Bug#685407: [wheezy] ext4 dir_index + nfs duplicate cookies problem with large dovecot maildirs
Jonathan Nieder wrote:
> Brian Kroth wrote:
>> linux-image-3.5-trunk-amd64 (3.5-1~experimental.1) on the server
>> does indeed appear to fix this.
[...]
> Very nice to hear.
>
> Please test the attached patches together against a 3.2.y kernel,
> for example using the following instructions.
Actually attached this time. Sorry for the confusion.
From: Bernd Schubert <bernd.schubert@itwm.fraunhofer.de>
Date: Tue, 13 Mar 2012 22:51:38 -0400
Subject: fs: add new FMODE flags: FMODE_32bithash and FMODE_64bithash
commit 6a8a13e03861c0ab83ab07d573ca793cff0e5d00 upstream.
Those flags are supposed to be set by NFS readdir() to tell ext3/ext4
to 32bit (NFSv2) or 64bit hash values (offsets) in seekdir().
Signed-off-by: Bernd Schubert <bernd.schubert@itwm.fraunhofer.de>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
---
include/linux/fs.h | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 29b6353..fb7ce74 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -92,6 +92,10 @@ struct inodes_stat_t {
/* File is opened using open(.., 3, ..) and is writeable only for ioctls
(specialy hack for floppy.c) */
#define FMODE_WRITE_IOCTL ((__force fmode_t)0x100)
+/* 32bit hashes as llseek() offset (for directories) */
+#define FMODE_32BITHASH ((__force fmode_t)0x200)
+/* 64bit hashes as llseek() offset (for directories) */
+#define FMODE_64BITHASH ((__force fmode_t)0x400)
/*
* Don't update ctime and mtime.
--
1.7.10.4
From: Fan Yong <yong.fan@whamcloud.com>
Date: Sun, 18 Mar 2012 22:44:40 -0400
Subject: ext4: return 32/64-bit dir name hash according to usage type
commit d1f5273e9adb40724a85272f248f210dc4ce919a upstream.
Traditionally ext2/3/4 has returned a 32-bit hash value from llseek()
to appease NFSv2, which can only handle a 32-bit cookie for seekdir()
and telldir(). However, this causes problems if there are 32-bit hash
collisions, since the NFSv2 server can get stuck resending the same
entries from the directory repeatedly.
Allow ext4 to return a full 64-bit hash (both major and minor) for
telldir to decrease the chance of hash collisions. This still needs
integration on the NFS side.
Patch-updated-by: Bernd Schubert <bernd.schubert@itwm.fraunhofer.de>
(blame me if something is not correct)
Signed-off-by: Fan Yong <yong.fan@whamcloud.com>
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Signed-off-by: Bernd Schubert <bernd.schubert@itwm.fraunhofer.de>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
---
fs/ext4/dir.c | 214 ++++++++++++++++++++++++++++++++++++++++++++------------
fs/ext4/ext4.h | 6 +-
fs/ext4/hash.c | 4 +-
3 files changed, 176 insertions(+), 48 deletions(-)
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 164c560..689d1b1 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -32,24 +32,8 @@ static unsigned char ext4_filetype_table[] = {
DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
};
-static int ext4_readdir(struct file *, void *, filldir_t);
static int ext4_dx_readdir(struct file *filp,
void *dirent, filldir_t filldir);
-static int ext4_release_dir(struct inode *inode,
- struct file *filp);
-
-const struct file_operations ext4_dir_operations = {
- .llseek = ext4_llseek,
- .read = generic_read_dir,
- .readdir = ext4_readdir, /* we take BKL. needed?*/
- .unlocked_ioctl = ext4_ioctl,
-#ifdef CONFIG_COMPAT
- .compat_ioctl = ext4_compat_ioctl,
-#endif
- .fsync = ext4_sync_file,
- .release = ext4_release_dir,
-};
-
static unsigned char get_dtype(struct super_block *sb, int filetype)
{
@@ -60,6 +44,26 @@ static unsigned char get_dtype(struct super_block *sb, int filetype)
return (ext4_filetype_table[filetype]);
}
+/**
+ * Check if the given dir-inode refers to an htree-indexed directory
+ * (or a directory which chould potentially get coverted to use htree
+ * indexing).
+ *
+ * Return 1 if it is a dx dir, 0 if not
+ */
+static int is_dx_dir(struct inode *inode)
+{
+ struct super_block *sb = inode->i_sb;
+
+ if (EXT4_HAS_COMPAT_FEATURE(inode->i_sb,
+ EXT4_FEATURE_COMPAT_DIR_INDEX) &&
+ ((ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) ||
+ ((inode->i_size >> sb->s_blocksize_bits) == 1)))
+ return 1;
+
+ return 0;
+}
+
/*
* Return 0 if the directory entry is OK, and 1 if there is a problem
*
@@ -115,18 +119,13 @@ static int ext4_readdir(struct file *filp,
unsigned int offset;
int i, stored;
struct ext4_dir_entry_2 *de;
- struct super_block *sb;
int err;
struct inode *inode = filp->f_path.dentry->d_inode;
+ struct super_block *sb = inode->i_sb;
int ret = 0;
int dir_has_error = 0;
- sb = inode->i_sb;
-
- if (EXT4_HAS_COMPAT_FEATURE(inode->i_sb,
- EXT4_FEATURE_COMPAT_DIR_INDEX) &&
- ((ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) ||
- ((inode->i_size >> sb->s_blocksize_bits) == 1))) {
+ if (is_dx_dir(inode)) {
err = ext4_dx_readdir(filp, dirent, filldir);
if (err != ERR_BAD_DX_DIR) {
ret = err;
@@ -254,22 +253,134 @@ out:
return ret;
}
+static inline int is_32bit_api(void)
+{
+#ifdef CONFIG_COMPAT
+ return is_compat_task();
+#else
+ return (BITS_PER_LONG == 32);
+#endif
+}
+
/*
* These functions convert from the major/minor hash to an f_pos
- * value.
+ * value for dx directories
*
- * Currently we only use major hash numer. This is unfortunate, but
- * on 32-bit machines, the same VFS interface is used for lseek and
- * llseek, so if we use the 64 bit offset, then the 32-bit versions of
- * lseek/telldir/seekdir will blow out spectacularly, and from within
- * the ext2 low-level routine, we don't know if we're being called by
- * a 64-bit version of the system call or the 32-bit version of the
- * system call. Worse yet, NFSv2 only allows for a 32-bit readdir
- * cookie. Sigh.
+ * Upper layer (for example NFS) should specify FMODE_32BITHASH or
+ * FMODE_64BITHASH explicitly. On the other hand, we allow ext4 to be mounted
+ * directly on both 32-bit and 64-bit nodes, under such case, neither
+ * FMODE_32BITHASH nor FMODE_64BITHASH is specified.
*/
-#define hash2pos(major, minor) (major >> 1)
-#define pos2maj_hash(pos) ((pos << 1) & 0xffffffff)
-#define pos2min_hash(pos) (0)
+static inline loff_t hash2pos(struct file *filp, __u32 major, __u32 minor)
+{
+ if ((filp->f_mode & FMODE_32BITHASH) ||
+ (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
+ return major >> 1;
+ else
+ return ((__u64)(major >> 1) << 32) | (__u64)minor;
+}
+
+static inline __u32 pos2maj_hash(struct file *filp, loff_t pos)
+{
+ if ((filp->f_mode & FMODE_32BITHASH) ||
+ (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
+ return (pos << 1) & 0xffffffff;
+ else
+ return ((pos >> 32) << 1) & 0xffffffff;
+}
+
+static inline __u32 pos2min_hash(struct file *filp, loff_t pos)
+{
+ if ((filp->f_mode & FMODE_32BITHASH) ||
+ (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
+ return 0;
+ else
+ return pos & 0xffffffff;
+}
+
+/*
+ * Return 32- or 64-bit end-of-file for dx directories
+ */
+static inline loff_t ext4_get_htree_eof(struct file *filp)
+{
+ if ((filp->f_mode & FMODE_32BITHASH) ||
+ (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
+ return EXT4_HTREE_EOF_32BIT;
+ else
+ return EXT4_HTREE_EOF_64BIT;
+}
+
+
+/*
+ * ext4_dir_llseek() based on generic_file_llseek() to handle both
+ * non-htree and htree directories, where the "offset" is in terms
+ * of the filename hash value instead of the byte offset.
+ *
+ * NOTE: offsets obtained *before* ext4_set_inode_flag(dir, EXT4_INODE_INDEX)
+ * will be invalid once the directory was converted into a dx directory
+ */
+loff_t ext4_dir_llseek(struct file *file, loff_t offset, int origin)
+{
+ struct inode *inode = file->f_mapping->host;
+ loff_t ret = -EINVAL;
+ int dx_dir = is_dx_dir(inode);
+
+ mutex_lock(&inode->i_mutex);
+
+ /* NOTE: relative offsets with dx directories might not work
+ * as expected, as it is difficult to figure out the
+ * correct offset between dx hashes */
+
+ switch (origin) {
+ case SEEK_END:
+ if (unlikely(offset > 0))
+ goto out_err; /* not supported for directories */
+
+ /* so only negative offsets are left, does that have a
+ * meaning for directories at all? */
+ if (dx_dir)
+ offset += ext4_get_htree_eof(file);
+ else
+ offset += inode->i_size;
+ break;
+ case SEEK_CUR:
+ /*
+ * Here we special-case the lseek(fd, 0, SEEK_CUR)
+ * position-querying operation. Avoid rewriting the "same"
+ * f_pos value back to the file because a concurrent read(),
+ * write() or lseek() might have altered it
+ */
+ if (offset == 0) {
+ offset = file->f_pos;
+ goto out_ok;
+ }
+
+ offset += file->f_pos;
+ break;
+ }
+
+ if (unlikely(offset < 0))
+ goto out_err;
+
+ if (!dx_dir) {
+ if (offset > inode->i_sb->s_maxbytes)
+ goto out_err;
+ } else if (offset > ext4_get_htree_eof(file))
+ goto out_err;
+
+ /* Special lock needed here? */
+ if (offset != file->f_pos) {
+ file->f_pos = offset;
+ file->f_version = 0;
+ }
+
+out_ok:
+ ret = offset;
+out_err:
+ mutex_unlock(&inode->i_mutex);
+
+ return ret;
+}
/*
* This structure holds the nodes of the red-black tree used to store
@@ -330,15 +441,16 @@ static void free_rb_tree_fname(struct rb_root *root)
}
-static struct dir_private_info *ext4_htree_create_dir_info(loff_t pos)
+static struct dir_private_info *ext4_htree_create_dir_info(struct file *filp,
+ loff_t pos)
{
struct dir_private_info *p;
p = kzalloc(sizeof(struct dir_private_info), GFP_KERNEL);
if (!p)
return NULL;
- p->curr_hash = pos2maj_hash(pos);
- p->curr_minor_hash = pos2min_hash(pos);
+ p->curr_hash = pos2maj_hash(filp, pos);
+ p->curr_minor_hash = pos2min_hash(filp, pos);
return p;
}
@@ -429,7 +541,7 @@ static int call_filldir(struct file *filp, void *dirent,
"null fname?!?\n");
return 0;
}
- curr_pos = hash2pos(fname->hash, fname->minor_hash);
+ curr_pos = hash2pos(filp, fname->hash, fname->minor_hash);
while (fname) {
error = filldir(dirent, fname->name,
fname->name_len, curr_pos,
@@ -454,13 +566,13 @@ static int ext4_dx_readdir(struct file *filp,
int ret;
if (!info) {
- info = ext4_htree_create_dir_info(filp->f_pos);
+ info = ext4_htree_create_dir_info(filp, filp->f_pos);
if (!info)
return -ENOMEM;
filp->private_data = info;
}
- if (filp->f_pos == EXT4_HTREE_EOF)
+ if (filp->f_pos == ext4_get_htree_eof(filp))
return 0; /* EOF */
/* Some one has messed with f_pos; reset the world */
@@ -468,8 +580,8 @@ static int ext4_dx_readdir(struct file *filp,
free_rb_tree_fname(&info->root);
info->curr_node = NULL;
info->extra_fname = NULL;
- info->curr_hash = pos2maj_hash(filp->f_pos);
- info->curr_minor_hash = pos2min_hash(filp->f_pos);
+ info->curr_hash = pos2maj_hash(filp, filp->f_pos);
+ info->curr_minor_hash = pos2min_hash(filp, filp->f_pos);
}
/*
@@ -501,7 +613,7 @@ static int ext4_dx_readdir(struct file *filp,
if (ret < 0)
return ret;
if (ret == 0) {
- filp->f_pos = EXT4_HTREE_EOF;
+ filp->f_pos = ext4_get_htree_eof(filp);
break;
}
info->curr_node = rb_first(&info->root);
@@ -521,7 +633,7 @@ static int ext4_dx_readdir(struct file *filp,
info->curr_minor_hash = fname->minor_hash;
} else {
if (info->next_hash == ~0) {
- filp->f_pos = EXT4_HTREE_EOF;
+ filp->f_pos = ext4_get_htree_eof(filp);
break;
}
info->curr_hash = info->next_hash;
@@ -540,3 +652,15 @@ static int ext4_release_dir(struct inode *inode, struct file *filp)
return 0;
}
+
+const struct file_operations ext4_dir_operations = {
+ .llseek = ext4_dir_llseek,
+ .read = generic_read_dir,
+ .readdir = ext4_readdir,
+ .unlocked_ioctl = ext4_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = ext4_compat_ioctl,
+#endif
+ .fsync = ext4_sync_file,
+ .release = ext4_release_dir,
+};
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 8cb184c..2ac1eef 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1597,7 +1597,11 @@ struct dx_hash_info
u32 *seed;
};
-#define EXT4_HTREE_EOF 0x7fffffff
+
+/* 32 and 64 bit signed EOF for dx directories */
+#define EXT4_HTREE_EOF_32BIT ((1UL << (32 - 1)) - 1)
+#define EXT4_HTREE_EOF_64BIT ((1ULL << (64 - 1)) - 1)
+
/*
* Control parameters used by ext4_htree_next_block
diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c
index ac8f168..fa8e491 100644
--- a/fs/ext4/hash.c
+++ b/fs/ext4/hash.c
@@ -200,8 +200,8 @@ int ext4fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo)
return -1;
}
hash = hash & ~1;
- if (hash == (EXT4_HTREE_EOF << 1))
- hash = (EXT4_HTREE_EOF-1) << 1;
+ if (hash == (EXT4_HTREE_EOF_32BIT << 1))
+ hash = (EXT4_HTREE_EOF_32BIT - 1) << 1;
hinfo->hash = hash;
hinfo->minor_hash = minor_hash;
return 0;
--
1.7.10.4
From: Bernd Schubert <bernd.schubert@itwm.fraunhofer.de>
Date: Sun, 18 Mar 2012 22:44:49 -0400
Subject: nfsd: rename 'int access' to 'int may_flags' in nfsd_open()
commit 999448a8c0202d8c41711c92385323520644527b upstream.
Just rename this variable, as the next patch will add a flag and
'access' as variable name would not be correct any more.
Signed-off-by: Bernd Schubert <bernd.schubert@itwm.fraunhofer.de>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Acked-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
---
fs/nfsd/vfs.c | 18 ++++++++++--------
1 file changed, 10 insertions(+), 8 deletions(-)
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 5c3cd82..b395c61 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -726,12 +726,13 @@ static int nfsd_open_break_lease(struct inode *inode, int access)
/*
* Open an existing file or directory.
- * The access argument indicates the type of open (read/write/lock)
+ * The may_flags argument indicates the type of open (read/write/lock)
+ * and additional flags.
* N.B. After this call fhp needs an fh_put
*/
__be32
nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
- int access, struct file **filp)
+ int may_flags, struct file **filp)
{
struct dentry *dentry;
struct inode *inode;
@@ -746,7 +747,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
* and (hopefully) checked permission - so allow OWNER_OVERRIDE
* in case a chmod has now revoked permission.
*/
- err = fh_verify(rqstp, fhp, type, access | NFSD_MAY_OWNER_OVERRIDE);
+ err = fh_verify(rqstp, fhp, type, may_flags | NFSD_MAY_OWNER_OVERRIDE);
if (err)
goto out;
@@ -757,7 +758,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
* or any access when mandatory locking enabled
*/
err = nfserr_perm;
- if (IS_APPEND(inode) && (access & NFSD_MAY_WRITE))
+ if (IS_APPEND(inode) && (may_flags & NFSD_MAY_WRITE))
goto out;
/*
* We must ignore files (but only files) which might have mandatory
@@ -770,12 +771,12 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
if (!inode->i_fop)
goto out;
- host_err = nfsd_open_break_lease(inode, access);
+ host_err = nfsd_open_break_lease(inode, may_flags);
if (host_err) /* NOMEM or WOULDBLOCK */
goto out_nfserr;
- if (access & NFSD_MAY_WRITE) {
- if (access & NFSD_MAY_READ)
+ if (may_flags & NFSD_MAY_WRITE) {
+ if (may_flags & NFSD_MAY_READ)
flags = O_RDWR|O_LARGEFILE;
else
flags = O_WRONLY|O_LARGEFILE;
@@ -785,7 +786,8 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
if (IS_ERR(*filp))
host_err = PTR_ERR(*filp);
else
- host_err = ima_file_check(*filp, access);
+ host_err = ima_file_check(*filp, may_flags);
+
out_nfserr:
err = nfserrno(host_err);
out:
--
1.7.10.4
From: Bernd Schubert <bernd.schubert@itwm.fraunhofer.de>
Date: Sun, 18 Mar 2012 22:44:50 -0400
Subject: nfsd: vfs_llseek() with 32 or 64 bit offsets (hashes)
commit 06effdbb49af5f6c7d20affaec74603914acc768 upstream.
Use 32-bit or 64-bit llseek() hashes for directory offsets depending on
the NFS version. NFSv2 gets 32-bit hashes only.
NOTE: This patch got rather complex as Christoph asked to set the
filp->f_mode flag in the open call or immediatly after dentry_open()
in nfsd_open() to avoid races.
Personally I still do not see a reason for that and in my opinion
FMODE_32BITHASH/FMODE_64BITHASH flags could be set nfsd_readdir(), as it
follows directly after nfsd_open() without a chance of races.
Signed-off-by: Bernd Schubert <bernd.schubert@itwm.fraunhofer.de>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Acked-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
---
fs/nfsd/vfs.c | 15 +++++++++++++--
fs/nfsd/vfs.h | 2 ++
2 files changed, 15 insertions(+), 2 deletions(-)
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index b395c61..959039e 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -785,9 +785,15 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
flags, current_cred());
if (IS_ERR(*filp))
host_err = PTR_ERR(*filp);
- else
+ else {
host_err = ima_file_check(*filp, may_flags);
+ if (may_flags & NFSD_MAY_64BIT_COOKIE)
+ (*filp)->f_mode |= FMODE_64BITHASH;
+ else
+ (*filp)->f_mode |= FMODE_32BITHASH;
+ }
+
out_nfserr:
err = nfserrno(host_err);
out:
@@ -2011,8 +2017,13 @@ nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp,
__be32 err;
struct file *file;
loff_t offset = *offsetp;
+ int may_flags = NFSD_MAY_READ;
- err = nfsd_open(rqstp, fhp, S_IFDIR, NFSD_MAY_READ, &file);
+ /* NFSv2 only supports 32 bit cookies */
+ if (rqstp->rq_vers > 2)
+ may_flags |= NFSD_MAY_64BIT_COOKIE;
+
+ err = nfsd_open(rqstp, fhp, S_IFDIR, may_flags, &file);
if (err)
goto out;
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index 3f54ad0..85d4d42 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -27,6 +27,8 @@
#define NFSD_MAY_BYPASS_GSS 0x400
#define NFSD_MAY_READ_IF_EXEC 0x800
+#define NFSD_MAY_64BIT_COOKIE 0x1000 /* 64 bit readdir cookies for >= NFSv3 */
+
#define NFSD_MAY_CREATE (NFSD_MAY_EXEC|NFSD_MAY_WRITE)
#define NFSD_MAY_REMOVE (NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC)
--
1.7.10.4
From: Eric Sandeen <sandeen@redhat.com>
Date: Thu, 26 Apr 2012 13:10:39 -0500
Subject: ext3: return 32/64-bit dir name hash according to usage type
commit d7dab39b6e16d5eea78ed3c705d2a2d0772b4f06 upstream.
This is based on commit d1f5273e9adb40724a85272f248f210dc4ce919a
ext4: return 32/64-bit dir name hash according to usage type
by Fan Yong <yong.fan@whamcloud.com>
Traditionally ext2/3/4 has returned a 32-bit hash value from llseek()
to appease NFSv2, which can only handle a 32-bit cookie for seekdir()
and telldir(). However, this causes problems if there are 32-bit hash
collisions, since the NFSv2 server can get stuck resending the same
entries from the directory repeatedly.
Allow ext3 to return a full 64-bit hash (both major and minor) for
telldir to decrease the chance of hash collisions.
This patch does implement a new ext3_dir_llseek op, because with 64-bit
hashes, nfs will attempt to seek to a hash "offset" which is much
larger than ext3's s_maxbytes. So for dx dirs, we call
generic_file_llseek_size() with the appropriate max hash value as the
maximum seekable size. Otherwise we just pass through to
generic_file_llseek().
Patch-updated-by: Bernd Schubert <bernd.schubert@itwm.fraunhofer.de>
Patch-updated-by: Eric Sandeen <sandeen@redhat.com>
(blame us if something is not correct)
Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
---
fs/ext3/dir.c | 167 ++++++++++++++++++++++++++++++++++-------------
fs/ext3/hash.c | 4 +-
include/linux/ext3_fs.h | 6 +-
3 files changed, 129 insertions(+), 48 deletions(-)
diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c
index 34f0a07..3268697 100644
--- a/fs/ext3/dir.c
+++ b/fs/ext3/dir.c
@@ -25,6 +25,7 @@
#include <linux/jbd.h>
#include <linux/ext3_fs.h>
#include <linux/buffer_head.h>
+#include <linux/compat.h>
#include <linux/slab.h>
#include <linux/rbtree.h>
@@ -32,24 +33,8 @@ static unsigned char ext3_filetype_table[] = {
DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
};
-static int ext3_readdir(struct file *, void *, filldir_t);
static int ext3_dx_readdir(struct file * filp,
void * dirent, filldir_t filldir);
-static int ext3_release_dir (struct inode * inode,
- struct file * filp);
-
-const struct file_operations ext3_dir_operations = {
- .llseek = generic_file_llseek,
- .read = generic_read_dir,
- .readdir = ext3_readdir, /* we take BKL. needed?*/
- .unlocked_ioctl = ext3_ioctl,
-#ifdef CONFIG_COMPAT
- .compat_ioctl = ext3_compat_ioctl,
-#endif
- .fsync = ext3_sync_file, /* BKL held */
- .release = ext3_release_dir,
-};
-
static unsigned char get_dtype(struct super_block *sb, int filetype)
{
@@ -60,6 +45,25 @@ static unsigned char get_dtype(struct super_block *sb, int filetype)
return (ext3_filetype_table[filetype]);
}
+/**
+ * Check if the given dir-inode refers to an htree-indexed directory
+ * (or a directory which chould potentially get coverted to use htree
+ * indexing).
+ *
+ * Return 1 if it is a dx dir, 0 if not
+ */
+static int is_dx_dir(struct inode *inode)
+{
+ struct super_block *sb = inode->i_sb;
+
+ if (EXT3_HAS_COMPAT_FEATURE(inode->i_sb,
+ EXT3_FEATURE_COMPAT_DIR_INDEX) &&
+ ((EXT3_I(inode)->i_flags & EXT3_INDEX_FL) ||
+ ((inode->i_size >> sb->s_blocksize_bits) == 1)))
+ return 1;
+
+ return 0;
+}
int ext3_check_dir_entry (const char * function, struct inode * dir,
struct ext3_dir_entry_2 * de,
@@ -99,18 +103,13 @@ static int ext3_readdir(struct file * filp,
unsigned long offset;
int i, stored;
struct ext3_dir_entry_2 *de;
- struct super_block *sb;
int err;
struct inode *inode = filp->f_path.dentry->d_inode;
+ struct super_block *sb = inode->i_sb;
int ret = 0;
int dir_has_error = 0;
- sb = inode->i_sb;
-
- if (EXT3_HAS_COMPAT_FEATURE(inode->i_sb,
- EXT3_FEATURE_COMPAT_DIR_INDEX) &&
- ((EXT3_I(inode)->i_flags & EXT3_INDEX_FL) ||
- ((inode->i_size >> sb->s_blocksize_bits) == 1))) {
+ if (is_dx_dir(inode)) {
err = ext3_dx_readdir(filp, dirent, filldir);
if (err != ERR_BAD_DX_DIR) {
ret = err;
@@ -232,22 +231,87 @@ out:
return ret;
}
+static inline int is_32bit_api(void)
+{
+#ifdef CONFIG_COMPAT
+ return is_compat_task();
+#else
+ return (BITS_PER_LONG == 32);
+#endif
+}
+
/*
* These functions convert from the major/minor hash to an f_pos
- * value.
+ * value for dx directories
*
- * Currently we only use major hash numer. This is unfortunate, but
- * on 32-bit machines, the same VFS interface is used for lseek and
- * llseek, so if we use the 64 bit offset, then the 32-bit versions of
- * lseek/telldir/seekdir will blow out spectacularly, and from within
- * the ext2 low-level routine, we don't know if we're being called by
- * a 64-bit version of the system call or the 32-bit version of the
- * system call. Worse yet, NFSv2 only allows for a 32-bit readdir
- * cookie. Sigh.
+ * Upper layer (for example NFS) should specify FMODE_32BITHASH or
+ * FMODE_64BITHASH explicitly. On the other hand, we allow ext3 to be mounted
+ * directly on both 32-bit and 64-bit nodes, under such case, neither
+ * FMODE_32BITHASH nor FMODE_64BITHASH is specified.
*/
-#define hash2pos(major, minor) (major >> 1)
-#define pos2maj_hash(pos) ((pos << 1) & 0xffffffff)
-#define pos2min_hash(pos) (0)
+static inline loff_t hash2pos(struct file *filp, __u32 major, __u32 minor)
+{
+ if ((filp->f_mode & FMODE_32BITHASH) ||
+ (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
+ return major >> 1;
+ else
+ return ((__u64)(major >> 1) << 32) | (__u64)minor;
+}
+
+static inline __u32 pos2maj_hash(struct file *filp, loff_t pos)
+{
+ if ((filp->f_mode & FMODE_32BITHASH) ||
+ (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
+ return (pos << 1) & 0xffffffff;
+ else
+ return ((pos >> 32) << 1) & 0xffffffff;
+}
+
+static inline __u32 pos2min_hash(struct file *filp, loff_t pos)
+{
+ if ((filp->f_mode & FMODE_32BITHASH) ||
+ (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
+ return 0;
+ else
+ return pos & 0xffffffff;
+}
+
+/*
+ * Return 32- or 64-bit end-of-file for dx directories
+ */
+static inline loff_t ext3_get_htree_eof(struct file *filp)
+{
+ if ((filp->f_mode & FMODE_32BITHASH) ||
+ (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
+ return EXT3_HTREE_EOF_32BIT;
+ else
+ return EXT3_HTREE_EOF_64BIT;
+}
+
+
+/*
+ * ext3_dir_llseek() calls generic_file_llseek[_size]() to handle both
+ * non-htree and htree directories, where the "offset" is in terms
+ * of the filename hash value instead of the byte offset.
+ *
+ * Because we may return a 64-bit hash that is well beyond s_maxbytes,
+ * we need to pass the max hash as the maximum allowable offset in
+ * the htree directory case.
+ *
+ * NOTE: offsets obtained *before* ext3_set_inode_flag(dir, EXT3_INODE_INDEX)
+ * will be invalid once the directory was converted into a dx directory
+ */
+loff_t ext3_dir_llseek(struct file *file, loff_t offset, int origin)
+{
+ struct inode *inode = file->f_mapping->host;
+ int dx_dir = is_dx_dir(inode);
+
+ if (likely(dx_dir))
+ return generic_file_llseek_size(file, offset, origin,
+ ext3_get_htree_eof(file));
+ else
+ return generic_file_llseek(file, offset, origin);
+}
/*
* This structure holds the nodes of the red-black tree used to store
@@ -308,15 +372,16 @@ static void free_rb_tree_fname(struct rb_root *root)
}
-static struct dir_private_info *ext3_htree_create_dir_info(loff_t pos)
+static struct dir_private_info *ext3_htree_create_dir_info(struct file *filp,
+ loff_t pos)
{
struct dir_private_info *p;
p = kzalloc(sizeof(struct dir_private_info), GFP_KERNEL);
if (!p)
return NULL;
- p->curr_hash = pos2maj_hash(pos);
- p->curr_minor_hash = pos2min_hash(pos);
+ p->curr_hash = pos2maj_hash(filp, pos);
+ p->curr_minor_hash = pos2min_hash(filp, pos);
return p;
}
@@ -406,7 +471,7 @@ static int call_filldir(struct file * filp, void * dirent,
printk("call_filldir: called with null fname?!?\n");
return 0;
}
- curr_pos = hash2pos(fname->hash, fname->minor_hash);
+ curr_pos = hash2pos(filp, fname->hash, fname->minor_hash);
while (fname) {
error = filldir(dirent, fname->name,
fname->name_len, curr_pos,
@@ -431,13 +496,13 @@ static int ext3_dx_readdir(struct file * filp,
int ret;
if (!info) {
- info = ext3_htree_create_dir_info(filp->f_pos);
+ info = ext3_htree_create_dir_info(filp, filp->f_pos);
if (!info)
return -ENOMEM;
filp->private_data = info;
}
- if (filp->f_pos == EXT3_HTREE_EOF)
+ if (filp->f_pos == ext3_get_htree_eof(filp))
return 0; /* EOF */
/* Some one has messed with f_pos; reset the world */
@@ -445,8 +510,8 @@ static int ext3_dx_readdir(struct file * filp,
free_rb_tree_fname(&info->root);
info->curr_node = NULL;
info->extra_fname = NULL;
- info->curr_hash = pos2maj_hash(filp->f_pos);
- info->curr_minor_hash = pos2min_hash(filp->f_pos);
+ info->curr_hash = pos2maj_hash(filp, filp->f_pos);
+ info->curr_minor_hash = pos2min_hash(filp, filp->f_pos);
}
/*
@@ -478,7 +543,7 @@ static int ext3_dx_readdir(struct file * filp,
if (ret < 0)
return ret;
if (ret == 0) {
- filp->f_pos = EXT3_HTREE_EOF;
+ filp->f_pos = ext3_get_htree_eof(filp);
break;
}
info->curr_node = rb_first(&info->root);
@@ -498,7 +563,7 @@ static int ext3_dx_readdir(struct file * filp,
info->curr_minor_hash = fname->minor_hash;
} else {
if (info->next_hash == ~0) {
- filp->f_pos = EXT3_HTREE_EOF;
+ filp->f_pos = ext3_get_htree_eof(filp);
break;
}
info->curr_hash = info->next_hash;
@@ -517,3 +582,15 @@ static int ext3_release_dir (struct inode * inode, struct file * filp)
return 0;
}
+
+const struct file_operations ext3_dir_operations = {
+ .llseek = ext3_dir_llseek,
+ .read = generic_read_dir,
+ .readdir = ext3_readdir,
+ .unlocked_ioctl = ext3_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = ext3_compat_ioctl,
+#endif
+ .fsync = ext3_sync_file,
+ .release = ext3_release_dir,
+};
diff --git a/fs/ext3/hash.c b/fs/ext3/hash.c
index 7d215b4..d4d3ade 100644
--- a/fs/ext3/hash.c
+++ b/fs/ext3/hash.c
@@ -200,8 +200,8 @@ int ext3fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo)
return -1;
}
hash = hash & ~1;
- if (hash == (EXT3_HTREE_EOF << 1))
- hash = (EXT3_HTREE_EOF-1) << 1;
+ if (hash == (EXT3_HTREE_EOF_32BIT << 1))
+ hash = (EXT3_HTREE_EOF_32BIT - 1) << 1;
hinfo->hash = hash;
hinfo->minor_hash = minor_hash;
return 0;
diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h
index dec9911..d59ab12 100644
--- a/include/linux/ext3_fs.h
+++ b/include/linux/ext3_fs.h
@@ -781,7 +781,11 @@ struct dx_hash_info
u32 *seed;
};
-#define EXT3_HTREE_EOF 0x7fffffff
+
+/* 32 and 64 bit signed EOF for dx directories */
+#define EXT3_HTREE_EOF_32BIT ((1UL << (32 - 1)) - 1)
+#define EXT3_HTREE_EOF_64BIT ((1ULL << (64 - 1)) - 1)
+
/*
* Control parameters used by ext3_htree_next_block
--
1.7.10.4
Reply to: