fscrypt caches decrypted symlink targets in inode->i_link. The VFS
can return that target without calling the filesystem's ->get_link(),
so access checks in that callback cannot revoke a previously cached
link. CephFS subvolume quarantine needs those checks even when
readlinkat() uses an empty path on an O_PATH descriptor opened before
quarantine.

Add a filesystem opt-out that prevents both creation-time and lookup-
time cache installation. Leave cache readers unchanged: the option is
fixed before inode creation, so they find no cached target. Uncached
targets use the existing delayed-free callback.

Opting out costs a temporary allocation and decryption on each access
to an encrypted symlink, including readlink, traversal and lstat. Other
filesystems keep their existing caching behavior. The Ceph opt-in is
in the quarantine enforcement patch in this series.

Signed-off-by: Alex Markuze <amarkuze@redhat.com>
---
 fs/crypto/hooks.c       | 28 +++++++++++++++-------------
 include/linux/fscrypt.h |  7 +++++++
 2 files changed, 22 insertions(+), 13 deletions(-)

diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c
index a7a8a3f581a0..6bc7ac82ec34 100644
--- a/fs/crypto/hooks.c
+++ b/fs/crypto/hooks.c
@@ -321,11 +321,13 @@ int __fscrypt_encrypt_symlink(struct inode *inode, const char *target,
 	 */
 	sd->encrypted_path[ciphertext_len] = '\0';
 
-	/* Cache the plaintext symlink target for later use by get_link() */
-	err = -ENOMEM;
-	inode->i_link = kmemdup(target, len + 1, GFP_NOFS);
-	if (!inode->i_link)
-		goto err_free_sd;
+	/* Cache the plaintext target unless the filesystem revalidates it. */
+	if (!inode->i_sb->s_cop->no_symlink_cache) {
+		err = -ENOMEM;
+		inode->i_link = kmemdup(target, len + 1, GFP_NOFS);
+		if (!inode->i_link)
+			goto err_free_sd;
+	}
 
 	if (!disk_link->name)
 		disk_link->name = (unsigned char *)sd;
@@ -411,12 +413,12 @@ const char *fscrypt_get_symlink(struct inode *inode, const void *caddr,
 	pstr.name[pstr.len] = '\0';
 
 	/*
-	 * Cache decrypted symlink targets in i_link for later use.  Don't cache
-	 * symlink targets encoded without the key, since those become outdated
-	 * once the key is added.  This pairs with the READ_ONCE() above and in
-	 * the VFS path lookup code.
+	 * Cache decrypted targets unless the filesystem revalidates them.
+	 * Don't cache targets encoded without the key, since those become
+	 * outdated once the key is added. This pairs with the READ_ONCE()
+	 * above and in the VFS path lookup code.
 	 */
-	if (!has_key ||
+	if (inode->i_sb->s_cop->no_symlink_cache || !has_key ||
 	    cmpxchg_release(&inode->i_link, NULL, pstr.name) != NULL)
 		set_delayed_call(done, kfree_link, pstr.name);
 
@@ -442,9 +444,9 @@ EXPORT_SYMBOL_GPL(fscrypt_get_symlink);
  * This requires reading the symlink target from disk if needed, setting up the
  * inode's encryption key if possible, and then decrypting or encoding the
  * symlink target.  This makes lstat() more heavyweight than is normally the
- * case.  However, decrypted symlink targets will be cached in ->i_link, so
- * usually the symlink won't have to be read and decrypted again later if/when
- * it is actually followed, readlink() is called, or lstat() is called again.
+ * case. Unless the filesystem sets no_symlink_cache, decrypted targets
+ * are cached in ->i_link, avoiding another read and decryption when the
+ * symlink is followed, readlink() is called, or lstat() is called again.
  *
  * Return: 0 on success, -errno on failure
  */
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index 28f2108e29f3..ab77e685c75c 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -107,6 +107,13 @@ struct fscrypt_operations {
 	 */
 	unsigned int supports_subblock_data_units : 1;
 
+	/*
+	 * Don't populate ->i_link, so every access calls ->get_link() and the
+	 * filesystem can revalidate access. Set before creating any inodes;
+	 * this option cannot invalidate previously cached targets.
+	 */
+	unsigned int no_symlink_cache : 1;
+
 	/*
 	 * This field exists only for backwards compatibility reasons and should
 	 * only be set by the filesystems that are setting it already.  It