Merge tag 'fscrypt_for_linus' of git://git.kernel.org/pub/scm/fs/fscr…

…ypt/fscrypt

Pull fscrypt updates from Ted Ts'o:
 "Clean up fscrypt's dcache revalidation support, and other
  miscellaneous cleanups"

* tag 'fscrypt_for_linus' of git://git.kernel.org/pub/scm/fs/fscrypt/fscrypt:
  fscrypt: cache decrypted symlink target in ->i_link
  vfs: use READ_ONCE() to access ->i_link
  fscrypt: fix race where ->lookup() marks plaintext dentry as ciphertext
  fscrypt: only set dentry_operations on ciphertext dentries
  fs, fscrypt: clear DCACHE_ENCRYPTED_NAME when unaliasing directory
  fscrypt: fix race allowing rename() and link() of ciphertext dentries
  fscrypt: clean up and improve dentry revalidation
  fscrypt: use READ_ONCE() to access ->i_crypt_info
  fscrypt: remove WARN_ON_ONCE() when decryption fails
  fscrypt: drop inode argument from fscrypt_get_ctx()

fs/crypto/bio.c

@@ -36,12 +36,10 @@ static void __fscrypt_decrypt_bio(struct bio *bio, bool done)
 		int ret = fscrypt_decrypt_page(page->mapping->host, page,
 				PAGE_SIZE, 0, page->index);
 
-		if (ret) {
-			WARN_ON_ONCE(1);
+		if (ret)
 			SetPageError(page);
-		} else if (done) {
+		else if (done)
 			SetPageUptodate(page);
-		}
 		if (done)
 			unlock_page(page);
 	}
@@ -103,7 +101,7 @@ int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk,
 
 	BUG_ON(inode->i_sb->s_blocksize != PAGE_SIZE);
 
-	ctx = fscrypt_get_ctx(inode, GFP_NOFS);
+	ctx = fscrypt_get_ctx(GFP_NOFS);
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 

fs/crypto/crypto.c

@@ -87,23 +87,17 @@ EXPORT_SYMBOL(fscrypt_release_ctx);
 
 /**
  * fscrypt_get_ctx() - Gets an encryption context
- * @inode:       The inode for which we are doing the crypto
  * @gfp_flags:   The gfp flag for memory allocation
  *
  * Allocates and initializes an encryption context.
  *
- * Return: An allocated and initialized encryption context on success; error
- * value or NULL otherwise.
+ * Return: A new encryption context on success; an ERR_PTR() otherwise.
  */
-struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *inode, gfp_t gfp_flags)
+struct fscrypt_ctx *fscrypt_get_ctx(gfp_t gfp_flags)
 {
-	struct fscrypt_ctx *ctx = NULL;
-	struct fscrypt_info *ci = inode->i_crypt_info;
+	struct fscrypt_ctx *ctx;
 	unsigned long flags;
 
-	if (ci == NULL)
-		return ERR_PTR(-ENOKEY);
-
 	/*
 	 * We first try getting the ctx from a free list because in
 	 * the common case the ctx will have an allocated and
@@ -258,9 +252,9 @@ struct page *fscrypt_encrypt_page(const struct inode *inode,
 
 	BUG_ON(!PageLocked(page));
 
-	ctx = fscrypt_get_ctx(inode, gfp_flags);
+	ctx = fscrypt_get_ctx(gfp_flags);
 	if (IS_ERR(ctx))
-		return (struct page *)ctx;
+		return ERR_CAST(ctx);
 
 	/* The encryption operation will require a bounce page. */
 	ciphertext_page = fscrypt_alloc_bounce_page(ctx, gfp_flags);
@@ -313,45 +307,47 @@ int fscrypt_decrypt_page(const struct inode *inode, struct page *page,
 EXPORT_SYMBOL(fscrypt_decrypt_page);
 
 /*
- * Validate dentries for encrypted directories to make sure we aren't
- * potentially caching stale data after a key has been added or
- * removed.
+ * Validate dentries in encrypted directories to make sure we aren't potentially
+ * caching stale dentries after a key has been added.
  */
 static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	struct dentry *dir;
-	int dir_has_key, cached_with_key;
+	int err;
+	int valid;
+
+	/*
+	 * Plaintext names are always valid, since fscrypt doesn't support
+	 * reverting to ciphertext names without evicting the directory's inode
+	 * -- which implies eviction of the dentries in the directory.
+	 */
+	if (!(dentry->d_flags & DCACHE_ENCRYPTED_NAME))
+		return 1;
+
+	/*
+	 * Ciphertext name; valid if the directory's key is still unavailable.
+	 *
+	 * Although fscrypt forbids rename() on ciphertext names, we still must
+	 * use dget_parent() here rather than use ->d_parent directly.  That's
+	 * because a corrupted fs image may contain directory hard links, which
+	 * the VFS handles by moving the directory's dentry tree in the dcache
+	 * each time ->lookup() finds the directory and it already has a dentry
+	 * elsewhere.  Thus ->d_parent can be changing, and we must safely grab
+	 * a reference to some ->d_parent to prevent it from being freed.
+	 */
 
 	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
 	dir = dget_parent(dentry);
-	if (!IS_ENCRYPTED(d_inode(dir))) {
-		dput(dir);
-		return 0;
-	}
-
-	spin_lock(&dentry->d_lock);
-	cached_with_key = dentry->d_flags & DCACHE_ENCRYPTED_WITH_KEY;
-	spin_unlock(&dentry->d_lock);
-	dir_has_key = (d_inode(dir)->i_crypt_info != NULL);
+	err = fscrypt_get_encryption_info(d_inode(dir));
+	valid = !fscrypt_has_encryption_key(d_inode(dir));
 	dput(dir);
 
-	/*
-	 * If the dentry was cached without the key, and it is a
-	 * negative dentry, it might be a valid name.  We can't check
-	 * if the key has since been made available due to locking
-	 * reasons, so we fail the validation so ext4_lookup() can do
-	 * this check.
-	 *
-	 * We also fail the validation if the dentry was created with
-	 * the key present, but we no longer have the key, or vice versa.
-	 */
-	if ((!cached_with_key && d_is_negative(dentry)) ||
-			(!cached_with_key && dir_has_key) ||
-			(cached_with_key && !dir_has_key))
-		return 0;
-	return 1;
+	if (err < 0)
+		return err;
+
+	return valid;
 }
 
 const struct dentry_operations fscrypt_d_ops = {

fs/crypto/fname.c

@@ -269,7 +269,7 @@ int fscrypt_fname_disk_to_usr(struct inode *inode,
 	if (iname->len < FS_CRYPTO_BLOCK_SIZE)
 		return -EUCLEAN;
 
-	if (inode->i_crypt_info)
+	if (fscrypt_has_encryption_key(inode))
 		return fname_decrypt(inode, iname, oname);
 
 	if (iname->len <= FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE) {
@@ -336,7 +336,7 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
 	if (ret)
 		return ret;
 
-	if (dir->i_crypt_info) {
+	if (fscrypt_has_encryption_key(dir)) {
 		if (!fscrypt_fname_encrypted_size(dir, iname->len,
 						  dir->i_sb->s_cop->max_namelen,
 						  &fname->crypto_buf.len))
@@ -356,6 +356,7 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
 	}
 	if (!lookup)
 		return -ENOKEY;
+	fname->is_ciphertext_name = true;
 
 	/*
 	 * We don't have the key and we are doing a lookup; decode the

fs/crypto/hooks.c

@@ -49,14 +49,19 @@ int fscrypt_file_open(struct inode *inode, struct file *filp)
 }
 EXPORT_SYMBOL_GPL(fscrypt_file_open);
 
-int __fscrypt_prepare_link(struct inode *inode, struct inode *dir)
+int __fscrypt_prepare_link(struct inode *inode, struct inode *dir,
+			   struct dentry *dentry)
 {
 	int err;
 
 	err = fscrypt_require_key(dir);
 	if (err)
 		return err;
 
+	/* ... in case we looked up ciphertext name before key was added */
+	if (dentry->d_flags & DCACHE_ENCRYPTED_NAME)
+		return -ENOKEY;
+
 	if (!fscrypt_has_permitted_context(dir, inode))
 		return -EXDEV;
 
@@ -78,6 +83,11 @@ int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (err)
 		return err;
 
+	/* ... in case we looked up ciphertext name(s) before key was added */
+	if ((old_dentry->d_flags | new_dentry->d_flags) &
+	    DCACHE_ENCRYPTED_NAME)
+		return -ENOKEY;
+
 	if (old_dir != new_dir) {
 		if (IS_ENCRYPTED(new_dir) &&
 		    !fscrypt_has_permitted_context(new_dir,
@@ -94,21 +104,21 @@ int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry,
 }
 EXPORT_SYMBOL_GPL(__fscrypt_prepare_rename);
 
-int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry)
+int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry,
+			     struct fscrypt_name *fname)
 {
-	int err = fscrypt_get_encryption_info(dir);
+	int err = fscrypt_setup_filename(dir, &dentry->d_name, 1, fname);
 
-	if (err)
+	if (err && err != -ENOENT)
 		return err;
 
-	if (fscrypt_has_encryption_key(dir)) {
+	if (fname->is_ciphertext_name) {
 		spin_lock(&dentry->d_lock);
-		dentry->d_flags |= DCACHE_ENCRYPTED_WITH_KEY;
+		dentry->d_flags |= DCACHE_ENCRYPTED_NAME;
 		spin_unlock(&dentry->d_lock);
+		d_set_d_op(dentry, &fscrypt_d_ops);
 	}
-
-	d_set_d_op(dentry, &fscrypt_d_ops);
-	return 0;
+	return err;
 }
 EXPORT_SYMBOL_GPL(__fscrypt_prepare_lookup);
 
@@ -179,21 +189,30 @@ int __fscrypt_encrypt_symlink(struct inode *inode, const char *target,
 	sd->len = cpu_to_le16(ciphertext_len);
 
 	err = fname_encrypt(inode, &iname, sd->encrypted_path, ciphertext_len);
-	if (err) {
-		if (!disk_link->name)
-			kfree(sd);
-		return err;
-	}
+	if (err)
+		goto err_free_sd;
+
 	/*
 	 * Null-terminating the ciphertext doesn't make sense, but we still
 	 * count the null terminator in the length, so we might as well
 	 * initialize it just in case the filesystem writes it out.
 	 */
 	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;
+
 	if (!disk_link->name)
 		disk_link->name = (unsigned char *)sd;
 	return 0;
+
+err_free_sd:
+	if (!disk_link->name)
+		kfree(sd);
+	return err;
 }
 EXPORT_SYMBOL_GPL(__fscrypt_encrypt_symlink);
 
@@ -202,7 +221,7 @@ EXPORT_SYMBOL_GPL(__fscrypt_encrypt_symlink);
  * @inode: the symlink inode
  * @caddr: the on-disk contents of the symlink
  * @max_size: size of @caddr buffer
- * @done: if successful, will be set up to free the returned target
+ * @done: if successful, will be set up to free the returned target if needed
  *
  * If the symlink's encryption key is available, we decrypt its target.
  * Otherwise, we encode its target for presentation.
@@ -217,19 +236,26 @@ const char *fscrypt_get_symlink(struct inode *inode, const void *caddr,
 {
 	const struct fscrypt_symlink_data *sd;
 	struct fscrypt_str cstr, pstr;
+	bool has_key;
 	int err;
 
 	/* This is for encrypted symlinks only */
 	if (WARN_ON(!IS_ENCRYPTED(inode)))
 		return ERR_PTR(-EINVAL);
 
+	/* If the decrypted target is already cached, just return it. */
+	pstr.name = READ_ONCE(inode->i_link);
+	if (pstr.name)
+		return pstr.name;
+
 	/*
 	 * Try to set up the symlink's encryption key, but we can continue
 	 * regardless of whether the key is available or not.
 	 */
 	err = fscrypt_get_encryption_info(inode);
 	if (err)
 		return ERR_PTR(err);
+	has_key = fscrypt_has_encryption_key(inode);
 
 	/*
 	 * For historical reasons, encrypted symlink targets are prefixed with
@@ -261,7 +287,17 @@ const char *fscrypt_get_symlink(struct inode *inode, const void *caddr,
 		goto err_kfree;
 
 	pstr.name[pstr.len] = '\0';
-	set_delayed_call(done, kfree_link, pstr.name);
+
+	/*
+	 * 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.
+	 */
+	if (!has_key ||
+	    cmpxchg_release(&inode->i_link, NULL, pstr.name) != NULL)
+		set_delayed_call(done, kfree_link, pstr.name);
+
 	return pstr.name;
 
 err_kfree:

fs/crypto/keyinfo.c

@@ -508,7 +508,7 @@ int fscrypt_get_encryption_info(struct inode *inode)
 	u8 *raw_key = NULL;
 	int res;
 
-	if (inode->i_crypt_info)
+	if (fscrypt_has_encryption_key(inode))
 		return 0;
 
 	res = fscrypt_initialize(inode->i_sb->s_cop->flags);
@@ -572,7 +572,7 @@ int fscrypt_get_encryption_info(struct inode *inode)
 	if (res)
 		goto out;
 
-	if (cmpxchg(&inode->i_crypt_info, NULL, crypt_info) == NULL)
+	if (cmpxchg_release(&inode->i_crypt_info, NULL, crypt_info) == NULL)
 		crypt_info = NULL;
 out:
 	if (res == -ENOKEY)
@@ -583,9 +583,30 @@ int fscrypt_get_encryption_info(struct inode *inode)
 }
 EXPORT_SYMBOL(fscrypt_get_encryption_info);
 
+/**
+ * fscrypt_put_encryption_info - free most of an inode's fscrypt data
+ *
+ * Free the inode's fscrypt_info.  Filesystems must call this when the inode is
+ * being evicted.  An RCU grace period need not have elapsed yet.
+ */
 void fscrypt_put_encryption_info(struct inode *inode)
 {
 	put_crypt_info(inode->i_crypt_info);
 	inode->i_crypt_info = NULL;
 }
 EXPORT_SYMBOL(fscrypt_put_encryption_info);
+
+/**
+ * fscrypt_free_inode - free an inode's fscrypt data requiring RCU delay
+ *
+ * Free the inode's cached decrypted symlink target, if any.  Filesystems must
+ * call this after an RCU grace period, just before they free the inode.
+ */
+void fscrypt_free_inode(struct inode *inode)
+{
+	if (IS_ENCRYPTED(inode) && S_ISLNK(inode->i_mode)) {
+		kfree(inode->i_link);
+		inode->i_link = NULL;
+	}
+}
+EXPORT_SYMBOL(fscrypt_free_inode);

fs/crypto/policy.c

@@ -194,8 +194,8 @@ int fscrypt_has_permitted_context(struct inode *parent, struct inode *child)
 	res = fscrypt_get_encryption_info(child);
 	if (res)
 		return 0;
-	parent_ci = parent->i_crypt_info;
-	child_ci = child->i_crypt_info;
+	parent_ci = READ_ONCE(parent->i_crypt_info);
+	child_ci = READ_ONCE(child->i_crypt_info);
 
 	if (parent_ci && child_ci) {
 		return memcmp(parent_ci->ci_master_key_descriptor,
@@ -246,7 +246,7 @@ int fscrypt_inherit_context(struct inode *parent, struct inode *child,
 	if (res < 0)
 		return res;
 
-	ci = parent->i_crypt_info;
+	ci = READ_ONCE(parent->i_crypt_info);
 	if (ci == NULL)
 		return -ENOKEY;