From c197facc8ea08062f8f949aade6a33649ee06771 Mon Sep 17 00:00:00 2001 From: "hummerbliss@gmail.com" Date: Mon, 20 Apr 2009 17:12:35 +0200 Subject: netfilter: bridge: allow fragmentation of VLAN packets traversing a bridge br_nf_dev_queue_xmit only checks for ETH_P_IP packets for fragmenting but not VLAN packets. This results in dropping of large VLAN packets. This can be observed when connection tracking is enabled. Connection tracking re-assembles fragmented packets, and these have to re-fragmented when transmitting out. Also, make sure only refragmented packets are defragmented as per suggestion from Patrick McHardy. Signed-off-by: Saikiran Madugula Signed-off-by: Patrick McHardy --- net/bridge/br_netfilter.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 3953ac4214c..e4a418fcb35 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -788,15 +788,23 @@ static unsigned int br_nf_local_out(unsigned int hook, struct sk_buff *skb, return NF_STOLEN; } +#if defined(CONFIG_NF_CONNTRACK_IPV4) || defined(CONFIG_NF_CONNTRACK_IPV4_MODULE) static int br_nf_dev_queue_xmit(struct sk_buff *skb) { - if (skb->protocol == htons(ETH_P_IP) && + if (skb->nfct != NULL && + (skb->protocol == htons(ETH_P_IP) || IS_VLAN_IP(skb)) && skb->len > skb->dev->mtu && !skb_is_gso(skb)) return ip_fragment(skb, br_dev_queue_push_xmit); else return br_dev_queue_push_xmit(skb); } +#else +static int br_nf_dev_queue_xmit(struct sk_buff *skb) +{ + return br_dev_queue_push_xmit(skb); +} +#endif /* PF_BRIDGE/POST_ROUTING ********************************************/ static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff *skb, -- cgit v1.2.3-70-g09d2 From 5ff482940f5aa2cdc3424c4a8ea94b9833b2af5f Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 24 Apr 2009 15:37:44 +0200 Subject: netfilter: nf_ct_dccp/udplite: fix protocol registration error Commit d0dba725 (netfilter: ctnetlink: add callbacks to the per-proto nlattrs) changed the protocol registration function to abort if the to-be registered protocol doesn't provide a new callback function. The DCCP and UDP-Lite IPv6 protocols were missed in this conversion, add the required callback pointer. Reported-and-tested-by: Steven Jan Springl Signed-off-by: Patrick McHardy --- net/netfilter/nf_conntrack_proto_dccp.c | 1 + net/netfilter/nf_conntrack_proto_udplite.c | 1 + 2 files changed, 2 insertions(+) (limited to 'net') diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 50dac8dbe7d..5411d63f31a 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -777,6 +777,7 @@ static struct nf_conntrack_l4proto dccp_proto6 __read_mostly = { .print_conntrack = dccp_print_conntrack, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) .to_nlattr = dccp_to_nlattr, + .nlattr_size = dccp_nlattr_size, .from_nlattr = nlattr_to_dccp, .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, diff --git a/net/netfilter/nf_conntrack_proto_udplite.c b/net/netfilter/nf_conntrack_proto_udplite.c index 4614696c1b8..0badedc542d 100644 --- a/net/netfilter/nf_conntrack_proto_udplite.c +++ b/net/netfilter/nf_conntrack_proto_udplite.c @@ -204,6 +204,7 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 __read_mostly = .error = udplite_error, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, + .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif -- cgit v1.2.3-70-g09d2 From 4b0706624930dc75c3b0d0df463d89759ef7de29 Mon Sep 17 00:00:00 2001 From: Laszlo Attila Toth Date: Fri, 24 Apr 2009 16:55:25 +0200 Subject: netfilter: Kconfig: TProxy doesn't depend on NF_CONNTRACK Signed-off-by: Laszlo Attila Toth Signed-off-by: Patrick McHardy --- net/netfilter/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 2329c5f5055..881203c4a14 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -275,6 +275,8 @@ config NF_CT_NETLINK help This option enables support for a netlink-based userspace interface +endif # NF_CONNTRACK + # transparent proxy support config NETFILTER_TPROXY tristate "Transparent proxying support (EXPERIMENTAL)" @@ -290,8 +292,6 @@ config NETFILTER_TPROXY To compile it as a module, choose M here. If unsure, say N. -endif # NF_CONNTRACK - config NETFILTER_XTABLES tristate "Netfilter Xtables support (required for ip_tables)" default m if NETFILTER_ADVANCED=n -- cgit v1.2.3-70-g09d2 From 71951b64a5a87c09eb6fde59ce51aaab2fdaeab2 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 24 Apr 2009 16:58:41 +0200 Subject: netfilter: nf_ct_dccp: add missing role attributes for DCCP This patch adds missing role attribute to the DCCP type, otherwise the creation of entries is not of any use. The attribute added is CTA_PROTOINFO_DCCP_ROLE which contains the role of the conntrack original tuple. Signed-off-by: Pablo Neira Ayuso Signed-off-by: Patrick McHardy --- include/linux/netfilter/nfnetlink_conntrack.h | 1 + net/netfilter/nf_conntrack_proto_dccp.c | 15 ++++++++++++++- 2 files changed, 15 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h index 29fe9ea1d34..1a865e48b8e 100644 --- a/include/linux/netfilter/nfnetlink_conntrack.h +++ b/include/linux/netfilter/nfnetlink_conntrack.h @@ -100,6 +100,7 @@ enum ctattr_protoinfo_tcp { enum ctattr_protoinfo_dccp { CTA_PROTOINFO_DCCP_UNSPEC, CTA_PROTOINFO_DCCP_STATE, + CTA_PROTOINFO_DCCP_ROLE, __CTA_PROTOINFO_DCCP_MAX, }; #define CTA_PROTOINFO_DCCP_MAX (__CTA_PROTOINFO_DCCP_MAX - 1) diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 5411d63f31a..8e757dd5339 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -633,6 +633,8 @@ static int dccp_to_nlattr(struct sk_buff *skb, struct nlattr *nla, if (!nest_parms) goto nla_put_failure; NLA_PUT_U8(skb, CTA_PROTOINFO_DCCP_STATE, ct->proto.dccp.state); + NLA_PUT_U8(skb, CTA_PROTOINFO_DCCP_ROLE, + ct->proto.dccp.role[IP_CT_DIR_ORIGINAL]); nla_nest_end(skb, nest_parms); read_unlock_bh(&dccp_lock); return 0; @@ -644,6 +646,7 @@ nla_put_failure: static const struct nla_policy dccp_nla_policy[CTA_PROTOINFO_DCCP_MAX + 1] = { [CTA_PROTOINFO_DCCP_STATE] = { .type = NLA_U8 }, + [CTA_PROTOINFO_DCCP_ROLE] = { .type = NLA_U8 }, }; static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct) @@ -661,11 +664,21 @@ static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct) return err; if (!tb[CTA_PROTOINFO_DCCP_STATE] || - nla_get_u8(tb[CTA_PROTOINFO_DCCP_STATE]) >= CT_DCCP_IGNORE) + !tb[CTA_PROTOINFO_DCCP_ROLE] || + nla_get_u8(tb[CTA_PROTOINFO_DCCP_ROLE]) > CT_DCCP_ROLE_MAX || + nla_get_u8(tb[CTA_PROTOINFO_DCCP_STATE]) >= CT_DCCP_IGNORE) { return -EINVAL; + } write_lock_bh(&dccp_lock); ct->proto.dccp.state = nla_get_u8(tb[CTA_PROTOINFO_DCCP_STATE]); + if (nla_get_u8(tb[CTA_PROTOINFO_DCCP_ROLE]) == CT_DCCP_ROLE_CLIENT) { + ct->proto.dccp.role[IP_CT_DIR_ORIGINAL] = CT_DCCP_ROLE_CLIENT; + ct->proto.dccp.role[IP_CT_DIR_REPLY] = CT_DCCP_ROLE_SERVER; + } else { + ct->proto.dccp.role[IP_CT_DIR_ORIGINAL] = CT_DCCP_ROLE_SERVER; + ct->proto.dccp.role[IP_CT_DIR_REPLY] = CT_DCCP_ROLE_CLIENT; + } write_unlock_bh(&dccp_lock); return 0; } -- cgit v1.2.3-70-g09d2 From 37e55cf0ceb8803256bf69a3e45bd668bf90b76f Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Fri, 24 Apr 2009 17:05:21 +0200 Subject: netfilter: xt_recent: fix stack overread in compat code Related-to: commit 325fb5b4d26038cba665dd0d8ee09555321061f0 The compat path suffers from a similar problem. It only uses a __be32 when all of the recent code uses, and expects, an nf_inet_addr everywhere. As a result, addresses stored by xt_recents were filled with whatever other stuff was on the stack following the be32. Signed-off-by: Jan Engelhardt With a minor compile fix from Roman. Reported-and-tested-by: Roman Hoog Antink Signed-off-by: Patrick McHardy --- net/netfilter/xt_recent.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index 791e030ea90..eb0ceb84652 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -474,7 +474,7 @@ static ssize_t recent_old_proc_write(struct file *file, struct recent_table *t = pde->data; struct recent_entry *e; char buf[sizeof("+255.255.255.255")], *c = buf; - __be32 addr; + union nf_inet_addr addr = {}; int add; if (size > sizeof(buf)) @@ -506,14 +506,13 @@ static ssize_t recent_old_proc_write(struct file *file, add = 1; break; } - addr = in_aton(c); + addr.ip = in_aton(c); spin_lock_bh(&recent_lock); - e = recent_entry_lookup(t, (const void *)&addr, NFPROTO_IPV4, 0); + e = recent_entry_lookup(t, &addr, NFPROTO_IPV4, 0); if (e == NULL) { if (add) - recent_entry_init(t, (const void *)&addr, - NFPROTO_IPV4, 0); + recent_entry_init(t, &addr, NFPROTO_IPV4, 0); } else { if (add) recent_entry_update(t, e); -- cgit v1.2.3-70-g09d2 From adc667e84f086aa110d810f3476c494e48eaabaa Mon Sep 17 00:00:00 2001 From: Jay Vosburgh Date: Sat, 25 Apr 2009 18:03:35 -0700 Subject: vlan: update vlan carrier state for admin up/down Currently, the VLAN event handler does not adjust the VLAN device's carrier state when the real device or the VLAN device is set administratively up or down. The following patch adds a transfer of operating state from the real device to the VLAN device when the real device is administratively set up or down, and sets the carrier state up or down during init, open and close of the VLAN device. This permits observers above the VLAN device that care about the carrier state (bonding's link monitor, for example) to receive updates for administrative changes by more closely mimicing the behavior of real devices. Signed-off-by: Jay Vosburgh Signed-off-by: Patrick McHardy --- net/8021q/vlan.c | 2 ++ net/8021q/vlan_dev.c | 5 +++++ 2 files changed, 7 insertions(+) (limited to 'net') diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 2b7390e377b..d1e10546eb8 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -492,6 +492,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, continue; dev_change_flags(vlandev, flgs & ~IFF_UP); + vlan_transfer_operstate(dev, vlandev); } break; @@ -507,6 +508,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, continue; dev_change_flags(vlandev, flgs | IFF_UP); + vlan_transfer_operstate(dev, vlandev); } break; diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 6b092136401..b4b9068e55a 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -462,6 +462,7 @@ static int vlan_dev_open(struct net_device *dev) if (vlan->flags & VLAN_FLAG_GVRP) vlan_gvrp_request_join(dev); + netif_carrier_on(dev); return 0; clear_allmulti: @@ -471,6 +472,7 @@ del_unicast: if (compare_ether_addr(dev->dev_addr, real_dev->dev_addr)) dev_unicast_delete(real_dev, dev->dev_addr, ETH_ALEN); out: + netif_carrier_off(dev); return err; } @@ -492,6 +494,7 @@ static int vlan_dev_stop(struct net_device *dev) if (compare_ether_addr(dev->dev_addr, real_dev->dev_addr)) dev_unicast_delete(real_dev, dev->dev_addr, dev->addr_len); + netif_carrier_off(dev); return 0; } @@ -612,6 +615,8 @@ static int vlan_dev_init(struct net_device *dev) struct net_device *real_dev = vlan_dev_info(dev)->real_dev; int subclass = 0; + netif_carrier_off(dev); + /* IFF_BROADCAST|IFF_MULTICAST; ??? */ dev->flags = real_dev->flags & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI); dev->iflink = real_dev->ifindex; -- cgit v1.2.3-70-g09d2 From 6a783c9067e3f71aac61a9262fe42c1f68efd4fc Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Mon, 27 Apr 2009 02:58:59 -0700 Subject: xfrm: wrong hash value for temporary SA When kernel inserts a temporary SA for IKE, it uses the wrong hash value for dst list. Two hash values were calcultated before: one with source address and one with a wildcard source address. Bug hinted by Junwei Zhang Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- net/xfrm/xfrm_state.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 82271720d97..5f1f86565f1 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -794,7 +794,7 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, { static xfrm_address_t saddr_wildcard = { }; struct net *net = xp_net(pol); - unsigned int h; + unsigned int h, h_wildcard; struct hlist_node *entry; struct xfrm_state *x, *x0, *to_put; int acquire_in_progress = 0; @@ -819,8 +819,8 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, if (best) goto found; - h = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, family); - hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h, bydst) { + h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, family); + hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h_wildcard, bydst) { if (x->props.family == family && x->props.reqid == tmpl->reqid && !(x->props.flags & XFRM_STATE_WILDRECV) && -- cgit v1.2.3-70-g09d2 From c9503e0fe052020e0294cd07d0ecd982eb7c9177 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Mon, 27 Apr 2009 05:42:24 -0700 Subject: ipv4: Limit size of route cache hash table Right now we have no upper limit on the size of the route cache hash table. On a 128GB POWER6 box it ends up as 32MB: IP route cache hash table entries: 4194304 (order: 9, 33554432 bytes) It would be nice to cap this for memory consumption reasons, but a massive hashtable also causes a significant spike when measuring OS jitter. With a 32MB hashtable and 4 million entries, rt_worker_func is taking 5 ms to complete. On another system with more memory it's taking 14 ms. Even though rt_worker_func does call cond_sched() to limit its impact, in an HPC environment we want to keep all sources of OS jitter to a minimum. With the patch applied we limit the number of entries to 512k which can still be overriden by using the rt_entries boot option: IP route cache hash table entries: 524288 (order: 6, 4194304 bytes) With this patch rt_worker_func now takes 0.460 ms on the same system. Signed-off-by: Anton Blanchard Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/route.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/ipv4/route.c b/net/ipv4/route.c index c40debe51b3..c4c60e9f068 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -3397,7 +3397,7 @@ int __init ip_rt_init(void) 0, &rt_hash_log, &rt_hash_mask, - 0); + rhash_entries ? 0 : 512 * 1024); memset(rt_hash_table, 0, (rt_hash_mask + 1) * sizeof(struct rt_hash_bucket)); rt_hash_lock_init(); -- cgit v1.2.3-70-g09d2 From bf368e4e70cd4e0f880923c44e95a4273d725ab4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 28 Apr 2009 02:24:21 -0700 Subject: net: Avoid extra wakeups of threads blocked in wait_for_packet() In 2.6.25 we added UDP mem accounting. This unfortunatly added a penalty when a frame is transmitted, since we have at TX completion time to call sock_wfree() to perform necessary memory accounting. This calls sock_def_write_space() and utimately scheduler if any thread is waiting on the socket. Thread(s) waiting for an incoming frame was scheduled, then had to sleep again as event was meaningless. (All threads waiting on a socket are using same sk_sleep anchor) This adds lot of extra wakeups and increases latencies, as noted by Christoph Lameter, and slows down softirq handler. Reference : http://marc.info/?l=linux-netdev&m=124060437012283&w=2 Fortunatly, Davide Libenzi recently added concept of keyed wakeups into kernel, and particularly for sockets (see commit 37e5540b3c9d838eb20f2ca8ea2eb8072271e403 epoll keyed wakeups: make sockets use keyed wakeups) Davide goal was to optimize epoll, but this new wakeup infrastructure can help non epoll users as well, if they care to setup an appropriate handler. This patch introduces new DEFINE_WAIT_FUNC() helper and uses it in wait_for_packet(), so that only relevant event can wakeup a thread blocked in this function. Trace of function calls from bnx2 TX completion bnx2_poll_work() is : __kfree_skb() skb_release_head_state() sock_wfree() sock_def_write_space() __wake_up_sync_key() __wake_up_common() receiver_wake_function() : Stops here since thread is waiting for an INPUT Reported-by: Christoph Lameter Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/wait.h | 6 ++++-- net/core/datagram.c | 14 +++++++++++++- 2 files changed, 17 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/include/linux/wait.h b/include/linux/wait.h index 5d631c17eae..bc024632f36 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -440,13 +440,15 @@ void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait, int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key); int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key); -#define DEFINE_WAIT(name) \ +#define DEFINE_WAIT_FUNC(name, function) \ wait_queue_t name = { \ .private = current, \ - .func = autoremove_wake_function, \ + .func = function, \ .task_list = LIST_HEAD_INIT((name).task_list), \ } +#define DEFINE_WAIT(name) DEFINE_WAIT_FUNC(name, autoremove_wake_function) + #define DEFINE_WAIT_BIT(name, word, bit) \ struct wait_bit_queue name = { \ .key = __WAIT_BIT_KEY_INITIALIZER(word, bit), \ diff --git a/net/core/datagram.c b/net/core/datagram.c index d0de644b378..b01a76abe1d 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -64,13 +64,25 @@ static inline int connection_based(struct sock *sk) return sk->sk_type == SOCK_SEQPACKET || sk->sk_type == SOCK_STREAM; } +static int receiver_wake_function(wait_queue_t *wait, unsigned mode, int sync, + void *key) +{ + unsigned long bits = (unsigned long)key; + + /* + * Avoid a wakeup if event not interesting for us + */ + if (bits && !(bits & (POLLIN | POLLERR))) + return 0; + return autoremove_wake_function(wait, mode, sync, key); +} /* * Wait for a packet.. */ static int wait_for_packet(struct sock *sk, int *err, long *timeo_p) { int error; - DEFINE_WAIT(wait); + DEFINE_WAIT_FUNC(wait, receiver_wake_function); prepare_to_wait_exclusive(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); -- cgit v1.2.3-70-g09d2 From f3784d834c71689336fa272df420b45345cb6b84 Mon Sep 17 00:00:00 2001 From: Roger Quadros Date: Thu, 23 Apr 2009 14:50:54 +0300 Subject: Bluetooth: Ensure that HCI sysfs add/del is preempt safe Use a different work_struct variables for add_conn() and del_conn() and use single work queue instead of two for adding and deleting connections. It eliminates the following error on a preemptible kernel: [ 204.358032] Unable to handle kernel NULL pointer dereference at virtual address 0000000c [ 204.370697] pgd = c0004000 [ 204.373443] [0000000c] *pgd=00000000 [ 204.378601] Internal error: Oops: 17 [#1] PREEMPT [ 204.383361] Modules linked in: vfat fat rfcomm sco l2cap sd_mod scsi_mod iphb pvr2d drm omaplfb ps [ 204.438537] CPU: 0 Not tainted (2.6.28-maemo2 #1) [ 204.443664] PC is at klist_put+0x2c/0xb4 [ 204.447601] LR is at klist_put+0x18/0xb4 [ 204.451568] pc : [] lr : [] psr: a0000113 [ 204.451568] sp : cf1b3f10 ip : cf1b3f10 fp : cf1b3f2c [ 204.463104] r10: 00000000 r9 : 00000000 r8 : bf08029c [ 204.468353] r7 : c7869200 r6 : cfbe2690 r5 : c78692c8 r4 : 00000001 [ 204.474945] r3 : 00000001 r2 : cf1b2000 r1 : 00000001 r0 : 00000000 [ 204.481506] Flags: NzCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment kernel [ 204.488861] Control: 10c5387d Table: 887fc018 DAC: 00000017 [ 204.494628] Process btdelconn (pid: 515, stack limit = 0xcf1b22e0) Signed-off-by: Roger Quadros Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 3 ++- net/bluetooth/hci_sysfs.c | 37 ++++++++++++++++--------------------- 2 files changed, 18 insertions(+), 22 deletions(-) (limited to 'net') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 01f9316b4c2..1224bba24bd 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -180,7 +180,8 @@ struct hci_conn { struct timer_list disc_timer; struct timer_list idle_timer; - struct work_struct work; + struct work_struct work_add; + struct work_struct work_del; struct device dev; diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index ed82796d4a0..b7c51082dde 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -9,8 +9,7 @@ struct class *bt_class = NULL; EXPORT_SYMBOL_GPL(bt_class); -static struct workqueue_struct *btaddconn; -static struct workqueue_struct *btdelconn; +static struct workqueue_struct *bluetooth; static inline char *link_typetostr(int type) { @@ -88,9 +87,10 @@ static struct device_type bt_link = { static void add_conn(struct work_struct *work) { - struct hci_conn *conn = container_of(work, struct hci_conn, work); + struct hci_conn *conn = container_of(work, struct hci_conn, work_add); - flush_workqueue(btdelconn); + /* ensure previous add/del is complete */ + flush_workqueue(bluetooth); if (device_add(&conn->dev) < 0) { BT_ERR("Failed to register connection device"); @@ -114,9 +114,9 @@ void hci_conn_add_sysfs(struct hci_conn *conn) device_initialize(&conn->dev); - INIT_WORK(&conn->work, add_conn); + INIT_WORK(&conn->work_add, add_conn); - queue_work(btaddconn, &conn->work); + queue_work(bluetooth, &conn->work_add); } /* @@ -131,9 +131,12 @@ static int __match_tty(struct device *dev, void *data) static void del_conn(struct work_struct *work) { - struct hci_conn *conn = container_of(work, struct hci_conn, work); + struct hci_conn *conn = container_of(work, struct hci_conn, work_del); struct hci_dev *hdev = conn->hdev; + /* ensure previous add/del is complete */ + flush_workqueue(bluetooth); + while (1) { struct device *dev; @@ -156,9 +159,9 @@ void hci_conn_del_sysfs(struct hci_conn *conn) if (!device_is_registered(&conn->dev)) return; - INIT_WORK(&conn->work, del_conn); + INIT_WORK(&conn->work_del, del_conn); - queue_work(btdelconn, &conn->work); + queue_work(bluetooth, &conn->work_del); } static inline char *host_typetostr(int type) @@ -435,20 +438,13 @@ void hci_unregister_sysfs(struct hci_dev *hdev) int __init bt_sysfs_init(void) { - btaddconn = create_singlethread_workqueue("btaddconn"); - if (!btaddconn) - return -ENOMEM; - - btdelconn = create_singlethread_workqueue("btdelconn"); - if (!btdelconn) { - destroy_workqueue(btaddconn); + bluetooth = create_singlethread_workqueue("bluetooth"); + if (!bluetooth) return -ENOMEM; - } bt_class = class_create(THIS_MODULE, "bluetooth"); if (IS_ERR(bt_class)) { - destroy_workqueue(btdelconn); - destroy_workqueue(btaddconn); + destroy_workqueue(bluetooth); return PTR_ERR(bt_class); } @@ -457,8 +453,7 @@ int __init bt_sysfs_init(void) void bt_sysfs_cleanup(void) { - destroy_workqueue(btaddconn); - destroy_workqueue(btdelconn); + destroy_workqueue(bluetooth); class_destroy(bt_class); } -- cgit v1.2.3-70-g09d2 From 052b30b0a8eec8db5b18ad49effdf2a9ba4c1e1a Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Sun, 26 Apr 2009 20:01:22 +0200 Subject: Bluetooth: Add different pairing timeout for Legacy Pairing The Bluetooth stack uses a reference counting for all established ACL links and if no user (L2CAP connection) is present, the link will be terminated to save power. The problem part is the dedicated pairing when using Legacy Pairing (Bluetooth 2.0 and before). At that point no user is present and pairing attempts will be disconnected within 10 seconds or less. In previous kernel version this was not a problem since the disconnect timeout wasn't triggered on incoming connections for the first time. However this caused issues with broken host stacks that kept the connections around after dedicated pairing. When the support for Simple Pairing got added, the link establishment procedure needed to be changed and now causes issues when using Legacy Pairing When using Simple Pairing it is possible to do a proper reference counting of ACL link users. With Legacy Pairing this is not possible since the specification is unclear in some areas and too many broken Bluetooth devices have already been deployed. So instead of trying to deal with all the broken devices, a special pairing timeout will be introduced that increases the timeout to 60 seconds when pairing is triggered. If a broken devices now puts the stack into an unforeseen state, the worst that happens is the disconnect timeout triggers after 120 seconds instead of 4 seconds. This allows successful pairings with legacy and broken devices now. Based on a report by Johan Hedberg Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 1 + include/net/bluetooth/hci_core.h | 5 +++-- net/bluetooth/hci_conn.c | 1 + net/bluetooth/hci_event.c | 36 +++++++++++++++++++++++++++++++++++- 4 files changed, 40 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index f69f015bbcc..ed3aea1605e 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -101,6 +101,7 @@ enum { /* HCI timeouts */ #define HCI_CONNECT_TIMEOUT (40000) /* 40 seconds */ #define HCI_DISCONN_TIMEOUT (2000) /* 2 seconds */ +#define HCI_PAIRING_TIMEOUT (60000) /* 60 seconds */ #define HCI_IDLE_TIMEOUT (6000) /* 6 seconds */ #define HCI_INIT_TIMEOUT (10000) /* 10 seconds */ diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 1224bba24bd..be5bd713d2c 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -171,6 +171,7 @@ struct hci_conn { __u8 auth_type; __u8 sec_level; __u8 power_save; + __u16 disc_timeout; unsigned long pend; unsigned int sent; @@ -349,9 +350,9 @@ static inline void hci_conn_put(struct hci_conn *conn) if (conn->type == ACL_LINK) { del_timer(&conn->idle_timer); if (conn->state == BT_CONNECTED) { - timeo = msecs_to_jiffies(HCI_DISCONN_TIMEOUT); + timeo = msecs_to_jiffies(conn->disc_timeout); if (!conn->out) - timeo *= 5; + timeo *= 2; } else timeo = msecs_to_jiffies(10); } else diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 1181db08d9d..75ebbe2221a 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -215,6 +215,7 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst) conn->state = BT_OPEN; conn->power_save = 1; + conn->disc_timeout = HCI_DISCONN_TIMEOUT; switch (type) { case ACL_LINK: diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 15f40ea8d54..4e7cb88e5da 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -883,6 +883,7 @@ static inline void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *s if (conn->type == ACL_LINK) { conn->state = BT_CONFIG; hci_conn_hold(conn); + conn->disc_timeout = HCI_DISCONN_TIMEOUT; } else conn->state = BT_CONNECTED; @@ -1063,9 +1064,14 @@ static inline void hci_auth_complete_evt(struct hci_dev *hdev, struct sk_buff *s hci_proto_connect_cfm(conn, ev->status); hci_conn_put(conn); } - } else + } else { hci_auth_cfm(conn, ev->status); + hci_conn_hold(conn); + conn->disc_timeout = HCI_DISCONN_TIMEOUT; + hci_conn_put(conn); + } + if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->pend)) { if (!ev->status) { struct hci_cp_set_conn_encrypt cp; @@ -1479,7 +1485,21 @@ static inline void hci_mode_change_evt(struct hci_dev *hdev, struct sk_buff *skb static inline void hci_pin_code_request_evt(struct hci_dev *hdev, struct sk_buff *skb) { + struct hci_ev_pin_code_req *ev = (void *) skb->data; + struct hci_conn *conn; + BT_DBG("%s", hdev->name); + + hci_dev_lock(hdev); + + conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); + if (conn) { + hci_conn_hold(conn); + conn->disc_timeout = HCI_PAIRING_TIMEOUT; + hci_conn_put(conn); + } + + hci_dev_unlock(hdev); } static inline void hci_link_key_request_evt(struct hci_dev *hdev, struct sk_buff *skb) @@ -1489,7 +1509,21 @@ static inline void hci_link_key_request_evt(struct hci_dev *hdev, struct sk_buff static inline void hci_link_key_notify_evt(struct hci_dev *hdev, struct sk_buff *skb) { + struct hci_ev_link_key_notify *ev = (void *) skb->data; + struct hci_conn *conn; + BT_DBG("%s", hdev->name); + + hci_dev_lock(hdev); + + conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); + if (conn) { + hci_conn_hold(conn); + conn->disc_timeout = HCI_DISCONN_TIMEOUT; + hci_conn_put(conn); + } + + hci_dev_unlock(hdev); } static inline void hci_clock_offset_evt(struct hci_dev *hdev, struct sk_buff *skb) -- cgit v1.2.3-70-g09d2 From 3fdca1e1370ffe89980927cdef0583bebcd8caaf Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Tue, 28 Apr 2009 09:04:55 -0700 Subject: Bluetooth: Fix connection establishment with low security requirement The Bluetooth 2.1 specification introduced four different security modes that can be mapped using Legacy Pairing and Simple Pairing. With the usage of Simple Pairing it is required that all connections (except the ones for SDP) are encrypted. So even the low security requirement mandates an encrypted connection when using Simple Pairing. When using Legacy Pairing (for Bluetooth 2.0 devices and older) this is not required since it causes interoperability issues. To support this properly the low security requirement translates into different host controller transactions depending if Simple Pairing is supported or not. However in case of Simple Pairing the command to switch on encryption after a successful authentication is not triggered for the low security mode. This patch fixes this and actually makes the logic to differentiate between Simple Pairing and Legacy Pairing a lot simpler. Based on a report by Ville Tervo Signed-off-by: Marcel Holtmann --- net/bluetooth/hci_conn.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'net') diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 75ebbe2221a..375f4b4f7f7 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -425,12 +425,9 @@ int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) if (sec_level == BT_SECURITY_SDP) return 1; - if (sec_level == BT_SECURITY_LOW) { - if (conn->ssp_mode > 0 && conn->hdev->ssp_mode > 0) - return hci_conn_auth(conn, sec_level, auth_type); - else - return 1; - } + if (sec_level == BT_SECURITY_LOW && + (!conn->ssp_mode || !conn->hdev->ssp_mode)) + return 1; if (conn->link_mode & HCI_LM_ENCRYPT) return hci_conn_auth(conn, sec_level, auth_type); -- cgit v1.2.3-70-g09d2 From 942e4a2bd680c606af0211e64eb216be2e19bf61 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Tue, 28 Apr 2009 22:36:33 -0700 Subject: netfilter: revised locking for x_tables The x_tables are organized with a table structure and a per-cpu copies of the counters and rules. On older kernels there was a reader/writer lock per table which was a performance bottleneck. In 2.6.30-rc, this was converted to use RCU and the counters/rules which solved the performance problems for do_table but made replacing rules much slower because of the necessary RCU grace period. This version uses a per-cpu set of spinlocks and counters to allow to table processing to proceed without the cache thrashing of a global reader lock and keeps the same performance for table updates. Signed-off-by: Stephen Hemminger Acked-by: Linus Torvalds Signed-off-by: David S. Miller --- include/linux/netfilter/x_tables.h | 73 +++++++++++++++++++-- net/ipv4/netfilter/arp_tables.c | 125 +++++++++++------------------------- net/ipv4/netfilter/ip_tables.c | 126 +++++++++++-------------------------- net/ipv6/netfilter/ip6_tables.c | 123 +++++++++++------------------------- net/netfilter/x_tables.c | 53 ++++++++-------- 5 files changed, 204 insertions(+), 296 deletions(-) (limited to 'net') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 7b1a652066c..1b2e43502ef 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -354,9 +354,6 @@ struct xt_table /* What hooks you will enter on */ unsigned int valid_hooks; - /* Lock for the curtain */ - struct mutex lock; - /* Man behind the curtain... */ struct xt_table_info *private; @@ -434,8 +431,74 @@ extern void xt_proto_fini(struct net *net, u_int8_t af); extern struct xt_table_info *xt_alloc_table_info(unsigned int size); extern void xt_free_table_info(struct xt_table_info *info); -extern void xt_table_entry_swap_rcu(struct xt_table_info *old, - struct xt_table_info *new); + +/* + * Per-CPU spinlock associated with per-cpu table entries, and + * with a counter for the "reading" side that allows a recursive + * reader to avoid taking the lock and deadlocking. + * + * "reading" is used by ip/arp/ip6 tables rule processing which runs per-cpu. + * It needs to ensure that the rules are not being changed while the packet + * is being processed. In some cases, the read lock will be acquired + * twice on the same CPU; this is okay because of the count. + * + * "writing" is used when reading counters. + * During replace any readers that are using the old tables have to complete + * before freeing the old table. This is handled by the write locking + * necessary for reading the counters. + */ +struct xt_info_lock { + spinlock_t lock; + unsigned char readers; +}; +DECLARE_PER_CPU(struct xt_info_lock, xt_info_locks); + +/* + * Note: we need to ensure that preemption is disabled before acquiring + * the per-cpu-variable, so we do it as a two step process rather than + * using "spin_lock_bh()". + * + * We _also_ need to disable bottom half processing before updating our + * nesting count, to make sure that the only kind of re-entrancy is this + * code being called by itself: since the count+lock is not an atomic + * operation, we can allow no races. + * + * _Only_ that special combination of being per-cpu and never getting + * re-entered asynchronously means that the count is safe. + */ +static inline void xt_info_rdlock_bh(void) +{ + struct xt_info_lock *lock; + + local_bh_disable(); + lock = &__get_cpu_var(xt_info_locks); + if (!lock->readers++) + spin_lock(&lock->lock); +} + +static inline void xt_info_rdunlock_bh(void) +{ + struct xt_info_lock *lock = &__get_cpu_var(xt_info_locks); + + if (!--lock->readers) + spin_unlock(&lock->lock); + local_bh_enable(); +} + +/* + * The "writer" side needs to get exclusive access to the lock, + * regardless of readers. This must be called with bottom half + * processing (and thus also preemption) disabled. + */ +static inline void xt_info_wrlock(unsigned int cpu) +{ + spin_lock(&per_cpu(xt_info_locks, cpu).lock); +} + +static inline void xt_info_wrunlock(unsigned int cpu) +{ + spin_unlock(&per_cpu(xt_info_locks, cpu).lock); +} /* * This helper is performance critical and must be inlined diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 5ba533d234d..831fe1879dc 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -253,9 +253,9 @@ unsigned int arpt_do_table(struct sk_buff *skb, indev = in ? in->name : nulldevname; outdev = out ? out->name : nulldevname; - rcu_read_lock_bh(); - private = rcu_dereference(table->private); - table_base = rcu_dereference(private->entries[smp_processor_id()]); + xt_info_rdlock_bh(); + private = table->private; + table_base = private->entries[smp_processor_id()]; e = get_entry(table_base, private->hook_entry[hook]); back = get_entry(table_base, private->underflow[hook]); @@ -273,6 +273,7 @@ unsigned int arpt_do_table(struct sk_buff *skb, hdr_len = sizeof(*arp) + (2 * sizeof(struct in_addr)) + (2 * skb->dev->addr_len); + ADD_COUNTER(e->counters, hdr_len, 1); t = arpt_get_target(e); @@ -328,8 +329,7 @@ unsigned int arpt_do_table(struct sk_buff *skb, e = (void *)e + e->next_offset; } } while (!hotdrop); - - rcu_read_unlock_bh(); + xt_info_rdunlock_bh(); if (hotdrop) return NF_DROP; @@ -711,9 +711,12 @@ static void get_counters(const struct xt_table_info *t, /* Instead of clearing (by a previous call to memset()) * the counters and using adds, we set the counters * with data used by 'current' CPU - * We dont care about preemption here. + * + * Bottom half has to be disabled to prevent deadlock + * if new softirq were to run and call ipt_do_table */ - curcpu = raw_smp_processor_id(); + local_bh_disable(); + curcpu = smp_processor_id(); i = 0; ARPT_ENTRY_ITERATE(t->entries[curcpu], @@ -726,73 +729,22 @@ static void get_counters(const struct xt_table_info *t, if (cpu == curcpu) continue; i = 0; + xt_info_wrlock(cpu); ARPT_ENTRY_ITERATE(t->entries[cpu], t->size, add_entry_to_counter, counters, &i); + xt_info_wrunlock(cpu); } -} - - -/* We're lazy, and add to the first CPU; overflow works its fey magic - * and everything is OK. */ -static int -add_counter_to_entry(struct arpt_entry *e, - const struct xt_counters addme[], - unsigned int *i) -{ - ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt); - - (*i)++; - return 0; -} - -/* Take values from counters and add them back onto the current cpu */ -static void put_counters(struct xt_table_info *t, - const struct xt_counters counters[]) -{ - unsigned int i, cpu; - - local_bh_disable(); - cpu = smp_processor_id(); - i = 0; - ARPT_ENTRY_ITERATE(t->entries[cpu], - t->size, - add_counter_to_entry, - counters, - &i); local_bh_enable(); } -static inline int -zero_entry_counter(struct arpt_entry *e, void *arg) -{ - e->counters.bcnt = 0; - e->counters.pcnt = 0; - return 0; -} - -static void -clone_counters(struct xt_table_info *newinfo, const struct xt_table_info *info) -{ - unsigned int cpu; - const void *loc_cpu_entry = info->entries[raw_smp_processor_id()]; - - memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); - for_each_possible_cpu(cpu) { - memcpy(newinfo->entries[cpu], loc_cpu_entry, info->size); - ARPT_ENTRY_ITERATE(newinfo->entries[cpu], newinfo->size, - zero_entry_counter, NULL); - } -} - static struct xt_counters *alloc_counters(struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; struct xt_table_info *private = table->private; - struct xt_table_info *info; /* We need atomic snapshot of counters: rest doesn't change * (other than comefrom, which userspace doesn't care @@ -802,30 +754,11 @@ static struct xt_counters *alloc_counters(struct xt_table *table) counters = vmalloc_node(countersize, numa_node_id()); if (counters == NULL) - goto nomem; - - info = xt_alloc_table_info(private->size); - if (!info) - goto free_counters; - - clone_counters(info, private); - - mutex_lock(&table->lock); - xt_table_entry_swap_rcu(private, info); - synchronize_net(); /* Wait until smoke has cleared */ + return ERR_PTR(-ENOMEM); - get_counters(info, counters); - put_counters(private, counters); - mutex_unlock(&table->lock); - - xt_free_table_info(info); + get_counters(private, counters); return counters; - - free_counters: - vfree(counters); - nomem: - return ERR_PTR(-ENOMEM); } static int copy_entries_to_user(unsigned int total_size, @@ -1094,8 +1027,9 @@ static int __do_replace(struct net *net, const char *name, (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); - /* Get the old counters. */ + /* Get the old counters, and synchronize with replace */ get_counters(oldinfo, counters); + /* Decrease module usage counts and free resource */ loc_cpu_old_entry = oldinfo->entries[raw_smp_processor_id()]; ARPT_ENTRY_ITERATE(loc_cpu_old_entry, oldinfo->size, cleanup_entry, @@ -1165,10 +1099,23 @@ static int do_replace(struct net *net, void __user *user, unsigned int len) return ret; } +/* We're lazy, and add to the first CPU; overflow works its fey magic + * and everything is OK. */ +static int +add_counter_to_entry(struct arpt_entry *e, + const struct xt_counters addme[], + unsigned int *i) +{ + ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt); + + (*i)++; + return 0; +} + static int do_add_counters(struct net *net, void __user *user, unsigned int len, int compat) { - unsigned int i; + unsigned int i, curcpu; struct xt_counters_info tmp; struct xt_counters *paddc; unsigned int num_counters; @@ -1224,26 +1171,26 @@ static int do_add_counters(struct net *net, void __user *user, unsigned int len, goto free; } - mutex_lock(&t->lock); + local_bh_disable(); private = t->private; if (private->number != num_counters) { ret = -EINVAL; goto unlock_up_free; } - preempt_disable(); i = 0; /* Choose the copy that is on our node */ - loc_cpu_entry = private->entries[smp_processor_id()]; + curcpu = smp_processor_id(); + loc_cpu_entry = private->entries[curcpu]; + xt_info_wrlock(curcpu); ARPT_ENTRY_ITERATE(loc_cpu_entry, private->size, add_counter_to_entry, paddc, &i); - preempt_enable(); + xt_info_wrunlock(curcpu); unlock_up_free: - mutex_unlock(&t->lock); - + local_bh_enable(); xt_table_unlock(t); module_put(t->me); free: diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 810c0b62c7d..2ec8d7290c4 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -338,10 +338,9 @@ ipt_do_table(struct sk_buff *skb, tgpar.hooknum = hook; IP_NF_ASSERT(table->valid_hooks & (1 << hook)); - - rcu_read_lock_bh(); - private = rcu_dereference(table->private); - table_base = rcu_dereference(private->entries[smp_processor_id()]); + xt_info_rdlock_bh(); + private = table->private; + table_base = private->entries[smp_processor_id()]; e = get_entry(table_base, private->hook_entry[hook]); @@ -436,8 +435,7 @@ ipt_do_table(struct sk_buff *skb, e = (void *)e + e->next_offset; } } while (!hotdrop); - - rcu_read_unlock_bh(); + xt_info_rdunlock_bh(); #ifdef DEBUG_ALLOW_ALL return NF_ACCEPT; @@ -896,10 +894,13 @@ get_counters(const struct xt_table_info *t, /* Instead of clearing (by a previous call to memset()) * the counters and using adds, we set the counters - * with data used by 'current' CPU - * We dont care about preemption here. + * with data used by 'current' CPU. + * + * Bottom half has to be disabled to prevent deadlock + * if new softirq were to run and call ipt_do_table */ - curcpu = raw_smp_processor_id(); + local_bh_disable(); + curcpu = smp_processor_id(); i = 0; IPT_ENTRY_ITERATE(t->entries[curcpu], @@ -912,74 +913,22 @@ get_counters(const struct xt_table_info *t, if (cpu == curcpu) continue; i = 0; + xt_info_wrlock(cpu); IPT_ENTRY_ITERATE(t->entries[cpu], t->size, add_entry_to_counter, counters, &i); + xt_info_wrunlock(cpu); } - -} - -/* We're lazy, and add to the first CPU; overflow works its fey magic - * and everything is OK. */ -static int -add_counter_to_entry(struct ipt_entry *e, - const struct xt_counters addme[], - unsigned int *i) -{ - ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt); - - (*i)++; - return 0; -} - -/* Take values from counters and add them back onto the current cpu */ -static void put_counters(struct xt_table_info *t, - const struct xt_counters counters[]) -{ - unsigned int i, cpu; - - local_bh_disable(); - cpu = smp_processor_id(); - i = 0; - IPT_ENTRY_ITERATE(t->entries[cpu], - t->size, - add_counter_to_entry, - counters, - &i); local_bh_enable(); } - -static inline int -zero_entry_counter(struct ipt_entry *e, void *arg) -{ - e->counters.bcnt = 0; - e->counters.pcnt = 0; - return 0; -} - -static void -clone_counters(struct xt_table_info *newinfo, const struct xt_table_info *info) -{ - unsigned int cpu; - const void *loc_cpu_entry = info->entries[raw_smp_processor_id()]; - - memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); - for_each_possible_cpu(cpu) { - memcpy(newinfo->entries[cpu], loc_cpu_entry, info->size); - IPT_ENTRY_ITERATE(newinfo->entries[cpu], newinfo->size, - zero_entry_counter, NULL); - } -} - static struct xt_counters * alloc_counters(struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; struct xt_table_info *private = table->private; - struct xt_table_info *info; /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care @@ -988,30 +937,11 @@ static struct xt_counters * alloc_counters(struct xt_table *table) counters = vmalloc_node(countersize, numa_node_id()); if (counters == NULL) - goto nomem; + return ERR_PTR(-ENOMEM); - info = xt_alloc_table_info(private->size); - if (!info) - goto free_counters; - - clone_counters(info, private); - - mutex_lock(&table->lock); - xt_table_entry_swap_rcu(private, info); - synchronize_net(); /* Wait until smoke has cleared */ - - get_counters(info, counters); - put_counters(private, counters); - mutex_unlock(&table->lock); - - xt_free_table_info(info); + get_counters(private, counters); return counters; - - free_counters: - vfree(counters); - nomem: - return ERR_PTR(-ENOMEM); } static int @@ -1306,8 +1236,9 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); - /* Get the old counters. */ + /* Get the old counters, and synchronize with replace */ get_counters(oldinfo, counters); + /* Decrease module usage counts and free resource */ loc_cpu_old_entry = oldinfo->entries[raw_smp_processor_id()]; IPT_ENTRY_ITERATE(loc_cpu_old_entry, oldinfo->size, cleanup_entry, @@ -1377,11 +1308,23 @@ do_replace(struct net *net, void __user *user, unsigned int len) return ret; } +/* We're lazy, and add to the first CPU; overflow works its fey magic + * and everything is OK. */ +static int +add_counter_to_entry(struct ipt_entry *e, + const struct xt_counters addme[], + unsigned int *i) +{ + ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt); + + (*i)++; + return 0; +} static int do_add_counters(struct net *net, void __user *user, unsigned int len, int compat) { - unsigned int i; + unsigned int i, curcpu; struct xt_counters_info tmp; struct xt_counters *paddc; unsigned int num_counters; @@ -1437,25 +1380,26 @@ do_add_counters(struct net *net, void __user *user, unsigned int len, int compat goto free; } - mutex_lock(&t->lock); + local_bh_disable(); private = t->private; if (private->number != num_counters) { ret = -EINVAL; goto unlock_up_free; } - preempt_disable(); i = 0; /* Choose the copy that is on our node */ - loc_cpu_entry = private->entries[raw_smp_processor_id()]; + curcpu = smp_processor_id(); + loc_cpu_entry = private->entries[curcpu]; + xt_info_wrlock(curcpu); IPT_ENTRY_ITERATE(loc_cpu_entry, private->size, add_counter_to_entry, paddc, &i); - preempt_enable(); + xt_info_wrunlock(curcpu); unlock_up_free: - mutex_unlock(&t->lock); + local_bh_enable(); xt_table_unlock(t); module_put(t->me); free: diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 800ae854247..219e165aea1 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -365,9 +365,9 @@ ip6t_do_table(struct sk_buff *skb, IP_NF_ASSERT(table->valid_hooks & (1 << hook)); - rcu_read_lock_bh(); - private = rcu_dereference(table->private); - table_base = rcu_dereference(private->entries[smp_processor_id()]); + xt_info_rdlock_bh(); + private = table->private; + table_base = private->entries[smp_processor_id()]; e = get_entry(table_base, private->hook_entry[hook]); @@ -466,7 +466,7 @@ ip6t_do_table(struct sk_buff *skb, #ifdef CONFIG_NETFILTER_DEBUG ((struct ip6t_entry *)table_base)->comefrom = NETFILTER_LINK_POISON; #endif - rcu_read_unlock_bh(); + xt_info_rdunlock_bh(); #ifdef DEBUG_ALLOW_ALL return NF_ACCEPT; @@ -926,9 +926,12 @@ get_counters(const struct xt_table_info *t, /* Instead of clearing (by a previous call to memset()) * the counters and using adds, we set the counters * with data used by 'current' CPU - * We dont care about preemption here. + * + * Bottom half has to be disabled to prevent deadlock + * if new softirq were to run and call ipt_do_table */ - curcpu = raw_smp_processor_id(); + local_bh_disable(); + curcpu = smp_processor_id(); i = 0; IP6T_ENTRY_ITERATE(t->entries[curcpu], @@ -941,72 +944,22 @@ get_counters(const struct xt_table_info *t, if (cpu == curcpu) continue; i = 0; + xt_info_wrlock(cpu); IP6T_ENTRY_ITERATE(t->entries[cpu], t->size, add_entry_to_counter, counters, &i); + xt_info_wrunlock(cpu); } -} - -/* We're lazy, and add to the first CPU; overflow works its fey magic - * and everything is OK. */ -static int -add_counter_to_entry(struct ip6t_entry *e, - const struct xt_counters addme[], - unsigned int *i) -{ - ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt); - - (*i)++; - return 0; -} - -/* Take values from counters and add them back onto the current cpu */ -static void put_counters(struct xt_table_info *t, - const struct xt_counters counters[]) -{ - unsigned int i, cpu; - - local_bh_disable(); - cpu = smp_processor_id(); - i = 0; - IP6T_ENTRY_ITERATE(t->entries[cpu], - t->size, - add_counter_to_entry, - counters, - &i); local_bh_enable(); } -static inline int -zero_entry_counter(struct ip6t_entry *e, void *arg) -{ - e->counters.bcnt = 0; - e->counters.pcnt = 0; - return 0; -} - -static void -clone_counters(struct xt_table_info *newinfo, const struct xt_table_info *info) -{ - unsigned int cpu; - const void *loc_cpu_entry = info->entries[raw_smp_processor_id()]; - - memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); - for_each_possible_cpu(cpu) { - memcpy(newinfo->entries[cpu], loc_cpu_entry, info->size); - IP6T_ENTRY_ITERATE(newinfo->entries[cpu], newinfo->size, - zero_entry_counter, NULL); - } -} - static struct xt_counters *alloc_counters(struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; struct xt_table_info *private = table->private; - struct xt_table_info *info; /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care @@ -1015,30 +968,11 @@ static struct xt_counters *alloc_counters(struct xt_table *table) counters = vmalloc_node(countersize, numa_node_id()); if (counters == NULL) - goto nomem; + return ERR_PTR(-ENOMEM); - info = xt_alloc_table_info(private->size); - if (!info) - goto free_counters; - - clone_counters(info, private); - - mutex_lock(&table->lock); - xt_table_entry_swap_rcu(private, info); - synchronize_net(); /* Wait until smoke has cleared */ - - get_counters(info, counters); - put_counters(private, counters); - mutex_unlock(&table->lock); - - xt_free_table_info(info); + get_counters(private, counters); return counters; - - free_counters: - vfree(counters); - nomem: - return ERR_PTR(-ENOMEM); } static int @@ -1334,8 +1268,9 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); - /* Get the old counters. */ + /* Get the old counters, and synchronize with replace */ get_counters(oldinfo, counters); + /* Decrease module usage counts and free resource */ loc_cpu_old_entry = oldinfo->entries[raw_smp_processor_id()]; IP6T_ENTRY_ITERATE(loc_cpu_old_entry, oldinfo->size, cleanup_entry, @@ -1405,11 +1340,24 @@ do_replace(struct net *net, void __user *user, unsigned int len) return ret; } +/* We're lazy, and add to the first CPU; overflow works its fey magic + * and everything is OK. */ +static int +add_counter_to_entry(struct ip6t_entry *e, + const struct xt_counters addme[], + unsigned int *i) +{ + ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt); + + (*i)++; + return 0; +} + static int do_add_counters(struct net *net, void __user *user, unsigned int len, int compat) { - unsigned int i; + unsigned int i, curcpu; struct xt_counters_info tmp; struct xt_counters *paddc; unsigned int num_counters; @@ -1465,25 +1413,28 @@ do_add_counters(struct net *net, void __user *user, unsigned int len, goto free; } - mutex_lock(&t->lock); + + local_bh_disable(); private = t->private; if (private->number != num_counters) { ret = -EINVAL; goto unlock_up_free; } - preempt_disable(); i = 0; /* Choose the copy that is on our node */ - loc_cpu_entry = private->entries[raw_smp_processor_id()]; + curcpu = smp_processor_id(); + xt_info_wrlock(curcpu); + loc_cpu_entry = private->entries[curcpu]; IP6T_ENTRY_ITERATE(loc_cpu_entry, private->size, add_counter_to_entry, paddc, &i); - preempt_enable(); + xt_info_wrunlock(curcpu); + unlock_up_free: - mutex_unlock(&t->lock); + local_bh_enable(); xt_table_unlock(t); module_put(t->me); free: diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 509a95621f9..150e5cf62f8 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -625,20 +625,6 @@ void xt_free_table_info(struct xt_table_info *info) } EXPORT_SYMBOL(xt_free_table_info); -void xt_table_entry_swap_rcu(struct xt_table_info *oldinfo, - struct xt_table_info *newinfo) -{ - unsigned int cpu; - - for_each_possible_cpu(cpu) { - void *p = oldinfo->entries[cpu]; - rcu_assign_pointer(oldinfo->entries[cpu], newinfo->entries[cpu]); - newinfo->entries[cpu] = p; - } - -} -EXPORT_SYMBOL_GPL(xt_table_entry_swap_rcu); - /* Find table by name, grabs mutex & ref. Returns ERR_PTR() on error. */ struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af, const char *name) @@ -676,32 +662,43 @@ void xt_compat_unlock(u_int8_t af) EXPORT_SYMBOL_GPL(xt_compat_unlock); #endif +DEFINE_PER_CPU(struct xt_info_lock, xt_info_locks); +EXPORT_PER_CPU_SYMBOL_GPL(xt_info_locks); + + struct xt_table_info * xt_replace_table(struct xt_table *table, unsigned int num_counters, struct xt_table_info *newinfo, int *error) { - struct xt_table_info *oldinfo, *private; + struct xt_table_info *private; /* Do the substitution. */ - mutex_lock(&table->lock); + local_bh_disable(); private = table->private; + /* Check inside lock: is the old number correct? */ if (num_counters != private->number) { duprintf("num_counters != table->private->number (%u/%u)\n", num_counters, private->number); - mutex_unlock(&table->lock); + local_bh_enable(); *error = -EAGAIN; return NULL; } - oldinfo = private; - rcu_assign_pointer(table->private, newinfo); - newinfo->initial_entries = oldinfo->initial_entries; - mutex_unlock(&table->lock); - synchronize_net(); - return oldinfo; + table->private = newinfo; + newinfo->initial_entries = private->initial_entries; + + /* + * Even though table entries have now been swapped, other CPU's + * may still be using the old entries. This is okay, because + * resynchronization happens because of the locking done + * during the get_counters() routine. + */ + local_bh_enable(); + + return private; } EXPORT_SYMBOL_GPL(xt_replace_table); @@ -734,7 +731,6 @@ struct xt_table *xt_register_table(struct net *net, struct xt_table *table, /* Simplifies replace_table code. */ table->private = bootstrap; - mutex_init(&table->lock); if (!xt_replace_table(table, 0, newinfo, &ret)) goto unlock; @@ -1147,7 +1143,14 @@ static struct pernet_operations xt_net_ops = { static int __init xt_init(void) { - int i, rv; + unsigned int i; + int rv; + + for_each_possible_cpu(i) { + struct xt_info_lock *lock = &per_cpu(xt_info_locks, i); + spin_lock_init(&lock->lock); + lock->readers = 0; + } xt = kmalloc(sizeof(struct xt_af) * NFPROTO_NUMPROTO, GFP_KERNEL); if (!xt) -- cgit v1.2.3-70-g09d2