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

S390 bpf_jit.S is removed in net-next and had changes in 'net',
since that code isn't used any more take the removal.

TLS data structures split the TX and RX components in 'net-next',
put the new struct members from the bug fix in 'net' into the RX
part.

The 'net-next' tree had some reworking of how the ERSPAN code works in
the GRE tunneling code, overlapping with a one-line headroom
calculation fix in 'net'.

Overlapping changes in __sock_map_ctx_update_elem(), keep the bits
that read the prog members via READ_ONCE() into local variables
before using them.

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

6 files changed, 39 insertions, 94 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 5e10aaeebfcc..092f7c4de903 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7,6 +7,9 @@
  */
 #include "sched.h"
 
+#include <linux/kthread.h>
+#include <linux/nospec.h>
+
 #include <asm/switch_to.h>
 #include <asm/tlb.h>
 
@@ -2718,20 +2721,28 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 		membarrier_mm_sync_core_before_usermode(mm);
 		mmdrop(mm);
 	}
-	if (unlikely(prev_state == TASK_DEAD)) {
-		if (prev->sched_class->task_dead)
-			prev->sched_class->task_dead(prev);
+	if (unlikely(prev_state & (TASK_DEAD|TASK_PARKED))) {
+		switch (prev_state) {
+		case TASK_DEAD:
+			if (prev->sched_class->task_dead)
+				prev->sched_class->task_dead(prev);
 
-		/*
-		 * Remove function-return probe instances associated with this
-		 * task and put them back on the free list.
-		 */
-		kprobe_flush_task(prev);
+			/*
+			 * Remove function-return probe instances associated with this
+			 * task and put them back on the free list.
+			 */
+			kprobe_flush_task(prev);
+
+			/* Task is done with its stack. */
+			put_task_stack(prev);
 
-		/* Task is done with its stack. */
-		put_task_stack(prev);
+			put_task_struct(prev);
+			break;
 
-		put_task_struct(prev);
+		case TASK_PARKED:
+			kthread_park_complete(prev);
+			break;
+		}
 	}
 
 	tick_nohz_task_switch();
@@ -3498,23 +3509,8 @@ static void __sched notrace __schedule(bool preempt)
 
 void __noreturn do_task_dead(void)
 {
-	/*
-	 * The setting of TASK_RUNNING by try_to_wake_up() may be delayed
-	 * when the following two conditions become true.
-	 *   - There is race condition of mmap_sem (It is acquired by
-	 *     exit_mm()), and
-	 *   - SMI occurs before setting TASK_RUNINNG.
-	 *     (or hypervisor of virtual machine switches to other guest)
-	 *  As a result, we may become TASK_RUNNING after becoming TASK_DEAD
-	 *
-	 * To avoid it, we have to wait for releasing tsk->pi_lock which
-	 * is held by try_to_wake_up()
-	 */
-	raw_spin_lock_irq(&current->pi_lock);
-	raw_spin_unlock_irq(&current->pi_lock);
-
 	/* Causes final put_task_struct in finish_task_switch(): */
-	__set_current_state(TASK_DEAD);
+	set_special_state(TASK_DEAD);
 
 	/* Tell freezer to ignore us: */
 	current->flags |= PF_NOFREEZE;
@@ -6928,11 +6924,15 @@ 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/deadline.c b/kernel/sched/deadline.c
index e7b3008b85bb..1356afd1eeb6 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1117,7 +1117,7 @@ extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
  * should be larger than 2^(64 - 20 - 8), which is more than 64 seconds.
  * So, overflow is not an issue here.
  */
-u64 grub_reclaim(u64 delta, struct rq *rq, struct sched_dl_entity *dl_se)
+static u64 grub_reclaim(u64 delta, struct rq *rq, struct sched_dl_entity *dl_se)
 {
 	u64 u_inact = rq->dl.this_bw - rq->dl.running_bw; /* Utot - Uact */
 	u64 u_act;
@@ -2731,8 +2731,6 @@ bool dl_cpu_busy(unsigned int cpu)
 #endif
 
 #ifdef CONFIG_SCHED_DEBUG
-extern void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq);
-
 void print_dl_stats(struct seq_file *m, int cpu)
 {
 	print_dl_rq(m, cpu, &cpu_rq(cpu)->dl);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 54dc31e7ab9b..79f574dba096 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;
@@ -9847,6 +9792,7 @@ static int idle_balance(struct rq *this_rq, struct rq_flags *rf)
 	if (curr_cost > this_rq->max_idle_balance_cost)
 		this_rq->max_idle_balance_cost = curr_cost;
 
+out:
 	/*
 	 * While browsing the domains, we released the rq lock, a task could
 	 * have been enqueued in the meantime. Since we're not going idle,
@@ -9855,7 +9801,6 @@ static int idle_balance(struct rq *this_rq, struct rq_flags *rf)
 	if (this_rq->cfs.h_nr_running && !pulled_task)
 		pulled_task = 1;
 
-out:
 	/* Move the next balance forward */
 	if (time_after(this_rq->next_balance, next_balance))
 		this_rq->next_balance = next_balance;
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 7aef6b4e885a..ef3c4e6f5345 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2701,8 +2701,6 @@ int sched_rr_handler(struct ctl_table *table, int write,
 }
 
 #ifdef CONFIG_SCHED_DEBUG
-extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq);
-
 void print_rt_stats(struct seq_file *m, int cpu)
 {
 	rt_rq_iter_t iter;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 15750c222ca2..1f0a4bc6a39d 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2025,8 +2025,9 @@ extern bool sched_debug_enabled;
 extern void print_cfs_stats(struct seq_file *m, int cpu);
 extern void print_rt_stats(struct seq_file *m, int cpu);
 extern void print_dl_stats(struct seq_file *m, int cpu);
-extern void
-print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
+extern void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
+extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq);
+extern void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq);
 #ifdef CONFIG_NUMA_BALANCING
 extern void
 show_numa_stats(struct task_struct *p, struct seq_file *m);