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
  ...

8 files changed, 66 insertions, 82 deletions

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 422370293cfd..e7bf01373bc4 100644
--- a/fs/binfmt_elf.c
+++ b/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,
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index d2e36f82c35d..ffca4bbc3d63 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/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;
diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c
index 4d24d17bcfc1..504b3c3539dc 100644
--- a/fs/compat_binfmt_elf.c
+++ b/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.
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 8c514367ba5a..b6b194ec1b4f 100644
--- a/fs/jbd2/commit.c
+++ b/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
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index a097048ed1a3..d8a5d0a08f07 100644
--- a/fs/jbd2/journal.c
+++ b/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) {
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 51a4213afa2e..fe12b519d09b 100644
--- a/fs/proc/array.c
+++ b/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);
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index d700c42b3572..e47c3e8c4dfe 100644
--- a/fs/proc/stat.c
+++ b/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);
diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c
index 33de567c25af..7981c4ffe787 100644
--- a/fs/proc/uptime.c
+++ b/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",