Merge branch 'linus' into x86/xen

8 files changed, 125 insertions, 58 deletions

diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c
index 8ca3bfd72427..2eea96ec78ed 100644
--- a/fs/ext3/dir.c
+++ b/fs/ext3/dir.c
@@ -272,7 +272,7 @@ static void free_rb_tree_fname(struct rb_root *root)
 
         while (n) {
                 /* Do the node's children first */
-                if ((n)->rb_left) {
+                if (n->rb_left) {
                         n = n->rb_left;
                         continue;
                 }
@@ -301,24 +301,18 @@ static void free_rb_tree_fname(struct rb_root *root)
                         parent->rb_right = NULL;
                 n = parent;
         }
-        root->rb_node = NULL;
 }
 
 
-static struct dir_private_info *create_dir_info(loff_t pos)
+static struct dir_private_info *ext3_htree_create_dir_info(loff_t pos)
 {
         struct dir_private_info *p;
 
-        p = kmalloc(sizeof(struct dir_private_info), GFP_KERNEL);
+        p = kzalloc(sizeof(struct dir_private_info), GFP_KERNEL);
         if (!p)
                 return NULL;
-        p->root.rb_node = NULL;
-        p->curr_node = NULL;
-        p->extra_fname = NULL;
-        p->last_pos = 0;
         p->curr_hash = pos2maj_hash(pos);
         p->curr_minor_hash = pos2min_hash(pos);
-        p->next_hash = 0;
         return p;
 }
 
@@ -433,7 +427,7 @@ static int ext3_dx_readdir(struct file * filp,
         int     ret;
 
         if (!info) {
-                info = create_dir_info(filp->f_pos);
+                info = ext3_htree_create_dir_info(filp->f_pos);
                 if (!info)
                         return -ENOMEM;
                 filp->private_data = info;
diff --git a/fs/ext3/ialloc.c b/fs/ext3/ialloc.c
index 77126821b2e9..47b678d73e7a 100644
--- a/fs/ext3/ialloc.c
+++ b/fs/ext3/ialloc.c
@@ -669,6 +669,14 @@ struct inode *ext3_orphan_get(struct super_block *sb, unsigned long ino)
         if (IS_ERR(inode))
                 goto iget_failed;
 
+        /*
+         * If the orphans has i_nlinks > 0 then it should be able to be
+         * truncated, otherwise it won't be removed from the orphan list
+         * during processing and an infinite loop will result.
+         */
+        if (inode->i_nlink && !ext3_can_truncate(inode))
+                goto bad_orphan;
+
         if (NEXT_ORPHAN(inode) > max_ino)
                 goto bad_orphan;
         brelse(bitmap_bh);
@@ -690,6 +698,7 @@ bad_orphan:
                 printk(KERN_NOTICE "NEXT_ORPHAN(inode)=%u\n",
                        NEXT_ORPHAN(inode));
                 printk(KERN_NOTICE "max_ino=%lu\n", max_ino);
+                printk(KERN_NOTICE "i_nlink=%u\n", inode->i_nlink);
                 /* Avoid freeing blocks if we got a bad deleted inode */
                 if (inode->i_nlink == 0)
                         inode->i_blocks = 0;
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 6ae4ecf3ce40..3bf07d70b914 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -2127,7 +2127,21 @@ static void ext3_free_data(handle_t *handle, struct inode *inode,
 
         if (this_bh) {
                 BUFFER_TRACE(this_bh, "call ext3_journal_dirty_metadata");
-                ext3_journal_dirty_metadata(handle, this_bh);
+
+                /*
+                 * The buffer head should have an attached journal head at this
+                 * point. However, if the data is corrupted and an indirect
+                 * block pointed to itself, it would have been detached when
+                 * the block was cleared. Check for this instead of OOPSing.
+                 */
+                if (bh2jh(this_bh))
+                        ext3_journal_dirty_metadata(handle, this_bh);
+                else
+                        ext3_error(inode->i_sb, "ext3_free_data",
+                                   "circular indirect block detected, "
+                                   "inode=%lu, block=%llu",
+                                   inode->i_ino,
+                                   (unsigned long long)this_bh->b_blocknr);
         }
 }
 
@@ -2253,6 +2267,19 @@ static void ext3_free_branches(handle_t *handle, struct inode *inode,
         }
 }
 
+int ext3_can_truncate(struct inode *inode)
+{
+        if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
+                return 0;
+        if (S_ISREG(inode->i_mode))
+                return 1;
+        if (S_ISDIR(inode->i_mode))
+                return 1;
+        if (S_ISLNK(inode->i_mode))
+                return !ext3_inode_is_fast_symlink(inode);
+        return 0;
+}
+
 /*
  * ext3_truncate()
  *
@@ -2297,12 +2324,7 @@ void ext3_truncate(struct inode *inode)
         unsigned blocksize = inode->i_sb->s_blocksize;
         struct page *page;
 
-        if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
-            S_ISLNK(inode->i_mode)))
-                return;
-        if (ext3_inode_is_fast_symlink(inode))
-                return;
-        if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
+        if (!ext3_can_truncate(inode))
                 return;
 
         /*
@@ -2513,6 +2535,16 @@ static int __ext3_get_inode_loc(struct inode *inode,
         }
         if (!buffer_uptodate(bh)) {
                 lock_buffer(bh);
+
+                /*
+                 * If the buffer has the write error flag, we have failed
+                 * to write out another inode in the same block.  In this
+                 * case, we don't have to read the block because we may
+                 * read the old inode data successfully.
+                 */
+                if (buffer_write_io_error(bh) && !buffer_uptodate(bh))
+                        set_buffer_uptodate(bh);
+
                 if (buffer_uptodate(bh)) {
                         /* someone brought it uptodate while we waited */
                         unlock_buffer(bh);
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index 0b8cf80154f1..de13e919cd81 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -240,13 +240,13 @@ static inline unsigned dx_root_limit (struct inode *dir, unsigned infosize)
 {
         unsigned entry_space = dir->i_sb->s_blocksize - EXT3_DIR_REC_LEN(1) -
                 EXT3_DIR_REC_LEN(2) - infosize;
-        return 0? 20: entry_space / sizeof(struct dx_entry);
+        return entry_space / sizeof(struct dx_entry);
 }
 
 static inline unsigned dx_node_limit (struct inode *dir)
 {
         unsigned entry_space = dir->i_sb->s_blocksize - EXT3_DIR_REC_LEN(0);
-        return 0? 22: entry_space / sizeof(struct dx_entry);
+        return entry_space / sizeof(struct dx_entry);
 }
 
 /*
@@ -991,19 +991,21 @@ static struct buffer_head * ext3_dx_find_entry(struct dentry *dentry,
                 de = (struct ext3_dir_entry_2 *) bh->b_data;
                 top = (struct ext3_dir_entry_2 *) ((char *) de + sb->s_blocksize -
                                        EXT3_DIR_REC_LEN(0));
-                for (; de < top; de = ext3_next_entry(de))
-                if (ext3_match (namelen, name, de)) {
-                        if (!ext3_check_dir_entry("ext3_find_entry",
-                                                  dir, de, bh,
-                                  (block<<EXT3_BLOCK_SIZE_BITS(sb))
-                                          +((char *)de - bh->b_data))) {
-                                brelse (bh);
+                for (; de < top; de = ext3_next_entry(de)) {
+                        int off = (block << EXT3_BLOCK_SIZE_BITS(sb))
+                                  + ((char *) de - bh->b_data);
+
+                        if (!ext3_check_dir_entry(__func__, dir, de, bh, off)) {
+                                brelse(bh);
                                 *err = ERR_BAD_DX_DIR;
                                 goto errout;
                         }
-                        *res_dir = de;
-                        dx_release (frames);
-                        return bh;
+
+                        if (ext3_match(namelen, name, de)) {
+                                *res_dir = de;
+                                dx_release(frames);
+                                return bh;
+                        }
                 }
                 brelse (bh);
                 /* Check to see if we should continue to search */
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 2845425077e8..615788c6843a 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -842,7 +842,7 @@ static int parse_options (char *options, struct super_block *sb,
         int data_opt = 0;
         int option;
 #ifdef CONFIG_QUOTA
-        int qtype;
+        int qtype, qfmt;
         char *qname;
 #endif
 
@@ -1018,9 +1018,11 @@ static int parse_options (char *options, struct super_block *sb,
                 case Opt_grpjquota:
                         qtype = GRPQUOTA;
 set_qf_name:
-                        if (sb_any_quota_enabled(sb)) {
+                        if ((sb_any_quota_enabled(sb) ||
+                             sb_any_quota_suspended(sb)) &&
+                            !sbi->s_qf_names[qtype]) {
                                 printk(KERN_ERR
-                                        "EXT3-fs: Cannot change journalled "
+                                        "EXT3-fs: Cannot change journaled "
                                         "quota options when quota turned on.\n");
                                 return 0;
                         }
@@ -1056,9 +1058,11 @@ set_qf_name:
                 case Opt_offgrpjquota:
                         qtype = GRPQUOTA;
 clear_qf_name:
-                        if (sb_any_quota_enabled(sb)) {
+                        if ((sb_any_quota_enabled(sb) ||
+                             sb_any_quota_suspended(sb)) &&
+                            sbi->s_qf_names[qtype]) {
                                 printk(KERN_ERR "EXT3-fs: Cannot change "
-                                        "journalled quota options when "
+                                        "journaled quota options when "
                                         "quota turned on.\n");
                                 return 0;
                         }
@@ -1069,10 +1073,20 @@ clear_qf_name:
                         sbi->s_qf_names[qtype] = NULL;
                         break;
                 case Opt_jqfmt_vfsold:
-                        sbi->s_jquota_fmt = QFMT_VFS_OLD;
-                        break;
+                        qfmt = QFMT_VFS_OLD;
+                        goto set_qf_format;
                 case Opt_jqfmt_vfsv0:
-                        sbi->s_jquota_fmt = QFMT_VFS_V0;
+                        qfmt = QFMT_VFS_V0;
+set_qf_format:
+                        if ((sb_any_quota_enabled(sb) ||
+                             sb_any_quota_suspended(sb)) &&
+                            sbi->s_jquota_fmt != qfmt) {
+                                printk(KERN_ERR "EXT3-fs: Cannot change "
+                                        "journaled quota options when "
+                                        "quota turned on.\n");
+                                return 0;
+                        }
+                        sbi->s_jquota_fmt = qfmt;
                         break;
                 case Opt_quota:
                 case Opt_usrquota:
@@ -1084,7 +1098,8 @@ clear_qf_name:
                         set_opt(sbi->s_mount_opt, GRPQUOTA);
                         break;
                 case Opt_noquota:
-                        if (sb_any_quota_enabled(sb)) {
+                        if (sb_any_quota_enabled(sb) ||
+                            sb_any_quota_suspended(sb)) {
                                 printk(KERN_ERR "EXT3-fs: Cannot change quota "
                                         "options when quota turned on.\n");
                                 return 0;
@@ -1169,14 +1184,14 @@ clear_qf_name:
                 }
 
                 if (!sbi->s_jquota_fmt) {
-                        printk(KERN_ERR "EXT3-fs: journalled quota format "
+                        printk(KERN_ERR "EXT3-fs: journaled quota format "
                                         "not specified.\n");
                         return 0;
                 }
         } else {
                 if (sbi->s_jquota_fmt) {
-                        printk(KERN_ERR "EXT3-fs: journalled quota format "
-                                        "specified with no journalling "
+                        printk(KERN_ERR "EXT3-fs: journaled quota format "
+                                        "specified with no journaling "
                                         "enabled.\n");
                         return 0;
                 }
@@ -1370,7 +1385,7 @@ static void ext3_orphan_cleanup (struct super_block * sb,
                         int ret = ext3_quota_on_mount(sb, i);
                         if (ret < 0)
                                 printk(KERN_ERR
-                                        "EXT3-fs: Cannot turn on journalled "
+                                        "EXT3-fs: Cannot turn on journaled "
                                         "quota: error %d\n", ret);
                 }
         }
@@ -2712,7 +2727,7 @@ static int ext3_release_dquot(struct dquot *dquot)
 
 static int ext3_mark_dquot_dirty(struct dquot *dquot)
 {
-        /* Are we journalling quotas? */
+        /* Are we journaling quotas? */
         if (EXT3_SB(dquot->dq_sb)->s_qf_names[USRQUOTA] ||
             EXT3_SB(dquot->dq_sb)->s_qf_names[GRPQUOTA]) {
                 dquot_mark_dquot_dirty(dquot);
@@ -2759,23 +2774,42 @@ static int ext3_quota_on(struct super_block *sb, int type, int format_id,
 
         if (!test_opt(sb, QUOTA))
                 return -EINVAL;
-        /* Not journalling quota or remount? */
-        if ((!EXT3_SB(sb)->s_qf_names[USRQUOTA] &&
-            !EXT3_SB(sb)->s_qf_names[GRPQUOTA]) || remount)
+        /* When remounting, no checks are needed and in fact, path is NULL */
+        if (remount)
                 return vfs_quota_on(sb, type, format_id, path, remount);
+
         err = path_lookup(path, LOOKUP_FOLLOW, &nd);
         if (err)
                 return err;
+
         /* Quotafile not on the same filesystem? */
         if (nd.path.mnt->mnt_sb != sb) {
                 path_put(&nd.path);
                 return -EXDEV;
         }
-        /* Quotafile not in fs root? */
-        if (nd.path.dentry->d_parent->d_inode != sb->s_root->d_inode)
-                printk(KERN_WARNING
-                        "EXT3-fs: Quota file not on filesystem root. "
-                        "Journalled quota will not work.\n");
+        /* Journaling quota? */
+        if (EXT3_SB(sb)->s_qf_names[type]) {
+                /* Quotafile not of fs root? */
+                if (nd.path.dentry->d_parent->d_inode != sb->s_root->d_inode)
+                        printk(KERN_WARNING
+                                "EXT3-fs: Quota file not on filesystem root. "
+                                "Journaled quota will not work.\n");
+        }
+
+        /*
+         * When we journal data on quota file, we have to flush journal to see
+         * all updates to the file when we bypass pagecache...
+         */
+        if (ext3_should_journal_data(nd.path.dentry->d_inode)) {
+                /*
+                 * We don't need to lock updates but journal_flush() could
+                 * otherwise be livelocked...
+                 */
+                journal_lock_updates(EXT3_SB(sb)->s_journal);
+                journal_flush(EXT3_SB(sb)->s_journal);
+                journal_unlock_updates(EXT3_SB(sb)->s_journal);
+        }
+
         path_put(&nd.path);
         return vfs_quota_on(sb, type, format_id, path, remount);
 }
diff --git a/fs/ext3/xattr_security.c b/fs/ext3/xattr_security.c
index 821efaf2b94e..37b81097bdf2 100644
--- a/fs/ext3/xattr_security.c
+++ b/fs/ext3/xattr_security.c
@@ -15,7 +15,7 @@ static size_t
 ext3_xattr_security_list(struct inode *inode, char *list, size_t list_size,
                          const char *name, size_t name_len)
 {
-        const size_t prefix_len = sizeof(XATTR_SECURITY_PREFIX)-1;
+        const size_t prefix_len = XATTR_SECURITY_PREFIX_LEN;
         const size_t total_len = prefix_len + name_len + 1;
 
 
diff --git a/fs/ext3/xattr_trusted.c b/fs/ext3/xattr_trusted.c
index 0327497a55ce..c7c41a410c4b 100644
--- a/fs/ext3/xattr_trusted.c
+++ b/fs/ext3/xattr_trusted.c
@@ -13,13 +13,11 @@
 #include <linux/ext3_fs.h>
 #include "xattr.h"
 
-#define XATTR_TRUSTED_PREFIX "trusted."
-
 static size_t
 ext3_xattr_trusted_list(struct inode *inode, char *list, size_t list_size,
                         const char *name, size_t name_len)
 {
-        const size_t prefix_len = sizeof(XATTR_TRUSTED_PREFIX)-1;
+        const size_t prefix_len = XATTR_TRUSTED_PREFIX_LEN;
         const size_t total_len = prefix_len + name_len + 1;
 
         if (!capable(CAP_SYS_ADMIN))
diff --git a/fs/ext3/xattr_user.c b/fs/ext3/xattr_user.c
index 1abd8f92c440..430fe63b31b3 100644
--- a/fs/ext3/xattr_user.c
+++ b/fs/ext3/xattr_user.c
@@ -12,13 +12,11 @@
 #include <linux/ext3_fs.h>
 #include "xattr.h"
 
-#define XATTR_USER_PREFIX "user."
-
 static size_t
 ext3_xattr_user_list(struct inode *inode, char *list, size_t list_size,
                      const char *name, size_t name_len)
 {
-        const size_t prefix_len = sizeof(XATTR_USER_PREFIX)-1;
+        const size_t prefix_len = XATTR_USER_PREFIX_LEN;
         const size_t total_len = prefix_len + name_len + 1;
 
         if (!test_opt(inode->i_sb, XATTR_USER))