qemu/include/net/net.h

224 lines
8.0 KiB
C
Raw Normal View History

#ifndef QEMU_NET_H
#define QEMU_NET_H
#include "qemu/queue.h"
#include "qemu-common.h"
#include "qapi/qmp/qdict.h"
#include "qemu/option.h"
#include "net/queue.h"
#include "migration/vmstate.h"
#include "qapi-types.h"
#define MAX_QUEUE_NUM 1024
/* Maximum GSO packet size (64k) plus plenty of room for
* the ethernet and virtio_net headers
*/
#define NET_BUFSIZE (4096 + 65536)
struct MACAddr {
uint8_t a[6];
};
/* qdev nic properties */
typedef struct NICPeers {
NetClientState *ncs[MAX_QUEUE_NUM];
int32_t queues;
} NICPeers;
typedef struct NICConf {
MACAddr macaddr;
NICPeers peers;
int32_t bootindex;
} NICConf;
#define DEFINE_NIC_PROPERTIES(_state, _conf) \
DEFINE_PROP_MACADDR("mac", _state, _conf.macaddr), \
DEFINE_PROP_VLAN("vlan", _state, _conf.peers), \
DEFINE_PROP_NETDEV("netdev", _state, _conf.peers)
/* Net clients */
typedef void (NetPoll)(NetClientState *, bool enable);
typedef int (NetCanReceive)(NetClientState *);
typedef ssize_t (NetReceive)(NetClientState *, const uint8_t *, size_t);
typedef ssize_t (NetReceiveIOV)(NetClientState *, const struct iovec *, int);
typedef void (NetCleanup) (NetClientState *);
typedef void (LinkStatusChanged)(NetClientState *);
typedef void (NetClientDestructor)(NetClientState *);
net: add support of mac-programming over macvtap in QEMU side Currently macvtap based macvlan device is working in promiscuous mode, we want to implement mac-programming over macvtap through Libvirt for better performance. Design: QEMU notifies Libvirt when rx-filter config is changed in guest, then Libvirt query the rx-filter information by a monitor command, and sync the change to macvtap device. Related rx-filter config of the nic contains main mac, rx-mode items and vlan table. This patch adds a QMP event to notify management of rx-filter change, and adds a monitor command for management to query rx-filter information. Test: If we repeatedly add/remove vlan, and change macaddr of vlan interfaces in guest by a loop script. Result: The events will flood the QMP client(management), management takes too much resource to process the events. Event_throttle API (set rate to 1 ms) can avoid the events to flood QMP client, but it could cause an unexpected delay (~1ms), guests guests normally expect rx-filter updates immediately. So we use a flag for each nic to avoid events flooding, the event is emitted once until the query command is executed. The flag implementation could not introduce unexpected delay. There maybe exist an uncontrollable delay if we let Libvirt do the real change, guests normally expect rx-filter updates immediately. But it's another separate issue, we can investigate it when the work in Libvirt side is done. Michael S. Tsirkin: tweaked to enable events on start Michael S. Tsirkin: fixed not to crash when no id Michael S. Tsirkin: fold in patch: "additional fixes for mac-programming feature" Amos Kong: always notify QMP client if mactable is changed Amos Kong: return NULL list if no net client supports rx-filter query Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Amos Kong <akong@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2013-06-14 11:45:52 +04:00
typedef RxFilterInfo *(QueryRxFilter)(NetClientState *);
typedef bool (HasUfo)(NetClientState *);
typedef bool (HasVnetHdr)(NetClientState *);
typedef bool (HasVnetHdrLen)(NetClientState *, int);
typedef void (UsingVnetHdr)(NetClientState *, bool);
typedef void (SetOffload)(NetClientState *, int, int, int, int, int);
typedef void (SetVnetHdrLen)(NetClientState *, int);
typedef int (SetVnetLE)(NetClientState *, bool);
typedef int (SetVnetBE)(NetClientState *, bool);
typedef struct NetClientInfo {
NetClientOptionsKind type;
size_t size;
NetReceive *receive;
NetReceive *receive_raw;
NetReceiveIOV *receive_iov;
NetCanReceive *can_receive;
NetCleanup *cleanup;
LinkStatusChanged *link_status_changed;
net: add support of mac-programming over macvtap in QEMU side Currently macvtap based macvlan device is working in promiscuous mode, we want to implement mac-programming over macvtap through Libvirt for better performance. Design: QEMU notifies Libvirt when rx-filter config is changed in guest, then Libvirt query the rx-filter information by a monitor command, and sync the change to macvtap device. Related rx-filter config of the nic contains main mac, rx-mode items and vlan table. This patch adds a QMP event to notify management of rx-filter change, and adds a monitor command for management to query rx-filter information. Test: If we repeatedly add/remove vlan, and change macaddr of vlan interfaces in guest by a loop script. Result: The events will flood the QMP client(management), management takes too much resource to process the events. Event_throttle API (set rate to 1 ms) can avoid the events to flood QMP client, but it could cause an unexpected delay (~1ms), guests guests normally expect rx-filter updates immediately. So we use a flag for each nic to avoid events flooding, the event is emitted once until the query command is executed. The flag implementation could not introduce unexpected delay. There maybe exist an uncontrollable delay if we let Libvirt do the real change, guests normally expect rx-filter updates immediately. But it's another separate issue, we can investigate it when the work in Libvirt side is done. Michael S. Tsirkin: tweaked to enable events on start Michael S. Tsirkin: fixed not to crash when no id Michael S. Tsirkin: fold in patch: "additional fixes for mac-programming feature" Amos Kong: always notify QMP client if mactable is changed Amos Kong: return NULL list if no net client supports rx-filter query Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Amos Kong <akong@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2013-06-14 11:45:52 +04:00
QueryRxFilter *query_rx_filter;
NetPoll *poll;
HasUfo *has_ufo;
HasVnetHdr *has_vnet_hdr;
HasVnetHdrLen *has_vnet_hdr_len;
UsingVnetHdr *using_vnet_hdr;
SetOffload *set_offload;
SetVnetHdrLen *set_vnet_hdr_len;
SetVnetLE *set_vnet_le;
SetVnetBE *set_vnet_be;
} NetClientInfo;
struct NetClientState {
NetClientInfo *info;
int link_down;
QTAILQ_ENTRY(NetClientState) next;
NetClientState *peer;
NetQueue *incoming_queue;
char *model;
char *name;
char info_str[256];
unsigned receive_disabled : 1;
NetClientDestructor *destructor;
unsigned int queue_index;
net: add support of mac-programming over macvtap in QEMU side Currently macvtap based macvlan device is working in promiscuous mode, we want to implement mac-programming over macvtap through Libvirt for better performance. Design: QEMU notifies Libvirt when rx-filter config is changed in guest, then Libvirt query the rx-filter information by a monitor command, and sync the change to macvtap device. Related rx-filter config of the nic contains main mac, rx-mode items and vlan table. This patch adds a QMP event to notify management of rx-filter change, and adds a monitor command for management to query rx-filter information. Test: If we repeatedly add/remove vlan, and change macaddr of vlan interfaces in guest by a loop script. Result: The events will flood the QMP client(management), management takes too much resource to process the events. Event_throttle API (set rate to 1 ms) can avoid the events to flood QMP client, but it could cause an unexpected delay (~1ms), guests guests normally expect rx-filter updates immediately. So we use a flag for each nic to avoid events flooding, the event is emitted once until the query command is executed. The flag implementation could not introduce unexpected delay. There maybe exist an uncontrollable delay if we let Libvirt do the real change, guests normally expect rx-filter updates immediately. But it's another separate issue, we can investigate it when the work in Libvirt side is done. Michael S. Tsirkin: tweaked to enable events on start Michael S. Tsirkin: fixed not to crash when no id Michael S. Tsirkin: fold in patch: "additional fixes for mac-programming feature" Amos Kong: always notify QMP client if mactable is changed Amos Kong: return NULL list if no net client supports rx-filter query Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Amos Kong <akong@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2013-06-14 11:45:52 +04:00
unsigned rxfilter_notify_enabled:1;
QTAILQ_HEAD(NetFilterHead, NetFilterState) filters;
};
typedef struct NICState {
NetClientState *ncs;
NICConf *conf;
void *opaque;
bool peer_deleted;
} NICState;
char *qemu_mac_strdup_printf(const uint8_t *macaddr);
NetClientState *qemu_find_netdev(const char *id);
int qemu_find_net_clients_except(const char *id, NetClientState **ncs,
NetClientOptionsKind type, int max);
NetClientState *qemu_new_net_client(NetClientInfo *info,
NetClientState *peer,
const char *model,
const char *name);
NICState *qemu_new_nic(NetClientInfo *info,
NICConf *conf,
const char *model,
const char *name,
void *opaque);
void qemu_del_nic(NICState *nic);
NetClientState *qemu_get_subqueue(NICState *nic, int queue_index);
NetClientState *qemu_get_queue(NICState *nic);
NICState *qemu_get_nic(NetClientState *nc);
void *qemu_get_nic_opaque(NetClientState *nc);
void qemu_del_net_client(NetClientState *nc);
NetClientState *qemu_find_vlan_client_by_name(Monitor *mon, int vlan_id,
const char *client_str);
typedef void (*qemu_nic_foreach)(NICState *nic, void *opaque);
void qemu_foreach_nic(qemu_nic_foreach func, void *opaque);
int qemu_can_send_packet(NetClientState *nc);
ssize_t qemu_sendv_packet(NetClientState *nc, const struct iovec *iov,
int iovcnt);
ssize_t qemu_sendv_packet_async(NetClientState *nc, const struct iovec *iov,
int iovcnt, NetPacketSent *sent_cb);
void qemu_send_packet(NetClientState *nc, const uint8_t *buf, int size);
ssize_t qemu_send_packet_raw(NetClientState *nc, const uint8_t *buf, int size);
ssize_t qemu_send_packet_async(NetClientState *nc, const uint8_t *buf,
int size, NetPacketSent *sent_cb);
void qemu_purge_queued_packets(NetClientState *nc);
void qemu_flush_queued_packets(NetClientState *nc);
void qemu_format_nic_info_str(NetClientState *nc, uint8_t macaddr[6]);
bool qemu_has_ufo(NetClientState *nc);
bool qemu_has_vnet_hdr(NetClientState *nc);
bool qemu_has_vnet_hdr_len(NetClientState *nc, int len);
void qemu_using_vnet_hdr(NetClientState *nc, bool enable);
void qemu_set_offload(NetClientState *nc, int csum, int tso4, int tso6,
int ecn, int ufo);
void qemu_set_vnet_hdr_len(NetClientState *nc, int len);
int qemu_set_vnet_le(NetClientState *nc, bool is_le);
int qemu_set_vnet_be(NetClientState *nc, bool is_be);
void qemu_macaddr_default_if_unset(MACAddr *macaddr);
int qemu_show_nic_models(const char *arg, const char *const *models);
void qemu_check_nic_model(NICInfo *nd, const char *model);
int qemu_find_nic_model(NICInfo *nd, const char * const *models,
const char *default_model);
ssize_t qemu_deliver_packet_iov(NetClientState *sender,
unsigned flags,
const struct iovec *iov,
int iovcnt,
void *opaque);
void print_net_client(Monitor *mon, NetClientState *nc);
void hmp_info_network(Monitor *mon, const QDict *qdict);
/* NIC info */
#define MAX_NICS 8
struct NICInfo {
MACAddr macaddr;
char *model;
char *name;
char *devaddr;
NetClientState *netdev;
int used; /* is this slot in nd_table[] being used? */
int instantiated; /* does this NICInfo correspond to an instantiated NIC? */
int nvectors;
};
extern int nb_nics;
extern NICInfo nd_table[MAX_NICS];
extern int default_net;
extern const char *host_net_devices[];
/* from net.c */
extern const char *legacy_tftp_prefix;
extern const char *legacy_bootp_filename;
int net_client_init(QemuOpts *opts, int is_netdev, Error **errp);
int net_client_parse(QemuOptsList *opts_list, const char *str);
int net_init_clients(void);
void net_check_clients(void);
void net_cleanup(void);
void hmp_host_net_add(Monitor *mon, const QDict *qdict);
void hmp_host_net_remove(Monitor *mon, const QDict *qdict);
void netdev_add(QemuOpts *opts, Error **errp);
qmp: Wean off qerror_report() The traditional QMP command handler interface int qmp_FOO(Monitor *mon, const QDict *params, QObject **ret_data); doesn't provide for returning an Error object. Instead, the handler is expected to stash it in the monitor with qerror_report(). When we rebased QMP on top of QAPI, we didn't change this interface. Instead, commit 776574d introduced "middle mode" as a temporary aid for converting existing QMP commands to QAPI one by one. More than three years later, we're still using it. Middle mode has two effects: * Instead of the native input marshallers static void qmp_marshal_input_FOO(QDict *, QObject **, Error **) it generates input marshallers conforming to the traditional QMP command handler interface. * It suppresses generation of code to register them with qmp_register_command() This permits giving them internal linkage. As long as we need qmp-commands.hx, we can't use the registry behind qmp_register_command(), so the latter has to stay for now. The former has to go to get rid of qerror_report(). Changing all QMP commands to fit the QAPI mold in one go was impractical back when we started, but by now there are just a few stragglers left: do_qmp_capabilities(), qmp_qom_set(), qmp_qom_get(), qmp_object_add(), qmp_netdev_add(), do_device_add(). Switch middle mode to generate native input marshallers, and adapt the stragglers. Simplifies both the monitor code and the stragglers. Rename do_qmp_capabilities() to qmp_capabilities(), and do_device_add() to qmp_device_add, because that's how QMP command handlers are named today. Signed-off-by: Markus Armbruster <armbru@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Luiz Capitulino <lcapitulino@redhat.com>
2015-03-13 19:25:50 +03:00
void qmp_netdev_add(QDict *qdict, QObject **ret, Error **errp);
int net_hub_id_for_client(NetClientState *nc, int *id);
NetClientState *net_hub_port_find(int hub_id);
#define DEFAULT_NETWORK_SCRIPT "/etc/qemu-ifup"
#define DEFAULT_NETWORK_DOWN_SCRIPT "/etc/qemu-ifdown"
Add support for net bridge The most common use of -net tap is to connect a tap device to a bridge. This requires the use of a script and running qemu as root in order to allocate a tap device to pass to the script. This model is great for portability and flexibility but it's incredibly difficult to eliminate the need to run qemu as root. The only really viable mechanism is to use tunctl to create a tap device, attach it to a bridge as root, and then hand that tap device to qemu. The problem with this mechanism is that it requires administrator intervention whenever a user wants to create a guest. By essentially writing a helper that implements the most common qemu-ifup script that can be safely given cap_net_admin, we can dramatically simplify things for non-privileged users. We still support existing -net tap options as a mechanism for advanced users and backwards compatibility. Currently, this is very Linux centric but there's really no reason why it couldn't be extended for other Unixes. A typical invocation would be similar to one of the following: qemu linux.img -net bridge -net nic,model=virtio qemu linux.img -net tap,helper="/usr/local/libexec/qemu-bridge-helper" -net nic,model=virtio qemu linux.img -netdev bridge,id=hn0 -device virtio-net-pci,netdev=hn0,id=nic1 qemu linux.img -netdev tap,helper="/usr/local/libexec/qemu-bridge-helper",id=hn0 -device virtio-net-pci,netdev=hn0,id=nic1 The default bridge that we attach to is br0. The thinking is that a distro could preconfigure such an interface to allow out-of-the-box bridged networking. Alternatively, if a user wants to use a different bridge, a typical invocation would be simliar to one of the following: qemu linux.img -net bridge,br=qemubr0 -net nic,model=virtio qemu linux.img -net tap,helper="/usr/local/libexec/qemu-bridge-helper --br=qemubr0" -net nic,model=virtio qemu linux.img -netdev bridge,br=qemubr0,id=hn0 -device virtio-net-pci,netdev=hn0,id=nic1 qemu linux.img -netdev tap,helper="/usr/local/libexec/qemu-bridge-helper --br=qemubr0",id=hn0 -device virtio-net-pci,netdev=hn0,id=nic1 Signed-off-by: Anthony Liguori <aliguori@us.ibm.com> Signed-off-by: Richa Marwaha <rmarwah@linux.vnet.ibm.com> Signed-off-by: Corey Bryant <coreyb@linux.vnet.ibm.com> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2012-01-26 18:42:27 +04:00
#define DEFAULT_BRIDGE_HELPER CONFIG_QEMU_HELPERDIR "/qemu-bridge-helper"
#define DEFAULT_BRIDGE_INTERFACE "br0"
void qdev_set_nic_properties(DeviceState *dev, NICInfo *nd);
#define POLYNOMIAL 0x04c11db6
unsigned compute_mcast_idx(const uint8_t *ep);
#define vmstate_offset_macaddr(_state, _field) \
vmstate_offset_array(_state, _field.a, uint8_t, \
sizeof(typeof_field(_state, _field)))
#define VMSTATE_MACADDR(_field, _state) { \
.name = (stringify(_field)), \
.size = sizeof(MACAddr), \
.info = &vmstate_info_buffer, \
.flags = VMS_BUFFER, \
.offset = vmstate_offset_macaddr(_state, _field), \
}
#endif