[PATCH 3/4] fs/resctrl: Fix deadlock for errors during mount

[Tony Luck]

From: Reinette Chatre <reinette.chatre@xxxxxxxxx>

Sashiko noticed[1] a deadlock in the resctrl mount code.

rdt_get_tree() acquires rdtgroup_mutex before calling kernfs_get_tree(). If
superblock setup fails inside kernfs_get_tree(), the VFS calls kill_sb on
the same thread before the call returns.  rdt_kill_sb() unconditionally
attempts to acquire rdtgroup_mutex and deadlock occurs.

Move the call to kernfs_get_tree() outside of locks.

Add resctrl_unmount() helper to keep code consistent between the
rdt_get_tree() failure path and a normal unmount.

If kernfs_get_tree() fails and ctx->kfc.new_sb_created is set, then rdt_kill_sb()
has already been called and no further cleanup is needed.

Fixes: 5ff193fbde20 ("x86/intel_rdt: Add basic resctrl filesystem support")
Co-developed-by: Tony Luck <tony.luck@xxxxxxxxx>
Signed-off-by: Tony Luck <tony.luck@xxxxxxxxx>
Link: https://sashiko.dev/#/patchset/20260429184858.36423-1-tony.luck%40intel.com [1]
---
 fs/resctrl/rdtgroup.c | 63 ++++++++++++++++++++++++-------------------
 1 file changed, 36 insertions(+), 27 deletions(-)

diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index 0db1a92aefbe..62e1e4c30f78 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -2970,6 +2970,29 @@ static void resctrl_fs_teardown(void)
 	rdtgroup_destroy_root();
 }
 
+static void resctrl_unmount(void)
+{
+	struct rdt_resource *r;
+
+	cpus_read_lock();
+	mutex_lock(&rdtgroup_mutex);
+
+	rdt_disable_ctx();
+
+	/* Put everything back to default values. */
+	for_each_alloc_capable_rdt_resource(r)
+		resctrl_arch_reset_all_ctrls(r);
+
+	resctrl_fs_teardown();
+	if (resctrl_arch_alloc_capable())
+		resctrl_arch_disable_alloc();
+	if (resctrl_arch_mon_capable())
+		resctrl_arch_disable_mon();
+	resctrl_mounted = false;
+	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
+}
+
 static int rdt_get_tree(struct fs_context *fc)
 {
 	struct rdt_fs_context *ctx = rdt_fc2context(fc);
@@ -3043,10 +3066,6 @@ static int rdt_get_tree(struct fs_context *fc)
 	if (ret)
 		goto out_mondata;
 
-	ret = kernfs_get_tree(fc);
-	if (ret < 0)
-		goto out_psl;
-
 	if (resctrl_arch_alloc_capable())
 		resctrl_arch_enable_alloc();
 	if (resctrl_arch_mon_capable())
@@ -3062,10 +3081,19 @@ static int rdt_get_tree(struct fs_context *fc)
 						   RESCTRL_PICK_ANY_CPU);
 	}
 
-	goto out;
+	rdt_last_cmd_clear();
+	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
+
+	ret = kernfs_get_tree(fc);
+	/*
+	 * resctrl can only be mounted once, new superblock only expected
+	 * to be created once.
+	 */
+	if (!ctx->kfc.new_sb_created)
+		resctrl_unmount();
+	return ret;
 
-out_psl:
-	rdt_pseudo_lock_release();
 out_mondata:
 	if (resctrl_arch_mon_capable()) {
 		mon_put_kn_priv();
@@ -3086,7 +3114,6 @@ static int rdt_get_tree(struct fs_context *fc)
 out_root:
 	rdtgroup_destroy_root();
 out:
-	rdt_last_cmd_clear();
 	mutex_unlock(&rdtgroup_mutex);
 	cpus_read_unlock();
 	return ret;
@@ -3173,26 +3200,8 @@ static int rdt_init_fs_context(struct fs_context *fc)
 
 static void rdt_kill_sb(struct super_block *sb)
 {
-	struct rdt_resource *r;
-
-	cpus_read_lock();
-	mutex_lock(&rdtgroup_mutex);
-
-	rdt_disable_ctx();
-
-	/* Put everything back to default values. */
-	for_each_alloc_capable_rdt_resource(r)
-		resctrl_arch_reset_all_ctrls(r);
-
-	resctrl_fs_teardown();
-	if (resctrl_arch_alloc_capable())
-		resctrl_arch_disable_alloc();
-	if (resctrl_arch_mon_capable())
-		resctrl_arch_disable_mon();
-	resctrl_mounted = false;
+	resctrl_unmount();
 	kernfs_kill_sb(sb);
-	mutex_unlock(&rdtgroup_mutex);
-	cpus_read_unlock();
 }
 
 static struct file_system_type rdt_fs_type = {
-- 
2.54.0