From 6049f2530cf2cb48a6fe8735309cc0b97aa7f700 Mon Sep 17 00:00:00 2001 From: Fernando Luis Vazquez Cao Date: Tue, 4 Feb 2014 19:35:02 +0900 Subject: rtnetlink: fix oops in rtnl_link_get_slave_info_data_size We should check whether rtnetlink link operations are defined before calling get_slave_size(). Without this, the following oops can occur when adding a tap device to OVS. [ 87.839553] BUG: unable to handle kernel NULL pointer dereference at 00000000000000a8 [ 87.839595] IP: [] if_nlmsg_size+0xf0/0x220 [...] [ 87.840651] Call Trace: [ 87.840664] [] ? rtmsg_ifinfo+0x2b/0x100 [ 87.840688] [] ? __netdev_adjacent_dev_insert+0x150/0x1a0 [ 87.840718] [] ? rtnetlink_event+0x30/0x40 [ 87.840742] [] ? notifier_call_chain+0x44/0x70 [ 87.840768] [] ? __netdev_upper_dev_link+0x3c6/0x3f0 [ 87.840798] [] ? netdev_create+0xcc/0x160 [openvswitch] [ 87.840828] [] ? ovs_vport_add+0x4a/0xd0 [openvswitch] [ 87.840857] [] ? new_vport+0x9/0x50 [openvswitch] [ 87.840884] [] ? ovs_vport_cmd_new+0x11e/0x210 [openvswitch] [ 87.840915] [] ? genl_family_rcv_msg+0x19a/0x360 [ 87.840941] [] ? genl_family_rcv_msg+0x360/0x360 [ 87.840967] [] ? genl_rcv_msg+0x79/0xc0 [ 87.840991] [] ? __kmalloc_reserve.isra.25+0x29/0x80 [ 87.841018] [] ? netlink_rcv_skb+0xa9/0xc0 [ 87.841042] [] ? genl_rcv+0x1f/0x30 [ 87.841064] [] ? netlink_unicast+0xe8/0x1e0 [ 87.841088] [] ? netlink_sendmsg+0x31a/0x750 [ 87.841113] [] ? sock_sendmsg+0x86/0xc0 [ 87.841136] [] ? __netdev_update_features+0x4d/0x200 [ 87.841163] [] ? ethtool_get_value+0x2e/0x50 [ 87.841188] [] ? ___sys_sendmsg+0x359/0x370 [ 87.841212] [] ? dev_ioctl+0x1a6/0x5c0 [ 87.841236] [] ? autoremove_wake_function+0x30/0x30 [ 87.841264] [] ? sock_do_ioctl+0x3d/0x50 [ 87.841288] [] ? sock_ioctl+0x1e8/0x2c0 [ 87.841312] [] ? do_vfs_ioctl+0x2cf/0x4b0 [ 87.841335] [] ? __sys_sendmsg+0x39/0x70 [ 87.841362] [] ? system_call_fastpath+0x16/0x1b [ 87.841386] Code: c0 74 10 48 89 ef ff d0 83 c0 07 83 e0 fc 48 98 49 01 c7 48 89 ef e8 d0 d6 fe ff 48 85 c0 0f 84 df 00 00 00 48 8b 90 08 07 00 00 <48> 8b 8a a8 00 00 00 31 d2 48 85 c9 74 0c 48 89 ee 48 89 c7 ff [ 87.841529] RIP [] if_nlmsg_size+0xf0/0x220 [ 87.841555] RSP [ 87.841569] CR2: 00000000000000a8 [ 87.851442] ---[ end trace e42ab217691b4fc2 ]--- Signed-off-by: Fernando Luis Vazquez Cao Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/core') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 393b1bc9a61..048dc8d183a 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -374,7 +374,7 @@ static size_t rtnl_link_get_slave_info_data_size(const struct net_device *dev) if (!master_dev) return 0; ops = master_dev->rtnl_link_ops; - if (!ops->get_slave_size) + if (!ops || !ops->get_slave_size) return 0; /* IFLA_INFO_SLAVE_DATA + nested data */ return nla_total_size(sizeof(struct nlattr)) + -- cgit v1.2.3-70-g09d2 From 00fe11b3c67dc670fe6391d22f1fe64e7c99a8ec Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Thu, 6 Feb 2014 18:34:12 +0100 Subject: netpoll: fix netconsole IPv6 setup Currently, to make netconsole start over IPv6, the source address needs to be specified. Without a source address, netpoll_parse_options assumes we're setting up over IPv4 and the destination IPv6 address is rejected. Check if the IP version has been forced by a source address before checking for a version mismatch when parsing the destination address. Signed-off-by: Sabrina Dubroca Acked-by: Cong Wang Signed-off-by: David S. Miller --- net/core/netpoll.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'net/core') diff --git a/net/core/netpoll.c b/net/core/netpoll.c index c03f3dec476..a664f7829a6 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -948,6 +948,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt) { char *cur=opt, *delim; int ipv6; + bool ipversion_set = false; if (*cur != '@') { if ((delim = strchr(cur, '@')) == NULL) @@ -960,6 +961,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt) cur++; if (*cur != '/') { + ipversion_set = true; if ((delim = strchr(cur, '/')) == NULL) goto parse_failed; *delim = 0; @@ -1002,7 +1004,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt) ipv6 = netpoll_parse_ip_addr(cur, &np->remote_ip); if (ipv6 < 0) goto parse_failed; - else if (np->ipv6 != (bool)ipv6) + else if (ipversion_set && np->ipv6 != (bool)ipv6) goto parse_failed; else np->ipv6 = (bool)ipv6; -- cgit v1.2.3-70-g09d2 From ed98df3361f059db42786c830ea96e2d18b8d4db Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 6 Feb 2014 10:42:42 -0800 Subject: net: use __GFP_NORETRY for high order allocations sock_alloc_send_pskb() & sk_page_frag_refill() have a loop trying high order allocations to prepare skb with low number of fragments as this increases performance. Problem is that under memory pressure/fragmentation, this can trigger OOM while the intent was only to try the high order allocations, then fallback to order-0 allocations. We had various reports from unexpected regressions. According to David, setting __GFP_NORETRY should be fine, as the asynchronous compaction is still enabled, and this will prevent OOM from kicking as in : CFSClientEventm invoked oom-killer: gfp_mask=0x42d0, order=3, oom_adj=0, oom_score_adj=0, oom_score_badness=2 (enabled),memcg_scoring=disabled CFSClientEventm Call Trace: [] dump_header+0xe1/0x23e [] oom_kill_process+0x6a/0x323 [] out_of_memory+0x4b3/0x50d [] __alloc_pages_may_oom+0xa2/0xc7 [] __alloc_pages_nodemask+0x1002/0x17f0 [] alloc_pages_current+0x103/0x2b0 [] sk_page_frag_refill+0x8f/0x160 [] tcp_sendmsg+0x560/0xee0 [] inet_sendmsg+0x67/0x100 [] __sock_sendmsg_nosec+0x6c/0x90 [] sock_sendmsg+0xc5/0xf0 [] __sys_sendmsg+0x136/0x430 [] sys_sendmsg+0x88/0x110 [] system_call_fastpath+0x16/0x1b Out of Memory: Kill process 2856 (bash) score 9999 or sacrifice child Signed-off-by: Eric Dumazet Acked-by: David Rientjes Acked-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- net/core/sock.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'net/core') diff --git a/net/core/sock.c b/net/core/sock.c index 0c127dcdf6a..5b6a9431b01 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1775,7 +1775,9 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, while (order) { if (npages >= 1 << order) { page = alloc_pages(sk->sk_allocation | - __GFP_COMP | __GFP_NOWARN, + __GFP_COMP | + __GFP_NOWARN | + __GFP_NORETRY, order); if (page) goto fill_page; @@ -1845,7 +1847,7 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio) gfp_t gfp = prio; if (order) - gfp |= __GFP_COMP | __GFP_NOWARN; + gfp |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY; pfrag->page = alloc_pages(gfp, order); if (likely(pfrag->page)) { pfrag->offset = 0; -- cgit v1.2.3-70-g09d2 From 0a59f3a9fd7e2801a445682465ea0522ea497183 Mon Sep 17 00:00:00 2001 From: Rashika Kheria Date: Sun, 9 Feb 2014 20:26:25 +0530 Subject: net: Mark functions as static in core/dev.c MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Mark functions as static in core/dev.c because they are not used outside this file. This eliminates the following warning in core/dev.c: net/core/dev.c:2806:5: warning: no previous prototype for ‘__dev_queue_xmit’ [-Wmissing-prototypes] net/core/dev.c:4640:5: warning: no previous prototype for ‘netdev_adjacent_sysfs_add’ [-Wmissing-prototypes] net/core/dev.c:4650:6: warning: no previous prototype for ‘netdev_adjacent_sysfs_del’ [-Wmissing-prototypes] Signed-off-by: Rashika Kheria Reviewed-by: Josh Triplett Reviewed-by: Veaceslav Falico Signed-off-by: David S. Miller --- net/core/dev.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'net/core') diff --git a/net/core/dev.c b/net/core/dev.c index 3721db71635..4ad1b78c9c7 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2803,7 +2803,7 @@ EXPORT_SYMBOL(dev_loopback_xmit); * the BH enable code must have IRQs enabled so that it will not deadlock. * --BLG */ -int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) +static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) { struct net_device *dev = skb->dev; struct netdev_queue *txq; @@ -4637,7 +4637,7 @@ struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev) } EXPORT_SYMBOL(netdev_master_upper_dev_get_rcu); -int netdev_adjacent_sysfs_add(struct net_device *dev, +static int netdev_adjacent_sysfs_add(struct net_device *dev, struct net_device *adj_dev, struct list_head *dev_list) { @@ -4647,7 +4647,7 @@ int netdev_adjacent_sysfs_add(struct net_device *dev, return sysfs_create_link(&(dev->dev.kobj), &(adj_dev->dev.kobj), linkname); } -void netdev_adjacent_sysfs_del(struct net_device *dev, +static void netdev_adjacent_sysfs_del(struct net_device *dev, char *name, struct list_head *dev_list) { -- cgit v1.2.3-70-g09d2 From 946c032e5a53992ea45e062ecb08670ba39b99e3 Mon Sep 17 00:00:00 2001 From: Maciej Żenczykowski Date: Fri, 7 Feb 2014 16:23:48 -0800 Subject: net: fix 'ip rule' iif/oif device rename MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ip rules with iif/oif references do not update: (detach/attach) across interface renames. Signed-off-by: Maciej Żenczykowski CC: Willem de Bruijn CC: Eric Dumazet CC: Chris Davis CC: Carlo Contavalli Google-Bug-Id: 12936021 Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/fib_rules.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'net/core') diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index f409e0bd35c..185c341fafb 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -745,6 +745,13 @@ static int fib_rules_event(struct notifier_block *this, unsigned long event, attach_rules(&ops->rules_list, dev); break; + case NETDEV_CHANGENAME: + list_for_each_entry(ops, &net->rules_ops, list) { + detach_rules(&ops->rules_list, dev); + attach_rules(&ops->rules_list, dev); + } + break; + case NETDEV_UNREGISTER: list_for_each_entry(ops, &net->rules_ops, list) detach_rules(&ops->rules_list, dev); -- cgit v1.2.3-70-g09d2