Re: [libvirt] [PATCH 2/3] qemu: support passing pre-opened UNIX socket listen FD

There is a race condition when spawning QEMU where libvirt has spawned QEMU but the monitor socket is not yet open. Libvirt has to repeatedly try to connect() to QEMU's monitor until eventually it succeeds, or times out. We use kill() to check if QEMU is still alive so we avoid waiting a long time if QEMU exited, but having a timeout at all is still unpleasant. With QEMU 2.12 we can pass in a pre-opened FD for UNIX domain or TCP sockets. If libvirt has called bind() and listen() on this FD, then we have a guarantee that libvirt can immediately call connect() and succeed without any race. Although we only really care about this for the monitor socket and agent socket, this patch does FD passing for all UNIX socket based character devices since there appears to be no downside to it. We don't do FD passing for TCP sockets, however, because it is only possible to pass a single FD, while some hostnames may require listening on multiple FDs to cover IPv4 and IPv6 concurrently. Signed-off-by: Daniel P. Berrangé <berrange(a)redhat.com&gt; --- src/qemu/qemu_command.c | 58 +++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 56 insertions(+), 2 deletions(-) diff --git a/src/qemu/qemu_command.c b/src/qemu/qemu_command.c index fa0aa5d5c3..291aad13cf 100644 --- a/src/qemu/qemu_command.c +++ b/src/qemu/qemu_command.c @@ -5010,8 +5010,62 @@ qemuBuildChrChardevStr(virLogManagerPtr logManager, break; case VIR_DOMAIN_CHR_TYPE_UNIX: - virBufferAsprintf(&buf, "socket,id=%s,path=", charAlias); - virQEMUBuildBufferEscapeComma(&buf, dev->data.nix.path); +#ifndef WIN32 + if (virQEMUCapsGet(qemuCaps, QEMU_CAPS_CHARDEV_FD_PASS)) { + struct sockaddr_un addr; + socklen_t addrlen = sizeof(addr); + int fd; + + if ((fd = socket(AF_UNIX, SOCK_STREAM, 0)) < 0) { + virReportSystemError(errno, "%s", + _("Unable to create UNIX socket")); + goto cleanup; + } + + memset(&addr, 0, sizeof(addr)); + addr.sun_family = AF_UNIX; + if (virStrcpyStatic(addr.sun_path, dev->data.nix.path) == NULL) { + virReportError(VIR_ERR_INTERNAL_ERROR, + _("Monitor path %s too big for destination"), + dev->data.nix.path);

+ VIR_FORCE_CLOSE(fd); + goto cleanup; + } + + if (unlink(dev->data.nix.path) < 0 && errno != ENOENT) { + virReportSystemError(errno, + _("Unable to unlink %s"), + dev->data.nix.path); + VIR_FORCE_CLOSE(fd); + goto cleanup; + } + + if (bind(fd, (struct sockaddr *)&addr, addrlen) < 0) { + virReportSystemError(errno, + _("Unable to bind to monitor %s"), + dev->data.nix.path);

+ VIR_FORCE_CLOSE(fd); + goto cleanup; + } + + if (listen(fd, 1) < 0) { + virReportSystemError(errno, + _("Unable to listen to monitor %s"), + dev->data.nix.path);

+ VIR_FORCE_CLOSE(fd); + goto cleanup; + } + + virBufferAsprintf(&buf, "socket,id=%s,fd=%d", charAlias, fd); + + virCommandPassFD(cmd, fd, VIR_COMMAND_PASS_FD_CLOSE_PARENT); + } else { +#endif /* WIN32 */ + virBufferAsprintf(&buf, "socket,id=%s,path=", charAlias); + virQEMUBuildBufferEscapeComma(&buf, dev->data.nix.path); +#ifndef WIN32 + } +#endif /* WIN32 */ if (dev->data.nix.listen) virBufferAdd(&buf, nowait ? ",server,nowait" : ",server", -1);