From 44b52bccf855b0706de624c29fc3d82ca954bb4e Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 3 Apr 2012 10:08:48 +0200 Subject: netfilter: xt_CT: remove a compile warning MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If CONFIG_NF_CONNTRACK_TIMEOUT=n we have following warning : CC [M] net/netfilter/xt_CT.o net/netfilter/xt_CT.c: In function ‘xt_ct_tg_check_v1’: net/netfilter/xt_CT.c:284: warning: label ‘err4’ defined but not used Reported-by: Eric Dumazet Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_CT.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net') diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 0c8e43810ce3..138b75e41fdd 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -281,8 +281,10 @@ out: info->ct = ct; return 0; +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT err4: rcu_read_unlock(); +#endif err3: nf_conntrack_free(ct); err2: -- cgit v1.2.3 From 2def16ae6b0c77571200f18ba4be049b03d75579 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 2 Apr 2012 22:33:02 +0000 Subject: net: fix /proc/net/dev regression Commit f04565ddf52 (dev: use name hash for dev_seq_ops) added a second regression, as some devices are missing from /proc/net/dev if many devices are defined. When seq_file buffer is filled, the last ->next/show() method is canceled (pos value is reverted to value prior ->next() call) Problem is after above commit, we dont restart the lookup at right position in ->start() method. Fix this by removing the internal 'pos' pointer added in commit, since we need to use the 'loff_t *pos' provided by seq_file layer. This also reverts commit 5cac98dd0 (net: Fix corruption in /proc/*/net/dev_mcast), since its not needed anymore. Reported-by: Ben Greear Signed-off-by: Eric Dumazet Cc: Mihai Maruseac Tested-by: Ben Greear Signed-off-by: David S. Miller --- net/core/dev.c | 58 +++++++++++------------------------------------ net/core/dev_addr_lists.c | 3 ++- 2 files changed, 15 insertions(+), 46 deletions(-) (limited to 'net') diff --git a/net/core/dev.c b/net/core/dev.c index 6c7dc9d78e10..c25d453b2803 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4028,54 +4028,41 @@ static int dev_ifconf(struct net *net, char __user *arg) #ifdef CONFIG_PROC_FS -#define BUCKET_SPACE (32 - NETDEV_HASHBITS) - -struct dev_iter_state { - struct seq_net_private p; - unsigned int pos; /* bucket << BUCKET_SPACE + offset */ -}; +#define BUCKET_SPACE (32 - NETDEV_HASHBITS - 1) #define get_bucket(x) ((x) >> BUCKET_SPACE) #define get_offset(x) ((x) & ((1 << BUCKET_SPACE) - 1)) #define set_bucket_offset(b, o) ((b) << BUCKET_SPACE | (o)) -static inline struct net_device *dev_from_same_bucket(struct seq_file *seq) +static inline struct net_device *dev_from_same_bucket(struct seq_file *seq, loff_t *pos) { - struct dev_iter_state *state = seq->private; struct net *net = seq_file_net(seq); struct net_device *dev; struct hlist_node *p; struct hlist_head *h; - unsigned int count, bucket, offset; + unsigned int count = 0, offset = get_offset(*pos); - bucket = get_bucket(state->pos); - offset = get_offset(state->pos); - h = &net->dev_name_head[bucket]; - count = 0; + h = &net->dev_name_head[get_bucket(*pos)]; hlist_for_each_entry_rcu(dev, p, h, name_hlist) { - if (count++ == offset) { - state->pos = set_bucket_offset(bucket, count); + if (++count == offset) return dev; - } } return NULL; } -static inline struct net_device *dev_from_new_bucket(struct seq_file *seq) +static inline struct net_device *dev_from_bucket(struct seq_file *seq, loff_t *pos) { - struct dev_iter_state *state = seq->private; struct net_device *dev; unsigned int bucket; - bucket = get_bucket(state->pos); do { - dev = dev_from_same_bucket(seq); + dev = dev_from_same_bucket(seq, pos); if (dev) return dev; - bucket++; - state->pos = set_bucket_offset(bucket, 0); + bucket = get_bucket(*pos) + 1; + *pos = set_bucket_offset(bucket, 1); } while (bucket < NETDEV_HASHENTRIES); return NULL; @@ -4088,33 +4075,20 @@ static inline struct net_device *dev_from_new_bucket(struct seq_file *seq) void *dev_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { - struct dev_iter_state *state = seq->private; - rcu_read_lock(); if (!*pos) return SEQ_START_TOKEN; - /* check for end of the hash */ - if (state->pos == 0 && *pos > 1) + if (get_bucket(*pos) >= NETDEV_HASHENTRIES) return NULL; - return dev_from_new_bucket(seq); + return dev_from_bucket(seq, pos); } void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - struct net_device *dev; - ++*pos; - - if (v == SEQ_START_TOKEN) - return dev_from_new_bucket(seq); - - dev = dev_from_same_bucket(seq); - if (dev) - return dev; - - return dev_from_new_bucket(seq); + return dev_from_bucket(seq, pos); } void dev_seq_stop(struct seq_file *seq, void *v) @@ -4213,13 +4187,7 @@ static const struct seq_operations dev_seq_ops = { static int dev_seq_open(struct inode *inode, struct file *file) { return seq_open_net(inode, file, &dev_seq_ops, - sizeof(struct dev_iter_state)); -} - -int dev_seq_open_ops(struct inode *inode, struct file *file, - const struct seq_operations *ops) -{ - return seq_open_net(inode, file, ops, sizeof(struct dev_iter_state)); + sizeof(struct seq_net_private)); } static const struct file_operations dev_seq_fops = { diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 29c07fef9228..626698f0db8b 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -696,7 +696,8 @@ static const struct seq_operations dev_mc_seq_ops = { static int dev_mc_seq_open(struct inode *inode, struct file *file) { - return dev_seq_open_ops(inode, file, &dev_mc_seq_ops); + return seq_open_net(inode, file, &dev_mc_seq_ops, + sizeof(struct seq_net_private)); } static const struct file_operations dev_mc_seq_fops = { -- cgit v1.2.3 From 2f53384424251c06038ae612e56231b96ab610ee Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 3 Apr 2012 09:37:01 +0000 Subject: tcp: allow splice() to build full TSO packets MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit vmsplice()/splice(pipe, socket) call do_tcp_sendpages() one page at a time, adding at most 4096 bytes to an skb. (assuming PAGE_SIZE=4096) The call to tcp_push() at the end of do_tcp_sendpages() forces an immediate xmit when pipe is not already filled, and tso_fragment() try to split these skb to MSS multiples. 4096 bytes are usually split in a skb with 2 MSS, and a remaining sub-mss skb (assuming MTU=1500) This makes slow start suboptimal because many small frames are sent to qdisc/driver layers instead of big ones (constrained by cwnd and packets in flight of course) In fact, applications using sendmsg() (adding an additional memory copy) instead of vmsplice()/splice()/sendfile() are a bit faster because of this anomaly, especially if serving small files in environments with large initial [c]wnd. Call tcp_push() only if MSG_MORE is not set in the flags parameter. This bit is automatically provided by splice() internals but for the last page, or on all pages if user specified SPLICE_F_MORE splice() flag. In some workloads, this can reduce number of sent logical packets by an order of magnitude, making zero-copy TCP actually faster than one-copy :) Reported-by: Tom Herbert Cc: Nandita Dukkipati Cc: Neal Cardwell Cc: Tom Herbert Cc: Yuchung Cheng Cc: H.K. Jerry Chu Cc: Maciej Żenczykowski Cc: Mahesh Bandewar Cc: Ilpo Järvinen Signed-off-by: Eric Dumazet com> Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index cfd7edda0a8e..2ff6f45a76f4 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -860,7 +860,7 @@ wait_for_memory: } out: - if (copied) + if (copied && !(flags & MSG_MORE)) tcp_push(sk, flags, mss_now, tp->nonagle); return copied; -- cgit v1.2.3 From f03fb3f455c6c3a3dfcef6c7f2dcab104c813f4b Mon Sep 17 00:00:00 2001 From: Jan Seiffert Date: Fri, 30 Mar 2012 05:08:19 +0000 Subject: bpf jit: Make the filter.c::__load_pointer helper non-static for the jits The function is renamed to make it a little more clear what it does. It is not added to any .h because it is not for general consumption, only for bpf internal use (and so by the jits). Signed-of-by: Jan Seiffert Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/filter.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/core/filter.c b/net/core/filter.c index cf4989ac503b..6f755cca4520 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -39,8 +39,11 @@ #include #include -/* No hurry in this branch */ -static void *__load_pointer(const struct sk_buff *skb, int k, unsigned int size) +/* No hurry in this branch + * + * Exported for the bpf jit load helper. + */ +void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size) { u8 *ptr = NULL; @@ -59,7 +62,7 @@ static inline void *load_pointer(const struct sk_buff *skb, int k, { if (k >= 0) return skb_header_pointer(skb, k, size, buffer); - return __load_pointer(skb, k, size); + return bpf_internal_load_pointer_neg_helper(skb, k, size); } /** -- cgit v1.2.3 From ca53e4405347a1e19eaf59c757ceaaaa1a784758 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 3 Apr 2012 12:32:15 +0200 Subject: netfilter: xt_CT: allocation has to be GFP_ATOMIC under rcu_read_lock section Reported-by: Tetsuo Handa Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- net/netfilter/xt_CT.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 138b75e41fdd..4babb278e41e 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -261,7 +261,7 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par) goto err4; } timeout_ext = nf_ct_timeout_ext_add(ct, timeout, - GFP_KERNEL); + GFP_ATOMIC); if (timeout_ext == NULL) { ret = -ENOMEM; goto err4; -- cgit v1.2.3 From ee14186f8d2338227888f3c00a06caf31f94de38 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 3 Apr 2012 14:50:07 +0200 Subject: netfilter: xt_CT: fix missing put timeout object in error path The error path misses putting the timeout object. This patch adds new function xt_ct_tg_timeout_put() to put the timeout object. Reported-by: Tetsuo Handa Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- net/netfilter/xt_CT.c | 24 +++++++++++++++++++----- 1 file changed, 19 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 4babb278e41e..59530e93fa58 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -150,6 +150,17 @@ err1: return ret; } +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT +static void __xt_ct_tg_timeout_put(struct ctnl_timeout *timeout) +{ + typeof(nf_ct_timeout_put_hook) timeout_put; + + timeout_put = rcu_dereference(nf_ct_timeout_put_hook); + if (timeout_put) + timeout_put(timeout); +} +#endif + static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par) { struct xt_ct_target_info_v1 *info = par->targinfo; @@ -158,7 +169,9 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par) struct nf_conn *ct; int ret = 0; u8 proto; - +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT + struct ctnl_timeout *timeout; +#endif if (info->flags & ~XT_CT_NOTRACK) return -EINVAL; @@ -216,7 +229,6 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par) #ifdef CONFIG_NF_CONNTRACK_TIMEOUT if (info->timeout) { typeof(nf_ct_timeout_find_get_hook) timeout_find_get; - struct ctnl_timeout *timeout; struct nf_conn_timeout *timeout_ext; rcu_read_lock(); @@ -245,7 +257,7 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par) pr_info("Timeout policy `%s' can only be " "used by L3 protocol number %d\n", info->timeout, timeout->l3num); - goto err4; + goto err5; } /* Make sure the timeout policy matches any existing * protocol tracker, otherwise default to generic. @@ -258,13 +270,13 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par) "used by L4 protocol number %d\n", info->timeout, timeout->l4proto->l4proto); - goto err4; + goto err5; } timeout_ext = nf_ct_timeout_ext_add(ct, timeout, GFP_ATOMIC); if (timeout_ext == NULL) { ret = -ENOMEM; - goto err4; + goto err5; } } else { ret = -ENOENT; @@ -282,6 +294,8 @@ out: return 0; #ifdef CONFIG_NF_CONNTRACK_TIMEOUT +err5: + __xt_ct_tg_timeout_put(timeout); err4: rcu_read_unlock(); #endif -- cgit v1.2.3 From d96fc659aeb27686cef42d305cfd0c9702f8841c Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 3 Apr 2012 16:45:54 +0200 Subject: netfilter: nf_conntrack: fix count leak in error path of __nf_conntrack_alloc We have to decrement the conntrack counter if we fail to access the zone extension. Reported-by: Tetsuo Handa Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- net/netfilter/nf_conntrack_core.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index cbdb754dbb10..3cc4487ac349 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -735,6 +735,7 @@ __nf_conntrack_alloc(struct net *net, u16 zone, #ifdef CONFIG_NF_CONNTRACK_ZONES out_free: + atomic_dec(&net->ct.count); kmem_cache_free(net->ct.nf_conntrack_cachep, ct); return ERR_PTR(-ENOMEM); #endif -- cgit v1.2.3 From acdd5985364f8dc511a0762fab2e683f29d9d692 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 3 Apr 2012 22:17:53 +0000 Subject: sctp: Allow struct sctp_event_subscribe to grow without breaking binaries getsockopt(..., SCTP_EVENTS, ...) performs a length check and returns an error if the user provides less bytes than the size of struct sctp_event_subscribe. Struct sctp_event_subscribe needs to be extended by an u8 for every new event or notification type that is added. This obviously makes getsockopt fail for binaries that are compiled against an older versions of which do not contain all event types. This patch changes getsockopt behaviour to no longer return an error if not enough bytes are being provided by the user. Instead, it returns as much of sctp_event_subscribe as fits into the provided buffer. This leads to the new behavior that users see what they have been aware of at compile time. The setsockopt(..., SCTP_EVENTS, ...) API is already behaving like this. Signed-off-by: Thomas Graf Acked-by: Vlad Yasevich Signed-off-by: David S. Miller --- net/sctp/socket.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 06b42b7f5a02..92ba71dfe080 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4133,9 +4133,10 @@ static int sctp_getsockopt_disable_fragments(struct sock *sk, int len, static int sctp_getsockopt_events(struct sock *sk, int len, char __user *optval, int __user *optlen) { - if (len < sizeof(struct sctp_event_subscribe)) + if (len <= 0) return -EINVAL; - len = sizeof(struct sctp_event_subscribe); + if (len > sizeof(struct sctp_event_subscribe)) + len = sizeof(struct sctp_event_subscribe); if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &sctp_sk(sk)->subscribe, len)) -- cgit v1.2.3 From 78d50217baf36093ab320f95bae0d6452daec85c Mon Sep 17 00:00:00 2001 From: "RongQing.Li" Date: Wed, 4 Apr 2012 16:47:04 +0000 Subject: ipv6: fix array index in ip6_mc_add_src() Convert array index from the loop bound to the loop index. And remove the void type conversion to ip6_mc_del1_src() return code, seem it is unnecessary, since ip6_mc_del1_src() does not use __must_check similar attribute, no compiler will report the warning when it is removed. v2: enrich the commit header Signed-off-by: RongQing.Li Signed-off-by: David S. Miller --- net/ipv6/mcast.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 16c33e308121..b2869cab2092 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -2044,7 +2044,7 @@ static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca, if (!delta) pmc->mca_sfcount[sfmode]--; for (j=0; jmca_sfcount[MCAST_EXCLUDE] != 0)) { struct ip6_sf_list *psf; -- cgit v1.2.3 From 35f9c09fe9c72eb8ca2b8e89a593e1c151f28fc2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 5 Apr 2012 03:05:35 +0000 Subject: tcp: tcp_sendpages() should call tcp_push() once MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 2f533844242 (tcp: allow splice() to build full TSO packets) added a regression for splice() calls using SPLICE_F_MORE. We need to call tcp_flush() at the end of the last page processed in tcp_sendpages(), or else transmits can be deferred and future sends stall. Add a new internal flag, MSG_SENDPAGE_NOTLAST, acting like MSG_MORE, but with different semantic. For all sendpage() providers, its a transparent change. Only sock_sendpage() and tcp_sendpages() can differentiate the two different flags provided by pipe_to_sendpage() Reported-by: Tom Herbert Cc: Nandita Dukkipati Cc: Neal Cardwell Cc: Tom Herbert Cc: Yuchung Cheng Cc: H.K. Jerry Chu Cc: Maciej Żenczykowski Cc: Mahesh Bandewar Cc: Ilpo Järvinen Signed-off-by: Eric Dumazet com> Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 2 +- net/socket.c | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2ff6f45a76f4..5d54ed30e821 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -860,7 +860,7 @@ wait_for_memory: } out: - if (copied && !(flags & MSG_MORE)) + if (copied && !(flags & MSG_SENDPAGE_NOTLAST)) tcp_push(sk, flags, mss_now, tp->nonagle); return copied; diff --git a/net/socket.c b/net/socket.c index 484cc6953fc6..851edcd6b098 100644 --- a/net/socket.c +++ b/net/socket.c @@ -811,9 +811,9 @@ static ssize_t sock_sendpage(struct file *file, struct page *page, sock = file->private_data; - flags = !(file->f_flags & O_NONBLOCK) ? 0 : MSG_DONTWAIT; - if (more) - flags |= MSG_MORE; + flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0; + /* more is a combination of MSG_MORE and MSG_SENDPAGE_NOTLAST */ + flags |= more; return kernel_sendpage(sock, page, offset, size, flags); } -- cgit v1.2.3 From bcf1b70ac6eb0ed8286c66e6bf37cb747cbaa04c Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Thu, 5 Apr 2012 12:07:45 +0000 Subject: phonet: Check input from user before allocating MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A phonet packet is limited to USHRT_MAX bytes, this is never checked during tx which means that the user can specify any size he wishes, and the kernel will attempt to allocate that size. In the good case, it'll lead to the following warning, but it may also cause the kernel to kick in the OOM and kill a random task on the server. [ 8921.744094] WARNING: at mm/page_alloc.c:2255 __alloc_pages_slowpath+0x65/0x730() [ 8921.749770] Pid: 5081, comm: trinity Tainted: G W 3.4.0-rc1-next-20120402-sasha #46 [ 8921.756672] Call Trace: [ 8921.758185] [] warn_slowpath_common+0x87/0xb0 [ 8921.762868] [] warn_slowpath_null+0x15/0x20 [ 8921.765399] [] __alloc_pages_slowpath+0x65/0x730 [ 8921.769226] [] ? zone_watermark_ok+0x1a/0x20 [ 8921.771686] [] ? get_page_from_freelist+0x625/0x660 [ 8921.773919] [] __alloc_pages_nodemask+0x1f8/0x240 [ 8921.776248] [] kmalloc_large_node+0x70/0xc0 [ 8921.778294] [] __kmalloc_node_track_caller+0x34/0x1c0 [ 8921.780847] [] ? sock_alloc_send_pskb+0xbc/0x260 [ 8921.783179] [] __alloc_skb+0x75/0x170 [ 8921.784971] [] sock_alloc_send_pskb+0xbc/0x260 [ 8921.787111] [] ? release_sock+0x7e/0x90 [ 8921.788973] [] sock_alloc_send_skb+0x10/0x20 [ 8921.791052] [] pep_sendmsg+0x60/0x380 [ 8921.792931] [] ? pn_socket_bind+0x156/0x180 [ 8921.794917] [] ? pn_socket_autobind+0x3f/0x90 [ 8921.797053] [] pn_socket_sendmsg+0x4f/0x70 [ 8921.798992] [] sock_aio_write+0x187/0x1b0 [ 8921.801395] [] ? sub_preempt_count+0xae/0xf0 [ 8921.803501] [] ? __lock_acquire+0x42c/0x4b0 [ 8921.805505] [] ? __sock_recv_ts_and_drops+0x140/0x140 [ 8921.807860] [] do_sync_readv_writev+0xbc/0x110 [ 8921.809986] [] ? might_fault+0x97/0xa0 [ 8921.811998] [] ? security_file_permission+0x1e/0x90 [ 8921.814595] [] do_readv_writev+0xe2/0x1e0 [ 8921.816702] [] ? do_setitimer+0x1ac/0x200 [ 8921.818819] [] ? get_parent_ip+0x11/0x50 [ 8921.820863] [] ? sub_preempt_count+0xae/0xf0 [ 8921.823318] [] vfs_writev+0x46/0x60 [ 8921.825219] [] sys_writev+0x4f/0xb0 [ 8921.827127] [] system_call_fastpath+0x16/0x1b [ 8921.829384] ---[ end trace dffe390f30db9eb7 ]--- Signed-off-by: Sasha Levin Acked-by: Rémi Denis-Courmont Signed-off-by: David S. Miller --- net/phonet/pep.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'net') diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 9f60008740e3..9726fe684ab8 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -1130,6 +1130,9 @@ static int pep_sendmsg(struct kiocb *iocb, struct sock *sk, int flags = msg->msg_flags; int err, done; + if (len > USHRT_MAX) + return -EMSGSIZE; + if ((msg->msg_flags & ~(MSG_DONTWAIT|MSG_EOR|MSG_NOSIGNAL| MSG_CMSG_COMPAT)) || !(msg->msg_flags & MSG_EOR)) -- cgit v1.2.3 From 4a7e7c2ad540e54c75489a70137bf0ec15d3a127 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 5 Apr 2012 22:17:46 +0000 Subject: netlink: fix races after skb queueing As soon as an skb is queued into socket receive_queue, another thread can consume it, so we are not allowed to reference skb anymore, or risk use after free. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/netlink/af_netlink.c | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-) (limited to 'net') diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 32bb75324e76..faa48f70b7c9 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -829,12 +829,19 @@ int netlink_attachskb(struct sock *sk, struct sk_buff *skb, return 0; } -int netlink_sendskb(struct sock *sk, struct sk_buff *skb) +static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb) { int len = skb->len; skb_queue_tail(&sk->sk_receive_queue, skb); sk->sk_data_ready(sk, len); + return len; +} + +int netlink_sendskb(struct sock *sk, struct sk_buff *skb) +{ + int len = __netlink_sendskb(sk, skb); + sock_put(sk); return len; } @@ -957,8 +964,7 @@ static int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb) if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && !test_bit(0, &nlk->state)) { skb_set_owner_r(skb, sk); - skb_queue_tail(&sk->sk_receive_queue, skb); - sk->sk_data_ready(sk, skb->len); + __netlink_sendskb(sk, skb); return atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1); } return -1; @@ -1698,10 +1704,8 @@ static int netlink_dump(struct sock *sk) if (sk_filter(sk, skb)) kfree_skb(skb); - else { - skb_queue_tail(&sk->sk_receive_queue, skb); - sk->sk_data_ready(sk, skb->len); - } + else + __netlink_sendskb(sk, skb); return 0; } @@ -1715,10 +1719,8 @@ static int netlink_dump(struct sock *sk) if (sk_filter(sk, skb)) kfree_skb(skb); - else { - skb_queue_tail(&sk->sk_receive_queue, skb); - sk->sk_data_ready(sk, skb->len); - } + else + __netlink_sendskb(sk, skb); if (cb->done) cb->done(cb); -- cgit v1.2.3 From 110c43304db6f06490961529536c362d9ac5732f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 6 Apr 2012 10:49:10 +0200 Subject: net: fix a race in sock_queue_err_skb() As soon as an skb is queued into socket error queue, another thread can consume it, so we are not allowed to reference skb anymore, or risk use after free. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/skbuff.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/core/skbuff.c b/net/core/skbuff.c index f223cdc75da6..baf8d281152c 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3161,6 +3161,8 @@ static void sock_rmem_free(struct sk_buff *skb) */ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) { + int len = skb->len; + if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= (unsigned)sk->sk_rcvbuf) return -ENOMEM; @@ -3175,7 +3177,7 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) skb_queue_tail(&sk->sk_error_queue, skb); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk, skb->len); + sk->sk_data_ready(sk, len); return 0; } EXPORT_SYMBOL(sock_queue_err_skb); -- cgit v1.2.3