Merge branch 'master' into upstream-fixes

15 files changed, 457 insertions, 131 deletions

diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index ba1c88af49fe..82011019494c 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -308,7 +308,7 @@ static struct adfs_discmap *adfs_read_map(struct super_block *sb, struct adfs_di
         if (adfs_checkmap(sb, dm))
                 return dm;
 
-        adfs_error(sb, NULL, "map corrupted");
+        adfs_error(sb, "map corrupted");
 
 error_free:
         while (--zone >= 0)
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 63614ed16336..5c4fcd1dbf59 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -395,14 +395,16 @@ static int fuse_readpages(struct file *file, struct address_space *mapping,
         struct fuse_readpages_data data;
         int err;
 
+        err = -EIO;
         if (is_bad_inode(inode))
-                return -EIO;
+                goto clean_pages_up;
 
         data.file = file;
         data.inode = inode;
         data.req = fuse_get_req(fc);
+        err = PTR_ERR(data.req);
         if (IS_ERR(data.req))
-                return PTR_ERR(data.req);
+                goto clean_pages_up;
 
         err = read_cache_pages(mapping, pages, fuse_readpages_fill, &data);
         if (!err) {
@@ -412,6 +414,10 @@ static int fuse_readpages(struct file *file, struct address_space *mapping,
                         fuse_put_request(fc, data.req);
         }
         return err;
+
+clean_pages_up:
+        put_pages_list(pages);
+        return err;
 }
 
 static size_t fuse_send_write(struct fuse_req *req, struct file *file,
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index 43e3f566aad6..a223cf4faa9b 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -168,16 +168,15 @@ void jfs_dirty_inode(struct inode *inode)
         set_cflag(COMMIT_Dirty, inode);
 }
 
-static int
-jfs_get_blocks(struct inode *ip, sector_t lblock, unsigned long max_blocks,
-                        struct buffer_head *bh_result, int create)
+int jfs_get_block(struct inode *ip, sector_t lblock,
+                  struct buffer_head *bh_result, int create)
 {
         s64 lblock64 = lblock;
         int rc = 0;
         xad_t xad;
         s64 xaddr;
         int xflag;
-        s32 xlen = max_blocks;
+        s32 xlen = bh_result->b_size >> ip->i_blkbits;
 
         /*
          * Take appropriate lock on inode
@@ -188,7 +187,7 @@ jfs_get_blocks(struct inode *ip, sector_t lblock, unsigned long max_blocks,
                 IREAD_LOCK(ip);
 
         if (((lblock64 << ip->i_sb->s_blocksize_bits) < ip->i_size) &&
-            (!xtLookup(ip, lblock64, max_blocks, &xflag, &xaddr, &xlen, 0)) &&
+            (!xtLookup(ip, lblock64, xlen, &xflag, &xaddr, &xlen, 0)) &&
             xaddr) {
                 if (xflag & XAD_NOTRECORDED) {
                         if (!create)
@@ -255,13 +254,6 @@ jfs_get_blocks(struct inode *ip, sector_t lblock, unsigned long max_blocks,
         return rc;
 }
 
-static int jfs_get_block(struct inode *ip, sector_t lblock,
-                         struct buffer_head *bh_result, int create)
-{
-        return jfs_get_blocks(ip, lblock, bh_result->b_size >> ip->i_blkbits,
-                        bh_result, create);
-}
-
 static int jfs_writepage(struct page *page, struct writeback_control *wbc)
 {
         return nobh_writepage(page, jfs_get_block, wbc);
diff --git a/fs/jfs/jfs_inode.h b/fs/jfs/jfs_inode.h
index b5c7da6190dc..1fc48df670c8 100644
--- a/fs/jfs/jfs_inode.h
+++ b/fs/jfs/jfs_inode.h
@@ -32,6 +32,7 @@ extern void jfs_truncate_nolock(struct inode *, loff_t);
 extern void jfs_free_zero_link(struct inode *);
 extern struct dentry *jfs_get_parent(struct dentry *dentry);
 extern void jfs_set_inode_flags(struct inode *);
+extern int jfs_get_block(struct inode *, sector_t, struct buffer_head *, int);
 
 extern const struct address_space_operations jfs_aops;
 extern struct inode_operations jfs_dir_inode_operations;
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 4f6cfebc82db..143bcd1d5eaa 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -26,6 +26,7 @@
 #include <linux/moduleparam.h>
 #include <linux/kthread.h>
 #include <linux/posix_acl.h>
+#include <linux/buffer_head.h>
 #include <asm/uaccess.h>
 #include <linux/seq_file.h>
 
@@ -298,7 +299,7 @@ static int parse_options(char *options, struct super_block *sb, s64 *newLVSize,
                         break;
                 }
 
-#if defined(CONFIG_QUOTA)
+#ifdef CONFIG_QUOTA
                 case Opt_quota:
                 case Opt_usrquota:
                         *flag |= JFS_USRQUOTA;
@@ -597,7 +598,7 @@ static int jfs_show_options(struct seq_file *seq, struct vfsmount *vfs)
         if (sbi->flag & JFS_NOINTEGRITY)
                 seq_puts(seq, ",nointegrity");
 
-#if defined(CONFIG_QUOTA)
+#ifdef CONFIG_QUOTA
         if (sbi->flag & JFS_USRQUOTA)
                 seq_puts(seq, ",usrquota");
 
@@ -608,6 +609,113 @@ static int jfs_show_options(struct seq_file *seq, struct vfsmount *vfs)
         return 0;
 }
 
+#ifdef CONFIG_QUOTA
+
+/* Read data from quotafile - avoid pagecache and such because we cannot afford
+ * acquiring the locks... As quota files are never truncated and quota code
+ * itself serializes the operations (and noone else should touch the files)
+ * we don't have to be afraid of races */
+static ssize_t jfs_quota_read(struct super_block *sb, int type, char *data,
+                              size_t len, loff_t off)
+{
+        struct inode *inode = sb_dqopt(sb)->files[type];
+        sector_t blk = off >> sb->s_blocksize_bits;
+        int err = 0;
+        int offset = off & (sb->s_blocksize - 1);
+        int tocopy;
+        size_t toread;
+        struct buffer_head tmp_bh;
+        struct buffer_head *bh;
+        loff_t i_size = i_size_read(inode);
+
+        if (off > i_size)
+                return 0;
+        if (off+len > i_size)
+                len = i_size-off;
+        toread = len;
+        while (toread > 0) {
+                tocopy = sb->s_blocksize - offset < toread ?
+                                sb->s_blocksize - offset : toread;
+
+                tmp_bh.b_state = 0;
+                tmp_bh.b_size = 1 << inode->i_blkbits;
+                err = jfs_get_block(inode, blk, &tmp_bh, 0);
+                if (err)
+                        return err;
+                if (!buffer_mapped(&tmp_bh))    /* A hole? */
+                        memset(data, 0, tocopy);
+                else {
+                        bh = sb_bread(sb, tmp_bh.b_blocknr);
+                        if (!bh)
+                                return -EIO;
+                        memcpy(data, bh->b_data+offset, tocopy);
+                        brelse(bh);
+                }
+                offset = 0;
+                toread -= tocopy;
+                data += tocopy;
+                blk++;
+        }
+        return len;
+}
+
+/* Write to quotafile */
+static ssize_t jfs_quota_write(struct super_block *sb, int type,
+                               const char *data, size_t len, loff_t off)
+{
+        struct inode *inode = sb_dqopt(sb)->files[type];
+        sector_t blk = off >> sb->s_blocksize_bits;
+        int err = 0;
+        int offset = off & (sb->s_blocksize - 1);
+        int tocopy;
+        size_t towrite = len;
+        struct buffer_head tmp_bh;
+        struct buffer_head *bh;
+
+        mutex_lock(&inode->i_mutex);
+        while (towrite > 0) {
+                tocopy = sb->s_blocksize - offset < towrite ?
+                                sb->s_blocksize - offset : towrite;
+
+                tmp_bh.b_state = 0;
+                tmp_bh.b_size = 1 << inode->i_blkbits;
+                err = jfs_get_block(inode, blk, &tmp_bh, 1);
+                if (err)
+                        goto out;
+                if (offset || tocopy != sb->s_blocksize)
+                        bh = sb_bread(sb, tmp_bh.b_blocknr);
+                else
+                        bh = sb_getblk(sb, tmp_bh.b_blocknr);
+                if (!bh) {
+                        err = -EIO;
+                        goto out;
+                }
+                lock_buffer(bh);
+                memcpy(bh->b_data+offset, data, tocopy);
+                flush_dcache_page(bh->b_page);
+                set_buffer_uptodate(bh);
+                mark_buffer_dirty(bh);
+                unlock_buffer(bh);
+                brelse(bh);
+                offset = 0;
+                towrite -= tocopy;
+                data += tocopy;
+                blk++;
+        }
+out:
+        if (len == towrite)
+                return err;
+        if (inode->i_size < off+len-towrite)
+                i_size_write(inode, off+len-towrite);
+        inode->i_version++;
+        inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+        mark_inode_dirty(inode);
+        mutex_unlock(&inode->i_mutex);
+        return len - towrite;
+}
+
+#endif
+
 static struct super_operations jfs_super_operations = {
         .alloc_inode    = jfs_alloc_inode,
         .destroy_inode  = jfs_destroy_inode,
@@ -621,7 +729,11 @@ static struct super_operations jfs_super_operations = {
         .unlockfs       = jfs_unlockfs,
         .statfs         = jfs_statfs,
         .remount_fs     = jfs_remount,
-        .show_options   = jfs_show_options
+        .show_options   = jfs_show_options,
+#ifdef CONFIG_QUOTA
+        .quota_read     = jfs_quota_read,
+        .quota_write    = jfs_quota_write,
+#endif
 };
 
 static struct export_operations jfs_export_operations = {
diff --git a/fs/locks.c b/fs/locks.c
index b0b41a64e10b..d7c53392cac1 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1421,8 +1421,9 @@ static int __setlease(struct file *filp, long arg, struct file_lock **flp)
         if (!leases_enable)
                 goto out;
 
-        error = lease_alloc(filp, arg, &fl);
-        if (error)
+        error = -ENOMEM;
+        fl = locks_alloc_lock();
+        if (fl == NULL)
                 goto out;
 
         locks_copy_lock(fl, lease);
@@ -1430,6 +1431,7 @@ static int __setlease(struct file *filp, long arg, struct file_lock **flp)
         locks_insert_lock(before, fl);
 
         *flp = fl;
+        error = 0;
 out:
         return error;
 }
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 1b8346dd0572..9503240ef0e5 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -2375,7 +2375,6 @@ leave:
         mlog(0, "returning %d\n", ret);
         return ret;
 }
-EXPORT_SYMBOL_GPL(dlm_migrate_lockres);
 
 int dlm_lock_basts_flushed(struct dlm_ctxt *dlm, struct dlm_lock *lock)
 {
diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c
index b0c3134f4f70..37be4b2e0d4a 100644
--- a/fs/ocfs2/dlm/dlmunlock.c
+++ b/fs/ocfs2/dlm/dlmunlock.c
@@ -155,7 +155,7 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm,
         else
                 status = dlm_get_unlock_actions(dlm, res, lock, lksb, &actions);
 
-        if (status != DLM_NORMAL)
+        if (status != DLM_NORMAL && (status != DLM_CANCELGRANT || !master_node))
                 goto leave;
 
         /* By now this has been masked out of cancel requests. */
@@ -183,8 +183,7 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm,
                 spin_lock(&lock->spinlock);
                 /* if the master told us the lock was already granted,
                  * let the ast handle all of these actions */
-                if (status == DLM_NORMAL &&
-                    lksb->status == DLM_CANCELGRANT) {
+                if (status == DLM_CANCELGRANT) {
                         actions &= ~(DLM_UNLOCK_REMOVE_LOCK|
                                      DLM_UNLOCK_REGRANT_LOCK|
                                      DLM_UNLOCK_CLEAR_CONVERT_TYPE);
@@ -349,14 +348,9 @@ static enum dlm_status dlm_send_remote_unlock_request(struct dlm_ctxt *dlm,
                                         vec, veclen, owner, &status);
         if (tmpret >= 0) {
                 // successfully sent and received
-                if (status == DLM_CANCELGRANT)
-                        ret = DLM_NORMAL;
-                else if (status == DLM_FORWARD) {
+                if (status == DLM_FORWARD)
                         mlog(0, "master was in-progress.  retry\n");
-                        ret = DLM_FORWARD;
-                } else
-                        ret = status;
-                lksb->status = status;
+                ret = status;
         } else {
                 mlog_errno(tmpret);
                 if (dlm_is_host_down(tmpret)) {
@@ -372,7 +366,6 @@ static enum dlm_status dlm_send_remote_unlock_request(struct dlm_ctxt *dlm,
                         /* something bad.  this will BUG in ocfs2 */
                         ret = dlm_err_to_dlm_status(tmpret);
                 }
-                lksb->status = ret;
         }
 
         return ret;
@@ -483,6 +476,10 @@ int dlm_unlock_lock_handler(struct o2net_msg *msg, u32 len, void *data)
 
         /* lock was found on queue */
         lksb = lock->lksb;
+        if (flags & (LKM_VALBLK|LKM_PUT_LVB) &&
+            lock->ml.type != LKM_EXMODE)
+                flags &= ~(LKM_VALBLK|LKM_PUT_LVB);
+
         /* unlockast only called on originating node */
         if (flags & LKM_PUT_LVB) {
                 lksb->flags |= DLM_LKSB_PUT_LVB;
@@ -507,11 +504,8 @@ not_found:
                                "cookie=%u:%llu\n",
                                dlm_get_lock_cookie_node(unlock->cookie),
                                dlm_get_lock_cookie_seq(unlock->cookie));
-        else {
-                /* send the lksb->status back to the other node */
-                status = lksb->status;
+        else
                 dlm_lock_put(lock);
-        }
 
 leave:
         if (res)
@@ -533,26 +527,22 @@ static enum dlm_status dlm_get_cancel_actions(struct dlm_ctxt *dlm,
 
         if (dlm_lock_on_list(&res->blocked, lock)) {
                 /* cancel this outright */
-                lksb->status = DLM_NORMAL;
                 status = DLM_NORMAL;
                 *actions = (DLM_UNLOCK_CALL_AST |
                             DLM_UNLOCK_REMOVE_LOCK);
         } else if (dlm_lock_on_list(&res->converting, lock)) {
                 /* cancel the request, put back on granted */
-                lksb->status = DLM_NORMAL;
                 status = DLM_NORMAL;
                 *actions = (DLM_UNLOCK_CALL_AST |
                             DLM_UNLOCK_REMOVE_LOCK |
                             DLM_UNLOCK_REGRANT_LOCK |
                             DLM_UNLOCK_CLEAR_CONVERT_TYPE);
         } else if (dlm_lock_on_list(&res->granted, lock)) {
-                /* too late, already granted.  DLM_CANCELGRANT */
-                lksb->status = DLM_CANCELGRANT;
-                status = DLM_NORMAL;
+                /* too late, already granted. */
+                status = DLM_CANCELGRANT;
                 *actions = DLM_UNLOCK_CALL_AST;
         } else {
                 mlog(ML_ERROR, "lock to cancel is not on any list!\n");
-                lksb->status = DLM_IVLOCKID;
                 status = DLM_IVLOCKID;
                 *actions = 0;
         }
@@ -569,13 +559,11 @@ static enum dlm_status dlm_get_unlock_actions(struct dlm_ctxt *dlm,
 
         /* unlock request */
         if (!dlm_lock_on_list(&res->granted, lock)) {
-                lksb->status = DLM_DENIED;
                 status = DLM_DENIED;
                 dlm_error(status);
                 *actions = 0;
         } else {
                 /* unlock granted lock */
-                lksb->status = DLM_NORMAL;
                 status = DLM_NORMAL;
                 *actions = (DLM_UNLOCK_FREE_LOCK |
                             DLM_UNLOCK_CALL_AST |
@@ -632,6 +620,8 @@ retry:
 
         spin_lock(&res->spinlock);
         is_master = (res->owner == dlm->node_num);
+        if (flags & LKM_VALBLK && lock->ml.type != LKM_EXMODE)
+                flags &= ~LKM_VALBLK;
         spin_unlock(&res->spinlock);
 
         if (is_master) {
@@ -665,7 +655,7 @@ retry:
         }
 
         if (call_ast) {
-                mlog(0, "calling unlockast(%p, %d)\n", data, lksb->status);
+                mlog(0, "calling unlockast(%p, %d)\n", data, status);
                 if (is_master) {
                         /* it is possible that there is one last bast 
                          * pending.  make sure it is flushed, then
@@ -677,9 +667,12 @@ retry:
                         wait_event(dlm->ast_wq, 
                                    dlm_lock_basts_flushed(dlm, lock));
                 }
-                (*unlockast)(data, lksb->status);
+                (*unlockast)(data, status);
         }
 
+        if (status == DLM_CANCELGRANT)
+                status = DLM_NORMAL;
+
         if (status == DLM_NORMAL) {
                 mlog(0, "kicking the thread\n");
                 dlm_kick_thread(dlm, res);
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index 0d1973ea32b0..1f17a4d08287 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -840,6 +840,12 @@ static int ocfs2_local_alloc_new_window(struct ocfs2_super *osb,
 
         mlog(0, "Allocating %u clusters for a new window.\n",
              ocfs2_local_alloc_window_bits(osb));
+
+        /* Instruct the allocation code to try the most recently used
+         * cluster group. We'll re-record the group used this pass
+         * below. */
+        ac->ac_last_group = osb->la_last_gd;
+
         /* we used the generic suballoc reserve function, but we set
          * everything up nicely, so there's no reason why we can't use
          * the more specific cluster api to claim bits. */
@@ -852,6 +858,8 @@ static int ocfs2_local_alloc_new_window(struct ocfs2_super *osb,
                 goto bail;
         }
 
+        osb->la_last_gd = ac->ac_last_group;
+
         la->la_bm_off = cpu_to_le32(cluster_off);
         alloc->id1.bitmap1.i_total = cpu_to_le32(cluster_count);
         /* just in case... In the future when we find space ourselves,
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index cd4a6f253d13..0462a7f4e21b 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -197,7 +197,6 @@ struct ocfs2_super
         struct ocfs2_node_map recovery_map;
         struct ocfs2_node_map umount_map;
 
-        u32 num_clusters;
         u64 root_blkno;
         u64 system_dir_blkno;
         u64 bitmap_blkno;
@@ -237,6 +236,7 @@ struct ocfs2_super
 
         enum ocfs2_local_alloc_state local_alloc_state;
         struct buffer_head *local_alloc_bh;
+        u64 la_last_gd;
 
         /* Next two fields are for local node slot recovery during
          * mount. */
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 195523090c87..9d91e66f51a9 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -70,12 +70,6 @@ static int ocfs2_block_group_search(struct inode *inode,
                                     struct buffer_head *group_bh,
                                     u32 bits_wanted, u32 min_bits,
                                     u16 *bit_off, u16 *bits_found);
-static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
-                              u32 bits_wanted,
-                              u32 min_bits,
-                              u16 *bit_off,
-                              unsigned int *num_bits,
-                              u64 *bg_blkno);
 static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb,
                                      struct ocfs2_alloc_context *ac,
                                      u32 bits_wanted,
@@ -85,11 +79,6 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb,
                                      u64 *bg_blkno);
 static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh,
                                          int nr);
-static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb,
-                                             struct buffer_head *bg_bh,
-                                             unsigned int bits_wanted,
-                                             u16 *bit_off,
-                                             u16 *bits_found);
 static inline int ocfs2_block_group_set_bits(struct ocfs2_journal_handle *handle,
                                              struct inode *alloc_inode,
                                              struct ocfs2_group_desc *bg,
@@ -143,6 +132,64 @@ static u32 ocfs2_bits_per_group(struct ocfs2_chain_list *cl)
         return (u32)le16_to_cpu(cl->cl_cpg) * (u32)le16_to_cpu(cl->cl_bpc);
 }
 
+/* somewhat more expensive than our other checks, so use sparingly. */
+static int ocfs2_check_group_descriptor(struct super_block *sb,
+                                        struct ocfs2_dinode *di,
+                                        struct ocfs2_group_desc *gd)
+{
+        unsigned int max_bits;
+
+        if (!OCFS2_IS_VALID_GROUP_DESC(gd)) {
+                OCFS2_RO_ON_INVALID_GROUP_DESC(sb, gd);
+                return -EIO;
+        }
+
+        if (di->i_blkno != gd->bg_parent_dinode) {
+                ocfs2_error(sb, "Group descriptor # %llu has bad parent "
+                            "pointer (%llu, expected %llu)",
+                            (unsigned long long)le64_to_cpu(gd->bg_blkno),
+                            (unsigned long long)le64_to_cpu(gd->bg_parent_dinode),
+                            (unsigned long long)le64_to_cpu(di->i_blkno));
+                return -EIO;
+        }
+
+        max_bits = le16_to_cpu(di->id2.i_chain.cl_cpg) * le16_to_cpu(di->id2.i_chain.cl_bpc);
+        if (le16_to_cpu(gd->bg_bits) > max_bits) {
+                ocfs2_error(sb, "Group descriptor # %llu has bit count of %u",
+                            (unsigned long long)le64_to_cpu(gd->bg_blkno),
+                            le16_to_cpu(gd->bg_bits));
+                return -EIO;
+        }
+
+        if (le16_to_cpu(gd->bg_chain) >=
+            le16_to_cpu(di->id2.i_chain.cl_next_free_rec)) {
+                ocfs2_error(sb, "Group descriptor # %llu has bad chain %u",
+                            (unsigned long long)le64_to_cpu(gd->bg_blkno),
+                            le16_to_cpu(gd->bg_chain));
+                return -EIO;
+        }
+
+        if (le16_to_cpu(gd->bg_free_bits_count) > le16_to_cpu(gd->bg_bits)) {
+                ocfs2_error(sb, "Group descriptor # %llu has bit count %u but "
+                            "claims that %u are free",
+                            (unsigned long long)le64_to_cpu(gd->bg_blkno),
+                            le16_to_cpu(gd->bg_bits),
+                            le16_to_cpu(gd->bg_free_bits_count));
+                return -EIO;
+        }
+
+        if (le16_to_cpu(gd->bg_bits) > (8 * le16_to_cpu(gd->bg_size))) {
+                ocfs2_error(sb, "Group descriptor # %llu has bit count %u but "
+                            "max bitmap bits of %u",
+                            (unsigned long long)le64_to_cpu(gd->bg_blkno),
+                            le16_to_cpu(gd->bg_bits),
+                            8 * le16_to_cpu(gd->bg_size));
+                return -EIO;
+        }
+
+        return 0;
+}
+
 static int ocfs2_block_group_fill(struct ocfs2_journal_handle *handle,
                                   struct inode *alloc_inode,
                                   struct buffer_head *bg_bh,
@@ -663,6 +710,7 @@ static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh,
 static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb,
                                              struct buffer_head *bg_bh,
                                              unsigned int bits_wanted,
+                                             unsigned int total_bits,
                                              u16 *bit_off,
                                              u16 *bits_found)
 {
@@ -679,10 +727,8 @@ static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb,
         found = start = best_offset = best_size = 0;
         bitmap = bg->bg_bitmap;
 
-        while((offset = ocfs2_find_next_zero_bit(bitmap,
-                                                 le16_to_cpu(bg->bg_bits),
-                                                 start)) != -1) {
-                if (offset == le16_to_cpu(bg->bg_bits))
+        while((offset = ocfs2_find_next_zero_bit(bitmap, total_bits, start)) != -1) {
+                if (offset == total_bits)
                         break;
 
                 if (!ocfs2_test_bg_bit_allocatable(bg_bh, offset)) {
@@ -911,14 +957,35 @@ static int ocfs2_cluster_group_search(struct inode *inode,
 {
         int search = -ENOSPC;
         int ret;
-        struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) group_bh->b_data;
+        struct ocfs2_group_desc *gd = (struct ocfs2_group_desc *) group_bh->b_data;
         u16 tmp_off, tmp_found;
+        unsigned int max_bits, gd_cluster_off;
 
         BUG_ON(!ocfs2_is_cluster_bitmap(inode));
 
-        if (bg->bg_free_bits_count) {
+        if (gd->bg_free_bits_count) {
+                max_bits = le16_to_cpu(gd->bg_bits);
+
+                /* Tail groups in cluster bitmaps which aren't cpg
+                 * aligned are prone to partial extention by a failed
+                 * fs resize. If the file system resize never got to
+                 * update the dinode cluster count, then we don't want
+                 * to trust any clusters past it, regardless of what
+                 * the group descriptor says. */
+                gd_cluster_off = ocfs2_blocks_to_clusters(inode->i_sb,
+                                                          le64_to_cpu(gd->bg_blkno));
+                if ((gd_cluster_off + max_bits) >
+                    OCFS2_I(inode)->ip_clusters) {
+                        max_bits = OCFS2_I(inode)->ip_clusters - gd_cluster_off;
+                        mlog(0, "Desc %llu, bg_bits %u, clusters %u, use %u\n",
+                             (unsigned long long)le64_to_cpu(gd->bg_blkno),
+                             le16_to_cpu(gd->bg_bits),
+                             OCFS2_I(inode)->ip_clusters, max_bits);
+                }
+
                 ret = ocfs2_block_group_find_clear_bits(OCFS2_SB(inode->i_sb),
                                                         group_bh, bits_wanted,
+                                                        max_bits,
                                                         &tmp_off, &tmp_found);
                 if (ret)
                         return ret;
@@ -951,17 +1018,109 @@ static int ocfs2_block_group_search(struct inode *inode,
         if (bg->bg_free_bits_count)
                 ret = ocfs2_block_group_find_clear_bits(OCFS2_SB(inode->i_sb),
                                                         group_bh, bits_wanted,
+                                                        le16_to_cpu(bg->bg_bits),
                                                         bit_off, bits_found);
 
         return ret;
 }
 
+static int ocfs2_alloc_dinode_update_counts(struct inode *inode,
+                                       struct ocfs2_journal_handle *handle,
+                                       struct buffer_head *di_bh,
+                                       u32 num_bits,
+                                       u16 chain)
+{
+        int ret;
+        u32 tmp_used;
+        struct ocfs2_dinode *di = (struct ocfs2_dinode *) di_bh->b_data;
+        struct ocfs2_chain_list *cl = (struct ocfs2_chain_list *) &di->id2.i_chain;
+
+        ret = ocfs2_journal_access(handle, inode, di_bh,
+                                   OCFS2_JOURNAL_ACCESS_WRITE);
+        if (ret < 0) {
+                mlog_errno(ret);
+                goto out;
+        }
+
+        tmp_used = le32_to_cpu(di->id1.bitmap1.i_used);
+        di->id1.bitmap1.i_used = cpu_to_le32(num_bits + tmp_used);
+        le32_add_cpu(&cl->cl_recs[chain].c_free, -num_bits);
+
+        ret = ocfs2_journal_dirty(handle, di_bh);
+        if (ret < 0)
+                mlog_errno(ret);
+
+out:
+        return ret;
+}
+
+static int ocfs2_search_one_group(struct ocfs2_alloc_context *ac,
+                                  u32 bits_wanted,
+                                  u32 min_bits,
+                                  u16 *bit_off,
+                                  unsigned int *num_bits,
+                                  u64 gd_blkno,
+                                  u16 *bits_left)
+{
+        int ret;
+        u16 found;
+        struct buffer_head *group_bh = NULL;
+        struct ocfs2_group_desc *gd;
+        struct inode *alloc_inode = ac->ac_inode;
+        struct ocfs2_journal_handle *handle = ac->ac_handle;
+
+        ret = ocfs2_read_block(OCFS2_SB(alloc_inode->i_sb), gd_blkno,
+                               &group_bh, OCFS2_BH_CACHED, alloc_inode);
+        if (ret < 0) {
+                mlog_errno(ret);
+                return ret;
+        }
+
+        gd = (struct ocfs2_group_desc *) group_bh->b_data;
+        if (!OCFS2_IS_VALID_GROUP_DESC(gd)) {
+                OCFS2_RO_ON_INVALID_GROUP_DESC(alloc_inode->i_sb, gd);
+                ret = -EIO;
+                goto out;
+        }
+
+        ret = ac->ac_group_search(alloc_inode, group_bh, bits_wanted, min_bits,
+                                  bit_off, &found);
+        if (ret < 0) {
+                if (ret != -ENOSPC)
+                        mlog_errno(ret);
+                goto out;
+        }
+
+        *num_bits = found;
+
+        ret = ocfs2_alloc_dinode_update_counts(alloc_inode, handle, ac->ac_bh,
+                                               *num_bits,
+                                               le16_to_cpu(gd->bg_chain));
+        if (ret < 0) {
+                mlog_errno(ret);
+                goto out;
+        }
+
+        ret = ocfs2_block_group_set_bits(handle, alloc_inode, gd, group_bh,
+                                         *bit_off, *num_bits);
+        if (ret < 0)
+                mlog_errno(ret);
+
+        *bits_left = le16_to_cpu(gd->bg_free_bits_count);
+
+out:
+        brelse(group_bh);
+
+        return ret;
+}
+
 static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
                               u32 bits_wanted,
                               u32 min_bits,
                               u16 *bit_off,
                               unsigned int *num_bits,
-                              u64 *bg_blkno)
+                              u64 *bg_blkno,
+                              u16 *bits_left)
 {
         int status;
         u16 chain, tmp_bits;
@@ -988,9 +1147,9 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
                 goto bail;
         }
         bg = (struct ocfs2_group_desc *) group_bh->b_data;
-        if (!OCFS2_IS_VALID_GROUP_DESC(bg)) {
-                OCFS2_RO_ON_INVALID_GROUP_DESC(alloc_inode->i_sb, bg);
-                status = -EIO;
+        status = ocfs2_check_group_descriptor(alloc_inode->i_sb, fe, bg);
+        if (status) {
+                mlog_errno(status);
                 goto bail;
         }
 
@@ -1018,9 +1177,9 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
                         goto bail;
                 }
                 bg = (struct ocfs2_group_desc *) group_bh->b_data;
-                if (!OCFS2_IS_VALID_GROUP_DESC(bg)) {
-                        OCFS2_RO_ON_INVALID_GROUP_DESC(alloc_inode->i_sb, bg);
-                        status = -EIO;
+                status = ocfs2_check_group_descriptor(alloc_inode->i_sb, fe, bg);
+                if (status) {
+                        mlog_errno(status);
                         goto bail;
                 }
         }
@@ -1099,6 +1258,7 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
              (unsigned long long)fe->i_blkno);
 
         *bg_blkno = le64_to_cpu(bg->bg_blkno);
+        *bits_left = le16_to_cpu(bg->bg_free_bits_count);
 bail:
         if (group_bh)
                 brelse(group_bh);
@@ -1120,6 +1280,8 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb,
 {
         int status;
         u16 victim, i;
+        u16 bits_left = 0;
+        u64 hint_blkno = ac->ac_last_group;
         struct ocfs2_chain_list *cl;
         struct ocfs2_dinode *fe;
 
@@ -1146,6 +1308,28 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb,
                 goto bail;
         }
 
+        if (hint_blkno) {
+                /* Attempt to short-circuit the usual search mechanism
+                 * by jumping straight to the most recently used
+                 * allocation group. This helps us mantain some
+                 * contiguousness across allocations. */
+                status = ocfs2_search_one_group(ac, bits_wanted, min_bits,
+                                                bit_off, num_bits,
+                                                hint_blkno, &bits_left);
+                if (!status) {
+                        /* Be careful to update *bg_blkno here as the
+                         * caller is expecting it to be filled in, and
+                         * ocfs2_search_one_group() won't do that for
+                         * us. */
+                        *bg_blkno = hint_blkno;
+                        goto set_hint;
+                }
+                if (status < 0 && status != -ENOSPC) {
+                        mlog_errno(status);
+                        goto bail;
+                }
+        }
+
         cl = (struct ocfs2_chain_list *) &fe->id2.i_chain;
 
         victim = ocfs2_find_victim_chain(cl);
@@ -1153,9 +1337,9 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb,
         ac->ac_allow_chain_relink = 1;
 
         status = ocfs2_search_chain(ac, bits_wanted, min_bits, bit_off,
-                                    num_bits, bg_blkno);
+                                    num_bits, bg_blkno, &bits_left);
         if (!status)
-                goto bail;
+                goto set_hint;
         if (status < 0 && status != -ENOSPC) {
                 mlog_errno(status);
                 goto bail;
@@ -1177,8 +1361,8 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb,
 
                 ac->ac_chain = i;
                 status = ocfs2_search_chain(ac, bits_wanted, min_bits,
-                                            bit_off, num_bits,
-                                            bg_blkno);
+                                            bit_off, num_bits, bg_blkno,
+                                            &bits_left);
                 if (!status)
                         break;
                 if (status < 0 && status != -ENOSPC) {
@@ -1186,8 +1370,19 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb,
                         goto bail;
                 }
         }
-bail:
 
+set_hint:
+        if (status != -ENOSPC) {
+                /* If the next search of this group is not likely to
+                 * yield a suitable extent, then we reset the last
+                 * group hint so as to not waste a disk read */
+                if (bits_left < min_bits)
+                        ac->ac_last_group = 0;
+                else
+                        ac->ac_last_group = *bg_blkno;
+        }
+
+bail:
         mlog_exit(status);
         return status;
 }
@@ -1341,7 +1536,7 @@ int ocfs2_claim_clusters(struct ocfs2_super *osb,
 {
         int status;
         unsigned int bits_wanted = ac->ac_bits_wanted - ac->ac_bits_given;
-        u64 bg_blkno;
+        u64 bg_blkno = 0;
         u16 bg_bit_off;
 
         mlog_entry_void();
@@ -1494,9 +1689,9 @@ static int ocfs2_free_suballoc_bits(struct ocfs2_journal_handle *handle,
         }
 
         group = (struct ocfs2_group_desc *) group_bh->b_data;
-        if (!OCFS2_IS_VALID_GROUP_DESC(group)) {
-                OCFS2_RO_ON_INVALID_GROUP_DESC(alloc_inode->i_sb, group);
-                status = -EIO;
+        status = ocfs2_check_group_descriptor(alloc_inode->i_sb, fe, group);
+        if (status) {
+                mlog_errno(status);
                 goto bail;
         }
         BUG_ON((count + start_bit) > le16_to_cpu(group->bg_bits));
diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h
index a76c82a7ceac..c787838d1052 100644
--- a/fs/ocfs2/suballoc.h
+++ b/fs/ocfs2/suballoc.h
@@ -49,6 +49,8 @@ struct ocfs2_alloc_context {
         u16    ac_chain;
         int    ac_allow_chain_relink;
         group_search_t *ac_group_search;
+
+        u64    ac_last_group;
 };
 
 void ocfs2_free_alloc_context(struct ocfs2_alloc_context *ac);
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 382706a67ffd..d17e33e66a1e 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1442,8 +1442,13 @@ static int ocfs2_initialize_super(struct super_block *sb,
 
         osb->bitmap_blkno = OCFS2_I(inode)->ip_blkno;
 
+        /* We don't have a cluster lock on the bitmap here because
+         * we're only interested in static information and the extra
+         * complexity at mount time isn't worht it. Don't pass the
+         * inode in to the read function though as we don't want it to
+         * be put in the cache. */
         status = ocfs2_read_block(osb, osb->bitmap_blkno, &bitmap_bh, 0,
-                                  inode);
+                                  NULL);
         iput(inode);
         if (status < 0) {
                 mlog_errno(status);
@@ -1452,7 +1457,6 @@ static int ocfs2_initialize_super(struct super_block *sb,
 
         di = (struct ocfs2_dinode *) bitmap_bh->b_data;
         osb->bitmap_cpg = le16_to_cpu(di->id2.i_chain.cl_cpg);
-        osb->num_clusters = le32_to_cpu(di->id1.bitmap1.i_total);
         brelse(bitmap_bh);
         mlog(0, "cluster bitmap inode: %llu, clusters per group: %u\n",
              (unsigned long long)osb->bitmap_blkno, osb->bitmap_cpg);
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 4df822c881b6..7de172efa084 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -115,6 +115,13 @@ static struct inode *udf_alloc_inode(struct super_block *sb)
         ei = (struct udf_inode_info *)kmem_cache_alloc(udf_inode_cachep, SLAB_KERNEL);
         if (!ei)
                 return NULL;
+
+        ei->i_unique = 0;
+        ei->i_lenExtents = 0;
+        ei->i_next_alloc_block = 0;
+        ei->i_next_alloc_goal = 0;
+        ei->i_strat4096 = 0;
+
         return &ei->vfs_inode;
 }
 
diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c
index eef6763f3a67..d2bbcd882a69 100644
--- a/fs/xfs/xfs_alloc.c
+++ b/fs/xfs/xfs_alloc.c
@@ -1835,40 +1835,47 @@ xfs_alloc_fix_freelist(
                                 &agbp)))
                         return error;
                 if (!pag->pagf_init) {
+                        ASSERT(flags & XFS_ALLOC_FLAG_TRYLOCK);
+                        ASSERT(!(flags & XFS_ALLOC_FLAG_FREEING));
                         args->agbp = NULL;
                         return 0;
                 }
         } else
                 agbp = NULL;
 
-        /* If this is a metadata preferred pag and we are user data
+        /*
+         * If this is a metadata preferred pag and we are user data
          * then try somewhere else if we are not being asked to
          * try harder at this point
          */
-        if (pag->pagf_metadata && args->userdata && flags) {
+        if (pag->pagf_metadata && args->userdata &&
+            (flags & XFS_ALLOC_FLAG_TRYLOCK)) {
+                ASSERT(!(flags & XFS_ALLOC_FLAG_FREEING));
                 args->agbp = NULL;
                 return 0;
         }
 
-        need = XFS_MIN_FREELIST_PAG(pag, mp);
-        delta = need > pag->pagf_flcount ? need - pag->pagf_flcount : 0;
-        /*
-         * If it looks like there isn't a long enough extent, or enough
-         * total blocks, reject it.
-         */
-        longest = (pag->pagf_longest > delta) ?
-                (pag->pagf_longest - delta) :
-                (pag->pagf_flcount > 0 || pag->pagf_longest > 0);
-        if (args->minlen + args->alignment + args->minalignslop - 1 > longest ||
-            (!(flags & XFS_ALLOC_FLAG_FREEING) &&
-             (int)(pag->pagf_freeblks + pag->pagf_flcount -
-                   need - args->total) <
-             (int)args->minleft)) {
-                if (agbp)
-                        xfs_trans_brelse(tp, agbp);
-                args->agbp = NULL;
-                return 0;
+        if (!(flags & XFS_ALLOC_FLAG_FREEING)) {
+                need = XFS_MIN_FREELIST_PAG(pag, mp);
+                delta = need > pag->pagf_flcount ? need - pag->pagf_flcount : 0;
+                /*
+                 * If it looks like there isn't a long enough extent, or enough
+                 * total blocks, reject it.
+                 */
+                longest = (pag->pagf_longest > delta) ?
+                        (pag->pagf_longest - delta) :
+                        (pag->pagf_flcount > 0 || pag->pagf_longest > 0);
+                if ((args->minlen + args->alignment + args->minalignslop - 1) >
+                                longest ||
+                    ((int)(pag->pagf_freeblks + pag->pagf_flcount -
+                           need - args->total) < (int)args->minleft)) {
+                        if (agbp)
+                                xfs_trans_brelse(tp, agbp);
+                        args->agbp = NULL;
+                        return 0;
+                }
         }
+
         /*
          * Get the a.g. freespace buffer.
          * Can fail if we're not blocking on locks, and it's held.
@@ -1878,6 +1885,8 @@ xfs_alloc_fix_freelist(
                                 &agbp)))
                         return error;
                 if (agbp == NULL) {
+                        ASSERT(flags & XFS_ALLOC_FLAG_TRYLOCK);
+                        ASSERT(!(flags & XFS_ALLOC_FLAG_FREEING));
                         args->agbp = NULL;
                         return 0;
                 }
@@ -1887,22 +1896,24 @@ xfs_alloc_fix_freelist(
          */
         agf = XFS_BUF_TO_AGF(agbp);
         need = XFS_MIN_FREELIST(agf, mp);
-        delta = need > be32_to_cpu(agf->agf_flcount) ?
-                (need - be32_to_cpu(agf->agf_flcount)) : 0;
         /*
          * If there isn't enough total or single-extent, reject it.
          */
-        longest = be32_to_cpu(agf->agf_longest);
-        longest = (longest > delta) ? (longest - delta) :
-                (be32_to_cpu(agf->agf_flcount) > 0 || longest > 0);
-        if (args->minlen + args->alignment + args->minalignslop - 1 > longest ||
-             (!(flags & XFS_ALLOC_FLAG_FREEING) &&
-                (int)(be32_to_cpu(agf->agf_freeblks) +
-                   be32_to_cpu(agf->agf_flcount) - need - args->total) <
-             (int)args->minleft)) {
-                xfs_trans_brelse(tp, agbp);
-                args->agbp = NULL;
-                return 0;
+        if (!(flags & XFS_ALLOC_FLAG_FREEING)) {
+                delta = need > be32_to_cpu(agf->agf_flcount) ?
+                        (need - be32_to_cpu(agf->agf_flcount)) : 0;
+                longest = be32_to_cpu(agf->agf_longest);
+                longest = (longest > delta) ? (longest - delta) :
+                        (be32_to_cpu(agf->agf_flcount) > 0 || longest > 0);
+                if ((args->minlen + args->alignment + args->minalignslop - 1) >
+                                longest ||
+                    ((int)(be32_to_cpu(agf->agf_freeblks) +
+                     be32_to_cpu(agf->agf_flcount) - need - args->total) <
+                                (int)args->minleft)) {
+                        xfs_trans_brelse(tp, agbp);
+                        args->agbp = NULL;
+                        return 0;
+                }
         }
         /*
          * Make the freelist shorter if it's too long.
@@ -1950,12 +1961,11 @@ xfs_alloc_fix_freelist(
                  * on a completely full ag.
                  */
                 if (targs.agbno == NULLAGBLOCK) {
-                        if (!(flags & XFS_ALLOC_FLAG_FREEING)) {
-                                xfs_trans_brelse(tp, agflbp);
-                                args->agbp = NULL;
-                                return 0;
-                        }
-                        break;
+                        if (flags & XFS_ALLOC_FLAG_FREEING)
+                                break;
+                        xfs_trans_brelse(tp, agflbp);
+                        args->agbp = NULL;
+                        return 0;
                 }
                 /*
                  * Put each allocated block on the list.
@@ -2442,31 +2452,26 @@ xfs_free_extent(
         xfs_fsblock_t   bno,    /* starting block number of extent */
         xfs_extlen_t    len)    /* length of extent */
 {
-#ifdef DEBUG
-        xfs_agf_t       *agf;   /* a.g. freespace header */
-#endif
-        xfs_alloc_arg_t args;   /* allocation argument structure */
+        xfs_alloc_arg_t args;
         int             error;
 
         ASSERT(len != 0);
+        memset(&args, 0, sizeof(xfs_alloc_arg_t));
         args.tp = tp;
         args.mp = tp->t_mountp;
         args.agno = XFS_FSB_TO_AGNO(args.mp, bno);
         ASSERT(args.agno < args.mp->m_sb.sb_agcount);
         args.agbno = XFS_FSB_TO_AGBNO(args.mp, bno);
-        args.alignment = 1;
-        args.minlen = args.minleft = args.minalignslop = 0;
         down_read(&args.mp->m_peraglock);
         args.pag = &args.mp->m_perag[args.agno];
         if ((error = xfs_alloc_fix_freelist(&args, XFS_ALLOC_FLAG_FREEING)))
                 goto error0;
 #ifdef DEBUG
         ASSERT(args.agbp != NULL);
-        agf = XFS_BUF_TO_AGF(args.agbp);
-        ASSERT(args.agbno + len <= be32_to_cpu(agf->agf_length));
+        ASSERT((args.agbno + len) <=
+                be32_to_cpu(XFS_BUF_TO_AGF(args.agbp)->agf_length));
 #endif
-        error = xfs_free_ag_extent(tp, args.agbp, args.agno, args.agbno,
-                len, 0);
+        error = xfs_free_ag_extent(tp, args.agbp, args.agno, args.agbno, len, 0);
 error0:
         up_read(&args.mp->m_peraglock);
         return error;