11 files changed, 94 insertions, 71 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index e2f46ba37f72..105f273b6f86 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -886,7 +886,9 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
                  * per-subsystem and moved to css->id so that lookups are
                  * successful until the target css is released.
                  */
+                mutex_lock(&cgroup_mutex);
                 idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
+                mutex_unlock(&cgroup_mutex);
                 cgrp->id = -1;
 
                 call_rcu(&cgrp->rcu_head, cgroup_free_rcu);
@@ -1566,10 +1568,10 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
                 mutex_lock(&cgroup_mutex);
                 mutex_lock(&cgroup_root_mutex);
 
-                root_cgrp->id = idr_alloc(&root->cgroup_idr, root_cgrp,
-                                           0, 1, GFP_KERNEL);
-                if (root_cgrp->id < 0)
+                ret = idr_alloc(&root->cgroup_idr, root_cgrp, 0, 1, GFP_KERNEL);
+                if (ret < 0)
                         goto unlock_drop;
+                root_cgrp->id = ret;
 
                 /* Check for name clashes with existing mounts */
                 ret = -EBUSY;
@@ -2763,10 +2765,7 @@ static int cgroup_cfts_commit(struct cftype *cfts, bool is_add)
          */
         update_before = cgroup_serial_nr_next;
 
-        mutex_unlock(&cgroup_mutex);
-
         /* add/rm files for all cgroups created before */
-        rcu_read_lock();
         css_for_each_descendant_pre(css, cgroup_css(root, ss)) {
                 struct cgroup *cgrp = css->cgroup;
 
@@ -2775,23 +2774,19 @@ static int cgroup_cfts_commit(struct cftype *cfts, bool is_add)
 
                 inode = cgrp->dentry->d_inode;
                 dget(cgrp->dentry);
-                rcu_read_unlock();
-
                 dput(prev);
                 prev = cgrp->dentry;
 
+                mutex_unlock(&cgroup_mutex);
                 mutex_lock(&inode->i_mutex);
                 mutex_lock(&cgroup_mutex);
                 if (cgrp->serial_nr < update_before && !cgroup_is_dead(cgrp))
                         ret = cgroup_addrm_files(cgrp, cfts, is_add);
-                mutex_unlock(&cgroup_mutex);
                 mutex_unlock(&inode->i_mutex);
-
-                rcu_read_lock();
                 if (ret)
                         break;
         }
-        rcu_read_unlock();
+        mutex_unlock(&cgroup_mutex);
         dput(prev);
         deactivate_super(sb);
         return ret;
@@ -2910,9 +2905,14 @@ static void cgroup_enable_task_cg_lists(void)
                  * We should check if the process is exiting, otherwise
                  * it will race with cgroup_exit() in that the list
                  * entry won't be deleted though the process has exited.
+                 * Do it while holding siglock so that we don't end up
+                 * racing against cgroup_exit().
                  */
+                spin_lock_irq(&p->sighand->siglock);
                 if (!(p->flags & PF_EXITING) && list_empty(&p->cg_list))
                         list_add(&p->cg_list, &task_css_set(p)->tasks);
+                spin_unlock_irq(&p->sighand->siglock);
+
                 task_unlock(p);
         } while_each_thread(g, p);
         read_unlock(&tasklist_lock);
@@ -4158,7 +4158,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
         struct cgroup *cgrp;
         struct cgroup_name *name;
         struct cgroupfs_root *root = parent->root;
-        int ssid, err = 0;
+        int ssid, err;
         struct cgroup_subsys *ss;
         struct super_block *sb = root->sb;
 
@@ -4168,19 +4168,13 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
                 return -ENOMEM;
 
         name = cgroup_alloc_name(dentry);
-        if (!name)
+        if (!name) {
+                err = -ENOMEM;
                 goto err_free_cgrp;
+        }
         rcu_assign_pointer(cgrp->name, name);
 
         /*
-         * Temporarily set the pointer to NULL, so idr_find() won't return
-         * a half-baked cgroup.
-         */
-        cgrp->id = idr_alloc(&root->cgroup_idr, NULL, 1, 0, GFP_KERNEL);
-        if (cgrp->id < 0)
-                goto err_free_name;
-
-        /*
          * Only live parents can have children.  Note that the liveliness
          * check isn't strictly necessary because cgroup_mkdir() and
          * cgroup_rmdir() are fully synchronized by i_mutex; however, do it
@@ -4189,7 +4183,17 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
          */
         if (!cgroup_lock_live_group(parent)) {
                 err = -ENODEV;
-                goto err_free_id;
+                goto err_free_name;
+        }
+
+        /*
+         * Temporarily set the pointer to NULL, so idr_find() won't return
+         * a half-baked cgroup.
+         */
+        cgrp->id = idr_alloc(&root->cgroup_idr, NULL, 1, 0, GFP_KERNEL);
+        if (cgrp->id < 0) {
+                err = -ENOMEM;
+                goto err_unlock;
         }
 
         /* Grab a reference on the superblock so the hierarchy doesn't
@@ -4221,7 +4225,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
          */
         err = cgroup_create_file(dentry, S_IFDIR | mode, sb);
         if (err < 0)
-                goto err_unlock;
+                goto err_free_id;
         lockdep_assert_held(&dentry->d_inode->i_mutex);
 
         cgrp->serial_nr = cgroup_serial_nr_next++;
@@ -4257,12 +4261,12 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 
         return 0;
 
-err_unlock:
-        mutex_unlock(&cgroup_mutex);
-        /* Release the reference count that we took on the superblock */
-        deactivate_super(sb);
 err_free_id:
         idr_remove(&root->cgroup_idr, cgrp->id);
+        /* Release the reference count that we took on the superblock */
+        deactivate_super(sb);
+err_unlock:
+        mutex_unlock(&cgroup_mutex);
 err_free_name:
         kfree(rcu_dereference_raw(cgrp->name));
 err_free_cgrp:
diff --git a/kernel/power/console.c b/kernel/power/console.c
index eacb8bd8cab4..aba9c545a0e3 100644
--- a/kernel/power/console.c
+++ b/kernel/power/console.c
@@ -9,6 +9,7 @@
 #include <linux/kbd_kern.h>
 #include <linux/vt.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include "power.h"
 
 #define SUSPEND_CONSOLE (MAX_NR_CONSOLES-1)
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index b1d255f04135..4dae9cbe9259 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1076,7 +1076,6 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
                 next_seq = log_next_seq;
 
                 len = 0;
-                prev = 0;
                 while (len >= 0 && seq < next_seq) {
                         struct printk_log *msg = log_from_idx(idx);
                         int textlen;
@@ -2788,7 +2787,6 @@ bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog,
         next_idx = idx;
 
         l = 0;
-        prev = 0;
         while (seq < dumper->next_seq) {
                 struct printk_log *msg = log_from_idx(idx);
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b46131ef6aab..6edbef296ece 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1952,7 +1952,7 @@ static int dl_overflow(struct task_struct *p, int policy,
 {
 
         struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
-        u64 period = attr->sched_period;
+        u64 period = attr->sched_period ?: attr->sched_deadline;
         u64 runtime = attr->sched_runtime;
         u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0;
         int cpus, err = -1;
@@ -3661,13 +3661,14 @@ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
  * @pid: the pid in question.
  * @uattr: structure containing the extended parameters.
  */
-SYSCALL_DEFINE2(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr)
+SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
+                               unsigned int, flags)
 {
         struct sched_attr attr;
         struct task_struct *p;
         int retval;
 
-        if (!uattr || pid < 0)
+        if (!uattr || pid < 0 || flags)
                 return -EINVAL;
 
         if (sched_copy_attr(uattr, &attr))
@@ -3786,7 +3787,7 @@ static int sched_read_attr(struct sched_attr __user *uattr,
                 attr->size = usize;
         }
 
-        ret = copy_to_user(uattr, attr, usize);
+        ret = copy_to_user(uattr, attr, attr->size);
         if (ret)
                 return -EFAULT;
 
@@ -3804,8 +3805,8 @@ err_size:
  * @uattr: structure containing the extended parameters.
  * @size: sizeof(attr) for fwd/bwd comp.
  */
-SYSCALL_DEFINE3(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
-                unsigned int, size)
+SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
+                unsigned int, size, unsigned int, flags)
 {
         struct sched_attr attr = {
                 .size = sizeof(struct sched_attr),
@@ -3814,7 +3815,7 @@ SYSCALL_DEFINE3(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
         int retval;
 
         if (!uattr || pid < 0 || size > PAGE_SIZE ||
-            size < SCHED_ATTR_SIZE_VER0)
+            size < SCHED_ATTR_SIZE_VER0 || flags)
                 return -EINVAL;
 
         rcu_read_lock();
@@ -7422,6 +7423,7 @@ static int sched_dl_global_constraints(void)
         u64 period = global_rt_period();
         u64 new_bw = to_ratio(period, runtime);
         int cpu, ret = 0;
+        unsigned long flags;
 
         /*
          * Here we want to check the bandwidth not being set to some
@@ -7435,10 +7437,10 @@ static int sched_dl_global_constraints(void)
         for_each_possible_cpu(cpu) {
                 struct dl_bw *dl_b = dl_bw_of(cpu);
 
-                raw_spin_lock(&dl_b->lock);
+                raw_spin_lock_irqsave(&dl_b->lock, flags);
                 if (new_bw < dl_b->total_bw)
                         ret = -EBUSY;
-                raw_spin_unlock(&dl_b->lock);
+                raw_spin_unlock_irqrestore(&dl_b->lock, flags);
 
                 if (ret)
                         break;
@@ -7451,6 +7453,7 @@ static void sched_dl_do_global(void)
 {
         u64 new_bw = -1;
         int cpu;
+        unsigned long flags;
 
         def_dl_bandwidth.dl_period = global_rt_period();
         def_dl_bandwidth.dl_runtime = global_rt_runtime();
@@ -7464,9 +7467,9 @@ static void sched_dl_do_global(void)
         for_each_possible_cpu(cpu) {
                 struct dl_bw *dl_b = dl_bw_of(cpu);
 
-                raw_spin_lock(&dl_b->lock);
+                raw_spin_lock_irqsave(&dl_b->lock, flags);
                 dl_b->bw = new_bw;
-                raw_spin_unlock(&dl_b->lock);
+                raw_spin_unlock_irqrestore(&dl_b->lock, flags);
         }
 }
 
@@ -7475,7 +7478,8 @@ static int sched_rt_global_validate(void)
         if (sysctl_sched_rt_period <= 0)
                 return -EINVAL;
 
-        if (sysctl_sched_rt_runtime > sysctl_sched_rt_period)
+        if ((sysctl_sched_rt_runtime != RUNTIME_INF) &&
+                (sysctl_sched_rt_runtime > sysctl_sched_rt_period))
                 return -EINVAL;
 
         return 0;
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index 045fc74e3f09..5b8838b56d1c 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -70,7 +70,7 @@ static void cpudl_heapify(struct cpudl *cp, int idx)
 
 static void cpudl_change_key(struct cpudl *cp, int idx, u64 new_dl)
 {
-        WARN_ON(idx > num_present_cpus() || idx == IDX_INVALID);
+        WARN_ON(!cpu_present(idx) || idx == IDX_INVALID);
 
         if (dl_time_before(new_dl, cp->elements[idx].dl)) {
                 cp->elements[idx].dl = new_dl;
@@ -117,7 +117,7 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
         }
 
 out:
-        WARN_ON(best_cpu > num_present_cpus() && best_cpu != -1);
+        WARN_ON(!cpu_present(best_cpu) && best_cpu != -1);
 
         return best_cpu;
 }
@@ -137,7 +137,7 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid)
         int old_idx, new_cpu;
         unsigned long flags;
 
-        WARN_ON(cpu > num_present_cpus());
+        WARN_ON(!cpu_present(cpu));
 
         raw_spin_lock_irqsave(&cp->lock, flags);
         old_idx = cp->cpu_to_idx[cpu];
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 0dd5e0971a07..15cbc17fbf84 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -121,7 +121,7 @@ static inline void dl_clear_overload(struct rq *rq)
 
 static void update_dl_migration(struct dl_rq *dl_rq)
 {
-        if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_total > 1) {
+        if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_running > 1) {
                 if (!dl_rq->overloaded) {
                         dl_set_overload(rq_of_dl_rq(dl_rq));
                         dl_rq->overloaded = 1;
@@ -137,7 +137,6 @@ static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
         struct task_struct *p = dl_task_of(dl_se);
         dl_rq = &rq_of_dl_rq(dl_rq)->dl;
 
-        dl_rq->dl_nr_total++;
         if (p->nr_cpus_allowed > 1)
                 dl_rq->dl_nr_migratory++;
 
@@ -149,7 +148,6 @@ static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
         struct task_struct *p = dl_task_of(dl_se);
         dl_rq = &rq_of_dl_rq(dl_rq)->dl;
 
-        dl_rq->dl_nr_total--;
         if (p->nr_cpus_allowed > 1)
                 dl_rq->dl_nr_migratory--;
 
@@ -717,6 +715,7 @@ void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 
         WARN_ON(!dl_prio(prio));
         dl_rq->dl_nr_running++;
+        inc_nr_running(rq_of_dl_rq(dl_rq));
 
         inc_dl_deadline(dl_rq, deadline);
         inc_dl_migration(dl_se, dl_rq);
@@ -730,6 +729,7 @@ void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
         WARN_ON(!dl_prio(prio));
         WARN_ON(!dl_rq->dl_nr_running);
         dl_rq->dl_nr_running--;
+        dec_nr_running(rq_of_dl_rq(dl_rq));
 
         dec_dl_deadline(dl_rq, dl_se->deadline);
         dec_dl_migration(dl_se, dl_rq);
@@ -836,8 +836,6 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 
         if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
                 enqueue_pushable_dl_task(rq, p);
-
-        inc_nr_running(rq);
 }
 
 static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
@@ -850,8 +848,6 @@ static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 {
         update_curr_dl(rq);
         __dequeue_task_dl(rq, p, flags);
-
-        dec_nr_running(rq);
 }
 
 /*
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 966cc2bfcb77..78157099b167 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1757,6 +1757,8 @@ void task_numa_work(struct callback_head *work)
                         start = end;
                         if (pages <= 0)
                                 goto out;
+
+                        cond_resched();
                 } while (end != vma->vm_end);
         }
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c2119fd20f8b..f964add50f38 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -462,7 +462,6 @@ struct dl_rq {
         } earliest_dl;
 
         unsigned long dl_nr_migratory;
-        unsigned long dl_nr_total;
         int overloaded;
 
         /*
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index 0abb36464281..4d23dc4d8139 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -116,20 +116,42 @@ static enum hrtimer_restart sched_clock_poll(struct hrtimer *hrt)
 void __init sched_clock_register(u64 (*read)(void), int bits,
                                  unsigned long rate)
 {
+        u64 res, wrap, new_mask, new_epoch, cyc, ns;
+        u32 new_mult, new_shift;
+        ktime_t new_wrap_kt;
         unsigned long r;
-        u64 res, wrap;
         char r_unit;
 
         if (cd.rate > rate)
                 return;
 
         WARN_ON(!irqs_disabled());
-        read_sched_clock = read;
-        sched_clock_mask = CLOCKSOURCE_MASK(bits);
-        cd.rate = rate;
 
         /* calculate the mult/shift to convert counter ticks to ns. */
-        clocks_calc_mult_shift(&cd.mult, &cd.shift, rate, NSEC_PER_SEC, 3600);
+        clocks_calc_mult_shift(&new_mult, &new_shift, rate, NSEC_PER_SEC, 3600);
+
+        new_mask = CLOCKSOURCE_MASK(bits);
+
+        /* calculate how many ns until we wrap */
+        wrap = clocks_calc_max_nsecs(new_mult, new_shift, 0, new_mask);
+        new_wrap_kt = ns_to_ktime(wrap - (wrap >> 3));
+
+        /* update epoch for new counter and update epoch_ns from old counter*/
+        new_epoch = read();
+        cyc = read_sched_clock();
+        ns = cd.epoch_ns + cyc_to_ns((cyc - cd.epoch_cyc) & sched_clock_mask,
+                          cd.mult, cd.shift);
+
+        raw_write_seqcount_begin(&cd.seq);
+        read_sched_clock = read;
+        sched_clock_mask = new_mask;
+        cd.rate = rate;
+        cd.wrap_kt = new_wrap_kt;
+        cd.mult = new_mult;
+        cd.shift = new_shift;
+        cd.epoch_cyc = new_epoch;
+        cd.epoch_ns = ns;
+        raw_write_seqcount_end(&cd.seq);
 
         r = rate;
         if (r >= 4000000) {
@@ -141,22 +163,12 @@ void __init sched_clock_register(u64 (*read)(void), int bits,
         } else
                 r_unit = ' ';
 
-        /* calculate how many ns until we wrap */
-        wrap = clocks_calc_max_nsecs(cd.mult, cd.shift, 0, sched_clock_mask);
-        cd.wrap_kt = ns_to_ktime(wrap - (wrap >> 3));
-
         /* calculate the ns resolution of this counter */
-        res = cyc_to_ns(1ULL, cd.mult, cd.shift);
+        res = cyc_to_ns(1ULL, new_mult, new_shift);
+
         pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lluns\n",
                 bits, r, r_unit, res, wrap);
 
-        update_sched_clock();
-
-        /*
-         * Ensure that sched_clock() starts off at 0ns
-         */
-        cd.epoch_ns = 0;
-
         /* Enable IRQ time accounting if we have a fast enough sched_clock */
         if (irqtime > 0 || (irqtime == -1 && rate >= 1000000))
                 enable_sched_clock_irqtime();
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 240fb62cf394..dd06439b9c84 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -225,7 +225,7 @@ static u32 map_id_up(struct uid_gid_map *map, u32 id)
  *
  *      When there is no mapping defined for the user-namespace uid
  *      pair INVALID_UID is returned.  Callers are expected to test
- *      for and handle handle INVALID_UID being returned.  INVALID_UID
+ *      for and handle INVALID_UID being returned.  INVALID_UID
  *      may be tested for using uid_valid().
  */
 kuid_t make_kuid(struct user_namespace *ns, uid_t uid)
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 82ef9f3b7473..193e977a10ea 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1851,6 +1851,12 @@ static void destroy_worker(struct worker *worker)
         if (worker->flags & WORKER_IDLE)
                 pool->nr_idle--;
 
+        /*
+         * Once WORKER_DIE is set, the kworker may destroy itself at any
+         * point.  Pin to ensure the task stays until we're done with it.
+         */
+        get_task_struct(worker->task);
+
         list_del_init(&worker->entry);
         worker->flags |= WORKER_DIE;
 
@@ -1859,6 +1865,7 @@ static void destroy_worker(struct worker *worker)
         spin_unlock_irq(&pool->lock);
 
         kthread_stop(worker->task);
+        put_task_struct(worker->task);
         kfree(worker);
 
         spin_lock_irq(&pool->lock);