OpenCloudOS-Kernel/include/linux/if_vlan.h

734 lines
19 KiB
C
Raw Normal View History

/*
* VLAN An implementation of 802.1Q VLAN tagging.
*
* Authors: Ben Greear <greearb@candelatech.com>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
*/
#ifndef _LINUX_IF_VLAN_H_
#define _LINUX_IF_VLAN_H_
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/rtnetlink.h>
#include <linux/bug.h>
#include <uapi/linux/if_vlan.h>
#define VLAN_HLEN 4 /* The additional bytes required by VLAN
* (in addition to the Ethernet header)
*/
#define VLAN_ETH_HLEN 18 /* Total octets in header. */
#define VLAN_ETH_ZLEN 64 /* Min. octets in frame sans FCS */
/*
* According to 802.3ac, the packet can be 4 bytes longer. --Klika Jan
*/
#define VLAN_ETH_DATA_LEN 1500 /* Max. octets in payload */
#define VLAN_ETH_FRAME_LEN 1518 /* Max. octets in frame sans FCS */
/*
* struct vlan_hdr - vlan header
* @h_vlan_TCI: priority and VLAN ID
* @h_vlan_encapsulated_proto: packet type ID or len
*/
struct vlan_hdr {
__be16 h_vlan_TCI;
__be16 h_vlan_encapsulated_proto;
};
/**
* struct vlan_ethhdr - vlan ethernet header (ethhdr + vlan_hdr)
* @h_dest: destination ethernet address
* @h_source: source ethernet address
* @h_vlan_proto: ethernet protocol
* @h_vlan_TCI: priority and VLAN ID
* @h_vlan_encapsulated_proto: packet type ID or len
*/
struct vlan_ethhdr {
unsigned char h_dest[ETH_ALEN];
unsigned char h_source[ETH_ALEN];
__be16 h_vlan_proto;
__be16 h_vlan_TCI;
__be16 h_vlan_encapsulated_proto;
};
#include <linux/skbuff.h>
static inline struct vlan_ethhdr *vlan_eth_hdr(const struct sk_buff *skb)
{
return (struct vlan_ethhdr *)skb_mac_header(skb);
}
#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 */
#define VLAN_N_VID 4096
/* found in socket.c */
[NET]: Make the device list and device lookups per namespace. This patch makes most of the generic device layer network namespace safe. This patch makes dev_base_head a network namespace variable, and then it picks up a few associated variables. The functions: dev_getbyhwaddr dev_getfirsthwbytype dev_get_by_flags dev_get_by_name __dev_get_by_name dev_get_by_index __dev_get_by_index dev_ioctl dev_ethtool dev_load wireless_process_ioctl were modified to take a network namespace argument, and deal with it. vlan_ioctl_set and brioctl_set were modified so their hooks will receive a network namespace argument. So basically anthing in the core of the network stack that was affected to by the change of dev_base was modified to handle multiple network namespaces. The rest of the network stack was simply modified to explicitly use &init_net the initial network namespace. This can be fixed when those components of the network stack are modified to handle multiple network namespaces. For now the ifindex generator is left global. Fundametally ifindex numbers are per namespace, or else we will have corner case problems with migration when we get that far. At the same time there are assumptions in the network stack that the ifindex of a network device won't change. Making the ifindex number global seems a good compromise until the network stack can cope with ifindex changes when you change namespaces, and the like. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-09-18 02:56:21 +08:00
extern void vlan_ioctl_set(int (*hook)(struct net *, void __user *));
static inline bool is_vlan_dev(const struct net_device *dev)
{
return dev->priv_flags & IFF_802_1Q_VLAN;
}
#define skb_vlan_tag_present(__skb) ((__skb)->vlan_tci & VLAN_TAG_PRESENT)
#define skb_vlan_tag_get(__skb) ((__skb)->vlan_tci & ~VLAN_TAG_PRESENT)
#define skb_vlan_tag_get_id(__skb) ((__skb)->vlan_tci & VLAN_VID_MASK)
#define skb_vlan_tag_get_prio(__skb) ((__skb)->vlan_tci & VLAN_PRIO_MASK)
static inline int vlan_get_rx_ctag_filter_info(struct net_device *dev)
{
ASSERT_RTNL();
return notifier_to_errno(call_netdevice_notifiers(NETDEV_CVLAN_FILTER_PUSH_INFO, dev));
}
static inline void vlan_drop_rx_ctag_filter_info(struct net_device *dev)
{
ASSERT_RTNL();
call_netdevice_notifiers(NETDEV_CVLAN_FILTER_DROP_INFO, dev);
}
static inline int vlan_get_rx_stag_filter_info(struct net_device *dev)
{
ASSERT_RTNL();
return notifier_to_errno(call_netdevice_notifiers(NETDEV_SVLAN_FILTER_PUSH_INFO, dev));
}
static inline void vlan_drop_rx_stag_filter_info(struct net_device *dev)
{
ASSERT_RTNL();
call_netdevice_notifiers(NETDEV_SVLAN_FILTER_DROP_INFO, dev);
}
/**
* struct vlan_pcpu_stats - VLAN percpu rx/tx stats
* @rx_packets: number of received packets
* @rx_bytes: number of received bytes
* @rx_multicast: number of received multicast packets
* @tx_packets: number of transmitted packets
* @tx_bytes: number of transmitted bytes
* @syncp: synchronization point for 64bit counters
* @rx_errors: number of rx errors
* @tx_dropped: number of tx drops
*/
struct vlan_pcpu_stats {
u64 rx_packets;
u64 rx_bytes;
u64 rx_multicast;
u64 tx_packets;
u64 tx_bytes;
struct u64_stats_sync syncp;
u32 rx_errors;
u32 tx_dropped;
};
#if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE)
extern struct net_device *__vlan_find_dev_deep_rcu(struct net_device *real_dev,
__be16 vlan_proto, u16 vlan_id);
extern struct net_device *vlan_dev_real_dev(const struct net_device *dev);
extern u16 vlan_dev_vlan_id(const struct net_device *dev);
extern __be16 vlan_dev_vlan_proto(const struct net_device *dev);
/**
* struct vlan_priority_tci_mapping - vlan egress priority mappings
* @priority: skb priority
* @vlan_qos: vlan priority: (skb->priority << 13) & 0xE000
* @next: pointer to next struct
*/
struct vlan_priority_tci_mapping {
u32 priority;
u16 vlan_qos;
struct vlan_priority_tci_mapping *next;
};
struct proc_dir_entry;
struct netpoll;
/**
* struct vlan_dev_priv - VLAN private device data
* @nr_ingress_mappings: number of ingress priority mappings
* @ingress_priority_map: ingress priority mappings
* @nr_egress_mappings: number of egress priority mappings
* @egress_priority_map: hash of egress priority mappings
* @vlan_proto: VLAN encapsulation protocol
* @vlan_id: VLAN identifier
* @flags: device flags
* @real_dev: underlying netdevice
* @real_dev_addr: address of underlying netdevice
* @dent: proc dir entry
* @vlan_pcpu_stats: ptr to percpu rx stats
*/
struct vlan_dev_priv {
unsigned int nr_ingress_mappings;
u32 ingress_priority_map[8];
unsigned int nr_egress_mappings;
struct vlan_priority_tci_mapping *egress_priority_map[16];
__be16 vlan_proto;
u16 vlan_id;
u16 flags;
struct net_device *real_dev;
unsigned char real_dev_addr[ETH_ALEN];
struct proc_dir_entry *dent;
struct vlan_pcpu_stats __percpu *vlan_pcpu_stats;
#ifdef CONFIG_NET_POLL_CONTROLLER
struct netpoll *netpoll;
#endif
unsigned int nest_level;
};
static inline struct vlan_dev_priv *vlan_dev_priv(const struct net_device *dev)
{
return netdev_priv(dev);
}
static inline u16
vlan_dev_get_egress_qos_mask(struct net_device *dev, u32 skprio)
{
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[(skprio & 0xF)];
while (mp) {
if (mp->priority == skprio) {
return mp->vlan_qos; /* This should already be shifted
* to mask correctly with the
* VLAN's TCI */
}
mp = mp->next;
}
return 0;
}
extern bool vlan_do_receive(struct sk_buff **skb);
extern int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid);
extern void vlan_vid_del(struct net_device *dev, __be16 proto, u16 vid);
extern int vlan_vids_add_by_dev(struct net_device *dev,
const struct net_device *by_dev);
extern void vlan_vids_del_by_dev(struct net_device *dev,
const struct net_device *by_dev);
extern bool vlan_uses_dev(const struct net_device *dev);
static inline int vlan_get_encap_level(struct net_device *dev)
{
BUG_ON(!is_vlan_dev(dev));
return vlan_dev_priv(dev)->nest_level;
}
#else
static inline struct net_device *
__vlan_find_dev_deep_rcu(struct net_device *real_dev,
__be16 vlan_proto, u16 vlan_id)
{
return NULL;
}
static inline struct net_device *vlan_dev_real_dev(const struct net_device *dev)
{
BUG();
return NULL;
}
static inline u16 vlan_dev_vlan_id(const struct net_device *dev)
{
BUG();
return 0;
}
static inline __be16 vlan_dev_vlan_proto(const struct net_device *dev)
{
BUG();
return 0;
}
static inline u16 vlan_dev_get_egress_qos_mask(struct net_device *dev,
u32 skprio)
{
return 0;
}
static inline bool vlan_do_receive(struct sk_buff **skb)
{
vlan: Centralize handling of hardware acceleration. Currently each driver that is capable of vlan hardware acceleration must be aware of the vlan groups that are configured and then pass the stripped tag to a specialized receive function. This is different from other types of hardware offload in that it places a significant amount of knowledge in the driver itself rather keeping it in the networking core. This makes vlan offloading function more similarly to other forms of offloading (such as checksum offloading or TSO) by doing the following: * On receive, stripped vlans are passed directly to the network core, without attempting to check for vlan groups or reconstructing the header if no group * vlans are made less special by folding the logic into the main receive routines * On transmit, the device layer will add the vlan header in software if the hardware doesn't support it, instead of spreading that logic out in upper layers, such as bonding. There are a number of advantages to this: * Fixes all bugs with drivers incorrectly dropping vlan headers at once. * Avoids having to disable VLAN acceleration when in promiscuous mode (good for bridging since it always puts devices in promiscuous mode). * Keeps VLAN tag separate until given to ultimate consumer, which avoids needing to do header reconstruction as in tg3 unless absolutely necessary. * Consolidates common code in core networking. Signed-off-by: Jesse Gross <jesse@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-20 21:56:06 +08:00
return false;
}
static inline int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid)
{
return 0;
}
static inline void vlan_vid_del(struct net_device *dev, __be16 proto, u16 vid)
{
}
static inline int vlan_vids_add_by_dev(struct net_device *dev,
const struct net_device *by_dev)
{
return 0;
}
static inline void vlan_vids_del_by_dev(struct net_device *dev,
const struct net_device *by_dev)
{
}
static inline bool vlan_uses_dev(const struct net_device *dev)
{
return false;
}
static inline int vlan_get_encap_level(struct net_device *dev)
{
BUG();
return 0;
}
#endif
/**
* eth_type_vlan - check for valid vlan ether type.
* @ethertype: ether type to check
*
* Returns true if the ether type is a vlan ether type.
*/
static inline bool eth_type_vlan(__be16 ethertype)
{
switch (ethertype) {
case htons(ETH_P_8021Q):
case htons(ETH_P_8021AD):
return true;
default:
return false;
}
}
static inline bool vlan_hw_offload_capable(netdev_features_t features,
__be16 proto)
{
if (proto == htons(ETH_P_8021Q) && features & NETIF_F_HW_VLAN_CTAG_TX)
return true;
if (proto == htons(ETH_P_8021AD) && features & NETIF_F_HW_VLAN_STAG_TX)
return true;
return false;
}
/**
* __vlan_insert_inner_tag - inner VLAN tag inserting
* @skb: skbuff to tag
* @vlan_proto: VLAN encapsulation protocol
* @vlan_tci: VLAN TCI to insert
* @mac_len: MAC header length including outer vlan headers
*
* Inserts the VLAN tag into @skb as part of the payload at offset mac_len
* Returns error if skb_cow_head fails.
*
* Does not change skb->protocol so this function can be used during receive.
*/
static inline int __vlan_insert_inner_tag(struct sk_buff *skb,
__be16 vlan_proto, u16 vlan_tci,
unsigned int mac_len)
{
struct vlan_ethhdr *veth;
if (skb_cow_head(skb, VLAN_HLEN) < 0)
return -ENOMEM;
skb_push(skb, VLAN_HLEN);
/* Move the mac header sans proto to the beginning of the new header. */
if (likely(mac_len > ETH_TLEN))
memmove(skb->data, skb->data + VLAN_HLEN, mac_len - ETH_TLEN);
skb->mac_header -= VLAN_HLEN;
veth = (struct vlan_ethhdr *)(skb->data + mac_len - ETH_HLEN);
/* first, the ethernet type */
if (likely(mac_len >= ETH_TLEN)) {
/* h_vlan_encapsulated_proto should already be populated, and
* skb->data has space for h_vlan_proto
*/
veth->h_vlan_proto = vlan_proto;
} else {
/* h_vlan_encapsulated_proto should not be populated, and
* skb->data has no space for h_vlan_proto
*/
veth->h_vlan_encapsulated_proto = skb->protocol;
}
/* now, the TCI */
veth->h_vlan_TCI = htons(vlan_tci);
return 0;
}
/**
* __vlan_insert_tag - regular VLAN tag inserting
* @skb: skbuff to tag
* @vlan_proto: VLAN encapsulation protocol
* @vlan_tci: VLAN TCI to insert
*
* Inserts the VLAN tag into @skb as part of the payload
* Returns error if skb_cow_head fails.
*
* Does not change skb->protocol so this function can be used during receive.
*/
static inline int __vlan_insert_tag(struct sk_buff *skb,
__be16 vlan_proto, u16 vlan_tci)
{
return __vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, ETH_HLEN);
}
/**
* vlan_insert_inner_tag - inner VLAN tag inserting
* @skb: skbuff to tag
* @vlan_proto: VLAN encapsulation protocol
* @vlan_tci: VLAN TCI to insert
* @mac_len: MAC header length including outer vlan headers
*
* Inserts the VLAN tag into @skb as part of the payload at offset mac_len
* Returns a VLAN tagged skb. If a new skb is created, @skb is freed.
*
* Following the skb_unshare() example, in case of error, the calling function
* doesn't have to worry about freeing the original skb.
*
* Does not change skb->protocol so this function can be used during receive.
*/
static inline struct sk_buff *vlan_insert_inner_tag(struct sk_buff *skb,
__be16 vlan_proto,
u16 vlan_tci,
unsigned int mac_len)
{
int err;
err = __vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, mac_len);
if (err) {
dev_kfree_skb_any(skb);
return NULL;
}
return skb;
}
/**
* vlan_insert_tag - regular VLAN tag inserting
* @skb: skbuff to tag
* @vlan_proto: VLAN encapsulation protocol
* @vlan_tci: VLAN TCI to insert
*
* Inserts the VLAN tag into @skb as part of the payload
* Returns a VLAN tagged skb. If a new skb is created, @skb is freed.
*
* Following the skb_unshare() example, in case of error, the calling function
* doesn't have to worry about freeing the original skb.
*
* Does not change skb->protocol so this function can be used during receive.
*/
static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb,
__be16 vlan_proto, u16 vlan_tci)
{
return vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, ETH_HLEN);
}
/**
* vlan_insert_tag_set_proto - regular VLAN tag inserting
* @skb: skbuff to tag
* @vlan_proto: VLAN encapsulation protocol
* @vlan_tci: VLAN TCI to insert
*
* Inserts the VLAN tag into @skb as part of the payload
* Returns a VLAN tagged skb. If a new skb is created, @skb is freed.
*
* Following the skb_unshare() example, in case of error, the calling function
* doesn't have to worry about freeing the original skb.
*/
static inline struct sk_buff *vlan_insert_tag_set_proto(struct sk_buff *skb,
__be16 vlan_proto,
u16 vlan_tci)
{
skb = vlan_insert_tag(skb, vlan_proto, vlan_tci);
if (skb)
skb->protocol = vlan_proto;
return skb;
}
/*
* __vlan_hwaccel_push_inside - pushes vlan tag to the payload
* @skb: skbuff to tag
*
* Pushes the VLAN tag from @skb->vlan_tci inside to the payload.
*
* Following the skb_unshare() example, in case of error, the calling function
* doesn't have to worry about freeing the original skb.
*/
static inline struct sk_buff *__vlan_hwaccel_push_inside(struct sk_buff *skb)
{
skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto,
skb_vlan_tag_get(skb));
if (likely(skb))
skb->vlan_tci = 0;
return skb;
}
/**
* __vlan_hwaccel_put_tag - hardware accelerated VLAN inserting
* @skb: skbuff to tag
* @vlan_proto: VLAN encapsulation protocol
* @vlan_tci: VLAN TCI to insert
*
* Puts the VLAN TCI in @skb->vlan_tci and lets the device do the rest
*/
static inline void __vlan_hwaccel_put_tag(struct sk_buff *skb,
__be16 vlan_proto, u16 vlan_tci)
{
skb->vlan_proto = vlan_proto;
skb->vlan_tci = VLAN_TAG_PRESENT | vlan_tci;
}
/**
* __vlan_get_tag - get the VLAN ID that is part of the payload
* @skb: skbuff to query
* @vlan_tci: buffer to store value
*
* Returns error if the skb is not of VLAN type
*/
static inline int __vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci)
{
struct vlan_ethhdr *veth = (struct vlan_ethhdr *)skb->data;
if (!eth_type_vlan(veth->h_vlan_proto))
return -EINVAL;
*vlan_tci = ntohs(veth->h_vlan_TCI);
return 0;
}
/**
* __vlan_hwaccel_get_tag - get the VLAN ID that is in @skb->cb[]
* @skb: skbuff to query
* @vlan_tci: buffer to store value
*
* Returns error if @skb->vlan_tci is not set correctly
*/
static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb,
u16 *vlan_tci)
{
if (skb_vlan_tag_present(skb)) {
*vlan_tci = skb_vlan_tag_get(skb);
return 0;
} else {
*vlan_tci = 0;
return -EINVAL;
}
}
#define HAVE_VLAN_GET_TAG
/**
* vlan_get_tag - get the VLAN ID from the skb
* @skb: skbuff to query
* @vlan_tci: buffer to store value
*
* Returns error if the skb is not VLAN tagged
*/
static inline int vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci)
{
if (skb->dev->features & NETIF_F_HW_VLAN_CTAG_TX) {
return __vlan_hwaccel_get_tag(skb, vlan_tci);
} else {
return __vlan_get_tag(skb, vlan_tci);
}
}
/**
* vlan_get_protocol - get protocol EtherType.
* @skb: skbuff to query
* @type: first vlan protocol
* @depth: buffer to store length of eth and vlan tags in bytes
*
* Returns the EtherType of the packet, regardless of whether it is
* vlan encapsulated (normal or hardware accelerated) or not.
*/
static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type,
int *depth)
{
unsigned int vlan_depth = skb->mac_len;
/* if type is 802.1Q/AD then the header should already be
* present at mac_len - VLAN_HLEN (if mac_len > 0), or at
* ETH_HLEN otherwise
*/
if (eth_type_vlan(type)) {
if (vlan_depth) {
if (WARN_ON(vlan_depth < VLAN_HLEN))
return 0;
vlan_depth -= VLAN_HLEN;
} else {
vlan_depth = ETH_HLEN;
}
do {
struct vlan_hdr *vh;
if (unlikely(!pskb_may_pull(skb,
vlan_depth + VLAN_HLEN)))
return 0;
vh = (struct vlan_hdr *)(skb->data + vlan_depth);
type = vh->h_vlan_encapsulated_proto;
vlan_depth += VLAN_HLEN;
} while (eth_type_vlan(type));
}
if (depth)
*depth = vlan_depth;
return type;
}
/**
* vlan_get_protocol - get protocol EtherType.
* @skb: skbuff to query
*
* Returns the EtherType of the packet, regardless of whether it is
* vlan encapsulated (normal or hardware accelerated) or not.
*/
static inline __be16 vlan_get_protocol(struct sk_buff *skb)
{
return __vlan_get_protocol(skb, skb->protocol, NULL);
}
static inline void vlan_set_encap_proto(struct sk_buff *skb,
struct vlan_hdr *vhdr)
{
__be16 proto;
unsigned short *rawp;
/*
* Was a VLAN packet, grab the encapsulated protocol, which the layer
* three protocols care about.
*/
proto = vhdr->h_vlan_encapsulated_proto;
if (eth_proto_is_802_3(proto)) {
skb->protocol = proto;
return;
}
rawp = (unsigned short *)(vhdr + 1);
if (*rawp == 0xFFFF)
/*
* This is a magic hack to spot IPX packets. Older Novell
* breaks the protocol design and runs IPX over 802.3 without
* an 802.2 LLC layer. We look for FFFF which isn't a used
* 802.2 SSAP/DSAP. This won't work for fault tolerant netware
* but does for the rest.
*/
skb->protocol = htons(ETH_P_802_3);
else
/*
* Real 802.2 LLC
*/
skb->protocol = htons(ETH_P_802_2);
}
bonding: Fix stacked device detection in arp monitoring Prior to commit fbd929f2dce460456807a51e18d623db3db9f077 bonding: support QinQ for bond arp interval the arp monitoring code allowed for proper detection of devices stacked on top of vlans. Since the above commit, the code can still detect a device stacked on top of single vlan, but not a device stacked on top of Q-in-Q configuration. The search will only set the inner vlan tag if the route device is the vlan device. However, this is not always the case, as it is possible to extend the stacked configuration. With this patch it is possible to provision devices on top Q-in-Q vlan configuration that should be used as a source of ARP monitoring information. For example: ip link add link bond0 vlan10 type vlan proto 802.1q id 10 ip link add link vlan10 vlan100 type vlan proto 802.1q id 100 ip link add link vlan100 type macvlan Note: This patch limites the number of stacked VLANs to 2, just like before. The original, however had another issue in that if we had more then 2 levels of VLANs, we would end up generating incorrectly tagged traffic. This is no longer possible. Fixes: fbd929f2dce460456807a51e18d623db3db9f077 (bonding: support QinQ for bond arp interval) CC: Jay Vosburgh <j.vosburgh@gmail.com> CC: Veaceslav Falico <vfalico@redhat.com> CC: Andy Gospodarek <andy@greyhouse.net> CC: Ding Tianhong <dingtianhong@huawei.com> CC: Patric McHardy <kaber@trash.net> Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-05-17 05:20:38 +08:00
/**
* skb_vlan_tagged - check if skb is vlan tagged.
* @skb: skbuff to query
*
* Returns true if the skb is tagged, regardless of whether it is hardware
* accelerated or not.
*/
static inline bool skb_vlan_tagged(const struct sk_buff *skb)
{
if (!skb_vlan_tag_present(skb) &&
likely(!eth_type_vlan(skb->protocol)))
return false;
return true;
}
/**
* skb_vlan_tagged_multi - check if skb is vlan tagged with multiple headers.
* @skb: skbuff to query
*
* Returns true if the skb is tagged with multiple vlan headers, regardless
* of whether it is hardware accelerated or not.
*/
vlan: Fix reading memory beyond skb->tail in skb_vlan_tagged_multi Syzkaller spotted an old bug which leads to reading skb beyond tail by 4 bytes on vlan tagged packets. This is caused because skb_vlan_tagged_multi() did not check skb_headlen. BUG: KMSAN: uninit-value in eth_type_vlan include/linux/if_vlan.h:283 [inline] BUG: KMSAN: uninit-value in skb_vlan_tagged_multi include/linux/if_vlan.h:656 [inline] BUG: KMSAN: uninit-value in vlan_features_check include/linux/if_vlan.h:672 [inline] BUG: KMSAN: uninit-value in dflt_features_check net/core/dev.c:2949 [inline] BUG: KMSAN: uninit-value in netif_skb_features+0xd1b/0xdc0 net/core/dev.c:3009 CPU: 1 PID: 3582 Comm: syzkaller435149 Not tainted 4.16.0+ #82 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:17 [inline] dump_stack+0x185/0x1d0 lib/dump_stack.c:53 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067 __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676 eth_type_vlan include/linux/if_vlan.h:283 [inline] skb_vlan_tagged_multi include/linux/if_vlan.h:656 [inline] vlan_features_check include/linux/if_vlan.h:672 [inline] dflt_features_check net/core/dev.c:2949 [inline] netif_skb_features+0xd1b/0xdc0 net/core/dev.c:3009 validate_xmit_skb+0x89/0x1320 net/core/dev.c:3084 __dev_queue_xmit+0x1cb2/0x2b60 net/core/dev.c:3549 dev_queue_xmit+0x4b/0x60 net/core/dev.c:3590 packet_snd net/packet/af_packet.c:2944 [inline] packet_sendmsg+0x7c57/0x8a10 net/packet/af_packet.c:2969 sock_sendmsg_nosec net/socket.c:630 [inline] sock_sendmsg net/socket.c:640 [inline] sock_write_iter+0x3b9/0x470 net/socket.c:909 do_iter_readv_writev+0x7bb/0x970 include/linux/fs.h:1776 do_iter_write+0x30d/0xd40 fs/read_write.c:932 vfs_writev fs/read_write.c:977 [inline] do_writev+0x3c9/0x830 fs/read_write.c:1012 SYSC_writev+0x9b/0xb0 fs/read_write.c:1085 SyS_writev+0x56/0x80 fs/read_write.c:1082 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 RIP: 0033:0x43ffa9 RSP: 002b:00007fff2cff3948 EFLAGS: 00000217 ORIG_RAX: 0000000000000014 RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 000000000043ffa9 RDX: 0000000000000001 RSI: 0000000020000080 RDI: 0000000000000003 RBP: 00000000006cb018 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000217 R12: 00000000004018d0 R13: 0000000000401960 R14: 0000000000000000 R15: 0000000000000000 Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline] kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:188 kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:314 kmsan_slab_alloc+0x11/0x20 mm/kmsan/kmsan.c:321 slab_post_alloc_hook mm/slab.h:445 [inline] slab_alloc_node mm/slub.c:2737 [inline] __kmalloc_node_track_caller+0xaed/0x11c0 mm/slub.c:4369 __kmalloc_reserve net/core/skbuff.c:138 [inline] __alloc_skb+0x2cf/0x9f0 net/core/skbuff.c:206 alloc_skb include/linux/skbuff.h:984 [inline] alloc_skb_with_frags+0x1d4/0xb20 net/core/skbuff.c:5234 sock_alloc_send_pskb+0xb56/0x1190 net/core/sock.c:2085 packet_alloc_skb net/packet/af_packet.c:2803 [inline] packet_snd net/packet/af_packet.c:2894 [inline] packet_sendmsg+0x6444/0x8a10 net/packet/af_packet.c:2969 sock_sendmsg_nosec net/socket.c:630 [inline] sock_sendmsg net/socket.c:640 [inline] sock_write_iter+0x3b9/0x470 net/socket.c:909 do_iter_readv_writev+0x7bb/0x970 include/linux/fs.h:1776 do_iter_write+0x30d/0xd40 fs/read_write.c:932 vfs_writev fs/read_write.c:977 [inline] do_writev+0x3c9/0x830 fs/read_write.c:1012 SYSC_writev+0x9b/0xb0 fs/read_write.c:1085 SyS_writev+0x56/0x80 fs/read_write.c:1082 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 Fixes: 58e998c6d239 ("offloading: Force software GSO for multiple vlan tags.") Reported-and-tested-by: syzbot+0bbe42c764feafa82c5a@syzkaller.appspotmail.com Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-17 17:46:14 +08:00
static inline bool skb_vlan_tagged_multi(struct sk_buff *skb)
{
__be16 protocol = skb->protocol;
if (!skb_vlan_tag_present(skb)) {
struct vlan_ethhdr *veh;
if (likely(!eth_type_vlan(protocol)))
return false;
vlan: Fix reading memory beyond skb->tail in skb_vlan_tagged_multi Syzkaller spotted an old bug which leads to reading skb beyond tail by 4 bytes on vlan tagged packets. This is caused because skb_vlan_tagged_multi() did not check skb_headlen. BUG: KMSAN: uninit-value in eth_type_vlan include/linux/if_vlan.h:283 [inline] BUG: KMSAN: uninit-value in skb_vlan_tagged_multi include/linux/if_vlan.h:656 [inline] BUG: KMSAN: uninit-value in vlan_features_check include/linux/if_vlan.h:672 [inline] BUG: KMSAN: uninit-value in dflt_features_check net/core/dev.c:2949 [inline] BUG: KMSAN: uninit-value in netif_skb_features+0xd1b/0xdc0 net/core/dev.c:3009 CPU: 1 PID: 3582 Comm: syzkaller435149 Not tainted 4.16.0+ #82 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:17 [inline] dump_stack+0x185/0x1d0 lib/dump_stack.c:53 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067 __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676 eth_type_vlan include/linux/if_vlan.h:283 [inline] skb_vlan_tagged_multi include/linux/if_vlan.h:656 [inline] vlan_features_check include/linux/if_vlan.h:672 [inline] dflt_features_check net/core/dev.c:2949 [inline] netif_skb_features+0xd1b/0xdc0 net/core/dev.c:3009 validate_xmit_skb+0x89/0x1320 net/core/dev.c:3084 __dev_queue_xmit+0x1cb2/0x2b60 net/core/dev.c:3549 dev_queue_xmit+0x4b/0x60 net/core/dev.c:3590 packet_snd net/packet/af_packet.c:2944 [inline] packet_sendmsg+0x7c57/0x8a10 net/packet/af_packet.c:2969 sock_sendmsg_nosec net/socket.c:630 [inline] sock_sendmsg net/socket.c:640 [inline] sock_write_iter+0x3b9/0x470 net/socket.c:909 do_iter_readv_writev+0x7bb/0x970 include/linux/fs.h:1776 do_iter_write+0x30d/0xd40 fs/read_write.c:932 vfs_writev fs/read_write.c:977 [inline] do_writev+0x3c9/0x830 fs/read_write.c:1012 SYSC_writev+0x9b/0xb0 fs/read_write.c:1085 SyS_writev+0x56/0x80 fs/read_write.c:1082 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 RIP: 0033:0x43ffa9 RSP: 002b:00007fff2cff3948 EFLAGS: 00000217 ORIG_RAX: 0000000000000014 RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 000000000043ffa9 RDX: 0000000000000001 RSI: 0000000020000080 RDI: 0000000000000003 RBP: 00000000006cb018 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000217 R12: 00000000004018d0 R13: 0000000000401960 R14: 0000000000000000 R15: 0000000000000000 Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline] kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:188 kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:314 kmsan_slab_alloc+0x11/0x20 mm/kmsan/kmsan.c:321 slab_post_alloc_hook mm/slab.h:445 [inline] slab_alloc_node mm/slub.c:2737 [inline] __kmalloc_node_track_caller+0xaed/0x11c0 mm/slub.c:4369 __kmalloc_reserve net/core/skbuff.c:138 [inline] __alloc_skb+0x2cf/0x9f0 net/core/skbuff.c:206 alloc_skb include/linux/skbuff.h:984 [inline] alloc_skb_with_frags+0x1d4/0xb20 net/core/skbuff.c:5234 sock_alloc_send_pskb+0xb56/0x1190 net/core/sock.c:2085 packet_alloc_skb net/packet/af_packet.c:2803 [inline] packet_snd net/packet/af_packet.c:2894 [inline] packet_sendmsg+0x6444/0x8a10 net/packet/af_packet.c:2969 sock_sendmsg_nosec net/socket.c:630 [inline] sock_sendmsg net/socket.c:640 [inline] sock_write_iter+0x3b9/0x470 net/socket.c:909 do_iter_readv_writev+0x7bb/0x970 include/linux/fs.h:1776 do_iter_write+0x30d/0xd40 fs/read_write.c:932 vfs_writev fs/read_write.c:977 [inline] do_writev+0x3c9/0x830 fs/read_write.c:1012 SYSC_writev+0x9b/0xb0 fs/read_write.c:1085 SyS_writev+0x56/0x80 fs/read_write.c:1082 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 Fixes: 58e998c6d239 ("offloading: Force software GSO for multiple vlan tags.") Reported-and-tested-by: syzbot+0bbe42c764feafa82c5a@syzkaller.appspotmail.com Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-17 17:46:14 +08:00
if (unlikely(!pskb_may_pull(skb, VLAN_ETH_HLEN)))
return false;
veh = (struct vlan_ethhdr *)skb->data;
protocol = veh->h_vlan_encapsulated_proto;
}
if (!eth_type_vlan(protocol))
return false;
return true;
}
/**
* vlan_features_check - drop unsafe features for skb with multiple tags.
* @skb: skbuff to query
* @features: features to be checked
*
* Returns features without unsafe ones if the skb has multiple tags.
*/
vlan: Fix reading memory beyond skb->tail in skb_vlan_tagged_multi Syzkaller spotted an old bug which leads to reading skb beyond tail by 4 bytes on vlan tagged packets. This is caused because skb_vlan_tagged_multi() did not check skb_headlen. BUG: KMSAN: uninit-value in eth_type_vlan include/linux/if_vlan.h:283 [inline] BUG: KMSAN: uninit-value in skb_vlan_tagged_multi include/linux/if_vlan.h:656 [inline] BUG: KMSAN: uninit-value in vlan_features_check include/linux/if_vlan.h:672 [inline] BUG: KMSAN: uninit-value in dflt_features_check net/core/dev.c:2949 [inline] BUG: KMSAN: uninit-value in netif_skb_features+0xd1b/0xdc0 net/core/dev.c:3009 CPU: 1 PID: 3582 Comm: syzkaller435149 Not tainted 4.16.0+ #82 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:17 [inline] dump_stack+0x185/0x1d0 lib/dump_stack.c:53 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067 __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676 eth_type_vlan include/linux/if_vlan.h:283 [inline] skb_vlan_tagged_multi include/linux/if_vlan.h:656 [inline] vlan_features_check include/linux/if_vlan.h:672 [inline] dflt_features_check net/core/dev.c:2949 [inline] netif_skb_features+0xd1b/0xdc0 net/core/dev.c:3009 validate_xmit_skb+0x89/0x1320 net/core/dev.c:3084 __dev_queue_xmit+0x1cb2/0x2b60 net/core/dev.c:3549 dev_queue_xmit+0x4b/0x60 net/core/dev.c:3590 packet_snd net/packet/af_packet.c:2944 [inline] packet_sendmsg+0x7c57/0x8a10 net/packet/af_packet.c:2969 sock_sendmsg_nosec net/socket.c:630 [inline] sock_sendmsg net/socket.c:640 [inline] sock_write_iter+0x3b9/0x470 net/socket.c:909 do_iter_readv_writev+0x7bb/0x970 include/linux/fs.h:1776 do_iter_write+0x30d/0xd40 fs/read_write.c:932 vfs_writev fs/read_write.c:977 [inline] do_writev+0x3c9/0x830 fs/read_write.c:1012 SYSC_writev+0x9b/0xb0 fs/read_write.c:1085 SyS_writev+0x56/0x80 fs/read_write.c:1082 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 RIP: 0033:0x43ffa9 RSP: 002b:00007fff2cff3948 EFLAGS: 00000217 ORIG_RAX: 0000000000000014 RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 000000000043ffa9 RDX: 0000000000000001 RSI: 0000000020000080 RDI: 0000000000000003 RBP: 00000000006cb018 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000217 R12: 00000000004018d0 R13: 0000000000401960 R14: 0000000000000000 R15: 0000000000000000 Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline] kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:188 kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:314 kmsan_slab_alloc+0x11/0x20 mm/kmsan/kmsan.c:321 slab_post_alloc_hook mm/slab.h:445 [inline] slab_alloc_node mm/slub.c:2737 [inline] __kmalloc_node_track_caller+0xaed/0x11c0 mm/slub.c:4369 __kmalloc_reserve net/core/skbuff.c:138 [inline] __alloc_skb+0x2cf/0x9f0 net/core/skbuff.c:206 alloc_skb include/linux/skbuff.h:984 [inline] alloc_skb_with_frags+0x1d4/0xb20 net/core/skbuff.c:5234 sock_alloc_send_pskb+0xb56/0x1190 net/core/sock.c:2085 packet_alloc_skb net/packet/af_packet.c:2803 [inline] packet_snd net/packet/af_packet.c:2894 [inline] packet_sendmsg+0x6444/0x8a10 net/packet/af_packet.c:2969 sock_sendmsg_nosec net/socket.c:630 [inline] sock_sendmsg net/socket.c:640 [inline] sock_write_iter+0x3b9/0x470 net/socket.c:909 do_iter_readv_writev+0x7bb/0x970 include/linux/fs.h:1776 do_iter_write+0x30d/0xd40 fs/read_write.c:932 vfs_writev fs/read_write.c:977 [inline] do_writev+0x3c9/0x830 fs/read_write.c:1012 SYSC_writev+0x9b/0xb0 fs/read_write.c:1085 SyS_writev+0x56/0x80 fs/read_write.c:1082 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 Fixes: 58e998c6d239 ("offloading: Force software GSO for multiple vlan tags.") Reported-and-tested-by: syzbot+0bbe42c764feafa82c5a@syzkaller.appspotmail.com Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-17 17:46:14 +08:00
static inline netdev_features_t vlan_features_check(struct sk_buff *skb,
netdev_features_t features)
{
if (skb_vlan_tagged_multi(skb)) {
/* In the case of multi-tagged packets, use a direct mask
* instead of using netdev_interesect_features(), to make
* sure that only devices supporting NETIF_F_HW_CSUM will
* have checksum offloading support.
*/
features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_HW_CSUM |
NETIF_F_FRAGLIST | NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_STAG_TX;
}
return features;
}
/**
* compare_vlan_header - Compare two vlan headers
* @h1: Pointer to vlan header
* @h2: Pointer to vlan header
*
* Compare two vlan headers, returns 0 if equal.
*
* Please note that alignment of h1 & h2 are only guaranteed to be 16 bits.
*/
static inline unsigned long compare_vlan_header(const struct vlan_hdr *h1,
const struct vlan_hdr *h2)
{
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
return *(u32 *)h1 ^ *(u32 *)h2;
#else
return ((__force u32)h1->h_vlan_TCI ^ (__force u32)h2->h_vlan_TCI) |
((__force u32)h1->h_vlan_encapsulated_proto ^
(__force u32)h2->h_vlan_encapsulated_proto);
#endif
}
#endif /* !(_LINUX_IF_VLAN_H_) */