Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  ext4: Remove automatic enabling of the HUGE_FILE feature flag
  ext4: Replace hackish ext4_mb_poll_new_transaction with commit callback
  ext4: Update Documentation/filesystems/ext4.txt
  ext4: Remove unused mount options: nomballoc, mballoc, nocheck
  ext4: Remove compile warnings when building w/o CONFIG_PROC_FS
  ext4: Add missing newlines to printk messages
  ext4: Fix file fragmentation during large file write.
  vfs: Add no_nrwrite_index_update writeback control flag
  vfs: Remove the range_cont writeback mode.
  ext4: Use tag dirty lookup during mpage_da_submit_io
  ext4: let the block device know when unused blocks can be discarded
  ext4: Don't reuse released data blocks until transaction commits
  ext4: Use an rbtree for tracking blocks freed during transaction.
  ext4: Do mballoc init before doing filesystem recovery
  ext4: Free ext4_prealloc_space using kmem_cache_free
  ext4: Fix Kconfig typo for ext4dev
  ext4: Remove an old reference to ext4dev in Makefile comment

1 files changed, 76 insertions, 67 deletions

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 9b4ec9decfd1..8dbf6953845b 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1648,6 +1648,7 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd)
         int ret = 0, err, nr_pages, i;
         unsigned long index, end;
         struct pagevec pvec;
+        long pages_skipped;
 
         BUG_ON(mpd->next_page <= mpd->first_page);
         pagevec_init(&pvec, 0);
@@ -1655,20 +1656,30 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd)
         end = mpd->next_page - 1;
 
         while (index <= end) {
-                /* XXX: optimize tail */
-                nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE);
+                /*
+                 * We can use PAGECACHE_TAG_DIRTY lookup here because
+                 * even though we have cleared the dirty flag on the page
+                 * We still keep the page in the radix tree with tag
+                 * PAGECACHE_TAG_DIRTY. See clear_page_dirty_for_io.
+                 * The PAGECACHE_TAG_DIRTY is cleared in set_page_writeback
+                 * which is called via the below writepage callback.
+                 */
+                nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
+                                        PAGECACHE_TAG_DIRTY,
+                                        min(end - index,
+                                        (pgoff_t)PAGEVEC_SIZE-1) + 1);
                 if (nr_pages == 0)
                         break;
                 for (i = 0; i < nr_pages; i++) {
                         struct page *page = pvec.pages[i];
 
-                        index = page->index;
-                        if (index > end)
-                                break;
-                        index++;
-
+                        pages_skipped = mpd->wbc->pages_skipped;
                         err = mapping->a_ops->writepage(page, mpd->wbc);
-                        if (!err)
+                        if (!err && (pages_skipped == mpd->wbc->pages_skipped))
+                                /*
+                                 * have successfully written the page
+                                 * without skipping the same
+                                 */
                                 mpd->pages_written++;
                         /*
                          * In error case, we have to continue because
@@ -2104,7 +2115,6 @@ static int mpage_da_writepages(struct address_space *mapping,
                                struct writeback_control *wbc,
                                struct mpage_da_data *mpd)
 {
-        long to_write;
         int ret;
 
         if (!mpd->get_block)
@@ -2119,19 +2129,18 @@ static int mpage_da_writepages(struct address_space *mapping,
         mpd->pages_written = 0;
         mpd->retval = 0;
 
-        to_write = wbc->nr_to_write;
-
         ret = write_cache_pages(mapping, wbc, __mpage_da_writepage, mpd);
-
         /*
          * Handle last extent of pages
          */
         if (!mpd->io_done && mpd->next_page != mpd->first_page) {
                 if (mpage_da_map_blocks(mpd) == 0)
                         mpage_da_submit_io(mpd);
-        }
 
-        wbc->nr_to_write = to_write - mpd->pages_written;
+                mpd->io_done = 1;
+                ret = MPAGE_DA_EXTENT_TAIL;
+        }
+        wbc->nr_to_write -= mpd->pages_written;
         return ret;
 }
 
@@ -2360,12 +2369,14 @@ static int ext4_da_writepages_trans_blocks(struct inode *inode)
 static int ext4_da_writepages(struct address_space *mapping,
                               struct writeback_control *wbc)
 {
+        pgoff_t index;
+        int range_whole = 0;
         handle_t *handle = NULL;
-        loff_t range_start = 0;
         struct mpage_da_data mpd;
         struct inode *inode = mapping->host;
+        int no_nrwrite_index_update;
+        long pages_written = 0, pages_skipped;
         int needed_blocks, ret = 0, nr_to_writebump = 0;
-        long to_write, pages_skipped = 0;
         struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
 
         /*
@@ -2385,23 +2396,26 @@ static int ext4_da_writepages(struct address_space *mapping,
                 nr_to_writebump = sbi->s_mb_stream_request - wbc->nr_to_write;
                 wbc->nr_to_write = sbi->s_mb_stream_request;
         }
+        if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
+                range_whole = 1;
 
-        if (!wbc->range_cyclic)
-                /*
-                 * If range_cyclic is not set force range_cont
-                 * and save the old writeback_index
-                 */
-                wbc->range_cont = 1;
-
-        range_start =  wbc->range_start;
-        pages_skipped = wbc->pages_skipped;
+        if (wbc->range_cyclic)
+                index = mapping->writeback_index;
+        else
+                index = wbc->range_start >> PAGE_CACHE_SHIFT;
 
         mpd.wbc = wbc;
         mpd.inode = mapping->host;
 
-restart_loop:
-        to_write = wbc->nr_to_write;
-        while (!ret && to_write > 0) {
+        /*
+         * we don't want write_cache_pages to update
+         * nr_to_write and writeback_index
+         */
+        no_nrwrite_index_update = wbc->no_nrwrite_index_update;
+        wbc->no_nrwrite_index_update = 1;
+        pages_skipped = wbc->pages_skipped;
+
+        while (!ret && wbc->nr_to_write > 0) {
 
                 /*
                  * we  insert one extent at a time. So we need
@@ -2422,48 +2436,53 @@ restart_loop:
                         dump_stack();
                         goto out_writepages;
                 }
-                to_write -= wbc->nr_to_write;
-
                 mpd.get_block = ext4_da_get_block_write;
                 ret = mpage_da_writepages(mapping, wbc, &mpd);
 
                 ext4_journal_stop(handle);
 
-                if (mpd.retval == -ENOSPC)
+                if (mpd.retval == -ENOSPC) {
+                        /* commit the transaction which would
+                         * free blocks released in the transaction
+                         * and try again
+                         */
                         jbd2_journal_force_commit_nested(sbi->s_journal);
-
-                /* reset the retry count */
-                if (ret == MPAGE_DA_EXTENT_TAIL) {
+                        wbc->pages_skipped = pages_skipped;
+                        ret = 0;
+                } else if (ret == MPAGE_DA_EXTENT_TAIL) {
                         /*
                          * got one extent now try with
                          * rest of the pages
                          */
-                        to_write += wbc->nr_to_write;
+                        pages_written += mpd.pages_written;
+                        wbc->pages_skipped = pages_skipped;
                         ret = 0;
-                } else if (wbc->nr_to_write) {
+                } else if (wbc->nr_to_write)
                         /*
                          * There is no more writeout needed
                          * or we requested for a noblocking writeout
                          * and we found the device congested
                          */
-                        to_write += wbc->nr_to_write;
                         break;
-                }
-                wbc->nr_to_write = to_write;
-        }
-
-        if (wbc->range_cont && (pages_skipped != wbc->pages_skipped)) {
-                /* We skipped pages in this loop */
-                wbc->range_start = range_start;
-                wbc->nr_to_write = to_write +
-                                wbc->pages_skipped - pages_skipped;
-                wbc->pages_skipped = pages_skipped;
-                goto restart_loop;
         }
+        if (pages_skipped != wbc->pages_skipped)
+                printk(KERN_EMERG "This should not happen leaving %s "
+                                "with nr_to_write = %ld ret = %d\n",
+                                __func__, wbc->nr_to_write, ret);
+
+        /* Update index */
+        index += pages_written;
+        if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
+                /*
+                 * set the writeback_index so that range_cyclic
+                 * mode will write it back later
+                 */
+                mapping->writeback_index = index;
 
 out_writepages:
-        wbc->nr_to_write = to_write - nr_to_writebump;
-        wbc->range_start = range_start;
+        if (!no_nrwrite_index_update)
+                wbc->no_nrwrite_index_update = 0;
+        wbc->nr_to_write -= nr_to_writebump;
         return ret;
 }
 
@@ -4175,7 +4194,6 @@ static int ext4_inode_blocks_set(handle_t *handle,
         struct inode *inode = &(ei->vfs_inode);
         u64 i_blocks = inode->i_blocks;
         struct super_block *sb = inode->i_sb;
-        int err = 0;
 
         if (i_blocks <= ~0U) {
                 /*
@@ -4185,36 +4203,27 @@ static int ext4_inode_blocks_set(handle_t *handle,
                 raw_inode->i_blocks_lo   = cpu_to_le32(i_blocks);
                 raw_inode->i_blocks_high = 0;
                 ei->i_flags &= ~EXT4_HUGE_FILE_FL;
-        } else if (i_blocks <= 0xffffffffffffULL) {
+                return 0;
+        }
+        if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_HUGE_FILE))
+                return -EFBIG;
+
+        if (i_blocks <= 0xffffffffffffULL) {
                 /*
                  * i_blocks can be represented in a 48 bit variable
                  * as multiple of 512 bytes
                  */
-                err = ext4_update_rocompat_feature(handle, sb,
-                                            EXT4_FEATURE_RO_COMPAT_HUGE_FILE);
-                if (err)
-                        goto  err_out;
-                /* i_block is stored in the split  48 bit fields */
                 raw_inode->i_blocks_lo   = cpu_to_le32(i_blocks);
                 raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32);
                 ei->i_flags &= ~EXT4_HUGE_FILE_FL;
         } else {
-                /*
-                 * i_blocks should be represented in a 48 bit variable
-                 * as multiple of  file system block size
-                 */
-                err = ext4_update_rocompat_feature(handle, sb,
-                                            EXT4_FEATURE_RO_COMPAT_HUGE_FILE);
-                if (err)
-                        goto  err_out;
                 ei->i_flags |= EXT4_HUGE_FILE_FL;
                 /* i_block is stored in file system block size */
                 i_blocks = i_blocks >> (inode->i_blkbits - 9);
                 raw_inode->i_blocks_lo   = cpu_to_le32(i_blocks);
                 raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32);
         }
-err_out:
-        return err;
+        return 0;
 }
 
 /*