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

8 files changed, 118 insertions, 29 deletions

diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index 22ad967d1e5f..830d7f095748 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -129,7 +129,7 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key,
 	struct bpf_cgroup_storage *storage;
 	struct bpf_storage_buffer *new;
 
-	if (flags & BPF_NOEXIST)
+	if (flags != BPF_ANY && flags != BPF_EXIST)
 		return -EINVAL;
 
 	storage = cgroup_storage_lookup((struct bpf_cgroup_storage_map *)map,
@@ -195,6 +195,9 @@ static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr)
 	if (attr->key_size != sizeof(struct bpf_cgroup_storage_key))
 		return ERR_PTR(-EINVAL);
 
+	if (attr->value_size == 0)
+		return ERR_PTR(-EINVAL);
+
 	if (attr->value_size > PAGE_SIZE)
 		return ERR_PTR(-E2BIG);
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index e986518d7bc3..3584ab27d25c 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2842,6 +2842,15 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 	u64 umin_val, umax_val;
 	u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32;
 
+	if (insn_bitness == 32) {
+		/* Relevant for 32-bit RSH: Information can propagate towards
+		 * LSB, so it isn't sufficient to only truncate the output to
+		 * 32 bits.
+		 */
+		coerce_reg_to_size(dst_reg, 4);
+		coerce_reg_to_size(&src_reg, 4);
+	}
+
 	smin_val = src_reg.smin_value;
 	smax_val = src_reg.smax_value;
 	umin_val = src_reg.umin_value;
@@ -3077,7 +3086,6 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 	if (BPF_CLASS(insn->code) != BPF_ALU64) {
 		/* 32-bit ALU ops are (32,32)->32 */
 		coerce_reg_to_size(dst_reg, 4);
-		coerce_reg_to_size(&src_reg, 4);
 	}
 
 	__reg_deduce_bounds(dst_reg);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index dcb093e7b377..5a97f34bc14c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8314,6 +8314,8 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size,
 			goto unlock;
 
 		list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
+			if (event->cpu != smp_processor_id())
+				continue;
 			if (event->attr.type != PERF_TYPE_TRACEPOINT)
 				continue;
 			if (event->attr.config != entry->type)
@@ -9431,9 +9433,7 @@ static void free_pmu_context(struct pmu *pmu)
 	if (pmu->task_ctx_nr > perf_invalid_context)
 		return;
 
-	mutex_lock(&pmus_lock);
 	free_percpu(pmu->pmu_cpu_context);
-	mutex_unlock(&pmus_lock);
 }
 
 /*
@@ -9689,12 +9689,8 @@ EXPORT_SYMBOL_GPL(perf_pmu_register);
 
 void perf_pmu_unregister(struct pmu *pmu)
 {
-	int remove_device;
-
 	mutex_lock(&pmus_lock);
-	remove_device = pmu_bus_running;
 	list_del_rcu(&pmu->entry);
-	mutex_unlock(&pmus_lock);
 
 	/*
 	 * We dereference the pmu list under both SRCU and regular RCU, so
@@ -9706,13 +9702,14 @@ void perf_pmu_unregister(struct pmu *pmu)
 	free_percpu(pmu->pmu_disable_count);
 	if (pmu->type >= PERF_TYPE_MAX)
 		idr_remove(&pmu_idr, pmu->type);
-	if (remove_device) {
+	if (pmu_bus_running) {
 		if (pmu->nr_addr_filters)
 			device_remove_file(pmu->dev, &dev_attr_nr_addr_filters);
 		device_del(pmu->dev);
 		put_device(pmu->dev);
 	}
 	free_pmu_context(pmu);
+	mutex_unlock(&pmus_lock);
 }
 EXPORT_SYMBOL_GPL(perf_pmu_unregister);
 
diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c
index 0be047dbd897..65a3b7e55b9f 100644
--- a/kernel/locking/test-ww_mutex.c
+++ b/kernel/locking/test-ww_mutex.c
@@ -260,7 +260,7 @@ static void test_cycle_work(struct work_struct *work)
 {
 	struct test_cycle *cycle = container_of(work, typeof(*cycle), work);
 	struct ww_acquire_ctx ctx;
-	int err;
+	int err, erra = 0;
 
 	ww_acquire_init(&ctx, &ww_class);
 	ww_mutex_lock(&cycle->a_mutex, &ctx);
@@ -270,17 +270,19 @@ static void test_cycle_work(struct work_struct *work)
 
 	err = ww_mutex_lock(cycle->b_mutex, &ctx);
 	if (err == -EDEADLK) {
+		err = 0;
 		ww_mutex_unlock(&cycle->a_mutex);
 		ww_mutex_lock_slow(cycle->b_mutex, &ctx);
-		err = ww_mutex_lock(&cycle->a_mutex, &ctx);
+		erra = ww_mutex_lock(&cycle->a_mutex, &ctx);
 	}
 
 	if (!err)
 		ww_mutex_unlock(cycle->b_mutex);
-	ww_mutex_unlock(&cycle->a_mutex);
+	if (!erra)
+		ww_mutex_unlock(&cycle->a_mutex);
 	ww_acquire_fini(&ctx);
 
-	cycle->result = err;
+	cycle->result = err ?: erra;
 }
 
 static int __test_cycle(unsigned int nthreads)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 625bc9897f62..ad97f3ba5ec5 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1167,7 +1167,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 
 	if (task_cpu(p) != new_cpu) {
 		if (p->sched_class->migrate_task_rq)
-			p->sched_class->migrate_task_rq(p);
+			p->sched_class->migrate_task_rq(p, new_cpu);
 		p->se.nr_migrations++;
 		rseq_migrate(p);
 		perf_event_task_migrate(p);
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 997ea7b839fa..91e4202b0634 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1607,7 +1607,7 @@ out:
 	return cpu;
 }
 
-static void migrate_task_rq_dl(struct task_struct *p)
+static void migrate_task_rq_dl(struct task_struct *p, int new_cpu __maybe_unused)
 {
 	struct rq *rq;
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f808ddf2a868..7fc4a371bdd2 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1392,6 +1392,17 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
 	int last_cpupid, this_cpupid;
 
 	this_cpupid = cpu_pid_to_cpupid(dst_cpu, current->pid);
+	last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
+
+	/*
+	 * Allow first faults or private faults to migrate immediately early in
+	 * the lifetime of a task. The magic number 4 is based on waiting for
+	 * two full passes of the "multi-stage node selection" test that is
+	 * executed below.
+	 */
+	if ((p->numa_preferred_nid == -1 || p->numa_scan_seq <= 4) &&
+	    (cpupid_pid_unset(last_cpupid) || cpupid_match_pid(p, last_cpupid)))
+		return true;
 
 	/*
 	 * Multi-stage node selection is used in conjunction with a periodic
@@ -1410,7 +1421,6 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
 	 * This quadric squishes small probabilities, making it less likely we
 	 * act on an unlikely task<->page relation.
 	 */
-	last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
 	if (!cpupid_pid_unset(last_cpupid) &&
 				cpupid_to_nid(last_cpupid) != dst_nid)
 		return false;
@@ -1514,6 +1524,21 @@ struct task_numa_env {
 static void task_numa_assign(struct task_numa_env *env,
 			     struct task_struct *p, long imp)
 {
+	struct rq *rq = cpu_rq(env->dst_cpu);
+
+	/* Bail out if run-queue part of active NUMA balance. */
+	if (xchg(&rq->numa_migrate_on, 1))
+		return;
+
+	/*
+	 * Clear previous best_cpu/rq numa-migrate flag, since task now
+	 * found a better CPU to move/swap.
+	 */
+	if (env->best_cpu != -1) {
+		rq = cpu_rq(env->best_cpu);
+		WRITE_ONCE(rq->numa_migrate_on, 0);
+	}
+
 	if (env->best_task)
 		put_task_struct(env->best_task);
 	if (p)
@@ -1553,6 +1578,13 @@ static bool load_too_imbalanced(long src_load, long dst_load,
 }
 
 /*
+ * Maximum NUMA importance can be 1998 (2*999);
+ * SMALLIMP @ 30 would be close to 1998/64.
+ * Used to deter task migration.
+ */
+#define SMALLIMP	30
+
+/*
  * This checks if the overall compute and NUMA accesses of the system would
  * be improved if the source tasks was migrated to the target dst_cpu taking
  * into account that it might be best if task running on the dst_cpu should
@@ -1569,6 +1601,9 @@ static void task_numa_compare(struct task_numa_env *env,
 	long moveimp = imp;
 	int dist = env->dist;
 
+	if (READ_ONCE(dst_rq->numa_migrate_on))
+		return;
+
 	rcu_read_lock();
 	cur = task_rcu_dereference(&dst_rq->curr);
 	if (cur && ((cur->flags & PF_EXITING) || is_idle_task(cur)))
@@ -1582,7 +1617,7 @@ static void task_numa_compare(struct task_numa_env *env,
 		goto unlock;
 
 	if (!cur) {
-		if (maymove || imp > env->best_imp)
+		if (maymove && moveimp >= env->best_imp)
 			goto assign;
 		else
 			goto unlock;
@@ -1625,16 +1660,22 @@ static void task_numa_compare(struct task_numa_env *env,
 			       task_weight(cur, env->dst_nid, dist);
 	}
 
-	if (imp <= env->best_imp)
-		goto unlock;
-
 	if (maymove && moveimp > imp && moveimp > env->best_imp) {
-		imp = moveimp - 1;
+		imp = moveimp;
 		cur = NULL;
 		goto assign;
 	}
 
 	/*
+	 * If the NUMA importance is less than SMALLIMP,
+	 * task migration might only result in ping pong
+	 * of tasks and also hurt performance due to cache
+	 * misses.
+	 */
+	if (imp < SMALLIMP || imp <= env->best_imp + SMALLIMP / 2)
+		goto unlock;
+
+	/*
 	 * In the overloaded case, try and keep the load balanced.
 	 */
 	load = task_h_load(env->p) - task_h_load(cur);
@@ -1710,6 +1751,7 @@ static int task_numa_migrate(struct task_struct *p)
 		.best_cpu = -1,
 	};
 	struct sched_domain *sd;
+	struct rq *best_rq;
 	unsigned long taskweight, groupweight;
 	int nid, ret, dist;
 	long taskimp, groupimp;
@@ -1805,20 +1847,17 @@ static int task_numa_migrate(struct task_struct *p)
 	if (env.best_cpu == -1)
 		return -EAGAIN;
 
-	/*
-	 * Reset the scan period if the task is being rescheduled on an
-	 * alternative node to recheck if the tasks is now properly placed.
-	 */
-	p->numa_scan_period = task_scan_start(p);
-
+	best_rq = cpu_rq(env.best_cpu);
 	if (env.best_task == NULL) {
 		ret = migrate_task_to(p, env.best_cpu);
+		WRITE_ONCE(best_rq->numa_migrate_on, 0);
 		if (ret != 0)
 			trace_sched_stick_numa(p, env.src_cpu, env.best_cpu);
 		return ret;
 	}
 
 	ret = migrate_swap(p, env.best_task, env.best_cpu, env.src_cpu);
+	WRITE_ONCE(best_rq->numa_migrate_on, 0);
 
 	if (ret != 0)
 		trace_sched_stick_numa(p, env.src_cpu, task_cpu(env.best_task));
@@ -2596,6 +2635,39 @@ void task_tick_numa(struct rq *rq, struct task_struct *curr)
 	}
 }
 
+static void update_scan_period(struct task_struct *p, int new_cpu)
+{
+	int src_nid = cpu_to_node(task_cpu(p));
+	int dst_nid = cpu_to_node(new_cpu);
+
+	if (!static_branch_likely(&sched_numa_balancing))
+		return;
+
+	if (!p->mm || !p->numa_faults || (p->flags & PF_EXITING))
+		return;
+
+	if (src_nid == dst_nid)
+		return;
+
+	/*
+	 * Allow resets if faults have been trapped before one scan
+	 * has completed. This is most likely due to a new task that
+	 * is pulled cross-node due to wakeups or load balancing.
+	 */
+	if (p->numa_scan_seq) {
+		/*
+		 * Avoid scan adjustments if moving to the preferred
+		 * node or if the task was not previously running on
+		 * the preferred node.
+		 */
+		if (dst_nid == p->numa_preferred_nid ||
+		    (p->numa_preferred_nid != -1 && src_nid != p->numa_preferred_nid))
+			return;
+	}
+
+	p->numa_scan_period = task_scan_start(p);
+}
+
 #else
 static void task_tick_numa(struct rq *rq, struct task_struct *curr)
 {
@@ -2609,6 +2681,10 @@ static inline void account_numa_dequeue(struct rq *rq, struct task_struct *p)
 {
 }
 
+static inline void update_scan_period(struct task_struct *p, int new_cpu)
+{
+}
+
 #endif /* CONFIG_NUMA_BALANCING */
 
 static void
@@ -6275,7 +6351,7 @@ static void detach_entity_cfs_rq(struct sched_entity *se);
  * cfs_rq_of(p) references at time of call are still valid and identify the
  * previous CPU. The caller guarantees p->pi_lock or task_rq(p)->lock is held.
  */
-static void migrate_task_rq_fair(struct task_struct *p)
+static void migrate_task_rq_fair(struct task_struct *p, int new_cpu)
 {
 	/*
 	 * As blocked tasks retain absolute vruntime the migration needs to
@@ -6328,6 +6404,8 @@ static void migrate_task_rq_fair(struct task_struct *p)
 
 	/* We have migrated, no longer consider this task hot */
 	p->se.exec_start = 0;
+
+	update_scan_period(p, new_cpu);
 }
 
 static void task_dead_fair(struct task_struct *p)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 4a2e8cae63c4..455fa330de04 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -783,6 +783,7 @@ struct rq {
 #ifdef CONFIG_NUMA_BALANCING
 	unsigned int		nr_numa_running;
 	unsigned int		nr_preferred_running;
+	unsigned int		numa_migrate_on;
 #endif
 	#define CPU_LOAD_IDX_MAX 5
 	unsigned long		cpu_load[CPU_LOAD_IDX_MAX];
@@ -1523,7 +1524,7 @@ struct sched_class {
 
 #ifdef CONFIG_SMP
 	int  (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags);
-	void (*migrate_task_rq)(struct task_struct *p);
+	void (*migrate_task_rq)(struct task_struct *p, int new_cpu);
 
 	void (*task_woken)(struct rq *this_rq, struct task_struct *task);