From f2f79cca13e36972978ffd1fb6483c8a1141b510 Mon Sep 17 00:00:00 2001 From: Daniel Baluta Date: Sat, 13 Jul 2013 11:26:51 +0300 Subject: ndisc: bool initializations should use true and false Signed-off-by: Daniel Baluta Signed-off-by: David S. Miller --- net/ipv6/ndisc.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index b3b5730b48c..24c03396e00 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -479,7 +479,7 @@ static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, if (ifp) { src_addr = solicited_addr; if (ifp->flags & IFA_F_OPTIMISTIC) - override = 0; + override = false; inc_opt |= ifp->idev->cnf.force_tllao; in6_ifa_put(ifp); } else { @@ -557,7 +557,7 @@ void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh, } if (ipv6_addr_any(saddr)) - inc_opt = 0; + inc_opt = false; if (inc_opt) optlen += ndisc_opt_addr_space(dev); @@ -790,7 +790,7 @@ static void ndisc_recv_ns(struct sk_buff *skb) (is_router = pndisc_is_router(&msg->target, dev)) >= 0)) { if (!(NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED) && skb->pkt_type != PACKET_HOST && - inc != 0 && + inc && idev->nd_parms->proxy_delay != 0) { /* * for anycast or proxy, -- cgit v1.2.3-18-g5258 From 8a73125c36809527236e1d8d367a09a3f0e9f9e1 Mon Sep 17 00:00:00 2001 From: Dragos Foianu Date: Sat, 13 Jul 2013 14:43:00 +0100 Subject: ethtool: fixed trailing statements in ethtool Applied fixes suggested by checkpatch.pl. Signed-off-by: Dragos Foianu Signed-off-by: David S. Miller --- net/core/ethtool.c | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-) (limited to 'net') diff --git a/net/core/ethtool.c b/net/core/ethtool.c index ab5fa6336c8..78e9d9223e4 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -279,11 +279,16 @@ static u32 __ethtool_get_flags(struct net_device *dev) { u32 flags = 0; - if (dev->features & NETIF_F_LRO) flags |= ETH_FLAG_LRO; - if (dev->features & NETIF_F_HW_VLAN_CTAG_RX) flags |= ETH_FLAG_RXVLAN; - if (dev->features & NETIF_F_HW_VLAN_CTAG_TX) flags |= ETH_FLAG_TXVLAN; - if (dev->features & NETIF_F_NTUPLE) flags |= ETH_FLAG_NTUPLE; - if (dev->features & NETIF_F_RXHASH) flags |= ETH_FLAG_RXHASH; + if (dev->features & NETIF_F_LRO) + flags |= ETH_FLAG_LRO; + if (dev->features & NETIF_F_HW_VLAN_CTAG_RX) + flags |= ETH_FLAG_RXVLAN; + if (dev->features & NETIF_F_HW_VLAN_CTAG_TX) + flags |= ETH_FLAG_TXVLAN; + if (dev->features & NETIF_F_NTUPLE) + flags |= ETH_FLAG_NTUPLE; + if (dev->features & NETIF_F_RXHASH) + flags |= ETH_FLAG_RXHASH; return flags; } @@ -295,11 +300,16 @@ static int __ethtool_set_flags(struct net_device *dev, u32 data) if (data & ~ETH_ALL_FLAGS) return -EINVAL; - if (data & ETH_FLAG_LRO) features |= NETIF_F_LRO; - if (data & ETH_FLAG_RXVLAN) features |= NETIF_F_HW_VLAN_CTAG_RX; - if (data & ETH_FLAG_TXVLAN) features |= NETIF_F_HW_VLAN_CTAG_TX; - if (data & ETH_FLAG_NTUPLE) features |= NETIF_F_NTUPLE; - if (data & ETH_FLAG_RXHASH) features |= NETIF_F_RXHASH; + if (data & ETH_FLAG_LRO) + features |= NETIF_F_LRO; + if (data & ETH_FLAG_RXVLAN) + features |= NETIF_F_HW_VLAN_CTAG_RX; + if (data & ETH_FLAG_TXVLAN) + features |= NETIF_F_HW_VLAN_CTAG_TX; + if (data & ETH_FLAG_NTUPLE) + features |= NETIF_F_NTUPLE; + if (data & ETH_FLAG_RXHASH) + features |= NETIF_F_RXHASH; /* allow changing only bits set in hw_features */ changed = (features ^ dev->features) & ETH_ALL_FEATURES; -- cgit v1.2.3-18-g5258 From b6a82dd233cabcc1517c0744d7a8f0b61f559caf Mon Sep 17 00:00:00 2001 From: Dragos Foianu Date: Sat, 13 Jul 2013 15:03:55 +0100 Subject: net/irda: fixed style issues in irlan_eth Applied fixes suggested by checkpatch.pl Signed-off-by: Dragos Foianu Signed-off-by: David S. Miller --- net/irda/irlan/irlan_eth.c | 31 ++++++++++++++----------------- 1 file changed, 14 insertions(+), 17 deletions(-) (limited to 'net') diff --git a/net/irda/irlan/irlan_eth.c b/net/irda/irlan/irlan_eth.c index d14152e866d..ffcec225b5d 100644 --- a/net/irda/irlan/irlan_eth.c +++ b/net/irda/irlan/irlan_eth.c @@ -44,12 +44,12 @@ static int irlan_eth_open(struct net_device *dev); static int irlan_eth_close(struct net_device *dev); static netdev_tx_t irlan_eth_xmit(struct sk_buff *skb, struct net_device *dev); -static void irlan_eth_set_multicast_list( struct net_device *dev); +static void irlan_eth_set_multicast_list(struct net_device *dev); static const struct net_device_ops irlan_eth_netdev_ops = { - .ndo_open = irlan_eth_open, - .ndo_stop = irlan_eth_close, - .ndo_start_xmit = irlan_eth_xmit, + .ndo_open = irlan_eth_open, + .ndo_stop = irlan_eth_close, + .ndo_start_xmit = irlan_eth_xmit, .ndo_set_rx_mode = irlan_eth_set_multicast_list, .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, @@ -110,7 +110,7 @@ static int irlan_eth_open(struct net_device *dev) { struct irlan_cb *self = netdev_priv(dev); - IRDA_DEBUG(2, "%s()\n", __func__ ); + IRDA_DEBUG(2, "%s()\n", __func__); /* Ready to play! */ netif_stop_queue(dev); /* Wait until data link is ready */ @@ -137,7 +137,7 @@ static int irlan_eth_close(struct net_device *dev) { struct irlan_cb *self = netdev_priv(dev); - IRDA_DEBUG(2, "%s()\n", __func__ ); + IRDA_DEBUG(2, "%s()\n", __func__); /* Stop device */ netif_stop_queue(dev); @@ -310,35 +310,32 @@ static void irlan_eth_set_multicast_list(struct net_device *dev) { struct irlan_cb *self = netdev_priv(dev); - IRDA_DEBUG(2, "%s()\n", __func__ ); + IRDA_DEBUG(2, "%s()\n", __func__); /* Check if data channel has been connected yet */ if (self->client.state != IRLAN_DATA) { - IRDA_DEBUG(1, "%s(), delaying!\n", __func__ ); + IRDA_DEBUG(1, "%s(), delaying!\n", __func__); return; } if (dev->flags & IFF_PROMISC) { /* Enable promiscuous mode */ IRDA_WARNING("Promiscuous mode not implemented by IrLAN!\n"); - } - else if ((dev->flags & IFF_ALLMULTI) || + } else if ((dev->flags & IFF_ALLMULTI) || netdev_mc_count(dev) > HW_MAX_ADDRS) { /* Disable promiscuous mode, use normal mode. */ - IRDA_DEBUG(4, "%s(), Setting multicast filter\n", __func__ ); + IRDA_DEBUG(4, "%s(), Setting multicast filter\n", __func__); /* hardware_set_filter(NULL); */ irlan_set_multicast_filter(self, TRUE); - } - else if (!netdev_mc_empty(dev)) { - IRDA_DEBUG(4, "%s(), Setting multicast filter\n", __func__ ); + } else if (!netdev_mc_empty(dev)) { + IRDA_DEBUG(4, "%s(), Setting multicast filter\n", __func__); /* Walk the address list, and load the filter */ /* hardware_set_filter(dev->mc_list); */ irlan_set_multicast_filter(self, TRUE); - } - else { - IRDA_DEBUG(4, "%s(), Clearing multicast filter\n", __func__ ); + } else { + IRDA_DEBUG(4, "%s(), Clearing multicast filter\n", __func__); irlan_set_multicast_filter(self, FALSE); } -- cgit v1.2.3-18-g5258 From 21d1196a35f5686c4323e42a62fdb4b23b0ab4a3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 15 Jul 2013 20:03:19 -0700 Subject: ipv4: set transport header earlier commit 45f00f99d6e ("ipv4: tcp: clean up tcp_v4_early_demux()") added a performance regression for non GRO traffic, basically disabling IP early demux. IPv6 stack resets transport header in ip6_rcv() before calling IP early demux in ip6_rcv_finish(), while IPv4 does this only in ip_local_deliver_finish(), _after_ IP early demux. GRO traffic happened to enable IP early demux because transport header is also set in inet_gro_receive() Instead of reverting the faulty commit, we can make IPv4/IPv6 behave the same : transport_header should be set in ip_rcv() instead of ip_local_deliver_finish() ip_local_deliver_finish() can also use skb_network_header_len() which is faster than ip_hdrlen() Signed-off-by: Eric Dumazet Cc: Neal Cardwell Cc: Tom Herbert Signed-off-by: David S. Miller --- net/ipv4/ip_input.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 3da817b89e9..15e3e683ade 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -190,10 +190,7 @@ static int ip_local_deliver_finish(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); - __skb_pull(skb, ip_hdrlen(skb)); - - /* Point into the IP datagram, just past the header. */ - skb_reset_transport_header(skb); + __skb_pull(skb, skb_network_header_len(skb)); rcu_read_lock(); { @@ -437,6 +434,8 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, goto drop; } + skb->transport_header = skb->network_header + iph->ihl*4; + /* Remove any debris in the socket control block */ memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); -- cgit v1.2.3-18-g5258 From ae8e9c5a1a7889315229a741fd48a5dd0bc2964c Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 16 Jul 2013 17:09:15 -0700 Subject: net: Fix sysfs_format_mac() code duplication. It's just a duplicate implementation of "%*phC". Thanks to Joe Perches for showing that we had exactly this support in the lib/vsprintf.c code already. Signed-off-by: David S. Miller --- net/ethernet/eth.c | 21 +-------------------- 1 file changed, 1 insertion(+), 20 deletions(-) (limited to 'net') diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 5359560926b..be1f64d3535 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -401,27 +401,8 @@ struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs, } EXPORT_SYMBOL(alloc_etherdev_mqs); -static size_t _format_mac_addr(char *buf, int buflen, - const unsigned char *addr, int len) -{ - int i; - char *cp = buf; - - for (i = 0; i < len; i++) { - cp += scnprintf(cp, buflen - (cp - buf), "%02x", addr[i]); - if (i == len - 1) - break; - cp += scnprintf(cp, buflen - (cp - buf), ":"); - } - return cp - buf; -} - ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len) { - size_t l; - - l = _format_mac_addr(buf, PAGE_SIZE, addr, len); - l += scnprintf(buf + l, PAGE_SIZE - l, "\n"); - return (ssize_t)l; + return scnprintf(buf, PAGE_SIZE, "%*phC\n", len, addr); } EXPORT_SYMBOL(sysfs_format_mac); -- cgit v1.2.3-18-g5258 From 87f40dd6ce7042caca0b3b557e8923127f51f902 Mon Sep 17 00:00:00 2001 From: Paolo Valente Date: Tue, 16 Jul 2013 08:52:30 +0200 Subject: pkt_sched: sch_qfq: remove a source of high packet delay/jitter QFQ+ inherits from QFQ a design choice that may cause a high packet delay/jitter and a severe short-term unfairness. As QFQ, QFQ+ uses a special quantity, the system virtual time, to track the service provided by the ideal system it approximates. When a packet is dequeued, this quantity must be incremented by the size of the packet, divided by the sum of the weights of the aggregates waiting to be served. Tracking this sum correctly is a non-trivial task, because, to preserve tight service guarantees, the decrement of this sum must be delayed in a special way [1]: this sum can be decremented only after that its value would decrease also in the ideal system approximated by QFQ+. For efficiency, QFQ+ keeps track only of the 'instantaneous' weight sum, increased and decreased immediately as the weight of an aggregate changes, and as an aggregate is created or destroyed (which, in its turn, happens as a consequence of some class being created/destroyed/changed). However, to avoid the problems caused to service guarantees by these immediate decreases, QFQ+ increments the system virtual time using the maximum value allowed for the weight sum, 2^10, in place of the dynamic, instantaneous value. The instantaneous value of the weight sum is used only to check whether a request of weight increase or a class creation can be satisfied. Unfortunately, the problems caused by this choice are worse than the temporary degradation of the service guarantees that may occur, when a class is changed or destroyed, if the instantaneous value of the weight sum was used to update the system virtual time. In fact, the fraction of the link bandwidth guaranteed by QFQ+ to each aggregate is equal to the ratio between the weight of the aggregate and the sum of the weights of the competing aggregates. The packet delay guaranteed to the aggregate is instead inversely proportional to the guaranteed bandwidth. By using the maximum possible value, and not the actual value of the weight sum, QFQ+ provides each aggregate with the worst possible service guarantees, and not with service guarantees related to the actual set of competing aggregates. To see the consequences of this fact, consider the following simple example. Suppose that only the following aggregates are backlogged, i.e., that only the classes in the following aggregates have packets to transmit: one aggregate with weight 10, say A, and ten aggregates with weight 1, say B1, B2, ..., B10. In particular, suppose that these aggregates are always backlogged. Given the weight distribution, the smoothest and fairest service order would be: A B1 A B2 A B3 A B4 A B5 A B6 A B7 A B8 A B9 A B10 A B1 A B2 ... QFQ+ would provide exactly this optimal service if it used the actual value for the weight sum instead of the maximum possible value, i.e., 11 instead of 2^10. In contrast, since QFQ+ uses the latter value, it serves aggregates as follows (easy to prove and to reproduce experimentally): A B1 B2 B3 B4 B5 B6 B7 B8 B9 B10 A A A A A A A A A A B1 B2 ... B10 A A ... By replacing 10 with N in the above example, and by increasing N, one can increase at will the maximum packet delay and the jitter experienced by the classes in aggregate A. This patch addresses this issue by just using the above 'instantaneous' value of the weight sum, instead of the maximum possible value, when updating the system virtual time. After the instantaneous weight sum is decreased, QFQ+ may deviate from the ideal service for a time interval in the order of the time to serve one maximum-size packet for each backlogged class. The worst-case extent of the deviation exhibited by QFQ+ during this time interval [1] is basically the same as of the deviation described above (but, without this patch, QFQ+ suffers from such a deviation all the time). Finally, this patch modifies the comment to the function qfq_slot_insert, to make it coherent with the fact that the weight sum used by QFQ+ can now be lower than the maximum possible value. [1] P. Valente, "Extending WF2Q+ to support a dynamic traffic mix", Proceedings of AAA-IDEA'05, June 2005. Signed-off-by: Paolo Valente Signed-off-by: David S. Miller --- net/sched/sch_qfq.c | 85 +++++++++++++++++++++++++++++++++++------------------ 1 file changed, 56 insertions(+), 29 deletions(-) (limited to 'net') diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index a7ab323849b..8056fb4e618 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -113,7 +113,6 @@ #define FRAC_BITS 30 /* fixed point arithmetic */ #define ONE_FP (1UL << FRAC_BITS) -#define IWSUM (ONE_FP/QFQ_MAX_WSUM) #define QFQ_MTU_SHIFT 16 /* to support TSO/GSO */ #define QFQ_MIN_LMAX 512 /* see qfq_slot_insert */ @@ -189,6 +188,7 @@ struct qfq_sched { struct qfq_aggregate *in_serv_agg; /* Aggregate being served. */ u32 num_active_agg; /* Num. of active aggregates */ u32 wsum; /* weight sum */ + u32 iwsum; /* inverse weight sum */ unsigned long bitmaps[QFQ_MAX_STATE]; /* Group bitmaps. */ struct qfq_group groups[QFQ_MAX_INDEX + 1]; /* The groups. */ @@ -314,6 +314,7 @@ static void qfq_update_agg(struct qfq_sched *q, struct qfq_aggregate *agg, q->wsum += (int) agg->class_weight * (new_num_classes - agg->num_classes); + q->iwsum = ONE_FP / q->wsum; agg->num_classes = new_num_classes; } @@ -340,6 +341,10 @@ static void qfq_destroy_agg(struct qfq_sched *q, struct qfq_aggregate *agg) { if (!hlist_unhashed(&agg->nonfull_next)) hlist_del_init(&agg->nonfull_next); + q->wsum -= agg->class_weight; + if (q->wsum != 0) + q->iwsum = ONE_FP / q->wsum; + if (q->in_serv_agg == agg) q->in_serv_agg = qfq_choose_next_agg(q); kfree(agg); @@ -834,38 +839,60 @@ static void qfq_make_eligible(struct qfq_sched *q) } } - /* - * The index of the slot in which the aggregate is to be inserted must - * not be higher than QFQ_MAX_SLOTS-2. There is a '-2' and not a '-1' - * because the start time of the group may be moved backward by one - * slot after the aggregate has been inserted, and this would cause - * non-empty slots to be right-shifted by one position. + * The index of the slot in which the input aggregate agg is to be + * inserted must not be higher than QFQ_MAX_SLOTS-2. There is a '-2' + * and not a '-1' because the start time of the group may be moved + * backward by one slot after the aggregate has been inserted, and + * this would cause non-empty slots to be right-shifted by one + * position. + * + * QFQ+ fully satisfies this bound to the slot index if the parameters + * of the classes are not changed dynamically, and if QFQ+ never + * happens to postpone the service of agg unjustly, i.e., it never + * happens that the aggregate becomes backlogged and eligible, or just + * eligible, while an aggregate with a higher approximated finish time + * is being served. In particular, in this case QFQ+ guarantees that + * the timestamps of agg are low enough that the slot index is never + * higher than 2. Unfortunately, QFQ+ cannot provide the same + * guarantee if it happens to unjustly postpone the service of agg, or + * if the parameters of some class are changed. + * + * As for the first event, i.e., an out-of-order service, the + * upper bound to the slot index guaranteed by QFQ+ grows to + * 2 + + * QFQ_MAX_AGG_CLASSES * ((1<budget -= len; - q->V += (u64)len * IWSUM; + q->V += (u64)len * q->iwsum; pr_debug("qfq dequeue: len %u F %lld now %lld\n", len, (unsigned long long) in_serv_agg->F, (unsigned long long) q->V); -- cgit v1.2.3-18-g5258 From d4b812dea4a236f729526facf97df1a9d18e191c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 18 Jul 2013 07:19:26 -0700 Subject: vlan: mask vlan prio bits In commit 48cc32d38a52d0b68f91a171a8d00531edc6a46e ("vlan: don't deliver frames for unknown vlans to protocols") Florian made sure we set pkt_type to PACKET_OTHERHOST if the vlan id is set and we could find a vlan device for this particular id. But we also have a problem if prio bits are set. Steinar reported an issue on a router receiving IPv6 frames with a vlan tag of 4000 (id 0, prio 2), and tunneled into a sit device, because skb->vlan_tci is set. Forwarded frame is completely corrupted : We can see (8100:4000) being inserted in the middle of IPv6 source address : 16:48:00.780413 IP6 2001:16d8:8100:4000:ee1c:0:9d9:bc87 > 9f94:4d95:2001:67c:29f4::: ICMP6, unknown icmp6 type (0), length 64 0x0000: 0000 0029 8000 c7c3 7103 0001 a0ae e651 0x0010: 0000 0000 ccce 0b00 0000 0000 1011 1213 0x0020: 1415 1617 1819 1a1b 1c1d 1e1f 2021 2223 0x0030: 2425 2627 2829 2a2b 2c2d 2e2f 3031 3233 It seems we are not really ready to properly cope with this right now. We can probably do better in future kernels : vlan_get_ingress_priority() should be a netdev property instead of a per vlan_dev one. For stable kernels, lets clear vlan_tci to fix the bugs. Reported-by: Steinar H. Gunderson Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/8021q/vlan_core.c | 2 +- net/core/dev.c | 11 +++++++++-- 2 files changed, 10 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 8a15eaadc4b..4a78c4de9f2 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -9,7 +9,7 @@ bool vlan_do_receive(struct sk_buff **skbp) { struct sk_buff *skb = *skbp; __be16 vlan_proto = skb->vlan_proto; - u16 vlan_id = skb->vlan_tci & VLAN_VID_MASK; + u16 vlan_id = vlan_tx_tag_get_id(skb); struct net_device *vlan_dev; struct vlan_pcpu_stats *rx_stats; diff --git a/net/core/dev.c b/net/core/dev.c index a3d8d44cb7f..26755dd40da 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3580,8 +3580,15 @@ ncls: } } - if (vlan_tx_nonzero_tag_present(skb)) - skb->pkt_type = PACKET_OTHERHOST; + if (unlikely(vlan_tx_tag_present(skb))) { + if (vlan_tx_tag_get_id(skb)) + skb->pkt_type = PACKET_OTHERHOST; + /* Note: we might in the future use prio bits + * and set skb->priority like in vlan_do_receive() + * For the time being, just ignore Priority Code Point + */ + skb->vlan_tci = 0; + } /* deliver only exact match when indicated */ null_or_dev = deliver_exact ? skb->dev : NULL; -- cgit v1.2.3-18-g5258 From 3e3aac497513c669e1c62c71e1d552ea85c1d974 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 18 Jul 2013 09:35:10 -0700 Subject: vlan: fix a race in egress prio management egress_priority_map[] hash table updates are protected by rtnl, and we never remove elements until device is dismantled. We have to make sure that before inserting an new element in hash table, all its fields are committed to memory or else another cpu could find corrupt values and crash. Signed-off-by: Eric Dumazet Cc: Patrick McHardy Signed-off-by: David S. Miller --- net/8021q/vlan_dev.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'net') diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 3a8c8fd63c8..1cd3d2a406f 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -73,6 +73,8 @@ vlan_dev_get_egress_qos_mask(struct net_device *dev, struct sk_buff *skb) { struct vlan_priority_tci_mapping *mp; + smp_rmb(); /* coupled with smp_wmb() in vlan_dev_set_egress_priority() */ + mp = vlan_dev_priv(dev)->egress_priority_map[(skb->priority & 0xF)]; while (mp) { if (mp->priority == skb->priority) { @@ -249,6 +251,11 @@ int vlan_dev_set_egress_priority(const struct net_device *dev, np->next = mp; np->priority = skb_prio; np->vlan_qos = vlan_qos; + /* Before inserting this element in hash table, make sure all its fields + * are committed to memory. + * coupled with smp_rmb() in vlan_dev_get_egress_qos_mask() + */ + smp_wmb(); vlan->egress_priority_map[skb_prio & 0xF] = np; if (vlan_qos) vlan->nr_egress_mappings++; -- cgit v1.2.3-18-g5258