writeback: put unused inodes to LRU after writeback completion

commit 4eff96dd5283a102e0c1cac95247090be74a38ed upstream.

Commit 169ebd90131b ("writeback: Avoid iput() from flusher thread")
removed iget-iput pair from inode writeback.  As a side effect, inodes
that are dirty during iput_final() call won't be ever added to inode LRU
(iput_final() doesn't add dirty inodes to LRU and later when the inode
is cleaned there's noone to add the inode there).  Thus inodes are
effectively unreclaimable until someone looks them up again.

The practical effect of this bug is limited by the fact that inodes are
pinned by a dentry for long enough that the inode gets cleaned.  But
still the bug can have nasty consequences leading up to OOM conditions
under certain circumstances.  Following can easily reproduce the
problem:

  for (( i = 0; i < 1000; i++ )); do
    mkdir $i
    for (( j = 0; j < 1000; j++ )); do
      touch $i/$j
      echo 2 > /proc/sys/vm/drop_caches
    done
  done

then one needs to run 'sync; ls -lR' to make inodes reclaimable again.

We fix the issue by inserting unused clean inodes into the LRU after
writeback finishes in inode_sync_complete().

Signed-off-by: Jan Kara <jack@suse.cz>
Reported-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: Dave Chinner <david@fromorbit.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 5602d73d4ec7a590ba76173802a1f3b51ba93802..af321a6f71ffa4fb9c3ac7131d137a92e794e981 100644 (file)
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -228,6 +228,8 @@ static void requeue_io(struct inode *inode, struct bdi_writeback *wb)
 static void inode_sync_complete(struct inode *inode)
 {
        inode->i_state &= ~I_SYNC;
+       /* If inode is clean an unused, put it into LRU now... */
+       inode_add_lru(inode);
        /* Waiters must see I_SYNC cleared before being woken up */
        smp_mb();
        wake_up_bit(&inode->i_state, __I_SYNC);

diff --git a/fs/inode.c b/fs/inode.c
index ac8d904b3f1624bfa945ba088d2909e740e16a6c..7c14897f9a9ff142ad8571cc52cc7ab9a86be7e4 100644 (file)
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -408,6 +408,19 @@ static void inode_lru_list_add(struct inode *inode)
        spin_unlock(&inode->i_sb->s_inode_lru_lock);
 }
 
+/*
+ * Add inode to LRU if needed (inode is unused and clean).
+ *
+ * Needs inode->i_lock held.
+ */
+void inode_add_lru(struct inode *inode)
+{
+       if (!(inode->i_state & (I_DIRTY | I_SYNC | I_FREEING | I_WILL_FREE)) &&
+           !atomic_read(&inode->i_count) && inode->i_sb->s_flags & MS_ACTIVE)
+               inode_lru_list_add(inode);
+}
+
+
 static void inode_lru_list_del(struct inode *inode)
 {
        spin_lock(&inode->i_sb->s_inode_lru_lock);
@@ -1390,8 +1403,7 @@ static void iput_final(struct inode *inode)
 
        if (!drop && (sb->s_flags & MS_ACTIVE)) {
                inode->i_state |= I_REFERENCED;
-               if (!(inode->i_state & (I_DIRTY|I_SYNC)))
-                       inode_lru_list_add(inode);
+               inode_add_lru(inode);
                spin_unlock(&inode->i_lock);
                return;
        }

diff --git a/fs/internal.h b/fs/internal.h
index 371bcc4b1697df808e506a6f88735209dec17dd8..52813bd2a2290632ce1f6d7b89b511967fee41d2 100644 (file)
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -110,6 +110,7 @@ extern int open_check_o_direct(struct file *f);
  * inode.c
  */
 extern spinlock_t inode_sb_list_lock;
+extern void inode_add_lru(struct inode *inode);
 
 /*
  * fs-writeback.c