summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/ax25/ax25_ip.c4
-rw-r--r--net/ax25/ax25_route.c19
-rw-r--r--net/batman-adv/bat_v_elp.c3
-rw-r--r--net/batman-adv/hard-interface.c5
-rw-r--r--net/batman-adv/soft-interface.c4
-rw-r--r--net/bpf/test_run.c45
-rw-r--r--net/bridge/br_multicast.c9
-rw-r--r--net/bridge/netfilter/ebtables.c9
-rw-r--r--net/can/bcm.c27
-rw-r--r--net/ceph/messenger.c20
-rw-r--r--net/compat.c6
-rw-r--r--net/core/dev.c7
-rw-r--r--net/core/filter.c14
-rw-r--r--net/core/skbuff.c4
-rw-r--r--net/core/skmsg.c3
-rw-r--r--net/core/sock.c2
-rw-r--r--net/dccp/ccid.h4
-rw-r--r--net/decnet/dn_dev.c2
-rw-r--r--net/dsa/dsa2.c16
-rw-r--r--net/dsa/master.c4
-rw-r--r--net/dsa/port.c8
-rw-r--r--net/dsa/slave.c17
-rw-r--r--net/ipv4/cipso_ipv4.c20
-rw-r--r--net/ipv4/esp4.c2
-rw-r--r--net/ipv4/fib_frontend.c4
-rw-r--r--net/ipv4/gre_demux.c17
-rw-r--r--net/ipv4/icmp.c7
-rw-r--r--net/ipv4/inet_diag.c10
-rw-r--r--net/ipv4/inetpeer.c1
-rw-r--r--net/ipv4/ip_gre.c43
-rw-r--r--net/ipv4/ip_input.c9
-rw-r--r--net/ipv4/ip_options.c22
-rw-r--r--net/ipv4/ip_tunnel.c8
-rw-r--r--net/ipv4/ip_vti.c50
-rw-r--r--net/ipv4/netfilter/ipt_CLUSTERIP.c2
-rw-r--r--net/ipv4/netfilter/nf_nat_l3proto_ipv4.c1
-rw-r--r--net/ipv4/netfilter/nf_nat_snmp_basic_main.c7
-rw-r--r--net/ipv4/netlink.c17
-rw-r--r--net/ipv4/route.c9
-rw-r--r--net/ipv4/tcp.c2
-rw-r--r--net/ipv4/tcp_ipv4.c5
-rw-r--r--net/ipv4/tcp_output.c1
-rw-r--r--net/ipv4/udp.c6
-rw-r--r--net/ipv6/addrconf.c9
-rw-r--r--net/ipv6/esp6.c2
-rw-r--r--net/ipv6/fou6.c2
-rw-r--r--net/ipv6/ip6_gre.c78
-rw-r--r--net/ipv6/ip6mr.c7
-rw-r--r--net/ipv6/netfilter.c4
-rw-r--r--net/ipv6/netfilter/nf_nat_l3proto_ipv6.c1
-rw-r--r--net/ipv6/route.c39
-rw-r--r--net/ipv6/seg6.c4
-rw-r--r--net/ipv6/seg6_iptunnel.c2
-rw-r--r--net/ipv6/sit.c4
-rw-r--r--net/ipv6/udp.c12
-rw-r--r--net/ipv6/xfrm6_tunnel.c2
-rw-r--r--net/key/af_key.c42
-rw-r--r--net/l2tp/l2tp_core.c9
-rw-r--r--net/l2tp/l2tp_core.h20
-rw-r--r--net/l2tp/l2tp_ip.c3
-rw-r--r--net/l2tp/l2tp_ip6.c3
-rw-r--r--net/mac80211/agg-tx.c4
-rw-r--r--net/mac80211/cfg.c10
-rw-r--r--net/mac80211/main.c4
-rw-r--r--net/mac80211/mesh.h6
-rw-r--r--net/mac80211/mesh_pathtbl.c157
-rw-r--r--net/mac80211/rx.c13
-rw-r--r--net/mac80211/tx.c12
-rw-r--r--net/mac80211/util.c6
-rw-r--r--net/mpls/af_mpls.c3
-rw-r--r--net/netfilter/ipvs/Kconfig1
-rw-r--r--net/netfilter/ipvs/ip_vs_core.c10
-rw-r--r--net/netfilter/ipvs/ip_vs_ctl.c23
-rw-r--r--net/netfilter/nf_conntrack_core.c16
-rw-r--r--net/netfilter/nf_tables_api.c88
-rw-r--r--net/netfilter/nfnetlink_osf.c4
-rw-r--r--net/netfilter/nft_compat.c180
-rw-r--r--net/netfilter/nft_dynset.c18
-rw-r--r--net/netfilter/nft_immediate.c6
-rw-r--r--net/netfilter/nft_lookup.c18
-rw-r--r--net/netfilter/nft_objref.c18
-rw-r--r--net/netfilter/x_tables.c2
-rw-r--r--net/netlabel/netlabel_kapi.c3
-rw-r--r--net/netrom/nr_timer.c20
-rw-r--r--net/nfc/llcp_commands.c20
-rw-r--r--net/nfc/llcp_core.c24
-rw-r--r--net/packet/af_packet.c2
-rw-r--r--net/phonet/pep.c32
-rw-r--r--net/rds/bind.c6
-rw-r--r--net/rose/rose_route.c5
-rw-r--r--net/rxrpc/recvmsg.c3
-rw-r--r--net/sched/act_ipt.c3
-rw-r--r--net/sched/act_skbedit.c3
-rw-r--r--net/sched/act_tunnel_key.c3
-rw-r--r--net/sched/cls_flower.c6
-rw-r--r--net/sched/cls_tcindex.c80
-rw-r--r--net/sched/sch_generic.c2
-rw-r--r--net/sched/sch_netem.c10
-rw-r--r--net/sctp/chunk.c2
-rw-r--r--net/sctp/diag.c1
-rw-r--r--net/sctp/ipv6.c3
-rw-r--r--net/sctp/offload.c1
-rw-r--r--net/sctp/protocol.c3
-rw-r--r--net/sctp/sm_make_chunk.c11
-rw-r--r--net/sctp/socket.c4
-rw-r--r--net/sctp/stream.c82
-rw-r--r--net/sctp/transport.c3
-rw-r--r--net/smc/af_smc.c11
-rw-r--r--net/smc/smc.h6
-rw-r--r--net/smc/smc_cdc.c23
-rw-r--r--net/smc/smc_cdc.h53
-rw-r--r--net/smc/smc_clc.c2
-rw-r--r--net/smc/smc_close.c9
-rw-r--r--net/smc/smc_core.c6
-rw-r--r--net/smc/smc_core.h20
-rw-r--r--net/smc/smc_ib.c6
-rw-r--r--net/smc/smc_llc.c3
-rw-r--r--net/smc/smc_pnet.c2
-rw-r--r--net/smc/smc_tx.c64
-rw-r--r--net/smc/smc_wr.c46
-rw-r--r--net/smc/smc_wr.h1
-rw-r--r--net/socket.c83
-rw-r--r--net/sunrpc/auth_gss/gss_krb5_seqnum.c49
-rw-r--r--net/sunrpc/debugfs.c2
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_sendto.c105
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_transport.c9
-rw-r--r--net/sunrpc/xprtrdma/verbs.c3
-rw-r--r--net/tipc/link.c17
-rw-r--r--net/tipc/msg.h22
-rw-r--r--net/tipc/node.c11
-rw-r--r--net/tipc/socket.c17
-rw-r--r--net/tls/tls_sw.c6
-rw-r--r--net/unix/af_unix.c57
-rw-r--r--net/unix/diag.c3
-rw-r--r--net/vmw_vsock/virtio_transport.c29
-rw-r--r--net/vmw_vsock/vmci_transport.c4
-rw-r--r--net/wireless/ap.c2
-rw-r--r--net/wireless/core.c2
-rw-r--r--net/wireless/core.h2
-rw-r--r--net/wireless/nl80211.c4
-rw-r--r--net/wireless/pmsr.c26
-rw-r--r--net/wireless/reg.c13
-rw-r--r--net/wireless/sme.c2
-rw-r--r--net/wireless/util.c35
-rw-r--r--net/x25/af_x25.c19
-rw-r--r--net/xdp/xdp_umem.c11
-rw-r--r--net/xdp/xsk.c20
-rw-r--r--net/xfrm/xfrm_interface.c4
-rw-r--r--net/xfrm/xfrm_policy.c67
-rw-r--r--net/xfrm/xfrm_state.c30
-rw-r--r--net/xfrm/xfrm_user.c15
151 files changed, 1699 insertions, 871 deletions
diff --git a/net/ax25/ax25_ip.c b/net/ax25/ax25_ip.c
index 70417e9b932d..314bbc8010fb 100644
--- a/net/ax25/ax25_ip.c
+++ b/net/ax25/ax25_ip.c
@@ -114,6 +114,7 @@ netdev_tx_t ax25_ip_xmit(struct sk_buff *skb)
dst = (ax25_address *)(bp + 1);
src = (ax25_address *)(bp + 8);
+ ax25_route_lock_use();
route = ax25_get_route(dst, NULL);
if (route) {
digipeat = route->digipeat;
@@ -206,9 +207,8 @@ netdev_tx_t ax25_ip_xmit(struct sk_buff *skb)
ax25_queue_xmit(skb, dev);
put:
- if (route)
- ax25_put_route(route);
+ ax25_route_lock_unuse();
return NETDEV_TX_OK;
}
diff --git a/net/ax25/ax25_route.c b/net/ax25/ax25_route.c
index a0eff323af12..66f74c85cf6b 100644
--- a/net/ax25/ax25_route.c
+++ b/net/ax25/ax25_route.c
@@ -40,7 +40,7 @@
#include <linux/export.h>
static ax25_route *ax25_route_list;
-static DEFINE_RWLOCK(ax25_route_lock);
+DEFINE_RWLOCK(ax25_route_lock);
void ax25_rt_device_down(struct net_device *dev)
{
@@ -335,6 +335,7 @@ const struct seq_operations ax25_rt_seqops = {
* Find AX.25 route
*
* Only routes with a reference count of zero can be destroyed.
+ * Must be called with ax25_route_lock read locked.
*/
ax25_route *ax25_get_route(ax25_address *addr, struct net_device *dev)
{
@@ -342,7 +343,6 @@ ax25_route *ax25_get_route(ax25_address *addr, struct net_device *dev)
ax25_route *ax25_def_rt = NULL;
ax25_route *ax25_rt;
- read_lock(&ax25_route_lock);
/*
* Bind to the physical interface we heard them on, or the default
* route if none is found;
@@ -365,11 +365,6 @@ ax25_route *ax25_get_route(ax25_address *addr, struct net_device *dev)
if (ax25_spe_rt != NULL)
ax25_rt = ax25_spe_rt;
- if (ax25_rt != NULL)
- ax25_hold_route(ax25_rt);
-
- read_unlock(&ax25_route_lock);
-
return ax25_rt;
}
@@ -400,9 +395,12 @@ int ax25_rt_autobind(ax25_cb *ax25, ax25_address *addr)
ax25_route *ax25_rt;
int err = 0;
- if ((ax25_rt = ax25_get_route(addr, NULL)) == NULL)
+ ax25_route_lock_use();
+ ax25_rt = ax25_get_route(addr, NULL);
+ if (!ax25_rt) {
+ ax25_route_lock_unuse();
return -EHOSTUNREACH;
-
+ }
if ((ax25->ax25_dev = ax25_dev_ax25dev(ax25_rt->dev)) == NULL) {
err = -EHOSTUNREACH;
goto put;
@@ -437,8 +435,7 @@ int ax25_rt_autobind(ax25_cb *ax25, ax25_address *addr)
}
put:
- ax25_put_route(ax25_rt);
-
+ ax25_route_lock_unuse();
return err;
}
diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c
index e8090f099eb8..ef0dec20c7d8 100644
--- a/net/batman-adv/bat_v_elp.c
+++ b/net/batman-adv/bat_v_elp.c
@@ -104,6 +104,9 @@ static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh)
ret = cfg80211_get_station(real_netdev, neigh->addr, &sinfo);
+ /* free the TID stats immediately */
+ cfg80211_sinfo_release_content(&sinfo);
+
dev_put(real_netdev);
if (ret == -ENOENT) {
/* Node is not associated anymore! It would be
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index 508f4416dfc9..415d494cbe22 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -20,7 +20,6 @@
#include "main.h"
#include <linux/atomic.h>
-#include <linux/bug.h>
#include <linux/byteorder/generic.h>
#include <linux/errno.h>
#include <linux/gfp.h>
@@ -179,8 +178,10 @@ static bool batadv_is_on_batman_iface(const struct net_device *net_dev)
parent_dev = __dev_get_by_index((struct net *)parent_net,
dev_get_iflink(net_dev));
/* if we got a NULL parent_dev there is something broken.. */
- if (WARN(!parent_dev, "Cannot find parent device"))
+ if (!parent_dev) {
+ pr_err("Cannot find parent device\n");
return false;
+ }
if (batadv_mutual_parents(net_dev, net, parent_dev, parent_net))
return false;
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 5db5a0a4c959..ffc83bebfe40 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -221,10 +221,14 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb,
netif_trans_update(soft_iface);
vid = batadv_get_vid(skb, 0);
+
+ skb_reset_mac_header(skb);
ethhdr = eth_hdr(skb);
switch (ntohs(ethhdr->h_proto)) {
case ETH_P_8021Q:
+ if (!pskb_may_pull(skb, sizeof(*vhdr)))
+ goto dropped;
vhdr = vlan_eth_hdr(skb);
/* drop batman-in-batman packets to prevent loops */
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index fa2644d276ef..e31e1b20f7f4 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -13,27 +13,13 @@
#include <net/sock.h>
#include <net/tcp.h>
-static __always_inline u32 bpf_test_run_one(struct bpf_prog *prog, void *ctx,
- struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE])
-{
- u32 ret;
-
- preempt_disable();
- rcu_read_lock();
- bpf_cgroup_storage_set(storage);
- ret = BPF_PROG_RUN(prog, ctx);
- rcu_read_unlock();
- preempt_enable();
-
- return ret;
-}
-
-static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *ret,
- u32 *time)
+static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat,
+ u32 *retval, u32 *time)
{
struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = { 0 };
enum bpf_cgroup_storage_type stype;
u64 time_start, time_spent = 0;
+ int ret = 0;
u32 i;
for_each_cgroup_storage_type(stype) {
@@ -48,25 +34,42 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *ret,
if (!repeat)
repeat = 1;
+
+ rcu_read_lock();
+ preempt_disable();
time_start = ktime_get_ns();
for (i = 0; i < repeat; i++) {
- *ret = bpf_test_run_one(prog, ctx, storage);
+ bpf_cgroup_storage_set(storage);
+ *retval = BPF_PROG_RUN(prog, ctx);
+
+ if (signal_pending(current)) {
+ ret = -EINTR;
+ break;
+ }
+
if (need_resched()) {
- if (signal_pending(current))
- break;
time_spent += ktime_get_ns() - time_start;
+ preempt_enable();
+ rcu_read_unlock();
+
cond_resched();
+
+ rcu_read_lock();
+ preempt_disable();
time_start = ktime_get_ns();
}
}
time_spent += ktime_get_ns() - time_start;
+ preempt_enable();
+ rcu_read_unlock();
+
do_div(time_spent, repeat);
*time = time_spent > U32_MAX ? U32_MAX : (u32)time_spent;
for_each_cgroup_storage_type(stype)
bpf_cgroup_storage_free(storage[stype]);
- return 0;
+ return ret;
}
static int bpf_test_finish(const union bpf_attr *kattr,
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 3aeff0895669..ac92b2eb32b1 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1204,14 +1204,7 @@ static void br_multicast_query_received(struct net_bridge *br,
return;
br_multicast_update_query_timer(br, query, max_delay);
-
- /* Based on RFC4541, section 2.1.1 IGMP Forwarding Rules,
- * the arrival port for IGMP Queries where the source address
- * is 0.0.0.0 should not be added to router port list.
- */
- if ((saddr->proto == htons(ETH_P_IP) && saddr->u.ip4) ||
- saddr->proto == htons(ETH_P_IPV6))
- br_multicast_mark_router(br, port);
+ br_multicast_mark_router(br, port);
}
static void br_ip4_multicast_query(struct net_bridge *br,
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 5e55cef0cec3..6693e209efe8 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -2293,9 +2293,12 @@ static int compat_do_replace(struct net *net, void __user *user,
xt_compat_lock(NFPROTO_BRIDGE);
- ret = xt_compat_init_offsets(NFPROTO_BRIDGE, tmp.nentries);
- if (ret < 0)
- goto out_unlock;
+ if (tmp.nentries) {
+ ret = xt_compat_init_offsets(NFPROTO_BRIDGE, tmp.nentries);
+ if (ret < 0)
+ goto out_unlock;
+ }
+
ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state);
if (ret < 0)
goto out_unlock;
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 0af8f0db892a..79bb8afa9c0c 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -67,6 +67,9 @@
*/
#define MAX_NFRAMES 256
+/* limit timers to 400 days for sending/timeouts */
+#define BCM_TIMER_SEC_MAX (400 * 24 * 60 * 60)
+
/* use of last_frames[index].flags */
#define RX_RECV 0x40 /* received data for this element */
#define RX_THR 0x80 /* element not been sent due to throttle feature */
@@ -140,6 +143,22 @@ static inline ktime_t bcm_timeval_to_ktime(struct bcm_timeval tv)
return ktime_set(tv.tv_sec, tv.tv_usec * NSEC_PER_USEC);
}
+/* check limitations for timeval provided by user */
+static bool bcm_is_invalid_tv(struct bcm_msg_head *msg_head)
+{
+ if ((msg_head->ival1.tv_sec < 0) ||
+ (msg_head->ival1.tv_sec > BCM_TIMER_SEC_MAX) ||
+ (msg_head->ival1.tv_usec < 0) ||
+ (msg_head->ival1.tv_usec >= USEC_PER_SEC) ||
+ (msg_head->ival2.tv_sec < 0) ||
+ (msg_head->ival2.tv_sec > BCM_TIMER_SEC_MAX) ||
+ (msg_head->ival2.tv_usec < 0) ||
+ (msg_head->ival2.tv_usec >= USEC_PER_SEC))
+ return true;
+
+ return false;
+}
+
#define CFSIZ(flags) ((flags & CAN_FD_FRAME) ? CANFD_MTU : CAN_MTU)
#define OPSIZ sizeof(struct bcm_op)
#define MHSIZ sizeof(struct bcm_msg_head)
@@ -873,6 +892,10 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
if (msg_head->nframes < 1 || msg_head->nframes > MAX_NFRAMES)
return -EINVAL;
+ /* check timeval limitations */
+ if ((msg_head->flags & SETTIMER) && bcm_is_invalid_tv(msg_head))
+ return -EINVAL;
+
/* check the given can_id */
op = bcm_find_op(&bo->tx_ops, msg_head, ifindex);
if (op) {
@@ -1053,6 +1076,10 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
(!(msg_head->can_id & CAN_RTR_FLAG))))
return -EINVAL;
+ /* check timeval limitations */
+ if ((msg_head->flags & SETTIMER) && bcm_is_invalid_tv(msg_head))
+ return -EINVAL;
+
/* check the given can_id */
op = bcm_find_op(&bo->rx_ops, msg_head, ifindex);
if (op) {
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index d5718284db57..7e71b0df1fbc 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -2058,6 +2058,8 @@ static int process_connect(struct ceph_connection *con)
dout("process_connect on %p tag %d\n", con, (int)con->in_tag);
if (con->auth) {
+ int len = le32_to_cpu(con->in_reply.authorizer_len);
+
/*
* Any connection that defines ->get_authorizer()
* should also define ->add_authorizer_challenge() and
@@ -2067,8 +2069,7 @@ static int process_connect(struct ceph_connection *con)
*/
if (con->in_reply.tag == CEPH_MSGR_TAG_CHALLENGE_AUTHORIZER) {
ret = con->ops->add_authorizer_challenge(
- con, con->auth->authorizer_reply_buf,
- le32_to_cpu(con->in_reply.authorizer_len));
+ con, con->auth->authorizer_reply_buf, len);
if (ret < 0)
return ret;
@@ -2078,10 +2079,12 @@ static int process_connect(struct ceph_connection *con)
return 0;
}
- ret = con->ops->verify_authorizer_reply(con);
- if (ret < 0) {
- con->error_msg = "bad authorize reply";
- return ret;
+ if (len) {
+ ret = con->ops->verify_authorizer_reply(con);
+ if (ret < 0) {
+ con->error_msg = "bad authorize reply";
+ return ret;
+ }
}
}
@@ -3206,9 +3209,10 @@ void ceph_con_keepalive(struct ceph_connection *con)
dout("con_keepalive %p\n", con);
mutex_lock(&con->mutex);
clear_standby(con);
+ con_flag_set(con, CON_FLAG_KEEPALIVE_PENDING);
mutex_unlock(&con->mutex);
- if (con_flag_test_and_set(con, CON_FLAG_KEEPALIVE_PENDING) == 0 &&
- con_flag_test_and_set(con, CON_FLAG_WRITE_PENDING) == 0)
+
+ if (con_flag_test_and_set(con, CON_FLAG_WRITE_PENDING) == 0)
queue_con(con);
}
EXPORT_SYMBOL(ceph_con_keepalive);
diff --git a/net/compat.c b/net/compat.c
index 959d1c51826d..3d348198004f 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -388,8 +388,12 @@ static int __compat_sys_setsockopt(int fd, int level, int optname,
char __user *optval, unsigned int optlen)
{
int err;
- struct socket *sock = sockfd_lookup(fd, &err);
+ struct socket *sock;
+
+ if (optlen > INT_MAX)
+ return -EINVAL;
+ sock = sockfd_lookup(fd, &err);
if (sock) {
err = security_socket_setsockopt(sock, level, optname);
if (err) {
diff --git a/net/core/dev.c b/net/core/dev.c
index 82f20022259d..5d03889502eb 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8152,7 +8152,7 @@ static netdev_features_t netdev_sync_upper_features(struct net_device *lower,
netdev_features_t feature;
int feature_bit;
- for_each_netdev_feature(&upper_disables, feature_bit) {
+ for_each_netdev_feature(upper_disables, feature_bit) {
feature = __NETIF_F_BIT(feature_bit);
if (!(upper->wanted_features & feature)
&& (features & feature)) {
@@ -8172,7 +8172,7 @@ static void netdev_sync_lower_features(struct net_device *upper,
netdev_features_t feature;
int feature_bit;
- for_each_netdev_feature(&upper_disables, feature_bit) {
+ for_each_netdev_feature(upper_disables, feature_bit) {
feature = __NETIF_F_BIT(feature_bit);
if (!(features & feature) && (lower->features & feature)) {
netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n",
@@ -8712,6 +8712,9 @@ int init_dummy_netdev(struct net_device *dev)
set_bit(__LINK_STATE_PRESENT, &dev->state);
set_bit(__LINK_STATE_START, &dev->state);
+ /* napi_busy_loop stats accounting wants this */
+ dev_net_set(dev, &init_net);
+
/* Note : We dont allocate pcpu_refcnt for dummy devices,
* because users of this 'device' dont need to change
* its refcount.
diff --git a/net/core/filter.c b/net/core/filter.c
index 7559d6835ecb..f7d0004fc160 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2789,8 +2789,7 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb)
u32 off = skb_mac_header_len(skb);
int ret;
- /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */
- if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb)))
+ if (!skb_is_gso_tcp(skb))
return -ENOTSUPP;
ret = skb_cow(skb, len_diff);
@@ -2831,8 +2830,7 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb)
u32 off = skb_mac_header_len(skb);
int ret;
- /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */
- if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb)))
+ if (!skb_is_gso_tcp(skb))
return -ENOTSUPP;
ret = skb_unclone(skb, GFP_ATOMIC);
@@ -2957,8 +2955,7 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 len_diff)
u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb);
int ret;
- /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */
- if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb)))
+ if (!skb_is_gso_tcp(skb))
return -ENOTSUPP;
ret = skb_cow(skb, len_diff);
@@ -2987,8 +2984,7 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 len_diff)
u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb);
int ret;
- /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */
- if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb)))
+ if (!skb_is_gso_tcp(skb))
return -ENOTSUPP;
ret = skb_unclone(skb, GFP_ATOMIC);
@@ -4112,10 +4108,12 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
/* Only some socketops are supported */
switch (optname) {
case SO_RCVBUF:
+ val = min_t(u32, val, sysctl_rmem_max);
sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF);
break;
case SO_SNDBUF:
+ val = min_t(u32, val, sysctl_wmem_max);
sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF);
break;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 26d848484912..2415d9cb9b89 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -356,6 +356,8 @@ static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
*/
void *netdev_alloc_frag(unsigned int fragsz)
{
+ fragsz = SKB_DATA_ALIGN(fragsz);
+
return __netdev_alloc_frag(fragsz, GFP_ATOMIC);
}
EXPORT_SYMBOL(netdev_alloc_frag);
@@ -369,6 +371,8 @@ static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
void *napi_alloc_frag(unsigned int fragsz)
{
+ fragsz = SKB_DATA_ALIGN(fragsz);
+
return __napi_alloc_frag(fragsz, GFP_ATOMIC);
}
EXPORT_SYMBOL(napi_alloc_frag);
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index d6d5c20d7044..8c826603bf36 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -545,8 +545,7 @@ static void sk_psock_destroy_deferred(struct work_struct *gc)
struct sk_psock *psock = container_of(gc, struct sk_psock, gc);
/* No sk_callback_lock since already detached. */
- if (psock->parser.enabled)
- strp_done(&psock->parser.strp);
+ strp_done(&psock->parser.strp);
cancel_work_sync(&psock->work);
diff --git a/net/core/sock.c b/net/core/sock.c
index 6aa2e7e0b4fb..bc3512f230a3 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2380,7 +2380,7 @@ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind)
}
if (sk_has_memory_pressure(sk)) {
- int alloc;
+ u64 alloc;
if (!sk_under_memory_pressure(sk))
return 1;
diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h
index 6eb837a47b5c..baaaeb2b2c42 100644
--- a/net/dccp/ccid.h
+++ b/net/dccp/ccid.h
@@ -202,7 +202,7 @@ static inline void ccid_hc_tx_packet_recv(struct ccid *ccid, struct sock *sk,
static inline int ccid_hc_tx_parse_options(struct ccid *ccid, struct sock *sk,
u8 pkt, u8 opt, u8 *val, u8 len)
{
- if (ccid->ccid_ops->ccid_hc_tx_parse_options == NULL)
+ if (!ccid || !ccid->ccid_ops->ccid_hc_tx_parse_options)
return 0;
return ccid->ccid_ops->ccid_hc_tx_parse_options(sk, pkt, opt, val, len);
}
@@ -214,7 +214,7 @@ static inline int ccid_hc_tx_parse_options(struct ccid *ccid, struct sock *sk,
static inline int ccid_hc_rx_parse_options(struct ccid *ccid, struct sock *sk,
u8 pkt, u8 opt, u8 *val, u8 len)
{
- if (ccid->ccid_ops->ccid_hc_rx_parse_options == NULL)
+ if (!ccid || !ccid->ccid_ops->ccid_hc_rx_parse_options)
return 0;
return ccid->ccid_ops->ccid_hc_rx_parse_options(sk, pkt, opt, val, len);
}
diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c
index d0b3e69c6b39..0962f9201baa 100644
--- a/net/decnet/dn_dev.c
+++ b/net/decnet/dn_dev.c
@@ -56,7 +56,7 @@
#include <net/dn_neigh.h>
#include <net/dn_fib.h>
-#define DN_IFREQ_SIZE (sizeof(struct ifreq) - sizeof(struct sockaddr) + sizeof(struct sockaddr_dn))
+#define DN_IFREQ_SIZE (offsetof(struct ifreq, ifr_ifru) + sizeof(struct sockaddr_dn))
static char dn_rt_all_end_mcast[ETH_ALEN] = {0xAB,0x00,0x00,0x04,0x00,0x00};
static char dn_rt_all_rt_mcast[ETH_ALEN] = {0xAB,0x00,0x00,0x03,0x00,0x00};
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index a1917025e155..410f19148106 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -612,8 +612,8 @@ static int dsa_switch_parse_ports_of(struct dsa_switch *ds,
{
struct device_node *ports, *port;
struct dsa_port *dp;
+ int err = 0;
u32 reg;
- int err;
ports = of_get_child_by_name(dn, "ports");
if (!ports) {
@@ -624,19 +624,23 @@ static int dsa_switch_parse_ports_of(struct dsa_switch *ds,
for_each_available_child_of_node(ports, port) {
err = of_property_read_u32(port, "reg", &reg);
if (err)
- return err;
+ goto out_put_node;
- if (reg >= ds->num_ports)
- return -EINVAL;
+ if (reg >= ds->num_ports) {
+ err = -EINVAL;
+ goto out_put_node;
+ }
dp = &ds->ports[reg];
err = dsa_port_parse_of(dp, port);
if (err)
- return err;
+ goto out_put_node;
}
- return 0;
+out_put_node:
+ of_node_put(ports);
+ return err;
}
static int dsa_switch_parse_member_of(struct dsa_switch *ds,
diff --git a/net/dsa/master.c b/net/dsa/master.c
index 71bb15f491c8..54f5551fb799 100644
--- a/net/dsa/master.c
+++ b/net/dsa/master.c
@@ -205,6 +205,8 @@ static void dsa_master_reset_mtu(struct net_device *dev)
rtnl_unlock();
}
+static struct lock_class_key dsa_master_addr_list_lock_key;
+
int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
{
int ret;
@@ -218,6 +220,8 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
wmb();
dev->dsa_ptr = cpu_dp;
+ lockdep_set_class(&dev->addr_list_lock,
+ &dsa_master_addr_list_lock_key);
ret = dsa_master_ethtool_setup(dev);
if (ret)
diff --git a/net/dsa/port.c b/net/dsa/port.c
index 2d7e01b23572..c2261697ee83 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -69,7 +69,6 @@ static void dsa_port_set_state_now(struct dsa_port *dp, u8 state)
int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy)
{
- u8 stp_state = dp->bridge_dev ? BR_STATE_BLOCKING : BR_STATE_FORWARDING;
struct dsa_switch *ds = dp->ds;
int port = dp->index;
int err;
@@ -80,7 +79,8 @@ int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy)
return err;
}
- dsa_port_set_state_now(dp, stp_state);
+ if (!dp->bridge_dev)
+ dsa_port_set_state_now(dp, BR_STATE_FORWARDING);
return 0;
}
@@ -90,7 +90,8 @@ void dsa_port_disable(struct dsa_port *dp, struct phy_device *phy)
struct dsa_switch *ds = dp->ds;
int port = dp->index;
- dsa_port_set_state_now(dp, BR_STATE_DISABLED);
+ if (!dp->bridge_dev)
+ dsa_port_set_state_now(dp, BR_STATE_DISABLED);
if (ds->ops->port_disable)
ds->ops->port_disable(ds, port, phy);
@@ -291,6 +292,7 @@ static struct phy_device *dsa_port_get_phy_device(struct dsa_port *dp)
return ERR_PTR(-EPROBE_DEFER);
}
+ of_node_put(phy_dn);
return phydev;
}
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index a3fcc1d01615..a1c9fe155057 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -140,11 +140,14 @@ static int dsa_slave_close(struct net_device *dev)
static void dsa_slave_change_rx_flags(struct net_device *dev, int change)
{
struct net_device *master = dsa_slave_to_master(dev);
-
- if (change & IFF_ALLMULTI)
- dev_set_allmulti(master, dev->flags & IFF_ALLMULTI ? 1 : -1);
- if (change & IFF_PROMISC)
- dev_set_promiscuity(master, dev->flags & IFF_PROMISC ? 1 : -1);
+ if (dev->flags & IFF_UP) {
+ if (change & IFF_ALLMULTI)
+ dev_set_allmulti(master,
+ dev->flags & IFF_ALLMULTI ? 1 : -1);
+ if (change & IFF_PROMISC)
+ dev_set_promiscuity(master,
+ dev->flags & IFF_PROMISC ? 1 : -1);
+ }
}
static void dsa_slave_set_rx_mode(struct net_device *dev)
@@ -639,7 +642,7 @@ static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e)
int ret;
/* Port's PHY and MAC both need to be EEE capable */
- if (!dev->phydev && !dp->pl)
+ if (!dev->phydev || !dp->pl)
return -ENODEV;
if (!ds->ops->set_mac_eee)
@@ -659,7 +662,7 @@ static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e)
int ret;
/* Port's PHY and MAC both need to be EEE capable */
- if (!dev->phydev && !dp->pl)
+ if (!dev->phydev || !dp->pl)
return -ENODEV;
if (!ds->ops->get_mac_eee)
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 777fa3b7fb13..f0165c5f376b 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -667,7 +667,8 @@ static int cipso_v4_map_lvl_valid(const struct cipso_v4_doi *doi_def, u8 level)
case CIPSO_V4_MAP_PASS:
return 0;
case CIPSO_V4_MAP_TRANS:
- if (doi_def->map.std->lvl.cipso[level] < CIPSO_V4_INV_LVL)
+ if ((level < doi_def->map.std->lvl.cipso_size) &&
+ (doi_def->map.std->lvl.cipso[level] < CIPSO_V4_INV_LVL))
return 0;
break;
}
@@ -1735,13 +1736,26 @@ validate_return:
*/
void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway)
{
+ unsigned char optbuf[sizeof(struct ip_options) + 40];
+ struct ip_options *opt = (struct ip_options *)optbuf;
+
if (ip_hdr(skb)->protocol == IPPROTO_ICMP || error != -EACCES)
return;
+ /*
+ * We might be called above the IP layer,
+ * so we can not use icmp_send and IPCB here.
+ */
+
+ memset(opt, 0, sizeof(struct ip_options));
+ opt->optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr);
+ if (__ip_options_compile(dev_net(skb->dev), opt, skb, NULL))
+ return;
+
if (gateway)
- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_NET_ANO, 0);
+ __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_NET_ANO, 0, opt);
else
- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_ANO, 0);
+ __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_ANO, 0, opt);
}
/**
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 5459f41fc26f..10e809b296ec 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -328,7 +328,7 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
skb->len += tailen;
skb->data_len += tailen;
skb->truesize += tailen;
- if (sk)
+ if (sk && sk_fullsock(sk))
refcount_add(tailen, &sk->sk_wmem_alloc);
goto out;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index fe4f6a624238..ed14ec245584 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -710,6 +710,10 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
case RTA_GATEWAY:
cfg->fc_gw = nla_get_be32(attr);
break;
+ case RTA_VIA:
+ NL_SET_ERR_MSG(extack, "IPv4 does not support RTA_VIA attribute");
+ err = -EINVAL;
+ goto errout;
case RTA_PRIORITY:
cfg->fc_priority = nla_get_u32(attr);
break;
diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
index a4bf22ee3aed..7c4a41dc04bb 100644
--- a/net/ipv4/gre_demux.c
+++ b/net/ipv4/gre_demux.c
@@ -25,6 +25,7 @@
#include <linux/spinlock.h>
#include <net/protocol.h>
#include <net/gre.h>
+#include <net/erspan.h>
#include <net/icmp.h>
#include <net/route.h>
@@ -119,6 +120,22 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
hdr_len += 4;
}
tpi->hdr_len = hdr_len;
+
+ /* ERSPAN ver 1 and 2 protocol sets GRE key field
+ * to 0 and sets the configured key in the
+ * inner erspan header field
+ */
+ if (greh->protocol == htons(ETH_P_ERSPAN) ||
+ greh->protocol == htons(ETH_P_ERSPAN2)) {
+ struct erspan_base_hdr *ershdr;
+
+ if (!pskb_may_pull(skb, nhs + hdr_len + sizeof(*ershdr)))
+ return -EINVAL;
+
+ ershdr = (struct erspan_base_hdr *)options;
+ tpi->key = cpu_to_be32(get_session_id(ershdr));
+ }
+
return hdr_len;
}
EXPORT_SYMBOL(gre_parse_header);
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 065997f414e6..3f24414150e2 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -570,7 +570,8 @@ relookup_failed:
* MUST reply to only the first fragment.
*/
-void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
+void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
+ const struct ip_options *opt)
{
struct iphdr *iph;
int room;
@@ -691,7 +692,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
iph->tos;
mark = IP4_REPLY_MARK(net, skb_in->mark);
- if (ip_options_echo(net, &icmp_param.replyopts.opt.opt, skb_in))
+ if (__ip_options_echo(net, &icmp_param.replyopts.opt.opt, skb_in, opt))
goto out_unlock;
@@ -742,7 +743,7 @@ out_bh_enable:
local_bh_enable();
out:;
}
-EXPORT_SYMBOL(icmp_send);
+EXPORT_SYMBOL(__icmp_send);
static void icmp_socket_deliver(struct sk_buff *skb, u32 info)
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 1a4e9ff02762..5731670c560b 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -108,6 +108,7 @@ static size_t inet_sk_attr_size(struct sock *sk,
+ nla_total_size(1) /* INET_DIAG_TOS */
+ nla_total_size(1) /* INET_DIAG_TCLASS */
+ nla_total_size(4) /* INET_DIAG_MARK */
+ + nla_total_size(4) /* INET_DIAG_CLASS_ID */
+ nla_total_size(sizeof(struct inet_diag_meminfo))
+ nla_total_size(sizeof(struct inet_diag_msg))
+ nla_total_size(SK_MEMINFO_VARS * sizeof(u32))
@@ -287,12 +288,19 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
goto errout;
}
- if (ext & (1 << (INET_DIAG_CLASS_ID - 1))) {
+ if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) ||
+ ext & (1 << (INET_DIAG_TCLASS - 1))) {
u32 classid = 0;
#ifdef CONFIG_SOCK_CGROUP_DATA
classid = sock_cgroup_classid(&sk->sk_cgrp_data);
#endif
+ /* Fallback to socket priority if class id isn't set.
+ * Classful qdiscs use it as direct reference to class.
+ * For cgroup2 classid is always zero.
+ */
+ if (!classid)
+ classid = sk->sk_priority;
if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid))
goto errout;
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index d757b9642d0d..be778599bfed 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -216,6 +216,7 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base,
atomic_set(&p->rid, 0);
p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW;
p->rate_tokens = 0;
+ p->n_redirects = 0;
/* 60*HZ is arbitrary, but chosen enough high so that the first
* calculation of tokens is at its maximum.
*/
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index b1a74d80d868..6ae89f2b541b 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -268,20 +268,11 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
int len;
itn = net_generic(net, erspan_net_id);
- len = gre_hdr_len + sizeof(*ershdr);
-
- /* Check based hdr len */
- if (unlikely(!pskb_may_pull(skb, len)))
- return PACKET_REJECT;
iph = ip_hdr(skb);
ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len);
ver = ershdr->ver;
- /* The original GRE header does not have key field,
- * Use ERSPAN 10-bit session ID as key.
- */
- tpi->key = cpu_to_be32(get_session_id(ershdr));
tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex,
tpi->flags | TUNNEL_KEY,
iph->saddr, iph->daddr, tpi->key);
@@ -1464,12 +1455,31 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev)
{
struct ip_tunnel *t = netdev_priv(dev);
struct ip_tunnel_parm *p = &t->parms;
+ __be16 o_flags = p->o_flags;
+
+ if (t->erspan_ver == 1 || t->erspan_ver == 2) {
+ if (!t->collect_md)
+ o_flags |= TUNNEL_KEY;
+
+ if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver))
+ goto nla_put_failure;
+
+ if (t->erspan_ver == 1) {
+ if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index))
+ goto nla_put_failure;
+ } else {
+ if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, t->dir))
+ goto nla_put_failure;
+ if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, t->hwid))
+ goto nla_put_failure;
+ }
+ }
if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) ||
nla_put_be16(skb, IFLA_GRE_IFLAGS,
gre_tnl_flags_to_gre_flags(p->i_flags)) ||
nla_put_be16(skb, IFLA_GRE_OFLAGS,
- gre_tnl_flags_to_gre_flags(p->o_flags)) ||
+ gre_tnl_flags_to_gre_flags(o_flags)) ||
nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) ||
nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) ||
nla_put_in_addr(skb, IFLA_GRE_LOCAL, p->iph.saddr) ||
@@ -1499,19 +1509,6 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev)
goto nla_put_failure;
}
- if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver))
- goto nla_put_failure;
-
- if (t->erspan_ver == 1) {
- if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index))
- goto nla_put_failure;
- } else if (t->erspan_ver == 2) {
- if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, t->dir))
- goto nla_put_failure;
- if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, t->hwid))
- goto nla_put_failure;
- }
-
return 0;
nla_put_failure:
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 51d8efba6de2..1f4737b77067 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -307,11 +307,10 @@ drop:
}
static int ip_rcv_finish_core(struct net *net, struct sock *sk,
- struct sk_buff *skb)
+ struct sk_buff *skb, struct net_device *dev)
{
const struct iphdr *iph = ip_hdr(skb);
int (*edemux)(struct sk_buff *skb);
- struct net_device *dev = skb->dev;
struct rtable *rt;
int err;
@@ -400,6 +399,7 @@ drop_error:
static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
+ struct net_device *dev = skb->dev;
int ret;
/* if ingress device is enslaved to an L3 master device pass the
@@ -409,7 +409,7 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
if (!skb)
return NET_RX_SUCCESS;
- ret = ip_rcv_finish_core(net, sk, skb);
+ ret = ip_rcv_finish_core(net, sk, skb, dev);
if (ret != NET_RX_DROP)
ret = dst_input(skb);
return ret;
@@ -545,6 +545,7 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk,
INIT_LIST_HEAD(&sublist);
list_for_each_entry_safe(skb, next, head, list) {
+ struct net_device *dev = skb->dev;
struct dst_entry *dst;
skb_list_del_init(skb);
@@ -554,7 +555,7 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk,
skb = l3mdev_ip_rcv(skb);
if (!skb)
continue;
- if (ip_rcv_finish_core(net, sk, skb) == NET_RX_DROP)
+ if (ip_rcv_finish_core(net, sk, skb, dev) == NET_RX_DROP)
continue;
dst = skb_dst(skb);
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index ed194d46c00e..32a35043c9f5 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -251,8 +251,9 @@ static void spec_dst_fill(__be32 *spec_dst, struct sk_buff *skb)
* If opt == NULL, then skb->data should point to IP header.
*/
-int ip_options_compile(struct net *net,
- struct ip_options *opt, struct sk_buff *skb)
+int __ip_options_compile(struct net *net,
+ struct ip_options *opt, struct sk_buff *skb,
+ __be32 *info)
{
__be32 spec_dst = htonl(INADDR_ANY);
unsigned char *pp_ptr = NULL;
@@ -468,11 +469,22 @@ eol:
return 0;
error:
- if (skb) {
- icmp_send(skb, ICMP_PARAMETERPROB, 0, htonl((pp_ptr-iph)<<24));
- }
+ if (info)
+ *info = htonl((pp_ptr-iph)<<24);
return -EINVAL;
}
+
+int ip_options_compile(struct net *net,
+ struct ip_options *opt, struct sk_buff *skb)
+{
+ int ret;
+ __be32 info;
+
+ ret = __ip_options_compile(net, opt, skb, &info);
+ if (ret != 0 && skb)
+ icmp_send(skb, ICMP_PARAMETERPROB, 0, info);
+ return ret;
+}
EXPORT_SYMBOL(ip_options_compile);
/*
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index c4f5602308ed..054d01c16dc6 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -644,13 +644,19 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
dst = tnl_params->daddr;
if (dst == 0) {
/* NBMA tunnel */
+ struct ip_tunnel_info *tun_info;
if (!skb_dst(skb)) {
dev->stats.tx_fifo_errors++;
goto tx_error;
}
- if (skb->protocol == htons(ETH_P_IP)) {
+ tun_info = skb_tunnel_info(skb);
+ if (tun_info && (tun_info->mode & IP_TUNNEL_INFO_TX) &&
+ ip_tunnel_info_af(tun_info) == AF_INET &&
+ tun_info->key.u.ipv4.dst)
+ dst = tun_info->key.u.ipv4.dst;
+ else if (skb->protocol == htons(ETH_P_IP)) {
rt = skb_rtable(skb);
dst = rt_nexthop(rt, inner_iph->daddr);
}
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index d7b43e700023..68a21bf75dd0 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -74,6 +74,33 @@ drop:
return 0;
}
+static int vti_input_ipip(struct sk_buff *skb, int nexthdr, __be32 spi,
+ int encap_type)
+{
+ struct ip_tunnel *tunnel;
+ const struct iphdr *iph = ip_hdr(skb);
+ struct net *net = dev_net(skb->dev);
+ struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
+
+ tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
+ iph->saddr, iph->daddr, 0);
+ if (tunnel) {
+ if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
+ goto drop;
+
+ XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel;
+
+ skb->dev = tunnel->dev;
+
+ return xfrm_input(skb, nexthdr, spi, encap_type);
+ }
+
+ return -EINVAL;
+drop:
+ kfree_skb(skb);
+ return 0;
+}
+
static int vti_rcv(struct sk_buff *skb)
{
XFRM_SPI_SKB_CB(skb)->family = AF_INET;
@@ -82,6 +109,14 @@ static int vti_rcv(struct sk_buff *skb)
return vti_input(skb, ip_hdr(skb)->protocol, 0, 0);
}
+static int vti_rcv_ipip(struct sk_buff *skb)
+{
+ XFRM_SPI_SKB_CB(skb)->family = AF_INET;
+ XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
+
+ return vti_input_ipip(skb, ip_hdr(skb)->protocol, ip_hdr(skb)->saddr, 0);
+}
+
static int vti_rcv_cb(struct sk_buff *skb, int err)
{
unsigned short family;
@@ -435,6 +470,12 @@ static struct xfrm4_protocol vti_ipcomp4_protocol __read_mostly = {
.priority = 100,
};
+static struct xfrm_tunnel ipip_handler __read_mostly = {
+ .handler = vti_rcv_ipip,
+ .err_handler = vti4_err,
+ .priority = 0,
+};
+
static int __net_init vti_init_net(struct net *net)
{
int err;
@@ -603,6 +644,13 @@ static int __init vti_init(void)
if (err < 0)
goto xfrm_proto_comp_failed;
+ msg = "ipip tunnel";
+ err = xfrm4_tunnel_register(&ipip_handler, AF_INET);
+ if (err < 0) {
+ pr_info("%s: cant't register tunnel\n",__func__);
+ goto xfrm_tunnel_failed;
+ }
+
msg = "netlink interface";
err = rtnl_link_register(&vti_link_ops);
if (err < 0)
@@ -612,6 +660,8 @@ static int __init vti_init(void)
rtnl_link_failed:
xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
+xfrm_tunnel_failed:
+ xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
xfrm_proto_comp_failed:
xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
xfrm_proto_ah_failed:
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index b61977db9b7f..2a909e5f9ba0 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -846,9 +846,9 @@ static int clusterip_net_init(struct net *net)
static void clusterip_net_exit(struct net *net)
{
+#ifdef CONFIG_PROC_FS
struct clusterip_net *cn = clusterip_pernet(net);
-#ifdef CONFIG_PROC_FS
mutex_lock(&cn->mutex);
proc_remove(cn->procdir);
cn->procdir = NULL;
diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
index 2687db015b6f..fa2ba7c500e4 100644
--- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
@@ -215,6 +215,7 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb,
/* Change outer to look like the reply to an incoming packet */
nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple);
+ target.dst.protonum = IPPROTO_ICMP;
if (!nf_nat_ipv4_manip_pkt(skb, 0, &target, manip))
return 0;
diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic_main.c b/net/ipv4/netfilter/nf_nat_snmp_basic_main.c
index a0aa13bcabda..0a8a60c1bf9a 100644
--- a/net/ipv4/netfilter/nf_nat_snmp_basic_main.c
+++ b/net/ipv4/netfilter/nf_nat_snmp_basic_main.c
@@ -105,6 +105,8 @@ static void fast_csum(struct snmp_ctx *ctx, unsigned char offset)
int snmp_version(void *context, size_t hdrlen, unsigned char tag,
const void *data, size_t datalen)
{
+ if (datalen != 1)
+ return -EINVAL;
if (*(unsigned char *)data > 1)
return -ENOTSUPP;
return 1;
@@ -114,8 +116,11 @@ int snmp_helper(void *context, size_t hdrlen, unsigned char tag,
const void *data, size_t datalen)
{
struct snmp_ctx *ctx = (struct snmp_ctx *)context;
- __be32 *pdata = (__be32 *)data;
+ __be32 *pdata;
+ if (datalen != 4)
+ return -EINVAL;
+ pdata = (__be32 *)data;
if (*pdata == ctx->from) {
pr_debug("%s: %pI4 to %pI4\n", __func__,
(void *)&ctx->from, (void *)&ctx->to);
diff --git a/net/ipv4/netlink.c b/net/ipv4/netlink.c
index f86bb4f06609..d8e3a1fb8e82 100644
--- a/net/ipv4/netlink.c
+++ b/net/ipv4/netlink.c
@@ -3,9 +3,10 @@
#include <linux/types.h>
#include <net/net_namespace.h>
#include <net/netlink.h>
+#include <linux/in6.h>
#include <net/ip.h>
-int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto,
+int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, u8 family,
struct netlink_ext_ack *extack)
{
*ip_proto = nla_get_u8(attr);
@@ -13,11 +14,19 @@ int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto,
switch (*ip_proto) {
case IPPROTO_TCP:
case IPPROTO_UDP:
+ return 0;
case IPPROTO_ICMP:
+ if (family != AF_INET)
+ break;
+ return 0;
+#if IS_ENABLED(CONFIG_IPV6)
+ case IPPROTO_ICMPV6:
+ if (family != AF_INET6)
+ break;
return 0;
- default:
- NL_SET_ERR_MSG(extack, "Unsupported ip proto");
- return -EOPNOTSUPP;
+#endif
}
+ NL_SET_ERR_MSG(extack, "Unsupported ip proto");
+ return -EOPNOTSUPP;
}
EXPORT_SYMBOL_GPL(rtm_getroute_parse_ip_proto);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index ce92f73cf104..7bb9128c8363 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -887,13 +887,15 @@ void ip_rt_send_redirect(struct sk_buff *skb)
/* No redirected packets during ip_rt_redirect_silence;
* reset the algorithm.
*/
- if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence))
+ if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence)) {
peer->rate_tokens = 0;
+ peer->n_redirects = 0;
+ }
/* Too many ignored redirects; do not send anything
* set dst.rate_last to the last seen redirected packet.
*/
- if (peer->rate_tokens >= ip_rt_redirect_number) {
+ if (peer->n_redirects >= ip_rt_redirect_number) {
peer->rate_last = jiffies;
goto out_put_peer;
}
@@ -910,6 +912,7 @@ void ip_rt_send_redirect(struct sk_buff *skb)
icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw);
peer->rate_last = jiffies;
++peer->rate_tokens;
+ ++peer->n_redirects;
#ifdef CONFIG_IP_ROUTE_VERBOSE
if (log_martians &&
peer->rate_tokens == ip_rt_redirect_number)
@@ -2800,7 +2803,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
if (tb[RTA_IP_PROTO]) {
err = rtm_getroute_parse_ip_proto(tb[RTA_IP_PROTO],
- &ip_proto, extack);
+ &ip_proto, AF_INET, extack);
if (err)
return err;
}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 2079145a3b7c..cf3c5095c10e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2528,6 +2528,7 @@ void tcp_write_queue_purge(struct sock *sk)
sk_mem_reclaim(sk);
tcp_clear_all_retrans_hints(tcp_sk(sk));
tcp_sk(sk)->packets_out = 0;
+ inet_csk(sk)->icsk_backoff = 0;
}
int tcp_disconnect(struct sock *sk, int flags)
@@ -2576,7 +2577,6 @@ int tcp_disconnect(struct sock *sk, int flags)
tp->write_seq += tp->max_window + 2;
if (tp->write_seq == 0)
tp->write_seq = 1;
- icsk->icsk_backoff = 0;
tp->snd_cwnd = 2;
icsk->icsk_probes_out = 0;
tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index efc6fef692ff..ec3cea9d6828 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -536,12 +536,15 @@ int tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
if (sock_owned_by_user(sk))
break;
+ skb = tcp_rtx_queue_head(sk);
+ if (WARN_ON_ONCE(!skb))
+ break;
+
icsk->icsk_backoff--;
icsk->icsk_rto = tp->srtt_us ? __tcp_set_rto(tp) :
TCP_TIMEOUT_INIT;
icsk->icsk_rto = inet_csk_rto_backoff(icsk, TCP_RTO_MAX);
- skb = tcp_rtx_queue_head(sk);
tcp_mstamp_refresh(tp);
delta_us = (u32)(tp->tcp_mstamp - tcp_skb_timestamp_us(skb));
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 730bc44dbad9..ccc78f3a4b60 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2347,6 +2347,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
/* "skb_mstamp_ns" is used as a start point for the retransmit timer */
skb->skb_mstamp_ns = tp->tcp_wstamp_ns = tp->tcp_clock_cache;
list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue);
+ tcp_init_tso_segs(skb, mss_now);
goto repair; /* Skip network transmission */
}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 5c3cd5d84a6f..372fdc5381a9 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -562,10 +562,12 @@ static int __udp4_lib_err_encap_no_sk(struct sk_buff *skb, u32 info)
for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) {
int (*handler)(struct sk_buff *skb, u32 info);
+ const struct ip_tunnel_encap_ops *encap;
- if (!iptun_encaps[i])
+ encap = rcu_dereference(iptun_encaps[i]);
+ if (!encap)
continue;
- handler = rcu_dereference(iptun_encaps[i]->err_handler);
+ handler = encap->err_handler;
if (handler && !handler(skb, info))
return 0;
}
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 93d5ad2b1a69..72ffd3d760ff 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1165,7 +1165,8 @@ check_cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long *expires)
list_for_each_entry(ifa, &idev->addr_list, if_list) {
if (ifa == ifp)
continue;
- if (!ipv6_prefix_equal(&ifa->addr, &ifp->addr,
+ if (ifa->prefix_len != ifp->prefix_len ||
+ !ipv6_prefix_equal(&ifa->addr, &ifp->addr,
ifp->prefix_len))
continue;
if (ifa->flags & (IFA_F_PERMANENT | IFA_F_NOPREFIXROUTE))
@@ -3495,8 +3496,8 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
if (!addrconf_link_ready(dev)) {
/* device is not ready yet. */
- pr_info("ADDRCONF(NETDEV_UP): %s: link is not ready\n",
- dev->name);
+ pr_debug("ADDRCONF(NETDEV_UP): %s: link is not ready\n",
+ dev->name);
break;
}
@@ -5120,6 +5121,8 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb,
if (idev) {
err = in6_dump_addrs(idev, skb, cb, s_ip_idx,
&fillargs);
+ if (err > 0)
+ err = 0;
}
goto put_tgt_net;
}
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 5afe9f83374d..239d4a65ad6e 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -296,7 +296,7 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info
skb->len += tailen;
skb->data_len += tailen;
skb->truesize += tailen;
- if (sk)
+ if (sk && sk_fullsock(sk))
refcount_add(tailen, &sk->sk_wmem_alloc);
goto out;
diff --git a/net/ipv6/fou6.c b/net/ipv6/fou6.c
index b858bd5280bf..867474abe269 100644
--- a/net/ipv6/fou6.c
+++ b/net/ipv6/fou6.c
@@ -72,7 +72,7 @@ static int gue6_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
static int gue6_err_proto_handler(int proto, struct sk_buff *skb,
struct inet6_skb_parm *opt,
- u8 type, u8 code, int offset, u32 info)
+ u8 type, u8 code, int offset, __be32 info)
{
const struct inet6_protocol *ipprot;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index b1be67ca6768..26f25b6e2833 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -534,13 +534,9 @@ static int ip6erspan_rcv(struct sk_buff *skb, int gre_hdr_len,
struct ip6_tnl *tunnel;
u8 ver;
- if (unlikely(!pskb_may_pull(skb, sizeof(*ershdr))))
- return PACKET_REJECT;
-
ipv6h = ipv6_hdr(skb);
ershdr = (struct erspan_base_hdr *)skb->data;
ver = ershdr->ver;
- tpi->key = cpu_to_be32(get_session_id(ershdr));
tunnel = ip6gre_tunnel_lookup(skb->dev,
&ipv6h->saddr, &ipv6h->daddr, tpi->key,
@@ -1723,6 +1719,27 @@ static int ip6erspan_tap_validate(struct nlattr *tb[], struct nlattr *data[],
return 0;
}
+static void ip6erspan_set_version(struct nlattr *data[],
+ struct __ip6_tnl_parm *parms)
+{
+ if (!data)
+ return;
+
+ parms->erspan_ver = 1;
+ if (data[IFLA_GRE_ERSPAN_VER])
+ parms->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]);
+
+ if (parms->erspan_ver == 1) {
+ if (data[IFLA_GRE_ERSPAN_INDEX])
+ parms->index = nla_get_u32(data[IFLA_GRE_ERSPAN_INDEX]);
+ } else if (parms->erspan_ver == 2) {
+ if (data[IFLA_GRE_ERSPAN_DIR])
+ parms->dir = nla_get_u8(data[IFLA_GRE_ERSPAN_DIR]);
+ if (data[IFLA_GRE_ERSPAN_HWID])
+ parms->hwid = nla_get_u16(data[IFLA_GRE_ERSPAN_HWID]);
+ }
+}
+
static void ip6gre_netlink_parms(struct nlattr *data[],
struct __ip6_tnl_parm *parms)
{
@@ -1771,20 +1788,6 @@ static void ip6gre_netlink_parms(struct nlattr *data[],
if (data[IFLA_GRE_COLLECT_METADATA])
parms->collect_md = true;
-
- parms->erspan_ver = 1;
- if (data[IFLA_GRE_ERSPAN_VER])
- parms->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]);
-
- if (parms->erspan_ver == 1) {
- if (data[IFLA_GRE_ERSPAN_INDEX])
- parms->index = nla_get_u32(data[IFLA_GRE_ERSPAN_INDEX]);
- } else if (parms->erspan_ver == 2) {
- if (data[IFLA_GRE_ERSPAN_DIR])
- parms->dir = nla_get_u8(data[IFLA_GRE_ERSPAN_DIR]);
- if (data[IFLA_GRE_ERSPAN_HWID])
- parms->hwid = nla_get_u16(data[IFLA_GRE_ERSPAN_HWID]);
- }
}
static int ip6gre_tap_init(struct net_device *dev)
@@ -2102,12 +2105,31 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
struct __ip6_tnl_parm *p = &t->parms;
+ __be16 o_flags = p->o_flags;
+
+ if (p->erspan_ver == 1 || p->erspan_ver == 2) {
+ if (!p->collect_md)
+ o_flags |= TUNNEL_KEY;
+
+ if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, p->erspan_ver))
+ goto nla_put_failure;
+
+ if (p->erspan_ver == 1) {
+ if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, p->index))
+ goto nla_put_failure;
+ } else {
+ if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, p->dir))
+ goto nla_put_failure;
+ if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, p->hwid))
+ goto nla_put_failure;
+ }
+ }
if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) ||
nla_put_be16(skb, IFLA_GRE_IFLAGS,
gre_tnl_flags_to_gre_flags(p->i_flags)) ||
nla_put_be16(skb, IFLA_GRE_OFLAGS,
- gre_tnl_flags_to_gre_flags(p->o_flags)) ||
+ gre_tnl_flags_to_gre_flags(o_flags)) ||
nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) ||
nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) ||
nla_put_in6_addr(skb, IFLA_GRE_LOCAL, &p->laddr) ||
@@ -2116,8 +2138,7 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev)
nla_put_u8(skb, IFLA_GRE_ENCAP_LIMIT, p->encap_limit) ||
nla_put_be32(skb, IFLA_GRE_FLOWINFO, p->flowinfo) ||
nla_put_u32(skb, IFLA_GRE_FLAGS, p->flags) ||
- nla_put_u32(skb, IFLA_GRE_FWMARK, p->fwmark) ||
- nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, p->index))
+ nla_put_u32(skb, IFLA_GRE_FWMARK, p->fwmark))
goto nla_put_failure;
if (nla_put_u16(skb, IFLA_GRE_ENCAP_TYPE,
@@ -2135,19 +2156,6 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev)
goto nla_put_failure;
}
- if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, p->erspan_ver))
- goto nla_put_failure;
-
- if (p->erspan_ver == 1) {
- if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, p->index))
- goto nla_put_failure;
- } else if (p->erspan_ver == 2) {
- if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, p->dir))
- goto nla_put_failure;
- if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, p->hwid))
- goto nla_put_failure;
- }
-
return 0;
nla_put_failure:
@@ -2202,6 +2210,7 @@ static int ip6erspan_newlink(struct net *src_net, struct net_device *dev,
int err;
ip6gre_netlink_parms(data, &nt->parms);
+ ip6erspan_set_version(data, &nt->parms);
ign = net_generic(net, ip6gre_net_id);
if (nt->parms.collect_md) {
@@ -2247,6 +2256,7 @@ static int ip6erspan_changelink(struct net_device *dev, struct nlattr *tb[],
if (IS_ERR(t))
return PTR_ERR(t);
+ ip6erspan_set_version(data, &p);
ip6gre_tunnel_unlink_md(ign, t);
ip6gre_tunnel_unlink(ign, t);
ip6erspan_tnl_change(t, &p, !tb[IFLA_MTU]);
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 30337b38274b..cc01aa3f2b5e 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1516,6 +1516,9 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all)
continue;
rhltable_remove(&mrt->mfc_hash, &c->mnode, ip6mr_rht_params);
list_del_rcu(&c->list);
+ call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net),
+ FIB_EVENT_ENTRY_DEL,
+ (struct mfc6_cache *)c, mrt->id);
mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE);
mr_cache_put(c);
}
@@ -1524,10 +1527,6 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all)
spin_lock_bh(&mfc_unres_lock);
list_for_each_entry_safe(c, tmp, &mrt->mfc_unres_queue, list) {
list_del(&c->list);
- call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net),
- FIB_EVENT_ENTRY_DEL,
- (struct mfc6_cache *)c,
- mrt->id);
mr6_netlink_event(mrt, (struct mfc6_cache *)c,
RTM_DELROUTE);
ip6mr_destroy_unres(mrt, (struct mfc6_cache *)c);
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 8b075f0bc351..6d0b1f3e927b 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -23,9 +23,11 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb)
struct sock *sk = sk_to_full_sk(skb->sk);
unsigned int hh_len;
struct dst_entry *dst;
+ int strict = (ipv6_addr_type(&iph->daddr) &
+ (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL));
struct flowi6 fl6 = {
.flowi6_oif = sk && sk->sk_bound_dev_if ? sk->sk_bound_dev_if :
- rt6_need_strict(&iph->daddr) ? skb_dst(skb)->dev->ifindex : 0,
+ strict ? skb_dst(skb)->dev->ifindex : 0,
.flowi6_mark = skb->mark,
.flowi6_uid = sock_net_uid(net, sk),
.daddr = iph->daddr,
diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
index 23022447eb49..7a41ee3c11b4 100644
--- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
@@ -226,6 +226,7 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb,
}
nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple);
+ target.dst.protonum = IPPROTO_ICMPV6;
if (!nf_nat_ipv6_manip_pkt(skb, 0, &target, manip))
return 0;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 964491cf3672..8dad1d690b78 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1274,18 +1274,29 @@ static DEFINE_SPINLOCK(rt6_exception_lock);
static void rt6_remove_exception(struct rt6_exception_bucket *bucket,
struct rt6_exception *rt6_ex)
{
+ struct fib6_info *from;
struct net *net;
if (!bucket || !rt6_ex)
return;
net = dev_net(rt6_ex->rt6i->dst.dev);
+ net->ipv6.rt6_stats->fib_rt_cache--;
+
+ /* purge completely the exception to allow releasing the held resources:
+ * some [sk] cache may keep the dst around for unlimited time
+ */
+ from = rcu_dereference_protected(rt6_ex->rt6i->from,
+ lockdep_is_held(&rt6_exception_lock));
+ rcu_assign_pointer(rt6_ex->rt6i->from, NULL);
+ fib6_info_release(from);
+ dst_dev_put(&rt6_ex->rt6i->dst);
+
hlist_del_rcu(&rt6_ex->hlist);
dst_release(&rt6_ex->rt6i->dst);
kfree_rcu(rt6_ex, rcu);
WARN_ON_ONCE(!bucket->depth);
bucket->depth--;
- net->ipv6.rt6_stats->fib_rt_cache--;
}
/* Remove oldest rt6_ex in bucket and free the memory
@@ -1599,15 +1610,15 @@ static int rt6_remove_exception_rt(struct rt6_info *rt)
static void rt6_update_exception_stamp_rt(struct rt6_info *rt)
{
struct rt6_exception_bucket *bucket;
- struct fib6_info *from = rt->from;
struct in6_addr *src_key = NULL;
struct rt6_exception *rt6_ex;
-
- if (!from ||
- !(rt->rt6i_flags & RTF_CACHE))
- return;
+ struct fib6_info *from;
rcu_read_lock();
+ from = rcu_dereference(rt->from);
+ if (!from || !(rt->rt6i_flags & RTF_CACHE))
+ goto unlock;
+
bucket = rcu_dereference(from->rt6i_exception_bucket);
#ifdef CONFIG_IPV6_SUBTREES
@@ -1626,6 +1637,7 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt)
if (rt6_ex)
rt6_ex->stamp = jiffies;
+unlock:
rcu_read_unlock();
}
@@ -2742,20 +2754,24 @@ static int ip6_route_check_nh_onlink(struct net *net,
u32 tbid = l3mdev_fib_table(dev) ? : RT_TABLE_MAIN;
const struct in6_addr *gw_addr = &cfg->fc_gateway;
u32 flags = RTF_LOCAL | RTF_ANYCAST | RTF_REJECT;
+ struct fib6_info *from;
struct rt6_info *grt;
int err;
err = 0;
grt = ip6_nh_lookup_table(net, cfg, gw_addr, tbid, 0);
if (grt) {
+ rcu_read_lock();
+ from = rcu_dereference(grt->from);
if (!grt->dst.error &&
/* ignore match if it is the default route */
- grt->from && !ipv6_addr_any(&grt->from->fib6_dst.addr) &&
+ from && !ipv6_addr_any(&from->fib6_dst.addr) &&
(grt->rt6i_flags & flags || dev != grt->dst.dev)) {
NL_SET_ERR_MSG(extack,
"Nexthop has invalid gateway or device mismatch");
err = -EINVAL;
}
+ rcu_read_unlock();
ip6_rt_put(grt);
}
@@ -4166,6 +4182,10 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
cfg->fc_gateway = nla_get_in6_addr(tb[RTA_GATEWAY]);
cfg->fc_flags |= RTF_GATEWAY;
}
+ if (tb[RTA_VIA]) {
+ NL_SET_ERR_MSG(extack, "IPv6 does not support RTA_VIA attribute");
+ goto errout;
+ }
if (tb[RTA_DST]) {
int plen = (rtm->rtm_dst_len + 7) >> 3;
@@ -4649,7 +4669,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
table = rt->fib6_table->tb6_id;
else
table = RT6_TABLE_UNSPEC;
- rtm->rtm_table = table;
+ rtm->rtm_table = table < 256 ? table : RT_TABLE_COMPAT;
if (nla_put_u32(skb, RTA_TABLE, table))
goto nla_put_failure;
@@ -4873,7 +4893,8 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
if (tb[RTA_IP_PROTO]) {
err = rtm_getroute_parse_ip_proto(tb[RTA_IP_PROTO],
- &fl6.flowi6_proto, extack);
+ &fl6.flowi6_proto, AF_INET6,
+ extack);
if (err)
goto errout;
}
diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c
index 8d0ba757a46c..9b2f272ca164 100644
--- a/net/ipv6/seg6.c
+++ b/net/ipv6/seg6.c
@@ -221,9 +221,7 @@ static int seg6_genl_get_tunsrc(struct sk_buff *skb, struct genl_info *info)
rcu_read_unlock();
genlmsg_end(msg, hdr);
- genlmsg_reply(msg, info);
-
- return 0;
+ return genlmsg_reply(msg, info);
nla_put_failure:
rcu_read_unlock();
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 8181ee7e1e27..ee5403cbe655 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -146,6 +146,8 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
} else {
ip6_flow_hdr(hdr, 0, flowlabel);
hdr->hop_limit = ip6_dst_hoplimit(skb_dst(skb));
+
+ memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
}
hdr->nexthdr = NEXTHDR_ROUTING;
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 1e03305c0549..09e440e8dfae 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -546,7 +546,8 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
}
err = 0;
- if (!ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4, type, data_len))
+ if (__in6_dev_get(skb->dev) &&
+ !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4, type, data_len))
goto out;
if (t->parms.iph.daddr == 0)
@@ -1872,6 +1873,7 @@ static int __net_init sit_init_net(struct net *net)
err_reg_dev:
ipip6_dev_free(sitn->fb_tunnel_dev);
+ free_netdev(sitn->fb_tunnel_dev);
err_alloc_dev:
return err;
}
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 2596ffdeebea..b444483cdb2b 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -288,8 +288,8 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
int peeked, peeking, off;
int err;
int is_udplite = IS_UDPLITE(sk);
+ struct udp_mib __percpu *mib;
bool checksum_valid = false;
- struct udp_mib *mib;
int is_udp4;
if (flags & MSG_ERRQUEUE)
@@ -420,17 +420,19 @@ EXPORT_SYMBOL(udpv6_encap_enable);
*/
static int __udp6_lib_err_encap_no_sk(struct sk_buff *skb,
struct inet6_skb_parm *opt,
- u8 type, u8 code, int offset, u32 info)
+ u8 type, u8 code, int offset, __be32 info)
{
int i;
for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) {
int (*handler)(struct sk_buff *skb, struct inet6_skb_parm *opt,
- u8 type, u8 code, int offset, u32 info);
+ u8 type, u8 code, int offset, __be32 info);
+ const struct ip6_tnl_encap_ops *encap;
- if (!ip6tun_encaps[i])
+ encap = rcu_dereference(ip6tun_encaps[i]);
+ if (!encap)
continue;
- handler = rcu_dereference(ip6tun_encaps[i]->err_handler);
+ handler = encap->err_handler;
if (handler && !handler(skb, opt, type, code, offset, info))
return 0;
}
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index f5b4febeaa25..bc65db782bfb 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -344,8 +344,8 @@ static void __net_exit xfrm6_tunnel_net_exit(struct net *net)
struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net);
unsigned int i;
- xfrm_state_flush(net, IPSEC_PROTO_ANY, false);
xfrm_flush_gc();
+ xfrm_state_flush(net, IPSEC_PROTO_ANY, false, true);
for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++)
WARN_ON_ONCE(!hlist_empty(&xfrm6_tn->spi_byaddr[i]));
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 655c787f9d54..5651c29cb5bd 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -196,30 +196,22 @@ static int pfkey_release(struct socket *sock)
return 0;
}
-static int pfkey_broadcast_one(struct sk_buff *skb, struct sk_buff **skb2,
- gfp_t allocation, struct sock *sk)
+static int pfkey_broadcast_one(struct sk_buff *skb, gfp_t allocation,
+ struct sock *sk)
{
int err = -ENOBUFS;
- sock_hold(sk);
- if (*skb2 == NULL) {
- if (refcount_read(&skb->users) != 1) {
- *skb2 = skb_clone(skb, allocation);
- } else {
- *skb2 = skb;
- refcount_inc(&skb->users);
- }
- }
- if (*skb2 != NULL) {
- if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) {
- skb_set_owner_r(*skb2, sk);
- skb_queue_tail(&sk->sk_receive_queue, *skb2);
- sk->sk_data_ready(sk);
- *skb2 = NULL;
- err = 0;
- }
+ if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
+ return err;
+
+ skb = skb_clone(skb, allocation);
+
+ if (skb) {
+ skb_set_owner_r(skb, sk);
+ skb_queue_tail(&sk->sk_receive_queue, skb);
+ sk->sk_data_ready(sk);
+ err = 0;
}
- sock_put(sk);
return err;
}
@@ -234,7 +226,6 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation,
{
struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id);
struct sock *sk;
- struct sk_buff *skb2 = NULL;
int err = -ESRCH;
/* XXX Do we need something like netlink_overrun? I think
@@ -253,7 +244,7 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation,
* socket.
*/
if (pfk->promisc)
- pfkey_broadcast_one(skb, &skb2, GFP_ATOMIC, sk);
+ pfkey_broadcast_one(skb, GFP_ATOMIC, sk);
/* the exact target will be processed later */
if (sk == one_sk)
@@ -268,7 +259,7 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation,
continue;
}
- err2 = pfkey_broadcast_one(skb, &skb2, GFP_ATOMIC, sk);
+ err2 = pfkey_broadcast_one(skb, GFP_ATOMIC, sk);
/* Error is cleared after successful sending to at least one
* registered KM */
@@ -278,9 +269,8 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation,
rcu_read_unlock();
if (one_sk != NULL)
- err = pfkey_broadcast_one(skb, &skb2, allocation, one_sk);
+ err = pfkey_broadcast_one(skb, allocation, one_sk);
- kfree_skb(skb2);
kfree_skb(skb);
return err;
}
@@ -1783,7 +1773,7 @@ static int pfkey_flush(struct sock *sk, struct sk_buff *skb, const struct sadb_m
if (proto == 0)
return -EINVAL;
- err = xfrm_state_flush(net, proto, true);
+ err = xfrm_state_flush(net, proto, true, false);
err2 = unicast_flush_resp(sk, hdr);
if (err || err2) {
if (err == -ESRCH) /* empty table - go quietly */
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 26f1d435696a..fed6becc5daf 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -83,8 +83,7 @@
#define L2TP_SLFLAG_S 0x40000000
#define L2TP_SL_SEQ_MASK 0x00ffffff
-#define L2TP_HDR_SIZE_SEQ 10
-#define L2TP_HDR_SIZE_NOSEQ 6
+#define L2TP_HDR_SIZE_MAX 14
/* Default trace flags */
#define L2TP_DEFAULT_DEBUG_FLAGS 0
@@ -808,7 +807,7 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb)
__skb_pull(skb, sizeof(struct udphdr));
/* Short packet? */
- if (!pskb_may_pull(skb, L2TP_HDR_SIZE_SEQ)) {
+ if (!pskb_may_pull(skb, L2TP_HDR_SIZE_MAX)) {
l2tp_info(tunnel, L2TP_MSG_DATA,
"%s: recv short packet (len=%d)\n",
tunnel->name, skb->len);
@@ -884,6 +883,10 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb)
goto error;
}
+ if (tunnel->version == L2TP_HDR_VER_3 &&
+ l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr))
+ goto error;
+
l2tp_recv_common(session, skb, ptr, optr, hdrflags, length);
l2tp_session_dec_refcount(session);
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 9c9afe94d389..b2ce90260c35 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -301,6 +301,26 @@ static inline bool l2tp_tunnel_uses_xfrm(const struct l2tp_tunnel *tunnel)
}
#endif
+static inline int l2tp_v3_ensure_opt_in_linear(struct l2tp_session *session, struct sk_buff *skb,
+ unsigned char **ptr, unsigned char **optr)
+{
+ int opt_len = session->peer_cookie_len + l2tp_get_l2specific_len(session);
+
+ if (opt_len > 0) {
+ int off = *ptr - *optr;
+
+ if (!pskb_may_pull(skb, off + opt_len))
+ return -1;
+
+ if (skb->data != *optr) {
+ *optr = skb->data;
+ *ptr = skb->data + off;
+ }
+ }
+
+ return 0;
+}
+
#define l2tp_printk(ptr, type, func, fmt, ...) \
do { \
if (((ptr)->debug) & (type)) \
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 35f6f86d4dcc..d4c60523c549 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -165,6 +165,9 @@ static int l2tp_ip_recv(struct sk_buff *skb)
print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length);
}
+ if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr))
+ goto discard_sess;
+
l2tp_recv_common(session, skb, ptr, optr, 0, skb->len);
l2tp_session_dec_refcount(session);
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 237f1a4a0b0c..0ae6899edac0 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -178,6 +178,9 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length);
}
+ if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr))
+ goto discard_sess;
+
l2tp_recv_common(session, skb, ptr, optr, 0, skb->len);
l2tp_session_dec_refcount(session);
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index 69e831bc317b..54821fb1a960 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -8,7 +8,7 @@
* Copyright 2007, Michael Wu <flamingice@sourmilk.net>
* Copyright 2007-2010, Intel Corporation
* Copyright(c) 2015-2017 Intel Deutschland GmbH
- * Copyright (C) 2018 Intel Corporation
+ * Copyright (C) 2018 - 2019 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -366,6 +366,8 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid,
set_bit(HT_AGG_STATE_STOPPING, &tid_tx->state);
+ ieee80211_agg_stop_txq(sta, tid);
+
spin_unlock_bh(&sta->lock);
ht_dbg(sta->sdata, "Tx BA session stop requested for %pM tid %u\n",
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index de65fe3ed9cc..96496b2c1670 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -941,6 +941,7 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
BSS_CHANGED_P2P_PS |
BSS_CHANGED_TXPOWER;
int err;
+ int prev_beacon_int;
old = sdata_dereference(sdata->u.ap.beacon, sdata);
if (old)
@@ -963,6 +964,7 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
sdata->needed_rx_chains = sdata->local->rx_chains;
+ prev_beacon_int = sdata->vif.bss_conf.beacon_int;
sdata->vif.bss_conf.beacon_int = params->beacon_interval;
if (params->he_cap)
@@ -974,8 +976,10 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
if (!err)
ieee80211_vif_copy_chanctx_to_vlans(sdata, false);
mutex_unlock(&local->mtx);
- if (err)
+ if (err) {
+ sdata->vif.bss_conf.beacon_int = prev_beacon_int;
return err;
+ }
/*
* Apply control port protocol, this allows us to
@@ -1490,6 +1494,10 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev,
if (params->sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER))
sta->sta.tdls = true;
+ if (sta->sta.tdls && sdata->vif.type == NL80211_IFTYPE_STATION &&
+ !sdata->u.mgd.associated)
+ return -EINVAL;
+
err = sta_apply_parameters(local, sta, params);
if (err) {
sta_info_free(local, sta);
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 87a729926734..977dea436ee8 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -615,13 +615,13 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len,
* We need a bit of data queued to build aggregates properly, so
* instruct the TCP stack to allow more than a single ms of data
* to be queued in the stack. The value is a bit-shift of 1
- * second, so 8 is ~4ms of queued data. Only affects local TCP
+ * second, so 7 is ~8ms of queued data. Only affects local TCP
* sockets.
* This is the default, anyhow - drivers may need to override it
* for local reasons (longer buffers, longer completion time, or
* similar).
*/
- local->hw.tx_sk_pacing_shift = 8;
+ local->hw.tx_sk_pacing_shift = 7;
/* set up some defaults */
local->hw.queues = 1;
diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h
index cad6592c52a1..2ec7011a4d07 100644
--- a/net/mac80211/mesh.h
+++ b/net/mac80211/mesh.h
@@ -70,6 +70,7 @@ enum mesh_deferred_task_flags {
* @dst: mesh path destination mac address
* @mpp: mesh proxy mac address
* @rhash: rhashtable list pointer
+ * @walk_list: linked list containing all mesh_path objects.
* @gate_list: list pointer for known gates list
* @sdata: mesh subif
* @next_hop: mesh neighbor to which frames for this destination will be
@@ -105,6 +106,7 @@ struct mesh_path {
u8 dst[ETH_ALEN];
u8 mpp[ETH_ALEN]; /* used for MPP or MAP */
struct rhash_head rhash;
+ struct hlist_node walk_list;
struct hlist_node gate_list;
struct ieee80211_sub_if_data *sdata;
struct sta_info __rcu *next_hop;
@@ -133,12 +135,16 @@ struct mesh_path {
* gate's mpath may or may not be resolved and active.
* @gates_lock: protects updates to known_gates
* @rhead: the rhashtable containing struct mesh_paths, keyed by dest addr
+ * @walk_head: linked list containging all mesh_path objects
+ * @walk_lock: lock protecting walk_head
* @entries: number of entries in the table
*/
struct mesh_table {
struct hlist_head known_gates;
spinlock_t gates_lock;
struct rhashtable rhead;
+ struct hlist_head walk_head;
+ spinlock_t walk_lock;
atomic_t entries; /* Up to MAX_MESH_NEIGHBOURS */
};
diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c
index a5125624a76d..88a6d5e18ccc 100644
--- a/net/mac80211/mesh_pathtbl.c
+++ b/net/mac80211/mesh_pathtbl.c
@@ -59,8 +59,10 @@ static struct mesh_table *mesh_table_alloc(void)
return NULL;
INIT_HLIST_HEAD(&newtbl->known_gates);
+ INIT_HLIST_HEAD(&newtbl->walk_head);
atomic_set(&newtbl->entries, 0);
spin_lock_init(&newtbl->gates_lock);
+ spin_lock_init(&newtbl->walk_lock);
return newtbl;
}
@@ -249,28 +251,15 @@ mpp_path_lookup(struct ieee80211_sub_if_data *sdata, const u8 *dst)
static struct mesh_path *
__mesh_path_lookup_by_idx(struct mesh_table *tbl, int idx)
{
- int i = 0, ret;
- struct mesh_path *mpath = NULL;
- struct rhashtable_iter iter;
-
- ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_ATOMIC);
- if (ret)
- return NULL;
-
- rhashtable_walk_start(&iter);
+ int i = 0;
+ struct mesh_path *mpath;
- while ((mpath = rhashtable_walk_next(&iter))) {
- if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN)
- continue;
- if (IS_ERR(mpath))
- break;
+ hlist_for_each_entry_rcu(mpath, &tbl->walk_head, walk_list) {
if (i++ == idx)
break;
}
- rhashtable_walk_stop(&iter);
- rhashtable_walk_exit(&iter);
- if (IS_ERR(mpath) || !mpath)
+ if (!mpath)
return NULL;
if (mpath_expired(mpath)) {
@@ -432,6 +421,7 @@ struct mesh_path *mesh_path_add(struct ieee80211_sub_if_data *sdata,
return ERR_PTR(-ENOMEM);
tbl = sdata->u.mesh.mesh_paths;
+ spin_lock_bh(&tbl->walk_lock);
do {
ret = rhashtable_lookup_insert_fast(&tbl->rhead,
&new_mpath->rhash,
@@ -441,20 +431,20 @@ struct mesh_path *mesh_path_add(struct ieee80211_sub_if_data *sdata,
mpath = rhashtable_lookup_fast(&tbl->rhead,
dst,
mesh_rht_params);
-
+ else if (!ret)
+ hlist_add_head(&new_mpath->walk_list, &tbl->walk_head);
} while (unlikely(ret == -EEXIST && !mpath));
+ spin_unlock_bh(&tbl->walk_lock);
- if (ret && ret != -EEXIST)
- return ERR_PTR(ret);
-
- /* At this point either new_mpath was added, or we found a
- * matching entry already in the table; in the latter case
- * free the unnecessary new entry.
- */
- if (ret == -EEXIST) {
+ if (ret) {
kfree(new_mpath);
+
+ if (ret != -EEXIST)
+ return ERR_PTR(ret);
+
new_mpath = mpath;
}
+
sdata->u.mesh.mesh_paths_generation++;
return new_mpath;
}
@@ -480,9 +470,17 @@ int mpp_path_add(struct ieee80211_sub_if_data *sdata,
memcpy(new_mpath->mpp, mpp, ETH_ALEN);
tbl = sdata->u.mesh.mpp_paths;
+
+ spin_lock_bh(&tbl->walk_lock);
ret = rhashtable_lookup_insert_fast(&tbl->rhead,
&new_mpath->rhash,
mesh_rht_params);
+ if (!ret)
+ hlist_add_head_rcu(&new_mpath->walk_list, &tbl->walk_head);
+ spin_unlock_bh(&tbl->walk_lock);
+
+ if (ret)
+ kfree(new_mpath);
sdata->u.mesh.mpp_paths_generation++;
return ret;
@@ -503,20 +501,9 @@ void mesh_plink_broken(struct sta_info *sta)
struct mesh_table *tbl = sdata->u.mesh.mesh_paths;
static const u8 bcast[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
struct mesh_path *mpath;
- struct rhashtable_iter iter;
- int ret;
-
- ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_ATOMIC);
- if (ret)
- return;
- rhashtable_walk_start(&iter);
-
- while ((mpath = rhashtable_walk_next(&iter))) {
- if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN)
- continue;
- if (IS_ERR(mpath))
- break;
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(mpath, &tbl->walk_head, walk_list) {
if (rcu_access_pointer(mpath->next_hop) == sta &&
mpath->flags & MESH_PATH_ACTIVE &&
!(mpath->flags & MESH_PATH_FIXED)) {
@@ -530,8 +517,7 @@ void mesh_plink_broken(struct sta_info *sta)
WLAN_REASON_MESH_PATH_DEST_UNREACHABLE, bcast);
}
}
- rhashtable_walk_stop(&iter);
- rhashtable_walk_exit(&iter);
+ rcu_read_unlock();
}
static void mesh_path_free_rcu(struct mesh_table *tbl,
@@ -551,6 +537,7 @@ static void mesh_path_free_rcu(struct mesh_table *tbl,
static void __mesh_path_del(struct mesh_table *tbl, struct mesh_path *mpath)
{
+ hlist_del_rcu(&mpath->walk_list);
rhashtable_remove_fast(&tbl->rhead, &mpath->rhash, mesh_rht_params);
mesh_path_free_rcu(tbl, mpath);
}
@@ -571,27 +558,14 @@ void mesh_path_flush_by_nexthop(struct sta_info *sta)
struct ieee80211_sub_if_data *sdata = sta->sdata;
struct mesh_table *tbl = sdata->u.mesh.mesh_paths;
struct mesh_path *mpath;
- struct rhashtable_iter iter;
- int ret;
-
- ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_ATOMIC);
- if (ret)
- return;
-
- rhashtable_walk_start(&iter);
-
- while ((mpath = rhashtable_walk_next(&iter))) {
- if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN)
- continue;
- if (IS_ERR(mpath))
- break;
+ struct hlist_node *n;
+ spin_lock_bh(&tbl->walk_lock);
+ hlist_for_each_entry_safe(mpath, n, &tbl->walk_head, walk_list) {
if (rcu_access_pointer(mpath->next_hop) == sta)
__mesh_path_del(tbl, mpath);
}
-
- rhashtable_walk_stop(&iter);
- rhashtable_walk_exit(&iter);
+ spin_unlock_bh(&tbl->walk_lock);
}
static void mpp_flush_by_proxy(struct ieee80211_sub_if_data *sdata,
@@ -599,51 +573,26 @@ static void mpp_flush_by_proxy(struct ieee80211_sub_if_data *sdata,
{
struct mesh_table *tbl = sdata->u.mesh.mpp_paths;
struct mesh_path *mpath;
- struct rhashtable_iter iter;
- int ret;
-
- ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_ATOMIC);
- if (ret)
- return;
-
- rhashtable_walk_start(&iter);
-
- while ((mpath = rhashtable_walk_next(&iter))) {
- if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN)
- continue;
- if (IS_ERR(mpath))
- break;
+ struct hlist_node *n;
+ spin_lock_bh(&tbl->walk_lock);
+ hlist_for_each_entry_safe(mpath, n, &tbl->walk_head, walk_list) {
if (ether_addr_equal(mpath->mpp, proxy))
__mesh_path_del(tbl, mpath);
}
-
- rhashtable_walk_stop(&iter);
- rhashtable_walk_exit(&iter);
+ spin_unlock_bh(&tbl->walk_lock);
}
static void table_flush_by_iface(struct mesh_table *tbl)
{
struct mesh_path *mpath;
- struct rhashtable_iter iter;
- int ret;
-
- ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_ATOMIC);
- if (ret)
- return;
-
- rhashtable_walk_start(&iter);
+ struct hlist_node *n;
- while ((mpath = rhashtable_walk_next(&iter))) {
- if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN)
- continue;
- if (IS_ERR(mpath))
- break;
+ spin_lock_bh(&tbl->walk_lock);
+ hlist_for_each_entry_safe(mpath, n, &tbl->walk_head, walk_list) {
__mesh_path_del(tbl, mpath);
}
-
- rhashtable_walk_stop(&iter);
- rhashtable_walk_exit(&iter);
+ spin_unlock_bh(&tbl->walk_lock);
}
/**
@@ -675,15 +624,15 @@ static int table_path_del(struct mesh_table *tbl,
{
struct mesh_path *mpath;
- rcu_read_lock();
+ spin_lock_bh(&tbl->walk_lock);
mpath = rhashtable_lookup_fast(&tbl->rhead, addr, mesh_rht_params);
if (!mpath) {
- rcu_read_unlock();
+ spin_unlock_bh(&tbl->walk_lock);
return -ENXIO;
}
__mesh_path_del(tbl, mpath);
- rcu_read_unlock();
+ spin_unlock_bh(&tbl->walk_lock);
return 0;
}
@@ -854,28 +803,16 @@ void mesh_path_tbl_expire(struct ieee80211_sub_if_data *sdata,
struct mesh_table *tbl)
{
struct mesh_path *mpath;
- struct rhashtable_iter iter;
- int ret;
+ struct hlist_node *n;
- ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_KERNEL);
- if (ret)
- return;
-
- rhashtable_walk_start(&iter);
-
- while ((mpath = rhashtable_walk_next(&iter))) {
- if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN)
- continue;
- if (IS_ERR(mpath))
- break;
+ spin_lock_bh(&tbl->walk_lock);
+ hlist_for_each_entry_safe(mpath, n, &tbl->walk_head, walk_list) {
if ((!(mpath->flags & MESH_PATH_RESOLVING)) &&
(!(mpath->flags & MESH_PATH_FIXED)) &&
time_after(jiffies, mpath->exp_time + MESH_PATH_EXPIRE))
__mesh_path_del(tbl, mpath);
}
-
- rhashtable_walk_stop(&iter);
- rhashtable_walk_exit(&iter);
+ spin_unlock_bh(&tbl->walk_lock);
}
void mesh_path_expire(struct ieee80211_sub_if_data *sdata)
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 45aad3d3108c..c2a6da5d80da 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -231,7 +231,7 @@ static void ieee80211_handle_mu_mimo_mon(struct ieee80211_sub_if_data *sdata,
struct ieee80211_hdr_3addr hdr;
u8 category;
u8 action_code;
- } __packed action;
+ } __packed __aligned(2) action;
if (!sdata)
return;
@@ -2644,6 +2644,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx)
struct ieee80211_sub_if_data *sdata = rx->sdata;
struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
u16 ac, q, hdrlen;
+ int tailroom = 0;
hdr = (struct ieee80211_hdr *) skb->data;
hdrlen = ieee80211_hdrlen(hdr->frame_control);
@@ -2723,15 +2724,21 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx)
skb_set_queue_mapping(skb, q);
if (!--mesh_hdr->ttl) {
- IEEE80211_IFSTA_MESH_CTR_INC(ifmsh, dropped_frames_ttl);
+ if (!is_multicast_ether_addr(hdr->addr1))
+ IEEE80211_IFSTA_MESH_CTR_INC(ifmsh,
+ dropped_frames_ttl);
goto out;
}
if (!ifmsh->mshcfg.dot11MeshForwarding)
goto out;
+ if (sdata->crypto_tx_tailroom_needed_cnt)
+ tailroom = IEEE80211_ENCRYPT_TAILROOM;
+
fwd_skb = skb_copy_expand(skb, local->tx_headroom +
- sdata->encrypt_headroom, 0, GFP_ATOMIC);
+ sdata->encrypt_headroom,
+ tailroom, GFP_ATOMIC);
if (!fwd_skb)
goto out;
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index f170d6c6629a..928f13a208b0 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1938,9 +1938,16 @@ static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata,
int head_need, bool may_encrypt)
{
struct ieee80211_local *local = sdata->local;
+ struct ieee80211_hdr *hdr;
+ bool enc_tailroom;
int tail_need = 0;
- if (may_encrypt && sdata->crypto_tx_tailroom_needed_cnt) {
+ hdr = (struct ieee80211_hdr *) skb->data;
+ enc_tailroom = may_encrypt &&
+ (sdata->crypto_tx_tailroom_needed_cnt ||
+ ieee80211_is_mgmt(hdr->frame_control));
+
+ if (enc_tailroom) {
tail_need = IEEE80211_ENCRYPT_TAILROOM;
tail_need -= skb_tailroom(skb);
tail_need = max_t(int, tail_need, 0);
@@ -1948,8 +1955,7 @@ static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata,
if (skb_cloned(skb) &&
(!ieee80211_hw_check(&local->hw, SUPPORTS_CLONED_SKBS) ||
- !skb_clone_writable(skb, ETH_HLEN) ||
- (may_encrypt && sdata->crypto_tx_tailroom_needed_cnt)))
+ !skb_clone_writable(skb, ETH_HLEN) || enc_tailroom))
I802_DEBUG_INC(local->tx_expand_skb_head_cloned);
else if (head_need || tail_need)
I802_DEBUG_INC(local->tx_expand_skb_head);
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index d0eb38b890aa..ba950ae974fc 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -5,7 +5,7 @@
* Copyright 2007 Johannes Berg <johannes@sipsolutions.net>
* Copyright 2013-2014 Intel Mobile Communications GmbH
* Copyright (C) 2015-2017 Intel Deutschland GmbH
- * Copyright (C) 2018 Intel Corporation
+ * Copyright (C) 2018-2019 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -2146,6 +2146,10 @@ int ieee80211_reconfig(struct ieee80211_local *local)
case NL80211_IFTYPE_AP_VLAN:
case NL80211_IFTYPE_MONITOR:
break;
+ case NL80211_IFTYPE_ADHOC:
+ if (sdata->vif.bss_conf.ibss_joined)
+ WARN_ON(drv_join_ibss(local, sdata));
+ /* fall through */
default:
ieee80211_reconfig_stations(sdata);
/* fall through */
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 7d55d4c04088..fa763e2e50ec 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -1838,6 +1838,9 @@ static int rtm_to_route_config(struct sk_buff *skb,
goto errout;
break;
}
+ case RTA_GATEWAY:
+ NL_SET_ERR_MSG(extack, "MPLS does not support RTA_GATEWAY attribute");
+ goto errout;
case RTA_VIA:
{
if (nla_get_via(nla, &cfg->rc_via_alen,
diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
index cad48d07c818..8401cefd9f65 100644
--- a/net/netfilter/ipvs/Kconfig
+++ b/net/netfilter/ipvs/Kconfig
@@ -29,6 +29,7 @@ config IP_VS_IPV6
bool "IPv6 support for IPVS"
depends on IPV6 = y || IP_VS = IPV6
select IP6_NF_IPTABLES
+ select NF_DEFRAG_IPV6
---help---
Add IPv6 support to IPVS.
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index fe9abf3cc10a..235205c93e14 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1536,14 +1536,12 @@ ip_vs_try_to_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb,
/* sorry, all this trouble for a no-hit :) */
IP_VS_DBG_PKT(12, af, pp, skb, iph->off,
"ip_vs_in: packet continues traversal as normal");
- if (iph->fragoffs) {
- /* Fragment that couldn't be mapped to a conn entry
- * is missing module nf_defrag_ipv6
- */
- IP_VS_DBG_RL("Unhandled frag, load nf_defrag_ipv6\n");
+
+ /* Fragment couldn't be mapped to a conn entry */
+ if (iph->fragoffs)
IP_VS_DBG_PKT(7, af, pp, skb, iph->off,
"unhandled fragment");
- }
+
*verdict = NF_ACCEPT;
return 0;
}
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 432141f04af3..ac8d848d7624 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -43,6 +43,7 @@
#ifdef CONFIG_IP_VS_IPV6
#include <net/ipv6.h>
#include <net/ip6_route.h>
+#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
#endif
#include <net/route.h>
#include <net/sock.h>
@@ -900,11 +901,17 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest,
#ifdef CONFIG_IP_VS_IPV6
if (udest->af == AF_INET6) {
+ int ret;
+
atype = ipv6_addr_type(&udest->addr.in6);
if ((!(atype & IPV6_ADDR_UNICAST) ||
atype & IPV6_ADDR_LINKLOCAL) &&
!__ip_vs_addr_is_local_v6(svc->ipvs->net, &udest->addr.in6))
return -EINVAL;
+
+ ret = nf_defrag_ipv6_enable(svc->ipvs->net);
+ if (ret)
+ return ret;
} else
#endif
{
@@ -1228,6 +1235,10 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u,
ret = -EINVAL;
goto out_err;
}
+
+ ret = nf_defrag_ipv6_enable(ipvs->net);
+ if (ret)
+ goto out_err;
}
#endif
@@ -2221,6 +2232,18 @@ static int ip_vs_set_timeout(struct netns_ipvs *ipvs, struct ip_vs_timeout_user
u->udp_timeout);
#ifdef CONFIG_IP_VS_PROTO_TCP
+ if (u->tcp_timeout < 0 || u->tcp_timeout > (INT_MAX / HZ) ||
+ u->tcp_fin_timeout < 0 || u->tcp_fin_timeout > (INT_MAX / HZ)) {
+ return -EINVAL;
+ }
+#endif
+
+#ifdef CONFIG_IP_VS_PROTO_UDP
+ if (u->udp_timeout < 0 || u->udp_timeout > (INT_MAX / HZ))
+ return -EINVAL;
+#endif
+
+#ifdef CONFIG_IP_VS_PROTO_TCP
if (u->tcp_timeout) {
pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP);
pd->timeout_table[IP_VS_TCP_S_ESTABLISHED]
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 741b533148ba..db4d46332e86 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1007,6 +1007,22 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple,
}
if (nf_ct_key_equal(h, tuple, zone, net)) {
+ /* Tuple is taken already, so caller will need to find
+ * a new source port to use.
+ *
+ * Only exception:
+ * If the *original tuples* are identical, then both
+ * conntracks refer to the same flow.
+ * This is a rare situation, it can occur e.g. when
+ * more than one UDP packet is sent from same socket
+ * in different threads.
+ *
+ * Let nf_ct_resolve_clash() deal with this later.
+ */
+ if (nf_ct_tuple_equal(&ignored_conntrack->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
+ &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple))
+ continue;
+
NF_CT_STAT_INC_ATOMIC(net, found);
rcu_read_unlock();
return 1;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index fb07f6cfc719..4893f248dfdc 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -116,6 +116,23 @@ static void nft_trans_destroy(struct nft_trans *trans)
kfree(trans);
}
+static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set)
+{
+ struct net *net = ctx->net;
+ struct nft_trans *trans;
+
+ if (!nft_set_is_anonymous(set))
+ return;
+
+ list_for_each_entry_reverse(trans, &net->nft.commit_list, list) {
+ if (trans->msg_type == NFT_MSG_NEWSET &&
+ nft_trans_set(trans) == set) {
+ nft_trans_set_bound(trans) = true;
+ break;
+ }
+ }
+}
+
static int nf_tables_register_hook(struct net *net,
const struct nft_table *table,
struct nft_chain *chain)
@@ -211,18 +228,6 @@ static int nft_delchain(struct nft_ctx *ctx)
return err;
}
-/* either expr ops provide both activate/deactivate, or neither */
-static bool nft_expr_check_ops(const struct nft_expr_ops *ops)
-{
- if (!ops)
- return true;
-
- if (WARN_ON_ONCE((!ops->activate ^ !ops->deactivate)))
- return false;
-
- return true;
-}
-
static void nft_rule_expr_activate(const struct nft_ctx *ctx,
struct nft_rule *rule)
{
@@ -238,14 +243,15 @@ static void nft_rule_expr_activate(const struct nft_ctx *ctx,
}
static void nft_rule_expr_deactivate(const struct nft_ctx *ctx,
- struct nft_rule *rule)
+ struct nft_rule *rule,
+ enum nft_trans_phase phase)
{
struct nft_expr *expr;
expr = nft_expr_first(rule);
while (expr != nft_expr_last(rule) && expr->ops) {
if (expr->ops->deactivate)
- expr->ops->deactivate(ctx, expr);
+ expr->ops->deactivate(ctx, expr, phase);
expr = nft_expr_next(expr);
}
@@ -296,7 +302,7 @@ static int nft_delrule(struct nft_ctx *ctx, struct nft_rule *rule)
nft_trans_destroy(trans);
return err;
}
- nft_rule_expr_deactivate(ctx, rule);
+ nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_PREPARE);
return 0;
}
@@ -307,6 +313,9 @@ static int nft_delrule_by_chain(struct nft_ctx *ctx)
int err;
list_for_each_entry(rule, &ctx->chain->rules, list) {
+ if (!nft_is_active_next(ctx->net, rule))
+ continue;
+
err = nft_delrule(ctx, rule);
if (err < 0)
return err;
@@ -1929,9 +1938,6 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk,
*/
int nft_register_expr(struct nft_expr_type *type)
{
- if (!nft_expr_check_ops(type->ops))
- return -EINVAL;
-
nfnl_lock(NFNL_SUBSYS_NFTABLES);
if (type->family == NFPROTO_UNSPEC)
list_add_tail_rcu(&type->list, &nf_tables_expressions);
@@ -2079,10 +2085,6 @@ static int nf_tables_expr_parse(const struct nft_ctx *ctx,
err = PTR_ERR(ops);
goto err1;
}
- if (!nft_expr_check_ops(ops)) {
- err = -EINVAL;
- goto err1;
- }
} else
ops = type->ops;
@@ -2511,7 +2513,7 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx,
static void nf_tables_rule_release(const struct nft_ctx *ctx,
struct nft_rule *rule)
{
- nft_rule_expr_deactivate(ctx, rule);
+ nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_RELEASE);
nf_tables_rule_destroy(ctx, rule);
}
@@ -3708,39 +3710,30 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
bind:
binding->chain = ctx->chain;
list_add_tail_rcu(&binding->list, &set->bindings);
+ nft_set_trans_bind(ctx, set);
+
return 0;
}
EXPORT_SYMBOL_GPL(nf_tables_bind_set);
-void nf_tables_rebind_set(const struct nft_ctx *ctx, struct nft_set *set,
- struct nft_set_binding *binding)
-{
- if (list_empty(&set->bindings) && nft_set_is_anonymous(set) &&
- nft_is_active(ctx->net, set))
- list_add_tail_rcu(&set->list, &ctx->table->sets);
-
- list_add_tail_rcu(&binding->list, &set->bindings);
-}
-EXPORT_SYMBOL_GPL(nf_tables_rebind_set);
-
void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
- struct nft_set_binding *binding)
+ struct nft_set_binding *binding, bool event)
{
list_del_rcu(&binding->list);
- if (list_empty(&set->bindings) && nft_set_is_anonymous(set) &&
- nft_is_active(ctx->net, set))
+ if (list_empty(&set->bindings) && nft_set_is_anonymous(set)) {
list_del_rcu(&set->list);
+ if (event)
+ nf_tables_set_notify(ctx, set, NFT_MSG_DELSET,
+ GFP_KERNEL);
+ }
}
EXPORT_SYMBOL_GPL(nf_tables_unbind_set);
void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set)
{
- if (list_empty(&set->bindings) && nft_set_is_anonymous(set) &&
- nft_is_active(ctx->net, set)) {
- nf_tables_set_notify(ctx, set, NFT_MSG_DELSET, GFP_ATOMIC);
+ if (list_empty(&set->bindings) && nft_set_is_anonymous(set))
nft_set_destroy(set);
- }
}
EXPORT_SYMBOL_GPL(nf_tables_destroy_set);
@@ -6535,6 +6528,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
nf_tables_rule_notify(&trans->ctx,
nft_trans_rule(trans),
NFT_MSG_DELRULE);
+ nft_rule_expr_deactivate(&trans->ctx,
+ nft_trans_rule(trans),
+ NFT_TRANS_COMMIT);
break;
case NFT_MSG_NEWSET:
nft_clear(net, nft_trans_set(trans));
@@ -6621,7 +6617,8 @@ static void nf_tables_abort_release(struct nft_trans *trans)
nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans));
break;
case NFT_MSG_NEWSET:
- nft_set_destroy(nft_trans_set(trans));
+ if (!nft_trans_set_bound(trans))
+ nft_set_destroy(nft_trans_set(trans));
break;
case NFT_MSG_NEWSETELEM:
nft_set_elem_destroy(nft_trans_elem_set(trans),
@@ -6682,7 +6679,9 @@ static int __nf_tables_abort(struct net *net)
case NFT_MSG_NEWRULE:
trans->ctx.chain->use--;
list_del_rcu(&nft_trans_rule(trans)->list);
- nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans));
+ nft_rule_expr_deactivate(&trans->ctx,
+ nft_trans_rule(trans),
+ NFT_TRANS_ABORT);
break;
case NFT_MSG_DELRULE:
trans->ctx.chain->use++;
@@ -6692,7 +6691,8 @@ static int __nf_tables_abort(struct net *net)
break;
case NFT_MSG_NEWSET:
trans->ctx.table->use--;
- list_del_rcu(&nft_trans_set(trans)->list);
+ if (!nft_trans_set_bound(trans))
+ list_del_rcu(&nft_trans_set(trans)->list);
break;
case NFT_MSG_DELSET:
trans->ctx.table->use++;
diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c
index 6f41dd74729d..1f1d90c1716b 100644
--- a/net/netfilter/nfnetlink_osf.c
+++ b/net/netfilter/nfnetlink_osf.c
@@ -66,6 +66,7 @@ static bool nf_osf_match_one(const struct sk_buff *skb,
int ttl_check,
struct nf_osf_hdr_ctx *ctx)
{
+ const __u8 *optpinit = ctx->optp;
unsigned int check_WSS = 0;
int fmatch = FMATCH_WRONG;
int foptsize, optnum;
@@ -155,6 +156,9 @@ static bool nf_osf_match_one(const struct sk_buff *skb,
}
}
+ if (fmatch != FMATCH_OK)
+ ctx->optp = optpinit;
+
return fmatch == FMATCH_OK;
}
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 7334e0b80a5e..0a4bad55a8aa 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -22,11 +22,15 @@
#include <linux/netfilter_bridge/ebtables.h>
#include <linux/netfilter_arp/arp_tables.h>
#include <net/netfilter/nf_tables.h>
+#include <net/netns/generic.h>
struct nft_xt {
struct list_head head;
struct nft_expr_ops ops;
- unsigned int refcnt;
+ refcount_t refcnt;
+
+ /* used only when transaction mutex is locked */
+ unsigned int listcnt;
/* Unlike other expressions, ops doesn't have static storage duration.
* nft core assumes they do. We use kfree_rcu so that nft core can
@@ -43,10 +47,39 @@ struct nft_xt_match_priv {
void *info;
};
+struct nft_compat_net {
+ struct list_head nft_target_list;
+ struct list_head nft_match_list;
+};
+
+static unsigned int nft_compat_net_id __read_mostly;
+static struct nft_expr_type nft_match_type;
+static struct nft_expr_type nft_target_type;
+
+static struct nft_compat_net *nft_compat_pernet(struct net *net)
+{
+ return net_generic(net, nft_compat_net_id);
+}
+
+static void nft_xt_get(struct nft_xt *xt)
+{
+ /* refcount_inc() warns on 0 -> 1 transition, but we can't
+ * init the reference count to 1 in .select_ops -- we can't
+ * undo such an increase when another expression inside the same
+ * rule fails afterwards.
+ */
+ if (xt->listcnt == 0)
+ refcount_set(&xt->refcnt, 1);
+ else
+ refcount_inc(&xt->refcnt);
+
+ xt->listcnt++;
+}
+
static bool nft_xt_put(struct nft_xt *xt)
{
- if (--xt->refcnt == 0) {
- list_del(&xt->head);
+ if (refcount_dec_and_test(&xt->refcnt)) {
+ WARN_ON_ONCE(!list_empty(&xt->head));
kfree_rcu(xt, rcu_head);
return true;
}
@@ -273,7 +306,7 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
return -EINVAL;
nft_xt = container_of(expr->ops, struct nft_xt, ops);
- nft_xt->refcnt++;
+ nft_xt_get(nft_xt);
return 0;
}
@@ -282,6 +315,7 @@ nft_target_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
{
struct xt_target *target = expr->ops->data;
void *info = nft_expr_priv(expr);
+ struct module *me = target->me;
struct xt_tgdtor_param par;
par.net = ctx->net;
@@ -292,7 +326,7 @@ nft_target_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
par.target->destroy(&par);
if (nft_xt_put(container_of(expr->ops, struct nft_xt, ops)))
- module_put(target->me);
+ module_put(me);
}
static int nft_extension_dump_info(struct sk_buff *skb, int attr,
@@ -486,7 +520,7 @@ __nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
return ret;
nft_xt = container_of(expr->ops, struct nft_xt, ops);
- nft_xt->refcnt++;
+ nft_xt_get(nft_xt);
return 0;
}
@@ -540,6 +574,18 @@ nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
__nft_match_destroy(ctx, expr, nft_expr_priv(expr));
}
+static void nft_compat_deactivate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ enum nft_trans_phase phase)
+{
+ struct nft_xt *xt = container_of(expr->ops, struct nft_xt, ops);
+
+ if (phase == NFT_TRANS_ABORT || phase == NFT_TRANS_COMMIT) {
+ if (--xt->listcnt == 0)
+ list_del_init(&xt->head);
+ }
+}
+
static void
nft_match_large_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
{
@@ -734,10 +780,6 @@ static const struct nfnetlink_subsystem nfnl_compat_subsys = {
.cb = nfnl_nft_compat_cb,
};
-static LIST_HEAD(nft_match_list);
-
-static struct nft_expr_type nft_match_type;
-
static bool nft_match_cmp(const struct xt_match *match,
const char *name, u32 rev, u32 family)
{
@@ -749,6 +791,7 @@ static const struct nft_expr_ops *
nft_match_select_ops(const struct nft_ctx *ctx,
const struct nlattr * const tb[])
{
+ struct nft_compat_net *cn;
struct nft_xt *nft_match;
struct xt_match *match;
unsigned int matchsize;
@@ -765,8 +808,10 @@ nft_match_select_ops(const struct nft_ctx *ctx,
rev = ntohl(nla_get_be32(tb[NFTA_MATCH_REV]));
family = ctx->family;
+ cn = nft_compat_pernet(ctx->net);
+
/* Re-use the existing match if it's already loaded. */
- list_for_each_entry(nft_match, &nft_match_list, head) {
+ list_for_each_entry(nft_match, &cn->nft_match_list, head) {
struct xt_match *match = nft_match->ops.data;
if (nft_match_cmp(match, mt_name, rev, family))
@@ -789,11 +834,12 @@ nft_match_select_ops(const struct nft_ctx *ctx,
goto err;
}
- nft_match->refcnt = 0;
+ refcount_set(&nft_match->refcnt, 0);
nft_match->ops.type = &nft_match_type;
nft_match->ops.eval = nft_match_eval;
nft_match->ops.init = nft_match_init;
nft_match->ops.destroy = nft_match_destroy;
+ nft_match->ops.deactivate = nft_compat_deactivate;
nft_match->ops.dump = nft_match_dump;
nft_match->ops.validate = nft_match_validate;
nft_match->ops.data = match;
@@ -810,7 +856,8 @@ nft_match_select_ops(const struct nft_ctx *ctx,
nft_match->ops.size = matchsize;
- list_add(&nft_match->head, &nft_match_list);
+ nft_match->listcnt = 0;
+ list_add(&nft_match->head, &cn->nft_match_list);
return &nft_match->ops;
err:
@@ -826,10 +873,6 @@ static struct nft_expr_type nft_match_type __read_mostly = {
.owner = THIS_MODULE,
};
-static LIST_HEAD(nft_target_list);
-
-static struct nft_expr_type nft_target_type;
-
static bool nft_target_cmp(const struct xt_target *tg,
const char *name, u32 rev, u32 family)
{
@@ -841,6 +884,7 @@ static const struct nft_expr_ops *
nft_target_select_ops(const struct nft_ctx *ctx,
const struct nlattr * const tb[])
{
+ struct nft_compat_net *cn;
struct nft_xt *nft_target;
struct xt_target *target;
char *tg_name;
@@ -861,8 +905,9 @@ nft_target_select_ops(const struct nft_ctx *ctx,
strcmp(tg_name, "standard") == 0)
return ERR_PTR(-EINVAL);
+ cn = nft_compat_pernet(ctx->net);
/* Re-use the existing target if it's already loaded. */
- list_for_each_entry(nft_target, &nft_target_list, head) {
+ list_for_each_entry(nft_target, &cn->nft_target_list, head) {
struct xt_target *target = nft_target->ops.data;
if (!target->target)
@@ -893,11 +938,12 @@ nft_target_select_ops(const struct nft_ctx *ctx,
goto err;
}
- nft_target->refcnt = 0;
+ refcount_set(&nft_target->refcnt, 0);
nft_target->ops.type = &nft_target_type;
nft_target->ops.size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize));
nft_target->ops.init = nft_target_init;
nft_target->ops.destroy = nft_target_destroy;
+ nft_target->ops.deactivate = nft_compat_deactivate;
nft_target->ops.dump = nft_target_dump;
nft_target->ops.validate = nft_target_validate;
nft_target->ops.data = target;
@@ -907,7 +953,8 @@ nft_target_select_ops(const struct nft_ctx *ctx,
else
nft_target->ops.eval = nft_target_eval_xt;
- list_add(&nft_target->head, &nft_target_list);
+ nft_target->listcnt = 0;
+ list_add(&nft_target->head, &cn->nft_target_list);
return &nft_target->ops;
err:
@@ -923,13 +970,74 @@ static struct nft_expr_type nft_target_type __read_mostly = {
.owner = THIS_MODULE,
};
+static int __net_init nft_compat_init_net(struct net *net)
+{
+ struct nft_compat_net *cn = nft_compat_pernet(net);
+
+ INIT_LIST_HEAD(&cn->nft_target_list);
+ INIT_LIST_HEAD(&cn->nft_match_list);
+
+ return 0;
+}
+
+static void __net_exit nft_compat_exit_net(struct net *net)
+{
+ struct nft_compat_net *cn = nft_compat_pernet(net);
+ struct nft_xt *xt, *next;
+
+ if (list_empty(&cn->nft_match_list) &&
+ list_empty(&cn->nft_target_list))
+ return;
+
+ /* If there was an error that caused nft_xt expr to not be initialized
+ * fully and noone else requested the same expression later, the lists
+ * contain 0-refcount entries that still hold module reference.
+ *
+ * Clean them here.
+ */
+ mutex_lock(&net->nft.commit_mutex);
+ list_for_each_entry_safe(xt, next, &cn->nft_target_list, head) {
+ struct xt_target *target = xt->ops.data;
+
+ list_del_init(&xt->head);
+
+ if (refcount_read(&xt->refcnt))
+ continue;
+ module_put(target->me);
+ kfree(xt);
+ }
+
+ list_for_each_entry_safe(xt, next, &cn->nft_match_list, head) {
+ struct xt_match *match = xt->ops.data;
+
+ list_del_init(&xt->head);
+
+ if (refcount_read(&xt->refcnt))
+ continue;
+ module_put(match->me);
+ kfree(xt);
+ }
+ mutex_unlock(&net->nft.commit_mutex);
+}
+
+static struct pernet_operations nft_compat_net_ops = {
+ .init = nft_compat_init_net,
+ .exit = nft_compat_exit_net,
+ .id = &nft_compat_net_id,
+ .size = sizeof(struct nft_compat_net),
+};
+
static int __init nft_compat_module_init(void)
{
int ret;
+ ret = register_pernet_subsys(&nft_compat_net_ops);
+ if (ret < 0)
+ goto err_target;
+
ret = nft_register_expr(&nft_match_type);
if (ret < 0)
- return ret;
+ goto err_pernet;
ret = nft_register_expr(&nft_target_type);
if (ret < 0)
@@ -942,45 +1050,21 @@ static int __init nft_compat_module_init(void)
}
return ret;
-
err_target:
nft_unregister_expr(&nft_target_type);
err_match:
nft_unregister_expr(&nft_match_type);
+err_pernet:
+ unregister_pernet_subsys(&nft_compat_net_ops);
return ret;
}
static void __exit nft_compat_module_exit(void)
{
- struct nft_xt *xt, *next;
-
- /* list should be empty here, it can be non-empty only in case there
- * was an error that caused nft_xt expr to not be initialized fully
- * and noone else requested the same expression later.
- *
- * In this case, the lists contain 0-refcount entries that still
- * hold module reference.
- */
- list_for_each_entry_safe(xt, next, &nft_target_list, head) {
- struct xt_target *target = xt->ops.data;
-
- if (WARN_ON_ONCE(xt->refcnt))
- continue;
- module_put(target->me);
- kfree(xt);
- }
-
- list_for_each_entry_safe(xt, next, &nft_match_list, head) {
- struct xt_match *match = xt->ops.data;
-
- if (WARN_ON_ONCE(xt->refcnt))
- continue;
- module_put(match->me);
- kfree(xt);
- }
nfnetlink_subsys_unregister(&nfnl_compat_subsys);
nft_unregister_expr(&nft_target_type);
nft_unregister_expr(&nft_match_type);
+ unregister_pernet_subsys(&nft_compat_net_ops);
}
MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_NFT_COMPAT);
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index 07d4efd3d851..f1172f99752b 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -235,20 +235,17 @@ err1:
return err;
}
-static void nft_dynset_activate(const struct nft_ctx *ctx,
- const struct nft_expr *expr)
-{
- struct nft_dynset *priv = nft_expr_priv(expr);
-
- nf_tables_rebind_set(ctx, priv->set, &priv->binding);
-}
-
static void nft_dynset_deactivate(const struct nft_ctx *ctx,
- const struct nft_expr *expr)
+ const struct nft_expr *expr,
+ enum nft_trans_phase phase)
{
struct nft_dynset *priv = nft_expr_priv(expr);
- nf_tables_unbind_set(ctx, priv->set, &priv->binding);
+ if (phase == NFT_TRANS_PREPARE)
+ return;
+
+ nf_tables_unbind_set(ctx, priv->set, &priv->binding,
+ phase == NFT_TRANS_COMMIT);
}
static void nft_dynset_destroy(const struct nft_ctx *ctx,
@@ -296,7 +293,6 @@ static const struct nft_expr_ops nft_dynset_ops = {
.eval = nft_dynset_eval,
.init = nft_dynset_init,
.destroy = nft_dynset_destroy,
- .activate = nft_dynset_activate,
.deactivate = nft_dynset_deactivate,
.dump = nft_dynset_dump,
};
diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c
index 0777a93211e2..3f6d1d2a6281 100644
--- a/net/netfilter/nft_immediate.c
+++ b/net/netfilter/nft_immediate.c
@@ -72,10 +72,14 @@ static void nft_immediate_activate(const struct nft_ctx *ctx,
}
static void nft_immediate_deactivate(const struct nft_ctx *ctx,
- const struct nft_expr *expr)
+ const struct nft_expr *expr,
+ enum nft_trans_phase phase)
{
const struct nft_immediate_expr *priv = nft_expr_priv(expr);
+ if (phase == NFT_TRANS_COMMIT)
+ return;
+
return nft_data_release(&priv->data, nft_dreg_to_type(priv->dreg));
}
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index 227b2b15a19c..14496da5141d 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -121,20 +121,17 @@ static int nft_lookup_init(const struct nft_ctx *ctx,
return 0;
}
-static void nft_lookup_activate(const struct nft_ctx *ctx,
- const struct nft_expr *expr)
-{
- struct nft_lookup *priv = nft_expr_priv(expr);
-
- nf_tables_rebind_set(ctx, priv->set, &priv->binding);
-}
-
static void nft_lookup_deactivate(const struct nft_ctx *ctx,
- const struct nft_expr *expr)
+ const struct nft_expr *expr,
+ enum nft_trans_phase phase)
{
struct nft_lookup *priv = nft_expr_priv(expr);
- nf_tables_unbind_set(ctx, priv->set, &priv->binding);
+ if (phase == NFT_TRANS_PREPARE)
+ return;
+
+ nf_tables_unbind_set(ctx, priv->set, &priv->binding,
+ phase == NFT_TRANS_COMMIT);
}
static void nft_lookup_destroy(const struct nft_ctx *ctx,
@@ -225,7 +222,6 @@ static const struct nft_expr_ops nft_lookup_ops = {
.size = NFT_EXPR_SIZE(sizeof(struct nft_lookup)),
.eval = nft_lookup_eval,
.init = nft_lookup_init,
- .activate = nft_lookup_activate,
.deactivate = nft_lookup_deactivate,
.destroy = nft_lookup_destroy,
.dump = nft_lookup_dump,
diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c
index a3185ca2a3a9..ae178e914486 100644
--- a/net/netfilter/nft_objref.c
+++ b/net/netfilter/nft_objref.c
@@ -155,20 +155,17 @@ nla_put_failure:
return -1;
}
-static void nft_objref_map_activate(const struct nft_ctx *ctx,
- const struct nft_expr *expr)
-{
- struct nft_objref_map *priv = nft_expr_priv(expr);
-
- nf_tables_rebind_set(ctx, priv->set, &priv->binding);
-}
-
static void nft_objref_map_deactivate(const struct nft_ctx *ctx,
- const struct nft_expr *expr)
+ const struct nft_expr *expr,
+ enum nft_trans_phase phase)
{
struct nft_objref_map *priv = nft_expr_priv(expr);
- nf_tables_unbind_set(ctx, priv->set, &priv->binding);
+ if (phase == NFT_TRANS_PREPARE)
+ return;
+
+ nf_tables_unbind_set(ctx, priv->set, &priv->binding,
+ phase == NFT_TRANS_COMMIT);
}
static void nft_objref_map_destroy(const struct nft_ctx *ctx,
@@ -185,7 +182,6 @@ static const struct nft_expr_ops nft_objref_map_ops = {
.size = NFT_EXPR_SIZE(sizeof(struct nft_objref_map)),
.eval = nft_objref_map_eval,
.init = nft_objref_map_init,
- .activate = nft_objref_map_activate,
.deactivate = nft_objref_map_deactivate,
.destroy = nft_objref_map_destroy,
.dump = nft_objref_map_dump,
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index aecadd471e1d..13e1ac333fa4 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -1899,7 +1899,7 @@ static int __init xt_init(void)
seqcount_init(&per_cpu(xt_recseq, i));
}
- xt = kmalloc_array(NFPROTO_NUMPROTO, sizeof(struct xt_af), GFP_KERNEL);
+ xt = kcalloc(NFPROTO_NUMPROTO, sizeof(struct xt_af), GFP_KERNEL);
if (!xt)
return -ENOMEM;
diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c
index ea7c67050792..ee3e5b6471a6 100644
--- a/net/netlabel/netlabel_kapi.c
+++ b/net/netlabel/netlabel_kapi.c
@@ -903,7 +903,8 @@ int netlbl_bitmap_walk(const unsigned char *bitmap, u32 bitmap_len,
(state == 0 && (byte & bitmask) == 0))
return bit_spot;
- bit_spot++;
+ if (++bit_spot >= bitmap_len)
+ return -1;
bitmask >>= 1;
if (bitmask == 0) {
byte = bitmap[++byte_offset];
diff --git a/net/netrom/nr_timer.c b/net/netrom/nr_timer.c
index cbd51ed5a2d7..908e53ab47a4 100644
--- a/net/netrom/nr_timer.c
+++ b/net/netrom/nr_timer.c
@@ -52,21 +52,21 @@ void nr_start_t1timer(struct sock *sk)
{
struct nr_sock *nr = nr_sk(sk);
- mod_timer(&nr->t1timer, jiffies + nr->t1);
+ sk_reset_timer(sk, &nr->t1timer, jiffies + nr->t1);
}
void nr_start_t2timer(struct sock *sk)
{
struct nr_sock *nr = nr_sk(sk);
- mod_timer(&nr->t2timer, jiffies + nr->t2);
+ sk_reset_timer(sk, &nr->t2timer, jiffies + nr->t2);
}
void nr_start_t4timer(struct sock *sk)
{
struct nr_sock *nr = nr_sk(sk);
- mod_timer(&nr->t4timer, jiffies + nr->t4);
+ sk_reset_timer(sk, &nr->t4timer, jiffies + nr->t4);
}
void nr_start_idletimer(struct sock *sk)
@@ -74,37 +74,37 @@ void nr_start_idletimer(struct sock *sk)
struct nr_sock *nr = nr_sk(sk);
if (nr->idle > 0)
- mod_timer(&nr->idletimer, jiffies + nr->idle);
+ sk_reset_timer(sk, &nr->idletimer, jiffies + nr->idle);
}
void nr_start_heartbeat(struct sock *sk)
{
- mod_timer(&sk->sk_timer, jiffies + 5 * HZ);
+ sk_reset_timer(sk, &sk->sk_timer, jiffies + 5 * HZ);
}
void nr_stop_t1timer(struct sock *sk)
{
- del_timer(&nr_sk(sk)->t1timer);
+ sk_stop_timer(sk, &nr_sk(sk)->t1timer);
}
void nr_stop_t2timer(struct sock *sk)
{
- del_timer(&nr_sk(sk)->t2timer);
+ sk_stop_timer(sk, &nr_sk(sk)->t2timer);
}
void nr_stop_t4timer(struct sock *sk)
{
- del_timer(&nr_sk(sk)->t4timer);
+ sk_stop_timer(sk, &nr_sk(sk)->t4timer);
}
void nr_stop_idletimer(struct sock *sk)
{
- del_timer(&nr_sk(sk)->idletimer);
+ sk_stop_timer(sk, &nr_sk(sk)->idletimer);
}
void nr_stop_heartbeat(struct sock *sk)
{
- del_timer(&sk->sk_timer);
+ sk_stop_timer(sk, &sk->sk_timer);
}
int nr_t1timer_running(struct sock *sk)
diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c
index 6a196e438b6c..d1fc019e932e 100644
--- a/net/nfc/llcp_commands.c
+++ b/net/nfc/llcp_commands.c
@@ -419,6 +419,10 @@ int nfc_llcp_send_connect(struct nfc_llcp_sock *sock)
sock->service_name,
sock->service_name_len,
&service_name_tlv_length);
+ if (!service_name_tlv) {
+ err = -ENOMEM;
+ goto error_tlv;
+ }
size += service_name_tlv_length;
}
@@ -429,9 +433,17 @@ int nfc_llcp_send_connect(struct nfc_llcp_sock *sock)
miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&miux, 0,
&miux_tlv_length);
+ if (!miux_tlv) {
+ err = -ENOMEM;
+ goto error_tlv;
+ }
size += miux_tlv_length;
rw_tlv = nfc_llcp_build_tlv(LLCP_TLV_RW, &rw, 0, &rw_tlv_length);
+ if (!rw_tlv) {
+ err = -ENOMEM;
+ goto error_tlv;
+ }
size += rw_tlv_length;
pr_debug("SKB size %d SN length %zu\n", size, sock->service_name_len);
@@ -484,9 +496,17 @@ int nfc_llcp_send_cc(struct nfc_llcp_sock *sock)
miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&miux, 0,
&miux_tlv_length);
+ if (!miux_tlv) {
+ err = -ENOMEM;
+ goto error_tlv;
+ }
size += miux_tlv_length;
rw_tlv = nfc_llcp_build_tlv(LLCP_TLV_RW, &rw, 0, &rw_tlv_length);
+ if (!rw_tlv) {
+ err = -ENOMEM;
+ goto error_tlv;
+ }
size += rw_tlv_length;
skb = llcp_allocate_pdu(sock, LLCP_PDU_CC, size);
diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c
index ef4026a23e80..4fa015208aab 100644
--- a/net/nfc/llcp_core.c
+++ b/net/nfc/llcp_core.c
@@ -532,10 +532,10 @@ static u8 nfc_llcp_reserve_sdp_ssap(struct nfc_llcp_local *local)
static int nfc_llcp_build_gb(struct nfc_llcp_local *local)
{
- u8 *gb_cur, *version_tlv, version, version_length;
- u8 *lto_tlv, lto_length;
- u8 *wks_tlv, wks_length;
- u8 *miux_tlv, miux_length;
+ u8 *gb_cur, version, version_length;
+ u8 lto_length, wks_length, miux_length;
+ u8 *version_tlv = NULL, *lto_tlv = NULL,
+ *wks_tlv = NULL, *miux_tlv = NULL;
__be16 wks = cpu_to_be16(local->local_wks);
u8 gb_len = 0;
int ret = 0;
@@ -543,17 +543,33 @@ static int nfc_llcp_build_gb(struct nfc_llcp_local *local)
version = LLCP_VERSION_11;
version_tlv = nfc_llcp_build_tlv(LLCP_TLV_VERSION, &version,
1, &version_length);
+ if (!version_tlv) {
+ ret = -ENOMEM;
+ goto out;
+ }
gb_len += version_length;
lto_tlv = nfc_llcp_build_tlv(LLCP_TLV_LTO, &local->lto, 1, &lto_length);
+ if (!lto_tlv) {
+ ret = -ENOMEM;
+ goto out;
+ }
gb_len += lto_length;
pr_debug("Local wks 0x%lx\n", local->local_wks);
wks_tlv = nfc_llcp_build_tlv(LLCP_TLV_WKS, (u8 *)&wks, 2, &wks_length);
+ if (!wks_tlv) {
+ ret = -ENOMEM;
+ goto out;
+ }
gb_len += wks_length;
miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&local->miux, 0,
&miux_length);
+ if (!miux_tlv) {
+ ret = -ENOMEM;
+ goto out;
+ }
gb_len += miux_length;
gb_len += ARRAY_SIZE(llcp_magic);
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 3b1a78906bc0..1cd1d83a4be0 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -4292,7 +4292,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
rb->frames_per_block = req->tp_block_size / req->tp_frame_size;
if (unlikely(rb->frames_per_block == 0))
goto out;
- if (unlikely(req->tp_block_size > UINT_MAX / req->tp_block_nr))
+ if (unlikely(rb->frames_per_block > UINT_MAX / req->tp_block_nr))
goto out;
if (unlikely((rb->frames_per_block * req->tp_block_nr) !=
req->tp_frame_nr))
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index 9fc76b19cd3c..db3473540303 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -132,7 +132,7 @@ static int pep_indicate(struct sock *sk, u8 id, u8 code,
ph->utid = 0;
ph->message_id = id;
ph->pipe_handle = pn->pipe_handle;
- ph->data[0] = code;
+ ph->error_code = code;
return pn_skb_send(sk, skb, NULL);
}
@@ -153,7 +153,7 @@ static int pipe_handler_request(struct sock *sk, u8 id, u8 code,
ph->utid = id; /* whatever */
ph->message_id = id;
ph->pipe_handle = pn->pipe_handle;
- ph->data[0] = code;
+ ph->error_code = code;
return pn_skb_send(sk, skb, NULL);
}
@@ -208,7 +208,7 @@ static int pep_ctrlreq_error(struct sock *sk, struct sk_buff *oskb, u8 code,
struct pnpipehdr *ph;
struct sockaddr_pn dst;
u8 data[4] = {
- oph->data[0], /* PEP type */
+ oph->pep_type, /* PEP type */
code, /* error code, at an unusual offset */
PAD, PAD,
};
@@ -221,7 +221,7 @@ static int pep_ctrlreq_error(struct sock *sk, struct sk_buff *oskb, u8 code,
ph->utid = oph->utid;
ph->message_id = PNS_PEP_CTRL_RESP;
ph->pipe_handle = oph->pipe_handle;
- ph->data[0] = oph->data[1]; /* CTRL id */
+ ph->data0 = oph->data[0]; /* CTRL id */
pn_skb_get_src_sockaddr(oskb, &dst);
return pn_skb_send(sk, skb, &dst);
@@ -272,17 +272,17 @@ static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb)
return -EINVAL;
hdr = pnp_hdr(skb);
- if (hdr->data[0] != PN_PEP_TYPE_COMMON) {
+ if (hdr->pep_type != PN_PEP_TYPE_COMMON) {
net_dbg_ratelimited("Phonet unknown PEP type: %u\n",
- (unsigned int)hdr->data[0]);
+ (unsigned int)hdr->pep_type);
return -EOPNOTSUPP;
}
- switch (hdr->data[1]) {
+ switch (hdr->data[0]) {
case PN_PEP_IND_FLOW_CONTROL:
switch (pn->tx_fc) {
case PN_LEGACY_FLOW_CONTROL:
- switch (hdr->data[4]) {
+ switch (hdr->data[3]) {
case PEP_IND_BUSY:
atomic_set(&pn->tx_credits, 0);
break;
@@ -292,7 +292,7 @@ static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb)
}
break;
case PN_ONE_CREDIT_FLOW_CONTROL:
- if (hdr->data[4] == PEP_IND_READY)
+ if (hdr->data[3] == PEP_IND_READY)
atomic_set(&pn->tx_credits, wake = 1);
break;
}
@@ -301,12 +301,12 @@ static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb)
case PN_PEP_IND_ID_MCFC_GRANT_CREDITS:
if (pn->tx_fc != PN_MULTI_CREDIT_FLOW_CONTROL)
break;
- atomic_add(wake = hdr->data[4], &pn->tx_credits);
+ atomic_add(wake = hdr->data[3], &pn->tx_credits);
break;
default:
net_dbg_ratelimited("Phonet unknown PEP indication: %u\n",
- (unsigned int)hdr->data[1]);
+ (unsigned int)hdr->data[0]);
return -EOPNOTSUPP;
}
if (wake)
@@ -318,7 +318,7 @@ static int pipe_rcv_created(struct sock *sk, struct sk_buff *skb)
{
struct pep_sock *pn = pep_sk(sk);
struct pnpipehdr *hdr = pnp_hdr(skb);
- u8 n_sb = hdr->data[0];
+ u8 n_sb = hdr->data0;
pn->rx_fc = pn->tx_fc = PN_LEGACY_FLOW_CONTROL;
__skb_pull(skb, sizeof(*hdr));
@@ -506,7 +506,7 @@ static int pep_connresp_rcv(struct sock *sk, struct sk_buff *skb)
return -ECONNREFUSED;
/* Parse sub-blocks */
- n_sb = hdr->data[4];
+ n_sb = hdr->data[3];
while (n_sb > 0) {
u8 type, buf[6], len = sizeof(buf);
const u8 *data = pep_get_sb(skb, &type, &len, buf);
@@ -739,7 +739,7 @@ static int pipe_do_remove(struct sock *sk)
ph->utid = 0;
ph->message_id = PNS_PIPE_REMOVE_REQ;
ph->pipe_handle = pn->pipe_handle;
- ph->data[0] = PAD;
+ ph->data0 = PAD;
return pn_skb_send(sk, skb, NULL);
}
@@ -817,7 +817,7 @@ static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp,
peer_type = hdr->other_pep_type << 8;
/* Parse sub-blocks (options) */
- n_sb = hdr->data[4];
+ n_sb = hdr->data[3];
while (n_sb > 0) {
u8 type, buf[1], len = sizeof(buf);
const u8 *data = pep_get_sb(skb, &type, &len, buf);
@@ -1109,7 +1109,7 @@ static int pipe_skb_send(struct sock *sk, struct sk_buff *skb)
ph->utid = 0;
if (pn->aligned) {
ph->message_id = PNS_PIPE_ALIGNED_DATA;
- ph->data[0] = 0; /* padding */
+ ph->data0 = 0; /* padding */
} else
ph->message_id = PNS_PIPE_DATA;
ph->pipe_handle = pn->pipe_handle;
diff --git a/net/rds/bind.c b/net/rds/bind.c
index 762d2c6788a3..17c9d9f0c848 100644
--- a/net/rds/bind.c
+++ b/net/rds/bind.c
@@ -78,10 +78,10 @@ struct rds_sock *rds_find_bound(const struct in6_addr *addr, __be16 port,
__rds_create_bind_key(key, addr, port, scope_id);
rcu_read_lock();
rs = rhashtable_lookup(&bind_hash_table, key, ht_parms);
- if (rs && !sock_flag(rds_rs_to_sk(rs), SOCK_DEAD))
- rds_sock_addref(rs);
- else
+ if (rs && (sock_flag(rds_rs_to_sk(rs), SOCK_DEAD) ||
+ !refcount_inc_not_zero(&rds_rs_to_sk(rs)->sk_refcnt)))
rs = NULL;
+
rcu_read_unlock();
rdsdebug("returning rs %p for %pI6c:%u\n", rs, addr,
diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c
index 77e9f85a2c92..f2ff21d7df08 100644
--- a/net/rose/rose_route.c
+++ b/net/rose/rose_route.c
@@ -850,6 +850,7 @@ void rose_link_device_down(struct net_device *dev)
/*
* Route a frame to an appropriate AX.25 connection.
+ * A NULL ax25_cb indicates an internally generated frame.
*/
int rose_route_frame(struct sk_buff *skb, ax25_cb *ax25)
{
@@ -867,6 +868,10 @@ int rose_route_frame(struct sk_buff *skb, ax25_cb *ax25)
if (skb->len < ROSE_MIN_LEN)
return res;
+
+ if (!ax25)
+ return rose_loopback_queue(skb, NULL);
+
frametype = skb->data[2];
lci = ((skb->data[0] << 8) & 0xF00) + ((skb->data[1] << 0) & 0x0FF);
if (frametype == ROSE_CALL_REQUEST &&
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index eaf19ebaa964..3f7bb11f3290 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -596,6 +596,7 @@ error_requeue_call:
}
error_no_call:
release_sock(&rx->sk);
+error_trace:
trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, 0, 0, 0, ret);
return ret;
@@ -604,7 +605,7 @@ wait_interrupted:
wait_error:
finish_wait(sk_sleep(&rx->sk), &wait);
call = NULL;
- goto error_no_call;
+ goto error_trace;
}
/**
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 8af6c11d2482..faa1addf89b3 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -199,8 +199,7 @@ err3:
err2:
kfree(tname);
err1:
- if (ret == ACT_P_CREATED)
- tcf_idr_release(*a, bind);
+ tcf_idr_release(*a, bind);
return err;
}
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 64dba3708fce..cfceed28c333 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -189,8 +189,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
params_new = kzalloc(sizeof(*params_new), GFP_KERNEL);
if (unlikely(!params_new)) {
- if (ret == ACT_P_CREATED)
- tcf_idr_release(*a, bind);
+ tcf_idr_release(*a, bind);
return -ENOMEM;
}
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 8b43fe0130f7..3f943de9a2c9 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -377,7 +377,8 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
return ret;
release_tun_meta:
- dst_release(&metadata->dst);
+ if (metadata)
+ dst_release(&metadata->dst);
err_out:
if (exists)
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index f6aa57fbbbaf..12ca9d13db83 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -1371,7 +1371,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
if (!tc_skip_hw(fnew->flags)) {
err = fl_hw_replace_filter(tp, fnew, extack);
if (err)
- goto errout_mask;
+ goto errout_mask_ht;
}
if (!tc_in_hw(fnew->flags))
@@ -1401,6 +1401,10 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
kfree(mask);
return 0;
+errout_mask_ht:
+ rhashtable_remove_fast(&fnew->mask->ht, &fnew->ht_node,
+ fnew->mask->filter_ht_params);
+
errout_mask:
fl_mask_put(head, fnew->mask, false);
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 9ccc93f257db..38bb882bb958 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -48,7 +48,7 @@ struct tcindex_data {
u32 hash; /* hash table size; 0 if undefined */
u32 alloc_hash; /* allocated size */
u32 fall_through; /* 0: only classify if explicit match */
- struct rcu_head rcu;
+ struct rcu_work rwork;
};
static inline int tcindex_filter_is_set(struct tcindex_filter_result *r)
@@ -221,17 +221,11 @@ found:
return 0;
}
-static int tcindex_destroy_element(struct tcf_proto *tp,
- void *arg, struct tcf_walker *walker)
-{
- bool last;
-
- return tcindex_delete(tp, arg, &last, NULL);
-}
-
-static void __tcindex_destroy(struct rcu_head *head)
+static void tcindex_destroy_work(struct work_struct *work)
{
- struct tcindex_data *p = container_of(head, struct tcindex_data, rcu);
+ struct tcindex_data *p = container_of(to_rcu_work(work),
+ struct tcindex_data,
+ rwork);
kfree(p->perfect);
kfree(p->h);
@@ -258,9 +252,11 @@ static int tcindex_filter_result_init(struct tcindex_filter_result *r)
return tcf_exts_init(&r->exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
}
-static void __tcindex_partial_destroy(struct rcu_head *head)
+static void tcindex_partial_destroy_work(struct work_struct *work)
{
- struct tcindex_data *p = container_of(head, struct tcindex_data, rcu);
+ struct tcindex_data *p = container_of(to_rcu_work(work),
+ struct tcindex_data,
+ rwork);
kfree(p->perfect);
kfree(p);
@@ -275,7 +271,7 @@ static void tcindex_free_perfect_hash(struct tcindex_data *cp)
kfree(cp->perfect);
}
-static int tcindex_alloc_perfect_hash(struct tcindex_data *cp)
+static int tcindex_alloc_perfect_hash(struct net *net, struct tcindex_data *cp)
{
int i, err = 0;
@@ -289,6 +285,9 @@ static int tcindex_alloc_perfect_hash(struct tcindex_data *cp)
TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
if (err < 0)
goto errout;
+#ifdef CONFIG_NET_CLS_ACT
+ cp->perfect[i].exts.net = net;
+#endif
}
return 0;
@@ -305,9 +304,9 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
struct nlattr *est, bool ovr, struct netlink_ext_ack *extack)
{
struct tcindex_filter_result new_filter_result, *old_r = r;
- struct tcindex_filter_result cr;
struct tcindex_data *cp = NULL, *oldp;
struct tcindex_filter *f = NULL; /* make gcc behave */
+ struct tcf_result cr = {};
int err, balloc = 0;
struct tcf_exts e;
@@ -337,7 +336,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
if (p->perfect) {
int i;
- if (tcindex_alloc_perfect_hash(cp) < 0)
+ if (tcindex_alloc_perfect_hash(net, cp) < 0)
goto errout;
for (i = 0; i < cp->hash; i++)
cp->perfect[i].res = p->perfect[i].res;
@@ -348,11 +347,8 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
err = tcindex_filter_result_init(&new_filter_result);
if (err < 0)
goto errout1;
- err = tcindex_filter_result_init(&cr);
- if (err < 0)
- goto errout1;
if (old_r)
- cr.res = r->res;
+ cr = r->res;
if (tb[TCA_TCINDEX_HASH])
cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]);
@@ -406,7 +402,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
err = -ENOMEM;
if (!cp->perfect && !cp->h) {
if (valid_perfect_hash(cp)) {
- if (tcindex_alloc_perfect_hash(cp) < 0)
+ if (tcindex_alloc_perfect_hash(net, cp) < 0)
goto errout_alloc;
balloc = 1;
} else {
@@ -443,8 +439,8 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
}
if (tb[TCA_TCINDEX_CLASSID]) {
- cr.res.classid = nla_get_u32(tb[TCA_TCINDEX_CLASSID]);
- tcf_bind_filter(tp, &cr.res, base);
+ cr.classid = nla_get_u32(tb[TCA_TCINDEX_CLASSID]);
+ tcf_bind_filter(tp, &cr, base);
}
if (old_r && old_r != r) {
@@ -456,7 +452,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
}
oldp = p;
- r->res = cr.res;
+ r->res = cr;
tcf_exts_change(&r->exts, &e);
rcu_assign_pointer(tp->root, cp);
@@ -475,10 +471,12 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
; /* nothing */
rcu_assign_pointer(*fp, f);
+ } else {
+ tcf_exts_destroy(&new_filter_result.exts);
}
if (oldp)
- call_rcu(&oldp->rcu, __tcindex_partial_destroy);
+ tcf_queue_work(&oldp->rwork, tcindex_partial_destroy_work);
return 0;
errout_alloc:
@@ -487,7 +485,6 @@ errout_alloc:
else if (balloc == 2)
kfree(cp->h);
errout1:
- tcf_exts_destroy(&cr.exts);
tcf_exts_destroy(&new_filter_result.exts);
errout:
kfree(cp);
@@ -562,15 +559,34 @@ static void tcindex_destroy(struct tcf_proto *tp,
struct netlink_ext_ack *extack)
{
struct tcindex_data *p = rtnl_dereference(tp->root);
- struct tcf_walker walker;
+ int i;
pr_debug("tcindex_destroy(tp %p),p %p\n", tp, p);
- walker.count = 0;
- walker.skip = 0;
- walker.fn = tcindex_destroy_element;
- tcindex_walk(tp, &walker);
- call_rcu(&p->rcu, __tcindex_destroy);
+ if (p->perfect) {
+ for (i = 0; i < p->hash; i++) {
+ struct tcindex_filter_result *r = p->perfect + i;
+
+ tcf_unbind_filter(tp, &r->res);
+ if (tcf_exts_get_net(&r->exts))
+ tcf_queue_work(&r->rwork,
+ tcindex_destroy_rexts_work);
+ else
+ __tcindex_destroy_rexts(r);
+ }
+ }
+
+ for (i = 0; p->h && i < p->hash; i++) {
+ struct tcindex_filter *f, *next;
+ bool last;
+
+ for (f = rtnl_dereference(p->h[i]); f; f = next) {
+ next = rtnl_dereference(f->next);
+ tcindex_delete(tp, &f->result, &last, NULL);
+ }
+ }
+
+ tcf_queue_work(&p->rwork, tcindex_destroy_work);
}
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 66ba2ce2320f..968a85fe4d4a 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -500,7 +500,7 @@ static void dev_watchdog_down(struct net_device *dev)
* netif_carrier_on - set carrier
* @dev: network device
*
- * Device has detected that carrier.
+ * Device has detected acquisition of carrier.
*/
void netif_carrier_on(struct net_device *dev)
{
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 75046ec72144..cc9d8133afcd 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -447,6 +447,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
int nb = 0;
int count = 1;
int rc = NET_XMIT_SUCCESS;
+ int rc_drop = NET_XMIT_DROP;
/* Do not fool qdisc_drop_all() */
skb->prev = NULL;
@@ -486,6 +487,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
q->duplicate = 0;
rootq->enqueue(skb2, rootq, to_free);
q->duplicate = dupsave;
+ rc_drop = NET_XMIT_SUCCESS;
}
/*
@@ -498,7 +500,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
if (skb_is_gso(skb)) {
segs = netem_segment(skb, sch, to_free);
if (!segs)
- return NET_XMIT_DROP;
+ return rc_drop;
} else {
segs = skb;
}
@@ -521,8 +523,10 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
1<<(prandom_u32() % 8);
}
- if (unlikely(sch->q.qlen >= sch->limit))
- return qdisc_drop_all(skb, sch, to_free);
+ if (unlikely(sch->q.qlen >= sch->limit)) {
+ qdisc_drop_all(skb, sch, to_free);
+ return rc_drop;
+ }
qdisc_qstats_backlog_inc(sch, skb);
diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c
index 64bef313d436..5cb7c1ff97e9 100644
--- a/net/sctp/chunk.c
+++ b/net/sctp/chunk.c
@@ -192,7 +192,7 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc,
if (unlikely(!max_data)) {
max_data = sctp_min_frag_point(sctp_sk(asoc->base.sk),
sctp_datachk_len(&asoc->stream));
- pr_warn_ratelimited("%s: asoc:%p frag_point is zero, forcing max_data to default minimum (%Zu)",
+ pr_warn_ratelimited("%s: asoc:%p frag_point is zero, forcing max_data to default minimum (%zu)",
__func__, asoc, max_data);
}
diff --git a/net/sctp/diag.c b/net/sctp/diag.c
index 078f01a8d582..435847d98b51 100644
--- a/net/sctp/diag.c
+++ b/net/sctp/diag.c
@@ -256,6 +256,7 @@ static size_t inet_assoc_attr_size(struct sctp_association *asoc)
+ nla_total_size(1) /* INET_DIAG_TOS */
+ nla_total_size(1) /* INET_DIAG_TCLASS */
+ nla_total_size(4) /* INET_DIAG_MARK */
+ + nla_total_size(4) /* INET_DIAG_CLASS_ID */
+ nla_total_size(addrlen * asoc->peer.transport_count)
+ nla_total_size(addrlen * addrcnt)
+ nla_total_size(sizeof(struct inet_diag_meminfo))
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index ed8e006dae85..6200cd2b4b99 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -280,7 +280,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
if (saddr) {
fl6->saddr = saddr->v6.sin6_addr;
- fl6->fl6_sport = saddr->v6.sin6_port;
+ if (!fl6->fl6_sport)
+ fl6->fl6_sport = saddr->v6.sin6_port;
pr_debug("src=%pI6 - ", &fl6->saddr);
}
diff --git a/net/sctp/offload.c b/net/sctp/offload.c
index 123e9f2dc226..edfcf16e704c 100644
--- a/net/sctp/offload.c
+++ b/net/sctp/offload.c
@@ -36,6 +36,7 @@ static __le32 sctp_gso_make_checksum(struct sk_buff *skb)
{
skb->ip_summed = CHECKSUM_NONE;
skb->csum_not_inet = 0;
+ gso_reset_checksum(skb, ~0);
return sctp_compute_cksum(skb, skb_transport_offset(skb));
}
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 4e0eeb113ef5..6abc8b274270 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -440,7 +440,8 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
}
if (saddr) {
fl4->saddr = saddr->v4.sin_addr.s_addr;
- fl4->fl4_sport = saddr->v4.sin_port;
+ if (!fl4->fl4_sport)
+ fl4->fl4_sport = saddr->v4.sin_port;
}
pr_debug("%s: dst:%pI4, src:%pI4 - ", __func__, &fl4->daddr,
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index f4ac6c592e13..d05c57664e36 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -495,7 +495,10 @@ struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc,
*
* [INIT ACK back to where the INIT came from.]
*/
- retval->transport = chunk->transport;
+ if (chunk->transport)
+ retval->transport =
+ sctp_assoc_lookup_paddr(asoc,
+ &chunk->transport->ipaddr);
retval->subh.init_hdr =
sctp_addto_chunk(retval, sizeof(initack), &initack);
@@ -642,8 +645,10 @@ struct sctp_chunk *sctp_make_cookie_ack(const struct sctp_association *asoc,
*
* [COOKIE ACK back to where the COOKIE ECHO came from.]
*/
- if (retval && chunk)
- retval->transport = chunk->transport;
+ if (retval && chunk && chunk->transport)
+ retval->transport =
+ sctp_assoc_lookup_paddr(asoc,
+ &chunk->transport->ipaddr);
return retval;
}
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index f93c3cf9e567..65d6d04546ae 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -2027,7 +2027,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len)
struct sctp_endpoint *ep = sctp_sk(sk)->ep;
struct sctp_transport *transport = NULL;
struct sctp_sndrcvinfo _sinfo, *sinfo;
- struct sctp_association *asoc;
+ struct sctp_association *asoc, *tmp;
struct sctp_cmsgs cmsgs;
union sctp_addr *daddr;
bool new = false;
@@ -2053,7 +2053,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len)
/* SCTP_SENDALL process */
if ((sflags & SCTP_SENDALL) && sctp_style(sk, UDP)) {
- list_for_each_entry(asoc, &ep->asocs, asocs) {
+ list_for_each_entry_safe(asoc, tmp, &ep->asocs, asocs) {
err = sctp_sendmsg_check_sflags(asoc, sflags, msg,
msg_len);
if (err == 0)
diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 3892e7630f3a..2936ed17bf9e 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -84,6 +84,19 @@ static void fa_zero(struct flex_array *fa, size_t index, size_t count)
}
}
+static size_t fa_index(struct flex_array *fa, void *elem, size_t count)
+{
+ size_t index = 0;
+
+ while (count--) {
+ if (elem == flex_array_get(fa, index))
+ break;
+ index++;
+ }
+
+ return index;
+}
+
/* Migrates chunks from stream queues to new stream queues if needed,
* but not across associations. Also, removes those chunks to streams
* higher than the new max.
@@ -131,8 +144,10 @@ static void sctp_stream_outq_migrate(struct sctp_stream *stream,
}
}
- for (i = outcnt; i < stream->outcnt; i++)
+ for (i = outcnt; i < stream->outcnt; i++) {
kfree(SCTP_SO(stream, i)->ext);
+ SCTP_SO(stream, i)->ext = NULL;
+ }
}
static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt,
@@ -147,6 +162,13 @@ static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt,
if (stream->out) {
fa_copy(out, stream->out, 0, min(outcnt, stream->outcnt));
+ if (stream->out_curr) {
+ size_t index = fa_index(stream->out, stream->out_curr,
+ stream->outcnt);
+
+ BUG_ON(index == stream->outcnt);
+ stream->out_curr = flex_array_get(out, index);
+ }
fa_free(stream->out);
}
@@ -585,9 +607,9 @@ struct sctp_chunk *sctp_process_strreset_outreq(
struct sctp_strreset_outreq *outreq = param.v;
struct sctp_stream *stream = &asoc->stream;
__u32 result = SCTP_STRRESET_DENIED;
- __u16 i, nums, flags = 0;
__be16 *str_p = NULL;
__u32 request_seq;
+ __u16 i, nums;
request_seq = ntohl(outreq->request_seq);
@@ -615,6 +637,15 @@ struct sctp_chunk *sctp_process_strreset_outreq(
if (!(asoc->strreset_enable & SCTP_ENABLE_RESET_STREAM_REQ))
goto out;
+ nums = (ntohs(param.p->length) - sizeof(*outreq)) / sizeof(__u16);
+ str_p = outreq->list_of_streams;
+ for (i = 0; i < nums; i++) {
+ if (ntohs(str_p[i]) >= stream->incnt) {
+ result = SCTP_STRRESET_ERR_WRONG_SSN;
+ goto out;
+ }
+ }
+
if (asoc->strreset_chunk) {
if (!sctp_chunk_lookup_strreset_param(
asoc, outreq->response_seq,
@@ -637,32 +668,19 @@ struct sctp_chunk *sctp_process_strreset_outreq(
sctp_chunk_put(asoc->strreset_chunk);
asoc->strreset_chunk = NULL;
}
-
- flags = SCTP_STREAM_RESET_INCOMING_SSN;
}
- nums = (ntohs(param.p->length) - sizeof(*outreq)) / sizeof(__u16);
- if (nums) {
- str_p = outreq->list_of_streams;
- for (i = 0; i < nums; i++) {
- if (ntohs(str_p[i]) >= stream->incnt) {
- result = SCTP_STRRESET_ERR_WRONG_SSN;
- goto out;
- }
- }
-
+ if (nums)
for (i = 0; i < nums; i++)
SCTP_SI(stream, ntohs(str_p[i]))->mid = 0;
- } else {
+ else
for (i = 0; i < stream->incnt; i++)
SCTP_SI(stream, i)->mid = 0;
- }
result = SCTP_STRRESET_PERFORMED;
*evp = sctp_ulpevent_make_stream_reset_event(asoc,
- flags | SCTP_STREAM_RESET_OUTGOING_SSN, nums, str_p,
- GFP_ATOMIC);
+ SCTP_STREAM_RESET_INCOMING_SSN, nums, str_p, GFP_ATOMIC);
out:
sctp_update_strreset_result(asoc, result);
@@ -738,9 +756,6 @@ struct sctp_chunk *sctp_process_strreset_inreq(
result = SCTP_STRRESET_PERFORMED;
- *evp = sctp_ulpevent_make_stream_reset_event(asoc,
- SCTP_STREAM_RESET_INCOMING_SSN, nums, str_p, GFP_ATOMIC);
-
out:
sctp_update_strreset_result(asoc, result);
err:
@@ -873,6 +888,14 @@ struct sctp_chunk *sctp_process_strreset_addstrm_out(
if (!(asoc->strreset_enable & SCTP_ENABLE_CHANGE_ASSOC_REQ))
goto out;
+ in = ntohs(addstrm->number_of_streams);
+ incnt = stream->incnt + in;
+ if (!in || incnt > SCTP_MAX_STREAM)
+ goto out;
+
+ if (sctp_stream_alloc_in(stream, incnt, GFP_ATOMIC))
+ goto out;
+
if (asoc->strreset_chunk) {
if (!sctp_chunk_lookup_strreset_param(
asoc, 0, SCTP_PARAM_RESET_ADD_IN_STREAMS)) {
@@ -896,14 +919,6 @@ struct sctp_chunk *sctp_process_strreset_addstrm_out(
}
}
- in = ntohs(addstrm->number_of_streams);
- incnt = stream->incnt + in;
- if (!in || incnt > SCTP_MAX_STREAM)
- goto out;
-
- if (sctp_stream_alloc_in(stream, incnt, GFP_ATOMIC))
- goto out;
-
stream->incnt = incnt;
result = SCTP_STRRESET_PERFORMED;
@@ -973,9 +988,6 @@ struct sctp_chunk *sctp_process_strreset_addstrm_in(
result = SCTP_STRRESET_PERFORMED;
- *evp = sctp_ulpevent_make_stream_change_event(asoc,
- 0, 0, ntohs(addstrm->number_of_streams), GFP_ATOMIC);
-
out:
sctp_update_strreset_result(asoc, result);
err:
@@ -1036,10 +1048,10 @@ struct sctp_chunk *sctp_process_strreset_resp(
sout->mid_uo = 0;
}
}
-
- flags = SCTP_STREAM_RESET_OUTGOING_SSN;
}
+ flags |= SCTP_STREAM_RESET_OUTGOING_SSN;
+
for (i = 0; i < stream->outcnt; i++)
SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN;
@@ -1058,6 +1070,8 @@ struct sctp_chunk *sctp_process_strreset_resp(
nums = (ntohs(inreq->param_hdr.length) - sizeof(*inreq)) /
sizeof(__u16);
+ flags |= SCTP_STREAM_RESET_INCOMING_SSN;
+
*evp = sctp_ulpevent_make_stream_reset_event(asoc, flags,
nums, str_p, GFP_ATOMIC);
} else if (req->type == SCTP_PARAM_RESET_TSN_REQUEST) {
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 033696e6f74f..ad158d311ffa 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -207,7 +207,8 @@ void sctp_transport_reset_hb_timer(struct sctp_transport *transport)
/* When a data chunk is sent, reset the heartbeat interval. */
expires = jiffies + sctp_transport_timeout(transport);
- if (time_before(transport->hb_timer.expires, expires) &&
+ if ((time_before(transport->hb_timer.expires, expires) ||
+ !timer_pending(&transport->hb_timer)) &&
!mod_timer(&transport->hb_timer,
expires + prandom_u32_max(transport->rto)))
sctp_transport_hold(transport);
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index c4e56602e0c6..b04a813fc865 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1505,6 +1505,11 @@ static int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
smc = smc_sk(sk);
lock_sock(sk);
+ if (sk->sk_state == SMC_CLOSED && (sk->sk_shutdown & RCV_SHUTDOWN)) {
+ /* socket was connected before, no more data to read */
+ rc = 0;
+ goto out;
+ }
if ((sk->sk_state == SMC_INIT) ||
(sk->sk_state == SMC_LISTEN) ||
(sk->sk_state == SMC_CLOSED))
@@ -1840,7 +1845,11 @@ static ssize_t smc_splice_read(struct socket *sock, loff_t *ppos,
smc = smc_sk(sk);
lock_sock(sk);
-
+ if (sk->sk_state == SMC_CLOSED && (sk->sk_shutdown & RCV_SHUTDOWN)) {
+ /* socket was connected before, no more data to read */
+ rc = 0;
+ goto out;
+ }
if (sk->sk_state == SMC_INIT ||
sk->sk_state == SMC_LISTEN ||
sk->sk_state == SMC_CLOSED)
diff --git a/net/smc/smc.h b/net/smc/smc.h
index 5721416d0605..adbdf195eb08 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -113,9 +113,9 @@ struct smc_host_cdc_msg { /* Connection Data Control message */
} __aligned(8);
enum smc_urg_state {
- SMC_URG_VALID, /* data present */
- SMC_URG_NOTYET, /* data pending */
- SMC_URG_READ /* data was already read */
+ SMC_URG_VALID = 1, /* data present */
+ SMC_URG_NOTYET = 2, /* data pending */
+ SMC_URG_READ = 3, /* data was already read */
};
struct smc_connection {
diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index db83332ac1c8..fb07ad8d69a6 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -21,13 +21,6 @@
/********************************** send *************************************/
-struct smc_cdc_tx_pend {
- struct smc_connection *conn; /* socket connection */
- union smc_host_cursor cursor; /* tx sndbuf cursor sent */
- union smc_host_cursor p_cursor; /* rx RMBE cursor produced */
- u16 ctrl_seq; /* conn. tx sequence # */
-};
-
/* handler for send/transmission completion of a CDC msg */
static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd,
struct smc_link *link,
@@ -61,12 +54,14 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd,
int smc_cdc_get_free_slot(struct smc_connection *conn,
struct smc_wr_buf **wr_buf,
+ struct smc_rdma_wr **wr_rdma_buf,
struct smc_cdc_tx_pend **pend)
{
struct smc_link *link = &conn->lgr->lnk[SMC_SINGLE_LINK];
int rc;
rc = smc_wr_tx_get_free_slot(link, smc_cdc_tx_handler, wr_buf,
+ wr_rdma_buf,
(struct smc_wr_tx_pend_priv **)pend);
if (!conn->alert_token_local)
/* abnormal termination */
@@ -96,6 +91,7 @@ int smc_cdc_msg_send(struct smc_connection *conn,
struct smc_wr_buf *wr_buf,
struct smc_cdc_tx_pend *pend)
{
+ union smc_host_cursor cfed;
struct smc_link *link;
int rc;
@@ -105,12 +101,10 @@ int smc_cdc_msg_send(struct smc_connection *conn,
conn->tx_cdc_seq++;
conn->local_tx_ctrl.seqno = conn->tx_cdc_seq;
- smc_host_msg_to_cdc((struct smc_cdc_msg *)wr_buf,
- &conn->local_tx_ctrl, conn);
+ smc_host_msg_to_cdc((struct smc_cdc_msg *)wr_buf, conn, &cfed);
rc = smc_wr_tx_send(link, (struct smc_wr_tx_pend_priv *)pend);
if (!rc)
- smc_curs_copy(&conn->rx_curs_confirmed,
- &conn->local_tx_ctrl.cons, conn);
+ smc_curs_copy(&conn->rx_curs_confirmed, &cfed, conn);
return rc;
}
@@ -121,11 +115,14 @@ static int smcr_cdc_get_slot_and_msg_send(struct smc_connection *conn)
struct smc_wr_buf *wr_buf;
int rc;
- rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend);
+ rc = smc_cdc_get_free_slot(conn, &wr_buf, NULL, &pend);
if (rc)
return rc;
- return smc_cdc_msg_send(conn, wr_buf, pend);
+ spin_lock_bh(&conn->send_lock);
+ rc = smc_cdc_msg_send(conn, wr_buf, pend);
+ spin_unlock_bh(&conn->send_lock);
+ return rc;
}
int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn)
diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h
index b5bfe38c7f9b..f1cdde9d4b89 100644
--- a/net/smc/smc_cdc.h
+++ b/net/smc/smc_cdc.h
@@ -160,7 +160,9 @@ static inline void smcd_curs_copy(union smcd_cdc_cursor *tgt,
#endif
}
-/* calculate cursor difference between old and new, where old <= new */
+/* calculate cursor difference between old and new, where old <= new and
+ * difference cannot exceed size
+ */
static inline int smc_curs_diff(unsigned int size,
union smc_host_cursor *old,
union smc_host_cursor *new)
@@ -185,28 +187,51 @@ static inline int smc_curs_comp(unsigned int size,
return smc_curs_diff(size, old, new);
}
+/* calculate cursor difference between old and new, where old <= new and
+ * difference may exceed size
+ */
+static inline int smc_curs_diff_large(unsigned int size,
+ union smc_host_cursor *old,
+ union smc_host_cursor *new)
+{
+ if (old->wrap < new->wrap)
+ return min_t(int,
+ (size - old->count) + new->count +
+ (new->wrap - old->wrap - 1) * size,
+ size);
+
+ if (old->wrap > new->wrap) /* wrap has switched from 0xffff to 0x0000 */
+ return min_t(int,
+ (size - old->count) + new->count +
+ (new->wrap + 0xffff - old->wrap) * size,
+ size);
+
+ return max_t(int, 0, (new->count - old->count));
+}
+
static inline void smc_host_cursor_to_cdc(union smc_cdc_cursor *peer,
union smc_host_cursor *local,
+ union smc_host_cursor *save,
struct smc_connection *conn)
{
- union smc_host_cursor temp;
-
- smc_curs_copy(&temp, local, conn);
- peer->count = htonl(temp.count);
- peer->wrap = htons(temp.wrap);
+ smc_curs_copy(save, local, conn);
+ peer->count = htonl(save->count);
+ peer->wrap = htons(save->wrap);
/* peer->reserved = htons(0); must be ensured by caller */
}
static inline void smc_host_msg_to_cdc(struct smc_cdc_msg *peer,
- struct smc_host_cdc_msg *local,
- struct smc_connection *conn)
+ struct smc_connection *conn,
+ union smc_host_cursor *save)
{
+ struct smc_host_cdc_msg *local = &conn->local_tx_ctrl;
+
peer->common.type = local->common.type;
peer->len = local->len;
peer->seqno = htons(local->seqno);
peer->token = htonl(local->token);
- smc_host_cursor_to_cdc(&peer->prod, &local->prod, conn);
- smc_host_cursor_to_cdc(&peer->cons, &local->cons, conn);
+ smc_host_cursor_to_cdc(&peer->prod, &local->prod, save, conn);
+ smc_host_cursor_to_cdc(&peer->cons, &local->cons, save, conn);
peer->prod_flags = local->prod_flags;
peer->conn_state_flags = local->conn_state_flags;
}
@@ -270,10 +295,16 @@ static inline void smc_cdc_msg_to_host(struct smc_host_cdc_msg *local,
smcr_cdc_msg_to_host(local, peer, conn);
}
-struct smc_cdc_tx_pend;
+struct smc_cdc_tx_pend {
+ struct smc_connection *conn; /* socket connection */
+ union smc_host_cursor cursor; /* tx sndbuf cursor sent */
+ union smc_host_cursor p_cursor; /* rx RMBE cursor produced */
+ u16 ctrl_seq; /* conn. tx sequence # */
+};
int smc_cdc_get_free_slot(struct smc_connection *conn,
struct smc_wr_buf **wr_buf,
+ struct smc_rdma_wr **wr_rdma_buf,
struct smc_cdc_tx_pend **pend);
void smc_cdc_tx_dismiss_slots(struct smc_connection *conn);
int smc_cdc_msg_send(struct smc_connection *conn, struct smc_wr_buf *wr_buf,
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 776e9dfc915d..d53fd588d1f5 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -378,7 +378,7 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info)
vec.iov_len = sizeof(struct smc_clc_msg_decline);
len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1,
sizeof(struct smc_clc_msg_decline));
- if (len < sizeof(struct smc_clc_msg_decline))
+ if (len < 0 || len < sizeof(struct smc_clc_msg_decline))
len = -EPROTO;
return len > 0 ? 0 : len;
}
diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
index ea2b87f29469..e39cadda1bf5 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -345,14 +345,7 @@ static void smc_close_passive_work(struct work_struct *work)
switch (sk->sk_state) {
case SMC_INIT:
- if (atomic_read(&conn->bytes_to_rcv) ||
- (rxflags->peer_done_writing &&
- !smc_cdc_rxed_any_close(conn))) {
- sk->sk_state = SMC_APPCLOSEWAIT1;
- } else {
- sk->sk_state = SMC_CLOSED;
- sock_put(sk); /* passive closing */
- }
+ sk->sk_state = SMC_APPCLOSEWAIT1;
break;
case SMC_ACTIVE:
sk->sk_state = SMC_APPCLOSEWAIT1;
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 35c1cdc93e1c..aa1c551cee81 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -128,6 +128,8 @@ static void smc_lgr_unregister_conn(struct smc_connection *conn)
{
struct smc_link_group *lgr = conn->lgr;
+ if (!lgr)
+ return;
write_lock_bh(&lgr->conns_lock);
if (conn->alert_token_local) {
__smc_lgr_unregister_conn(conn);
@@ -300,13 +302,13 @@ static void smc_buf_unuse(struct smc_connection *conn,
conn->sndbuf_desc->used = 0;
if (conn->rmb_desc) {
if (!conn->rmb_desc->regerr) {
- conn->rmb_desc->used = 0;
if (!lgr->is_smcd) {
/* unregister rmb with peer */
smc_llc_do_delete_rkey(
&lgr->lnk[SMC_SINGLE_LINK],
conn->rmb_desc);
}
+ conn->rmb_desc->used = 0;
} else {
/* buf registration failed, reuse not possible */
write_lock_bh(&lgr->rmbs_lock);
@@ -628,6 +630,8 @@ int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact,
local_contact = SMC_REUSE_CONTACT;
conn->lgr = lgr;
smc_lgr_register_conn(conn); /* add smc conn to lgr */
+ if (delayed_work_pending(&lgr->free_work))
+ cancel_delayed_work(&lgr->free_work);
write_unlock_bh(&lgr->conns_lock);
break;
}
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index b00287989a3d..8806d2afa6ed 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -52,6 +52,24 @@ enum smc_wr_reg_state {
FAILED /* ib_wr_reg_mr response: failure */
};
+struct smc_rdma_sge { /* sges for RDMA writes */
+ struct ib_sge wr_tx_rdma_sge[SMC_IB_MAX_SEND_SGE];
+};
+
+#define SMC_MAX_RDMA_WRITES 2 /* max. # of RDMA writes per
+ * message send
+ */
+
+struct smc_rdma_sges { /* sges per message send */
+ struct smc_rdma_sge tx_rdma_sge[SMC_MAX_RDMA_WRITES];
+};
+
+struct smc_rdma_wr { /* work requests per message
+ * send
+ */
+ struct ib_rdma_wr wr_tx_rdma[SMC_MAX_RDMA_WRITES];
+};
+
struct smc_link {
struct smc_ib_device *smcibdev; /* ib-device */
u8 ibport; /* port - values 1 | 2 */
@@ -64,6 +82,8 @@ struct smc_link {
struct smc_wr_buf *wr_tx_bufs; /* WR send payload buffers */
struct ib_send_wr *wr_tx_ibs; /* WR send meta data */
struct ib_sge *wr_tx_sges; /* WR send gather meta data */
+ struct smc_rdma_sges *wr_tx_rdma_sges;/*RDMA WRITE gather meta data*/
+ struct smc_rdma_wr *wr_tx_rdmas; /* WR RDMA WRITE */
struct smc_wr_tx_pend *wr_tx_pends; /* WR send waiting for CQE */
/* above four vectors have wr_tx_cnt elements and use the same index */
dma_addr_t wr_tx_dma_addr; /* DMA address of wr_tx_bufs */
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index e519ef29c0ff..76487a16934e 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -289,8 +289,8 @@ int smc_ib_create_protection_domain(struct smc_link *lnk)
static void smc_ib_qp_event_handler(struct ib_event *ibevent, void *priv)
{
- struct smc_ib_device *smcibdev =
- (struct smc_ib_device *)ibevent->device;
+ struct smc_link *lnk = (struct smc_link *)priv;
+ struct smc_ib_device *smcibdev = lnk->smcibdev;
u8 port_idx;
switch (ibevent->event) {
@@ -298,7 +298,7 @@ static void smc_ib_qp_event_handler(struct ib_event *ibevent, void *priv)
case IB_EVENT_GID_CHANGE:
case IB_EVENT_PORT_ERR:
case IB_EVENT_QP_ACCESS_ERR:
- port_idx = ibevent->element.port_num - 1;
+ port_idx = ibevent->element.qp->port - 1;
set_bit(port_idx, &smcibdev->port_event_mask);
schedule_work(&smcibdev->port_event_work);
break;
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index a6d3623d06f4..4fd60c522802 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -166,7 +166,8 @@ static int smc_llc_add_pending_send(struct smc_link *link,
{
int rc;
- rc = smc_wr_tx_get_free_slot(link, smc_llc_tx_handler, wr_buf, pend);
+ rc = smc_wr_tx_get_free_slot(link, smc_llc_tx_handler, wr_buf, NULL,
+ pend);
if (rc < 0)
return rc;
BUILD_BUG_ON_MSG(
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 7cb3e4f07c10..632c3109dee5 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -27,7 +27,7 @@
static struct nla_policy smc_pnet_policy[SMC_PNETID_MAX + 1] = {
[SMC_PNETID_NAME] = {
.type = NLA_NUL_STRING,
- .len = SMC_MAX_PNETID_LEN - 1
+ .len = SMC_MAX_PNETID_LEN
},
[SMC_PNETID_ETHNAME] = {
.type = NLA_NUL_STRING,
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index d8366ed51757..f93f3580c100 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -165,12 +165,11 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len)
conn->local_tx_ctrl.prod_flags.urg_data_pending = 1;
if (!atomic_read(&conn->sndbuf_space) || conn->urg_tx_pend) {
+ if (send_done)
+ return send_done;
rc = smc_tx_wait(smc, msg->msg_flags);
- if (rc) {
- if (send_done)
- return send_done;
+ if (rc)
goto out_err;
- }
continue;
}
@@ -267,27 +266,23 @@ int smcd_tx_ism_write(struct smc_connection *conn, void *data, size_t len,
/* sndbuf consumer: actual data transfer of one target chunk with RDMA write */
static int smc_tx_rdma_write(struct smc_connection *conn, int peer_rmbe_offset,
- int num_sges, struct ib_sge sges[])
+ int num_sges, struct ib_rdma_wr *rdma_wr)
{
struct smc_link_group *lgr = conn->lgr;
- struct ib_rdma_wr rdma_wr;
struct smc_link *link;
int rc;
- memset(&rdma_wr, 0, sizeof(rdma_wr));
link = &lgr->lnk[SMC_SINGLE_LINK];
- rdma_wr.wr.wr_id = smc_wr_tx_get_next_wr_id(link);
- rdma_wr.wr.sg_list = sges;
- rdma_wr.wr.num_sge = num_sges;
- rdma_wr.wr.opcode = IB_WR_RDMA_WRITE;
- rdma_wr.remote_addr =
+ rdma_wr->wr.wr_id = smc_wr_tx_get_next_wr_id(link);
+ rdma_wr->wr.num_sge = num_sges;
+ rdma_wr->remote_addr =
lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].dma_addr +
/* RMBE within RMB */
conn->tx_off +
/* offset within RMBE */
peer_rmbe_offset;
- rdma_wr.rkey = lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].rkey;
- rc = ib_post_send(link->roce_qp, &rdma_wr.wr, NULL);
+ rdma_wr->rkey = lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].rkey;
+ rc = ib_post_send(link->roce_qp, &rdma_wr->wr, NULL);
if (rc) {
conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1;
smc_lgr_terminate(lgr);
@@ -314,24 +309,25 @@ static inline void smc_tx_advance_cursors(struct smc_connection *conn,
/* SMC-R helper for smc_tx_rdma_writes() */
static int smcr_tx_rdma_writes(struct smc_connection *conn, size_t len,
size_t src_off, size_t src_len,
- size_t dst_off, size_t dst_len)
+ size_t dst_off, size_t dst_len,
+ struct smc_rdma_wr *wr_rdma_buf)
{
dma_addr_t dma_addr =
sg_dma_address(conn->sndbuf_desc->sgt[SMC_SINGLE_LINK].sgl);
- struct smc_link *link = &conn->lgr->lnk[SMC_SINGLE_LINK];
int src_len_sum = src_len, dst_len_sum = dst_len;
- struct ib_sge sges[SMC_IB_MAX_SEND_SGE];
int sent_count = src_off;
int srcchunk, dstchunk;
int num_sges;
int rc;
for (dstchunk = 0; dstchunk < 2; dstchunk++) {
+ struct ib_sge *sge =
+ wr_rdma_buf->wr_tx_rdma[dstchunk].wr.sg_list;
+
num_sges = 0;
for (srcchunk = 0; srcchunk < 2; srcchunk++) {
- sges[srcchunk].addr = dma_addr + src_off;
- sges[srcchunk].length = src_len;
- sges[srcchunk].lkey = link->roce_pd->local_dma_lkey;
+ sge[srcchunk].addr = dma_addr + src_off;
+ sge[srcchunk].length = src_len;
num_sges++;
src_off += src_len;
@@ -344,7 +340,8 @@ static int smcr_tx_rdma_writes(struct smc_connection *conn, size_t len,
src_len = dst_len - src_len; /* remainder */
src_len_sum += src_len;
}
- rc = smc_tx_rdma_write(conn, dst_off, num_sges, sges);
+ rc = smc_tx_rdma_write(conn, dst_off, num_sges,
+ &wr_rdma_buf->wr_tx_rdma[dstchunk]);
if (rc)
return rc;
if (dst_len_sum == len)
@@ -403,7 +400,8 @@ static int smcd_tx_rdma_writes(struct smc_connection *conn, size_t len,
/* sndbuf consumer: prepare all necessary (src&dst) chunks of data transmit;
* usable snd_wnd as max transmit
*/
-static int smc_tx_rdma_writes(struct smc_connection *conn)
+static int smc_tx_rdma_writes(struct smc_connection *conn,
+ struct smc_rdma_wr *wr_rdma_buf)
{
size_t len, src_len, dst_off, dst_len; /* current chunk values */
union smc_host_cursor sent, prep, prod, cons;
@@ -464,7 +462,7 @@ static int smc_tx_rdma_writes(struct smc_connection *conn)
dst_off, dst_len);
else
rc = smcr_tx_rdma_writes(conn, len, sent.count, src_len,
- dst_off, dst_len);
+ dst_off, dst_len, wr_rdma_buf);
if (rc)
return rc;
@@ -485,31 +483,30 @@ static int smc_tx_rdma_writes(struct smc_connection *conn)
static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn)
{
struct smc_cdc_producer_flags *pflags;
+ struct smc_rdma_wr *wr_rdma_buf;
struct smc_cdc_tx_pend *pend;
struct smc_wr_buf *wr_buf;
int rc;
- spin_lock_bh(&conn->send_lock);
- rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend);
+ rc = smc_cdc_get_free_slot(conn, &wr_buf, &wr_rdma_buf, &pend);
if (rc < 0) {
if (rc == -EBUSY) {
struct smc_sock *smc =
container_of(conn, struct smc_sock, conn);
- if (smc->sk.sk_err == ECONNABORTED) {
- rc = sock_error(&smc->sk);
- goto out_unlock;
- }
+ if (smc->sk.sk_err == ECONNABORTED)
+ return sock_error(&smc->sk);
rc = 0;
if (conn->alert_token_local) /* connection healthy */
mod_delayed_work(system_wq, &conn->tx_work,
SMC_TX_WORK_DELAY);
}
- goto out_unlock;
+ return rc;
}
+ spin_lock_bh(&conn->send_lock);
if (!conn->local_tx_ctrl.prod_flags.urg_data_present) {
- rc = smc_tx_rdma_writes(conn);
+ rc = smc_tx_rdma_writes(conn, wr_rdma_buf);
if (rc) {
smc_wr_tx_put_slot(&conn->lgr->lnk[SMC_SINGLE_LINK],
(struct smc_wr_tx_pend_priv *)pend);
@@ -536,7 +533,7 @@ static int smcd_tx_sndbuf_nonempty(struct smc_connection *conn)
spin_lock_bh(&conn->send_lock);
if (!pflags->urg_data_present)
- rc = smc_tx_rdma_writes(conn);
+ rc = smc_tx_rdma_writes(conn, NULL);
if (!rc)
rc = smcd_cdc_msg_send(conn);
@@ -598,7 +595,8 @@ void smc_tx_consumer_update(struct smc_connection *conn, bool force)
if (to_confirm > conn->rmbe_update_limit) {
smc_curs_copy(&prod, &conn->local_rx_ctrl.prod, conn);
sender_free = conn->rmb_desc->len -
- smc_curs_diff(conn->rmb_desc->len, &prod, &cfed);
+ smc_curs_diff_large(conn->rmb_desc->len,
+ &cfed, &prod);
}
if (conn->local_rx_ctrl.prod_flags.cons_curs_upd_req ||
diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
index c2694750a6a8..253aa75dc2b6 100644
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -160,6 +160,7 @@ static inline int smc_wr_tx_get_free_slot_index(struct smc_link *link, u32 *idx)
* @link: Pointer to smc_link used to later send the message.
* @handler: Send completion handler function pointer.
* @wr_buf: Out value returns pointer to message buffer.
+ * @wr_rdma_buf: Out value returns pointer to rdma work request.
* @wr_pend_priv: Out value returns pointer serving as handler context.
*
* Return: 0 on success, or -errno on error.
@@ -167,6 +168,7 @@ static inline int smc_wr_tx_get_free_slot_index(struct smc_link *link, u32 *idx)
int smc_wr_tx_get_free_slot(struct smc_link *link,
smc_wr_tx_handler handler,
struct smc_wr_buf **wr_buf,
+ struct smc_rdma_wr **wr_rdma_buf,
struct smc_wr_tx_pend_priv **wr_pend_priv)
{
struct smc_wr_tx_pend *wr_pend;
@@ -204,6 +206,8 @@ int smc_wr_tx_get_free_slot(struct smc_link *link,
wr_ib = &link->wr_tx_ibs[idx];
wr_ib->wr_id = wr_id;
*wr_buf = &link->wr_tx_bufs[idx];
+ if (wr_rdma_buf)
+ *wr_rdma_buf = &link->wr_tx_rdmas[idx];
*wr_pend_priv = &wr_pend->priv;
return 0;
}
@@ -218,10 +222,10 @@ int smc_wr_tx_put_slot(struct smc_link *link,
u32 idx = pend->idx;
/* clear the full struct smc_wr_tx_pend including .priv */
- memset(&link->wr_tx_pends[pend->idx], 0,
- sizeof(link->wr_tx_pends[pend->idx]));
- memset(&link->wr_tx_bufs[pend->idx], 0,
- sizeof(link->wr_tx_bufs[pend->idx]));
+ memset(&link->wr_tx_pends[idx], 0,
+ sizeof(link->wr_tx_pends[idx]));
+ memset(&link->wr_tx_bufs[idx], 0,
+ sizeof(link->wr_tx_bufs[idx]));
test_and_clear_bit(idx, link->wr_tx_mask);
return 1;
}
@@ -465,12 +469,26 @@ static void smc_wr_init_sge(struct smc_link *lnk)
lnk->wr_tx_dma_addr + i * SMC_WR_BUF_SIZE;
lnk->wr_tx_sges[i].length = SMC_WR_TX_SIZE;
lnk->wr_tx_sges[i].lkey = lnk->roce_pd->local_dma_lkey;
+ lnk->wr_tx_rdma_sges[i].tx_rdma_sge[0].wr_tx_rdma_sge[0].lkey =
+ lnk->roce_pd->local_dma_lkey;
+ lnk->wr_tx_rdma_sges[i].tx_rdma_sge[0].wr_tx_rdma_sge[1].lkey =
+ lnk->roce_pd->local_dma_lkey;
+ lnk->wr_tx_rdma_sges[i].tx_rdma_sge[1].wr_tx_rdma_sge[0].lkey =
+ lnk->roce_pd->local_dma_lkey;
+ lnk->wr_tx_rdma_sges[i].tx_rdma_sge[1].wr_tx_rdma_sge[1].lkey =
+ lnk->roce_pd->local_dma_lkey;
lnk->wr_tx_ibs[i].next = NULL;
lnk->wr_tx_ibs[i].sg_list = &lnk->wr_tx_sges[i];
lnk->wr_tx_ibs[i].num_sge = 1;
lnk->wr_tx_ibs[i].opcode = IB_WR_SEND;
lnk->wr_tx_ibs[i].send_flags =
IB_SEND_SIGNALED | IB_SEND_SOLICITED;
+ lnk->wr_tx_rdmas[i].wr_tx_rdma[0].wr.opcode = IB_WR_RDMA_WRITE;
+ lnk->wr_tx_rdmas[i].wr_tx_rdma[1].wr.opcode = IB_WR_RDMA_WRITE;
+ lnk->wr_tx_rdmas[i].wr_tx_rdma[0].wr.sg_list =
+ lnk->wr_tx_rdma_sges[i].tx_rdma_sge[0].wr_tx_rdma_sge;
+ lnk->wr_tx_rdmas[i].wr_tx_rdma[1].wr.sg_list =
+ lnk->wr_tx_rdma_sges[i].tx_rdma_sge[1].wr_tx_rdma_sge;
}
for (i = 0; i < lnk->wr_rx_cnt; i++) {
lnk->wr_rx_sges[i].addr =
@@ -521,8 +539,12 @@ void smc_wr_free_link_mem(struct smc_link *lnk)
lnk->wr_tx_mask = NULL;
kfree(lnk->wr_tx_sges);
lnk->wr_tx_sges = NULL;
+ kfree(lnk->wr_tx_rdma_sges);
+ lnk->wr_tx_rdma_sges = NULL;
kfree(lnk->wr_rx_sges);
lnk->wr_rx_sges = NULL;
+ kfree(lnk->wr_tx_rdmas);
+ lnk->wr_tx_rdmas = NULL;
kfree(lnk->wr_rx_ibs);
lnk->wr_rx_ibs = NULL;
kfree(lnk->wr_tx_ibs);
@@ -552,10 +574,20 @@ int smc_wr_alloc_link_mem(struct smc_link *link)
GFP_KERNEL);
if (!link->wr_rx_ibs)
goto no_mem_wr_tx_ibs;
+ link->wr_tx_rdmas = kcalloc(SMC_WR_BUF_CNT,
+ sizeof(link->wr_tx_rdmas[0]),
+ GFP_KERNEL);
+ if (!link->wr_tx_rdmas)
+ goto no_mem_wr_rx_ibs;
+ link->wr_tx_rdma_sges = kcalloc(SMC_WR_BUF_CNT,
+ sizeof(link->wr_tx_rdma_sges[0]),
+ GFP_KERNEL);
+ if (!link->wr_tx_rdma_sges)
+ goto no_mem_wr_tx_rdmas;
link->wr_tx_sges = kcalloc(SMC_WR_BUF_CNT, sizeof(link->wr_tx_sges[0]),
GFP_KERNEL);
if (!link->wr_tx_sges)
- goto no_mem_wr_rx_ibs;
+ goto no_mem_wr_tx_rdma_sges;
link->wr_rx_sges = kcalloc(SMC_WR_BUF_CNT * 3,
sizeof(link->wr_rx_sges[0]),
GFP_KERNEL);
@@ -579,6 +611,10 @@ no_mem_wr_rx_sges:
kfree(link->wr_rx_sges);
no_mem_wr_tx_sges:
kfree(link->wr_tx_sges);
+no_mem_wr_tx_rdma_sges:
+ kfree(link->wr_tx_rdma_sges);
+no_mem_wr_tx_rdmas:
+ kfree(link->wr_tx_rdmas);
no_mem_wr_rx_ibs:
kfree(link->wr_rx_ibs);
no_mem_wr_tx_ibs:
diff --git a/net/smc/smc_wr.h b/net/smc/smc_wr.h
index 1d85bb14fd6f..09bf32fd3959 100644
--- a/net/smc/smc_wr.h
+++ b/net/smc/smc_wr.h
@@ -85,6 +85,7 @@ void smc_wr_add_dev(struct smc_ib_device *smcibdev);
int smc_wr_tx_get_free_slot(struct smc_link *link, smc_wr_tx_handler handler,
struct smc_wr_buf **wr_buf,
+ struct smc_rdma_wr **wrs,
struct smc_wr_tx_pend_priv **wr_pend_priv);
int smc_wr_tx_put_slot(struct smc_link *link,
struct smc_wr_tx_pend_priv *wr_pend_priv);
diff --git a/net/socket.c b/net/socket.c
index e89884e2197b..320f51b22b19 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -577,6 +577,7 @@ static void __sock_release(struct socket *sock, struct inode *inode)
if (inode)
inode_lock(inode);
sock->ops->release(sock);
+ sock->sk = NULL;
if (inode)
inode_unlock(inode);
sock->ops = NULL;
@@ -941,8 +942,7 @@ void dlci_ioctl_set(int (*hook) (unsigned int, void __user *))
EXPORT_SYMBOL(dlci_ioctl_set);
static long sock_do_ioctl(struct net *net, struct socket *sock,
- unsigned int cmd, unsigned long arg,
- unsigned int ifreq_size)
+ unsigned int cmd, unsigned long arg)
{
int err;
void __user *argp = (void __user *)arg;
@@ -968,11 +968,11 @@ static long sock_do_ioctl(struct net *net, struct socket *sock,
} else {
struct ifreq ifr;
bool need_copyout;
- if (copy_from_user(&ifr, argp, ifreq_size))
+ if (copy_from_user(&ifr, argp, sizeof(struct ifreq)))
return -EFAULT;
err = dev_ioctl(net, cmd, &ifr, &need_copyout);
if (!err && need_copyout)
- if (copy_to_user(argp, &ifr, ifreq_size))
+ if (copy_to_user(argp, &ifr, sizeof(struct ifreq)))
return -EFAULT;
}
return err;
@@ -1071,8 +1071,7 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
err = open_related_ns(&net->ns, get_net_ns);
break;
default:
- err = sock_do_ioctl(net, sock, cmd, arg,
- sizeof(struct ifreq));
+ err = sock_do_ioctl(net, sock, cmd, arg);
break;
}
return err;
@@ -2780,8 +2779,7 @@ static int do_siocgstamp(struct net *net, struct socket *sock,
int err;
set_fs(KERNEL_DS);
- err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv,
- sizeof(struct compat_ifreq));
+ err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv);
set_fs(old_fs);
if (!err)
err = compat_put_timeval(&ktv, up);
@@ -2797,8 +2795,7 @@ static int do_siocgstampns(struct net *net, struct socket *sock,
int err;
set_fs(KERNEL_DS);
- err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts,
- sizeof(struct compat_ifreq));
+ err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts);
set_fs(old_fs);
if (!err)
err = compat_put_timespec(&kts, up);
@@ -2994,6 +2991,54 @@ static int compat_ifr_data_ioctl(struct net *net, unsigned int cmd,
return dev_ioctl(net, cmd, &ifreq, NULL);
}
+static int compat_ifreq_ioctl(struct net *net, struct socket *sock,
+ unsigned int cmd,
+ struct compat_ifreq __user *uifr32)
+{
+ struct ifreq __user *uifr;
+ int err;
+
+ /* Handle the fact that while struct ifreq has the same *layout* on
+ * 32/64 for everything but ifreq::ifru_ifmap and ifreq::ifru_data,
+ * which are handled elsewhere, it still has different *size* due to
+ * ifreq::ifru_ifmap (which is 16 bytes on 32 bit, 24 bytes on 64-bit,
+ * resulting in struct ifreq being 32 and 40 bytes respectively).
+ * As a result, if the struct happens to be at the end of a page and
+ * the next page isn't readable/writable, we get a fault. To prevent
+ * that, copy back and forth to the full size.
+ */
+
+ uifr = compat_alloc_user_space(sizeof(*uifr));
+ if (copy_in_user(uifr, uifr32, sizeof(*uifr32)))
+ return -EFAULT;
+
+ err = sock_do_ioctl(net, sock, cmd, (unsigned long)uifr);
+
+ if (!err) {
+ switch (cmd) {
+ case SIOCGIFFLAGS:
+ case SIOCGIFMETRIC:
+ case SIOCGIFMTU:
+ case SIOCGIFMEM:
+ case SIOCGIFHWADDR:
+ case SIOCGIFINDEX:
+ case SIOCGIFADDR:
+ case SIOCGIFBRDADDR:
+ case SIOCGIFDSTADDR:
+ case SIOCGIFNETMASK:
+ case SIOCGIFPFLAGS:
+ case SIOCGIFTXQLEN:
+ case SIOCGMIIPHY:
+ case SIOCGMIIREG:
+ case SIOCGIFNAME:
+ if (copy_in_user(uifr32, uifr, sizeof(*uifr32)))
+ err = -EFAULT;
+ break;
+ }
+ }
+ return err;
+}
+
static int compat_sioc_ifmap(struct net *net, unsigned int cmd,
struct compat_ifreq __user *uifr32)
{
@@ -3109,8 +3154,7 @@ static int routing_ioctl(struct net *net, struct socket *sock,
}
set_fs(KERNEL_DS);
- ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r,
- sizeof(struct compat_ifreq));
+ ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r);
set_fs(old_fs);
out:
@@ -3210,21 +3254,22 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
case SIOCSIFTXQLEN:
case SIOCBRADDIF:
case SIOCBRDELIF:
+ case SIOCGIFNAME:
case SIOCSIFNAME:
case SIOCGMIIPHY:
case SIOCGMIIREG:
case SIOCSMIIREG:
- case SIOCSARP:
- case SIOCGARP:
- case SIOCDARP:
- case SIOCATMARK:
case SIOCBONDENSLAVE:
case SIOCBONDRELEASE:
case SIOCBONDSETHWADDR:
case SIOCBONDCHANGEACTIVE:
- case SIOCGIFNAME:
- return sock_do_ioctl(net, sock, cmd, arg,
- sizeof(struct compat_ifreq));
+ return compat_ifreq_ioctl(net, sock, cmd, argp);
+
+ case SIOCSARP:
+ case SIOCGARP:
+ case SIOCDARP:
+ case SIOCATMARK:
+ return sock_do_ioctl(net, sock, cmd, arg);
}
return -ENOIOCTLCMD;
diff --git a/net/sunrpc/auth_gss/gss_krb5_seqnum.c b/net/sunrpc/auth_gss/gss_krb5_seqnum.c
index fb6656295204..507105127095 100644
--- a/net/sunrpc/auth_gss/gss_krb5_seqnum.c
+++ b/net/sunrpc/auth_gss/gss_krb5_seqnum.c
@@ -44,7 +44,7 @@ krb5_make_rc4_seq_num(struct krb5_ctx *kctx, int direction, s32 seqnum,
unsigned char *cksum, unsigned char *buf)
{
struct crypto_sync_skcipher *cipher;
- unsigned char plain[8];
+ unsigned char *plain;
s32 code;
dprintk("RPC: %s:\n", __func__);
@@ -52,6 +52,10 @@ krb5_make_rc4_seq_num(struct krb5_ctx *kctx, int direction, s32 seqnum,
if (IS_ERR(cipher))
return PTR_ERR(cipher);
+ plain = kmalloc(8, GFP_NOFS);
+ if (!plain)
+ return -ENOMEM;
+
plain[0] = (unsigned char) ((seqnum >> 24) & 0xff);
plain[1] = (unsigned char) ((seqnum >> 16) & 0xff);
plain[2] = (unsigned char) ((seqnum >> 8) & 0xff);
@@ -67,6 +71,7 @@ krb5_make_rc4_seq_num(struct krb5_ctx *kctx, int direction, s32 seqnum,
code = krb5_encrypt(cipher, cksum, plain, buf, 8);
out:
+ kfree(plain);
crypto_free_sync_skcipher(cipher);
return code;
}
@@ -77,12 +82,17 @@ krb5_make_seq_num(struct krb5_ctx *kctx,
u32 seqnum,
unsigned char *cksum, unsigned char *buf)
{
- unsigned char plain[8];
+ unsigned char *plain;
+ s32 code;
if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC)
return krb5_make_rc4_seq_num(kctx, direction, seqnum,
cksum, buf);
+ plain = kmalloc(8, GFP_NOFS);
+ if (!plain)
+ return -ENOMEM;
+
plain[0] = (unsigned char) (seqnum & 0xff);
plain[1] = (unsigned char) ((seqnum >> 8) & 0xff);
plain[2] = (unsigned char) ((seqnum >> 16) & 0xff);
@@ -93,7 +103,9 @@ krb5_make_seq_num(struct krb5_ctx *kctx,
plain[6] = direction;
plain[7] = direction;
- return krb5_encrypt(key, cksum, plain, buf, 8);
+ code = krb5_encrypt(key, cksum, plain, buf, 8);
+ kfree(plain);
+ return code;
}
static s32
@@ -101,7 +113,7 @@ krb5_get_rc4_seq_num(struct krb5_ctx *kctx, unsigned char *cksum,
unsigned char *buf, int *direction, s32 *seqnum)
{
struct crypto_sync_skcipher *cipher;
- unsigned char plain[8];
+ unsigned char *plain;
s32 code;
dprintk("RPC: %s:\n", __func__);
@@ -113,20 +125,28 @@ krb5_get_rc4_seq_num(struct krb5_ctx *kctx, unsigned char *cksum,
if (code)
goto out;
+ plain = kmalloc(8, GFP_NOFS);
+ if (!plain) {
+ code = -ENOMEM;
+ goto out;
+ }
+
code = krb5_decrypt(cipher, cksum, buf, plain, 8);
if (code)
- goto out;
+ goto out_plain;
if ((plain[4] != plain[5]) || (plain[4] != plain[6])
|| (plain[4] != plain[7])) {
code = (s32)KG_BAD_SEQ;
- goto out;
+ goto out_plain;
}
*direction = plain[4];
*seqnum = ((plain[0] << 24) | (plain[1] << 16) |
(plain[2] << 8) | (plain[3]));
+out_plain:
+ kfree(plain);
out:
crypto_free_sync_skcipher(cipher);
return code;
@@ -139,7 +159,7 @@ krb5_get_seq_num(struct krb5_ctx *kctx,
int *direction, u32 *seqnum)
{
s32 code;
- unsigned char plain[8];
+ unsigned char *plain;
struct crypto_sync_skcipher *key = kctx->seq;
dprintk("RPC: krb5_get_seq_num:\n");
@@ -147,18 +167,25 @@ krb5_get_seq_num(struct krb5_ctx *kctx,
if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC)
return krb5_get_rc4_seq_num(kctx, cksum, buf,
direction, seqnum);
+ plain = kmalloc(8, GFP_NOFS);
+ if (!plain)
+ return -ENOMEM;
if ((code = krb5_decrypt(key, cksum, buf, plain, 8)))
- return code;
+ goto out;
if ((plain[4] != plain[5]) || (plain[4] != plain[6]) ||
- (plain[4] != plain[7]))
- return (s32)KG_BAD_SEQ;
+ (plain[4] != plain[7])) {
+ code = (s32)KG_BAD_SEQ;
+ goto out;
+ }
*direction = plain[4];
*seqnum = ((plain[0]) |
(plain[1] << 8) | (plain[2] << 16) | (plain[3] << 24));
- return 0;
+out:
+ kfree(plain);
+ return code;
}
diff --git a/net/sunrpc/debugfs.c b/net/sunrpc/debugfs.c
index 45a033329cd4..19bb356230ed 100644
--- a/net/sunrpc/debugfs.c
+++ b/net/sunrpc/debugfs.c
@@ -146,7 +146,7 @@ rpc_clnt_debugfs_register(struct rpc_clnt *clnt)
rcu_read_lock();
xprt = rcu_dereference(clnt->cl_xprt);
/* no "debugfs" dentry? Don't bother with the symlink. */
- if (!xprt->debugfs) {
+ if (IS_ERR_OR_NULL(xprt->debugfs)) {
rcu_read_unlock();
return;
}
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index cf51b8f9b15f..1f200119268c 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -537,6 +537,99 @@ void svc_rdma_sync_reply_hdr(struct svcxprt_rdma *rdma,
DMA_TO_DEVICE);
}
+/* If the xdr_buf has more elements than the device can
+ * transmit in a single RDMA Send, then the reply will
+ * have to be copied into a bounce buffer.
+ */
+static bool svc_rdma_pull_up_needed(struct svcxprt_rdma *rdma,
+ struct xdr_buf *xdr,
+ __be32 *wr_lst)
+{
+ int elements;
+
+ /* xdr->head */
+ elements = 1;
+
+ /* xdr->pages */
+ if (!wr_lst) {
+ unsigned int remaining;
+ unsigned long pageoff;
+
+ pageoff = xdr->page_base & ~PAGE_MASK;
+ remaining = xdr->page_len;
+ while (remaining) {
+ ++elements;
+ remaining -= min_t(u32, PAGE_SIZE - pageoff,
+ remaining);
+ pageoff = 0;
+ }
+ }
+
+ /* xdr->tail */
+ if (xdr->tail[0].iov_len)
+ ++elements;
+
+ /* assume 1 SGE is needed for the transport header */
+ return elements >= rdma->sc_max_send_sges;
+}
+
+/* The device is not capable of sending the reply directly.
+ * Assemble the elements of @xdr into the transport header
+ * buffer.
+ */
+static int svc_rdma_pull_up_reply_msg(struct svcxprt_rdma *rdma,
+ struct svc_rdma_send_ctxt *ctxt,
+ struct xdr_buf *xdr, __be32 *wr_lst)
+{
+ unsigned char *dst, *tailbase;
+ unsigned int taillen;
+
+ dst = ctxt->sc_xprt_buf;
+ dst += ctxt->sc_sges[0].length;
+
+ memcpy(dst, xdr->head[0].iov_base, xdr->head[0].iov_len);
+ dst += xdr->head[0].iov_len;
+
+ tailbase = xdr->tail[0].iov_base;
+ taillen = xdr->tail[0].iov_len;
+ if (wr_lst) {
+ u32 xdrpad;
+
+ xdrpad = xdr_padsize(xdr->page_len);
+ if (taillen && xdrpad) {
+ tailbase += xdrpad;
+ taillen -= xdrpad;
+ }
+ } else {
+ unsigned int len, remaining;
+ unsigned long pageoff;
+ struct page **ppages;
+
+ ppages = xdr->pages + (xdr->page_base >> PAGE_SHIFT);
+ pageoff = xdr->page_base & ~PAGE_MASK;
+ remaining = xdr->page_len;
+ while (remaining) {
+ len = min_t(u32, PAGE_SIZE - pageoff, remaining);
+
+ memcpy(dst, page_address(*ppages), len);
+ remaining -= len;
+ dst += len;
+ pageoff = 0;
+ }
+ }
+
+ if (taillen)
+ memcpy(dst, tailbase, taillen);
+
+ ctxt->sc_sges[0].length += xdr->len;
+ ib_dma_sync_single_for_device(rdma->sc_pd->device,
+ ctxt->sc_sges[0].addr,
+ ctxt->sc_sges[0].length,
+ DMA_TO_DEVICE);
+
+ return 0;
+}
+
/* svc_rdma_map_reply_msg - Map the buffer holding RPC message
* @rdma: controlling transport
* @ctxt: send_ctxt for the Send WR
@@ -559,8 +652,10 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
u32 xdr_pad;
int ret;
- if (++ctxt->sc_cur_sge_no >= rdma->sc_max_send_sges)
- return -EIO;
+ if (svc_rdma_pull_up_needed(rdma, xdr, wr_lst))
+ return svc_rdma_pull_up_reply_msg(rdma, ctxt, xdr, wr_lst);
+
+ ++ctxt->sc_cur_sge_no;
ret = svc_rdma_dma_map_buf(rdma, ctxt,
xdr->head[0].iov_base,
xdr->head[0].iov_len);
@@ -591,8 +686,7 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
while (remaining) {
len = min_t(u32, PAGE_SIZE - page_off, remaining);
- if (++ctxt->sc_cur_sge_no >= rdma->sc_max_send_sges)
- return -EIO;
+ ++ctxt->sc_cur_sge_no;
ret = svc_rdma_dma_map_page(rdma, ctxt, *ppages++,
page_off, len);
if (ret < 0)
@@ -606,8 +700,7 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
len = xdr->tail[0].iov_len;
tail:
if (len) {
- if (++ctxt->sc_cur_sge_no >= rdma->sc_max_send_sges)
- return -EIO;
+ ++ctxt->sc_cur_sge_no;
ret = svc_rdma_dma_map_buf(rdma, ctxt, base, len);
if (ret < 0)
return ret;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 924c17d46903..57f86c63a463 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -419,12 +419,9 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
/* Transport header, head iovec, tail iovec */
newxprt->sc_max_send_sges = 3;
/* Add one SGE per page list entry */
- newxprt->sc_max_send_sges += svcrdma_max_req_size / PAGE_SIZE;
- if (newxprt->sc_max_send_sges > dev->attrs.max_send_sge) {
- pr_err("svcrdma: too few Send SGEs available (%d needed)\n",
- newxprt->sc_max_send_sges);
- goto errout;
- }
+ newxprt->sc_max_send_sges += (svcrdma_max_req_size / PAGE_SIZE) + 1;
+ if (newxprt->sc_max_send_sges > dev->attrs.max_send_sge)
+ newxprt->sc_max_send_sges = dev->attrs.max_send_sge;
newxprt->sc_max_req_size = svcrdma_max_req_size;
newxprt->sc_max_requests = svcrdma_max_requests;
newxprt->sc_max_bc_requests = svcrdma_max_bc_requests;
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 4994e75945b8..21113bfd4eca 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -527,7 +527,8 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
sendcq = ib_alloc_cq(ia->ri_device, NULL,
ep->rep_attr.cap.max_send_wr + 1,
- 1, IB_POLL_WORKQUEUE);
+ ia->ri_device->num_comp_vectors > 1 ? 1 : 0,
+ IB_POLL_WORKQUEUE);
if (IS_ERR(sendcq)) {
rc = PTR_ERR(sendcq);
goto out1;
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 2792a3cae682..85ad5c0678d0 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1145,7 +1145,7 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb,
default:
pr_warn("Dropping received illegal msg type\n");
kfree_skb(skb);
- return false;
+ return true;
};
}
@@ -1425,6 +1425,10 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
l->rcv_unacked = 0;
} else {
/* RESET_MSG or ACTIVATE_MSG */
+ if (mtyp == ACTIVATE_MSG) {
+ msg_set_dest_session_valid(hdr, 1);
+ msg_set_dest_session(hdr, l->peer_session);
+ }
msg_set_max_pkt(hdr, l->advertised_mtu);
strcpy(data, l->if_name);
msg_set_size(hdr, INT_H_SIZE + TIPC_MAX_IF_NAME);
@@ -1642,6 +1646,17 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
break;
}
+
+ /* If this endpoint was re-created while peer was ESTABLISHING
+ * it doesn't know current session number. Force re-synch.
+ */
+ if (mtyp == ACTIVATE_MSG && msg_dest_session_valid(hdr) &&
+ l->session != msg_dest_session(hdr)) {
+ if (less(l->session, msg_dest_session(hdr)))
+ l->session = msg_dest_session(hdr) + 1;
+ break;
+ }
+
/* ACTIVATE_MSG serves as PEER_RESET if link is already down */
if (mtyp == RESET_MSG || !link_is_up(l))
rc = tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT);
diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index a0924956bb61..d7e4b8b93f9d 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -360,6 +360,28 @@ static inline void msg_set_bcast_ack(struct tipc_msg *m, u16 n)
msg_set_bits(m, 1, 0, 0xffff, n);
}
+/* Note: reusing bits in word 1 for ACTIVATE_MSG only, to re-synch
+ * link peer session number
+ */
+static inline bool msg_dest_session_valid(struct tipc_msg *m)
+{
+ return msg_bits(m, 1, 16, 0x1);
+}
+
+static inline void msg_set_dest_session_valid(struct tipc_msg *m, bool valid)
+{
+ msg_set_bits(m, 1, 16, 0x1, valid);
+}
+
+static inline u16 msg_dest_session(struct tipc_msg *m)
+{
+ return msg_bits(m, 1, 0, 0xffff);
+}
+
+static inline void msg_set_dest_session(struct tipc_msg *m, u16 n)
+{
+ msg_set_bits(m, 1, 0, 0xffff, n);
+}
/*
* Word 2
diff --git a/net/tipc/node.c b/net/tipc/node.c
index db2a6c3e0be9..2dc4919ab23c 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -830,15 +830,16 @@ static void tipc_node_link_down(struct tipc_node *n, int bearer_id, bool delete)
tipc_node_write_lock(n);
if (!tipc_link_is_establishing(l)) {
__tipc_node_link_down(n, &bearer_id, &xmitq, &maddr);
- if (delete) {
- kfree(l);
- le->link = NULL;
- n->link_cnt--;
- }
} else {
/* Defuse pending tipc_node_link_up() */
+ tipc_link_reset(l);
tipc_link_fsm_evt(l, LINK_RESET_EVT);
}
+ if (delete) {
+ kfree(l);
+ le->link = NULL;
+ n->link_cnt--;
+ }
trace_tipc_node_link_down(n, true, "node link down or deleted!");
tipc_node_write_unlock(n);
if (delete)
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 1217c90a363b..70343ac448b1 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -379,16 +379,18 @@ static int tipc_sk_sock_err(struct socket *sock, long *timeout)
#define tipc_wait_for_cond(sock_, timeo_, condition_) \
({ \
+ DEFINE_WAIT_FUNC(wait_, woken_wake_function); \
struct sock *sk_; \
int rc_; \
\
while ((rc_ = !(condition_))) { \
- DEFINE_WAIT_FUNC(wait_, woken_wake_function); \
+ /* coupled with smp_wmb() in tipc_sk_proto_rcv() */ \
+ smp_rmb(); \
sk_ = (sock_)->sk; \
rc_ = tipc_sk_sock_err((sock_), timeo_); \
if (rc_) \
break; \
- prepare_to_wait(sk_sleep(sk_), &wait_, TASK_INTERRUPTIBLE); \
+ add_wait_queue(sk_sleep(sk_), &wait_); \
release_sock(sk_); \
*(timeo_) = wait_woken(&wait_, TASK_INTERRUPTIBLE, *(timeo_)); \
sched_annotate_sleep(); \
@@ -1677,7 +1679,7 @@ static void tipc_sk_send_ack(struct tipc_sock *tsk)
static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop)
{
struct sock *sk = sock->sk;
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
long timeo = *timeop;
int err = sock_error(sk);
@@ -1685,15 +1687,17 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop)
return err;
for (;;) {
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
if (timeo && skb_queue_empty(&sk->sk_receive_queue)) {
if (sk->sk_shutdown & RCV_SHUTDOWN) {
err = -ENOTCONN;
break;
}
+ add_wait_queue(sk_sleep(sk), &wait);
release_sock(sk);
- timeo = schedule_timeout(timeo);
+ timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo);
+ sched_annotate_sleep();
lock_sock(sk);
+ remove_wait_queue(sk_sleep(sk), &wait);
}
err = 0;
if (!skb_queue_empty(&sk->sk_receive_queue))
@@ -1709,7 +1713,6 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop)
if (err)
break;
}
- finish_wait(sk_sleep(sk), &wait);
*timeop = timeo;
return err;
}
@@ -1982,6 +1985,8 @@ static void tipc_sk_proto_rcv(struct sock *sk,
return;
case SOCK_WAKEUP:
tipc_dest_del(&tsk->cong_links, msg_orignode(hdr), 0);
+ /* coupled with smp_rmb() in tipc_wait_for_cond() */
+ smp_wmb();
tsk->cong_link_cnt--;
wakeup = true;
break;
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 11cdc8f7db63..bf5b54b513bc 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -439,6 +439,8 @@ static int tls_do_encryption(struct sock *sk,
struct scatterlist *sge = sk_msg_elem(msg_en, start);
int rc;
+ memcpy(rec->iv_data, tls_ctx->tx.iv, sizeof(rec->iv_data));
+
sge->offset += tls_ctx->tx.prepend_size;
sge->length -= tls_ctx->tx.prepend_size;
@@ -448,7 +450,7 @@ static int tls_do_encryption(struct sock *sk,
aead_request_set_ad(aead_req, TLS_AAD_SPACE_SIZE);
aead_request_set_crypt(aead_req, rec->sg_aead_in,
rec->sg_aead_out,
- data_len, tls_ctx->tx.iv);
+ data_len, rec->iv_data);
aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_BACKLOG,
tls_encrypt_done, sk);
@@ -1792,7 +1794,9 @@ void tls_sw_free_resources_tx(struct sock *sk)
if (atomic_read(&ctx->encrypt_pending))
crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
+ release_sock(sk);
cancel_delayed_work_sync(&ctx->tx_work.work);
+ lock_sock(sk);
/* Tx whatever records we can transmit and abandon the rest */
tls_tx_records(sk, -1);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 74d1eed7cbd4..a95d479caeea 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -890,7 +890,7 @@ retry:
addr->hash ^= sk->sk_type;
__unix_remove_socket(sk);
- u->addr = addr;
+ smp_store_release(&u->addr, addr);
__unix_insert_socket(&unix_socket_table[addr->hash], sk);
spin_unlock(&unix_table_lock);
err = 0;
@@ -1060,7 +1060,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
err = 0;
__unix_remove_socket(sk);
- u->addr = addr;
+ smp_store_release(&u->addr, addr);
__unix_insert_socket(list, sk);
out_unlock:
@@ -1331,15 +1331,29 @@ restart:
RCU_INIT_POINTER(newsk->sk_wq, &newu->peer_wq);
otheru = unix_sk(other);
- /* copy address information from listening to new sock*/
- if (otheru->addr) {
- refcount_inc(&otheru->addr->refcnt);
- newu->addr = otheru->addr;
- }
+ /* copy address information from listening to new sock
+ *
+ * The contents of *(otheru->addr) and otheru->path
+ * are seen fully set up here, since we have found
+ * otheru in hash under unix_table_lock. Insertion
+ * into the hash chain we'd found it in had been done
+ * in an earlier critical area protected by unix_table_lock,
+ * the same one where we'd set *(otheru->addr) contents,
+ * as well as otheru->path and otheru->addr itself.
+ *
+ * Using smp_store_release() here to set newu->addr
+ * is enough to make those stores, as well as stores
+ * to newu->path visible to anyone who gets newu->addr
+ * by smp_load_acquire(). IOW, the same warranties
+ * as for unix_sock instances bound in unix_bind() or
+ * in unix_autobind().
+ */
if (otheru->path.dentry) {
path_get(&otheru->path);
newu->path = otheru->path;
}
+ refcount_inc(&otheru->addr->refcnt);
+ smp_store_release(&newu->addr, otheru->addr);
/* Set credentials */
copy_peercred(sk, other);
@@ -1453,7 +1467,7 @@ out:
static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer)
{
struct sock *sk = sock->sk;
- struct unix_sock *u;
+ struct unix_address *addr;
DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, uaddr);
int err = 0;
@@ -1468,19 +1482,15 @@ static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer)
sock_hold(sk);
}
- u = unix_sk(sk);
- unix_state_lock(sk);
- if (!u->addr) {
+ addr = smp_load_acquire(&unix_sk(sk)->addr);
+ if (!addr) {
sunaddr->sun_family = AF_UNIX;
sunaddr->sun_path[0] = 0;
err = sizeof(short);
} else {
- struct unix_address *addr = u->addr;
-
err = addr->len;
memcpy(sunaddr, addr->name, addr->len);
}
- unix_state_unlock(sk);
sock_put(sk);
out:
return err;
@@ -2073,11 +2083,11 @@ static int unix_seqpacket_recvmsg(struct socket *sock, struct msghdr *msg,
static void unix_copy_addr(struct msghdr *msg, struct sock *sk)
{
- struct unix_sock *u = unix_sk(sk);
+ struct unix_address *addr = smp_load_acquire(&unix_sk(sk)->addr);
- if (u->addr) {
- msg->msg_namelen = u->addr->len;
- memcpy(msg->msg_name, u->addr->name, u->addr->len);
+ if (addr) {
+ msg->msg_namelen = addr->len;
+ memcpy(msg->msg_name, addr->name, addr->len);
}
}
@@ -2581,15 +2591,14 @@ static int unix_open_file(struct sock *sk)
if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
return -EPERM;
- unix_state_lock(sk);
+ if (!smp_load_acquire(&unix_sk(sk)->addr))
+ return -ENOENT;
+
path = unix_sk(sk)->path;
- if (!path.dentry) {
- unix_state_unlock(sk);
+ if (!path.dentry)
return -ENOENT;
- }
path_get(&path);
- unix_state_unlock(sk);
fd = get_unused_fd_flags(O_CLOEXEC);
if (fd < 0)
@@ -2830,7 +2839,7 @@ static int unix_seq_show(struct seq_file *seq, void *v)
(s->sk_state == TCP_ESTABLISHED ? SS_CONNECTING : SS_DISCONNECTING),
sock_i_ino(s));
- if (u->addr) {
+ if (u->addr) { // under unix_table_lock here
int i, len;
seq_putc(seq, ' ');
diff --git a/net/unix/diag.c b/net/unix/diag.c
index 384c84e83462..3183d9b8ab33 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -10,7 +10,8 @@
static int sk_diag_dump_name(struct sock *sk, struct sk_buff *nlskb)
{
- struct unix_address *addr = unix_sk(sk)->addr;
+ /* might or might not have unix_table_lock */
+ struct unix_address *addr = smp_load_acquire(&unix_sk(sk)->addr);
if (!addr)
return 0;
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 5d3cce9e8744..15eb5d3d4750 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -75,6 +75,9 @@ static u32 virtio_transport_get_local_cid(void)
{
struct virtio_vsock *vsock = virtio_vsock_get();
+ if (!vsock)
+ return VMADDR_CID_ANY;
+
return vsock->guest_cid;
}
@@ -584,10 +587,6 @@ static int virtio_vsock_probe(struct virtio_device *vdev)
virtio_vsock_update_guest_cid(vsock);
- ret = vsock_core_init(&virtio_transport.transport);
- if (ret < 0)
- goto out_vqs;
-
vsock->rx_buf_nr = 0;
vsock->rx_buf_max_nr = 0;
atomic_set(&vsock->queued_replies, 0);
@@ -618,8 +617,6 @@ static int virtio_vsock_probe(struct virtio_device *vdev)
mutex_unlock(&the_virtio_vsock_mutex);
return 0;
-out_vqs:
- vsock->vdev->config->del_vqs(vsock->vdev);
out:
kfree(vsock);
mutex_unlock(&the_virtio_vsock_mutex);
@@ -637,6 +634,9 @@ static void virtio_vsock_remove(struct virtio_device *vdev)
flush_work(&vsock->event_work);
flush_work(&vsock->send_pkt_work);
+ /* Reset all connected sockets when the device disappear */
+ vsock_for_each_connected_socket(virtio_vsock_reset_sock);
+
vdev->config->reset(vdev);
mutex_lock(&vsock->rx_lock);
@@ -669,7 +669,6 @@ static void virtio_vsock_remove(struct virtio_device *vdev)
mutex_lock(&the_virtio_vsock_mutex);
the_virtio_vsock = NULL;
- vsock_core_exit();
mutex_unlock(&the_virtio_vsock_mutex);
vdev->config->del_vqs(vdev);
@@ -702,14 +701,28 @@ static int __init virtio_vsock_init(void)
virtio_vsock_workqueue = alloc_workqueue("virtio_vsock", 0, 0);
if (!virtio_vsock_workqueue)
return -ENOMEM;
+
ret = register_virtio_driver(&virtio_vsock_driver);
if (ret)
- destroy_workqueue(virtio_vsock_workqueue);
+ goto out_wq;
+
+ ret = vsock_core_init(&virtio_transport.transport);
+ if (ret)
+ goto out_vdr;
+
+ return 0;
+
+out_vdr:
+ unregister_virtio_driver(&virtio_vsock_driver);
+out_wq:
+ destroy_workqueue(virtio_vsock_workqueue);
return ret;
+
}
static void __exit virtio_vsock_exit(void)
{
+ vsock_core_exit();
unregister_virtio_driver(&virtio_vsock_driver);
destroy_workqueue(virtio_vsock_workqueue);
}
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index c361ce782412..c3d5ab01fba7 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -1651,6 +1651,10 @@ static void vmci_transport_cleanup(struct work_struct *work)
static void vmci_transport_destruct(struct vsock_sock *vsk)
{
+ /* transport can be NULL if we hit a failure at init() time */
+ if (!vmci_trans(vsk))
+ return;
+
/* Ensure that the detach callback doesn't use the sk/vsk
* we are about to destruct.
*/
diff --git a/net/wireless/ap.c b/net/wireless/ap.c
index 882d97bdc6bf..550ac9d827fe 100644
--- a/net/wireless/ap.c
+++ b/net/wireless/ap.c
@@ -41,6 +41,8 @@ int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev,
cfg80211_sched_dfs_chan_update(rdev);
}
+ schedule_work(&cfg80211_disconnect_work);
+
return err;
}
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 623dfe5e211c..b36ad8efb5e5 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -1068,6 +1068,8 @@ static void __cfg80211_unregister_wdev(struct wireless_dev *wdev, bool sync)
ASSERT_RTNL();
+ flush_work(&wdev->pmsr_free_wk);
+
nl80211_notify_iface(rdev, wdev, NL80211_CMD_DEL_INTERFACE);
list_del_rcu(&wdev->list);
diff --git a/net/wireless/core.h b/net/wireless/core.h
index c5d6f3418601..f6b40563dc63 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -445,6 +445,8 @@ void cfg80211_process_wdev_events(struct wireless_dev *wdev);
bool cfg80211_does_bw_fit_range(const struct ieee80211_freq_range *freq_range,
u32 center_freq_khz, u32 bw_khz);
+extern struct work_struct cfg80211_disconnect_work;
+
/**
* cfg80211_chandef_dfs_usable - checks if chandef is DFS usable
* @wiphy: the wiphy to validate against
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 5e49492d5911..d91a408db113 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -250,7 +250,7 @@ nl80211_pmsr_ftm_req_attr_policy[NL80211_PMSR_FTM_REQ_ATTR_MAX + 1] = {
[NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION] =
NLA_POLICY_MAX(NLA_U8, 15),
[NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST] =
- NLA_POLICY_MAX(NLA_U8, 15),
+ NLA_POLICY_MAX(NLA_U8, 31),
[NL80211_PMSR_FTM_REQ_ATTR_NUM_FTMR_RETRIES] = { .type = NLA_U8 },
[NL80211_PMSR_FTM_REQ_ATTR_REQUEST_LCI] = { .type = NLA_FLAG },
[NL80211_PMSR_FTM_REQ_ATTR_REQUEST_CIVICLOC] = { .type = NLA_FLAG },
@@ -555,7 +555,7 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
},
[NL80211_ATTR_TIMEOUT] = NLA_POLICY_MIN(NLA_U32, 1),
[NL80211_ATTR_PEER_MEASUREMENTS] =
- NLA_POLICY_NESTED(NL80211_PMSR_FTM_REQ_ATTR_MAX,
+ NLA_POLICY_NESTED(NL80211_PMSR_ATTR_MAX,
nl80211_pmsr_attr_policy),
};
diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c
index de9286703280..0216ab555249 100644
--- a/net/wireless/pmsr.c
+++ b/net/wireless/pmsr.c
@@ -256,8 +256,7 @@ int nl80211_pmsr_start(struct sk_buff *skb, struct genl_info *info)
if (err)
goto out_err;
} else {
- memcpy(req->mac_addr, nla_data(info->attrs[NL80211_ATTR_MAC]),
- ETH_ALEN);
+ memcpy(req->mac_addr, wdev_address(wdev), ETH_ALEN);
memset(req->mac_addr_mask, 0xff, ETH_ALEN);
}
@@ -272,6 +271,7 @@ int nl80211_pmsr_start(struct sk_buff *skb, struct genl_info *info)
req->n_peers = count;
req->cookie = cfg80211_assign_cookie(rdev);
+ req->nl_portid = info->snd_portid;
err = rdev_start_pmsr(rdev, wdev, req);
if (err)
@@ -530,14 +530,14 @@ free:
}
EXPORT_SYMBOL_GPL(cfg80211_pmsr_report);
-void cfg80211_pmsr_free_wk(struct work_struct *work)
+static void cfg80211_pmsr_process_abort(struct wireless_dev *wdev)
{
- struct wireless_dev *wdev = container_of(work, struct wireless_dev,
- pmsr_free_wk);
struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
struct cfg80211_pmsr_request *req, *tmp;
LIST_HEAD(free_list);
+ lockdep_assert_held(&wdev->mtx);
+
spin_lock_bh(&wdev->pmsr_lock);
list_for_each_entry_safe(req, tmp, &wdev->pmsr_list, list) {
if (req->nl_portid)
@@ -547,14 +547,22 @@ void cfg80211_pmsr_free_wk(struct work_struct *work)
spin_unlock_bh(&wdev->pmsr_lock);
list_for_each_entry_safe(req, tmp, &free_list, list) {
- wdev_lock(wdev);
rdev_abort_pmsr(rdev, wdev, req);
- wdev_unlock(wdev);
kfree(req);
}
}
+void cfg80211_pmsr_free_wk(struct work_struct *work)
+{
+ struct wireless_dev *wdev = container_of(work, struct wireless_dev,
+ pmsr_free_wk);
+
+ wdev_lock(wdev);
+ cfg80211_pmsr_process_abort(wdev);
+ wdev_unlock(wdev);
+}
+
void cfg80211_pmsr_wdev_down(struct wireless_dev *wdev)
{
struct cfg80211_pmsr_request *req;
@@ -568,8 +576,8 @@ void cfg80211_pmsr_wdev_down(struct wireless_dev *wdev)
spin_unlock_bh(&wdev->pmsr_lock);
if (found)
- schedule_work(&wdev->pmsr_free_wk);
- flush_work(&wdev->pmsr_free_wk);
+ cfg80211_pmsr_process_abort(wdev);
+
WARN_ON(!list_empty(&wdev->pmsr_list));
}
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index ecfb1a06dbb2..dd58b9909ac9 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -1024,8 +1024,13 @@ static void regdb_fw_cb(const struct firmware *fw, void *context)
}
rtnl_lock();
- if (WARN_ON(regdb && !IS_ERR(regdb))) {
- /* just restore and free new db */
+ if (regdb && !IS_ERR(regdb)) {
+ /* negative case - a bug
+ * positive case - can happen due to race in case of multiple cb's in
+ * queue, due to usage of asynchronous callback
+ *
+ * Either case, just restore and free new db.
+ */
} else if (set_error) {
regdb = ERR_PTR(set_error);
} else if (fw) {
@@ -1255,7 +1260,7 @@ static bool is_valid_rd(const struct ieee80211_regdomain *rd)
* definitions (the "2.4 GHz band", the "5 GHz band" and the "60GHz band"),
* however it is safe for now to assume that a frequency rule should not be
* part of a frequency's band if the start freq or end freq are off by more
- * than 2 GHz for the 2.4 and 5 GHz bands, and by more than 10 GHz for the
+ * than 2 GHz for the 2.4 and 5 GHz bands, and by more than 20 GHz for the
* 60 GHz band.
* This resolution can be lowered and should be considered as we add
* regulatory rule support for other "bands".
@@ -1270,7 +1275,7 @@ static bool freq_in_rule_band(const struct ieee80211_freq_range *freq_range,
* with the Channel starting frequency above 45 GHz.
*/
u32 limit = freq_khz > 45 * ONE_GHZ_IN_KHZ ?
- 10 * ONE_GHZ_IN_KHZ : 2 * ONE_GHZ_IN_KHZ;
+ 20 * ONE_GHZ_IN_KHZ : 2 * ONE_GHZ_IN_KHZ;
if (abs(freq_khz - freq_range->start_freq_khz) <= limit)
return true;
if (abs(freq_khz - freq_range->end_freq_khz) <= limit)
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index f741d8376a46..7d34cb884840 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -667,7 +667,7 @@ static void disconnect_work(struct work_struct *work)
rtnl_unlock();
}
-static DECLARE_WORK(cfg80211_disconnect_work, disconnect_work);
+DECLARE_WORK(cfg80211_disconnect_work, disconnect_work);
/*
diff --git a/net/wireless/util.c b/net/wireless/util.c
index cd48cdd582c0..ec30e3732c7b 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -5,7 +5,7 @@
* Copyright 2007-2009 Johannes Berg <johannes@sipsolutions.net>
* Copyright 2013-2014 Intel Mobile Communications GmbH
* Copyright 2017 Intel Deutschland GmbH
- * Copyright (C) 2018 Intel Corporation
+ * Copyright (C) 2018-2019 Intel Corporation
*/
#include <linux/export.h>
#include <linux/bitops.h>
@@ -19,6 +19,7 @@
#include <linux/mpls.h>
#include <linux/gcd.h>
#include <linux/bitfield.h>
+#include <linux/nospec.h>
#include "core.h"
#include "rdev-ops.h"
@@ -715,20 +716,25 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb,
{
unsigned int dscp;
unsigned char vlan_priority;
+ unsigned int ret;
/* skb->priority values from 256->263 are magic values to
* directly indicate a specific 802.1d priority. This is used
* to allow 802.1d priority to be passed directly in from VLAN
* tags, etc.
*/
- if (skb->priority >= 256 && skb->priority <= 263)
- return skb->priority - 256;
+ if (skb->priority >= 256 && skb->priority <= 263) {
+ ret = skb->priority - 256;
+ goto out;
+ }
if (skb_vlan_tag_present(skb)) {
vlan_priority = (skb_vlan_tag_get(skb) & VLAN_PRIO_MASK)
>> VLAN_PRIO_SHIFT;
- if (vlan_priority > 0)
- return vlan_priority;
+ if (vlan_priority > 0) {
+ ret = vlan_priority;
+ goto out;
+ }
}
switch (skb->protocol) {
@@ -747,8 +753,9 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb,
if (!mpls)
return 0;
- return (ntohl(mpls->entry) & MPLS_LS_TC_MASK)
+ ret = (ntohl(mpls->entry) & MPLS_LS_TC_MASK)
>> MPLS_LS_TC_SHIFT;
+ goto out;
}
case htons(ETH_P_80221):
/* 802.21 is always network control traffic */
@@ -761,18 +768,24 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb,
unsigned int i, tmp_dscp = dscp >> 2;
for (i = 0; i < qos_map->num_des; i++) {
- if (tmp_dscp == qos_map->dscp_exception[i].dscp)
- return qos_map->dscp_exception[i].up;
+ if (tmp_dscp == qos_map->dscp_exception[i].dscp) {
+ ret = qos_map->dscp_exception[i].up;
+ goto out;
+ }
}
for (i = 0; i < 8; i++) {
if (tmp_dscp >= qos_map->up[i].low &&
- tmp_dscp <= qos_map->up[i].high)
- return i;
+ tmp_dscp <= qos_map->up[i].high) {
+ ret = i;
+ goto out;
+ }
}
}
- return dscp >> 5;
+ ret = dscp >> 5;
+out:
+ return array_index_nospec(ret, IEEE80211_NUM_TIDS);
}
EXPORT_SYMBOL(cfg80211_classify8021d);
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 5121729b8b63..eff31348e20b 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -352,17 +352,15 @@ static unsigned int x25_new_lci(struct x25_neigh *nb)
unsigned int lci = 1;
struct sock *sk;
- read_lock_bh(&x25_list_lock);
-
- while ((sk = __x25_find_socket(lci, nb)) != NULL) {
+ while ((sk = x25_find_socket(lci, nb)) != NULL) {
sock_put(sk);
if (++lci == 4096) {
lci = 0;
break;
}
+ cond_resched();
}
- read_unlock_bh(&x25_list_lock);
return lci;
}
@@ -681,8 +679,7 @@ static int x25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
struct sockaddr_x25 *addr = (struct sockaddr_x25 *)uaddr;
int len, i, rc = 0;
- if (!sock_flag(sk, SOCK_ZAPPED) ||
- addr_len != sizeof(struct sockaddr_x25) ||
+ if (addr_len != sizeof(struct sockaddr_x25) ||
addr->sx25_family != AF_X25) {
rc = -EINVAL;
goto out;
@@ -701,9 +698,13 @@ static int x25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
}
lock_sock(sk);
- x25_sk(sk)->source_addr = addr->sx25_addr;
- x25_insert_socket(sk);
- sock_reset_flag(sk, SOCK_ZAPPED);
+ if (sock_flag(sk, SOCK_ZAPPED)) {
+ x25_sk(sk)->source_addr = addr->sx25_addr;
+ x25_insert_socket(sk);
+ sock_reset_flag(sk, SOCK_ZAPPED);
+ } else {
+ rc = -EINVAL;
+ }
release_sock(sk);
SOCK_DEBUG(sk, "x25_bind: socket is bound\n");
out:
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index d4de871e7d4d..37e1fe180769 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -125,9 +125,10 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
return 0;
err_unreg_umem:
- xdp_clear_umem_at_qid(dev, queue_id);
if (!force_zc)
err = 0; /* fallback to copy mode */
+ if (err)
+ xdp_clear_umem_at_qid(dev, queue_id);
out_rtnl_unlock:
rtnl_unlock();
return err;
@@ -259,10 +260,10 @@ static int xdp_umem_pin_pages(struct xdp_umem *umem)
if (!umem->pgs)
return -ENOMEM;
- down_write(&current->mm->mmap_sem);
- npgs = get_user_pages(umem->address, umem->npgs,
- gup_flags, &umem->pgs[0], NULL);
- up_write(&current->mm->mmap_sem);
+ down_read(&current->mm->mmap_sem);
+ npgs = get_user_pages_longterm(umem->address, umem->npgs,
+ gup_flags, &umem->pgs[0], NULL);
+ up_read(&current->mm->mmap_sem);
if (npgs != umem->npgs) {
if (npgs >= 0) {
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index a03268454a27..85e4fe4f18cc 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -366,7 +366,6 @@ static int xsk_release(struct socket *sock)
xskq_destroy(xs->rx);
xskq_destroy(xs->tx);
- xdp_put_umem(xs->umem);
sock_orphan(sk);
sock->sk = NULL;
@@ -669,6 +668,8 @@ static int xsk_mmap(struct file *file, struct socket *sock,
if (!umem)
return -EINVAL;
+ /* Matches the smp_wmb() in XDP_UMEM_REG */
+ smp_rmb();
if (offset == XDP_UMEM_PGOFF_FILL_RING)
q = READ_ONCE(umem->fq);
else if (offset == XDP_UMEM_PGOFF_COMPLETION_RING)
@@ -678,6 +679,8 @@ static int xsk_mmap(struct file *file, struct socket *sock,
if (!q)
return -EINVAL;
+ /* Matches the smp_wmb() in xsk_init_queue */
+ smp_rmb();
qpg = virt_to_head_page(q->ring);
if (size > (PAGE_SIZE << compound_order(qpg)))
return -EINVAL;
@@ -714,6 +717,18 @@ static const struct proto_ops xsk_proto_ops = {
.sendpage = sock_no_sendpage,
};
+static void xsk_destruct(struct sock *sk)
+{
+ struct xdp_sock *xs = xdp_sk(sk);
+
+ if (!sock_flag(sk, SOCK_DEAD))
+ return;
+
+ xdp_put_umem(xs->umem);
+
+ sk_refcnt_debug_dec(sk);
+}
+
static int xsk_create(struct net *net, struct socket *sock, int protocol,
int kern)
{
@@ -740,6 +755,9 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol,
sk->sk_family = PF_XDP;
+ sk->sk_destruct = xsk_destruct;
+ sk_refcnt_debug_inc(sk);
+
sock_set_flag(sk, SOCK_RCU_FREE);
xs = xdp_sk(sk);
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index 6be8c7df15bb..dbb3c1945b5c 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -76,10 +76,10 @@ static struct xfrm_if *xfrmi_decode_session(struct sk_buff *skb)
int ifindex;
struct xfrm_if *xi;
- if (!skb->dev)
+ if (!secpath_exists(skb) || !skb->dev)
return NULL;
- xfrmn = net_generic(dev_net(skb->dev), xfrmi_net_id);
+ xfrmn = net_generic(xs_net(xfrm_input_state(skb)), xfrmi_net_id);
ifindex = skb->dev->ifindex;
for_each_xfrmi_rcu(xfrmn->xfrmi[0], xi) {
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 934492bad8e0..8d1a898d0ba5 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -680,16 +680,6 @@ static void xfrm_hash_resize(struct work_struct *work)
mutex_unlock(&hash_resize_mutex);
}
-static void xfrm_hash_reset_inexact_table(struct net *net)
-{
- struct xfrm_pol_inexact_bin *b;
-
- lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
-
- list_for_each_entry(b, &net->xfrm.inexact_bins, inexact_bins)
- INIT_HLIST_HEAD(&b->hhead);
-}
-
/* Make sure *pol can be inserted into fastbin.
* Useful to check that later insert requests will be sucessful
* (provided xfrm_policy_lock is held throughout).
@@ -833,13 +823,13 @@ static void xfrm_policy_inexact_list_reinsert(struct net *net,
u16 family)
{
unsigned int matched_s, matched_d;
- struct hlist_node *newpos = NULL;
struct xfrm_policy *policy, *p;
matched_s = 0;
matched_d = 0;
list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) {
+ struct hlist_node *newpos = NULL;
bool matches_s, matches_d;
if (!policy->bydst_reinsert)
@@ -849,16 +839,19 @@ static void xfrm_policy_inexact_list_reinsert(struct net *net,
policy->bydst_reinsert = false;
hlist_for_each_entry(p, &n->hhead, bydst) {
- if (policy->priority >= p->priority)
+ if (policy->priority > p->priority)
+ newpos = &p->bydst;
+ else if (policy->priority == p->priority &&
+ policy->pos > p->pos)
newpos = &p->bydst;
else
break;
}
if (newpos)
- hlist_add_behind(&policy->bydst, newpos);
+ hlist_add_behind_rcu(&policy->bydst, newpos);
else
- hlist_add_head(&policy->bydst, &n->hhead);
+ hlist_add_head_rcu(&policy->bydst, &n->hhead);
/* paranoia checks follow.
* Check that the reinserted policy matches at least
@@ -893,12 +886,13 @@ static void xfrm_policy_inexact_node_reinsert(struct net *net,
struct rb_root *new,
u16 family)
{
- struct rb_node **p, *parent = NULL;
struct xfrm_pol_inexact_node *node;
+ struct rb_node **p, *parent;
/* we should not have another subtree here */
WARN_ON_ONCE(!RB_EMPTY_ROOT(&n->root));
-
+restart:
+ parent = NULL;
p = &new->rb_node;
while (*p) {
u8 prefixlen;
@@ -918,12 +912,11 @@ static void xfrm_policy_inexact_node_reinsert(struct net *net,
} else {
struct xfrm_policy *tmp;
- hlist_for_each_entry(tmp, &node->hhead, bydst)
- tmp->bydst_reinsert = true;
- hlist_for_each_entry(tmp, &n->hhead, bydst)
+ hlist_for_each_entry(tmp, &n->hhead, bydst) {
tmp->bydst_reinsert = true;
+ hlist_del_rcu(&tmp->bydst);
+ }
- INIT_HLIST_HEAD(&node->hhead);
xfrm_policy_inexact_list_reinsert(net, node, family);
if (node->prefixlen == n->prefixlen) {
@@ -935,8 +928,7 @@ static void xfrm_policy_inexact_node_reinsert(struct net *net,
kfree_rcu(n, rcu);
n = node;
n->prefixlen = prefixlen;
- *p = new->rb_node;
- parent = NULL;
+ goto restart;
}
}
@@ -965,12 +957,11 @@ static void xfrm_policy_inexact_node_merge(struct net *net,
family);
}
- hlist_for_each_entry(tmp, &v->hhead, bydst)
- tmp->bydst_reinsert = true;
- hlist_for_each_entry(tmp, &n->hhead, bydst)
+ hlist_for_each_entry(tmp, &v->hhead, bydst) {
tmp->bydst_reinsert = true;
+ hlist_del_rcu(&tmp->bydst);
+ }
- INIT_HLIST_HEAD(&n->hhead);
xfrm_policy_inexact_list_reinsert(net, n, family);
}
@@ -1235,6 +1226,7 @@ static void xfrm_hash_rebuild(struct work_struct *work)
} while (read_seqretry(&net->xfrm.policy_hthresh.lock, seq));
spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+ write_seqcount_begin(&xfrm_policy_hash_generation);
/* make sure that we can insert the indirect policies again before
* we start with destructive action.
@@ -1278,10 +1270,14 @@ static void xfrm_hash_rebuild(struct work_struct *work)
}
/* reset the bydst and inexact table in all directions */
- xfrm_hash_reset_inexact_table(net);
-
for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
- INIT_HLIST_HEAD(&net->xfrm.policy_inexact[dir]);
+ struct hlist_node *n;
+
+ hlist_for_each_entry_safe(policy, n,
+ &net->xfrm.policy_inexact[dir],
+ bydst_inexact_list)
+ hlist_del_init(&policy->bydst_inexact_list);
+
hmask = net->xfrm.policy_bydst[dir].hmask;
odst = net->xfrm.policy_bydst[dir].table;
for (i = hmask; i >= 0; i--)
@@ -1313,6 +1309,9 @@ static void xfrm_hash_rebuild(struct work_struct *work)
newpos = NULL;
chain = policy_hash_bysel(net, &policy->selector,
policy->family, dir);
+
+ hlist_del_rcu(&policy->bydst);
+
if (!chain) {
void *p = xfrm_policy_inexact_insert(policy, dir, 0);
@@ -1334,6 +1333,7 @@ static void xfrm_hash_rebuild(struct work_struct *work)
out_unlock:
__xfrm_policy_inexact_flush(net);
+ write_seqcount_end(&xfrm_policy_hash_generation);
spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
mutex_unlock(&hash_resize_mutex);
@@ -2600,7 +2600,10 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
dst_copy_metrics(dst1, dst);
if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) {
- __u32 mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]);
+ __u32 mark = 0;
+
+ if (xfrm[i]->props.smark.v || xfrm[i]->props.smark.m)
+ mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]);
family = xfrm[i]->props.family;
dst = xfrm_dst_lookup(xfrm[i], tos, fl->flowi_oif,
@@ -3311,8 +3314,10 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
if (ifcb) {
xi = ifcb->decode_session(skb);
- if (xi)
+ if (xi) {
if_id = xi->p.if_id;
+ net = xi->net;
+ }
}
rcu_read_unlock();
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 23c92891758a..1bb971f46fc6 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -432,7 +432,7 @@ void xfrm_state_free(struct xfrm_state *x)
}
EXPORT_SYMBOL(xfrm_state_free);
-static void xfrm_state_gc_destroy(struct xfrm_state *x)
+static void ___xfrm_state_destroy(struct xfrm_state *x)
{
tasklet_hrtimer_cancel(&x->mtimer);
del_timer_sync(&x->rtimer);
@@ -474,7 +474,7 @@ static void xfrm_state_gc_task(struct work_struct *work)
synchronize_rcu();
hlist_for_each_entry_safe(x, tmp, &gc_list, gclist)
- xfrm_state_gc_destroy(x);
+ ___xfrm_state_destroy(x);
}
static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
@@ -598,14 +598,19 @@ struct xfrm_state *xfrm_state_alloc(struct net *net)
}
EXPORT_SYMBOL(xfrm_state_alloc);
-void __xfrm_state_destroy(struct xfrm_state *x)
+void __xfrm_state_destroy(struct xfrm_state *x, bool sync)
{
WARN_ON(x->km.state != XFRM_STATE_DEAD);
- spin_lock_bh(&xfrm_state_gc_lock);
- hlist_add_head(&x->gclist, &xfrm_state_gc_list);
- spin_unlock_bh(&xfrm_state_gc_lock);
- schedule_work(&xfrm_state_gc_work);
+ if (sync) {
+ synchronize_rcu();
+ ___xfrm_state_destroy(x);
+ } else {
+ spin_lock_bh(&xfrm_state_gc_lock);
+ hlist_add_head(&x->gclist, &xfrm_state_gc_list);
+ spin_unlock_bh(&xfrm_state_gc_lock);
+ schedule_work(&xfrm_state_gc_work);
+ }
}
EXPORT_SYMBOL(__xfrm_state_destroy);
@@ -708,7 +713,7 @@ xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool
}
#endif
-int xfrm_state_flush(struct net *net, u8 proto, bool task_valid)
+int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync)
{
int i, err = 0, cnt = 0;
@@ -730,7 +735,10 @@ restart:
err = xfrm_state_delete(x);
xfrm_audit_state_delete(x, err ? 0 : 1,
task_valid);
- xfrm_state_put(x);
+ if (sync)
+ xfrm_state_put_sync(x);
+ else
+ xfrm_state_put(x);
if (!err)
cnt++;
@@ -2215,7 +2223,7 @@ void xfrm_state_delete_tunnel(struct xfrm_state *x)
if (atomic_read(&t->tunnel_users) == 2)
xfrm_state_delete(t);
atomic_dec(&t->tunnel_users);
- xfrm_state_put(t);
+ xfrm_state_put_sync(t);
x->tunnel = NULL;
}
}
@@ -2375,8 +2383,8 @@ void xfrm_state_fini(struct net *net)
unsigned int sz;
flush_work(&net->xfrm.state_hash_work);
- xfrm_state_flush(net, IPSEC_PROTO_ANY, false);
flush_work(&xfrm_state_gc_work);
+ xfrm_state_flush(net, IPSEC_PROTO_ANY, false, true);
WARN_ON(!list_empty(&net->xfrm.state_all));
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 277c1c46fe94..a131f9ff979e 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -1488,10 +1488,15 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family)
if (!ut[i].family)
ut[i].family = family;
- if ((ut[i].mode == XFRM_MODE_TRANSPORT) &&
- (ut[i].family != prev_family))
- return -EINVAL;
-
+ switch (ut[i].mode) {
+ case XFRM_MODE_TUNNEL:
+ case XFRM_MODE_BEET:
+ break;
+ default:
+ if (ut[i].family != prev_family)
+ return -EINVAL;
+ break;
+ }
if (ut[i].mode >= XFRM_MODE_MAX)
return -EINVAL;
@@ -1927,7 +1932,7 @@ static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh,
struct xfrm_usersa_flush *p = nlmsg_data(nlh);
int err;
- err = xfrm_state_flush(net, p->proto, true);
+ err = xfrm_state_flush(net, p->proto, true, false);
if (err) {
if (err == -ESRCH) /* empty table */
return 0;