Merge branch 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler fixes from Ingo Molnar:
 "Various fixlets, mostly related to the (root-only) SCHED_DEADLINE
  policy, but also a hotplug bug fix and a fix for a NR_CPUS related
  overallocation bug causing a suspend/resume regression"

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched: Fix hotplug vs. set_cpus_allowed_ptr()
  sched/cpupri: Replace NR_CPUS arrays
  sched/deadline: Replace NR_CPUS arrays
  sched/deadline: Restrict user params max value to 2^63 ns
  sched/deadline: Change sched_getparam() behaviour vs SCHED_DEADLINE
  sched: Disallow sched_attr::sched_policy < 0
  sched: Make sched_setattr() correctly return -EFBIG

6 files changed, 78 insertions, 31 deletions

diff --git a/kernel/cpu.c b/kernel/cpu.c
index a9e710eef0e2..247979a1b815 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -726,10 +726,12 @@ void set_cpu_present(unsigned int cpu, bool present)
 
 void set_cpu_online(unsigned int cpu, bool online)
 {
-        if (online)
+        if (online) {
                 cpumask_set_cpu(cpu, to_cpumask(cpu_online_bits));
-        else
+                cpumask_set_cpu(cpu, to_cpumask(cpu_active_bits));
+        } else {
                 cpumask_clear_cpu(cpu, to_cpumask(cpu_online_bits));
+        }
 }
 
 void set_cpu_active(unsigned int cpu, bool active)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 204d3d281809..0a7251678982 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3195,17 +3195,40 @@ __getparam_dl(struct task_struct *p, struct sched_attr *attr)
  * We ask for the deadline not being zero, and greater or equal
  * than the runtime, as well as the period of being zero or
  * greater than deadline. Furthermore, we have to be sure that
- * user parameters are above the internal resolution (1us); we
- * check sched_runtime only since it is always the smaller one.
+ * user parameters are above the internal resolution of 1us (we
+ * check sched_runtime only since it is always the smaller one) and
+ * below 2^63 ns (we have to check both sched_deadline and
+ * sched_period, as the latter can be zero).
  */
 static bool
 __checkparam_dl(const struct sched_attr *attr)
 {
-        return attr && attr->sched_deadline != 0 &&
-                (attr->sched_period == 0 ||
-                (s64)(attr->sched_period   - attr->sched_deadline) >= 0) &&
-                (s64)(attr->sched_deadline - attr->sched_runtime ) >= 0  &&
-                attr->sched_runtime >= (2 << (DL_SCALE - 1));
+        /* deadline != 0 */
+        if (attr->sched_deadline == 0)
+                return false;
+
+        /*
+         * Since we truncate DL_SCALE bits, make sure we're at least
+         * that big.
+         */
+        if (attr->sched_runtime < (1ULL << DL_SCALE))
+                return false;
+
+        /*
+         * Since we use the MSB for wrap-around and sign issues, make
+         * sure it's not set (mind that period can be equal to zero).
+         */
+        if (attr->sched_deadline & (1ULL << 63) ||
+            attr->sched_period & (1ULL << 63))
+                return false;
+
+        /* runtime <= deadline <= period (if period != 0) */
+        if ((attr->sched_period != 0 &&
+             attr->sched_period < attr->sched_deadline) ||
+            attr->sched_deadline < attr->sched_runtime)
+                return false;
+
+        return true;
 }
 
 /*
@@ -3658,8 +3681,12 @@ SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
         if (!uattr || pid < 0 || flags)
                 return -EINVAL;
 
-        if (sched_copy_attr(uattr, &attr))
-                return -EFAULT;
+        retval = sched_copy_attr(uattr, &attr);
+        if (retval)
+                return retval;
+
+        if (attr.sched_policy < 0)
+                return -EINVAL;
 
         rcu_read_lock();
         retval = -ESRCH;
@@ -3709,7 +3736,7 @@ SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
  */
 SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
 {
-        struct sched_param lp;
+        struct sched_param lp = { .sched_priority = 0 };
         struct task_struct *p;
         int retval;
 
@@ -3726,11 +3753,8 @@ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
         if (retval)
                 goto out_unlock;
 
-        if (task_has_dl_policy(p)) {
-                retval = -EINVAL;
-                goto out_unlock;
-        }
-        lp.sched_priority = p->rt_priority;
+        if (task_has_rt_policy(p))
+                lp.sched_priority = p->rt_priority;
         rcu_read_unlock();
 
         /*
@@ -5052,7 +5076,6 @@ static int sched_cpu_active(struct notifier_block *nfb,
                                       unsigned long action, void *hcpu)
 {
         switch (action & ~CPU_TASKS_FROZEN) {
-        case CPU_STARTING:
         case CPU_DOWN_FAILED:
                 set_cpu_active((long)hcpu, true);
                 return NOTIFY_OK;
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index ab001b5d5048..bd95963dae80 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -13,6 +13,7 @@
 
 #include <linux/gfp.h>
 #include <linux/kernel.h>
+#include <linux/slab.h>
 #include "cpudeadline.h"
 
 static inline int parent(int i)
@@ -39,8 +40,10 @@ static void cpudl_exchange(struct cpudl *cp, int a, int b)
 {
         int cpu_a = cp->elements[a].cpu, cpu_b = cp->elements[b].cpu;
 
-        swap(cp->elements[a], cp->elements[b]);
-        swap(cp->cpu_to_idx[cpu_a], cp->cpu_to_idx[cpu_b]);
+        swap(cp->elements[a].cpu, cp->elements[b].cpu);
+        swap(cp->elements[a].dl , cp->elements[b].dl );
+
+        swap(cp->elements[cpu_a].idx, cp->elements[cpu_b].idx);
 }
 
 static void cpudl_heapify(struct cpudl *cp, int idx)
@@ -140,7 +143,7 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid)
         WARN_ON(!cpu_present(cpu));
 
         raw_spin_lock_irqsave(&cp->lock, flags);
-        old_idx = cp->cpu_to_idx[cpu];
+        old_idx = cp->elements[cpu].idx;
         if (!is_valid) {
                 /* remove item */
                 if (old_idx == IDX_INVALID) {
@@ -155,8 +158,8 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid)
                 cp->elements[old_idx].dl = cp->elements[cp->size - 1].dl;
                 cp->elements[old_idx].cpu = new_cpu;
                 cp->size--;
-                cp->cpu_to_idx[new_cpu] = old_idx;
-                cp->cpu_to_idx[cpu] = IDX_INVALID;
+                cp->elements[new_cpu].idx = old_idx;
+                cp->elements[cpu].idx = IDX_INVALID;
                 while (old_idx > 0 && dl_time_before(
                                 cp->elements[parent(old_idx)].dl,
                                 cp->elements[old_idx].dl)) {
@@ -173,7 +176,7 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid)
                 cp->size++;
                 cp->elements[cp->size - 1].dl = 0;
                 cp->elements[cp->size - 1].cpu = cpu;
-                cp->cpu_to_idx[cpu] = cp->size - 1;
+                cp->elements[cpu].idx = cp->size - 1;
                 cpudl_change_key(cp, cp->size - 1, dl);
                 cpumask_clear_cpu(cpu, cp->free_cpus);
         } else {
@@ -195,10 +198,21 @@ int cpudl_init(struct cpudl *cp)
         memset(cp, 0, sizeof(*cp));
         raw_spin_lock_init(&cp->lock);
         cp->size = 0;
-        for (i = 0; i < NR_CPUS; i++)
-                cp->cpu_to_idx[i] = IDX_INVALID;
-        if (!alloc_cpumask_var(&cp->free_cpus, GFP_KERNEL))
+
+        cp->elements = kcalloc(nr_cpu_ids,
+                               sizeof(struct cpudl_item),
+                               GFP_KERNEL);
+        if (!cp->elements)
+                return -ENOMEM;
+
+        if (!alloc_cpumask_var(&cp->free_cpus, GFP_KERNEL)) {
+                kfree(cp->elements);
                 return -ENOMEM;
+        }
+
+        for_each_possible_cpu(i)
+                cp->elements[i].idx = IDX_INVALID;
+
         cpumask_setall(cp->free_cpus);
 
         return 0;
@@ -211,4 +225,5 @@ int cpudl_init(struct cpudl *cp)
 void cpudl_cleanup(struct cpudl *cp)
 {
         free_cpumask_var(cp->free_cpus);
+        kfree(cp->elements);
 }
diff --git a/kernel/sched/cpudeadline.h b/kernel/sched/cpudeadline.h
index a202789a412c..538c9796ad4a 100644
--- a/kernel/sched/cpudeadline.h
+++ b/kernel/sched/cpudeadline.h
@@ -5,17 +5,17 @@
 
 #define IDX_INVALID     -1
 
-struct array_item {
+struct cpudl_item {
         u64 dl;
         int cpu;
+        int idx;
 };
 
 struct cpudl {
         raw_spinlock_t lock;
         int size;
-        int cpu_to_idx[NR_CPUS];
-        struct array_item elements[NR_CPUS];
         cpumask_var_t free_cpus;
+        struct cpudl_item *elements;
 };
 
 
diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c
index 3031bac8aa3e..8834243abee2 100644
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -30,6 +30,7 @@
 #include <linux/gfp.h>
 #include <linux/sched.h>
 #include <linux/sched/rt.h>
+#include <linux/slab.h>
 #include "cpupri.h"
 
 /* Convert between a 140 based task->prio, and our 102 based cpupri */
@@ -218,8 +219,13 @@ int cpupri_init(struct cpupri *cp)
                         goto cleanup;
         }
 
+        cp->cpu_to_pri = kcalloc(nr_cpu_ids, sizeof(int), GFP_KERNEL);
+        if (!cp->cpu_to_pri)
+                goto cleanup;
+
         for_each_possible_cpu(i)
                 cp->cpu_to_pri[i] = CPUPRI_INVALID;
+
         return 0;
 
 cleanup:
@@ -236,6 +242,7 @@ void cpupri_cleanup(struct cpupri *cp)
 {
         int i;
 
+        kfree(cp->cpu_to_pri);
         for (i = 0; i < CPUPRI_NR_PRIORITIES; i++)
                 free_cpumask_var(cp->pri_to_cpu[i].mask);
 }
diff --git a/kernel/sched/cpupri.h b/kernel/sched/cpupri.h
index f6d756173491..6b033347fdfd 100644
--- a/kernel/sched/cpupri.h
+++ b/kernel/sched/cpupri.h
@@ -17,7 +17,7 @@ struct cpupri_vec {
 
 struct cpupri {
         struct cpupri_vec pri_to_cpu[CPUPRI_NR_PRIORITIES];
-        int               cpu_to_pri[NR_CPUS];
+        int *cpu_to_pri;
 };
 
 #ifdef CONFIG_SMP