kernfs: Separate kernfs_pr_cont_buf and rename_lock

JIRA: https://issues.redhat.com/browse/RHEL-52956
Upstream status: Linus

commit 1a702dc
Author: Hao Luo <haoluo@google.com>
Date:   Mon May 16 12:09:51 2022 -0700

    kernfs: Separate kernfs_pr_cont_buf and rename_lock.

    Previously the protection of kernfs_pr_cont_buf was piggy backed by
    rename_lock, which means that pr_cont() needs to be protected under
    rename_lock. This can cause potential circular lock dependencies.

    If there is an OOM, we have the following call hierarchy:

     -> cpuset_print_current_mems_allowed()
       -> pr_cont_cgroup_name()
         -> pr_cont_kernfs_name()

    pr_cont_kernfs_name() will grab rename_lock and call printk. So we have
    the following lock dependencies:

     kernfs_rename_lock -> console_sem

    Sometimes, printk does a wakeup before releasing console_sem, which has
    the dependence chain:

     console_sem -> p->pi_lock -> rq->lock

    Now, imagine one wants to read cgroup_name under rq->lock, for example,
    printing cgroup_name in a tracepoint in the scheduler code. They will
    be holding rq->lock and take rename_lock:

     rq->lock -> kernfs_rename_lock

    Now they will deadlock.

    A prevention to this circular lock dependency is to separate the
    protection of pr_cont_buf from rename_lock. In principle, rename_lock
    is to protect the integrity of cgroup name when copying to buf. Once
    pr_cont_buf has got its content, rename_lock can be dropped. So it's
    safe to drop rename_lock after kernfs_name_locked (and
    kernfs_path_from_node_locked) and rely on a dedicated pr_cont_lock
    to protect pr_cont_buf.

    Acked-by: Tejun Heo <tj@kernel.org>
    Signed-off-by: Hao Luo <haoluo@google.com>
    Link: https://lore.kernel.org/r/20220516190951.3144144-1-haoluo@google.com
    Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Signed-off-by: Ian Kent <ikent@redhat.com>

Author: Ian Kent

fs/kernfs/dir.c

@@ -18,7 +18,15 @@
 #include "kernfs-internal.h"
 
 static DEFINE_SPINLOCK(kernfs_rename_lock);	/* kn->parent and ->name */
-static char kernfs_pr_cont_buf[PATH_MAX];	/* protected by rename_lock */
+/*
+ * Don't use rename_lock to piggy back on pr_cont_buf. We don't want to
+ * call pr_cont() while holding rename_lock. Because sometimes pr_cont()
+ * will perform wakeups when releasing console_sem. Holding rename_lock
+ * will introduce deadlock if the scheduler reads the kernfs_name in the
+ * wakeup path.
+ */
+static DEFINE_SPINLOCK(kernfs_pr_cont_lock);
+static char kernfs_pr_cont_buf[PATH_MAX];	/* protected by pr_cont_lock */
 static DEFINE_SPINLOCK(kernfs_idr_lock);	/* root->ino_idr */
 
 #define rb_to_kn(X) rb_entry((X), struct kernfs_node, rb)
@@ -234,12 +242,12 @@ void pr_cont_kernfs_name(struct kernfs_node *kn)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&kernfs_rename_lock, flags);
+	spin_lock_irqsave(&kernfs_pr_cont_lock, flags);
 
-	kernfs_name_locked(kn, kernfs_pr_cont_buf, sizeof(kernfs_pr_cont_buf));
+	kernfs_name(kn, kernfs_pr_cont_buf, sizeof(kernfs_pr_cont_buf));
 	pr_cont("%s", kernfs_pr_cont_buf);
 
-	spin_unlock_irqrestore(&kernfs_rename_lock, flags);
+	spin_unlock_irqrestore(&kernfs_pr_cont_lock, flags);
 }
 
 /**
@@ -253,10 +261,10 @@ void pr_cont_kernfs_path(struct kernfs_node *kn)
 	unsigned long flags;
 	int sz;
 
-	spin_lock_irqsave(&kernfs_rename_lock, flags);
+	spin_lock_irqsave(&kernfs_pr_cont_lock, flags);
 
-	sz = kernfs_path_from_node_locked(kn, NULL, kernfs_pr_cont_buf,
-					  sizeof(kernfs_pr_cont_buf));
+	sz = kernfs_path_from_node(kn, NULL, kernfs_pr_cont_buf,
+				   sizeof(kernfs_pr_cont_buf));
 	if (sz < 0) {
 		pr_cont("(error)");
 		goto out;
@@ -270,7 +278,7 @@ void pr_cont_kernfs_path(struct kernfs_node *kn)
 	pr_cont("%s", kernfs_pr_cont_buf);
 
 out:
-	spin_unlock_irqrestore(&kernfs_rename_lock, flags);
+	spin_unlock_irqrestore(&kernfs_pr_cont_lock, flags);
 }
 
 /**
@@ -841,13 +849,12 @@ static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent,
 
 	lockdep_assert_held_read(&kernfs_root(parent)->kernfs_rwsem);
 
-	/* grab kernfs_rename_lock to piggy back on kernfs_pr_cont_buf */
-	spin_lock_irq(&kernfs_rename_lock);
+	spin_lock_irq(&kernfs_pr_cont_lock);
 
 	len = strlcpy(kernfs_pr_cont_buf, path, sizeof(kernfs_pr_cont_buf));
 
 	if (len >= sizeof(kernfs_pr_cont_buf)) {
-		spin_unlock_irq(&kernfs_rename_lock);
+		spin_unlock_irq(&kernfs_pr_cont_lock);
 		return NULL;
 	}
 
@@ -859,7 +866,7 @@ static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent,
 		parent = kernfs_find_ns(parent, name, ns);
 	}
 
-	spin_unlock_irq(&kernfs_rename_lock);
+	spin_unlock_irq(&kernfs_pr_cont_lock);
 
 	return parent;
 }