8:40 a.m.
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>
---
src/qemu/qemu_command.c | 64 ++++++++++++++++++-
src/qemu/qemu_command.h | 4 ++
.../disk-drive-write-cache.x86_64-latest.args | 3 +-
...irtio-scsi-reservations.x86_64-latest.args | 3 +-
tests/qemuxml2argvmock.c | 16 +++++
5 files changed, 84 insertions(+), 6 deletions(-)
diff --git a/src/qemu/qemu_command.c b/src/qemu/qemu_command.c
index c4237339bf..6834480e1f 100644
--- a/src/qemu/qemu_command.c
+++ b/src/qemu/qemu_command.c
@@ -4913,6 +4913,56 @@ qemuBuildChrChardevReconnectStr(virBufferPtr buf,
}
+int
+qemuOpenChrChardevUNIXSocket(const virDomainChrSourceDef *dev)
+{
+ 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 error;
+ }
+
+ 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,
+ _("UNIX socket path '%s' too long"),
+ dev->data.nix.path);
+ goto error;
+ }
+
+ if (unlink(dev->data.nix.path) < 0 && errno != ENOENT) {
+ virReportSystemError(errno,
+ _("Unable to unlink %s"),
+ dev->data.nix.path);
+ goto error;
+ }
+
+ if (bind(fd, (struct sockaddr *)&addr, addrlen) < 0) {
+ virReportSystemError(errno,
+ _("Unable to bind to UNIX socket path
'%s'"),
+ dev->data.nix.path);
+ goto error;
+ }
+
+ if (listen(fd, 1) < 0) {
+ virReportSystemError(errno,
+ _("Unable to listen to UNIX socket path
'%s'"),
+ dev->data.nix.path);
+ goto error;
+ }
+
+ return fd;
+
+ error:
+ VIR_FORCE_CLOSE(fd);
+ return -1;
+}
+
/* This function outputs a -chardev command line option which describes only the
* host side of the character device */
static char *
@@ -5042,8 +5092,18 @@ qemuBuildChrChardevStr(virLogManagerPtr logManager,
break;
case VIR_DOMAIN_CHR_TYPE_UNIX:
- virBufferAsprintf(&buf, "socket,id=%s,path=", charAlias);
- virQEMUBuildBufferEscapeComma(&buf, dev->data.nix.path);
+ if (virQEMUCapsGet(qemuCaps, QEMU_CAPS_CHARDEV_FD_PASS)) {
+ int fd = qemuOpenChrChardevUNIXSocket(dev);
+ if (fd < 0)
+ goto cleanup;
+
+ virBufferAsprintf(&buf, "socket,id=%s,fd=%d", charAlias, fd);
+
+ virCommandPassFD(cmd, fd, VIR_COMMAND_PASS_FD_CLOSE_PARENT);
+ } else {
+ virBufferAsprintf(&buf, "socket,id=%s,path=", charAlias);
+ virQEMUBuildBufferEscapeComma(&buf, dev->data.nix.path);
+ }
if (dev->data.nix.listen)
virBufferAdd(&buf, nowait ? ",server,nowait" :
",server", -1);
diff --git a/src/qemu/qemu_command.h b/src/qemu/qemu_command.h
index 28bc33558b..f722b1be72 100644
--- a/src/qemu/qemu_command.h
+++ b/src/qemu/qemu_command.h
@@ -70,6 +70,10 @@ int qemuBuildTLSx509BackendProps(const char *tlspath,
virQEMUCapsPtr qemuCaps,
virJSONValuePtr *propsret);
+/* Open a UNIX socket for chardev FD passing */
+int
+qemuOpenChrChardevUNIXSocket(const virDomainChrSourceDef *dev);
+
/* Generate '-device' string for chardev device */
int
qemuBuildChrDeviceStr(char **deviceStr,
diff --git a/tests/qemuxml2argvdata/disk-drive-write-cache.x86_64-latest.args
b/tests/qemuxml2argvdata/disk-drive-write-cache.x86_64-latest.args
index a63c5b7477..9e5b611351 100644
--- a/tests/qemuxml2argvdata/disk-drive-write-cache.x86_64-latest.args
+++ b/tests/qemuxml2argvdata/disk-drive-write-cache.x86_64-latest.args
@@ -17,8 +17,7 @@ file=/tmp/lib/domain--1-QEMUGuest1/master-key.aes \
-display none \
-no-user-config \
-nodefaults \
--chardev socket,id=charmonitor,path=/tmp/lib/domain--1-QEMUGuest1/monitor.sock,\
-server,nowait \
+-chardev socket,id=charmonitor,fd=1729,server,nowait \
-mon chardev=charmonitor,id=monitor,mode=control \
-rtc base=utc \
-no-shutdown \
diff --git a/tests/qemuxml2argvdata/disk-virtio-scsi-reservations.x86_64-latest.args
b/tests/qemuxml2argvdata/disk-virtio-scsi-reservations.x86_64-latest.args
index 768bc22f9f..ad88d3319a 100644
--- a/tests/qemuxml2argvdata/disk-virtio-scsi-reservations.x86_64-latest.args
+++ b/tests/qemuxml2argvdata/disk-virtio-scsi-reservations.x86_64-latest.args
@@ -21,8 +21,7 @@ path=/path/to/qemu-pr-helper.sock \
-display none \
-no-user-config \
-nodefaults \
--chardev socket,id=charmonitor,path=/tmp/lib/domain--1-QEMUGuest1/monitor.sock,\
-server,nowait \
+-chardev socket,id=charmonitor,fd=1729,server,nowait \
-mon chardev=charmonitor,id=monitor,mode=control \
-rtc base=utc \
-no-shutdown \
diff --git a/tests/qemuxml2argvmock.c b/tests/qemuxml2argvmock.c
index 6d78063f00..b1edbdd0e6 100644
--- a/tests/qemuxml2argvmock.c
+++ b/tests/qemuxml2argvmock.c
@@ -37,6 +37,7 @@
#include "virtpm.h"
#include "virutil.h"
#include "qemu/qemu_interface.h"
+#include "qemu/qemu_command.h"
#include <time.h>
#include <unistd.h>
@@ -227,3 +228,18 @@ qemuInterfaceOpenVhostNet(virDomainDefPtr def ATTRIBUTE_UNUSED,
vhostfd[i] = STDERR_FILENO + 42 + i;
return 0;
}
+
+
+int
+qemuOpenChrChardevUNIXSocket(const virDomainChrSourceDef *dev ATTRIBUTE_UNUSED)
+
+{
+ /* We need to return an FD number for a UNIX listener socket,
+ * which will be given to QEMU via a CLI arg. We need a fixed
+ * number to get stable tests. This is obviously not a real
+ * FD number, so when virCommand closes the FD in the parent
+ * it will get EINVAL, but that's (hopefully) not going to
+ * be a problem....
+ */
+ return 1729;
+}
--
2.17.0