linux_dsm_epyc7002/net/8021q/vlan_dev.c
dingtianhong dc8eaaa006 vlan: Fix lockdep warning when vlan dev handle notification
When I open the LOCKDEP config and run these steps:

modprobe 8021q
vconfig add eth2 20
vconfig add eth2.20 30
ifconfig eth2 xx.xx.xx.xx

then the Call Trace happened:

[32524.386288] =============================================
[32524.386293] [ INFO: possible recursive locking detected ]
[32524.386298] 3.14.0-rc2-0.7-default+ #35 Tainted: G           O
[32524.386302] ---------------------------------------------
[32524.386306] ifconfig/3103 is trying to acquire lock:
[32524.386310]  (&vlan_netdev_addr_lock_key/1){+.....}, at: [<ffffffff814275f4>] dev_mc_sync+0x64/0xb0
[32524.386326]
[32524.386326] but task is already holding lock:
[32524.386330]  (&vlan_netdev_addr_lock_key/1){+.....}, at: [<ffffffff8141af83>] dev_set_rx_mode+0x23/0x40
[32524.386341]
[32524.386341] other info that might help us debug this:
[32524.386345]  Possible unsafe locking scenario:
[32524.386345]
[32524.386350]        CPU0
[32524.386352]        ----
[32524.386354]   lock(&vlan_netdev_addr_lock_key/1);
[32524.386359]   lock(&vlan_netdev_addr_lock_key/1);
[32524.386364]
[32524.386364]  *** DEADLOCK ***
[32524.386364]
[32524.386368]  May be due to missing lock nesting notation
[32524.386368]
[32524.386373] 2 locks held by ifconfig/3103:
[32524.386376]  #0:  (rtnl_mutex){+.+.+.}, at: [<ffffffff81431d42>] rtnl_lock+0x12/0x20
[32524.386387]  #1:  (&vlan_netdev_addr_lock_key/1){+.....}, at: [<ffffffff8141af83>] dev_set_rx_mode+0x23/0x40
[32524.386398]
[32524.386398] stack backtrace:
[32524.386403] CPU: 1 PID: 3103 Comm: ifconfig Tainted: G           O 3.14.0-rc2-0.7-default+ #35
[32524.386409] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2007
[32524.386414]  ffffffff81ffae40 ffff8800d9625ae8 ffffffff814f68a2 ffff8800d9625bc8
[32524.386421]  ffffffff810a35fb ffff8800d8a8d9d0 00000000d9625b28 ffff8800d8a8e5d0
[32524.386428]  000003cc00000000 0000000000000002 ffff8800d8a8e5f8 0000000000000000
[32524.386435] Call Trace:
[32524.386441]  [<ffffffff814f68a2>] dump_stack+0x6a/0x78
[32524.386448]  [<ffffffff810a35fb>] __lock_acquire+0x7ab/0x1940
[32524.386454]  [<ffffffff810a323a>] ? __lock_acquire+0x3ea/0x1940
[32524.386459]  [<ffffffff810a4874>] lock_acquire+0xe4/0x110
[32524.386464]  [<ffffffff814275f4>] ? dev_mc_sync+0x64/0xb0
[32524.386471]  [<ffffffff814fc07a>] _raw_spin_lock_nested+0x2a/0x40
[32524.386476]  [<ffffffff814275f4>] ? dev_mc_sync+0x64/0xb0
[32524.386481]  [<ffffffff814275f4>] dev_mc_sync+0x64/0xb0
[32524.386489]  [<ffffffffa0500cab>] vlan_dev_set_rx_mode+0x2b/0x50 [8021q]
[32524.386495]  [<ffffffff8141addf>] __dev_set_rx_mode+0x5f/0xb0
[32524.386500]  [<ffffffff8141af8b>] dev_set_rx_mode+0x2b/0x40
[32524.386506]  [<ffffffff8141b3cf>] __dev_open+0xef/0x150
[32524.386511]  [<ffffffff8141b177>] __dev_change_flags+0xa7/0x190
[32524.386516]  [<ffffffff8141b292>] dev_change_flags+0x32/0x80
[32524.386524]  [<ffffffff8149ca56>] devinet_ioctl+0x7d6/0x830
[32524.386532]  [<ffffffff81437b0b>] ? dev_ioctl+0x34b/0x660
[32524.386540]  [<ffffffff814a05b0>] inet_ioctl+0x80/0xa0
[32524.386550]  [<ffffffff8140199d>] sock_do_ioctl+0x2d/0x60
[32524.386558]  [<ffffffff81401a52>] sock_ioctl+0x82/0x2a0
[32524.386568]  [<ffffffff811a7123>] do_vfs_ioctl+0x93/0x590
[32524.386578]  [<ffffffff811b2705>] ? rcu_read_lock_held+0x45/0x50
[32524.386586]  [<ffffffff811b39e5>] ? __fget_light+0x105/0x110
[32524.386594]  [<ffffffff811a76b1>] SyS_ioctl+0x91/0xb0
[32524.386604]  [<ffffffff815057e2>] system_call_fastpath+0x16/0x1b

========================================================================

The reason is that all of the addr_lock_key for vlan dev have the same class,
so if we change the status for vlan dev, the vlan dev and its real dev will
hold the same class of addr_lock_key together, so the warning happened.

we should distinguish the lock depth for vlan dev and its real dev.

v1->v2: Convert the vlan_netdev_addr_lock_key to an array of eight elements, which
	could support to add 8 vlan id on a same vlan dev, I think it is enough for current
	scene, because a netdev's name is limited to IFNAMSIZ which could not hold 8 vlan id,
	and the vlan dev would not meet the same class key with its real dev.

	The new function vlan_dev_get_lockdep_subkey() will return the subkey and make the vlan
	dev could get a suitable class key.

v2->v3: According David's suggestion, I use the subclass to distinguish the lock key for vlan dev
	and its real dev, but it make no sense, because the difference for subclass in the
	lock_class_key doesn't mean that the difference class for lock_key, so I use lock_depth
	to distinguish the different depth for every vlan dev, the same depth of the vlan dev
	could have the same lock_class_key, I import the MAX_LOCK_DEPTH from the include/linux/sched.h,
	I think it is enough here, the lockdep should never exceed that value.

v3->v4: Add a huge array of locking keys will waste static kernel memory and is not a appropriate method,
	we could use _nested() variants to fix the problem, calculate the depth for every vlan dev,
	and use the depth as the subclass for addr_lock_key.

Signed-off-by: Ding Tianhong <dingtianhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-04-18 17:48:30 -04:00

838 lines
22 KiB
C

/* -*- linux-c -*-
* INET 802.1Q VLAN
* Ethernet-type device handling.
*
* Authors: Ben Greear <greearb@candelatech.com>
* Please send support related email to: netdev@vger.kernel.org
* VLAN Home Page: http://www.candelatech.com/~greear/vlan.html
*
* Fixes: Mar 22 2001: Martin Bokaemper <mbokaemper@unispherenetworks.com>
* - reset skb->pkt_type on incoming packets when MAC was changed
* - see that changed MAC is saddr for outgoing packets
* Oct 20, 2001: Ard van Breeman:
* - Fix MC-list, finally.
* - Flush MC-list on VLAN destroy.
*
*
* 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.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/ethtool.h>
#include <net/arp.h>
#include "vlan.h"
#include "vlanproc.h"
#include <linux/if_vlan.h>
#include <linux/netpoll.h>
/*
* Rebuild the Ethernet MAC header. This is called after an ARP
* (or in future other address resolution) has completed on this
* sk_buff. We now let ARP fill in the other fields.
*
* This routine CANNOT use cached dst->neigh!
* Really, it is used only when dst->neigh is wrong.
*
* TODO: This needs a checkup, I'm ignorant here. --BLG
*/
static int vlan_dev_rebuild_header(struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
struct vlan_ethhdr *veth = (struct vlan_ethhdr *)(skb->data);
switch (veth->h_vlan_encapsulated_proto) {
#ifdef CONFIG_INET
case htons(ETH_P_IP):
/* TODO: Confirm this will work with VLAN headers... */
return arp_find(veth->h_dest, skb);
#endif
default:
pr_debug("%s: unable to resolve type %X addresses\n",
dev->name, ntohs(veth->h_vlan_encapsulated_proto));
ether_addr_copy(veth->h_source, dev->dev_addr);
break;
}
return 0;
}
/*
* Create the VLAN header for an arbitrary protocol layer
*
* saddr=NULL means use device source address
* daddr=NULL means leave destination address (eg unresolved arp)
*
* This is called when the SKB is moving down the stack towards the
* physical devices.
*/
static int vlan_dev_hard_header(struct sk_buff *skb, struct net_device *dev,
unsigned short type,
const void *daddr, const void *saddr,
unsigned int len)
{
struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
struct vlan_hdr *vhdr;
unsigned int vhdrlen = 0;
u16 vlan_tci = 0;
int rc;
if (!(vlan->flags & VLAN_FLAG_REORDER_HDR)) {
vhdr = (struct vlan_hdr *) skb_push(skb, VLAN_HLEN);
vlan_tci = vlan->vlan_id;
vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb->priority);
vhdr->h_vlan_TCI = htons(vlan_tci);
/*
* 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 && type != ETH_P_802_2)
vhdr->h_vlan_encapsulated_proto = htons(type);
else
vhdr->h_vlan_encapsulated_proto = htons(len);
skb->protocol = vlan->vlan_proto;
type = ntohs(vlan->vlan_proto);
vhdrlen = VLAN_HLEN;
}
/* Before delegating work to the lower layer, enter our MAC-address */
if (saddr == NULL)
saddr = dev->dev_addr;
/* Now make the underlying real hard header */
dev = vlan->real_dev;
rc = dev_hard_header(skb, dev, type, daddr, saddr, len + vhdrlen);
if (rc > 0)
rc += vhdrlen;
return rc;
}
static inline netdev_tx_t vlan_netpoll_send_skb(struct vlan_dev_priv *vlan, struct sk_buff *skb)
{
#ifdef CONFIG_NET_POLL_CONTROLLER
if (vlan->netpoll)
netpoll_send_skb(vlan->netpoll, skb);
#else
BUG();
#endif
return NETDEV_TX_OK;
}
static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb,
struct net_device *dev)
{
struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
struct vlan_ethhdr *veth = (struct vlan_ethhdr *)(skb->data);
unsigned int len;
int ret;
/* Handle non-VLAN frames if they are sent to us, for example by DHCP.
*
* NOTE: THIS ASSUMES DIX ETHERNET, SPECIFICALLY NOT SUPPORTING
* OTHER THINGS LIKE FDDI/TokenRing/802.3 SNAPs...
*/
if (veth->h_vlan_proto != vlan->vlan_proto ||
vlan->flags & VLAN_FLAG_REORDER_HDR) {
u16 vlan_tci;
vlan_tci = vlan->vlan_id;
vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb->priority);
skb = __vlan_hwaccel_put_tag(skb, vlan->vlan_proto, vlan_tci);
}
skb->dev = vlan->real_dev;
len = skb->len;
if (unlikely(netpoll_tx_running(dev)))
return vlan_netpoll_send_skb(vlan, skb);
ret = dev_queue_xmit(skb);
if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) {
struct vlan_pcpu_stats *stats;
stats = this_cpu_ptr(vlan->vlan_pcpu_stats);
u64_stats_update_begin(&stats->syncp);
stats->tx_packets++;
stats->tx_bytes += len;
u64_stats_update_end(&stats->syncp);
} else {
this_cpu_inc(vlan->vlan_pcpu_stats->tx_dropped);
}
return ret;
}
static int vlan_dev_change_mtu(struct net_device *dev, int new_mtu)
{
/* TODO: gotta make sure the underlying layer can handle it,
* maybe an IFF_VLAN_CAPABLE flag for devices?
*/
if (vlan_dev_priv(dev)->real_dev->mtu < new_mtu)
return -ERANGE;
dev->mtu = new_mtu;
return 0;
}
void vlan_dev_set_ingress_priority(const struct net_device *dev,
u32 skb_prio, u16 vlan_prio)
{
struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
if (vlan->ingress_priority_map[vlan_prio & 0x7] && !skb_prio)
vlan->nr_ingress_mappings--;
else if (!vlan->ingress_priority_map[vlan_prio & 0x7] && skb_prio)
vlan->nr_ingress_mappings++;
vlan->ingress_priority_map[vlan_prio & 0x7] = skb_prio;
}
int vlan_dev_set_egress_priority(const struct net_device *dev,
u32 skb_prio, u16 vlan_prio)
{
struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
struct vlan_priority_tci_mapping *mp = NULL;
struct vlan_priority_tci_mapping *np;
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];
while (mp) {
if (mp->priority == skb_prio) {
if (mp->vlan_qos && !vlan_qos)
vlan->nr_egress_mappings--;
else if (!mp->vlan_qos && vlan_qos)
vlan->nr_egress_mappings++;
mp->vlan_qos = vlan_qos;
return 0;
}
mp = mp->next;
}
/* Create a new mapping then. */
mp = vlan->egress_priority_map[skb_prio & 0xF];
np = kmalloc(sizeof(struct vlan_priority_tci_mapping), GFP_KERNEL);
if (!np)
return -ENOBUFS;
np->next = mp;
np->priority = skb_prio;
np->vlan_qos = vlan_qos;
/* Before inserting this element in hash table, make sure all its fields
* are committed to memory.
* coupled with smp_rmb() in vlan_dev_get_egress_qos_mask()
*/
smp_wmb();
vlan->egress_priority_map[skb_prio & 0xF] = np;
if (vlan_qos)
vlan->nr_egress_mappings++;
return 0;
}
/* Flags are defined in the vlan_flags enum in include/linux/if_vlan.h file. */
int vlan_dev_change_flags(const struct net_device *dev, u32 flags, u32 mask)
{
struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
u32 old_flags = vlan->flags;
if (mask & ~(VLAN_FLAG_REORDER_HDR | VLAN_FLAG_GVRP |
VLAN_FLAG_LOOSE_BINDING | VLAN_FLAG_MVRP))
return -EINVAL;
vlan->flags = (old_flags & ~mask) | (flags & mask);
if (netif_running(dev) && (vlan->flags ^ old_flags) & VLAN_FLAG_GVRP) {
if (vlan->flags & VLAN_FLAG_GVRP)
vlan_gvrp_request_join(dev);
else
vlan_gvrp_request_leave(dev);
}
if (netif_running(dev) && (vlan->flags ^ old_flags) & VLAN_FLAG_MVRP) {
if (vlan->flags & VLAN_FLAG_MVRP)
vlan_mvrp_request_join(dev);
else
vlan_mvrp_request_leave(dev);
}
return 0;
}
void vlan_dev_get_realdev_name(const struct net_device *dev, char *result)
{
strncpy(result, vlan_dev_priv(dev)->real_dev->name, 23);
}
static int vlan_dev_open(struct net_device *dev)
{
struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
struct net_device *real_dev = vlan->real_dev;
int err;
if (!(real_dev->flags & IFF_UP) &&
!(vlan->flags & VLAN_FLAG_LOOSE_BINDING))
return -ENETDOWN;
if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr)) {
err = dev_uc_add(real_dev, dev->dev_addr);
if (err < 0)
goto out;
}
if (dev->flags & IFF_ALLMULTI) {
err = dev_set_allmulti(real_dev, 1);
if (err < 0)
goto del_unicast;
}
if (dev->flags & IFF_PROMISC) {
err = dev_set_promiscuity(real_dev, 1);
if (err < 0)
goto clear_allmulti;
}
ether_addr_copy(vlan->real_dev_addr, real_dev->dev_addr);
if (vlan->flags & VLAN_FLAG_GVRP)
vlan_gvrp_request_join(dev);
if (vlan->flags & VLAN_FLAG_MVRP)
vlan_mvrp_request_join(dev);
if (netif_carrier_ok(real_dev))
netif_carrier_on(dev);
return 0;
clear_allmulti:
if (dev->flags & IFF_ALLMULTI)
dev_set_allmulti(real_dev, -1);
del_unicast:
if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr))
dev_uc_del(real_dev, dev->dev_addr);
out:
netif_carrier_off(dev);
return err;
}
static int vlan_dev_stop(struct net_device *dev)
{
struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
struct net_device *real_dev = vlan->real_dev;
dev_mc_unsync(real_dev, dev);
dev_uc_unsync(real_dev, dev);
if (dev->flags & IFF_ALLMULTI)
dev_set_allmulti(real_dev, -1);
if (dev->flags & IFF_PROMISC)
dev_set_promiscuity(real_dev, -1);
if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr))
dev_uc_del(real_dev, dev->dev_addr);
netif_carrier_off(dev);
return 0;
}
static int vlan_dev_set_mac_address(struct net_device *dev, void *p)
{
struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
struct sockaddr *addr = p;
int err;
if (!is_valid_ether_addr(addr->sa_data))
return -EADDRNOTAVAIL;
if (!(dev->flags & IFF_UP))
goto out;
if (!ether_addr_equal(addr->sa_data, real_dev->dev_addr)) {
err = dev_uc_add(real_dev, addr->sa_data);
if (err < 0)
return err;
}
if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr))
dev_uc_del(real_dev, dev->dev_addr);
out:
ether_addr_copy(dev->dev_addr, addr->sa_data);
return 0;
}
static int vlan_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
{
struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
const struct net_device_ops *ops = real_dev->netdev_ops;
struct ifreq ifrr;
int err = -EOPNOTSUPP;
strncpy(ifrr.ifr_name, real_dev->name, IFNAMSIZ);
ifrr.ifr_ifru = ifr->ifr_ifru;
switch (cmd) {
case SIOCGMIIPHY:
case SIOCGMIIREG:
case SIOCSMIIREG:
if (netif_device_present(real_dev) && ops->ndo_do_ioctl)
err = ops->ndo_do_ioctl(real_dev, &ifrr, cmd);
break;
}
if (!err)
ifr->ifr_ifru = ifrr.ifr_ifru;
return err;
}
static int vlan_dev_neigh_setup(struct net_device *dev, struct neigh_parms *pa)
{
struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
const struct net_device_ops *ops = real_dev->netdev_ops;
int err = 0;
if (netif_device_present(real_dev) && ops->ndo_neigh_setup)
err = ops->ndo_neigh_setup(real_dev, pa);
return err;
}
#if IS_ENABLED(CONFIG_FCOE)
static int vlan_dev_fcoe_ddp_setup(struct net_device *dev, u16 xid,
struct scatterlist *sgl, unsigned int sgc)
{
struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
const struct net_device_ops *ops = real_dev->netdev_ops;
int rc = 0;
if (ops->ndo_fcoe_ddp_setup)
rc = ops->ndo_fcoe_ddp_setup(real_dev, xid, sgl, sgc);
return rc;
}
static int vlan_dev_fcoe_ddp_done(struct net_device *dev, u16 xid)
{
struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
const struct net_device_ops *ops = real_dev->netdev_ops;
int len = 0;
if (ops->ndo_fcoe_ddp_done)
len = ops->ndo_fcoe_ddp_done(real_dev, xid);
return len;
}
static int vlan_dev_fcoe_enable(struct net_device *dev)
{
struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
const struct net_device_ops *ops = real_dev->netdev_ops;
int rc = -EINVAL;
if (ops->ndo_fcoe_enable)
rc = ops->ndo_fcoe_enable(real_dev);
return rc;
}
static int vlan_dev_fcoe_disable(struct net_device *dev)
{
struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
const struct net_device_ops *ops = real_dev->netdev_ops;
int rc = -EINVAL;
if (ops->ndo_fcoe_disable)
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_priv(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;
}
static int vlan_dev_fcoe_ddp_target(struct net_device *dev, u16 xid,
struct scatterlist *sgl, unsigned int sgc)
{
struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
const struct net_device_ops *ops = real_dev->netdev_ops;
int rc = 0;
if (ops->ndo_fcoe_ddp_target)
rc = ops->ndo_fcoe_ddp_target(real_dev, xid, sgl, sgc);
return rc;
}
#endif
static void vlan_dev_change_rx_flags(struct net_device *dev, int change)
{
struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
if (dev->flags & IFF_UP) {
if (change & IFF_ALLMULTI)
dev_set_allmulti(real_dev, dev->flags & IFF_ALLMULTI ? 1 : -1);
if (change & IFF_PROMISC)
dev_set_promiscuity(real_dev, dev->flags & IFF_PROMISC ? 1 : -1);
}
}
static int vlan_calculate_locking_subclass(struct net_device *real_dev)
{
int subclass = 0;
while (is_vlan_dev(real_dev)) {
subclass++;
real_dev = vlan_dev_priv(real_dev)->real_dev;
}
return subclass;
}
static void vlan_dev_mc_sync(struct net_device *to, struct net_device *from)
{
int err = 0, subclass;
subclass = vlan_calculate_locking_subclass(to);
spin_lock_nested(&to->addr_list_lock, subclass);
err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len);
if (!err)
__dev_set_rx_mode(to);
spin_unlock(&to->addr_list_lock);
}
static void vlan_dev_uc_sync(struct net_device *to, struct net_device *from)
{
int err = 0, subclass;
subclass = vlan_calculate_locking_subclass(to);
spin_lock_nested(&to->addr_list_lock, subclass);
err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len);
if (!err)
__dev_set_rx_mode(to);
spin_unlock(&to->addr_list_lock);
}
static void vlan_dev_set_rx_mode(struct net_device *vlan_dev)
{
vlan_dev_mc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
vlan_dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
}
/*
* vlan network devices have devices nesting below it, and are a special
* "super class" of normal network devices; split their locks off into a
* separate class since they always nest.
*/
static struct lock_class_key vlan_netdev_xmit_lock_key;
static struct lock_class_key vlan_netdev_addr_lock_key;
static void vlan_dev_set_lockdep_one(struct net_device *dev,
struct netdev_queue *txq,
void *_subclass)
{
lockdep_set_class_and_subclass(&txq->_xmit_lock,
&vlan_netdev_xmit_lock_key,
*(int *)_subclass);
}
static void vlan_dev_set_lockdep_class(struct net_device *dev, int subclass)
{
lockdep_set_class_and_subclass(&dev->addr_list_lock,
&vlan_netdev_addr_lock_key,
subclass);
netdev_for_each_tx_queue(dev, vlan_dev_set_lockdep_one, &subclass);
}
static const struct header_ops vlan_header_ops = {
.create = vlan_dev_hard_header,
.rebuild = vlan_dev_rebuild_header,
.parse = eth_header_parse,
};
static int vlan_passthru_hard_header(struct sk_buff *skb, struct net_device *dev,
unsigned short type,
const void *daddr, const void *saddr,
unsigned int len)
{
struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
struct net_device *real_dev = vlan->real_dev;
if (saddr == NULL)
saddr = dev->dev_addr;
return dev_hard_header(skb, real_dev, type, daddr, saddr, len);
}
static const struct header_ops vlan_passthru_header_ops = {
.create = vlan_passthru_hard_header,
.rebuild = dev_rebuild_header,
.parse = eth_header_parse,
};
static struct device_type vlan_type = {
.name = "vlan",
};
static const struct net_device_ops vlan_netdev_ops;
static int vlan_dev_init(struct net_device *dev)
{
struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
int subclass = 0;
netif_carrier_off(dev);
/* IFF_BROADCAST|IFF_MULTICAST; ??? */
dev->flags = real_dev->flags & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI |
IFF_MASTER | IFF_SLAVE);
dev->iflink = real_dev->ifindex;
dev->state = (real_dev->state & ((1<<__LINK_STATE_NOCARRIER) |
(1<<__LINK_STATE_DORMANT))) |
(1<<__LINK_STATE_PRESENT);
dev->hw_features = NETIF_F_ALL_CSUM | NETIF_F_SG |
NETIF_F_FRAGLIST | NETIF_F_ALL_TSO |
NETIF_F_HIGHDMA | NETIF_F_SCTP_CSUM |
NETIF_F_ALL_FCOE;
dev->features |= real_dev->vlan_features | NETIF_F_LLTX;
dev->gso_max_size = real_dev->gso_max_size;
if (dev->features & NETIF_F_VLAN_FEATURES)
netdev_warn(real_dev, "VLAN features are set incorrectly. Q-in-Q configurations may not work correctly.\n");
/* ipv6 shared card related stuff */
dev->dev_id = real_dev->dev_id;
if (is_zero_ether_addr(dev->dev_addr))
eth_hw_addr_inherit(dev, real_dev);
if (is_zero_ether_addr(dev->broadcast))
memcpy(dev->broadcast, real_dev->broadcast, dev->addr_len);
#if IS_ENABLED(CONFIG_FCOE)
dev->fcoe_ddp_xid = real_dev->fcoe_ddp_xid;
#endif
dev->needed_headroom = real_dev->needed_headroom;
if (vlan_hw_offload_capable(real_dev->features,
vlan_dev_priv(dev)->vlan_proto)) {
dev->header_ops = &vlan_passthru_header_ops;
dev->hard_header_len = real_dev->hard_header_len;
} else {
dev->header_ops = &vlan_header_ops;
dev->hard_header_len = real_dev->hard_header_len + VLAN_HLEN;
}
dev->netdev_ops = &vlan_netdev_ops;
SET_NETDEV_DEVTYPE(dev, &vlan_type);
subclass = vlan_calculate_locking_subclass(dev);
vlan_dev_set_lockdep_class(dev, subclass);
vlan_dev_priv(dev)->vlan_pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats);
if (!vlan_dev_priv(dev)->vlan_pcpu_stats)
return -ENOMEM;
return 0;
}
static void vlan_dev_uninit(struct net_device *dev)
{
struct vlan_priority_tci_mapping *pm;
struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
int i;
free_percpu(vlan->vlan_pcpu_stats);
vlan->vlan_pcpu_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;
kfree(pm);
}
}
}
static netdev_features_t vlan_dev_fix_features(struct net_device *dev,
netdev_features_t features)
{
struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
netdev_features_t old_features = features;
features &= real_dev->vlan_features;
features |= NETIF_F_RXCSUM;
features &= real_dev->features;
features |= old_features & NETIF_F_SOFT_FEATURES;
features |= NETIF_F_LLTX;
return features;
}
static int vlan_ethtool_get_settings(struct net_device *dev,
struct ethtool_cmd *cmd)
{
const struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
return __ethtool_get_settings(vlan->real_dev, cmd);
}
static void vlan_ethtool_get_drvinfo(struct net_device *dev,
struct ethtool_drvinfo *info)
{
strlcpy(info->driver, vlan_fullname, sizeof(info->driver));
strlcpy(info->version, vlan_version, sizeof(info->version));
strlcpy(info->fw_version, "N/A", sizeof(info->fw_version));
}
static struct rtnl_link_stats64 *vlan_dev_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
{
if (vlan_dev_priv(dev)->vlan_pcpu_stats) {
struct vlan_pcpu_stats *p;
u32 rx_errors = 0, tx_dropped = 0;
int i;
for_each_possible_cpu(i) {
u64 rxpackets, rxbytes, rxmulticast, txpackets, txbytes;
unsigned int start;
p = per_cpu_ptr(vlan_dev_priv(dev)->vlan_pcpu_stats, i);
do {
start = u64_stats_fetch_begin_irq(&p->syncp);
rxpackets = p->rx_packets;
rxbytes = p->rx_bytes;
rxmulticast = p->rx_multicast;
txpackets = p->tx_packets;
txbytes = p->tx_bytes;
} while (u64_stats_fetch_retry_irq(&p->syncp, start));
stats->rx_packets += rxpackets;
stats->rx_bytes += rxbytes;
stats->multicast += rxmulticast;
stats->tx_packets += txpackets;
stats->tx_bytes += txbytes;
/* rx_errors & tx_dropped are u32 */
rx_errors += p->rx_errors;
tx_dropped += p->tx_dropped;
}
stats->rx_errors = rx_errors;
stats->tx_dropped = tx_dropped;
}
return stats;
}
#ifdef CONFIG_NET_POLL_CONTROLLER
static void vlan_dev_poll_controller(struct net_device *dev)
{
return;
}
static int vlan_dev_netpoll_setup(struct net_device *dev, struct netpoll_info *npinfo)
{
struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
struct net_device *real_dev = vlan->real_dev;
struct netpoll *netpoll;
int err = 0;
netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL);
err = -ENOMEM;
if (!netpoll)
goto out;
err = __netpoll_setup(netpoll, real_dev);
if (err) {
kfree(netpoll);
goto out;
}
vlan->netpoll = netpoll;
out:
return err;
}
static void vlan_dev_netpoll_cleanup(struct net_device *dev)
{
struct vlan_dev_priv *vlan= vlan_dev_priv(dev);
struct netpoll *netpoll = vlan->netpoll;
if (!netpoll)
return;
vlan->netpoll = NULL;
__netpoll_free_async(netpoll);
}
#endif /* CONFIG_NET_POLL_CONTROLLER */
static const struct ethtool_ops vlan_ethtool_ops = {
.get_settings = vlan_ethtool_get_settings,
.get_drvinfo = vlan_ethtool_get_drvinfo,
.get_link = ethtool_op_get_link,
};
static const struct net_device_ops vlan_netdev_ops = {
.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_change_rx_flags = vlan_dev_change_rx_flags,
.ndo_do_ioctl = vlan_dev_ioctl,
.ndo_neigh_setup = vlan_dev_neigh_setup,
.ndo_get_stats64 = vlan_dev_get_stats64,
#if IS_ENABLED(CONFIG_FCOE)
.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,
.ndo_fcoe_ddp_target = vlan_dev_fcoe_ddp_target,
#endif
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = vlan_dev_poll_controller,
.ndo_netpoll_setup = vlan_dev_netpoll_setup,
.ndo_netpoll_cleanup = vlan_dev_netpoll_cleanup,
#endif
.ndo_fix_features = vlan_dev_fix_features,
};
void vlan_setup(struct net_device *dev)
{
ether_setup(dev);
dev->priv_flags |= IFF_802_1Q_VLAN;
dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING);
dev->tx_queue_len = 0;
dev->netdev_ops = &vlan_netdev_ops;
dev->destructor = free_netdev;
dev->ethtool_ops = &vlan_ethtool_ops;
memset(dev->broadcast, 0, ETH_ALEN);
}