31 files changed, 840 insertions, 524 deletions
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 367eaf2c78b7..0ebbbe37a60f 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -347,12 +347,17 @@ static void audit_remove_parent_watches(struct audit_parent *parent)
 /* Get path information necessary for adding watches. */
 static int audit_get_nd(struct audit_watch *watch, struct path *parent)
 {
-	struct dentry *d = kern_path_locked(watch->path, parent);
+	struct dentry *d;
+
+	d = kern_path_locked_negative(watch->path, parent);
 	if (IS_ERR(d))
 		return PTR_ERR(d);
-	/* update watch filter fields */
-	watch->dev = d->d_sb->s_dev;
-	watch->ino = d_backing_inode(d)->i_ino;
+
+	if (d_is_positive(d)) {
+		/* update watch filter fields */
+		watch->dev = d->d_sb->s_dev;
+		watch->ino = d_backing_inode(d)->i_ino;
+	}
 
 	inode_unlock(d_backing_inode(parent->dentry));
 	dput(d);
@@ -418,11 +423,10 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list)
 	/* caller expects mutex locked */
 	mutex_lock(&audit_filter_mutex);
 
-	if (ret && ret != -ENOENT) {
+	if (ret) {
 		audit_put_watch(watch);
 		return ret;
 	}
-	ret = 0;
 
 	/* either find an old parent or attach a new one */
 	parent = audit_find_parent(d_backing_inode(parent_path.dentry));
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 5a5adc66b8e2..92b606d60020 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -2189,7 +2189,7 @@ static long bpf_for_each_hash_elem(struct bpf_map *map, bpf_callback_t callback_
 		b = &htab->buckets[i];
 		rcu_read_lock();
 		head = &b->head;
-		hlist_nulls_for_each_entry_rcu(elem, n, head, hash_node) {
+		hlist_nulls_for_each_entry_safe(elem, n, head, hash_node) {
 			key = elem->key;
 			if (is_percpu) {
 				/* current cpu value for percpu map */
diff --git a/kernel/bpf/preload/bpf_preload_kern.c b/kernel/bpf/preload/bpf_preload_kern.c
index 2fdf3c978db1..774e5a538811 100644
--- a/kernel/bpf/preload/bpf_preload_kern.c
+++ b/kernel/bpf/preload/bpf_preload_kern.c
@@ -89,5 +89,6 @@ static void __exit fini(void)
 }
 late_initcall(load);
 module_exit(fini);
+MODULE_IMPORT_NS("BPF_INTERNAL");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Embedded BPF programs for introspection in bpffs");
diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c
index d869f51ea93a..9a5f94371e50 100644
--- a/kernel/bpf/queue_stack_maps.c
+++ b/kernel/bpf/queue_stack_maps.c
@@ -9,13 +9,14 @@
 #include <linux/slab.h>
 #include <linux/btf_ids.h>
 #include "percpu_freelist.h"
+#include <asm/rqspinlock.h>
 
 #define QUEUE_STACK_CREATE_FLAG_MASK \
 	(BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK)
 
 struct bpf_queue_stack {
 	struct bpf_map map;
-	raw_spinlock_t lock;
+	rqspinlock_t lock;
 	u32 head, tail;
 	u32 size; /* max_entries + 1 */
 
@@ -78,7 +79,7 @@ static struct bpf_map *queue_stack_map_alloc(union bpf_attr *attr)
 
 	qs->size = size;
 
-	raw_spin_lock_init(&qs->lock);
+	raw_res_spin_lock_init(&qs->lock);
 
 	return &qs->map;
 }
@@ -98,12 +99,8 @@ static long __queue_map_get(struct bpf_map *map, void *value, bool delete)
 	int err = 0;
 	void *ptr;
 
-	if (in_nmi()) {
-		if (!raw_spin_trylock_irqsave(&qs->lock, flags))
-			return -EBUSY;
-	} else {
-		raw_spin_lock_irqsave(&qs->lock, flags);
-	}
+	if (raw_res_spin_lock_irqsave(&qs->lock, flags))
+		return -EBUSY;
 
 	if (queue_stack_map_is_empty(qs)) {
 		memset(value, 0, qs->map.value_size);
@@ -120,7 +117,7 @@ static long __queue_map_get(struct bpf_map *map, void *value, bool delete)
 	}
 
 out:
-	raw_spin_unlock_irqrestore(&qs->lock, flags);
+	raw_res_spin_unlock_irqrestore(&qs->lock, flags);
 	return err;
 }
 
@@ -133,12 +130,8 @@ static long __stack_map_get(struct bpf_map *map, void *value, bool delete)
 	void *ptr;
 	u32 index;
 
-	if (in_nmi()) {
-		if (!raw_spin_trylock_irqsave(&qs->lock, flags))
-			return -EBUSY;
-	} else {
-		raw_spin_lock_irqsave(&qs->lock, flags);
-	}
+	if (raw_res_spin_lock_irqsave(&qs->lock, flags))
+		return -EBUSY;
 
 	if (queue_stack_map_is_empty(qs)) {
 		memset(value, 0, qs->map.value_size);
@@ -157,7 +150,7 @@ static long __stack_map_get(struct bpf_map *map, void *value, bool delete)
 		qs->head = index;
 
 out:
-	raw_spin_unlock_irqrestore(&qs->lock, flags);
+	raw_res_spin_unlock_irqrestore(&qs->lock, flags);
 	return err;
 }
 
@@ -203,12 +196,8 @@ static long queue_stack_map_push_elem(struct bpf_map *map, void *value,
 	if (flags & BPF_NOEXIST || flags > BPF_EXIST)
 		return -EINVAL;
 
-	if (in_nmi()) {
-		if (!raw_spin_trylock_irqsave(&qs->lock, irq_flags))
-			return -EBUSY;
-	} else {
-		raw_spin_lock_irqsave(&qs->lock, irq_flags);
-	}
+	if (raw_res_spin_lock_irqsave(&qs->lock, irq_flags))
+		return -EBUSY;
 
 	if (queue_stack_map_is_full(qs)) {
 		if (!replace) {
@@ -227,7 +216,7 @@ static long queue_stack_map_push_elem(struct bpf_map *map, void *value,
 		qs->head = 0;
 
 out:
-	raw_spin_unlock_irqrestore(&qs->lock, irq_flags);
+	raw_res_spin_unlock_irqrestore(&qs->lock, irq_flags);
 	return err;
 }
 
diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index 1499d8caa9a3..719d73299397 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -11,6 +11,7 @@
 #include <linux/kmemleak.h>
 #include <uapi/linux/btf.h>
 #include <linux/btf_ids.h>
+#include <asm/rqspinlock.h>
 
 #define RINGBUF_CREATE_FLAG_MASK (BPF_F_NUMA_NODE)
 
@@ -29,7 +30,7 @@ struct bpf_ringbuf {
 	u64 mask;
 	struct page **pages;
 	int nr_pages;
-	raw_spinlock_t spinlock ____cacheline_aligned_in_smp;
+	rqspinlock_t spinlock ____cacheline_aligned_in_smp;
 	/* For user-space producer ring buffers, an atomic_t busy bit is used
 	 * to synchronize access to the ring buffers in the kernel, rather than
 	 * the spinlock that is used for kernel-producer ring buffers. This is
@@ -173,7 +174,7 @@ static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node)
 	if (!rb)
 		return NULL;
 
-	raw_spin_lock_init(&rb->spinlock);
+	raw_res_spin_lock_init(&rb->spinlock);
 	atomic_set(&rb->busy, 0);
 	init_waitqueue_head(&rb->waitq);
 	init_irq_work(&rb->work, bpf_ringbuf_notify);
@@ -416,12 +417,8 @@ static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size)
 
 	cons_pos = smp_load_acquire(&rb->consumer_pos);
 
-	if (in_nmi()) {
-		if (!raw_spin_trylock_irqsave(&rb->spinlock, flags))
-			return NULL;
-	} else {
-		raw_spin_lock_irqsave(&rb->spinlock, flags);
-	}
+	if (raw_res_spin_lock_irqsave(&rb->spinlock, flags))
+		return NULL;
 
 	pend_pos = rb->pending_pos;
 	prod_pos = rb->producer_pos;
@@ -446,7 +443,7 @@ static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size)
 	 */
 	if (new_prod_pos - cons_pos > rb->mask ||
 	    new_prod_pos - pend_pos > rb->mask) {
-		raw_spin_unlock_irqrestore(&rb->spinlock, flags);
+		raw_res_spin_unlock_irqrestore(&rb->spinlock, flags);
 		return NULL;
 	}
 
@@ -458,7 +455,7 @@ static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size)
 	/* pairs with consumer's smp_load_acquire() */
 	smp_store_release(&rb->producer_pos, new_prod_pos);
 
-	raw_spin_unlock_irqrestore(&rb->spinlock, flags);
+	raw_res_spin_unlock_irqrestore(&rb->spinlock, flags);
 
 	return (void *)hdr + BPF_RINGBUF_HDR_SZ;
 }
diff --git a/kernel/bpf/rqspinlock.c b/kernel/bpf/rqspinlock.c
index b896c4a75a5c..338305c8852c 100644
--- a/kernel/bpf/rqspinlock.c
+++ b/kernel/bpf/rqspinlock.c
@@ -253,7 +253,7 @@ static noinline int check_timeout(rqspinlock_t *lock, u32 mask,
 	})
 #else
 #define RES_CHECK_TIMEOUT(ts, ret, mask)			      \
-	({ (ret) = check_timeout(&(ts)); })
+	({ (ret) = check_timeout((lock), (mask), &(ts)); })
 #endif
 
 /*
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 9794446bc8c6..64c3393e8270 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1583,7 +1583,7 @@ struct bpf_map *bpf_map_get(u32 ufd)
 
 	return map;
 }
-EXPORT_SYMBOL(bpf_map_get);
+EXPORT_SYMBOL_NS(bpf_map_get, "BPF_INTERNAL");
 
 struct bpf_map *bpf_map_get_with_uref(u32 ufd)
 {
@@ -3364,7 +3364,7 @@ struct bpf_link *bpf_link_get_from_fd(u32 ufd)
 	bpf_link_inc(link);
 	return link;
 }
-EXPORT_SYMBOL(bpf_link_get_from_fd);
+EXPORT_SYMBOL_NS(bpf_link_get_from_fd, "BPF_INTERNAL");
 
 static void bpf_tracing_link_release(struct bpf_link *link)
 {
@@ -6020,7 +6020,7 @@ int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size)
 		return ____bpf_sys_bpf(cmd, attr, size);
 	}
 }
-EXPORT_SYMBOL(kern_sys_bpf);
+EXPORT_SYMBOL_NS(kern_sys_bpf, "BPF_INTERNAL");
 
 static const struct bpf_func_proto bpf_sys_bpf_proto = {
 	.func		= bpf_sys_bpf,
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 27f08aa17b56..63e5b90da1f3 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -90,7 +90,7 @@
 DEFINE_MUTEX(cgroup_mutex);
 DEFINE_SPINLOCK(css_set_lock);
 
-#ifdef CONFIG_PROVE_RCU
+#if (defined CONFIG_PROVE_RCU || defined CONFIG_LOCKDEP)
 EXPORT_SYMBOL_GPL(cgroup_mutex);
 EXPORT_SYMBOL_GPL(css_set_lock);
 #endif
@@ -2353,9 +2353,37 @@ static struct file_system_type cgroup2_fs_type = {
 };
 
 #ifdef CONFIG_CPUSETS_V1
+enum cpuset_param {
+	Opt_cpuset_v2_mode,
+};
+
+static const struct fs_parameter_spec cpuset_fs_parameters[] = {
+	fsparam_flag  ("cpuset_v2_mode", Opt_cpuset_v2_mode),
+	{}
+};
+
+static int cpuset_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+	struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
+	struct fs_parse_result result;
+	int opt;
+
+	opt = fs_parse(fc, cpuset_fs_parameters, param, &result);
+	if (opt < 0)
+		return opt;
+
+	switch (opt) {
+	case Opt_cpuset_v2_mode:
+		ctx->flags |= CGRP_ROOT_CPUSET_V2_MODE;
+		return 0;
+	}
+	return -EINVAL;
+}
+
 static const struct fs_context_operations cpuset_fs_context_ops = {
 	.get_tree	= cgroup1_get_tree,
 	.free		= cgroup_fs_context_free,
+	.parse_param	= cpuset_parse_param,
 };
 
 /*
@@ -2392,6 +2420,7 @@ static int cpuset_init_fs_context(struct fs_context *fc)
 static struct file_system_type cpuset_fs_type = {
 	.name			= "cpuset",
 	.init_fs_context	= cpuset_init_fs_context,
+	.parameters		= cpuset_fs_parameters,
 	.fs_flags		= FS_USERNS_MOUNT,
 };
 #endif
@@ -5923,6 +5952,12 @@ static void kill_css(struct cgroup_subsys_state *css)
 	if (css->flags & CSS_DYING)
 		return;
 
+	/*
+	 * Call css_killed(), if defined, before setting the CSS_DYING flag
+	 */
+	if (css->ss->css_killed)
+		css->ss->css_killed(css);
+
 	css->flags |= CSS_DYING;
 
 	/*
diff --git a/kernel/cgroup/cpuset-internal.h b/kernel/cgroup/cpuset-internal.h
index 976a8bc3ff60..383963e28ac6 100644
--- a/kernel/cgroup/cpuset-internal.h
+++ b/kernel/cgroup/cpuset-internal.h
@@ -33,6 +33,7 @@ enum prs_errcode {
 	PERR_CPUSEMPTY,
 	PERR_HKEEPING,
 	PERR_ACCESS,
+	PERR_REMOTE,
 };
 
 /* bits in struct cpuset flags field */
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 39c1fc643d77..306b60430091 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -61,10 +61,17 @@ static const char * const perr_strings[] = {
 	[PERR_CPUSEMPTY] = "cpuset.cpus and cpuset.cpus.exclusive are empty",
 	[PERR_HKEEPING]  = "partition config conflicts with housekeeping setup",
 	[PERR_ACCESS]    = "Enable partition not permitted",
+	[PERR_REMOTE]    = "Have remote partition underneath",
 };
 
 /*
- * Exclusive CPUs distributed out to sub-partitions of top_cpuset
+ * For local partitions, update to subpartitions_cpus & isolated_cpus is done
+ * in update_parent_effective_cpumask(). For remote partitions, it is done in
+ * the remote_partition_*() and remote_cpus_update() helpers.
+ */
+/*
+ * Exclusive CPUs distributed out to local or remote sub-partitions of
+ * top_cpuset
  */
 static cpumask_var_t	subpartitions_cpus;
 
@@ -86,7 +93,6 @@ static struct list_head remote_children;
  * A flag to force sched domain rebuild at the end of an operation.
  * It can be set in
  *  - update_partition_sd_lb()
- *  - remote_partition_check()
  *  - update_cpumasks_hier()
  *  - cpuset_update_flag()
  *  - cpuset_hotplug_update_tasks()
@@ -1089,9 +1095,14 @@ void cpuset_reset_sched_domains(void)
  *
  * Iterate through each task of @cs updating its cpus_allowed to the
  * effective cpuset's.  As this function is called with cpuset_mutex held,
- * cpuset membership stays stable. For top_cpuset, task_cpu_possible_mask()
- * is used instead of effective_cpus to make sure all offline CPUs are also
- * included as hotplug code won't update cpumasks for tasks in top_cpuset.
+ * cpuset membership stays stable.
+ *
+ * For top_cpuset, task_cpu_possible_mask() is used instead of effective_cpus
+ * to make sure all offline CPUs are also included as hotplug code won't
+ * update cpumasks for tasks in top_cpuset.
+ *
+ * As task_cpu_possible_mask() can be task dependent in arm64, we have to
+ * do cpu masking per task instead of doing it once for all.
  */
 void cpuset_update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus)
 {
@@ -1151,7 +1162,7 @@ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs,
  *
  * Return: 0 if successful, an error code otherwise
  */
-static int update_partition_exclusive(struct cpuset *cs, int new_prs)
+static int update_partition_exclusive_flag(struct cpuset *cs, int new_prs)
 {
 	bool exclusive = (new_prs > PRS_MEMBER);
 
@@ -1234,12 +1245,12 @@ static void reset_partition_data(struct cpuset *cs)
 }
 
 /*
- * partition_xcpus_newstate - Exclusive CPUs state change
+ * isolated_cpus_update - Update the isolated_cpus mask
  * @old_prs: old partition_root_state
  * @new_prs: new partition_root_state
  * @xcpus: exclusive CPUs with state change
  */
-static void partition_xcpus_newstate(int old_prs, int new_prs, struct cpumask *xcpus)
+static void isolated_cpus_update(int old_prs, int new_prs, struct cpumask *xcpus)
 {
 	WARN_ON_ONCE(old_prs == new_prs);
 	if (new_prs == PRS_ISOLATED)
@@ -1273,8 +1284,8 @@ static bool partition_xcpus_add(int new_prs, struct cpuset *parent,
 
 	isolcpus_updated = (new_prs != parent->partition_root_state);
 	if (isolcpus_updated)
-		partition_xcpus_newstate(parent->partition_root_state, new_prs,
-					 xcpus);
+		isolated_cpus_update(parent->partition_root_state, new_prs,
+				     xcpus);
 
 	cpumask_andnot(parent->effective_cpus, parent->effective_cpus, xcpus);
 	return isolcpus_updated;
@@ -1304,8 +1315,8 @@ static bool partition_xcpus_del(int old_prs, struct cpuset *parent,
 
 	isolcpus_updated = (old_prs != parent->partition_root_state);
 	if (isolcpus_updated)
-		partition_xcpus_newstate(old_prs, parent->partition_root_state,
-					 xcpus);
+		isolated_cpus_update(old_prs, parent->partition_root_state,
+				     xcpus);
 
 	cpumask_and(xcpus, xcpus, cpu_active_mask);
 	cpumask_or(parent->effective_cpus, parent->effective_cpus, xcpus);
@@ -1340,20 +1351,57 @@ EXPORT_SYMBOL_GPL(cpuset_cpu_is_isolated);
  * compute_effective_exclusive_cpumask - compute effective exclusive CPUs
  * @cs: cpuset
  * @xcpus: effective exclusive CPUs value to be set
- * Return: true if xcpus is not empty, false otherwise.
+ * @real_cs: the real cpuset (can be NULL)
+ * Return: 0 if there is no sibling conflict, > 0 otherwise
  *
- * Starting with exclusive_cpus (cpus_allowed if exclusive_cpus is not set),
- * it must be a subset of parent's effective_xcpus.
+ * If exclusive_cpus isn't explicitly set or a real_cs is provided, we have to
+ * scan the sibling cpusets and exclude their exclusive_cpus or effective_xcpus
+ * as well. The provision of real_cs means that a cpumask is being changed and
+ * the given cs is a trial one.
  */
-static bool compute_effective_exclusive_cpumask(struct cpuset *cs,
-						struct cpumask *xcpus)
+static int compute_effective_exclusive_cpumask(struct cpuset *cs,
+					       struct cpumask *xcpus,
+					       struct cpuset *real_cs)
 {
+	struct cgroup_subsys_state *css;
 	struct cpuset *parent = parent_cs(cs);
+	struct cpuset *sibling;
+	int retval = 0;
 
 	if (!xcpus)
 		xcpus = cs->effective_xcpus;
 
-	return cpumask_and(xcpus, user_xcpus(cs), parent->effective_xcpus);
+	cpumask_and(xcpus, user_xcpus(cs), parent->effective_xcpus);
+
+	if (!real_cs) {
+		if (!cpumask_empty(cs->exclusive_cpus))
+			return 0;
+	} else {
+		cs = real_cs;
+	}
+
+	/*
+	 * Exclude exclusive CPUs from siblings
+	 */
+	rcu_read_lock();
+	cpuset_for_each_child(sibling, css, parent) {
+		if (sibling == cs)
+			continue;
+
+		if (!cpumask_empty(sibling->exclusive_cpus) &&
+		    cpumask_intersects(xcpus, sibling->exclusive_cpus)) {
+			cpumask_andnot(xcpus, xcpus, sibling->exclusive_cpus);
+			retval++;
+			continue;
+		}
+		if (!cpumask_empty(sibling->effective_xcpus) &&
+		    cpumask_intersects(xcpus, sibling->effective_xcpus)) {
+			cpumask_andnot(xcpus, xcpus, sibling->effective_xcpus);
+			retval++;
+		}
+	}
+	rcu_read_unlock();
+	return retval;
 }
 
 static inline bool is_remote_partition(struct cpuset *cs)
@@ -1395,7 +1443,7 @@ static int remote_partition_enable(struct cpuset *cs, int new_prs,
 	 * remote partition root underneath it, its exclusive_cpus must
 	 * have overlapped with subpartitions_cpus.
 	 */
-	compute_effective_exclusive_cpumask(cs, tmp->new_cpus);
+	compute_effective_exclusive_cpumask(cs, tmp->new_cpus, NULL);
 	if (cpumask_empty(tmp->new_cpus) ||
 	    cpumask_intersects(tmp->new_cpus, subpartitions_cpus) ||
 	    cpumask_subset(top_cpuset.effective_cpus, tmp->new_cpus))
@@ -1404,8 +1452,11 @@ static int remote_partition_enable(struct cpuset *cs, int new_prs,
 	spin_lock_irq(&callback_lock);
 	isolcpus_updated = partition_xcpus_add(new_prs, NULL, tmp->new_cpus);
 	list_add(&cs->remote_sibling, &remote_children);
+	cpumask_copy(cs->effective_xcpus, tmp->new_cpus);
 	spin_unlock_irq(&callback_lock);
 	update_unbound_workqueue_cpumask(isolcpus_updated);
+	cpuset_force_rebuild();
+	cs->prs_err = 0;
 
 	/*
 	 * Propagate changes in top_cpuset's effective_cpus down the hierarchy.
@@ -1428,20 +1479,24 @@ static void remote_partition_disable(struct cpuset *cs, struct tmpmasks *tmp)
 {
 	bool isolcpus_updated;
 
-	compute_effective_exclusive_cpumask(cs, tmp->new_cpus);
 	WARN_ON_ONCE(!is_remote_partition(cs));
-	WARN_ON_ONCE(!cpumask_subset(tmp->new_cpus, subpartitions_cpus));
+	WARN_ON_ONCE(!cpumask_subset(cs->effective_xcpus, subpartitions_cpus));
 
 	spin_lock_irq(&callback_lock);
 	list_del_init(&cs->remote_sibling);
 	isolcpus_updated = partition_xcpus_del(cs->partition_root_state,
-					       NULL, tmp->new_cpus);
-	cs->partition_root_state = -cs->partition_root_state;
-	if (!cs->prs_err)
-		cs->prs_err = PERR_INVCPUS;
+					       NULL, cs->effective_xcpus);
+	if (cs->prs_err)
+		cs->partition_root_state = -cs->partition_root_state;
+	else
+		cs->partition_root_state = PRS_MEMBER;
+
+	/* effective_xcpus may need to be changed */
+	compute_effective_exclusive_cpumask(cs, NULL, NULL);
 	reset_partition_data(cs);
 	spin_unlock_irq(&callback_lock);
 	update_unbound_workqueue_cpumask(isolcpus_updated);
+	cpuset_force_rebuild();
 
 	/*
 	 * Propagate changes in top_cpuset's effective_cpus down the hierarchy.
@@ -1453,14 +1508,15 @@ static void remote_partition_disable(struct cpuset *cs, struct tmpmasks *tmp)
 /*
  * remote_cpus_update - cpus_exclusive change of remote partition
  * @cs: the cpuset to be updated
- * @newmask: the new effective_xcpus mask
+ * @xcpus: the new exclusive_cpus mask, if non-NULL
+ * @excpus: the new effective_xcpus mask
  * @tmp: temporary masks
  *
  * top_cpuset and subpartitions_cpus will be updated or partition can be
  * invalidated.
  */
-static void remote_cpus_update(struct cpuset *cs, struct cpumask *newmask,
-			       struct tmpmasks *tmp)
+static void remote_cpus_update(struct cpuset *cs, struct cpumask *xcpus,
+			       struct cpumask *excpus, struct tmpmasks *tmp)
 {
 	bool adding, deleting;
 	int prs = cs->partition_root_state;
@@ -1471,29 +1527,45 @@ static void remote_cpus_update(struct cpuset *cs, struct cpumask *newmask,
 
 	WARN_ON_ONCE(!cpumask_subset(cs->effective_xcpus, subpartitions_cpus));
 
-	if (cpumask_empty(newmask))
+	if (cpumask_empty(excpus)) {
+		cs->prs_err = PERR_CPUSEMPTY;
 		goto invalidate;
+	}
 
-	adding   = cpumask_andnot(tmp->addmask, newmask, cs->effective_xcpus);
-	deleting = cpumask_andnot(tmp->delmask, cs->effective_xcpus, newmask);
+	adding   = cpumask_andnot(tmp->addmask, excpus, cs->effective_xcpus);
+	deleting = cpumask_andnot(tmp->delmask, cs->effective_xcpus, excpus);
 
 	/*
 	 * Additions of remote CPUs is only allowed if those CPUs are
 	 * not allocated to other partitions and there are effective_cpus
 	 * left in the top cpuset.
 	 */
-	if (adding && (!capable(CAP_SYS_ADMIN) ||
-		       cpumask_intersects(tmp->addmask, subpartitions_cpus) ||
-		       cpumask_subset(top_cpuset.effective_cpus, tmp->addmask)))
-		goto invalidate;
+	if (adding) {
+		if (!capable(CAP_SYS_ADMIN))
+			cs->prs_err = PERR_ACCESS;
+		else if (cpumask_intersects(tmp->addmask, subpartitions_cpus) ||
+			 cpumask_subset(top_cpuset.effective_cpus, tmp->addmask))
+			cs->prs_err = PERR_NOCPUS;
+		if (cs->prs_err)
+			goto invalidate;
+	}
 
 	spin_lock_irq(&callback_lock);
 	if (adding)
 		isolcpus_updated += partition_xcpus_add(prs, NULL, tmp->addmask);
 	if (deleting)
 		isolcpus_updated += partition_xcpus_del(prs, NULL, tmp->delmask);
+	/*
+	 * Need to update effective_xcpus and exclusive_cpus now as
+	 * update_sibling_cpumasks() below may iterate back to the same cs.
+	 */
+	cpumask_copy(cs->effective_xcpus, excpus);
+	if (xcpus)
+		cpumask_copy(cs->exclusive_cpus, xcpus);
 	spin_unlock_irq(&callback_lock);
 	update_unbound_workqueue_cpumask(isolcpus_updated);
+	if (adding || deleting)
+		cpuset_force_rebuild();
 
 	/*
 	 * Propagate changes in top_cpuset's effective_cpus down the hierarchy.
@@ -1507,47 +1579,6 @@ invalidate:
 }
 
 /*
- * remote_partition_check - check if a child remote partition needs update
- * @cs: the cpuset to be updated
- * @newmask: the new effective_xcpus mask
- * @delmask: temporary mask for deletion (not in tmp)
- * @tmp: temporary masks
- *
- * This should be called before the given cs has updated its cpus_allowed
- * and/or effective_xcpus.
- */
-static void remote_partition_check(struct cpuset *cs, struct cpumask *newmask,
-				   struct cpumask *delmask, struct tmpmasks *tmp)
-{
-	struct cpuset *child, *next;
-	int disable_cnt = 0;
-
-	/*
-	 * Compute the effective exclusive CPUs that will be deleted.
-	 */
-	if (!cpumask_andnot(delmask, cs->effective_xcpus, newmask) ||
-	    !cpumask_intersects(delmask, subpartitions_cpus))
-		return;	/* No deletion of exclusive CPUs in partitions */
-
-	/*
-	 * Searching the remote children list to look for those that will
-	 * be impacted by the deletion of exclusive CPUs.
-	 *
-	 * Since a cpuset must be removed from the remote children list
-	 * before it can go offline and holding cpuset_mutex will prevent
-	 * any change in cpuset status. RCU read lock isn't needed.
-	 */
-	lockdep_assert_held(&cpuset_mutex);
-	list_for_each_entry_safe(child, next, &remote_children, remote_sibling)
-		if (cpumask_intersects(child->effective_cpus, delmask)) {
-			remote_partition_disable(child, tmp);
-			disable_cnt++;
-		}
-	if (disable_cnt)
-		cpuset_force_rebuild();
-}
-
-/*
  * prstate_housekeeping_conflict - check for partition & housekeeping conflicts
  * @prstate: partition root state to be checked
  * @new_cpus: cpu mask
@@ -1601,7 +1632,7 @@ static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus)
  * The partcmd_update command is used by update_cpumasks_hier() with newmask
  * NULL and update_cpumask() with newmask set. The partcmd_invalidate is used
  * by update_cpumask() with NULL newmask. In both cases, the callers won't
- * check for error and so partition_root_state and prs_error will be updated
+ * check for error and so partition_root_state and prs_err will be updated
  * directly.
  */
 static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
@@ -1614,11 +1645,12 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 	int old_prs, new_prs;
 	int part_error = PERR_NONE;	/* Partition error? */
 	int subparts_delta = 0;
-	struct cpumask *xcpus;		/* cs effective_xcpus */
 	int isolcpus_updated = 0;
+	struct cpumask *xcpus = user_xcpus(cs);
 	bool nocpu;
 
 	lockdep_assert_held(&cpuset_mutex);
+	WARN_ON_ONCE(is_remote_partition(cs));
 
 	/*
 	 * new_prs will only be changed for the partcmd_update and
@@ -1626,7 +1658,6 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 	 */
 	adding = deleting = false;
 	old_prs = new_prs = cs->partition_root_state;
-	xcpus = user_xcpus(cs);
 
 	if (cmd == partcmd_invalidate) {
 		if (is_prs_invalid(old_prs))
@@ -1661,12 +1692,19 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 
 	if ((cmd == partcmd_enable) || (cmd == partcmd_enablei)) {
 		/*
+		 * Need to call compute_effective_exclusive_cpumask() in case
+		 * exclusive_cpus not set. Sibling conflict should only happen
+		 * if exclusive_cpus isn't set.
+		 */
+		xcpus = tmp->new_cpus;
+		if (compute_effective_exclusive_cpumask(cs, xcpus, NULL))
+			WARN_ON_ONCE(!cpumask_empty(cs->exclusive_cpus));
+
+		/*
 		 * Enabling partition root is not allowed if its
-		 * effective_xcpus is empty or doesn't overlap with
-		 * parent's effective_xcpus.
+		 * effective_xcpus is empty.
 		 */
-		if (cpumask_empty(xcpus) ||
-		    !cpumask_intersects(xcpus, parent->effective_xcpus))
+		if (cpumask_empty(xcpus))
 			return PERR_INVCPUS;
 
 		if (prstate_housekeeping_conflict(new_prs, xcpus))
@@ -1679,19 +1717,22 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 		if (nocpu)
 			return PERR_NOCPUS;
 
-		cpumask_copy(tmp->delmask, xcpus);
-		deleting = true;
-		subparts_delta++;
+		deleting = cpumask_and(tmp->delmask, xcpus, parent->effective_xcpus);
+		if (deleting)
+			subparts_delta++;
 		new_prs = (cmd == partcmd_enable) ? PRS_ROOT : PRS_ISOLATED;
 	} else if (cmd == partcmd_disable) {
 		/*
-		 * May need to add cpus to parent's effective_cpus for
-		 * valid partition root.
+		 * May need to add cpus back to parent's effective_cpus
+		 * (and maybe removed from subpartitions_cpus/isolated_cpus)
+		 * for valid partition root. xcpus may contain CPUs that
+		 * shouldn't be removed from the two global cpumasks.
 		 */
-		adding = !is_prs_invalid(old_prs) &&
-			  cpumask_and(tmp->addmask, xcpus, parent->effective_xcpus);
-		if (adding)
+		if (is_partition_valid(cs)) {
+			cpumask_copy(tmp->addmask, cs->effective_xcpus);
+			adding = true;
 			subparts_delta--;
+		}
 		new_prs = PRS_MEMBER;
 	} else if (newmask) {
 		/*
@@ -1701,6 +1742,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 			part_error = PERR_CPUSEMPTY;
 			goto write_error;
 		}
+
 		/* Check newmask again, whether cpus are available for parent/cs */
 		nocpu |= tasks_nocpu_error(parent, cs, newmask);
 
@@ -1829,7 +1871,7 @@ write_error:
 	 * CPU lists in cs haven't been updated yet. So defer it to later.
 	 */
 	if ((old_prs != new_prs) && (cmd != partcmd_update))  {
-		int err = update_partition_exclusive(cs, new_prs);
+		int err = update_partition_exclusive_flag(cs, new_prs);
 
 		if (err)
 			return err;
@@ -1867,7 +1909,7 @@ write_error:
 	update_unbound_workqueue_cpumask(isolcpus_updated);
 
 	if ((old_prs != new_prs) && (cmd == partcmd_update))
-		update_partition_exclusive(cs, new_prs);
+		update_partition_exclusive_flag(cs, new_prs);
 
 	if (adding || deleting) {
 		cpuset_update_tasks_cpumask(parent, tmp->addmask);
@@ -1917,7 +1959,7 @@ static void compute_partition_effective_cpumask(struct cpuset *cs,
 	 *  2) All the effective_cpus will be used up and cp
 	 *     has tasks
 	 */
-	compute_effective_exclusive_cpumask(cs, new_ecpus);
+	compute_effective_exclusive_cpumask(cs, new_ecpus, NULL);
 	cpumask_and(new_ecpus, new_ecpus, cpu_active_mask);
 
 	rcu_read_lock();
@@ -1925,6 +1967,11 @@ static void compute_partition_effective_cpumask(struct cpuset *cs,
 		if (!is_partition_valid(child))
 			continue;
 
+		/*
+		 * There shouldn't be a remote partition underneath another
+		 * partition root.
+		 */
+		WARN_ON_ONCE(is_remote_partition(child));
 		child->prs_err = 0;
 		if (!cpumask_subset(child->effective_xcpus,
 				    cs->effective_xcpus))
@@ -1980,32 +2027,39 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp,
 		bool remote = is_remote_partition(cp);
 		bool update_parent = false;
 
+		old_prs = new_prs = cp->partition_root_state;
+
 		/*
-		 * Skip descendent remote partition that acquires CPUs
-		 * directly from top cpuset unless it is cs.
+		 * For child remote partition root (!= cs), we need to call
+		 * remote_cpus_update() if effective_xcpus will be changed.
+		 * Otherwise, we can skip the whole subtree.
+		 *
+		 * remote_cpus_update() will reuse tmp->new_cpus only after
+		 * its value is being processed.
 		 */
 		if (remote && (cp != cs)) {
-			pos_css = css_rightmost_descendant(pos_css);
-			continue;
-		}
+			compute_effective_exclusive_cpumask(cp, tmp->new_cpus, NULL);
+			if (cpumask_equal(cp->effective_xcpus, tmp->new_cpus)) {
+				pos_css = css_rightmost_descendant(pos_css);
+				continue;
+			}
+			rcu_read_unlock();
+			remote_cpus_update(cp, NULL, tmp->new_cpus, tmp);
+			rcu_read_lock();
 
-		/*
-		 * Update effective_xcpus if exclusive_cpus set.
-		 * The case when exclusive_cpus isn't set is handled later.
-		 */
-		if (!cpumask_empty(cp->exclusive_cpus) && (cp != cs)) {
-			spin_lock_irq(&callback_lock);
-			compute_effective_exclusive_cpumask(cp, NULL);
-			spin_unlock_irq(&callback_lock);
+			/* Remote partition may be invalidated */
+			new_prs = cp->partition_root_state;
+			remote = (new_prs == old_prs);
 		}
 
-		old_prs = new_prs = cp->partition_root_state;
-		if (remote || (is_partition_valid(parent) &&
-			       is_partition_valid(cp)))
+		if (remote || (is_partition_valid(parent) && is_partition_valid(cp)))
 			compute_partition_effective_cpumask(cp, tmp->new_cpus);
 		else
 			compute_effective_cpumask(tmp->new_cpus, cp, parent);
 
+		if (remote)
+			goto get_css;	/* Ready to update cpuset data */
+
 		/*
 		 * A partition with no effective_cpus is allowed as long as
 		 * there is no task associated with it. Call
@@ -2025,9 +2079,6 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp,
 		if (is_in_v2_mode() && !remote && cpumask_empty(tmp->new_cpus))
 			cpumask_copy(tmp->new_cpus, parent->effective_cpus);
 
-		if (remote)
-			goto get_css;
-
 		/*
 		 * Skip the whole subtree if
 		 * 1) the cpumask remains the same,
@@ -2088,6 +2139,9 @@ get_css:
 		spin_lock_irq(&callback_lock);
 		cpumask_copy(cp->effective_cpus, tmp->new_cpus);
 		cp->partition_root_state = new_prs;
+		if (!cpumask_empty(cp->exclusive_cpus) && (cp != cs))
+			compute_effective_exclusive_cpumask(cp, NULL, NULL);
+
 		/*
 		 * Make sure effective_xcpus is properly set for a valid
 		 * partition root.
@@ -2174,7 +2228,14 @@ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs,
 						  parent);
 			if (cpumask_equal(tmp->new_cpus, sibling->effective_cpus))
 				continue;
+		} else if (is_remote_partition(sibling)) {
+			/*
+			 * Change in a sibling cpuset won't affect a remote
+			 * partition root.
+			 */
+			continue;
 		}
+
 		if (!css_tryget_online(&sibling->css))
 			continue;
 
@@ -2231,8 +2292,9 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 		 * trialcs->effective_xcpus is used as a temporary cpumask
 		 * for checking validity of the partition root.
 		 */
+		trialcs->partition_root_state = PRS_MEMBER;
 		if (!cpumask_empty(trialcs->exclusive_cpus) || is_partition_valid(cs))
-			compute_effective_exclusive_cpumask(trialcs, NULL);
+			compute_effective_exclusive_cpumask(trialcs, NULL, cs);
 	}
 
 	/* Nothing to do if the cpus didn't change */
@@ -2305,19 +2367,13 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 		 * Call remote_cpus_update() to handle valid remote partition
 		 */
 		if (is_remote_partition(cs))
-			remote_cpus_update(cs, xcpus, &tmp);
+			remote_cpus_update(cs, NULL, xcpus, &tmp);
 		else if (invalidate)
 			update_parent_effective_cpumask(cs, partcmd_invalidate,
 							NULL, &tmp);
 		else
 			update_parent_effective_cpumask(cs, partcmd_update,
 							xcpus, &tmp);
-	} else if (!cpumask_empty(cs->exclusive_cpus)) {
-		/*
-		 * Use trialcs->effective_cpus as a temp cpumask
-		 */
-		remote_partition_check(cs, trialcs->effective_xcpus,
-				       trialcs->effective_cpus, &tmp);
 	}
 
 	spin_lock_irq(&callback_lock);
@@ -2369,8 +2425,15 @@ static int update_exclusive_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 	if (cpumask_equal(cs->exclusive_cpus, trialcs->exclusive_cpus))
 		return 0;
 
-	if (*buf)
-		compute_effective_exclusive_cpumask(trialcs, NULL);
+	if (*buf) {
+		trialcs->partition_root_state = PRS_MEMBER;
+		/*
+		 * Reject the change if there is exclusive CPUs conflict with
+		 * the siblings.
+		 */
+		if (compute_effective_exclusive_cpumask(trialcs, NULL, cs))
+			return -EINVAL;
+	}
 
 	/*
 	 * Check all the descendants in update_cpumasks_hier() if
@@ -2401,8 +2464,8 @@ static int update_exclusive_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 			if (invalidate)
 				remote_partition_disable(cs, &tmp);
 			else
-				remote_cpus_update(cs, trialcs->effective_xcpus,
-						   &tmp);
+				remote_cpus_update(cs, trialcs->exclusive_cpus,
+						   trialcs->effective_xcpus, &tmp);
 		} else if (invalidate) {
 			update_parent_effective_cpumask(cs, partcmd_invalidate,
 							NULL, &tmp);
@@ -2410,12 +2473,6 @@ static int update_exclusive_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 			update_parent_effective_cpumask(cs, partcmd_update,
 						trialcs->effective_xcpus, &tmp);
 		}
-	} else if (!cpumask_empty(trialcs->exclusive_cpus)) {
-		/*
-		 * Use trialcs->effective_cpus as a temp cpumask
-		 */
-		remote_partition_check(cs, trialcs->effective_xcpus,
-				       trialcs->effective_cpus, &tmp);
 	}
 	spin_lock_irq(&callback_lock);
 	cpumask_copy(cs->exclusive_cpus, trialcs->exclusive_cpus);
@@ -2782,7 +2839,7 @@ static int update_prstate(struct cpuset *cs, int new_prs)
 	int err = PERR_NONE, old_prs = cs->partition_root_state;
 	struct cpuset *parent = parent_cs(cs);
 	struct tmpmasks tmpmask;
-	bool new_xcpus_state = false;
+	bool isolcpus_updated = false;
 
 	if (old_prs == new_prs)
 		return 0;
@@ -2796,18 +2853,7 @@ static int update_prstate(struct cpuset *cs, int new_prs)
 	if (alloc_cpumasks(NULL, &tmpmask))
 		return -ENOMEM;
 
-	/*
-	 * Setup effective_xcpus if not properly set yet, it will be cleared
-	 * later if partition becomes invalid.
-	 */
-	if ((new_prs > 0) && cpumask_empty(cs->exclusive_cpus)) {
-		spin_lock_irq(&callback_lock);
-		cpumask_and(cs->effective_xcpus,
-			    cs->cpus_allowed, parent->effective_xcpus);
-		spin_unlock_irq(&callback_lock);
-	}
-
-	err = update_partition_exclusive(cs, new_prs);
+	err = update_partition_exclusive_flag(cs, new_prs);
 	if (err)
 		goto out;
 
@@ -2821,6 +2867,19 @@ static int update_prstate(struct cpuset *cs, int new_prs)
 		}
 
 		/*
+		 * We don't support the creation of a new local partition with
+		 * a remote partition underneath it. This unsupported
+		 * setting can happen only if parent is the top_cpuset because
+		 * a remote partition cannot be created underneath an existing
+		 * local or remote partition.
+		 */
+		if ((parent == &top_cpuset) &&
+		    cpumask_intersects(cs->exclusive_cpus, subpartitions_cpus)) {
+			err = PERR_REMOTE;
+			goto out;
+		}
+
+		/*
 		 * If parent is valid partition, enable local partiion.
 		 * Otherwise, enable a remote partition.
 		 */
@@ -2835,8 +2894,9 @@ static int update_prstate(struct cpuset *cs, int new_prs)
 	} else if (old_prs && new_prs) {
 		/*
 		 * A change in load balance state only, no change in cpumasks.
+		 * Need to update isolated_cpus.
 		 */
-		new_xcpus_state = true;
+		isolcpus_updated = true;
 	} else {
 		/*
 		 * Switching back to member is always allowed even if it
@@ -2860,7 +2920,7 @@ out:
 	 */
 	if (err) {
 		new_prs = -new_prs;
-		update_partition_exclusive(cs, new_prs);
+		update_partition_exclusive_flag(cs, new_prs);
 	}
 
 	spin_lock_irq(&callback_lock);
@@ -2868,14 +2928,18 @@ out:
 	WRITE_ONCE(cs->prs_err, err);
 	if (!is_partition_valid(cs))
 		reset_partition_data(cs);
-	else if (new_xcpus_state)
-		partition_xcpus_newstate(old_prs, new_prs, cs->effective_xcpus);
+	else if (isolcpus_updated)
+		isolated_cpus_update(old_prs, new_prs, cs->effective_xcpus);
 	spin_unlock_irq(&callback_lock);
-	update_unbound_workqueue_cpumask(new_xcpus_state);
+	update_unbound_workqueue_cpumask(isolcpus_updated);
 
-	/* Force update if switching back to member */
+	/* Force update if switching back to member & update effective_xcpus */
 	update_cpumasks_hier(cs, &tmpmask, !new_prs);
 
+	/* A newly created partition must have effective_xcpus set */
+	WARN_ON_ONCE(!old_prs && (new_prs > 0)
+			      && cpumask_empty(cs->effective_xcpus));
+
 	/* Update sched domains and load balance flag */
 	update_partition_sd_lb(cs, old_prs);
 
@@ -3208,7 +3272,7 @@ int cpuset_common_seq_show(struct seq_file *sf, void *v)
 	return ret;
 }
 
-static int sched_partition_show(struct seq_file *seq, void *v)
+static int cpuset_partition_show(struct seq_file *seq, void *v)
 {
 	struct cpuset *cs = css_cs(seq_css(seq));
 	const char *err, *type = NULL;
@@ -3239,7 +3303,7 @@ static int sched_partition_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf,
+static ssize_t cpuset_partition_write(struct kernfs_open_file *of, char *buf,
 				     size_t nbytes, loff_t off)
 {
 	struct cpuset *cs = css_cs(of_css(of));
@@ -3260,11 +3324,8 @@ static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf,
 	css_get(&cs->css);
 	cpus_read_lock();
 	mutex_lock(&cpuset_mutex);
-	if (!is_cpuset_online(cs))
-		goto out_unlock;
-
-	retval = update_prstate(cs, val);
-out_unlock:
+	if (is_cpuset_online(cs))
+		retval = update_prstate(cs, val);
 	mutex_unlock(&cpuset_mutex);
 	cpus_read_unlock();
 	css_put(&cs->css);
@@ -3308,8 +3369,8 @@ static struct cftype dfl_files[] = {
 
 	{
 		.name = "cpus.partition",
-		.seq_show = sched_partition_show,
-		.write = sched_partition_write,
+		.seq_show = cpuset_partition_show,
+		.write = cpuset_partition_write,
 		.private = FILE_PARTITION_ROOT,
 		.flags = CFTYPE_NOT_ON_ROOT,
 		.file_offset = offsetof(struct cpuset, partition_file),
@@ -3475,9 +3536,6 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css)
 	cpus_read_lock();
 	mutex_lock(&cpuset_mutex);
 
-	if (is_partition_valid(cs))
-		update_prstate(cs, 0);
-
 	if (!cpuset_v2() && is_sched_load_balance(cs))
 		cpuset_update_flag(CS_SCHED_LOAD_BALANCE, cs, 0);
 
@@ -3488,6 +3546,22 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css)
 	cpus_read_unlock();
 }
 
+static void cpuset_css_killed(struct cgroup_subsys_state *css)
+{
+	struct cpuset *cs = css_cs(css);
+
+	cpus_read_lock();
+	mutex_lock(&cpuset_mutex);
+
+	/* Reset valid partition back to member */
+	if (is_partition_valid(cs))
+		update_prstate(cs, PRS_MEMBER);
+
+	mutex_unlock(&cpuset_mutex);
+	cpus_read_unlock();
+
+}
+
 static void cpuset_css_free(struct cgroup_subsys_state *css)
 {
 	struct cpuset *cs = css_cs(css);
@@ -3609,6 +3683,7 @@ struct cgroup_subsys cpuset_cgrp_subsys = {
 	.css_alloc	= cpuset_css_alloc,
 	.css_online	= cpuset_css_online,
 	.css_offline	= cpuset_css_offline,
+	.css_killed	= cpuset_css_killed,
 	.css_free	= cpuset_css_free,
 	.can_attach	= cpuset_can_attach,
 	.cancel_attach	= cpuset_cancel_attach,
@@ -3739,10 +3814,10 @@ retry:
 
 	if (remote && cpumask_empty(&new_cpus) &&
 	    partition_is_populated(cs, NULL)) {
+		cs->prs_err = PERR_HOTPLUG;
 		remote_partition_disable(cs, tmp);
 		compute_effective_cpumask(&new_cpus, cs, parent);
 		remote = false;
-		cpuset_force_rebuild();
 	}
 
 	/*
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index 4bb587d5d34f..b2239156b7de 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -318,10 +318,11 @@ __bpf_kfunc void cgroup_rstat_flush(struct cgroup *cgrp)
 
 	might_sleep();
 	for_each_possible_cpu(cpu) {
-		struct cgroup *pos = cgroup_rstat_updated_list(cgrp, cpu);
+		struct cgroup *pos;
 
 		/* Reacquire for each CPU to avoid disabling IRQs too long */
 		__cgroup_rstat_lock(cgrp, cpu);
+		pos = cgroup_rstat_updated_list(cgrp, cpu);
 		for (; pos; pos = pos->rstat_flush_next) {
 			struct cgroup_subsys_state *css;
 
diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c
index 3b2bdca9f1d4..77c8d9487a9a 100644
--- a/kernel/dma/coherent.c
+++ b/kernel/dma/coherent.c
@@ -336,16 +336,22 @@ static phys_addr_t dma_reserved_default_memory_size __initdata;
 
 static int rmem_dma_device_init(struct reserved_mem *rmem, struct device *dev)
 {
-	if (!rmem->priv) {
-		struct dma_coherent_mem *mem;
+	struct dma_coherent_mem *mem = rmem->priv;
 
+	if (!mem) {
 		mem = dma_init_coherent_memory(rmem->base, rmem->base,
 					       rmem->size, true);
 		if (IS_ERR(mem))
 			return PTR_ERR(mem);
 		rmem->priv = mem;
 	}
-	dma_assign_coherent_memory(dev, rmem->priv);
+
+	/* Warn if the device potentially can't use the reserved memory */
+	if (mem->device_base + rmem->size - 1 >
+	    min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit))
+		dev_warn(dev, "reserved memory is beyond device's set DMA address range\n");
+
+	dma_assign_coherent_memory(dev, mem);
 	return 0;
 }
 
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index 055da410ac71..8df0dfaaca18 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -64,8 +64,7 @@ struct cma *dma_contiguous_default_area;
  * Users, who want to set the size of global CMA area for their system
  * should use cma= kernel parameter.
  */
-static const phys_addr_t size_bytes __initconst =
-	(phys_addr_t)CMA_SIZE_MBYTES * SZ_1M;
+#define size_bytes ((phys_addr_t)CMA_SIZE_MBYTES * SZ_1M)
 static phys_addr_t  size_cmdline __initdata = -1;
 static phys_addr_t base_cmdline __initdata;
 static phys_addr_t limit_cmdline __initdata;
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index cda127027e48..051a32988040 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -910,6 +910,19 @@ int dma_set_coherent_mask(struct device *dev, u64 mask)
 }
 EXPORT_SYMBOL(dma_set_coherent_mask);
 
+static bool __dma_addressing_limited(struct device *dev)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (min_not_zero(dma_get_mask(dev), dev->bus_dma_limit) <
+			 dma_get_required_mask(dev))
+		return true;
+
+	if (unlikely(ops) || use_dma_iommu(dev))
+		return false;
+	return !dma_direct_all_ram_mapped(dev);
+}
+
 /**
  * dma_addressing_limited - return if the device is addressing limited
  * @dev:	device to check
@@ -920,15 +933,11 @@ EXPORT_SYMBOL(dma_set_coherent_mask);
  */
 bool dma_addressing_limited(struct device *dev)
 {
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	if (min_not_zero(dma_get_mask(dev), dev->bus_dma_limit) <
-			 dma_get_required_mask(dev))
-		return true;
-
-	if (unlikely(ops) || use_dma_iommu(dev))
+	if (!__dma_addressing_limited(dev))
 		return false;
-	return !dma_direct_all_ram_mapped(dev);
+
+	dev_dbg(dev, "device is DMA addressing limited\n");
+	return true;
 }
 EXPORT_SYMBOL_GPL(dma_addressing_limited);
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0bb21659e252..95e703891b24 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2451,6 +2451,7 @@ ctx_time_update_event(struct perf_event_context *ctx, struct perf_event *event)
 #define DETACH_GROUP	0x01UL
 #define DETACH_CHILD	0x02UL
 #define DETACH_DEAD	0x04UL
+#define DETACH_EXIT	0x08UL
 
 /*
  * Cross CPU call to remove a performance event
@@ -2465,6 +2466,7 @@ __perf_remove_from_context(struct perf_event *event,
 			   void *info)
 {
 	struct perf_event_pmu_context *pmu_ctx = event->pmu_ctx;
+	enum perf_event_state state = PERF_EVENT_STATE_OFF;
 	unsigned long flags = (unsigned long)info;
 
 	ctx_time_update(cpuctx, ctx);
@@ -2473,16 +2475,19 @@ __perf_remove_from_context(struct perf_event *event,
 	 * Ensure event_sched_out() switches to OFF, at the very least
 	 * this avoids raising perf_pending_task() at this time.
 	 */
-	if (flags & DETACH_DEAD)
+	if (flags & DETACH_EXIT)
+		state = PERF_EVENT_STATE_EXIT;
+	if (flags & DETACH_DEAD) {
 		event->pending_disable = 1;
+		state = PERF_EVENT_STATE_DEAD;
+	}
 	event_sched_out(event, ctx);
+	perf_event_set_state(event, min(event->state, state));
 	if (flags & DETACH_GROUP)
 		perf_group_detach(event);
 	if (flags & DETACH_CHILD)
 		perf_child_detach(event);
 	list_del_event(event, ctx);
-	if (flags & DETACH_DEAD)
-		event->state = PERF_EVENT_STATE_DEAD;
 
 	if (!pmu_ctx->nr_events) {
 		pmu_ctx->rotate_necessary = 0;
@@ -3938,7 +3943,7 @@ static int merge_sched_in(struct perf_event *event, void *data)
 			perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
 
 			if (*perf_event_fasync(event))
-				event->pending_kill = POLL_HUP;
+				event->pending_kill = POLL_ERR;
 
 			perf_event_wakeup(event);
 		} else {
@@ -5513,30 +5518,6 @@ static bool exclusive_event_installable(struct perf_event *event,
 
 static void perf_free_addr_filters(struct perf_event *event);
 
-static void perf_pending_task_sync(struct perf_event *event)
-{
-	struct callback_head *head = &event->pending_task;
-
-	if (!event->pending_work)
-		return;
-	/*
-	 * If the task is queued to the current task's queue, we
-	 * obviously can't wait for it to complete. Simply cancel it.
-	 */
-	if (task_work_cancel(current, head)) {
-		event->pending_work = 0;
-		local_dec(&event->ctx->nr_no_switch_fast);
-		return;
-	}
-
-	/*
-	 * All accesses related to the event are within the same RCU section in
-	 * perf_pending_task(). The RCU grace period before the event is freed
-	 * will make sure all those accesses are complete by then.
-	 */
-	rcuwait_wait_event(&event->pending_work_wait, !event->pending_work, TASK_UNINTERRUPTIBLE);
-}
-
 /* vs perf_event_alloc() error */
 static void __free_event(struct perf_event *event)
 {
@@ -5594,7 +5575,6 @@ static void _free_event(struct perf_event *event)
 {
 	irq_work_sync(&event->pending_irq);
 	irq_work_sync(&event->pending_disable_irq);
-	perf_pending_task_sync(event);
 
 	unaccount_event(event);
 
@@ -5687,10 +5667,17 @@ static void perf_remove_from_owner(struct perf_event *event)
 
 static void put_event(struct perf_event *event)
 {
+	struct perf_event *parent;
+
 	if (!atomic_long_dec_and_test(&event->refcount))
 		return;
 
+	parent = event->parent;
 	_free_event(event);
+
+	/* Matches the refcount bump in inherit_event() */
+	if (parent)
+		put_event(parent);
 }
 
 /*
@@ -5774,11 +5761,6 @@ again:
 		if (tmp == child) {
 			perf_remove_from_context(child, DETACH_GROUP);
 			list_move(&child->child_list, &free_list);
-			/*
-			 * This matches the refcount bump in inherit_event();
-			 * this can't be the last reference.
-			 */
-			put_event(event);
 		} else {
 			var = &ctx->refcount;
 		}
@@ -5804,7 +5786,8 @@ again:
 		void *var = &child->ctx->refcount;
 
 		list_del(&child->child_list);
-		free_event(child);
+		/* Last reference unless ->pending_task work is pending */
+		put_event(child);
 
 		/*
 		 * Wake any perf_event_free_task() waiting for this event to be
@@ -5815,7 +5798,11 @@ again:
 	}
 
 no_ctx:
-	put_event(event); /* Must be the 'last' reference */
+	/*
+	 * Last reference unless ->pending_task work is pending on this event
+	 * or any of its children.
+	 */
+	put_event(event);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(perf_event_release_kernel);
@@ -6088,7 +6075,7 @@ static __poll_t perf_poll(struct file *file, poll_table *wait)
 
 	if (unlikely(READ_ONCE(event->state) == PERF_EVENT_STATE_ERROR &&
 		     event->attr.pinned))
-		return events;
+		return EPOLLERR;
 
 	/*
 	 * Pin the event->rb by taking event->mmap_mutex; otherwise
@@ -7231,12 +7218,6 @@ static void perf_pending_task(struct callback_head *head)
 	int rctx;
 
 	/*
-	 * All accesses to the event must belong to the same implicit RCU read-side
-	 * critical section as the ->pending_work reset. See comment in
-	 * perf_pending_task_sync().
-	 */
-	rcu_read_lock();
-	/*
 	 * If we 'fail' here, that's OK, it means recursion is already disabled
 	 * and we won't recurse 'further'.
 	 */
@@ -7246,9 +7227,8 @@ static void perf_pending_task(struct callback_head *head)
 		event->pending_work = 0;
 		perf_sigtrap(event);
 		local_dec(&event->ctx->nr_no_switch_fast);
-		rcuwait_wake_up(&event->pending_work_wait);
 	}
-	rcu_read_unlock();
+	put_event(event);
 
 	if (rctx >= 0)
 		perf_swevent_put_recursion_context(rctx);
@@ -10243,6 +10223,7 @@ static int __perf_event_overflow(struct perf_event *event,
 		    !task_work_add(current, &event->pending_task, notify_mode)) {
 			event->pending_work = pending_id;
 			local_inc(&event->ctx->nr_no_switch_fast);
+			WARN_ON_ONCE(!atomic_long_inc_not_zero(&event->refcount));
 
 			event->pending_addr = 0;
 			if (valid_sample && (data->sample_flags & PERF_SAMPLE_ADDR))
@@ -12605,7 +12586,6 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	init_irq_work(&event->pending_irq, perf_pending_irq);
 	event->pending_disable_irq = IRQ_WORK_INIT_HARD(perf_pending_disable);
 	init_task_work(&event->pending_task, perf_pending_task);
-	rcuwait_init(&event->pending_work_wait);
 
 	mutex_init(&event->mmap_mutex);
 	raw_spin_lock_init(&event->addr_filters.lock);
@@ -13731,12 +13711,7 @@ perf_event_exit_event(struct perf_event *event, struct perf_event_context *ctx)
 		mutex_lock(&parent_event->child_mutex);
 	}
 
-	perf_remove_from_context(event, detach_flags);
-
-	raw_spin_lock_irq(&ctx->lock);
-	if (event->state > PERF_EVENT_STATE_EXIT)
-		perf_event_set_state(event, PERF_EVENT_STATE_EXIT);
-	raw_spin_unlock_irq(&ctx->lock);
+	perf_remove_from_context(event, detach_flags | DETACH_EXIT);
 
 	/*
 	 * Child events can be freed.
@@ -13747,8 +13722,7 @@ perf_event_exit_event(struct perf_event *event, struct perf_event_context *ctx)
 		 * Kick perf_poll() for is_event_hup();
 		 */
 		perf_event_wakeup(parent_event);
-		free_event(event);
-		put_event(parent_event);
+		put_event(event);
 		return;
 	}
 
@@ -13872,13 +13846,11 @@ static void perf_free_event(struct perf_event *event,
 	list_del_init(&event->child_list);
 	mutex_unlock(&parent->child_mutex);
 
-	put_event(parent);
-
 	raw_spin_lock_irq(&ctx->lock);
 	perf_group_detach(event);
 	list_del_event(event, ctx);
 	raw_spin_unlock_irq(&ctx->lock);
-	free_event(event);
+	put_event(event);
 }
 
 /*
@@ -14016,6 +13988,9 @@ inherit_event(struct perf_event *parent_event,
 	if (IS_ERR(child_event))
 		return child_event;
 
+	get_ctx(child_ctx);
+	child_event->ctx = child_ctx;
+
 	pmu_ctx = find_get_pmu_context(child_event->pmu, child_ctx, child_event);
 	if (IS_ERR(pmu_ctx)) {
 		free_event(child_event);
@@ -14037,8 +14012,6 @@ inherit_event(struct perf_event *parent_event,
 		return NULL;
 	}
 
-	get_ctx(child_ctx);
-
 	/*
 	 * Make the child state follow the state of the parent event,
 	 * not its attr.disabled bit.  We hold the parent's mutex,
@@ -14059,7 +14032,6 @@ inherit_event(struct perf_event *parent_event,
 		local64_set(&hwc->period_left, sample_period);
 	}
 
-	child_event->ctx = child_ctx;
 	child_event->overflow_handler = parent_event->overflow_handler;
 	child_event->overflow_handler_context
 		= parent_event->overflow_handler_context;
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 615b4e6d22c7..8d783b5882b6 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1956,6 +1956,9 @@ static void free_ret_instance(struct uprobe_task *utask,
 	 * to-be-reused return instances for future uretprobes. If ri_timer()
 	 * happens to be running right now, though, we fallback to safety and
 	 * just perform RCU-delated freeing of ri.
+	 * Admittedly, this is a rather simple use of seqcount, but it nicely
+	 * abstracts away all the necessary memory barriers, so we use
+	 * a well-supported kernel primitive here.
 	 */
 	if (raw_seqcount_try_begin(&utask->ri_seqcount, seq)) {
 		/* immediate reuse of ri without RCU GP is OK */
@@ -2016,12 +2019,20 @@ static void ri_timer(struct timer_list *timer)
 	/* RCU protects return_instance from freeing. */
 	guard(rcu)();
 
-	write_seqcount_begin(&utask->ri_seqcount);
+	/*
+	 * See free_ret_instance() for notes on seqcount use.
+	 * We also employ raw API variants to avoid lockdep false-positive
+	 * warning complaining about enabled preemption. The timer can only be
+	 * invoked once for a uprobe_task. Therefore there can only be one
+	 * writer. The reader does not require an even sequence count to make
+	 * progress, so it is OK to remain preemptible on PREEMPT_RT.
+	 */
+	raw_write_seqcount_begin(&utask->ri_seqcount);
 
 	for_each_ret_instance_rcu(ri, utask->return_instances)
 		hprobe_expire(&ri->hprobe, false);
 
-	write_seqcount_end(&utask->ri_seqcount);
+	raw_write_seqcount_end(&utask->ri_seqcount);
 }
 
 static struct uprobe_task *alloc_utask(void)
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 1a19d69b91ed..816f07f9d30f 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -81,9 +81,23 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
 	if (!cpufreq_this_cpu_can_update(sg_policy->policy))
 		return false;
 
-	if (unlikely(sg_policy->limits_changed)) {
-		sg_policy->limits_changed = false;
-		sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS);
+	if (unlikely(READ_ONCE(sg_policy->limits_changed))) {
+		WRITE_ONCE(sg_policy->limits_changed, false);
+		sg_policy->need_freq_update = true;
+
+		/*
+		 * The above limits_changed update must occur before the reads
+		 * of policy limits in cpufreq_driver_resolve_freq() or a policy
+		 * limits update might be missed, so use a memory barrier to
+		 * ensure it.
+		 *
+		 * This pairs with the write memory barrier in sugov_limits().
+		 */
+		smp_mb();
+
+		return true;
+	} else if (sg_policy->need_freq_update) {
+		/* ignore_dl_rate_limit() wants a new frequency to be found. */
 		return true;
 	}
 
@@ -95,10 +109,22 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
 static bool sugov_update_next_freq(struct sugov_policy *sg_policy, u64 time,
 				   unsigned int next_freq)
 {
-	if (sg_policy->need_freq_update)
+	if (sg_policy->need_freq_update) {
 		sg_policy->need_freq_update = false;
-	else if (sg_policy->next_freq == next_freq)
+		/*
+		 * The policy limits have changed, but if the return value of
+		 * cpufreq_driver_resolve_freq() after applying the new limits
+		 * is still equal to the previously selected frequency, the
+		 * driver callback need not be invoked unless the driver
+		 * specifically wants that to happen on every update of the
+		 * policy limits.
+		 */
+		if (sg_policy->next_freq == next_freq &&
+		    !cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS))
+			return false;
+	} else if (sg_policy->next_freq == next_freq) {
 		return false;
+	}
 
 	sg_policy->next_freq = next_freq;
 	sg_policy->last_freq_update_time = time;
@@ -365,7 +391,7 @@ static inline bool sugov_hold_freq(struct sugov_cpu *sg_cpu) { return false; }
 static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu)
 {
 	if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_min)
-		sg_cpu->sg_policy->limits_changed = true;
+		sg_cpu->sg_policy->need_freq_update = true;
 }
 
 static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu,
@@ -871,7 +897,16 @@ static void sugov_limits(struct cpufreq_policy *policy)
 		mutex_unlock(&sg_policy->work_lock);
 	}
 
-	sg_policy->limits_changed = true;
+	/*
+	 * The limits_changed update below must take place before the updates
+	 * of policy limits in cpufreq_set_policy() or a policy limits update
+	 * might be missed, so use a memory barrier to ensure it.
+	 *
+	 * This pairs with the memory barrier in sugov_should_update_freq().
+	 */
+	smp_wmb();
+
+	WRITE_ONCE(sg_policy->limits_changed, true);
 }
 
 struct cpufreq_governor schedutil_gov = {
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 66bcd40a28ca..fdbf249d1c68 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -163,7 +163,7 @@ enum scx_ops_flags {
 	/*
 	 * CPU cgroup support flags
 	 */
-	SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16,	/* cpu.weight */
+	SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16,	/* DEPRECATED, will be removed on 6.18 */
 
 	SCX_OPS_ALL_FLAGS	= SCX_OPS_KEEP_BUILTIN_IDLE |
 				  SCX_OPS_ENQ_LAST |
@@ -3899,35 +3899,6 @@ bool scx_can_stop_tick(struct rq *rq)
 
 DEFINE_STATIC_PERCPU_RWSEM(scx_cgroup_rwsem);
 static bool scx_cgroup_enabled;
-static bool cgroup_warned_missing_weight;
-static bool cgroup_warned_missing_idle;
-
-static void scx_cgroup_warn_missing_weight(struct task_group *tg)
-{
-	if (scx_ops_enable_state() == SCX_OPS_DISABLED ||
-	    cgroup_warned_missing_weight)
-		return;
-
-	if ((scx_ops.flags & SCX_OPS_HAS_CGROUP_WEIGHT) || !tg->css.parent)
-		return;
-
-	pr_warn("sched_ext: \"%s\" does not implement cgroup cpu.weight\n",
-		scx_ops.name);
-	cgroup_warned_missing_weight = true;
-}
-
-static void scx_cgroup_warn_missing_idle(struct task_group *tg)
-{
-	if (!scx_cgroup_enabled || cgroup_warned_missing_idle)
-		return;
-
-	if (!tg->idle)
-		return;
-
-	pr_warn("sched_ext: \"%s\" does not implement cgroup cpu.idle\n",
-		scx_ops.name);
-	cgroup_warned_missing_idle = true;
-}
 
 int scx_tg_online(struct task_group *tg)
 {
@@ -3937,8 +3908,6 @@ int scx_tg_online(struct task_group *tg)
 
 	percpu_down_read(&scx_cgroup_rwsem);
 
-	scx_cgroup_warn_missing_weight(tg);
-
 	if (scx_cgroup_enabled) {
 		if (SCX_HAS_OP(cgroup_init)) {
 			struct scx_cgroup_init_args args =
@@ -4076,9 +4045,7 @@ void scx_group_set_weight(struct task_group *tg, unsigned long weight)
 
 void scx_group_set_idle(struct task_group *tg, bool idle)
 {
-	percpu_down_read(&scx_cgroup_rwsem);
-	scx_cgroup_warn_missing_idle(tg);
-	percpu_up_read(&scx_cgroup_rwsem);
+	/* TODO: Implement ops->cgroup_set_idle() */
 }
 
 static void scx_cgroup_lock(void)
@@ -4272,9 +4239,6 @@ static int scx_cgroup_init(void)
 
 	percpu_rwsem_assert_held(&scx_cgroup_rwsem);
 
-	cgroup_warned_missing_weight = false;
-	cgroup_warned_missing_idle = false;
-
 	/*
 	 * scx_tg_on/offline() are excluded through scx_cgroup_rwsem. If we walk
 	 * cgroups and init, all online cgroups are initialized.
@@ -4284,9 +4248,6 @@ static int scx_cgroup_init(void)
 		struct task_group *tg = css_tg(css);
 		struct scx_cgroup_init_args args = { .weight = tg->scx_weight };
 
-		scx_cgroup_warn_missing_weight(tg);
-		scx_cgroup_warn_missing_idle(tg);
-
 		if ((tg->scx_flags &
 		     (SCX_TG_ONLINE | SCX_TG_INITED)) != SCX_TG_ONLINE)
 			continue;
@@ -4623,7 +4584,7 @@ unlock:
 
 static void free_exit_info(struct scx_exit_info *ei)
 {
-	kfree(ei->dump);
+	kvfree(ei->dump);
 	kfree(ei->msg);
 	kfree(ei->bt);
 	kfree(ei);
@@ -4639,7 +4600,7 @@ static struct scx_exit_info *alloc_exit_info(size_t exit_dump_len)
 
 	ei->bt = kcalloc(SCX_EXIT_BT_LEN, sizeof(ei->bt[0]), GFP_KERNEL);
 	ei->msg = kzalloc(SCX_EXIT_MSG_LEN, GFP_KERNEL);
-	ei->dump = kzalloc(exit_dump_len, GFP_KERNEL);
+	ei->dump = kvzalloc(exit_dump_len, GFP_KERNEL);
 
 	if (!ei->bt || !ei->msg || !ei->dump) {
 		free_exit_info(ei);
@@ -5252,6 +5213,9 @@ static int validate_ops(const struct sched_ext_ops *ops)
 		return -EINVAL;
 	}
 
+	if (ops->flags & SCX_OPS_HAS_CGROUP_WEIGHT)
+		pr_warn("SCX_OPS_HAS_CGROUP_WEIGHT is deprecated and a noop\n");
+
 	return 0;
 }
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e43993a4e580..0fb9bf995a47 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7081,9 +7081,6 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 		h_nr_idle = task_has_idle_policy(p);
 		if (task_sleep || task_delayed || !se->sched_delayed)
 			h_nr_runnable = 1;
-	} else {
-		cfs_rq = group_cfs_rq(se);
-		slice = cfs_rq_min_slice(cfs_rq);
 	}
 
 	for_each_sched_entity(se) {
@@ -7093,6 +7090,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 			if (p && &p->se == se)
 				return -1;
 
+			slice = cfs_rq_min_slice(cfs_rq);
 			break;
 		}
 
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 517ee2590a29..30899a8cc52c 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -366,7 +366,7 @@ static const struct debug_obj_descr hrtimer_debug_descr;
 
 static void *hrtimer_debug_hint(void *addr)
 {
-	return ((struct hrtimer *) addr)->function;
+	return ACCESS_PRIVATE((struct hrtimer *)addr, function);
 }
 
 /*
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index a47bcf71defc..9a3859443c04 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -509,6 +509,7 @@ void tick_resume(void)
 
 #ifdef CONFIG_SUSPEND
 static DEFINE_RAW_SPINLOCK(tick_freeze_lock);
+static DEFINE_WAIT_OVERRIDE_MAP(tick_freeze_map, LD_WAIT_SLEEP);
 static unsigned int tick_freeze_depth;
 
 /**
@@ -528,9 +529,22 @@ void tick_freeze(void)
 	if (tick_freeze_depth == num_online_cpus()) {
 		trace_suspend_resume(TPS("timekeeping_freeze"),
 				     smp_processor_id(), true);
+		/*
+		 * All other CPUs have their interrupts disabled and are
+		 * suspended to idle. Other tasks have been frozen so there
+		 * is no scheduling happening. This means that there is no
+		 * concurrency in the system at this point. Therefore it is
+		 * okay to acquire a sleeping lock on PREEMPT_RT, such as a
+		 * spinlock, because the lock cannot be held by other CPUs
+		 * or threads and acquiring it cannot block.
+		 *
+		 * Inform lockdep about the situation.
+		 */
+		lock_map_acquire_try(&tick_freeze_map);
 		system_state = SYSTEM_SUSPEND;
 		sched_clock_suspend();
 		timekeeping_suspend();
+		lock_map_release(&tick_freeze_map);
 	} else {
 		tick_suspend_local();
 	}
@@ -552,8 +566,16 @@ void tick_unfreeze(void)
 	raw_spin_lock(&tick_freeze_lock);
 
 	if (tick_freeze_depth == num_online_cpus()) {
+		/*
+		 * Similar to tick_freeze(). On resumption the first CPU may
+		 * acquire uncontended sleeping locks while other CPUs block on
+		 * tick_freeze_lock.
+		 */
+		lock_map_acquire_try(&tick_freeze_map);
 		timekeeping_resume();
 		sched_clock_resume();
+		lock_map_release(&tick_freeze_map);
+
 		system_state = SYSTEM_RUNNING;
 		trace_suspend_resume(TPS("timekeeping_freeze"),
 				     smp_processor_id(), false);
diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index 33082c4e8154..95c6e3473a76 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -89,8 +89,11 @@ static bool delete_fprobe_node(struct fprobe_hlist_node *node)
 {
 	lockdep_assert_held(&fprobe_mutex);
 
-	WRITE_ONCE(node->fp, NULL);
-	hlist_del_rcu(&node->hlist);
+	/* Avoid double deleting */
+	if (READ_ONCE(node->fp) != NULL) {
+		WRITE_ONCE(node->fp, NULL);
+		hlist_del_rcu(&node->hlist);
+	}
 	return !!find_first_fprobe_node(node->addr);
 }
 
@@ -411,6 +414,102 @@ static void fprobe_graph_remove_ips(unsigned long *addrs, int num)
 		ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0);
 }
 
+#ifdef CONFIG_MODULES
+
+#define FPROBE_IPS_BATCH_INIT 8
+/* instruction pointer address list */
+struct fprobe_addr_list {
+	int index;
+	int size;
+	unsigned long *addrs;
+};
+
+static int fprobe_addr_list_add(struct fprobe_addr_list *alist, unsigned long addr)
+{
+	unsigned long *addrs;
+
+	if (alist->index >= alist->size)
+		return -ENOMEM;
+
+	alist->addrs[alist->index++] = addr;
+	if (alist->index < alist->size)
+		return 0;
+
+	/* Expand the address list */
+	addrs = kcalloc(alist->size * 2, sizeof(*addrs), GFP_KERNEL);
+	if (!addrs)
+		return -ENOMEM;
+
+	memcpy(addrs, alist->addrs, alist->size * sizeof(*addrs));
+	alist->size *= 2;
+	kfree(alist->addrs);
+	alist->addrs = addrs;
+
+	return 0;
+}
+
+static void fprobe_remove_node_in_module(struct module *mod, struct hlist_head *head,
+					struct fprobe_addr_list *alist)
+{
+	struct fprobe_hlist_node *node;
+	int ret = 0;
+
+	hlist_for_each_entry_rcu(node, head, hlist) {
+		if (!within_module(node->addr, mod))
+			continue;
+		if (delete_fprobe_node(node))
+			continue;
+		/*
+		 * If failed to update alist, just continue to update hlist.
+		 * Therefore, at list user handler will not hit anymore.
+		 */
+		if (!ret)
+			ret = fprobe_addr_list_add(alist, node->addr);
+	}
+}
+
+/* Handle module unloading to manage fprobe_ip_table. */
+static int fprobe_module_callback(struct notifier_block *nb,
+				  unsigned long val, void *data)
+{
+	struct fprobe_addr_list alist = {.size = FPROBE_IPS_BATCH_INIT};
+	struct module *mod = data;
+	int i;
+
+	if (val != MODULE_STATE_GOING)
+		return NOTIFY_DONE;
+
+	alist.addrs = kcalloc(alist.size, sizeof(*alist.addrs), GFP_KERNEL);
+	/* If failed to alloc memory, we can not remove ips from hash. */
+	if (!alist.addrs)
+		return NOTIFY_DONE;
+
+	mutex_lock(&fprobe_mutex);
+	for (i = 0; i < FPROBE_IP_TABLE_SIZE; i++)
+		fprobe_remove_node_in_module(mod, &fprobe_ip_table[i], &alist);
+
+	if (alist.index < alist.size && alist.index > 0)
+		ftrace_set_filter_ips(&fprobe_graph_ops.ops,
+				      alist.addrs, alist.index, 1, 0);
+	mutex_unlock(&fprobe_mutex);
+
+	kfree(alist.addrs);
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block fprobe_module_nb = {
+	.notifier_call = fprobe_module_callback,
+	.priority = 0,
+};
+
+static int __init init_fprobe_module(void)
+{
+	return register_module_notifier(&fprobe_module_nb);
+}
+early_initcall(init_fprobe_module);
+#endif
+
 static int symbols_cmp(const void *a, const void *b)
 {
 	const char **str_a = (const char **) a;
@@ -445,6 +544,7 @@ struct filter_match_data {
 	size_t index;
 	size_t size;
 	unsigned long *addrs;
+	struct module **mods;
 };
 
 static int filter_match_callback(void *data, const char *name, unsigned long addr)
@@ -458,30 +558,47 @@ static int filter_match_callback(void *data, const char *name, unsigned long add
 	if (!ftrace_location(addr))
 		return 0;
 
-	if (match->addrs)
-		match->addrs[match->index] = addr;
+	if (match->addrs) {
+		struct module *mod = __module_text_address(addr);
+
+		if (mod && !try_module_get(mod))
+			return 0;
 
+		match->mods[match->index] = mod;
+		match->addrs[match->index] = addr;
+	}
 	match->index++;
 	return match->index == match->size;
 }
 
 /*
  * Make IP list from the filter/no-filter glob patterns.
- * Return the number of matched symbols, or -ENOENT.
+ * Return the number of matched symbols, or errno.
+ * If @addrs == NULL, this just counts the number of matched symbols. If @addrs
+ * is passed with an array, we need to pass the an @mods array of the same size
+ * to increment the module refcount for each symbol.
+ * This means we also need to call `module_put` for each element of @mods after
+ * using the @addrs.
  */
-static int ip_list_from_filter(const char *filter, const char *notfilter,
-			       unsigned long *addrs, size_t size)
+static int get_ips_from_filter(const char *filter, const char *notfilter,
+			       unsigned long *addrs, struct module **mods,
+			       size_t size)
 {
 	struct filter_match_data match = { .filter = filter, .notfilter = notfilter,
-		.index = 0, .size = size, .addrs = addrs};
+		.index = 0, .size = size, .addrs = addrs, .mods = mods};
 	int ret;
 
+	if (addrs && !mods)
+		return -EINVAL;
+
 	ret = kallsyms_on_each_symbol(filter_match_callback, &match);
 	if (ret < 0)
 		return ret;
-	ret = module_kallsyms_on_each_symbol(NULL, filter_match_callback, &match);
-	if (ret < 0)
-		return ret;
+	if (IS_ENABLED(CONFIG_MODULES)) {
+		ret = module_kallsyms_on_each_symbol(NULL, filter_match_callback, &match);
+		if (ret < 0)
+			return ret;
+	}
 
 	return match.index ?: -ENOENT;
 }
@@ -543,24 +660,35 @@ static int fprobe_init(struct fprobe *fp, unsigned long *addrs, int num)
  */
 int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter)
 {
-	unsigned long *addrs;
-	int ret;
+	unsigned long *addrs __free(kfree) = NULL;
+	struct module **mods __free(kfree) = NULL;
+	int ret, num;
 
 	if (!fp || !filter)
 		return -EINVAL;
 
-	ret = ip_list_from_filter(filter, notfilter, NULL, FPROBE_IPS_MAX);
-	if (ret < 0)
-		return ret;
+	num = get_ips_from_filter(filter, notfilter, NULL, NULL, FPROBE_IPS_MAX);
+	if (num < 0)
+		return num;
 
-	addrs = kcalloc(ret, sizeof(unsigned long), GFP_KERNEL);
+	addrs = kcalloc(num, sizeof(*addrs), GFP_KERNEL);
 	if (!addrs)
 		return -ENOMEM;
-	ret = ip_list_from_filter(filter, notfilter, addrs, ret);
-	if (ret > 0)
-		ret = register_fprobe_ips(fp, addrs, ret);
 
-	kfree(addrs);
+	mods = kcalloc(num, sizeof(*mods), GFP_KERNEL);
+	if (!mods)
+		return -ENOMEM;
+
+	ret = get_ips_from_filter(filter, notfilter, addrs, mods, num);
+	if (ret < 0)
+		return ret;
+
+	ret = register_fprobe_ips(fp, addrs, ret);
+
+	for (int i = 0; i < num; i++) {
+		if (mods[i])
+			module_put(mods[i]);
+	}
 	return ret;
 }
 EXPORT_SYMBOL_GPL(register_fprobe);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 1a48aedb5255..61130bb34d6c 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1297,6 +1297,8 @@ void ftrace_free_filter(struct ftrace_ops *ops)
 		return;
 	free_ftrace_hash(ops->func_hash->filter_hash);
 	free_ftrace_hash(ops->func_hash->notrace_hash);
+	ops->func_hash->filter_hash = EMPTY_HASH;
+	ops->func_hash->notrace_hash = EMPTY_HASH;
 }
 EXPORT_SYMBOL_GPL(ftrace_free_filter);
 
@@ -3256,6 +3258,31 @@ static int append_hash(struct ftrace_hash **hash, struct ftrace_hash *new_hash,
 }
 
 /*
+ * Remove functions from @hash that are in @notrace_hash
+ */
+static void remove_hash(struct ftrace_hash *hash, struct ftrace_hash *notrace_hash)
+{
+	struct ftrace_func_entry *entry;
+	struct hlist_node *tmp;
+	int size;
+	int i;
+
+	/* If the notrace hash is empty, there's nothing to do */
+	if (ftrace_hash_empty(notrace_hash))
+		return;
+
+	size = 1 << hash->size_bits;
+	for (i = 0; i < size; i++) {
+		hlist_for_each_entry_safe(entry, tmp, &hash->buckets[i], hlist) {
+			if (!__ftrace_lookup_ip(notrace_hash, entry->ip))
+				continue;
+			remove_hash_entry(hash, entry);
+			kfree(entry);
+		}
+	}
+}
+
+/*
  * Add to @hash only those that are in both @new_hash1 and @new_hash2
  *
  * The notrace_hash updates uses just the intersect_hash() function
@@ -3295,67 +3322,6 @@ static int intersect_hash(struct ftrace_hash **hash, struct ftrace_hash *new_has
 	return 0;
 }
 
-/* Return a new hash that has a union of all @ops->filter_hash entries */
-static struct ftrace_hash *append_hashes(struct ftrace_ops *ops)
-{
-	struct ftrace_hash *new_hash = NULL;
-	struct ftrace_ops *subops;
-	int size_bits;
-	int ret;
-
-	if (ops->func_hash->filter_hash)
-		size_bits = ops->func_hash->filter_hash->size_bits;
-	else
-		size_bits = FTRACE_HASH_DEFAULT_BITS;
-
-	list_for_each_entry(subops, &ops->subop_list, list) {
-		ret = append_hash(&new_hash, subops->func_hash->filter_hash, size_bits);
-		if (ret < 0) {
-			free_ftrace_hash(new_hash);
-			return NULL;
-		}
-		/* Nothing more to do if new_hash is empty */
-		if (ftrace_hash_empty(new_hash))
-			break;
-	}
-	/* Can't return NULL as that means this failed */
-	return new_hash ? : EMPTY_HASH;
-}
-
-/* Make @ops trace evenything except what all its subops do not trace */
-static struct ftrace_hash *intersect_hashes(struct ftrace_ops *ops)
-{
-	struct ftrace_hash *new_hash = NULL;
-	struct ftrace_ops *subops;
-	int size_bits;
-	int ret;
-
-	list_for_each_entry(subops, &ops->subop_list, list) {
-		struct ftrace_hash *next_hash;
-
-		if (!new_hash) {
-			size_bits = subops->func_hash->notrace_hash->size_bits;
-			new_hash = alloc_and_copy_ftrace_hash(size_bits, ops->func_hash->notrace_hash);
-			if (!new_hash)
-				return NULL;
-			continue;
-		}
-		size_bits = new_hash->size_bits;
-		next_hash = new_hash;
-		new_hash = alloc_ftrace_hash(size_bits);
-		ret = intersect_hash(&new_hash, next_hash, subops->func_hash->notrace_hash);
-		free_ftrace_hash(next_hash);
-		if (ret < 0) {
-			free_ftrace_hash(new_hash);
-			return NULL;
-		}
-		/* Nothing more to do if new_hash is empty */
-		if (ftrace_hash_empty(new_hash))
-			break;
-	}
-	return new_hash;
-}
-
 static bool ops_equal(struct ftrace_hash *A, struct ftrace_hash *B)
 {
 	struct ftrace_func_entry *entry;
@@ -3427,6 +3393,95 @@ static int ftrace_update_ops(struct ftrace_ops *ops, struct ftrace_hash *filter_
 	return 0;
 }
 
+static int add_first_hash(struct ftrace_hash **filter_hash, struct ftrace_hash **notrace_hash,
+			  struct ftrace_ops_hash *func_hash)
+{
+	/* If the filter hash is not empty, simply remove the nohash from it */
+	if (!ftrace_hash_empty(func_hash->filter_hash)) {
+		*filter_hash = copy_hash(func_hash->filter_hash);
+		if (!*filter_hash)
+			return -ENOMEM;
+		remove_hash(*filter_hash, func_hash->notrace_hash);
+		*notrace_hash = EMPTY_HASH;
+
+	} else {
+		*notrace_hash = copy_hash(func_hash->notrace_hash);
+		if (!*notrace_hash)
+			return -ENOMEM;
+		*filter_hash = EMPTY_HASH;
+	}
+	return 0;
+}
+
+static int add_next_hash(struct ftrace_hash **filter_hash, struct ftrace_hash **notrace_hash,
+			 struct ftrace_ops_hash *ops_hash, struct ftrace_ops_hash *subops_hash)
+{
+	int size_bits;
+	int ret;
+
+	/* If the subops trace all functions so must the main ops */
+	if (ftrace_hash_empty(ops_hash->filter_hash) ||
+	    ftrace_hash_empty(subops_hash->filter_hash)) {
+		*filter_hash = EMPTY_HASH;
+	} else {
+		/*
+		 * The main ops filter hash is not empty, so its
+		 * notrace_hash had better be, as the notrace hash
+		 * is only used for empty main filter hashes.
+		 */
+		WARN_ON_ONCE(!ftrace_hash_empty(ops_hash->notrace_hash));
+
+		size_bits = max(ops_hash->filter_hash->size_bits,
+				subops_hash->filter_hash->size_bits);
+
+		/* Copy the subops hash */
+		*filter_hash = alloc_and_copy_ftrace_hash(size_bits, subops_hash->filter_hash);
+		if (!filter_hash)
+			return -ENOMEM;
+		/* Remove any notrace functions from the copy */
+		remove_hash(*filter_hash, subops_hash->notrace_hash);
+
+		ret = append_hash(filter_hash, ops_hash->filter_hash,
+				  size_bits);
+		if (ret < 0) {
+			free_ftrace_hash(*filter_hash);
+			*filter_hash = EMPTY_HASH;
+			return ret;
+		}
+	}
+
+	/*
+	 * Only process notrace hashes if the main filter hash is empty
+	 * (tracing all functions), otherwise the filter hash will just
+	 * remove the notrace hash functions, and the notrace hash is
+	 * not needed.
+	 */
+	if (ftrace_hash_empty(*filter_hash)) {
+		/*
+		 * Intersect the notrace functions. That is, if two
+		 * subops are not tracing a set of functions, the
+		 * main ops will only not trace the functions that are
+		 * in both subops, but has to trace the functions that
+		 * are only notrace in one of the subops, for the other
+		 * subops to be able to trace them.
+		 */
+		size_bits = max(ops_hash->notrace_hash->size_bits,
+				subops_hash->notrace_hash->size_bits);
+		*notrace_hash = alloc_ftrace_hash(size_bits);
+		if (!*notrace_hash)
+			return -ENOMEM;
+
+		ret = intersect_hash(notrace_hash, ops_hash->notrace_hash,
+				     subops_hash->notrace_hash);
+		if (ret < 0) {
+			free_ftrace_hash(*notrace_hash);
+			*notrace_hash = EMPTY_HASH;
+			return ret;
+		}
+	}
+	return 0;
+}
+
 /**
  * ftrace_startup_subops - enable tracing for subops of an ops
  * @ops: Manager ops (used to pick all the functions of its subops)
@@ -3439,11 +3494,10 @@ static int ftrace_update_ops(struct ftrace_ops *ops, struct ftrace_hash *filter_
  */
 int ftrace_startup_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int command)
 {
-	struct ftrace_hash *filter_hash;
-	struct ftrace_hash *notrace_hash;
+	struct ftrace_hash *filter_hash = EMPTY_HASH;
+	struct ftrace_hash *notrace_hash = EMPTY_HASH;
 	struct ftrace_hash *save_filter_hash;
 	struct ftrace_hash *save_notrace_hash;
-	int size_bits;
 	int ret;
 
 	if (unlikely(ftrace_disabled))
@@ -3467,14 +3521,14 @@ int ftrace_startup_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int
 
 	/* For the first subops to ops just enable it normally */
 	if (list_empty(&ops->subop_list)) {
-		/* Just use the subops hashes */
-		filter_hash = copy_hash(subops->func_hash->filter_hash);
-		notrace_hash = copy_hash(subops->func_hash->notrace_hash);
-		if (!filter_hash || !notrace_hash) {
-			free_ftrace_hash(filter_hash);
-			free_ftrace_hash(notrace_hash);
-			return -ENOMEM;
-		}
+
+		/* The ops was empty, should have empty hashes */
+		WARN_ON_ONCE(!ftrace_hash_empty(ops->func_hash->filter_hash));
+		WARN_ON_ONCE(!ftrace_hash_empty(ops->func_hash->notrace_hash));
+
+		ret = add_first_hash(&filter_hash, &notrace_hash, subops->func_hash);
+		if (ret < 0)
+			return ret;
 
 		save_filter_hash = ops->func_hash->filter_hash;
 		save_notrace_hash = ops->func_hash->notrace_hash;
@@ -3500,48 +3554,16 @@ int ftrace_startup_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int
 
 	/*
 	 * Here there's already something attached. Here are the rules:
-	 *   o If either filter_hash is empty then the final stays empty
-	 *      o Otherwise, the final is a superset of both hashes
-	 *   o If either notrace_hash is empty then the final stays empty
-	 *      o Otherwise, the final is an intersection between the hashes
+	 *   If the new subops and main ops filter hashes are not empty:
+	 *     o Make a copy of the subops filter hash
+	 *     o Remove all functions in the nohash from it.
+	 *     o Add in the main hash filter functions
+	 *     o Remove any of these functions from the main notrace hash
 	 */
-	if (ftrace_hash_empty(ops->func_hash->filter_hash) ||
-	    ftrace_hash_empty(subops->func_hash->filter_hash)) {
-		filter_hash = EMPTY_HASH;
-	} else {
-		size_bits = max(ops->func_hash->filter_hash->size_bits,
-				subops->func_hash->filter_hash->size_bits);
-		filter_hash = alloc_and_copy_ftrace_hash(size_bits, ops->func_hash->filter_hash);
-		if (!filter_hash)
-			return -ENOMEM;
-		ret = append_hash(&filter_hash, subops->func_hash->filter_hash,
-				  size_bits);
-		if (ret < 0) {
-			free_ftrace_hash(filter_hash);
-			return ret;
-		}
-	}
 
-	if (ftrace_hash_empty(ops->func_hash->notrace_hash) ||
-	    ftrace_hash_empty(subops->func_hash->notrace_hash)) {
-		notrace_hash = EMPTY_HASH;
-	} else {
-		size_bits = max(ops->func_hash->filter_hash->size_bits,
-				subops->func_hash->filter_hash->size_bits);
-		notrace_hash = alloc_ftrace_hash(size_bits);
-		if (!notrace_hash) {
-			free_ftrace_hash(filter_hash);
-			return -ENOMEM;
-		}
-
-		ret = intersect_hash(&notrace_hash, ops->func_hash->filter_hash,
-				     subops->func_hash->filter_hash);
-		if (ret < 0) {
-			free_ftrace_hash(filter_hash);
-			free_ftrace_hash(notrace_hash);
-			return ret;
-		}
-	}
+	ret = add_next_hash(&filter_hash, &notrace_hash, ops->func_hash, subops->func_hash);
+	if (ret < 0)
+		return ret;
 
 	list_add(&subops->list, &ops->subop_list);
 
@@ -3557,6 +3579,45 @@ int ftrace_startup_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int
 	return ret;
 }
 
+static int rebuild_hashes(struct ftrace_hash **filter_hash, struct ftrace_hash **notrace_hash,
+			  struct ftrace_ops *ops)
+{
+	struct ftrace_ops_hash temp_hash;
+	struct ftrace_ops *subops;
+	bool first = true;
+	int ret;
+
+	temp_hash.filter_hash = EMPTY_HASH;
+	temp_hash.notrace_hash = EMPTY_HASH;
+
+	list_for_each_entry(subops, &ops->subop_list, list) {
+		*filter_hash = EMPTY_HASH;
+		*notrace_hash = EMPTY_HASH;
+
+		if (first) {
+			ret = add_first_hash(filter_hash, notrace_hash, subops->func_hash);
+			if (ret < 0)
+				return ret;
+			first = false;
+		} else {
+			ret = add_next_hash(filter_hash, notrace_hash,
+					    &temp_hash, subops->func_hash);
+			if (ret < 0) {
+				free_ftrace_hash(temp_hash.filter_hash);
+				free_ftrace_hash(temp_hash.notrace_hash);
+				return ret;
+			}
+		}
+
+		free_ftrace_hash(temp_hash.filter_hash);
+		free_ftrace_hash(temp_hash.notrace_hash);
+
+		temp_hash.filter_hash = *filter_hash;
+		temp_hash.notrace_hash = *notrace_hash;
+	}
+	return 0;
+}
+
 /**
  * ftrace_shutdown_subops - Remove a subops from a manager ops
  * @ops: A manager ops to remove @subops from
@@ -3571,8 +3632,8 @@ int ftrace_startup_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int
  */
 int ftrace_shutdown_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int command)
 {
-	struct ftrace_hash *filter_hash;
-	struct ftrace_hash *notrace_hash;
+	struct ftrace_hash *filter_hash = EMPTY_HASH;
+	struct ftrace_hash *notrace_hash = EMPTY_HASH;
 	int ret;
 
 	if (unlikely(ftrace_disabled))
@@ -3605,14 +3666,9 @@ int ftrace_shutdown_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, in
 	}
 
 	/* Rebuild the hashes without subops */
-	filter_hash = append_hashes(ops);
-	notrace_hash = intersect_hashes(ops);
-	if (!filter_hash || !notrace_hash) {
-		free_ftrace_hash(filter_hash);
-		free_ftrace_hash(notrace_hash);
-		list_add(&subops->list, &ops->subop_list);
-		return -ENOMEM;
-	}
+	ret = rebuild_hashes(&filter_hash, &notrace_hash, ops);
+	if (ret < 0)
+		return ret;
 
 	ret = ftrace_update_ops(ops, filter_hash, notrace_hash);
 	if (ret < 0) {
@@ -3628,11 +3684,11 @@ int ftrace_shutdown_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, in
 
 static int ftrace_hash_move_and_update_subops(struct ftrace_ops *subops,
 					      struct ftrace_hash **orig_subhash,
-					      struct ftrace_hash *hash,
-					      int enable)
+					      struct ftrace_hash *hash)
 {
 	struct ftrace_ops *ops = subops->managed;
-	struct ftrace_hash **orig_hash;
+	struct ftrace_hash *notrace_hash;
+	struct ftrace_hash *filter_hash;
 	struct ftrace_hash *save_hash;
 	struct ftrace_hash *new_hash;
 	int ret;
@@ -3649,24 +3705,18 @@ static int ftrace_hash_move_and_update_subops(struct ftrace_ops *subops,
 		return -ENOMEM;
 	}
 
-	/* Create a new_hash to hold the ops new functions */
-	if (enable) {
-		orig_hash = &ops->func_hash->filter_hash;
-		new_hash = append_hashes(ops);
-	} else {
-		orig_hash = &ops->func_hash->notrace_hash;
-		new_hash = intersect_hashes(ops);
+	ret = rebuild_hashes(&filter_hash, &notrace_hash, ops);
+	if (!ret) {
+		ret = ftrace_update_ops(ops, filter_hash, notrace_hash);
+		free_ftrace_hash(filter_hash);
+		free_ftrace_hash(notrace_hash);
 	}
 
-	/* Move the hash over to the new hash */
-	ret = __ftrace_hash_move_and_update_ops(ops, orig_hash, new_hash, enable);
-
-	free_ftrace_hash(new_hash);
-
 	if (ret) {
 		/* Put back the original hash */
-		free_ftrace_hash_rcu(*orig_subhash);
+		new_hash = *orig_subhash;
 		*orig_subhash = save_hash;
+		free_ftrace_hash_rcu(new_hash);
 	} else {
 		free_ftrace_hash_rcu(save_hash);
 	}
@@ -4890,7 +4940,7 @@ static int ftrace_hash_move_and_update_ops(struct ftrace_ops *ops,
 					   int enable)
 {
 	if (ops->flags & FTRACE_OPS_FL_SUBOP)
-		return ftrace_hash_move_and_update_subops(ops, orig_hash, hash, enable);
+		return ftrace_hash_move_and_update_subops(ops, orig_hash, hash);
 
 	/*
 	 * If this ops is not enabled, it could be sharing its filters
@@ -4909,7 +4959,7 @@ static int ftrace_hash_move_and_update_ops(struct ftrace_ops *ops,
 			list_for_each_entry(subops, &op->subop_list, list) {
 				if ((subops->flags & FTRACE_OPS_FL_ENABLED) &&
 				     subops->func_hash == ops->func_hash) {
-					return ftrace_hash_move_and_update_subops(subops, orig_hash, hash, enable);
+					return ftrace_hash_move_and_update_subops(subops, orig_hash, hash);
 				}
 			}
 		} while_for_each_ftrace_op(op);
@@ -5914,9 +5964,10 @@ int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
 
 	/* Make a copy hash to place the new and the old entries in */
 	size = hash->count + direct_functions->count;
-	if (size > 32)
-		size = 32;
-	new_hash = alloc_ftrace_hash(fls(size));
+	size = fls(size);
+	if (size > FTRACE_HASH_MAX_BITS)
+		size = FTRACE_HASH_MAX_BITS;
+	new_hash = alloc_ftrace_hash(size);
 	if (!new_hash)
 		goto out_unlock;
 
diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c
index 968c5c3b0246..e4077500a91d 100644
--- a/kernel/trace/rv/rv.c
+++ b/kernel/trace/rv/rv.c
@@ -225,7 +225,12 @@ bool rv_is_nested_monitor(struct rv_monitor_def *mdef)
  */
 bool rv_is_container_monitor(struct rv_monitor_def *mdef)
 {
-	struct rv_monitor_def *next = list_next_entry(mdef, list);
+	struct rv_monitor_def *next;
+
+	if (list_is_last(&mdef->list, &rv_monitors_list))
+		return false;
+
+	next = list_next_entry(mdef, list);
 
 	return next->parent == mdef->monitor || !mdef->monitor->enable;
 }
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index b581e388a9d9..8ddf6b17215c 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -9806,6 +9806,7 @@ static int instance_mkdir(const char *name)
 	return ret;
 }
 
+#ifdef CONFIG_MMU
 static u64 map_pages(unsigned long start, unsigned long size)
 {
 	unsigned long vmap_start, vmap_end;
@@ -9828,6 +9829,12 @@ static u64 map_pages(unsigned long start, unsigned long size)
 
 	return (u64)vmap_start;
 }
+#else
+static inline u64 map_pages(unsigned long start, unsigned long size)
+{
+	return 0;
+}
+#endif
 
 /**
  * trace_array_get_by_name - Create/Lookup a trace array, given its name.
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index ee40d4e6ad1c..4ef4df6623a8 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -80,11 +80,11 @@ FTRACE_ENTRY(funcgraph_entry, ftrace_graph_ent_entry,
 	F_STRUCT(
 		__field_struct(	struct ftrace_graph_ent,	graph_ent	)
 		__field_packed(	unsigned long,	graph_ent,	func		)
-		__field_packed(	unsigned long,	graph_ent,	depth		)
+		__field_packed(	unsigned int,	graph_ent,	depth		)
 		__dynamic_array(unsigned long,	args				)
 	),
 
-	F_printk("--> %ps (%lu)", (void *)__entry->func, __entry->depth)
+	F_printk("--> %ps (%u)", (void *)__entry->func, __entry->depth)
 );
 
 #ifdef CONFIG_FUNCTION_GRAPH_RETADDR
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 0993dfc1c5c1..2048560264bb 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -808,7 +808,7 @@ static __always_inline char *test_string(char *str)
 	kstr = ubuf->buffer;
 
 	/* For safety, do not trust the string pointer */
-	if (!strncpy_from_kernel_nofault(kstr, str, USTRING_BUF_SIZE))
+	if (strncpy_from_kernel_nofault(kstr, str, USTRING_BUF_SIZE) < 0)
 		return NULL;
 	return kstr;
 }
@@ -827,7 +827,7 @@ static __always_inline char *test_ustring(char *str)
 
 	/* user space address? */
 	ustr = (char __user *)str;
-	if (!strncpy_from_user_nofault(kstr, ustr, USTRING_BUF_SIZE))
+	if (strncpy_from_user_nofault(kstr, ustr, USTRING_BUF_SIZE) < 0)
 		return NULL;
 
 	return kstr;
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index 969f48742d72..33cfbd4ed76d 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -370,7 +370,6 @@ static enum print_line_t print_synth_event(struct trace_iterator *iter,
 				union trace_synth_field *data = &entry->fields[n_u64];
 
 				trace_seq_printf(s, print_fmt, se->fields[i]->name,
-						 STR_VAR_LEN_MAX,
 						 (char *)entry + data->as_dynamic.offset,
 						 i == se->n_fields - 1 ? "" : " ");
 				n_u64++;
diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c
index 5d7ca80173ea..b40fa59159ac 100644
--- a/kernel/trace/trace_fprobe.c
+++ b/kernel/trace/trace_fprobe.c
@@ -919,9 +919,15 @@ static void __find_tracepoint_module_cb(struct tracepoint *tp, struct module *mo
 	struct __find_tracepoint_cb_data *data = priv;
 
 	if (!data->tpoint && !strcmp(data->tp_name, tp->name)) {
-		data->tpoint = tp;
-		if (!data->mod)
+		/* If module is not specified, try getting module refcount. */
+		if (!data->mod && mod) {
+			/* If failed to get refcount, ignore this tracepoint. */
+			if (!try_module_get(mod))
+				return;
+
 			data->mod = mod;
+		}
+		data->tpoint = tp;
 	}
 }
 
@@ -933,7 +939,11 @@ static void __find_tracepoint_cb(struct tracepoint *tp, void *priv)
 		data->tpoint = tp;
 }
 
-/* Find a tracepoint from kernel and module. */
+/*
+ * Find a tracepoint from kernel and module. If the tracepoint is on the module,
+ * the module's refcount is incremented and returned as *@tp_mod. Thus, if it is
+ * not NULL, caller must call module_put(*tp_mod) after used the tracepoint.
+ */
 static struct tracepoint *find_tracepoint(const char *tp_name,
 					  struct module **tp_mod)
 {
@@ -962,7 +972,10 @@ static void reenable_trace_fprobe(struct trace_fprobe *tf)
 	}
 }
 
-/* Find a tracepoint from specified module. */
+/*
+ * Find a tracepoint from specified module. In this case, this does not get the
+ * module's refcount. The caller must ensure the module is not freed.
+ */
 static struct tracepoint *find_tracepoint_in_module(struct module *mod,
 						    const char *tp_name)
 {
@@ -1169,11 +1182,6 @@ static int trace_fprobe_create_internal(int argc, const char *argv[],
 	if (is_tracepoint) {
 		ctx->flags |= TPARG_FL_TPOINT;
 		tpoint = find_tracepoint(symbol, &tp_mod);
-		/* lock module until register this tprobe. */
-		if (tp_mod && !try_module_get(tp_mod)) {
-			tpoint = NULL;
-			tp_mod = NULL;
-		}
 		if (tpoint) {
 			ctx->funcname = kallsyms_lookup(
 				(unsigned long)tpoint->probestub,
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 2f077d4158e5..0c357a89c58e 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -880,8 +880,6 @@ static void print_graph_retval(struct trace_seq *s, struct ftrace_graph_ent_entr
 
 		if (print_retval || print_retaddr)
 			trace_seq_puts(s, " /*");
-		else
-			trace_seq_putc(s, '\n');
 	} else {
 		print_retaddr = false;
 		trace_seq_printf(s, "} /* %ps", func);
@@ -899,7 +897,7 @@ static void print_graph_retval(struct trace_seq *s, struct ftrace_graph_ent_entr
 	}
 
 	if (!entry || print_retval || print_retaddr)
-		trace_seq_puts(s, " */\n");
+		trace_seq_puts(s, " */");
 }
 
 #else
@@ -975,7 +973,7 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 		} else
 			trace_seq_puts(s, "();");
 	}
-	trace_seq_printf(s, "\n");
+	trace_seq_putc(s, '\n');
 
 	print_graph_irq(iter, graph_ret->func, TRACE_GRAPH_RET,
 			cpu, iter->ent->pid, flags);
@@ -1313,10 +1311,11 @@ print_graph_return(struct ftrace_graph_ret_entry *retentry, struct trace_seq *s,
 		 * that if the funcgraph-tail option is enabled.
 		 */
 		if (func_match && !(flags & TRACE_GRAPH_PRINT_TAIL))
-			trace_seq_puts(s, "}\n");
+			trace_seq_puts(s, "}");
 		else
-			trace_seq_printf(s, "} /* %ps */\n", (void *)func);
+			trace_seq_printf(s, "} /* %ps */", (void *)func);
 	}
+	trace_seq_putc(s, '\n');
 
 	/* Overrun */
 	if (flags & TRACE_GRAPH_PRINT_OVERRUN)
diff --git a/kernel/vhost_task.c b/kernel/vhost_task.c
index 2ef2e1b80091..2f844c279a3e 100644
--- a/kernel/vhost_task.c
+++ b/kernel/vhost_task.c
@@ -111,7 +111,7 @@ EXPORT_SYMBOL_GPL(vhost_task_stop);
  * @arg: data to be passed to fn and handled_kill
  * @name: the thread's name
  *
- * This returns a specialized task for use by the vhost layer or NULL on
+ * This returns a specialized task for use by the vhost layer or ERR_PTR() on
  * failure. The returned task is inactive, and the caller must fire it up
  * through vhost_task_start().
  */