qemu/include/net/net.h

268 lines
9.8 KiB
C
Raw Normal View History

#ifndef QEMU_NET_H
#define QEMU_NET_H
#include "qemu/queue.h"
#include "qapi/qapi-types-net.h"
#include "net/queue.h"
#include "hw/qdev-properties-system.h"
#define MAC_FMT "%02X:%02X:%02X:%02X:%02X:%02X"
#define MAC_ARG(x) ((uint8_t *)(x))[0], ((uint8_t *)(x))[1], \
((uint8_t *)(x))[2], ((uint8_t *)(x))[3], \
((uint8_t *)(x))[4], ((uint8_t *)(x))[5]
#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_NETDEV("netdev", _state, _conf.peers)
/* Net clients */
typedef void (NetPoll)(NetClientState *, bool enable);
typedef bool (NetCanReceive)(NetClientState *);
typedef int (NetStart)(NetClientState *);
typedef int (NetLoad)(NetClientState *);
typedef void (NetStop)(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 SocketReadState SocketReadState;
typedef void (SocketReadStateFinalize)(SocketReadState *rs);
typedef void (NetAnnounce)(NetClientState *);
typedef bool (SetSteeringEBPF)(NetClientState *, int);
typedef bool (NetCheckPeerType)(NetClientState *, ObjectClass *, Error **);
typedef struct NetClientInfo {
qapi: Change Netdev into a flat union This is a mostly-mechanical conversion that creates a new flat union 'Netdev' QAPI type that covers all the branches of the former 'NetClientOptions' simple union, where the branches are now listed in a new 'NetClientDriver' enum rather than generated from the simple union. The existence of a flat union has no change to the command line syntax accepted for new code, and will make it possible for a future patch to switch the QMP command to parse a boxed union for no change to valid QMP; but it does have some ripple effect on the C code when dealing with the new types. While making the conversion, note that the 'NetLegacy' type remains unchanged: it applies only to legacy command line options, and will not be ported to QMP, so it should remain a wrapper around a simple union; to avoid confusion, the type named 'NetClientOptions' is now gone, and we introduce 'NetLegacyOptions' in its place. Then, in the C code, we convert from NetLegacy to Netdev as soon as possible, so that the bulk of the net stack only has to deal with one QAPI type, not two. Note that since the old legacy code always rejected 'hubport', we can just omit that branch from the new 'NetLegacyOptions' simple union. Based on an idea originally by Zoltán Kővágó <DirtY.iCE.hu@gmail.com>: Message-Id: <01a527fbf1a5de880091f98cf011616a78adeeee.1441627176.git.DirtY.iCE.hu@gmail.com> although the sed script in that patch no longer applies due to other changes in the tree since then, and I also did some manual cleanups (such as fixing whitespace to keep checkpatch happy). Signed-off-by: Eric Blake <eblake@redhat.com> Message-Id: <1468468228-27827-13-git-send-email-eblake@redhat.com> Reviewed-by: Markus Armbruster <armbru@redhat.com> [Fixup from Eric squashed in] Signed-off-by: Markus Armbruster <armbru@redhat.com>
2016-07-14 06:50:23 +03:00
NetClientDriver type;
size_t size;
NetReceive *receive;
NetReceive *receive_raw;
NetReceiveIOV *receive_iov;
NetCanReceive *can_receive;
NetStart *start;
NetLoad *load;
NetStop *stop;
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;
NetAnnounce *announce;
SetSteeringEBPF *set_steering_ebpf;
NetCheckPeerType *check_peer_type;
} 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;
int vring_enable;
int vnet_hdr_len;
bool is_netdev;
bool do_not_pad; /* do not pad to the minimum ethernet frame length */
bool is_datapath;
QTAILQ_HEAD(, NetFilterState) filters;
};
typedef struct NICState {
NetClientState *ncs;
NICConf *conf;
void *opaque;
bool peer_deleted;
} NICState;
struct SocketReadState {
/* 0 = getting length, 1 = getting vnet header length, 2 = getting data */
int state;
/* This flag decide whether to read the vnet_hdr_len field */
bool vnet_hdr;
uint32_t index;
uint32_t packet_len;
uint32_t vnet_hdr_len;
uint8_t buf[NET_BUFSIZE];
SocketReadStateFinalize *finalize;
};
int net_fill_rstate(SocketReadState *rs, const uint8_t *buf, int size);
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,
qapi: Change Netdev into a flat union This is a mostly-mechanical conversion that creates a new flat union 'Netdev' QAPI type that covers all the branches of the former 'NetClientOptions' simple union, where the branches are now listed in a new 'NetClientDriver' enum rather than generated from the simple union. The existence of a flat union has no change to the command line syntax accepted for new code, and will make it possible for a future patch to switch the QMP command to parse a boxed union for no change to valid QMP; but it does have some ripple effect on the C code when dealing with the new types. While making the conversion, note that the 'NetLegacy' type remains unchanged: it applies only to legacy command line options, and will not be ported to QMP, so it should remain a wrapper around a simple union; to avoid confusion, the type named 'NetClientOptions' is now gone, and we introduce 'NetLegacyOptions' in its place. Then, in the C code, we convert from NetLegacy to Netdev as soon as possible, so that the bulk of the net stack only has to deal with one QAPI type, not two. Note that since the old legacy code always rejected 'hubport', we can just omit that branch from the new 'NetLegacyOptions' simple union. Based on an idea originally by Zoltán Kővágó <DirtY.iCE.hu@gmail.com>: Message-Id: <01a527fbf1a5de880091f98cf011616a78adeeee.1441627176.git.DirtY.iCE.hu@gmail.com> although the sed script in that patch no longer applies due to other changes in the tree since then, and I also did some manual cleanups (such as fixing whitespace to keep checkpatch happy). Signed-off-by: Eric Blake <eblake@redhat.com> Message-Id: <1468468228-27827-13-git-send-email-eblake@redhat.com> Reviewed-by: Markus Armbruster <armbru@redhat.com> [Fixup from Eric squashed in] Signed-off-by: Markus Armbruster <armbru@redhat.com>
2016-07-14 06:50:23 +03:00
NetClientDriver type, int max);
NetClientState *qemu_new_net_client(NetClientInfo *info,
NetClientState *peer,
const char *model,
const char *name);
NetClientState *qemu_new_net_control_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);
typedef void (*qemu_nic_foreach)(NICState *nic, void *opaque);
void qemu_foreach_nic(qemu_nic_foreach func, void *opaque);
int qemu_can_receive_packet(NetClientState *nc);
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);
ssize_t qemu_send_packet(NetClientState *nc, const uint8_t *buf, int size);
ssize_t qemu_receive_packet(NetClientState *nc, const uint8_t *buf, int size);
ssize_t qemu_receive_packet_iov(NetClientState *nc,
const struct iovec *iov,
int iovcnt);
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_flush_or_purge_queued_packets(NetClientState *nc, bool purge);
void qemu_set_info_str(NetClientState *nc, const char *fmt, ...);
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);
void print_net_client(Monitor *mon, NetClientState *nc);
void hmp_info_network(Monitor *mon, const QDict *qdict);
void net_socket_rs_init(SocketReadState *rs,
SocketReadStateFinalize *finalize,
bool vnet_hdr);
NetClientState *qemu_get_peer(NetClientState *nc, int queue_index);
/* 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 const char *host_net_devices[];
/* from net.c */
qapi: net: introduce a way to bypass qemu_opts_parse_noisily() As qemu_opts_parse_noisily() flattens the QAPI structures ("type" field of Netdev structure can collides with "type" field of SocketAddress), we introduce a way to bypass qemu_opts_parse_noisily() and use directly visit_type_Netdev() to parse the backend parameters. More details from Markus: qemu_init() passes the argument of -netdev, -nic, and -net to net_client_parse(). net_client_parse() parses with qemu_opts_parse_noisily(), passing QemuOptsList qemu_netdev_opts for -netdev, qemu_nic_opts for -nic, and qemu_net_opts for -net. Their desc[] are all empty, which means any keys are accepted. The result of the parse (a QemuOpts) is stored in the QemuOptsList. Note that QemuOpts is flat by design. In some places, we layer non-flat on top using dotted keys convention, but not here. net_init_clients() iterates over the stored QemuOpts, and passes them to net_init_netdev(), net_param_nic(), or net_init_client(), respectively. These functions pass the QemuOpts to net_client_init(). They also do other things with the QemuOpts, which we can ignore here. net_client_init() uses the opts visitor to convert the (flat) QemOpts to a (non-flat) QAPI object Netdev. Netdev is also the argument of QMP command netdev_add. The opts visitor was an early attempt to support QAPI in (QemuOpts-based) CLI. It restricts QAPI types to a certain shape; see commit eb7ee2cbeb "qapi: introduce OptsVisitor". A more modern way to support QAPI is qobject_input_visitor_new_str(). It uses keyval_parse() instead of QemuOpts for KEY=VALUE,... syntax, and it also supports JSON syntax. The former isn't quite as expressive as JSON, but it's a lot closer than QemuOpts + opts visitor. This commit paves the way to use of the modern way instead. Signed-off-by: Laurent Vivier <lvivier@redhat.com> Reviewed-by: Markus Armbruster <armbru@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Jason Wang <jasowang@redhat.com>
2022-10-21 12:09:09 +03:00
bool netdev_is_modern(const char *optarg);
void netdev_parse_modern(const char *optarg);
void net_client_parse(QemuOptsList *opts_list, const char *str);
void show_netdevs(void);
void 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);
int net_hub_id_for_client(NetClientState *nc, int *id);
NetClientState *net_hub_port_find(int hub_id);
#define DEFAULT_NETWORK_SCRIPT CONFIG_SYSCONFDIR "/qemu-ifup"
#define DEFAULT_NETWORK_DOWN_SCRIPT CONFIG_SYSCONFDIR "/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_BE 0x04c11db6
#define POLYNOMIAL_LE 0xedb88320
uint32_t net_crc32(const uint8_t *p, int len);
uint32_t net_crc32_le(const uint8_t *p, int len);
#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), \
}
static inline bool net_peer_needs_padding(NetClientState *nc)
{
return nc->peer && !nc->peer->do_not_pad;
}
#endif