From: Maxim Levitsky <mlevitsk@redhat.com>
To: qemu-devel@nongnu.org
Cc: "Fam Zheng" <fam@euphon.net>,
"Daniel P. Berrangé" <berrange@redhat.com>,
"Eduardo Habkost" <ehabkost@redhat.com>,
"Michael S. Tsirkin" <mst@redhat.com>,
"Maxim Levitsky" <mlevitsk@redhat.com>,
"Stefan Hajnoczi" <stefanha@redhat.com>,
"Paolo Bonzini" <pbonzini@redhat.com>
Subject: [PATCH v5 4/9] device-core: use RCU for list of childs of a bus
Date: Sun, 13 Sep 2020 19:02:54 +0300 [thread overview]
Message-ID: <20200913160259.32145-5-mlevitsk@redhat.com> (raw)
In-Reply-To: <20200913160259.32145-1-mlevitsk@redhat.com>
This fixes the race between device emulation code that tries to find
a child device to dispatch the request to (e.g a scsi disk),
and hotplug of a new device to that bus.
Note that this doesn't convert all the readers of the list
but only these that might go over that list without BQL held.
This is a very small first step to make this code thread safe.
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
---
hw/core/bus.c | 28 ++++++++++++++++++----------
hw/core/qdev.c | 37 +++++++++++++++++++++++--------------
hw/scsi/scsi-bus.c | 17 ++++++++++++++---
hw/scsi/virtio-scsi.c | 6 +++++-
include/hw/qdev-core.h | 9 +++++++++
5 files changed, 69 insertions(+), 28 deletions(-)
diff --git a/hw/core/bus.c b/hw/core/bus.c
index 6b987b6946..385eb3ad5a 100644
--- a/hw/core/bus.c
+++ b/hw/core/bus.c
@@ -49,12 +49,14 @@ int qbus_walk_children(BusState *bus,
}
}
- QTAILQ_FOREACH(kid, &bus->children, sibling) {
- err = qdev_walk_children(kid->child,
- pre_devfn, pre_busfn,
- post_devfn, post_busfn, opaque);
- if (err < 0) {
- return err;
+ WITH_RCU_READ_LOCK_GUARD() {
+ QTAILQ_FOREACH_RCU(kid, &bus->children, sibling) {
+ err = qdev_walk_children(kid->child,
+ pre_devfn, pre_busfn,
+ post_devfn, post_busfn, opaque);
+ if (err < 0) {
+ return err;
+ }
}
}
@@ -90,9 +92,13 @@ static void bus_reset_child_foreach(Object *obj, ResettableChildCallback cb,
BusState *bus = BUS(obj);
BusChild *kid;
- QTAILQ_FOREACH(kid, &bus->children, sibling) {
+ rcu_read_lock();
+
+ QTAILQ_FOREACH_RCU(kid, &bus->children, sibling) {
cb(OBJECT(kid->child), opaque, type);
}
+
+ rcu_read_unlock();
}
static void qbus_init(BusState *bus, DeviceState *parent, const char *name)
@@ -194,9 +200,11 @@ static void bus_set_realized(Object *obj, bool value, Error **errp)
/* TODO: recursive realization */
} else if (!value && bus->realized) {
- QTAILQ_FOREACH(kid, &bus->children, sibling) {
- DeviceState *dev = kid->child;
- qdev_unrealize(dev);
+ WITH_RCU_READ_LOCK_GUARD() {
+ QTAILQ_FOREACH_RCU(kid, &bus->children, sibling) {
+ DeviceState *dev = kid->child;
+ qdev_unrealize(dev);
+ }
}
if (bc->unrealize) {
bc->unrealize(bus);
diff --git a/hw/core/qdev.c b/hw/core/qdev.c
index 96772a15bd..28e5fff5ed 100644
--- a/hw/core/qdev.c
+++ b/hw/core/qdev.c
@@ -51,6 +51,12 @@ const VMStateDescription *qdev_get_vmsd(DeviceState *dev)
return dc->vmsd;
}
+static void bus_free_bus_child(BusChild *kid)
+{
+ object_unref(OBJECT(kid->child));
+ g_free(kid);
+}
+
static void bus_remove_child(BusState *bus, DeviceState *child)
{
BusChild *kid;
@@ -60,15 +66,16 @@ static void bus_remove_child(BusState *bus, DeviceState *child)
char name[32];
snprintf(name, sizeof(name), "child[%d]", kid->index);
- QTAILQ_REMOVE(&bus->children, kid, sibling);
+ QTAILQ_REMOVE_RCU(&bus->children, kid, sibling);
bus->num_children--;
/* This gives back ownership of kid->child back to us. */
object_property_del(OBJECT(bus), name);
- object_unref(OBJECT(kid->child));
- g_free(kid);
- return;
+
+ /* free the bus kid, when it is safe to do so*/
+ call_rcu(kid, bus_free_bus_child, rcu);
+ break;
}
}
}
@@ -83,7 +90,7 @@ static void bus_add_child(BusState *bus, DeviceState *child)
kid->child = child;
object_ref(OBJECT(kid->child));
- QTAILQ_INSERT_HEAD(&bus->children, kid, sibling);
+ QTAILQ_INSERT_HEAD_RCU(&bus->children, kid, sibling);
/* This transfers ownership of kid->child to the property. */
snprintf(name, sizeof(name), "child[%d]", kid->index);
@@ -659,17 +666,19 @@ DeviceState *qdev_find_recursive(BusState *bus, const char *id)
DeviceState *ret;
BusState *child;
- QTAILQ_FOREACH(kid, &bus->children, sibling) {
- DeviceState *dev = kid->child;
+ WITH_RCU_READ_LOCK_GUARD() {
+ QTAILQ_FOREACH_RCU(kid, &bus->children, sibling) {
+ DeviceState *dev = kid->child;
- if (dev->id && strcmp(dev->id, id) == 0) {
- return dev;
- }
+ if (dev->id && strcmp(dev->id, id) == 0) {
+ return dev;
+ }
- QLIST_FOREACH(child, &dev->child_bus, sibling) {
- ret = qdev_find_recursive(child, id);
- if (ret) {
- return ret;
+ QLIST_FOREACH(child, &dev->child_bus, sibling) {
+ ret = qdev_find_recursive(child, id);
+ if (ret) {
+ return ret;
+ }
}
}
}
diff --git a/hw/scsi/scsi-bus.c b/hw/scsi/scsi-bus.c
index f8adfbc2a5..92d412b65c 100644
--- a/hw/scsi/scsi-bus.c
+++ b/hw/scsi/scsi-bus.c
@@ -400,7 +400,10 @@ static bool scsi_target_emulate_report_luns(SCSITargetReq *r)
id = r->req.dev->id;
found_lun0 = false;
n = 0;
- QTAILQ_FOREACH(kid, &r->req.bus->qbus.children, sibling) {
+
+ rcu_read_lock();
+
+ QTAILQ_FOREACH_RCU(kid, &r->req.bus->qbus.children, sibling) {
DeviceState *qdev = kid->child;
SCSIDevice *dev = SCSI_DEVICE(qdev);
@@ -421,7 +424,7 @@ static bool scsi_target_emulate_report_luns(SCSITargetReq *r)
memset(r->buf, 0, len);
stl_be_p(&r->buf[0], n);
i = found_lun0 ? 8 : 16;
- QTAILQ_FOREACH(kid, &r->req.bus->qbus.children, sibling) {
+ QTAILQ_FOREACH_RCU(kid, &r->req.bus->qbus.children, sibling) {
DeviceState *qdev = kid->child;
SCSIDevice *dev = SCSI_DEVICE(qdev);
@@ -430,6 +433,9 @@ static bool scsi_target_emulate_report_luns(SCSITargetReq *r)
i += 8;
}
}
+
+ rcu_read_unlock();
+
assert(i == n + 8);
r->len = len;
return true;
@@ -1572,12 +1578,15 @@ SCSIDevice *scsi_device_find(SCSIBus *bus, int channel, int id, int lun)
BusChild *kid;
SCSIDevice *target_dev = NULL;
- QTAILQ_FOREACH(kid, &bus->qbus.children, sibling) {
+ rcu_read_lock();
+
+ QTAILQ_FOREACH_RCU(kid, &bus->qbus.children, sibling) {
DeviceState *qdev = kid->child;
SCSIDevice *dev = SCSI_DEVICE(qdev);
if (dev->channel == channel && dev->id == id) {
if (dev->lun == lun) {
+ rcu_read_unlock();
return dev;
}
@@ -1591,6 +1600,8 @@ SCSIDevice *scsi_device_find(SCSIBus *bus, int channel, int id, int lun)
}
}
}
+
+ rcu_read_unlock();
return target_dev;
}
diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c
index 3a71ea7097..971afbb217 100644
--- a/hw/scsi/virtio-scsi.c
+++ b/hw/scsi/virtio-scsi.c
@@ -367,12 +367,16 @@ static int virtio_scsi_do_tmf(VirtIOSCSI *s, VirtIOSCSIReq *req)
case VIRTIO_SCSI_T_TMF_I_T_NEXUS_RESET:
target = req->req.tmf.lun[1];
s->resetting++;
- QTAILQ_FOREACH(kid, &s->bus.qbus.children, sibling) {
+
+ rcu_read_lock();
+ QTAILQ_FOREACH_RCU(kid, &s->bus.qbus.children, sibling) {
d = SCSI_DEVICE(kid->child);
if (d->channel == 0 && d->id == target) {
qdev_reset_all(&d->qdev);
}
}
+ rcu_read_unlock();
+
s->resetting--;
break;
diff --git a/include/hw/qdev-core.h b/include/hw/qdev-core.h
index e025ba9653..7f91c8ead4 100644
--- a/include/hw/qdev-core.h
+++ b/include/hw/qdev-core.h
@@ -3,6 +3,8 @@
#include "qemu/queue.h"
#include "qemu/bitmap.h"
+#include "qemu/rcu.h"
+#include "qemu/rcu_queue.h"
#include "qom/object.h"
#include "hw/hotplug.h"
#include "hw/resettable.h"
@@ -229,6 +231,7 @@ struct BusClass {
};
typedef struct BusChild {
+ struct rcu_head rcu;
DeviceState *child;
int index;
QTAILQ_ENTRY(BusChild) sibling;
@@ -249,6 +252,12 @@ struct BusState {
int max_index;
bool realized;
int num_children;
+
+ /*
+ * children is a RCU QTAILQ, thus readers must use RCU to access it,
+ * and writers must hold the big qemu lock
+ */
+
QTAILQ_HEAD(, BusChild) children;
QLIST_ENTRY(BusState) sibling;
ResettableState reset;
--
2.26.2
next prev parent reply other threads:[~2020-09-13 16:07 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-09-13 16:02 [PATCH v5 0/9] Fix scsi devices plug/unplug races w.r.t virtio-scsi iothread Maxim Levitsky
2020-09-13 16:02 ` [PATCH v5 1/9] scsi/scsi_bus: switch search direction in scsi_device_find Maxim Levitsky
2020-09-25 13:36 ` Paolo Bonzini
2020-09-13 16:02 ` [PATCH v5 2/9] rcu: Implement drain_call_rcu Maxim Levitsky
2020-09-13 16:02 ` [PATCH v5 3/9] device_core: use drain_call_rcu in in hmp_device_del/qmp_device_add Maxim Levitsky
2020-09-13 16:02 ` Maxim Levitsky [this message]
2020-09-13 16:02 ` [PATCH v5 5/9] device-core: use atomic_set on .realized property Maxim Levitsky
2020-09-13 16:02 ` [PATCH v5 6/9] scsi/scsi-bus: scsi_device_find: don't return unrealized devices Maxim Levitsky
2020-09-13 16:02 ` [PATCH v5 7/9] scsi/scsi_bus: Add scsi_device_get Maxim Levitsky
2020-09-13 16:02 ` [PATCH v5 8/9] virtio-scsi: use scsi_device_get Maxim Levitsky
2020-09-13 16:02 ` [PATCH v5 9/9] scsi/scsi_bus: fix races in REPORT LUNS Maxim Levitsky
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200913160259.32145-5-mlevitsk@redhat.com \
--to=mlevitsk@redhat.com \
--cc=berrange@redhat.com \
--cc=ehabkost@redhat.com \
--cc=fam@euphon.net \
--cc=mst@redhat.com \
--cc=pbonzini@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=stefanha@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).