From 212f263930ebc1020ad12dd0fa52a058592709e8 Mon Sep 17 00:00:00 2001
From: Jon Paul Maloy <jon.maloy@ericsson.com>
Date: Wed, 28 Oct 2015 13:09:53 -0400
Subject: [PATCH 01/17] tipc: linearize arriving NAME_DISTR and LINK_PROTO
buffers
[ Upstream commit 5cbb28a4bf65c7e4daa6c25b651fed8eb888c620 ]
Testing of the new UDP bearer has revealed that reception of
NAME_DISTRIBUTOR, LINK_PROTOCOL/RESET and LINK_PROTOCOL/ACTIVATE
message buffers is not prepared for the case that those may be
non-linear.
We now linearize all such buffers before they are delivered up to the
generic reception layer.
In order for the commit to apply cleanly to 'net' and 'stable', we do
the change in the function tipc_udp_recv() for now. Later, we will post
a commit to 'net-next' moving the linearization to generic code, in
tipc_named_rcv() and tipc_link_proto_rcv().
Fixes: commit d0f91938bede ("tipc: add ip/udp media type")
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/tipc/udp_media.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index 6e648d9..cd7c5f1 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -48,6 +48,7 @@
#include <linux/tipc_netlink.h>
#include "core.h"
#include "bearer.h"
+#include "msg.h"
/* IANA assigned UDP port */
#define UDP_PORT_DEFAULT 6118
@@ -222,6 +223,10 @@ static int tipc_udp_recv(struct sock *sk, struct sk_buff *skb)
{
struct udp_bearer *ub;
struct tipc_bearer *b;
+ int usr = msg_user(buf_msg(skb));
+
+ if ((usr == LINK_PROTOCOL) || (usr == NAME_DISTRIBUTOR))
+ skb_linearize(skb);
ub = rcu_dereference_sk_user_data(sk);
if (!ub) {
--
2.4.1
From a04db8659b41413b9ef6751b1487c96f4fe5c8c1 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 29 Oct 2015 18:11:35 -0700
Subject: [PATCH 02/17] net: bcmgenet: Software reset EPHY after power on
[ Upstream commit 5dbebbb44a6ad94aab2cd1a46f7676f255403f64 ]
The EPHY on GENET v1->v3 is extremely finicky, and will show occasional
failures based on the timing and reset sequence, ranging from duplicate
packets, to extremely high latencies.
Perform an additional software reset, and re-configuration to make sure it is
in a consistent and working state.
Fixes: 6ac3ce8295e6 ("net: bcmgenet: Remove excessive PHY reset")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/broadcom/genet/bcmgenet.c | 4 +++-
drivers/net/ethernet/broadcom/genet/bcmgenet.h | 1 +
drivers/net/ethernet/broadcom/genet/bcmmii.c | 18 ++++++++++++++++++
3 files changed, 22 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 1805541..5e3cd76 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -907,8 +907,10 @@ static void bcmgenet_power_up(struct bcmgenet_priv *priv,
}
bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
- if (mode == GENET_POWER_PASSIVE)
+ if (mode == GENET_POWER_PASSIVE) {
bcmgenet_phy_power_set(priv->dev, true);
+ bcmgenet_mii_reset(priv->dev);
+ }
}
/* ioctl handle special commands that are not present in ethtool. */
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 7299d10..c739f7e 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -674,6 +674,7 @@ int bcmgenet_mii_init(struct net_device *dev);
int bcmgenet_mii_config(struct net_device *dev);
int bcmgenet_mii_probe(struct net_device *dev);
void bcmgenet_mii_exit(struct net_device *dev);
+void bcmgenet_mii_reset(struct net_device *dev);
void bcmgenet_phy_power_set(struct net_device *dev, bool enable);
void bcmgenet_mii_setup(struct net_device *dev);
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index c8affad..8bdfe53 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -163,6 +163,7 @@ void bcmgenet_mii_setup(struct net_device *dev)
phy_print_status(phydev);
}
+
static int bcmgenet_fixed_phy_link_update(struct net_device *dev,
struct fixed_phy_status *status)
{
@@ -172,6 +173,22 @@ static int bcmgenet_fixed_phy_link_update(struct net_device *dev,
return 0;
}
+/* Perform a voluntary PHY software reset, since the EPHY is very finicky about
+ * not doing it and will start corrupting packets
+ */
+void bcmgenet_mii_reset(struct net_device *dev)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+
+ if (GENET_IS_V4(priv))
+ return;
+
+ if (priv->phydev) {
+ phy_init_hw(priv->phydev);
+ phy_start_aneg(priv->phydev);
+ }
+}
+
void bcmgenet_phy_power_set(struct net_device *dev, bool enable)
{
struct bcmgenet_priv *priv = netdev_priv(dev);
@@ -214,6 +231,7 @@ static void bcmgenet_internal_phy_setup(struct net_device *dev)
reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
reg |= EXT_PWR_DN_EN_LD;
bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
+ bcmgenet_mii_reset(dev);
}
static void bcmgenet_moca_phy_setup(struct bcmgenet_priv *priv)
--
2.4.1
From 667672b33d13d71b92244bbd410f0a4122afa428 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Fri, 30 Oct 2015 10:23:33 +0200
Subject: [PATCH 03/17] ipv4: fix to not remove local route on link down
[ Upstream commit 4f823defdd5b106a5e89745ee8b163c71855de1e ]
When fib_netdev_event calls fib_disable_ip on NETDEV_DOWN event
we should not delete the local routes if the local address
is still present. The confusion comes from the fact that both
fib_netdev_event and fib_inetaddr_event use the NETDEV_DOWN
constant. Fix it by returning back the variable 'force'.
Steps to reproduce:
modprobe dummy
ifconfig dummy0 192.168.168.1 up
ifconfig dummy0 down
ip route list table local | grep dummy | grep host
local 192.168.168.1 dev dummy0 proto kernel scope host src 192.168.168.1
Fixes: 8a3d03166f19 ("net: track link-status of ipv4 nexthops")
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/ip_fib.h | 2 +-
net/ipv4/fib_frontend.c | 13 +++++++------
net/ipv4/fib_semantics.c | 11 ++++++++---
3 files changed, 16 insertions(+), 10 deletions(-)
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 727d6e9..965fa5b 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -317,7 +317,7 @@ void fib_flush_external(struct net *net);
/* Exported by fib_semantics.c */
int ip_fib_check_default(__be32 gw, struct net_device *dev);
-int fib_sync_down_dev(struct net_device *dev, unsigned long event);
+int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force);
int fib_sync_down_addr(struct net *net, __be32 local);
int fib_sync_up(struct net_device *dev, unsigned int nh_flags);
void fib_select_multipath(struct fib_result *res);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 690bcbc..457b2cd 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1110,9 +1110,10 @@ static void nl_fib_lookup_exit(struct net *net)
net->ipv4.fibnl = NULL;
}
-static void fib_disable_ip(struct net_device *dev, unsigned long event)
+static void fib_disable_ip(struct net_device *dev, unsigned long event,
+ bool force)
{
- if (fib_sync_down_dev(dev, event))
+ if (fib_sync_down_dev(dev, event, force))
fib_flush(dev_net(dev));
rt_cache_flush(dev_net(dev));
arp_ifdown(dev);
@@ -1140,7 +1141,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event,
/* Last address was deleted from this interface.
* Disable IP.
*/
- fib_disable_ip(dev, event);
+ fib_disable_ip(dev, event, true);
} else {
rt_cache_flush(dev_net(dev));
}
@@ -1157,7 +1158,7 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo
unsigned int flags;
if (event == NETDEV_UNREGISTER) {
- fib_disable_ip(dev, event);
+ fib_disable_ip(dev, event, true);
rt_flush_dev(dev);
return NOTIFY_DONE;
}
@@ -1178,14 +1179,14 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo
rt_cache_flush(net);
break;
case NETDEV_DOWN:
- fib_disable_ip(dev, event);
+ fib_disable_ip(dev, event, false);
break;
case NETDEV_CHANGE:
flags = dev_get_flags(dev);
if (flags & (IFF_RUNNING | IFF_LOWER_UP))
fib_sync_up(dev, RTNH_F_LINKDOWN);
else
- fib_sync_down_dev(dev, event);
+ fib_sync_down_dev(dev, event, false);
/* fall through */
case NETDEV_CHANGEMTU:
rt_cache_flush(net);
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 064bd3c..2aa5b5e 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1281,7 +1281,13 @@ int fib_sync_down_addr(struct net *net, __be32 local)
return ret;
}
-int fib_sync_down_dev(struct net_device *dev, unsigned long event)
+/* Event force Flags Description
+ * NETDEV_CHANGE 0 LINKDOWN Carrier OFF, not for scope host
+ * NETDEV_DOWN 0 LINKDOWN|DEAD Link down, not for scope host
+ * NETDEV_DOWN 1 LINKDOWN|DEAD Last address removed
+ * NETDEV_UNREGISTER 1 LINKDOWN|DEAD Device removed
+ */
+int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force)
{
int ret = 0;
int scope = RT_SCOPE_NOWHERE;
@@ -1290,8 +1296,7 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event)
struct hlist_head *head = &fib_info_devhash[hash];
struct fib_nh *nh;
- if (event == NETDEV_UNREGISTER ||
- event == NETDEV_DOWN)
+ if (force)
scope = -1;
hlist_for_each_entry(nh, head, nh_hash) {
--
2.4.1
From 79c1b779621a34487aaf8a7fa1e499c04fff5c79 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Fri, 30 Oct 2015 10:23:34 +0200
Subject: [PATCH 04/17] ipv4: update RTNH_F_LINKDOWN flag on UP event
[ Upstream commit c9b3292eeb52c6834e972eb5b8fe38914771ed12 ]
When nexthop is part of multipath route we should clear the
LINKDOWN flag when link goes UP or when first address is added.
This is needed because we always set LINKDOWN flag when DEAD flag
was set but now on UP the nexthop is not dead anymore. Examples when
LINKDOWN bit can be forgotten when no NETDEV_CHANGE is delivered:
- link goes down (LINKDOWN is set), then link goes UP and device
shows carrier OK but LINKDOWN remains set
- last address is deleted (LINKDOWN is set), then address is
added and device shows carrier OK but LINKDOWN remains set
Steps to reproduce:
modprobe dummy
ifconfig dummy0 192.168.168.1 up
here add a multipath route where one nexthop is for dummy0:
ip route add 1.2.3.4 nexthop dummy0 nexthop SOME_OTHER_DEVICE
ifconfig dummy0 down
ifconfig dummy0 up
now ip route shows nexthop that is not dead. Now set the sysctl var:
echo 1 > /proc/sys/net/ipv4/conf/dummy0/ignore_routes_with_linkdown
now ip route will show a dead nexthop because the forgotten
RTNH_F_LINKDOWN is propagated as RTNH_F_DEAD.
Fixes: 8a3d03166f19 ("net: track link-status of ipv4 nexthops")
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv4/fib_semantics.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 2aa5b5e..e966f85 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1445,6 +1445,13 @@ int fib_sync_up(struct net_device *dev, unsigned int nh_flags)
if (!(dev->flags & IFF_UP))
return 0;
+ if (nh_flags & RTNH_F_DEAD) {
+ unsigned int flags = dev_get_flags(dev);
+
+ if (flags & (IFF_RUNNING | IFF_LOWER_UP))
+ nh_flags |= RTNH_F_LINKDOWN;
+ }
+
prev_fi = NULL;
hash = fib_devindex_hashfn(dev->ifindex);
head = &fib_info_devhash[hash];
--
2.4.1
From 22c6a0b8732f4b426f64f18ca9097288cd996a64 Mon Sep 17 00:00:00 2001
From: Phil Reid <preid@electromag.com.au>
Date: Fri, 30 Oct 2015 16:43:55 +0800
Subject: [PATCH 05/17] stmmac: Correctly report PTP capabilities.
[ Upstream commit e6dbe1eb2db0d7a14991c06278dd3030c45fb825 ]
priv->hwts_*_en indicate if timestamping is enabled/disabled at run
time. But priv->dma_cap.time_stamp and priv->dma_cap.atime_stamp
indicates HW is support for PTPv1/PTPv2.
Signed-off-by: Phil Reid <preid@electromag.com.au>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 771cda2..2e51b81 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -721,10 +721,13 @@ static int stmmac_get_ts_info(struct net_device *dev,
{
struct stmmac_priv *priv = netdev_priv(dev);
- if ((priv->hwts_tx_en) && (priv->hwts_rx_en)) {
+ if ((priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp)) {
- info->so_timestamping = SOF_TIMESTAMPING_TX_HARDWARE |
+ info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
+ SOF_TIMESTAMPING_TX_HARDWARE |
+ SOF_TIMESTAMPING_RX_SOFTWARE |
SOF_TIMESTAMPING_RX_HARDWARE |
+ SOF_TIMESTAMPING_SOFTWARE |
SOF_TIMESTAMPING_RAW_HARDWARE;
if (priv->ptp_clock)
--
2.4.1
From 27cc4a97a3cdcb3b3daa126667d4e86c9b014909 Mon Sep 17 00:00:00 2001
From: Ani Sinha <ani@arista.com>
Date: Fri, 30 Oct 2015 16:54:31 -0700
Subject: [PATCH 06/17] ipmr: fix possible race resulting from improper usage
of IP_INC_STATS_BH() in preemptible context.
[ Upstream commit 44f49dd8b5a606870a1f21101522a0f9c4414784 ]
Fixes the following kernel BUG :
BUG: using __this_cpu_add() in preemptible [00000000] code: bash/2758
caller is __this_cpu_preempt_check+0x13/0x15
CPU: 0 PID: 2758 Comm: bash Tainted: P O 3.18.19 #2
ffffffff8170eaca ffff880110d1b788 ffffffff81482b2a 0000000000000000
0000000000000000 ffff880110d1b7b8 ffffffff812010ae ffff880007cab800
ffff88001a060800 ffff88013a899108 ffff880108b84240 ffff880110d1b7c8
Call Trace:
[<ffffffff81482b2a>] dump_stack+0x52/0x80
[<ffffffff812010ae>] check_preemption_disabled+0xce/0xe1
[<ffffffff812010d4>] __this_cpu_preempt_check+0x13/0x15
[<ffffffff81419d60>] ipmr_queue_xmit+0x647/0x70c
[<ffffffff8141a154>] ip_mr_forward+0x32f/0x34e
[<ffffffff8141af76>] ip_mroute_setsockopt+0xe03/0x108c
[<ffffffff810553fc>] ? get_parent_ip+0x11/0x42
[<ffffffff810e6974>] ? pollwake+0x4d/0x51
[<ffffffff81058ac0>] ? default_wake_function+0x0/0xf
[<ffffffff810553fc>] ? get_parent_ip+0x11/0x42
[<ffffffff810613d9>] ? __wake_up_common+0x45/0x77
[<ffffffff81486ea9>] ? _raw_spin_unlock_irqrestore+0x1d/0x32
[<ffffffff810618bc>] ? __wake_up_sync_key+0x4a/0x53
[<ffffffff8139a519>] ? sock_def_readable+0x71/0x75
[<ffffffff813dd226>] do_ip_setsockopt+0x9d/0xb55
[<ffffffff81429818>] ? unix_seqpacket_sendmsg+0x3f/0x41
[<ffffffff813963fe>] ? sock_sendmsg+0x6d/0x86
[<ffffffff813959d4>] ? sockfd_lookup_light+0x12/0x5d
[<ffffffff8139650a>] ? SyS_sendto+0xf3/0x11b
[<ffffffff810d5738>] ? new_sync_read+0x82/0xaa
[<ffffffff813ddd19>] compat_ip_setsockopt+0x3b/0x99
[<ffffffff813fb24a>] compat_raw_setsockopt+0x11/0x32
[<ffffffff81399052>] compat_sock_common_setsockopt+0x18/0x1f
[<ffffffff813c4d05>] compat_SyS_setsockopt+0x1a9/0x1cf
[<ffffffff813c4149>] compat_SyS_socketcall+0x180/0x1e3
[<ffffffff81488ea1>] cstar_dispatch+0x7/0x1e
Signed-off-by: Ani Sinha <ani@arista.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv4/ipmr.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 866ee89..8e8203d 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1682,8 +1682,8 @@ static inline int ipmr_forward_finish(struct sock *sk, struct sk_buff *skb)
{
struct ip_options *opt = &(IPCB(skb)->opt);
- IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS);
- IP_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len);
+ IP_INC_STATS(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS);
+ IP_ADD_STATS(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len);
if (unlikely(opt->optlen))
ip_forward_options(skb);
@@ -1745,7 +1745,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
* to blackhole.
*/
- IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
+ IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
ip_rt_put(rt);
goto out_free;
}
--
2.4.1
From 217a7af11532c12fc19168231216160cbf92adc8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Sun, 1 Nov 2015 01:34:50 +0100
Subject: [PATCH 07/17] qmi_wwan: fix entry for HP lt4112 LTE/HSPA+ Gobi 4G
Module
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
[ Upstream commit 70910791731b5956171e1bfcad707766b8e18fee ]
The lt4112 is a HP branded Huawei me906e modem. Like other Huawei
modems, it does not have a fixed interface to function mapping.
Instead it uses a Huawei specific scheme: functions are mapped by
subclass and protocol.
However, the HP vendor ID is used for modems from many different
manufacturers using different schemes, so we cannot apply a generic
vendor rule like we do for the Huawei vendor ID.
Replace the previous lt4112 entry pointing to an arbitrary interface
number with a device specific subclass + protocol match.
Reported-and-tested-by: Muri Nicanor <muri+libqmi@immerda.ch>
Tested-by: Martin Hauke <mardnh@gmx.de>
Fixes: bb2bdeb83fb1 ("qmi_wwan: Add support for HP lt4112 LTE/HSPA+ Gobi 4G Modem")
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/usb/qmi_wwan.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 2a7c1be..1ba1fdc 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -539,6 +539,10 @@ static const struct usb_device_id products[] = {
USB_CDC_PROTO_NONE),
.driver_info = (unsigned long)&qmi_wwan_info,
},
+ { /* HP lt4112 LTE/HSPA+ Gobi 4G Module (Huawei me906e) */
+ USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x581d, USB_CLASS_VENDOR_SPEC, 1, 7),
+ .driver_info = (unsigned long)&qmi_wwan_info,
+ },
/* 3. Combined interface devices matching on interface number */
{QMI_FIXED_INTF(0x0408, 0xea42, 4)}, /* Yota / Megafon M100-1 */
@@ -791,7 +795,6 @@ static const struct usb_device_id products[] = {
{QMI_FIXED_INTF(0x413c, 0x81a9, 8)}, /* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */
{QMI_FIXED_INTF(0x413c, 0x81b1, 8)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card */
{QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)}, /* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */
- {QMI_FIXED_INTF(0x03f0, 0x581d, 4)}, /* HP lt4112 LTE/HSPA+ Gobi 4G Module (Huawei me906e) */
/* 4. Gobi 1000 devices */
{QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */
--
2.4.1
From 8d81dd753b8725645da63cf78c8d280c27e414a3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 2 Nov 2015 17:08:19 -0800
Subject: [PATCH 08/17] sit: fix sit0 percpu double allocations
[ Upstream commit 4ece9009774596ee3df0acba65a324b7ea79387c ]
sit0 device allocates its percpu storage twice :
- One time in ipip6_tunnel_init()
- One time in ipip6_fb_tunnel_init()
Thus we leak 48 bytes per possible cpu per network namespace dismantle.
ipip6_fb_tunnel_init() can be much simpler and does not
return an error, and should be called after register_netdev()
Note that ipip6_tunnel_clone_6rd() also needs to be called
after register_netdev() (calling ipip6_tunnel_init())
Fixes: ebe084aafb7e ("sit: Use ipip6_tunnel_init as the ndo_init function.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv6/sit.c | 26 ++++----------------------
1 file changed, 4 insertions(+), 22 deletions(-)
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 94428fd..dcccae8 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1394,34 +1394,20 @@ static int ipip6_tunnel_init(struct net_device *dev)
return 0;
}
-static int __net_init ipip6_fb_tunnel_init(struct net_device *dev)
+static void __net_init ipip6_fb_tunnel_init(struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct iphdr *iph = &tunnel->parms.iph;
struct net *net = dev_net(dev);
struct sit_net *sitn = net_generic(net, sit_net_id);
- tunnel->dev = dev;
- tunnel->net = dev_net(dev);
-
iph->version = 4;
iph->protocol = IPPROTO_IPV6;
iph->ihl = 5;
iph->ttl = 64;
- dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
- if (!dev->tstats)
- return -ENOMEM;
-
- tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst);
- if (!tunnel->dst_cache) {
- free_percpu(dev->tstats);
- return -ENOMEM;
- }
-
dev_hold(dev);
rcu_assign_pointer(sitn->tunnels_wc[0], tunnel);
- return 0;
}
static int ipip6_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -1831,23 +1817,19 @@ static int __net_init sit_init_net(struct net *net)
*/
sitn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL;
- err = ipip6_fb_tunnel_init(sitn->fb_tunnel_dev);
- if (err)
- goto err_dev_free;
-
- ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn);
err = register_netdev(sitn->fb_tunnel_dev);
if (err)
goto err_reg_dev;
+ ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn);
+ ipip6_fb_tunnel_init(sitn->fb_tunnel_dev);
+
t = netdev_priv(sitn->fb_tunnel_dev);
strcpy(t->parms.name, sitn->fb_tunnel_dev->name);
return 0;
err_reg_dev:
- dev_put(sitn->fb_tunnel_dev);
-err_dev_free:
ipip6_dev_free(sitn->fb_tunnel_dev);
err_alloc_dev:
return err;
--
2.4.1
From 03ebc93ed50c5d98c9f86b5831f537a408935d83 Mon Sep 17 00:00:00 2001
From: Martin Habets <mhabets@solarflare.com>
Date: Mon, 2 Nov 2015 12:51:31 +0000
Subject: [PATCH 09/17] sfc: push partner queue for skb->xmit_more
[ Upstream commit b2663a4f30e85ec606b806f5135413e6d5c78d1e ]
When the IP stack passes SKBs the sfc driver puts them in 2 different TX
queues (called partners), one for checksummed and one for not checksummed.
If the SKB has xmit_more set the driver will delay pushing the work to the
NIC.
When later it does decide to push the buffers this patch ensures it also
pushes the partner queue, if that also has any delayed work. Before this
fix the work in the partner queue would be left for a long time and cause
a netdev watchdog.
Fixes: 70b33fb ("sfc: add support for skb->xmit_more")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Martin Habets <mhabets@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/sfc/ef10.c | 4 +++-
drivers/net/ethernet/sfc/farch.c | 4 +++-
drivers/net/ethernet/sfc/net_driver.h | 2 ++
drivers/net/ethernet/sfc/tx.c | 30 ++++++++++++++++++++++++++++--
4 files changed, 36 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index ff649eb..286cc6b 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -1849,7 +1849,9 @@ static void efx_ef10_tx_write(struct efx_tx_queue *tx_queue)
unsigned int write_ptr;
efx_qword_t *txd;
- BUG_ON(tx_queue->write_count == tx_queue->insert_count);
+ tx_queue->xmit_more_available = false;
+ if (unlikely(tx_queue->write_count == tx_queue->insert_count))
+ return;
do {
write_ptr = tx_queue->write_count & tx_queue->ptr_mask;
diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c
index f08266f..5a1c5a8 100644
--- a/drivers/net/ethernet/sfc/farch.c
+++ b/drivers/net/ethernet/sfc/farch.c
@@ -321,7 +321,9 @@ void efx_farch_tx_write(struct efx_tx_queue *tx_queue)
unsigned write_ptr;
unsigned old_write_count = tx_queue->write_count;
- BUG_ON(tx_queue->write_count == tx_queue->insert_count);
+ tx_queue->xmit_more_available = false;
+ if (unlikely(tx_queue->write_count == tx_queue->insert_count))
+ return;
do {
write_ptr = tx_queue->write_count & tx_queue->ptr_mask;
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index c530e1c..24038ef 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -219,6 +219,7 @@ struct efx_tx_buffer {
* @tso_packets: Number of packets via the TSO xmit path
* @pushes: Number of times the TX push feature has been used
* @pio_packets: Number of times the TX PIO feature has been used
+ * @xmit_more_available: Are any packets waiting to be pushed to the NIC
* @empty_read_count: If the completion path has seen the queue as empty
* and the transmission path has not yet checked this, the value of
* @read_count bitwise-added to %EFX_EMPTY_COUNT_VALID; otherwise 0.
@@ -253,6 +254,7 @@ struct efx_tx_queue {
unsigned int tso_packets;
unsigned int pushes;
unsigned int pio_packets;
+ bool xmit_more_available;
/* Statistics to supplement MAC stats */
unsigned long tx_packets;
diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index 1833a01..67f6afa 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -431,8 +431,20 @@ finish_packet:
efx_tx_maybe_stop_queue(tx_queue);
/* Pass off to hardware */
- if (!skb->xmit_more || netif_xmit_stopped(tx_queue->core_txq))
+ if (!skb->xmit_more || netif_xmit_stopped(tx_queue->core_txq)) {
+ struct efx_tx_queue *txq2 = efx_tx_queue_partner(tx_queue);
+
+ /* There could be packets left on the partner queue if those
+ * SKBs had skb->xmit_more set. If we do not push those they
+ * could be left for a long time and cause a netdev watchdog.
+ */
+ if (txq2->xmit_more_available)
+ efx_nic_push_buffers(txq2);
+
efx_nic_push_buffers(tx_queue);
+ } else {
+ tx_queue->xmit_more_available = skb->xmit_more;
+ }
tx_queue->tx_packets++;
@@ -722,6 +734,7 @@ void efx_init_tx_queue(struct efx_tx_queue *tx_queue)
tx_queue->read_count = 0;
tx_queue->old_read_count = 0;
tx_queue->empty_read_count = 0 | EFX_EMPTY_COUNT_VALID;
+ tx_queue->xmit_more_available = false;
/* Set up TX descriptor ring */
efx_nic_init_tx(tx_queue);
@@ -747,6 +760,7 @@ void efx_fini_tx_queue(struct efx_tx_queue *tx_queue)
++tx_queue->read_count;
}
+ tx_queue->xmit_more_available = false;
netdev_tx_reset_queue(tx_queue->core_txq);
}
@@ -1302,8 +1316,20 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
efx_tx_maybe_stop_queue(tx_queue);
/* Pass off to hardware */
- if (!skb->xmit_more || netif_xmit_stopped(tx_queue->core_txq))
+ if (!skb->xmit_more || netif_xmit_stopped(tx_queue->core_txq)) {
+ struct efx_tx_queue *txq2 = efx_tx_queue_partner(tx_queue);
+
+ /* There could be packets left on the partner queue if those
+ * SKBs had skb->xmit_more set. If we do not push those they
+ * could be left for a long time and cause a netdev watchdog.
+ */
+ if (txq2->xmit_more_available)
+ efx_nic_push_buffers(txq2);
+
efx_nic_push_buffers(tx_queue);
+ } else {
+ tx_queue->xmit_more_available = skb->xmit_more;
+ }
tx_queue->tso_bursts++;
return NETDEV_TX_OK;
--
2.4.1
From 80a7f5cf508c8054c3196e1110efecf5e842f698 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 2 Nov 2015 07:50:07 -0800
Subject: [PATCH 10/17] net: avoid NULL deref in inet_ctl_sock_destroy()
[ Upstream commit 8fa677d2706d325d71dab91bf6e6512c05214e37 ]
Under low memory conditions, tcp_sk_init() and icmp_sk_init()
can both iterate on all possible cpus and call inet_ctl_sock_destroy(),
with eventual NULL pointer.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/inet_common.h | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/include/net/inet_common.h b/include/net/inet_common.h
index 279f835..109e3ee 100644
--- a/include/net/inet_common.h
+++ b/include/net/inet_common.h
@@ -41,7 +41,8 @@ int inet_recv_error(struct sock *sk, struct msghdr *msg, int len,
static inline void inet_ctl_sock_destroy(struct sock *sk)
{
- sock_release(sk->sk_socket);
+ if (sk)
+ sock_release(sk->sk_socket);
}
#endif
--
2.4.1
From 4cc1b5dbe087a8b3ab518164fa90c9ab4d63e923 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Wed, 4 Nov 2015 14:47:53 +0100
Subject: [PATCH 11/17] ipv6: clean up dev_snmp6 proc entry when we fail to
initialize inet6_dev
[ Upstream commit 2a189f9e57650e9f310ddf4aad75d66c1233a064 ]
In ipv6_add_dev, when addrconf_sysctl_register fails, we do not clean up
the dev_snmp6 entry that we have already registered for this device.
Call snmp6_unregister_dev in this case.
Fixes: a317a2f19da7d ("ipv6: fail early when creating netdev named all or default")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv6/addrconf.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 36b85bd..dd00828 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -417,6 +417,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
if (err) {
ipv6_mc_destroy_dev(ndev);
del_timer(&ndev->regen_timer);
+ snmp6_unregister_dev(ndev);
goto err_release;
}
/* protected by rtnl_lock */
--
2.4.1
From 31aa0cfdfddba6e487aec78ff1f8fffb8bc3015d Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 3 Nov 2015 14:32:57 -0800
Subject: [PATCH 12/17] ipv4: disable BH when changing ip local port range
[ Upstream commit 4ee3bd4a8c7463cdef0b82ebc33fc94a9170a7e0 ]
This fixes the following lockdep warning:
[ INFO: inconsistent lock state ]
4.3.0-rc7+ #1197 Not tainted
---------------------------------
inconsistent {IN-SOFTIRQ-R} -> {SOFTIRQ-ON-W} usage.
sysctl/1019 [HC0[0]:SC0[0]:HE1:SE1] takes:
(&(&net->ipv4.ip_local_ports.lock)->seqcount){+.+-..}, at: [<ffffffff81921de7>] ipv4_local_port_range+0xb4/0x12a
{IN-SOFTIRQ-R} state was registered at:
[<ffffffff810bd682>] __lock_acquire+0x2f6/0xdf0
[<ffffffff810be6d5>] lock_acquire+0x11c/0x1a4
[<ffffffff818e599c>] inet_get_local_port_range+0x4e/0xae
[<ffffffff8166e8e3>] udp_flow_src_port.constprop.40+0x23/0x116
[<ffffffff81671cb9>] vxlan_xmit_one+0x219/0xa6a
[<ffffffff81672f75>] vxlan_xmit+0xa6b/0xaa5
[<ffffffff817f2deb>] dev_hard_start_xmit+0x2ae/0x465
[<ffffffff817f35ed>] __dev_queue_xmit+0x531/0x633
[<ffffffff817f3702>] dev_queue_xmit_sk+0x13/0x15
[<ffffffff818004a5>] neigh_resolve_output+0x12f/0x14d
[<ffffffff81959cfa>] ip6_finish_output2+0x344/0x39f
[<ffffffff8195bf58>] ip6_finish_output+0x88/0x8e
[<ffffffff8195bfef>] ip6_output+0x91/0xe5
[<ffffffff819792ae>] dst_output_sk+0x47/0x4c
[<ffffffff81979392>] NF_HOOK_THRESH.constprop.30+0x38/0x82
[<ffffffff8197981e>] mld_sendpack+0x189/0x266
[<ffffffff8197b28b>] mld_ifc_timer_expire+0x1ef/0x223
[<ffffffff810de581>] call_timer_fn+0xfb/0x28c
[<ffffffff810ded1e>] run_timer_softirq+0x1c7/0x1f1
Fixes: b8f1a55639e6 ("udp: Add function to make source port for UDP tunnels")
Cc: Tom Herbert <tom@herbertland.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv4/sysctl_net_ipv4.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 894da3a..ade7737 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -48,14 +48,14 @@ static void set_local_port_range(struct net *net, int range[2])
{
bool same_parity = !((range[0] ^ range[1]) & 1);
- write_seqlock(&net->ipv4.ip_local_ports.lock);
+ write_seqlock_bh(&net->ipv4.ip_local_ports.lock);
if (same_parity && !net->ipv4.ip_local_ports.warned) {
net->ipv4.ip_local_ports.warned = true;
pr_err_ratelimited("ip_local_port_range: prefer different parity for start/end values.\n");
}
net->ipv4.ip_local_ports.range[0] = range[0];
net->ipv4.ip_local_ports.range[1] = range[1];
- write_sequnlock(&net->ipv4.ip_local_ports.lock);
+ write_sequnlock_bh(&net->ipv4.ip_local_ports.lock);
}
/* Validate changes from /proc interface. */
--
2.4.1
From d04ea27f9dfc17ef6f031fd001b818b1ac70141d Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Tue, 3 Nov 2015 15:59:28 -0800
Subject: [PATCH 13/17] net: Fix prefsrc lookups
[ Upstream commit e1b8d903c6c3862160d2d5036806a94786c8fc4e ]
A bug report (https://bugzilla.kernel.org/show_bug.cgi?id=107071) noted
that the follwoing ip command is failing with v4.3:
$ ip route add 10.248.5.0/24 dev bond0.250 table vlan_250 src 10.248.5.154
RTNETLINK answers: Invalid argument
021dd3b8a142d changed the lookup of the given preferred source address to
use the table id passed in, but this assumes the local entries are in the
given table which is not necessarily true for non-VRF use cases. When
validating the preferred source fallback to the local table on failure.
Fixes: 021dd3b8a142d ("net: Add routes to the table associated with the device")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv4/fib_semantics.c | 13 ++++++++++---
1 file changed, 10 insertions(+), 3 deletions(-)
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index e966f85..ef5892f 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -864,14 +864,21 @@ static bool fib_valid_prefsrc(struct fib_config *cfg, __be32 fib_prefsrc)
if (cfg->fc_type != RTN_LOCAL || !cfg->fc_dst ||
fib_prefsrc != cfg->fc_dst) {
u32 tb_id = cfg->fc_table;
+ int rc;
if (tb_id == RT_TABLE_MAIN)
tb_id = RT_TABLE_LOCAL;
- if (inet_addr_type_table(cfg->fc_nlinfo.nl_net,
- fib_prefsrc, tb_id) != RTN_LOCAL) {
- return false;
+ rc = inet_addr_type_table(cfg->fc_nlinfo.nl_net,
+ fib_prefsrc, tb_id);
+
+ if (rc != RTN_LOCAL && tb_id != RT_TABLE_LOCAL) {
+ rc = inet_addr_type_table(cfg->fc_nlinfo.nl_net,
+ fib_prefsrc, RT_TABLE_LOCAL);
}
+
+ if (rc != RTN_LOCAL)
+ return false;
}
return true;
}
--
2.4.1
From 79f11d5fe0fd0547c8b1d03166e70f2f6ffae8a8 Mon Sep 17 00:00:00 2001
From: Tobias Klauser <tklauser@distanz.ch>
Date: Wed, 4 Nov 2015 13:49:49 +0100
Subject: [PATCH 14/17] tun_dst: Fix potential NULL dereference
[ Upstream commit f63ce5b6fa5e9a0faf7a0e1ef2993a502878c78a ]
In tun_dst_unclone() the return value of skb_metadata_dst() is checked
for being NULL after it is dereferenced. Fix this by moving the
dereference after the NULL check.
Found by the Coverity scanner (CID 1338068).
Fixes: fc4099f17240 ("openvswitch: Fix egress tunnel info.")
Cc: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/dst_metadata.h | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h
index ce00971..6816f0f 100644
--- a/include/net/dst_metadata.h
+++ b/include/net/dst_metadata.h
@@ -63,12 +63,13 @@ static inline struct metadata_dst *tun_rx_dst(int md_size)
static inline struct metadata_dst *tun_dst_unclone(struct sk_buff *skb)
{
struct metadata_dst *md_dst = skb_metadata_dst(skb);
- int md_size = md_dst->u.tun_info.options_len;
+ int md_size;
struct metadata_dst *new_md;
if (!md_dst)
return ERR_PTR(-EINVAL);
+ md_size = md_dst->u.tun_info.options_len;
new_md = metadata_dst_alloc(md_size, GFP_ATOMIC);
if (!new_md)
return ERR_PTR(-ENOMEM);
--
2.4.1
From 4a75ef6f762c85d73a76a9466672cf66965d82e2 Mon Sep 17 00:00:00 2001
From: Francesco Ruggeri <fruggeri@aristanetworks.com>
Date: Thu, 5 Nov 2015 08:16:14 -0800
Subject: [PATCH 15/17] packet: race condition in packet_bind
[ Upstream commit 30f7ea1c2b5f5fb7462c5ae44fe2e40cb2d6a474 ]
There is a race conditions between packet_notifier and packet_bind{_spkt}.
It happens if packet_notifier(NETDEV_UNREGISTER) executes between the
time packet_bind{_spkt} takes a reference on the new netdevice and the
time packet_do_bind sets po->ifindex.
In this case the notification can be missed.
If this happens during a dev_change_net_namespace this can result in the
netdevice to be moved to the new namespace while the packet_sock in the
old namespace still holds a reference on it. When the netdevice is later
deleted in the new namespace the deletion hangs since the packet_sock
is not found in the new namespace' &net->packet.sklist.
It can be reproduced with the script below.
This patch makes packet_do_bind check again for the presence of the
netdevice in the packet_sock's namespace after the synchronize_net
in unregister_prot_hook.
More in general it also uses the rcu lock for the duration of the bind
to stop dev_change_net_namespace/rollback_registered_many from
going past the synchronize_net following unlist_netdevice, so that
no NETDEV_UNREGISTER notifications can happen on the new netdevice
while the bind is executing. In order to do this some code from
packet_bind{_spkt} is consolidated into packet_do_dev.
import socket, os, time, sys
proto=7
realDev='em1'
vlanId=400
if len(sys.argv) > 1:
vlanId=int(sys.argv[1])
dev='vlan%d' % vlanId
os.system('taskset -p 0x10 %d' % os.getpid())
s = socket.socket(socket.PF_PACKET, socket.SOCK_RAW, proto)
os.system('ip link add link %s name %s type vlan id %d' %
(realDev, dev, vlanId))
os.system('ip netns add dummy')
pid=os.fork()
if pid == 0:
# dev should be moved while packet_do_bind is in synchronize net
os.system('taskset -p 0x20000 %d' % os.getpid())
os.system('ip link set %s netns dummy' % dev)
os.system('ip netns exec dummy ip link del %s' % dev)
s.close()
sys.exit(0)
time.sleep(.004)
try:
s.bind(('%s' % dev, proto+1))
except:
print 'Could not bind socket'
s.close()
os.system('ip netns del dummy')
sys.exit(0)
os.waitpid(pid, 0)
s.close()
os.system('ip netns del dummy')
sys.exit(0)
Signed-off-by: Francesco Ruggeri <fruggeri@arista.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/packet/af_packet.c | 80 +++++++++++++++++++++++++++++++-------------------
1 file changed, 49 insertions(+), 31 deletions(-)
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index aa4b15c..27b2898 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2903,22 +2903,40 @@ static int packet_release(struct socket *sock)
* Attach a packet hook.
*/
-static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
+static int packet_do_bind(struct sock *sk, const char *name, int ifindex,
+ __be16 proto)
{
struct packet_sock *po = pkt_sk(sk);
struct net_device *dev_curr;
__be16 proto_curr;
bool need_rehook;
+ struct net_device *dev = NULL;
+ int ret = 0;
+ bool unlisted = false;
- if (po->fanout) {
- if (dev)
- dev_put(dev);
-
+ if (po->fanout)
return -EINVAL;
- }
lock_sock(sk);
spin_lock(&po->bind_lock);
+ rcu_read_lock();
+
+ if (name) {
+ dev = dev_get_by_name_rcu(sock_net(sk), name);
+ if (!dev) {
+ ret = -ENODEV;
+ goto out_unlock;
+ }
+ } else if (ifindex) {
+ dev = dev_get_by_index_rcu(sock_net(sk), ifindex);
+ if (!dev) {
+ ret = -ENODEV;
+ goto out_unlock;
+ }
+ }
+
+ if (dev)
+ dev_hold(dev);
proto_curr = po->prot_hook.type;
dev_curr = po->prot_hook.dev;
@@ -2926,14 +2944,29 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
need_rehook = proto_curr != proto || dev_curr != dev;
if (need_rehook) {
- unregister_prot_hook(sk, true);
+ if (po->running) {
+ rcu_read_unlock();
+ __unregister_prot_hook(sk, true);
+ rcu_read_lock();
+ dev_curr = po->prot_hook.dev;
+ if (dev)
+ unlisted = !dev_get_by_index_rcu(sock_net(sk),
+ dev->ifindex);
+ }
po->num = proto;
po->prot_hook.type = proto;
- po->prot_hook.dev = dev;
- po->ifindex = dev ? dev->ifindex : 0;
- packet_cached_dev_assign(po, dev);
+ if (unlikely(unlisted)) {
+ dev_put(dev);
+ po->prot_hook.dev = NULL;
+ po->ifindex = -1;
+ packet_cached_dev_reset(po);
+ } else {
+ po->prot_hook.dev = dev;
+ po->ifindex = dev ? dev->ifindex : 0;
+ packet_cached_dev_assign(po, dev);
+ }
}
if (dev_curr)
dev_put(dev_curr);
@@ -2941,7 +2974,7 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
if (proto == 0 || !need_rehook)
goto out_unlock;
- if (!dev || (dev->flags & IFF_UP)) {
+ if (!unlisted && (!dev || (dev->flags & IFF_UP))) {
register_prot_hook(sk);
} else {
sk->sk_err = ENETDOWN;
@@ -2950,9 +2983,10 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
}
out_unlock:
+ rcu_read_unlock();
spin_unlock(&po->bind_lock);
release_sock(sk);
- return 0;
+ return ret;
}
/*
@@ -2964,8 +2998,6 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr,
{
struct sock *sk = sock->sk;
char name[15];
- struct net_device *dev;
- int err = -ENODEV;
/*
* Check legality
@@ -2975,19 +3007,13 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr,
return -EINVAL;
strlcpy(name, uaddr->sa_data, sizeof(name));
- dev = dev_get_by_name(sock_net(sk), name);
- if (dev)
- err = packet_do_bind(sk, dev, pkt_sk(sk)->num);
- return err;
+ return packet_do_bind(sk, name, 0, pkt_sk(sk)->num);
}
static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{
struct sockaddr_ll *sll = (struct sockaddr_ll *)uaddr;
struct sock *sk = sock->sk;
- struct net_device *dev = NULL;
- int err;
-
/*
* Check legality
@@ -2998,16 +3024,8 @@ static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len
if (sll->sll_family != AF_PACKET)
return -EINVAL;
- if (sll->sll_ifindex) {
- err = -ENODEV;
- dev = dev_get_by_index(sock_net(sk), sll->sll_ifindex);
- if (dev == NULL)
- goto out;
- }
- err = packet_do_bind(sk, dev, sll->sll_protocol ? : pkt_sk(sk)->num);
-
-out:
- return err;
+ return packet_do_bind(sk, NULL, sll->sll_ifindex,
+ sll->sll_protocol ? : pkt_sk(sk)->num);
}
static struct proto packet_proto = {
--
2.4.1
From b84e1a71f9b380b8fe8843e5af4c72cad640a1dc Mon Sep 17 00:00:00 2001
From: Jay Vosburgh <jay.vosburgh@canonical.com>
Date: Fri, 6 Nov 2015 17:23:23 -0800
Subject: [PATCH 16/17] bonding: fix panic on non-ARPHRD_ETHER enslave failure
[ Upstream commit 40baec225765c54eefa870530dd613bad9829bb7 ]
Since commit 7d5cd2ce529b, when bond_enslave fails on devices that
are not ARPHRD_ETHER, if needed, it resets the bonding device back to
ARPHRD_ETHER by calling ether_setup.
Unfortunately, ether_setup clobbers dev->flags, clearing IFF_UP
if the bond device is up, leaving it in a quasi-down state without
having actually gone through dev_close. For bonding, if any periodic
work queue items are active (miimon, arp_interval, etc), those will
remain running, as they are stopped by bond_close. At this point, if
the bonding module is unloaded or the bond is deleted, the system will
panic when the work function is called.
This panic is resolved by calling dev_close on the bond itself
prior to calling ether_setup.
Cc: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Fixes: 7d5cd2ce5292 ("bonding: correctly handle bonding type change on enslave failure")
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/bonding/bond_main.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 771a449..bcd7bdd 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1749,6 +1749,7 @@ err_undo_flags:
slave_dev->dev_addr))
eth_hw_addr_random(bond_dev);
if (bond_dev->type != ARPHRD_ETHER) {
+ dev_close(bond_dev);
ether_setup(bond_dev);
bond_dev->flags |= IFF_MASTER;
bond_dev->priv_flags &= ~IFF_TX_SKB_SHARING;
--
2.4.1
From b019533c6926b5dd5a7b1d6f8cb8616b51e39297 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 9 Nov 2015 17:51:23 -0800
Subject: [PATCH 17/17] net: fix a race in dst_release()
[ Upstream commit d69bbf88c8d0b367cf3e3a052f6daadf630ee566 ]
Only cpu seeing dst refcount going to 0 can safely
dereference dst->flags.
Otherwise an other cpu might already have freed the dst.
Fixes: 27b75c95f10d ("net: avoid RCU for NOCACHE dst")
Reported-by: Greg Thelen <gthelen@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/core/dst.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/core/dst.c b/net/core/dst.c
index 0771c8c..d6a5a0b 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -306,7 +306,7 @@ void dst_release(struct dst_entry *dst)
if (unlikely(newrefcnt < 0))
net_warn_ratelimited("%s: dst:%p refcnt:%d\n",
__func__, dst, newrefcnt);
- if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt)
+ if (!newrefcnt && unlikely(dst->flags & DST_NOCACHE))
call_rcu(&dst->rcu_head, dst_destroy_rcu);
}
}
--
2.4.1