timers: fix itimer/many thread hang, v2

This is the second resubmission of the posix timer rework patch, posted
a few days ago.

This includes the changes from the previous resubmittion, which addressed
Oleg Nesterov's comments, removing the RCU stuff from the patch and
un-inlining the thread_group_cputime() function for SMP.

In addition, per Ingo Molnar it simplifies the UP code, consolidating much
of it with the SMP version and depending on lower-level SMP/UP handling to
take care of the differences.

It also cleans up some UP compile errors, moves the scheduler stats-related
macros into kernel/sched_stats.h, cleans up a merge error in
kernel/fork.c and has a few other minor fixes and cleanups as suggested
by Oleg and Ingo. Thanks for the review, guys.

Signed-off-by: Frank Mayhar <fmayhar@google.com>
Cc: Roland McGrath <roland@redhat.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

4 files changed, 208 insertions, 133 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 1181b9aac48e..021ae012cc75 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -791,7 +791,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	int ret;
 
 	if (clone_flags & CLONE_THREAD) {
-		ret = thread_group_cputime_clone_thread(current, tsk);
+		ret = thread_group_cputime_clone_thread(current);
 		if (likely(!ret)) {
 			atomic_inc(&current->signal->count);
 			atomic_inc(&current->signal->live);
@@ -834,9 +834,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0;
 	sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0;
 	task_io_accounting_init(&sig->ioac);
-	INIT_LIST_HEAD(&sig->cpu_timers[0]);
-	INIT_LIST_HEAD(&sig->cpu_timers[1]);
-	INIT_LIST_HEAD(&sig->cpu_timers[2]);
 	taskstats_tgid_init(sig);
 
 	task_lock(current->group_leader);
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 9a7ea049fcdc..153dcb2639c3 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -7,50 +7,46 @@
 #include <linux/errno.h>
 #include <linux/math64.h>
 #include <asm/uaccess.h>
+#include <linux/kernel_stat.h>
 
-#ifdef CONFIG_SMP
 /*
- * Allocate the thread_group_cputime structure appropriately for SMP kernels
- * and fill in the current values of the fields.  Called from copy_signal()
- * via thread_group_cputime_clone_thread() when adding a second or subsequent
+ * Allocate the thread_group_cputime structure appropriately and fill in the
+ * current values of the fields.  Called from copy_signal() via
+ * thread_group_cputime_clone_thread() when adding a second or subsequent
  * thread to a thread group.  Assumes interrupts are enabled when called.
  */
-int thread_group_cputime_alloc_smp(struct task_struct *tsk)
+int thread_group_cputime_alloc(struct task_struct *tsk)
 {
 	struct signal_struct *sig = tsk->signal;
 	struct task_cputime *cputime;
 
 	/*
 	 * If we have multiple threads and we don't already have a
-	 * per-CPU task_cputime struct, allocate one and fill it in with
-	 * the times accumulated so far.
+	 * per-CPU task_cputime struct (checked in the caller), allocate
+	 * one and fill it in with the times accumulated so far.  We may
+	 * race with another thread so recheck after we pick up the sighand
+	 * lock.
 	 */
-	if (sig->cputime.totals)
-		return 0;
 	cputime = alloc_percpu(struct task_cputime);
 	if (cputime == NULL)
 		return -ENOMEM;
-	read_lock(&tasklist_lock);
 	spin_lock_irq(&tsk->sighand->siglock);
 	if (sig->cputime.totals) {
 		spin_unlock_irq(&tsk->sighand->siglock);
-		read_unlock(&tasklist_lock);
 		free_percpu(cputime);
 		return 0;
 	}
 	sig->cputime.totals = cputime;
-	cputime = per_cpu_ptr(sig->cputime.totals, get_cpu());
+	cputime = per_cpu_ptr(sig->cputime.totals, smp_processor_id());
 	cputime->utime = tsk->utime;
 	cputime->stime = tsk->stime;
 	cputime->sum_exec_runtime = tsk->se.sum_exec_runtime;
-	put_cpu_no_resched();
 	spin_unlock_irq(&tsk->sighand->siglock);
-	read_unlock(&tasklist_lock);
 	return 0;
 }
 
 /**
- * thread_group_cputime_smp - Sum the thread group time fields across all CPUs.
+ * thread_group_cputime - Sum the thread group time fields across all CPUs.
  *
  * @tsk:	The task we use to identify the thread group.
  * @times:	task_cputime structure in which we return the summed fields.
@@ -58,7 +54,7 @@ int thread_group_cputime_alloc_smp(struct task_struct *tsk)
  * Walk the list of CPUs to sum the per-CPU time fields in the thread group
  * time structure.
  */
-void thread_group_cputime_smp(
+void thread_group_cputime(
 	struct task_struct *tsk,
 	struct task_cputime *times)
 {
@@ -83,8 +79,6 @@ void thread_group_cputime_smp(
 	}
 }
 
-#endif /* CONFIG_SMP */
-
 /*
  * Called after updating RLIMIT_CPU to set timer expiration if necessary.
  */
@@ -300,7 +294,7 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p,
 		cpu->cpu = virt_ticks(p);
 		break;
 	case CPUCLOCK_SCHED:
-		cpu->sched = task_sched_runtime(p);
+		cpu->sched = p->se.sum_exec_runtime + task_delta_exec(p);
 		break;
 	}
 	return 0;
@@ -309,16 +303,15 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p,
 /*
  * Sample a process (thread group) clock for the given group_leader task.
  * Must be called with tasklist_lock held for reading.
- * Must be called with tasklist_lock held for reading, and p->sighand->siglock.
  */
-static int cpu_clock_sample_group_locked(unsigned int clock_idx,
-					 struct task_struct *p,
-					 union cpu_time_count *cpu)
+static int cpu_clock_sample_group(const clockid_t which_clock,
+				  struct task_struct *p,
+				  union cpu_time_count *cpu)
 {
 	struct task_cputime cputime;
 
 	thread_group_cputime(p, &cputime);
-	switch (clock_idx) {
+	switch (which_clock) {
 	default:
 		return -EINVAL;
 	case CPUCLOCK_PROF:
@@ -328,29 +321,12 @@ static int cpu_clock_sample_group_locked(unsigned int clock_idx,
 		cpu->cpu = cputime.utime;
 		break;
 	case CPUCLOCK_SCHED:
-		cpu->sched = thread_group_sched_runtime(p);
+		cpu->sched = cputime.sum_exec_runtime + task_delta_exec(p);
 		break;
 	}
 	return 0;
 }
 
-/*
- * Sample a process (thread group) clock for the given group_leader task.
- * Must be called with tasklist_lock held for reading.
- */
-static int cpu_clock_sample_group(const clockid_t which_clock,
-				  struct task_struct *p,
-				  union cpu_time_count *cpu)
-{
-	int ret;
-	unsigned long flags;
-	spin_lock_irqsave(&p->sighand->siglock, flags);
-	ret = cpu_clock_sample_group_locked(CPUCLOCK_WHICH(which_clock), p,
-					    cpu);
-	spin_unlock_irqrestore(&p->sighand->siglock, flags);
-	return ret;
-}
-
 
 int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
 {
@@ -1324,29 +1300,37 @@ static inline int task_cputime_expired(const struct task_cputime *sample,
  * fastpath_timer_check - POSIX CPU timers fast path.
  *
  * @tsk:	The task (thread) being checked.
- * @sig:	The signal pointer for that task.
  *
- * If there are no timers set return false.  Otherwise snapshot the task and
- * thread group timers, then compare them with the corresponding expiration
- # times.  Returns true if a timer has expired, else returns false.
+ * Check the task and thread group timers.  If both are zero (there are no
+ * timers set) return false.  Otherwise snapshot the task and thread group
+ * timers and compare them with the corresponding expiration times.  Return
+ * true if a timer has expired, else return false.
  */
-static inline int fastpath_timer_check(struct task_struct *tsk,
-					struct signal_struct *sig)
+static inline int fastpath_timer_check(struct task_struct *tsk)
 {
-	struct task_cputime task_sample = {
-		.utime = tsk->utime,
-		.stime = tsk->stime,
-		.sum_exec_runtime = tsk->se.sum_exec_runtime
-	};
-	struct task_cputime group_sample;
+	struct signal_struct *sig = tsk->signal;
 
-	if (task_cputime_zero(&tsk->cputime_expires) &&
-	    task_cputime_zero(&sig->cputime_expires))
+	if (unlikely(!sig))
 		return 0;
-	if (task_cputime_expired(&task_sample, &tsk->cputime_expires))
-		return 1;
-	thread_group_cputime(tsk, &group_sample);
-	return task_cputime_expired(&group_sample, &sig->cputime_expires);
+
+	if (!task_cputime_zero(&tsk->cputime_expires)) {
+		struct task_cputime task_sample = {
+			.utime = tsk->utime,
+			.stime = tsk->stime,
+			.sum_exec_runtime = tsk->se.sum_exec_runtime
+		};
+
+		if (task_cputime_expired(&task_sample, &tsk->cputime_expires))
+			return 1;
+	}
+	if (!task_cputime_zero(&sig->cputime_expires)) {
+		struct task_cputime group_sample;
+
+		thread_group_cputime(tsk, &group_sample);
+		if (task_cputime_expired(&group_sample, &sig->cputime_expires))
+			return 1;
+	}
+	return 0;
 }
 
 /*
@@ -1358,43 +1342,34 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 {
 	LIST_HEAD(firing);
 	struct k_itimer *timer, *next;
-	struct signal_struct *sig;
-	struct sighand_struct *sighand;
-	unsigned long flags;
 
 	BUG_ON(!irqs_disabled());
 
-	/* Pick up tsk->signal and make sure it's valid. */
-	sig = tsk->signal;
 	/*
 	 * The fast path checks that there are no expired thread or thread
-	 * group timers.  If that's so, just return.  Also check that
-	 * tsk->signal is non-NULL; this probably can't happen but cover the
-	 * possibility anyway.
+	 * group timers.  If that's so, just return.
 	 */
-	if (unlikely(!sig) || !fastpath_timer_check(tsk, sig))
+	if (!fastpath_timer_check(tsk))
 		return;
 
-	sighand = lock_task_sighand(tsk, &flags);
-	if (likely(sighand)) {
-		/*
-		 * Here we take off tsk->signal->cpu_timers[N] and
-		 * tsk->cpu_timers[N] all the timers that are firing, and
-		 * put them on the firing list.
-		 */
-		check_thread_timers(tsk, &firing);
-		check_process_timers(tsk, &firing);
+	spin_lock(&tsk->sighand->siglock);
+	/*
+	 * Here we take off tsk->signal->cpu_timers[N] and
+	 * tsk->cpu_timers[N] all the timers that are firing, and
+	 * put them on the firing list.
+	 */
+	check_thread_timers(tsk, &firing);
+	check_process_timers(tsk, &firing);
 
-		/*
-		 * We must release these locks before taking any timer's lock.
-		 * There is a potential race with timer deletion here, as the
-		 * siglock now protects our private firing list.  We have set
-		 * the firing flag in each timer, so that a deletion attempt
-		 * that gets the timer lock before we do will give it up and
-		 * spin until we've taken care of that timer below.
-		 */
-	}
-	unlock_task_sighand(tsk, &flags);
+	/*
+	 * We must release these locks before taking any timer's lock.
+	 * There is a potential race with timer deletion here, as the
+	 * siglock now protects our private firing list.  We have set
+	 * the firing flag in each timer, so that a deletion attempt
+	 * that gets the timer lock before we do will give it up and
+	 * spin until we've taken care of that timer below.
+	 */
+	spin_unlock(&tsk->sighand->siglock);
 
 	/*
 	 * Now that all the timers on our list have the firing flag,
@@ -1433,7 +1408,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
 	struct list_head *head;
 
 	BUG_ON(clock_idx == CPUCLOCK_SCHED);
-	cpu_clock_sample_group_locked(clock_idx, tsk, &now);
+	cpu_clock_sample_group(clock_idx, tsk, &now);
 
 	if (oldval) {
 		if (!cputime_eq(*oldval, cputime_zero)) {
diff --git a/kernel/sched.c b/kernel/sched.c
index c51b5d276665..260c22cc530a 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4039,55 +4039,22 @@ EXPORT_PER_CPU_SYMBOL(kstat);
 /*
  * Return any ns on the sched_clock that have not yet been banked in
  * @p in case that task is currently running.
- *
- * Called with task_rq_lock() held on @rq.
  */
-static unsigned long long task_delta_exec(struct task_struct *p, struct rq *rq)
+unsigned long long task_delta_exec(struct task_struct *p)
 {
+	struct rq *rq;
+	unsigned long flags;
+	u64 ns = 0;
+
+	rq = task_rq_lock(p, &flags);
 	if (task_current(rq, p)) {
 		u64 delta_exec;
 
 		update_rq_clock(rq);
 		delta_exec = rq->clock - p->se.exec_start;
 		if ((s64)delta_exec > 0)
-			return delta_exec;
+			ns = delta_exec;
 	}
-	return 0;
-}
-
-/*
- * Return p->sum_exec_runtime plus any more ns on the sched_clock
- * that have not yet been banked in case the task is currently running.
- */
-unsigned long long task_sched_runtime(struct task_struct *p)
-{
-	unsigned long flags;
-	u64 ns;
-	struct rq *rq;
-
-	rq = task_rq_lock(p, &flags);
-	ns = p->se.sum_exec_runtime + task_delta_exec(p, rq);
-	task_rq_unlock(rq, &flags);
-
-	return ns;
-}
-
-/*
- * Return sum_exec_runtime for the thread group plus any more ns on the
- * sched_clock that have not yet been banked in case the task is currently
- * running.
- */
-unsigned long long thread_group_sched_runtime(struct task_struct *p)
-{
-	unsigned long flags;
-	u64 ns;
-	struct rq *rq;
-	struct task_cputime totals;
-
-	rq = task_rq_lock(p, &flags);
-	thread_group_cputime(p, &totals);
-	ns = totals.sum_exec_runtime + task_delta_exec(p, rq);
-	task_rq_unlock(rq, &flags);
 
 	return ns;
 }
diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h
index 8385d43987e2..d6903bd0c7a8 100644
--- a/kernel/sched_stats.h
+++ b/kernel/sched_stats.h
@@ -270,3 +270,139 @@ sched_info_switch(struct task_struct *prev, struct task_struct *next)
 #define sched_info_switch(t, next)		do { } while (0)
 #endif /* CONFIG_SCHEDSTATS || CONFIG_TASK_DELAY_ACCT */
 
+/*
+ * The following are functions that support scheduler-internal time accounting.
+ * These functions are generally called at the timer tick.  None of this depends
+ * on CONFIG_SCHEDSTATS.
+ */
+
+#ifdef CONFIG_SMP
+
+/**
+ * thread_group_cputime_account_user - Maintain utime for a thread group.
+ *
+ * @tgtimes:	Pointer to thread_group_cputime structure.
+ * @cputime:	Time value by which to increment the utime field of that
+ *		structure.
+ *
+ * If thread group time is being maintained, get the structure for the
+ * running CPU and update the utime field there.
+ */
+static inline void thread_group_cputime_account_user(
+	struct thread_group_cputime *tgtimes,
+	cputime_t cputime)
+{
+	if (tgtimes->totals) {
+		struct task_cputime *times;
+
+		times = per_cpu_ptr(tgtimes->totals, get_cpu());
+		times->utime = cputime_add(times->utime, cputime);
+		put_cpu_no_resched();
+	}
+}
+
+/**
+ * thread_group_cputime_account_system - Maintain stime for a thread group.
+ *
+ * @tgtimes:	Pointer to thread_group_cputime structure.
+ * @cputime:	Time value by which to increment the stime field of that
+ *		structure.
+ *
+ * If thread group time is being maintained, get the structure for the
+ * running CPU and update the stime field there.
+ */
+static inline void thread_group_cputime_account_system(
+	struct thread_group_cputime *tgtimes,
+	cputime_t cputime)
+{
+	if (tgtimes->totals) {
+		struct task_cputime *times;
+
+		times = per_cpu_ptr(tgtimes->totals, get_cpu());
+		times->stime = cputime_add(times->stime, cputime);
+		put_cpu_no_resched();
+	}
+}
+
+/**
+ * thread_group_cputime_account_exec_runtime - Maintain exec runtime for a
+ *						thread group.
+ *
+ * @tgtimes:	Pointer to thread_group_cputime structure.
+ * @ns:		Time value by which to increment the sum_exec_runtime field
+ *		of that structure.
+ *
+ * If thread group time is being maintained, get the structure for the
+ * running CPU and update the sum_exec_runtime field there.
+ */
+static inline void thread_group_cputime_account_exec_runtime(
+	struct thread_group_cputime *tgtimes,
+	unsigned long long ns)
+{
+	if (tgtimes->totals) {
+		struct task_cputime *times;
+
+		times = per_cpu_ptr(tgtimes->totals, get_cpu());
+		times->sum_exec_runtime += ns;
+		put_cpu_no_resched();
+	}
+}
+
+#else /* CONFIG_SMP */
+
+static inline void thread_group_cputime_account_user(
+	struct thread_group_cputime *tgtimes,
+	cputime_t cputime)
+{
+	tgtimes->totals->utime = cputime_add(tgtimes->totals->utime, cputime);
+}
+
+static inline void thread_group_cputime_account_system(
+	struct thread_group_cputime *tgtimes,
+	cputime_t cputime)
+{
+	tgtimes->totals->stime = cputime_add(tgtimes->totals->stime, cputime);
+}
+
+static inline void thread_group_cputime_account_exec_runtime(
+	struct thread_group_cputime *tgtimes,
+	unsigned long long ns)
+{
+	tgtimes->totals->sum_exec_runtime += ns;
+}
+
+#endif /* CONFIG_SMP */
+
+/*
+ * These are the generic time-accounting routines that use the above
+ * functions.  They are the functions actually called by the scheduler.
+ */
+static inline void account_group_user_time(struct task_struct *tsk,
+					    cputime_t cputime)
+{
+	struct signal_struct *sig;
+
+	sig = tsk->signal;
+	if (likely(sig))
+		thread_group_cputime_account_user(&sig->cputime, cputime);
+}
+
+static inline void account_group_system_time(struct task_struct *tsk,
+					      cputime_t cputime)
+{
+	struct signal_struct *sig;
+
+	sig = tsk->signal;
+	if (likely(sig))
+		thread_group_cputime_account_system(&sig->cputime, cputime);
+}
+
+static inline void account_group_exec_runtime(struct task_struct *tsk,
+					       unsigned long long ns)
+{
+	struct signal_struct *sig;
+
+	sig = tsk->signal;
+	if (likely(sig))
+		thread_group_cputime_account_exec_runtime(&sig->cputime, ns);
+}