linux-doc.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Daniel Rosenberg <drosen@google.com>
To: "Theodore Ts'o" <tytso@mit.edu>,
	linux-ext4@vger.kernel.org, Jaegeuk Kim <jaegeuk@kernel.org>,
	Chao Yu <chao@kernel.org>,
	linux-f2fs-devel@lists.sourceforge.net,
	Eric Biggers <ebiggers@kernel.org>,
	linux-fscrypt@vger.kernel.org,
	Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Andreas Dilger <adilger.kernel@dilger.ca>,
	Jonathan Corbet <corbet@lwn.net>,
	linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-fsdevel@vger.kernel.org,
	Gabriel Krisman Bertazi <krisman@collabora.com>,
	kernel-team@android.com, Daniel Rosenberg <drosen@google.com>
Subject: [PATCH v2 2/6] vfs: Fold casefolding into vfs
Date: Mon,  6 Jan 2020 21:16:34 -0800	[thread overview]
Message-ID: <20200107051638.40893-3-drosen@google.com> (raw)
In-Reply-To: <20200107051638.40893-1-drosen@google.com>

Ext4 and F2fs are both using casefolding, and they, along with any other
filesystem that adds the feature, will be using identical dentry_ops.
Additionally, those dentry ops interfere with the dentry_ops required
for fscrypt once we add support for casefolding and encryption.
Moving this into the vfs removes code duplication as well as the
complication with encryption.

Currently this is pretty close to just moving the existing f2fs/ext4
code up a level into the vfs, although there is a lot of room for
improvement now.

Signed-off-by: Daniel Rosenberg <drosen@google.com>
---
 fs/dcache.c             | 28 ++++++++++++++++++++++++++++
 fs/namei.c              | 41 ++++++++++++++++++++++++++++++++++++++---
 include/linux/fs.h      | 10 ++++++++++
 include/linux/unicode.h | 14 ++++++++++++++
 4 files changed, 90 insertions(+), 3 deletions(-)

diff --git a/fs/dcache.c b/fs/dcache.c
index b280e07e162b1..a8bbb7f4fad30 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -32,6 +32,7 @@
 #include <linux/bit_spinlock.h>
 #include <linux/rculist_bl.h>
 #include <linux/list_lru.h>
+#include <linux/unicode.h>
 #include "internal.h"
 #include "mount.h"
 
@@ -247,7 +248,19 @@ static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *c
 	 * be no NUL in the ct/tcount data)
 	 */
 	const unsigned char *cs = READ_ONCE(dentry->d_name.name);
+#ifdef CONFIG_UNICODE
+	struct inode *parent = dentry->d_parent->d_inode;
 
+	if (unlikely(needs_casefold(parent))) {
+		const struct qstr n1 = QSTR_INIT(cs, tcount);
+		const struct qstr n2 = QSTR_INIT(ct, tcount);
+		int result = utf8_strncasecmp(dentry->d_sb->s_encoding,
+						&n1, &n2);
+
+		if (result >= 0 || sb_has_enc_strict_mode(dentry->d_sb))
+			return result;
+	}
+#endif
 	return dentry_string_cmp(cs, ct, tcount);
 }
 
@@ -2406,7 +2419,22 @@ struct dentry *d_hash_and_lookup(struct dentry *dir, struct qstr *name)
 	 * calculate the standard hash first, as the d_op->d_hash()
 	 * routine may choose to leave the hash value unchanged.
 	 */
+#ifdef CONFIG_UNICODE
+	unsigned char *hname = NULL;
+	int hlen = name->len;
+
+	if (IS_CASEFOLDED(dir->d_inode)) {
+		hname = kmalloc(PATH_MAX, GFP_ATOMIC);
+		if (!hname)
+			return ERR_PTR(-ENOMEM);
+		hlen = utf8_casefold(dir->d_sb->s_encoding,
+					name, hname, PATH_MAX);
+	}
+	name->hash = full_name_hash(dir, hname ?: name->name, hlen);
+	kfree(hname);
+#else
 	name->hash = full_name_hash(dir, name->name, name->len);
+#endif
 	if (dir->d_flags & DCACHE_OP_HASH) {
 		int err = dir->d_op->d_hash(dir, name);
 		if (unlikely(err < 0))
diff --git a/fs/namei.c b/fs/namei.c
index d6c91d1e88cb3..f8e65c9f31444 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -39,6 +39,7 @@
 #include <linux/bitops.h>
 #include <linux/init_task.h>
 #include <linux/uaccess.h>
+#include <linux/unicode.h>
 
 #include "internal.h"
 #include "mount.h"
@@ -2055,6 +2056,10 @@ static inline u64 hash_name(const void *salt, const char *name)
 static int link_path_walk(const char *name, struct nameidata *nd)
 {
 	int err;
+#ifdef CONFIG_UNICODE
+	char *hname = NULL;
+	int hlen = 0;
+#endif
 
 	if (IS_ERR(name))
 		return PTR_ERR(name);
@@ -2071,9 +2076,22 @@ static int link_path_walk(const char *name, struct nameidata *nd)
 		err = may_lookup(nd);
 		if (err)
 			return err;
-
+#ifdef CONFIG_UNICODE
+		if (needs_casefold(nd->path.dentry->d_inode)) {
+			struct qstr str = QSTR_INIT(name, PATH_MAX);
+
+			hname = kmalloc(PATH_MAX, GFP_ATOMIC);
+			if (!hname)
+				return -ENOMEM;
+			hlen = utf8_casefold(nd->path.dentry->d_sb->s_encoding,
+						&str, hname, PATH_MAX);
+		}
+		hash_len = hash_name(nd->path.dentry, hname ?: name);
+		kfree(hname);
+		hname = NULL;
+#else
 		hash_len = hash_name(nd->path.dentry, name);
-
+#endif
 		type = LAST_NORM;
 		if (name[0] == '.') switch (hashlen_len(hash_len)) {
 			case 2:
@@ -2445,9 +2463,26 @@ EXPORT_SYMBOL(vfs_path_lookup);
 static int lookup_one_len_common(const char *name, struct dentry *base,
 				 int len, struct qstr *this)
 {
+#ifdef CONFIG_UNICODE
+	char *hname = NULL;
+	int hlen = len;
+
+	if (needs_casefold(base->d_inode)) {
+		struct qstr str = QSTR_INIT(name, len);
+
+		hname = kmalloc(PATH_MAX, GFP_ATOMIC);
+		if (!hname)
+			return -ENOMEM;
+		hlen = utf8_casefold(base->d_sb->s_encoding,
+					&str, hname, PATH_MAX);
+	}
+	this->hash = full_name_hash(base, hname ?: name, hlen);
+	kfree(hname);
+#else
+	this->hash = full_name_hash(base, name, len);
+#endif
 	this->name = name;
 	this->len = len;
-	this->hash = full_name_hash(base, name, len);
 	if (!len)
 		return -EACCES;
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 98e0349adb526..9a7092449e94f 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 */
+#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 */
diff --git a/include/linux/unicode.h b/include/linux/unicode.h
index 990aa97d80496..182352f3cc30f 100644
--- a/include/linux/unicode.h
+++ b/include/linux/unicode.h
@@ -4,6 +4,8 @@
 
 #include <linux/init.h>
 #include <linux/dcache.h>
+#include <linux/fscrypt.h>
+#include <linux/fs.h>
 
 struct unicode_map {
 	const char *charset;
@@ -30,4 +32,16 @@ int utf8_casefold(const struct unicode_map *um, const struct qstr *str,
 struct unicode_map *utf8_load(const char *version);
 void utf8_unload(struct unicode_map *um);
 
+#ifdef CONFIG_UNICODE
+static inline bool needs_casefold(const struct inode *dir)
+{
+	return IS_CASEFOLDED(dir) && dir->i_sb->s_encoding &&
+			(!IS_ENCRYPTED(dir) || fscrypt_has_encryption_key(dir));
+}
+#else
+static inline bool needs_casefold(const struct inode *dir)
+{
+	return 0;
+}
+#endif
 #endif /* _LINUX_UNICODE_H */
-- 
2.24.1.735.g03f4e72817-goog


  parent reply	other threads:[~2020-01-07  5:17 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-01-07  5:16 [PATCH v2 0/6] Support for Casefolding and Encryption Daniel Rosenberg
2020-01-07  5:16 ` [PATCH v2 1/6] TMP: fscrypt: Add support for casefolding with encryption Daniel Rosenberg
2020-01-07  5:16 ` Daniel Rosenberg [this message]
2020-01-07  5:16 ` [PATCH v2 3/6] f2fs: Handle casefolding with Encryption Daniel Rosenberg
2020-01-07  5:16 ` [PATCH v2 4/6] ext4: Use struct super_blocks' casefold data Daniel Rosenberg
2020-01-07  5:16 ` [PATCH v2 5/6] ext4: Hande casefolding with encryption Daniel Rosenberg
2020-01-07  5:16 ` [PATCH v2 6/6] ext4: Optimize match for casefolded encrypted dirs Daniel Rosenberg
2020-01-08 18:50 ` [PATCH v2 0/6] Support for Casefolding and Encryption Theodore Y. Ts'o
2020-01-08 21:24   ` Daniel Rosenberg

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200107051638.40893-3-drosen@google.com \
    --to=drosen@google.com \
    --cc=adilger.kernel@dilger.ca \
    --cc=chao@kernel.org \
    --cc=corbet@lwn.net \
    --cc=ebiggers@kernel.org \
    --cc=jaegeuk@kernel.org \
    --cc=kernel-team@android.com \
    --cc=krisman@collabora.com \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-ext4@vger.kernel.org \
    --cc=linux-f2fs-devel@lists.sourceforge.net \
    --cc=linux-fscrypt@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=tytso@mit.edu \
    --cc=viro@zeniv.linux.org.uk \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).