diff mbox series

[v8,2/8] fs: Add standard casefolding support

Message ID 20200307023611.204708-3-drosen@google.com
State New
Headers show
Series Support for Casefolding and Encryption | expand

Commit Message

Daniel Rosenberg March 7, 2020, 2:36 a.m. UTC
This adds general supporting functions for filesystems that use
utf8 casefolding. It provides standard dentry_operations and adds the
necessary structures in struct super_block to allow this standardization.

Signed-off-by: Daniel Rosenberg <drosen@google.com>
---
 fs/libfs.c         | 114 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/fs.h |  22 +++++++++
 2 files changed, 136 insertions(+)

Comments

Al Viro March 7, 2020, 3:48 a.m. UTC | #1
On Fri, Mar 06, 2020 at 06:36:05PM -0800, Daniel Rosenberg wrote:

> +/**
> + * generic_ci_d_hash - generic implementation of d_hash for casefolding
> + * @dentry: Entry whose name we are hashing
> + * @len: length of str
> + * @qstr: name of the dentry, safely paired with len
> + * @str: qstr to set hash of
> + *
> + * This performs a case insensitive hash of the given str.
> + * If casefolding is not required, it leaves the hash unchanged.
> + */
> +int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str)
> +{
> +	const struct inode *inode = READ_ONCE(dentry->d_inode);
> +	struct super_block *sb = dentry->d_sb;
> +	const struct unicode_map *um = sb->s_encoding;
> +	char small_name[DNAME_INLINE_LEN];
> +	struct qstr entry = QSTR_INIT(str->name, str->len);
> +	int ret = 0;
> +
> +	if (!inode || !needs_casefold(inode))
> +		return 0;
> +
> +	if (make_name_stable(um, dentry, &entry, small_name))
> +		goto err;
> +	ret = utf8_casefold_hash(um, dentry, &entry);
> +	if (ret < 0)
> +		goto err;
> +
> +	return 0;
> +err:
> +	if (sb_has_enc_strict_mode(sb))
> +		ret = -EINVAL;
> +	else
> +		ret = 0;
> +	return ret;
> +}

	Have you even tested that?  Could you tell me where does the calculated
hash go?  And just what is it doing trying to check if the name we are about to
look up in directory specified by 'dentry' might be pointing to dentry->d_iname?
Daniel Rosenberg March 12, 2020, 10:11 p.m. UTC | #2
On Fri, Mar 6, 2020 at 7:48 PM Al Viro <viro@zeniv.linux.org.uk> wrote:
>
> On Fri, Mar 06, 2020 at 06:36:05PM -0800, Daniel Rosenberg wrote:
>
>         Have you even tested that?  Could you tell me where does the calculated
> hash go?  And just what is it doing trying to check if the name we are about to
> look up in directory specified by 'dentry' might be pointing to dentry->d_iname?

Turns out I tested exactly not that :/ Ran tests on the wrong kernel.
I've fixed my setup so that shouldn't happen again. The calculated
hash there goes exactly nowhere because I failed to copy it back into
the original qstr.
I'm trying to see if the name is a small name, which, if my
understanding is correct, is the only time a name might change from
underneath you in an RCU context. This assumes that the name either
comes from the dentry, or is otherwise not subject to changes. It's
based around the check that take_dentry_name_snapshot does. It does
feel a bit sketchy to assume that, so I'm very open to other
suggestions there.

I'm going through that hassle because the various utf8 functions do a
lot of dereferencing the string and manipulating pointers by those
values, expecting them to be consistent. It might be enough to just go
through that code and add a bunch of checks to make sure we can't
accidentally walk off of either end.
diff mbox series

Patch

diff --git a/fs/libfs.c b/fs/libfs.c
index c686bd9caac67..0eaa63a9ae037 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -20,6 +20,8 @@ 
 #include <linux/fs_context.h>
 #include <linux/pseudo_fs.h>
 #include <linux/fsnotify.h>
+#include <linux/unicode.h>
+#include <linux/fscrypt.h>
 
 #include <linux/uaccess.h>
 
@@ -1361,3 +1363,115 @@  bool is_empty_dir_inode(struct inode *inode)
 	return (inode->i_fop == &empty_dir_operations) &&
 		(inode->i_op == &empty_dir_inode_operations);
 }
+
+#ifdef CONFIG_UNICODE
+/**
+ * needs_casefold - determine if casefolding applies for a given directory
+ * @dir:	Folder to check
+ *
+ * This function returns true if dentries within this folder should be
+ * casefolded. If a folder is encrypted, but we don't have the key, it is not
+ * meaningful to casefold the no-key token name.
+ */
+bool needs_casefold(const struct inode *dir)
+{
+	return IS_CASEFOLDED(dir) && dir->i_sb->s_encoding &&
+			(!IS_ENCRYPTED(dir) || fscrypt_has_encryption_key(dir));
+}
+EXPORT_SYMBOL(needs_casefold);
+
+/*
+ * Under RCU, small names may change, but utf8 expects a stable name
+ * This operates similarly to take_dentry_name_snapshot, except that there
+ * is no guarantee that it grabs a coherent string.
+ */
+static int make_name_stable(const struct unicode_map *um,
+			   const struct dentry *dentry, struct qstr *entry,
+			   char *buff)
+{
+	if (dentry->d_iname != (const unsigned char *)entry->name)
+		return 0;
+
+	memcpy(buff, entry->name, entry->len + 1);
+	entry->name = buff;
+	return utf8_validate(um, entry);
+}
+
+/**
+ * generic_ci_d_compare - generic implementation of d_compare for casefolding
+ * @dentry: Entry we are comparing against
+ * @len: length of str
+ * @str: name of the dentry, safely paired with len
+ * @name: qstr to test against
+ *
+ * This performs a case insensitive comparison between the given name and str.
+ * It can be used as d_compare for dentry_operations.
+ */
+int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
+			  const char *str, const struct qstr *name)
+{
+	const struct dentry *parent = READ_ONCE(dentry->d_parent);
+	const struct inode *inode = READ_ONCE(parent->d_inode);
+	const struct super_block *sb = dentry->d_sb;
+	const struct unicode_map *um = sb->s_encoding;
+	char small_name[DNAME_INLINE_LEN];
+	struct qstr entry = QSTR_INIT(str, len);
+	int ret;
+
+	if (!inode || !needs_casefold(inode))
+		goto fallback;
+
+	/* Under RCU, small names may change, but utf8 expects a stable name */
+	if (make_name_stable(um, dentry, &entry, small_name))
+		goto err;
+	ret = utf8_strncasecmp(um, name, &entry);
+	if (ret >= 0)
+		return ret;
+err:
+	if (sb_has_enc_strict_mode(sb))
+		return -EINVAL;
+fallback:
+	if (len != name->len)
+		return 1;
+	return !!memcmp(str, name->name, len);
+}
+EXPORT_SYMBOL(generic_ci_d_compare);
+
+/**
+ * generic_ci_d_hash - generic implementation of d_hash for casefolding
+ * @dentry: Entry whose name we are hashing
+ * @len: length of str
+ * @qstr: name of the dentry, safely paired with len
+ * @str: qstr to set hash of
+ *
+ * This performs a case insensitive hash of the given str.
+ * If casefolding is not required, it leaves the hash unchanged.
+ */
+int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str)
+{
+	const struct inode *inode = READ_ONCE(dentry->d_inode);
+	struct super_block *sb = dentry->d_sb;
+	const struct unicode_map *um = sb->s_encoding;
+	char small_name[DNAME_INLINE_LEN];
+	struct qstr entry = QSTR_INIT(str->name, str->len);
+	int ret = 0;
+
+	if (!inode || !needs_casefold(inode))
+		return 0;
+
+	if (make_name_stable(um, dentry, &entry, small_name))
+		goto err;
+	ret = utf8_casefold_hash(um, dentry, &entry);
+	if (ret < 0)
+		goto err;
+
+	return 0;
+err:
+	if (sb_has_enc_strict_mode(sb))
+		ret = -EINVAL;
+	else
+		ret = 0;
+	return ret;
+}
+EXPORT_SYMBOL(generic_ci_d_hash);
+#endif
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3cd4fe6b845e7..8d20a3daa49a0 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1382,6 +1382,12 @@  extern int send_sigurg(struct fown_struct *fown);
 #define SB_ACTIVE	(1<<30)
 #define SB_NOUSER	(1<<31)
 
+/* These flags relate to encoding and casefolding, and are stored on disk */
+#define SB_ENC_STRICT_MODE_FL	(1 << 0)
+
+#define sb_has_enc_strict_mode(sb) \
+	(sb->s_encoding_flags & SB_ENC_STRICT_MODE_FL)
+
 /*
  *	Umount options
  */
@@ -1449,6 +1455,10 @@  struct super_block {
 #endif
 #ifdef CONFIG_FS_VERITY
 	const struct fsverity_operations *s_vop;
+#endif
+#ifdef CONFIG_UNICODE
+	struct unicode_map *s_encoding;
+	u16 s_encoding_flags;
 #endif
 	struct hlist_bl_head	s_roots;	/* alternate root dentries for NFS */
 	struct list_head	s_mounts;	/* list of mounts; _not_ for fs use */
@@ -3368,6 +3378,18 @@  extern int generic_file_fsync(struct file *, loff_t, loff_t, int);
 
 extern int generic_check_addressable(unsigned, u64);
 
+#ifdef CONFIG_UNICODE
+extern int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str);
+extern int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
+				const char *str, const struct qstr *name);
+extern bool needs_casefold(const struct inode *dir);
+#else
+static inline bool needs_casefold(const struct inode *dir)
+{
+	return false;
+}
+#endif
+
 #ifdef CONFIG_MIGRATION
 extern int buffer_migrate_page(struct address_space *,
 				struct page *, struct page *,