qemu: Process RDMA GID state change event

This event is emitted on the monitor when a GID table in pvrdma device
is modified and the change needs to be propagate to the backend RDMA
device's GID table.

The control over the RDMA device's GID table is done by updating the
device's Ethernet function addresses.
Usually the first GID entry is determine by the MAC address, the second
by the first IPv6 address and the third by the IPv4 address. Other
entries can be added by adding more IP addresses. The opposite is the
same, i.e. whenever an address is removed, the corresponding GID entry
is removed.

The process is done by the network and RDMA stacks. Whenever an address
is added the ib_core driver is notified and calls the device driver's
add_gid function which in turn update the device.

To support this in pvrdma device we need to hook into the create_bind
and destroy_bind HW commands triggered by pvrdma driver in guest.
Whenever a changed is made to the pvrdma device's GID table a special
QMP messages is sent to be processed by libvirt to update the address of
the backend Ethernet device.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: Michal Privoznik <mprivozn@redhat.com>
This commit is contained in:
Yuval Shaia 2018-12-24 12:15:12 +02:00 committed by Michal Privoznik
parent 45b439c3af
commit ed357cef18
7 changed files with 190 additions and 0 deletions

View File

@ -13605,6 +13605,9 @@ qemuProcessEventFree(struct qemuProcessEvent *event)
case QEMU_PROCESS_EVENT_GUESTPANIC:
qemuMonitorEventPanicInfoFree(event->data);
break;
case QEMU_PROCESS_EVENT_RDMA_GID_STATUS_CHANGED:
qemuMonitorEventRdmaGidStatusFree(event->data);
break;
case QEMU_PROCESS_EVENT_WATCHDOG:
case QEMU_PROCESS_EVENT_DEVICE_DELETED:
case QEMU_PROCESS_EVENT_NIC_RX_FILTER_CHANGED:

View File

@ -490,6 +490,7 @@ typedef enum {
QEMU_PROCESS_EVENT_BLOCK_JOB,
QEMU_PROCESS_EVENT_MONITOR_EOF,
QEMU_PROCESS_EVENT_PR_DISCONNECT,
QEMU_PROCESS_EVENT_RDMA_GID_STATUS_CHANGED,
QEMU_PROCESS_EVENT_LAST
} qemuProcessEventType;

View File

@ -4792,6 +4792,50 @@ processPRDisconnectEvent(virDomainObjPtr vm)
}
static void
processRdmaGidStatusChangedEvent(virDomainObjPtr vm,
qemuMonitorRdmaGidStatusPtr info)
{
unsigned int prefix_len;
virSocketAddr addr;
VIR_AUTOFREE(char *) addrStr = NULL;
int rc;
if (!virDomainObjIsActive(vm))
return;
VIR_DEBUG("netdev=%s, gid_status=%d, subnet_prefix=0x%llx, interface_id=0x%llx",
info->netdev, info->gid_status, info->subnet_prefix,
info->interface_id);
if (info->subnet_prefix) {
uint32_t ipv6[4] = {0};
prefix_len = 64;
memcpy(&ipv6[0], &info->subnet_prefix, sizeof(info->subnet_prefix));
memcpy(&ipv6[2], &info->interface_id, sizeof(info->interface_id));
virSocketAddrSetIPv6AddrNetOrder(&addr, ipv6);
} else {
prefix_len = 24;
virSocketAddrSetIPv4AddrNetOrder(&addr, info->interface_id >> 32);
}
if (!(addrStr = virSocketAddrFormat(&addr)))
return;
if (info->gid_status) {
VIR_DEBUG("Adding %s to %s", addrStr, info->netdev);
rc = virNetDevIPAddrAdd(info->netdev, &addr, NULL, prefix_len);
} else {
VIR_DEBUG("Removing %s from %s", addrStr, info->netdev);
rc = virNetDevIPAddrDel(info->netdev, &addr, prefix_len);
}
if (rc < 0)
VIR_WARN("Fail to update address %s to %s", addrStr, info->netdev);
}
static void qemuProcessEventHandler(void *data, void *opaque)
{
struct qemuProcessEvent *processEvent = data;
@ -4832,6 +4876,9 @@ static void qemuProcessEventHandler(void *data, void *opaque)
case QEMU_PROCESS_EVENT_PR_DISCONNECT:
processPRDisconnectEvent(vm);
break;
case QEMU_PROCESS_EVENT_RDMA_GID_STATUS_CHANGED:
processRdmaGidStatusChangedEvent(vm, processEvent->data);
break;
case QEMU_PROCESS_EVENT_LAST:
break;
}

View File

@ -1684,6 +1684,24 @@ qemuMonitorEmitPRManagerStatusChanged(qemuMonitorPtr mon,
}
int
qemuMonitorEmitRdmaGidStatusChanged(qemuMonitorPtr mon,
const char *netdev,
bool gid_status,
uint64_t subnet_prefix,
uint64_t interface_id)
{
int ret = -1;
VIR_DEBUG("netdev=%s, gid_status=%d, subnet_prefix=0x%lx, interface_id=0x%lx",
netdev, gid_status, subnet_prefix, interface_id);
QEMU_MONITOR_CALLBACK(mon, ret, domainRdmaGidStatusChanged, mon->vm,
netdev, gid_status, subnet_prefix, interface_id);
return ret;
}
int
qemuMonitorSetCapabilities(qemuMonitorPtr mon)
{
@ -4315,6 +4333,17 @@ qemuMonitorEventPanicInfoFree(qemuMonitorEventPanicInfoPtr info)
}
void
qemuMonitorEventRdmaGidStatusFree(qemuMonitorRdmaGidStatusPtr info)
{
if (!info)
return;
VIR_FREE(info->netdev);
VIR_FREE(info);
}
int
qemuMonitorSetWatchdogAction(qemuMonitorPtr mon,
const char *action)

View File

@ -106,8 +106,20 @@ struct _qemuMonitorEventPanicInfo {
} data;
};
typedef struct _qemuMonitorRdmaGidStatus qemuMonitorRdmaGidStatus;
typedef qemuMonitorRdmaGidStatus *qemuMonitorRdmaGidStatusPtr;
struct _qemuMonitorRdmaGidStatus {
char *netdev;
bool gid_status;
unsigned long long subnet_prefix;
unsigned long long interface_id;
};
char *qemuMonitorGuestPanicEventInfoFormatMsg(qemuMonitorEventPanicInfoPtr info);
void qemuMonitorEventPanicInfoFree(qemuMonitorEventPanicInfoPtr info);
void qemuMonitorEventRdmaGidStatusFree(qemuMonitorRdmaGidStatusPtr info);
typedef void (*qemuMonitorDestroyCallback)(qemuMonitorPtr mon,
virDomainObjPtr vm,
@ -278,6 +290,14 @@ typedef int (*qemuMonitorDomainPRManagerStatusChangedCallback)(qemuMonitorPtr mo
bool connected,
void *opaque);
typedef int (*qemuMonitorDomainRdmaGidStatusChangedCallback)(qemuMonitorPtr mon,
virDomainObjPtr vm,
const char *netdev,
bool gid_status,
uint64_t subnet_prefix,
uint64_t interface_id,
void *opaque);
typedef struct _qemuMonitorCallbacks qemuMonitorCallbacks;
typedef qemuMonitorCallbacks *qemuMonitorCallbacksPtr;
struct _qemuMonitorCallbacks {
@ -311,6 +331,7 @@ struct _qemuMonitorCallbacks {
qemuMonitorDomainBlockThresholdCallback domainBlockThreshold;
qemuMonitorDomainDumpCompletedCallback domainDumpCompleted;
qemuMonitorDomainPRManagerStatusChangedCallback domainPRManagerStatusChanged;
qemuMonitorDomainRdmaGidStatusChangedCallback domainRdmaGidStatusChanged;
};
char *qemuMonitorEscapeArg(const char *in);
@ -445,6 +466,10 @@ int qemuMonitorEmitPRManagerStatusChanged(qemuMonitorPtr mon,
const char *prManager,
bool connected);
int qemuMonitorEmitRdmaGidStatusChanged(qemuMonitorPtr mon, const char *netdev,
bool gid_status, uint64_t subnet_prefix,
uint64_t interface_id);
int qemuMonitorStartCPUs(qemuMonitorPtr mon);
int qemuMonitorStopCPUs(qemuMonitorPtr mon);

View File

@ -89,6 +89,7 @@ static void qemuMonitorJSONHandleAcpiOstInfo(qemuMonitorPtr mon, virJSONValuePtr
static void qemuMonitorJSONHandleBlockThreshold(qemuMonitorPtr mon, virJSONValuePtr data);
static void qemuMonitorJSONHandleDumpCompleted(qemuMonitorPtr mon, virJSONValuePtr data);
static void qemuMonitorJSONHandlePRManagerStatusChanged(qemuMonitorPtr mon, virJSONValuePtr data);
static void qemuMonitorJSONHandleRdmaGidStatusChanged(qemuMonitorPtr mon, virJSONValuePtr data);
typedef struct {
const char *type;
@ -112,6 +113,7 @@ static qemuEventHandler eventHandlers[] = {
{ "NIC_RX_FILTER_CHANGED", qemuMonitorJSONHandleNicRxFilterChanged, },
{ "POWERDOWN", qemuMonitorJSONHandlePowerdown, },
{ "PR_MANAGER_STATUS_CHANGED", qemuMonitorJSONHandlePRManagerStatusChanged, },
{ "RDMA_GID_STATUS_CHANGED", qemuMonitorJSONHandleRdmaGidStatusChanged, },
{ "RESET", qemuMonitorJSONHandleReset, },
{ "RESUME", qemuMonitorJSONHandleResume, },
{ "RTC_CHANGE", qemuMonitorJSONHandleRTCChange, },
@ -1349,6 +1351,40 @@ static void qemuMonitorJSONHandlePRManagerStatusChanged(qemuMonitorPtr mon,
}
static void qemuMonitorJSONHandleRdmaGidStatusChanged(qemuMonitorPtr mon,
virJSONValuePtr data)
{
const char *netdev;
bool gid_status;
unsigned long long subnet_prefix, interface_id;
if (!(netdev = virJSONValueObjectGetString(data, "netdev"))) {
VIR_WARN("missing netdev in GID_STATUS_CHANGED event");
return;
}
if (virJSONValueObjectGetBoolean(data, "gid-status", &gid_status)) {
VIR_WARN("missing gid-status in GID_STATUS_CHANGED event");
return;
}
if (virJSONValueObjectGetNumberUlong(data, "subnet-prefix",
&subnet_prefix)) {
VIR_WARN("missing subnet-prefix in GID_STATUS_CHANGED event");
return;
}
if (virJSONValueObjectGetNumberUlong(data, "interface-id",
&interface_id)) {
VIR_WARN("missing interface-id in GID_STATUS_CHANGED event");
return;
}
qemuMonitorEmitRdmaGidStatusChanged(mon, netdev, gid_status, subnet_prefix,
interface_id);
}
int
qemuMonitorJSONHumanCommandWithFd(qemuMonitorPtr mon,
const char *cmd_str,

View File

@ -1715,6 +1715,54 @@ qemuProcessHandlePRManagerStatusChanged(qemuMonitorPtr mon ATTRIBUTE_UNUSED,
}
static int
qemuProcessHandleRdmaGidStatusChanged(qemuMonitorPtr mon ATTRIBUTE_UNUSED,
virDomainObjPtr vm,
const char *netdev,
bool gid_status,
uint64_t subnet_prefix,
uint64_t interface_id,
void *opaque)
{
virQEMUDriverPtr driver = opaque;
struct qemuProcessEvent *processEvent = NULL;
qemuMonitorRdmaGidStatusPtr info = NULL;
int ret = -1;
virObjectLock(vm);
VIR_DEBUG("netdev=%s,gid_status=%d,subnet_prefix=0x%lx,interface_id=0x%lx",
netdev, gid_status, subnet_prefix, interface_id);
if (VIR_ALLOC(info) < 0 ||
VIR_STRDUP(info->netdev, netdev) < 0)
goto cleanup;
info->gid_status = gid_status;
info->subnet_prefix = subnet_prefix;
info->interface_id = interface_id;
if (VIR_ALLOC(processEvent) < 0)
goto cleanup;
processEvent->eventType = QEMU_PROCESS_EVENT_RDMA_GID_STATUS_CHANGED;
processEvent->vm = virObjectRef(vm);
VIR_STEAL_PTR(processEvent->data, info);
if (virThreadPoolSendJob(driver->workerPool, 0, processEvent) < 0) {
qemuProcessEventFree(processEvent);
virObjectUnref(vm);
goto cleanup;
}
ret = 0;
cleanup:
qemuMonitorEventRdmaGidStatusFree(info);
virObjectUnlock(vm);
return ret;
}
static qemuMonitorCallbacks monitorCallbacks = {
.eofNotify = qemuProcessHandleMonitorEOF,
.errorNotify = qemuProcessHandleMonitorError,
@ -1744,6 +1792,7 @@ static qemuMonitorCallbacks monitorCallbacks = {
.domainBlockThreshold = qemuProcessHandleBlockThreshold,
.domainDumpCompleted = qemuProcessHandleDumpCompleted,
.domainPRManagerStatusChanged = qemuProcessHandlePRManagerStatusChanged,
.domainRdmaGidStatusChanged = qemuProcessHandleRdmaGidStatusChanged,
};
static void