7 files changed, 159 insertions, 37 deletions

diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 8750ae1b8636..e2edff38be52 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -4742,6 +4742,7 @@ int ocfs2_add_clusters_in_btree(handle_t *handle,
                                 enum ocfs2_alloc_restarted *reason_ret)
 {
         int status = 0, err = 0;
+        int need_free = 0;
         int free_extents;
         enum ocfs2_alloc_restarted reason = RESTART_NONE;
         u32 bit_off, num_bits;
@@ -4796,7 +4797,8 @@ int ocfs2_add_clusters_in_btree(handle_t *handle,
                                               OCFS2_JOURNAL_ACCESS_WRITE);
         if (status < 0) {
                 mlog_errno(status);
-                goto leave;
+                need_free = 1;
+                goto bail;
         }
 
         block = ocfs2_clusters_to_blocks(osb->sb, bit_off);
@@ -4807,7 +4809,8 @@ int ocfs2_add_clusters_in_btree(handle_t *handle,
                                      num_bits, flags, meta_ac);
         if (status < 0) {
                 mlog_errno(status);
-                goto leave;
+                need_free = 1;
+                goto bail;
         }
 
         ocfs2_journal_dirty(handle, et->et_root_bh);
@@ -4821,6 +4824,19 @@ int ocfs2_add_clusters_in_btree(handle_t *handle,
                 reason = RESTART_TRANS;
         }
 
+bail:
+        if (need_free) {
+                if (data_ac->ac_which == OCFS2_AC_USE_LOCAL)
+                        ocfs2_free_local_alloc_bits(osb, handle, data_ac,
+                                        bit_off, num_bits);
+                else
+                        ocfs2_free_clusters(handle,
+                                        data_ac->ac_inode,
+                                        data_ac->ac_bh,
+                                        ocfs2_clusters_to_blocks(osb->sb, bit_off),
+                                        num_bits);
+        }
+
 leave:
         if (reason_ret)
                 *reason_ret = reason;
@@ -6805,6 +6821,8 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
                                          struct buffer_head *di_bh)
 {
         int ret, i, has_data, num_pages = 0;
+        int need_free = 0;
+        u32 bit_off, num;
         handle_t *handle;
         u64 uninitialized_var(block);
         struct ocfs2_inode_info *oi = OCFS2_I(inode);
@@ -6850,7 +6868,6 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
         }
 
         if (has_data) {
-                u32 bit_off, num;
                 unsigned int page_end;
                 u64 phys;
 
@@ -6886,6 +6903,7 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
                 ret = ocfs2_grab_eof_pages(inode, 0, end, pages, &num_pages);
                 if (ret) {
                         mlog_errno(ret);
+                        need_free = 1;
                         goto out_commit;
                 }
 
@@ -6896,6 +6914,7 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
                 ret = ocfs2_read_inline_data(inode, pages[0], di_bh);
                 if (ret) {
                         mlog_errno(ret);
+                        need_free = 1;
                         goto out_commit;
                 }
 
@@ -6927,6 +6946,7 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
                 ret = ocfs2_insert_extent(handle, &et, 0, block, 1, 0, NULL);
                 if (ret) {
                         mlog_errno(ret);
+                        need_free = 1;
                         goto out_commit;
                 }
 
@@ -6938,6 +6958,18 @@ out_commit:
                 dquot_free_space_nodirty(inode,
                                           ocfs2_clusters_to_bytes(osb->sb, 1));
 
+        if (need_free) {
+                if (data_ac->ac_which == OCFS2_AC_USE_LOCAL)
+                        ocfs2_free_local_alloc_bits(osb, handle, data_ac,
+                                        bit_off, num);
+                else
+                        ocfs2_free_clusters(handle,
+                                        data_ac->ac_inode,
+                                        data_ac->ac_bh,
+                                        ocfs2_clusters_to_blocks(osb->sb, bit_off),
+                                        num);
+        }
+
         ocfs2_commit_trans(osb, handle);
 
 out_unlock:
@@ -7126,7 +7158,7 @@ int ocfs2_truncate_inline(struct inode *inode, struct buffer_head *di_bh,
         if (end > i_size_read(inode))
                 end = i_size_read(inode);
 
-        BUG_ON(start >= end);
+        BUG_ON(start > end);
 
         if (!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) ||
             !(le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_DATA_FL) ||
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index d77d71ead8d1..51632c40e896 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -185,6 +185,9 @@ static int ocfs2_sync_file(struct file *file, loff_t start, loff_t end,
                               file->f_path.dentry->d_name.name,
                               (unsigned long long)datasync);
 
+        if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb))
+                return -EROFS;
+
         err = filemap_write_and_wait_range(inode->i_mapping, start, end);
         if (err)
                 return err;
@@ -474,11 +477,6 @@ static int ocfs2_truncate_file(struct inode *inode,
                 goto bail;
         }
 
-        /* lets handle the simple truncate cases before doing any more
-         * cluster locking. */
-        if (new_i_size == le64_to_cpu(fe->i_size))
-                goto bail;
-
         down_write(&OCFS2_I(inode)->ip_alloc_sem);
 
         ocfs2_resv_discard(&osb->osb_la_resmap,
@@ -718,7 +716,8 @@ leave:
  * While a write will already be ordering the data, a truncate will not.
  * Thus, we need to explicitly order the zeroed pages.
  */
-static handle_t *ocfs2_zero_start_ordered_transaction(struct inode *inode)
+static handle_t *ocfs2_zero_start_ordered_transaction(struct inode *inode,
+                                                struct buffer_head *di_bh)
 {
         struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
         handle_t *handle = NULL;
@@ -735,7 +734,14 @@ static handle_t *ocfs2_zero_start_ordered_transaction(struct inode *inode)
         }
 
         ret = ocfs2_jbd2_file_inode(handle, inode);
-        if (ret < 0)
+        if (ret < 0) {
+                mlog_errno(ret);
+                goto out;
+        }
+
+        ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
+                                      OCFS2_JOURNAL_ACCESS_WRITE);
+        if (ret)
                 mlog_errno(ret);
 
 out:
@@ -751,7 +757,7 @@ out:
  * to be too fragile to do exactly what we need without us having to
  * worry about recursive locking in ->write_begin() and ->write_end(). */
 static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
-                                 u64 abs_to)
+                                 u64 abs_to, struct buffer_head *di_bh)
 {
         struct address_space *mapping = inode->i_mapping;
         struct page *page;
@@ -759,6 +765,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
         handle_t *handle = NULL;
         int ret = 0;
         unsigned zero_from, zero_to, block_start, block_end;
+        struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
 
         BUG_ON(abs_from >= abs_to);
         BUG_ON(abs_to > (((u64)index + 1) << PAGE_CACHE_SHIFT));
@@ -801,7 +808,8 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
                 }
 
                 if (!handle) {
-                        handle = ocfs2_zero_start_ordered_transaction(inode);
+                        handle = ocfs2_zero_start_ordered_transaction(inode,
+                                                                      di_bh);
                         if (IS_ERR(handle)) {
                                 ret = PTR_ERR(handle);
                                 handle = NULL;
@@ -818,8 +826,22 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
                         ret = 0;
         }
 
-        if (handle)
+        if (handle) {
+                /*
+                 * fs-writeback will release the dirty pages without page lock
+                 * whose offset are over inode size, the release happens at
+                 * block_write_full_page_endio().
+                 */
+                i_size_write(inode, abs_to);
+                inode->i_blocks = ocfs2_inode_sector_count(inode);
+                di->i_size = cpu_to_le64((u64)i_size_read(inode));
+                inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+                di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec);
+                di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
+                di->i_mtime_nsec = di->i_ctime_nsec;
+                ocfs2_journal_dirty(handle, di_bh);
                 ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
+        }
 
 out_unlock:
         unlock_page(page);
@@ -915,7 +937,7 @@ out:
  * has made sure that the entire range needs zeroing.
  */
 static int ocfs2_zero_extend_range(struct inode *inode, u64 range_start,
-                                   u64 range_end)
+                                   u64 range_end, struct buffer_head *di_bh)
 {
         int rc = 0;
         u64 next_pos;
@@ -931,7 +953,7 @@ static int ocfs2_zero_extend_range(struct inode *inode, u64 range_start,
                 next_pos = (zero_pos & PAGE_CACHE_MASK) + PAGE_CACHE_SIZE;
                 if (next_pos > range_end)
                         next_pos = range_end;
-                rc = ocfs2_write_zero_page(inode, zero_pos, next_pos);
+                rc = ocfs2_write_zero_page(inode, zero_pos, next_pos, di_bh);
                 if (rc < 0) {
                         mlog_errno(rc);
                         break;
@@ -977,7 +999,7 @@ int ocfs2_zero_extend(struct inode *inode, struct buffer_head *di_bh,
                         range_end = zero_to_size;
 
                 ret = ocfs2_zero_extend_range(inode, range_start,
-                                              range_end);
+                                              range_end, di_bh);
                 if (ret) {
                         mlog_errno(ret);
                         break;
@@ -1145,14 +1167,14 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
                 goto bail_unlock_rw;
         }
 
-        if (size_change && attr->ia_size != i_size_read(inode)) {
+        if (size_change) {
                 status = inode_newsize_ok(inode, attr->ia_size);
                 if (status)
                         goto bail_unlock;
 
                 inode_dio_wait(inode);
 
-                if (i_size_read(inode) > attr->ia_size) {
+                if (i_size_read(inode) >= attr->ia_size) {
                         if (ocfs2_should_order_data(inode)) {
                                 status = ocfs2_begin_ordered_truncate(inode,
                                                                       attr->ia_size);
@@ -2371,8 +2393,8 @@ out_dio:
 
         if (((file->f_flags & O_DSYNC) && !direct_io) || IS_SYNC(inode) ||
             ((file->f_flags & O_DIRECT) && !direct_io)) {
-                ret = filemap_fdatawrite_range(file->f_mapping, pos,
-                                               pos + count - 1);
+                ret = filemap_fdatawrite_range(file->f_mapping, *ppos,
+                                               *ppos + count - 1);
                 if (ret < 0)
                         written = ret;
 
@@ -2385,8 +2407,8 @@ out_dio:
                 }
 
                 if (!ret)
-                        ret = filemap_fdatawait_range(file->f_mapping, pos,
-                                                      pos + count - 1);
+                        ret = filemap_fdatawait_range(file->f_mapping, *ppos,
+                                                      *ppos + count - 1);
         }
 
         /*
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index cd5496b7a0a3..044013455621 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -781,6 +781,48 @@ bail:
         return status;
 }
 
+int ocfs2_free_local_alloc_bits(struct ocfs2_super *osb,
+                                handle_t *handle,
+                                struct ocfs2_alloc_context *ac,
+                                u32 bit_off,
+                                u32 num_bits)
+{
+        int status, start;
+        u32 clear_bits;
+        struct inode *local_alloc_inode;
+        void *bitmap;
+        struct ocfs2_dinode *alloc;
+        struct ocfs2_local_alloc *la;
+
+        BUG_ON(ac->ac_which != OCFS2_AC_USE_LOCAL);
+
+        local_alloc_inode = ac->ac_inode;
+        alloc = (struct ocfs2_dinode *) osb->local_alloc_bh->b_data;
+        la = OCFS2_LOCAL_ALLOC(alloc);
+
+        bitmap = la->la_bitmap;
+        start = bit_off - le32_to_cpu(la->la_bm_off);
+        clear_bits = num_bits;
+
+        status = ocfs2_journal_access_di(handle,
+                        INODE_CACHE(local_alloc_inode),
+                        osb->local_alloc_bh,
+                        OCFS2_JOURNAL_ACCESS_WRITE);
+        if (status < 0) {
+                mlog_errno(status);
+                goto bail;
+        }
+
+        while (clear_bits--)
+                ocfs2_clear_bit(start++, bitmap);
+
+        le32_add_cpu(&alloc->id1.bitmap1.i_used, -num_bits);
+        ocfs2_journal_dirty(handle, osb->local_alloc_bh);
+
+bail:
+        return status;
+}
+
 static u32 ocfs2_local_alloc_count_bits(struct ocfs2_dinode *alloc)
 {
         u32 count;
diff --git a/fs/ocfs2/localalloc.h b/fs/ocfs2/localalloc.h
index 1be9b5864460..44a7d1fb2dec 100644
--- a/fs/ocfs2/localalloc.h
+++ b/fs/ocfs2/localalloc.h
@@ -55,6 +55,12 @@ int ocfs2_claim_local_alloc_bits(struct ocfs2_super *osb,
                                  u32 *bit_off,
                                  u32 *num_bits);
 
+int ocfs2_free_local_alloc_bits(struct ocfs2_super *osb,
+                                handle_t *handle,
+                                struct ocfs2_alloc_context *ac,
+                                u32 bit_off,
+                                u32 num_bits);
+
 void ocfs2_local_alloc_seen_free_bits(struct ocfs2_super *osb,
                                       unsigned int num_clusters);
 void ocfs2_la_enable_worker(struct work_struct *work);
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index f4d609be9400..3683643f3f0e 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -664,6 +664,7 @@ static int ocfs2_link(struct dentry *old_dentry,
         struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
         struct ocfs2_dir_lookup_result lookup = { NULL, };
         sigset_t oldset;
+        u64 old_de_ino;
 
         trace_ocfs2_link((unsigned long long)OCFS2_I(inode)->ip_blkno,
                          old_dentry->d_name.len, old_dentry->d_name.name,
@@ -686,6 +687,22 @@ static int ocfs2_link(struct dentry *old_dentry,
                 goto out;
         }
 
+        err = ocfs2_lookup_ino_from_name(dir, old_dentry->d_name.name,
+                        old_dentry->d_name.len, &old_de_ino);
+        if (err) {
+                err = -ENOENT;
+                goto out;
+        }
+
+        /*
+         * Check whether another node removed the source inode while we
+         * were in the vfs.
+         */
+        if (old_de_ino != OCFS2_I(inode)->ip_blkno) {
+                err = -ENOENT;
+                goto out;
+        }
+
         err = ocfs2_check_dir_for_entry(dir, dentry->d_name.name,
                                         dentry->d_name.len);
         if (err)
diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index aaa50611ec66..d7b5108789e2 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -717,6 +717,12 @@ static int ocfs2_release_dquot(struct dquot *dquot)
          */
         if (status < 0)
                 mlog_errno(status);
+        /*
+         * Clear dq_off so that we search for the structure in quota file next
+         * time we acquire it. The structure might be deleted and reallocated
+         * elsewhere by another node while our dquot structure is on freelist.
+         */
+        dquot->dq_off = 0;
         clear_bit(DQ_ACTIVE_B, &dquot->dq_flags);
 out_trans:
         ocfs2_commit_trans(osb, handle);
@@ -756,16 +762,17 @@ static int ocfs2_acquire_dquot(struct dquot *dquot)
         status = ocfs2_lock_global_qf(info, 1);
         if (status < 0)
                 goto out;
-        if (!test_bit(DQ_READ_B, &dquot->dq_flags)) {
-                status = ocfs2_qinfo_lock(info, 0);
-                if (status < 0)
-                        goto out_dq;
-                status = qtree_read_dquot(&info->dqi_gi, dquot);
-                ocfs2_qinfo_unlock(info, 0);
-                if (status < 0)
-                        goto out_dq;
-        }
-        set_bit(DQ_READ_B, &dquot->dq_flags);
+        status = ocfs2_qinfo_lock(info, 0);
+        if (status < 0)
+                goto out_dq;
+        /*
+         * We always want to read dquot structure from disk because we don't
+         * know what happened with it while it was on freelist.
+         */
+        status = qtree_read_dquot(&info->dqi_gi, dquot);
+        ocfs2_qinfo_unlock(info, 0);
+        if (status < 0)
+                goto out_dq;
 
         OCFS2_DQUOT(dquot)->dq_use_count++;
         OCFS2_DQUOT(dquot)->dq_origspace = dquot->dq_dqb.dqb_curspace;
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index 2e4344be3b96..2001862bf2b1 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -1303,10 +1303,6 @@ int ocfs2_local_release_dquot(handle_t *handle, struct dquot *dquot)
         ocfs2_journal_dirty(handle, od->dq_chunk->qc_headerbh);
 
 out:
-        /* Clear the read bit so that next time someone uses this
-         * dquot he reads fresh info from disk and allocates local
-         * dquot structure */
-        clear_bit(DQ_READ_B, &dquot->dq_flags);
         return status;
 }