summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2015-04-27 14:05:19 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2015-04-27 14:05:19 -0700
commit2decb2682f80759f631c8332f9a2a34a02150a03 (patch)
tree6c30015e4118ff6a56c67043f2ba842ed4a6e011 /net
parentb787f68c36d49bb1d9236f403813641efa74a031 (diff)
parent22a8f237c0551bae95ffcd2a7ff17d6f5fcce7e7 (diff)
downloadkernel-2decb2682f80759f631c8332f9a2a34a02150a03.tar.gz
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Pull networking fixes from David Miller: 1) mlx4 doesn't check fully for supported valid RSS hash function, fix from Amir Vadai 2) Off by one in ibmveth_change_mtu(), from David Gibson 3) Prevent altera chip from reporting false error interrupts in some circumstances, from Chee Nouk Phoon 4) Get rid of that stupid endless loop trying to allocate a FIN packet in TCP, and in the process kill deadlocks. From Eric Dumazet 5) Fix get_rps_cpus() crash due to wrong invalid-cpu value, also from Eric Dumazet 6) Fix two bugs in async rhashtable resizing, from Thomas Graf 7) Fix topology server listener socket namespace bug in TIPC, from Ying Xue 8) Add some missing HAS_DMA kconfig dependencies, from Geert Uytterhoeven 9) bgmac driver intends to force re-polling but does so by returning the wrong value from it's ->poll() handler. Fix from Rafał Miłecki 10) When the creater of an rhashtable configures a max size for it, don't bark in the logs and drop insertions when that is exceeded. Fix from Johannes Berg 11) Recover from out of order packets in ppp mppe properly, from Sylvain Rochet * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (41 commits) bnx2x: really disable TPA if 'disable_tpa' option is set net:treewide: Fix typo in drivers/net net/mlx4_en: Prevent setting invalid RSS hash function mdio-mux-gpio: use new gpiod_get_array and gpiod_put_array functions netfilter; Add some missing default cases to switch statements in nft_reject. ppp: mppe: discard late packet in stateless mode ppp: mppe: sanity error path rework net/bonding: Make DRV macros private net: rfs: fix crash in get_rps_cpus() altera tse: add support for fixed-links. pxa168: fix double deallocation of managed resources net: fix crash in build_skb() net: eth: altera: Resolve false errors from MSGDMA to TSE ehea: Fix memory hook reference counting crashes net/tg3: Release IRQs on permanent error net: mdio-gpio: support access that may sleep inet: fix possible panic in reqsk_queue_unlink() rhashtable: don't attempt to grow when at max_size bgmac: fix requests for extra polling calls from NAPI tcp: avoid looping in tcp_send_fin() ...
Diffstat (limited to 'net')
-rw-r--r--net/core/dev.c12
-rw-r--r--net/core/skbuff.c30
-rw-r--r--net/dccp/ipv4.c3
-rw-r--r--net/dccp/ipv6.c3
-rw-r--r--net/dccp/minisocks.c3
-rw-r--r--net/ipv4/inet_connection_sock.c34
-rw-r--r--net/ipv4/tcp_ipv4.c3
-rw-r--r--net/ipv4/tcp_minisocks.c7
-rw-r--r--net/ipv4/tcp_output.c64
-rw-r--r--net/ipv6/ip6_gre.c9
-rw-r--r--net/ipv6/tcp_ipv6.c3
-rw-r--r--net/mpls/af_mpls.c125
-rw-r--r--net/mpls/internal.h6
-rw-r--r--net/netfilter/nft_reject.c2
-rw-r--r--net/netfilter/nft_reject_inet.c2
-rw-r--r--net/netlink/af_netlink.c6
-rw-r--r--net/tipc/link.c1
-rw-r--r--net/tipc/server.c9
-rw-r--r--net/tipc/socket.c3
-rw-r--r--net/unix/garbage.c70
20 files changed, 290 insertions, 105 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index 1796cef55ab5..c7ba0388f1be 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3079,7 +3079,7 @@ static struct rps_dev_flow *
set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
struct rps_dev_flow *rflow, u16 next_cpu)
{
- if (next_cpu != RPS_NO_CPU) {
+ if (next_cpu < nr_cpu_ids) {
#ifdef CONFIG_RFS_ACCEL
struct netdev_rx_queue *rxqueue;
struct rps_dev_flow_table *flow_table;
@@ -3184,7 +3184,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
* If the desired CPU (where last recvmsg was done) is
* different from current CPU (one in the rx-queue flow
* table entry), switch if one of the following holds:
- * - Current CPU is unset (equal to RPS_NO_CPU).
+ * - Current CPU is unset (>= nr_cpu_ids).
* - Current CPU is offline.
* - The current CPU's queue tail has advanced beyond the
* last packet that was enqueued using this table entry.
@@ -3192,14 +3192,14 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
* have been dequeued, thus preserving in order delivery.
*/
if (unlikely(tcpu != next_cpu) &&
- (tcpu == RPS_NO_CPU || !cpu_online(tcpu) ||
+ (tcpu >= nr_cpu_ids || !cpu_online(tcpu) ||
((int)(per_cpu(softnet_data, tcpu).input_queue_head -
rflow->last_qtail)) >= 0)) {
tcpu = next_cpu;
rflow = set_rps_cpu(dev, skb, rflow, next_cpu);
}
- if (tcpu != RPS_NO_CPU && cpu_online(tcpu)) {
+ if (tcpu < nr_cpu_ids && cpu_online(tcpu)) {
*rflowp = rflow;
cpu = tcpu;
goto done;
@@ -3240,14 +3240,14 @@ bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index,
struct rps_dev_flow_table *flow_table;
struct rps_dev_flow *rflow;
bool expire = true;
- int cpu;
+ unsigned int cpu;
rcu_read_lock();
flow_table = rcu_dereference(rxqueue->rps_flow_table);
if (flow_table && flow_id <= flow_table->mask) {
rflow = &flow_table->flows[flow_id];
cpu = ACCESS_ONCE(rflow->cpu);
- if (rflow->filter == filter_id && cpu != RPS_NO_CPU &&
+ if (rflow->filter == filter_id && cpu < nr_cpu_ids &&
((int)(per_cpu(softnet_data, cpu).input_queue_head -
rflow->last_qtail) <
(int)(10 * flow_table->mask)))
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index d1967dab9cc6..3cfff2a3d651 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -280,13 +280,14 @@ nodata:
EXPORT_SYMBOL(__alloc_skb);
/**
- * build_skb - build a network buffer
+ * __build_skb - build a network buffer
* @data: data buffer provided by caller
- * @frag_size: size of fragment, or 0 if head was kmalloced
+ * @frag_size: size of data, or 0 if head was kmalloced
*
* Allocate a new &sk_buff. Caller provides space holding head and
* skb_shared_info. @data must have been allocated by kmalloc() only if
- * @frag_size is 0, otherwise data should come from the page allocator.
+ * @frag_size is 0, otherwise data should come from the page allocator
+ * or vmalloc()
* The return is the new skb buffer.
* On a failure the return is %NULL, and @data is not freed.
* Notes :
@@ -297,7 +298,7 @@ EXPORT_SYMBOL(__alloc_skb);
* before giving packet to stack.
* RX rings only contains data buffers, not full skbs.
*/
-struct sk_buff *build_skb(void *data, unsigned int frag_size)
+struct sk_buff *__build_skb(void *data, unsigned int frag_size)
{
struct skb_shared_info *shinfo;
struct sk_buff *skb;
@@ -311,7 +312,6 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
memset(skb, 0, offsetof(struct sk_buff, tail));
skb->truesize = SKB_TRUESIZE(size);
- skb->head_frag = frag_size != 0;
atomic_set(&skb->users, 1);
skb->head = data;
skb->data = data;
@@ -328,6 +328,23 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
return skb;
}
+
+/* build_skb() is wrapper over __build_skb(), that specifically
+ * takes care of skb->head and skb->pfmemalloc
+ * This means that if @frag_size is not zero, then @data must be backed
+ * by a page fragment, not kmalloc() or vmalloc()
+ */
+struct sk_buff *build_skb(void *data, unsigned int frag_size)
+{
+ struct sk_buff *skb = __build_skb(data, frag_size);
+
+ if (skb && frag_size) {
+ skb->head_frag = 1;
+ if (virt_to_head_page(data)->pfmemalloc)
+ skb->pfmemalloc = 1;
+ }
+ return skb;
+}
EXPORT_SYMBOL(build_skb);
struct netdev_alloc_cache {
@@ -348,7 +365,8 @@ static struct page *__page_frag_refill(struct netdev_alloc_cache *nc,
gfp_t gfp = gfp_mask;
if (order) {
- gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY;
+ gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY |
+ __GFP_NOMEMALLOC;
page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, order);
nc->frag.size = PAGE_SIZE << (page ? order : 0);
}
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 2b4f21d34df6..ccf4c5629b3c 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -453,7 +453,8 @@ static struct sock *dccp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
iph->saddr, iph->daddr);
if (req) {
nsk = dccp_check_req(sk, skb, req);
- reqsk_put(req);
+ if (!nsk)
+ reqsk_put(req);
return nsk;
}
nsk = inet_lookup_established(sock_net(sk), &dccp_hashinfo,
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 9d0551092c6c..5165571f397a 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -301,7 +301,8 @@ static struct sock *dccp_v6_hnd_req(struct sock *sk,struct sk_buff *skb)
&iph->daddr, inet6_iif(skb));
if (req) {
nsk = dccp_check_req(sk, skb, req);
- reqsk_put(req);
+ if (!nsk)
+ reqsk_put(req);
return nsk;
}
nsk = __inet6_lookup_established(sock_net(sk), &dccp_hashinfo,
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index 5f566663e47f..30addee2dd03 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -186,8 +186,7 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
if (child == NULL)
goto listen_overflow;
- inet_csk_reqsk_queue_unlink(sk, req);
- inet_csk_reqsk_queue_removed(sk, req);
+ inet_csk_reqsk_queue_drop(sk, req);
inet_csk_reqsk_queue_add(sk, req, child);
out:
return child;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 5c3dd6267ed3..8976ca423a07 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -564,6 +564,40 @@ int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req)
}
EXPORT_SYMBOL(inet_rtx_syn_ack);
+/* return true if req was found in the syn_table[] */
+static bool reqsk_queue_unlink(struct request_sock_queue *queue,
+ struct request_sock *req)
+{
+ struct listen_sock *lopt = queue->listen_opt;
+ struct request_sock **prev;
+ bool found = false;
+
+ spin_lock(&queue->syn_wait_lock);
+
+ for (prev = &lopt->syn_table[req->rsk_hash]; *prev != NULL;
+ prev = &(*prev)->dl_next) {
+ if (*prev == req) {
+ *prev = req->dl_next;
+ found = true;
+ break;
+ }
+ }
+
+ spin_unlock(&queue->syn_wait_lock);
+ if (del_timer(&req->rsk_timer))
+ reqsk_put(req);
+ return found;
+}
+
+void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req)
+{
+ if (reqsk_queue_unlink(&inet_csk(sk)->icsk_accept_queue, req)) {
+ reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req);
+ reqsk_put(req);
+ }
+}
+EXPORT_SYMBOL(inet_csk_reqsk_queue_drop);
+
static void reqsk_timer_handler(unsigned long data)
{
struct request_sock *req = (struct request_sock *)data;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 3571f2be4470..fc1c658ec6c1 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1348,7 +1348,8 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
req = inet_csk_search_req(sk, th->source, iph->saddr, iph->daddr);
if (req) {
nsk = tcp_check_req(sk, skb, req, false);
- reqsk_put(req);
+ if (!nsk)
+ reqsk_put(req);
return nsk;
}
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 63d6311b5365..e5d7649136fc 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -755,10 +755,11 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
if (!child)
goto listen_overflow;
- inet_csk_reqsk_queue_unlink(sk, req);
- inet_csk_reqsk_queue_removed(sk, req);
-
+ inet_csk_reqsk_queue_drop(sk, req);
inet_csk_reqsk_queue_add(sk, req, child);
+ /* Warning: caller must not call reqsk_put(req);
+ * child stole last reference on it.
+ */
return child;
listen_overflow:
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8c8d7e06b72f..a369e8a70b2c 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2812,39 +2812,65 @@ begin_fwd:
}
}
-/* Send a fin. The caller locks the socket for us. This cannot be
- * allowed to fail queueing a FIN frame under any circumstances.
+/* We allow to exceed memory limits for FIN packets to expedite
+ * connection tear down and (memory) recovery.
+ * Otherwise tcp_send_fin() could be tempted to either delay FIN
+ * or even be forced to close flow without any FIN.
+ */
+static void sk_forced_wmem_schedule(struct sock *sk, int size)
+{
+ int amt, status;
+
+ if (size <= sk->sk_forward_alloc)
+ return;
+ amt = sk_mem_pages(size);
+ sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
+ sk_memory_allocated_add(sk, amt, &status);
+}
+
+/* Send a FIN. The caller locks the socket for us.
+ * We should try to send a FIN packet really hard, but eventually give up.
*/
void tcp_send_fin(struct sock *sk)
{
+ struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk);
struct tcp_sock *tp = tcp_sk(sk);
- struct sk_buff *skb = tcp_write_queue_tail(sk);
- int mss_now;
- /* Optimization, tack on the FIN if we have a queue of
- * unsent frames. But be careful about outgoing SACKS
- * and IP options.
+ /* Optimization, tack on the FIN if we have one skb in write queue and
+ * this skb was not yet sent, or we are under memory pressure.
+ * Note: in the latter case, FIN packet will be sent after a timeout,
+ * as TCP stack thinks it has already been transmitted.
*/
- mss_now = tcp_current_mss(sk);
-
- if (tcp_send_head(sk)) {
- TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_FIN;
- TCP_SKB_CB(skb)->end_seq++;
+ if (tskb && (tcp_send_head(sk) || sk_under_memory_pressure(sk))) {
+coalesce:
+ TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN;
+ TCP_SKB_CB(tskb)->end_seq++;
tp->write_seq++;
+ if (!tcp_send_head(sk)) {
+ /* This means tskb was already sent.
+ * Pretend we included the FIN on previous transmit.
+ * We need to set tp->snd_nxt to the value it would have
+ * if FIN had been sent. This is because retransmit path
+ * does not change tp->snd_nxt.
+ */
+ tp->snd_nxt++;
+ return;
+ }
} else {
- /* Socket is locked, keep trying until memory is available. */
- for (;;) {
- skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation);
- if (skb)
- break;
- yield();
+ skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation);
+ if (unlikely(!skb)) {
+ if (tskb)
+ goto coalesce;
+ return;
}
+ skb_reserve(skb, MAX_TCP_HEADER);
+ sk_forced_wmem_schedule(sk, skb->truesize);
/* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */
tcp_init_nondata_skb(skb, tp->write_seq,
TCPHDR_ACK | TCPHDR_FIN);
tcp_queue_skb(sk, skb);
}
- __tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_OFF);
+ __tcp_push_pending_frames(sk, tcp_current_mss(sk), TCP_NAGLE_OFF);
}
/* We get here when a process closes a file descriptor (either due to
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index b5e6cc1d4a73..a38d3ac0f18f 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1246,7 +1246,6 @@ static void ip6gre_tunnel_setup(struct net_device *dev)
static int ip6gre_tunnel_init(struct net_device *dev)
{
struct ip6_tnl *tunnel;
- int i;
tunnel = netdev_priv(dev);
@@ -1260,16 +1259,10 @@ static int ip6gre_tunnel_init(struct net_device *dev)
if (ipv6_addr_any(&tunnel->parms.raddr))
dev->header_ops = &ip6gre_header_ops;
- dev->tstats = alloc_percpu(struct pcpu_sw_netstats);
+ dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
if (!dev->tstats)
return -ENOMEM;
- for_each_possible_cpu(i) {
- struct pcpu_sw_netstats *ip6gre_tunnel_stats;
- ip6gre_tunnel_stats = per_cpu_ptr(dev->tstats, i);
- u64_stats_init(&ip6gre_tunnel_stats->syncp);
- }
-
return 0;
}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index ad51df85aa00..b6575d665568 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -946,7 +946,8 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk, struct sk_buff *skb)
&ipv6_hdr(skb)->daddr, tcp_v6_iif(skb));
if (req) {
nsk = tcp_check_req(sk, skb, req, false);
- reqsk_put(req);
+ if (!nsk)
+ reqsk_put(req);
return nsk;
}
nsk = __inet6_lookup_established(sock_net(sk), &tcp_hashinfo,
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index db8a2ea6d4de..954810c76a86 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -53,6 +53,11 @@ static struct mpls_route *mpls_route_input_rcu(struct net *net, unsigned index)
return rt;
}
+static inline struct mpls_dev *mpls_dev_get(const struct net_device *dev)
+{
+ return rcu_dereference_rtnl(dev->mpls_ptr);
+}
+
static bool mpls_output_possible(const struct net_device *dev)
{
return dev && (dev->flags & IFF_UP) && netif_carrier_ok(dev);
@@ -136,6 +141,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
struct mpls_route *rt;
struct mpls_entry_decoded dec;
struct net_device *out_dev;
+ struct mpls_dev *mdev;
unsigned int hh_len;
unsigned int new_header_size;
unsigned int mtu;
@@ -143,6 +149,10 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
/* Careful this entire function runs inside of an rcu critical section */
+ mdev = mpls_dev_get(dev);
+ if (!mdev || !mdev->input_enabled)
+ goto drop;
+
if (skb->pkt_type != PACKET_HOST)
goto drop;
@@ -352,9 +362,9 @@ static int mpls_route_add(struct mpls_route_config *cfg)
if (!dev)
goto errout;
- /* For now just support ethernet devices */
+ /* Ensure this is a supported device */
err = -EINVAL;
- if ((dev->type != ARPHRD_ETHER) && (dev->type != ARPHRD_LOOPBACK))
+ if (!mpls_dev_get(dev))
goto errout;
err = -EINVAL;
@@ -428,10 +438,89 @@ errout:
return err;
}
+#define MPLS_PERDEV_SYSCTL_OFFSET(field) \
+ (&((struct mpls_dev *)0)->field)
+
+static const struct ctl_table mpls_dev_table[] = {
+ {
+ .procname = "input",
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ .data = MPLS_PERDEV_SYSCTL_OFFSET(input_enabled),
+ },
+ { }
+};
+
+static int mpls_dev_sysctl_register(struct net_device *dev,
+ struct mpls_dev *mdev)
+{
+ char path[sizeof("net/mpls/conf/") + IFNAMSIZ];
+ struct ctl_table *table;
+ int i;
+
+ table = kmemdup(&mpls_dev_table, sizeof(mpls_dev_table), GFP_KERNEL);
+ if (!table)
+ goto out;
+
+ /* Table data contains only offsets relative to the base of
+ * the mdev at this point, so make them absolute.
+ */
+ for (i = 0; i < ARRAY_SIZE(mpls_dev_table); i++)
+ table[i].data = (char *)mdev + (uintptr_t)table[i].data;
+
+ snprintf(path, sizeof(path), "net/mpls/conf/%s", dev->name);
+
+ mdev->sysctl = register_net_sysctl(dev_net(dev), path, table);
+ if (!mdev->sysctl)
+ goto free;
+
+ return 0;
+
+free:
+ kfree(table);
+out:
+ return -ENOBUFS;
+}
+
+static void mpls_dev_sysctl_unregister(struct mpls_dev *mdev)
+{
+ struct ctl_table *table;
+
+ table = mdev->sysctl->ctl_table_arg;
+ unregister_net_sysctl_table(mdev->sysctl);
+ kfree(table);
+}
+
+static struct mpls_dev *mpls_add_dev(struct net_device *dev)
+{
+ struct mpls_dev *mdev;
+ int err = -ENOMEM;
+
+ ASSERT_RTNL();
+
+ mdev = kzalloc(sizeof(*mdev), GFP_KERNEL);
+ if (!mdev)
+ return ERR_PTR(err);
+
+ err = mpls_dev_sysctl_register(dev, mdev);
+ if (err)
+ goto free;
+
+ rcu_assign_pointer(dev->mpls_ptr, mdev);
+
+ return mdev;
+
+free:
+ kfree(mdev);
+ return ERR_PTR(err);
+}
+
static void mpls_ifdown(struct net_device *dev)
{
struct mpls_route __rcu **platform_label;
struct net *net = dev_net(dev);
+ struct mpls_dev *mdev;
unsigned index;
platform_label = rtnl_dereference(net->mpls.platform_label);
@@ -443,14 +532,35 @@ static void mpls_ifdown(struct net_device *dev)
continue;
rt->rt_dev = NULL;
}
+
+ mdev = mpls_dev_get(dev);
+ if (!mdev)
+ return;
+
+ mpls_dev_sysctl_unregister(mdev);
+
+ RCU_INIT_POINTER(dev->mpls_ptr, NULL);
+
+ kfree(mdev);
}
static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
void *ptr)
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+ struct mpls_dev *mdev;
switch(event) {
+ case NETDEV_REGISTER:
+ /* For now just support ethernet devices */
+ if ((dev->type == ARPHRD_ETHER) ||
+ (dev->type == ARPHRD_LOOPBACK)) {
+ mdev = mpls_add_dev(dev);
+ if (IS_ERR(mdev))
+ return notifier_from_errno(PTR_ERR(mdev));
+ }
+ break;
+
case NETDEV_UNREGISTER:
mpls_ifdown(dev);
break;
@@ -536,6 +646,15 @@ int nla_get_labels(const struct nlattr *nla,
if ((dec.bos != bos) || dec.ttl || dec.tc)
return -EINVAL;
+ switch (dec.label) {
+ case LABEL_IMPLICIT_NULL:
+ /* RFC3032: This is a label that an LSR may
+ * assign and distribute, but which never
+ * actually appears in the encapsulation.
+ */
+ return -EINVAL;
+ }
+
label[i] = dec.label;
}
*labels = nla_labels;
@@ -912,7 +1031,7 @@ static int mpls_platform_labels(struct ctl_table *table, int write,
return ret;
}
-static struct ctl_table mpls_table[] = {
+static const struct ctl_table mpls_table[] = {
{
.procname = "platform_labels",
.data = NULL,
diff --git a/net/mpls/internal.h b/net/mpls/internal.h
index fb6de92052c4..693877d69606 100644
--- a/net/mpls/internal.h
+++ b/net/mpls/internal.h
@@ -22,6 +22,12 @@ struct mpls_entry_decoded {
u8 bos;
};
+struct mpls_dev {
+ int input_enabled;
+
+ struct ctl_table_header *sysctl;
+};
+
struct sk_buff;
static inline struct mpls_shim_hdr *mpls_hdr(const struct sk_buff *skb)
diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c
index 57d3e1af5630..0522fc9bfb0a 100644
--- a/net/netfilter/nft_reject.c
+++ b/net/netfilter/nft_reject.c
@@ -63,6 +63,8 @@ int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr)
if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code))
goto nla_put_failure;
break;
+ default:
+ break;
}
return 0;
diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c
index 62cabee42fbe..635dbba93d01 100644
--- a/net/netfilter/nft_reject_inet.c
+++ b/net/netfilter/nft_reject_inet.c
@@ -108,6 +108,8 @@ static int nft_reject_inet_dump(struct sk_buff *skb,
if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code))
goto nla_put_failure;
break;
+ default:
+ break;
}
return 0;
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 19909d0786a2..ec4adbdcb9b4 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1629,13 +1629,11 @@ static struct sk_buff *netlink_alloc_large_skb(unsigned int size,
if (data == NULL)
return NULL;
- skb = build_skb(data, size);
+ skb = __build_skb(data, size);
if (skb == NULL)
vfree(data);
- else {
- skb->head_frag = 0;
+ else
skb->destructor = netlink_skb_destructor;
- }
return skb;
}
diff --git a/net/tipc/link.c b/net/tipc/link.c
index a6b30df6ec02..57be6e6aff99 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -2143,7 +2143,6 @@ int tipc_nl_link_dump(struct sk_buff *skb, struct netlink_callback *cb)
err = __tipc_nl_add_node_links(net, &msg, node,
&prev_link);
tipc_node_unlock(node);
- tipc_node_put(node);
if (err)
goto out;
diff --git a/net/tipc/server.c b/net/tipc/server.c
index ab6183cdb121..77ff03ed1e18 100644
--- a/net/tipc/server.c
+++ b/net/tipc/server.c
@@ -102,7 +102,7 @@ static void tipc_conn_kref_release(struct kref *kref)
}
saddr->scope = -TIPC_NODE_SCOPE;
kernel_bind(sock, (struct sockaddr *)saddr, sizeof(*saddr));
- sk_release_kernel(sk);
+ sock_release(sock);
con->sock = NULL;
}
@@ -321,12 +321,9 @@ static struct socket *tipc_create_listen_sock(struct tipc_conn *con)
struct socket *sock = NULL;
int ret;
- ret = sock_create_kern(AF_TIPC, SOCK_SEQPACKET, 0, &sock);
+ ret = __sock_create(s->net, AF_TIPC, SOCK_SEQPACKET, 0, &sock, 1);
if (ret < 0)
return NULL;
-
- sk_change_net(sock->sk, s->net);
-
ret = kernel_setsockopt(sock, SOL_TIPC, TIPC_IMPORTANCE,
(char *)&s->imp, sizeof(s->imp));
if (ret < 0)
@@ -376,7 +373,7 @@ static struct socket *tipc_create_listen_sock(struct tipc_conn *con)
create_err:
kernel_sock_shutdown(sock, SHUT_RDWR);
- sk_release_kernel(sock->sk);
+ sock_release(sock);
return NULL;
}
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index ee90d74d7516..9074b5cede38 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1764,13 +1764,14 @@ static int tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk,
int tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq)
{
u32 dnode, dport = 0;
- int err = -TIPC_ERR_NO_PORT;
+ int err;
struct sk_buff *skb;
struct tipc_sock *tsk;
struct tipc_net *tn;
struct sock *sk;
while (skb_queue_len(inputq)) {
+ err = -TIPC_ERR_NO_PORT;
skb = NULL;
dport = tipc_skb_peek_port(inputq, dport);
tsk = tipc_sk_lookup(net, dport);
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 99f7012b23b9..a73a226f2d33 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -95,39 +95,36 @@ static DECLARE_WAIT_QUEUE_HEAD(unix_gc_wait);
unsigned int unix_tot_inflight;
-
struct sock *unix_get_socket(struct file *filp)
{
struct sock *u_sock = NULL;
struct inode *inode = file_inode(filp);
- /*
- * Socket ?
- */
+ /* Socket ? */
if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) {
struct socket *sock = SOCKET_I(inode);
struct sock *s = sock->sk;
- /*
- * PF_UNIX ?
- */
+ /* PF_UNIX ? */
if (s && sock->ops && sock->ops->family == PF_UNIX)
u_sock = s;
}
return u_sock;
}
-/*
- * Keep the number of times in flight count for the file
- * descriptor if it is for an AF_UNIX socket.
+/* Keep the number of times in flight count for the file
+ * descriptor if it is for an AF_UNIX socket.
*/
void unix_inflight(struct file *fp)
{
struct sock *s = unix_get_socket(fp);
+
if (s) {
struct unix_sock *u = unix_sk(s);
+
spin_lock(&unix_gc_lock);
+
if (atomic_long_inc_return(&u->inflight) == 1) {
BUG_ON(!list_empty(&u->link));
list_add_tail(&u->link, &gc_inflight_list);
@@ -142,10 +139,13 @@ void unix_inflight(struct file *fp)
void unix_notinflight(struct file *fp)
{
struct sock *s = unix_get_socket(fp);
+
if (s) {
struct unix_sock *u = unix_sk(s);
+
spin_lock(&unix_gc_lock);
BUG_ON(list_empty(&u->link));
+
if (atomic_long_dec_and_test(&u->inflight))
list_del_init(&u->link);
unix_tot_inflight--;
@@ -161,32 +161,27 @@ static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *),
spin_lock(&x->sk_receive_queue.lock);
skb_queue_walk_safe(&x->sk_receive_queue, skb, next) {
- /*
- * Do we have file descriptors ?
- */
+ /* Do we have file descriptors ? */
if (UNIXCB(skb).fp) {
bool hit = false;
- /*
- * Process the descriptors of this socket
- */
+ /* Process the descriptors of this socket */
int nfd = UNIXCB(skb).fp->count;
struct file **fp = UNIXCB(skb).fp->fp;
+
while (nfd--) {
- /*
- * Get the socket the fd matches
- * if it indeed does so
- */
+ /* Get the socket the fd matches if it indeed does so */
struct sock *sk = unix_get_socket(*fp++);
+
if (sk) {
struct unix_sock *u = unix_sk(sk);
- /*
- * Ignore non-candidates, they could
+ /* Ignore non-candidates, they could
* have been added to the queues after
* starting the garbage collection
*/
if (test_bit(UNIX_GC_CANDIDATE, &u->gc_flags)) {
hit = true;
+
func(u);
}
}
@@ -203,24 +198,22 @@ static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *),
static void scan_children(struct sock *x, void (*func)(struct unix_sock *),
struct sk_buff_head *hitlist)
{
- if (x->sk_state != TCP_LISTEN)
+ if (x->sk_state != TCP_LISTEN) {
scan_inflight(x, func, hitlist);
- else {
+ } else {
struct sk_buff *skb;
struct sk_buff *next;
struct unix_sock *u;
LIST_HEAD(embryos);
- /*
- * For a listening socket collect the queued embryos
+ /* For a listening socket collect the queued embryos
* and perform a scan on them as well.
*/
spin_lock(&x->sk_receive_queue.lock);
skb_queue_walk_safe(&x->sk_receive_queue, skb, next) {
u = unix_sk(skb->sk);
- /*
- * An embryo cannot be in-flight, so it's safe
+ /* An embryo cannot be in-flight, so it's safe
* to use the list link.
*/
BUG_ON(!list_empty(&u->link));
@@ -249,8 +242,7 @@ static void inc_inflight(struct unix_sock *usk)
static void inc_inflight_move_tail(struct unix_sock *u)
{
atomic_long_inc(&u->inflight);
- /*
- * If this still might be part of a cycle, move it to the end
+ /* If this still might be part of a cycle, move it to the end
* of the list, so that it's checked even if it was already
* passed over
*/
@@ -263,8 +255,7 @@ static bool gc_in_progress;
void wait_for_unix_gc(void)
{
- /*
- * If number of inflight sockets is insane,
+ /* If number of inflight sockets is insane,
* force a garbage collect right now.
*/
if (unix_tot_inflight > UNIX_INFLIGHT_TRIGGER_GC && !gc_in_progress)
@@ -288,8 +279,7 @@ void unix_gc(void)
goto out;
gc_in_progress = true;
- /*
- * First, select candidates for garbage collection. Only
+ /* First, select candidates for garbage collection. Only
* in-flight sockets are considered, and from those only ones
* which don't have any external reference.
*
@@ -320,15 +310,13 @@ void unix_gc(void)
}
}
- /*
- * Now remove all internal in-flight reference to children of
+ /* Now remove all internal in-flight reference to children of
* the candidates.
*/
list_for_each_entry(u, &gc_candidates, link)
scan_children(&u->sk, dec_inflight, NULL);
- /*
- * Restore the references for children of all candidates,
+ /* Restore the references for children of all candidates,
* which have remaining references. Do this recursively, so
* only those remain, which form cyclic references.
*
@@ -350,8 +338,7 @@ void unix_gc(void)
}
list_del(&cursor);
- /*
- * not_cycle_list contains those sockets which do not make up a
+ /* not_cycle_list contains those sockets which do not make up a
* cycle. Restore these to the inflight list.
*/
while (!list_empty(&not_cycle_list)) {
@@ -360,8 +347,7 @@ void unix_gc(void)
list_move_tail(&u->link, &gc_inflight_list);
}
- /*
- * Now gc_candidates contains only garbage. Restore original
+ /* Now gc_candidates contains only garbage. Restore original
* inflight counters for these as well, and remove the skbuffs
* which are creating the cycle(s).
*/