From 140ee9603c753ce11fc3088c1988a77e92183f9b Mon Sep 17 00:00:00 2001 From: Gui Jianfeng Date: Wed, 5 Mar 2008 13:43:32 -0800 Subject: SCTP: Fix chunk parameter processing bug If an address family is not listed in "Supported Address Types" parameter(INIT Chunk), but the packet is sent by that family, this address family should be considered as supported by peer. Otherwise, an error condition will occur. For instance, if kernel receives an IPV6 SCTP INIT chunk with "Support Address Types" parameter which indicates just supporting IPV4 Address family. Kernel will reply an IPV6 SCTP INIT ACK packet, but the source ipv6 address in ipv6 header will be vacant. This is not correct. refer to RFC4460 as following: IMPLEMENTATION NOTE: If an SCTP endpoint lists in the 'Supported Address Types' parameter either IPv4 or IPv6, but uses the other family for sending the packet containing the INIT chunk, or if it also lists addresses of the other family in the INIT chunk, then the address family that is not listed in the 'Supported Address Types' parameter SHOULD also be considered as supported by the receiver of the INIT chunk. The receiver of the INIT chunk SHOULD NOT respond with any kind of error indication. Here is a fix to comply to RFC. Signed-off-by: Gui Jianfeng Acked-by: Vlad Yasevich Signed-off-by: David S. Miller --- net/sctp/sm_make_chunk.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'net') diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index e45be4e3f80d..578630e8e00d 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2375,6 +2375,14 @@ static int sctp_process_param(struct sctp_association *asoc, asoc->peer.ipv4_address = 0; asoc->peer.ipv6_address = 0; + /* Assume that peer supports the address family + * by which it sends a packet. + */ + if (peer_addr->sa.sa_family == AF_INET6) + asoc->peer.ipv6_address = 1; + else if (peer_addr->sa.sa_family == AF_INET) + asoc->peer.ipv4_address = 1; + /* Cycle through address types; avoid divide by 0. */ sat = ntohs(param.p->length) - sizeof(sctp_paramhdr_t); if (sat) -- cgit v1.2.3 From 219b99a9edab4fdc478c819acb38f4a592dffd7d Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Wed, 5 Mar 2008 13:44:46 -0800 Subject: [SCTP]: Bring MAX_BURST socket option into ietf API extension compliance Brings max_burst socket option set/get into line with the latest ietf socket extensions api draft, while maintaining backwards compatibility. Signed-off-by: Neil Horman Signed-off-by: Vlad Yasevich Signed-off-by: David S. Miller --- net/sctp/socket.c | 73 +++++++++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 60 insertions(+), 13 deletions(-) (limited to 'net') diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 939892691a26..d994d822900d 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2933,17 +2933,39 @@ static int sctp_setsockopt_maxburst(struct sock *sk, char __user *optval, int optlen) { + struct sctp_assoc_value params; + struct sctp_sock *sp; + struct sctp_association *asoc; int val; + int assoc_id = 0; - if (optlen != sizeof(int)) + if (optlen < sizeof(int)) return -EINVAL; - if (get_user(val, (int __user *)optval)) - return -EFAULT; - if (val < 0) + if (optlen == sizeof(int)) { + printk(KERN_WARNING + "SCTP: Use of int in max_burst socket option deprecated\n"); + printk(KERN_WARNING + "SCTP: Use struct sctp_assoc_value instead\n"); + if (copy_from_user(&val, optval, optlen)) + return -EFAULT; + } else if (optlen == sizeof(struct sctp_assoc_value)) { + if (copy_from_user(¶ms, optval, optlen)) + return -EFAULT; + val = params.assoc_value; + assoc_id = params.assoc_id; + } else return -EINVAL; - sctp_sk(sk)->max_burst = val; + sp = sctp_sk(sk); + + if (assoc_id != 0) { + asoc = sctp_id2assoc(sk, assoc_id); + if (!asoc) + return -EINVAL; + asoc->max_burst = val; + } else + sp->max_burst = val; return 0; } @@ -5005,20 +5027,45 @@ static int sctp_getsockopt_maxburst(struct sock *sk, int len, char __user *optval, int __user *optlen) { - int val; + struct sctp_assoc_value params; + struct sctp_sock *sp; + struct sctp_association *asoc; if (len < sizeof(int)) return -EINVAL; - len = sizeof(int); + if (len == sizeof(int)) { + printk(KERN_WARNING + "SCTP: Use of int in max_burst socket option deprecated\n"); + printk(KERN_WARNING + "SCTP: Use struct sctp_assoc_value instead\n"); + params.assoc_id = 0; + } else if (len == sizeof (struct sctp_assoc_value)) { + if (copy_from_user(¶ms, optval, len)) + return -EFAULT; + } else + return -EINVAL; - val = sctp_sk(sk)->max_burst; - if (put_user(len, optlen)) - return -EFAULT; - if (copy_to_user(optval, &val, len)) - return -EFAULT; + sp = sctp_sk(sk); + + if (params.assoc_id != 0) { + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc) + return -EINVAL; + params.assoc_value = asoc->max_burst; + } else + params.assoc_value = sp->max_burst; + + if (len == sizeof(int)) { + if (copy_to_user(optval, ¶ms.assoc_value, len)) + return -EFAULT; + } else { + if (copy_to_user(optval, ¶ms, len)) + return -EFAULT; + } + + return 0; - return -ENOTSUPP; } static int sctp_getsockopt_hmac_ident(struct sock *sk, int len, -- cgit v1.2.3 From 147e2d59833e994cc99341806a88b9e59be41391 Mon Sep 17 00:00:00 2001 From: Dave Young Date: Wed, 5 Mar 2008 18:45:59 -0800 Subject: bluetooth: hci_core: defer hci_unregister_sysfs() Alon Bar-Lev reports: Feb 16 23:41:33 alon1 usb 3-1: configuration #1 chosen from 1 choice Feb 16 23:41:33 alon1 BUG: unable to handle kernel NULL pointer dereference at virtual address 00000008 Feb 16 23:41:33 alon1 printing eip: c01b2db6 *pde = 00000000 Feb 16 23:41:33 alon1 Oops: 0000 [#1] PREEMPT Feb 16 23:41:33 alon1 Modules linked in: ppp_deflate zlib_deflate zlib_inflate bsd_comp ppp_async rfcomm l2cap hci_usb vmnet(P) vmmon(P) tun radeon drm autofs4 ipv6 aes_generic crypto_algapi ieee80211_crypt_ccmp nf_nat_irc nf_nat_ftp nf_conntrack_irc nf_conntrack_ftp ipt_MASQUERADE iptable_nat nf_nat ipt_REJECT xt_tcpudp ipt_LOG xt_limit xt_state nf_conntrack_ipv4 nf_conntrack iptable_filter ip_tables x_tables snd_pcm_oss snd_mixer_oss snd_seq_dummy snd_seq_oss snd_seq_midi_event snd_seq snd_seq_device bluetooth ppp_generic slhc ioatdma dca cfq_iosched cpufreq_powersave cpufreq_ondemand cpufreq_conservative acpi_cpufreq freq_table uinput fan af_packet nls_cp1255 nls_iso8859_1 nls_utf8 nls_base pcmcia snd_intel8x0 snd_ac97_codec ac97_bus snd_pcm nsc_ircc snd_timer ipw2200 thinkpad_acpi irda snd ehci_hcd yenta_socket uhci_hcd psmouse ieee80211 soundcore intel_agp hwmon rsrc_nonstatic pcspkr e1000 crc_ccitt snd_page_alloc i2c_i801 ieee80211_crypt pcmcia_core agpgart thermal bat! tery nvram rtc sr_mod ac sg firmware_class button processor cdrom unix usbcore evdev ext3 jbd ext2 mbcache loop ata_piix libata sd_mod scsi_mod Feb 16 23:41:33 alon1 Feb 16 23:41:33 alon1 Pid: 4, comm: events/0 Tainted: P (2.6.24-gentoo-r2 #1) Feb 16 23:41:33 alon1 EIP: 0060:[] EFLAGS: 00010282 CPU: 0 Feb 16 23:41:33 alon1 EIP is at sysfs_get_dentry+0x26/0x80 Feb 16 23:41:33 alon1 EAX: 00000000 EBX: 00000000 ECX: 00000000 EDX: f48a2210 Feb 16 23:41:33 alon1 ESI: f72eb900 EDI: f4803ae0 EBP: f4803ae0 ESP: f7c49efc Feb 16 23:41:33 alon1 hcid[7004]: HCI dev 0 registered Feb 16 23:41:33 alon1 DS: 007b ES: 007b FS: 0000 GS: 0000 SS: 0068 Feb 16 23:41:33 alon1 Process events/0 (pid: 4, ti=f7c48000 task=f7c3efc0 task.ti=f7c48000) Feb 16 23:41:33 alon1 Stack: f7cb6140 f4822668 f7e71e10 c01b304d ffffffff ffffffff fffffffe c030ba9c Feb 16 23:41:33 alon1 f7cb6140 f4822668 f6da6720 f7cb6140 f4822668 f6da6720 c030ba8e c01ce20b Feb 16 23:41:33 alon1 f6e9dd00 c030ba8e f6da6720 f6e9dd00 f6e9dd00 00000000 f4822600 00000000 Feb 16 23:41:33 alon1 Call Trace: Feb 16 23:41:33 alon1 [] sysfs_move_dir+0x3d/0x1f0 Feb 16 23:41:33 alon1 [] kobject_move+0x9b/0x120 Feb 16 23:41:33 alon1 [] device_move+0x51/0x110 Feb 16 23:41:33 alon1 [] del_conn+0x0/0x70 [bluetooth] Feb 16 23:41:33 alon1 [] del_conn+0x19/0x70 [bluetooth] Feb 16 23:41:33 alon1 [] run_workqueue+0x81/0x140 Feb 16 23:41:33 alon1 [] schedule+0x168/0x2e0 Feb 16 23:41:33 alon1 [] autoremove_wake_function+0x0/0x50 Feb 16 23:41:33 alon1 [] worker_thread+0x9b/0xf0 Feb 16 23:41:33 alon1 [] autoremove_wake_function+0x0/0x50 Feb 16 23:41:33 alon1 [] worker_thread+0x0/0xf0 Feb 16 23:41:33 alon1 [] kthread+0x42/0x70 Feb 16 23:41:33 alon1 [] kthread+0x0/0x70 Feb 16 23:41:33 alon1 [] kernel_thread_helper+0x7/0x18 Feb 16 23:41:33 alon1 ======================= Feb 16 23:41:33 alon1 Code: 26 00 00 00 00 57 89 c7 a1 50 1b 3a c0 56 53 8b 70 38 85 f6 74 08 8b 0e 85 c9 74 58 ff 06 8b 56 50 39 fa 74 47 89 fb eb 02 89 c3 <8b> 43 08 39 c2 75 f7 8b 46 08 83 c0 68 e8 98 e7 10 00 8b 43 10 Feb 16 23:41:33 alon1 EIP: [] sysfs_get_dentry+0x26/0x80 SS:ESP 0068:f7c49efc Feb 16 23:41:33 alon1 ---[ end trace aae864e9592acc1d ]--- Defer hci_unregister_sysfs because hci device could be destructed while hci conn devices still there. Signed-off-by: Dave Young Tested-by: Stefan Seyfried Acked-by: Alon Bar-Lev Signed-off-by: Andrew Morton Acked-by: Marcel Holtmann --- net/bluetooth/hci_core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 930b58e7149a..aec6929f5c16 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -902,8 +902,6 @@ int hci_unregister_dev(struct hci_dev *hdev) BT_DBG("%p name %s type %d", hdev, hdev->name, hdev->type); - hci_unregister_sysfs(hdev); - write_lock_bh(&hci_dev_list_lock); list_del(&hdev->list); write_unlock_bh(&hci_dev_list_lock); @@ -915,6 +913,8 @@ int hci_unregister_dev(struct hci_dev *hdev) hci_notify(hdev, HCI_DEV_UNREG); + hci_unregister_sysfs(hdev); + __hci_dev_put(hdev); return 0; -- cgit v1.2.3 From 04005dd9ae7bf1031408869c33df96149ebb1086 Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Wed, 5 Mar 2008 18:47:03 -0800 Subject: bluetooth: Make hci_sock_cleanup() return void hci_sock_cleanup() always returns 0 and its return value isn't used anywhere in the code. Compile-tested with 'make allyesconfig && make net/bluetooth/bluetooth.ko' Signed-off-by: Tobias Klauser Signed-off-by: Andrew Morton Acked-by: Marcel Holtmann --- include/net/bluetooth/bluetooth.h | 2 +- net/bluetooth/hci_sock.c | 4 +--- 2 files changed, 2 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 771d17783c18..750648df13f4 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -170,7 +170,7 @@ static inline int skb_frags_no(struct sk_buff *skb) int bt_err(__u16 code); extern int hci_sock_init(void); -extern int hci_sock_cleanup(void); +extern void hci_sock_cleanup(void); extern int bt_sysfs_init(void); extern void bt_sysfs_cleanup(void); diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 14991323c273..b5d4019d3572 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -734,7 +734,7 @@ error: return err; } -int __exit hci_sock_cleanup(void) +void __exit hci_sock_cleanup(void) { if (bt_sock_unregister(BTPROTO_HCI) < 0) BT_ERR("HCI socket unregistration failed"); @@ -742,6 +742,4 @@ int __exit hci_sock_cleanup(void) hci_unregister_notifier(&hci_sock_nblock); proto_unregister(&hci_sk_proto); - - return 0; } -- cgit v1.2.3 From a4e2acf01a7e5fcd960fc332335ca10313641f4b Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Wed, 5 Mar 2008 18:47:40 -0800 Subject: bluetooth: make bnep_sock_cleanup() return void bnep_sock_cleanup() always returns 0 and its return value isn't used anywhere in the code. Signed-off-by: Tobias Klauser Signed-off-by: Andrew Morton Signed-off-by: David S. Miller --- net/bluetooth/bnep/bnep.h | 2 +- net/bluetooth/bnep/sock.c | 4 +--- 2 files changed, 2 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/bluetooth/bnep/bnep.h b/net/bluetooth/bnep/bnep.h index a2992280c3d1..e69244dd8de8 100644 --- a/net/bluetooth/bnep/bnep.h +++ b/net/bluetooth/bnep/bnep.h @@ -174,7 +174,7 @@ struct bnep_session { void bnep_net_setup(struct net_device *dev); int bnep_sock_init(void); -int bnep_sock_cleanup(void); +void bnep_sock_cleanup(void); static inline int bnep_mc_hash(__u8 *addr) { diff --git a/net/bluetooth/bnep/sock.c b/net/bluetooth/bnep/sock.c index 81065e548a1f..201e5b1ce473 100644 --- a/net/bluetooth/bnep/sock.c +++ b/net/bluetooth/bnep/sock.c @@ -257,12 +257,10 @@ error: return err; } -int __exit bnep_sock_cleanup(void) +void __exit bnep_sock_cleanup(void) { if (bt_sock_unregister(BTPROTO_BNEP) < 0) BT_ERR("Can't unregister BNEP socket"); proto_unregister(&bnep_proto); - - return 0; } -- cgit v1.2.3 From 1ff82fe0024e8070c38346b8abc1ff09612dea4c Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 5 Mar 2008 18:53:55 -0800 Subject: RxRPC: fix rxrpc_recvmsg()'s returning of msg_name Fix rxrpc_recvmsg() to return msg_name correctly. We shouldn't overwrite the *msg struct, but should rather write into msg->msg_name (there's a '&' unary operator that shouldn't be there). Signed-off-by: David Howells Signed-off-by: Andrew Morton Signed-off-by: David S. Miller --- net/rxrpc/ar-recvmsg.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c index f19121d4795b..a39bf97f8830 100644 --- a/net/rxrpc/ar-recvmsg.c +++ b/net/rxrpc/ar-recvmsg.c @@ -143,7 +143,8 @@ int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock, /* copy the peer address and timestamp */ if (!continue_call) { if (msg->msg_name && msg->msg_namelen > 0) - memcpy(&msg->msg_name, &call->conn->trans->peer->srx, + memcpy(msg->msg_name, + &call->conn->trans->peer->srx, sizeof(call->conn->trans->peer->srx)); sock_recv_timestamp(msg, &rx->sk, skb); } -- cgit v1.2.3 From ee1a2c564f67407947e89f1dac75ac0af0ba88c7 Mon Sep 17 00:00:00 2001 From: Tom Talpey Date: Wed, 27 Feb 2008 15:04:26 -0500 Subject: SUNRPC: Fix a nfs4 over rdma transport oops Prevent an RPC oops when freeing a dynamically allocated RDMA buffer, used in certain special-case large metadata operations. Signed-off-by: Tom Talpey Signed-off-by: James Lentini Signed-off-by: Trond Myklebust --- net/sunrpc/xprtrdma/transport.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 02c522c17de5..a564c1a39ec5 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -614,7 +614,11 @@ xprt_rdma_free(void *buffer) return; req = container_of(buffer, struct rpcrdma_req, rl_xdr_buf[0]); - r_xprt = container_of(req->rl_buffer, struct rpcrdma_xprt, rx_buf); + if (req->rl_iov.length == 0) { /* see allocate above */ + r_xprt = container_of(((struct rpcrdma_req *) req->rl_buffer)->rl_buffer, + struct rpcrdma_xprt, rx_buf); + } else + r_xprt = container_of(req->rl_buffer, struct rpcrdma_xprt, rx_buf); rep = req->rl_reply; dprintk("RPC: %s: called on 0x%p%s\n", -- cgit v1.2.3 From cabaa9bfb01eb4cee97ffb8a18405f4c5175d3d9 Mon Sep 17 00:00:00 2001 From: Eric Leblond Date: Mon, 10 Mar 2008 16:41:43 -0700 Subject: [NETFILTER]: nfnetlink_queue: fix computation of allocated size for netlink skb. Size of the netlink skb was wrongly computed because the formula was using NLMSG_ALIGN instead of NLMSG_SPACE. NLMSG_ALIGN does not add the room for netlink header as NLMSG_SPACE does. This was causing a failure of message building in some cases. On my test system, all messages for packets in range [8*k+41, 8*k+48] where k is an integer were invalid and the corresponding packets were dropped. Signed-off-by: Eric Leblond Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- net/netfilter/nfnetlink_queue.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 0043d3a9f87e..c0cc3d3618a3 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -224,7 +224,7 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, struct net_device *indev; struct net_device *outdev; - size = NLMSG_ALIGN(sizeof(struct nfgenmsg)) + size = NLMSG_SPACE(sizeof(struct nfgenmsg)) + nla_total_size(sizeof(struct nfqnl_msg_packet_hdr)) + nla_total_size(sizeof(u_int32_t)) /* ifindex */ + nla_total_size(sizeof(u_int32_t)) /* ifindex */ -- cgit v1.2.3 From 7000d38d6126d6ef928605bdacebc9f12279c5aa Mon Sep 17 00:00:00 2001 From: Eric Leblond Date: Mon, 10 Mar 2008 16:42:04 -0700 Subject: [NETFILTER]: nfnetlink_log: fix computation of netlink skb size This patch is similar to nfnetlink_queue fixes. It fixes the computation of skb size by using NLMSG_SPACE instead of NLMSG_ALIGN. Signed-off-by: Eric Leblond Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- net/netfilter/nfnetlink_log.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 7efa40d47393..c6802c0d6ed8 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -556,7 +556,7 @@ nfulnl_log_packet(unsigned int pf, /* FIXME: do we want to make the size calculation conditional based on * what is actually present? way more branches and checks, but more * memory efficient... */ - size = NLMSG_ALIGN(sizeof(struct nfgenmsg)) + size = NLMSG_SPACE(sizeof(struct nfgenmsg)) + nla_total_size(sizeof(struct nfulnl_msg_packet_hdr)) + nla_total_size(sizeof(u_int32_t)) /* ifindex */ + nla_total_size(sizeof(u_int32_t)) /* ifindex */ -- cgit v1.2.3 From 4f4c9430cf5ee1ca3567bc88faf8b4c18ed0bd13 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Mon, 10 Mar 2008 16:42:40 -0700 Subject: [NETFILTER]: xt_time: fix failure to match on Sundays From: Andrew Schulman xt_time_match() in net/netfilter/xt_time.c in kernel 2.6.24 never matches on Sundays. On my host I have a rule like iptables -A OUTPUT -m time --weekdays Sun -j REJECT and it never matches. The problem is in localtime_2(), which uses r->weekday = (4 + r->dse) % 7; to map the epoch day onto a weekday in {0,...,6}. In particular this gives 0 for Sundays. But 0 has to be wrong; a weekday of 0 can never match. xt_time_match() has if (!(info->weekdays_match & (1 << current_time.weekday))) return false; and when current_time.weekday = 0, the result of the & is always zero, even when info->weekdays_match = XT_TIME_ALL_WEEKDAYS = 0xFE. Signed-off-by: Jan Engelhardt Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- net/netfilter/xt_time.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/netfilter/xt_time.c b/net/netfilter/xt_time.c index e9a8794bc3ab..9fa2e0824708 100644 --- a/net/netfilter/xt_time.c +++ b/net/netfilter/xt_time.c @@ -95,8 +95,11 @@ static inline void localtime_2(struct xtm *r, time_t time) */ r->dse = time / 86400; - /* 1970-01-01 (w=0) was a Thursday (4). */ - r->weekday = (4 + r->dse) % 7; + /* + * 1970-01-01 (w=0) was a Thursday (4). + * -1 and +1 map Sunday properly onto 7. + */ + r->weekday = (4 + r->dse - 1) % 7 + 1; } static void localtime_3(struct xtm *r, time_t time) -- cgit v1.2.3 From 3d89e9cf3690b4645ce73b86c219c8188f8fa50a Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Mon, 10 Mar 2008 16:43:10 -0700 Subject: [NETFILTER]: nf_conntrack: add \n to "expectation table full" message Signed-off-by: Alexey Dobriyan Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- net/netfilter/nf_conntrack_expect.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index e06bf0028bb1..684ec9c1ad38 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -381,7 +381,7 @@ int nf_ct_expect_related(struct nf_conntrack_expect *expect) if (nf_ct_expect_count >= nf_ct_expect_max) { if (net_ratelimit()) printk(KERN_WARNING - "nf_conntrack: expectation table full"); + "nf_conntrack: expectation table full\n"); ret = -EMFILE; goto out; } -- cgit v1.2.3 From 019f692ea719a2da17606511d2648b8cc1762268 Mon Sep 17 00:00:00 2001 From: Pekka Enberg Date: Mon, 10 Mar 2008 16:43:41 -0700 Subject: [NETFILTER]: nf_conntrack: replace horrible hack with ksize() There's a horrible slab abuse in net/netfilter/nf_conntrack_extend.c that can be replaced with a call to ksize(). Cc: Christoph Lameter Signed-off-by: Pekka Enberg Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/net/netfilter/nf_conntrack_extend.h | 1 - net/netfilter/nf_conntrack_extend.c | 19 +++---------------- 2 files changed, 3 insertions(+), 17 deletions(-) (limited to 'net') diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h index 49aac6323fbe..f736e842977f 100644 --- a/include/net/netfilter/nf_conntrack_extend.h +++ b/include/net/netfilter/nf_conntrack_extend.h @@ -17,7 +17,6 @@ enum nf_ct_ext_id struct nf_ct_ext { u8 offset[NF_CT_EXT_NUM]; u8 len; - u8 real_len; char data[0]; }; diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index 8b9be1e978cd..2bd9963b5b3e 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -19,14 +19,6 @@ static struct nf_ct_ext_type *nf_ct_ext_types[NF_CT_EXT_NUM]; static DEFINE_MUTEX(nf_ct_ext_type_mutex); -/* Horrible trick to figure out smallest amount worth kmallocing. */ -#define CACHE(x) (x) + 0 * -enum { - NF_CT_EXT_MIN_SIZE = -#include - 1 }; -#undef CACHE - void __nf_ct_ext_destroy(struct nf_conn *ct) { unsigned int i; @@ -53,7 +45,7 @@ EXPORT_SYMBOL(__nf_ct_ext_destroy); static void * nf_ct_ext_create(struct nf_ct_ext **ext, enum nf_ct_ext_id id, gfp_t gfp) { - unsigned int off, len, real_len; + unsigned int off, len; struct nf_ct_ext_type *t; rcu_read_lock(); @@ -61,16 +53,14 @@ nf_ct_ext_create(struct nf_ct_ext **ext, enum nf_ct_ext_id id, gfp_t gfp) BUG_ON(t == NULL); off = ALIGN(sizeof(struct nf_ct_ext), t->align); len = off + t->len; - real_len = t->alloc_size; rcu_read_unlock(); - *ext = kzalloc(real_len, gfp); + *ext = kzalloc(t->alloc_size, gfp); if (!*ext) return NULL; (*ext)->offset[id] = off; (*ext)->len = len; - (*ext)->real_len = real_len; return (void *)(*ext) + off; } @@ -95,7 +85,7 @@ void *__nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp) newlen = newoff + t->len; rcu_read_unlock(); - if (newlen >= ct->ext->real_len) { + if (newlen >= ksize(ct->ext)) { new = kmalloc(newlen, gfp); if (!new) return NULL; @@ -114,7 +104,6 @@ void *__nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp) rcu_read_unlock(); } kfree(ct->ext); - new->real_len = newlen; ct->ext = new; } @@ -156,8 +145,6 @@ static void update_alloc_size(struct nf_ct_ext_type *type) t1->alloc_size = ALIGN(t1->alloc_size, t2->align) + t2->len; } - if (t1->alloc_size < NF_CT_EXT_MIN_SIZE) - t1->alloc_size = NF_CT_EXT_MIN_SIZE; } } -- cgit v1.2.3 From b7047a1c886386b10a103b4fea26678db8b57832 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 10 Mar 2008 16:44:13 -0700 Subject: [NETFILTER]: nfnetlink_log: fix EPERM when binding/unbinding and instance 0 exists When binding or unbinding to an address family, the res_id is usually set to zero. When logging instance 0 already exists and is owned by a different process, this makes nfunl_recv_config return -EPERM without performing the bind operation. Since no operation on the foreign logging instance itself was requested, this is incorrect. Move bind/unbind commands before the queue instance permissions checks. Also remove an incorrect comment. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- net/netfilter/nfnetlink_log.c | 30 ++++++++++++++++-------------- 1 file changed, 16 insertions(+), 14 deletions(-) (limited to 'net') diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index c6802c0d6ed8..bf3f19b21fe4 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -702,20 +702,30 @@ nfulnl_recv_config(struct sock *ctnl, struct sk_buff *skb, struct nfgenmsg *nfmsg = NLMSG_DATA(nlh); u_int16_t group_num = ntohs(nfmsg->res_id); struct nfulnl_instance *inst; + struct nfulnl_msg_config_cmd *cmd = NULL; int ret = 0; + if (nfula[NFULA_CFG_CMD]) { + u_int8_t pf = nfmsg->nfgen_family; + cmd = nla_data(nfula[NFULA_CFG_CMD]); + + /* Commands without queue context */ + switch (cmd->command) { + case NFULNL_CFG_CMD_PF_BIND: + return nf_log_register(pf, &nfulnl_logger); + case NFULNL_CFG_CMD_PF_UNBIND: + nf_log_unregister_pf(pf); + return 0; + } + } + inst = instance_lookup_get(group_num); if (inst && inst->peer_pid != NETLINK_CB(skb).pid) { ret = -EPERM; goto out_put; } - if (nfula[NFULA_CFG_CMD]) { - u_int8_t pf = nfmsg->nfgen_family; - struct nfulnl_msg_config_cmd *cmd; - - cmd = nla_data(nfula[NFULA_CFG_CMD]); - + if (cmd != NULL) { switch (cmd->command) { case NFULNL_CFG_CMD_BIND: if (inst) { @@ -738,14 +748,6 @@ nfulnl_recv_config(struct sock *ctnl, struct sk_buff *skb, instance_destroy(inst); goto out; - case NFULNL_CFG_CMD_PF_BIND: - ret = nf_log_register(pf, &nfulnl_logger); - break; - case NFULNL_CFG_CMD_PF_UNBIND: - /* This is a bug and a feature. We cannot unregister - * other handlers, like nfnetlink_inst can */ - nf_log_unregister_pf(pf); - break; default: ret = -ENOTSUPP; break; -- cgit v1.2.3 From 914afea84e3e20cdbcd040f8387a0e6ef20ffc97 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 10 Mar 2008 16:44:36 -0700 Subject: [NETFILTER]: nfnetlink_queue: fix EPERM when binding/unbinding and instance 0 exists Similar to the nfnetlink_log problem, nfnetlink_queue incorrectly returns -EPERM when binding or unbinding to an address family and queueing instance 0 exists and is owned by a different process. Unlike nfnetlink_log it previously completes the operation, but it is still incorrect. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- net/netfilter/nfnetlink_queue.c | 15 ++++----------- 1 file changed, 4 insertions(+), 11 deletions(-) (limited to 'net') diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index c0cc3d3618a3..012cb6910820 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -703,19 +703,12 @@ nfqnl_recv_config(struct sock *ctnl, struct sk_buff *skb, /* Commands without queue context - might sleep */ switch (cmd->command) { case NFQNL_CFG_CMD_PF_BIND: - ret = nf_register_queue_handler(ntohs(cmd->pf), - &nfqh); - break; + return nf_register_queue_handler(ntohs(cmd->pf), + &nfqh); case NFQNL_CFG_CMD_PF_UNBIND: - ret = nf_unregister_queue_handler(ntohs(cmd->pf), - &nfqh); - break; - default: - break; + return nf_unregister_queue_handler(ntohs(cmd->pf), + &nfqh); } - - if (ret < 0) - return ret; } rcu_read_lock(); -- cgit v1.2.3 From 94be1a3f365e2b9f2615575d7fef16a0bad106a3 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 10 Mar 2008 16:45:05 -0700 Subject: [NETFILTER]: nf_queue: don't return error when unregistering a non-existant handler Commit ce7663d84: [NETFILTER]: nfnetlink_queue: don't unregister handler of other subsystem changed nf_unregister_queue_handler to return an error when attempting to unregister a queue handler that is not identical to the one passed in. This is correct in case we really do have a different queue handler already registered, but some existing userspace code always does an unbind before bind and aborts if that fails, so try to be nice and return success in that case. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- net/netfilter/nf_queue.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index bfc2928c1912..ddc80ea114cd 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -51,7 +51,7 @@ int nf_unregister_queue_handler(int pf, const struct nf_queue_handler *qh) return -EINVAL; mutex_lock(&queue_handler_mutex); - if (queue_handler[pf] != qh) { + if (queue_handler[pf] && queue_handler[pf] != qh) { mutex_unlock(&queue_handler_mutex); return -EINVAL; } -- cgit v1.2.3 From 5ea3a7480606cef06321cd85bc5113c72d2c7c68 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Tue, 11 Mar 2008 17:55:27 -0700 Subject: [TCP]: Prevent sending past receiver window with TSO (at last skb) With TSO it was possible to send past the receiver window when the skb to be sent was the last in the write queue while the receiver window is the limiting factor. One can notice that there's a loophole in the tcp_mss_split_point that lacked a receiver window check for the tcp_write_queue_tail() if also cwnd was smaller than the full skb. Noticed by Thomas Gleixner in form of "Treason uncloaked! Peer ... shrinks window .... Repaired." messages (the peer didn't actually shrink its window as the message suggests, we had just sent something past it without a permission to do so). Signed-off-by: Ilpo Järvinen Tested-by: Thomas Gleixner Signed-off-by: David S. Miller --- net/ipv4/tcp_output.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index ed750f9ceb07..01578f544ad6 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1035,6 +1035,13 @@ static void tcp_cwnd_validate(struct sock *sk) * introducing MSS oddities to segment boundaries. In rare cases where * mss_now != mss_cache, we will request caller to create a small skb * per input skb which could be mostly avoided here (if desired). + * + * We explicitly want to create a request for splitting write queue tail + * to a small skb for Nagle purposes while avoiding unnecessary modulos, + * thus all the complexity (cwnd_len is always MSS multiple which we + * return whenever allowed by the other factors). Basically we need the + * modulo only when the receiver window alone is the limiting factor or + * when we would be allowed to send the split-due-to-Nagle skb fully. */ static unsigned int tcp_mss_split_point(struct sock *sk, struct sk_buff *skb, unsigned int mss_now, unsigned int cwnd) @@ -1048,10 +1055,11 @@ static unsigned int tcp_mss_split_point(struct sock *sk, struct sk_buff *skb, if (likely(cwnd_len <= window && skb != tcp_write_queue_tail(sk))) return cwnd_len; - if (skb == tcp_write_queue_tail(sk) && cwnd_len <= skb->len) + needed = min(skb->len, window); + + if (skb == tcp_write_queue_tail(sk) && cwnd_len <= needed) return cwnd_len; - needed = min(skb->len, window); return needed - needed % mss_now; } -- cgit v1.2.3 From 22626216c46f2ec86287e75ea86dd9ac3df54265 Mon Sep 17 00:00:00 2001 From: Chidambar 'ilLogict' Zinnoury Date: Tue, 11 Mar 2008 18:05:02 -0700 Subject: [SCTP]: Fix local_addr deletions during list traversals. Since the lists are circular, we need to explicitely tag the address to be deleted since we might end up freeing the list head instead. This fixes some interesting SCTP crashes. Signed-off-by: Chidambar 'ilLogict' Zinnoury Signed-off-by: Vlad Yasevich Signed-off-by: David S. Miller --- net/sctp/bind_addr.c | 4 +++- net/sctp/ipv6.c | 4 +++- net/sctp/protocol.c | 4 +++- 3 files changed, 9 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index a27511ebc4cb..ceefda025e2d 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -209,6 +209,7 @@ int sctp_add_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *new, int sctp_del_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *del_addr) { struct sctp_sockaddr_entry *addr, *temp; + int found = 0; /* We hold the socket lock when calling this function, * and that acts as a writer synchronizing lock. @@ -216,13 +217,14 @@ int sctp_del_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *del_addr) list_for_each_entry_safe(addr, temp, &bp->address_list, list) { if (sctp_cmp_addr_exact(&addr->a, del_addr)) { /* Found the exact match. */ + found = 1; addr->valid = 0; list_del_rcu(&addr->list); break; } } - if (addr && !addr->valid) { + if (found) { call_rcu(&addr->rcu, sctp_local_addr_free); SCTP_DBG_OBJCNT_DEC(addr); return 0; diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 87f940587d5f..9aa0733aee87 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -89,6 +89,7 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev, struct inet6_ifaddr *ifa = (struct inet6_ifaddr *)ptr; struct sctp_sockaddr_entry *addr = NULL; struct sctp_sockaddr_entry *temp; + int found = 0; switch (ev) { case NETDEV_UP: @@ -111,13 +112,14 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev, &sctp_local_addr_list, list) { if (ipv6_addr_equal(&addr->a.v6.sin6_addr, &ifa->addr)) { + found = 1; addr->valid = 0; list_del_rcu(&addr->list); break; } } spin_unlock_bh(&sctp_local_addr_lock); - if (addr && !addr->valid) + if (found) call_rcu(&addr->rcu, sctp_local_addr_free); break; } diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 688546dccd82..ad0a4069b95b 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -628,6 +628,7 @@ static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev, struct in_ifaddr *ifa = (struct in_ifaddr *)ptr; struct sctp_sockaddr_entry *addr = NULL; struct sctp_sockaddr_entry *temp; + int found = 0; switch (ev) { case NETDEV_UP: @@ -647,13 +648,14 @@ static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev, list_for_each_entry_safe(addr, temp, &sctp_local_addr_list, list) { if (addr->a.v4.sin_addr.s_addr == ifa->ifa_local) { + found = 1; addr->valid = 0; list_del_rcu(&addr->list); break; } } spin_unlock_bh(&sctp_local_addr_lock); - if (addr && !addr->valid) + if (found) call_rcu(&addr->rcu, sctp_local_addr_free); break; } -- cgit v1.2.3 From c48cbb405c4f338ce3263c44d621eff41d9a95fc Mon Sep 17 00:00:00 2001 From: Tom Tucker Date: Tue, 11 Mar 2008 14:31:39 -0400 Subject: SVCRDMA: Add xprt refs to fix close/unmount crash RDMA connection shutdown on an SMP machine can cause a kernel crash due to the transport close path racing with the I/O tasklet. Additional transport references were added as follows: - A reference when on the DTO Q to avoid having the transport deleted while queued for I/O. - A reference while there is a QP able to generate events. - A reference until the DISCONNECTED event is received on the CM ID Signed-off-by: Tom Tucker Signed-off-by: J. Bruce Fields Signed-off-by: Linus Torvalds --- net/sunrpc/xprtrdma/svc_rdma_transport.c | 96 +++++++++++++++++++------------- 1 file changed, 58 insertions(+), 38 deletions(-) (limited to 'net') diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index f09444c451bc..16fd3f6718ff 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -54,7 +54,6 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv, int flags); static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt); static void svc_rdma_release_rqst(struct svc_rqst *); -static void rdma_destroy_xprt(struct svcxprt_rdma *xprt); static void dto_tasklet_func(unsigned long data); static void svc_rdma_detach(struct svc_xprt *xprt); static void svc_rdma_free(struct svc_xprt *xprt); @@ -247,6 +246,7 @@ static void dto_tasklet_func(unsigned long data) sq_cq_reap(xprt); } + svc_xprt_put(&xprt->sc_xprt); spin_lock_irqsave(&dto_lock, flags); } spin_unlock_irqrestore(&dto_lock, flags); @@ -275,8 +275,10 @@ static void rq_comp_handler(struct ib_cq *cq, void *cq_context) * add it */ spin_lock_irqsave(&dto_lock, flags); - if (list_empty(&xprt->sc_dto_q)) + if (list_empty(&xprt->sc_dto_q)) { + svc_xprt_get(&xprt->sc_xprt); list_add_tail(&xprt->sc_dto_q, &dto_xprt_q); + } spin_unlock_irqrestore(&dto_lock, flags); /* Tasklet does all the work to avoid irqsave locks. */ @@ -386,8 +388,10 @@ static void sq_comp_handler(struct ib_cq *cq, void *cq_context) * add it */ spin_lock_irqsave(&dto_lock, flags); - if (list_empty(&xprt->sc_dto_q)) + if (list_empty(&xprt->sc_dto_q)) { + svc_xprt_get(&xprt->sc_xprt); list_add_tail(&xprt->sc_dto_q, &dto_xprt_q); + } spin_unlock_irqrestore(&dto_lock, flags); /* Tasklet does all the work to avoid irqsave locks. */ @@ -611,6 +615,7 @@ static int rdma_cma_handler(struct rdma_cm_id *cma_id, switch (event->event) { case RDMA_CM_EVENT_ESTABLISHED: /* Accept complete */ + svc_xprt_get(xprt); dprintk("svcrdma: Connection completed on DTO xprt=%p, " "cm_id=%p\n", xprt, cma_id); clear_bit(RDMAXPRT_CONN_PENDING, &rdma->sc_flags); @@ -661,15 +666,15 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv, listen_id = rdma_create_id(rdma_listen_handler, cma_xprt, RDMA_PS_TCP); if (IS_ERR(listen_id)) { - rdma_destroy_xprt(cma_xprt); + svc_xprt_put(&cma_xprt->sc_xprt); dprintk("svcrdma: rdma_create_id failed = %ld\n", PTR_ERR(listen_id)); return (void *)listen_id; } ret = rdma_bind_addr(listen_id, sa); if (ret) { - rdma_destroy_xprt(cma_xprt); rdma_destroy_id(listen_id); + svc_xprt_put(&cma_xprt->sc_xprt); dprintk("svcrdma: rdma_bind_addr failed = %d\n", ret); return ERR_PTR(ret); } @@ -678,8 +683,9 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv, ret = rdma_listen(listen_id, RPCRDMA_LISTEN_BACKLOG); if (ret) { rdma_destroy_id(listen_id); - rdma_destroy_xprt(cma_xprt); + svc_xprt_put(&cma_xprt->sc_xprt); dprintk("svcrdma: rdma_listen failed = %d\n", ret); + return ERR_PTR(ret); } /* @@ -820,6 +826,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) newxprt->sc_sq_depth = qp_attr.cap.max_send_wr; newxprt->sc_max_requests = qp_attr.cap.max_recv_wr; } + svc_xprt_get(&newxprt->sc_xprt); newxprt->sc_qp = newxprt->sc_cm_id->qp; /* Register all of physical memory */ @@ -891,8 +898,15 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) errout: dprintk("svcrdma: failure accepting new connection rc=%d.\n", ret); + /* Take a reference in case the DTO handler runs */ + svc_xprt_get(&newxprt->sc_xprt); + if (newxprt->sc_qp && !IS_ERR(newxprt->sc_qp)) { + ib_destroy_qp(newxprt->sc_qp); + svc_xprt_put(&newxprt->sc_xprt); + } rdma_destroy_id(newxprt->sc_cm_id); - rdma_destroy_xprt(newxprt); + /* This call to put will destroy the transport */ + svc_xprt_put(&newxprt->sc_xprt); return NULL; } @@ -919,54 +933,60 @@ static void svc_rdma_release_rqst(struct svc_rqst *rqstp) rqstp->rq_xprt_ctxt = NULL; } -/* Disable data ready events for this connection */ +/* + * When connected, an svc_xprt has at least three references: + * + * - A reference held by the QP. We still hold that here because this + * code deletes the QP and puts the reference. + * + * - A reference held by the cm_id between the ESTABLISHED and + * DISCONNECTED events. If the remote peer disconnected first, this + * reference could be gone. + * + * - A reference held by the svc_recv code that called this function + * as part of close processing. + * + * At a minimum two references should still be held. + */ static void svc_rdma_detach(struct svc_xprt *xprt) { struct svcxprt_rdma *rdma = container_of(xprt, struct svcxprt_rdma, sc_xprt); - unsigned long flags; - dprintk("svc: svc_rdma_detach(%p)\n", xprt); - /* - * Shutdown the connection. This will ensure we don't get any - * more events from the provider. - */ + + /* Disconnect and flush posted WQE */ rdma_disconnect(rdma->sc_cm_id); - rdma_destroy_id(rdma->sc_cm_id); - /* We may already be on the DTO list */ - spin_lock_irqsave(&dto_lock, flags); - if (!list_empty(&rdma->sc_dto_q)) - list_del_init(&rdma->sc_dto_q); - spin_unlock_irqrestore(&dto_lock, flags); + /* Destroy the QP if present (not a listener) */ + if (rdma->sc_qp && !IS_ERR(rdma->sc_qp)) { + ib_destroy_qp(rdma->sc_qp); + svc_xprt_put(xprt); + } + + /* Destroy the CM ID */ + rdma_destroy_id(rdma->sc_cm_id); } static void svc_rdma_free(struct svc_xprt *xprt) { struct svcxprt_rdma *rdma = (struct svcxprt_rdma *)xprt; dprintk("svcrdma: svc_rdma_free(%p)\n", rdma); - rdma_destroy_xprt(rdma); - kfree(rdma); -} - -static void rdma_destroy_xprt(struct svcxprt_rdma *xprt) -{ - if (xprt->sc_qp && !IS_ERR(xprt->sc_qp)) - ib_destroy_qp(xprt->sc_qp); - - if (xprt->sc_sq_cq && !IS_ERR(xprt->sc_sq_cq)) - ib_destroy_cq(xprt->sc_sq_cq); + /* We should only be called from kref_put */ + BUG_ON(atomic_read(&xprt->xpt_ref.refcount) != 0); + if (rdma->sc_sq_cq && !IS_ERR(rdma->sc_sq_cq)) + ib_destroy_cq(rdma->sc_sq_cq); - if (xprt->sc_rq_cq && !IS_ERR(xprt->sc_rq_cq)) - ib_destroy_cq(xprt->sc_rq_cq); + if (rdma->sc_rq_cq && !IS_ERR(rdma->sc_rq_cq)) + ib_destroy_cq(rdma->sc_rq_cq); - if (xprt->sc_phys_mr && !IS_ERR(xprt->sc_phys_mr)) - ib_dereg_mr(xprt->sc_phys_mr); + if (rdma->sc_phys_mr && !IS_ERR(rdma->sc_phys_mr)) + ib_dereg_mr(rdma->sc_phys_mr); - if (xprt->sc_pd && !IS_ERR(xprt->sc_pd)) - ib_dealloc_pd(xprt->sc_pd); + if (rdma->sc_pd && !IS_ERR(rdma->sc_pd)) + ib_dealloc_pd(rdma->sc_pd); - destroy_context_cache(xprt->sc_ctxt_head); + destroy_context_cache(rdma->sc_ctxt_head); + kfree(rdma); } static int svc_rdma_has_wspace(struct svc_xprt *xprt) -- cgit v1.2.3 From 3fedb3c5a80595d94f7cbe47a6dba9184d869eb8 Mon Sep 17 00:00:00 2001 From: Tom Tucker Date: Tue, 11 Mar 2008 14:31:40 -0400 Subject: SVCRDMA: Fix erroneous BUG_ON in send_write The assertion that checks for sge context overflow is incorrectly hard-coded to 32. This causes a kernel bug check when using big-data mounts. Changed the BUG_ON to use the computed value RPCSVC_MAXPAGES. Signed-off-by: Tom Tucker Signed-off-by: J. Bruce Fields Signed-off-by: Linus Torvalds --- net/sunrpc/xprtrdma/svc_rdma_sendto.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 0598b229c11d..981f190c1b39 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -156,7 +156,7 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp, struct svc_rdma_op_ctxt *ctxt; int ret = 0; - BUG_ON(sge_count >= 32); + BUG_ON(sge_count > RPCSVC_MAXPAGES); dprintk("svcrdma: RDMA_WRITE rmr=%x, to=%llx, xdr_off=%d, " "write_len=%d, xdr_sge=%p, sge_count=%d\n", rmr, (unsigned long long)to, xdr_off, -- cgit v1.2.3 From e6f1cebf71c4e7aae7dfa43414ce2631291def9f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 17 Mar 2008 22:44:53 -0700 Subject: [NET] endianness noise: INADDR_ANY Signed-off-by: Al Viro Signed-off-by: David S. Miller --- arch/sparc/kernel/sys_sunos.c | 2 +- arch/sparc64/kernel/sys_sunos32.c | 2 +- fs/nfs/super.c | 2 +- net/ipv4/af_inet.c | 2 +- net/ipv4/ip_sockglue.c | 2 +- net/ipv4/ipconfig.c | 9 +++++---- net/sctp/protocol.c | 10 +++++----- net/sunrpc/svc_xprt.c | 2 +- 8 files changed, 16 insertions(+), 15 deletions(-) (limited to 'net') diff --git a/arch/sparc/kernel/sys_sunos.c b/arch/sparc/kernel/sys_sunos.c index 28c187c5d9fd..f5b608bbe8af 100644 --- a/arch/sparc/kernel/sys_sunos.c +++ b/arch/sparc/kernel/sys_sunos.c @@ -659,7 +659,7 @@ sunos_nfs_get_server_fd (int fd, struct sockaddr_in *addr) socket = SOCKET_I(inode); local.sin_family = AF_INET; - local.sin_addr.s_addr = INADDR_ANY; + local.sin_addr.s_addr = htonl(INADDR_ANY); /* IPPORT_RESERVED = 1024, can't find the definition in the kernel */ try_port = 1024; diff --git a/arch/sparc64/kernel/sys_sunos32.c b/arch/sparc64/kernel/sys_sunos32.c index cfc22d3fe54c..e91194fe39d7 100644 --- a/arch/sparc64/kernel/sys_sunos32.c +++ b/arch/sparc64/kernel/sys_sunos32.c @@ -618,7 +618,7 @@ sunos_nfs_get_server_fd (int fd, struct sockaddr_in *addr) socket = SOCKET_I(inode); local.sin_family = AF_INET; - local.sin_addr.s_addr = INADDR_ANY; + local.sin_addr.s_addr = htonl(INADDR_ANY); /* IPPORT_RESERVED = 1024, can't find the definition in the kernel */ try_port = 1024; diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 1fb381843650..bdcf6d3ef62f 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -632,7 +632,7 @@ static int nfs_verify_server_address(struct sockaddr *addr) switch (addr->sa_family) { case AF_INET: { struct sockaddr_in *sa = (struct sockaddr_in *)addr; - return sa->sin_addr.s_addr != INADDR_ANY; + return sa->sin_addr.s_addr != htonl(INADDR_ANY); } case AF_INET6: { struct in6_addr *sa = &((struct sockaddr_in6 *)addr)->sin6_addr; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 09ca5293d08f..0d109504ed86 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -458,7 +458,7 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) err = -EADDRNOTAVAIL; if (!sysctl_ip_nonlocal_bind && !inet->freebind && - addr->sin_addr.s_addr != INADDR_ANY && + addr->sin_addr.s_addr != htonl(INADDR_ANY) && chk_addr_ret != RTN_LOCAL && chk_addr_ret != RTN_MULTICAST && chk_addr_ret != RTN_BROADCAST) diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index de0572c88859..f72457b4b0a7 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -583,7 +583,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, } if (!mreq.imr_ifindex) { - if (mreq.imr_address.s_addr == INADDR_ANY) { + if (mreq.imr_address.s_addr == htonl(INADDR_ANY)) { inet->mc_index = 0; inet->mc_addr = 0; err = 0; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 5dd938579eeb..7c992fbbc2c3 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -103,6 +103,7 @@ - '3' from resolv.h */ #define NONE __constant_htonl(INADDR_NONE) +#define ANY __constant_htonl(INADDR_ANY) /* * Public IP configuration @@ -1479,19 +1480,19 @@ static int __init ip_auto_config_setup(char *addrs) DBG(("IP-Config: Parameter #%d: `%s'\n", num, ip)); switch (num) { case 0: - if ((ic_myaddr = in_aton(ip)) == INADDR_ANY) + if ((ic_myaddr = in_aton(ip)) == ANY) ic_myaddr = NONE; break; case 1: - if ((ic_servaddr = in_aton(ip)) == INADDR_ANY) + if ((ic_servaddr = in_aton(ip)) == ANY) ic_servaddr = NONE; break; case 2: - if ((ic_gateway = in_aton(ip)) == INADDR_ANY) + if ((ic_gateway = in_aton(ip)) == ANY) ic_gateway = NONE; break; case 3: - if ((ic_netmask = in_aton(ip)) == INADDR_ANY) + if ((ic_netmask = in_aton(ip)) == ANY) ic_netmask = NONE; break; case 4: diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index ad0a4069b95b..7a7646a9565c 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -337,14 +337,14 @@ static int sctp_v4_cmp_addr(const union sctp_addr *addr1, static void sctp_v4_inaddr_any(union sctp_addr *addr, __be16 port) { addr->v4.sin_family = AF_INET; - addr->v4.sin_addr.s_addr = INADDR_ANY; + addr->v4.sin_addr.s_addr = htonl(INADDR_ANY); addr->v4.sin_port = port; } /* Is this a wildcard address? */ static int sctp_v4_is_any(const union sctp_addr *addr) { - return INADDR_ANY == addr->v4.sin_addr.s_addr; + return htonl(INADDR_ANY) == addr->v4.sin_addr.s_addr; } /* This function checks if the address is a valid address to be used for @@ -375,7 +375,7 @@ static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp) int ret = inet_addr_type(&init_net, addr->v4.sin_addr.s_addr); - if (addr->v4.sin_addr.s_addr != INADDR_ANY && + if (addr->v4.sin_addr.s_addr != htonl(INADDR_ANY) && ret != RTN_LOCAL && !sp->inet.freebind && !sysctl_ip_nonlocal_bind) @@ -785,8 +785,8 @@ static int sctp_inet_cmp_addr(const union sctp_addr *addr1, /* PF_INET only supports AF_INET addresses. */ if (addr1->sa.sa_family != addr2->sa.sa_family) return 0; - if (INADDR_ANY == addr1->v4.sin_addr.s_addr || - INADDR_ANY == addr2->v4.sin_addr.s_addr) + if (htonl(INADDR_ANY) == addr1->v4.sin_addr.s_addr || + htonl(INADDR_ANY) == addr2->v4.sin_addr.s_addr) return 1; if (addr1->v4.sin_addr.s_addr == addr2->v4.sin_addr.s_addr) return 1; diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index ea377e06afae..332eb47539e1 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -185,7 +185,7 @@ int svc_create_xprt(struct svc_serv *serv, char *xprt_name, unsigned short port, struct svc_xprt_class *xcl; struct sockaddr_in sin = { .sin_family = AF_INET, - .sin_addr.s_addr = INADDR_ANY, + .sin_addr.s_addr = htonl(INADDR_ANY), .sin_port = htons(port), }; dprintk("svc: creating transport %s[%d]\n", xprt_name, port); -- cgit v1.2.3 From 0382b9c35469be273ed10fa374496a924055a3c8 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 17 Mar 2008 22:46:46 -0700 Subject: [PKT_SCHED]: annotate cls_u32 Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/pkt_cls.h | 8 ++++---- net/sched/cls_u32.c | 8 ++++---- net/sched/em_u32.c | 2 +- 3 files changed, 9 insertions(+), 9 deletions(-) (limited to 'net') diff --git a/include/linux/pkt_cls.h b/include/linux/pkt_cls.h index 28dfc61cf79e..99efbed81fa2 100644 --- a/include/linux/pkt_cls.h +++ b/include/linux/pkt_cls.h @@ -201,8 +201,8 @@ enum struct tc_u32_key { - __u32 mask; - __u32 val; + __be32 mask; + __be32 val; int off; int offmask; }; @@ -213,12 +213,12 @@ struct tc_u32_sel unsigned char offshift; unsigned char nkeys; - __u16 offmask; + __be16 offmask; __u16 off; short offoff; short hoff; - __u32 hmask; + __be32 hmask; struct tc_u32_key keys[0]; }; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index b18fa95ef248..c5c16b4b6e98 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -89,7 +89,7 @@ static const struct tcf_ext_map u32_ext_map = { static struct tc_u_common *u32_list; -static __inline__ unsigned u32_hash_fold(u32 key, struct tc_u32_sel *sel, u8 fshift) +static __inline__ unsigned u32_hash_fold(__be32 key, struct tc_u32_sel *sel, u8 fshift) { unsigned h = ntohl(key & sel->hmask)>>fshift; @@ -137,7 +137,7 @@ next_knode: for (i = n->sel.nkeys; i>0; i--, key++) { - if ((*(u32*)(ptr+key->off+(off2&key->offmask))^key->val)&key->mask) { + if ((*(__be32*)(ptr+key->off+(off2&key->offmask))^key->val)&key->mask) { n = n->next; goto next_knode; } @@ -182,7 +182,7 @@ check_terminal: ht = n->ht_down; sel = 0; if (ht->divisor) - sel = ht->divisor&u32_hash_fold(*(u32*)(ptr+n->sel.hoff), &n->sel,n->fshift); + sel = ht->divisor&u32_hash_fold(*(__be32*)(ptr+n->sel.hoff), &n->sel,n->fshift); if (!(n->sel.flags&(TC_U32_VAROFFSET|TC_U32_OFFSET|TC_U32_EAT))) goto next_ht; @@ -190,7 +190,7 @@ check_terminal: if (n->sel.flags&(TC_U32_OFFSET|TC_U32_VAROFFSET)) { off2 = n->sel.off + 3; if (n->sel.flags&TC_U32_VAROFFSET) - off2 += ntohs(n->sel.offmask & *(u16*)(ptr+n->sel.offoff)) >>n->sel.offshift; + off2 += ntohs(n->sel.offmask & *(__be16*)(ptr+n->sel.offoff)) >>n->sel.offshift; off2 &= ~3; } if (n->sel.flags&TC_U32_EAT) { diff --git a/net/sched/em_u32.c b/net/sched/em_u32.c index 112796e4a7c4..953f1479f7da 100644 --- a/net/sched/em_u32.c +++ b/net/sched/em_u32.c @@ -35,7 +35,7 @@ static int em_u32_match(struct sk_buff *skb, struct tcf_ematch *em, if (!tcf_valid_offset(skb, ptr, sizeof(u32))) return 0; - return !(((*(u32*) ptr) ^ key->val) & key->mask); + return !(((*(__be32*) ptr) ^ key->val) & key->mask); } static struct tcf_ematch_ops em_u32_ops = { -- cgit v1.2.3 From bc92dd194d05e8334b210552fbc0ac5711d72ea9 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 17 Mar 2008 22:47:32 -0700 Subject: [SCTP]: fix misannotated __sctp_rcv_asconf_lookup() Signed-off-by: Al Viro Signed-off-by: David S. Miller --- net/sctp/input.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/sctp/input.c b/net/sctp/input.c index 57fe2f81eca8..812ff1756c3e 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -944,7 +944,7 @@ static struct sctp_association *__sctp_rcv_init_lookup(struct sk_buff *skb, static struct sctp_association *__sctp_rcv_asconf_lookup( sctp_chunkhdr_t *ch, const union sctp_addr *laddr, - __be32 peer_port, + __be16 peer_port, struct sctp_transport **transportp) { sctp_addip_chunk_t *asconf = (struct sctp_addip_chunk *)ch; -- cgit v1.2.3 From 27724426a9000086993a8107a11cff276c4bd4d4 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 17 Mar 2008 22:48:03 -0700 Subject: [SUNRPC]: net/* NULL noise Signed-off-by: Al Viro Signed-off-by: David S. Miller --- net/sunrpc/auth_gss/gss_mech_switch.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c index 61801a069ff0..bce9d527af08 100644 --- a/net/sunrpc/auth_gss/gss_mech_switch.c +++ b/net/sunrpc/auth_gss/gss_mech_switch.c @@ -317,7 +317,7 @@ gss_delete_sec_context(struct gss_ctx **context_handle) if (!*context_handle) return(GSS_S_NO_CONTEXT); - if ((*context_handle)->internal_ctx_id != 0) + if ((*context_handle)->internal_ctx_id) (*context_handle)->mech_type->gm_ops ->gss_delete_sec_context((*context_handle) ->internal_ctx_id); -- cgit v1.2.3 From 9534f035ee67630688447e8aac91b1d365a51913 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 17 Mar 2008 22:49:48 -0700 Subject: [8021Q]: vlan_dev misannotations Signed-off-by: Al Viro Signed-off-by: David S. Miller --- net/8021q/vlan_dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 77f04e49a1a0..8fbcefe10c9f 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -382,7 +382,7 @@ static int vlan_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) vlan_dev_info(dev)->cnt_encap_on_xmit++; pr_debug("%s: proto to encap: 0x%hx\n", - __FUNCTION__, htons(veth->h_vlan_proto)); + __FUNCTION__, ntohs(veth->h_vlan_proto)); /* Construct the second two bytes. This field looks something * like: * usr_priority: 3 bits (high bits) -- cgit v1.2.3 From 5e226e4d9016daee170699f8a4188a5505021756 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 17 Mar 2008 22:50:23 -0700 Subject: [IPV4]: esp_output() misannotations Signed-off-by: Al Viro Signed-off-by: David S. Miller --- net/ipv4/esp4.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 091e6709f831..f3ceca31aa45 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -168,7 +168,7 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) struct xfrm_encap_tmpl *encap = x->encap; struct udphdr *uh; __be32 *udpdata32; - unsigned int sport, dport; + __be16 sport, dport; int encap_type; spin_lock_bh(&x->lock); -- cgit v1.2.3