_VIRT_CPU_ACCOUNTING_NATIVE is not set
 CONFIG_SMP=y
 CONFIG_NR_CPUS=2
 CONFIG_EXPERIMENTAL=y

arch/powerpc/configs/pasemi_defconfig

@@ -1,6 +1,6 @@
 CONFIG_PPC64=y
 CONFIG_ALTIVEC=y
-# CONFIG_VIRT_CPU_ACCOUNTING is not set
+# CONFIG_VIRT_CPU_ACCOUNTING_NATIVE is not set
 CONFIG_SMP=y
 CONFIG_NR_CPUS=2
 CONFIG_EXPERIMENTAL=y

arch/powerpc/include/asm/cputime.h

@@ -8,15 +8,15 @@
  * as published by the Free Software Foundation; either version
  * 2 of the License, or (at your option) any later version.
  *
- * If we have CONFIG_VIRT_CPU_ACCOUNTING, we measure cpu time in
+ * If we have CONFIG_VIRT_CPU_ACCOUNTING_NATIVE, we measure cpu time in
  * the same units as the timebase.  Otherwise we measure cpu time
  * in jiffies using the generic definitions.
  */
 
 #ifndef __POWERPC_CPUTIME_H
 #define __POWERPC_CPUTIME_H
 
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 #include <asm-generic/cputime.h>
 #ifdef __KERNEL__
 static inline void setup_cputime_one_jiffy(void) { }
@@ -231,5 +231,5 @@ static inline cputime_t clock_t_to_cputime(const unsigned long clk)
 static inline void arch_vtime_task_switch(struct task_struct *tsk) { }
 
 #endif /* __KERNEL__ */
-#endif /* CONFIG_VIRT_CPU_ACCOUNTING */
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 #endif /* __POWERPC_CPUTIME_H */

arch/powerpc/include/asm/lppaca.h

@@ -145,7 +145,7 @@ struct dtl_entry {
 extern struct kmem_cache *dtl_cache;
 
 /*
- * When CONFIG_VIRT_CPU_ACCOUNTING = y, the cpu accounting code controls
+ * When CONFIG_VIRT_CPU_ACCOUNTING_NATIVE = y, the cpu accounting code controls
  * reading from the dispatch trace log.  If other code wants to consume
  * DTL entries, it can set this pointer to a function that will get
  * called once for each DTL entry that gets processed.