1 files changed, 70 insertions, 24 deletions

diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 0de69c9a08be..1fbb0e20131b 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -165,7 +165,7 @@ int ocfs2_get_block(struct inode *inode, sector_t iblock,
          * ocfs2 never allocates in this function - the only time we
          * need to use BH_New is when we're extending i_size on a file
          * system which doesn't support holes, in which case BH_New
-         * allows block_prepare_write() to zero.
+         * allows __block_write_begin() to zero.
          *
          * If we see this on a sparse file system, then a truncate has
          * raced us and removed the cluster. In this case, we clear
@@ -407,21 +407,6 @@ static int ocfs2_writepage(struct page *page, struct writeback_control *wbc)
         return ret;
 }
 
-/*
- * This is called from ocfs2_write_zero_page() which has handled it's
- * own cluster locking and has ensured allocation exists for those
- * blocks to be written.
- */
-int ocfs2_prepare_write_nolock(struct inode *inode, struct page *page,
-                               unsigned from, unsigned to)
-{
-        int ret;
-
-        ret = block_prepare_write(page, from, to, ocfs2_get_block);
-
-        return ret;
-}
-
 /* Taken from ext3. We don't necessarily need the full blown
  * functionality yet, but IMHO it's better to cut and paste the whole
  * thing so we can avoid introducing our own bugs (and easily pick up
@@ -588,11 +573,14 @@ static void ocfs2_dio_end_io(struct kiocb *iocb,
         /* this io's submitter should not have unlocked this before we could */
         BUG_ON(!ocfs2_iocb_is_rw_locked(iocb));
 
+        if (ocfs2_iocb_is_sem_locked(iocb)) {
+                up_read(&inode->i_alloc_sem);
+                ocfs2_iocb_clear_sem_locked(iocb);
+        }
+
         ocfs2_iocb_clear_rw_locked(iocb);
 
         level = ocfs2_iocb_rw_locked_level(iocb);
-        if (!level)
-                up_read(&inode->i_alloc_sem);
         ocfs2_rw_unlock(inode, level);
 
         if (is_async)
@@ -732,7 +720,7 @@ static int ocfs2_should_read_blk(struct inode *inode, struct page *page,
 }
 
 /*
- * Some of this taken from block_prepare_write(). We already have our
+ * Some of this taken from __block_write_begin(). We already have our
  * mapping by now though, and the entire write will be allocating or
  * it won't, so not much need to use BH_New.
  *
@@ -883,8 +871,8 @@ struct ocfs2_write_ctxt {
          * out in so that future reads from that region will get
          * zero's.
          */
-        struct page                     *w_pages[OCFS2_MAX_CTXT_PAGES];
         unsigned int                    w_num_pages;
+        struct page                     *w_pages[OCFS2_MAX_CTXT_PAGES];
         struct page                     *w_target_page;
 
         /*
@@ -1642,13 +1630,51 @@ static int ocfs2_zero_tail(struct inode *inode, struct buffer_head *di_bh,
         return ret;
 }
 
-int ocfs2_write_begin_nolock(struct address_space *mapping,
+/*
+ * Try to flush truncate logs if we can free enough clusters from it.
+ * As for return value, "< 0" means error, "0" no space and "1" means
+ * we have freed enough spaces and let the caller try to allocate again.
+ */
+static int ocfs2_try_to_free_truncate_log(struct ocfs2_super *osb,
+                                          unsigned int needed)
+{
+        tid_t target;
+        int ret = 0;
+        unsigned int truncated_clusters;
+
+        mutex_lock(&osb->osb_tl_inode->i_mutex);
+        truncated_clusters = osb->truncated_clusters;
+        mutex_unlock(&osb->osb_tl_inode->i_mutex);
+
+        /*
+         * Check whether we can succeed in allocating if we free
+         * the truncate log.
+         */
+        if (truncated_clusters < needed)
+                goto out;
+
+        ret = ocfs2_flush_truncate_log(osb);
+        if (ret) {
+                mlog_errno(ret);
+                goto out;
+        }
+
+        if (jbd2_journal_start_commit(osb->journal->j_journal, &target)) {
+                jbd2_log_wait_commit(osb->journal->j_journal, target);
+                ret = 1;
+        }
+out:
+        return ret;
+}
+
+int ocfs2_write_begin_nolock(struct file *filp,
+                             struct address_space *mapping,
                              loff_t pos, unsigned len, unsigned flags,
                              struct page **pagep, void **fsdata,
                              struct buffer_head *di_bh, struct page *mmap_page)
 {
         int ret, cluster_of_pages, credits = OCFS2_INODE_UPDATE_CREDITS;
-        unsigned int clusters_to_alloc, extents_to_split;
+        unsigned int clusters_to_alloc, extents_to_split, clusters_need = 0;
         struct ocfs2_write_ctxt *wc;
         struct inode *inode = mapping->host;
         struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
@@ -1657,7 +1683,9 @@ int ocfs2_write_begin_nolock(struct address_space *mapping,
         struct ocfs2_alloc_context *meta_ac = NULL;
         handle_t *handle;
         struct ocfs2_extent_tree et;
+        int try_free = 1, ret1;
 
+try_again:
         ret = ocfs2_alloc_write_ctxt(&wc, osb, pos, len, di_bh);
         if (ret) {
                 mlog_errno(ret);
@@ -1692,7 +1720,8 @@ int ocfs2_write_begin_nolock(struct address_space *mapping,
                 mlog_errno(ret);
                 goto out;
         } else if (ret == 1) {
-                ret = ocfs2_refcount_cow(inode, di_bh,
+                clusters_need = wc->w_clen;
+                ret = ocfs2_refcount_cow(inode, filp, di_bh,
                                          wc->w_cpos, wc->w_clen, UINT_MAX);
                 if (ret) {
                         mlog_errno(ret);
@@ -1706,6 +1735,7 @@ int ocfs2_write_begin_nolock(struct address_space *mapping,
                 mlog_errno(ret);
                 goto out;
         }
+        clusters_need += clusters_to_alloc;
 
         di = (struct ocfs2_dinode *)wc->w_di_bh->b_data;
 
@@ -1828,6 +1858,22 @@ out:
                 ocfs2_free_alloc_context(data_ac);
         if (meta_ac)
                 ocfs2_free_alloc_context(meta_ac);
+
+        if (ret == -ENOSPC && try_free) {
+                /*
+                 * Try to free some truncate log so that we can have enough
+                 * clusters to allocate.
+                 */
+                try_free = 0;
+
+                ret1 = ocfs2_try_to_free_truncate_log(osb, clusters_need);
+                if (ret1 == 1)
+                        goto try_again;
+
+                if (ret1 < 0)
+                        mlog_errno(ret1);
+        }
+
         return ret;
 }
 
@@ -1854,7 +1900,7 @@ static int ocfs2_write_begin(struct file *file, struct address_space *mapping,
          */
         down_write(&OCFS2_I(inode)->ip_alloc_sem);
 
-        ret = ocfs2_write_begin_nolock(mapping, pos, len, flags, pagep,
+        ret = ocfs2_write_begin_nolock(file, mapping, pos, len, flags, pagep,
                                        fsdata, di_bh, NULL);
         if (ret) {
                 mlog_errno(ret);