Don't send protocol messages to a shm_mq that no longer exists.

Commit 2bd9e412f92bc6a68f3e8bcb18e04955cc35001d introduced a mechanism
for relaying protocol messages from a background worker to another
backend via a shm_mq.  However, there was no provision for shutting
down the communication channel.  Therefore, a protocol message sent
late in the shutdown sequence, such as a DEBUG message resulting from
cranking up log_min_messages, could crash the server.  To fix, install
an on_dsm_detach callback that disables sending messages to the shm_mq
when the associated DSM is detached.

diff --git a/src/backend/access/transam/parallel.c b/src/backend/access/transam/parallel.c
index 29d6ed57cc251b290104c3a8faae5ab3c8302567..0b94c0f87e967b49ed1704ce9114bfd7e1c23db7 100644 (file)
--- a/src/backend/access/transam/parallel.c
+++ b/src/backend/access/transam/parallel.c
@@ -867,7 +867,7 @@ ParallelWorkerMain(Datum main_arg)
                                         ParallelWorkerNumber * PARALLEL_ERROR_QUEUE_SIZE);
        shm_mq_set_sender(mq, MyProc);
        mqh = shm_mq_attach(mq, seg, NULL);
-       pq_redirect_to_shm_mq(mq, mqh);
+       pq_redirect_to_shm_mq(seg, mqh);
        pq_set_parallel_master(fps->parallel_master_pid,
                                                   fps->parallel_master_backend_id);
 

diff --git a/src/backend/libpq/pqmq.c b/src/backend/libpq/pqmq.c
index 9ca6b7ce0d1b7a348f6d29a22bf83139b1e42765..0a3c2b70cbe46f68f3ad076260007a2e9db48f62 100644 (file)
--- a/src/backend/libpq/pqmq.c
+++ b/src/backend/libpq/pqmq.c
@@ -26,6 +26,7 @@ static bool pq_mq_busy = false;
 static pid_t pq_mq_parallel_master_pid = 0;
 static pid_t pq_mq_parallel_master_backend_id = InvalidBackendId;
 
+static void pq_cleanup_redirect_to_shm_mq(dsm_segment *seg, Datum arg);
 static void mq_comm_reset(void);
 static int     mq_flush(void);
 static int     mq_flush_if_writable(void);
@@ -51,13 +52,26 @@ static PQcommMethods PqCommMqMethods = {
  * message queue.
  */
 void
-pq_redirect_to_shm_mq(shm_mq *mq, shm_mq_handle *mqh)
+pq_redirect_to_shm_mq(dsm_segment *seg, shm_mq_handle *mqh)
 {
        PqCommMethods = &PqCommMqMethods;
-       pq_mq = mq;
+       pq_mq = shm_mq_get_queue(mqh);
        pq_mq_handle = mqh;
        whereToSendOutput = DestRemote;
        FrontendProtocol = PG_PROTOCOL_LATEST;
+       on_dsm_detach(seg, pq_cleanup_redirect_to_shm_mq, (Datum) 0);
+}
+
+/*
+ * When the DSM that contains our shm_mq goes away, we need to stop sending
+ * messages to it.
+ */
+static void
+pq_cleanup_redirect_to_shm_mq(dsm_segment *seg, Datum arg)
+{
+       pq_mq = NULL;
+       pq_mq_handle = NULL;
+       whereToSendOutput = DestNone;
 }
 
 /*
@@ -123,9 +137,19 @@ mq_putmessage(char msgtype, const char *s, size_t len)
                if (pq_mq != NULL)
                        shm_mq_detach(pq_mq);
                pq_mq = NULL;
+               pq_mq_handle = NULL;
                return EOF;
        }
 
+       /*
+        * If the message queue is already gone, just ignore the message. This
+        * doesn't necessarily indicate a problem; for example, DEBUG messages
+        * can be generated late in the shutdown sequence, after all DSMs have
+        * already been detached.
+        */
+       if (pq_mq == NULL)
+               return 0;
+
        pq_mq_busy = true;
 
        iov[0].data = &msgtype;

diff --git a/src/include/libpq/pqmq.h b/src/include/libpq/pqmq.h
index 901756596a4717e76cb70e8d26f874e59442b50f..97f17da89db64e7cd8ce5703227852de13ee5932 100644 (file)
--- a/src/include/libpq/pqmq.h
+++ b/src/include/libpq/pqmq.h
@@ -16,7 +16,7 @@
 #include "lib/stringinfo.h"
 #include "storage/shm_mq.h"
 
-extern void pq_redirect_to_shm_mq(shm_mq *, shm_mq_handle *);
+extern void pq_redirect_to_shm_mq(dsm_segment *seg, shm_mq_handle *mqh);
 extern void pq_set_parallel_master(pid_t pid, BackendId backend_id);
 
 extern void pq_parse_errornotice(StringInfo str, ErrorData *edata);