[PATCH 2/2] ovl: enable RCU'd ->get_acl()

[Miklos Szeredi <mszeredi@xxxxxxxxxx>]

Overlayfs does not cache ACL's (to avoid double caching).  Instead it just
calls the underlying filesystem's i_op->get_acl(), which will return the
cached value, if possible.

In rcu path walk, however, get_cached_acl_rcu() is employed to get the
value from the cache, which will fail on overlayfs resulting in dropping
out of rcu walk mode.  This can result in a big performance hit in certain
situations.

Fix by calling ->get_acl() with LOOKUP_RCU flag in case of ACL_DONT_CACHE
(which indicates pass-through)

Reported-by: garyhuang <zjh.20052005@xxxxxxx>
Signed-off-by: Miklos Szeredi <mszeredi@xxxxxxxxxx>
---
 fs/overlayfs/inode.c | 7 ++++---
 fs/posix_acl.c       | 8 +++++++-
 include/linux/fs.h   | 5 +++++
 3 files changed, 16 insertions(+), 4 deletions(-)

diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 727154a1d3ce..6a55231b262a 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -13,6 +13,7 @@
 #include <linux/fiemap.h>
 #include <linux/fileattr.h>
 #include <linux/security.h>
+#include <linux/namei.h>
 #include "overlayfs.h"
 
 
@@ -454,12 +455,12 @@ struct posix_acl *ovl_get_acl(struct inode *inode, int type, int flags)
 	const struct cred *old_cred;
 	struct posix_acl *acl;
 
-	if (flags)
-		return ERR_PTR(-EINVAL);
-
 	if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !IS_POSIXACL(realinode))
 		return NULL;
 
+	if (flags & LOOKUP_RCU)
+		return get_cached_acl_rcu(realinode, type);
+
 	old_cred = ovl_override_creds(inode->i_sb);
 	acl = get_acl(realinode, type);
 	revert_creds(old_cred);
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 6b7f793e2b6f..4d1c6c266cf0 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -22,6 +22,7 @@
 #include <linux/xattr.h>
 #include <linux/export.h>
 #include <linux/user_namespace.h>
+#include <linux/namei.h>
 
 static struct posix_acl **acl_by_type(struct inode *inode, int type)
 {
@@ -56,7 +57,12 @@ EXPORT_SYMBOL(get_cached_acl);
 
 struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type)
 {
-	return rcu_dereference(*acl_by_type(inode, type));
+	struct posix_acl *acl = rcu_dereference(*acl_by_type(inode, type));
+
+	if (acl == ACL_DONT_CACHE)
+		acl = inode->i_op->get_acl(inode, type, LOOKUP_RCU);
+
+	return acl;
 }
 EXPORT_SYMBOL(get_cached_acl_rcu);
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 1c56d4fc4efe..20b7db2d0a85 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -581,6 +581,11 @@ static inline void mapping_allow_writable(struct address_space *mapping)
 
 struct posix_acl;
 #define ACL_NOT_CACHED ((void *)(-1))
+/*
+ * ACL_DONT_CACHE is for stacked filesystems, that rely on underlying fs to
+ * cache the ACL.  This also means that ->get_acl() can be called in RCU mode
+ * with the LOOKUP_RCU flag.
+ */
 #define ACL_DONT_CACHE ((void *)(-3))
 
 static inline struct posix_acl *
-- 
2.31.1