writeback: put unused inodes to LRU after writeback completion

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>
Cc: <stable@vger.kernel.org>		[3.5+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 51ea267d444c4d7aef1259521aa1f06154f26d13..3e3422f7f0a4b4c46080cf798c4185af0642e05d 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 b03c7195724685e74cba0275adaa718755eb5455..64999f144153d7740018203f884c24eb2a829f54 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 916b7cbf3e3e4fae7bc831c66373b5d5ea7a3c4a..2f6af7f645ebc3d8862da4edb1d71bc811c8d788 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