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

net/devlink/leftover.c / net/core/devlink.c:
  565b4824c39f ("devlink: change port event netdev notifier from per-net to global")
  f05bd8ebeb69 ("devlink: move code to a dedicated directory")
  687125b5799c ("devlink: split out core code")
https://lore.kernel.org/all/20230208094657.379f2b1a@canb.auug.org.au/

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

4 files changed, 54 insertions, 35 deletions

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 205dc9edcaa9..ca826bd1eba3 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1205,12 +1205,13 @@ void rebuild_sched_domains(void)
 /**
  * update_tasks_cpumask - Update the cpumasks of tasks in the cpuset.
  * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed
+ * @new_cpus: the temp variable for the new effective_cpus mask
  *
  * Iterate through each task of @cs updating its cpus_allowed to the
  * effective cpuset's.  As this function is called with cpuset_rwsem held,
  * cpuset membership stays stable.
  */
-static void update_tasks_cpumask(struct cpuset *cs)
+static void update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus)
 {
 	struct css_task_iter it;
 	struct task_struct *task;
@@ -1224,7 +1225,10 @@ static void update_tasks_cpumask(struct cpuset *cs)
 		if (top_cs && (task->flags & PF_KTHREAD) &&
 		    kthread_is_per_cpu(task))
 			continue;
-		set_cpus_allowed_ptr(task, cs->effective_cpus);
+
+		cpumask_and(new_cpus, cs->effective_cpus,
+			    task_cpu_possible_mask(task));
+		set_cpus_allowed_ptr(task, new_cpus);
 	}
 	css_task_iter_end(&it);
 }
@@ -1509,7 +1513,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd,
 	spin_unlock_irq(&callback_lock);
 
 	if (adding || deleting)
-		update_tasks_cpumask(parent);
+		update_tasks_cpumask(parent, tmp->new_cpus);
 
 	/*
 	 * Set or clear CS_SCHED_LOAD_BALANCE when partcmd_update, if necessary.
@@ -1661,7 +1665,7 @@ update_parent_subparts:
 		WARN_ON(!is_in_v2_mode() &&
 			!cpumask_equal(cp->cpus_allowed, cp->effective_cpus));
 
-		update_tasks_cpumask(cp);
+		update_tasks_cpumask(cp, tmp->new_cpus);
 
 		/*
 		 * On legacy hierarchy, if the effective cpumask of any non-
@@ -2309,7 +2313,7 @@ static int update_prstate(struct cpuset *cs, int new_prs)
 		}
 	}
 
-	update_tasks_cpumask(parent);
+	update_tasks_cpumask(parent, tmpmask.new_cpus);
 
 	if (parent->child_ecpus_count)
 		update_sibling_cpumasks(parent, cs, &tmpmask);
@@ -3348,7 +3352,7 @@ hotplug_update_tasks_legacy(struct cpuset *cs,
 	 * as the tasks will be migrated to an ancestor.
 	 */
 	if (cpus_updated && !cpumask_empty(cs->cpus_allowed))
-		update_tasks_cpumask(cs);
+		update_tasks_cpumask(cs, new_cpus);
 	if (mems_updated && !nodes_empty(cs->mems_allowed))
 		update_tasks_nodemask(cs);
 
@@ -3385,7 +3389,7 @@ hotplug_update_tasks(struct cpuset *cs,
 	spin_unlock_irq(&callback_lock);
 
 	if (cpus_updated)
-		update_tasks_cpumask(cs);
+		update_tasks_cpumask(cs, new_cpus);
 	if (mems_updated)
 		update_tasks_nodemask(cs);
 }
@@ -3692,15 +3696,38 @@ void __init cpuset_init_smp(void)
  * Description: Returns the cpumask_var_t cpus_allowed of the cpuset
  * attached to the specified @tsk.  Guaranteed to return some non-empty
  * subset of cpu_online_mask, even if this means going outside the
- * tasks cpuset.
+ * tasks cpuset, except when the task is in the top cpuset.
  **/
 
 void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
 {
 	unsigned long flags;
+	struct cpuset *cs;
 
 	spin_lock_irqsave(&callback_lock, flags);
-	guarantee_online_cpus(tsk, pmask);
+	rcu_read_lock();
+
+	cs = task_cs(tsk);
+	if (cs != &top_cpuset)
+		guarantee_online_cpus(tsk, pmask);
+	/*
+	 * Tasks in the top cpuset won't get update to their cpumasks
+	 * when a hotplug online/offline event happens. So we include all
+	 * offline cpus in the allowed cpu list.
+	 */
+	if ((cs == &top_cpuset) || cpumask_empty(pmask)) {
+		const struct cpumask *possible_mask = task_cpu_possible_mask(tsk);
+
+		/*
+		 * We first exclude cpus allocated to partitions. If there is no
+		 * allowable online cpu left, we fall back to all possible cpus.
+		 */
+		cpumask_andnot(pmask, possible_mask, top_cpuset.subparts_cpus);
+		if (!cpumask_intersects(pmask, cpu_online_mask))
+			cpumask_copy(pmask, possible_mask);
+	}
+
+	rcu_read_unlock();
 	spin_unlock_irqrestore(&callback_lock, flags);
 }
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index d56328e5080e..c4be13e50547 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4813,19 +4813,17 @@ find_get_pmu_context(struct pmu *pmu, struct perf_event_context *ctx,
 
 		cpc = per_cpu_ptr(pmu->cpu_pmu_context, event->cpu);
 		epc = &cpc->epc;
-
+		raw_spin_lock_irq(&ctx->lock);
 		if (!epc->ctx) {
 			atomic_set(&epc->refcount, 1);
 			epc->embedded = 1;
-			raw_spin_lock_irq(&ctx->lock);
 			list_add(&epc->pmu_ctx_entry, &ctx->pmu_ctx_list);
 			epc->ctx = ctx;
-			raw_spin_unlock_irq(&ctx->lock);
 		} else {
 			WARN_ON_ONCE(epc->ctx != ctx);
 			atomic_inc(&epc->refcount);
 		}
-
+		raw_spin_unlock_irq(&ctx->lock);
 		return epc;
 	}
 
@@ -4896,33 +4894,30 @@ static void free_epc_rcu(struct rcu_head *head)
 
 static void put_pmu_ctx(struct perf_event_pmu_context *epc)
 {
+	struct perf_event_context *ctx = epc->ctx;
 	unsigned long flags;
 
-	if (!atomic_dec_and_test(&epc->refcount))
+	/*
+	 * XXX
+	 *
+	 * lockdep_assert_held(&ctx->mutex);
+	 *
+	 * can't because of the call-site in _free_event()/put_event()
+	 * which isn't always called under ctx->mutex.
+	 */
+	if (!atomic_dec_and_raw_lock_irqsave(&epc->refcount, &ctx->lock, flags))
 		return;
 
-	if (epc->ctx) {
-		struct perf_event_context *ctx = epc->ctx;
+	WARN_ON_ONCE(list_empty(&epc->pmu_ctx_entry));
 
-		/*
-		 * XXX
-		 *
-		 * lockdep_assert_held(&ctx->mutex);
-		 *
-		 * can't because of the call-site in _free_event()/put_event()
-		 * which isn't always called under ctx->mutex.
-		 */
-
-		WARN_ON_ONCE(list_empty(&epc->pmu_ctx_entry));
-		raw_spin_lock_irqsave(&ctx->lock, flags);
-		list_del_init(&epc->pmu_ctx_entry);
-		epc->ctx = NULL;
-		raw_spin_unlock_irqrestore(&ctx->lock, flags);
-	}
+	list_del_init(&epc->pmu_ctx_entry);
+	epc->ctx = NULL;
 
 	WARN_ON_ONCE(!list_empty(&epc->pinned_active));
 	WARN_ON_ONCE(!list_empty(&epc->flexible_active));
 
+	raw_spin_unlock_irqrestore(&ctx->lock, flags);
+
 	if (epc->embedded)
 		return;
 
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 5c3fb6168eef..798a9042421f 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -1915,7 +1915,7 @@ static void debugfs_add_domain_dir(struct irq_domain *d)
 
 static void debugfs_remove_domain_dir(struct irq_domain *d)
 {
-	debugfs_remove(debugfs_lookup(d->name, domain_dir));
+	debugfs_lookup_and_remove(d->name, domain_dir);
 }
 
 void __init irq_domain_debugfs_init(struct dentry *root)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 78ed5f1baa8c..c9e40f692650 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -9148,9 +9148,6 @@ buffer_percent_write(struct file *filp, const char __user *ubuf,
 	if (val > 100)
 		return -EINVAL;
 
-	if (!val)
-		val = 1;
-
 	tr->buffer_percent = val;
 
 	(*ppos)++;