Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/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;
 }
 
 /*
@@ -83,7 +109,7 @@ 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;
 }
 
@@ -91,18 +117,15 @@ void arch_vtime_task_switch(struct task_struct *prev)
  * 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;
@@ -110,15 +133,25 @@ static cputime_t vtime_delta(struct task_struct *tsk)
 
 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"

arch/mn10300/include/asm/Kbuild

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

arch/nios2/include/asm/Kbuild

@@ -6,7 +6,6 @@ generic-y += bitsperlong.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/openrisc/include/asm/Kbuild

@@ -12,7 +12,6 @@ generic-y += checksum.h
 generic-y += clkdev.h
 generic-y += cmpxchg-local.h
 generic-y += cmpxchg.h
-generic-y += cputime.h
 generic-y += current.h
 generic-y += device.h
 generic-y += div64.h

arch/parisc/include/asm/Kbuild

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

arch/parisc/kernel/binfmt_elf32.c

@@ -91,14 +91,7 @@ struct elf_prpsinfo32
 	current->thread.map_base = DEFAULT_MAP_BASE32; \
 	current->thread.task_size = DEFAULT_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/parisc/kernel/setup.c

@@ -36,6 +36,7 @@
 #undef PCI_DEBUG
 #include <linux/proc_fs.h>
 #include <linux/export.h>
+#include <linux/sched.h>
 
 #include <asm/processor.h>
 #include <asm/sections.h>
@@ -176,6 +177,7 @@ void __init setup_arch(char **cmdline_p)
 	conswitchp = &dummy_con;	/* we use do_take_over_console() later ! */
 #endif
 
+	clear_sched_clock_stable();
 }
 
 /*

arch/powerpc/include/asm/accounting.h

@@ -12,9 +12,17 @@
 
 /* Stuff for accurate time accounting */
 struct cpu_accounting_data {
-	unsigned long user_time;	/* accumulated usermode TB ticks */
-	unsigned long system_time;	/* accumulated system TB ticks */
-	unsigned long user_time_scaled;	/* accumulated usermode SPURR ticks */
+	/* Accumulated cputime values to flush on ticks*/
+	unsigned long utime;
+	unsigned long stime;
+	unsigned long utime_scaled;
+	unsigned long stime_scaled;
+	unsigned long gtime;
+	unsigned long hardirq_time;
+	unsigned long softirq_time;
+	unsigned long steal_time;
+	unsigned long idle_time;
+	/* Internal counters */
 	unsigned long starttime;	/* TB value snapshot */
 	unsigned long starttime_user;	/* TB value on exit to usermode */
 	unsigned long startspurr;	/* SPURR value snapshot */

arch/powerpc/include/asm/cputime.h

@@ -16,12 +16,7 @@
 #ifndef __POWERPC_CPUTIME_H
 #define __POWERPC_CPUTIME_H
 
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-#include <asm-generic/cputime.h>
-#ifdef __KERNEL__
-static inline void setup_cputime_one_jiffy(void) { }
-#endif
-#else
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 
 #include <linux/types.h>
 #include <linux/time.h>
@@ -36,65 +31,6 @@ typedef u64 __nocast cputime64_t;
 #define cmpxchg_cputime(ptr, old, new) cmpxchg(ptr, old, new)
 
 #ifdef __KERNEL__
-
-/*
- * One jiffy in timebase units computed during initialization
- */
-extern cputime_t cputime_one_jiffy;
-
-/*
- * Convert cputime <-> jiffies
- */
-extern u64 __cputime_jiffies_factor;
-
-static inline unsigned long cputime_to_jiffies(const cputime_t ct)
-{
-	return mulhdu((__force u64) ct, __cputime_jiffies_factor);
-}
-
-static inline cputime_t jiffies_to_cputime(const unsigned long jif)
-{
-	u64 ct;
-	unsigned long sec;
-
-	/* have to be a little careful about overflow */
-	ct = jif % HZ;
-	sec = jif / HZ;
-	if (ct) {
-		ct *= tb_ticks_per_sec;
-		do_div(ct, HZ);
-	}
-	if (sec)
-		ct += (cputime_t) sec * tb_ticks_per_sec;
-	return (__force cputime_t) ct;
-}
-
-static inline void setup_cputime_one_jiffy(void)
-{
-	cputime_one_jiffy = jiffies_to_cputime(1);
-}
-
-static inline cputime64_t jiffies64_to_cputime64(const u64 jif)
-{
-	u64 ct;
-	u64 sec = jif;
-
-	/* have to be a little careful about overflow */
-	ct = do_div(sec, HZ);
-	if (ct) {
-		ct *= tb_ticks_per_sec;
-		do_div(ct, HZ);
-	}
-	if (sec)
-		ct += (u64) sec * tb_ticks_per_sec;
-	return (__force cputime64_t) ct;
-}
-
-static inline u64 cputime64_to_jiffies64(const cputime_t ct)
-{
-	return mulhdu((__force u64) ct, __cputime_jiffies_factor);
-}
-
 /*
  * Convert cputime <-> microseconds
  */
@@ -105,117 +41,6 @@ static inline unsigned long cputime_to_usecs(const cputime_t ct)
 	return mulhdu((__force u64) ct, __cputime_usec_factor);
 }
 
-static inline cputime_t usecs_to_cputime(const unsigned long us)
-{
-	u64 ct;
-	unsigned long sec;
-
-	/* have to be a little careful about overflow */
-	ct = us % 1000000;
-	sec = us / 1000000;
-	if (ct) {
-		ct *= tb_ticks_per_sec;
-		do_div(ct, 1000000);
-	}
-	if (sec)
-		ct += (cputime_t) sec * tb_ticks_per_sec;
-	return (__force cputime_t) ct;
-}
-
-#define usecs_to_cputime64(us)		usecs_to_cputime(us)
-
-/*
- * Convert cputime <-> seconds
- */
-extern u64 __cputime_sec_factor;
-
-static inline unsigned long cputime_to_secs(const cputime_t ct)
-{
-	return mulhdu((__force u64) ct, __cputime_sec_factor);
-}
-
-static inline cputime_t secs_to_cputime(const unsigned long sec)
-{
-	return (__force cputime_t)((u64) sec * tb_ticks_per_sec);
-}
-
-/*
- * Convert cputime <-> timespec
- */
-static inline void cputime_to_timespec(const cputime_t ct, struct timespec *p)
-{
-	u64 x = (__force u64) ct;
-	unsigned int frac;
-
-	frac = do_div(x, tb_ticks_per_sec);
-	p->tv_sec = x;
-	x = (u64) frac * 1000000000;
-	do_div(x, tb_ticks_per_sec);
-	p->tv_nsec = x;
-}
-
-static inline cputime_t timespec_to_cputime(const struct timespec *p)
-{
-	u64 ct;
-
-	ct = (u64) p->tv_nsec * tb_ticks_per_sec;
-	do_div(ct, 1000000000);
-	return (__force cputime_t)(ct + (u64) p->tv_sec * tb_ticks_per_sec);
-}
-
-/*
- * Convert cputime <-> timeval
- */
-static inline void cputime_to_timeval(const cputime_t ct, struct timeval *p)
-{
-	u64 x = (__force u64) ct;
-	unsigned int frac;
-
-	frac = do_div(x, tb_ticks_per_sec);
-	p->tv_sec = x;
-	x = (u64) frac * 1000000;
-	do_div(x, tb_ticks_per_sec);
-	p->tv_usec = x;
-}
-
-static inline cputime_t timeval_to_cputime(const struct timeval *p)
-{
-	u64 ct;
-
-	ct = (u64) p->tv_usec * tb_ticks_per_sec;
-	do_div(ct, 1000000);
-	return (__force cputime_t)(ct + (u64) p->tv_sec * tb_ticks_per_sec);
-}
-
-/*
- * Convert cputime <-> clock_t (units of 1/USER_HZ seconds)
- */
-extern u64 __cputime_clockt_factor;
-
-static inline unsigned long cputime_to_clock_t(const cputime_t ct)
-{
-	return mulhdu((__force u64) ct, __cputime_clockt_factor);
-}
-
-static inline cputime_t clock_t_to_cputime(const unsigned long clk)
-{
-	u64 ct;
-	unsigned long sec;
-
-	/* have to be a little careful about overflow */
-	ct = clk % USER_HZ;
-	sec = clk / USER_HZ;
-	if (ct) {
-		ct *= tb_ticks_per_sec;
-		do_div(ct, USER_HZ);
-	}
-	if (sec)
-		ct += (u64) sec * tb_ticks_per_sec;
-	return (__force cputime_t) ct;
-}
-
-#define cputime64_to_clock_t(ct)	cputime_to_clock_t((cputime_t)(ct))
-
 /*
  * PPC64 uses PACA which is task independent for storing accounting data while
  * PPC32 uses struct thread_info, therefore at task switch the accounting data

arch/powerpc/include/asm/paca.h

@@ -187,7 +187,6 @@ struct paca_struct {
 
 	/* Stuff for accurate time accounting */
 	struct cpu_accounting_data accounting;
-	u64 stolen_time;		/* TB ticks taken by hypervisor */
 	u64 dtl_ridx;			/* read index in dispatch log */
 	struct dtl_entry *dtl_curr;	/* pointer corresponding to dtl_ridx */
 

arch/powerpc/kernel/asm-offsets.c

@@ -249,9 +249,9 @@ int main(void)
 	DEFINE(ACCOUNT_STARTTIME_USER,
 	       offsetof(struct paca_struct, accounting.starttime_user));
 	DEFINE(ACCOUNT_USER_TIME,
-	       offsetof(struct paca_struct, accounting.user_time));
+	       offsetof(struct paca_struct, accounting.utime));
 	DEFINE(ACCOUNT_SYSTEM_TIME,
-	       offsetof(struct paca_struct, accounting.system_time));
+	       offsetof(struct paca_struct, accounting.stime));
 	DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save));
 	DEFINE(PACA_NAPSTATELOST, offsetof(struct paca_struct, nap_state_lost));
 	DEFINE(PACA_SPRG_VDSO, offsetof(struct paca_struct, sprg_vdso));
@@ -262,9 +262,9 @@ int main(void)
 	DEFINE(ACCOUNT_STARTTIME_USER,
 	       offsetof(struct thread_info, accounting.starttime_user));
 	DEFINE(ACCOUNT_USER_TIME,
-	       offsetof(struct thread_info, accounting.user_time));
+	       offsetof(struct thread_info, accounting.utime));
 	DEFINE(ACCOUNT_SYSTEM_TIME,
-	       offsetof(struct thread_info, accounting.system_time));
+	       offsetof(struct thread_info, accounting.stime));
 #endif
 #endif /* CONFIG_PPC64 */
 

arch/powerpc/kernel/time.c

@@ -57,6 +57,7 @@
 #include <linux/clk-provider.h>
 #include <linux/suspend.h>
 #include <linux/rtc.h>
+#include <linux/cputime.h>
 #include <asm/trace.h>
 
 #include <asm/io.h>
@@ -72,7 +73,6 @@
 #include <asm/smp.h>
 #include <asm/vdso_datapage.h>
 #include <asm/firmware.h>
-#include <asm/cputime.h>
 #include <asm/asm-prototypes.h>
 
 /* powerpc clocksource/clockevent code */
@@ -152,20 +152,11 @@ EXPORT_SYMBOL_GPL(ppc_tb_freq);
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 /*
- * Factors for converting from cputime_t (timebase ticks) to
- * jiffies, microseconds, seconds, and clock_t (1/USER_HZ seconds).
- * These are all stored as 0.64 fixed-point binary fractions.
+ * Factor for converting from cputime_t (timebase ticks) to
+ * microseconds. This is stored as 0.64 fixed-point binary fraction.
  */
-u64 __cputime_jiffies_factor;
-EXPORT_SYMBOL(__cputime_jiffies_factor);
 u64 __cputime_usec_factor;
 EXPORT_SYMBOL(__cputime_usec_factor);
-u64 __cputime_sec_factor;
-EXPORT_SYMBOL(__cputime_sec_factor);
-u64 __cputime_clockt_factor;
-EXPORT_SYMBOL(__cputime_clockt_factor);
-
-cputime_t cputime_one_jiffy;
 
 #ifdef CONFIG_PPC_SPLPAR
 void (*dtl_consumer)(struct dtl_entry *, u64);
@@ -181,14 +172,8 @@ static void calc_cputime_factors(void)
 {
 	struct div_result res;
 
-	div128_by_32(HZ, 0, tb_ticks_per_sec, &res);
-	__cputime_jiffies_factor = res.result_low;
 	div128_by_32(1000000, 0, tb_ticks_per_sec, &res);
 	__cputime_usec_factor = res.result_low;
-	div128_by_32(1, 0, tb_ticks_per_sec, &res);
-	__cputime_sec_factor = res.result_low;
-	div128_by_32(USER_HZ, 0, tb_ticks_per_sec, &res);
-	__cputime_clockt_factor = res.result_low;
 }
 
 /*
@@ -271,25 +256,19 @@ void accumulate_stolen_time(void)
 
 	sst = scan_dispatch_log(acct->starttime_user);
 	ust = scan_dispatch_log(acct->starttime);
-	acct->system_time -= sst;
-	acct->user_time -= ust;
-	local_paca->stolen_time += ust + sst;
+	acct->stime -= sst;
+	acct->utime -= ust;
+	acct->steal_time += ust + sst;
 
 	local_paca->soft_enabled = save_soft_enabled;
 }
 
 static inline u64 calculate_stolen_time(u64 stop_tb)
 {
-	u64 stolen = 0;
+	if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx))
+		return scan_dispatch_log(stop_tb);
 
-	if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) {
-		stolen = scan_dispatch_log(stop_tb);
-		get_paca()->accounting.system_time -= stolen;
-	}
-
-	stolen += get_paca()->stolen_time;
-	get_paca()->stolen_time = 0;
-	return stolen;
+	return 0;
 }
 
 #else /* CONFIG_PPC_SPLPAR */
@@ -305,28 +284,27 @@ static inline u64 calculate_stolen_time(u64 stop_tb)
  * or soft irq state.
  */
 static unsigned long vtime_delta(struct task_struct *tsk,
-				 unsigned long *sys_scaled,
-				 unsigned long *stolen)
+				 unsigned long *stime_scaled,
+				 unsigned long *steal_time)
 {
 	unsigned long now, nowscaled, deltascaled;
-	unsigned long udelta, delta, user_scaled;
+	unsigned long stime;
+	unsigned long utime, utime_scaled;
 	struct cpu_accounting_data *acct = get_accounting(tsk);
 
 	WARN_ON_ONCE(!irqs_disabled());
 
 	now = mftb();
 	nowscaled = read_spurr(now);
-	acct->system_time += now - acct->starttime;
+	stime = now - acct->starttime;
 	acct->starttime = now;
 	deltascaled = nowscaled - acct->startspurr;
 	acct->startspurr = nowscaled;
 
-	*stolen = calculate_stolen_time(now);
+	*steal_time = calculate_stolen_time(now);
 
-	delta = acct->system_time;
-	acct->system_time = 0;
-	udelta = acct->user_time - acct->utime_sspurr;
-	acct->utime_sspurr = acct->user_time;
+	utime = acct->utime - acct->utime_sspurr;
+	acct->utime_sspurr = acct->utime;
 
 	/*
 	 * Because we don't read the SPURR on every kernel entry/exit,
@@ -338,62 +316,105 @@ static unsigned long vtime_delta(struct task_struct *tsk,
 	 * the user ticks get saved up in paca->user_time_scaled to be
 	 * used by account_process_tick.
 	 */
-	*sys_scaled = delta;
-	user_scaled = udelta;
-	if (deltascaled != delta + udelta) {
-		if (udelta) {
-			*sys_scaled = deltascaled * delta / (delta + udelta);
-			user_scaled = deltascaled - *sys_scaled;
+	*stime_scaled = stime;
+	utime_scaled = utime;
+	if (deltascaled != stime + utime) {
+		if (utime) {
+			*stime_scaled = deltascaled * stime / (stime + utime);
+			utime_scaled = deltascaled - *stime_scaled;
 		} else {
-			*sys_scaled = deltascaled;
+			*stime_scaled = deltascaled;
 		}
 	}
-	acct->user_time_scaled += user_scaled;
+	acct->utime_scaled += utime_scaled;
 
-	return delta;
+	return stime;
 }
 
 void vtime_account_system(struct task_struct *tsk)
 {
-	unsigned long delta, sys_scaled, stolen;
+	unsigned long stime, stime_scaled, steal_time;
+	struct cpu_accounting_data *acct = get_accounting(tsk);
+
+	stime = vtime_delta(tsk, &stime_scaled, &steal_time);
 
-	delta = vtime_delta(tsk, &sys_scaled, &stolen);
-	account_system_time(tsk, 0, delta);
-	tsk->stimescaled += sys_scaled;
-	if (stolen)
-		account_steal_time(stolen);
+	stime -= min(stime, steal_time);
+	acct->steal_time += steal_time;
+
+	if ((tsk->flags & PF_VCPU) && !irq_count()) {
+		acct->gtime += stime;
+		acct->utime_scaled += stime_scaled;
+	} else {
+		if (hardirq_count())
+			acct->hardirq_time += stime;
+		else if (in_serving_softirq())
+			acct->softirq_time += stime;
+		else
+			acct->stime += stime;
+
+		acct->stime_scaled += stime_scaled;
+	}
 }
 EXPORT_SYMBOL_GPL(vtime_account_system);
 
 void vtime_account_idle(struct task_struct *tsk)
 {
-	unsigned long delta, sys_scaled, stolen;
+	unsigned long stime, stime_scaled, steal_time;
+	struct cpu_accounting_data *acct = get_accounting(tsk);
 
-	delta = vtime_delta(tsk, &sys_scaled, &stolen);
-	account_idle_time(delta + stolen);
+	stime = vtime_delta(tsk, &stime_scaled, &steal_time);
+	acct->idle_time += stime + steal_time;
 }
 
 /*
- * Transfer the user time accumulated in the paca
- * by the exception entry and exit code to the generic
- * process user time records.
+ * Account the whole cputime accumulated in the paca
  * Must be called with interrupts disabled.
  * Assumes that vtime_account_system/idle() has been called
  * recently (i.e. since the last entry from usermode) so that
  * get_paca()->user_time_scaled is up to date.
  */
-void vtime_account_user(struct task_struct *tsk)
+void vtime_flush(struct task_struct *tsk)
 {
-	cputime_t utime, utimescaled;
 	struct cpu_accounting_data *acct = get_accounting(tsk);
 
-	utime = acct->user_time;
-	utimescaled = acct->user_time_scaled;
-	acct->user_time = 0;
-	acct->user_time_scaled = 0;
+	if (acct->utime)
+		account_user_time(tsk, cputime_to_nsecs(acct->utime));
+
+	if (acct->utime_scaled)
+		tsk->utimescaled += cputime_to_nsecs(acct->utime_scaled);
+
+	if (acct->gtime)
+		account_guest_time(tsk, cputime_to_nsecs(acct->gtime));
+
+	if (acct->steal_time)
+		account_steal_time(cputime_to_nsecs(acct->steal_time));
+
+	if (acct->idle_time)
+		account_idle_time(cputime_to_nsecs(acct->idle_time));
+
+	if (acct->stime)
+		account_system_index_time(tsk, cputime_to_nsecs(acct->stime),
+					  CPUTIME_SYSTEM);
+	if (acct->stime_scaled)
+		tsk->stimescaled += cputime_to_nsecs(acct->stime_scaled);
+
+	if (acct->hardirq_time)
+		account_system_index_time(tsk, cputime_to_nsecs(acct->hardirq_time),
+					  CPUTIME_IRQ);
+	if (acct->softirq_time)
+		account_system_index_time(tsk, cputime_to_nsecs(acct->softirq_time),
+					  CPUTIME_SOFTIRQ);
+
+	acct->utime = 0;
+	acct->utime_scaled = 0;
 	acct->utime_sspurr = 0;
-	account_user_time(tsk, utime);
-	tsk->utimescaled += utimescaled;
+	acct->gtime = 0;
+	acct->steal_time = 0;
+	acct->idle_time = 0;
+	acct->stime = 0;
+	acct->stime_scaled = 0;
+	acct->hardirq_time = 0;
+	acct->softirq_time = 0;
 }
 
 #ifdef CONFIG_PPC32
@@ -407,8 +428,7 @@ void arch_vtime_task_switch(struct task_struct *prev)
 	struct cpu_accounting_data *acct = get_accounting(current);
 
 	acct->starttime = get_accounting(prev)->starttime;
-	acct->system_time = 0;
-	acct->user_time = 0;
+	acct->startspurr = get_accounting(prev)->startspurr;
 }
 #endif /* CONFIG_PPC32 */
 
@@ -1018,7 +1038,6 @@ void __init time_init(void)
 	tb_ticks_per_sec = ppc_tb_freq;
 	tb_ticks_per_usec = ppc_tb_freq / 1000000;
 	calc_cputime_factors();
-	setup_cputime_one_jiffy();
 
 	/*
 	 * Compute scale factor for sched_clock.

arch/powerpc/xmon/xmon.c

@@ -2287,14 +2287,14 @@ static void dump_one_paca(int cpu)
 	DUMP(p, subcore_sibling_mask, "x");
 #endif
 
-	DUMP(p, accounting.user_time, "llx");
-	DUMP(p, accounting.system_time, "llx");
-	DUMP(p, accounting.user_time_scaled, "llx");
+	DUMP(p, accounting.utime, "llx");
+	DUMP(p, accounting.stime, "llx");
+	DUMP(p, accounting.utime_scaled, "llx");
 	DUMP(p, accounting.starttime, "llx");
 	DUMP(p, accounting.starttime_user, "llx");
 	DUMP(p, accounting.startspurr, "llx");
 	DUMP(p, accounting.utime_sspurr, "llx");
-	DUMP(p, stolen_time, "llx");
+	DUMP(p, accounting.steal_time, "llx");
 #undef DUMP
 
 	catch_memory_errors = 0;

arch/s390/appldata/appldata_os.c

@@ -113,21 +113,21 @@ static void appldata_get_os_data(void *data)
 	j = 0;
 	for_each_online_cpu(i) {
 		os_data->os_cpu[j].per_cpu_user =
-			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_USER]);
+			nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_USER]);
 		os_data->os_cpu[j].per_cpu_nice =
-			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_NICE]);
+			nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_NICE]);
 		os_data->os_cpu[j].per_cpu_system =
-			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]);
+			nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]);
 		os_data->os_cpu[j].per_cpu_idle =
-			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IDLE]);
+			nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IDLE]);
 		os_data->os_cpu[j].per_cpu_irq =
-			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IRQ]);
+			nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IRQ]);
 		os_data->os_cpu[j].per_cpu_softirq =
-			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]);
+			nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]);
 		os_data->os_cpu[j].per_cpu_iowait =
-			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IOWAIT]);
+			nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IOWAIT]);
 		os_data->os_cpu[j].per_cpu_steal =
-			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_STEAL]);
+			nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_STEAL]);
 		os_data->os_cpu[j].cpu_id = i;
 		j++;
 	}

arch/s390/include/asm/cputime.h

@@ -25,33 +25,6 @@ static inline unsigned long __div(unsigned long long n, unsigned long base)
 	return n / base;
 }
 
-#define cputime_one_jiffy		jiffies_to_cputime(1)
-
-/*
- * Convert cputime to jiffies and back.
- */
-static inline unsigned long cputime_to_jiffies(const cputime_t cputime)
-{
-	return __div((__force unsigned long long) cputime, CPUTIME_PER_SEC / HZ);
-}
-
-static inline cputime_t jiffies_to_cputime(const unsigned int jif)
-{
-	return (__force cputime_t)(jif * (CPUTIME_PER_SEC / HZ));
-}
-
-static inline u64 cputime64_to_jiffies64(cputime64_t cputime)
-{
-	unsigned long long jif = (__force unsigned long long) cputime;
-	do_div(jif, CPUTIME_PER_SEC / HZ);
-	return jif;
-}
-
-static inline cputime64_t jiffies64_to_cputime64(const u64 jif)
-{
-	return (__force cputime64_t)(jif * (CPUTIME_PER_SEC / HZ));
-}
-
 /*
  * Convert cputime to microseconds and back.
  */
@@ -60,88 +33,8 @@ static inline unsigned int cputime_to_usecs(const cputime_t cputime)
 	return (__force unsigned long long) cputime >> 12;
 }
 
-static inline cputime_t usecs_to_cputime(const unsigned int m)
-{
-	return (__force cputime_t)(m * CPUTIME_PER_USEC);
-}
-
-#define usecs_to_cputime64(m)		usecs_to_cputime(m)
-
-/*
- * Convert cputime to milliseconds and back.
- */
-static inline unsigned int cputime_to_secs(const cputime_t cputime)
-{
-	return __div((__force unsigned long long) cputime, CPUTIME_PER_SEC / 2) >> 1;
-}
-
-static inline cputime_t secs_to_cputime(const unsigned int s)
-{
-	return (__force cputime_t)(s * CPUTIME_PER_SEC);
-}
-
-/*
- * Convert cputime to timespec and back.
- */
-static inline cputime_t timespec_to_cputime(const struct timespec *value)
-{
-	unsigned long long ret = value->tv_sec * CPUTIME_PER_SEC;
-	return (__force cputime_t)(ret + __div(value->tv_nsec * CPUTIME_PER_USEC, NSEC_PER_USEC));
-}
-
-static inline void cputime_to_timespec(const cputime_t cputime,
-				       struct timespec *value)
-{
-	unsigned long long __cputime = (__force unsigned long long) cputime;
-	value->tv_nsec = (__cputime % CPUTIME_PER_SEC) * NSEC_PER_USEC / CPUTIME_PER_USEC;
-	value->tv_sec = __cputime / CPUTIME_PER_SEC;
-}
-
-/*
- * Convert cputime to timeval and back.
- * Since cputime and timeval have the same resolution (microseconds)
- * this is easy.
- */
-static inline cputime_t timeval_to_cputime(const struct timeval *value)
-{
-	unsigned long long ret = value->tv_sec * CPUTIME_PER_SEC;
-	return (__force cputime_t)(ret + value->tv_usec * CPUTIME_PER_USEC);
-}
-
-static inline void cputime_to_timeval(const cputime_t cputime,
-				      struct timeval *value)
-{
-	unsigned long long __cputime = (__force unsigned long long) cputime;
-	value->tv_usec = (__cputime % CPUTIME_PER_SEC) / CPUTIME_PER_USEC;
-	value->tv_sec = __cputime / CPUTIME_PER_SEC;
-}
-
-/*
- * Convert cputime to clock and back.
- */
-static inline clock_t cputime_to_clock_t(cputime_t cputime)
-{
-	unsigned long long clock = (__force unsigned long long) cputime;
-	do_div(clock, CPUTIME_PER_SEC / USER_HZ);
-	return clock;
-}
-
-static inline cputime_t clock_t_to_cputime(unsigned long x)
-{
-	return (__force cputime_t)(x * (CPUTIME_PER_SEC / USER_HZ));
-}
-
-/*
- * Convert cputime64 to clock.
- */
-static inline clock_t cputime64_to_clock_t(cputime64_t cputime)
-{
-	unsigned long long clock = (__force unsigned long long) cputime;
-	do_div(clock, CPUTIME_PER_SEC / USER_HZ);
-	return clock;
-}
 
-cputime64_t arch_cpu_idle_time(int cpu);
+u64 arch_cpu_idle_time(int cpu);
 
 #define arch_idle_time(cpu) arch_cpu_idle_time(cpu)
 

arch/s390/include/asm/lowcore.h

@@ -85,53 +85,56 @@ struct lowcore {
 	__u64	mcck_enter_timer;		/* 0x02c0 */
 	__u64	exit_timer;			/* 0x02c8 */
 	__u64	user_timer;			/* 0x02d0 */
-	__u64	system_timer;			/* 0x02d8 */
-	__u64	steal_timer;			/* 0x02e0 */
-	__u64	last_update_timer;		/* 0x02e8 */
-	__u64	last_update_clock;		/* 0x02f0 */
-	__u64	int_clock;			/* 0x02f8 */
-	__u64	mcck_clock;			/* 0x0300 */
-	__u64	clock_comparator;		/* 0x0308 */
+	__u64	guest_timer;			/* 0x02d8 */
+	__u64	system_timer;			/* 0x02e0 */
+	__u64	hardirq_timer;			/* 0x02e8 */
+	__u64	softirq_timer;			/* 0x02f0 */
+	__u64	steal_timer;			/* 0x02f8 */
+	__u64	last_update_timer;		/* 0x0300 */
+	__u64	last_update_clock;		/* 0x0308 */
+	__u64	int_clock;			/* 0x0310 */
+	__u64	mcck_clock;			/* 0x0318 */
+	__u64	clock_comparator;		/* 0x0320 */
 
 	/* Current process. */
-	__u64	current_task;			/* 0x0310 */
-	__u8	pad_0x318[0x320-0x318];		/* 0x0318 */
-	__u64	kernel_stack;			/* 0x0320 */
+	__u64	current_task;			/* 0x0328 */
+	__u8	pad_0x318[0x320-0x318];		/* 0x0330 */
+	__u64	kernel_stack;			/* 0x0338 */
 
 	/* Interrupt, panic and restart stack. */
-	__u64	async_stack;			/* 0x0328 */
-	__u64	panic_stack;			/* 0x0330 */
-	__u64	restart_stack;			/* 0x0338 */
+	__u64	async_stack;			/* 0x0340 */
+	__u64	panic_stack;			/* 0x0348 */
+	__u64	restart_stack;			/* 0x0350 */
 
 	/* Restart function and parameter. */
-	__u64	restart_fn;			/* 0x0340 */
-	__u64	restart_data;			/* 0x0348 */
-	__u64	restart_source;			/* 0x0350 */
+	__u64	restart_fn;			/* 0x0358 */
+	__u64	restart_data;			/* 0x0360 */
+	__u64	restart_source;			/* 0x0368 */
 
 	/* Address space pointer. */
-	__u64	kernel_asce;			/* 0x0358 */
-	__u64	user_asce;			/* 0x0360 */
+	__u64	kernel_asce;			/* 0x0370 */
+	__u64	user_asce;			/* 0x0378 */
 
 	/*
 	 * The lpp and current_pid fields form a
 	 * 64-bit value that is set as program
 	 * parameter with the LPP instruction.
 	 */
-	__u32	lpp;				/* 0x0368 */
-	__u32	current_pid;			/* 0x036c */
+	__u32	lpp;				/* 0x0380 */
+	__u32	current_pid;			/* 0x0384 */
 
 	/* SMP info area */
-	__u32	cpu_nr;				/* 0x0370 */
-	__u32	softirq_pending;		/* 0x0374 */
-	__u64	percpu_offset;			/* 0x0378 */
-	__u64	vdso_per_cpu_data;		/* 0x0380 */
-	__u64	machine_flags;			/* 0x0388 */
-	__u32	preempt_count;			/* 0x0390 */
-	__u8	pad_0x0394[0x0398-0x0394];	/* 0x0394 */
-	__u64	gmap;				/* 0x0398 */
-	__u32	spinlock_lockval;		/* 0x03a0 */
-	__u32	fpu_flags;			/* 0x03a4 */
-	__u8	pad_0x03a8[0x0400-0x03a8];	/* 0x03a8 */
+	__u32	cpu_nr;				/* 0x0388 */
+	__u32	softirq_pending;		/* 0x038c */
+	__u64	percpu_offset;			/* 0x0390 */
+	__u64	vdso_per_cpu_data;		/* 0x0398 */
+	__u64	machine_flags;			/* 0x03a0 */
+	__u32	preempt_count;			/* 0x03a8 */
+	__u8	pad_0x03ac[0x03b0-0x03ac];	/* 0x03ac */
+	__u64	gmap;				/* 0x03b0 */
+	__u32	spinlock_lockval;		/* 0x03b8 */
+	__u32	fpu_flags;			/* 0x03bc */
+	__u8	pad_0x03c0[0x0400-0x03c0];	/* 0x03c0 */
 
 	/* Per cpu primary space access list */
 	__u32	paste[16];			/* 0x0400 */

arch/s390/include/asm/processor.h

@@ -111,7 +111,10 @@ struct thread_struct {
 	unsigned int  acrs[NUM_ACRS];
         unsigned long ksp;              /* kernel stack pointer             */
 	unsigned long user_timer;	/* task cputime in user space */
+	unsigned long guest_timer;	/* task cputime in kvm guest */
 	unsigned long system_timer;	/* task cputime in kernel space */
+	unsigned long hardirq_timer;	/* task cputime in hardirq context */
+	unsigned long softirq_timer;	/* task cputime in softirq context */
 	unsigned long sys_call_table;	/* system call table address */
 	mm_segment_t mm_segment;
 	unsigned long gmap_addr;	/* address of last gmap fault. */

arch/s390/kernel/idle.c

@@ -12,7 +12,7 @@
 #include <linux/notifier.h>
 #include <linux/init.h>
 #include <linux/cpu.h>
-#include <asm/cputime.h>
+#include <linux/cputime.h>
 #include <asm/nmi.h>
 #include <asm/smp.h>
 #include "entry.h"
@@ -43,7 +43,7 @@ void enabled_wait(void)
 	idle->clock_idle_enter = idle->clock_idle_exit = 0ULL;
 	idle->idle_time += idle_time;
 	idle->idle_count++;
-	account_idle_time(idle_time);
+	account_idle_time(cputime_to_nsecs(idle_time));
 	write_seqcount_end(&idle->seqcount);
 }
 NOKPROBE_SYMBOL(enabled_wait);
@@ -84,7 +84,7 @@ static ssize_t show_idle_time(struct device *dev,
 }
 DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL);
 
-cputime64_t arch_cpu_idle_time(int cpu)
+u64 arch_cpu_idle_time(int cpu)
 {
 	struct s390_idle_data *idle = &per_cpu(s390_idle, cpu);
 	unsigned long long now, idle_enter, idle_exit;
@@ -96,7 +96,8 @@ cputime64_t arch_cpu_idle_time(int cpu)
 		idle_enter = ACCESS_ONCE(idle->clock_idle_enter);
 		idle_exit = ACCESS_ONCE(idle->clock_idle_exit);
 	} while (read_seqcount_retry(&idle->seqcount, seq));
-	return idle_enter ? ((idle_exit ?: now) - idle_enter) : 0;
+
+	return cputime_to_nsecs(idle_enter ? ((idle_exit ?: now) - idle_enter) : 0);
 }
 
 void arch_cpu_idle_enter(void)

arch/s390/kernel/vtime.c

@@ -6,13 +6,13 @@
  */
 
 #include <linux/kernel_stat.h>
+#include <linux/cputime.h>
 #include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/timex.h>
 #include <linux/types.h>
 #include <linux/time.h>
 
-#include <asm/cputime.h>
 #include <asm/vtimer.h>
 #include <asm/vtime.h>
 #include <asm/cpu_mf.h>
@@ -90,14 +90,41 @@ static void update_mt_scaling(void)
 	__this_cpu_write(mt_scaling_jiffies, jiffies_64);
 }
 
+static inline u64 update_tsk_timer(unsigned long *tsk_vtime, u64 new)
+{
+	u64 delta;
+
+	delta = new - *tsk_vtime;
+	*tsk_vtime = new;
+	return delta;
+}
+
+
+static inline u64 scale_vtime(u64 vtime)
+{
+	u64 mult = __this_cpu_read(mt_scaling_mult);
+	u64 div = __this_cpu_read(mt_scaling_div);
+
+	if (smp_cpu_mtid)
+		return vtime * mult / div;
+	return vtime;
+}
+
+static void account_system_index_scaled(struct task_struct *p,
+					cputime_t cputime, cputime_t scaled,
+					enum cpu_usage_stat index)
+{
+	p->stimescaled += cputime_to_nsecs(scaled);
+	account_system_index_time(p, cputime_to_nsecs(cputime), index);
+}
+
 /*
  * Update process times based on virtual cpu times stored by entry.S
  * to the lowcore fields user_timer, system_timer & steal_clock.
  */
 static int do_account_vtime(struct task_struct *tsk)
 {
-	u64 timer, clock, user, system, steal;
-	u64 user_scaled, system_scaled;
+	u64 timer, clock, user, guest, system, hardirq, softirq, steal;
 
 	timer = S390_lowcore.last_update_timer;
 	clock = S390_lowcore.last_update_clock;
@@ -110,53 +137,76 @@ static int do_account_vtime(struct task_struct *tsk)
 #endif
 		: "=m" (S390_lowcore.last_update_timer),
 		  "=m" (S390_lowcore.last_update_clock));
-	S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer;
-	S390_lowcore.steal_timer += S390_lowcore.last_update_clock - clock;
+	clock = S390_lowcore.last_update_clock - clock;
+	timer -= S390_lowcore.last_update_timer;
+
+	if (hardirq_count())
+		S390_lowcore.hardirq_timer += timer;
+	else
+		S390_lowcore.system_timer += timer;
 
 	/* Update MT utilization calculation */
 	if (smp_cpu_mtid &&
 	    time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies)))
 		update_mt_scaling();
 
-	user = S390_lowcore.user_timer - tsk->thread.user_timer;
-	S390_lowcore.steal_timer -= user;
-	tsk->thread.user_timer = S390_lowcore.user_timer;
-
-	system = S390_lowcore.system_timer - tsk->thread.system_timer;
-	S390_lowcore.steal_timer -= system;
-	tsk->thread.system_timer = S390_lowcore.system_timer;
-
-	user_scaled = user;
-	system_scaled = system;
-	/* Do MT utilization scaling */
-	if (smp_cpu_mtid) {
-		u64 mult = __this_cpu_read(mt_scaling_mult);
-		u64 div = __this_cpu_read(mt_scaling_div);
+	/* Calculate cputime delta */
+	user = update_tsk_timer(&tsk->thread.user_timer,
+				READ_ONCE(S390_lowcore.user_timer));
+	guest = update_tsk_timer(&tsk->thread.guest_timer,
+				 READ_ONCE(S390_lowcore.guest_timer));
+	system = update_tsk_timer(&tsk->thread.system_timer,
+				  READ_ONCE(S390_lowcore.system_timer));
+	hardirq = update_tsk_timer(&tsk->thread.hardirq_timer,
+				   READ_ONCE(S390_lowcore.hardirq_timer));
+	softirq = update_tsk_timer(&tsk->thread.softirq_timer,
+				   READ_ONCE(S390_lowcore.softirq_timer));
+	S390_lowcore.steal_timer +=
+		clock - user - guest - system - hardirq - softirq;
+
+	/* Push account value */
+	if (user) {
+		account_user_time(tsk, cputime_to_nsecs(user));
+		tsk->utimescaled += cputime_to_nsecs(scale_vtime(user));
+	}
 
-		user_scaled = (user_scaled * mult) / div;
-		system_scaled = (system_scaled * mult) / div;
+	if (guest) {
+		account_guest_time(tsk, cputime_to_nsecs(guest));
+		tsk->utimescaled += cputime_to_nsecs(scale_vtime(guest));
 	}
-	account_user_time(tsk, user);
-	tsk->utimescaled += user_scaled;
-	account_system_time(tsk, 0, system);
-	tsk->stimescaled += system_scaled;
+
+	if (system)
+		account_system_index_scaled(tsk, system, scale_vtime(system),
+					    CPUTIME_SYSTEM);
+	if (hardirq)
+		account_system_index_scaled(tsk, hardirq, scale_vtime(hardirq),
+					    CPUTIME_IRQ);
+	if (softirq)
+		account_system_index_scaled(tsk, softirq, scale_vtime(softirq),
+					    CPUTIME_SOFTIRQ);
 
 	steal = S390_lowcore.steal_timer;
 	if ((s64) steal > 0) {
 		S390_lowcore.steal_timer = 0;
-		account_steal_time(steal);
+		account_steal_time(cputime_to_nsecs(steal));
 	}
 
-	return virt_timer_forward(user + system);
+	return virt_timer_forward(user + guest + system + hardirq + softirq);
 }
 
 void vtime_task_switch(struct task_struct *prev)
 {
 	do_account_vtime(prev);
 	prev->thread.user_timer = S390_lowcore.user_timer;
+	prev->thread.guest_timer = S390_lowcore.guest_timer;
 	prev->thread.system_timer = S390_lowcore.system_timer;
+	prev->thread.hardirq_timer = S390_lowcore.hardirq_timer;
+	prev->thread.softirq_timer = S390_lowcore.softirq_timer;
 	S390_lowcore.user_timer = current->thread.user_timer;
+	S390_lowcore.guest_timer = current->thread.guest_timer;
 	S390_lowcore.system_timer = current->thread.system_timer;
+	S390_lowcore.hardirq_timer = current->thread.hardirq_timer;
+	S390_lowcore.softirq_timer = current->thread.softirq_timer;
 }
 
 /*
@@ -164,7 +214,7 @@ void vtime_task_switch(struct task_struct *prev)
  * accounting system time in order to correctly compute
  * the stolen time accounting.
  */
-void vtime_account_user(struct task_struct *tsk)
+void vtime_flush(struct task_struct *tsk)
 {
 	if (do_account_vtime(tsk))
 		virt_timer_expire();
@@ -176,32 +226,22 @@ void vtime_account_user(struct task_struct *tsk)
  */
 void vtime_account_irq_enter(struct task_struct *tsk)
 {
-	u64 timer, system, system_scaled;
+	u64 timer;
 
 	timer = S390_lowcore.last_update_timer;
 	S390_lowcore.last_update_timer = get_vtimer();
-	S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer;
-
-	/* Update MT utilization calculation */
-	if (smp_cpu_mtid &&
-	    time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies)))
-		update_mt_scaling();
-
-	system = S390_lowcore.system_timer - tsk->thread.system_timer;
-	S390_lowcore.steal_timer -= system;
-	tsk->thread.system_timer = S390_lowcore.system_timer;
-	system_scaled = system;
-	/* Do MT utilization scaling */
-	if (smp_cpu_mtid) {
-		u64 mult = __this_cpu_read(mt_scaling_mult);
-		u64 div = __this_cpu_read(mt_scaling_div);
-
-		system_scaled = (system_scaled * mult) / div;
-	}
-	account_system_time(tsk, 0, system);
-	tsk->stimescaled += system_scaled;
-
-	virt_timer_forward(system);
+	timer -= S390_lowcore.last_update_timer;
+
+	if ((tsk->flags & PF_VCPU) && (irq_count() == 0))
+		S390_lowcore.guest_timer += timer;
+	else if (hardirq_count())
+		S390_lowcore.hardirq_timer += timer;
+	else if (in_serving_softirq())
+		S390_lowcore.softirq_timer += timer;
+	else
+		S390_lowcore.system_timer += timer;
+
+	virt_timer_forward(timer);
 }
 EXPORT_SYMBOL_GPL(vtime_account_irq_enter);
 

arch/score/include/asm/Kbuild

@@ -4,7 +4,6 @@ header-y +=
 
 generic-y += barrier.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h

arch/sh/include/asm/Kbuild

@@ -1,7 +1,6 @@
 
 generic-y += bitsperlong.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += current.h
 generic-y += delay.h
 generic-y += div64.h

arch/sparc/include/asm/Kbuild

@@ -2,7 +2,6 @@
 
 
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += div64.h
 generic-y += emergency-restart.h
 generic-y += exec.h

arch/tile/include/asm/Kbuild

@@ -4,7 +4,6 @@ header-y += ../arch/
 generic-y += bug.h
 generic-y += bugs.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += exec.h

arch/um/include/asm/Kbuild

@@ -1,7 +1,6 @@
 generic-y += barrier.h
 generic-y += bug.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += current.h
 generic-y += delay.h
 generic-y += device.h

arch/unicore32/include/asm/Kbuild

@@ -4,7 +4,6 @@ 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 += div64.h

arch/x86/include/asm/Kbuild

@@ -7,7 +7,6 @@ generated-y += unistd_64_x32.h
 generated-y += xen-hypercalls.h
 
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += dma-contiguous.h
 generic-y += early_ioremap.h
 generic-y += mcs_spinlock.h

arch/x86/kernel/apm_32.c

@@ -905,8 +905,8 @@ static int apm_cpu_idle(struct cpuidle_device *dev,
 {
 	static int use_apm_idle; /* = 0 */
 	static unsigned int last_jiffies; /* = 0 */
-	static unsigned int last_stime; /* = 0 */
-	cputime_t stime, utime;
+	static u64 last_stime; /* = 0 */
+	u64 stime, utime;
 
 	int apm_idle_done = 0;
 	unsigned int jiffies_since_last_check = jiffies - last_jiffies;
@@ -919,7 +919,7 @@ recalc:
 	} else if (jiffies_since_last_check > idle_period) {
 		unsigned int idle_percentage;
 
-		idle_percentage = cputime_to_jiffies(stime - last_stime);
+		idle_percentage = nsecs_to_jiffies(stime - last_stime);
 		idle_percentage *= 100;
 		idle_percentage /= jiffies_since_last_check;
 		use_apm_idle = (idle_percentage > idle_threshold);

arch/x86/kernel/cpu/amd.c

@@ -555,8 +555,10 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 	if (c->x86_power & (1 << 8)) {
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
-		if (!check_tsc_unstable())
-			set_sched_clock_stable();
+		if (check_tsc_unstable())
+			clear_sched_clock_stable();
+	} else {
+		clear_sched_clock_stable();
 	}
 
 	/* Bit 12 of 8000_0007 edx is accumulated power mechanism. */

arch/x86/kernel/cpu/centaur.c

@@ -1,5 +1,5 @@
-#include <linux/bitops.h>
-#include <linux/kernel.h>
+
+#include <linux/sched.h>
 
 #include <asm/cpufeature.h>
 #include <asm/e820.h>
@@ -104,6 +104,8 @@ static void early_init_centaur(struct cpuinfo_x86 *c)
 #ifdef CONFIG_X86_64
 	set_cpu_cap(c, X86_FEATURE_SYSENTER32);
 #endif
+
+	clear_sched_clock_stable();
 }
 
 static void init_centaur(struct cpuinfo_x86 *c)

arch/x86/kernel/cpu/common.c

@@ -83,6 +83,7 @@ static void default_init(struct cpuinfo_x86 *c)
 			strcpy(c->x86_model_id, "386");
 	}
 #endif
+	clear_sched_clock_stable();
 }
 
 static const struct cpu_dev default_cpu = {
@@ -1056,6 +1057,8 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 	 */
 	if (this_cpu->c_init)
 		this_cpu->c_init(c);
+	else
+		clear_sched_clock_stable();
 
 	/* Disable the PN if appropriate */
 	squash_the_stupid_serial_number(c);

arch/x86/kernel/cpu/cyrix.c

@@ -9,6 +9,7 @@
 #include <asm/pci-direct.h>
 #include <asm/tsc.h>
 #include <asm/cpufeature.h>
+#include <linux/sched.h>
 
 #include "cpu.h"
 
@@ -183,6 +184,7 @@ static void early_init_cyrix(struct cpuinfo_x86 *c)
 		set_cpu_cap(c, X86_FEATURE_CYRIX_ARR);
 		break;
 	}
+	clear_sched_clock_stable();
 }
 
 static void init_cyrix(struct cpuinfo_x86 *c)

arch/x86/kernel/cpu/intel.c

@@ -119,8 +119,10 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 	if (c->x86_power & (1 << 8)) {
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
-		if (!check_tsc_unstable())
-			set_sched_clock_stable();
+		if (check_tsc_unstable())
+			clear_sched_clock_stable();
+	} else {
+		clear_sched_clock_stable();
 	}
 
 	/* Penwell and Cloverview have the TSC which doesn't sleep on S3 */

arch/x86/kernel/cpu/transmeta.c

@@ -1,4 +1,5 @@
 #include <linux/kernel.h>
+#include <linux/sched.h>
 #include <linux/mm.h>
 #include <asm/cpufeature.h>
 #include <asm/msr.h>
@@ -14,6 +15,8 @@ static void early_init_transmeta(struct cpuinfo_x86 *c)
 		if (xlvl >= 0x80860001)
 			c->x86_capability[CPUID_8086_0001_EDX] = cpuid_edx(0x80860001);
 	}
+
+	clear_sched_clock_stable();
 }
 
 static void init_transmeta(struct cpuinfo_x86 *c)

arch/x86/kernel/itmt.c

@@ -132,10 +132,8 @@ int sched_set_itmt_support(void)
 
 	sysctl_sched_itmt_enabled = 1;
 
-	if (sysctl_sched_itmt_enabled) {
-		x86_topology_update = true;
-		rebuild_sched_domains();
-	}
+	x86_topology_update = true;
+	rebuild_sched_domains();
 
 	mutex_unlock(&itmt_update_mutex);
 

arch/x86/kernel/kvmclock.c

@@ -107,12 +107,12 @@ static inline void kvm_sched_clock_init(bool stable)
 {
 	if (!stable) {
 		pv_time_ops.sched_clock = kvm_clock_read;
+		clear_sched_clock_stable();
 		return;
 	}
 
 	kvm_sched_clock_offset = kvm_clock_read();
 	pv_time_ops.sched_clock = kvm_sched_clock_read;
-	set_sched_clock_stable();
 
 	printk(KERN_INFO "kvm-clock: using sched offset of %llu cycles\n",
 			kvm_sched_clock_offset);

arch/x86/kernel/tsc.c

@@ -1107,6 +1107,16 @@ static u64 read_tsc(struct clocksource *cs)
 	return (u64)rdtsc_ordered();
 }
 
+static void tsc_cs_mark_unstable(struct clocksource *cs)
+{
+	if (tsc_unstable)
+		return;
+	tsc_unstable = 1;
+	clear_sched_clock_stable();
+	disable_sched_clock_irqtime();
+	pr_info("Marking TSC unstable due to clocksource watchdog\n");
+}
+
 /*
  * .mask MUST be CLOCKSOURCE_MASK(64). See comment above read_tsc()
  */
@@ -1119,6 +1129,7 @@ static struct clocksource clocksource_tsc = {
 				  CLOCK_SOURCE_MUST_VERIFY,
 	.archdata               = { .vclock_mode = VCLOCK_TSC },
 	.resume			= tsc_resume,
+	.mark_unstable		= tsc_cs_mark_unstable,
 };
 
 void mark_tsc_unstable(char *reason)

arch/x86/kvm/hyperv.c

@@ -964,10 +964,11 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
 /* Calculate cpu time spent by current task in 100ns units */
 static u64 current_task_runtime_100ns(void)
 {
-	cputime_t utime, stime;
+	u64 utime, stime;
 
 	task_cputime_adjusted(current, &utime, &stime);
-	return div_u64(cputime_to_nsecs(utime + stime), 100);
+
+	return div_u64(utime + stime, 100);
 }
 
 static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)

arch/xtensa/include/asm/Kbuild

@@ -1,7 +1,6 @@
 generic-y += bitsperlong.h
 generic-y += bug.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += div64.h
 generic-y += dma-contiguous.h
 generic-y += emergency-restart.h

drivers/cpufreq/cpufreq.c

@@ -132,7 +132,7 @@ static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall)
 	u64 cur_wall_time;
 	u64 busy_time;
 
-	cur_wall_time = jiffies64_to_cputime64(get_jiffies_64());
+	cur_wall_time = jiffies64_to_nsecs(get_jiffies_64());
 
 	busy_time = kcpustat_cpu(cpu).cpustat[CPUTIME_USER];
 	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SYSTEM];
@@ -143,9 +143,9 @@ static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall)
 
 	idle_time = cur_wall_time - busy_time;
 	if (wall)
-		*wall = cputime_to_usecs(cur_wall_time);
+		*wall = div_u64(cur_wall_time, NSEC_PER_USEC);
 
-	return cputime_to_usecs(idle_time);
+	return div_u64(idle_time, NSEC_PER_USEC);
 }
 
 u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy)

drivers/cpufreq/cpufreq_governor.c

@@ -152,7 +152,7 @@ unsigned int dbs_update(struct cpufreq_policy *policy)
 		if (ignore_nice) {
 			u64 cur_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
 
-			idle_time += cputime_to_usecs(cur_nice - j_cdbs->prev_cpu_nice);
+			idle_time += div_u64(cur_nice - j_cdbs->prev_cpu_nice, NSEC_PER_USEC);
 			j_cdbs->prev_cpu_nice = cur_nice;
 		}
 

drivers/cpufreq/cpufreq_stats.c

@@ -13,7 +13,6 @@
 #include <linux/cpufreq.h>
 #include <linux/module.h>
 #include <linux/slab.h>
-#include <linux/cputime.h>
 
 static DEFINE_SPINLOCK(cpufreq_stats_lock);
 

drivers/isdn/mISDN/stack.c

@@ -203,7 +203,7 @@ mISDNStackd(void *data)
 {
 	struct mISDNstack *st = data;
 #ifdef MISDN_MSG_STATS
-	cputime_t utime, stime;
+	u64 utime, stime;
 #endif
 	int err = 0;
 
@@ -308,7 +308,7 @@ mISDNStackd(void *data)
 	       st->stopped_cnt);
 	task_cputime(st->thread, &utime, &stime);
 	printk(KERN_DEBUG
-	       "mISDNStackd daemon for %s utime(%ld) stime(%ld)\n",
+	       "mISDNStackd daemon for %s utime(%llu) stime(%llu)\n",
 	       dev_name(&st->dev->dev), utime, stime);
 	printk(KERN_DEBUG
 	       "mISDNStackd daemon for %s nvcsw(%ld) nivcsw(%ld)\n",

drivers/macintosh/rack-meter.c

@@ -52,8 +52,8 @@ struct rackmeter_dma {
 struct rackmeter_cpu {
 	struct delayed_work	sniffer;
 	struct rackmeter	*rm;
-	cputime64_t		prev_wall;
-	cputime64_t		prev_idle;
+	u64			prev_wall;
+	u64			prev_idle;
 	int			zero;
 } ____cacheline_aligned;
 
@@ -81,7 +81,7 @@ static int rackmeter_ignore_nice;
 /* This is copied from cpufreq_ondemand, maybe we should put it in
  * a common header somewhere
  */
-static inline cputime64_t get_cpu_idle_time(unsigned int cpu)
+static inline u64 get_cpu_idle_time(unsigned int cpu)
 {
 	u64 retval;
 
@@ -217,23 +217,23 @@ static void rackmeter_do_timer(struct work_struct *work)
 		container_of(work, struct rackmeter_cpu, sniffer.work);
 	struct rackmeter *rm = rcpu->rm;
 	unsigned int cpu = smp_processor_id();
-	cputime64_t cur_jiffies, total_idle_ticks;
-	unsigned int total_ticks, idle_ticks;
+	u64 cur_nsecs, total_idle_nsecs;
+	u64 total_nsecs, idle_nsecs;
 	int i, offset, load, cumm, pause;
 
-	cur_jiffies = jiffies64_to_cputime64(get_jiffies_64());
-	total_ticks = (unsigned int) (cur_jiffies - rcpu->prev_wall);
-	rcpu->prev_wall = cur_jiffies;
+	cur_nsecs = jiffies64_to_nsecs(get_jiffies_64());
+	total_nsecs = cur_nsecs - rcpu->prev_wall;
+	rcpu->prev_wall = cur_nsecs;
 
-	total_idle_ticks = get_cpu_idle_time(cpu);
-	idle_ticks = (unsigned int) (total_idle_ticks - rcpu->prev_idle);
-	idle_ticks = min(idle_ticks, total_ticks);
-	rcpu->prev_idle = total_idle_ticks;
+	total_idle_nsecs = get_cpu_idle_time(cpu);
+	idle_nsecs = total_idle_nsecs - rcpu->prev_idle;
+	idle_nsecs = min(idle_nsecs, total_nsecs);
+	rcpu->prev_idle = total_idle_nsecs;
 
 	/* We do a very dumb calculation to update the LEDs for now,
 	 * we'll do better once we have actual PWM implemented
 	 */
-	load = (9 * (total_ticks - idle_ticks)) / total_ticks;
+	load = div64_u64(9 * (total_nsecs - idle_nsecs), total_nsecs);
 
 	offset = cpu << 3;
 	cumm = 0;
@@ -278,7 +278,7 @@ static void rackmeter_init_cpu_sniffer(struct rackmeter *rm)
 			continue;
 		rcpu = &rm->cpu[cpu];
 		rcpu->prev_idle = get_cpu_idle_time(cpu);
-		rcpu->prev_wall = jiffies64_to_cputime64(get_jiffies_64());
+		rcpu->prev_wall = jiffies64_to_nsecs(get_jiffies_64());
 		schedule_delayed_work_on(cpu, &rm->cpu[cpu].sniffer,
 					 msecs_to_jiffies(CPU_SAMPLING_RATE));
 	}

fs/binfmt_elf.c

@@ -1428,17 +1428,18 @@ static void fill_prstatus(struct elf_prstatus *prstatus,
 		 * group-wide total, not its individual thread total.
 		 */
 		thread_group_cputime(p, &cputime);
-		cputime_to_timeval(cputime.utime, &prstatus->pr_utime);
-		cputime_to_timeval(cputime.stime, &prstatus->pr_stime);
+		prstatus->pr_utime = ns_to_timeval(cputime.utime);
+		prstatus->pr_stime = ns_to_timeval(cputime.stime);
 	} else {
-		cputime_t utime, stime;
+		u64 utime, stime;
 
 		task_cputime(p, &utime, &stime);
-		cputime_to_timeval(utime, &prstatus->pr_utime);
-		cputime_to_timeval(stime, &prstatus->pr_stime);
+		prstatus->pr_utime = ns_to_timeval(utime);
+		prstatus->pr_stime = ns_to_timeval(stime);
 	}
-	cputime_to_timeval(p->signal->cutime, &prstatus->pr_cutime);
-	cputime_to_timeval(p->signal->cstime, &prstatus->pr_cstime);
+
+	prstatus->pr_cutime = ns_to_timeval(p->signal->cutime);
+	prstatus->pr_cstime = ns_to_timeval(p->signal->cstime);
 }
 
 static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p,

fs/binfmt_elf_fdpic.c

@@ -1349,17 +1349,17 @@ static void fill_prstatus(struct elf_prstatus *prstatus,
 		 * group-wide total, not its individual thread total.
 		 */
 		thread_group_cputime(p, &cputime);
-		cputime_to_timeval(cputime.utime, &prstatus->pr_utime);
-		cputime_to_timeval(cputime.stime, &prstatus->pr_stime);
+		prstatus->pr_utime = ns_to_timeval(cputime.utime);
+		prstatus->pr_stime = ns_to_timeval(cputime.stime);
 	} else {
-		cputime_t utime, stime;
+		u64 utime, stime;
 
 		task_cputime(p, &utime, &stime);
-		cputime_to_timeval(utime, &prstatus->pr_utime);
-		cputime_to_timeval(stime, &prstatus->pr_stime);
+		prstatus->pr_utime = ns_to_timeval(utime);
+		prstatus->pr_stime = ns_to_timeval(stime);
 	}
-	cputime_to_timeval(p->signal->cutime, &prstatus->pr_cutime);
-	cputime_to_timeval(p->signal->cstime, &prstatus->pr_cstime);
+	prstatus->pr_cutime = ns_to_timeval(p->signal->cutime);
+	prstatus->pr_cstime = ns_to_timeval(p->signal->cstime);
 
 	prstatus->pr_exec_fdpic_loadmap = p->mm->context.exec_fdpic_loadmap;
 	prstatus->pr_interp_fdpic_loadmap = p->mm->context.interp_fdpic_loadmap;

fs/compat_binfmt_elf.c

@@ -51,22 +51,8 @@
 #define elf_prstatus	compat_elf_prstatus
 #define elf_prpsinfo	compat_elf_prpsinfo
 
-/*
- * Compat version of cputime_to_compat_timeval, perhaps this
- * should be an inline in <linux/compat.h>.
- */
-static void cputime_to_compat_timeval(const cputime_t cputime,
-				      struct compat_timeval *value)
-{
-	struct timeval tv;
-	cputime_to_timeval(cputime, &tv);
-	value->tv_sec = tv.tv_sec;
-	value->tv_usec = tv.tv_usec;
-}
-
-#undef cputime_to_timeval
-#define cputime_to_timeval cputime_to_compat_timeval
-
+#undef ns_to_timeval
+#define ns_to_timeval ns_to_compat_timeval
 
 /*
  * To use this file, asm/elf.h must define compat_elf_check_arch.

fs/jbd2/commit.c

@@ -393,7 +393,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	/* Do we need to erase the effects of a prior jbd2_journal_flush? */
 	if (journal->j_flags & JBD2_FLUSHED) {
 		jbd_debug(3, "super block updated\n");
-		mutex_lock(&journal->j_checkpoint_mutex);
+		mutex_lock_io(&journal->j_checkpoint_mutex);
 		/*
 		 * We hold j_checkpoint_mutex so tail cannot change under us.
 		 * We don't need any special data guarantees for writing sb

fs/jbd2/journal.c

@@ -944,7 +944,7 @@ out:
  */
 void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block)
 {
-	mutex_lock(&journal->j_checkpoint_mutex);
+	mutex_lock_io(&journal->j_checkpoint_mutex);
 	if (tid_gt(tid, journal->j_tail_sequence))
 		__jbd2_update_log_tail(journal, tid, block);
 	mutex_unlock(&journal->j_checkpoint_mutex);
@@ -1304,7 +1304,7 @@ static int journal_reset(journal_t *journal)
 		journal->j_flags |= JBD2_FLUSHED;
 	} else {
 		/* Lock here to make assertions happy... */
-		mutex_lock(&journal->j_checkpoint_mutex);
+		mutex_lock_io(&journal->j_checkpoint_mutex);
 		/*
 		 * Update log tail information. We use REQ_FUA since new
 		 * transaction will start reusing journal space and so we
@@ -1691,7 +1691,7 @@ int jbd2_journal_destroy(journal_t *journal)
 	spin_lock(&journal->j_list_lock);
 	while (journal->j_checkpoint_transactions != NULL) {
 		spin_unlock(&journal->j_list_lock);
-		mutex_lock(&journal->j_checkpoint_mutex);
+		mutex_lock_io(&journal->j_checkpoint_mutex);
 		err = jbd2_log_do_checkpoint(journal);
 		mutex_unlock(&journal->j_checkpoint_mutex);
 		/*
@@ -1713,7 +1713,7 @@ int jbd2_journal_destroy(journal_t *journal)
 
 	if (journal->j_sb_buffer) {
 		if (!is_journal_aborted(journal)) {
-			mutex_lock(&journal->j_checkpoint_mutex);
+			mutex_lock_io(&journal->j_checkpoint_mutex);
 
 			write_lock(&journal->j_state_lock);
 			journal->j_tail_sequence =
@@ -1955,7 +1955,7 @@ int jbd2_journal_flush(journal_t *journal)
 	spin_lock(&journal->j_list_lock);
 	while (!err && journal->j_checkpoint_transactions != NULL) {
 		spin_unlock(&journal->j_list_lock);
-		mutex_lock(&journal->j_checkpoint_mutex);
+		mutex_lock_io(&journal->j_checkpoint_mutex);
 		err = jbd2_log_do_checkpoint(journal);
 		mutex_unlock(&journal->j_checkpoint_mutex);
 		spin_lock(&journal->j_list_lock);
@@ -1965,7 +1965,7 @@ int jbd2_journal_flush(journal_t *journal)
 	if (is_journal_aborted(journal))
 		return -EIO;
 
-	mutex_lock(&journal->j_checkpoint_mutex);
+	mutex_lock_io(&journal->j_checkpoint_mutex);
 	if (!err) {
 		err = jbd2_cleanup_journal_tail(journal);
 		if (err < 0) {

fs/proc/array.c

@@ -401,8 +401,8 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	unsigned long long start_time;
 	unsigned long cmin_flt = 0, cmaj_flt = 0;
 	unsigned long  min_flt = 0,  maj_flt = 0;
-	cputime_t cutime, cstime, utime, stime;
-	cputime_t cgtime, gtime;
+	u64 cutime, cstime, utime, stime;
+	u64 cgtime, gtime;
 	unsigned long rsslim = 0;
 	char tcomm[sizeof(task->comm)];
 	unsigned long flags;
@@ -497,10 +497,10 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	seq_put_decimal_ull(m, " ", cmin_flt);
 	seq_put_decimal_ull(m, " ", maj_flt);
 	seq_put_decimal_ull(m, " ", cmaj_flt);
-	seq_put_decimal_ull(m, " ", cputime_to_clock_t(utime));
-	seq_put_decimal_ull(m, " ", cputime_to_clock_t(stime));
-	seq_put_decimal_ll(m, " ", cputime_to_clock_t(cutime));
-	seq_put_decimal_ll(m, " ", cputime_to_clock_t(cstime));
+	seq_put_decimal_ull(m, " ", nsec_to_clock_t(utime));
+	seq_put_decimal_ull(m, " ", nsec_to_clock_t(stime));
+	seq_put_decimal_ll(m, " ", nsec_to_clock_t(cutime));
+	seq_put_decimal_ll(m, " ", nsec_to_clock_t(cstime));
 	seq_put_decimal_ll(m, " ", priority);
 	seq_put_decimal_ll(m, " ", nice);
 	seq_put_decimal_ll(m, " ", num_threads);
@@ -542,8 +542,8 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	seq_put_decimal_ull(m, " ", task->rt_priority);
 	seq_put_decimal_ull(m, " ", task->policy);
 	seq_put_decimal_ull(m, " ", delayacct_blkio_ticks(task));
-	seq_put_decimal_ull(m, " ", cputime_to_clock_t(gtime));
-	seq_put_decimal_ll(m, " ", cputime_to_clock_t(cgtime));
+	seq_put_decimal_ull(m, " ", nsec_to_clock_t(gtime));
+	seq_put_decimal_ll(m, " ", nsec_to_clock_t(cgtime));
 
 	if (mm && permitted) {
 		seq_put_decimal_ull(m, " ", mm->start_data);

fs/proc/stat.c

@@ -21,9 +21,9 @@
 
 #ifdef arch_idle_time
 
-static cputime64_t get_idle_time(int cpu)
+static u64 get_idle_time(int cpu)
 {
-	cputime64_t idle;
+	u64 idle;
 
 	idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE];
 	if (cpu_online(cpu) && !nr_iowait_cpu(cpu))
@@ -31,9 +31,9 @@ static cputime64_t get_idle_time(int cpu)
 	return idle;
 }
 
-static cputime64_t get_iowait_time(int cpu)
+static u64 get_iowait_time(int cpu)
 {
-	cputime64_t iowait;
+	u64 iowait;
 
 	iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT];
 	if (cpu_online(cpu) && nr_iowait_cpu(cpu))
@@ -45,32 +45,32 @@ static cputime64_t get_iowait_time(int cpu)
 
 static u64 get_idle_time(int cpu)
 {
-	u64 idle, idle_time = -1ULL;
+	u64 idle, idle_usecs = -1ULL;
 
 	if (cpu_online(cpu))
-		idle_time = get_cpu_idle_time_us(cpu, NULL);
+		idle_usecs = get_cpu_idle_time_us(cpu, NULL);
 
-	if (idle_time == -1ULL)
+	if (idle_usecs == -1ULL)
 		/* !NO_HZ or cpu offline so we can rely on cpustat.idle */
 		idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE];
 	else
-		idle = usecs_to_cputime64(idle_time);
+		idle = idle_usecs * NSEC_PER_USEC;
 
 	return idle;
 }
 
 static u64 get_iowait_time(int cpu)
 {
-	u64 iowait, iowait_time = -1ULL;
+	u64 iowait, iowait_usecs = -1ULL;
 
 	if (cpu_online(cpu))
-		iowait_time = get_cpu_iowait_time_us(cpu, NULL);
+		iowait_usecs = get_cpu_iowait_time_us(cpu, NULL);
 
-	if (iowait_time == -1ULL)
+	if (iowait_usecs == -1ULL)
 		/* !NO_HZ or cpu offline so we can rely on cpustat.iowait */
 		iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT];
 	else
-		iowait = usecs_to_cputime64(iowait_time);
+		iowait = iowait_usecs * NSEC_PER_USEC;
 
 	return iowait;
 }
@@ -115,16 +115,16 @@ static int show_stat(struct seq_file *p, void *v)
 	}
 	sum += arch_irq_stat();
 
-	seq_put_decimal_ull(p, "cpu  ", cputime64_to_clock_t(user));
-	seq_put_decimal_ull(p, " ", cputime64_to_clock_t(nice));
-	seq_put_decimal_ull(p, " ", cputime64_to_clock_t(system));
-	seq_put_decimal_ull(p, " ", cputime64_to_clock_t(idle));
-	seq_put_decimal_ull(p, " ", cputime64_to_clock_t(iowait));
-	seq_put_decimal_ull(p, " ", cputime64_to_clock_t(irq));
-	seq_put_decimal_ull(p, " ", cputime64_to_clock_t(softirq));
-	seq_put_decimal_ull(p, " ", cputime64_to_clock_t(steal));
-	seq_put_decimal_ull(p, " ", cputime64_to_clock_t(guest));
-	seq_put_decimal_ull(p, " ", cputime64_to_clock_t(guest_nice));
+	seq_put_decimal_ull(p, "cpu  ", nsec_to_clock_t(user));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(system));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(iowait));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(irq));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(softirq));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(steal));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest_nice));
 	seq_putc(p, '\n');
 
 	for_each_online_cpu(i) {
@@ -140,16 +140,16 @@ static int show_stat(struct seq_file *p, void *v)
 		guest = kcpustat_cpu(i).cpustat[CPUTIME_GUEST];
 		guest_nice = kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE];
 		seq_printf(p, "cpu%d", i);
-		seq_put_decimal_ull(p, " ", cputime64_to_clock_t(user));
-		seq_put_decimal_ull(p, " ", cputime64_to_clock_t(nice));
-		seq_put_decimal_ull(p, " ", cputime64_to_clock_t(system));
-		seq_put_decimal_ull(p, " ", cputime64_to_clock_t(idle));
-		seq_put_decimal_ull(p, " ", cputime64_to_clock_t(iowait));
-		seq_put_decimal_ull(p, " ", cputime64_to_clock_t(irq));
-		seq_put_decimal_ull(p, " ", cputime64_to_clock_t(softirq));
-		seq_put_decimal_ull(p, " ", cputime64_to_clock_t(steal));
-		seq_put_decimal_ull(p, " ", cputime64_to_clock_t(guest));
-		seq_put_decimal_ull(p, " ", cputime64_to_clock_t(guest_nice));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(user));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(system));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(iowait));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(irq));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(softirq));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(steal));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest_nice));
 		seq_putc(p, '\n');
 	}
 	seq_put_decimal_ull(p, "intr ", (unsigned long long)sum);

fs/proc/uptime.c

@@ -5,23 +5,20 @@
 #include <linux/seq_file.h>
 #include <linux/time.h>
 #include <linux/kernel_stat.h>
-#include <linux/cputime.h>
 
 static int uptime_proc_show(struct seq_file *m, void *v)
 {
 	struct timespec uptime;
 	struct timespec idle;
-	u64 idletime;
 	u64 nsec;
 	u32 rem;
 	int i;
 
-	idletime = 0;
+	nsec = 0;
 	for_each_possible_cpu(i)
-		idletime += (__force u64) kcpustat_cpu(i).cpustat[CPUTIME_IDLE];
+		nsec += (__force u64) kcpustat_cpu(i).cpustat[CPUTIME_IDLE];
 
 	get_monotonic_boottime(&uptime);
-	nsec = cputime64_to_jiffies64(idletime) * TICK_NSEC;
 	idle.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem);
 	idle.tv_nsec = rem;
 	seq_printf(m, "%lu.%02lu %lu.%02lu\n",

include/asm-generic/cputime.h

@@ -1,15 +0,0 @@
-#ifndef _ASM_GENERIC_CPUTIME_H
-#define _ASM_GENERIC_CPUTIME_H
-
-#include <linux/time.h>
-#include <linux/jiffies.h>
-
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
-# include <asm-generic/cputime_jiffies.h>
-#endif
-
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
-# include <asm-generic/cputime_nsecs.h>
-#endif
-
-#endif

include/asm-generic/cputime_jiffies.h

@@ -1,75 +0,0 @@
-#ifndef _ASM_GENERIC_CPUTIME_JIFFIES_H
-#define _ASM_GENERIC_CPUTIME_JIFFIES_H
-
-typedef unsigned long __nocast cputime_t;
-
-#define cmpxchg_cputime(ptr, old, new) cmpxchg(ptr, old, new)
-
-#define cputime_one_jiffy		jiffies_to_cputime(1)
-#define cputime_to_jiffies(__ct)	(__force unsigned long)(__ct)
-#define jiffies_to_cputime(__hz)	(__force cputime_t)(__hz)
-
-typedef u64 __nocast cputime64_t;
-
-#define cputime64_to_jiffies64(__ct)	(__force u64)(__ct)
-#define jiffies64_to_cputime64(__jif)	(__force cputime64_t)(__jif)
-
-
-/*
- * Convert nanoseconds <-> cputime
- */
-#define cputime_to_nsecs(__ct)		\
-	jiffies_to_nsecs(cputime_to_jiffies(__ct))
-#define nsecs_to_cputime64(__nsec)	\
-	jiffies64_to_cputime64(nsecs_to_jiffies64(__nsec))
-#define nsecs_to_cputime(__nsec)	\
-	jiffies_to_cputime(nsecs_to_jiffies(__nsec))
-
-
-/*
- * Convert cputime to microseconds and back.
- */
-#define cputime_to_usecs(__ct)		\
-	jiffies_to_usecs(cputime_to_jiffies(__ct))
-#define usecs_to_cputime(__usec)	\
-	jiffies_to_cputime(usecs_to_jiffies(__usec))
-#define usecs_to_cputime64(__usec)	\
-	jiffies64_to_cputime64(nsecs_to_jiffies64((__usec) * 1000))
-
-/*
- * Convert cputime to seconds and back.
- */
-#define cputime_to_secs(jif)		(cputime_to_jiffies(jif) / HZ)
-#define secs_to_cputime(sec)		jiffies_to_cputime((sec) * HZ)
-
-/*
- * Convert cputime to timespec and back.
- */
-#define timespec_to_cputime(__val)	\
-	jiffies_to_cputime(timespec_to_jiffies(__val))
-#define cputime_to_timespec(__ct,__val)	\
-	jiffies_to_timespec(cputime_to_jiffies(__ct),__val)
-
-/*
- * Convert cputime to timeval and back.
- */
-#define timeval_to_cputime(__val)	\
-	jiffies_to_cputime(timeval_to_jiffies(__val))
-#define cputime_to_timeval(__ct,__val)	\
-	jiffies_to_timeval(cputime_to_jiffies(__ct),__val)
-
-/*
- * Convert cputime to clock and back.
- */
-#define cputime_to_clock_t(__ct)	\
-	jiffies_to_clock_t(cputime_to_jiffies(__ct))
-#define clock_t_to_cputime(__x)		\
-	jiffies_to_cputime(clock_t_to_jiffies(__x))
-
-/*
- * Convert cputime64 to clock.
- */
-#define cputime64_to_clock_t(__ct)	\
-	jiffies_64_to_clock_t(cputime64_to_jiffies64(__ct))
-
-#endif

include/asm-generic/cputime_nsecs.h

@@ -1,121 +0,0 @@
-/*
- * Definitions for measuring cputime in nsecs resolution.
- *
- * Based on <arch/ia64/include/asm/cputime.h>
- *
- * Copyright (C) 2007 FUJITSU LIMITED
- * Copyright (C) 2007 Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
- */
-
-#ifndef _ASM_GENERIC_CPUTIME_NSECS_H
-#define _ASM_GENERIC_CPUTIME_NSECS_H
-
-#include <linux/math64.h>
-
-typedef u64 __nocast cputime_t;
-typedef u64 __nocast cputime64_t;
-
-#define cmpxchg_cputime(ptr, old, new) cmpxchg64(ptr, old, new)
-
-#define cputime_one_jiffy		jiffies_to_cputime(1)
-
-#define cputime_div(__ct, divisor)  div_u64((__force u64)__ct, divisor)
-#define cputime_div_rem(__ct, divisor, remainder) \
-	div_u64_rem((__force u64)__ct, divisor, remainder);
-
-/*
- * Convert cputime <-> jiffies (HZ)
- */
-#define cputime_to_jiffies(__ct)	\
-	cputime_div(__ct, NSEC_PER_SEC / HZ)
-#define jiffies_to_cputime(__jif)	\
-	(__force cputime_t)((__jif) * (NSEC_PER_SEC / HZ))
-#define cputime64_to_jiffies64(__ct)	\
-	cputime_div(__ct, NSEC_PER_SEC / HZ)
-#define jiffies64_to_cputime64(__jif)	\
-	(__force cputime64_t)((__jif) * (NSEC_PER_SEC / HZ))
-
-
-/*
- * Convert cputime <-> nanoseconds
- */
-#define cputime_to_nsecs(__ct)		\
-	(__force u64)(__ct)
-#define nsecs_to_cputime(__nsecs)	\
-	(__force cputime_t)(__nsecs)
-#define nsecs_to_cputime64(__nsecs)	\
-	(__force cputime64_t)(__nsecs)
-
-
-/*
- * Convert cputime <-> microseconds
- */
-#define cputime_to_usecs(__ct)		\
-	cputime_div(__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)		\
-	cputime_div(__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 = (u64)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)
-{
-	u32 rem;
-
-	val->tv_sec = cputime_div_rem(ct, NSEC_PER_SEC, &rem);
-	val->tv_nsec = rem;
-}
-
-/*
- * Convert cputime <-> timeval (msec)
- */
-static inline cputime_t timeval_to_cputime(const struct timeval *val)
-{
-	u64 ret = (u64)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)
-{
-	u32 rem;
-
-	val->tv_sec = cputime_div_rem(ct, NSEC_PER_SEC, &rem);
-	val->tv_usec = rem / NSEC_PER_USEC;
-}
-
-/*
- * Convert cputime <-> clock (USER_HZ)
- */
-#define cputime_to_clock_t(__ct)	\
-	cputime_div(__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)
-
-#endif

include/linux/clocksource.h

@@ -62,6 +62,8 @@ struct module;
  * @archdata:		arch-specific data
  * @suspend:		suspend function for the clocksource, if necessary
  * @resume:		resume function for the clocksource, if necessary
+ * @mark_unstable:	Optional function to inform the clocksource driver that
+ *			the watchdog marked the clocksource unstable
  * @owner:		module reference, must be set by clocksource in modules
  *
  * Note: This struct is not used in hotpathes of the timekeeping code
@@ -93,6 +95,7 @@ struct clocksource {
 	unsigned long flags;
 	void (*suspend)(struct clocksource *cs);
 	void (*resume)(struct clocksource *cs);
+	void (*mark_unstable)(struct clocksource *cs);
 
 	/* private: */
 #ifdef CONFIG_CLOCKSOURCE_WATCHDOG

include/linux/compat.h

@@ -731,7 +731,25 @@ asmlinkage long compat_sys_fanotify_mark(int, unsigned int, __u32, __u32,
 static inline bool in_compat_syscall(void) { return is_compat_task(); }
 #endif
 
-#else
+/**
+ * ns_to_compat_timeval - Compat version of ns_to_timeval
+ * @nsec:	the nanoseconds value to be converted
+ *
+ * Returns the compat_timeval representation of the nsec parameter.
+ */
+static inline struct compat_timeval ns_to_compat_timeval(s64 nsec)
+{
+	struct timeval tv;
+	struct compat_timeval ctv;
+
+	tv = ns_to_timeval(nsec);
+	ctv.tv_sec = tv.tv_sec;
+	ctv.tv_usec = tv.tv_usec;
+
+	return ctv;
+}
+
+#else /* !CONFIG_COMPAT */
 
 #define is_compat_task() (0)
 static inline bool in_compat_syscall(void) { return false; }

include/linux/cputime.h

@@ -1,6 +1,7 @@
 #ifndef __LINUX_CPUTIME_H
 #define __LINUX_CPUTIME_H
 
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 #include <asm/cputime.h>
 
 #ifndef cputime_to_nsecs
@@ -8,9 +9,5 @@
 	(cputime_to_usecs(__ct) * NSEC_PER_USEC)
 #endif
 
-#ifndef nsecs_to_cputime
-# define nsecs_to_cputime(__nsecs)	\
-	usecs_to_cputime((__nsecs) / NSEC_PER_USEC)
-#endif
-
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 #endif /* __LINUX_CPUTIME_H */

include/linux/delayacct.h

@@ -17,6 +17,7 @@
 #ifndef _LINUX_DELAYACCT_H
 #define _LINUX_DELAYACCT_H
 
+#include <uapi/linux/taskstats.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
 

include/linux/jiffies.h

@@ -293,6 +293,8 @@ static inline u64 jiffies_to_nsecs(const unsigned long j)
 	return (u64)jiffies_to_usecs(j) * NSEC_PER_USEC;
 }
 
+extern u64 jiffies64_to_nsecs(u64 j);
+
 extern unsigned long __msecs_to_jiffies(const unsigned int m);
 #if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
 /*

include/linux/kernel_stat.h

@@ -9,7 +9,6 @@
 #include <linux/sched.h>
 #include <linux/vtime.h>
 #include <asm/irq.h>
-#include <linux/cputime.h>
 
 /*
  * 'kernel_stat.h' contains the definitions needed for doing
@@ -78,15 +77,18 @@ static inline unsigned int kstat_cpu_irqs_sum(unsigned int cpu)
 	return kstat_cpu(cpu).irqs_sum;
 }
 
-extern void account_user_time(struct task_struct *, cputime_t);
-extern void account_system_time(struct task_struct *, int, cputime_t);
-extern void account_steal_time(cputime_t);
-extern void account_idle_time(cputime_t);
+extern void account_user_time(struct task_struct *, u64);
+extern void account_guest_time(struct task_struct *, u64);
+extern void account_system_time(struct task_struct *, int, u64);
+extern void account_system_index_time(struct task_struct *, u64,
+				      enum cpu_usage_stat);
+extern void account_steal_time(u64);
+extern void account_idle_time(u64);
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 static inline void account_process_tick(struct task_struct *tsk, int user)
 {
-	vtime_account_user(tsk);
+	vtime_flush(tsk);
 }
 #else
 extern void account_process_tick(struct task_struct *, int user);

include/linux/mutex.h

@@ -156,10 +156,12 @@ extern int __must_check mutex_lock_interruptible_nested(struct mutex *lock,
 					unsigned int subclass);
 extern int __must_check mutex_lock_killable_nested(struct mutex *lock,
 					unsigned int subclass);
+extern void mutex_lock_io_nested(struct mutex *lock, unsigned int subclass);
 
 #define mutex_lock(lock) mutex_lock_nested(lock, 0)
 #define mutex_lock_interruptible(lock) mutex_lock_interruptible_nested(lock, 0)
 #define mutex_lock_killable(lock) mutex_lock_killable_nested(lock, 0)
+#define mutex_lock_io(lock) mutex_lock_io_nested(lock, 0)
 
 #define mutex_lock_nest_lock(lock, nest_lock)				\
 do {									\
@@ -171,11 +173,13 @@ do {									\
 extern void mutex_lock(struct mutex *lock);
 extern int __must_check mutex_lock_interruptible(struct mutex *lock);
 extern int __must_check mutex_lock_killable(struct mutex *lock);
+extern void mutex_lock_io(struct mutex *lock);
 
 # define mutex_lock_nested(lock, subclass) mutex_lock(lock)
 # define mutex_lock_interruptible_nested(lock, subclass) mutex_lock_interruptible(lock)
 # define mutex_lock_killable_nested(lock, subclass) mutex_lock_killable(lock)
 # define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock)
+# define mutex_lock_io_nested(lock, subclass) mutex_lock(lock)
 #endif
 
 /*

include/linux/posix-timers.h

@@ -8,19 +8,9 @@
 #include <linux/alarmtimer.h>
 
 
-static inline unsigned long long cputime_to_expires(cputime_t expires)
-{
-	return (__force unsigned long long)expires;
-}
-
-static inline cputime_t expires_to_cputime(unsigned long long expires)
-{
-	return (__force cputime_t)expires;
-}
-
 struct cpu_timer_list {
 	struct list_head entry;
-	unsigned long long expires, incr;
+	u64 expires, incr;
 	struct task_struct *task;
 	int firing;
 };
@@ -129,7 +119,7 @@ void run_posix_cpu_timers(struct task_struct *task);
 void posix_cpu_timers_exit(struct task_struct *task);
 void posix_cpu_timers_exit_group(struct task_struct *task);
 void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx,
-			   cputime_t *newval, cputime_t *oldval);
+			   u64 *newval, u64 *oldval);
 
 long clock_nanosleep_restart(struct restart_block *restart_block);
 

include/linux/sched.h

@@ -29,7 +29,6 @@ struct sched_param {
 
 #include <asm/page.h>
 #include <asm/ptrace.h>
-#include <linux/cputime.h>
 
 #include <linux/smp.h>
 #include <linux/sem.h>
@@ -461,12 +460,10 @@ extern signed long schedule_timeout_idle(signed long timeout);
 asmlinkage void schedule(void);
 extern void schedule_preempt_disabled(void);
 
+extern int __must_check io_schedule_prepare(void);
+extern void io_schedule_finish(int token);
 extern long io_schedule_timeout(long timeout);
-
-static inline void io_schedule(void)
-{
-	io_schedule_timeout(MAX_SCHEDULE_TIMEOUT);
-}
+extern void io_schedule(void);
 
 void __noreturn do_task_dead(void);
 
@@ -565,15 +562,13 @@ struct pacct_struct {
 	int			ac_flag;
 	long			ac_exitcode;
 	unsigned long		ac_mem;
-	cputime_t		ac_utime, ac_stime;
+	u64			ac_utime, ac_stime;
 	unsigned long		ac_minflt, ac_majflt;
 };
 
 struct cpu_itimer {
-	cputime_t expires;
-	cputime_t incr;
-	u32 error;
-	u32 incr_error;
+	u64 expires;
+	u64 incr;
 };
 
 /**
@@ -587,8 +582,8 @@ struct cpu_itimer {
  */
 struct prev_cputime {
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-	cputime_t utime;
-	cputime_t stime;
+	u64 utime;
+	u64 stime;
 	raw_spinlock_t lock;
 #endif
 };
@@ -603,8 +598,8 @@ static inline void prev_cputime_init(struct prev_cputime *prev)
 
 /**
  * struct task_cputime - collected CPU time counts
- * @utime:		time spent in user mode, in &cputime_t units
- * @stime:		time spent in kernel mode, in &cputime_t units
+ * @utime:		time spent in user mode, in nanoseconds
+ * @stime:		time spent in kernel mode, in nanoseconds
  * @sum_exec_runtime:	total time spent on the CPU, in nanoseconds
  *
  * This structure groups together three kinds of CPU time that are tracked for
@@ -612,8 +607,8 @@ static inline void prev_cputime_init(struct prev_cputime *prev)
  * these counts together and treat all three of them in parallel.
  */
 struct task_cputime {
-	cputime_t utime;
-	cputime_t stime;
+	u64 utime;
+	u64 stime;
 	unsigned long long sum_exec_runtime;
 };
 
@@ -622,13 +617,6 @@ struct task_cputime {
 #define prof_exp	stime
 #define sched_exp	sum_exec_runtime
 
-#define INIT_CPUTIME	\
-	(struct task_cputime) {					\
-		.utime = 0,					\
-		.stime = 0,					\
-		.sum_exec_runtime = 0,				\
-	}
-
 /*
  * This is the atomic variant of task_cputime, which can be used for
  * storing and updating task_cputime statistics without locking.
@@ -787,9 +775,9 @@ struct signal_struct {
 	 * in __exit_signal, except for the group leader.
 	 */
 	seqlock_t stats_lock;
-	cputime_t utime, stime, cutime, cstime;
-	cputime_t gtime;
-	cputime_t cgtime;
+	u64 utime, stime, cutime, cstime;
+	u64 gtime;
+	u64 cgtime;
 	struct prev_cputime prev_cputime;
 	unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
 	unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
@@ -1668,11 +1656,11 @@ struct task_struct {
 	int __user *set_child_tid;		/* CLONE_CHILD_SETTID */
 	int __user *clear_child_tid;		/* CLONE_CHILD_CLEARTID */
 
-	cputime_t utime, stime;
+	u64 utime, stime;
 #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
-	cputime_t utimescaled, stimescaled;
+	u64 utimescaled, stimescaled;
 #endif
-	cputime_t gtime;
+	u64 gtime;
 	struct prev_cputime prev_cputime;
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
 	seqcount_t vtime_seqcount;
@@ -1824,7 +1812,7 @@ struct task_struct {
 #if defined(CONFIG_TASK_XACCT)
 	u64 acct_rss_mem1;	/* accumulated rss usage */
 	u64 acct_vm_mem1;	/* accumulated virtual memory usage */
-	cputime_t acct_timexpd;	/* stime + utime since last update */
+	u64 acct_timexpd;	/* stime + utime since last update */
 #endif
 #ifdef CONFIG_CPUSETS
 	nodemask_t mems_allowed;	/* Protected by alloc_lock */
@@ -2269,17 +2257,17 @@ struct task_struct *try_get_task_struct(struct task_struct **ptask);
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
 extern void task_cputime(struct task_struct *t,
-			 cputime_t *utime, cputime_t *stime);
-extern cputime_t task_gtime(struct task_struct *t);
+			 u64 *utime, u64 *stime);
+extern u64 task_gtime(struct task_struct *t);
 #else
 static inline void task_cputime(struct task_struct *t,
-				cputime_t *utime, cputime_t *stime)
+				u64 *utime, u64 *stime)
 {
 	*utime = t->utime;
 	*stime = t->stime;
 }
 
-static inline cputime_t task_gtime(struct task_struct *t)
+static inline u64 task_gtime(struct task_struct *t)
 {
 	return t->gtime;
 }
@@ -2287,23 +2275,23 @@ static inline cputime_t task_gtime(struct task_struct *t)
 
 #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
 static inline void task_cputime_scaled(struct task_struct *t,
-				       cputime_t *utimescaled,
-				       cputime_t *stimescaled)
+				       u64 *utimescaled,
+				       u64 *stimescaled)
 {
 	*utimescaled = t->utimescaled;
 	*stimescaled = t->stimescaled;
 }
 #else
 static inline void task_cputime_scaled(struct task_struct *t,
-				       cputime_t *utimescaled,
-				       cputime_t *stimescaled)
+				       u64 *utimescaled,
+				       u64 *stimescaled)
 {
 	task_cputime(t, utimescaled, stimescaled);
 }
 #endif
 
-extern void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st);
-extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st);
+extern void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st);
+extern void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st);
 
 /*
  * Per process flags
@@ -2522,10 +2510,18 @@ extern u64 sched_clock_cpu(int cpu);
 extern void sched_clock_init(void);
 
 #ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+static inline void sched_clock_init_late(void)
+{
+}
+
 static inline void sched_clock_tick(void)
 {
 }
 
+static inline void clear_sched_clock_stable(void)
+{
+}
+
 static inline void sched_clock_idle_sleep_event(void)
 {
 }
@@ -2544,6 +2540,7 @@ static inline u64 local_clock(void)
 	return sched_clock();
 }
 #else
+extern void sched_clock_init_late(void);
 /*
  * Architectures can set this to 1 if they have specified
  * CONFIG_HAVE_UNSTABLE_SCHED_CLOCK in their arch Kconfig,
@@ -2551,7 +2548,6 @@ static inline u64 local_clock(void)
  * is reliable after all:
  */
 extern int sched_clock_stable(void);
-extern void set_sched_clock_stable(void);
 extern void clear_sched_clock_stable(void);
 
 extern void sched_clock_tick(void);

include/linux/sched/sysctl.h

@@ -59,6 +59,7 @@ extern unsigned int sysctl_sched_cfs_bandwidth_slice;
 extern unsigned int sysctl_sched_autogroup_enabled;
 #endif
 
+extern int sysctl_sched_rr_timeslice;
 extern int sched_rr_timeslice;
 
 extern int sched_rr_handler(struct ctl_table *table, int write,

include/linux/vtime.h

@@ -58,27 +58,28 @@ static inline void vtime_task_switch(struct task_struct *prev)
 
 extern void vtime_account_system(struct task_struct *tsk);
 extern void vtime_account_idle(struct task_struct *tsk);
-extern void vtime_account_user(struct task_struct *tsk);
 
 #else /* !CONFIG_VIRT_CPU_ACCOUNTING */
 
 static inline void vtime_task_switch(struct task_struct *prev) { }
 static inline void vtime_account_system(struct task_struct *tsk) { }
-static inline void vtime_account_user(struct task_struct *tsk) { }
 #endif /* !CONFIG_VIRT_CPU_ACCOUNTING */
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
 extern void arch_vtime_task_switch(struct task_struct *tsk);
+extern void vtime_account_user(struct task_struct *tsk);
 extern void vtime_user_enter(struct task_struct *tsk);
 
 static inline void vtime_user_exit(struct task_struct *tsk)
 {
 	vtime_account_user(tsk);
 }
+
 extern void vtime_guest_enter(struct task_struct *tsk);
 extern void vtime_guest_exit(struct task_struct *tsk);
 extern void vtime_init_idle(struct task_struct *tsk, int cpu);
 #else /* !CONFIG_VIRT_CPU_ACCOUNTING_GEN  */
+static inline void vtime_account_user(struct task_struct *tsk) { }
 static inline void vtime_user_enter(struct task_struct *tsk) { }
 static inline void vtime_user_exit(struct task_struct *tsk) { }
 static inline void vtime_guest_enter(struct task_struct *tsk) { }
@@ -93,9 +94,11 @@ static inline void vtime_account_irq_exit(struct task_struct *tsk)
 	/* On hard|softirq exit we always account to hard|softirq cputime */
 	vtime_account_system(tsk);
 }
+extern void vtime_flush(struct task_struct *tsk);
 #else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 static inline void vtime_account_irq_enter(struct task_struct *tsk) { }
 static inline void vtime_account_irq_exit(struct task_struct *tsk) { }
+static inline void vtime_flush(struct task_struct *tsk) { }
 #endif
 
 

include/trace/events/timer.h

@@ -269,17 +269,17 @@ DEFINE_EVENT(hrtimer_class, hrtimer_cancel,
 TRACE_EVENT(itimer_state,
 
 	TP_PROTO(int which, const struct itimerval *const value,
-		 cputime_t expires),
+		 unsigned long long expires),
 
 	TP_ARGS(which, value, expires),
 
 	TP_STRUCT__entry(
-		__field(	int,		which		)
-		__field(	cputime_t,	expires		)
-		__field(	long,		value_sec	)
-		__field(	long,		value_usec	)
-		__field(	long,		interval_sec	)
-		__field(	long,		interval_usec	)
+		__field(	int,			which		)
+		__field(	unsigned long long,	expires		)
+		__field(	long,			value_sec	)
+		__field(	long,			value_usec	)
+		__field(	long,			interval_sec	)
+		__field(	long,			interval_usec	)
 	),
 
 	TP_fast_assign(
@@ -292,7 +292,7 @@ TRACE_EVENT(itimer_state,
 	),
 
 	TP_printk("which=%d expires=%llu it_value=%ld.%ld it_interval=%ld.%ld",
-		  __entry->which, (unsigned long long)__entry->expires,
+		  __entry->which, __entry->expires,
 		  __entry->value_sec, __entry->value_usec,
 		  __entry->interval_sec, __entry->interval_usec)
 );
@@ -305,14 +305,14 @@ TRACE_EVENT(itimer_state,
  */
 TRACE_EVENT(itimer_expire,
 
-	TP_PROTO(int which, struct pid *pid, cputime_t now),
+	TP_PROTO(int which, struct pid *pid, unsigned long long now),
 
 	TP_ARGS(which, pid, now),
 
 	TP_STRUCT__entry(
-		__field( int ,		which	)
-		__field( pid_t,		pid	)
-		__field( cputime_t,	now	)
+		__field( int ,			which	)
+		__field( pid_t,			pid	)
+		__field( unsigned long long,	now	)
 	),
 
 	TP_fast_assign(
@@ -322,7 +322,7 @@ TRACE_EVENT(itimer_expire,
 	),
 
 	TP_printk("which=%d pid=%d now=%llu", __entry->which,
-		  (int) __entry->pid, (unsigned long long)__entry->now)
+		  (int) __entry->pid, __entry->now)
 );
 
 #ifdef CONFIG_NO_HZ_COMMON

init/main.c

@@ -625,7 +625,6 @@ asmlinkage __visible void __init start_kernel(void)
 	numa_policy_init();
 	if (late_time_init)
 		late_time_init();
-	sched_clock_init();
 	calibrate_delay();
 	pidmap_init();
 	anon_vma_init();

kernel/acct.c

@@ -453,8 +453,8 @@ static void fill_ac(acct_t *ac)
 	spin_lock_irq(&current->sighand->siglock);
 	tty = current->signal->tty;	/* Safe as we hold the siglock */
 	ac->ac_tty = tty ? old_encode_dev(tty_devnum(tty)) : 0;
-	ac->ac_utime = encode_comp_t(jiffies_to_AHZ(cputime_to_jiffies(pacct->ac_utime)));
-	ac->ac_stime = encode_comp_t(jiffies_to_AHZ(cputime_to_jiffies(pacct->ac_stime)));
+	ac->ac_utime = encode_comp_t(nsec_to_AHZ(pacct->ac_utime));
+	ac->ac_stime = encode_comp_t(nsec_to_AHZ(pacct->ac_stime));
 	ac->ac_flag = pacct->ac_flag;
 	ac->ac_mem = encode_comp_t(pacct->ac_mem);
 	ac->ac_minflt = encode_comp_t(pacct->ac_minflt);
@@ -530,7 +530,7 @@ out:
 void acct_collect(long exitcode, int group_dead)
 {
 	struct pacct_struct *pacct = &current->signal->pacct;
-	cputime_t utime, stime;
+	u64 utime, stime;
 	unsigned long vsize = 0;
 
 	if (group_dead && current->mm) {
@@ -559,6 +559,7 @@ void acct_collect(long exitcode, int group_dead)
 		pacct->ac_flag |= ACORE;
 	if (current->flags & PF_SIGNALED)
 		pacct->ac_flag |= AXSIG;
+
 	task_cputime(current, &utime, &stime);
 	pacct->ac_utime += utime;
 	pacct->ac_stime += stime;

kernel/delayacct.c

@@ -82,19 +82,19 @@ void __delayacct_blkio_end(void)
 
 int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
 {
-	cputime_t utime, stime, stimescaled, utimescaled;
+	u64 utime, stime, stimescaled, utimescaled;
 	unsigned long long t2, t3;
 	unsigned long flags, t1;
 	s64 tmp;
 
 	task_cputime(tsk, &utime, &stime);
 	tmp = (s64)d->cpu_run_real_total;
-	tmp += cputime_to_nsecs(utime + stime);
+	tmp += utime + stime;
 	d->cpu_run_real_total = (tmp < (s64)d->cpu_run_real_total) ? 0 : tmp;
 
 	task_cputime_scaled(tsk, &utimescaled, &stimescaled);
 	tmp = (s64)d->cpu_scaled_run_real_total;
-	tmp += cputime_to_nsecs(utimescaled + stimescaled);
+	tmp += utimescaled + stimescaled;
 	d->cpu_scaled_run_real_total =
 		(tmp < (s64)d->cpu_scaled_run_real_total) ? 0 : tmp;
 

kernel/exit.c

@@ -86,7 +86,7 @@ static void __exit_signal(struct task_struct *tsk)
 	bool group_dead = thread_group_leader(tsk);
 	struct sighand_struct *sighand;
 	struct tty_struct *uninitialized_var(tty);
-	cputime_t utime, stime;
+	u64 utime, stime;
 
 	sighand = rcu_dereference_check(tsk->sighand,
 					lockdep_tasklist_lock_is_held());
@@ -1091,7 +1091,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		struct signal_struct *sig = p->signal;
 		struct signal_struct *psig = current->signal;
 		unsigned long maxrss;
-		cputime_t tgutime, tgstime;
+		u64 tgutime, tgstime;
 
 		/*
 		 * The resource counters for the group leader are in its

kernel/fork.c

@@ -1314,7 +1314,7 @@ static void posix_cpu_timers_init_group(struct signal_struct *sig)
 
 	cpu_limit = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
 	if (cpu_limit != RLIM_INFINITY) {
-		sig->cputime_expires.prof_exp = secs_to_cputime(cpu_limit);
+		sig->cputime_expires.prof_exp = cpu_limit * NSEC_PER_SEC;
 		sig->cputimer.running = true;
 	}
 

kernel/locking/mutex.c

@@ -783,6 +783,20 @@ mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass)
 }
 EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested);
 
+void __sched
+mutex_lock_io_nested(struct mutex *lock, unsigned int subclass)
+{
+	int token;
+
+	might_sleep();
+
+	token = io_schedule_prepare();
+	__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE,
+			    subclass, NULL, _RET_IP_, NULL, 0);
+	io_schedule_finish(token);
+}
+EXPORT_SYMBOL_GPL(mutex_lock_io_nested);
+
 static inline int
 ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
 {
@@ -950,6 +964,16 @@ int __sched mutex_lock_killable(struct mutex *lock)
 }
 EXPORT_SYMBOL(mutex_lock_killable);
 
+void __sched mutex_lock_io(struct mutex *lock)
+{
+	int token;
+
+	token = io_schedule_prepare();
+	mutex_lock(lock);
+	io_schedule_finish(token);
+}
+EXPORT_SYMBOL_GPL(mutex_lock_io);
+
 static noinline void __sched
 __mutex_lock_slowpath(struct mutex *lock)
 {

kernel/sched/Makefile

@@ -18,8 +18,8 @@ endif
 obj-y += core.o loadavg.o clock.o cputime.o
 obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o
 obj-y += wait.o swait.o completion.o idle.o
-obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o
-obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
+obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o
+obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o
 obj-$(CONFIG_SCHED_DEBUG) += debug.o
 obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o