12 files changed, 108 insertions, 42 deletions

diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 60fe74035db..19e3a96aa02 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -176,7 +176,8 @@ static int ocfs2_dinode_insert_check(struct inode *inode,
 
         BUG_ON(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL);
         mlog_bug_on_msg(!ocfs2_sparse_alloc(osb) &&
-                        (OCFS2_I(inode)->ip_clusters != rec->e_cpos),
+                        (OCFS2_I(inode)->ip_clusters !=
+                         le32_to_cpu(rec->e_cpos)),
                         "Device %s, asking for sparse allocation: inode %llu, "
                         "cpos %u, clusters %u\n",
                         osb->dev_str,
@@ -4796,6 +4797,29 @@ out:
         return ret;
 }
 
+static int ocfs2_replace_extent_rec(struct inode *inode,
+                                    handle_t *handle,
+                                    struct ocfs2_path *path,
+                                    struct ocfs2_extent_list *el,
+                                    int split_index,
+                                    struct ocfs2_extent_rec *split_rec)
+{
+        int ret;
+
+        ret = ocfs2_path_bh_journal_access(handle, inode, path,
+                                           path_num_items(path) - 1);
+        if (ret) {
+                mlog_errno(ret);
+                goto out;
+        }
+
+        el->l_recs[split_index] = *split_rec;
+
+        ocfs2_journal_dirty(handle, path_leaf_bh(path));
+out:
+        return ret;
+}
+
 /*
  * Mark part or all of the extent record at split_index in the leaf
  * pointed to by path as written. This removes the unwritten
@@ -4885,7 +4909,9 @@ static int __ocfs2_mark_extent_written(struct inode *inode,
 
         if (ctxt.c_contig_type == CONTIG_NONE) {
                 if (ctxt.c_split_covers_rec)
-                        el->l_recs[split_index] = *split_rec;
+                        ret = ocfs2_replace_extent_rec(inode, handle,
+                                                       path, el,
+                                                       split_index, split_rec);
                 else
                         ret = ocfs2_split_and_insert(inode, handle, path, et,
                                                      &last_eb_bh, split_index,
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index a067a6cffb0..8e1709a679b 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -227,7 +227,7 @@ int ocfs2_read_inline_data(struct inode *inode, struct page *page,
         size = i_size_read(inode);
 
         if (size > PAGE_CACHE_SIZE ||
-            size > ocfs2_max_inline_data(inode->i_sb)) {
+            size > ocfs2_max_inline_data_with_xattr(inode->i_sb, di)) {
                 ocfs2_error(inode->i_sb,
                             "Inode %llu has with inline data has bad size: %Lu",
                             (unsigned long long)OCFS2_I(inode)->ip_blkno,
@@ -1555,6 +1555,7 @@ static int ocfs2_try_to_write_inline_data(struct address_space *mapping,
         int ret, written = 0;
         loff_t end = pos + len;
         struct ocfs2_inode_info *oi = OCFS2_I(inode);
+        struct ocfs2_dinode *di = NULL;
 
         mlog(0, "Inode %llu, write of %u bytes at off %llu. features: 0x%x\n",
              (unsigned long long)oi->ip_blkno, len, (unsigned long long)pos,
@@ -1587,7 +1588,9 @@ static int ocfs2_try_to_write_inline_data(struct address_space *mapping,
         /*
          * Check whether the write can fit.
          */
-        if (mmap_page || end > ocfs2_max_inline_data(inode->i_sb))
+        di = (struct ocfs2_dinode *)wc->w_di_bh->b_data;
+        if (mmap_page ||
+            end > ocfs2_max_inline_data_with_xattr(inode->i_sb, di))
                 return 0;
 
 do_inline_write:
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 54e182a27ca..0a281394785 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -1849,12 +1849,12 @@ int dlm_assert_master_handler(struct o2net_msg *msg, u32 len, void *data,
                 if (!mle) {
                         if (res->owner != DLM_LOCK_RES_OWNER_UNKNOWN &&
                             res->owner != assert->node_idx) {
-                                mlog(ML_ERROR, "assert_master from "
-                                          "%u, but current owner is "
-                                          "%u! (%.*s)\n",
-                                       assert->node_idx, res->owner,
-                                       namelen, name);
-                                goto kill;
+                                mlog(ML_ERROR, "DIE! Mastery assert from %u, "
+                                     "but current owner is %u! (%.*s)\n",
+                                     assert->node_idx, res->owner, namelen,
+                                     name);
+                                __dlm_print_one_lock_resource(res);
+                                BUG();
                         }
                 } else if (mle->type != DLM_MLE_MIGRATION) {
                         if (res->owner != DLM_LOCK_RES_OWNER_UNKNOWN) {
diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c
index d1295203029..4060bb328bc 100644
--- a/fs/ocfs2/dlm/dlmthread.c
+++ b/fs/ocfs2/dlm/dlmthread.c
@@ -181,8 +181,7 @@ static int dlm_purge_lockres(struct dlm_ctxt *dlm,
 
                 spin_lock(&res->spinlock);
                 /* This ensures that clear refmap is sent after the set */
-                __dlm_wait_on_lockres_flags(res, (DLM_LOCK_RES_SETREF_INPROG |
-                                                  DLM_LOCK_RES_MIGRATING));
+                __dlm_wait_on_lockres_flags(res, DLM_LOCK_RES_SETREF_INPROG);
                 spin_unlock(&res->spinlock);
 
                 /* clear our bit from the master's refmap, ignore errors */
diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c
index 86ca085ef32..fcf879ed693 100644
--- a/fs/ocfs2/dlm/dlmunlock.c
+++ b/fs/ocfs2/dlm/dlmunlock.c
@@ -117,11 +117,11 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm,
         else
                 BUG_ON(res->owner == dlm->node_num);
 
-        spin_lock(&dlm->spinlock);
+        spin_lock(&dlm->ast_lock);
         /* We want to be sure that we're not freeing a lock
          * that still has AST's pending... */
         in_use = !list_empty(&lock->ast_list);
-        spin_unlock(&dlm->spinlock);
+        spin_unlock(&dlm->ast_lock);
         if (in_use) {
                mlog(ML_ERROR, "lockres %.*s: Someone is calling dlmunlock "
                     "while waiting for an ast!", res->lockname.len,
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 206a2370876..7219a86d34c 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -320,9 +320,14 @@ static void ocfs2_schedule_blocked_lock(struct ocfs2_super *osb,
                                         struct ocfs2_lock_res *lockres);
 static inline void ocfs2_recover_from_dlm_error(struct ocfs2_lock_res *lockres,
                                                 int convert);
-#define ocfs2_log_dlm_error(_func, _err, _lockres) do {                 \
-        mlog(ML_ERROR, "DLM error %d while calling %s on resource %s\n", \
-             _err, _func, _lockres->l_name);                            \
+#define ocfs2_log_dlm_error(_func, _err, _lockres) do {                                 \
+        if ((_lockres)->l_type != OCFS2_LOCK_TYPE_DENTRY)                               \
+                mlog(ML_ERROR, "DLM error %d while calling %s on resource %s\n",        \
+                     _err, _func, _lockres->l_name);                                    \
+        else                                                                            \
+                mlog(ML_ERROR, "DLM error %d while calling %s on resource %.*s%08x\n",  \
+                     _err, _func, OCFS2_DENTRY_LOCK_INO_START - 1, (_lockres)->l_name,  \
+                     (unsigned int)ocfs2_get_dentry_lock_ino(_lockres));                \
 } while (0)
 static int ocfs2_downconvert_thread(void *arg);
 static void ocfs2_downconvert_on_unlock(struct ocfs2_super *osb,
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index 3c3532e1307..172850a9a12 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -513,8 +513,10 @@ static inline int ocfs2_jbd2_file_inode(handle_t *handle, struct inode *inode)
 static inline int ocfs2_begin_ordered_truncate(struct inode *inode,
                                                loff_t new_size)
 {
-        return jbd2_journal_begin_ordered_truncate(&OCFS2_I(inode)->ip_jinode,
-                                                   new_size);
+        return jbd2_journal_begin_ordered_truncate(
+                                OCFS2_SB(inode->i_sb)->journal->j_journal,
+                                &OCFS2_I(inode)->ip_jinode,
+                                new_size);
 }
 
 #endif /* OCFS2_JOURNAL_H */
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 084aba86c3b..4b11762f249 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -532,7 +532,8 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb,
 
                 fe->i_dyn_features = cpu_to_le16(feat | OCFS2_INLINE_DATA_FL);
 
-                fe->id2.i_data.id_count = cpu_to_le16(ocfs2_max_inline_data(osb->sb));
+                fe->id2.i_data.id_count = cpu_to_le16(
+                                ocfs2_max_inline_data_with_xattr(osb->sb, fe));
         } else {
                 fel = &fe->id2.i_list;
                 fel->l_tree_depth = 0;
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 077384135f4..946d3c34b90 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -341,6 +341,9 @@ struct ocfs2_super
         struct ocfs2_node_map           osb_recovering_orphan_dirs;
         unsigned int                    *osb_orphan_wipes;
         wait_queue_head_t               osb_wipe_event;
+
+        /* used to protect metaecc calculation check of xattr. */
+        spinlock_t osb_xattr_lock;
 };
 
 #define OCFS2_SB(sb)        ((struct ocfs2_super *)(sb)->s_fs_info)
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index c7ae45aaa36..2332ef740f4 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -1070,12 +1070,6 @@ static inline int ocfs2_fast_symlink_chars(struct super_block *sb)
                  offsetof(struct ocfs2_dinode, id2.i_symlink);
 }
 
-static inline int ocfs2_max_inline_data(struct super_block *sb)
-{
-        return sb->s_blocksize -
-                offsetof(struct ocfs2_dinode, id2.i_data.id_data);
-}
-
 static inline int ocfs2_max_inline_data_with_xattr(struct super_block *sb,
                                                    struct ocfs2_dinode *di)
 {
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index b1cb38fbe80..7ac83a81ee5 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1537,6 +1537,13 @@ static int ocfs2_get_sector(struct super_block *sb,
         unlock_buffer(*bh);
         ll_rw_block(READ, 1, bh);
         wait_on_buffer(*bh);
+        if (!buffer_uptodate(*bh)) {
+                mlog_errno(-EIO);
+                brelse(*bh);
+                *bh = NULL;
+                return -EIO;
+        }
+
         return 0;
 }
 
@@ -1747,6 +1754,7 @@ static int ocfs2_initialize_super(struct super_block *sb,
         INIT_LIST_HEAD(&osb->blocked_lock_list);
         osb->blocked_lock_count = 0;
         spin_lock_init(&osb->osb_lock);
+        spin_lock_init(&osb->osb_xattr_lock);
         ocfs2_init_inode_steal_slot(osb);
 
         atomic_set(&osb->alloc_stats.moves, 0);
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index 915039fffe6..2563df89fc2 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -82,13 +82,14 @@ struct ocfs2_xattr_set_ctxt {
 
 #define OCFS2_XATTR_ROOT_SIZE   (sizeof(struct ocfs2_xattr_def_value_root))
 #define OCFS2_XATTR_INLINE_SIZE 80
+#define OCFS2_XATTR_HEADER_GAP  4
 #define OCFS2_XATTR_FREE_IN_IBODY       (OCFS2_MIN_XATTR_INLINE_SIZE \
                                          - sizeof(struct ocfs2_xattr_header) \
-                                         - sizeof(__u32))
+                                         - OCFS2_XATTR_HEADER_GAP)
 #define OCFS2_XATTR_FREE_IN_BLOCK(ptr)  ((ptr)->i_sb->s_blocksize \
                                          - sizeof(struct ocfs2_xattr_block) \
                                          - sizeof(struct ocfs2_xattr_header) \
-                                         - sizeof(__u32))
+                                         - OCFS2_XATTR_HEADER_GAP)
 
 static struct ocfs2_xattr_def_value_root def_xv = {
         .xv.xr_list.l_count = cpu_to_le16(1),
@@ -274,10 +275,12 @@ static int ocfs2_read_xattr_bucket(struct ocfs2_xattr_bucket *bucket,
                                bucket->bu_blocks, bucket->bu_bhs, 0,
                                NULL);
         if (!rc) {
+                spin_lock(&OCFS2_SB(bucket->bu_inode->i_sb)->osb_xattr_lock);
                 rc = ocfs2_validate_meta_ecc_bhs(bucket->bu_inode->i_sb,
                                                  bucket->bu_bhs,
                                                  bucket->bu_blocks,
                                                  &bucket_xh(bucket)->xh_check);
+                spin_unlock(&OCFS2_SB(bucket->bu_inode->i_sb)->osb_xattr_lock);
                 if (rc)
                         mlog_errno(rc);
         }
@@ -310,9 +313,11 @@ static void ocfs2_xattr_bucket_journal_dirty(handle_t *handle,
 {
         int i;
 
+        spin_lock(&OCFS2_SB(bucket->bu_inode->i_sb)->osb_xattr_lock);
         ocfs2_compute_meta_ecc_bhs(bucket->bu_inode->i_sb,
                                    bucket->bu_bhs, bucket->bu_blocks,
                                    &bucket_xh(bucket)->xh_check);
+        spin_unlock(&OCFS2_SB(bucket->bu_inode->i_sb)->osb_xattr_lock);
 
         for (i = 0; i < bucket->bu_blocks; i++)
                 ocfs2_journal_dirty(handle, bucket->bu_bhs[i]);
@@ -542,8 +547,12 @@ int ocfs2_calc_xattr_init(struct inode *dir,
          * when blocksize = 512, may reserve one more cluser for
          * xattr bucket, otherwise reserve one metadata block
          * for them is ok.
+         * If this is a new directory with inline data,
+         * we choose to reserve the entire inline area for
+         * directory contents and force an external xattr block.
          */
         if (dir->i_sb->s_blocksize == OCFS2_MIN_BLOCKSIZE ||
+            (S_ISDIR(mode) && ocfs2_supports_inline_data(osb)) ||
             (s_size + a_size) > OCFS2_XATTR_FREE_IN_IBODY) {
                 ret = ocfs2_reserve_new_metadata_blocks(osb, 1, xattr_ac);
                 if (ret) {
@@ -1507,7 +1516,7 @@ static int ocfs2_xattr_set_entry(struct inode *inode,
                 last += 1;
         }
 
-        free = min_offs - ((void *)last - xs->base) - sizeof(__u32);
+        free = min_offs - ((void *)last - xs->base) - OCFS2_XATTR_HEADER_GAP;
         if (free < 0)
                 return -EIO;
 
@@ -2190,7 +2199,7 @@ static int ocfs2_xattr_can_be_in_inode(struct inode *inode,
                 last += 1;
         }
 
-        free = min_offs - ((void *)last - xs->base) - sizeof(__u32);
+        free = min_offs - ((void *)last - xs->base) - OCFS2_XATTR_HEADER_GAP;
         if (free < 0)
                 return 0;
 
@@ -2592,8 +2601,9 @@ static int __ocfs2_xattr_set_handle(struct inode *inode,
 
         if (!ret) {
                 /* Update inode ctime. */
-                ret = ocfs2_journal_access(ctxt->handle, inode, xis->inode_bh,
-                                           OCFS2_JOURNAL_ACCESS_WRITE);
+                ret = ocfs2_journal_access_di(ctxt->handle, inode,
+                                              xis->inode_bh,
+                                              OCFS2_JOURNAL_ACCESS_WRITE);
                 if (ret) {
                         mlog_errno(ret);
                         goto out;
@@ -4785,19 +4795,33 @@ static int ocfs2_xattr_bucket_set_value_outside(struct inode *inode,
                                                 char *val,
                                                 int value_len)
 {
-        int offset;
+        int ret, offset, block_off;
         struct ocfs2_xattr_value_root *xv;
         struct ocfs2_xattr_entry *xe = xs->here;
+        struct ocfs2_xattr_header *xh = bucket_xh(xs->bucket);
+        void *base;
 
         BUG_ON(!xs->base || !xe || ocfs2_xattr_is_local(xe));
 
-        offset = le16_to_cpu(xe->xe_name_offset) +
-                 OCFS2_XATTR_SIZE(xe->xe_name_len);
+        ret = ocfs2_xattr_bucket_get_name_value(inode, xh,
+                                                xe - xh->xh_entries,
+                                                &block_off,
+                                                &offset);
+        if (ret) {
+                mlog_errno(ret);
+                goto out;
+        }
 
-        xv = (struct ocfs2_xattr_value_root *)(xs->base + offset);
+        base = bucket_block(xs->bucket, block_off);
+        xv = (struct ocfs2_xattr_value_root *)(base + offset +
+                 OCFS2_XATTR_SIZE(xe->xe_name_len));
 
-        return __ocfs2_xattr_set_value_outside(inode, handle,
-                                               xv, val, value_len);
+        ret = __ocfs2_xattr_set_value_outside(inode, handle,
+                                              xv, val, value_len);
+        if (ret)
+                mlog_errno(ret);
+out:
+        return ret;
 }
 
 static int ocfs2_rm_xattr_cluster(struct inode *inode,
@@ -5060,8 +5084,8 @@ try_again:
         xh_free_start = le16_to_cpu(xh->xh_free_start);
         header_size = sizeof(struct ocfs2_xattr_header) +
                         count * sizeof(struct ocfs2_xattr_entry);
-        max_free = OCFS2_XATTR_BUCKET_SIZE -
-                le16_to_cpu(xh->xh_name_value_len) - header_size;
+        max_free = OCFS2_XATTR_BUCKET_SIZE - header_size -
+                le16_to_cpu(xh->xh_name_value_len) - OCFS2_XATTR_HEADER_GAP;
 
         mlog_bug_on_msg(header_size > blocksize, "bucket %llu has header size "
                         "of %u which exceed block size\n",
@@ -5094,7 +5118,7 @@ try_again:
                         need = 0;
         }
 
-        free = xh_free_start - header_size;
+        free = xh_free_start - header_size - OCFS2_XATTR_HEADER_GAP;
         /*
          * We need to make sure the new name/value pair
          * can exist in the same block.
@@ -5127,7 +5151,8 @@ try_again:
                         }
 
                         xh_free_start = le16_to_cpu(xh->xh_free_start);
-                        free = xh_free_start - header_size;
+                        free = xh_free_start - header_size
+                                - OCFS2_XATTR_HEADER_GAP;
                         if (xh_free_start % blocksize < need)
                                 free -= xh_free_start % blocksize;