From 30b678d844af3305cda5953467005cebb5d7b687 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Mon, 30 Jul 2012 15:57:00 +0000 Subject: net: Allow driver to limit number of GSO segments per skb A peer (or local user) may cause TCP to use a nominal MSS of as little as 88 (actual MSS of 76 with timestamps). Given that we have a sufficiently prodigious local sender and the peer ACKs quickly enough, it is nevertheless possible to grow the window for such a connection to the point that we will try to send just under 64K at once. This results in a single skb that expands to 861 segments. In some drivers with TSO support, such an skb will require hundreds of DMA descriptors; a substantial fraction of a TX ring or even more than a full ring. The TX queue selected for the skb may stall and trigger the TX watchdog repeatedly (since the problem skb will be retried after the TX reset). This particularly affects sfc, for which the issue is designated as CVE-2012-3412. Therefore: 1. Add the field net_device::gso_max_segs holding the device-specific limit. 2. In netif_skb_features(), if the number of segments is too high then mask out GSO features to force fall back to software GSO. Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index eb06e58bed0b..a9db4f33407f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1300,6 +1300,8 @@ struct net_device { /* for setting kernel sock attribute on TCP connection setup */ #define GSO_MAX_SIZE 65536 unsigned int gso_max_size; +#define GSO_MAX_SEGS 65535 + u16 gso_max_segs; #ifdef CONFIG_DCB /* Data Center Bridging netlink ops */ -- cgit v1.3-8-gc7d7 From 47be03a28cc6c80e3aa2b3e8ed6d960ff0c5c0af Mon Sep 17 00:00:00 2001 From: Amerigo Wang Date: Fri, 10 Aug 2012 01:24:37 +0000 Subject: netpoll: use GFP_ATOMIC in slave_enable_netpoll() and __netpoll_setup() slave_enable_netpoll() and __netpoll_setup() may be called with read_lock() held, so should use GFP_ATOMIC to allocate memory. Eric suggested to pass gfp flags to __netpoll_setup(). Cc: Eric Dumazet Cc: "David S. Miller" Reported-by: Dan Carpenter Signed-off-by: Eric Dumazet Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 6 +++--- drivers/net/team/team.c | 16 +++++++++------- include/linux/netdevice.h | 3 ++- include/linux/netpoll.h | 2 +- net/8021q/vlan_dev.c | 7 ++++--- net/bridge/br_device.c | 12 ++++++------ net/bridge/br_if.c | 2 +- net/bridge/br_private.h | 4 ++-- net/core/netpoll.c | 8 ++++---- 9 files changed, 32 insertions(+), 28 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 6fae5f3ec7f6..8697136e27c0 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1235,12 +1235,12 @@ static inline int slave_enable_netpoll(struct slave *slave) struct netpoll *np; int err = 0; - np = kzalloc(sizeof(*np), GFP_KERNEL); + np = kzalloc(sizeof(*np), GFP_ATOMIC); err = -ENOMEM; if (!np) goto out; - err = __netpoll_setup(np, slave->dev); + err = __netpoll_setup(np, slave->dev, GFP_ATOMIC); if (err) { kfree(np); goto out; @@ -1292,7 +1292,7 @@ static void bond_netpoll_cleanup(struct net_device *bond_dev) read_unlock(&bond->lock); } -static int bond_netpoll_setup(struct net_device *dev, struct netpoll_info *ni) +static int bond_netpoll_setup(struct net_device *dev, struct netpoll_info *ni, gfp_t gfp) { struct bonding *bond = netdev_priv(dev); struct slave *slave; diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 87707ab39430..341b65dbbcd3 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -795,16 +795,17 @@ static void team_port_leave(struct team *team, struct team_port *port) } #ifdef CONFIG_NET_POLL_CONTROLLER -static int team_port_enable_netpoll(struct team *team, struct team_port *port) +static int team_port_enable_netpoll(struct team *team, struct team_port *port, + gfp_t gfp) { struct netpoll *np; int err; - np = kzalloc(sizeof(*np), GFP_KERNEL); + np = kzalloc(sizeof(*np), gfp); if (!np) return -ENOMEM; - err = __netpoll_setup(np, port->dev); + err = __netpoll_setup(np, port->dev, gfp); if (err) { kfree(np); return err; @@ -833,7 +834,8 @@ static struct netpoll_info *team_netpoll_info(struct team *team) } #else -static int team_port_enable_netpoll(struct team *team, struct team_port *port) +static int team_port_enable_netpoll(struct team *team, struct team_port *port, + gfp_t gfp) { return 0; } @@ -913,7 +915,7 @@ static int team_port_add(struct team *team, struct net_device *port_dev) } if (team_netpoll_info(team)) { - err = team_port_enable_netpoll(team, port); + err = team_port_enable_netpoll(team, port, GFP_KERNEL); if (err) { netdev_err(dev, "Failed to enable netpoll on device %s\n", portname); @@ -1443,7 +1445,7 @@ static void team_netpoll_cleanup(struct net_device *dev) } static int team_netpoll_setup(struct net_device *dev, - struct netpoll_info *npifo) + struct netpoll_info *npifo, gfp_t gfp) { struct team *team = netdev_priv(dev); struct team_port *port; @@ -1451,7 +1453,7 @@ static int team_netpoll_setup(struct net_device *dev, mutex_lock(&team->lock); list_for_each_entry(port, &team->port_list, list) { - err = team_port_enable_netpoll(team, port); + err = team_port_enable_netpoll(team, port, gfp); if (err) { __team_netpoll_cleanup(team); break; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a9db4f33407f..3560d688161e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -953,7 +953,8 @@ struct net_device_ops { #ifdef CONFIG_NET_POLL_CONTROLLER void (*ndo_poll_controller)(struct net_device *dev); int (*ndo_netpoll_setup)(struct net_device *dev, - struct netpoll_info *info); + struct netpoll_info *info, + gfp_t gfp); void (*ndo_netpoll_cleanup)(struct net_device *dev); #endif int (*ndo_set_vf_mac)(struct net_device *dev, diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 28f5389c924b..bf2d51eec0f3 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -43,7 +43,7 @@ struct netpoll_info { void netpoll_send_udp(struct netpoll *np, const char *msg, int len); void netpoll_print_options(struct netpoll *np); int netpoll_parse_options(struct netpoll *np, char *opt); -int __netpoll_setup(struct netpoll *np, struct net_device *ndev); +int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp); int netpoll_setup(struct netpoll *np); int netpoll_trap(void); void netpoll_set_trap(int trap); diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 73a2a83ee2da..ee4ae0944cef 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -669,19 +669,20 @@ static void vlan_dev_poll_controller(struct net_device *dev) return; } -static int vlan_dev_netpoll_setup(struct net_device *dev, struct netpoll_info *npinfo) +static int vlan_dev_netpoll_setup(struct net_device *dev, struct netpoll_info *npinfo, + gfp_t gfp) { struct vlan_dev_priv *info = vlan_dev_priv(dev); struct net_device *real_dev = info->real_dev; struct netpoll *netpoll; int err = 0; - netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL); + netpoll = kzalloc(sizeof(*netpoll), gfp); err = -ENOMEM; if (!netpoll) goto out; - err = __netpoll_setup(netpoll, real_dev); + err = __netpoll_setup(netpoll, real_dev, gfp); if (err) { kfree(netpoll); goto out; diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 333484537600..ed0e0f9dc788 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -213,7 +213,8 @@ static void br_netpoll_cleanup(struct net_device *dev) } } -static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni) +static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni, + gfp_t gfp) { struct net_bridge *br = netdev_priv(dev); struct net_bridge_port *p, *n; @@ -222,8 +223,7 @@ static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni) list_for_each_entry_safe(p, n, &br->port_list, list) { if (!p->dev) continue; - - err = br_netpoll_enable(p); + err = br_netpoll_enable(p, gfp); if (err) goto fail; } @@ -236,17 +236,17 @@ fail: goto out; } -int br_netpoll_enable(struct net_bridge_port *p) +int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp) { struct netpoll *np; int err = 0; - np = kzalloc(sizeof(*p->np), GFP_KERNEL); + np = kzalloc(sizeof(*p->np), gfp); err = -ENOMEM; if (!np) goto out; - err = __netpoll_setup(np, p->dev); + err = __netpoll_setup(np, p->dev, gfp); if (err) { kfree(np); goto out; diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index e1144e1617be..171fd6b9bfe6 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -361,7 +361,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) if (err) goto err2; - if (br_netpoll_info(br) && ((err = br_netpoll_enable(p)))) + if (br_netpoll_info(br) && ((err = br_netpoll_enable(p, GFP_KERNEL)))) goto err3; err = netdev_set_master(dev, br->dev); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index a768b2408edf..f507d2af9646 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -316,7 +316,7 @@ static inline void br_netpoll_send_skb(const struct net_bridge_port *p, netpoll_send_skb(np, skb); } -extern int br_netpoll_enable(struct net_bridge_port *p); +extern int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp); extern void br_netpoll_disable(struct net_bridge_port *p); #else static inline struct netpoll_info *br_netpoll_info(struct net_bridge *br) @@ -329,7 +329,7 @@ static inline void br_netpoll_send_skb(const struct net_bridge_port *p, { } -static inline int br_netpoll_enable(struct net_bridge_port *p) +static inline int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp) { return 0; } diff --git a/net/core/netpoll.c b/net/core/netpoll.c index b4c90e42b443..37cc854774a4 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -715,7 +715,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt) } EXPORT_SYMBOL(netpoll_parse_options); -int __netpoll_setup(struct netpoll *np, struct net_device *ndev) +int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp) { struct netpoll_info *npinfo; const struct net_device_ops *ops; @@ -734,7 +734,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev) } if (!ndev->npinfo) { - npinfo = kmalloc(sizeof(*npinfo), GFP_KERNEL); + npinfo = kmalloc(sizeof(*npinfo), gfp); if (!npinfo) { err = -ENOMEM; goto out; @@ -752,7 +752,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev) ops = np->dev->netdev_ops; if (ops->ndo_netpoll_setup) { - err = ops->ndo_netpoll_setup(ndev, npinfo); + err = ops->ndo_netpoll_setup(ndev, npinfo, gfp); if (err) goto free_npinfo; } @@ -857,7 +857,7 @@ int netpoll_setup(struct netpoll *np) refill_skbs(); rtnl_lock(); - err = __netpoll_setup(np, ndev); + err = __netpoll_setup(np, ndev, GFP_KERNEL); rtnl_unlock(); if (err) -- cgit v1.3-8-gc7d7 From c0de08d04215031d68fa13af36f347a6cfa252ca Mon Sep 17 00:00:00 2001 From: Eric Leblond Date: Thu, 16 Aug 2012 22:02:58 +0000 Subject: af_packet: don't emit packet on orig fanout group If a packet is emitted on one socket in one group of fanout sockets, it is transmitted again. It is thus read again on one of the sockets of the fanout group. This result in a loop for software which generate packets when receiving one. This retransmission is not the intended behavior: a fanout group must behave like a single socket. The packet should not be transmitted on a socket if it originates from a socket belonging to the same fanout group. This patch fixes the issue by changing the transmission check to take fanout group info account. Reported-by: Aleksandr Kotov Signed-off-by: Eric Leblond Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ net/core/dev.c | 16 ++++++++++++++-- net/packet/af_packet.c | 9 +++++++++ 3 files changed, 25 insertions(+), 2 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3560d688161e..59dc05f38247 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1522,6 +1522,8 @@ struct packet_type { struct sk_buff **(*gro_receive)(struct sk_buff **head, struct sk_buff *skb); int (*gro_complete)(struct sk_buff *skb); + bool (*id_match)(struct packet_type *ptype, + struct sock *sk); void *af_packet_priv; struct list_head list; }; diff --git a/net/core/dev.c b/net/core/dev.c index a39354ee1432..debd9372472f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1642,6 +1642,19 @@ static inline int deliver_skb(struct sk_buff *skb, return pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } +static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb) +{ + if (ptype->af_packet_priv == NULL) + return false; + + if (ptype->id_match) + return ptype->id_match(ptype, skb->sk); + else if ((struct sock *)ptype->af_packet_priv == skb->sk) + return true; + + return false; +} + /* * Support routine. Sends outgoing frames to any network * taps currently in use. @@ -1659,8 +1672,7 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) * they originated from - MvS (miquels@drinkel.ow.org) */ if ((ptype->dev == dev || !ptype->dev) && - (ptype->af_packet_priv == NULL || - (struct sock *)ptype->af_packet_priv != skb->sk)) { + (!skb_loop_sk(ptype, skb))) { if (pt_prev) { deliver_skb(skb2, pt_prev, skb->dev); pt_prev = ptype; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 8ac890a1a4c0..aee7196aac36 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1273,6 +1273,14 @@ static void __fanout_unlink(struct sock *sk, struct packet_sock *po) spin_unlock(&f->lock); } +bool match_fanout_group(struct packet_type *ptype, struct sock * sk) +{ + if (ptype->af_packet_priv == (void*)((struct packet_sock *)sk)->fanout) + return true; + + return false; +} + static int fanout_add(struct sock *sk, u16 id, u16 type_flags) { struct packet_sock *po = pkt_sk(sk); @@ -1325,6 +1333,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) match->prot_hook.dev = po->prot_hook.dev; match->prot_hook.func = packet_rcv_fanout; match->prot_hook.af_packet_priv = match; + match->prot_hook.id_match = match_fanout_group; dev_add_pack(&match->prot_hook); list_add(&match->list, &fanout_list); } -- cgit v1.3-8-gc7d7