diff mbox series

[v2] vfs: Don't evict inode under the inode lru traversing context

Message ID 20240809031628.1069873-1-chengzhihao@huaweicloud.com
State New
Headers show
Series [v2] vfs: Don't evict inode under the inode lru traversing context | expand

Commit Message

Zhihao Cheng Aug. 9, 2024, 3:16 a.m. UTC 
From: Zhihao Cheng <chengzhihao1@huawei.com>

The inode reclaiming process(See function prune_icache_sb) collects all
reclaimable inodes and mark them with I_FREEING flag at first, at that
time, other processes will be stuck if they try getting these inodes
(See function find_inode_fast), then the reclaiming process destroy the
inodes by function dispose_list(). Some filesystems(eg. ext4 with
ea_inode feature, ubifs with xattr) may do inode lookup in the inode
evicting callback function, if the inode lookup is operated under the
inode lru traversing context, deadlock problems may happen.

Case 1: In function ext4_evict_inode(), the ea inode lookup could happen
        if ea_inode feature is enabled, the lookup process will be stuck
	under the evicting context like this:

 1. File A has inode i_reg and an ea inode i_ea
 2. getfattr(A, xattr_buf) // i_ea is added into lru // lru->i_ea
 3. Then, following three processes running like this:

    PA                              PB
 echo 2 > /proc/sys/vm/drop_caches
  shrink_slab
   prune_dcache_sb
   // i_reg is added into lru, lru->i_ea->i_reg
   prune_icache_sb
    list_lru_walk_one
     inode_lru_isolate
      i_ea->i_state |= I_FREEING // set inode state
     inode_lru_isolate
      __iget(i_reg)
      spin_unlock(&i_reg->i_lock)
      spin_unlock(lru_lock)
                                     rm file A
                                      i_reg->nlink = 0
      iput(i_reg) // i_reg->nlink is 0, do evict
       ext4_evict_inode
        ext4_xattr_delete_inode
         ext4_xattr_inode_dec_ref_all
          ext4_xattr_inode_iget
           ext4_iget(i_ea->i_ino)
            iget_locked
             find_inode_fast
              __wait_on_freeing_inode(i_ea) ----→ AA deadlock
    dispose_list // cannot be executed by prune_icache_sb
     wake_up_bit(&i_ea->i_state)

Case 2: In deleted inode writing function ubifs_jnl_write_inode(), file
        deleting process holds BASEHD's wbuf->io_mutex while getting the
	xattr inode, which could race with inode reclaiming process(The
        reclaiming process could try locking BASEHD's wbuf->io_mutex in
	inode evicting function), then an ABBA deadlock problem would
	happen as following:

 1. File A has inode ia and a xattr(with inode ixa), regular file B has
    inode ib and a xattr.
 2. getfattr(A, xattr_buf) // ixa is added into lru // lru->ixa
 3. Then, following three processes running like this:

        PA                PB                        PC
                echo 2 > /proc/sys/vm/drop_caches
                 shrink_slab
                  prune_dcache_sb
                  // ib and ia are added into lru, lru->ixa->ib->ia
                  prune_icache_sb
                   list_lru_walk_one
                    inode_lru_isolate
                     ixa->i_state |= I_FREEING // set inode state
                    inode_lru_isolate
                     __iget(ib)
                     spin_unlock(&ib->i_lock)
                     spin_unlock(lru_lock)
                                                   rm file B
                                                    ib->nlink = 0
 rm file A
  iput(ia)
   ubifs_evict_inode(ia)
    ubifs_jnl_delete_inode(ia)
     ubifs_jnl_write_inode(ia)
      make_reservation(BASEHD) // Lock wbuf->io_mutex
      ubifs_iget(ixa->i_ino)
       iget_locked
        find_inode_fast
         __wait_on_freeing_inode(ixa)
          |          iput(ib) // ib->nlink is 0, do evict
          |           ubifs_evict_inode
          |            ubifs_jnl_delete_inode(ib)
          ↓             ubifs_jnl_write_inode
     ABBA deadlock ←-----make_reservation(BASEHD)
                   dispose_list // cannot be executed by prune_icache_sb
                    wake_up_bit(&ixa->i_state)

Fix the possible deadlock by using new inode state flag I_LRU_ISOLATING
to pin the inode in memory while inode_lru_isolate() reclaims its pages
instead of using ordinary inode reference. This way inode deletion
cannot be triggered from inode_lru_isolate() thus avoiding the deadlock.
evict() is made to wait for I_LRU_ISOLATING to be cleared before
proceeding with inode cleanup.

Link: https://lore.kernel.org/all/37c29c42-7685-d1f0-067d-63582ffac405@huaweicloud.com/
Link: https://bugzilla.kernel.org/show_bug.cgi?id=219022
Fixes: e50e5129f384 ("ext4: xattr-in-inode support")
Fixes: 7959cf3a7506 ("ubifs: journal: Handle xattrs like files")
Cc: stable@vger.kernel.org
Signed-off-by: Zhihao Cheng <chengzhihao1@huawei.com>
Suggested-by: Jan Kara <jack@suse.cz>
Suggested-by: Mateusz Guzik <mjguzik@gmail.com>
Reviewed-by: Jan Kara <jack@suse.cz>
---
 v1->v2: Update commit message according to Jan's suggestion.
         Rename functions, inode_lru_isolating -> inode_pin_lru_isolating,
	 inode_lru_finish_isolating -> inode_unpin_lru_isolating.
	 Add lockdep_assert is inode_pin_lru_isolating().
	 Wait once for flag I_LRU_ISOLATING in
	 inode_wait_for_lru_isolating().
	 ** Add smp_mb() in inode_unpin_lru_isolating() to avoid forever
	 waiting by out-of-order execution, just like unlock_new_inode()
	 and inode_sync_complete() do. **
 fs/inode.c         | 39 +++++++++++++++++++++++++++++++++++++--
 include/linux/fs.h |  5 +++++
 2 files changed, 42 insertions(+), 2 deletions(-)

Comments

Christian Brauner Aug. 9, 2024, 3:15 p.m. UTC | #1 
On Fri, 09 Aug 2024 11:16:28 +0800, Zhihao Cheng wrote:
> The inode reclaiming process(See function prune_icache_sb) collects all
> reclaimable inodes and mark them with I_FREEING flag at first, at that
> time, other processes will be stuck if they try getting these inodes
> (See function find_inode_fast), then the reclaiming process destroy the
> inodes by function dispose_list(). Some filesystems(eg. ext4 with
> ea_inode feature, ubifs with xattr) may do inode lookup in the inode
> evicting callback function, if the inode lookup is operated under the
> inode lru traversing context, deadlock problems may happen.
> 
> [...]

I've replaced the BUG_ON() with WARN_ON().

---

Applied to the vfs.fixes branch of the vfs/vfs.git tree.
Patches in the vfs.fixes branch should appear in linux-next soon.

Please report any outstanding bugs that were missed during review in a
new review to the original patch series allowing us to drop it.

It's encouraged to provide Acked-bys and Reviewed-bys even though the
patch has now been applied. If possible patch trailers will be updated.

Note that commit hashes shown below are subject to change due to rebase,
trailer updates or similar. If in doubt, please check the listed branch.

tree:   https://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs.git
branch: vfs.fixes

[1/1] vfs: Don't evict inode under the inode lru traversing context
      https://git.kernel.org/vfs/vfs/c/24b0ba4e047d
diff mbox series

Patch

diff --git a/fs/inode.c b/fs/inode.c
index 86670941884b..bbeef7323cdd 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -488,6 +488,39 @@  static void inode_lru_list_del(struct inode *inode)
 		this_cpu_dec(nr_unused);
 }
 
+static void inode_pin_lru_isolating(struct inode *inode)
+{
+	lockdep_assert_held(&inode->i_lock);
+	BUG_ON(inode->i_state & (I_LRU_ISOLATING | I_FREEING | I_WILL_FREE));
+	inode->i_state |= I_LRU_ISOLATING;
+}
+
+static void inode_unpin_lru_isolating(struct inode *inode)
+{
+	spin_lock(&inode->i_lock);
+	BUG_ON(!(inode->i_state & I_LRU_ISOLATING));
+	inode->i_state &= ~I_LRU_ISOLATING;
+	smp_mb();
+	wake_up_bit(&inode->i_state, __I_LRU_ISOLATING);
+	spin_unlock(&inode->i_lock);
+}
+
+static void inode_wait_for_lru_isolating(struct inode *inode)
+{
+	spin_lock(&inode->i_lock);
+	if (inode->i_state & I_LRU_ISOLATING) {
+		DEFINE_WAIT_BIT(wq, &inode->i_state, __I_LRU_ISOLATING);
+		wait_queue_head_t *wqh;
+
+		wqh = bit_waitqueue(&inode->i_state, __I_LRU_ISOLATING);
+		spin_unlock(&inode->i_lock);
+		__wait_on_bit(wqh, &wq, bit_wait, TASK_UNINTERRUPTIBLE);
+		spin_lock(&inode->i_lock);
+		BUG_ON(inode->i_state & I_LRU_ISOLATING);
+	}
+	spin_unlock(&inode->i_lock);
+}
+
 /**
  * inode_sb_list_add - add inode to the superblock list of inodes
  * @inode: inode to add
@@ -657,6 +690,8 @@  static void evict(struct inode *inode)
 
 	inode_sb_list_del(inode);
 
+	inode_wait_for_lru_isolating(inode);
+
 	/*
 	 * Wait for flusher thread to be done with the inode so that filesystem
 	 * does not start destroying it while writeback is still running. Since
@@ -855,7 +890,7 @@  static enum lru_status inode_lru_isolate(struct list_head *item,
 	 * be under pressure before the cache inside the highmem zone.
 	 */
 	if (inode_has_buffers(inode) || !mapping_empty(&inode->i_data)) {
-		__iget(inode);
+		inode_pin_lru_isolating(inode);
 		spin_unlock(&inode->i_lock);
 		spin_unlock(lru_lock);
 		if (remove_inode_buffers(inode)) {
@@ -867,7 +902,7 @@  static enum lru_status inode_lru_isolate(struct list_head *item,
 				__count_vm_events(PGINODESTEAL, reap);
 			mm_account_reclaimed_pages(reap);
 		}
-		iput(inode);
+		inode_unpin_lru_isolating(inode);
 		spin_lock(lru_lock);
 		return LRU_RETRY;
 	}
diff --git a/include/linux/fs.h b/include/linux/fs.h
index fd34b5755c0b..fb0426f349fc 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2392,6 +2392,9 @@  static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src,
  *
  * I_PINNING_FSCACHE_WB	Inode is pinning an fscache object for writeback.
  *
+ * I_LRU_ISOLATING	Inode is pinned being isolated from LRU without holding
+ *			i_count.
+ *
  * Q: What is the difference between I_WILL_FREE and I_FREEING?
  */
 #define I_DIRTY_SYNC		(1 << 0)
@@ -2415,6 +2418,8 @@  static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src,
 #define I_DONTCACHE		(1 << 16)
 #define I_SYNC_QUEUED		(1 << 17)
 #define I_PINNING_NETFS_WB	(1 << 18)
+#define __I_LRU_ISOLATING	19
+#define I_LRU_ISOLATING		(1 << __I_LRU_ISOLATING)
 
 #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
 #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES)