[Qemu-devel] [PATCH 05/12] net: multiqueue support

[Jason Wang <jasowang@redhat.com>]

This patch adds basic multiqueue support for qemu. The idea is simple, an array
of NetClientStates were introduced in NICState, parse_netdev() were extended to
find and match all NetClientStates belongs to the backend and place their
pointers in NICConf. Then qemu_new_nic can setup a N:N mapping between NICStates
that belongs to a nic and NICStates belongs to the netdev. After this, each
peers of a NICStaet were abstracted as a queue.

To adapt this change, set_link/netdev_del command will find all the
NetClientStates of a nic or a netdev, and change all their state in one run.

Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 hw/dp8393x.c         |    2 +-
 hw/mcf_fec.c         |    2 +-
 hw/qdev-properties.c |   46 +++++++++++--
 hw/qdev-properties.h |    6 +-
 net.c                |  172 +++++++++++++++++++++++++++++++++++++-------------
 net.h                |   27 +++++++-
 6 files changed, 195 insertions(+), 60 deletions(-)

diff --git a/hw/dp8393x.c b/hw/dp8393x.c
index 8f20a4a..fad0837 100644
--- a/hw/dp8393x.c
+++ b/hw/dp8393x.c
@@ -899,7 +899,7 @@ void dp83932_init(NICInfo *nd, hwaddr base, int it_shift,
     s->regs[SONIC_SR] = 0x0004; /* only revision recognized by Linux */
 
     s->conf.macaddr = nd->macaddr;
-    s->conf.peer = nd->netdev;
+    s->conf.peers.ncs[0] = nd->netdev;
 
     s->nic = qemu_new_nic(&net_dp83932_info, &s->conf, nd->model, nd->name, s);
 
diff --git a/hw/mcf_fec.c b/hw/mcf_fec.c
index 7fc89b5..c298bec 100644
--- a/hw/mcf_fec.c
+++ b/hw/mcf_fec.c
@@ -472,7 +472,7 @@ void mcf_fec_init(MemoryRegion *sysmem, NICInfo *nd,
     memory_region_add_subregion(sysmem, base, &s->iomem);
 
     s->conf.macaddr = nd->macaddr;
-    s->conf.peer = nd->netdev;
+    s->conf.peers[0] = nd->netdev;
 
     s->nic = qemu_new_nic(&net_mcf_fec_info, &s->conf, nd->model, nd->name, s);
 
diff --git a/hw/qdev-properties.c b/hw/qdev-properties.c
index 81d901c..6e45def 100644
--- a/hw/qdev-properties.c
+++ b/hw/qdev-properties.c
@@ -585,16 +585,47 @@ PropertyInfo qdev_prop_chr = {
 
 static int parse_netdev(DeviceState *dev, const char *str, void **ptr)
 {
-    NetClientState *netdev = qemu_find_netdev(str);
+    NICPeers *peers_ptr = (NICPeers *)ptr;
+    NICConf *conf = container_of(peers_ptr, NICConf, peers);
+    NetClientState **ncs = peers_ptr->ncs;
+    NetClientState *peers[MAX_QUEUE_NUM];
+    int queues, i = 0;
+    int ret;
 
-    if (netdev == NULL) {
-        return -ENOENT;
+    queues = qemu_find_net_clients_except(str, peers,
+                                          NET_CLIENT_OPTIONS_KIND_NIC,
+                                          MAX_QUEUE_NUM);
+    if (queues == 0) {
+        ret = -ENOENT;
+        goto err;
     }
-    if (netdev->peer) {
-        return -EEXIST;
+
+    if (queues > MAX_QUEUE_NUM) {
+        ret = -E2BIG;
+        goto err;
+    }
+
+    for (i = 0; i < queues; i++) {
+        if (peers[i] == NULL) {
+            ret = -ENOENT;
+            goto err;
+        }
+
+        if (peers[i]->peer) {
+            ret = -EEXIST;
+            goto err;
+        }
+
+        ncs[i] = peers[i];
+        ncs[i]->queue_index = i;
     }
-    *ptr = netdev;
+
+    conf->queues = queues;
+
     return 0;
+
+err:
+    return ret;
 }
 
 static const char *print_netdev(void *ptr)
@@ -661,7 +692,8 @@ static void set_vlan(Object *obj, Visitor *v, void *opaque,
 {
     DeviceState *dev = DEVICE(obj);
     Property *prop = opaque;
-    NetClientState **ptr = qdev_get_prop_ptr(dev, prop);
+    NICPeers *peers_ptr = qdev_get_prop_ptr(dev, prop);
+    NetClientState **ptr = &peers_ptr->ncs[0];
     Error *local_err = NULL;
     int32_t id;
     NetClientState *hubport;
diff --git a/hw/qdev-properties.h b/hw/qdev-properties.h
index 5b046ab..2d90848 100644
--- a/hw/qdev-properties.h
+++ b/hw/qdev-properties.h
@@ -31,7 +31,7 @@ extern PropertyInfo qdev_prop_pci_host_devaddr;
         .name      = (_name),                                    \
         .info      = &(_prop),                                   \
         .offset    = offsetof(_state, _field)                    \
-            + type_check(_type,typeof_field(_state, _field)),    \
+            + type_check(_type, typeof_field(_state, _field)),   \
         }
 #define DEFINE_PROP_DEFAULT(_name, _state, _field, _defval, _prop, _type) { \
         .name      = (_name),                                           \
@@ -77,9 +77,9 @@ extern PropertyInfo qdev_prop_pci_host_devaddr;
 #define DEFINE_PROP_STRING(_n, _s, _f)             \
     DEFINE_PROP(_n, _s, _f, qdev_prop_string, char*)
 #define DEFINE_PROP_NETDEV(_n, _s, _f)             \
-    DEFINE_PROP(_n, _s, _f, qdev_prop_netdev, NetClientState*)
+    DEFINE_PROP(_n, _s, _f, qdev_prop_netdev, NICPeers)
 #define DEFINE_PROP_VLAN(_n, _s, _f)             \
-    DEFINE_PROP(_n, _s, _f, qdev_prop_vlan, NetClientState*)
+    DEFINE_PROP(_n, _s, _f, qdev_prop_vlan, NICPeers)
 #define DEFINE_PROP_DRIVE(_n, _s, _f) \
     DEFINE_PROP(_n, _s, _f, qdev_prop_drive, BlockDriverState *)
 #define DEFINE_PROP_MACADDR(_n, _s, _f)         \
diff --git a/net.c b/net.c
index 97ee542..4ceba33 100644
--- a/net.c
+++ b/net.c
@@ -181,17 +181,12 @@ static char *assign_name(NetClientState *nc1, const char *model)
     return g_strdup(buf);
 }
 
-NetClientState *qemu_new_net_client(NetClientInfo *info,
-                                    NetClientState *peer,
-                                    const char *model,
-                                    const char *name)
+void qemu_net_client_setup(NetClientState *nc,
+                           NetClientInfo *info,
+                           NetClientState *peer,
+                           const char *model,
+                           const char *name)
 {
-    NetClientState *nc;
-
-    assert(info->size >= sizeof(NetClientState));
-
-    nc = g_malloc0(info->size);
-
     nc->info = info;
     nc->model = g_strdup(model);
     if (name) {
@@ -208,6 +203,20 @@ NetClientState *qemu_new_net_client(NetClientInfo *info,
     QTAILQ_INSERT_TAIL(&net_clients, nc, next);
 
     nc->send_queue = qemu_new_net_queue(nc);
+}
+
+
+NetClientState *qemu_new_net_client(NetClientInfo *info,
+                                    NetClientState *peer,
+                                    const char *model,
+                                    const char *name)
+{
+    NetClientState *nc;
+
+    assert(info->size >= sizeof(NetClientState));
+
+    nc = g_malloc0(info->size);
+    qemu_net_client_setup(nc, info, peer, model, name);
 
     return nc;
 }
@@ -219,28 +228,43 @@ NICState *qemu_new_nic(NetClientInfo *info,
                        void *opaque)
 {
     NetClientState *nc;
+    NetClientState **peers = conf->peers.ncs;
     NICState *nic;
+    int i;
 
     assert(info->type == NET_CLIENT_OPTIONS_KIND_NIC);
     assert(info->size >= sizeof(NICState));
 
-    nc = qemu_new_net_client(info, conf->peer, model, name);
+    nc = qemu_new_net_client(info, peers[0], model, name);
+    nc->queue_index = 0;
 
     nic = qemu_get_nic(nc);
     nic->conf = conf;
     nic->opaque = opaque;
 
+    for (i = 1; i < conf->queues; i++) {
+        qemu_net_client_setup(&nic->ncs[i], info, peers[i], model, nc->name);
+        nic->ncs[i].queue_index = i;
+    }
+
     return nic;
 }
 
+NetClientState *qemu_get_subqueue(NICState *nic, int queue_index)
+{
+    return &nic->ncs[queue_index];
+}
+
 NetClientState *qemu_get_queue(NICState *nic)
 {
-    return &nic->nc;
+    return qemu_get_subqueue(nic, 0);
 }
 
 NICState *qemu_get_nic(NetClientState *nc)
 {
-    return DO_UPCAST(NICState, nc, nc);
+    NetClientState *nc0 = nc - nc->queue_index;
+
+    return DO_UPCAST(NICState, ncs[0], nc0);
 }
 
 void *qemu_get_nic_opaque(NetClientState *nc)
@@ -254,12 +278,10 @@ static void qemu_cleanup_net_client(NetClientState *nc)
 {
     QTAILQ_REMOVE(&net_clients, nc, next);
 
-    if (nc->info->cleanup) {
-        nc->info->cleanup(nc);
-    }
+    nc->info->cleanup(nc);
 }
 
-static void qemu_free_net_client(NetClientState *nc)
+static void qemu_free_net_client(NetClientState *nc, bool free)
 {
     if (nc->send_queue) {
         qemu_del_net_queue(nc->send_queue);
@@ -269,11 +291,24 @@ static void qemu_free_net_client(NetClientState *nc)
     }
     g_free(nc->name);
     g_free(nc->model);
-    g_free(nc);
+
+    if (free)
+        g_free(nc);
 }
 
 void qemu_del_net_client(NetClientState *nc)
 {
+    NetClientState *ncs[MAX_QUEUE_NUM];
+    int queues, i;
+
+    /* If the NetClientState belongs to a multiqueue backend, we will change all
+     * other NetClientStates also.
+     */
+    queues = qemu_find_net_clients_except(nc->name, ncs,
+                                          NET_CLIENT_OPTIONS_KIND_NIC,
+                                          MAX_QUEUE_NUM);
+    assert(queues != 0);
+
     /* If there is a peer NIC, delete and cleanup client, but do not free. */
     if (nc->peer && nc->peer->info->type == NET_CLIENT_OPTIONS_KIND_NIC) {
         NICState *nic = qemu_get_nic(nc->peer);
@@ -281,34 +316,50 @@ void qemu_del_net_client(NetClientState *nc)
             return;
         }
         nic->peer_deleted = true;
-        /* Let NIC know peer is gone. */
-        nc->peer->link_down = true;
+
+        for (i = 0; i < queues; i++) {
+            ncs[i]->peer->link_down = true;
+        }
+
         if (nc->peer->info->link_status_changed) {
             nc->peer->info->link_status_changed(nc->peer);
         }
-        qemu_cleanup_net_client(nc);
+
+        for (i = 0; i < queues; i++) {
+            qemu_cleanup_net_client(ncs[i]);
+        }
+
         return;
     }
 
     assert(nc->info->type != NET_CLIENT_OPTIONS_KIND_NIC);
 
-    qemu_cleanup_net_client(nc);
-    qemu_free_net_client(nc);
+    for (i = 0; i < queues; i++) {
+        qemu_cleanup_net_client(ncs[i]);
+        qemu_free_net_client(ncs[i], true);
+    }
 }
 
 void qemu_del_nic(NICState *nic)
 {
-    NetClientState *nc = qemu_get_queue(nic);
+    int i, queues = nic->conf->queues;
+
     /* If this is a peer NIC and peer has already been deleted, free it now. */
-    if (nc->peer && nc->info->type == NET_CLIENT_OPTIONS_KIND_NIC) {
-        NICState *nic = qemu_get_nic(nc);
-        if (nic->peer_deleted) {
-            qemu_free_net_client(nc->peer);
+    if (nic->peer_deleted) {
+        for (i = 0; i < queues; i++) {
+            qemu_free_net_client(qemu_get_subqueue(nic, i)->peer, true);
         }
     }
 
-    qemu_cleanup_net_client(nc);
-    qemu_free_net_client(nc);
+    for (i = 1; i < queues; i++) {
+        NetClientState *nc = qemu_get_subqueue(nic, i);
+
+        qemu_cleanup_net_client(nc);
+        qemu_free_net_client(nc, false);
+    }
+
+    qemu_cleanup_net_client(qemu_get_subqueue(nic, 0));
+    qemu_free_net_client(qemu_get_subqueue(nic, 0), true);
 }
 
 void qemu_foreach_nic(qemu_nic_foreach func, void *opaque)
@@ -317,7 +368,9 @@ void qemu_foreach_nic(qemu_nic_foreach func, void *opaque)
 
     QTAILQ_FOREACH(nc, &net_clients, next) {
         if (nc->info->type == NET_CLIENT_OPTIONS_KIND_NIC) {
-            func(qemu_get_nic(nc), opaque);
+            if (nc->queue_index == 0) {
+                func(qemu_get_nic(nc), opaque);
+            }
         }
     }
 }
@@ -507,6 +560,27 @@ NetClientState *qemu_find_netdev(const char *id)
     return NULL;
 }
 
+int qemu_find_net_clients_except(const char *id, NetClientState **ncs,
+                                 NetClientOptionsKind type, int max)
+{
+    NetClientState *nc;
+    int ret = 0;
+
+    QTAILQ_FOREACH(nc, &net_clients, next) {
+        if (nc->info->type == type) {
+            continue;
+        }
+        if (!strcmp(nc->name, id)) {
+            if (ret < max) {
+                ncs[ret] = nc;
+            }
+            ret++;
+        }
+    }
+
+    return ret;
+}
+
 static int nic_get_free_idx(void)
 {
     int index;
@@ -873,8 +947,11 @@ void qmp_netdev_del(const char *id, Error **errp)
 
 void print_net_client(Monitor *mon, NetClientState *nc)
 {
-    monitor_printf(mon, "%s: type=%s,%s\n", nc->name,
-                   NetClientOptionsKind_lookup[nc->info->type], nc->info_str);
+    monitor_printf(mon, "%s: index=%d,type=%s,%s,link=%s\n", nc->name,
+                       nc->queue_index,
+                       NetClientOptionsKind_lookup[nc->info->type],
+                       nc->info_str,
+                       nc->link_down ? "down" : "up");
 }
 
 void do_info_network(Monitor *mon)
@@ -905,20 +982,23 @@ void do_info_network(Monitor *mon)
 
 void qmp_set_link(const char *name, bool up, Error **errp)
 {
-    NetClientState *nc = NULL;
+    NetClientState *ncs[MAX_QUEUE_NUM];
+    NetClientState *nc;
+    int queues, i;
 
-    QTAILQ_FOREACH(nc, &net_clients, next) {
-        if (!strcmp(nc->name, name)) {
-            goto done;
-        }
-    }
-done:
-    if (!nc) {
+    queues = qemu_find_net_clients_except(name, ncs,
+                                          NET_CLIENT_OPTIONS_KIND_MAX,
+                                          MAX_QUEUE_NUM);
+
+    if (queues == 0) {
         error_set(errp, QERR_DEVICE_NOT_FOUND, name);
         return;
     }
+    nc = ncs[0];
 
-    nc->link_down = !up;
+    for (i = 0; i < queues; i++) {
+        ncs[i]->link_down = !up;
+    }
 
     if (nc->info->link_status_changed) {
         nc->info->link_status_changed(nc);
@@ -938,9 +1018,13 @@ done:
 
 void net_cleanup(void)
 {
-    NetClientState *nc, *next_vc;
+    NetClientState *nc;
 
-    QTAILQ_FOREACH_SAFE(nc, &net_clients, next, next_vc) {
+    /* We may del multiple entries during qemu_del_net_client(),
+     * so QTAILQ_FOREACH_SAFE() is also not safe here.
+     */
+    while (!QTAILQ_EMPTY(&net_clients)) {
+        nc = QTAILQ_FIRST(&net_clients);
         if (nc->info->type == NET_CLIENT_OPTIONS_KIND_NIC) {
             qemu_del_nic(qemu_get_nic(nc));
         } else {
diff --git a/net.h b/net.h
index 0d53337..6ff1afc 100644
--- a/net.h
+++ b/net.h
@@ -9,24 +9,32 @@
 #include "vmstate.h"
 #include "qapi-types.h"
 
+#define MAX_QUEUE_NUM 1024
+
 struct MACAddr {
     uint8_t a[6];
 };
 
 /* qdev nic properties */
 
+typedef struct NICPeers {
+    NetClientState *ncs[MAX_QUEUE_NUM];
+} NICPeers;
+
 typedef struct NICConf {
     MACAddr macaddr;
-    NetClientState *peer;
+    NICPeers peers;
     int32_t bootindex;
+    int32_t queues;
 } NICConf;
 
 #define DEFINE_NIC_PROPERTIES(_state, _conf)                            \
     DEFINE_PROP_MACADDR("mac",   _state, _conf.macaddr),                \
-    DEFINE_PROP_VLAN("vlan",     _state, _conf.peer),                   \
-    DEFINE_PROP_NETDEV("netdev", _state, _conf.peer),                   \
+    DEFINE_PROP_VLAN("vlan",     _state, _conf.peers),                   \
+    DEFINE_PROP_NETDEV("netdev", _state, _conf.peers),                   \
     DEFINE_PROP_INT32("bootindex", _state, _conf.bootindex, -1)
 
+
 /* Net clients */
 
 typedef void (NetPoll)(NetClientState *, bool enable);
@@ -58,16 +66,26 @@ struct NetClientState {
     char *name;
     char info_str[256];
     unsigned receive_disabled : 1;
+    unsigned int queue_index;
 };
 
 typedef struct NICState {
-    NetClientState nc;
+    NetClientState ncs[MAX_QUEUE_NUM];
     NICConf *conf;
     void *opaque;
     bool peer_deleted;
 } NICState;
 
 NetClientState *qemu_find_netdev(const char *id);
+int qemu_find_net_clients_except(const char *id,
+                                 NetClientState **ncs,
+                                 NetClientOptionsKind type,
+                                 int max);
+void qemu_net_client_setup(NetClientState *nc,
+                           NetClientInfo *info,
+                           NetClientState *peer,
+                           const char *model,
+                           const char *name);
 NetClientState *qemu_new_net_client(NetClientInfo *info,
                                     NetClientState *peer,
                                     const char *model,
@@ -78,6 +96,7 @@ NICState *qemu_new_nic(NetClientInfo *info,
                        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);
-- 
1.7.1