summaryrefslogtreecommitdiffstats
path: root/fs/cifs/smbdirect.c
diff options
context:
space:
mode:
authorVincent Whitchurch <vincent.whitchurch@axis.com>2022-06-01 07:03:18 +0200
committerSteve French <stfrench@microsoft.com>2022-06-01 07:03:18 +0200
commitcc391b694ff085f62f133e6b8f864d43a8e69dfd (patch)
treef0e4f32bac269c482937fa067ec661157f18bf73 /fs/cifs/smbdirect.c
parentcifs: when extending a file with falloc we should make files not-sparse (diff)
downloadlinux-cc391b694ff085f62f133e6b8f864d43a8e69dfd.tar.xz
linux-cc391b694ff085f62f133e6b8f864d43a8e69dfd.zip
cifs: fix potential deadlock in direct reclaim
The srv_mutex is used during writeback so cifs should ensure that allocations done when that mutex is held are done with GFP_NOFS, to avoid having direct reclaim ending up waiting for the same mutex and causing a deadlock. This is detected by lockdep with the splat below: ====================================================== WARNING: possible circular locking dependency detected 5.18.0 #70 Not tainted ------------------------------------------------------ kswapd0/49 is trying to acquire lock: ffff8880195782e0 (&tcp_ses->srv_mutex){+.+.}-{3:3}, at: compound_send_recv but task is already holding lock: ffffffffa98e66c0 (fs_reclaim){+.+.}-{0:0}, at: balance_pgdat which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (fs_reclaim){+.+.}-{0:0}: fs_reclaim_acquire kmem_cache_alloc_trace __request_module crypto_alg_mod_lookup crypto_alloc_tfm_node crypto_alloc_shash cifs_alloc_hash smb311_crypto_shash_allocate smb311_update_preauth_hash compound_send_recv cifs_send_recv SMB2_negotiate smb2_negotiate cifs_negotiate_protocol cifs_get_smb_ses cifs_mount cifs_smb3_do_mount smb3_get_tree vfs_get_tree path_mount __x64_sys_mount do_syscall_64 entry_SYSCALL_64_after_hwframe -> #0 (&tcp_ses->srv_mutex){+.+.}-{3:3}: __lock_acquire lock_acquire __mutex_lock mutex_lock_nested compound_send_recv cifs_send_recv SMB2_write smb2_sync_write cifs_write cifs_writepage_locked cifs_writepage shrink_page_list shrink_lruvec shrink_node balance_pgdat kswapd kthread ret_from_fork other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(fs_reclaim); lock(&tcp_ses->srv_mutex); lock(fs_reclaim); lock(&tcp_ses->srv_mutex); *** DEADLOCK *** 1 lock held by kswapd0/49: #0: ffffffffa98e66c0 (fs_reclaim){+.+.}-{0:0}, at: balance_pgdat stack backtrace: CPU: 2 PID: 49 Comm: kswapd0 Not tainted 5.18.0 #70 Call Trace: <TASK> dump_stack_lvl dump_stack print_circular_bug.cold check_noncircular __lock_acquire lock_acquire __mutex_lock mutex_lock_nested compound_send_recv cifs_send_recv SMB2_write smb2_sync_write cifs_write cifs_writepage_locked cifs_writepage shrink_page_list shrink_lruvec shrink_node balance_pgdat kswapd kthread ret_from_fork </TASK> Fix this by using the memalloc_nofs_save/restore APIs around the places where the srv_mutex is held. Do this in a wrapper function for the lock/unlock of the srv_mutex, and rename the srv_mutex to avoid missing call sites in the conversion. Note that there is another lockdep warning involving internal crypto locks, which was masked by this problem and is visible after this fix, see the discussion in this thread: https://lore.kernel.org/all/20220523123755.GA13668@axis.com/ Link: https://lore.kernel.org/r/CANT5p=rqcYfYMVHirqvdnnca4Mo+JQSw5Qu12v=kPfpk5yhhmg@mail.gmail.com/ Reported-by: Shyam Prasad N <nspmangalore@gmail.com> Suggested-by: Lars Persson <larper@axis.com> Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com> Reviewed-by: Enzo Matsumiya <ematsumiya@suse.de> Signed-off-by: Vincent Whitchurch <vincent.whitchurch@axis.com> Signed-off-by: Steve French <stfrench@microsoft.com>
Diffstat (limited to 'fs/cifs/smbdirect.c')
-rw-r--r--fs/cifs/smbdirect.c4
1 files changed, 2 insertions, 2 deletions
diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c
index c3278db1cade..5fbbec22bcc8 100644
--- a/fs/cifs/smbdirect.c
+++ b/fs/cifs/smbdirect.c
@@ -1382,9 +1382,9 @@ void smbd_destroy(struct TCP_Server_Info *server)
log_rdma_event(INFO, "freeing mr list\n");
wake_up_interruptible_all(&info->wait_mr);
while (atomic_read(&info->mr_used_count)) {
- mutex_unlock(&server->srv_mutex);
+ cifs_server_unlock(server);
msleep(1000);
- mutex_lock(&server->srv_mutex);
+ cifs_server_lock(server);
}
destroy_mr_list(info);