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

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (40 commits)
  sched/tracing: Add a new tracepoint for sleeptime
  sched: Disable scheduler warnings during oopses
  sched: Fix cgroup movement of waking process
  sched: Fix cgroup movement of newly created process
  sched: Fix cgroup movement of forking process
  sched: Remove cfs bandwidth period check in tg_set_cfs_period()
  sched: Fix load-balance lock-breaking
  sched: Replace all_pinned with a generic flags field
  sched: Only queue remote wakeups when crossing cache boundaries
  sched: Add missing rcu_dereference() around ->real_parent usage
  [S390] fix cputime overflow in uptime_proc_show
  [S390] cputime: add sparse checking and cleanup
  sched: Mark parent and real_parent as __rcu
  sched, nohz: Fix missing RCU read lock
  sched, nohz: Set the NOHZ_BALANCE_KICK flag for idle load balancer
  sched, nohz: Fix the idle cpu check in nohz_idle_balance
  sched: Use jump_labels for sched_feat
  sched/accounting: Fix parameter passing in task_group_account_field
  sched/accounting: Fix user/system tick double accounting
  sched/accounting: Re-use scheduler statistics for the root cgroup
  ...

Fix up conflicts in
 - arch/ia64/include/asm/cputime.h, include/asm-generic/cputime.h
	usecs_to_cputime64() vs the sparse cleanups
 - kernel/sched/fair.c, kernel/time/tick-sched.c
	scheduler changes in multiple branches

5 files changed, 133 insertions, 167 deletions

diff --git a/arch/ia64/include/asm/cputime.h b/arch/ia64/include/asm/cputime.h
index 5a274af31b2..3deac956d32 100644
--- a/arch/ia64/include/asm/cputime.h
+++ b/arch/ia64/include/asm/cputime.h
@@ -26,60 +26,53 @@
 #include <linux/jiffies.h>
 #include <asm/processor.h>
 
-typedef u64 cputime_t;
-typedef u64 cputime64_t;
+typedef u64 __nocast cputime_t;
+typedef u64 __nocast cputime64_t;
 
-#define cputime_zero			((cputime_t)0)
 #define cputime_one_jiffy		jiffies_to_cputime(1)
-#define cputime_max			((~((cputime_t)0) >> 1) - 1)
-#define cputime_add(__a, __b)		((__a) +  (__b))
-#define cputime_sub(__a, __b)		((__a) -  (__b))
-#define cputime_div(__a, __n)		((__a) /  (__n))
-#define cputime_halve(__a)		((__a) >> 1)
-#define cputime_eq(__a, __b)		((__a) == (__b))
-#define cputime_gt(__a, __b)		((__a) >  (__b))
-#define cputime_ge(__a, __b)		((__a) >= (__b))
-#define cputime_lt(__a, __b)		((__a) <  (__b))
-#define cputime_le(__a, __b)		((__a) <= (__b))
-
-#define cputime64_zero			((cputime64_t)0)
-#define cputime64_add(__a, __b)		((__a) + (__b))
-#define cputime64_sub(__a, __b)		((__a) - (__b))
-#define cputime_to_cputime64(__ct)	(__ct)
 
 /*
  * Convert cputime <-> jiffies (HZ)
  */
-#define cputime_to_jiffies(__ct)	((__ct) / (NSEC_PER_SEC / HZ))
-#define jiffies_to_cputime(__jif)	((__jif) * (NSEC_PER_SEC / HZ))
-#define cputime64_to_jiffies64(__ct)	((__ct) / (NSEC_PER_SEC / HZ))
-#define jiffies64_to_cputime64(__jif)	((__jif) * (NSEC_PER_SEC / HZ))
+#define cputime_to_jiffies(__ct)	\
+	((__force u64)(__ct) / (NSEC_PER_SEC / HZ))
+#define jiffies_to_cputime(__jif)	\
+	(__force cputime_t)((__jif) * (NSEC_PER_SEC / HZ))
+#define cputime64_to_jiffies64(__ct)	\
+	((__force u64)(__ct) / (NSEC_PER_SEC / HZ))
+#define jiffies64_to_cputime64(__jif)	\
+	(__force cputime64_t)((__jif) * (NSEC_PER_SEC / HZ))
 
 /*
  * Convert cputime <-> microseconds
  */
-#define cputime_to_usecs(__ct)		((__ct) / NSEC_PER_USEC)
-#define usecs_to_cputime(__usecs)	((__usecs) * NSEC_PER_USEC)
-#define usecs_to_cputime64(__usecs)	usecs_to_cputime(__usecs)
+#define cputime_to_usecs(__ct)		\
+	((__force u64)(__ct) / NSEC_PER_USEC)
+#define usecs_to_cputime(__usecs)	\
+	(__force cputime_t)((__usecs) * NSEC_PER_USEC)
+#define usecs_to_cputime64(__usecs)	\
+	(__force cputime64_t)((__usecs) * NSEC_PER_USEC)
 
 /*
  * Convert cputime <-> seconds
  */
-#define cputime_to_secs(__ct)		((__ct) / NSEC_PER_SEC)
-#define secs_to_cputime(__secs)		((__secs) * NSEC_PER_SEC)
+#define cputime_to_secs(__ct)		\
+	((__force u64)(__ct) / NSEC_PER_SEC)
+#define secs_to_cputime(__secs)		\
+	(__force cputime_t)((__secs) * NSEC_PER_SEC)
 
 /*
  * Convert cputime <-> timespec (nsec)
  */
 static inline cputime_t timespec_to_cputime(const struct timespec *val)
 {
-	cputime_t ret = val->tv_sec * NSEC_PER_SEC;
-	return (ret + val->tv_nsec);
+	u64 ret = val->tv_sec * NSEC_PER_SEC + val->tv_nsec;
+	return (__force cputime_t) ret;
 }
 static inline void cputime_to_timespec(const cputime_t ct, struct timespec *val)
 {
-	val->tv_sec  = ct / NSEC_PER_SEC;
-	val->tv_nsec = ct % NSEC_PER_SEC;
+	val->tv_sec  = (__force u64) ct / NSEC_PER_SEC;
+	val->tv_nsec = (__force u64) ct % NSEC_PER_SEC;
 }
 
 /*
@@ -87,25 +80,28 @@ static inline void cputime_to_timespec(const cputime_t ct, struct timespec *val)
  */
 static inline cputime_t timeval_to_cputime(struct timeval *val)
 {
-	cputime_t ret = val->tv_sec * NSEC_PER_SEC;
-	return (ret + val->tv_usec * NSEC_PER_USEC);
+	u64 ret = val->tv_sec * NSEC_PER_SEC + val->tv_usec * NSEC_PER_USEC;
+	return (__force cputime_t) ret;
 }
 static inline void cputime_to_timeval(const cputime_t ct, struct timeval *val)
 {
-	val->tv_sec = ct / NSEC_PER_SEC;
-	val->tv_usec = (ct % NSEC_PER_SEC) / NSEC_PER_USEC;
+	val->tv_sec = (__force u64) ct / NSEC_PER_SEC;
+	val->tv_usec = ((__force u64) ct % NSEC_PER_SEC) / NSEC_PER_USEC;
 }
 
 /*
  * Convert cputime <-> clock (USER_HZ)
  */
-#define cputime_to_clock_t(__ct)	((__ct) / (NSEC_PER_SEC / USER_HZ))
-#define clock_t_to_cputime(__x)		((__x) * (NSEC_PER_SEC / USER_HZ))
+#define cputime_to_clock_t(__ct)	\
+	((__force u64)(__ct) / (NSEC_PER_SEC / USER_HZ))
+#define clock_t_to_cputime(__x)		\
+	(__force cputime_t)((__x) * (NSEC_PER_SEC / USER_HZ))
 
 /*
  * Convert cputime64 to clock.
  */
-#define cputime64_to_clock_t(__ct)      cputime_to_clock_t((cputime_t)__ct)
+#define cputime64_to_clock_t(__ct)	\
+	cputime_to_clock_t((__force cputime_t)__ct)
 
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING */
 #endif /* __IA64_CPUTIME_H */
diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h
index 98b7c4b49c9..6ec1c380a4d 100644
--- a/arch/powerpc/include/asm/cputime.h
+++ b/arch/powerpc/include/asm/cputime.h
@@ -29,25 +29,8 @@ static inline void setup_cputime_one_jiffy(void) { }
 #include <asm/time.h>
 #include <asm/param.h>
 
-typedef u64 cputime_t;
-typedef u64 cputime64_t;
-
-#define cputime_zero			((cputime_t)0)
-#define cputime_max			((~((cputime_t)0) >> 1) - 1)
-#define cputime_add(__a, __b)		((__a) +  (__b))
-#define cputime_sub(__a, __b)		((__a) -  (__b))
-#define cputime_div(__a, __n)		((__a) /  (__n))
-#define cputime_halve(__a)		((__a) >> 1)
-#define cputime_eq(__a, __b)		((__a) == (__b))
-#define cputime_gt(__a, __b)		((__a) >  (__b))
-#define cputime_ge(__a, __b)		((__a) >= (__b))
-#define cputime_lt(__a, __b)		((__a) <  (__b))
-#define cputime_le(__a, __b)		((__a) <= (__b))
-
-#define cputime64_zero			((cputime64_t)0)
-#define cputime64_add(__a, __b)		((__a) + (__b))
-#define cputime64_sub(__a, __b)		((__a) - (__b))
-#define cputime_to_cputime64(__ct)	(__ct)
+typedef u64 __nocast cputime_t;
+typedef u64 __nocast cputime64_t;
 
 #ifdef __KERNEL__
 
@@ -65,7 +48,7 @@ DECLARE_PER_CPU(unsigned long, cputime_scaled_last_delta);
 
 static inline unsigned long cputime_to_jiffies(const cputime_t ct)
 {
-	return mulhdu(ct, __cputime_jiffies_factor);
+	return mulhdu((__force u64) ct, __cputime_jiffies_factor);
 }
 
 /* Estimate the scaled cputime by scaling the real cputime based on
@@ -74,14 +57,15 @@ static inline cputime_t cputime_to_scaled(const cputime_t ct)
 {
 	if (cpu_has_feature(CPU_FTR_SPURR) &&
 	    __get_cpu_var(cputime_last_delta))
-		return ct * __get_cpu_var(cputime_scaled_last_delta) /
-			    __get_cpu_var(cputime_last_delta);
+		return (__force u64) ct *
+			__get_cpu_var(cputime_scaled_last_delta) /
+			__get_cpu_var(cputime_last_delta);
 	return ct;
 }
 
 static inline cputime_t jiffies_to_cputime(const unsigned long jif)
 {
-	cputime_t ct;
+	u64 ct;
 	unsigned long sec;
 
 	/* have to be a little careful about overflow */
@@ -93,7 +77,7 @@ static inline cputime_t jiffies_to_cputime(const unsigned long jif)
 	}
 	if (sec)
 		ct += (cputime_t) sec * tb_ticks_per_sec;
-	return ct;
+	return (__force cputime_t) ct;
 }
 
 static inline void setup_cputime_one_jiffy(void)
@@ -103,7 +87,7 @@ static inline void setup_cputime_one_jiffy(void)
 
 static inline cputime64_t jiffies64_to_cputime64(const u64 jif)
 {
-	cputime_t ct;
+	u64 ct;
 	u64 sec;
 
 	/* have to be a little careful about overflow */
@@ -114,13 +98,13 @@ static inline cputime64_t jiffies64_to_cputime64(const u64 jif)
 		do_div(ct, HZ);
 	}
 	if (sec)
-		ct += (cputime_t) sec * tb_ticks_per_sec;
-	return ct;
+		ct += (u64) sec * tb_ticks_per_sec;
+	return (__force cputime64_t) ct;
 }
 
 static inline u64 cputime64_to_jiffies64(const cputime_t ct)
 {
-	return mulhdu(ct, __cputime_jiffies_factor);
+	return mulhdu((__force u64) ct, __cputime_jiffies_factor);
 }
 
 /*
@@ -130,12 +114,12 @@ extern u64 __cputime_msec_factor;
 
 static inline unsigned long cputime_to_usecs(const cputime_t ct)
 {
-	return mulhdu(ct, __cputime_msec_factor) * USEC_PER_MSEC;
+	return mulhdu((__force u64) ct, __cputime_msec_factor) * USEC_PER_MSEC;
 }
 
 static inline cputime_t usecs_to_cputime(const unsigned long us)
 {
-	cputime_t ct;
+	u64 ct;
 	unsigned long sec;
 
 	/* have to be a little careful about overflow */
@@ -147,7 +131,7 @@ static inline cputime_t usecs_to_cputime(const unsigned long us)
 	}
 	if (sec)
 		ct += (cputime_t) sec * tb_ticks_per_sec;
-	return ct;
+	return (__force cputime_t) ct;
 }
 
 #define usecs_to_cputime64(us)		usecs_to_cputime(us)
@@ -159,12 +143,12 @@ extern u64 __cputime_sec_factor;
 
 static inline unsigned long cputime_to_secs(const cputime_t ct)
 {
-	return mulhdu(ct, __cputime_sec_factor);
+	return mulhdu((__force u64) ct, __cputime_sec_factor);
 }
 
 static inline cputime_t secs_to_cputime(const unsigned long sec)
 {
-	return (cputime_t) sec * tb_ticks_per_sec;
+	return (__force cputime_t)((u64) sec * tb_ticks_per_sec);
 }
 
 /*
@@ -172,7 +156,7 @@ static inline cputime_t secs_to_cputime(const unsigned long sec)
  */
 static inline void cputime_to_timespec(const cputime_t ct, struct timespec *p)
 {
-	u64 x = ct;
+	u64 x = (__force u64) ct;
 	unsigned int frac;
 
 	frac = do_div(x, tb_ticks_per_sec);
@@ -184,11 +168,11 @@ static inline void cputime_to_timespec(const cputime_t ct, struct timespec *p)
 
 static inline cputime_t timespec_to_cputime(const struct timespec *p)
 {
-	cputime_t ct;
+	u64 ct;
 
 	ct = (u64) p->tv_nsec * tb_ticks_per_sec;
 	do_div(ct, 1000000000);
-	return ct + (u64) p->tv_sec * tb_ticks_per_sec;
+	return (__force cputime_t)(ct + (u64) p->tv_sec * tb_ticks_per_sec);
 }
 
 /*
@@ -196,7 +180,7 @@ static inline cputime_t timespec_to_cputime(const struct timespec *p)
  */
 static inline void cputime_to_timeval(const cputime_t ct, struct timeval *p)
 {
-	u64 x = ct;
+	u64 x = (__force u64) ct;
 	unsigned int frac;
 
 	frac = do_div(x, tb_ticks_per_sec);
@@ -208,11 +192,11 @@ static inline void cputime_to_timeval(const cputime_t ct, struct timeval *p)
 
 static inline cputime_t timeval_to_cputime(const struct timeval *p)
 {
-	cputime_t ct;
+	u64 ct;
 
 	ct = (u64) p->tv_usec * tb_ticks_per_sec;
 	do_div(ct, 1000000);
-	return ct + (u64) p->tv_sec * tb_ticks_per_sec;
+	return (__force cputime_t)(ct + (u64) p->tv_sec * tb_ticks_per_sec);
 }
 
 /*
@@ -222,12 +206,12 @@ extern u64 __cputime_clockt_factor;
 
 static inline unsigned long cputime_to_clock_t(const cputime_t ct)
 {
-	return mulhdu(ct, __cputime_clockt_factor);
+	return mulhdu((__force u64) ct, __cputime_clockt_factor);
 }
 
 static inline cputime_t clock_t_to_cputime(const unsigned long clk)
 {
-	cputime_t ct;
+	u64 ct;
 	unsigned long sec;
 
 	/* have to be a little careful about overflow */
@@ -238,8 +222,8 @@ static inline cputime_t clock_t_to_cputime(const unsigned long clk)
 		do_div(ct, USER_HZ);
 	}
 	if (sec)
-		ct += (cputime_t) sec * tb_ticks_per_sec;
-	return ct;
+		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))
diff --git a/arch/s390/appldata/appldata_os.c b/arch/s390/appldata/appldata_os.c
index 92f1cb745d6..4de031d6b76 100644
--- a/arch/s390/appldata/appldata_os.c
+++ b/arch/s390/appldata/appldata_os.c
@@ -115,21 +115,21 @@ 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(kstat_cpu(i).cpustat.user);
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_USER]);
 		os_data->os_cpu[j].per_cpu_nice =
-			cputime_to_jiffies(kstat_cpu(i).cpustat.nice);
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_NICE]);
 		os_data->os_cpu[j].per_cpu_system =
-			cputime_to_jiffies(kstat_cpu(i).cpustat.system);
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]);
 		os_data->os_cpu[j].per_cpu_idle =
-			cputime_to_jiffies(kstat_cpu(i).cpustat.idle);
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IDLE]);
 		os_data->os_cpu[j].per_cpu_irq =
-			cputime_to_jiffies(kstat_cpu(i).cpustat.irq);
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IRQ]);
 		os_data->os_cpu[j].per_cpu_softirq =
-			cputime_to_jiffies(kstat_cpu(i).cpustat.softirq);
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]);
 		os_data->os_cpu[j].per_cpu_iowait =
-			cputime_to_jiffies(kstat_cpu(i).cpustat.iowait);
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IOWAIT]);
 		os_data->os_cpu[j].per_cpu_steal =
-			cputime_to_jiffies(kstat_cpu(i).cpustat.steal);
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_STEAL]);
 		os_data->os_cpu[j].cpu_id = i;
 		j++;
 	}
diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h
index b9acaaa175d..c23c3900c30 100644
--- a/arch/s390/include/asm/cputime.h
+++ b/arch/s390/include/asm/cputime.h
@@ -16,75 +16,60 @@
 
 /* We want to use full resolution of the CPU timer: 2**-12 micro-seconds. */
 
-typedef unsigned long long cputime_t;
-typedef unsigned long long cputime64_t;
+typedef unsigned long long __nocast cputime_t;
+typedef unsigned long long __nocast cputime64_t;
 
-#ifndef __s390x__
-
-static inline unsigned int
-__div(unsigned long long n, unsigned int base)
+static inline unsigned long __div(unsigned long long n, unsigned long base)
 {
+#ifndef __s390x__
 	register_pair rp;
 
 	rp.pair = n >> 1;
 	asm ("dr %0,%1" : "+d" (rp) : "d" (base >> 1));
 	return rp.subreg.odd;
+#else /* __s390x__ */
+	return n / base;
+#endif /* __s390x__ */
 }
 
-#else /* __s390x__ */
+#define cputime_one_jiffy		jiffies_to_cputime(1)
 
-static inline unsigned int
-__div(unsigned long long n, unsigned int base)
+/*
+ * Convert cputime to jiffies and back.
+ */
+static inline unsigned long cputime_to_jiffies(const cputime_t cputime)
 {
-	return n / base;
+	return __div((__force unsigned long long) cputime, 4096000000ULL / HZ);
 }
 
-#endif /* __s390x__ */
+static inline cputime_t jiffies_to_cputime(const unsigned int jif)
+{
+	return (__force cputime_t)(jif * (4096000000ULL / HZ));
+}
 
-#define cputime_zero			(0ULL)
-#define cputime_one_jiffy		jiffies_to_cputime(1)
-#define cputime_max			((~0UL >> 1) - 1)
-#define cputime_add(__a, __b)		((__a) +  (__b))
-#define cputime_sub(__a, __b)		((__a) -  (__b))
-#define cputime_div(__a, __n) ({		\
-	unsigned long long __div = (__a);	\
-	do_div(__div,__n);			\
-	__div;					\
-})
-#define cputime_halve(__a)		((__a) >> 1)
-#define cputime_eq(__a, __b)		((__a) == (__b))
-#define cputime_gt(__a, __b)		((__a) >  (__b))
-#define cputime_ge(__a, __b)		((__a) >= (__b))
-#define cputime_lt(__a, __b)		((__a) <  (__b))
-#define cputime_le(__a, __b)		((__a) <= (__b))
-#define cputime_to_jiffies(__ct)	(__div((__ct), 4096000000ULL / HZ))
-#define cputime_to_scaled(__ct)		(__ct)
-#define jiffies_to_cputime(__hz)	((cputime_t)(__hz) * (4096000000ULL / HZ))
-
-#define cputime64_zero			(0ULL)
-#define cputime64_add(__a, __b)		((__a) + (__b))
-#define cputime_to_cputime64(__ct)	(__ct)
-
-static inline u64
-cputime64_to_jiffies64(cputime64_t cputime)
-{
-	do_div(cputime, 4096000000ULL / HZ);
-	return cputime;
+static inline u64 cputime64_to_jiffies64(cputime64_t cputime)
+{
+	unsigned long long jif = (__force unsigned long long) cputime;
+	do_div(jif, 4096000000ULL / HZ);
+	return jif;
+}
+
+static inline cputime64_t jiffies64_to_cputime64(const u64 jif)
+{
+	return (__force cputime64_t)(jif * (4096000000ULL / HZ));
 }
 
 /*
  * Convert cputime to microseconds and back.
  */
-static inline unsigned int
-cputime_to_usecs(const cputime_t cputime)
+static inline unsigned int cputime_to_usecs(const cputime_t cputime)
 {
-	return cputime_div(cputime, 4096);
+	return (__force unsigned long long) cputime >> 12;
 }
 
-static inline cputime_t
-usecs_to_cputime(const unsigned int m)
+static inline cputime_t usecs_to_cputime(const unsigned int m)
 {
-	return (cputime_t) m * 4096;
+	return (__force cputime_t)(m * 4096ULL);
 }
 
 #define usecs_to_cputime64(m)		usecs_to_cputime(m)
@@ -92,40 +77,39 @@ usecs_to_cputime(const unsigned int m)
 /*
  * Convert cputime to milliseconds and back.
  */
-static inline unsigned int
-cputime_to_secs(const cputime_t cputime)
+static inline unsigned int cputime_to_secs(const cputime_t cputime)
 {
-	return __div(cputime, 2048000000) >> 1;
+	return __div((__force unsigned long long) cputime, 2048000000) >> 1;
 }
 
-static inline cputime_t
-secs_to_cputime(const unsigned int s)
+static inline cputime_t secs_to_cputime(const unsigned int s)
 {
-	return (cputime_t) s * 4096000000ULL;
+	return (__force cputime_t)(s * 4096000000ULL);
 }
 
 /*
  * Convert cputime to timespec and back.
  */
-static inline cputime_t
-timespec_to_cputime(const struct timespec *value)
+static inline cputime_t timespec_to_cputime(const struct timespec *value)
 {
-	return value->tv_nsec * 4096 / 1000 + (u64) value->tv_sec * 4096000000ULL;
+	unsigned long long ret = value->tv_sec * 4096000000ULL;
+	return (__force cputime_t)(ret + value->tv_nsec * 4096 / 1000);
 }
 
-static inline void
-cputime_to_timespec(const cputime_t cputime, struct timespec *value)
+static inline void cputime_to_timespec(const cputime_t cputime,
+				       struct timespec *value)
 {
+	unsigned long long __cputime = (__force unsigned long long) cputime;
 #ifndef __s390x__
 	register_pair rp;
 
-	rp.pair = cputime >> 1;
+	rp.pair = __cputime >> 1;
 	asm ("dr %0,%1" : "+d" (rp) : "d" (2048000000UL));
 	value->tv_nsec = rp.subreg.even * 1000 / 4096;
 	value->tv_sec = rp.subreg.odd;
 #else
-	value->tv_nsec = (cputime % 4096000000ULL) * 1000 / 4096;
-	value->tv_sec = cputime / 4096000000ULL;
+	value->tv_nsec = (__cputime % 4096000000ULL) * 1000 / 4096;
+	value->tv_sec = __cputime / 4096000000ULL;
 #endif
 }
 
@@ -134,50 +118,52 @@ cputime_to_timespec(const cputime_t cputime, struct timespec *value)
  * Since cputime and timeval have the same resolution (microseconds)
  * this is easy.
  */
-static inline cputime_t
-timeval_to_cputime(const struct timeval *value)
+static inline cputime_t timeval_to_cputime(const struct timeval *value)
 {
-	return value->tv_usec * 4096 + (u64) value->tv_sec * 4096000000ULL;
+	unsigned long long ret = value->tv_sec * 4096000000ULL;
+	return (__force cputime_t)(ret + value->tv_usec * 4096ULL);
 }
 
-static inline void
-cputime_to_timeval(const cputime_t cputime, struct timeval *value)
+static inline void cputime_to_timeval(const cputime_t cputime,
+				      struct timeval *value)
 {
+	unsigned long long __cputime = (__force unsigned long long) cputime;
 #ifndef __s390x__
 	register_pair rp;
 
-	rp.pair = cputime >> 1;
+	rp.pair = __cputime >> 1;
 	asm ("dr %0,%1" : "+d" (rp) : "d" (2048000000UL));
 	value->tv_usec = rp.subreg.even / 4096;
 	value->tv_sec = rp.subreg.odd;
 #else
-	value->tv_usec = (cputime % 4096000000ULL) / 4096;
-	value->tv_sec = cputime / 4096000000ULL;
+	value->tv_usec = (__cputime % 4096000000ULL) / 4096;
+	value->tv_sec = __cputime / 4096000000ULL;
 #endif
 }
 
 /*
  * Convert cputime to clock and back.
  */
-static inline clock_t
-cputime_to_clock_t(cputime_t cputime)
+static inline clock_t cputime_to_clock_t(cputime_t cputime)
 {
-	return cputime_div(cputime, 4096000000ULL / USER_HZ);
+	unsigned long long clock = (__force unsigned long long) cputime;
+	do_div(clock, 4096000000ULL / USER_HZ);
+	return clock;
 }
 
-static inline cputime_t
-clock_t_to_cputime(unsigned long x)
+static inline cputime_t clock_t_to_cputime(unsigned long x)
 {
-	return (cputime_t) x * (4096000000ULL / USER_HZ);
+	return (__force cputime_t)(x * (4096000000ULL / USER_HZ));
 }
 
 /*
  * Convert cputime64 to clock.
  */
-static inline clock_t
-cputime64_to_clock_t(cputime64_t cputime)
+static inline clock_t cputime64_to_clock_t(cputime64_t cputime)
 {
-       return cputime_div(cputime, 4096000000ULL / USER_HZ);
+	unsigned long long clock = (__force unsigned long long) cputime;
+	do_div(clock, 4096000000ULL / USER_HZ);
+	return clock;
 }
 
 struct s390_idle_data {
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index c9e09ea0564..6919e936345 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -218,7 +218,7 @@ static inline void fpu_fxsave(struct fpu *fpu)
 #ifdef CONFIG_SMP
 #define safe_address (__per_cpu_offset[0])
 #else
-#define safe_address (kstat_cpu(0).cpustat.user)
+#define safe_address (__get_cpu_var(kernel_cpustat).cpustat[CPUTIME_USER])
 #endif
 
 /*