From: Sam Li <faithilikerun@gmail.com>

Linux recently added a new io_uring(7) optimization API that QEMU

doesn't take advantage of yet. The liburing library that QEMU uses

has added a corresponding new API calling io_uring_register_ring_fd().

When this API is called after creating the ring, the io_uring_submit()

library function passes a flag to the io_uring_enter(2) syscall

allowing it to skip the ring file descriptor fdget()/fdput()

operations. This saves some CPU cycles.

Signed-off-by: Sam Li <faithilikerun@gmail.com>

Message-id: 20220531105011.111082-1-faithilikerun@gmail.com

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

---

meson.build | 1 +

block/io_uring.c | 12 +++++++++++-

2 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/meson.build b/meson.build

index XXXXXXX..XXXXXXX 100644

--- a/meson.build

+++ b/meson.build

@@ -XXX,XX +XXX,XX @@ config_host_data.set('CONFIG_LIBNFS', libnfs.found())

config_host_data.set('CONFIG_LIBSSH', libssh.found())

config_host_data.set('CONFIG_LINUX_AIO', libaio.found())

config_host_data.set('CONFIG_LINUX_IO_URING', linux_io_uring.found())

+config_host_data.set('CONFIG_LIBURING_REGISTER_RING_FD', cc.has_function('io_uring_register_ring_fd', prefix: '#include <liburing.h>', dependencies:linux_io_uring))

config_host_data.set('CONFIG_LIBPMEM', libpmem.found())

config_host_data.set('CONFIG_NUMA', numa.found())

config_host_data.set('CONFIG_OPENGL', opengl.found())

diff --git a/block/io_uring.c b/block/io_uring.c

index XXXXXXX..XXXXXXX 100644

--- a/block/io_uring.c

+++ b/block/io_uring.c

@@ -XXX,XX +XXX,XX @@

#include "qapi/error.h"

#include "trace.h"

+

/* io_uring ring size */

#define MAX_ENTRIES 128

@@ -XXX,XX +XXX,XX @@ LuringState *luring_init(Error **errp)

}

ioq_init(&s->io_q);

+#ifdef CONFIG_LIBURING_REGISTER_RING_FD

+ if (io_uring_register_ring_fd(&s->ring) < 0) {

+ /*

+ * Only warn about this error: we will fallback to the non-optimized

+ * io_uring operations.

+ */

+ warn_report("failed to register linux io_uring ring file descriptor");

+ }

+#endif

+

return s;

-

}

void luring_cleanup(LuringState *s)

--

2.36.1

From: Jagannathan Raman <jag.raman@oracle.com>

Add blocker to prevent hot-unplug of devices

TYPE_VFIO_USER_SERVER, which is introduced shortly, attaches itself to a

PCIDevice on which it depends. If the attached PCIDevice gets removed

while the server in use, it could cause it crash. To prevent this,

TYPE_VFIO_USER_SERVER adds an unplug blocker for the PCIDevice.

Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>

Signed-off-by: John G Johnson <john.g.johnson@oracle.com>

Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>

Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>

Message-id: c41ef80b7cc063314d629737bed2159e5713f2e0.1655151679.git.jag.raman@oracle.com

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

---

include/hw/qdev-core.h | 29 +++++++++++++++++++++++++++++

hw/core/qdev.c | 24 ++++++++++++++++++++++++

softmmu/qdev-monitor.c | 4 ++++

3 files changed, 57 insertions(+)

diff --git a/include/hw/qdev-core.h b/include/hw/qdev-core.h

index XXXXXXX..XXXXXXX 100644

--- a/include/hw/qdev-core.h

+++ b/include/hw/qdev-core.h

@@ -XXX,XX +XXX,XX @@ struct DeviceState {

int instance_id_alias;

int alias_required_for_version;

ResettableState reset;

+ GSList *unplug_blockers;

};

struct DeviceListener {

@@ -XXX,XX +XXX,XX @@ void qdev_simple_device_unplug_cb(HotplugHandler *hotplug_dev,

void qdev_machine_creation_done(void);

bool qdev_machine_modified(void);

+/**

+ * qdev_add_unplug_blocker: Add an unplug blocker to a device

+ *

+ * @dev: Device to be blocked from unplug

+ * @reason: Reason for blocking

+ */

+void qdev_add_unplug_blocker(DeviceState *dev, Error *reason);

+

+/**

+ * qdev_del_unplug_blocker: Remove an unplug blocker from a device

+ *

+ * @dev: Device to be unblocked

+ * @reason: Pointer to the Error used with qdev_add_unplug_blocker.

+ * Used as a handle to lookup the blocker for deletion.

+ */

+void qdev_del_unplug_blocker(DeviceState *dev, Error *reason);

+

+/**

+ * qdev_unplug_blocked: Confirm if a device is blocked from unplug

+ *

+ * @dev: Device to be tested

+ * @reason: Returns one of the reasons why the device is blocked,

+ * if any

+ *

+ * Returns: true if device is blocked from unplug, false otherwise

+ */

+bool qdev_unplug_blocked(DeviceState *dev, Error **errp);

+

/**

* GpioPolarity: Polarity of a GPIO line

*

diff --git a/hw/core/qdev.c b/hw/core/qdev.c

index XXXXXXX..XXXXXXX 100644

--- a/hw/core/qdev.c

+++ b/hw/core/qdev.c

@@ -XXX,XX +XXX,XX @@ char *qdev_get_dev_path(DeviceState *dev)

return NULL;

}

+void qdev_add_unplug_blocker(DeviceState *dev, Error *reason)

+{

+ dev->unplug_blockers = g_slist_prepend(dev->unplug_blockers, reason);

+}

+

+void qdev_del_unplug_blocker(DeviceState *dev, Error *reason)

+{

+ dev->unplug_blockers = g_slist_remove(dev->unplug_blockers, reason);

+}

+

+bool qdev_unplug_blocked(DeviceState *dev, Error **errp)

+{

+ ERRP_GUARD();

+

+ if (dev->unplug_blockers) {

+ error_propagate(errp, error_copy(dev->unplug_blockers->data));

+ return true;

+ }

+

+ return false;

+}

+

static bool device_get_realized(Object *obj, Error **errp)

{

DeviceState *dev = DEVICE(obj);

@@ -XXX,XX +XXX,XX @@ static void device_finalize(Object *obj)

DeviceState *dev = DEVICE(obj);

+ g_assert(!dev->unplug_blockers);

+

QLIST_FOREACH_SAFE(ngl, &dev->gpios, node, next) {

QLIST_REMOVE(ngl, node);

qemu_free_irqs(ngl->in, ngl->num_in);

diff --git a/softmmu/qdev-monitor.c b/softmmu/qdev-monitor.c

index XXXXXXX..XXXXXXX 100644

--- a/softmmu/qdev-monitor.c

+++ b/softmmu/qdev-monitor.c

@@ -XXX,XX +XXX,XX @@ void qdev_unplug(DeviceState *dev, Error **errp)

HotplugHandlerClass *hdc;

Error *local_err = NULL;

+ if (qdev_unplug_blocked(dev, errp)) {

+ return;

+ }

+

if (dev->parent_bus && !qbus_is_hotpluggable(dev->parent_bus)) {

error_setg(errp, QERR_BUS_NO_HOTPLUG, dev->parent_bus->name);

return;

--

2.36.1

From: Jagannathan Raman <jag.raman@oracle.com>

Allow hotplugging of PCI(e) devices to remote machine

Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>

Signed-off-by: John G Johnson <john.g.johnson@oracle.com>

Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>

Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>

Message-id: d1e6cfa0afb528ad343758f9b1d918be0175c5e5.1655151679.git.jag.raman@oracle.com

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

---

hw/remote/machine.c | 10 ++++++++++

1 file changed, 10 insertions(+)

diff --git a/hw/remote/machine.c b/hw/remote/machine.c

index XXXXXXX..XXXXXXX 100644

--- a/hw/remote/machine.c

+++ b/hw/remote/machine.c

@@ -XXX,XX +XXX,XX @@

#include "qapi/error.h"

#include "hw/pci/pci_host.h"

#include "hw/remote/iohub.h"

+#include "hw/qdev-core.h"

static void remote_machine_init(MachineState *machine)

{

@@ -XXX,XX +XXX,XX @@ static void remote_machine_init(MachineState *machine)

pci_bus_irqs(pci_host->bus, remote_iohub_set_irq, remote_iohub_map_irq,

&s->iohub, REMOTE_IOHUB_NB_PIRQS);

+

+ qbus_set_hotplug_handler(BUS(pci_host->bus), OBJECT(s));

}

static void remote_machine_class_init(ObjectClass *oc, void *data)

{

MachineClass *mc = MACHINE_CLASS(oc);

+ HotplugHandlerClass *hc = HOTPLUG_HANDLER_CLASS(oc);

mc->init = remote_machine_init;

mc->desc = "Experimental remote machine";

+

+ hc->unplug = qdev_simple_device_unplug_cb;

}

static const TypeInfo remote_machine = {

@@ -XXX,XX +XXX,XX @@ static const TypeInfo remote_machine = {

.parent = TYPE_MACHINE,

.instance_size = sizeof(RemoteMachineState),

.class_init = remote_machine_class_init,

+ .interfaces = (InterfaceInfo[]) {

+ { TYPE_HOTPLUG_HANDLER },

+ { }

+ }

};

static void remote_machine_register_types(void)

--

2.36.1

From: Jagannathan Raman <jag.raman@oracle.com>

Add vfio-user to x-remote machine. It is a boolean, which indicates if

the machine supports vfio-user protocol. The machine configures the bus

differently vfio-user and multiprocess protocols, so this property

informs it on how to configure the bus.

This property should be short lived. Once vfio-user fully replaces

multiprocess, this property could be removed.

Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>

Signed-off-by: John G Johnson <john.g.johnson@oracle.com>

Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>

Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>

Message-id: 5d51a152a419cbda35d070b8e49b772b60a7230a.1655151679.git.jag.raman@oracle.com

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

---

include/hw/remote/machine.h | 2 ++

hw/remote/machine.c | 23 +++++++++++++++++++++++

2 files changed, 25 insertions(+)

diff --git a/include/hw/remote/machine.h b/include/hw/remote/machine.h

index XXXXXXX..XXXXXXX 100644

--- a/include/hw/remote/machine.h

+++ b/include/hw/remote/machine.h

@@ -XXX,XX +XXX,XX @@ struct RemoteMachineState {

RemotePCIHost *host;

RemoteIOHubState iohub;

+

+ bool vfio_user;

};

/* Used to pass to co-routine device and ioc. */

diff --git a/hw/remote/machine.c b/hw/remote/machine.c

index XXXXXXX..XXXXXXX 100644

--- a/hw/remote/machine.c

+++ b/hw/remote/machine.c

@@ -XXX,XX +XXX,XX @@ static void remote_machine_init(MachineState *machine)

qbus_set_hotplug_handler(BUS(pci_host->bus), OBJECT(s));

}

+static bool remote_machine_get_vfio_user(Object *obj, Error **errp)

+{

+ RemoteMachineState *s = REMOTE_MACHINE(obj);

+

+ return s->vfio_user;

+}

+

+static void remote_machine_set_vfio_user(Object *obj, bool value, Error **errp)

+{

+ RemoteMachineState *s = REMOTE_MACHINE(obj);

+

+ if (phase_check(PHASE_MACHINE_CREATED)) {

+ error_setg(errp, "Error enabling vfio-user - machine already created");

+ return;

+ }

+

+ s->vfio_user = value;

+}

+

static void remote_machine_class_init(ObjectClass *oc, void *data)

{

MachineClass *mc = MACHINE_CLASS(oc);

@@ -XXX,XX +XXX,XX @@ static void remote_machine_class_init(ObjectClass *oc, void *data)

mc->desc = "Experimental remote machine";

hc->unplug = qdev_simple_device_unplug_cb;

+

+ object_class_property_add_bool(oc, "vfio-user",

+ remote_machine_get_vfio_user,

+ remote_machine_set_vfio_user);

}

static const TypeInfo remote_machine = {

--

2.36.1

From: Jagannathan Raman <jag.raman@oracle.com>

create a context with the vfio-user library to run a PCI device

Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>

Signed-off-by: John G Johnson <john.g.johnson@oracle.com>

Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>

Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>

Message-id: a452871ac8c812ff96fc4f0ce6037f4769953fab.1655151679.git.jag.raman@oracle.com

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

---

hw/remote/vfio-user-obj.c | 82 +++++++++++++++++++++++++++++++++++++++

1 file changed, 82 insertions(+)

diff --git a/hw/remote/vfio-user-obj.c b/hw/remote/vfio-user-obj.c

index XXXXXXX..XXXXXXX 100644

--- a/hw/remote/vfio-user-obj.c

+++ b/hw/remote/vfio-user-obj.c

@@ -XXX,XX +XXX,XX @@

#include "hw/remote/machine.h"

#include "qapi/error.h"

#include "qapi/qapi-visit-sockets.h"

+#include "qemu/notify.h"

+#include "sysemu/sysemu.h"

+#include "libvfio-user.h"

#define TYPE_VFU_OBJECT "x-vfio-user-server"

OBJECT_DECLARE_TYPE(VfuObject, VfuObjectClass, VFU_OBJECT)

@@ -XXX,XX +XXX,XX @@ struct VfuObject {

char *device;

Error *err;

+

+ Notifier machine_done;

+

+ vfu_ctx_t *vfu_ctx;

};

+static void vfu_object_init_ctx(VfuObject *o, Error **errp);

+

static bool vfu_object_auto_shutdown(void)

{

bool auto_shutdown = true;

@@ -XXX,XX +XXX,XX @@ static void vfu_object_set_socket(Object *obj, Visitor *v, const char *name,

{

VfuObject *o = VFU_OBJECT(obj);

+ if (o->vfu_ctx) {

+ error_setg(errp, "vfu: Unable to set socket property - server busy");

+ return;

+ }

+

qapi_free_SocketAddress(o->socket);

o->socket = NULL;

@@ -XXX,XX +XXX,XX @@ static void vfu_object_set_socket(Object *obj, Visitor *v, const char *name,

}

trace_vfu_prop("socket", o->socket->u.q_unix.path);

+

+ vfu_object_init_ctx(o, errp);

}

static void vfu_object_set_device(Object *obj, const char *str, Error **errp)

{

VfuObject *o = VFU_OBJECT(obj);

+ if (o->vfu_ctx) {

+ error_setg(errp, "vfu: Unable to set device property - server busy");

+ return;

+ }

+

g_free(o->device);

o->device = g_strdup(str);

trace_vfu_prop("device", str);

+

+ vfu_object_init_ctx(o, errp);

+}

+

+/*

+ * TYPE_VFU_OBJECT depends on the availability of the 'socket' and 'device'

+ * properties. It also depends on devices instantiated in QEMU. These

+ * dependencies are not available during the instance_init phase of this

+ * object's life-cycle. As such, the server is initialized after the

+ * machine is setup. machine_init_done_notifier notifies TYPE_VFU_OBJECT

+ * when the machine is setup, and the dependencies are available.