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

Cross-merge networking fixes after downstream PR (net-6.12-rc7).

Conflicts:

drivers/net/ethernet/freescale/enetc/enetc_pf.c
  e15c5506dd39 ("net: enetc: allocate vf_state during PF probes")
  3774409fd4c6 ("net: enetc: build enetc_pf_common.c as a separate module")
https://lore.kernel.org/20241105114100.118bd35e@canb.auug.org.au

Adjacent changes:

drivers/net/ethernet/ti/am65-cpsw-nuss.c
  de794169cf17 ("net: ethernet: ti: am65-cpsw: Fix multi queue Rx on J7")
  4a7b2ba94a59 ("net: ethernet: ti: am65-cpsw: Use tstats instead of open coded version")

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

10 files changed, 77 insertions, 24 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index cdd09769e6c5..df27d08a7232 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -13959,7 +13959,7 @@ static void perf_event_clear_cpumask(unsigned int cpu)
 	}
 
 	/* migrate */
-	list_for_each_entry_rcu(pmu, &pmus, entry, lockdep_is_held(&pmus_srcu)) {
+	list_for_each_entry(pmu, &pmus, entry) {
 		if (pmu->scope == PERF_PMU_SCOPE_NONE ||
 		    WARN_ON_ONCE(pmu->scope >= PERF_PMU_MAX_SCOPE))
 			continue;
diff --git a/kernel/fork.c b/kernel/fork.c
index 3bf38d260cb3..22f43721d031 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -105,6 +105,7 @@
 #include <linux/rseq.h>
 #include <uapi/linux/pidfd.h>
 #include <linux/pidfs.h>
+#include <linux/tick.h>
 
 #include <asm/pgalloc.h>
 #include <linux/uaccess.h>
@@ -2292,6 +2293,7 @@ __latent_entropy struct task_struct *copy_process(
 	acct_clear_integrals(p);
 
 	posix_cputimers_init(&p->posix_cputimers);
+	tick_dep_init_task(p);
 
 	p->io_context = NULL;
 	audit_set_context(p, NULL);
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 3a24d6b5f559..396a067a8a56 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -718,7 +718,7 @@ static int msi_domain_alloc(struct irq_domain *domain, unsigned int virq,
 		ret = ops->msi_init(domain, info, virq + i, hwirq + i, arg);
 		if (ret < 0) {
 			if (ops->msi_free) {
-				for (i--; i > 0; i--)
+				for (i--; i >= 0; i--)
 					ops->msi_free(domain, info, virq + i);
 			}
 			irq_domain_free_irqs_top(domain, virq, nr_irqs);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index dbfb5717d6af..719e0ed1e976 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4711,7 +4711,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	if (rt_prio(p->prio)) {
 		p->sched_class = &rt_sched_class;
 #ifdef CONFIG_SCHED_CLASS_EXT
-	} else if (task_should_scx(p)) {
+	} else if (task_should_scx(p->policy)) {
 		p->sched_class = &ext_sched_class;
 #endif
 	} else {
@@ -7025,7 +7025,7 @@ int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flag
 }
 EXPORT_SYMBOL(default_wake_function);
 
-const struct sched_class *__setscheduler_class(struct task_struct *p, int prio)
+const struct sched_class *__setscheduler_class(int policy, int prio)
 {
 	if (dl_prio(prio))
 		return &dl_sched_class;
@@ -7034,7 +7034,7 @@ const struct sched_class *__setscheduler_class(struct task_struct *p, int prio)
 		return &rt_sched_class;
 
 #ifdef CONFIG_SCHED_CLASS_EXT
-	if (task_should_scx(p))
+	if (task_should_scx(policy))
 		return &ext_sched_class;
 #endif
 
@@ -7142,7 +7142,7 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 		queue_flag &= ~DEQUEUE_MOVE;
 
 	prev_class = p->sched_class;
-	next_class = __setscheduler_class(p, prio);
+	next_class = __setscheduler_class(p->policy, prio);
 
 	if (prev_class != next_class && p->se.sched_delayed)
 		dequeue_task(rq, p, DEQUEUE_SLEEP | DEQUEUE_DELAYED | DEQUEUE_NOCLOCK);
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 8b98ab2dca5a..b5f4b1a5ae98 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -4257,14 +4257,14 @@ static const struct kset_uevent_ops scx_uevent_ops = {
  * Used by sched_fork() and __setscheduler_prio() to pick the matching
  * sched_class. dl/rt are already handled.
  */
-bool task_should_scx(struct task_struct *p)
+bool task_should_scx(int policy)
 {
 	if (!scx_enabled() ||
 	    unlikely(scx_ops_enable_state() == SCX_OPS_DISABLING))
 		return false;
 	if (READ_ONCE(scx_switching_all))
 		return true;
-	return p->policy == SCHED_EXT;
+	return policy == SCHED_EXT;
 }
 
 /**
@@ -4494,11 +4494,16 @@ static void scx_ops_disable_workfn(struct kthread_work *work)
 	scx_task_iter_start(&sti);
 	while ((p = scx_task_iter_next_locked(&sti))) {
 		const struct sched_class *old_class = p->sched_class;
+		const struct sched_class *new_class =
+			__setscheduler_class(p->policy, p->prio);
 		struct sched_enq_and_set_ctx ctx;
 
+		if (old_class != new_class && p->se.sched_delayed)
+			dequeue_task(task_rq(p), p, DEQUEUE_SLEEP | DEQUEUE_DELAYED);
+
 		sched_deq_and_put_task(p, DEQUEUE_SAVE | DEQUEUE_MOVE, &ctx);
 
-		p->sched_class = __setscheduler_class(p, p->prio);
+		p->sched_class = new_class;
 		check_class_changing(task_rq(p), p, old_class);
 
 		sched_enq_and_set_task(&ctx);
@@ -5204,12 +5209,17 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 	scx_task_iter_start(&sti);
 	while ((p = scx_task_iter_next_locked(&sti))) {
 		const struct sched_class *old_class = p->sched_class;
+		const struct sched_class *new_class =
+			__setscheduler_class(p->policy, p->prio);
 		struct sched_enq_and_set_ctx ctx;
 
+		if (old_class != new_class && p->se.sched_delayed)
+			dequeue_task(task_rq(p), p, DEQUEUE_SLEEP | DEQUEUE_DELAYED);
+
 		sched_deq_and_put_task(p, DEQUEUE_SAVE | DEQUEUE_MOVE, &ctx);
 
 		p->scx.slice = SCX_SLICE_DFL;
-		p->sched_class = __setscheduler_class(p, p->prio);
+		p->sched_class = new_class;
 		check_class_changing(task_rq(p), p, old_class);
 
 		sched_enq_and_set_task(&ctx);
diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h
index 246019519231..b1675bb59fc4 100644
--- a/kernel/sched/ext.h
+++ b/kernel/sched/ext.h
@@ -18,7 +18,7 @@ bool scx_can_stop_tick(struct rq *rq);
 void scx_rq_activate(struct rq *rq);
 void scx_rq_deactivate(struct rq *rq);
 int scx_check_setscheduler(struct task_struct *p, int policy);
-bool task_should_scx(struct task_struct *p);
+bool task_should_scx(int policy);
 void init_sched_ext_class(void);
 
 static inline u32 scx_cpuperf_target(s32 cpu)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c157d4860a3b..2d16c8545c71 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3369,7 +3369,7 @@ retry_pids:
 		vma = vma_next(&vmi);
 	}
 
-	do {
+	for (; vma; vma = vma_next(&vmi)) {
 		if (!vma_migratable(vma) || !vma_policy_mof(vma) ||
 			is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_MIXEDMAP)) {
 			trace_sched_skip_vma_numa(mm, vma, NUMAB_SKIP_UNSUITABLE);
@@ -3491,7 +3491,7 @@ retry_pids:
 		 */
 		if (vma_pids_forced)
 			break;
-	} for_each_vma(vmi, vma);
+	}
 
 	/*
 	 * If no VMAs are remaining and VMAs were skipped due to the PID
@@ -5625,8 +5625,9 @@ pick_next_entity(struct rq *rq, struct cfs_rq *cfs_rq)
 	struct sched_entity *se = pick_eevdf(cfs_rq);
 	if (se->sched_delayed) {
 		dequeue_entities(rq, se, DEQUEUE_SLEEP | DEQUEUE_DELAYED);
-		SCHED_WARN_ON(se->sched_delayed);
-		SCHED_WARN_ON(se->on_rq);
+		/*
+		 * Must not reference @se again, see __block_task().
+		 */
 		return NULL;
 	}
 	return se;
@@ -7176,7 +7177,11 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 		/* Fix-up what dequeue_task_fair() skipped */
 		hrtick_update(rq);
 
-		/* Fix-up what block_task() skipped. */
+		/*
+		 * Fix-up what block_task() skipped.
+		 *
+		 * Must be last, @p might not be valid after this.
+		 */
 		__block_task(rq, p);
 	}
 
@@ -7193,12 +7198,14 @@ static bool dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	if (!(p->se.sched_delayed && (task_on_rq_migrating(p) || (flags & DEQUEUE_SAVE))))
 		util_est_dequeue(&rq->cfs, p);
 
-	if (dequeue_entities(rq, &p->se, flags) < 0) {
-		util_est_update(&rq->cfs, p, DEQUEUE_SLEEP);
+	util_est_update(&rq->cfs, p, flags & DEQUEUE_SLEEP);
+	if (dequeue_entities(rq, &p->se, flags) < 0)
 		return false;
-	}
 
-	util_est_update(&rq->cfs, p, flags & DEQUEUE_SLEEP);
+	/*
+	 * Must not reference @p after dequeue_entities(DEQUEUE_DELAYED).
+	 */
+
 	hrtick_update(rq);
 	return true;
 }
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 081519ffab46..6c54a57275cc 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2769,8 +2769,6 @@ static inline void sub_nr_running(struct rq *rq, unsigned count)
 
 static inline void __block_task(struct rq *rq, struct task_struct *p)
 {
-	WRITE_ONCE(p->on_rq, 0);
-	ASSERT_EXCLUSIVE_WRITER(p->on_rq);
 	if (p->sched_contributes_to_load)
 		rq->nr_uninterruptible++;
 
@@ -2778,6 +2776,38 @@ static inline void __block_task(struct rq *rq, struct task_struct *p)
 		atomic_inc(&rq->nr_iowait);
 		delayacct_blkio_start();
 	}
+
+	ASSERT_EXCLUSIVE_WRITER(p->on_rq);
+
+	/*
+	 * The moment this write goes through, ttwu() can swoop in and migrate
+	 * this task, rendering our rq->__lock ineffective.
+	 *
+	 * __schedule()				try_to_wake_up()
+	 *   LOCK rq->__lock			  LOCK p->pi_lock
+	 *   pick_next_task()
+	 *     pick_next_task_fair()
+	 *       pick_next_entity()
+	 *         dequeue_entities()
+	 *           __block_task()
+	 *             RELEASE p->on_rq = 0	  if (p->on_rq && ...)
+	 *					    break;
+	 *
+	 *					  ACQUIRE (after ctrl-dep)
+	 *
+	 *					  cpu = select_task_rq();
+	 *					  set_task_cpu(p, cpu);
+	 *					  ttwu_queue()
+	 *					    ttwu_do_activate()
+	 *					      LOCK rq->__lock
+	 *					      activate_task()
+	 *					        STORE p->on_rq = 1
+	 *   UNLOCK rq->__lock
+	 *
+	 * Callers must ensure to not reference @p after this -- we no longer
+	 * own it.
+	 */
+	smp_store_release(&p->on_rq, 0);
 }
 
 extern void activate_task(struct rq *rq, struct task_struct *p, int flags);
@@ -3800,7 +3830,7 @@ static inline int rt_effective_prio(struct task_struct *p, int prio)
 
 extern int __sched_setscheduler(struct task_struct *p, const struct sched_attr *attr, bool user, bool pi);
 extern int __sched_setaffinity(struct task_struct *p, struct affinity_context *ctx);
-extern const struct sched_class *__setscheduler_class(struct task_struct *p, int prio);
+extern const struct sched_class *__setscheduler_class(int policy, int prio);
 extern void set_load_weight(struct task_struct *p, bool update_load);
 extern void enqueue_task(struct rq *rq, struct task_struct *p, int flags);
 extern bool dequeue_task(struct rq *rq, struct task_struct *p, int flags);
diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c
index 0470bcc3d204..24f9f90b6574 100644
--- a/kernel/sched/syscalls.c
+++ b/kernel/sched/syscalls.c
@@ -707,7 +707,7 @@ change:
 	}
 
 	prev_class = p->sched_class;
-	next_class = __setscheduler_class(p, newprio);
+	next_class = __setscheduler_class(policy, newprio);
 
 	if (prev_class != next_class && p->se.sched_delayed)
 		dequeue_task(rq, p, DEQUEUE_SLEEP | DEQUEUE_DELAYED | DEQUEUE_NOCLOCK);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a8f52b6527ca..2b64b3ec67d9 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -5501,6 +5501,10 @@ static const struct file_operations tracing_iter_fops = {
 
 static const char readme_msg[] =
 	"tracing mini-HOWTO:\n\n"
+	"By default tracefs removes all OTH file permission bits.\n"
+	"When mounting tracefs an optional group id can be specified\n"
+	"which adds the group to every directory and file in tracefs:\n\n"
+	"\t e.g. mount -t tracefs [-o [gid=<gid>]] nodev /sys/kernel/tracing\n\n"
 	"# echo 0 > tracing_on : quick way to disable tracing\n"
 	"# echo 1 > tracing_on : quick way to re-enable tracing\n\n"
 	" Important files:\n"