From ae24e578de02b87cce3dc59248c29b2ecb071e9e Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 22 Dec 2009 09:42:06 +0100 Subject: ipvs: ip_vs_wrr.c: use lib/gcd.c Remove the private version of the greatest common divider to use lib/gcd.c, the latter also implementing the a < b case. [akpm@linux-foundation.org: repair neighboring whitespace because the diff looked odd] Signed-off-by: Florian Fainelli Cc: Sergei Shtylyov Cc: Takashi Iwai Acked-by: Simon Horman Cc: Julius Volz Cc: David S. Miller Cc: Patrick McHardy Signed-off-by: Andrew Morton Signed-off-by: Patrick McHardy --- net/netfilter/ipvs/Kconfig | 3 ++- net/netfilter/ipvs/ip_vs_wrr.c | 15 +-------------- 2 files changed, 3 insertions(+), 15 deletions(-) (limited to 'net') diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig index 79a6980..f2d7623 100644 --- a/net/netfilter/ipvs/Kconfig +++ b/net/netfilter/ipvs/Kconfig @@ -112,7 +112,8 @@ config IP_VS_RR module, choose M here. If unsure, say N. config IP_VS_WRR - tristate "weighted round-robin scheduling" + tristate "weighted round-robin scheduling" + select GCD ---help--- The weighted robin-robin scheduling algorithm directs network connections to different real servers based on server weights diff --git a/net/netfilter/ipvs/ip_vs_wrr.c b/net/netfilter/ipvs/ip_vs_wrr.c index 6182e8e..3c115fc 100644 --- a/net/netfilter/ipvs/ip_vs_wrr.c +++ b/net/netfilter/ipvs/ip_vs_wrr.c @@ -24,6 +24,7 @@ #include #include #include +#include #include @@ -38,20 +39,6 @@ struct ip_vs_wrr_mark { }; -/* - * Get the gcd of server weights - */ -static int gcd(int a, int b) -{ - int c; - - while ((c = a % b)) { - a = b; - b = c; - } - return b; -} - static int ip_vs_wrr_gcd_weight(struct ip_vs_service *svc) { struct ip_vs_dest *dest; -- cgit v1.1 From 1f731b63752dac76ff4dbf568a08ff2e3663316f Mon Sep 17 00:00:00 2001 From: Bernard Pidoux F6BVP Date: Thu, 17 Dec 2009 05:25:18 +0000 Subject: rose_loopback_timer sets VC number <= ROSE_DEFAULT_MAXVC cat /proc/net/rose displayed a rose sockets abnormal lci value, i.e. greater than maximum number of VCs per neighbour allowed. This number prevents further test of lci value during rose operations. Example (lines shortened) : [bernard]# cat /proc/net/rose dest_addr dest_call src_addr src_call dev lci neigh st vs vr va * * 2080175520 F6BVP-1 rose0 000 00000 0 0 0 0 2080175520 FPAD-0 2080175520 WP-0 rose0 FFE 00001 3 0 0 0 Here are the default parameters : linux/include/net/rose.h:#define ROSE_DEFAULT_MAXVC 50 /* Maximum number of VCs per neighbour */ linux/net/rose/af_rose.c:int sysctl_rose_maximum_vcs = ROSE_DEFAULT_MAXVC; With the following patch, rose_loopback_timer() attributes a VC number within limits. Signed-off-by: Bernard Pidoux Signed-off-by: David S. Miller --- net/rose/rose_loopback.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c index 114df6e..968e8ba 100644 --- a/net/rose/rose_loopback.c +++ b/net/rose/rose_loopback.c @@ -75,7 +75,7 @@ static void rose_loopback_timer(unsigned long param) lci_i = ((skb->data[0] << 8) & 0xF00) + ((skb->data[1] << 0) & 0x0FF); frametype = skb->data[2]; dest = (rose_address *)(skb->data + 4); - lci_o = 0xFFF - lci_i; + lci_o = ROSE_DEFAULT_MAXVC + 1 - lci_i; skb_reset_transport_header(skb); -- cgit v1.1 From 8ffd32083c849dcf476e56e6c5f728c80797ecdd Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Mon, 21 Dec 2009 14:25:06 +0000 Subject: net/sctp/socket.c: squish warning net/sctp/socket.c: In function 'sctp_setsockopt_autoclose': net/sctp/socket.c:2090: warning: comparison is always false due to limited range of data type Cc: Andrei Pelinescu-Onciul Cc: Vlad Yasevich Cc: "David S. Miller" Signed-off-by: Andrew Morton Signed-off-by: David S. Miller --- net/sctp/socket.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'net') diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 89ab66e..67fdac9 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2087,8 +2087,7 @@ static int sctp_setsockopt_autoclose(struct sock *sk, char __user *optval, if (copy_from_user(&sp->autoclose, optval, optlen)) return -EFAULT; /* make sure it won't exceed MAX_SCHEDULE_TIMEOUT */ - if (sp->autoclose > (MAX_SCHEDULE_TIMEOUT / HZ) ) - sp->autoclose = (__u32)(MAX_SCHEDULE_TIMEOUT / HZ) ; + sp->autoclose = min_t(long, sp->autoclose, MAX_SCHEDULE_TIMEOUT / HZ); return 0; } -- cgit v1.1 From 04bcef2a83f40c6db24222b27a52892cba39dffb Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Mon, 4 Jan 2010 16:37:12 +0100 Subject: ipvs: Add boundary check on ioctl arguments The ipvs code has a nifty system for doing the size of ioctl command copies; it defines an array with values into which it indexes the cmd to find the right length. Unfortunately, the ipvs code forgot to check if the cmd was in the range that the array provides, allowing for an index outside of the array, which then gives a "garbage" result into the length, which then gets used for copying into a stack buffer. Fix this by adding sanity checks on these as well as the copy size. [ horms@verge.net.au: adjusted limit to IP_VS_SO_GET_MAX ] Signed-off-by: Arjan van de Ven Acked-by: Julian Anastasov Signed-off-by: Simon Horman Signed-off-by: Patrick McHardy --- net/netfilter/ipvs/ip_vs_ctl.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 6bde12d..c37ac2d 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2077,6 +2077,10 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) if (!capable(CAP_NET_ADMIN)) return -EPERM; + if (cmd < IP_VS_BASE_CTL || cmd > IP_VS_SO_SET_MAX) + return -EINVAL; + if (len < 0 || len > MAX_ARG_LEN) + return -EINVAL; if (len != set_arglen[SET_CMDID(cmd)]) { pr_err("set_ctl: len %u != %u\n", len, set_arglen[SET_CMDID(cmd)]); @@ -2352,17 +2356,25 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { unsigned char arg[128]; int ret = 0; + unsigned int copylen; if (!capable(CAP_NET_ADMIN)) return -EPERM; + if (cmd < IP_VS_BASE_CTL || cmd > IP_VS_SO_GET_MAX) + return -EINVAL; + if (*len < get_arglen[GET_CMDID(cmd)]) { pr_err("get_ctl: len %u < %u\n", *len, get_arglen[GET_CMDID(cmd)]); return -EINVAL; } - if (copy_from_user(arg, user, get_arglen[GET_CMDID(cmd)]) != 0) + copylen = get_arglen[GET_CMDID(cmd)]; + if (copylen > 128) + return -EINVAL; + + if (copy_from_user(arg, user, copylen) != 0) return -EFAULT; if (mutex_lock_interruptible(&__ip_vs_mutex)) -- cgit v1.1 From 7ad6848c7e81a603605fad3f3575841aab004eea Mon Sep 17 00:00:00 2001 From: Octavian Purdila Date: Wed, 6 Jan 2010 20:37:01 -0800 Subject: ip: fix mc_loop checks for tunnels with multicast outer addresses When we have L3 tunnels with different inner/outer families (i.e. IPV4/IPV6) which use a multicast address as the outer tunnel destination address, multicast packets will be loopbacked back to the sending socket even if IP*_MULTICAST_LOOP is set to disabled. The mc_loop flag is present in the family specific part of the socket (e.g. the IPv4 or IPv4 specific part). setsockopt sets the inner family mc_loop flag. When the packet is pushed through the L3 tunnel it will eventually be processed by the outer family which if different will check the flag in a different part of the socket then it was set. Signed-off-by: Octavian Purdila Signed-off-by: David S. Miller --- net/ipv4/ip_output.c | 2 +- net/ipv6/ip6_output.c | 3 +-- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index e34013a..3451799 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -254,7 +254,7 @@ int ip_mc_output(struct sk_buff *skb) */ if (rt->rt_flags&RTCF_MULTICAST) { - if ((!sk || inet_sk(sk)->mc_loop) + if (sk_mc_loop(sk) #ifdef CONFIG_IP_MROUTE /* Small optimization: do not loopback not local frames, which returned after forwarding; they will be dropped diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index cd48801a..eb6d097 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -121,10 +121,9 @@ static int ip6_output2(struct sk_buff *skb) skb->dev = dev; if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) { - struct ipv6_pinfo* np = skb->sk ? inet6_sk(skb->sk) : NULL; struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); - if (!(dev->flags & IFF_LOOPBACK) && (!np || np->mc_loop) && + if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(skb->sk) && ((mroute6_socket(dev_net(dev)) && !(IP6CB(skb)->flags & IP6SKB_FORWARDED)) || ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr, -- cgit v1.1 From aaff23a95aea5f000895f50d90e91f1e2f727002 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Thu, 7 Jan 2010 18:33:18 +0100 Subject: netfilter: nf_ct_ftp: fix out of bounds read in update_nl_seq() As noticed by Dan Carpenter , update_nl_seq() currently contains an out of bounds read of the seq_aft_nl array when looking for the oldest sequence number position. Fix it to only compare valid positions. Cc: stable@kernel.org Signed-off-by: Patrick McHardy --- net/netfilter/nf_conntrack_ftp.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'net') diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index 38ea7ef..f0732aa 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -323,24 +323,24 @@ static void update_nl_seq(struct nf_conn *ct, u32 nl_seq, struct nf_ct_ftp_master *info, int dir, struct sk_buff *skb) { - unsigned int i, oldest = NUM_SEQ_TO_REMEMBER; + unsigned int i, oldest; /* Look for oldest: if we find exact match, we're done. */ for (i = 0; i < info->seq_aft_nl_num[dir]; i++) { if (info->seq_aft_nl[dir][i] == nl_seq) return; - - if (oldest == info->seq_aft_nl_num[dir] || - before(info->seq_aft_nl[dir][i], - info->seq_aft_nl[dir][oldest])) - oldest = i; } if (info->seq_aft_nl_num[dir] < NUM_SEQ_TO_REMEMBER) { info->seq_aft_nl[dir][info->seq_aft_nl_num[dir]++] = nl_seq; - } else if (oldest != NUM_SEQ_TO_REMEMBER && - after(nl_seq, info->seq_aft_nl[dir][oldest])) { - info->seq_aft_nl[dir][oldest] = nl_seq; + } else { + if (before(info->seq_aft_nl[dir][0], info->seq_aft_nl[dir][1])) + oldest = 0; + else + oldest = 1; + + if (after(nl_seq, info->seq_aft_nl[dir][oldest])) + info->seq_aft_nl[dir][oldest] = nl_seq; } } -- cgit v1.1 From 704da560c0a0120d8869187f511491a00951a1d3 Mon Sep 17 00:00:00 2001 From: Octavian Purdila Date: Fri, 8 Jan 2010 00:00:09 -0800 Subject: tcp: update the netstamp_needed counter when cloning sockets This fixes a netstamp_needed accounting issue when the listen socket has SO_TIMESTAMP set: s = socket(AF_INET, SOCK_STREAM, 0); setsockopt(s, SOL_SOCKET, SO_TIMESTAMP, 1); -> netstamp_needed = 1 bind(s, ...); listen(s, ...); s2 = accept(s, ...); -> netstamp_needed = 1 close(s2); -> netstamp_needed = 0 close(s); -> netstamp_needed = -1 Signed-off-by: Octavian Purdila Signed-off-by: David S. Miller --- net/core/sock.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net') diff --git a/net/core/sock.c b/net/core/sock.c index 76ff58d..e1f6f22 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1205,6 +1205,10 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) if (newsk->sk_prot->sockets_allocated) percpu_counter_inc(newsk->sk_prot->sockets_allocated); + + if (sock_flag(newsk, SOCK_TIMESTAMP) || + sock_flag(newsk, SOCK_TIMESTAMPING_RX_SOFTWARE)) + net_enable_timestamp(); } out: return newsk; -- cgit v1.1 From dce766af541f6605fa9889892c0280bab31c66ab Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 8 Jan 2010 17:31:24 +0100 Subject: netfilter: ebtables: enforce CAP_NET_ADMIN normal users are currently allowed to set/modify ebtables rules. Restrict it to processes with CAP_NET_ADMIN. Note that this cannot be reproduced with unmodified ebtables binary because it uses SOCK_RAW. Signed-off-by: Florian Westphal Cc: stable@kernel.org Signed-off-by: Patrick McHardy --- net/bridge/netfilter/ebtables.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'net') diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index bd1c654..0b7f262 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1406,6 +1406,9 @@ static int do_ebt_set_ctl(struct sock *sk, { int ret; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + switch(cmd) { case EBT_SO_SET_ENTRIES: ret = do_replace(sock_net(sk), user, len); @@ -1425,6 +1428,9 @@ static int do_ebt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) struct ebt_replace tmp; struct ebt_table *t; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (copy_from_user(&tmp, user, sizeof(tmp))) return -EFAULT; -- cgit v1.1 From eb70df13ee52dbc0f2c0ffd8ed34a8cd27440baf Mon Sep 17 00:00:00 2001 From: Jarek Poplawski Date: Sun, 10 Jan 2010 22:04:19 +0000 Subject: af_packet: Don't use skb after dev_queue_xmit() tpacket_snd() can change and kfree an skb after dev_queue_xmit(), which is illegal. With debugging by: Stephen Hemminger Reported-by: Michael Breuer With help from: David S. Miller Signed-off-by: Jarek Poplawski Tested-by: Michael Breuer Signed-off-by: David S. Miller --- net/packet/af_packet.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index e0516a2..f126d18 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1021,8 +1021,20 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) status = TP_STATUS_SEND_REQUEST; err = dev_queue_xmit(skb); - if (unlikely(err > 0 && (err = net_xmit_errno(err)) != 0)) - goto out_xmit; + if (unlikely(err > 0)) { + err = net_xmit_errno(err); + if (err && __packet_get_status(po, ph) == + TP_STATUS_AVAILABLE) { + /* skb was destructed already */ + skb = NULL; + goto out_status; + } + /* + * skb was dropped but not destructed yet; + * let's treat it like congestion or err < 0 + */ + err = 0; + } packet_increment_head(&po->tx_ring); len_sum += tp_len; } while (likely((ph != NULL) || @@ -1033,9 +1045,6 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) err = len_sum; goto out_put; -out_xmit: - skb->destructor = sock_wfree; - atomic_dec(&po->tx_ring.pending); out_status: __packet_set_status(po, ph, status); kfree_skb(skb); -- cgit v1.1