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

Cross-merge networking fixes after downstream PR (net-6.17-rc7).

No conflicts.

Adjacent changes:

drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
  9536fbe10c9d ("net/mlx5e: Add PSP steering in local NIC RX")
  7601a0a46216 ("net/mlx5e: Add a miss level for ipsec crypto offload")

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

5 files changed, 44 insertions, 21 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 312c6a8b55bb..77d02f87f3f1 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -126,8 +126,31 @@ DEFINE_PERCPU_RWSEM(cgroup_threadgroup_rwsem);
  * of concurrent destructions.  Use a separate workqueue so that cgroup
  * destruction work items don't end up filling up max_active of system_wq
  * which may lead to deadlock.
+ *
+ * A cgroup destruction should enqueue work sequentially to:
+ * cgroup_offline_wq: use for css offline work
+ * cgroup_release_wq: use for css release work
+ * cgroup_free_wq: use for free work
+ *
+ * Rationale for using separate workqueues:
+ * The cgroup root free work may depend on completion of other css offline
+ * operations. If all tasks were enqueued to a single workqueue, this could
+ * create a deadlock scenario where:
+ * - Free work waits for other css offline work to complete.
+ * - But other css offline work is queued after free work in the same queue.
+ *
+ * Example deadlock scenario with single workqueue (cgroup_destroy_wq):
+ * 1. umount net_prio
+ * 2. net_prio root destruction enqueues work to cgroup_destroy_wq (CPUx)
+ * 3. perf_event CSS A offline enqueues work to same cgroup_destroy_wq (CPUx)
+ * 4. net_prio cgroup_destroy_root->cgroup_lock_and_drain_offline.
+ * 5. net_prio root destruction blocks waiting for perf_event CSS A offline,
+ *    which can never complete as it's behind in the same queue and
+ *    workqueue's max_active is 1.
  */
-static struct workqueue_struct *cgroup_destroy_wq;
+static struct workqueue_struct *cgroup_offline_wq;
+static struct workqueue_struct *cgroup_release_wq;
+static struct workqueue_struct *cgroup_free_wq;
 
 /* generate an array of cgroup subsystem pointers */
 #define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys,
@@ -4159,6 +4182,7 @@ static void cgroup_file_release(struct kernfs_open_file *of)
 		cft->release(of);
 	put_cgroup_ns(ctx->ns);
 	kfree(ctx);
+	of->priv = NULL;
 }
 
 static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
@@ -5558,7 +5582,7 @@ static void css_release_work_fn(struct work_struct *work)
 	cgroup_unlock();
 
 	INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn);
-	queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork);
+	queue_rcu_work(cgroup_free_wq, &css->destroy_rwork);
 }
 
 static void css_release(struct percpu_ref *ref)
@@ -5567,7 +5591,7 @@ static void css_release(struct percpu_ref *ref)
 		container_of(ref, struct cgroup_subsys_state, refcnt);
 
 	INIT_WORK(&css->destroy_work, css_release_work_fn);
-	queue_work(cgroup_destroy_wq, &css->destroy_work);
+	queue_work(cgroup_release_wq, &css->destroy_work);
 }
 
 static void init_and_link_css(struct cgroup_subsys_state *css,
@@ -5701,7 +5725,7 @@ err_list_del:
 	list_del_rcu(&css->sibling);
 err_free_css:
 	INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn);
-	queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork);
+	queue_rcu_work(cgroup_free_wq, &css->destroy_rwork);
 	return ERR_PTR(err);
 }
 
@@ -5939,7 +5963,7 @@ static void css_killed_ref_fn(struct percpu_ref *ref)
 
 	if (atomic_dec_and_test(&css->online_cnt)) {
 		INIT_WORK(&css->destroy_work, css_killed_work_fn);
-		queue_work(cgroup_destroy_wq, &css->destroy_work);
+		queue_work(cgroup_offline_wq, &css->destroy_work);
 	}
 }
 
@@ -6325,8 +6349,14 @@ static int __init cgroup_wq_init(void)
 	 * We would prefer to do this in cgroup_init() above, but that
 	 * is called before init_workqueues(): so leave this until after.
 	 */
-	cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1);
-	BUG_ON(!cgroup_destroy_wq);
+	cgroup_offline_wq = alloc_workqueue("cgroup_offline", 0, 1);
+	BUG_ON(!cgroup_offline_wq);
+
+	cgroup_release_wq = alloc_workqueue("cgroup_release", 0, 1);
+	BUG_ON(!cgroup_release_wq);
+
+	cgroup_free_wq = alloc_workqueue("cgroup_free", 0, 1);
+	BUG_ON(!cgroup_free_wq);
 	return 0;
 }
 core_initcall(cgroup_wq_init);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index be00629f0ba4..ccba6fc3c3fe 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -9551,7 +9551,7 @@ static unsigned long tg_weight(struct task_group *tg)
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	return scale_load_down(tg->shares);
 #else
-	return sched_weight_from_cgroup(tg->scx_weight);
+	return sched_weight_from_cgroup(tg->scx.weight);
 #endif
 }
 
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 4ae32ef179dd..088ceff38c8a 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -6788,12 +6788,8 @@ __bpf_kfunc u32 scx_bpf_reenqueue_local(void)
 		 * CPUs disagree, they use %ENQUEUE_RESTORE which is bypassed to
 		 * the current local DSQ for running tasks and thus are not
 		 * visible to the BPF scheduler.
-		 *
-		 * Also skip re-enqueueing tasks that can only run on this
-		 * CPU, as they would just be re-added to the same local
-		 * DSQ without any benefit.
 		 */
-		if (p->migration_pending || is_migration_disabled(p) || p->nr_cpus_allowed == 1)
+		if (p->migration_pending)
 			continue;
 
 		dispatch_dequeue(rq, p);
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 30899a8cc52c..e8c479329282 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -787,10 +787,10 @@ static void retrigger_next_event(void *arg)
 	 * of the next expiring timer is enough. The return from the SMP
 	 * function call will take care of the reprogramming in case the
 	 * CPU was in a NOHZ idle sleep.
+	 *
+	 * In periodic low resolution mode, the next softirq expiration
+	 * must also be updated.
 	 */
-	if (!hrtimer_hres_active(base) && !tick_nohz_active)
-		return;
-
 	raw_spin_lock(&base->lock);
 	hrtimer_update_base(base);
 	if (hrtimer_hres_active(base))
@@ -2295,11 +2295,6 @@ int hrtimers_cpu_dying(unsigned int dying_cpu)
 				     &new_base->clock_base[i]);
 	}
 
-	/*
-	 * The migration might have changed the first expiring softirq
-	 * timer on this CPU. Update it.
-	 */
-	__hrtimer_get_next_event(new_base, HRTIMER_ACTIVE_SOFT);
 	/* Tell the other CPU to retrigger the next event */
 	smp_call_function_single(ncpu, retrigger_next_event, NULL, 0);
 
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index ccae62d4fb91..fa60362a3f31 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -908,6 +908,8 @@ static int trace_kprobe_create_internal(int argc, const char *argv[],
 			return -EINVAL;
 		}
 		buf = kmemdup(&argv[0][1], len + 1, GFP_KERNEL);
+		if (!buf)
+			return -ENOMEM;
 		buf[len] = '\0';
 		ret = kstrtouint(buf, 0, &maxactive);
 		if (ret || !maxactive) {