Linux-libre 4.2.4-gnupck-4.2.4-gnu

8 files changed, 130 insertions, 45 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index c6c4240e7..fe6f855de 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -46,7 +46,6 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/rwsem.h>
-#include <linux/percpu-rwsem.h>
 #include <linux/string.h>
 #include <linux/sort.h>
 #include <linux/kmod.h>
@@ -104,8 +103,6 @@ static DEFINE_SPINLOCK(cgroup_idr_lock);
  */
 static DEFINE_SPINLOCK(release_agent_path_lock);
 
-struct percpu_rw_semaphore cgroup_threadgroup_rwsem;
-
 #define cgroup_assert_mutex_or_rcu_locked()				\
 	rcu_lockdep_assert(rcu_read_lock_held() ||			\
 			   lockdep_is_held(&cgroup_mutex),		\
@@ -870,6 +867,48 @@ static struct css_set *find_css_set(struct css_set *old_cset,
 	return cset;
 }
 
+void cgroup_threadgroup_change_begin(struct task_struct *tsk)
+{
+	down_read(&tsk->signal->group_rwsem);
+}
+
+void cgroup_threadgroup_change_end(struct task_struct *tsk)
+{
+	up_read(&tsk->signal->group_rwsem);
+}
+
+/**
+ * threadgroup_lock - lock threadgroup
+ * @tsk: member task of the threadgroup to lock
+ *
+ * Lock the threadgroup @tsk belongs to.  No new task is allowed to enter
+ * and member tasks aren't allowed to exit (as indicated by PF_EXITING) or
+ * change ->group_leader/pid.  This is useful for cases where the threadgroup
+ * needs to stay stable across blockable operations.
+ *
+ * fork and exit explicitly call threadgroup_change_{begin|end}() for
+ * synchronization.  While held, no new task will be added to threadgroup
+ * and no existing live task will have its PF_EXITING set.
+ *
+ * de_thread() does threadgroup_change_{begin|end}() when a non-leader
+ * sub-thread becomes a new leader.
+ */
+static void threadgroup_lock(struct task_struct *tsk)
+{
+	down_write(&tsk->signal->group_rwsem);
+}
+
+/**
+ * threadgroup_unlock - unlock threadgroup
+ * @tsk: member task of the threadgroup to unlock
+ *
+ * Reverse threadgroup_lock().
+ */
+static inline void threadgroup_unlock(struct task_struct *tsk)
+{
+	up_write(&tsk->signal->group_rwsem);
+}
+
 static struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root)
 {
 	struct cgroup *root_cgrp = kf_root->kn->priv;
@@ -2066,9 +2105,9 @@ static void cgroup_task_migrate(struct cgroup *old_cgrp,
 	lockdep_assert_held(&css_set_rwsem);
 
 	/*
-	 * We are synchronized through cgroup_threadgroup_rwsem against
-	 * PF_EXITING setting such that we can't race against cgroup_exit()
-	 * changing the css_set to init_css_set and dropping the old one.
+	 * We are synchronized through threadgroup_lock() against PF_EXITING
+	 * setting such that we can't race against cgroup_exit() changing the
+	 * css_set to init_css_set and dropping the old one.
 	 */
 	WARN_ON_ONCE(tsk->flags & PF_EXITING);
 	old_cset = task_css_set(tsk);
@@ -2125,11 +2164,10 @@ static void cgroup_migrate_finish(struct list_head *preloaded_csets)
  * @src_cset and add it to @preloaded_csets, which should later be cleaned
  * up by cgroup_migrate_finish().
  *
- * This function may be called without holding cgroup_threadgroup_rwsem
- * even if the target is a process.  Threads may be created and destroyed
- * but as long as cgroup_mutex is not dropped, no new css_set can be put
- * into play and the preloaded css_sets are guaranteed to cover all
- * migrations.
+ * This function may be called without holding threadgroup_lock even if the
+ * target is a process.  Threads may be created and destroyed but as long
+ * as cgroup_mutex is not dropped, no new css_set can be put into play and
+ * the preloaded css_sets are guaranteed to cover all migrations.
  */
 static void cgroup_migrate_add_src(struct css_set *src_cset,
 				   struct cgroup *dst_cgrp,
@@ -2232,7 +2270,7 @@ err:
  * @threadgroup: whether @leader points to the whole process or a single task
  *
  * Migrate a process or task denoted by @leader to @cgrp.  If migrating a
- * process, the caller must be holding cgroup_threadgroup_rwsem.  The
+ * process, the caller must be holding threadgroup_lock of @leader.  The
  * caller is also responsible for invoking cgroup_migrate_add_src() and
  * cgroup_migrate_prepare_dst() on the targets before invoking this
  * function and following up with cgroup_migrate_finish().
@@ -2360,7 +2398,7 @@ out_release_tset:
  * @leader: the task or the leader of the threadgroup to be attached
  * @threadgroup: attach the whole threadgroup?
  *
- * Call holding cgroup_mutex and cgroup_threadgroup_rwsem.
+ * Call holding cgroup_mutex and threadgroup_lock of @leader.
  */
 static int cgroup_attach_task(struct cgroup *dst_cgrp,
 			      struct task_struct *leader, bool threadgroup)
@@ -2452,13 +2490,14 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
 	if (!cgrp)
 		return -ENODEV;
 
-	percpu_down_write(&cgroup_threadgroup_rwsem);
+retry_find_task:
 	rcu_read_lock();
 	if (pid) {
 		tsk = find_task_by_vpid(pid);
 		if (!tsk) {
+			rcu_read_unlock();
 			ret = -ESRCH;
-			goto out_unlock_rcu;
+			goto out_unlock_cgroup;
 		}
 	} else {
 		tsk = current;
@@ -2474,23 +2513,37 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
 	 */
 	if (tsk == kthreadd_task || (tsk->flags & PF_NO_SETAFFINITY)) {
 		ret = -EINVAL;
-		goto out_unlock_rcu;
+		rcu_read_unlock();
+		goto out_unlock_cgroup;
 	}
 
 	get_task_struct(tsk);
 	rcu_read_unlock();
 
+	threadgroup_lock(tsk);
+	if (threadgroup) {
+		if (!thread_group_leader(tsk)) {
+			/*
+			 * a race with de_thread from another thread's exec()
+			 * may strip us of our leadership, if this happens,
+			 * there is no choice but to throw this task away and
+			 * try again; this is
+			 * "double-double-toil-and-trouble-check locking".
+			 */
+			threadgroup_unlock(tsk);
+			put_task_struct(tsk);
+			goto retry_find_task;
+		}
+	}
+
 	ret = cgroup_procs_write_permission(tsk, cgrp, of);
 	if (!ret)
 		ret = cgroup_attach_task(cgrp, tsk, threadgroup);
 
-	put_task_struct(tsk);
-	goto out_unlock_threadgroup;
+	threadgroup_unlock(tsk);
 
-out_unlock_rcu:
-	rcu_read_unlock();
-out_unlock_threadgroup:
-	percpu_up_write(&cgroup_threadgroup_rwsem);
+	put_task_struct(tsk);
+out_unlock_cgroup:
 	cgroup_kn_unlock(of->kn);
 	return ret ?: nbytes;
 }
@@ -2635,8 +2688,6 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 
 	lockdep_assert_held(&cgroup_mutex);
 
-	percpu_down_write(&cgroup_threadgroup_rwsem);
-
 	/* look up all csses currently attached to @cgrp's subtree */
 	down_read(&css_set_rwsem);
 	css_for_each_descendant_pre(css, cgroup_css(cgrp, NULL)) {
@@ -2692,8 +2743,17 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 				goto out_finish;
 			last_task = task;
 
+			threadgroup_lock(task);
+			/* raced against de_thread() from another thread? */
+			if (!thread_group_leader(task)) {
+				threadgroup_unlock(task);
+				put_task_struct(task);
+				continue;
+			}
+
 			ret = cgroup_migrate(src_cset->dfl_cgrp, task, true);
 
+			threadgroup_unlock(task);
 			put_task_struct(task);
 
 			if (WARN(ret, "cgroup: failed to update controllers for the default hierarchy (%d), further operations may crash or hang\n", ret))
@@ -2703,7 +2763,6 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 
 out_finish:
 	cgroup_migrate_finish(&preloaded_csets);
-	percpu_up_write(&cgroup_threadgroup_rwsem);
 	return ret;
 }
 
@@ -5013,7 +5072,6 @@ int __init cgroup_init(void)
 	unsigned long key;
 	int ssid, err;
 
-	BUG_ON(percpu_init_rwsem(&cgroup_threadgroup_rwsem));
 	BUG_ON(cgroup_init_cftypes(NULL, cgroup_dfl_base_files));
 	BUG_ON(cgroup_init_cftypes(NULL, cgroup_legacy_base_files));
 
diff --git a/kernel/fork.c b/kernel/fork.c
index aef3961c4..45927e013 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1146,6 +1146,10 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	tty_audit_fork(sig);
 	sched_autogroup_fork(sig);
 
+#ifdef CONFIG_CGROUPS
+	init_rwsem(&sig->group_rwsem);
+#endif
+
 	sig->oom_score_adj = current->signal->oom_score_adj;
 	sig->oom_score_adj_min = current->signal->oom_score_adj_min;
 
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 0e97c142c..4e6267a34 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -12,6 +12,7 @@
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
+#include <linux/mutex.h>
 
 #include "internals.h"
 
@@ -323,18 +324,29 @@ void register_handler_proc(unsigned int irq, struct irqaction *action)
 
 void register_irq_proc(unsigned int irq, struct irq_desc *desc)
 {
+	static DEFINE_MUTEX(register_lock);
 	char name [MAX_NAMELEN];
 
-	if (!root_irq_dir || (desc->irq_data.chip == &no_irq_chip) || desc->dir)
+	if (!root_irq_dir || (desc->irq_data.chip == &no_irq_chip))
 		return;
 
+	/*
+	 * irq directories are registered only when a handler is
+	 * added, not when the descriptor is created, so multiple
+	 * tasks might try to register at the same time.
+	 */
+	mutex_lock(&register_lock);
+
+	if (desc->dir)
+		goto out_unlock;
+
 	memset(name, 0, MAX_NAMELEN);
 	sprintf(name, "%d", irq);
 
 	/* create /proc/irq/1234 */
 	desc->dir = proc_mkdir(name, root_irq_dir);
 	if (!desc->dir)
-		return;
+		goto out_unlock;
 
 #ifdef CONFIG_SMP
 	/* create /proc/irq/<irq>/smp_affinity */
@@ -355,6 +367,9 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc)
 
 	proc_create_data("spurious", 0444, desc->dir,
 			 &irq_spurious_proc_fops, (void *)(long)irq);
+
+out_unlock:
+	mutex_unlock(&register_lock);
 }
 
 void unregister_irq_proc(unsigned int irq, struct irq_desc *desc)
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index 38c49202d..8ed01611a 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -289,7 +289,7 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 	if (pv_enabled())
 		goto queue;
 
-	if (virt_queued_spin_lock(lock))
+	if (virt_spin_lock(lock))
 		return;
 
 	/*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e9673433c..677663167 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2461,11 +2461,11 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 	 * If a task dies, then it sets TASK_DEAD in tsk->state and calls
 	 * schedule one last time. The schedule call will never return, and
 	 * the scheduled task must drop that reference.
-	 * The test for TASK_DEAD must occur while the runqueue locks are
-	 * still held, otherwise prev could be scheduled on another cpu, die
-	 * there before we look at prev->state, and then the reference would
-	 * be dropped twice.
-	 *		Manfred Spraul <manfred@colorfullife.com>
+	 *
+	 * We must observe prev->state before clearing prev->on_cpu (in
+	 * finish_lock_switch), otherwise a concurrent wakeup can get prev
+	 * running on another CPU and we could rave with its RUNNING -> DEAD
+	 * transition, resulting in a double drop.
 	 */
 	prev_state = prev->state;
 	vtime_task_switch(prev);
@@ -2614,13 +2614,20 @@ unsigned long nr_running(void)
 
 /*
  * Check if only the current task is running on the cpu.
+ *
+ * Caution: this function does not check that the caller has disabled
+ * preemption, thus the result might have a time-of-check-to-time-of-use
+ * race.  The caller is responsible to use it correctly, for example:
+ *
+ * - from a non-preemptable section (of course)
+ *
+ * - from a thread that is bound to a single CPU
+ *
+ * - in a loop with very short iterations (e.g. a polling loop)
  */
 bool single_task_running(void)
 {
-	if (cpu_rq(smp_processor_id())->nr_running == 1)
-		return true;
-	else
-		return false;
+	return raw_rq()->nr_running == 1;
 }
 EXPORT_SYMBOL(single_task_running);
 
@@ -4492,7 +4499,7 @@ SYSCALL_DEFINE0(sched_yield)
 
 int __sched _cond_resched(void)
 {
-	if (should_resched()) {
+	if (should_resched(0)) {
 		preempt_schedule_common();
 		return 1;
 	}
@@ -4510,7 +4517,7 @@ EXPORT_SYMBOL(_cond_resched);
  */
 int __cond_resched_lock(spinlock_t *lock)
 {
-	int resched = should_resched();
+	int resched = should_resched(PREEMPT_LOCK_OFFSET);
 	int ret = 0;
 
 	lockdep_assert_held(lock);
@@ -4532,7 +4539,7 @@ int __sched __cond_resched_softirq(void)
 {
 	BUG_ON(!in_softirq());
 
-	if (should_resched()) {
+	if (should_resched(SOFTIRQ_DISABLE_OFFSET)) {
 		local_bh_enable();
 		preempt_schedule_common();
 		local_bh_disable();
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 84d48790b..08ab96b36 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1091,9 +1091,10 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 	 * After ->on_cpu is cleared, the task can be moved to a different CPU.
 	 * We must ensure this doesn't happen until the switch is completely
 	 * finished.
+	 *
+	 * Pairs with the control dependency and rmb in try_to_wake_up().
 	 */
-	smp_wmb();
-	prev->on_cpu = 0;
+	smp_store_release(&prev->on_cpu, 0);
 #endif
 #ifdef CONFIG_DEBUG_SPINLOCK
 	/* this is a valid case when another task releases the spinlock */
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 841b72f72..3a38775b5 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -217,7 +217,7 @@ static void clocksource_watchdog(unsigned long data)
 			continue;
 
 		/* Check the deviation from the watchdog clocksource. */
-		if ((abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD)) {
+		if (abs64(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD) {
 			pr_warn("timekeeping watchdog: Marking clocksource '%s' as unstable because the skew is too large:\n",
 				cs->name);
 			pr_warn("                      '%s' wd_now: %llx wd_last: %llx mask: %llx\n",
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index bca3667a2..a20d4110e 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1607,7 +1607,7 @@ static __always_inline void timekeeping_freqadjust(struct timekeeper *tk,
 	negative = (tick_error < 0);
 
 	/* Sort out the magnitude of the correction */
-	tick_error = abs(tick_error);
+	tick_error = abs64(tick_error);
 	for (adj = 0; tick_error > interval; adj++)
 		tick_error >>= 1;