Tools: hv: Reopen the devices if read() or write() returns errors

The state machine in the hv_utils driver can run out of order in some
corner cases, e.g. if the kvp daemon doesn't call write() fast enough
due to some reason, kvp_timeout_func() can run first and move the state
to HVUTIL_READY; next, when kvp_on_msg() is called it returns -EINVAL
since kvp_transaction.state is smaller than HVUTIL_USERSPACE_REQ; later,
the daemon's write() gets an error -EINVAL, and the daemon will exit().

We can reproduce the issue by sending a SIGSTOP signal to the daemon, wait
for 1 minute, and send a SIGCONT signal to the daemon: the daemon will
exit() quickly.

We can fix the issue by forcing a reset of the device (which means the
daemon can close() and open() the device again) and doing extra necessary
clean-up.

Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

1 files changed, 21 insertions, 15 deletions

diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c
index e9ef4ca6a655..ee9c1bb2293e 100644
--- a/tools/hv/hv_kvp_daemon.c
+++ b/tools/hv/hv_kvp_daemon.c
@@ -76,7 +76,7 @@ enum {
 	DNS
 };
 
-static int in_hand_shake = 1;
+static int in_hand_shake;
 
 static char *os_name = "";
 static char *os_major = "";
@@ -1360,7 +1360,7 @@ void print_usage(char *argv[])
 
 int main(int argc, char *argv[])
 {
-	int kvp_fd, len;
+	int kvp_fd = -1, len;
 	int error;
 	struct pollfd pfd;
 	char    *p;
@@ -1400,14 +1400,6 @@ int main(int argc, char *argv[])
 	openlog("KVP", 0, LOG_USER);
 	syslog(LOG_INFO, "KVP starting; pid is:%d", getpid());
 
-	kvp_fd = open("/dev/vmbus/hv_kvp", O_RDWR | O_CLOEXEC);
-
-	if (kvp_fd < 0) {
-		syslog(LOG_ERR, "open /dev/vmbus/hv_kvp failed; error: %d %s",
-			errno, strerror(errno));
-		exit(EXIT_FAILURE);
-	}
-
 	/*
 	 * Retrieve OS release information.
 	 */
@@ -1423,6 +1415,18 @@ int main(int argc, char *argv[])
 		exit(EXIT_FAILURE);
 	}
 
+reopen_kvp_fd:
+	if (kvp_fd != -1)
+		close(kvp_fd);
+	in_hand_shake = 1;
+	kvp_fd = open("/dev/vmbus/hv_kvp", O_RDWR | O_CLOEXEC);
+
+	if (kvp_fd < 0) {
+		syslog(LOG_ERR, "open /dev/vmbus/hv_kvp failed; error: %d %s",
+		       errno, strerror(errno));
+		exit(EXIT_FAILURE);
+	}
+
 	/*
 	 * Register ourselves with the kernel.
 	 */
@@ -1456,9 +1460,7 @@ int main(int argc, char *argv[])
 		if (len != sizeof(struct hv_kvp_msg)) {
 			syslog(LOG_ERR, "read failed; error:%d %s",
 			       errno, strerror(errno));
-
-			close(kvp_fd);
-			return EXIT_FAILURE;
+			goto reopen_kvp_fd;
 		}
 
 		/*
@@ -1617,13 +1619,17 @@ int main(int argc, char *argv[])
 			break;
 		}
 
-		/* Send the value back to the kernel. */
+		/*
+		 * Send the value back to the kernel. Note: the write() may
+		 * return an error due to hibernation; we can ignore the error
+		 * by resetting the dev file, i.e. closing and re-opening it.
+		 */
 kvp_done:
 		len = write(kvp_fd, hv_msg, sizeof(struct hv_kvp_msg));
 		if (len != sizeof(struct hv_kvp_msg)) {
 			syslog(LOG_ERR, "write failed; error: %d %s", errno,
 			       strerror(errno));
-			exit(EXIT_FAILURE);
+			goto reopen_kvp_fd;
 		}
 	}