client: Fix libcephfs aio metadata corruption.

Problem: With cephfs nfs-ganesha, there were following asserts hit while doing write on a file. 1. FAILED ceph_assert((bool)_front == (bool)_size) 2. FAILED ceph_assert(cap_refs[c] > 0) Cause: In aio path, the client_lock was not being held in the internal callback after the io is done where it's expected to be taken leading to corruption. Fix: Take client_lock in the callback Fixes: https://tracker.ceph.com/issues/68146 Signed-off-by: Kotresh HR <khiremat@redhat.com>
ceph · Sep 26, 2024 · 42f75b2 · 42f75b2
1 parent 624f695
commit 42f75b2
Showing 1 changed file with 5 additions and 1 deletion.
diff --git a/src/client/Client.cc b/src/client/Client.cc
@@ -10716,7 +10716,7 @@ void Client::C_Read_Finisher::finish_io(int r)
 {
   utime_t lat;
 
-  // Caller holds client_lock so we don't need to take it.
+  std::scoped_lock lock(clnt->client_lock);
 
   if (r >= 0) {
     if (is_read_async) {
@@ -11403,6 +11403,8 @@ void Client::C_Write_Finisher::finish_io(int r)
 {
   bool fini;
 
+  std::scoped_lock lock(clnt->client_lock);
+
   clnt->put_cap_ref(in, CEPH_CAP_FILE_BUFFER);
 
   if (r >= 0) {
@@ -11438,6 +11440,8 @@ void Client::C_Write_Finisher::finish_fsync(int r)
   bool fini;
   client_t const whoami = clnt->whoami;  // For the benefit of ldout prefix
 
+  ceph_assert(ceph_mutex_is_locked_by_me(clnt->client_lock));
+
   ldout(clnt->cct, 3) << "finish_fsync r = " << r << dendl;
 
   fsync_finished = true;