Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Pull networking fixes from David Miller:
1) We've discovered a common error in several networking drivers, they
put VLAN offload features into ->vlan_features, which would suggest
that they support offloading 2 or more levels of VLAN encapsulation.
Not only do these devices not do that, but we don't have the
infrastructure yet to handle that at all.
Fixes from Vlad Yasevich.
2) Fix tcpdump crash with bridging and vlans, also from Vlad.
3) Some MAINTAINERS updates for random32 and bonding.
4) Fix late reseeds of prandom generator, from Sasha Levin.
5) Bridge doesn't handle stacked vlans properly, fix from Toshiaki
Makita.
6) Fix deadlock in openvswitch, from Flavio Leitner.
7) get_timewait4_sock() doesn't report delay times correctly, fix from
Eric Dumazet.
8) Duplicate address detection and addrconf verification need to run in
contexts where RTNL can be obtained. Move them to run from a
workqueue. From Hannes Frederic Sowa.
9) Fix route refcount leaking in ip tunnels, from Pravin B Shelar.
10) Don't return -EINTR from non-blocking recvmsg() on AF_UNIX sockets,
from Eric Dumazet.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (28 commits)
vlan: Warn the user if lowerdev has bad vlan features.
veth: Turn off vlan rx acceleration in vlan_features
ifb: Remove vlan acceleration from vlan_features
qlge: Do not propaged vlan tag offloads to vlans
bridge: Fix crash with vlan filtering and tcpdump
net: Account for all vlan headers in skb_mac_gso_segment
MAINTAINERS: bonding: change email address
MAINTAINERS: bonding: change email address
ipv6: move DAD and addrconf_verify processing to workqueue
tcp: fix get_timewait4_sock() delay computation on 64bit
openvswitch: fix a possible deadlock and lockdep warning
bridge: Fix handling stacked vlan tags
bridge: Fix inabillity to retrieve vlan tags when tx offload is disabled
vhost: validate vhost_get_vq_desc return value
vhost: fix total length when packets are too short
random32: avoid attempt to late reseed if in the middle of seeding
random32: assign to network folks in MAINTAINERS
net/mlx4_core: pass pci_device_id.driver_data to __mlx4_init_one during reset
core, nfqueue, openvswitch: Orphan frags in skb_zerocopy and handle errors
vlan: Set hard_header_len according to available acceleration
...
diff --git a/MAINTAINERS b/MAINTAINERS
index 82640e6..a80c84e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1832,8 +1832,8 @@
F: include/net/bluetooth/
BONDING DRIVER
-M: Jay Vosburgh <fubar@us.ibm.com>
-M: Veaceslav Falico <vfalico@redhat.com>
+M: Jay Vosburgh <j.vosburgh@gmail.com>
+M: Veaceslav Falico <vfalico@gmail.com>
M: Andy Gospodarek <andy@greyhouse.net>
L: netdev@vger.kernel.org
W: http://sourceforge.net/projects/bonding/
@@ -6006,6 +6006,7 @@
F: include/uapi/linux/netdevice.h
F: tools/net/
F: tools/testing/selftests/net/
+F: lib/random32.c
NETWORKING [IPv4/IPv6]
M: "David S. Miller" <davem@davemloft.net>
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 3b6d0ba..70a225c8 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -17649,8 +17649,6 @@
tg3_init_bufmgr_config(tp);
- features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
-
/* 5700 B0 chips do not support checksumming correctly due
* to hardware bugs.
*/
@@ -17682,7 +17680,8 @@
features |= NETIF_F_TSO_ECN;
}
- dev->features |= features;
+ dev->features |= features | NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_CTAG_RX;
dev->vlan_features |= features;
/*
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index f418f4f..8d76fca 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -22,6 +22,7 @@
#include <linux/interrupt.h>
#include <net/ip.h>
#include <net/ipv6.h>
+#include <linux/io.h>
#include <linux/of.h>
#include <linux/of_irq.h>
#include <linux/of_mdio.h>
@@ -88,8 +89,9 @@
#define MVNETA_TX_IN_PRGRS BIT(1)
#define MVNETA_TX_FIFO_EMPTY BIT(8)
#define MVNETA_RX_MIN_FRAME_SIZE 0x247c
-#define MVNETA_SGMII_SERDES_CFG 0x24A0
+#define MVNETA_SERDES_CFG 0x24A0
#define MVNETA_SGMII_SERDES_PROTO 0x0cc7
+#define MVNETA_RGMII_SERDES_PROTO 0x0667
#define MVNETA_TYPE_PRIO 0x24bc
#define MVNETA_FORCE_UNI BIT(21)
#define MVNETA_TXQ_CMD_1 0x24e4
@@ -161,7 +163,7 @@
#define MVNETA_GMAC_MAX_RX_SIZE_MASK 0x7ffc
#define MVNETA_GMAC0_PORT_ENABLE BIT(0)
#define MVNETA_GMAC_CTRL_2 0x2c08
-#define MVNETA_GMAC2_PSC_ENABLE BIT(3)
+#define MVNETA_GMAC2_PCS_ENABLE BIT(3)
#define MVNETA_GMAC2_PORT_RGMII BIT(4)
#define MVNETA_GMAC2_PORT_RESET BIT(6)
#define MVNETA_GMAC_STATUS 0x2c10
@@ -710,35 +712,6 @@
mvreg_write(pp, MVNETA_RXQ_CONFIG_REG(rxq->id), val);
}
-
-
-/* Sets the RGMII Enable bit (RGMIIEn) in port MAC control register */
-static void mvneta_gmac_rgmii_set(struct mvneta_port *pp, int enable)
-{
- u32 val;
-
- val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
-
- if (enable)
- val |= MVNETA_GMAC2_PORT_RGMII;
- else
- val &= ~MVNETA_GMAC2_PORT_RGMII;
-
- mvreg_write(pp, MVNETA_GMAC_CTRL_2, val);
-}
-
-/* Config SGMII port */
-static void mvneta_port_sgmii_config(struct mvneta_port *pp)
-{
- u32 val;
-
- val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
- val |= MVNETA_GMAC2_PSC_ENABLE;
- mvreg_write(pp, MVNETA_GMAC_CTRL_2, val);
-
- mvreg_write(pp, MVNETA_SGMII_SERDES_CFG, MVNETA_SGMII_SERDES_PROTO);
-}
-
/* Start the Ethernet port RX and TX activity */
static void mvneta_port_up(struct mvneta_port *pp)
{
@@ -2756,12 +2729,15 @@
mvreg_write(pp, MVNETA_UNIT_INTR_CAUSE, 0);
if (phy_mode == PHY_INTERFACE_MODE_SGMII)
- mvneta_port_sgmii_config(pp);
+ mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_SGMII_SERDES_PROTO);
+ else
+ mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_RGMII_SERDES_PROTO);
- mvneta_gmac_rgmii_set(pp, 1);
+ val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
+
+ val |= MVNETA_GMAC2_PCS_ENABLE | MVNETA_GMAC2_PORT_RGMII;
/* Cancel Port Reset */
- val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
val &= ~MVNETA_GMAC2_PORT_RESET;
mvreg_write(pp, MVNETA_GMAC_CTRL_2, val);
@@ -2774,6 +2750,7 @@
static int mvneta_probe(struct platform_device *pdev)
{
const struct mbus_dram_target_info *dram_target_info;
+ struct resource *res;
struct device_node *dn = pdev->dev.of_node;
struct device_node *phy_node;
u32 phy_addr;
@@ -2838,9 +2815,15 @@
clk_prepare_enable(pp->clk);
- pp->base = of_iomap(dn, 0);
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!res) {
+ err = -ENODEV;
+ goto err_clk;
+ }
+
+ pp->base = devm_ioremap_resource(&pdev->dev, res);
if (pp->base == NULL) {
- err = -ENOMEM;
+ err = PTR_ERR(pp->base);
goto err_clk;
}
@@ -2848,7 +2831,7 @@
pp->stats = alloc_percpu(struct mvneta_pcpu_stats);
if (!pp->stats) {
err = -ENOMEM;
- goto err_unmap;
+ goto err_clk;
}
for_each_possible_cpu(cpu) {
@@ -2913,8 +2896,6 @@
mvneta_deinit(pp);
err_free_stats:
free_percpu(pp->stats);
-err_unmap:
- iounmap(pp->base);
err_clk:
clk_disable_unprepare(pp->clk);
err_free_irq:
@@ -2934,7 +2915,6 @@
mvneta_deinit(pp);
clk_disable_unprepare(pp->clk);
free_percpu(pp->stats);
- iounmap(pp->base);
irq_dispose_mapping(dev->irq);
free_netdev(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 936c153..d413e60 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -2681,7 +2681,11 @@
static pci_ers_result_t mlx4_pci_slot_reset(struct pci_dev *pdev)
{
- int ret = __mlx4_init_one(pdev, 0);
+ const struct pci_device_id *id;
+ int ret;
+
+ id = pci_match_id(mlx4_pci_table, pdev);
+ ret = __mlx4_init_one(pdev, id->driver_data);
return ret ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
}
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
index ce2cfdd..656c65d 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
@@ -4765,7 +4765,9 @@
ndev->features = ndev->hw_features;
ndev->vlan_features = ndev->hw_features;
/* vlan gets same features (except vlan filter) */
- ndev->vlan_features &= ~NETIF_F_HW_VLAN_CTAG_FILTER;
+ ndev->vlan_features &= ~(NETIF_F_HW_VLAN_CTAG_FILTER |
+ NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_CTAG_RX);
if (test_bit(QL_DMA64, &qdev->flags))
ndev->features |= NETIF_F_HIGHDMA;
diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c
index c14d39b..d7b2e94 100644
--- a/drivers/net/ifb.c
+++ b/drivers/net/ifb.c
@@ -180,7 +180,8 @@
dev->tx_queue_len = TX_Q_LIMIT;
dev->features |= IFB_FEATURES;
- dev->vlan_features |= IFB_FEATURES;
+ dev->vlan_features |= IFB_FEATURES & ~(NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_STAG_TX);
dev->flags |= IFF_NOARP;
dev->flags &= ~IFF_MULTICAST;
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index dd10d58..f9e96c4 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -752,14 +752,12 @@
// precondition: never called in_interrupt
static void usbnet_terminate_urbs(struct usbnet *dev)
{
- DECLARE_WAIT_QUEUE_HEAD_ONSTACK(unlink_wakeup);
DECLARE_WAITQUEUE(wait, current);
int temp;
/* ensure there are no more active urbs */
- add_wait_queue(&unlink_wakeup, &wait);
+ add_wait_queue(&dev->wait, &wait);
set_current_state(TASK_UNINTERRUPTIBLE);
- dev->wait = &unlink_wakeup;
temp = unlink_urbs(dev, &dev->txq) +
unlink_urbs(dev, &dev->rxq);
@@ -773,15 +771,14 @@
"waited for %d urb completions\n", temp);
}
set_current_state(TASK_RUNNING);
- dev->wait = NULL;
- remove_wait_queue(&unlink_wakeup, &wait);
+ remove_wait_queue(&dev->wait, &wait);
}
int usbnet_stop (struct net_device *net)
{
struct usbnet *dev = netdev_priv(net);
struct driver_info *info = dev->driver_info;
- int retval;
+ int retval, pm;
clear_bit(EVENT_DEV_OPEN, &dev->flags);
netif_stop_queue (net);
@@ -791,6 +788,8 @@
net->stats.rx_packets, net->stats.tx_packets,
net->stats.rx_errors, net->stats.tx_errors);
+ /* to not race resume */
+ pm = usb_autopm_get_interface(dev->intf);
/* allow minidriver to stop correctly (wireless devices to turn off
* radio etc) */
if (info->stop) {
@@ -817,6 +816,9 @@
dev->flags = 0;
del_timer_sync (&dev->delay);
tasklet_kill (&dev->bh);
+ if (!pm)
+ usb_autopm_put_interface(dev->intf);
+
if (info->manage_power &&
!test_and_clear_bit(EVENT_NO_RUNTIME_PM, &dev->flags))
info->manage_power(dev, 0);
@@ -1437,11 +1439,12 @@
/* restart RX again after disabling due to high error rate */
clear_bit(EVENT_RX_KILL, &dev->flags);
- // waiting for all pending urbs to complete?
- if (dev->wait) {
- if ((dev->txq.qlen + dev->rxq.qlen + dev->done.qlen) == 0) {
- wake_up (dev->wait);
- }
+ /* waiting for all pending urbs to complete?
+ * only then can we forgo submitting anew
+ */
+ if (waitqueue_active(&dev->wait)) {
+ if (dev->txq.qlen + dev->rxq.qlen + dev->done.qlen == 0)
+ wake_up_all(&dev->wait);
// or are we maybe short a few urbs?
} else if (netif_running (dev->net) &&
@@ -1580,6 +1583,7 @@
dev->driver_name = name;
dev->msg_enable = netif_msg_init (msg_level, NETIF_MSG_DRV
| NETIF_MSG_PROBE | NETIF_MSG_LINK);
+ init_waitqueue_head(&dev->wait);
skb_queue_head_init (&dev->rxq);
skb_queue_head_init (&dev->txq);
skb_queue_head_init (&dev->done);
@@ -1791,9 +1795,10 @@
spin_unlock_irq(&dev->txq.lock);
if (test_bit(EVENT_DEV_OPEN, &dev->flags)) {
- /* handle remote wakeup ASAP */
- if (!dev->wait &&
- netif_device_present(dev->net) &&
+ /* handle remote wakeup ASAP
+ * we cannot race against stop
+ */
+ if (netif_device_present(dev->net) &&
!timer_pending(&dev->delay) &&
!test_bit(EVENT_RX_HALT, &dev->flags))
rx_alloc_submit(dev, GFP_NOIO);
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 5b37437..c0e7c64 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -286,7 +286,10 @@
dev->features |= NETIF_F_LLTX;
dev->features |= VETH_FEATURES;
dev->vlan_features = dev->features &
- ~(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX);
+ ~(NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_STAG_TX |
+ NETIF_F_HW_VLAN_CTAG_RX |
+ NETIF_F_HW_VLAN_STAG_RX);
dev->destructor = veth_dev_free;
dev->hw_features = VETH_FEATURES;
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 5632a99..841b608 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -671,8 +671,7 @@
if (err)
break;
} while (rq->vq->num_free);
- if (unlikely(!virtqueue_kick(rq->vq)))
- return false;
+ virtqueue_kick(rq->vq);
return !oom;
}
@@ -877,7 +876,7 @@
err = xmit_skb(sq, skb);
/* This should not happen! */
- if (unlikely(err) || unlikely(!virtqueue_kick(sq->vq))) {
+ if (unlikely(err)) {
dev->stats.tx_fifo_errors++;
if (net_ratelimit())
dev_warn(&dev->dev,
@@ -886,6 +885,7 @@
kfree_skb(skb);
return NETDEV_TX_OK;
}
+ virtqueue_kick(sq->vq);
/* Don't wait up for transmitted skbs to be freed. */
skb_orphan(skb);
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index a0fa5de..e1e22e0 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -505,9 +505,13 @@
r = -ENOBUFS;
goto err;
}
- d = vhost_get_vq_desc(vq->dev, vq, vq->iov + seg,
+ r = vhost_get_vq_desc(vq->dev, vq, vq->iov + seg,
ARRAY_SIZE(vq->iov) - seg, &out,
&in, log, log_num);
+ if (unlikely(r < 0))
+ goto err;
+
+ d = r;
if (d == vq->num) {
r = 0;
goto err;
@@ -532,6 +536,12 @@
*iovcount = seg;
if (unlikely(log))
*log_num = nlogs;
+
+ /* Detect overrun */
+ if (unlikely(datalen > 0)) {
+ r = UIO_MAXIOV + 1;
+ goto err;
+ }
return headcount;
err:
vhost_discard_vq_desc(vq, headcount);
@@ -587,6 +597,14 @@
/* On error, stop handling until the next kick. */
if (unlikely(headcount < 0))
break;
+ /* On overrun, truncate and discard */
+ if (unlikely(headcount > UIO_MAXIOV)) {
+ msg.msg_iovlen = 1;
+ err = sock->ops->recvmsg(NULL, sock, &msg,
+ 1, MSG_DONTWAIT | MSG_TRUNC);
+ pr_debug("Discarded rx packet: len %zd\n", sock_len);
+ continue;
+ }
/* OK, now we need to know about added descriptors. */
if (!headcount) {
if (unlikely(vhost_enable_notify(&net->dev, vq))) {
diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index 1005ebf..5a09a48 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -163,4 +163,11 @@
/* changeable features with no special hardware requirements */
#define NETIF_F_SOFT_FEATURES (NETIF_F_GSO | NETIF_F_GRO)
+#define NETIF_F_VLAN_FEATURES (NETIF_F_HW_VLAN_CTAG_FILTER | \
+ NETIF_F_HW_VLAN_CTAG_RX | \
+ NETIF_F_HW_VLAN_CTAG_TX | \
+ NETIF_F_HW_VLAN_STAG_FILTER | \
+ NETIF_F_HW_VLAN_STAG_RX | \
+ NETIF_F_HW_VLAN_STAG_TX)
+
#endif /* _LINUX_NETDEV_FEATURES_H */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index e8eeebd..daafd95 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3014,7 +3014,7 @@
{
return __skb_gso_segment(skb, features, true);
}
-__be16 skb_network_protocol(struct sk_buff *skb);
+__be16 skb_network_protocol(struct sk_buff *skb, int *depth);
static inline bool can_checksum_protocol(netdev_features_t features,
__be16 protocol)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 5e1e6f2..15ede6a 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2451,8 +2451,8 @@
unsigned int flags);
void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to);
unsigned int skb_zerocopy_headlen(const struct sk_buff *from);
-void skb_zerocopy(struct sk_buff *to, const struct sk_buff *from,
- int len, int hlen);
+int skb_zerocopy(struct sk_buff *to, struct sk_buff *from,
+ int len, int hlen);
void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len);
int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen);
void skb_scrub_packet(struct sk_buff *skb, bool xnet);
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index e303eef..0662e98 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -30,7 +30,7 @@
struct driver_info *driver_info;
const char *driver_name;
void *driver_priv;
- wait_queue_head_t *wait;
+ wait_queue_head_t wait;
struct mutex phy_mutex;
unsigned char suspend_count;
unsigned char pkt_cnt, pkt_err;
diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h
index 9650a3f..b4956a5 100644
--- a/include/net/if_inet6.h
+++ b/include/net/if_inet6.h
@@ -31,8 +31,10 @@
#define IF_PREFIX_AUTOCONF 0x02
enum {
+ INET6_IFADDR_STATE_PREDAD,
INET6_IFADDR_STATE_DAD,
INET6_IFADDR_STATE_POSTDAD,
+ INET6_IFADDR_STATE_ERRDAD,
INET6_IFADDR_STATE_UP,
INET6_IFADDR_STATE_DEAD,
};
@@ -58,7 +60,7 @@
unsigned long cstamp; /* created timestamp */
unsigned long tstamp; /* updated timestamp */
- struct timer_list dad_timer;
+ struct delayed_work dad_work;
struct inet6_dev *idev;
struct rt6_info *rt;
diff --git a/lib/random32.c b/lib/random32.c
index 1e5b2df..6148967 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -244,8 +244,19 @@
static bool latch = false;
static DEFINE_SPINLOCK(lock);
+ /* Asking for random bytes might result in bytes getting
+ * moved into the nonblocking pool and thus marking it
+ * as initialized. In this case we would double back into
+ * this function and attempt to do a late reseed.
+ * Ignore the pointless attempt to reseed again if we're
+ * already waiting for bytes when the nonblocking pool
+ * got initialized.
+ */
+
/* only allow initial seeding (late == false) once */
- spin_lock_irqsave(&lock, flags);
+ if (!spin_trylock_irqsave(&lock, flags))
+ return;
+
if (latch && !late)
goto out;
latch = true;
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index ec99099..175273f 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -307,9 +307,11 @@
static void vlan_transfer_features(struct net_device *dev,
struct net_device *vlandev)
{
+ struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev);
+
vlandev->gso_max_size = dev->gso_max_size;
- if (dev->features & NETIF_F_HW_VLAN_CTAG_TX)
+ if (vlan_hw_offload_capable(dev->features, vlan->vlan_proto))
vlandev->hard_header_len = dev->hard_header_len;
else
vlandev->hard_header_len = dev->hard_header_len + VLAN_HLEN;
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 4b65aa4..27bfe2f 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -578,6 +578,9 @@
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;
@@ -592,7 +595,8 @@
#endif
dev->needed_headroom = real_dev->needed_headroom;
- if (real_dev->features & NETIF_F_HW_VLAN_CTAG_TX) {
+ 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 {
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 63f0455..8fe8b71 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -49,14 +49,14 @@
brstats->tx_bytes += skb->len;
u64_stats_update_end(&brstats->syncp);
- if (!br_allowed_ingress(br, br_get_vlan_info(br), skb, &vid))
- goto out;
-
BR_INPUT_SKB_CB(skb)->brdev = dev;
skb_reset_mac_header(skb);
skb_pull(skb, ETH_HLEN);
+ if (!br_allowed_ingress(br, br_get_vlan_info(br), skb, &vid))
+ goto out;
+
if (is_broadcast_ether_addr(dest))
br_flood_deliver(br, skb, false);
else if (is_multicast_ether_addr(dest)) {
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 28d5446..d0cca3c 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -29,6 +29,7 @@
struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev;
struct net_bridge *br = netdev_priv(brdev);
struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats);
+ struct net_port_vlans *pv;
u64_stats_update_begin(&brstats->syncp);
brstats->rx_packets++;
@@ -39,18 +40,18 @@
* packet is allowed except in promisc modue when someone
* may be running packet capture.
*/
+ pv = br_get_vlan_info(br);
if (!(brdev->flags & IFF_PROMISC) &&
- !br_allowed_egress(br, br_get_vlan_info(br), skb)) {
+ !br_allowed_egress(br, pv, skb)) {
kfree_skb(skb);
return NET_RX_DROP;
}
- skb = br_handle_vlan(br, br_get_vlan_info(br), skb);
- if (!skb)
- return NET_RX_DROP;
-
indev = skb->dev;
skb->dev = brdev;
+ skb = br_handle_vlan(br, pv, skb);
+ if (!skb)
+ return NET_RX_DROP;
return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, skb, indev, NULL,
netif_receive_skb);
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 8249ca76..f23c74b 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -119,22 +119,6 @@
kfree_rcu(v, rcu);
}
-/* Strip the tag from the packet. Will return skb with tci set 0. */
-static struct sk_buff *br_vlan_untag(struct sk_buff *skb)
-{
- if (skb->protocol != htons(ETH_P_8021Q)) {
- skb->vlan_tci = 0;
- return skb;
- }
-
- skb->vlan_tci = 0;
- skb = vlan_untag(skb);
- if (skb)
- skb->vlan_tci = 0;
-
- return skb;
-}
-
struct sk_buff *br_handle_vlan(struct net_bridge *br,
const struct net_port_vlans *pv,
struct sk_buff *skb)
@@ -144,13 +128,27 @@
if (!br->vlan_enabled)
goto out;
+ /* Vlan filter table must be configured at this point. The
+ * only exception is the bridge is set in promisc mode and the
+ * packet is destined for the bridge device. In this case
+ * pass the packet as is.
+ */
+ if (!pv) {
+ if ((br->dev->flags & IFF_PROMISC) && skb->dev == br->dev) {
+ goto out;
+ } else {
+ kfree_skb(skb);
+ return NULL;
+ }
+ }
+
/* At this point, we know that the frame was filtered and contains
* a valid vlan id. If the vlan id is set in the untagged bitmap,
* send untagged; otherwise, send tagged.
*/
br_vlan_get_tag(skb, &vid);
if (test_bit(vid, pv->untagged_bitmap))
- skb = br_vlan_untag(skb);
+ skb->vlan_tci = 0;
out:
return skb;
@@ -174,6 +172,18 @@
if (!v)
return false;
+ /* If vlan tx offload is disabled on bridge device and frame was
+ * sent from vlan device on the bridge device, it does not have
+ * HW accelerated vlan tag.
+ */
+ if (unlikely(!vlan_tx_tag_present(skb) &&
+ (skb->protocol == htons(ETH_P_8021Q) ||
+ skb->protocol == htons(ETH_P_8021AD)))) {
+ skb = vlan_untag(skb);
+ if (unlikely(!skb))
+ return false;
+ }
+
err = br_vlan_get_tag(skb, vid);
if (!*vid) {
u16 pvid = br_get_pvid(v);
diff --git a/net/core/dev.c b/net/core/dev.c
index b1b0c8d..45fa2f1 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2286,7 +2286,7 @@
}
EXPORT_SYMBOL(skb_checksum_help);
-__be16 skb_network_protocol(struct sk_buff *skb)
+__be16 skb_network_protocol(struct sk_buff *skb, int *depth)
{
__be16 type = skb->protocol;
int vlan_depth = ETH_HLEN;
@@ -2313,6 +2313,8 @@
vlan_depth += VLAN_HLEN;
}
+ *depth = vlan_depth;
+
return type;
}
@@ -2326,12 +2328,13 @@
{
struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
struct packet_offload *ptype;
- __be16 type = skb_network_protocol(skb);
+ int vlan_depth = skb->mac_len;
+ __be16 type = skb_network_protocol(skb, &vlan_depth);
if (unlikely(!type))
return ERR_PTR(-EINVAL);
- __skb_pull(skb, skb->mac_len);
+ __skb_pull(skb, vlan_depth);
rcu_read_lock();
list_for_each_entry_rcu(ptype, &offload_base, list) {
@@ -2498,8 +2501,10 @@
const struct net_device *dev,
netdev_features_t features)
{
+ int tmp;
+
if (skb->ip_summed != CHECKSUM_NONE &&
- !can_checksum_protocol(features, skb_network_protocol(skb))) {
+ !can_checksum_protocol(features, skb_network_protocol(skb, &tmp))) {
features &= ~NETIF_F_ALL_CSUM;
} else if (illegal_highdma(dev, skb)) {
features &= ~NETIF_F_SG;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 869c7af..90b96a1 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2127,25 +2127,31 @@
*
* The `hlen` as calculated by skb_zerocopy_headlen() specifies the
* headroom in the `to` buffer.
+ *
+ * Return value:
+ * 0: everything is OK
+ * -ENOMEM: couldn't orphan frags of @from due to lack of memory
+ * -EFAULT: skb_copy_bits() found some problem with skb geometry
*/
-void
-skb_zerocopy(struct sk_buff *to, const struct sk_buff *from, int len, int hlen)
+int
+skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen)
{
int i, j = 0;
int plen = 0; /* length of skb->head fragment */
+ int ret;
struct page *page;
unsigned int offset;
BUG_ON(!from->head_frag && !hlen);
/* dont bother with small payloads */
- if (len <= skb_tailroom(to)) {
- skb_copy_bits(from, 0, skb_put(to, len), len);
- return;
- }
+ if (len <= skb_tailroom(to))
+ return skb_copy_bits(from, 0, skb_put(to, len), len);
if (hlen) {
- skb_copy_bits(from, 0, skb_put(to, hlen), hlen);
+ ret = skb_copy_bits(from, 0, skb_put(to, hlen), hlen);
+ if (unlikely(ret))
+ return ret;
len -= hlen;
} else {
plen = min_t(int, skb_headlen(from), len);
@@ -2163,6 +2169,11 @@
to->len += len + plen;
to->data_len += len + plen;
+ if (unlikely(skb_orphan_frags(from, GFP_ATOMIC))) {
+ skb_tx_error(from);
+ return -ENOMEM;
+ }
+
for (i = 0; i < skb_shinfo(from)->nr_frags; i++) {
if (!len)
break;
@@ -2173,6 +2184,8 @@
j++;
}
skb_shinfo(to)->nr_frags = j;
+
+ return 0;
}
EXPORT_SYMBOL_GPL(skb_zerocopy);
@@ -2866,8 +2879,9 @@
int err = -ENOMEM;
int i = 0;
int pos;
+ int dummy;
- proto = skb_network_protocol(head_skb);
+ proto = skb_network_protocol(head_skb, &dummy);
if (unlikely(!proto))
return ERR_PTR(-EINVAL);
diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
index 1863422f..250be74 100644
--- a/net/ipv4/gre_demux.c
+++ b/net/ipv4/gre_demux.c
@@ -182,6 +182,14 @@
int i;
bool csum_err = false;
+#ifdef CONFIG_NET_IPGRE_BROADCAST
+ if (ipv4_is_multicast(ip_hdr(skb)->daddr)) {
+ /* Looped back packet, drop it! */
+ if (rt_is_output_route(skb_rtable(skb)))
+ goto drop;
+ }
+#endif
+
if (parse_gre_header(skb, &tpi, &csum_err) < 0)
goto drop;
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 78a89e6..a82a22d 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -416,9 +416,6 @@
#ifdef CONFIG_NET_IPGRE_BROADCAST
if (ipv4_is_multicast(iph->daddr)) {
- /* Looped back packet, drop it! */
- if (rt_is_output_route(skb_rtable(skb)))
- goto drop;
tunnel->dev->stats.multicast++;
skb->pkt_type = PACKET_BROADCAST;
}
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 6f847dd..8d69626 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -108,6 +108,7 @@
nf_reset(skb);
secpath_reset(skb);
skb_clear_hash_if_not_l4(skb);
+ skb_dst_drop(skb);
skb->vlan_tci = 0;
skb_set_queue_mapping(skb, 0);
skb->pkt_type = PACKET_HOST;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 3cf9765..1e4eac7 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2628,7 +2628,7 @@
{
__be32 dest, src;
__u16 destp, srcp;
- long delta = tw->tw_ttd - jiffies;
+ s32 delta = tw->tw_ttd - inet_tw_time_stamp();
dest = tw->tw_daddr;
src = tw->tw_rcv_saddr;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 344e972..6c7fa08 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -133,10 +133,12 @@
static struct hlist_head inet6_addr_lst[IN6_ADDR_HSIZE];
static DEFINE_SPINLOCK(addrconf_hash_lock);
-static void addrconf_verify(unsigned long);
+static void addrconf_verify(void);
+static void addrconf_verify_rtnl(void);
+static void addrconf_verify_work(struct work_struct *);
-static DEFINE_TIMER(addr_chk_timer, addrconf_verify, 0, 0);
-static DEFINE_SPINLOCK(addrconf_verify_lock);
+static struct workqueue_struct *addrconf_wq;
+static DECLARE_DELAYED_WORK(addr_chk_work, addrconf_verify_work);
static void addrconf_join_anycast(struct inet6_ifaddr *ifp);
static void addrconf_leave_anycast(struct inet6_ifaddr *ifp);
@@ -151,7 +153,7 @@
u32 flags, u32 noflags);
static void addrconf_dad_start(struct inet6_ifaddr *ifp);
-static void addrconf_dad_timer(unsigned long data);
+static void addrconf_dad_work(struct work_struct *w);
static void addrconf_dad_completed(struct inet6_ifaddr *ifp);
static void addrconf_dad_run(struct inet6_dev *idev);
static void addrconf_rs_timer(unsigned long data);
@@ -247,9 +249,9 @@
__in6_dev_put(idev);
}
-static void addrconf_del_dad_timer(struct inet6_ifaddr *ifp)
+static void addrconf_del_dad_work(struct inet6_ifaddr *ifp)
{
- if (del_timer(&ifp->dad_timer))
+ if (cancel_delayed_work(&ifp->dad_work))
__in6_ifa_put(ifp);
}
@@ -261,12 +263,12 @@
mod_timer(&idev->rs_timer, jiffies + when);
}
-static void addrconf_mod_dad_timer(struct inet6_ifaddr *ifp,
- unsigned long when)
+static void addrconf_mod_dad_work(struct inet6_ifaddr *ifp,
+ unsigned long delay)
{
- if (!timer_pending(&ifp->dad_timer))
+ if (!delayed_work_pending(&ifp->dad_work))
in6_ifa_hold(ifp);
- mod_timer(&ifp->dad_timer, jiffies + when);
+ mod_delayed_work(addrconf_wq, &ifp->dad_work, delay);
}
static int snmp6_alloc_dev(struct inet6_dev *idev)
@@ -751,8 +753,9 @@
in6_dev_put(ifp->idev);
- if (del_timer(&ifp->dad_timer))
- pr_notice("Timer is still running, when freeing ifa=%p\n", ifp);
+ if (cancel_delayed_work(&ifp->dad_work))
+ pr_notice("delayed DAD work was pending while freeing ifa=%p\n",
+ ifp);
if (ifp->state != INET6_IFADDR_STATE_DEAD) {
pr_warn("Freeing alive inet6 address %p\n", ifp);
@@ -849,8 +852,7 @@
spin_lock_init(&ifa->lock);
spin_lock_init(&ifa->state_lock);
- setup_timer(&ifa->dad_timer, addrconf_dad_timer,
- (unsigned long)ifa);
+ INIT_DELAYED_WORK(&ifa->dad_work, addrconf_dad_work);
INIT_HLIST_NODE(&ifa->addr_lst);
ifa->scope = scope;
ifa->prefix_len = pfxlen;
@@ -990,6 +992,8 @@
enum cleanup_prefix_rt_t action = CLEANUP_PREFIX_RT_NOP;
unsigned long expires;
+ ASSERT_RTNL();
+
spin_lock_bh(&ifp->state_lock);
state = ifp->state;
ifp->state = INET6_IFADDR_STATE_DEAD;
@@ -1021,7 +1025,7 @@
write_unlock_bh(&ifp->idev->lock);
- addrconf_del_dad_timer(ifp);
+ addrconf_del_dad_work(ifp);
ipv6_ifa_notify(RTM_DELADDR, ifp);
@@ -1604,7 +1608,7 @@
{
if (ifp->flags&IFA_F_PERMANENT) {
spin_lock_bh(&ifp->lock);
- addrconf_del_dad_timer(ifp);
+ addrconf_del_dad_work(ifp);
ifp->flags |= IFA_F_TENTATIVE;
if (dad_failed)
ifp->flags |= IFA_F_DADFAILED;
@@ -1625,20 +1629,21 @@
spin_unlock_bh(&ifp->lock);
}
ipv6_del_addr(ifp);
- } else
+ } else {
ipv6_del_addr(ifp);
+ }
}
static int addrconf_dad_end(struct inet6_ifaddr *ifp)
{
int err = -ENOENT;
- spin_lock(&ifp->state_lock);
+ spin_lock_bh(&ifp->state_lock);
if (ifp->state == INET6_IFADDR_STATE_DAD) {
ifp->state = INET6_IFADDR_STATE_POSTDAD;
err = 0;
}
- spin_unlock(&ifp->state_lock);
+ spin_unlock_bh(&ifp->state_lock);
return err;
}
@@ -1671,7 +1676,12 @@
}
}
- addrconf_dad_stop(ifp, 1);
+ spin_lock_bh(&ifp->state_lock);
+ /* transition from _POSTDAD to _ERRDAD */
+ ifp->state = INET6_IFADDR_STATE_ERRDAD;
+ spin_unlock_bh(&ifp->state_lock);
+
+ addrconf_mod_dad_work(ifp, 0);
}
/* Join to solicited addr multicast group. */
@@ -1680,6 +1690,8 @@
{
struct in6_addr maddr;
+ ASSERT_RTNL();
+
if (dev->flags&(IFF_LOOPBACK|IFF_NOARP))
return;
@@ -1691,6 +1703,8 @@
{
struct in6_addr maddr;
+ ASSERT_RTNL();
+
if (idev->dev->flags&(IFF_LOOPBACK|IFF_NOARP))
return;
@@ -1701,6 +1715,9 @@
static void addrconf_join_anycast(struct inet6_ifaddr *ifp)
{
struct in6_addr addr;
+
+ ASSERT_RTNL();
+
if (ifp->prefix_len >= 127) /* RFC 6164 */
return;
ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len);
@@ -1712,6 +1729,9 @@
static void addrconf_leave_anycast(struct inet6_ifaddr *ifp)
{
struct in6_addr addr;
+
+ ASSERT_RTNL();
+
if (ifp->prefix_len >= 127) /* RFC 6164 */
return;
ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len);
@@ -2271,11 +2291,13 @@
return;
}
- ifp->flags |= IFA_F_MANAGETEMPADDR;
update_lft = 0;
create = 1;
+ spin_lock_bh(&ifp->lock);
+ ifp->flags |= IFA_F_MANAGETEMPADDR;
ifp->cstamp = jiffies;
ifp->tokenized = tokenized;
+ spin_unlock_bh(&ifp->lock);
addrconf_dad_start(ifp);
}
@@ -2326,7 +2348,7 @@
create, now);
in6_ifa_put(ifp);
- addrconf_verify(0);
+ addrconf_verify();
}
}
inet6_prefix_notify(RTM_NEWPREFIX, in6_dev, pinfo);
@@ -2475,7 +2497,7 @@
manage_tempaddrs(idev, ifp, valid_lft, prefered_lft,
true, jiffies);
in6_ifa_put(ifp);
- addrconf_verify(0);
+ addrconf_verify_rtnl();
return 0;
}
@@ -3011,7 +3033,7 @@
hlist_for_each_entry_rcu(ifa, h, addr_lst) {
if (ifa->idev == idev) {
hlist_del_init_rcu(&ifa->addr_lst);
- addrconf_del_dad_timer(ifa);
+ addrconf_del_dad_work(ifa);
goto restart;
}
}
@@ -3049,7 +3071,7 @@
while (!list_empty(&idev->addr_list)) {
ifa = list_first_entry(&idev->addr_list,
struct inet6_ifaddr, if_list);
- addrconf_del_dad_timer(ifa);
+ addrconf_del_dad_work(ifa);
list_del(&ifa->if_list);
@@ -3148,10 +3170,10 @@
rand_num = prandom_u32() % (idev->cnf.rtr_solicit_delay ? : 1);
ifp->dad_probes = idev->cnf.dad_transmits;
- addrconf_mod_dad_timer(ifp, rand_num);
+ addrconf_mod_dad_work(ifp, rand_num);
}
-static void addrconf_dad_start(struct inet6_ifaddr *ifp)
+static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
{
struct inet6_dev *idev = ifp->idev;
struct net_device *dev = idev->dev;
@@ -3203,25 +3225,68 @@
read_unlock_bh(&idev->lock);
}
-static void addrconf_dad_timer(unsigned long data)
+static void addrconf_dad_start(struct inet6_ifaddr *ifp)
{
- struct inet6_ifaddr *ifp = (struct inet6_ifaddr *) data;
+ bool begin_dad = false;
+
+ spin_lock_bh(&ifp->state_lock);
+ if (ifp->state != INET6_IFADDR_STATE_DEAD) {
+ ifp->state = INET6_IFADDR_STATE_PREDAD;
+ begin_dad = true;
+ }
+ spin_unlock_bh(&ifp->state_lock);
+
+ if (begin_dad)
+ addrconf_mod_dad_work(ifp, 0);
+}
+
+static void addrconf_dad_work(struct work_struct *w)
+{
+ struct inet6_ifaddr *ifp = container_of(to_delayed_work(w),
+ struct inet6_ifaddr,
+ dad_work);
struct inet6_dev *idev = ifp->idev;
struct in6_addr mcaddr;
+ enum {
+ DAD_PROCESS,
+ DAD_BEGIN,
+ DAD_ABORT,
+ } action = DAD_PROCESS;
+
+ rtnl_lock();
+
+ spin_lock_bh(&ifp->state_lock);
+ if (ifp->state == INET6_IFADDR_STATE_PREDAD) {
+ action = DAD_BEGIN;
+ ifp->state = INET6_IFADDR_STATE_DAD;
+ } else if (ifp->state == INET6_IFADDR_STATE_ERRDAD) {
+ action = DAD_ABORT;
+ ifp->state = INET6_IFADDR_STATE_POSTDAD;
+ }
+ spin_unlock_bh(&ifp->state_lock);
+
+ if (action == DAD_BEGIN) {
+ addrconf_dad_begin(ifp);
+ goto out;
+ } else if (action == DAD_ABORT) {
+ addrconf_dad_stop(ifp, 1);
+ goto out;
+ }
+
if (!ifp->dad_probes && addrconf_dad_end(ifp))
goto out;
- write_lock(&idev->lock);
+ write_lock_bh(&idev->lock);
if (idev->dead || !(idev->if_flags & IF_READY)) {
- write_unlock(&idev->lock);
+ write_unlock_bh(&idev->lock);
goto out;
}
spin_lock(&ifp->lock);
if (ifp->state == INET6_IFADDR_STATE_DEAD) {
spin_unlock(&ifp->lock);
- write_unlock(&idev->lock);
+ write_unlock_bh(&idev->lock);
goto out;
}
@@ -3232,7 +3297,7 @@
ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED);
spin_unlock(&ifp->lock);
- write_unlock(&idev->lock);
+ write_unlock_bh(&idev->lock);
addrconf_dad_completed(ifp);
@@ -3240,16 +3305,17 @@
}
ifp->dad_probes--;
- addrconf_mod_dad_timer(ifp,
- NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME));
+ addrconf_mod_dad_work(ifp,
+ NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME));
spin_unlock(&ifp->lock);
- write_unlock(&idev->lock);
+ write_unlock_bh(&idev->lock);
/* send a neighbour solicitation for our addr */
addrconf_addr_solict_mult(&ifp->addr, &mcaddr);
ndisc_send_ns(ifp->idev->dev, NULL, &ifp->addr, &mcaddr, &in6addr_any);
out:
in6_ifa_put(ifp);
+ rtnl_unlock();
}
/* ifp->idev must be at least read locked */
@@ -3276,7 +3342,7 @@
struct in6_addr lladdr;
bool send_rs, send_mld;
- addrconf_del_dad_timer(ifp);
+ addrconf_del_dad_work(ifp);
/*
* Configure the address for reception. Now it is valid.
@@ -3517,23 +3583,23 @@
* Periodic address status verification
*/
-static void addrconf_verify(unsigned long foo)
+static void addrconf_verify_rtnl(void)
{
unsigned long now, next, next_sec, next_sched;
struct inet6_ifaddr *ifp;
int i;
+ ASSERT_RTNL();
+
rcu_read_lock_bh();
- spin_lock(&addrconf_verify_lock);
now = jiffies;
next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY);
- del_timer(&addr_chk_timer);
+ cancel_delayed_work(&addr_chk_work);
for (i = 0; i < IN6_ADDR_HSIZE; i++) {
restart:
- hlist_for_each_entry_rcu_bh(ifp,
- &inet6_addr_lst[i], addr_lst) {
+ hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[i], addr_lst) {
unsigned long age;
/* When setting preferred_lft to a value not zero or
@@ -3628,13 +3694,22 @@
ADBG(KERN_DEBUG "now = %lu, schedule = %lu, rounded schedule = %lu => %lu\n",
now, next, next_sec, next_sched);
-
- addr_chk_timer.expires = next_sched;
- add_timer(&addr_chk_timer);
- spin_unlock(&addrconf_verify_lock);
+ mod_delayed_work(addrconf_wq, &addr_chk_work, next_sched - now);
rcu_read_unlock_bh();
}
+static void addrconf_verify_work(struct work_struct *w)
+{
+ rtnl_lock();
+ addrconf_verify_rtnl();
+ rtnl_unlock();
+}
+
+static void addrconf_verify(void)
+{
+ mod_delayed_work(addrconf_wq, &addr_chk_work, 0);
+}
+
static struct in6_addr *extract_addr(struct nlattr *addr, struct nlattr *local,
struct in6_addr **peer_pfx)
{
@@ -3691,6 +3766,8 @@
bool was_managetempaddr;
bool had_prefixroute;
+ ASSERT_RTNL();
+
if (!valid_lft || (prefered_lft > valid_lft))
return -EINVAL;
@@ -3756,7 +3833,7 @@
!was_managetempaddr, jiffies);
}
- addrconf_verify(0);
+ addrconf_verify_rtnl();
return 0;
}
@@ -4386,6 +4463,8 @@
bool update_rs = false;
struct in6_addr ll_addr;
+ ASSERT_RTNL();
+
if (token == NULL)
return -EINVAL;
if (ipv6_addr_any(token))
@@ -4434,7 +4513,7 @@
}
write_unlock_bh(&idev->lock);
- addrconf_verify(0);
+ addrconf_verify_rtnl();
return 0;
}
@@ -4636,6 +4715,9 @@
{
struct net *net = dev_net(ifp->idev->dev);
+ if (event)
+ ASSERT_RTNL();
+
inet6_ifa_notify(event ? : RTM_NEWADDR, ifp);
switch (event) {
@@ -5244,6 +5326,12 @@
if (err < 0)
goto out_addrlabel;
+ addrconf_wq = create_workqueue("ipv6_addrconf");
+ if (!addrconf_wq) {
+ err = -ENOMEM;
+ goto out_nowq;
+ }
+
/* The addrconf netdev notifier requires that loopback_dev
* has it's ipv6 private information allocated and setup
* before it can bring up and give link-local addresses
@@ -5274,7 +5362,7 @@
register_netdevice_notifier(&ipv6_dev_notf);
- addrconf_verify(0);
+ addrconf_verify();
rtnl_af_register(&inet6_ops);
@@ -5302,6 +5390,8 @@
rtnl_af_unregister(&inet6_ops);
unregister_netdevice_notifier(&ipv6_dev_notf);
errlo:
+ destroy_workqueue(addrconf_wq);
+out_nowq:
unregister_pernet_subsys(&addrconf_ops);
out_addrlabel:
ipv6_addr_label_cleanup();
@@ -5337,7 +5427,8 @@
for (i = 0; i < IN6_ADDR_HSIZE; i++)
WARN_ON(!hlist_empty(&inet6_addr_lst[i]));
spin_unlock_bh(&addrconf_hash_lock);
-
- del_timer(&addr_chk_timer);
+ cancel_delayed_work(&addr_chk_work);
rtnl_unlock();
+
+ destroy_workqueue(addrconf_wq);
}
diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c
index f072fe8..108120f 100644
--- a/net/netfilter/nfnetlink_queue_core.c
+++ b/net/netfilter/nfnetlink_queue_core.c
@@ -354,13 +354,16 @@
skb = nfnetlink_alloc_skb(net, size, queue->peer_portid,
GFP_ATOMIC);
- if (!skb)
+ if (!skb) {
+ skb_tx_error(entskb);
return NULL;
+ }
nlh = nlmsg_put(skb, 0, 0,
NFNL_SUBSYS_QUEUE << 8 | NFQNL_MSG_PACKET,
sizeof(struct nfgenmsg), 0);
if (!nlh) {
+ skb_tx_error(entskb);
kfree_skb(skb);
return NULL;
}
@@ -488,13 +491,15 @@
nla->nla_type = NFQA_PAYLOAD;
nla->nla_len = nla_attr_size(data_len);
- skb_zerocopy(skb, entskb, data_len, hlen);
+ if (skb_zerocopy(skb, entskb, data_len, hlen))
+ goto nla_put_failure;
}
nlh->nlmsg_len = skb->len;
return skb;
nla_put_failure:
+ skb_tx_error(entskb);
kfree_skb(skb);
net_err_ratelimited("nf_queue: error creating packet message\n");
return NULL;
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 8601b32..270b77d 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -464,7 +464,9 @@
}
nla->nla_len = nla_attr_size(skb->len);
- skb_zerocopy(user_skb, skb, skb->len, hlen);
+ err = skb_zerocopy(user_skb, skb, skb->len, hlen);
+ if (err)
+ goto out;
/* Pad OVS_PACKET_ATTR_PACKET if linear copy was performed */
if (!(dp->user_features & OVS_DP_F_UNALIGNED)) {
@@ -478,6 +480,8 @@
err = genlmsg_unicast(ovs_dp_get_net(dp), user_skb, upcall_info->portid);
out:
+ if (err)
+ skb_tx_error(skb);
kfree_skb(nskb);
return err;
}
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index dda451f4..2998989 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -103,30 +103,24 @@
void ovs_flow_stats_get(struct sw_flow *flow, struct ovs_flow_stats *ovs_stats,
unsigned long *used, __be16 *tcp_flags)
{
- int cpu, cur_cpu;
+ int cpu;
*used = 0;
*tcp_flags = 0;
memset(ovs_stats, 0, sizeof(*ovs_stats));
+ local_bh_disable();
if (!flow->stats.is_percpu) {
stats_read(flow->stats.stat, ovs_stats, used, tcp_flags);
} else {
- cur_cpu = get_cpu();
for_each_possible_cpu(cpu) {
struct flow_stats *stats;
- if (cpu == cur_cpu)
- local_bh_disable();
-
stats = per_cpu_ptr(flow->stats.cpu_stats, cpu);
stats_read(stats, ovs_stats, used, tcp_flags);
-
- if (cpu == cur_cpu)
- local_bh_enable();
}
- put_cpu();
}
+ local_bh_enable();
}
static void stats_reset(struct flow_stats *stats)
@@ -141,25 +135,17 @@
void ovs_flow_stats_clear(struct sw_flow *flow)
{
- int cpu, cur_cpu;
+ int cpu;
+ local_bh_disable();
if (!flow->stats.is_percpu) {
stats_reset(flow->stats.stat);
} else {
- cur_cpu = get_cpu();
-
for_each_possible_cpu(cpu) {
-
- if (cpu == cur_cpu)
- local_bh_disable();
-
stats_reset(per_cpu_ptr(flow->stats.cpu_stats, cpu));
-
- if (cpu == cur_cpu)
- local_bh_enable();
}
- put_cpu();
}
+ local_bh_enable();
}
static int check_header(struct sk_buff *skb, int len)
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index ce6ec6c..94404f1 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1787,8 +1787,11 @@
goto out;
err = mutex_lock_interruptible(&u->readlock);
- if (err) {
- err = sock_intr_errno(sock_rcvtimeo(sk, noblock));
+ if (unlikely(err)) {
+ /* recvmsg() in non blocking mode is supposed to return -EAGAIN
+ * sk_rcvtimeo is not honored by mutex_lock_interruptible()
+ */
+ err = noblock ? -EAGAIN : -ERESTARTSYS;
goto out;
}
@@ -1913,6 +1916,7 @@
struct unix_sock *u = unix_sk(sk);
DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, msg->msg_name);
int copied = 0;
+ int noblock = flags & MSG_DONTWAIT;
int check_creds = 0;
int target;
int err = 0;
@@ -1928,7 +1932,7 @@
goto out;
target = sock_rcvlowat(sk, flags&MSG_WAITALL, size);
- timeo = sock_rcvtimeo(sk, flags&MSG_DONTWAIT);
+ timeo = sock_rcvtimeo(sk, noblock);
/* Lock the socket to prevent queue disordering
* while sleeps in memcpy_tomsg
@@ -1940,8 +1944,11 @@
}
err = mutex_lock_interruptible(&u->readlock);
- if (err) {
- err = sock_intr_errno(timeo);
+ if (unlikely(err)) {
+ /* recvmsg() in non blocking mode is supposed to return -EAGAIN
+ * sk_rcvtimeo is not honored by mutex_lock_interruptible()
+ */
+ err = noblock ? -EAGAIN : -ERESTARTSYS;
goto out;
}
