From 05423b241311c9380b7280179295bac7794281b6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 26 Oct 2009 18:40:35 -0700 Subject: vlan: allow null VLAN ID to be used We currently use a 16 bit field (vlan_tci) to store VLAN ID/PRIO on a skb. Null value is used as a special value, meaning vlan tagging not enabled. This forbids use of null vlan ID. As pointed by David, some drivers use the 3 high order bits (PRIO) As VLAN ID is 12 bits, we can use the remaining bit (CFI) as a flag, and allow null VLAN ID. In case future code really wants to use VLAN_CFI_MASK, we'll have to use a bit outside of vlan_tci. #define VLAN_PRIO_MASK 0xe000 /* Priority Code Point */ #define VLAN_PRIO_SHIFT 13 #define VLAN_CFI_MASK 0x1000 /* Canonical Format Indicator */ #define VLAN_TAG_PRESENT VLAN_CFI_MASK #define VLAN_VID_MASK 0x0fff /* VLAN Identifier */ Reported-by: Gertjan Hofman Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/8021q/vlan.h | 2 +- net/8021q/vlan_dev.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'net/8021q') diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index 82570bc2a180..4ade5edf1033 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -89,7 +89,7 @@ static inline u32 vlan_get_ingress_priority(struct net_device *dev, { struct vlan_dev_info *vip = vlan_dev_info(dev); - return vip->ingress_priority_map[(vlan_tci >> 13) & 0x7]; + return vip->ingress_priority_map[(vlan_tci >> VLAN_PRIO_SHIFT) & 0x7]; } #ifdef CONFIG_VLAN_8021Q_GVRP diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 4198ec5c8abc..e3701977f58d 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -393,7 +393,7 @@ int vlan_dev_set_egress_priority(const struct net_device *dev, struct vlan_dev_info *vlan = vlan_dev_info(dev); struct vlan_priority_tci_mapping *mp = NULL; struct vlan_priority_tci_mapping *np; - u32 vlan_qos = (vlan_prio << 13) & 0xE000; + u32 vlan_qos = (vlan_prio << VLAN_PRIO_SHIFT) & VLAN_PRIO_MASK; /* See if a priority mapping exists.. */ mp = vlan->egress_priority_map[skb_prio & 0xF]; -- cgit v1.2.2 From 23289a37e2b127dfc4de1313fba15bb4c9f0cd5b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 27 Oct 2009 07:06:36 +0000 Subject: net: add a list_head parameter to dellink() method Adding a list_head parameter to rtnl_link_ops->dellink() methods allow us to queue devices on a list, in order to dismantle them all at once. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/8021q/vlan.c | 8 ++++---- net/8021q/vlan.h | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'net/8021q') diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 8836575f9d79..6b5c9dddaa72 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -140,7 +140,7 @@ static void vlan_rcu_free(struct rcu_head *rcu) vlan_group_free(container_of(rcu, struct vlan_group, rcu)); } -void unregister_vlan_dev(struct net_device *dev) +void unregister_vlan_dev(struct net_device *dev, struct list_head *head) { struct vlan_dev_info *vlan = vlan_dev_info(dev); struct net_device *real_dev = vlan->real_dev; @@ -164,7 +164,7 @@ void unregister_vlan_dev(struct net_device *dev) synchronize_net(); - unregister_netdevice(dev); + unregister_netdevice_queue(dev, head); /* If the group is now empty, kill off the group. */ if (grp->nr_vlans == 0) { @@ -535,7 +535,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, if (grp->nr_vlans == 1) i = VLAN_GROUP_ARRAY_LEN; - unregister_vlan_dev(vlandev); + unregister_vlan_dev(vlandev, NULL); } break; } @@ -642,7 +642,7 @@ static int vlan_ioctl_handler(struct net *net, void __user *arg) err = -EPERM; if (!capable(CAP_NET_ADMIN)) break; - unregister_vlan_dev(dev); + unregister_vlan_dev(dev, NULL); err = 0; break; diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index 4ade5edf1033..68f9290e6837 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -82,7 +82,7 @@ void vlan_dev_get_realdev_name(const struct net_device *dev, char *result); int vlan_check_real_dev(struct net_device *real_dev, u16 vlan_id); void vlan_setup(struct net_device *dev); int register_vlan_dev(struct net_device *dev); -void unregister_vlan_dev(struct net_device *dev); +void unregister_vlan_dev(struct net_device *dev, struct list_head *head); static inline u32 vlan_get_ingress_priority(struct net_device *dev, u16 vlan_tci) -- cgit v1.2.2 From 63c8099d90096db56ee1c66c31f05d4fcfbc1c69 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 27 Oct 2009 07:06:49 +0000 Subject: vlan: Optimize multiple unregistration Use unregister_netdevice_many() to speedup master device unregister. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/8021q/vlan.c | 49 +++++++++++++++++++++++++++++++++---------------- 1 file changed, 33 insertions(+), 16 deletions(-) (limited to 'net/8021q') diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 6b5c9dddaa72..511afe72af31 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -159,11 +159,12 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head) if (real_dev->features & NETIF_F_HW_VLAN_FILTER) ops->ndo_vlan_rx_kill_vid(real_dev, vlan_id); - vlan_group_set_device(grp, vlan_id, NULL); grp->nr_vlans--; - synchronize_net(); - + if (!grp->killall) { + vlan_group_set_device(grp, vlan_id, NULL); + synchronize_net(); + } unregister_netdevice_queue(dev, head); /* If the group is now empty, kill off the group. */ @@ -183,6 +184,34 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head) dev_put(real_dev); } +void unregister_vlan_dev_alls(struct vlan_group *grp) +{ + LIST_HEAD(list); + int i; + struct net_device *vlandev; + struct vlan_group save; + + memcpy(&save, grp, sizeof(save)); + memset(&grp->vlan_devices_arrays, 0, sizeof(grp->vlan_devices_arrays)); + grp->killall = 1; + + synchronize_net(); + + /* Delete all VLANs for this dev. */ + for (i = 0; i < VLAN_GROUP_ARRAY_LEN; i++) { + vlandev = vlan_group_get_device(&save, i); + if (!vlandev) + continue; + + unregister_vlan_dev(vlandev, &list); + if (grp->nr_vlans == 0) + break; + } + unregister_netdevice_many(&list); + for (i = 0; i < VLAN_GROUP_ARRAY_SPLIT_PARTS; i++) + kfree(save.vlan_devices_arrays[i]); +} + static void vlan_transfer_operstate(const struct net_device *dev, struct net_device *vlandev) { @@ -524,19 +553,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, break; case NETDEV_UNREGISTER: - /* Delete all VLANs for this dev. */ - for (i = 0; i < VLAN_GROUP_ARRAY_LEN; i++) { - vlandev = vlan_group_get_device(grp, i); - if (!vlandev) - continue; - - /* unregistration of last vlan destroys group, abort - * afterwards */ - if (grp->nr_vlans == 1) - i = VLAN_GROUP_ARRAY_LEN; - - unregister_vlan_dev(vlandev, NULL); - } + unregister_vlan_dev_alls(grp); break; } -- cgit v1.2.2 From d6534799410d2b53e5e80b8a90d6a8bab3de30ed Mon Sep 17 00:00:00 2001 From: Yi Zou Date: Wed, 28 Oct 2009 18:25:16 +0000 Subject: vlan: Add support to netdev_ops.ndo_fcoe_get_wwn for VLAN device Implements the netdev_ops.ndo_fcoe_get_wwn for VLAN device. Signed-off-by: Yi Zou Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- net/8021q/vlan_dev.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'net/8021q') diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index e3701977f58d..790fd55ec318 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -626,6 +626,17 @@ static int vlan_dev_fcoe_disable(struct net_device *dev) rc = ops->ndo_fcoe_disable(real_dev); return rc; } + +static int vlan_dev_fcoe_get_wwn(struct net_device *dev, u64 *wwn, int type) +{ + struct net_device *real_dev = vlan_dev_info(dev)->real_dev; + const struct net_device_ops *ops = real_dev->netdev_ops; + int rc = -EINVAL; + + if (ops->ndo_fcoe_get_wwn) + rc = ops->ndo_fcoe_get_wwn(real_dev, wwn, type); + return rc; +} #endif static void vlan_dev_change_rx_flags(struct net_device *dev, int change) @@ -791,6 +802,7 @@ static const struct net_device_ops vlan_netdev_ops = { .ndo_fcoe_ddp_done = vlan_dev_fcoe_ddp_done, .ndo_fcoe_enable = vlan_dev_fcoe_enable, .ndo_fcoe_disable = vlan_dev_fcoe_disable, + .ndo_fcoe_get_wwn = vlan_dev_fcoe_get_wwn, #endif }; @@ -813,6 +825,7 @@ static const struct net_device_ops vlan_netdev_accel_ops = { .ndo_fcoe_ddp_done = vlan_dev_fcoe_ddp_done, .ndo_fcoe_enable = vlan_dev_fcoe_enable, .ndo_fcoe_disable = vlan_dev_fcoe_disable, + .ndo_fcoe_get_wwn = vlan_dev_fcoe_get_wwn, #endif }; -- cgit v1.2.2 From 5b252f0c2f98df21fadf0f6cf189b87a0b938228 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Thu, 29 Oct 2009 07:17:09 +0000 Subject: gro: Name the GRO result enumeration type This clarifies which return and parameter types are GRO result codes and not RX result codes. Signed-off-by: Ben Hutchings Acked-by: Herbert Xu Signed-off-by: David S. Miller --- net/8021q/vlan_core.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'net/8021q') diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 7f7de1a04de6..47a80d65c3b7 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -74,8 +74,9 @@ u16 vlan_dev_vlan_id(const struct net_device *dev) } EXPORT_SYMBOL(vlan_dev_vlan_id); -static int vlan_gro_common(struct napi_struct *napi, struct vlan_group *grp, - unsigned int vlan_tci, struct sk_buff *skb) +static gro_result_t +vlan_gro_common(struct napi_struct *napi, struct vlan_group *grp, + unsigned int vlan_tci, struct sk_buff *skb) { struct sk_buff *p; -- cgit v1.2.2 From c7c4b3b6e976b95facbb723951bdcd554a3530a4 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Thu, 29 Oct 2009 21:36:53 -0700 Subject: gro: Change all receive functions to return GRO result codes This will allow drivers to adjust their receive path dynamically based on whether GRO is being applied successfully. Currently all in-tree callers ignore the return values of these functions and do not need to be changed. Signed-off-by: Ben Hutchings Acked-by: Herbert Xu Signed-off-by: David S. Miller --- net/8021q/vlan_core.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'net/8021q') diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 47a80d65c3b7..8d5ca2ac4f8d 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -102,11 +102,12 @@ drop: return GRO_DROP; } -int vlan_gro_receive(struct napi_struct *napi, struct vlan_group *grp, - unsigned int vlan_tci, struct sk_buff *skb) +gro_result_t vlan_gro_receive(struct napi_struct *napi, struct vlan_group *grp, + unsigned int vlan_tci, struct sk_buff *skb) { if (netpoll_rx_on(skb)) - return vlan_hwaccel_receive_skb(skb, grp, vlan_tci); + return vlan_hwaccel_receive_skb(skb, grp, vlan_tci) + ? GRO_DROP : GRO_NORMAL; skb_gro_reset_offset(skb); @@ -114,17 +115,18 @@ int vlan_gro_receive(struct napi_struct *napi, struct vlan_group *grp, } EXPORT_SYMBOL(vlan_gro_receive); -int vlan_gro_frags(struct napi_struct *napi, struct vlan_group *grp, - unsigned int vlan_tci) +gro_result_t vlan_gro_frags(struct napi_struct *napi, struct vlan_group *grp, + unsigned int vlan_tci) { struct sk_buff *skb = napi_frags_skb(napi); if (!skb) - return NET_RX_DROP; + return GRO_DROP; if (netpoll_rx_on(skb)) { skb->protocol = eth_type_trans(skb, skb->dev); - return vlan_hwaccel_receive_skb(skb, grp, vlan_tci); + return vlan_hwaccel_receive_skb(skb, grp, vlan_tci) + ? GRO_DROP : GRO_NORMAL; } return napi_frags_finish(napi, skb, -- cgit v1.2.2 From 29906f6a427d2004a515ebbcdc7b28bae8f6c19c Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Thu, 29 Oct 2009 23:43:00 -0700 Subject: vlan: cleanup multiple unregistrations The temporary copy of the VLAN group is not neccessary since the lower device is already in the process of being unregistered, if it was neccessary the memset of the global group would introduce a race condition. With this removed, the changes to the original code are only a few lines, so remove the new function and move the code back into vlan_device_event(). Signed-off-by: Patrick McHardy Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/8021q/vlan.c | 52 ++++++++++++++++++++-------------------------------- 1 file changed, 20 insertions(+), 32 deletions(-) (limited to 'net/8021q') diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 511afe72af31..39f8d0120104 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -161,10 +161,10 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head) grp->nr_vlans--; - if (!grp->killall) { - vlan_group_set_device(grp, vlan_id, NULL); + vlan_group_set_device(grp, vlan_id, NULL); + if (!grp->killall) synchronize_net(); - } + unregister_netdevice_queue(dev, head); /* If the group is now empty, kill off the group. */ @@ -184,34 +184,6 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head) dev_put(real_dev); } -void unregister_vlan_dev_alls(struct vlan_group *grp) -{ - LIST_HEAD(list); - int i; - struct net_device *vlandev; - struct vlan_group save; - - memcpy(&save, grp, sizeof(save)); - memset(&grp->vlan_devices_arrays, 0, sizeof(grp->vlan_devices_arrays)); - grp->killall = 1; - - synchronize_net(); - - /* Delete all VLANs for this dev. */ - for (i = 0; i < VLAN_GROUP_ARRAY_LEN; i++) { - vlandev = vlan_group_get_device(&save, i); - if (!vlandev) - continue; - - unregister_vlan_dev(vlandev, &list); - if (grp->nr_vlans == 0) - break; - } - unregister_netdevice_many(&list); - for (i = 0; i < VLAN_GROUP_ARRAY_SPLIT_PARTS; i++) - kfree(save.vlan_devices_arrays[i]); -} - static void vlan_transfer_operstate(const struct net_device *dev, struct net_device *vlandev) { @@ -456,6 +428,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, struct vlan_group *grp; int i, flgs; struct net_device *vlandev; + LIST_HEAD(list); if (is_vlan_dev(dev)) __vlan_device_event(dev, event); @@ -553,7 +526,22 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, break; case NETDEV_UNREGISTER: - unregister_vlan_dev_alls(grp); + /* Delete all VLANs for this dev. */ + grp->killall = 1; + + for (i = 0; i < VLAN_GROUP_ARRAY_LEN; i++) { + vlandev = vlan_group_get_device(grp, i); + if (!vlandev) + continue; + + /* unregistration of last vlan destroys group, abort + * afterwards */ + if (grp->nr_vlans == 1) + i = VLAN_GROUP_ARRAY_LEN; + + unregister_vlan_dev(vlandev, &list); + } + unregister_netdevice_many(&list); break; } -- cgit v1.2.2 From 81adee47dfb608df3ad0b91d230fb3cef75f0060 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 8 Nov 2009 00:53:51 -0800 Subject: net: Support specifying the network namespace upon device creation. There is no good reason to not support userspace specifying the network namespace during device creation, and it makes it easier to create a network device and pass it to a child network namespace with a well known name. We have to be careful to ensure that the target network namespace for the new device exists through the life of the call. To keep that logic clear I have factored out the network namespace grabbing logic into rtnl_link_get_net. In addtion we need to continue to pass the source network namespace to the rtnl_link_ops.newlink method so that we can find the base device source network namespace. Signed-off-by: Eric W. Biederman Acked-by: Eric Dumazet --- net/8021q/vlan_netlink.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/8021q') diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index a91504850195..3c9cf6a8e7fb 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -119,7 +119,7 @@ static int vlan_get_tx_queues(struct net *net, return 0; } -static int vlan_newlink(struct net_device *dev, +static int vlan_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { struct vlan_dev_info *vlan = vlan_dev_info(dev); @@ -131,7 +131,7 @@ static int vlan_newlink(struct net_device *dev, if (!tb[IFLA_LINK]) return -EINVAL; - real_dev = __dev_get_by_index(dev_net(dev), nla_get_u32(tb[IFLA_LINK])); + real_dev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK])); if (!real_dev) return -ENODEV; -- cgit v1.2.2 From 9e067597ee0e51a07bc158e9e2703ca676920e8b Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Tue, 10 Nov 2009 07:54:48 +0000 Subject: vlan: eliminate use of dev_base_lock Do not need to use read_lock(&dev_base_lock), use RCU instead. Signed-off-by: Stephen Hemminger Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/8021q/vlanproc.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'net/8021q') diff --git a/net/8021q/vlanproc.c b/net/8021q/vlanproc.c index 6262c335f3c2..9ec1f057c03a 100644 --- a/net/8021q/vlanproc.c +++ b/net/8021q/vlanproc.c @@ -201,18 +201,17 @@ int vlan_proc_rem_dev(struct net_device *vlandev) /* start read of /proc/net/vlan/config */ static void *vlan_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(dev_base_lock) + __acquires(rcu) { struct net_device *dev; struct net *net = seq_file_net(seq); loff_t i = 1; - read_lock(&dev_base_lock); - + rcu_read_lock(); if (*pos == 0) return SEQ_START_TOKEN; - for_each_netdev(net, dev) { + for_each_netdev_rcu(net, dev) { if (!is_vlan_dev(dev)) continue; @@ -234,7 +233,7 @@ static void *vlan_seq_next(struct seq_file *seq, void *v, loff_t *pos) if (v == SEQ_START_TOKEN) dev = net_device_entry(&net->dev_base_head); - for_each_netdev_continue(net, dev) { + for_each_netdev_continue_rcu(net, dev) { if (!is_vlan_dev(dev)) continue; @@ -245,9 +244,9 @@ static void *vlan_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void vlan_seq_stop(struct seq_file *seq, void *v) - __releases(dev_base_lock) + __releases(rcu) { - read_unlock(&dev_base_lock); + rcu_read_unlock(); } static int vlan_seq_show(struct seq_file *seq, void *v) -- cgit v1.2.2 From cbbef5e183079455763fc470ccf69008f92ab4b6 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 10 Nov 2009 06:14:24 +0000 Subject: vlan/macvlan: propagate transmission state to upper layers Both vlan and macvlan devices usually don't use a qdisc and immediately queue packets to the underlying device. Propagate transmission state of the underlying device to the upper layers so they can react on congestion and/or inform the sending process. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- net/8021q/vlan_dev.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/8021q') diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 790fd55ec318..915965942139 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -332,7 +332,7 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb, } else txq->tx_dropped++; - return NETDEV_TX_OK; + return ret; } static netdev_tx_t vlan_dev_hwaccel_hard_start_xmit(struct sk_buff *skb, @@ -358,7 +358,7 @@ static netdev_tx_t vlan_dev_hwaccel_hard_start_xmit(struct sk_buff *skb, } else txq->tx_dropped++; - return NETDEV_TX_OK; + return ret; } static int vlan_dev_change_mtu(struct net_device *dev, int new_mtu) -- cgit v1.2.2 From b93ab837a2d3eb394082c9eae4ee0a4f83060027 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 13 Nov 2009 06:33:11 +0000 Subject: vlan: Use __vlan_hwaccel_put_tag() in rx Commit 05423b241311c9380 (vlan: allow null VLAN ID to be used) forgot to update __vlan_hwaccel_rx() & vlan_gro_common() We need to set VLAN_TAG_PRESENT flag in skb->vlan_tci Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/8021q/vlan_core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/8021q') diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 8d5ca2ac4f8d..971d3755ae87 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -14,7 +14,7 @@ int __vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp, if (skb_bond_should_drop(skb)) goto drop; - skb->vlan_tci = vlan_tci; + __vlan_hwaccel_put_tag(skb, vlan_tci); skb->dev = vlan_group_get_device(grp, vlan_tci & VLAN_VID_MASK); if (!skb->dev) @@ -83,7 +83,7 @@ vlan_gro_common(struct napi_struct *napi, struct vlan_group *grp, if (skb_bond_should_drop(skb)) goto drop; - skb->vlan_tci = vlan_tci; + __vlan_hwaccel_put_tag(skb, vlan_tci); skb->dev = vlan_group_get_device(grp, vlan_tci & VLAN_VID_MASK); if (!skb->dev) -- cgit v1.2.2 From 9793241fe92f7d9303fb221e43fc598eb065f267 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 17 Nov 2009 04:53:09 +0000 Subject: vlan: Precise RX stats accounting With multi queue devices, its possible that several cpus call vlan RX routines simultaneously for the same vlan device. We update RX stats counter without any locking, so we can get slightly wrong counters. One possible fix is to use percpu counters, to get precise accounting and also get guarantee of no cache line ping pongs between cpus. Note: this adds 16 bytes (32 bytes on 64bit arches) of percpu data per vlan device. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/8021q/vlan.h | 17 +++++++++++++++++ net/8021q/vlan_core.c | 12 +++++++----- net/8021q/vlan_dev.c | 47 +++++++++++++++++++++++++++++++++++++++++------ 3 files changed, 65 insertions(+), 11 deletions(-) (limited to 'net/8021q') diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index 68f9290e6837..5685296017e9 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -16,6 +16,21 @@ struct vlan_priority_tci_mapping { struct vlan_priority_tci_mapping *next; }; + +/** + * struct vlan_rx_stats - VLAN percpu rx stats + * @rx_packets: number of received packets + * @rx_bytes: number of received bytes + * @multicast: number of received multicast packets + * @rx_errors: number of errors + */ +struct vlan_rx_stats { + unsigned long rx_packets; + unsigned long rx_bytes; + unsigned long multicast; + unsigned long rx_errors; +}; + /** * struct vlan_dev_info - VLAN private device data * @nr_ingress_mappings: number of ingress priority mappings @@ -29,6 +44,7 @@ struct vlan_priority_tci_mapping { * @dent: proc dir entry * @cnt_inc_headroom_on_tx: statistic - number of skb expansions on TX * @cnt_encap_on_xmit: statistic - number of skb encapsulations on TX + * @vlan_rx_stats: ptr to percpu rx stats */ struct vlan_dev_info { unsigned int nr_ingress_mappings; @@ -45,6 +61,7 @@ struct vlan_dev_info { struct proc_dir_entry *dent; unsigned long cnt_inc_headroom_on_tx; unsigned long cnt_encap_on_xmit; + struct vlan_rx_stats *vlan_rx_stats; }; static inline struct vlan_dev_info *vlan_dev_info(const struct net_device *dev) diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 971d3755ae87..e75a2f3b10af 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -31,7 +31,7 @@ EXPORT_SYMBOL(__vlan_hwaccel_rx); int vlan_hwaccel_do_receive(struct sk_buff *skb) { struct net_device *dev = skb->dev; - struct net_device_stats *stats; + struct vlan_rx_stats *rx_stats; skb->dev = vlan_dev_info(dev)->real_dev; netif_nit_deliver(skb); @@ -40,15 +40,17 @@ int vlan_hwaccel_do_receive(struct sk_buff *skb) skb->priority = vlan_get_ingress_priority(dev, skb->vlan_tci); skb->vlan_tci = 0; - stats = &dev->stats; - stats->rx_packets++; - stats->rx_bytes += skb->len; + rx_stats = per_cpu_ptr(vlan_dev_info(dev)->vlan_rx_stats, + smp_processor_id()); + + rx_stats->rx_packets++; + rx_stats->rx_bytes += skb->len; switch (skb->pkt_type) { case PACKET_BROADCAST: break; case PACKET_MULTICAST: - stats->multicast++; + rx_stats->multicast++; break; case PACKET_OTHERHOST: /* Our lower layer thinks this is not local, let's make sure. diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 915965942139..de0dc6bacbe8 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -140,7 +140,7 @@ int vlan_skb_recv(struct sk_buff *skb, struct net_device *dev, struct packet_type *ptype, struct net_device *orig_dev) { struct vlan_hdr *vhdr; - struct net_device_stats *stats; + struct vlan_rx_stats *rx_stats; u16 vlan_id; u16 vlan_tci; @@ -163,9 +163,10 @@ int vlan_skb_recv(struct sk_buff *skb, struct net_device *dev, goto err_unlock; } - stats = &skb->dev->stats; - stats->rx_packets++; - stats->rx_bytes += skb->len; + rx_stats = per_cpu_ptr(vlan_dev_info(dev)->vlan_rx_stats, + smp_processor_id()); + rx_stats->rx_packets++; + rx_stats->rx_bytes += skb->len; skb_pull_rcsum(skb, VLAN_HLEN); @@ -180,7 +181,7 @@ int vlan_skb_recv(struct sk_buff *skb, struct net_device *dev, break; case PACKET_MULTICAST: - stats->multicast++; + rx_stats->multicast++; break; case PACKET_OTHERHOST: @@ -200,7 +201,7 @@ int vlan_skb_recv(struct sk_buff *skb, struct net_device *dev, skb = vlan_check_reorder_header(skb); if (!skb) { - stats->rx_errors++; + rx_stats->rx_errors++; goto err_unlock; } @@ -731,6 +732,11 @@ static int vlan_dev_init(struct net_device *dev) subclass = 1; vlan_dev_set_lockdep_class(dev, subclass); + + vlan_dev_info(dev)->vlan_rx_stats = alloc_percpu(struct vlan_rx_stats); + if (!vlan_dev_info(dev)->vlan_rx_stats) + return -ENOMEM; + return 0; } @@ -740,6 +746,8 @@ static void vlan_dev_uninit(struct net_device *dev) struct vlan_dev_info *vlan = vlan_dev_info(dev); int i; + free_percpu(vlan->vlan_rx_stats); + vlan->vlan_rx_stats = NULL; for (i = 0; i < ARRAY_SIZE(vlan->egress_priority_map); i++) { while ((pm = vlan->egress_priority_map[i]) != NULL) { vlan->egress_priority_map[i] = pm->next; @@ -775,6 +783,31 @@ static u32 vlan_ethtool_get_flags(struct net_device *dev) return dev_ethtool_get_flags(vlan->real_dev); } +static struct net_device_stats *vlan_dev_get_stats(struct net_device *dev) +{ + struct net_device_stats *stats = &dev->stats; + + dev_txq_stats_fold(dev, stats); + + if (vlan_dev_info(dev)->vlan_rx_stats) { + struct vlan_rx_stats *p, rx = {0}; + int i; + + for_each_possible_cpu(i) { + p = per_cpu_ptr(vlan_dev_info(dev)->vlan_rx_stats, i); + rx.rx_packets += p->rx_packets; + rx.rx_bytes += p->rx_bytes; + rx.rx_errors += p->rx_errors; + rx.multicast += p->multicast; + } + stats->rx_packets = rx.rx_packets; + stats->rx_bytes = rx.rx_bytes; + stats->rx_errors = rx.rx_errors; + stats->multicast = rx.multicast; + } + return stats; +} + static const struct ethtool_ops vlan_ethtool_ops = { .get_settings = vlan_ethtool_get_settings, .get_drvinfo = vlan_ethtool_get_drvinfo, @@ -797,6 +830,7 @@ static const struct net_device_ops vlan_netdev_ops = { .ndo_change_rx_flags = vlan_dev_change_rx_flags, .ndo_do_ioctl = vlan_dev_ioctl, .ndo_neigh_setup = vlan_dev_neigh_setup, + .ndo_get_stats = vlan_dev_get_stats, #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) .ndo_fcoe_ddp_setup = vlan_dev_fcoe_ddp_setup, .ndo_fcoe_ddp_done = vlan_dev_fcoe_ddp_done, @@ -820,6 +854,7 @@ static const struct net_device_ops vlan_netdev_accel_ops = { .ndo_change_rx_flags = vlan_dev_change_rx_flags, .ndo_do_ioctl = vlan_dev_ioctl, .ndo_neigh_setup = vlan_dev_neigh_setup, + .ndo_get_stats = vlan_dev_get_stats, #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) .ndo_fcoe_ddp_setup = vlan_dev_fcoe_ddp_setup, .ndo_fcoe_ddp_done = vlan_dev_fcoe_ddp_done, -- cgit v1.2.2 From f99189b186f3922ede4fa33c02f6edc735b8c981 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 17 Nov 2009 10:42:49 +0000 Subject: netns: net_identifiers should be read_mostly Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/8021q/vlan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/8021q') diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 39f8d0120104..d9cb020029b9 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -41,7 +41,7 @@ /* Global VLAN variables */ -int vlan_net_id; +int vlan_net_id __read_mostly; /* Our listing of VLAN group(s) */ static struct hlist_head vlan_group_hash[VLAN_GRP_HASH_SIZE]; -- cgit v1.2.2 From 5e7565930524410f097f5b04f8aba663089a6ffc Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 25 Nov 2009 07:54:54 +0000 Subject: vlan: support "loose binding" to the underlying network device Currently the UP/DOWN state of VLANs is synchronized to the state of the underlying device, meaning all VLANs are set down once the underlying device is set down. This causes all routes to the VLAN devices to vanish. Add a flag to specify a "loose binding" mode, in which only the operstate is transfered, but the VLAN device state is independant. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- net/8021q/vlan.c | 9 +++++++-- net/8021q/vlan_dev.c | 6 ++++-- net/8021q/vlan_netlink.c | 3 ++- 3 files changed, 13 insertions(+), 5 deletions(-) (limited to 'net/8021q') diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 1483243edf14..225aa2fac0e3 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -431,6 +431,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, struct vlan_group *grp; int i, flgs; struct net_device *vlandev; + struct vlan_dev_info *vlan; LIST_HEAD(list); if (is_vlan_dev(dev)) @@ -507,7 +508,9 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, if (!(flgs & IFF_UP)) continue; - dev_change_flags(vlandev, flgs & ~IFF_UP); + vlan = vlan_dev_info(vlandev); + if (!(vlan->flags & VLAN_FLAG_LOOSE_BINDING)) + dev_change_flags(vlandev, flgs & ~IFF_UP); vlan_transfer_operstate(dev, vlandev); } break; @@ -523,7 +526,9 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, if (flgs & IFF_UP) continue; - dev_change_flags(vlandev, flgs | IFF_UP); + vlan = vlan_dev_info(vlandev); + if (!(vlan->flags & VLAN_FLAG_LOOSE_BINDING)) + dev_change_flags(vlandev, flgs | IFF_UP); vlan_transfer_operstate(dev, vlandev); } break; diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index de0dc6bacbe8..b7889782047e 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -431,7 +431,8 @@ int vlan_dev_change_flags(const struct net_device *dev, u32 flags, u32 mask) struct vlan_dev_info *vlan = vlan_dev_info(dev); u32 old_flags = vlan->flags; - if (mask & ~(VLAN_FLAG_REORDER_HDR | VLAN_FLAG_GVRP)) + if (mask & ~(VLAN_FLAG_REORDER_HDR | VLAN_FLAG_GVRP | + VLAN_FLAG_LOOSE_BINDING)) return -EINVAL; vlan->flags = (old_flags & ~mask) | (flags & mask); @@ -456,7 +457,8 @@ static int vlan_dev_open(struct net_device *dev) struct net_device *real_dev = vlan->real_dev; int err; - if (!(real_dev->flags & IFF_UP)) + if (!(real_dev->flags & IFF_UP) && + !(vlan->flags & VLAN_FLAG_LOOSE_BINDING)) return -ENETDOWN; if (compare_ether_addr(dev->dev_addr, real_dev->dev_addr)) { diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index 3c9cf6a8e7fb..ddc105734af7 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -60,7 +60,8 @@ static int vlan_validate(struct nlattr *tb[], struct nlattr *data[]) if (data[IFLA_VLAN_FLAGS]) { flags = nla_data(data[IFLA_VLAN_FLAGS]); if ((flags->flags & flags->mask) & - ~(VLAN_FLAG_REORDER_HDR | VLAN_FLAG_GVRP)) + ~(VLAN_FLAG_REORDER_HDR | VLAN_FLAG_GVRP | + VLAN_FLAG_LOOSE_BINDING)) return -EINVAL; } -- cgit v1.2.2 From 946d1a9298c9e592b189a168326603c92d782b5f Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 29 Nov 2009 15:46:05 +0000 Subject: net: Simplify vlan pernet operations. Take advantage of the new pernet automatic storage management, and stop using compatibility network namespace functions. Signed-off-by: Eric W. Biederman Signed-off-by: David S. Miller --- net/8021q/vlan.c | 33 +++++++-------------------------- 1 file changed, 7 insertions(+), 26 deletions(-) (limited to 'net/8021q') diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 225aa2fac0e3..91e9073e1995 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -686,47 +686,28 @@ out: static int vlan_init_net(struct net *net) { + struct vlan_net *vn = net_generic(net, vlan_net_id); int err; - struct vlan_net *vn; - - err = -ENOMEM; - vn = kzalloc(sizeof(struct vlan_net), GFP_KERNEL); - if (vn == NULL) - goto err_alloc; - - err = net_assign_generic(net, vlan_net_id, vn); - if (err < 0) - goto err_assign; vn->name_type = VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD; err = vlan_proc_init(net); - if (err < 0) - goto err_proc; - return 0; - -err_proc: - /* nothing */ -err_assign: - kfree(vn); -err_alloc: return err; } static void vlan_exit_net(struct net *net) { - struct vlan_net *vn; - - vn = net_generic(net, vlan_net_id); rtnl_kill_links(net, &vlan_link_ops); + vlan_proc_cleanup(net); - kfree(vn); } static struct pernet_operations vlan_net_ops = { .init = vlan_init_net, .exit = vlan_exit_net, + .id = &vlan_net_id, + .size = sizeof(struct vlan_net), }; static int __init vlan_proto_init(void) @@ -736,7 +717,7 @@ static int __init vlan_proto_init(void) pr_info("%s v%s %s\n", vlan_fullname, vlan_version, vlan_copyright); pr_info("All bugs added by %s\n", vlan_buggyright); - err = register_pernet_gen_device(&vlan_net_id, &vlan_net_ops); + err = register_pernet_device(&vlan_net_ops); if (err < 0) goto err0; @@ -761,7 +742,7 @@ err4: err3: unregister_netdevice_notifier(&vlan_notifier_block); err2: - unregister_pernet_gen_device(vlan_net_id, &vlan_net_ops); + unregister_pernet_device(&vlan_net_ops); err0: return err; } @@ -781,7 +762,7 @@ static void __exit vlan_cleanup_module(void) for (i = 0; i < VLAN_GRP_HASH_SIZE; i++) BUG_ON(!hlist_empty(&vlan_group_hash[i])); - unregister_pernet_gen_device(vlan_net_id, &vlan_net_ops); + unregister_pernet_device(&vlan_net_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ vlan_gvrp_uninit(); -- cgit v1.2.2 From 91e2ff3528ac90b9dbcb04b76488e8ad74e3d3d9 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 2 Dec 2009 13:19:08 +0000 Subject: net: Teach vlans to cleanup as a pernet subsystem Take advantage of the fact that an explicit rtnl_kill_links is unnecessary (and skipping it improves batching), as network namespace exit calls dellink on all remaining virtual devices, and rtnl_link_unregister calls dellink on all outstanding devices in that network namespace. To do this we need to leave the vlan proc directories in place until after network device exit time, which is done by using register_pernet_subsys instead of register_pernet_device. Signed-off-by: Eric W. Biederman Signed-off-by: David S. Miller --- net/8021q/vlan.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'net/8021q') diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 91e9073e1995..ec3769295dac 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -698,8 +698,6 @@ static int vlan_init_net(struct net *net) static void vlan_exit_net(struct net *net) { - rtnl_kill_links(net, &vlan_link_ops); - vlan_proc_cleanup(net); } @@ -717,7 +715,7 @@ static int __init vlan_proto_init(void) pr_info("%s v%s %s\n", vlan_fullname, vlan_version, vlan_copyright); pr_info("All bugs added by %s\n", vlan_buggyright); - err = register_pernet_device(&vlan_net_ops); + err = register_pernet_subsys(&vlan_net_ops); if (err < 0) goto err0; @@ -742,7 +740,7 @@ err4: err3: unregister_netdevice_notifier(&vlan_notifier_block); err2: - unregister_pernet_device(&vlan_net_ops); + unregister_pernet_subsys(&vlan_net_ops); err0: return err; } @@ -762,7 +760,7 @@ static void __exit vlan_cleanup_module(void) for (i = 0; i < VLAN_GRP_HASH_SIZE; i++) BUG_ON(!hlist_empty(&vlan_group_hash[i])); - unregister_pernet_device(&vlan_net_ops); + unregister_pernet_subsys(&vlan_net_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ vlan_gvrp_uninit(); -- cgit v1.2.2 From fc4a7489663250360cd40d5adf06a08d1c5d54df Mon Sep 17 00:00:00 2001 From: Patrick Mullaney Date: Thu, 3 Dec 2009 15:59:22 -0800 Subject: netdevice: provide common routine for macvlan and vlan operstate management Provide common routine for the transition of operational state for a leaf device during a root device transition. Signed-off-by: Patrick Mullaney Acked-by: Arnd Bergmann Acked-by: Patrick McHardy Signed-off-by: David S. Miller --- net/8021q/vlan.c | 29 ++++------------------------- 1 file changed, 4 insertions(+), 25 deletions(-) (limited to 'net/8021q') diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index ec3769295dac..33f90e7362cc 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -184,27 +184,6 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head) dev_put(real_dev); } -static void vlan_transfer_operstate(const struct net_device *dev, - struct net_device *vlandev) -{ - /* Have to respect userspace enforced dormant state - * of real device, also must allow supplicant running - * on VLAN device - */ - if (dev->operstate == IF_OPER_DORMANT) - netif_dormant_on(vlandev); - else - netif_dormant_off(vlandev); - - if (netif_carrier_ok(dev)) { - if (!netif_carrier_ok(vlandev)) - netif_carrier_on(vlandev); - } else { - if (netif_carrier_ok(vlandev)) - netif_carrier_off(vlandev); - } -} - int vlan_check_real_dev(struct net_device *real_dev, u16 vlan_id) { const char *name = real_dev->name; @@ -262,7 +241,7 @@ int register_vlan_dev(struct net_device *dev) /* Account for reference in struct vlan_dev_info */ dev_hold(real_dev); - vlan_transfer_operstate(real_dev, dev); + netif_stacked_transfer_operstate(real_dev, dev); linkwatch_fire_event(dev); /* _MUST_ call rfc2863_policy() */ /* So, got the sucker initialized, now lets place @@ -453,7 +432,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, if (!vlandev) continue; - vlan_transfer_operstate(dev, vlandev); + netif_stacked_transfer_operstate(dev, vlandev); } break; @@ -511,7 +490,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, vlan = vlan_dev_info(vlandev); if (!(vlan->flags & VLAN_FLAG_LOOSE_BINDING)) dev_change_flags(vlandev, flgs & ~IFF_UP); - vlan_transfer_operstate(dev, vlandev); + netif_stacked_transfer_operstate(dev, vlandev); } break; @@ -529,7 +508,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, vlan = vlan_dev_info(vlandev); if (!(vlan->flags & VLAN_FLAG_LOOSE_BINDING)) dev_change_flags(vlandev, flgs | IFF_UP); - vlan_transfer_operstate(dev, vlandev); + netif_stacked_transfer_operstate(dev, vlandev); } break; -- cgit v1.2.2 From bf9ae5386bca8836c16e69ab8fdbe46767d7452a Mon Sep 17 00:00:00 2001 From: Octavian Purdila Date: Sat, 26 Dec 2009 11:50:59 +0000 Subject: llc: use dev_hard_header Using dev_hard_header allows us to use LLC with VLANs and potentially other Ethernet/TokernRing specific encapsulations. It also removes code duplication between LLC and Ethernet/TokenRing core code. Signed-off-by: Octavian Purdila Signed-off-by: David S. Miller --- net/8021q/vlan_dev.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'net/8021q') diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index b7889782047e..77a49ffdd0ef 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -263,11 +263,10 @@ static int vlan_dev_hard_header(struct sk_buff *skb, struct net_device *dev, vhdr->h_vlan_TCI = htons(vlan_tci); /* - * Set the protocol type. For a packet of type ETH_P_802_3 we - * put the length in here instead. It is up to the 802.2 - * layer to carry protocol information. + * Set the protocol type. For a packet of type ETH_P_802_3/2 we + * put the length in here instead. */ - if (type != ETH_P_802_3) + if (type != ETH_P_802_3 && type != ETH_P_802_2) vhdr->h_vlan_encapsulated_proto = htons(type); else vhdr->h_vlan_encapsulated_proto = htons(len); -- cgit v1.2.2 From 1f3c8804acba841b5573b953f5560d2683d2db0d Mon Sep 17 00:00:00 2001 From: Andy Gospodarek Date: Mon, 14 Dec 2009 10:48:58 +0000 Subject: bonding: allow arp_ip_targets on separate vlans to use arp validation This allows a bond device to specify an arp_ip_target as a host that is not on the same vlan as the base bond device and still use arp validation. A configuration like this, now works: BONDING_OPTS="mode=active-backup arp_interval=1000 arp_ip_target=10.0.100.1 arp_validate=3" 1: lo: mtu 16436 qdisc noqueue link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00 inet 127.0.0.1/8 scope host lo inet6 ::1/128 scope host valid_lft forever preferred_lft forever 2: eth1: mtu 1500 qdisc pfifo_fast master bond0 qlen 1000 link/ether 00:13:21:be:33:e9 brd ff:ff:ff:ff:ff:ff 3: eth0: mtu 1500 qdisc pfifo_fast master bond0 qlen 1000 link/ether 00:13:21:be:33:e9 brd ff:ff:ff:ff:ff:ff 8: bond0: mtu 1500 qdisc noqueue link/ether 00:13:21:be:33:e9 brd ff:ff:ff:ff:ff:ff inet6 fe80::213:21ff:febe:33e9/64 scope link valid_lft forever preferred_lft forever 9: bond0.100@bond0: mtu 1500 qdisc noqueue link/ether 00:13:21:be:33:e9 brd ff:ff:ff:ff:ff:ff inet 10.0.100.2/24 brd 10.0.100.255 scope global bond0.100 inet6 fe80::213:21ff:febe:33e9/64 scope link valid_lft forever preferred_lft forever Ethernet Channel Bonding Driver: v3.6.0 (September 26, 2009) Bonding Mode: fault-tolerance (active-backup) Primary Slave: None Currently Active Slave: eth1 MII Status: up MII Polling Interval (ms): 0 Up Delay (ms): 0 Down Delay (ms): 0 ARP Polling Interval (ms): 1000 ARP IP target/s (n.n.n.n form): 10.0.100.1 Slave Interface: eth1 MII Status: up Link Failure Count: 1 Permanent HW addr: 00:40:05:30:ff:30 Slave Interface: eth0 MII Status: up Link Failure Count: 0 Permanent HW addr: 00:13:21:be:33:e9 Signed-off-by: Andy Gospodarek Signed-off-by: Jay Vosburgh Signed-off-by: David S. Miller --- net/8021q/vlan_core.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/8021q') diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index e75a2f3b10af..c0316e0ca6e8 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -14,6 +14,7 @@ int __vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp, if (skb_bond_should_drop(skb)) goto drop; + skb->skb_iif = skb->dev->ifindex; __vlan_hwaccel_put_tag(skb, vlan_tci); skb->dev = vlan_group_get_device(grp, vlan_tci & VLAN_VID_MASK); @@ -85,6 +86,7 @@ vlan_gro_common(struct napi_struct *napi, struct vlan_group *grp, if (skb_bond_should_drop(skb)) goto drop; + skb->skb_iif = skb->dev->ifindex; __vlan_hwaccel_put_tag(skb, vlan_tci); skb->dev = vlan_group_get_device(grp, vlan_tci & VLAN_VID_MASK); -- cgit v1.2.2 From 2c8c1e7297e19bdef3c178c3ea41d898a7716e3e Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Sun, 17 Jan 2010 03:35:32 +0000 Subject: net: spread __net_init, __net_exit __net_init/__net_exit are apparently not going away, so use them to full extent. In some cases __net_init was removed, because it was called from __net_exit code. Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- net/8021q/vlan.c | 4 ++-- net/8021q/vlanproc.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'net/8021q') diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 33f90e7362cc..453512266ea1 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -663,7 +663,7 @@ out: return err; } -static int vlan_init_net(struct net *net) +static int __net_init vlan_init_net(struct net *net) { struct vlan_net *vn = net_generic(net, vlan_net_id); int err; @@ -675,7 +675,7 @@ static int vlan_init_net(struct net *net) return err; } -static void vlan_exit_net(struct net *net) +static void __net_exit vlan_exit_net(struct net *net) { vlan_proc_cleanup(net); } diff --git a/net/8021q/vlanproc.c b/net/8021q/vlanproc.c index 9ec1f057c03a..afead353e215 100644 --- a/net/8021q/vlanproc.c +++ b/net/8021q/vlanproc.c @@ -140,7 +140,7 @@ void vlan_proc_cleanup(struct net *net) * Create /proc/net/vlan entries */ -int vlan_proc_init(struct net *net) +int __net_init vlan_proc_init(struct net *net) { struct vlan_net *vn = net_generic(net, vlan_net_id); -- cgit v1.2.2 From 2dc85e91d05be91343033df78e4e6d99dc7ea50e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 24 Jan 2010 19:52:24 -0800 Subject: vlan: fix vlan_skb_recv() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Bruno Prémont found commit 9793241fe92f7d930 (vlan: Precise RX stats accounting) added a regression for non hw accelerated vlans. [ 26.390576] BUG: unable to handle kernel NULL pointer dereference at (null) [ 26.396369] IP: [] vlan_skb_recv+0x89/0x280 [8021q] vlan_dev_info() was used with original device, instead of skb->dev. Also spotted by Américo Wang. Reported-By: Bruno Prémont Tested-By: Bruno Prémont Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/8021q/vlan_dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/8021q') diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index b7889782047e..c1b92cab46c7 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -163,7 +163,7 @@ int vlan_skb_recv(struct sk_buff *skb, struct net_device *dev, goto err_unlock; } - rx_stats = per_cpu_ptr(vlan_dev_info(dev)->vlan_rx_stats, + rx_stats = per_cpu_ptr(vlan_dev_info(skb->dev)->vlan_rx_stats, smp_processor_id()); rx_stats->rx_packets++; rx_stats->rx_bytes += skb->len; -- cgit v1.2.2 From 8a83a00b0735190384a348156837918271034144 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sat, 30 Jan 2010 12:23:03 +0000 Subject: net: maintain namespace isolation between vlan and real device In the vlan and macvlan drivers, the start_xmit function forwards data to the dev_queue_xmit function for another device, which may potentially belong to a different namespace. To make sure that classification stays within a single namespace, this resets the potentially critical fields. Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- net/8021q/vlan_dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/8021q') diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index a9e1f1785614..9e83272fc5b0 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -322,7 +322,7 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb, } - skb->dev = vlan_dev_info(dev)->real_dev; + skb_set_dev(skb, vlan_dev_info(dev)->real_dev); len = skb->len; ret = dev_queue_xmit(skb); -- cgit v1.2.2 From 7d720c3e4f0c4fc152a6bf17e24244a3c85412d2 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 16 Feb 2010 15:20:26 +0000 Subject: percpu: add __percpu sparse annotations to net Add __percpu sparse annotations to net. These annotations are to make sparse consider percpu variables to be in a different address space and warn if accessed without going through percpu accessors. This patch doesn't affect normal builds. The macro and type tricks around snmp stats make things a bit interesting. DEFINE/DECLARE_SNMP_STAT() macros mark the target field as __percpu and SNMP_UPD_PO_STATS() macro is updated accordingly. All snmp_mib_*() users which used to cast the argument to (void **) are updated to cast it to (void __percpu **). Signed-off-by: Tejun Heo Acked-by: David S. Miller Cc: Patrick McHardy Cc: Arnaldo Carvalho de Melo Cc: Vlad Yasevich Cc: netdev@vger.kernel.org Signed-off-by: David S. Miller --- net/8021q/vlan.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/8021q') diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index 5685296017e9..6abdcac1b2e8 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -61,7 +61,7 @@ struct vlan_dev_info { struct proc_dir_entry *dent; unsigned long cnt_inc_headroom_on_tx; unsigned long cnt_encap_on_xmit; - struct vlan_rx_stats *vlan_rx_stats; + struct vlan_rx_stats __percpu *vlan_rx_stats; }; static inline struct vlan_dev_info *vlan_dev_info(const struct net_device *dev) -- cgit v1.2.2 From 0641e4fbf2f824faee00ea74c459a088d94905fd Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 18 Mar 2010 21:16:45 -0700 Subject: net: Potential null skb->dev dereference When doing "ifenslave -d bond0 eth0", there is chance to get NULL dereference in netif_receive_skb(), because dev->master suddenly becomes NULL after we tested it. We should use ACCESS_ONCE() to avoid this (or rcu_dereference()) Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/8021q/vlan_core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/8021q') diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index c0316e0ca6e8..c584a0af77d3 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -11,7 +11,7 @@ int __vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp, if (netpoll_rx(skb)) return NET_RX_DROP; - if (skb_bond_should_drop(skb)) + if (skb_bond_should_drop(skb, ACCESS_ONCE(skb->dev->master))) goto drop; skb->skb_iif = skb->dev->ifindex; @@ -83,7 +83,7 @@ vlan_gro_common(struct napi_struct *napi, struct vlan_group *grp, { struct sk_buff *p; - if (skb_bond_should_drop(skb)) + if (skb_bond_should_drop(skb, ACCESS_ONCE(skb->dev->master))) goto drop; skb->skb_iif = skb->dev->ifindex; -- cgit v1.2.2 From 669d3e0babb40018dd6e78f4093c13a2eac73866 Mon Sep 17 00:00:00 2001 From: Vasu Dev Date: Tue, 23 Mar 2010 14:41:45 +0000 Subject: vlan: adds vlan_dev_select_queue This is required to correctly select vlan tx queue for a driver supporting multi tx queue with ndo_select_queue implemented since currently selected vlan tx queue is unaligned to selected queue by real net_devce ndo_select_queue. Unaligned vlan tx queue selection causes thrash with higher vlan tx lock contention for least fcoe traffic and wrong socket tx queue_mapping for ixgbe having ndo_select_queue implemented. -v2 As per Eric Dumazet comments, mirrored vlan net_device_ops to have them with and without vlan_dev_select_queue and then select according to real dev ndo_select_queue present or not for a vlan net_device. This is to completely skip vlan_dev_select_queue calling for real net_device not supporting ndo_select_queue. Signed-off-by: Vasu Dev Signed-off-by: Jeff Kirsher Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/8021q/vlan_dev.c | 71 +++++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 68 insertions(+), 3 deletions(-) (limited to 'net/8021q') diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 9e83272fc5b0..2fd057c81bbf 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -361,6 +361,14 @@ static netdev_tx_t vlan_dev_hwaccel_hard_start_xmit(struct sk_buff *skb, return ret; } +static u16 vlan_dev_select_queue(struct net_device *dev, struct sk_buff *skb) +{ + struct net_device *rdev = vlan_dev_info(dev)->real_dev; + const struct net_device_ops *ops = rdev->netdev_ops; + + return ops->ndo_select_queue(rdev, skb); +} + static int vlan_dev_change_mtu(struct net_device *dev, int new_mtu) { /* TODO: gotta make sure the underlying layer can handle it, @@ -688,7 +696,8 @@ static const struct header_ops vlan_header_ops = { .parse = eth_header_parse, }; -static const struct net_device_ops vlan_netdev_ops, vlan_netdev_accel_ops; +static const struct net_device_ops vlan_netdev_ops, vlan_netdev_accel_ops, + vlan_netdev_ops_sq, vlan_netdev_accel_ops_sq; static int vlan_dev_init(struct net_device *dev) { @@ -722,11 +731,17 @@ static int vlan_dev_init(struct net_device *dev) if (real_dev->features & NETIF_F_HW_VLAN_TX) { dev->header_ops = real_dev->header_ops; dev->hard_header_len = real_dev->hard_header_len; - dev->netdev_ops = &vlan_netdev_accel_ops; + if (real_dev->netdev_ops->ndo_select_queue) + dev->netdev_ops = &vlan_netdev_accel_ops_sq; + else + dev->netdev_ops = &vlan_netdev_accel_ops; } else { dev->header_ops = &vlan_header_ops; dev->hard_header_len = real_dev->hard_header_len + VLAN_HLEN; - dev->netdev_ops = &vlan_netdev_ops; + if (real_dev->netdev_ops->ndo_select_queue) + dev->netdev_ops = &vlan_netdev_ops_sq; + else + dev->netdev_ops = &vlan_netdev_ops; } if (is_vlan_dev(real_dev)) @@ -865,6 +880,56 @@ static const struct net_device_ops vlan_netdev_accel_ops = { #endif }; +static const struct net_device_ops vlan_netdev_ops_sq = { + .ndo_select_queue = vlan_dev_select_queue, + .ndo_change_mtu = vlan_dev_change_mtu, + .ndo_init = vlan_dev_init, + .ndo_uninit = vlan_dev_uninit, + .ndo_open = vlan_dev_open, + .ndo_stop = vlan_dev_stop, + .ndo_start_xmit = vlan_dev_hard_start_xmit, + .ndo_validate_addr = eth_validate_addr, + .ndo_set_mac_address = vlan_dev_set_mac_address, + .ndo_set_rx_mode = vlan_dev_set_rx_mode, + .ndo_set_multicast_list = vlan_dev_set_rx_mode, + .ndo_change_rx_flags = vlan_dev_change_rx_flags, + .ndo_do_ioctl = vlan_dev_ioctl, + .ndo_neigh_setup = vlan_dev_neigh_setup, + .ndo_get_stats = vlan_dev_get_stats, +#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) + .ndo_fcoe_ddp_setup = vlan_dev_fcoe_ddp_setup, + .ndo_fcoe_ddp_done = vlan_dev_fcoe_ddp_done, + .ndo_fcoe_enable = vlan_dev_fcoe_enable, + .ndo_fcoe_disable = vlan_dev_fcoe_disable, + .ndo_fcoe_get_wwn = vlan_dev_fcoe_get_wwn, +#endif +}; + +static const struct net_device_ops vlan_netdev_accel_ops_sq = { + .ndo_select_queue = vlan_dev_select_queue, + .ndo_change_mtu = vlan_dev_change_mtu, + .ndo_init = vlan_dev_init, + .ndo_uninit = vlan_dev_uninit, + .ndo_open = vlan_dev_open, + .ndo_stop = vlan_dev_stop, + .ndo_start_xmit = vlan_dev_hwaccel_hard_start_xmit, + .ndo_validate_addr = eth_validate_addr, + .ndo_set_mac_address = vlan_dev_set_mac_address, + .ndo_set_rx_mode = vlan_dev_set_rx_mode, + .ndo_set_multicast_list = vlan_dev_set_rx_mode, + .ndo_change_rx_flags = vlan_dev_change_rx_flags, + .ndo_do_ioctl = vlan_dev_ioctl, + .ndo_neigh_setup = vlan_dev_neigh_setup, + .ndo_get_stats = vlan_dev_get_stats, +#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) + .ndo_fcoe_ddp_setup = vlan_dev_fcoe_ddp_setup, + .ndo_fcoe_ddp_done = vlan_dev_fcoe_ddp_done, + .ndo_fcoe_enable = vlan_dev_fcoe_enable, + .ndo_fcoe_disable = vlan_dev_fcoe_disable, + .ndo_fcoe_get_wwn = vlan_dev_fcoe_get_wwn, +#endif +}; + void vlan_setup(struct net_device *dev) { ether_setup(dev); -- cgit v1.2.2 From f6b9f4b263f3178fc0f23f0e67d04386528cc727 Mon Sep 17 00:00:00 2001 From: Vasu Dev Date: Tue, 23 Mar 2010 14:42:05 +0000 Subject: vlan: updates vlan real_num_tx_queues Updates real_num_tx_queues in case underlying real device has changed real_num_tx_queues. -v2 As per Eric Dumazet comment:- -- adds BUG_ON to catch case of real_num_tx_queues exceeding num_tx_queues. -- created this self contained patch to just update real_num_tx_queues. Signed-off-by: Vasu Dev Signed-off-by: Jeff Kirsher Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/8021q/vlan.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/8021q') diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 453512266ea1..db783d7af5a3 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -378,6 +378,8 @@ static void vlan_transfer_features(struct net_device *dev, #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) vlandev->fcoe_ddp_xid = dev->fcoe_ddp_xid; #endif + vlandev->real_num_tx_queues = dev->real_num_tx_queues; + BUG_ON(vlandev->real_num_tx_queues > vlandev->num_tx_queues); if (old_features != vlandev->features) netdev_features_change(vlandev); -- cgit v1.2.2 From 5a0e3ad6af8660be21ca98a971cd00f331318c05 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 24 Mar 2010 17:04:11 +0900 Subject: include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo Guess-its-ok-by: Christoph Lameter Cc: Ingo Molnar Cc: Lee Schermerhorn --- net/8021q/vlan.c | 1 + net/8021q/vlan_dev.c | 1 + 2 files changed, 2 insertions(+) (limited to 'net/8021q') diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index db783d7af5a3..97da977c2a23 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 2fd057c81bbf..29b6348c8d4d 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -21,6 +21,7 @@ */ #include +#include #include #include #include -- cgit v1.2.2