Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Conflicts:
	drivers/net/team/team.c
	drivers/net/usb/qmi_wwan.c
	net/batman-adv/bat_iv_ogm.c
	net/ipv4/fib_frontend.c
	net/ipv4/route.c
	net/l2tp/l2tp_netlink.c

The team, fib_frontend, route, and l2tp_netlink conflicts were simply
overlapping changes.

qmi_wwan and bat_iv_ogm were of the "use HEAD" variety.

With help from Antonio Quartulli.

Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 57 insertions, 72 deletions

diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index baa528d7dfbd..478bad2745e3 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -234,15 +234,19 @@ static int pid_ns_ctl_handler(struct ctl_table *table, int write,
          */
 
         tmp.data = &current->nsproxy->pid_ns->last_pid;
-        return proc_dointvec(&tmp, write, buffer, lenp, ppos);
+        return proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
 }
 
+extern int pid_max;
+static int zero = 0;
 static struct ctl_table pid_ns_ctl_table[] = {
         {
                 .procname = "ns_last_pid",
                 .maxlen = sizeof(int),
                 .mode = 0666, /* permissions are checked in the handler */
                 .proc_handler = pid_ns_ctl_handler,
+                .extra1 = &zero,
+                .extra2 = &pid_max,
         },
         { }
 };
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a4ea245f3d85..649c9f876cb1 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6014,11 +6014,6 @@ static void destroy_sched_domains(struct sched_domain *sd, int cpu)
  * SD_SHARE_PKG_RESOURCE set (Last Level Cache Domain) for this
  * allows us to avoid some pointer chasing select_idle_sibling().
  *
- * Iterate domains and sched_groups downward, assigning CPUs to be
- * select_idle_sibling() hw buddy.  Cross-wiring hw makes bouncing
- * due to random perturbation self canceling, ie sw buddies pull
- * their counterpart to their CPU's hw counterpart.
- *
  * Also keep a unique ID per domain (we use the first cpu number in
  * the cpumask of the domain), this allows us to quickly tell if
  * two cpus are in the same cache domain, see cpus_share_cache().
@@ -6032,40 +6027,8 @@ static void update_top_cache_domain(int cpu)
         int id = cpu;
 
         sd = highest_flag_domain(cpu, SD_SHARE_PKG_RESOURCES);
-        if (sd) {
-                struct sched_domain *tmp = sd;
-                struct sched_group *sg, *prev;
-                bool right;
-
-                /*
-                 * Traverse to first CPU in group, and count hops
-                 * to cpu from there, switching direction on each
-                 * hop, never ever pointing the last CPU rightward.
-                 */
-                do {
-                        id = cpumask_first(sched_domain_span(tmp));
-                        prev = sg = tmp->groups;
-                        right = 1;
-
-                        while (cpumask_first(sched_group_cpus(sg)) != id)
-                                sg = sg->next;
-
-                        while (!cpumask_test_cpu(cpu, sched_group_cpus(sg))) {
-                                prev = sg;
-                                sg = sg->next;
-                                right = !right;
-                        }
-
-                        /* A CPU went down, never point back to domain start. */
-                        if (right && cpumask_first(sched_group_cpus(sg->next)) == id)
-                                right = false;
-
-                        sg = right ? sg->next : prev;
-                        tmp->idle_buddy = cpumask_first(sched_group_cpus(sg));
-                } while ((tmp = tmp->child));
-
+        if (sd)
                 id = cpumask_first(sched_domain_span(sd));
-        }
 
         rcu_assign_pointer(per_cpu(sd_llc, cpu), sd);
         per_cpu(sd_llc_id, cpu) = id;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 42d9df6a5ca4..96e2b18b6283 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2637,6 +2637,8 @@ static int select_idle_sibling(struct task_struct *p, int target)
         int cpu = smp_processor_id();
         int prev_cpu = task_cpu(p);
         struct sched_domain *sd;
+        struct sched_group *sg;
+        int i;
 
         /*
          * If the task is going to be woken-up on this cpu and if it is
@@ -2653,17 +2655,29 @@ static int select_idle_sibling(struct task_struct *p, int target)
                 return prev_cpu;
 
         /*
-         * Otherwise, check assigned siblings to find an elegible idle cpu.
+         * Otherwise, iterate the domains and find an elegible idle cpu.
          */
         sd = rcu_dereference(per_cpu(sd_llc, target));
-
         for_each_lower_domain(sd) {
-                if (!cpumask_test_cpu(sd->idle_buddy, tsk_cpus_allowed(p)))
-                        continue;
-                if (idle_cpu(sd->idle_buddy))
-                        return sd->idle_buddy;
-        }
+                sg = sd->groups;
+                do {
+                        if (!cpumask_intersects(sched_group_cpus(sg),
+                                                tsk_cpus_allowed(p)))
+                                goto next;
 
+                        for_each_cpu(i, sched_group_cpus(sg)) {
+                                if (!idle_cpu(i))
+                                        goto next;
+                        }
+
+                        target = cpumask_first_and(sched_group_cpus(sg),
+                                        tsk_cpus_allowed(p));
+                        goto done;
+next:
+                        sg = sg->next;
+                } while (sg != sd->groups);
+        }
+done:
         return target;
 }
 
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 34e5eac81424..d3b91e75cecd 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -303,10 +303,11 @@ void getnstimeofday(struct timespec *ts)
                 seq = read_seqbegin(&tk->lock);
 
                 ts->tv_sec = tk->xtime_sec;
-                ts->tv_nsec = timekeeping_get_ns(tk);
+                nsecs = timekeeping_get_ns(tk);
 
         } while (read_seqretry(&tk->lock, seq));
 
+        ts->tv_nsec = 0;
         timespec_add_ns(ts, nsecs);
 }
 EXPORT_SYMBOL(getnstimeofday);
@@ -345,6 +346,7 @@ void ktime_get_ts(struct timespec *ts)
 {
         struct timekeeper *tk = &timekeeper;
         struct timespec tomono;
+        s64 nsec;
         unsigned int seq;
 
         WARN_ON(timekeeping_suspended);
@@ -352,13 +354,14 @@ void ktime_get_ts(struct timespec *ts)
         do {
                 seq = read_seqbegin(&tk->lock);
                 ts->tv_sec = tk->xtime_sec;
-                ts->tv_nsec = timekeeping_get_ns(tk);
+                nsec = timekeeping_get_ns(tk);
                 tomono = tk->wall_to_monotonic;
 
         } while (read_seqretry(&tk->lock, seq));
 
-        set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec,
-                                ts->tv_nsec + tomono.tv_nsec);
+        ts->tv_sec += tomono.tv_sec;
+        ts->tv_nsec = 0;
+        timespec_add_ns(ts, nsec + tomono.tv_nsec);
 }
 EXPORT_SYMBOL_GPL(ktime_get_ts);
 
@@ -1244,6 +1247,7 @@ void get_monotonic_boottime(struct timespec *ts)
 {
         struct timekeeper *tk = &timekeeper;
         struct timespec tomono, sleep;
+        s64 nsec;
         unsigned int seq;
 
         WARN_ON(timekeeping_suspended);
@@ -1251,14 +1255,15 @@ void get_monotonic_boottime(struct timespec *ts)
         do {
                 seq = read_seqbegin(&tk->lock);
                 ts->tv_sec = tk->xtime_sec;
-                ts->tv_nsec = timekeeping_get_ns(tk);
+                nsec = timekeeping_get_ns(tk);
                 tomono = tk->wall_to_monotonic;
                 sleep = tk->total_sleep_time;
 
         } while (read_seqretry(&tk->lock, seq));
 
-        set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec + sleep.tv_sec,
-                        ts->tv_nsec + tomono.tv_nsec + sleep.tv_nsec);
+        ts->tv_sec += tomono.tv_sec + sleep.tv_sec;
+        ts->tv_nsec = 0;
+        timespec_add_ns(ts, nsec + tomono.tv_nsec + sleep.tv_nsec);
 }
 EXPORT_SYMBOL_GPL(get_monotonic_boottime);
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 1e1373bcb3e3..3c5a79e2134c 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1349,8 +1349,16 @@ static void busy_worker_rebind_fn(struct work_struct *work)
         struct worker *worker = container_of(work, struct worker, rebind_work);
         struct global_cwq *gcwq = worker->pool->gcwq;
 
-        if (worker_maybe_bind_and_lock(worker))
-                worker_clr_flags(worker, WORKER_REBIND);
+        worker_maybe_bind_and_lock(worker);
+
+        /*
+         * %WORKER_REBIND must be cleared even if the above binding failed;
+         * otherwise, we may confuse the next CPU_UP cycle or oops / get
+         * stuck by calling idle_worker_rebind() prematurely.  If CPU went
+         * down again inbetween, %WORKER_UNBOUND would be set, so clearing
+         * %WORKER_REBIND is always safe.
+         */
+        worker_clr_flags(worker, WORKER_REBIND);
 
         spin_unlock_irq(&gcwq->lock);
 }
@@ -3568,18 +3576,17 @@ static int __devinit workqueue_cpu_down_callback(struct notifier_block *nfb,
 #ifdef CONFIG_SMP
 
 struct work_for_cpu {
-        struct completion completion;
+        struct work_struct work;
         long (*fn)(void *);
         void *arg;
         long ret;
 };
 
-static int do_work_for_cpu(void *_wfc)
+static void work_for_cpu_fn(struct work_struct *work)
 {
-        struct work_for_cpu *wfc = _wfc;
+        struct work_for_cpu *wfc = container_of(work, struct work_for_cpu, work);
+
         wfc->ret = wfc->fn(wfc->arg);
-        complete(&wfc->completion);
-        return 0;
 }
 
 /**
@@ -3594,19 +3601,11 @@ static int do_work_for_cpu(void *_wfc)
  */
 long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
 {
-        struct task_struct *sub_thread;
-        struct work_for_cpu wfc = {
-                .completion = COMPLETION_INITIALIZER_ONSTACK(wfc.completion),
-                .fn = fn,
-                .arg = arg,
-        };
+        struct work_for_cpu wfc = { .fn = fn, .arg = arg };
 
-        sub_thread = kthread_create(do_work_for_cpu, &wfc, "work_for_cpu");
-        if (IS_ERR(sub_thread))
-                return PTR_ERR(sub_thread);
-        kthread_bind(sub_thread, cpu);
-        wake_up_process(sub_thread);
-        wait_for_completion(&wfc.completion);
+        INIT_WORK_ONSTACK(&wfc.work, work_for_cpu_fn);
+        schedule_work_on(cpu, &wfc.work);
+        flush_work(&wfc.work);
         return wfc.ret;
 }
 EXPORT_SYMBOL_GPL(work_on_cpu);