From: Kuniyuki Iwashima kuniyu@amazon.com
[ Upstream commit fd86344823b521149bb31d91eba900ba3525efa6 ]
Commit dcf70df2048d ("af_unix: Fix up unix_edge.successor for embryo socket.") added spin_lock(&unix_gc_lock) in accept() path, and it caused regression in a stress test as reported by kernel test robot.
If the embryo socket is not part of the inflight graph, we need not hold the lock.
To decide that in O(1) time and avoid the regression in the normal use case,
1. add a new stat unix_sk(sk)->scm_stat.nr_unix_fds
2. count the number of inflight AF_UNIX sockets in the receive queue under unix_state_lock()
3. move unix_update_edges() call under unix_state_lock()
4. avoid locking if nr_unix_fds is 0 in unix_update_edges()
Reported-by: kernel test robot oliver.sang@intel.com Closes: https://lore.kernel.org/oe-lkp/202404101427.92a08551-oliver.sang@intel.com Signed-off-by: Kuniyuki Iwashima kuniyu@amazon.com Link: https://lore.kernel.org/r/20240413021928.20946-1-kuniyu@amazon.com Signed-off-by: Paolo Abeni pabeni@redhat.com (cherry picked from commit fd86344823b521149bb31d91eba900ba3525efa6) Signed-off-by: Lee Jones lee@kernel.org --- include/net/af_unix.h | 1 + net/unix/af_unix.c | 2 +- net/unix/garbage.c | 20 ++++++++++++++++---- 3 files changed, 18 insertions(+), 5 deletions(-)
diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 47042de4a2a9c..b6eedf7650da5 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -67,6 +67,7 @@ struct unix_skb_parms {
struct scm_stat { atomic_t nr_fds; + unsigned long nr_unix_fds; };
#define UNIXCB(skb) (*(struct unix_skb_parms *)&((skb)->cb)) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index df70d8a7ee837..236a2cd2bc93d 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1703,12 +1703,12 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags, }
tsk = skb->sk; - unix_update_edges(unix_sk(tsk)); skb_free_datagram(sk, skb); wake_up_interruptible(&unix_sk(sk)->peer_wait);
/* attach accepted sock to socket */ unix_state_lock(tsk); + unix_update_edges(unix_sk(tsk)); newsock->state = SS_CONNECTED; unix_sock_inherit_flags(sock, newsock); sock_graft(tsk, newsock); diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 12a4ec27e0d4d..95240a59808f2 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -209,6 +209,7 @@ void unix_add_edges(struct scm_fp_list *fpl, struct unix_sock *receiver) unix_add_edge(fpl, edge); } while (i < fpl->count_unix);
+ receiver->scm_stat.nr_unix_fds += fpl->count_unix; WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + fpl->count_unix); out: WRITE_ONCE(fpl->user->unix_inflight, fpl->user->unix_inflight + fpl->count); @@ -222,6 +223,7 @@ void unix_add_edges(struct scm_fp_list *fpl, struct unix_sock *receiver)
void unix_del_edges(struct scm_fp_list *fpl) { + struct unix_sock *receiver; int i = 0;
spin_lock(&unix_gc_lock); @@ -235,6 +237,8 @@ void unix_del_edges(struct scm_fp_list *fpl) unix_del_edge(fpl, edge); } while (i < fpl->count_unix);
+ receiver = fpl->edges[0].successor; + receiver->scm_stat.nr_unix_fds -= fpl->count_unix; WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - fpl->count_unix); out: WRITE_ONCE(fpl->user->unix_inflight, fpl->user->unix_inflight - fpl->count); @@ -246,10 +250,18 @@ void unix_del_edges(struct scm_fp_list *fpl)
void unix_update_edges(struct unix_sock *receiver) { - spin_lock(&unix_gc_lock); - unix_update_graph(unix_sk(receiver->listener)->vertex); - receiver->listener = NULL; - spin_unlock(&unix_gc_lock); + /* nr_unix_fds is only updated under unix_state_lock(). + * If it's 0 here, the embryo socket is not part of the + * inflight graph, and GC will not see it, so no lock needed. + */ + if (!receiver->scm_stat.nr_unix_fds) { + receiver->listener = NULL; + } else { + spin_lock(&unix_gc_lock); + unix_update_graph(unix_sk(receiver->listener)->vertex); + receiver->listener = NULL; + spin_unlock(&unix_gc_lock); + } }
int unix_prepare_fpl(struct scm_fp_list *fpl)