kernfs: Use RCU to access kernfs_node::name.

Using RCU lifetime rules to access kernfs_node::name can avoid the
trouble with kernfs_rename_lock in kernfs_name() and kernfs_path_from_node()
if the fs was created with KERNFS_ROOT_INVARIANT_PARENT. This is usefull
as it allows to implement kernfs_path_from_node() only with RCU
protection and avoiding kernfs_rename_lock. The lock is only required if
the __parent node can be changed and the function requires an unchanged
hierarchy while it iterates from the node to its parent.
The change is needed to allow the lookup of the node's path
(kernfs_path_from_node()) from context which runs always with disabled
preemption and or interrutps even on PREEMPT_RT. The problem is that
kernfs_rename_lock becomes a sleeping lock on PREEMPT_RT.

I went through all ::name users and added the required access for the lookup
with a few extensions:
- rdtgroup_pseudo_lock_create() drops all locks and then uses the name
  later on. resctrl supports rename with different parents. Here I made
  a temporal copy of the name while it is used outside of the lock.

- kernfs_rename_ns() accepts NULL as new_parent. This simplifies
  sysfs_move_dir_ns() where it can set NULL in order to reuse the current
  name.

- kernfs_rename_ns() is only using kernfs_rename_lock if the parents are
  different. All users use either kernfs_rwsem (for stable path view) or
  just RCU for the lookup. The ::name uses always RCU free.

Use RCU lifetime guarantees to access kernfs_node::name.

Suggested-by: Tejun Heo <tj@kernel.org>
Acked-by: Tejun Heo <tj@kernel.org>
Reported-by: syzbot+6ea37e2e6ffccf41a7e6@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/lkml/67251dc6.050a0220.529b6.015e.GAE@google.com/
Reported-by: Hillf Danton <hdanton@sina.com>
Closes: https://lore.kernel.org/20241102001224.2789-1-hdanton@sina.com
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://lore.kernel.org/r/20250213145023.2820193-7-bigeasy@linutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

3 files changed, 20 insertions, 9 deletions

diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 20c898f09b7e..dd5d6b4bfcc2 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -507,6 +507,11 @@ int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s,
 
 extern struct mutex rdtgroup_mutex;
 
+static inline const char *rdt_kn_name(const struct kernfs_node *kn)
+{
+	return rcu_dereference_check(kn->name, lockdep_is_held(&rdtgroup_mutex));
+}
+
 extern struct rdt_hw_resource rdt_resources_all[];
 extern struct rdtgroup rdtgroup_default;
 extern struct dentry *debugfs_resctrl;
diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index 42cc162f7fc9..7a2db7fa4108 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -52,7 +52,8 @@ static char *pseudo_lock_devnode(const struct device *dev, umode_t *mode)
 	rdtgrp = dev_get_drvdata(dev);
 	if (mode)
 		*mode = 0600;
-	return kasprintf(GFP_KERNEL, "pseudo_lock/%s", rdtgrp->kn->name);
+	guard(mutex)(&rdtgroup_mutex);
+	return kasprintf(GFP_KERNEL, "pseudo_lock/%s", rdt_kn_name(rdtgrp->kn));
 }
 
 static const struct class pseudo_lock_class = {
@@ -1293,6 +1294,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 	struct task_struct *thread;
 	unsigned int new_minor;
 	struct device *dev;
+	char *kn_name __free(kfree) = NULL;
 	int ret;
 
 	ret = pseudo_lock_region_alloc(plr);
@@ -1304,6 +1306,11 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 		ret = -EINVAL;
 		goto out_region;
 	}
+	kn_name = kstrdup(rdt_kn_name(rdtgrp->kn), GFP_KERNEL);
+	if (!kn_name) {
+		ret = -ENOMEM;
+		goto out_cstates;
+	}
 
 	plr->thread_done = 0;
 
@@ -1348,8 +1355,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 	mutex_unlock(&rdtgroup_mutex);
 
 	if (!IS_ERR_OR_NULL(debugfs_resctrl)) {
-		plr->debugfs_dir = debugfs_create_dir(rdtgrp->kn->name,
-						      debugfs_resctrl);
+		plr->debugfs_dir = debugfs_create_dir(kn_name, debugfs_resctrl);
 		if (!IS_ERR_OR_NULL(plr->debugfs_dir))
 			debugfs_create_file("pseudo_lock_measure", 0200,
 					    plr->debugfs_dir, rdtgrp,
@@ -1358,7 +1364,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 
 	dev = device_create(&pseudo_lock_class, NULL,
 			    MKDEV(pseudo_lock_major, new_minor),
-			    rdtgrp, "%s", rdtgrp->kn->name);
+			    rdtgrp, "%s", kn_name);
 
 	mutex_lock(&rdtgroup_mutex);
 
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 55dcdeea1a1b..10afc4eaa467 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -916,14 +916,14 @@ int proc_resctrl_show(struct seq_file *s, struct pid_namespace *ns,
 			continue;
 
 		seq_printf(s, "res:%s%s\n", (rdtg == &rdtgroup_default) ? "/" : "",
-			   rdtg->kn->name);
+			   rdt_kn_name(rdtg->kn));
 		seq_puts(s, "mon:");
 		list_for_each_entry(crg, &rdtg->mon.crdtgrp_list,
 				    mon.crdtgrp_list) {
 			if (!resctrl_arch_match_rmid(tsk, crg->mon.parent->closid,
 						     crg->mon.rmid))
 				continue;
-			seq_printf(s, "%s", crg->kn->name);
+			seq_printf(s, "%s", rdt_kn_name(crg->kn));
 			break;
 		}
 		seq_putc(s, '\n');
@@ -3675,7 +3675,7 @@ out_unlock:
  */
 static bool is_mon_groups(struct kernfs_node *kn, const char *name)
 {
-	return (!strcmp(kn->name, "mon_groups") &&
+	return (!strcmp(rdt_kn_name(kn), "mon_groups") &&
 		strcmp(name, "mon_groups"));
 }
 
@@ -3824,7 +3824,7 @@ static int rdtgroup_rmdir(struct kernfs_node *kn)
 			ret = rdtgroup_rmdir_ctrl(rdtgrp, tmpmask);
 		}
 	} else if (rdtgrp->type == RDTMON_GROUP &&
-		 is_mon_groups(parent_kn, kn->name)) {
+		 is_mon_groups(parent_kn, rdt_kn_name(kn))) {
 		ret = rdtgroup_rmdir_mon(rdtgrp, tmpmask);
 	} else {
 		ret = -EPERM;
@@ -3912,7 +3912,7 @@ static int rdtgroup_rename(struct kernfs_node *kn,
 
 	kn_parent = rdt_kn_parent(kn);
 	if (rdtgrp->type != RDTMON_GROUP || !kn_parent ||
-	    !is_mon_groups(kn_parent, kn->name)) {
+	    !is_mon_groups(kn_parent, rdt_kn_name(kn))) {
 		rdt_last_cmd_puts("Source must be a MON group\n");
 		ret = -EPERM;
 		goto out;