From b2a6662932c52304eee11323701f8a01aa110e37 Mon Sep 17 00:00:00 2001 From: "tsutomu.owa@toshiba.co.jp" Date: Tue, 12 Sep 2017 08:55:50 +0000 Subject: [PATCH] DLM: fix race condition between dlm_send and dlm_recv When kernel_sendpage(in send_to_sock) and kernel_recvmsg (in receive_from_sock) return error, close_connection may works at the same time. At that time, they may wait for each other by cancel_work_sync. Signed-off-by: Tadashi Miyauchi Signed-off-by: Tsutomu Owa Signed-off-by: David Teigland --- fs/dlm/lowcomms.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 980c58befd53..420946dcb7ca 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -110,6 +110,7 @@ struct connection { #define CF_IS_OTHERCON 5 #define CF_CLOSE 6 #define CF_APP_LIMITED 7 +#define CF_CLOSING 8 struct list_head writequeue; /* List of outgoing writequeue_entries */ spinlock_t writequeue_lock; int (*rx_action) (struct connection *); /* What to do when active */ @@ -581,9 +582,11 @@ static void make_sockaddr(struct sockaddr_storage *saddr, uint16_t port, static void close_connection(struct connection *con, bool and_other, bool tx, bool rx) { - if (tx && cancel_work_sync(&con->swork)) + bool closing = test_and_set_bit(CF_CLOSING, &con->flags); + + if (tx && !closing && cancel_work_sync(&con->swork)) log_print("canceled swork for node %d", con->nodeid); - if (rx && cancel_work_sync(&con->rwork)) + if (rx && !closing && cancel_work_sync(&con->rwork)) log_print("canceled rwork for node %d", con->nodeid); mutex_lock(&con->sock_mutex); @@ -603,6 +606,7 @@ static void close_connection(struct connection *con, bool and_other, con->retries = 0; mutex_unlock(&con->sock_mutex); + clear_bit(CF_CLOSING, &con->flags); } /* Data received from remote end */