Merge tag 'v4.17-rc5' into sched/core, to pick up fixes and dependencies

Signed-off-by: Ingo Molnar <mingo@kernel.org>

4 files changed, 14 insertions, 73 deletions

diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c
index 6be6c575b6cd..2d4ff5353ded 100644
--- a/kernel/sched/autogroup.c
+++ b/kernel/sched/autogroup.c
@@ -2,6 +2,7 @@
 /*
  * Auto-group scheduling implementation:
  */
+#include <linux/nospec.h>
 #include "sched.h"
 
 unsigned int __read_mostly sysctl_sched_autogroup_enabled = 1;
@@ -209,7 +210,7 @@ int proc_sched_autogroup_set_nice(struct task_struct *p, int nice)
         static unsigned long next = INITIAL_JIFFIES;
         struct autogroup *ag;
         unsigned long shares;
-        int err;
+        int err, idx;
 
         if (nice < MIN_NICE || nice > MAX_NICE)
                 return -EINVAL;
@@ -227,7 +228,9 @@ int proc_sched_autogroup_set_nice(struct task_struct *p, int nice)
 
         next = HZ / 10 + jiffies;
         ag = autogroup_task_get(p);
-        shares = scale_load(sched_prio_to_weight[nice + 20]);
+
+        idx = array_index_nospec(nice + 20, 40);
+        shares = scale_load(sched_prio_to_weight[idx]);
 
         down_write(&ag->lock);
         err = sched_group_set_shares(ag->tg, shares);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 71bdb86e07f9..4e0ebae045dc 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8,6 +8,7 @@
 #include "sched.h"
 
 #include <linux/kthread.h>
+#include <linux/nospec.h>
 
 #include <asm/switch_to.h>
 #include <asm/tlb.h>
@@ -6926,11 +6927,15 @@ static int cpu_weight_nice_write_s64(struct cgroup_subsys_state *css,
                                      struct cftype *cft, s64 nice)
 {
         unsigned long weight;
+        int idx;
 
         if (nice < MIN_NICE || nice > MAX_NICE)
                 return -ERANGE;
 
-        weight = sched_prio_to_weight[NICE_TO_PRIO(nice) - MAX_RT_PRIO];
+        idx = NICE_TO_PRIO(nice) - MAX_RT_PRIO;
+        idx = array_index_nospec(idx, 40);
+        weight = sched_prio_to_weight[idx];
+
         return sched_group_set_shares(css_tg(css), scale_load(weight));
 }
 #endif
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index d2c6083304b4..e13df951aca7 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -305,7 +305,8 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
          * Do not reduce the frequency if the CPU has not been idle
          * recently, as the reduction is likely to be premature then.
          */
-        if (busy && next_f < sg_policy->next_freq) {
+        if (busy && next_f < sg_policy->next_freq &&
+            sg_policy->next_freq != UINT_MAX) {
                 next_f = sg_policy->next_freq;
 
                 /* Reset cached freq as next_freq has changed */
@@ -396,19 +397,6 @@ static void sugov_irq_work(struct irq_work *irq_work)
 
         sg_policy = container_of(irq_work, struct sugov_policy, irq_work);
 
-        /*
-         * For RT tasks, the schedutil governor shoots the frequency to maximum.
-         * Special care must be taken to ensure that this kthread doesn't result
-         * in the same behavior.
-         *
-         * This is (mostly) guaranteed by the work_in_progress flag. The flag is
-         * updated only at the end of the sugov_work() function and before that
-         * the schedutil governor rejects all other frequency scaling requests.
-         *
-         * There is a very rare case though, where the RT thread yields right
-         * after the work_in_progress flag is cleared. The effects of that are
-         * neglected for now.
-         */
         kthread_queue_work(&sg_policy->worker, &sg_policy->work);
 }
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1f6a23a5b451..43c7b45f20be 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1854,7 +1854,6 @@ static int task_numa_migrate(struct task_struct *p)
 static void numa_migrate_preferred(struct task_struct *p)
 {
         unsigned long interval = HZ;
-        unsigned long numa_migrate_retry;
 
         /* This task has no NUMA fault statistics yet */
         if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults))
@@ -1862,18 +1861,7 @@ static void numa_migrate_preferred(struct task_struct *p)
 
         /* Periodically retry migrating the task to the preferred node */
         interval = min(interval, msecs_to_jiffies(p->numa_scan_period) / 16);
-        numa_migrate_retry = jiffies + interval;
-
-        /*
-         * Check that the new retry threshold is after the current one. If
-         * the retry is in the future, it implies that wake_affine has
-         * temporarily asked NUMA balancing to backoff from placement.
-         */
-        if (numa_migrate_retry > p->numa_migrate_retry)
-                return;
-
-        /* Safe to try placing the task on the preferred node */
-        p->numa_migrate_retry = numa_migrate_retry;
+        p->numa_migrate_retry = jiffies + interval;
 
         /* Success if task is already running on preferred CPU */
         if (task_node(p) == p->numa_preferred_nid)
@@ -5922,48 +5910,6 @@ wake_affine_weight(struct sched_domain *sd, struct task_struct *p,
         return this_eff_load < prev_eff_load ? this_cpu : nr_cpumask_bits;
 }
 
-#ifdef CONFIG_NUMA_BALANCING
-static void
-update_wa_numa_placement(struct task_struct *p, int prev_cpu, int target)
-{
-        unsigned long interval;
-
-        if (!static_branch_likely(&sched_numa_balancing))
-                return;
-
-        /* If balancing has no preference then continue gathering data */
-        if (p->numa_preferred_nid == -1)
-                return;
-
-        /*
-         * If the wakeup is not affecting locality then it is neutral from
-         * the perspective of NUMA balacing so continue gathering data.
-         */
-        if (cpu_to_node(prev_cpu) == cpu_to_node(target))
-                return;
-
-        /*
-         * Temporarily prevent NUMA balancing trying to place waker/wakee after
-         * wakee has been moved by wake_affine. This will potentially allow
-         * related tasks to converge and update their data placement. The
-         * 4 * numa_scan_period is to allow the two-pass filter to migrate
-         * hot data to the wakers node.
-         */
-        interval = max(sysctl_numa_balancing_scan_delay,
-                         p->numa_scan_period << 2);
-        p->numa_migrate_retry = jiffies + msecs_to_jiffies(interval);
-
-        interval = max(sysctl_numa_balancing_scan_delay,
-                         current->numa_scan_period << 2);
-        current->numa_migrate_retry = jiffies + msecs_to_jiffies(interval);
-}
-#else
-static void
-update_wa_numa_placement(struct task_struct *p, int prev_cpu, int target)
-{
-}
-#endif
-
 static int wake_affine(struct sched_domain *sd, struct task_struct *p,
                        int this_cpu, int prev_cpu, int sync)
 {
@@ -5979,7 +5925,6 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p,
         if (target == nr_cpumask_bits)
                 return prev_cpu;
 
-        update_wa_numa_placement(p, prev_cpu, target);
         schedstat_inc(sd->ttwu_move_affine);
         schedstat_inc(p->se.statistics.nr_wakeups_affine);
         return target;