[PATCH RFC] nfsd: avoid recursive locking through fsnotify

From: Khazhismel Kumykov
Date: Fri Mar 18 2022 - 20:16:50 EST


fsnotify_add_inode_mark may allocate with GFP_KERNEL, which may result
in recursing back into nfsd, resulting in deadlock. See below stack.

nfsd D 0 1591536 2 0x80004080
Call Trace:
__schedule+0x497/0x630
schedule+0x67/0x90
schedule_preempt_disabled+0xe/0x10
__mutex_lock+0x347/0x4b0
fsnotify_destroy_mark+0x22/0xa0
nfsd_file_free+0x79/0xd0 [nfsd]
nfsd_file_put_noref+0x7c/0x90 [nfsd]
nfsd_file_lru_dispose+0x6d/0xa0 [nfsd]
nfsd_file_lru_scan+0x57/0x80 [nfsd]
do_shrink_slab+0x1f2/0x330
shrink_slab+0x244/0x2f0
shrink_node+0xd7/0x490
do_try_to_free_pages+0x12f/0x3b0
try_to_free_pages+0x43f/0x540
__alloc_pages_slowpath+0x6ab/0x11c0
__alloc_pages_nodemask+0x274/0x2c0
alloc_slab_page+0x32/0x2e0
new_slab+0xa6/0x8b0
___slab_alloc+0x34b/0x520
kmem_cache_alloc+0x1c4/0x250
fsnotify_add_mark_locked+0x18d/0x4c0
fsnotify_add_mark+0x48/0x70
nfsd_file_acquire+0x570/0x6f0 [nfsd]
nfsd_read+0xa7/0x1c0 [nfsd]
nfsd3_proc_read+0xc1/0x110 [nfsd]
nfsd_dispatch+0xf7/0x240 [nfsd]
svc_process_common+0x2f4/0x610 [sunrpc]
svc_process+0xf9/0x110 [sunrpc]
nfsd+0x10e/0x180 [nfsd]
kthread+0x130/0x140
ret_from_fork+0x35/0x40

Signed-off-by: Khazhismel Kumykov <khazhy@xxxxxxxxxx>
---
fs/nfsd/filecache.c | 4 ++++
1 file changed, 4 insertions(+)

Marking this RFC since I haven't actually had a chance to test this, we
we're seeing this deadlock for some customers.

diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index fdf89fcf1a0c..a14760f9b486 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -121,6 +121,7 @@ nfsd_file_mark_find_or_create(struct nfsd_file *nf)
struct fsnotify_mark *mark;
struct nfsd_file_mark *nfm = NULL, *new;
struct inode *inode = nf->nf_inode;
+ unsigned int pflags;

do {
mutex_lock(&nfsd_file_fsnotify_group->mark_mutex);
@@ -149,7 +150,10 @@ nfsd_file_mark_find_or_create(struct nfsd_file *nf)
new->nfm_mark.mask = FS_ATTRIB|FS_DELETE_SELF;
refcount_set(&new->nfm_ref, 1);

+ /* fsnotify allocates, avoid recursion back into nfsd */
+ pflags = memalloc_nofs_save();
err = fsnotify_add_inode_mark(&new->nfm_mark, inode, 0);
+ memalloc_nofs_restore(pflags);

/*
* If the add was successful, then return the object.
--
2.35.1.894.gb6a874cedc-goog