ext4: Implement range_cyclic in ext4_da_writepages instead of write_cache_pages

With delayed allocation we lock the page in write_cache_pages() and
try to build an in memory extent of contiguous blocks.  This is needed
so that we can get large contiguous blocks request.  If range_cyclic
mode is enabled, write_cache_pages() will loop back to the 0 index if
no I/O has been done yet, and try to start writing from the beginning
of the range.  That causes an attempt to take the page lock of lower
index page while holding the page lock of higher index page, which can
cause a dead lock with another writeback thread.

The solution is to implement the range_cyclic behavior in
ext4_da_writepages() instead.

http://bugzilla.kernel.org/show_bug.cgi?id=12579

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 658c4a7f2578cd61b5b673166957711323a2af18..cbd2ca99d11351d757f36194173ee716d89bdc4f 100644 (file)
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2439,6 +2439,7 @@ static int ext4_da_writepages(struct address_space *mapping,
        int no_nrwrite_index_update;
        int pages_written = 0;
        long pages_skipped;
+       int range_cyclic, cycled = 1, io_done = 0;
        int needed_blocks, ret = 0, nr_to_writebump = 0;
        struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
 
@@ -2490,9 +2491,15 @@ static int ext4_da_writepages(struct address_space *mapping,
        if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
                range_whole = 1;
 
-       if (wbc->range_cyclic)
+       range_cyclic = wbc->range_cyclic;
+       if (wbc->range_cyclic) {
                index = mapping->writeback_index;
-       else
+               if (index)
+                       cycled = 0;
+               wbc->range_start = index << PAGE_CACHE_SHIFT;
+               wbc->range_end  = LLONG_MAX;
+               wbc->range_cyclic = 0;
+       } else
                index = wbc->range_start >> PAGE_CACHE_SHIFT;
 
        mpd.wbc = wbc;
@@ -2506,6 +2513,7 @@ static int ext4_da_writepages(struct address_space *mapping,
        wbc->no_nrwrite_index_update = 1;
        pages_skipped = wbc->pages_skipped;
 
+retry:
        while (!ret && wbc->nr_to_write > 0) {
 
                /*
@@ -2548,6 +2556,7 @@ static int ext4_da_writepages(struct address_space *mapping,
                        pages_written += mpd.pages_written;
                        wbc->pages_skipped = pages_skipped;
                        ret = 0;
+                       io_done = 1;
                } else if (wbc->nr_to_write)
                        /*
                         * There is no more writeout needed
@@ -2556,6 +2565,13 @@ static int ext4_da_writepages(struct address_space *mapping,
                         */
                        break;
        }
+       if (!io_done && !cycled) {
+               cycled = 1;
+               index = 0;
+               wbc->range_start = index << PAGE_CACHE_SHIFT;
+               wbc->range_end  = mapping->writeback_index - 1;
+               goto retry;
+       }
        if (pages_skipped != wbc->pages_skipped)
                printk(KERN_EMERG "This should not happen leaving %s "
                                "with nr_to_write = %ld ret = %d\n",
@@ -2563,6 +2579,7 @@ static int ext4_da_writepages(struct address_space *mapping,
 
        /* Update index */
        index += pages_written;
+       wbc->range_cyclic = range_cyclic;
        if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
                /*
                 * set the writeback_index so that range_cyclic