diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2010-10-23 11:47:02 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2010-10-23 11:47:02 -0700 |
commit | 5f05647dd81c11a6a165ccc8f0c1370b16f3bcb0 (patch) | |
tree | 7851ef1c93aa1aba7ef327ca4b75fd35e6d10f29 /drivers/net/macvtap.c | |
parent | 02f36038c568111ad4fc433f6fa760ff5e38fab4 (diff) | |
parent | ec37a48d1d16c30b655ac5280209edf52a6775d4 (diff) | |
download | op-kernel-dev-5f05647dd81c11a6a165ccc8f0c1370b16f3bcb0.zip op-kernel-dev-5f05647dd81c11a6a165ccc8f0c1370b16f3bcb0.tar.gz |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6: (1699 commits)
bnx2/bnx2x: Unsupported Ethtool operations should return -EINVAL.
vlan: Calling vlan_hwaccel_do_receive() is always valid.
tproxy: use the interface primary IP address as a default value for --on-ip
tproxy: added IPv6 support to the socket match
cxgb3: function namespace cleanup
tproxy: added IPv6 support to the TPROXY target
tproxy: added IPv6 socket lookup function to nf_tproxy_core
be2net: Changes to use only priority codes allowed by f/w
tproxy: allow non-local binds of IPv6 sockets if IP_TRANSPARENT is enabled
tproxy: added tproxy sockopt interface in the IPV6 layer
tproxy: added udp6_lib_lookup function
tproxy: added const specifiers to udp lookup functions
tproxy: split off ipv6 defragmentation to a separate module
l2tp: small cleanup
nf_nat: restrict ICMP translation for embedded header
can: mcp251x: fix generation of error frames
can: mcp251x: fix endless loop in interrupt handler if CANINTF_MERRF is set
can-raw: add msg_flags to distinguish local traffic
9p: client code cleanup
rds: make local functions/variables static
...
Fix up conflicts in net/core/dev.c, drivers/net/pcmcia/smc91c92_cs.c and
drivers/net/wireless/ath/ath9k/debug.c as per David
Diffstat (limited to 'drivers/net/macvtap.c')
-rw-r--r-- | drivers/net/macvtap.c | 99 |
1 files changed, 82 insertions, 17 deletions
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 3b1c54a..4256727 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -84,26 +84,45 @@ static const struct proto_ops macvtap_socket_ops; static DEFINE_SPINLOCK(macvtap_lock); /* - * Choose the next free queue, for now there is only one + * get_slot: return a [unused/occupied] slot in vlan->taps[]: + * - if 'q' is NULL, return the first empty slot; + * - otherwise, return the slot this pointer occupies. */ +static int get_slot(struct macvlan_dev *vlan, struct macvtap_queue *q) +{ + int i; + + for (i = 0; i < MAX_MACVTAP_QUEUES; i++) { + if (rcu_dereference(vlan->taps[i]) == q) + return i; + } + + /* Should never happen */ + BUG_ON(1); +} + static int macvtap_set_queue(struct net_device *dev, struct file *file, struct macvtap_queue *q) { struct macvlan_dev *vlan = netdev_priv(dev); + int index; int err = -EBUSY; spin_lock(&macvtap_lock); - if (rcu_dereference(vlan->tap)) + if (vlan->numvtaps == MAX_MACVTAP_QUEUES) goto out; err = 0; + index = get_slot(vlan, NULL); rcu_assign_pointer(q->vlan, vlan); - rcu_assign_pointer(vlan->tap, q); + rcu_assign_pointer(vlan->taps[index], q); sock_hold(&q->sk); q->file = file; file->private_data = q; + vlan->numvtaps++; + out: spin_unlock(&macvtap_lock); return err; @@ -124,9 +143,12 @@ static void macvtap_put_queue(struct macvtap_queue *q) spin_lock(&macvtap_lock); vlan = rcu_dereference(q->vlan); if (vlan) { - rcu_assign_pointer(vlan->tap, NULL); + int index = get_slot(vlan, q); + + rcu_assign_pointer(vlan->taps[index], NULL); rcu_assign_pointer(q->vlan, NULL); sock_put(&q->sk); + --vlan->numvtaps; } spin_unlock(&macvtap_lock); @@ -136,39 +158,82 @@ static void macvtap_put_queue(struct macvtap_queue *q) } /* - * Since we only support one queue, just dereference the pointer. + * Select a queue based on the rxq of the device on which this packet + * arrived. If the incoming device is not mq, calculate a flow hash + * to select a queue. If all fails, find the first available queue. + * Cache vlan->numvtaps since it can become zero during the execution + * of this function. */ static struct macvtap_queue *macvtap_get_queue(struct net_device *dev, struct sk_buff *skb) { struct macvlan_dev *vlan = netdev_priv(dev); + struct macvtap_queue *tap = NULL; + int numvtaps = vlan->numvtaps; + __u32 rxq; + + if (!numvtaps) + goto out; + + if (likely(skb_rx_queue_recorded(skb))) { + rxq = skb_get_rx_queue(skb); + + while (unlikely(rxq >= numvtaps)) + rxq -= numvtaps; + + tap = rcu_dereference(vlan->taps[rxq]); + if (tap) + goto out; + } + + /* Check if we can use flow to select a queue */ + rxq = skb_get_rxhash(skb); + if (rxq) { + tap = rcu_dereference(vlan->taps[rxq % numvtaps]); + if (tap) + goto out; + } - return rcu_dereference(vlan->tap); + /* Everything failed - find first available queue */ + for (rxq = 0; rxq < MAX_MACVTAP_QUEUES; rxq++) { + tap = rcu_dereference(vlan->taps[rxq]); + if (tap) + break; + } + +out: + return tap; } /* * The net_device is going away, give up the reference - * that it holds on the queue (all the queues one day) - * and safely set the pointer from the queues to NULL. + * that it holds on all queues and safely set the pointer + * from the queues to NULL. */ static void macvtap_del_queues(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); - struct macvtap_queue *q; + struct macvtap_queue *q, *qlist[MAX_MACVTAP_QUEUES]; + int i, j = 0; + /* macvtap_put_queue can free some slots, so go through all slots */ spin_lock(&macvtap_lock); - q = rcu_dereference(vlan->tap); - if (!q) { - spin_unlock(&macvtap_lock); - return; + for (i = 0; i < MAX_MACVTAP_QUEUES && vlan->numvtaps; i++) { + q = rcu_dereference(vlan->taps[i]); + if (q) { + qlist[j++] = q; + rcu_assign_pointer(vlan->taps[i], NULL); + rcu_assign_pointer(q->vlan, NULL); + vlan->numvtaps--; + } } - - rcu_assign_pointer(vlan->tap, NULL); - rcu_assign_pointer(q->vlan, NULL); + BUG_ON(vlan->numvtaps != 0); spin_unlock(&macvtap_lock); synchronize_rcu(); - sock_put(&q->sk); + + for (--j; j >= 0; j--) + sock_put(&qlist[j]->sk); } /* |