From a7cb5a49bf64ba64864ae16a6be028f8b0d3cc06 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 24 May 2012 01:10:10 -0600 Subject: userns: Print out socket uids in a user namespace aware fashion. Cc: Alexey Kuznetsov Cc: James Morris Cc: Hideaki YOSHIFUJI Cc: Patrick McHardy Cc: Arnaldo Carvalho de Melo Cc: Sridhar Samudrala Acked-by: Vlad Yasevich Acked-by: David S. Miller Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- net/ipv6/raw.c | 3 ++- net/ipv6/tcp_ipv6.c | 6 +++--- net/ipv6/udp.c | 3 ++- 3 files changed, 7 insertions(+), 5 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index ef0579d..7af88ef 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1251,7 +1251,8 @@ static void raw6_sock_seq_show(struct seq_file *seq, struct sock *sp, int i) sk_wmem_alloc_get(sp), sk_rmem_alloc_get(sp), 0, 0L, 0, - sock_i_uid(sp), 0, + from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), + 0, sock_i_ino(sp), atomic_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index c66b90f..4b5b335 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1803,7 +1803,7 @@ static void tcp_v6_destroy_sock(struct sock *sk) #ifdef CONFIG_PROC_FS /* Proc filesystem TCPv6 sock list dumping. */ static void get_openreq6(struct seq_file *seq, - const struct sock *sk, struct request_sock *req, int i, int uid) + const struct sock *sk, struct request_sock *req, int i, kuid_t uid) { int ttd = req->expires - jiffies; const struct in6_addr *src = &inet6_rsk(req)->loc_addr; @@ -1827,7 +1827,7 @@ static void get_openreq6(struct seq_file *seq, 1, /* timers active (only the expire timer) */ jiffies_to_clock_t(ttd), req->retrans, - uid, + from_kuid_munged(seq_user_ns(seq), uid), 0, /* non standard timer */ 0, /* open_requests have no inode */ 0, req); @@ -1877,7 +1877,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) timer_active, jiffies_to_clock_t(timer_expires - jiffies), icsk->icsk_retransmits, - sock_i_uid(sp), + from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), icsk->icsk_probes_out, sock_i_ino(sp), atomic_read(&sp->sk_refcnt), sp, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 99d0077..bbdff07 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1458,7 +1458,8 @@ static void udp6_sock_seq_show(struct seq_file *seq, struct sock *sp, int bucket sk_wmem_alloc_get(sp), sk_rmem_alloc_get(sp), 0, 0L, 0, - sock_i_uid(sp), 0, + from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), + 0, sock_i_ino(sp), atomic_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); -- cgit v1.1 From 4f82f45730c68fdaf9b0472495a965188404866e Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 24 May 2012 10:37:59 -0600 Subject: net ip6 flowlabel: Make owner a union of struct pid * and kuid_t Correct a long standing omission and use struct pid in the owner field of struct ip6_flowlabel when the share type is IPV6_FL_S_PROCESS. This guarantees we don't have issues when pid wraparound occurs. Use a kuid_t in the owner field of struct ip6_flowlabel when the share type is IPV6_FL_S_USER to add user namespace support. In /proc/net/ip6_flowlabel capture the current pid namespace when opening the file and release the pid namespace when the file is closed ensuring we print the pid owner value that is meaning to the reader of the file. Similarly use from_kuid_munged to print uid values that are meaningful to the reader of the file. This requires exporting pid_nr_ns so that ipv6 can continue to built as a module. Yoiks what silliness Acked-by: David S. Miller Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- net/ipv6/ip6_flowlabel.c | 50 +++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 43 insertions(+), 7 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 9772fbd..c836a6a 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include @@ -90,6 +91,11 @@ static struct ip6_flowlabel *fl_lookup(struct net *net, __be32 label) static void fl_free(struct ip6_flowlabel *fl) { + switch (fl->share) { + case IPV6_FL_S_PROCESS: + put_pid(fl->owner.pid); + break; + } if (fl) { release_net(fl->fl_net); kfree(fl->opt); @@ -394,10 +400,10 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq, case IPV6_FL_S_ANY: break; case IPV6_FL_S_PROCESS: - fl->owner = current->pid; + fl->owner.pid = get_task_pid(current, PIDTYPE_PID); break; case IPV6_FL_S_USER: - fl->owner = current_euid(); + fl->owner.uid = current_euid(); break; default: err = -EINVAL; @@ -561,7 +567,10 @@ recheck: err = -EPERM; if (fl1->share == IPV6_FL_S_EXCL || fl1->share != fl->share || - fl1->owner != fl->owner) + ((fl1->share == IPV6_FL_S_PROCESS) && + (fl1->owner.pid == fl->owner.pid)) || + ((fl1->share == IPV6_FL_S_USER) && + uid_eq(fl1->owner.uid, fl->owner.uid))) goto release; err = -EINVAL; @@ -621,6 +630,7 @@ done: struct ip6fl_iter_state { struct seq_net_private p; + struct pid_namespace *pid_ns; int bucket; }; @@ -699,6 +709,7 @@ static void ip6fl_seq_stop(struct seq_file *seq, void *v) static int ip6fl_seq_show(struct seq_file *seq, void *v) { + struct ip6fl_iter_state *state = ip6fl_seq_private(seq); if (v == SEQ_START_TOKEN) seq_printf(seq, "%-5s %-1s %-6s %-6s %-6s %-8s %-32s %s\n", "Label", "S", "Owner", "Users", "Linger", "Expires", "Dst", "Opt"); @@ -708,7 +719,11 @@ static int ip6fl_seq_show(struct seq_file *seq, void *v) "%05X %-1d %-6d %-6d %-6ld %-8ld %pi6 %-4d\n", (unsigned int)ntohl(fl->label), fl->share, - (int)fl->owner, + ((fl->share == IPV6_FL_S_PROCESS) ? + pid_nr_ns(fl->owner.pid, state->pid_ns) : + ((fl->share == IPV6_FL_S_USER) ? + from_kuid_munged(seq_user_ns(seq), fl->owner.uid) : + 0)), atomic_read(&fl->users), fl->linger/HZ, (long)(fl->expires - jiffies)/HZ, @@ -727,8 +742,29 @@ static const struct seq_operations ip6fl_seq_ops = { static int ip6fl_seq_open(struct inode *inode, struct file *file) { - return seq_open_net(inode, file, &ip6fl_seq_ops, - sizeof(struct ip6fl_iter_state)); + struct seq_file *seq; + struct ip6fl_iter_state *state; + int err; + + err = seq_open_net(inode, file, &ip6fl_seq_ops, + sizeof(struct ip6fl_iter_state)); + + if (!err) { + seq = file->private_data; + state = ip6fl_seq_private(seq); + rcu_read_lock(); + state->pid_ns = get_pid_ns(task_active_pid_ns(current)); + rcu_read_unlock(); + } + return err; +} + +static int ip6fl_seq_release(struct inode *inode, struct file *file) +{ + struct seq_file *seq = file->private_data; + struct ip6fl_iter_state *state = ip6fl_seq_private(seq); + put_pid_ns(state->pid_ns); + return seq_release_net(inode, file); } static const struct file_operations ip6fl_seq_fops = { @@ -736,7 +772,7 @@ static const struct file_operations ip6fl_seq_fops = { .open = ip6fl_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_net, + .release = ip6fl_seq_release, }; static int __net_init ip6_flowlabel_proc_init(struct net *net) -- cgit v1.1 From 898132ae76d1aeb52301f10e8795c34fbb54e853 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 16 Aug 2012 16:15:02 +0300 Subject: ipv6: move dereference after check in fl_free() There is a dereference before checking for NULL bug here. Generally free() functions should accept NULL pointers. For example, fl_create() can pass a NULL pointer to fl_free() on the error path. Signed-off-by: Dan Carpenter Signed-off-by: Eric W. Biederman --- net/ipv6/ip6_flowlabel.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index c836a6a..90bbefb 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -91,12 +91,9 @@ static struct ip6_flowlabel *fl_lookup(struct net *net, __be32 label) static void fl_free(struct ip6_flowlabel *fl) { - switch (fl->share) { - case IPV6_FL_S_PROCESS: - put_pid(fl->owner.pid); - break; - } if (fl) { + if (fl->share == IPV6_FL_S_PROCESS) + put_pid(fl->owner.pid); release_net(fl->fl_net); kfree(fl->opt); } -- cgit v1.1 From 748e2d9396a18c3fd3d07d47c1b41320acf1fbf4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 22 Aug 2012 21:50:59 +0000 Subject: net: reinstate rtnl in call_netdevice_notifiers() Eric Biederman pointed out that not holding RTNL while calling call_netdevice_notifiers() was racy. This patch is a direct transcription his feedback against commit 0115e8e30d6fc (net: remove delay at device dismantle) Thanks Eric ! Signed-off-by: Eric Dumazet Cc: Tom Herbert Cc: Mahesh Bandewar Cc: "Eric W. Biederman" Cc: Gao feng Acked-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index e581009..6bc85f7 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2566,14 +2566,10 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, void *data) { struct net_device *dev = (struct net_device *) data; - struct inet6_dev *idev; + struct inet6_dev *idev = __in6_dev_get(dev); int run_pending = 0; int err; - if (event == NETDEV_UNREGISTER_FINAL) - return NOTIFY_DONE; - - idev = __in6_dev_get(dev); switch (event) { case NETDEV_REGISTER: if (!idev && dev->mtu >= IPV6_MIN_MTU) { -- cgit v1.1 From eb7e0575966f9c84434e92c8a3f69719cc2e7571 Mon Sep 17 00:00:00 2001 From: Sorin Dumitru Date: Thu, 30 Aug 2012 02:01:45 +0000 Subject: ipv6: remove some deadcode __ipv6_regen_rndid no longer returns anything other than 0 so there's no point in verifying what it returns Signed-off-by: Sorin Dumitru Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 29 +++++++---------------------- 1 file changed, 7 insertions(+), 22 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 6bc85f7..055627f 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -127,8 +127,8 @@ static inline void addrconf_sysctl_unregister(struct inet6_dev *idev) #endif #ifdef CONFIG_IPV6_PRIVACY -static int __ipv6_regen_rndid(struct inet6_dev *idev); -static int __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr); +static void __ipv6_regen_rndid(struct inet6_dev *idev); +static void __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr); static void ipv6_regen_rndid(unsigned long data); #endif @@ -852,16 +852,7 @@ retry: } in6_ifa_hold(ifp); memcpy(addr.s6_addr, ifp->addr.s6_addr, 8); - if (__ipv6_try_regen_rndid(idev, tmpaddr) < 0) { - spin_unlock_bh(&ifp->lock); - write_unlock(&idev->lock); - pr_warn("%s: regeneration of randomized interface id failed\n", - __func__); - in6_ifa_put(ifp); - in6_dev_put(idev); - ret = -1; - goto out; - } + __ipv6_try_regen_rndid(idev, tmpaddr); memcpy(&addr.s6_addr[8], idev->rndid, 8); age = (now - ifp->tstamp) / HZ; tmp_valid_lft = min_t(__u32, @@ -1600,7 +1591,7 @@ static int ipv6_inherit_eui64(u8 *eui, struct inet6_dev *idev) #ifdef CONFIG_IPV6_PRIVACY /* (re)generation of randomized interface identifier (RFC 3041 3.2, 3.5) */ -static int __ipv6_regen_rndid(struct inet6_dev *idev) +static void __ipv6_regen_rndid(struct inet6_dev *idev) { regen: get_random_bytes(idev->rndid, sizeof(idev->rndid)); @@ -1627,8 +1618,6 @@ regen: if ((idev->rndid[2]|idev->rndid[3]|idev->rndid[4]|idev->rndid[5]|idev->rndid[6]|idev->rndid[7]) == 0x00) goto regen; } - - return 0; } static void ipv6_regen_rndid(unsigned long data) @@ -1642,8 +1631,7 @@ static void ipv6_regen_rndid(unsigned long data) if (idev->dead) goto out; - if (__ipv6_regen_rndid(idev) < 0) - goto out; + __ipv6_regen_rndid(idev); expires = jiffies + idev->cnf.temp_prefered_lft * HZ - @@ -1664,13 +1652,10 @@ out: in6_dev_put(idev); } -static int __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr) +static void __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr) { - int ret = 0; - if (tmpaddr && memcmp(idev->rndid, &tmpaddr->s6_addr[8], 8) == 0) - ret = __ipv6_regen_rndid(idev); - return ret; + __ipv6_regen_rndid(idev); } #endif -- cgit v1.1 From 8336886f786fdacbc19b719c1f7ea91eb70706d4 Mon Sep 17 00:00:00 2001 From: Jerry Chu Date: Fri, 31 Aug 2012 12:29:12 +0000 Subject: tcp: TCP Fast Open Server - support TFO listeners This patch builds on top of the previous patch to add the support for TFO listeners. This includes - 1. allocating, properly initializing, and managing the per listener fastopen_queue structure when TFO is enabled 2. changes to the inet_csk_accept code to support TFO. E.g., the request_sock can no longer be freed upon accept(), not until 3WHS finishes 3. allowing a TCP_SYN_RECV socket to properly poll() and sendmsg() if it's a TFO socket 4. properly closing a TFO listener, and a TFO socket before 3WHS finishes 5. supporting TCP_FASTOPEN socket option 6. modifying tcp_check_req() to use to check a TFO socket as well as request_sock 7. supporting TCP's TFO cookie option 8. adding a new SYN-ACK retransmit handler to use the timer directly off the TFO socket rather than the listener socket. Note that TFO server side will not retransmit anything other than SYN-ACK until the 3WHS is completed. The patch also contains an important function "reqsk_fastopen_remove()" to manage the somewhat complex relation between a listener, its request_sock, and the corresponding child socket. See the comment above the function for the detail. Signed-off-by: H.K. Jerry Chu Cc: Yuchung Cheng Cc: Neal Cardwell Cc: Eric Dumazet Cc: Tom Herbert Signed-off-by: David S. Miller --- net/ipv6/syncookies.c | 1 + net/ipv6/tcp_ipv6.c | 5 +++-- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index bb46061..182ab9a 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -190,6 +190,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq = inet_rsk(req); ireq6 = inet6_rsk(req); treq = tcp_rsk(req); + treq->listener = NULL; if (security_inet_conn_request(sk, skb, req)) goto out_free; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index f99b81d..09078b9 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -475,7 +475,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst, if (!dst && (dst = inet6_csk_route_req(sk, fl6, req)) == NULL) goto done; - skb = tcp_make_synack(sk, dst, req, rvp); + skb = tcp_make_synack(sk, dst, req, rvp, NULL); if (skb) { __tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr); @@ -987,7 +987,7 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, inet6_iif(skb)); if (req) - return tcp_check_req(sk, skb, req, prev); + return tcp_check_req(sk, skb, req, prev, false); nsk = __inet6_lookup_established(sock_net(sk), &tcp_hashinfo, &ipv6_hdr(skb)->saddr, th->source, @@ -1179,6 +1179,7 @@ have_isn: want_cookie) goto drop_and_free; + tcp_rsk(req)->listener = NULL; inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); return 0; -- cgit v1.1