All of lore.kernel.org
 help / color / mirror / Atom feed
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	stable@vger.kernel.org, Eric Sandeen <sandeen@redhat.com>,
	Jan Kara <jack@suse.cz>, Benjamin LaHaise <bcrl@kvack.org>
Subject: [ 26/32] ext3: return 32/64-bit dir name hash according to usage type
Date: Fri,  1 Nov 2013 14:43:37 -0700	[thread overview]
Message-ID: <20131101214319.993872325@linuxfoundation.org> (raw)
In-Reply-To: <20131101214313.735463599@linuxfoundation.org>

3.4-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Eric Sandeen <sandeen@redhat.com>

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>
Cc: Benjamin LaHaise <bcrl@kvack.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

---
 fs/ext3/dir.c  |  167 +++++++++++++++++++++++++++++++++++++++++----------------
 fs/ext3/ext3.h |    6 +-
 fs/ext3/hash.c |    4 -
 3 files changed, 129 insertions(+), 48 deletions(-)

--- a/fs/ext3/dir.c
+++ b/fs/ext3/dir.c
@@ -21,30 +21,15 @@
  *
  */
 
+#include <linux/compat.h>
 #include "ext3.h"
 
 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)
 {
@@ -55,6 +40,25 @@ static unsigned char get_dtype(struct su
 	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,
@@ -94,18 +98,13 @@ static int ext3_readdir(struct file * fi
 	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;
@@ -227,22 +226,87 @@ 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
+ *
+ * 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.
+ */
+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.
  *
- * 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.
+ * 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
  */
-#define hash2pos(major, minor)	(major >> 1)
-#define pos2maj_hash(pos)	((pos << 1) & 0xffffffff)
-#define pos2min_hash(pos)	(0)
+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
@@ -303,15 +367,16 @@ static void free_rb_tree_fname(struct rb
 }
 
 
-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;
 }
 
@@ -401,7 +466,7 @@ static int call_filldir(struct file * fi
 		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,
@@ -426,13 +491,13 @@ static int ext3_dx_readdir(struct file *
 	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 */
@@ -440,8 +505,8 @@ static int ext3_dx_readdir(struct file *
 		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);
 	}
 
 	/*
@@ -473,7 +538,7 @@ static int ext3_dx_readdir(struct file *
 			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);
@@ -493,7 +558,7 @@ static int ext3_dx_readdir(struct file *
 			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;
@@ -512,3 +577,15 @@ static int ext3_release_dir (struct inod
 
 	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,
+};
--- a/fs/ext3/ext3.h
+++ b/fs/ext3/ext3.h
@@ -920,7 +920,11 @@ 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
--- a/fs/ext3/hash.c
+++ b/fs/ext3/hash.c
@@ -198,8 +198,8 @@ int ext3fs_dirhash(const char *name, int
 		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;



  parent reply	other threads:[~2013-11-01 21:46 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-11-01 21:43 [ 00/32] 3.4.68-stable review Greg Kroah-Hartman
2013-11-01 21:43 ` [ 01/32] tcp: must unclone packets before mangling them Greg Kroah-Hartman
2013-11-01 21:43 ` [ 02/32] tcp: do not forget FIN in tcp_shifted_skb() Greg Kroah-Hartman
2013-11-01 21:43 ` [ 03/32] net: do not call sock_put() on TIMEWAIT sockets Greg Kroah-Hartman
2013-11-01 21:43 ` [ 04/32] net: mv643xx_eth: update statistics timer from timer context only Greg Kroah-Hartman
2013-11-01 21:43 ` [ 05/32] net: mv643xx_eth: fix orphaned statistics timer crash Greg Kroah-Hartman
2013-11-01 21:43 ` [ 06/32] net: heap overflow in __audit_sockaddr() Greg Kroah-Hartman
2013-11-01 21:43 ` [ 07/32] proc connector: fix info leaks Greg Kroah-Hartman
2013-11-01 21:43 ` [ 08/32] ipv4: fix ineffective source address selection Greg Kroah-Hartman
2013-11-01 21:43 ` [ 09/32] can: dev: fix nlmsg size calculation in can_get_size() Greg Kroah-Hartman
2013-11-01 21:43 ` [ 10/32] ipv6: restrict neighbor entry creation to output flow Greg Kroah-Hartman
2013-11-01 21:43 ` [ 11/32] bridge: Correctly clamp MAX forward_delay when enabling STP Greg Kroah-Hartman
2013-11-01 21:43   ` Greg Kroah-Hartman
2013-11-01 21:43 ` [ 12/32] net: vlan: fix nlmsg size calculation in vlan_get_size() Greg Kroah-Hartman
2013-11-01 21:43 ` [ 13/32] l2tp: must disable bh before calling l2tp_xmit_skb() Greg Kroah-Hartman
2013-11-01 21:43 ` [ 14/32] farsync: fix info leak in ioctl Greg Kroah-Hartman
2013-11-01 21:43 ` [ 15/32] unix_diag: fix info leak Greg Kroah-Hartman
2013-11-01 21:43 ` [ 16/32] connector: use nlmsg_len() to check message length Greg Kroah-Hartman
2013-11-01 21:43 ` [ 17/32] bnx2x: record rx queue for LRO packets Greg Kroah-Hartman
2013-11-01 21:43 ` [ 18/32] net: dst: provide accessor function to dst->xfrm Greg Kroah-Hartman
2013-11-01 21:43 ` [ 19/32] sctp: Use software crc32 checksum when xfrm transform will happen Greg Kroah-Hartman
2013-11-01 21:43 ` [ 20/32] sctp: Perform software checksum if packet has to be fragmented Greg Kroah-Hartman
2013-11-01 21:43 ` [ 21/32] wanxl: fix info leak in ioctl Greg Kroah-Hartman
2013-11-01 21:43 ` [ 22/32] net: unix: inherit SOCK_PASS{CRED, SEC} flags from socket to fix race Greg Kroah-Hartman
2013-11-01 21:43 ` [ 23/32] net: fix cipso packet validation when !NETLABEL Greg Kroah-Hartman
2013-11-01 21:43 ` [ 24/32] inet: fix possible memory corruption with UDP_CORK and UFO Greg Kroah-Hartman
2013-11-01 21:43 ` [ 25/32] davinci_emac.c: Fix IFF_ALLMULTI setup Greg Kroah-Hartman
2013-11-01 21:43 ` Greg Kroah-Hartman [this message]
2013-11-01 21:43 ` [ 27/32] dm snapshot: fix data corruption Greg Kroah-Hartman
2013-11-01 21:43 ` [ 28/32] writeback: fix negative bdi max pause Greg Kroah-Hartman
2013-11-01 21:43 ` [ 29/32] wireless: radiotap: fix parsing buffer overrun Greg Kroah-Hartman
2013-11-01 21:43 ` [ 30/32] USB: serial: ti_usb_3410_5052: add Abbott strip port ID to combined table as well Greg Kroah-Hartman
2013-11-01 21:43 ` [ 31/32] USB: serial: option: add support for Inovia SEW858 device Greg Kroah-Hartman
2013-11-01 21:43 ` [ 32/32] usb: serial: option: blacklist Olivetti Olicard200 Greg Kroah-Hartman
2013-11-02  2:28 ` [ 00/32] 3.4.68-stable review Guenter Roeck
2013-11-02 21:33 ` Shuah Khan
2013-11-04  3:07 ` Satoru Takeuchi

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=20131101214319.993872325@linuxfoundation.org \
    --to=gregkh@linuxfoundation.org \
    --cc=bcrl@kvack.org \
    --cc=jack@suse.cz \
    --cc=linux-kernel@vger.kernel.org \
    --cc=sandeen@redhat.com \
    --cc=stable@vger.kernel.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.