10 files changed, 113 insertions, 43 deletions

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index e5657788fedd..010a0083c0ae 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1608,11 +1608,13 @@ static int cpuset_write_u64(struct cgroup *cgrp, struct cftype *cft, u64 val)
 {
         struct cpuset *cs = cgroup_cs(cgrp);
         cpuset_filetype_t type = cft->private;
-        int retval = -ENODEV;
+        int retval = 0;
 
         mutex_lock(&cpuset_mutex);
-        if (!is_cpuset_online(cs))
+        if (!is_cpuset_online(cs)) {
+                retval = -ENODEV;
                 goto out_unlock;
+        }
 
         switch (type) {
         case FILE_CPU_EXCLUSIVE:
diff --git a/kernel/fork.c b/kernel/fork.c
index 403d2bb8a968..e23bb19e2a3e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1679,6 +1679,12 @@ SYSCALL_DEFINE5(clone, unsigned long, newsp, unsigned long, clone_flags,
                  int __user *, parent_tidptr,
                  int __user *, child_tidptr,
                  int, tls_val)
+#elif defined(CONFIG_CLONE_BACKWARDS3)
+SYSCALL_DEFINE6(clone, unsigned long, clone_flags, unsigned long, newsp,
+                int, stack_size,
+                int __user *, parent_tidptr,
+                int __user *, child_tidptr,
+                int, tls_val)
 #else
 SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
                  int __user *, parent_tidptr,
diff --git a/kernel/mutex.c b/kernel/mutex.c
index ff05f4bd86eb..a52ee7bb830d 100644
--- a/kernel/mutex.c
+++ b/kernel/mutex.c
@@ -686,7 +686,7 @@ __ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
         might_sleep();
         ret =  __mutex_lock_common(&lock->base, TASK_UNINTERRUPTIBLE,
                                    0, &ctx->dep_map, _RET_IP_, ctx);
-        if (!ret && ctx->acquired > 0)
+        if (!ret && ctx->acquired > 1)
                 return ww_mutex_deadlock_injection(lock, ctx);
 
         return ret;
@@ -702,7 +702,7 @@ __ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
         ret = __mutex_lock_common(&lock->base, TASK_INTERRUPTIBLE,
                                   0, &ctx->dep_map, _RET_IP_, ctx);
 
-        if (!ret && ctx->acquired > 0)
+        if (!ret && ctx->acquired > 1)
                 return ww_mutex_deadlock_injection(lock, ctx);
 
         return ret;
diff --git a/kernel/power/qos.c b/kernel/power/qos.c
index 06fe28589e9c..a394297f8b2f 100644
--- a/kernel/power/qos.c
+++ b/kernel/power/qos.c
@@ -296,6 +296,17 @@ int pm_qos_request_active(struct pm_qos_request *req)
 }
 EXPORT_SYMBOL_GPL(pm_qos_request_active);
 
+static void __pm_qos_update_request(struct pm_qos_request *req,
+                           s32 new_value)
+{
+        trace_pm_qos_update_request(req->pm_qos_class, new_value);
+
+        if (new_value != req->node.prio)
+                pm_qos_update_target(
+                        pm_qos_array[req->pm_qos_class]->constraints,
+                        &req->node, PM_QOS_UPDATE_REQ, new_value);
+}
+
 /**
  * pm_qos_work_fn - the timeout handler of pm_qos_update_request_timeout
  * @work: work struct for the delayed work (timeout)
@@ -308,7 +319,7 @@ static void pm_qos_work_fn(struct work_struct *work)
                                                   struct pm_qos_request,
                                                   work);
 
-        pm_qos_update_request(req, PM_QOS_DEFAULT_VALUE);
+        __pm_qos_update_request(req, PM_QOS_DEFAULT_VALUE);
 }
 
 /**
@@ -364,12 +375,7 @@ void pm_qos_update_request(struct pm_qos_request *req,
         }
 
         cancel_delayed_work_sync(&req->work);
-
-        trace_pm_qos_update_request(req->pm_qos_class, new_value);
-        if (new_value != req->node.prio)
-                pm_qos_update_target(
-                        pm_qos_array[req->pm_qos_class]->constraints,
-                        &req->node, PM_QOS_UPDATE_REQ, new_value);
+        __pm_qos_update_request(req, new_value);
 }
 EXPORT_SYMBOL_GPL(pm_qos_update_request);
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b7c32cb7bfeb..05c39f030314 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -933,6 +933,8 @@ static int effective_prio(struct task_struct *p)
 /**
  * task_curr - is this task currently executing on a CPU?
  * @p: the task in question.
+ *
+ * Return: 1 if the task is currently executing. 0 otherwise.
  */
 inline int task_curr(const struct task_struct *p)
 {
@@ -1482,7 +1484,7 @@ static void ttwu_queue(struct task_struct *p, int cpu)
  * the simpler "current->state = TASK_RUNNING" to mark yourself
  * runnable without the overhead of this.
  *
- * Returns %true if @p was woken up, %false if it was already running
+ * Return: %true if @p was woken up, %false if it was already running.
  * or @state didn't match @p's state.
  */
 static int
@@ -1491,7 +1493,13 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
         unsigned long flags;
         int cpu, success = 0;
 
-        smp_wmb();
+        /*
+         * If we are going to wake up a thread waiting for CONDITION we
+         * need to ensure that CONDITION=1 done by the caller can not be
+         * reordered with p->state check below. This pairs with mb() in
+         * set_current_state() the waiting thread does.
+         */
+        smp_mb__before_spinlock();
         raw_spin_lock_irqsave(&p->pi_lock, flags);
         if (!(p->state & state))
                 goto out;
@@ -1577,8 +1585,9 @@ out:
  * @p: The process to be woken up.
  *
  * Attempt to wake up the nominated process and move it to the set of runnable
- * processes.  Returns 1 if the process was woken up, 0 if it was already
- * running.
+ * processes.
+ *
+ * Return: 1 if the process was woken up, 0 if it was already running.
  *
  * It may be assumed that this function implies a write memory barrier before
  * changing the task state if and only if any tasks are woken up.
@@ -2191,6 +2200,8 @@ void scheduler_tick(void)
  * This makes sure that uptime, CFS vruntime, load
  * balancing, etc... continue to move forward, even
  * with a very low granularity.
+ *
+ * Return: Maximum deferment in nanoseconds.
  */
 u64 scheduler_tick_max_deferment(void)
 {
@@ -2394,6 +2405,12 @@ need_resched:
         if (sched_feat(HRTICK))
                 hrtick_clear(rq);
 
+        /*
+         * Make sure that signal_pending_state()->signal_pending() below
+         * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
+         * done by the caller to avoid the race with signal_wake_up().
+         */
+        smp_mb__before_spinlock();
         raw_spin_lock_irq(&rq->lock);
 
         switch_count = &prev->nivcsw;
@@ -2796,8 +2813,8 @@ EXPORT_SYMBOL(wait_for_completion);
  * specified timeout to expire. The timeout is in jiffies. It is not
  * interruptible.
  *
- * The return value is 0 if timed out, and positive (at least 1, or number of
- * jiffies left till timeout) if completed.
+ * Return: 0 if timed out, and positive (at least 1, or number of jiffies left
+ * till timeout) if completed.
  */
 unsigned long __sched
 wait_for_completion_timeout(struct completion *x, unsigned long timeout)
@@ -2829,8 +2846,8 @@ EXPORT_SYMBOL(wait_for_completion_io);
  * specified timeout to expire. The timeout is in jiffies. It is not
  * interruptible. The caller is accounted as waiting for IO.
  *
- * The return value is 0 if timed out, and positive (at least 1, or number of
- * jiffies left till timeout) if completed.
+ * Return: 0 if timed out, and positive (at least 1, or number of jiffies left
+ * till timeout) if completed.
  */
 unsigned long __sched
 wait_for_completion_io_timeout(struct completion *x, unsigned long timeout)
@@ -2846,7 +2863,7 @@ EXPORT_SYMBOL(wait_for_completion_io_timeout);
  * This waits for completion of a specific task to be signaled. It is
  * interruptible.
  *
- * The return value is -ERESTARTSYS if interrupted, 0 if completed.
+ * Return: -ERESTARTSYS if interrupted, 0 if completed.
  */
 int __sched wait_for_completion_interruptible(struct completion *x)
 {
@@ -2865,8 +2882,8 @@ EXPORT_SYMBOL(wait_for_completion_interruptible);
  * This waits for either a completion of a specific task to be signaled or for a
  * specified timeout to expire. It is interruptible. The timeout is in jiffies.
  *
- * The return value is -ERESTARTSYS if interrupted, 0 if timed out,
- * positive (at least 1, or number of jiffies left till timeout) if completed.
+ * Return: -ERESTARTSYS if interrupted, 0 if timed out, positive (at least 1,
+ * or number of jiffies left till timeout) if completed.
  */
 long __sched
 wait_for_completion_interruptible_timeout(struct completion *x,
@@ -2883,7 +2900,7 @@ EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);
  * This waits to be signaled for completion of a specific task. It can be
  * interrupted by a kill signal.
  *
- * The return value is -ERESTARTSYS if interrupted, 0 if completed.
+ * Return: -ERESTARTSYS if interrupted, 0 if completed.
  */
 int __sched wait_for_completion_killable(struct completion *x)
 {
@@ -2903,8 +2920,8 @@ EXPORT_SYMBOL(wait_for_completion_killable);
  * signaled or for a specified timeout to expire. It can be
  * interrupted by a kill signal. The timeout is in jiffies.
  *
- * The return value is -ERESTARTSYS if interrupted, 0 if timed out,
- * positive (at least 1, or number of jiffies left till timeout) if completed.
+ * Return: -ERESTARTSYS if interrupted, 0 if timed out, positive (at least 1,
+ * or number of jiffies left till timeout) if completed.
  */
 long __sched
 wait_for_completion_killable_timeout(struct completion *x,
@@ -2918,7 +2935,7 @@ EXPORT_SYMBOL(wait_for_completion_killable_timeout);
  *      try_wait_for_completion - try to decrement a completion without blocking
  *      @x:     completion structure
  *
- *      Returns: 0 if a decrement cannot be done without blocking
+ *      Return: 0 if a decrement cannot be done without blocking
  *               1 if a decrement succeeded.
  *
  *      If a completion is being used as a counting completion,
@@ -2945,7 +2962,7 @@ EXPORT_SYMBOL(try_wait_for_completion);
  *      completion_done - Test to see if a completion has any waiters
  *      @x:     completion structure
  *
- *      Returns: 0 if there are waiters (wait_for_completion() in progress)
+ *      Return: 0 if there are waiters (wait_for_completion() in progress)
  *               1 if there are no waiters.
  *
  */
@@ -3182,7 +3199,7 @@ SYSCALL_DEFINE1(nice, int, increment)
  * task_prio - return the priority value of a given task.
  * @p: the task in question.
  *
- * This is the priority value as seen by users in /proc.
+ * Return: The priority value as seen by users in /proc.
  * RT tasks are offset by -200. Normal tasks are centered
  * around 0, value goes from -16 to +15.
  */
@@ -3194,6 +3211,8 @@ int task_prio(const struct task_struct *p)
 /**
  * task_nice - return the nice value of a given task.
  * @p: the task in question.
+ *
+ * Return: The nice value [ -20 ... 0 ... 19 ].
  */
 int task_nice(const struct task_struct *p)
 {
@@ -3204,6 +3223,8 @@ EXPORT_SYMBOL(task_nice);
 /**
  * idle_cpu - is a given cpu idle currently?
  * @cpu: the processor in question.
+ *
+ * Return: 1 if the CPU is currently idle. 0 otherwise.
  */
 int idle_cpu(int cpu)
 {
@@ -3226,6 +3247,8 @@ int idle_cpu(int cpu)
 /**
  * idle_task - return the idle task for a given cpu.
  * @cpu: the processor in question.
+ *
+ * Return: The idle task for the cpu @cpu.
  */
 struct task_struct *idle_task(int cpu)
 {
@@ -3235,6 +3258,8 @@ struct task_struct *idle_task(int cpu)
 /**
  * find_process_by_pid - find a process with a matching PID value.
  * @pid: the pid in question.
+ *
+ * The task of @pid, if found. %NULL otherwise.
  */
 static struct task_struct *find_process_by_pid(pid_t pid)
 {
@@ -3432,6 +3457,8 @@ recheck:
  * @policy: new policy.
  * @param: structure containing the new RT priority.
  *
+ * Return: 0 on success. An error code otherwise.
+ *
  * NOTE that the task may be already dead.
  */
 int sched_setscheduler(struct task_struct *p, int policy,
@@ -3451,6 +3478,8 @@ EXPORT_SYMBOL_GPL(sched_setscheduler);
  * current context has permission.  For example, this is needed in
  * stop_machine(): we create temporary high priority worker threads,
  * but our caller might not have that capability.
+ *
+ * Return: 0 on success. An error code otherwise.
  */
 int sched_setscheduler_nocheck(struct task_struct *p, int policy,
                                const struct sched_param *param)
@@ -3485,6 +3514,8 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
  * @pid: the pid in question.
  * @policy: new policy.
  * @param: structure containing the new RT priority.
+ *
+ * Return: 0 on success. An error code otherwise.
  */
 SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy,
                 struct sched_param __user *, param)
@@ -3500,6 +3531,8 @@ SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy,
  * sys_sched_setparam - set/change the RT priority of a thread
  * @pid: the pid in question.
  * @param: structure containing the new RT priority.
+ *
+ * Return: 0 on success. An error code otherwise.
  */
 SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
 {
@@ -3509,6 +3542,9 @@ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
 /**
  * sys_sched_getscheduler - get the policy (scheduling class) of a thread
  * @pid: the pid in question.
+ *
+ * Return: On success, the policy of the thread. Otherwise, a negative error
+ * code.
  */
 SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
 {
@@ -3535,6 +3571,9 @@ SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
  * sys_sched_getparam - get the RT priority of a thread
  * @pid: the pid in question.
  * @param: structure containing the RT priority.
+ *
+ * Return: On success, 0 and the RT priority is in @param. Otherwise, an error
+ * code.
  */
 SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
 {
@@ -3659,6 +3698,8 @@ static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len,
  * @pid: pid of the process
  * @len: length in bytes of the bitmask pointed to by user_mask_ptr
  * @user_mask_ptr: user-space pointer to the new cpu mask
+ *
+ * Return: 0 on success. An error code otherwise.
  */
 SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len,
                 unsigned long __user *, user_mask_ptr)
@@ -3710,6 +3751,8 @@ out_unlock:
  * @pid: pid of the process
  * @len: length in bytes of the bitmask pointed to by user_mask_ptr
  * @user_mask_ptr: user-space pointer to hold the current cpu mask
+ *
+ * Return: 0 on success. An error code otherwise.
  */
 SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
                 unsigned long __user *, user_mask_ptr)
@@ -3744,6 +3787,8 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
  *
  * This function yields the current CPU to other tasks. If there are no
  * other threads running on this CPU then this function will return.
+ *
+ * Return: 0.
  */
 SYSCALL_DEFINE0(sched_yield)
 {
@@ -3869,7 +3914,7 @@ EXPORT_SYMBOL(yield);
  * It's the caller's job to ensure that the target task struct
  * can't go away on us before we can do any checks.
  *
- * Returns:
+ * Return:
  *      true (>0) if we indeed boosted the target task.
  *      false (0) if we failed to boost the target.
  *      -ESRCH if there's no task to yield to.
@@ -3972,8 +4017,9 @@ long __sched io_schedule_timeout(long timeout)
  * sys_sched_get_priority_max - return maximum RT priority.
  * @policy: scheduling class.
  *
- * this syscall returns the maximum rt_priority that can be used
- * by a given scheduling class.
+ * Return: On success, this syscall returns the maximum
+ * rt_priority that can be used by a given scheduling class.
+ * On failure, a negative error code is returned.
  */
 SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
 {
@@ -3997,8 +4043,9 @@ SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
  * sys_sched_get_priority_min - return minimum RT priority.
  * @policy: scheduling class.
  *
- * this syscall returns the minimum rt_priority that can be used
- * by a given scheduling class.
+ * Return: On success, this syscall returns the minimum
+ * rt_priority that can be used by a given scheduling class.
+ * On failure, a negative error code is returned.
  */
 SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
 {
@@ -4024,6 +4071,9 @@ SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
  *
  * this syscall writes the default timeslice value of a given process
  * into the user-space timespec buffer. A value of '0' means infinity.
+ *
+ * Return: On success, 0 and the timeslice is in @interval. Otherwise,
+ * an error code.
  */
 SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
                 struct timespec __user *, interval)
@@ -6632,6 +6682,8 @@ void normalize_rt_tasks(void)
  * @cpu: the processor in question.
  *
  * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
+ *
+ * Return: The current task for @cpu.
  */
 struct task_struct *curr_task(int cpu)
 {
diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c
index 1095e878a46f..8b836b376d91 100644
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -62,7 +62,7 @@ static int convert_prio(int prio)
  * any discrepancies created by racing against the uncertainty of the current
  * priority configuration.
  *
- * Returns: (int)bool - CPUs were found
+ * Return: (int)bool - CPUs were found
  */
 int cpupri_find(struct cpupri *cp, struct task_struct *p,
                 struct cpumask *lowest_mask)
@@ -203,7 +203,7 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri)
  * cpupri_init - initialize the cpupri structure
  * @cp: The cpupri context
  *
- * Returns: -ENOMEM if memory fails.
+ * Return: -ENOMEM on memory allocation failure.
  */
 int cpupri_init(struct cpupri *cp)
 {
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 9565645e3202..68f1609ca149 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2032,6 +2032,7 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
          */
         update_entity_load_avg(curr, 1);
         update_cfs_rq_blocked_load(cfs_rq, 1);
+        update_cfs_shares(cfs_rq);
 
 #ifdef CONFIG_SCHED_HRTICK
         /*
@@ -4280,6 +4281,8 @@ struct sg_lb_stats {
  * get_sd_load_idx - Obtain the load index for a given sched domain.
  * @sd: The sched_domain whose load_idx is to be obtained.
  * @idle: The Idle status of the CPU for whose sd load_icx is obtained.
+ *
+ * Return: The load index.
  */
 static inline int get_sd_load_idx(struct sched_domain *sd,
                                         enum cpu_idle_type idle)
@@ -4574,6 +4577,9 @@ static inline void update_sg_lb_stats(struct lb_env *env,
  *
  * Determine if @sg is a busier group than the previously selected
  * busiest group.
+ *
+ * Return: %true if @sg is a busier group than the previously selected
+ * busiest group. %false otherwise.
  */
 static bool update_sd_pick_busiest(struct lb_env *env,
                                    struct sd_lb_stats *sds,
@@ -4691,7 +4697,7 @@ static inline void update_sd_lb_stats(struct lb_env *env,
  * assuming lower CPU number will be equivalent to lower a SMT thread
  * number.
  *
- * Returns 1 when packing is required and a task should be moved to
+ * Return: 1 when packing is required and a task should be moved to
  * this CPU.  The amount of the imbalance is returned in *imbalance.
  *
  * @env: The load balancing environment.
@@ -4869,7 +4875,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
  * @balance: Pointer to a variable indicating if this_cpu
  *      is the appropriate cpu to perform load balancing at this_level.
  *
- * Returns:     - the busiest group if imbalance exists.
+ * Return:      - The busiest group if imbalance exists.
  *              - If no imbalance and user has opted for power-savings balance,
  *                 return the least loaded group whose CPUs can be
  *                 put to idle by rebalancing its tasks onto our group.
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index a326f27d7f09..0b479a6a22bb 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -121,7 +121,7 @@ void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate)
         BUG_ON(bits > 32);
         WARN_ON(!irqs_disabled());
         read_sched_clock = read;
-        sched_clock_mask = (1 << bits) - 1;
+        sched_clock_mask = (1ULL << bits) - 1;
         cd.rate = rate;
 
         /* calculate the mult/shift to convert counter ticks to ns. */
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index e77edc97e036..e8a1516cc0a3 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -182,7 +182,8 @@ static bool can_stop_full_tick(void)
                  * Don't allow the user to think they can get
                  * full NO_HZ with this machine.
                  */
-                WARN_ONCE(1, "NO_HZ FULL will not work with unstable sched clock");
+                WARN_ONCE(have_nohz_full_mask,
+                          "NO_HZ FULL will not work with unstable sched clock");
                 return false;
         }
 #endif
@@ -343,8 +344,6 @@ static int tick_nohz_init_all(void)
 
 void __init tick_nohz_init(void)
 {
-        int cpu;
-
         if (!have_nohz_full_mask) {
                 if (tick_nohz_init_all() < 0)
                         return;
diff --git a/kernel/wait.c b/kernel/wait.c
index dec68bd4e9d8..d550920e040c 100644
--- a/kernel/wait.c
+++ b/kernel/wait.c
@@ -363,8 +363,7 @@ EXPORT_SYMBOL(out_of_line_wait_on_atomic_t);
 
 /**
  * wake_up_atomic_t - Wake up a waiter on a atomic_t
- * @word: The word being waited on, a kernel virtual address
- * @bit: The bit of the word being waited on
+ * @p: The atomic_t being waited on, a kernel virtual address
  *
  * Wake up anyone waiting for the atomic_t to go to zero.
  *