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

Cross-merge networking fixes after downstream PR (net-6.14-rc4).

No conflicts or adjacent changes.

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

12 files changed, 221 insertions, 125 deletions

diff --git a/kernel/acct.c b/kernel/acct.c
index 31222e8cd534..6520baa13669 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -103,48 +103,50 @@ struct bsd_acct_struct {
 	atomic_long_t		count;
 	struct rcu_head		rcu;
 	struct mutex		lock;
-	int			active;
+	bool			active;
+	bool			check_space;
 	unsigned long		needcheck;
 	struct file		*file;
 	struct pid_namespace	*ns;
 	struct work_struct	work;
 	struct completion	done;
+	acct_t			ac;
 };
 
-static void do_acct_process(struct bsd_acct_struct *acct);
+static void fill_ac(struct bsd_acct_struct *acct);
+static void acct_write_process(struct bsd_acct_struct *acct);
 
 /*
  * Check the amount of free space and suspend/resume accordingly.
  */
-static int check_free_space(struct bsd_acct_struct *acct)
+static bool check_free_space(struct bsd_acct_struct *acct)
 {
 	struct kstatfs sbuf;
 
-	if (time_is_after_jiffies(acct->needcheck))
-		goto out;
+	if (!acct->check_space)
+		return acct->active;
 
 	/* May block */
 	if (vfs_statfs(&acct->file->f_path, &sbuf))
-		goto out;
+		return acct->active;
 
 	if (acct->active) {
 		u64 suspend = sbuf.f_blocks * SUSPEND;
 		do_div(suspend, 100);
 		if (sbuf.f_bavail <= suspend) {
-			acct->active = 0;
+			acct->active = false;
 			pr_info("Process accounting paused\n");
 		}
 	} else {
 		u64 resume = sbuf.f_blocks * RESUME;
 		do_div(resume, 100);
 		if (sbuf.f_bavail >= resume) {
-			acct->active = 1;
+			acct->active = true;
 			pr_info("Process accounting resumed\n");
 		}
 	}
 
 	acct->needcheck = jiffies + ACCT_TIMEOUT*HZ;
-out:
 	return acct->active;
 }
 
@@ -189,7 +191,11 @@ static void acct_pin_kill(struct fs_pin *pin)
 {
 	struct bsd_acct_struct *acct = to_acct(pin);
 	mutex_lock(&acct->lock);
-	do_acct_process(acct);
+	/*
+	 * Fill the accounting struct with the exiting task's info
+	 * before punting to the workqueue.
+	 */
+	fill_ac(acct);
 	schedule_work(&acct->work);
 	wait_for_completion(&acct->done);
 	cmpxchg(&acct->ns->bacct, pin, NULL);
@@ -202,6 +208,9 @@ static void close_work(struct work_struct *work)
 {
 	struct bsd_acct_struct *acct = container_of(work, struct bsd_acct_struct, work);
 	struct file *file = acct->file;
+
+	/* We were fired by acct_pin_kill() which holds acct->lock. */
+	acct_write_process(acct);
 	if (file->f_op->flush)
 		file->f_op->flush(file, NULL);
 	__fput_sync(file);
@@ -234,6 +243,20 @@ static int acct_on(struct filename *pathname)
 		return -EACCES;
 	}
 
+	/* Exclude kernel kernel internal filesystems. */
+	if (file_inode(file)->i_sb->s_flags & (SB_NOUSER | SB_KERNMOUNT)) {
+		kfree(acct);
+		filp_close(file, NULL);
+		return -EINVAL;
+	}
+
+	/* Exclude procfs and sysfs. */
+	if (file_inode(file)->i_sb->s_iflags & SB_I_USERNS_VISIBLE) {
+		kfree(acct);
+		filp_close(file, NULL);
+		return -EINVAL;
+	}
+
 	if (!(file->f_mode & FMODE_CAN_WRITE)) {
 		kfree(acct);
 		filp_close(file, NULL);
@@ -430,13 +453,27 @@ static u32 encode_float(u64 value)
  *  do_exit() or when switching to a different output file.
  */
 
-static void fill_ac(acct_t *ac)
+static void fill_ac(struct bsd_acct_struct *acct)
 {
 	struct pacct_struct *pacct = &current->signal->pacct;
+	struct file *file = acct->file;
+	acct_t *ac = &acct->ac;
 	u64 elapsed, run_time;
 	time64_t btime;
 	struct tty_struct *tty;
 
+	lockdep_assert_held(&acct->lock);
+
+	if (time_is_after_jiffies(acct->needcheck)) {
+		acct->check_space = false;
+
+		/* Don't fill in @ac if nothing will be written. */
+		if (!acct->active)
+			return;
+	} else {
+		acct->check_space = true;
+	}
+
 	/*
 	 * Fill the accounting struct with the needed info as recorded
 	 * by the different kernel functions.
@@ -484,64 +521,61 @@ static void fill_ac(acct_t *ac)
 	ac->ac_majflt = encode_comp_t(pacct->ac_majflt);
 	ac->ac_exitcode = pacct->ac_exitcode;
 	spin_unlock_irq(&current->sighand->siglock);
-}
-/*
- *  do_acct_process does all actual work. Caller holds the reference to file.
- */
-static void do_acct_process(struct bsd_acct_struct *acct)
-{
-	acct_t ac;
-	unsigned long flim;
-	const struct cred *orig_cred;
-	struct file *file = acct->file;
 
-	/*
-	 * Accounting records are not subject to resource limits.
-	 */
-	flim = rlimit(RLIMIT_FSIZE);
-	current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY;
-	/* Perform file operations on behalf of whoever enabled accounting */
-	orig_cred = override_creds(file->f_cred);
-
-	/*
-	 * First check to see if there is enough free_space to continue
-	 * the process accounting system.
-	 */
-	if (!check_free_space(acct))
-		goto out;
-
-	fill_ac(&ac);
 	/* we really need to bite the bullet and change layout */
-	ac.ac_uid = from_kuid_munged(file->f_cred->user_ns, orig_cred->uid);
-	ac.ac_gid = from_kgid_munged(file->f_cred->user_ns, orig_cred->gid);
+	ac->ac_uid = from_kuid_munged(file->f_cred->user_ns, current_uid());
+	ac->ac_gid = from_kgid_munged(file->f_cred->user_ns, current_gid());
 #if ACCT_VERSION == 1 || ACCT_VERSION == 2
 	/* backward-compatible 16 bit fields */
-	ac.ac_uid16 = ac.ac_uid;
-	ac.ac_gid16 = ac.ac_gid;
+	ac->ac_uid16 = ac->ac_uid;
+	ac->ac_gid16 = ac->ac_gid;
 #elif ACCT_VERSION == 3
 	{
 		struct pid_namespace *ns = acct->ns;
 
-		ac.ac_pid = task_tgid_nr_ns(current, ns);
+		ac->ac_pid = task_tgid_nr_ns(current, ns);
 		rcu_read_lock();
-		ac.ac_ppid = task_tgid_nr_ns(rcu_dereference(current->real_parent),
-					     ns);
+		ac->ac_ppid = task_tgid_nr_ns(rcu_dereference(current->real_parent), ns);
 		rcu_read_unlock();
 	}
 #endif
+}
+
+static void acct_write_process(struct bsd_acct_struct *acct)
+{
+	struct file *file = acct->file;
+	const struct cred *cred;
+	acct_t *ac = &acct->ac;
+
+	/* Perform file operations on behalf of whoever enabled accounting */
+	cred = override_creds(file->f_cred);
+
 	/*
-	 * Get freeze protection. If the fs is frozen, just skip the write
-	 * as we could deadlock the system otherwise.
+	 * First check to see if there is enough free_space to continue
+	 * the process accounting system. Then get freeze protection. If
+	 * the fs is frozen, just skip the write as we could deadlock
+	 * the system otherwise.
 	 */
-	if (file_start_write_trylock(file)) {
+	if (check_free_space(acct) && file_start_write_trylock(file)) {
 		/* it's been opened O_APPEND, so position is irrelevant */
 		loff_t pos = 0;
-		__kernel_write(file, &ac, sizeof(acct_t), &pos);
+		__kernel_write(file, ac, sizeof(acct_t), &pos);
 		file_end_write(file);
 	}
-out:
+
+	revert_creds(cred);
+}
+
+static void do_acct_process(struct bsd_acct_struct *acct)
+{
+	unsigned long flim;
+
+	/* Accounting records are not subject to resource limits. */
+	flim = rlimit(RLIMIT_FSIZE);
+	current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY;
+	fill_ac(acct);
+	acct_write_process(acct);
 	current->signal->rlim[RLIMIT_FSIZE].rlim_cur = flim;
-	revert_creds(orig_cred);
 }
 
 /**
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index d9061bd55436..afc665b7b1fe 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -4013,7 +4013,7 @@ static void __cgroup_kill(struct cgroup *cgrp)
 	lockdep_assert_held(&cgroup_mutex);
 
 	spin_lock_irq(&css_set_lock);
-	set_bit(CGRP_KILL, &cgrp->flags);
+	cgrp->kill_seq++;
 	spin_unlock_irq(&css_set_lock);
 
 	css_task_iter_start(&cgrp->self, CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED, &it);
@@ -4029,10 +4029,6 @@ static void __cgroup_kill(struct cgroup *cgrp)
 		send_sig(SIGKILL, task, 0);
 	}
 	css_task_iter_end(&it);
-
-	spin_lock_irq(&css_set_lock);
-	clear_bit(CGRP_KILL, &cgrp->flags);
-	spin_unlock_irq(&css_set_lock);
 }
 
 static void cgroup_kill(struct cgroup *cgrp)
@@ -6488,6 +6484,10 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs)
 	spin_lock_irq(&css_set_lock);
 	cset = task_css_set(current);
 	get_css_set(cset);
+	if (kargs->cgrp)
+		kargs->kill_seq = kargs->cgrp->kill_seq;
+	else
+		kargs->kill_seq = cset->dfl_cgrp->kill_seq;
 	spin_unlock_irq(&css_set_lock);
 
 	if (!(kargs->flags & CLONE_INTO_CGROUP)) {
@@ -6668,6 +6668,7 @@ void cgroup_post_fork(struct task_struct *child,
 		      struct kernel_clone_args *kargs)
 	__releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex)
 {
+	unsigned int cgrp_kill_seq = 0;
 	unsigned long cgrp_flags = 0;
 	bool kill = false;
 	struct cgroup_subsys *ss;
@@ -6681,10 +6682,13 @@ void cgroup_post_fork(struct task_struct *child,
 
 	/* init tasks are special, only link regular threads */
 	if (likely(child->pid)) {
-		if (kargs->cgrp)
+		if (kargs->cgrp) {
 			cgrp_flags = kargs->cgrp->flags;
-		else
+			cgrp_kill_seq = kargs->cgrp->kill_seq;
+		} else {
 			cgrp_flags = cset->dfl_cgrp->flags;
+			cgrp_kill_seq = cset->dfl_cgrp->kill_seq;
+		}
 
 		WARN_ON_ONCE(!list_empty(&child->cg_list));
 		cset->nr_tasks++;
@@ -6719,7 +6723,7 @@ void cgroup_post_fork(struct task_struct *child,
 		 * child down right after we finished preparing it for
 		 * userspace.
 		 */
-		kill = test_bit(CGRP_KILL, &cgrp_flags);
+		kill = kargs->kill_seq != cgrp_kill_seq;
 	}
 
 	spin_unlock_irq(&css_set_lock);
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index 5877974ece92..aac91466279f 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -590,7 +590,6 @@ static void root_cgroup_cputime(struct cgroup_base_stat *bstat)
 
 		cputime->sum_exec_runtime += user;
 		cputime->sum_exec_runtime += sys;
-		cputime->sum_exec_runtime += cpustat[CPUTIME_STEAL];
 
 #ifdef CONFIG_SCHED_CORE
 		bstat->forceidle_sum += cpustat[CPUTIME_FORCEIDLE];
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index 5432418c0fea..875f25ed6f71 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -31,10 +31,6 @@ config GENERIC_IRQ_EFFECTIVE_AFF_MASK
 config GENERIC_PENDING_IRQ
 	bool
 
-# Deduce delayed migration from top-level interrupt chip flags
-config GENERIC_PENDING_IRQ_CHIPFLAGS
-	bool
-
 # Support for generic irq migrating off cpu before the cpu is offline.
 config GENERIC_IRQ_MIGRATION
 	bool
diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c
index 83d46b9b8ec8..2b331822c7e7 100644
--- a/kernel/sched/autogroup.c
+++ b/kernel/sched/autogroup.c
@@ -150,7 +150,7 @@ void sched_autogroup_exit_task(struct task_struct *p)
 	 * see this thread after that: we can no longer use signal->autogroup.
 	 * See the PF_EXITING check in task_wants_autogroup().
 	 */
-	sched_move_task(p);
+	sched_move_task(p, true);
 }
 
 static void
@@ -182,7 +182,7 @@ autogroup_move_group(struct task_struct *p, struct autogroup *ag)
 	 * sched_autogroup_exit_task().
 	 */
 	for_each_thread(p, t)
-		sched_move_task(t);
+		sched_move_task(t, true);
 
 	unlock_task_sighand(p, &flags);
 	autogroup_kref_put(prev);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 165c90ba64ea..9aecd914ac69 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1063,9 +1063,10 @@ void wake_up_q(struct wake_q_head *head)
 		struct task_struct *task;
 
 		task = container_of(node, struct task_struct, wake_q);
-		/* Task can safely be re-inserted now: */
 		node = node->next;
-		task->wake_q.next = NULL;
+		/* pairs with cmpxchg_relaxed() in __wake_q_add() */
+		WRITE_ONCE(task->wake_q.next, NULL);
+		/* Task can safely be re-inserted now. */
 
 		/*
 		 * wake_up_process() executes a full barrier, which pairs with
@@ -9050,7 +9051,7 @@ static void sched_change_group(struct task_struct *tsk, struct task_group *group
  * now. This function just updates tsk->se.cfs_rq and tsk->se.parent to reflect
  * its new group.
  */
-void sched_move_task(struct task_struct *tsk)
+void sched_move_task(struct task_struct *tsk, bool for_autogroup)
 {
 	int queued, running, queue_flags =
 		DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
@@ -9079,7 +9080,8 @@ void sched_move_task(struct task_struct *tsk)
 		put_prev_task(rq, tsk);
 
 	sched_change_group(tsk, group);
-	scx_move_task(tsk);
+	if (!for_autogroup)
+		scx_cgroup_move_task(tsk);
 
 	if (queued)
 		enqueue_task(rq, tsk, queue_flags);
@@ -9180,7 +9182,7 @@ static void cpu_cgroup_attach(struct cgroup_taskset *tset)
 	struct cgroup_subsys_state *css;
 
 	cgroup_taskset_for_each(task, css, tset)
-		sched_move_task(task);
+		sched_move_task(task, false);
 
 	scx_cgroup_finish_attach();
 }
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 8857c0709bdd..5a81d9a1e31f 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -123,6 +123,19 @@ enum scx_ops_flags {
 	SCX_OPS_SWITCH_PARTIAL	= 1LLU << 3,
 
 	/*
+	 * A migration disabled task can only execute on its current CPU. By
+	 * default, such tasks are automatically put on the CPU's local DSQ with
+	 * the default slice on enqueue. If this ops flag is set, they also go
+	 * through ops.enqueue().
+	 *
+	 * A migration disabled task never invokes ops.select_cpu() as it can
+	 * only select the current CPU. Also, p->cpus_ptr will only contain its
+	 * current CPU while p->nr_cpus_allowed keeps tracking p->user_cpus_ptr
+	 * and thus may disagree with cpumask_weight(p->cpus_ptr).
+	 */
+	SCX_OPS_ENQ_MIGRATION_DISABLED = 1LLU << 4,
+
+	/*
 	 * CPU cgroup support flags
 	 */
 	SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16,	/* cpu.weight */
@@ -130,6 +143,7 @@ enum scx_ops_flags {
 	SCX_OPS_ALL_FLAGS	= SCX_OPS_KEEP_BUILTIN_IDLE |
 				  SCX_OPS_ENQ_LAST |
 				  SCX_OPS_ENQ_EXITING |
+				  SCX_OPS_ENQ_MIGRATION_DISABLED |
 				  SCX_OPS_SWITCH_PARTIAL |
 				  SCX_OPS_HAS_CGROUP_WEIGHT,
 };
@@ -416,7 +430,7 @@ struct sched_ext_ops {
 
 	/**
 	 * @update_idle: Update the idle state of a CPU
-	 * @cpu: CPU to udpate the idle state for
+	 * @cpu: CPU to update the idle state for
 	 * @idle: whether entering or exiting the idle state
 	 *
 	 * This operation is called when @rq's CPU goes or leaves the idle
@@ -882,6 +896,7 @@ static bool scx_warned_zero_slice;
 
 static DEFINE_STATIC_KEY_FALSE(scx_ops_enq_last);
 static DEFINE_STATIC_KEY_FALSE(scx_ops_enq_exiting);
+static DEFINE_STATIC_KEY_FALSE(scx_ops_enq_migration_disabled);
 static DEFINE_STATIC_KEY_FALSE(scx_ops_cpu_preempt);
 static DEFINE_STATIC_KEY_FALSE(scx_builtin_idle_enabled);
 
@@ -1214,7 +1229,7 @@ static bool scx_kf_allowed_if_unlocked(void)
 
 /**
  * nldsq_next_task - Iterate to the next task in a non-local DSQ
- * @dsq: user dsq being interated
+ * @dsq: user dsq being iterated
  * @cur: current position, %NULL to start iteration
  * @rev: walk backwards
  *
@@ -2014,6 +2029,11 @@ static void do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags,
 	    unlikely(p->flags & PF_EXITING))
 		goto local;
 
+	/* see %SCX_OPS_ENQ_MIGRATION_DISABLED */
+	if (!static_branch_unlikely(&scx_ops_enq_migration_disabled) &&
+	    is_migration_disabled(p))
+		goto local;
+
 	if (!SCX_HAS_OP(enqueue))
 		goto global;
 
@@ -2078,7 +2098,7 @@ static void set_task_runnable(struct rq *rq, struct task_struct *p)
 
 	/*
 	 * list_add_tail() must be used. scx_ops_bypass() depends on tasks being
-	 * appened to the runnable_list.
+	 * appended to the runnable_list.
 	 */
 	list_add_tail(&p->scx.runnable_node, &rq->scx.runnable_list);
 }
@@ -2313,12 +2333,35 @@ static void move_remote_task_to_local_dsq(struct task_struct *p, u64 enq_flags,
  *
  * - The BPF scheduler is bypassed while the rq is offline and we can always say
  *   no to the BPF scheduler initiated migrations while offline.
+ *
+ * The caller must ensure that @p and @rq are on different CPUs.
  */
 static bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *rq,
 				      bool trigger_error)
 {
 	int cpu = cpu_of(rq);
 
+	SCHED_WARN_ON(task_cpu(p) == cpu);
+
+	/*
+	 * If @p has migration disabled, @p->cpus_ptr is updated to contain only
+	 * the pinned CPU in migrate_disable_switch() while @p is being switched
+	 * out. However, put_prev_task_scx() is called before @p->cpus_ptr is
+	 * updated and thus another CPU may see @p on a DSQ inbetween leading to
+	 * @p passing the below task_allowed_on_cpu() check while migration is
+	 * disabled.
+	 *
+	 * Test the migration disabled state first as the race window is narrow
+	 * and the BPF scheduler failing to check migration disabled state can
+	 * easily be masked if task_allowed_on_cpu() is done first.
+	 */
+	if (unlikely(is_migration_disabled(p))) {
+		if (trigger_error)
+			scx_ops_error("SCX_DSQ_LOCAL[_ON] cannot move migration disabled %s[%d] from CPU %d to %d",
+				      p->comm, p->pid, task_cpu(p), cpu);
+		return false;
+	}
+
 	/*
 	 * We don't require the BPF scheduler to avoid dispatching to offline
 	 * CPUs mostly for convenience but also because CPUs can go offline
@@ -2327,14 +2370,11 @@ static bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *rq,
 	 */
 	if (!task_allowed_on_cpu(p, cpu)) {
 		if (trigger_error)
-			scx_ops_error("SCX_DSQ_LOCAL[_ON] verdict target cpu %d not allowed for %s[%d]",
-				      cpu_of(rq), p->comm, p->pid);
+			scx_ops_error("SCX_DSQ_LOCAL[_ON] target CPU %d not allowed for %s[%d]",
+				      cpu, p->comm, p->pid);
 		return false;
 	}
 
-	if (unlikely(is_migration_disabled(p)))
-		return false;
-
 	if (!scx_rq_online(rq))
 		return false;
 
@@ -2437,7 +2477,8 @@ static struct rq *move_task_between_dsqs(struct task_struct *p, u64 enq_flags,
 
 	if (dst_dsq->id == SCX_DSQ_LOCAL) {
 		dst_rq = container_of(dst_dsq, struct rq, scx.local_dsq);
-		if (!task_can_run_on_remote_rq(p, dst_rq, true)) {
+		if (src_rq != dst_rq &&
+		    unlikely(!task_can_run_on_remote_rq(p, dst_rq, true))) {
 			dst_dsq = find_global_dsq(p);
 			dst_rq = src_rq;
 		}
@@ -2480,7 +2521,7 @@ static struct rq *move_task_between_dsqs(struct task_struct *p, u64 enq_flags,
 /*
  * A poorly behaving BPF scheduler can live-lock the system by e.g. incessantly
  * banging on the same DSQ on a large NUMA system to the point where switching
- * to the bypass mode can take a long time. Inject artifical delays while the
+ * to the bypass mode can take a long time. Inject artificial delays while the
  * bypass mode is switching to guarantee timely completion.
  */
 static void scx_ops_breather(struct rq *rq)
@@ -2575,6 +2616,9 @@ static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq,
 {
 	struct rq *src_rq = task_rq(p);
 	struct rq *dst_rq = container_of(dst_dsq, struct rq, scx.local_dsq);
+#ifdef CONFIG_SMP
+	struct rq *locked_rq = rq;
+#endif
 
 	/*
 	 * We're synchronized against dequeue through DISPATCHING. As @p can't
@@ -2588,7 +2632,8 @@ static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq,
 	}
 
 #ifdef CONFIG_SMP
-	if (unlikely(!task_can_run_on_remote_rq(p, dst_rq, true))) {
+	if (src_rq != dst_rq &&
+	    unlikely(!task_can_run_on_remote_rq(p, dst_rq, true))) {
 		dispatch_enqueue(find_global_dsq(p), p,
 				 enq_flags | SCX_ENQ_CLEAR_OPSS);
 		return;
@@ -2611,8 +2656,9 @@ static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq,
 	atomic_long_set_release(&p->scx.ops_state, SCX_OPSS_NONE);
 
 	/* switch to @src_rq lock */
-	if (rq != src_rq) {
-		raw_spin_rq_unlock(rq);
+	if (locked_rq != src_rq) {
+		raw_spin_rq_unlock(locked_rq);
+		locked_rq = src_rq;
 		raw_spin_rq_lock(src_rq);
 	}
 
@@ -2630,6 +2676,8 @@ static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq,
 		} else {
 			move_remote_task_to_local_dsq(p, enq_flags,
 						      src_rq, dst_rq);
+			/* task has been moved to dst_rq, which is now locked */
+			locked_rq = dst_rq;
 		}
 
 		/* if the destination CPU is idle, wake it up */
@@ -2638,8 +2686,8 @@ static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq,
 	}
 
 	/* switch back to @rq lock */
-	if (rq != dst_rq) {
-		raw_spin_rq_unlock(dst_rq);
+	if (locked_rq != rq) {
+		raw_spin_rq_unlock(locked_rq);
 		raw_spin_rq_lock(rq);
 	}
 #else	/* CONFIG_SMP */
@@ -3144,7 +3192,7 @@ static struct task_struct *pick_task_scx(struct rq *rq)
  *
  * Unless overridden by ops.core_sched_before(), @p->scx.core_sched_at is used
  * to implement the default task ordering. The older the timestamp, the higher
- * prority the task - the global FIFO ordering matching the default scheduling
+ * priority the task - the global FIFO ordering matching the default scheduling
  * behavior.
  *
  * When ops.core_sched_before() is enabled, @p->scx.core_sched_at is used to
@@ -3851,7 +3899,7 @@ static void task_tick_scx(struct rq *rq, struct task_struct *curr, int queued)
 		curr->scx.slice = 0;
 		touch_core_sched(rq, curr);
 	} else if (SCX_HAS_OP(tick)) {
-		SCX_CALL_OP(SCX_KF_REST, tick, curr);
+		SCX_CALL_OP_TASK(SCX_KF_REST, tick, curr);
 	}
 
 	if (!curr->scx.slice)
@@ -3998,7 +4046,7 @@ static void scx_ops_disable_task(struct task_struct *p)
 	WARN_ON_ONCE(scx_get_task_state(p) != SCX_TASK_ENABLED);
 
 	if (SCX_HAS_OP(disable))
-		SCX_CALL_OP(SCX_KF_REST, disable, p);
+		SCX_CALL_OP_TASK(SCX_KF_REST, disable, p);
 	scx_set_task_state(p, SCX_TASK_READY);
 }
 
@@ -4027,7 +4075,7 @@ static void scx_ops_exit_task(struct task_struct *p)
 	}
 
 	if (SCX_HAS_OP(exit_task))
-		SCX_CALL_OP(SCX_KF_REST, exit_task, p, &args);
+		SCX_CALL_OP_TASK(SCX_KF_REST, exit_task, p, &args);
 	scx_set_task_state(p, SCX_TASK_NONE);
 }
 
@@ -4323,25 +4371,12 @@ err:
 	return ops_sanitize_err("cgroup_prep_move", ret);
 }
 
-void scx_move_task(struct task_struct *p)
+void scx_cgroup_move_task(struct task_struct *p)
 {
 	if (!scx_cgroup_enabled)
 		return;
 
 	/*
-	 * We're called from sched_move_task() which handles both cgroup and
-	 * autogroup moves. Ignore the latter.
-	 *
-	 * Also ignore exiting tasks, because in the exit path tasks transition
-	 * from the autogroup to the root group, so task_group_is_autogroup()
-	 * alone isn't able to catch exiting autogroup tasks. This is safe for
-	 * cgroup_move(), because cgroup migrations never happen for PF_EXITING
-	 * tasks.
-	 */
-	if (task_group_is_autogroup(task_group(p)) || (p->flags & PF_EXITING))
-		return;
-
-	/*
 	 * @p must have ops.cgroup_prep_move() called on it and thus
 	 * cgrp_moving_from set.
 	 */
@@ -4590,7 +4625,7 @@ static int scx_cgroup_init(void)
 	cgroup_warned_missing_idle = false;
 
 	/*
-	 * scx_tg_on/offline() are excluded thorugh scx_cgroup_rwsem. If we walk
+	 * scx_tg_on/offline() are excluded through scx_cgroup_rwsem. If we walk
 	 * cgroups and init, all online cgroups are initialized.
 	 */
 	rcu_read_lock();
@@ -5059,6 +5094,7 @@ static void scx_ops_disable_workfn(struct kthread_work *work)
 		static_branch_disable(&scx_has_op[i]);
 	static_branch_disable(&scx_ops_enq_last);
 	static_branch_disable(&scx_ops_enq_exiting);
+	static_branch_disable(&scx_ops_enq_migration_disabled);
 	static_branch_disable(&scx_ops_cpu_preempt);
 	static_branch_disable(&scx_builtin_idle_enabled);
 	synchronize_rcu();
@@ -5277,9 +5313,10 @@ static void scx_dump_task(struct seq_buf *s, struct scx_dump_ctx *dctx,
 		  scx_get_task_state(p), p->scx.flags & ~SCX_TASK_STATE_MASK,
 		  p->scx.dsq_flags, ops_state & SCX_OPSS_STATE_MASK,
 		  ops_state >> SCX_OPSS_QSEQ_SHIFT);
-	dump_line(s, "      sticky/holding_cpu=%d/%d dsq_id=%s dsq_vtime=%llu slice=%llu",
-		  p->scx.sticky_cpu, p->scx.holding_cpu, dsq_id_buf,
-		  p->scx.dsq_vtime, p->scx.slice);
+	dump_line(s, "      sticky/holding_cpu=%d/%d dsq_id=%s",
+		  p->scx.sticky_cpu, p->scx.holding_cpu, dsq_id_buf);
+	dump_line(s, "      dsq_vtime=%llu slice=%llu weight=%u",
+		  p->scx.dsq_vtime, p->scx.slice, p->scx.weight);
 	dump_line(s, "      cpus=%*pb", cpumask_pr_args(p->cpus_ptr));
 
 	if (SCX_HAS_OP(dump_task)) {
@@ -5667,6 +5704,8 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 
 	if (ops->flags & SCX_OPS_ENQ_EXITING)
 		static_branch_enable(&scx_ops_enq_exiting);
+	if (ops->flags & SCX_OPS_ENQ_MIGRATION_DISABLED)
+		static_branch_enable(&scx_ops_enq_migration_disabled);
 	if (scx_ops.cpu_acquire || scx_ops.cpu_release)
 		static_branch_enable(&scx_ops_cpu_preempt);
 
diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h
index 4d022d17ac7d..1079b56b0f7a 100644
--- a/kernel/sched/ext.h
+++ b/kernel/sched/ext.h
@@ -73,7 +73,7 @@ static inline void scx_update_idle(struct rq *rq, bool idle, bool do_notify) {}
 int scx_tg_online(struct task_group *tg);
 void scx_tg_offline(struct task_group *tg);
 int scx_cgroup_can_attach(struct cgroup_taskset *tset);
-void scx_move_task(struct task_struct *p);
+void scx_cgroup_move_task(struct task_struct *p);
 void scx_cgroup_finish_attach(void);
 void scx_cgroup_cancel_attach(struct cgroup_taskset *tset);
 void scx_group_set_weight(struct task_group *tg, unsigned long cgrp_weight);
@@ -82,7 +82,7 @@ void scx_group_set_idle(struct task_group *tg, bool idle);
 static inline int scx_tg_online(struct task_group *tg) { return 0; }
 static inline void scx_tg_offline(struct task_group *tg) {}
 static inline int scx_cgroup_can_attach(struct cgroup_taskset *tset) { return 0; }
-static inline void scx_move_task(struct task_struct *p) {}
+static inline void scx_cgroup_move_task(struct task_struct *p) {}
 static inline void scx_cgroup_finish_attach(void) {}
 static inline void scx_cgroup_cancel_attach(struct cgroup_taskset *tset) {}
 static inline void scx_group_set_weight(struct task_group *tg, unsigned long cgrp_weight) {}
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 38e0e323dda2..b93c8c3dc05a 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -572,7 +572,7 @@ extern void sched_online_group(struct task_group *tg,
 extern void sched_destroy_group(struct task_group *tg);
 extern void sched_release_group(struct task_group *tg);
 
-extern void sched_move_task(struct task_struct *tsk);
+extern void sched_move_task(struct task_struct *tsk, bool for_autogroup);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index b8e0ae15ca5b..bb6089c2951e 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1672,7 +1672,8 @@ static void *rb_range_buffer(struct ring_buffer_per_cpu *cpu_buffer, int idx)
  * must be the same.
  */
 static bool rb_meta_valid(struct ring_buffer_meta *meta, int cpu,
-			  struct trace_buffer *buffer, int nr_pages)
+			  struct trace_buffer *buffer, int nr_pages,
+			  unsigned long *subbuf_mask)
 {
 	int subbuf_size = PAGE_SIZE;
 	struct buffer_data_page *subbuf;
@@ -1680,6 +1681,9 @@ static bool rb_meta_valid(struct ring_buffer_meta *meta, int cpu,
 	unsigned long buffers_end;
 	int i;
 
+	if (!subbuf_mask)
+		return false;
+
 	/* Check the meta magic and meta struct size */
 	if (meta->magic != RING_BUFFER_META_MAGIC ||
 	    meta->struct_size != sizeof(*meta)) {
@@ -1712,6 +1716,8 @@ static bool rb_meta_valid(struct ring_buffer_meta *meta, int cpu,
 
 	subbuf = rb_subbufs_from_meta(meta);
 
+	bitmap_clear(subbuf_mask, 0, meta->nr_subbufs);
+
 	/* Is the meta buffers and the subbufs themselves have correct data? */
 	for (i = 0; i < meta->nr_subbufs; i++) {
 		if (meta->buffers[i] < 0 ||
@@ -1725,6 +1731,12 @@ static bool rb_meta_valid(struct ring_buffer_meta *meta, int cpu,
 			return false;
 		}
 
+		if (test_bit(meta->buffers[i], subbuf_mask)) {
+			pr_info("Ring buffer boot meta [%d] array has duplicates\n", cpu);
+			return false;
+		}
+
+		set_bit(meta->buffers[i], subbuf_mask);
 		subbuf = (void *)subbuf + subbuf_size;
 	}
 
@@ -1838,6 +1850,11 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer)
 				cpu_buffer->cpu);
 			goto invalid;
 		}
+
+		/* If the buffer has content, update pages_touched */
+		if (ret)
+			local_inc(&cpu_buffer->pages_touched);
+
 		entries += ret;
 		entry_bytes += local_read(&head_page->page->commit);
 		local_set(&cpu_buffer->head_page->entries, ret);
@@ -1889,17 +1906,22 @@ static void rb_meta_init_text_addr(struct ring_buffer_meta *meta)
 static void rb_range_meta_init(struct trace_buffer *buffer, int nr_pages)
 {
 	struct ring_buffer_meta *meta;
+	unsigned long *subbuf_mask;
 	unsigned long delta;
 	void *subbuf;
 	int cpu;
 	int i;
 
+	/* Create a mask to test the subbuf array */
+	subbuf_mask = bitmap_alloc(nr_pages + 1, GFP_KERNEL);
+	/* If subbuf_mask fails to allocate, then rb_meta_valid() will return false */
+
 	for (cpu = 0; cpu < nr_cpu_ids; cpu++) {
 		void *next_meta;
 
 		meta = rb_range_meta(buffer, nr_pages, cpu);
 
-		if (rb_meta_valid(meta, cpu, buffer, nr_pages)) {
+		if (rb_meta_valid(meta, cpu, buffer, nr_pages, subbuf_mask)) {
 			/* Make the mappings match the current address */
 			subbuf = rb_subbufs_from_meta(meta);
 			delta = (unsigned long)subbuf - meta->first_buffer;
@@ -1943,6 +1965,7 @@ static void rb_range_meta_init(struct trace_buffer *buffer, int nr_pages)
 			subbuf += meta->subbuf_size;
 		}
 	}
+	bitmap_free(subbuf_mask);
 }
 
 static void *rbm_start(struct seq_file *m, loff_t *pos)
@@ -7126,6 +7149,7 @@ int ring_buffer_map(struct trace_buffer *buffer, int cpu,
 		kfree(cpu_buffer->subbuf_ids);
 		cpu_buffer->subbuf_ids = NULL;
 		rb_free_meta_page(cpu_buffer);
+		atomic_dec(&cpu_buffer->resize_disabled);
 	}
 
 unlock:
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 1496a5ac33ae..0e6d517e74e0 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -5977,8 +5977,6 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr,
 ssize_t tracing_resize_ring_buffer(struct trace_array *tr,
 				  unsigned long size, int cpu_id)
 {
-	int ret;
-
 	guard(mutex)(&trace_types_lock);
 
 	if (cpu_id != RING_BUFFER_ALL_CPUS) {
@@ -5987,11 +5985,7 @@ ssize_t tracing_resize_ring_buffer(struct trace_array *tr,
 			return -EINVAL;
 	}
 
-	ret = __tracing_resize_ring_buffer(tr, size, cpu_id);
-	if (ret < 0)
-		ret = -ENOMEM;
-
-	return ret;
+	return __tracing_resize_ring_buffer(tr, size, cpu_id);
 }
 
 static void update_last_data(struct trace_array *tr)
@@ -8285,6 +8279,10 @@ static int tracing_buffers_mmap(struct file *filp, struct vm_area_struct *vma)
 	struct trace_iterator *iter = &info->iter;
 	int ret = 0;
 
+	/* Currently the boot mapped buffer is not supported for mmap */
+	if (iter->tr->flags & TRACE_ARRAY_FL_BOOT)
+		return -ENODEV;
+
 	ret = get_snapshot_map(iter->tr);
 	if (ret)
 		return ret;
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 3c2c45313c88..97152f2250fe 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3517,12 +3517,6 @@ repeat:
 		}
 
 		/*
-		 * Put the reference grabbed by send_mayday().  @pool won't
-		 * go away while we're still attached to it.
-		 */
-		put_pwq(pwq);
-
-		/*
 		 * Leave this pool. Notify regular workers; otherwise, we end up
 		 * with 0 concurrency and stalling the execution.
 		 */
@@ -3532,6 +3526,12 @@ repeat:
 
 		worker_detach_from_pool(rescuer);
 
+		/*
+		 * Put the reference grabbed by send_mayday().  @pool might
+		 * go away any time after it.
+		 */
+		put_pwq_unlocked(pwq);
+
 		raw_spin_lock_irq(&wq_mayday_lock);
 	}