8 files changed, 36 insertions, 17 deletions
diff --git a/include/asm-generic/bitops/__ffs.h b/include/asm-generic/bitops/__ffs.h
index 9a3274aecf8..937d7c43557 100644
--- a/include/asm-generic/bitops/__ffs.h
+++ b/include/asm-generic/bitops/__ffs.h
@@ -9,7 +9,7 @@
  *
  * Undefined if no bit exists, so code should check against 0 first.
  */
-static inline unsigned long __ffs(unsigned long word)
+static __always_inline unsigned long __ffs(unsigned long word)
 {
 	int num = 0;
 
diff --git a/include/asm-generic/bitops/__fls.h b/include/asm-generic/bitops/__fls.h
index be24465403d..a60a7ccb678 100644
--- a/include/asm-generic/bitops/__fls.h
+++ b/include/asm-generic/bitops/__fls.h
@@ -9,7 +9,7 @@
  *
  * Undefined if no set bit exists, so code should check against 0 first.
  */
-static inline unsigned long __fls(unsigned long word)
+static __always_inline unsigned long __fls(unsigned long word)
 {
 	int num = BITS_PER_LONG - 1;
 
diff --git a/include/asm-generic/bitops/fls.h b/include/asm-generic/bitops/fls.h
index 850859bc506..0576d1f42f4 100644
--- a/include/asm-generic/bitops/fls.h
+++ b/include/asm-generic/bitops/fls.h
@@ -9,7 +9,7 @@
  * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
  */
 
-static inline int fls(int x)
+static __always_inline int fls(int x)
 {
 	int r = 32;
 
diff --git a/include/asm-generic/bitops/fls64.h b/include/asm-generic/bitops/fls64.h
index 86d403f8b25..b097cf8444e 100644
--- a/include/asm-generic/bitops/fls64.h
+++ b/include/asm-generic/bitops/fls64.h
@@ -15,7 +15,7 @@
  * at position 64.
  */
 #if BITS_PER_LONG == 32
-static inline int fls64(__u64 x)
+static __always_inline int fls64(__u64 x)
 {
 	__u32 h = x >> 32;
 	if (h)
@@ -23,7 +23,7 @@ static inline int fls64(__u64 x)
 	return fls(x);
 }
 #elif BITS_PER_LONG == 64
-static inline int fls64(__u64 x)
+static __always_inline int fls64(__u64 x)
 {
 	if (x == 0)
 		return 0;
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 2f3c2d4ef73..ea0ea1a4c36 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -48,6 +48,12 @@ extern struct fs_struct init_fs;
 	.posix_timers	 = LIST_HEAD_INIT(sig.posix_timers),		\
 	.cpu_timers	= INIT_CPU_TIMERS(sig.cpu_timers),		\
 	.rlim		= INIT_RLIMITS,					\
+	.cputime	= { .totals = {					\
+		.utime = cputime_zero,					\
+		.stime = cputime_zero,					\
+		.sum_exec_runtime = 0,					\
+		.lock = __SPIN_LOCK_UNLOCKED(sig.cputime.totals.lock),	\
+	}, },								\
 }
 
 extern struct nsproxy init_nsproxy;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 54cbabf3b87..02e16d20730 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -453,6 +453,7 @@ struct task_cputime {
 	cputime_t utime;
 	cputime_t stime;
 	unsigned long long sum_exec_runtime;
+	spinlock_t lock;
 };
 /* Alternate field names when used to cache expirations. */
 #define prof_exp	stime
@@ -468,7 +469,7 @@ struct task_cputime {
  * used for thread group CPU clock calculations.
  */
 struct thread_group_cputime {
-	struct task_cputime *totals;
+	struct task_cputime totals;
 };
 
 /*
@@ -2183,24 +2184,30 @@ static inline int spin_needbreak(spinlock_t *lock)
  * Thread group CPU time accounting.
  */
 
-extern int thread_group_cputime_alloc(struct task_struct *);
-extern void thread_group_cputime(struct task_struct *, struct task_cputime *);
-
-static inline void thread_group_cputime_init(struct signal_struct *sig)
+static inline
+void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
 {
-	sig->cputime.totals = NULL;
+	struct task_cputime *totals = &tsk->signal->cputime.totals;
+	unsigned long flags;
+
+	spin_lock_irqsave(&totals->lock, flags);
+	*times = *totals;
+	spin_unlock_irqrestore(&totals->lock, flags);
 }
 
-static inline int thread_group_cputime_clone_thread(struct task_struct *curr)
+static inline void thread_group_cputime_init(struct signal_struct *sig)
 {
-	if (curr->signal->cputime.totals)
-		return 0;
-	return thread_group_cputime_alloc(curr);
+	sig->cputime.totals = (struct task_cputime){
+		.utime = cputime_zero,
+		.stime = cputime_zero,
+		.sum_exec_runtime = 0,
+	};
+
+	spin_lock_init(&sig->cputime.totals.lock);
 }
 
 static inline void thread_group_cputime_free(struct signal_struct *sig)
 {
-	free_percpu(sig->cputime.totals);
 }
 
 /*
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 20b59eb1fac..3cd51e579ab 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -118,6 +118,12 @@ struct execute_work {
 		init_timer(&(_work)->timer);			\
 	} while (0)
 
+#define INIT_DELAYED_WORK_ON_STACK(_work, _func)		\
+	do {							\
+		INIT_WORK(&(_work)->work, (_func));		\
+		init_timer_on_stack(&(_work)->timer);		\
+	} while (0)
+
 #define INIT_DELAYED_WORK_DEFERRABLE(_work, _func)			\
 	do {							\
 		INIT_WORK(&(_work)->work, (_func));		\
diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h
index 93a4edb148b..dfa80495882 100644
--- a/include/sound/soc-dapm.h
+++ b/include/sound/soc-dapm.h
@@ -108,7 +108,7 @@
 #define SND_SOC_DAPM_SWITCH_E(wname, wreg, wshift, winvert, wcontrols, \
 	wevent, wflags) \
 {	.id = snd_soc_dapm_switch, .name = wname, .reg = wreg, .shift = wshift, \
-	.invert = winvert, .kcontrols = wcontrols, .num_kcontrols = 1 \
+	.invert = winvert, .kcontrols = wcontrols, .num_kcontrols = 1, \
 	.event = wevent, .event_flags = wflags}
 #define SND_SOC_DAPM_MUX_E(wname, wreg, wshift, winvert, wcontrols, \
 	wevent, wflags) \