tuntap: reduce memory using of queues

[~andy/linux] / drivers / net / tun.c

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index aa963c44450a7e866eaa1c0670dcf36c5f3c147b..8939d2117de2420784ba524cfc013bb85aaa5f92 100644 (file)
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -109,11 +109,10 @@ struct tap_filter {
        unsigned char   addr[FLT_EXACT_COUNT][ETH_ALEN];
 };
 
-/* 1024 is probably a high enough limit: modern hypervisors seem to support on
- * the order of 100-200 CPUs so this leaves us some breathing space if we want
- * to match a queue per guest CPU.
- */
-#define MAX_TAP_QUEUES 1024
+/* DEFAULT_MAX_NUM_RSS_QUEUES were choosed to let the rx/tx queues allocated for
+ * the netdevice to be fit in one page. So we can make sure the success of
+ * memory allocation. TODO: increase the limit. */
+#define MAX_TAP_QUEUES DEFAULT_MAX_NUM_RSS_QUEUES
 
 #define TUN_FLOW_EXPIRE (3 * HZ)
 
@@ -185,6 +184,7 @@ struct tun_struct {
        unsigned long ageing_time;
        unsigned int numdisabled;
        struct list_head disabled;
+       void *security;
 };
 
 static inline u32 tun_hashfn(u32 rxhash)
@@ -428,8 +428,10 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
                /* Drop read queue */
                skb_queue_purge(&tfile->sk.sk_receive_queue);
                tun_set_real_num_queues(tun);
-       } else if (tfile->detached && clean)
+       } else if (tfile->detached && clean) {
                tun = tun_enable_queue(tfile);
+               sock_put(&tfile->sk);
+       }
 
        if (clean) {
                if (tun && tun->numqueues == 0 && tun->numdisabled == 0 &&
@@ -478,6 +480,9 @@ static void tun_detach_all(struct net_device *dev)
                sock_put(&tfile->sk);
        }
        BUG_ON(tun->numdisabled != 0);
+
+       if (tun->flags & TUN_PERSIST)
+               module_put(THIS_MODULE);
 }
 
 static int tun_attach(struct tun_struct *tun, struct file *file)
@@ -485,11 +490,13 @@ static int tun_attach(struct tun_struct *tun, struct file *file)
        struct tun_file *tfile = file->private_data;
        int err;
 
+       err = security_tun_dev_attach(tfile->socket.sk, tun->security);
+       if (err < 0)
+               goto out;
+
        err = -EINVAL;
        if (rtnl_dereference(tfile->tun))
                goto out;
-       if (tfile->detached && tun != tfile->detached)
-               goto out;
 
        err = -EBUSY;
        if (!(tun->flags & TUN_TAP_MQ) && tun->numqueues == 1)
@@ -1370,6 +1377,7 @@ static void tun_free_netdev(struct net_device *dev)
 
        BUG_ON(!(list_empty(&tun->disabled)));
        tun_flow_uninit(tun);
+       security_tun_dev_free_security(tun->security);
        free_netdev(dev);
 }
 
@@ -1543,6 +1551,9 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
        struct net_device *dev;
        int err;
 
+       if (tfile->detached)
+               return -EINVAL;
+
        dev = __dev_get_by_name(net, ifr->ifr_name);
        if (dev) {
                if (ifr->ifr_flags & IFF_TUN_EXCL)
@@ -1556,7 +1567,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 
                if (tun_not_capable(tun))
                        return -EPERM;
-               err = security_tun_dev_attach(tfile->socket.sk);
+               err = security_tun_dev_open(tun->security);
                if (err < 0)
                        return err;
 
@@ -1571,6 +1582,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
        else {
                char *name;
                unsigned long flags = 0;
+               int queues = ifr->ifr_flags & IFF_MULTI_QUEUE ?
+                            MAX_TAP_QUEUES : 1;
 
                if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
                        return -EPERM;
@@ -1594,8 +1607,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
                        name = ifr->ifr_name;
 
                dev = alloc_netdev_mqs(sizeof(struct tun_struct), name,
-                                      tun_setup,
-                                      MAX_TAP_QUEUES, MAX_TAP_QUEUES);
+                                      tun_setup, queues, queues);
+
                if (!dev)
                        return -ENOMEM;
 
@@ -1613,7 +1626,9 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 
                spin_lock_init(&tun->lock);
 
-               security_tun_dev_post_create(&tfile->sk);
+               err = security_tun_dev_alloc_security(&tun->security);
+               if (err < 0)
+                       goto err_free_dev;
 
                tun_net_init(dev);
 
@@ -1783,10 +1798,14 @@ static int tun_set_queue(struct file *file, struct ifreq *ifr)
 
        if (ifr->ifr_flags & IFF_ATTACH_QUEUE) {
                tun = tfile->detached;
-               if (!tun)
+               if (!tun) {
                        ret = -EINVAL;
-               else
-                       ret = tun_attach(tun, file);
+                       goto unlock;
+               }
+               ret = security_tun_dev_attach_queue(tun->security);
+               if (ret < 0)
+                       goto unlock;
+               ret = tun_attach(tun, file);
        } else if (ifr->ifr_flags & IFF_DETACH_QUEUE) {
                tun = rtnl_dereference(tfile->tun);
                if (!tun || !(tun->flags & TUN_TAP_MQ))
@@ -1796,6 +1815,7 @@ static int tun_set_queue(struct file *file, struct ifreq *ifr)
        } else
                ret = -EINVAL;
 
+unlock:
        rtnl_unlock();
        return ret;
 }
@@ -1873,10 +1893,11 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
                /* Disable/Enable persist mode. Keep an extra reference to the
                 * module to prevent the module being unprobed.
                 */
-               if (arg) {
+               if (arg && !(tun->flags & TUN_PERSIST)) {
                        tun->flags |= TUN_PERSIST;
                        __module_get(THIS_MODULE);
-               } else {
+               }
+               if (!arg && (tun->flags & TUN_PERSIST)) {
                        tun->flags &= ~TUN_PERSIST;
                        module_put(THIS_MODULE);
                }