summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2019-10-19 17:09:11 -0400
committerLinus Torvalds <torvalds@linux-foundation.org>2019-10-19 17:09:11 -0400
commit531e93d11470aa2e14e6a3febef50d9bc7bab7a1 (patch)
tree2ce0a1cb919f60309e605520a6736206fae0b09e /net
parent998d75510e373aab5644d777d3b058312d550159 (diff)
parent2a06b8982f8f2f40d03a3daf634676386bd84dbc (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from David Miller: "I was battling a cold after some recent trips, so quite a bit piled up meanwhile, sorry about that. Highlights: 1) Fix fd leak in various bpf selftests, from Brian Vazquez. 2) Fix crash in xsk when device doesn't support some methods, from Magnus Karlsson. 3) Fix various leaks and use-after-free in rxrpc, from David Howells. 4) Fix several SKB leaks due to confusion of who owns an SKB and who should release it in the llc code. From Eric Biggers. 5) Kill a bunc of KCSAN warnings in TCP, from Eric Dumazet. 6) Jumbo packets don't work after resume on r8169, as the BIOS resets the chip into non-jumbo mode during suspend. From Heiner Kallweit. 7) Corrupt L2 header during MPLS push, from Davide Caratti. 8) Prevent possible infinite loop in tc_ctl_action, from Eric Dumazet. 9) Get register bits right in bcmgenet driver, based upon chip version. From Florian Fainelli. 10) Fix mutex problems in microchip DSA driver, from Marek Vasut. 11) Cure race between route lookup and invalidation in ipv4, from Wei Wang. 12) Fix performance regression due to false sharing in 'net' structure, from Eric Dumazet" * git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (145 commits) net: reorder 'struct net' fields to avoid false sharing net: dsa: fix switch tree list net: ethernet: dwmac-sun8i: show message only when switching to promisc net: aquantia: add an error handling in aq_nic_set_multicast_list net: netem: correct the parent's backlog when corrupted packet was dropped net: netem: fix error path for corrupted GSO frames macb: propagate errors when getting optional clocks xen/netback: fix error path of xenvif_connect_data() net: hns3: fix mis-counting IRQ vector numbers issue net: usb: lan78xx: Connect PHY before registering MAC vsock/virtio: discard packets if credit is not respected vsock/virtio: send a credit update when buffer size is changed mlxsw: spectrum_trap: Push Ethernet header before reporting trap net: ensure correct skb->tstamp in various fragmenters net: bcmgenet: reset 40nm EPHY on energy detect net: bcmgenet: soft reset 40nm EPHYs before MAC init net: phy: bcm7xxx: define soft_reset for 40nm EPHY net: bcmgenet: don't set phydev->link from MAC net: Update address for MediaTek ethernet driver in MAINTAINERS ipv4: fix race condition between route lookup and invalidation ...
Diffstat (limited to 'net')
-rw-r--r--net/bridge/netfilter/nf_conntrack_bridge.c3
-rw-r--r--net/core/datagram.c2
-rw-r--r--net/core/filter.c8
-rw-r--r--net/core/net_namespace.c17
-rw-r--r--net/core/request_sock.c2
-rw-r--r--net/core/skbuff.c23
-rw-r--r--net/core/sock.c32
-rw-r--r--net/dsa/dsa2.c2
-rw-r--r--net/ipv4/inet_connection_sock.c6
-rw-r--r--net/ipv4/inet_diag.c2
-rw-r--r--net/ipv4/ip_output.c3
-rw-r--r--net/ipv4/route.c11
-rw-r--r--net/ipv4/tcp.c75
-rw-r--r--net/ipv4/tcp_diag.c5
-rw-r--r--net/ipv4/tcp_fastopen.c2
-rw-r--r--net/ipv4/tcp_input.c37
-rw-r--r--net/ipv4/tcp_ipv4.c30
-rw-r--r--net/ipv4/tcp_minisocks.c17
-rw-r--r--net/ipv4/tcp_output.c32
-rw-r--r--net/ipv4/tcp_timer.c11
-rw-r--r--net/ipv6/ip6_gre.c1
-rw-r--r--net/ipv6/ip6_output.c3
-rw-r--r--net/ipv6/netfilter.c3
-rw-r--r--net/ipv6/tcp_ipv6.c18
-rw-r--r--net/llc/af_llc.c34
-rw-r--r--net/llc/llc_c_ac.c8
-rw-r--r--net/llc/llc_conn.c69
-rw-r--r--net/llc/llc_if.c12
-rw-r--r--net/llc/llc_s_ac.c12
-rw-r--r--net/llc/llc_sap.c23
-rw-r--r--net/mac80211/mlme.c5
-rw-r--r--net/mac80211/rx.c11
-rw-r--r--net/mac80211/scan.c30
-rw-r--r--net/netfilter/nf_conntrack_core.c4
-rw-r--r--net/openvswitch/actions.c5
-rw-r--r--net/rxrpc/ar-internal.h1
-rw-r--r--net/rxrpc/call_accept.c5
-rw-r--r--net/rxrpc/call_object.c34
-rw-r--r--net/rxrpc/conn_client.c9
-rw-r--r--net/rxrpc/conn_object.c13
-rw-r--r--net/rxrpc/conn_service.c2
-rw-r--r--net/rxrpc/peer_event.c11
-rw-r--r--net/rxrpc/peer_object.c16
-rw-r--r--net/rxrpc/recvmsg.c6
-rw-r--r--net/rxrpc/sendmsg.c3
-rw-r--r--net/sched/act_api.c23
-rw-r--r--net/sched/act_mirred.c6
-rw-r--r--net/sched/act_mpls.c12
-rw-r--r--net/sched/cls_api.c36
-rw-r--r--net/sched/em_meta.c4
-rw-r--r--net/sched/sch_api.c3
-rw-r--r--net/sched/sch_etf.c2
-rw-r--r--net/sched/sch_netem.c11
-rw-r--r--net/sched/sch_taprio.c4
-rw-r--r--net/sctp/diag.c2
-rw-r--r--net/sctp/input.c16
-rw-r--r--net/sctp/socket.c4
-rw-r--r--net/smc/smc_core.c5
-rw-r--r--net/smc/smc_rx.c29
-rw-r--r--net/tipc/socket.c8
-rw-r--r--net/vmw_vsock/virtio_transport_common.c17
-rw-r--r--net/wireless/nl80211.c2
-rw-r--r--net/wireless/reg.c1
-rw-r--r--net/wireless/reg.h8
-rw-r--r--net/wireless/scan.c23
-rw-r--r--net/wireless/wext-sme.c8
-rw-r--r--net/x25/x25_dev.c2
-rw-r--r--net/xdp/xsk.c42
68 files changed, 564 insertions, 362 deletions
diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c
index 8842798c29e6..506d6141e44e 100644
--- a/net/bridge/netfilter/nf_conntrack_bridge.c
+++ b/net/bridge/netfilter/nf_conntrack_bridge.c
@@ -33,6 +33,7 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk,
{
int frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size;
unsigned int hlen, ll_rs, mtu;
+ ktime_t tstamp = skb->tstamp;
struct ip_frag_state state;
struct iphdr *iph;
int err;
@@ -80,6 +81,7 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk,
if (iter.frag)
ip_fraglist_prepare(skb, &iter);
+ skb->tstamp = tstamp;
err = output(net, sk, data, skb);
if (err || !iter.frag)
break;
@@ -104,6 +106,7 @@ slow_path:
goto blackhole;
}
+ skb2->tstamp = tstamp;
err = output(net, sk, data, skb2);
if (err)
goto blackhole;
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 4cc8dc5db2b7..c210fc116103 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -640,7 +640,7 @@ int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb,
skb->len += copied;
skb->truesize += truesize;
if (sk && sk->sk_type == SOCK_STREAM) {
- sk->sk_wmem_queued += truesize;
+ sk_wmem_queued_add(sk, truesize);
sk_mem_charge(sk, truesize);
} else {
refcount_add(truesize, &skb->sk->sk_wmem_alloc);
diff --git a/net/core/filter.c b/net/core/filter.c
index ed6563622ce3..3fed5755494b 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4252,12 +4252,14 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
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);
+ WRITE_ONCE(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);
+ WRITE_ONCE(sk->sk_sndbuf,
+ max_t(int, val * 2, SOCK_MIN_SNDBUF));
break;
case SO_MAX_PACING_RATE: /* 32bit version */
if (val != ~0U)
@@ -4274,7 +4276,7 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
case SO_RCVLOWAT:
if (val < 0)
val = INT_MAX;
- sk->sk_rcvlowat = val ? : 1;
+ WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
break;
case SO_MARK:
if (sk->sk_mark != val) {
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index a0e0d298c991..6d3e4821b02d 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -245,7 +245,8 @@ static int __peernet2id(struct net *net, struct net *peer)
return __peernet2id_alloc(net, peer, &no);
}
-static void rtnl_net_notifyid(struct net *net, int cmd, int id);
+static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid,
+ struct nlmsghdr *nlh);
/* This function returns the id of a peer netns. If no id is assigned, one will
* be allocated and returned.
*/
@@ -268,7 +269,7 @@ int peernet2id_alloc(struct net *net, struct net *peer)
id = __peernet2id_alloc(net, peer, &alloc);
spin_unlock_bh(&net->nsid_lock);
if (alloc && id >= 0)
- rtnl_net_notifyid(net, RTM_NEWNSID, id);
+ rtnl_net_notifyid(net, RTM_NEWNSID, id, 0, NULL);
if (alive)
put_net(peer);
return id;
@@ -532,7 +533,7 @@ static void unhash_nsid(struct net *net, struct net *last)
idr_remove(&tmp->netns_ids, id);
spin_unlock_bh(&tmp->nsid_lock);
if (id >= 0)
- rtnl_net_notifyid(tmp, RTM_DELNSID, id);
+ rtnl_net_notifyid(tmp, RTM_DELNSID, id, 0, NULL);
if (tmp == last)
break;
}
@@ -764,7 +765,8 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh,
err = alloc_netid(net, peer, nsid);
spin_unlock_bh(&net->nsid_lock);
if (err >= 0) {
- rtnl_net_notifyid(net, RTM_NEWNSID, err);
+ rtnl_net_notifyid(net, RTM_NEWNSID, err, NETLINK_CB(skb).portid,
+ nlh);
err = 0;
} else if (err == -ENOSPC && nsid >= 0) {
err = -EEXIST;
@@ -1051,9 +1053,12 @@ end:
return err < 0 ? err : skb->len;
}
-static void rtnl_net_notifyid(struct net *net, int cmd, int id)
+static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid,
+ struct nlmsghdr *nlh)
{
struct net_fill_args fillargs = {
+ .portid = portid,
+ .seq = nlh ? nlh->nlmsg_seq : 0,
.cmd = cmd,
.nsid = id,
};
@@ -1068,7 +1073,7 @@ static void rtnl_net_notifyid(struct net *net, int cmd, int id)
if (err < 0)
goto err_out;
- rtnl_notify(msg, net, 0, RTNLGRP_NSID, NULL, 0);
+ rtnl_notify(msg, net, portid, RTNLGRP_NSID, nlh, 0);
return;
err_out:
diff --git a/net/core/request_sock.c b/net/core/request_sock.c
index c9bb00008528..f35c2e998406 100644
--- a/net/core/request_sock.c
+++ b/net/core/request_sock.c
@@ -96,7 +96,7 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req,
fastopenq = &inet_csk(lsk)->icsk_accept_queue.fastopenq;
- tcp_sk(sk)->fastopen_rsk = NULL;
+ RCU_INIT_POINTER(tcp_sk(sk)->fastopen_rsk, NULL);
spin_lock_bh(&fastopenq->lock);
fastopenq->qlen--;
tcp_rsk(req)->tfo_listener = false;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 529133611ea2..867e61df00db 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4415,7 +4415,7 @@ static void skb_set_err_queue(struct sk_buff *skb)
int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
{
if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
- (unsigned int)sk->sk_rcvbuf)
+ (unsigned int)READ_ONCE(sk->sk_rcvbuf))
return -ENOMEM;
skb_orphan(skb);
@@ -5477,12 +5477,14 @@ static void skb_mod_eth_type(struct sk_buff *skb, struct ethhdr *hdr,
* @skb: buffer
* @mpls_lse: MPLS label stack entry to push
* @mpls_proto: ethertype of the new MPLS header (expects 0x8847 or 0x8848)
+ * @mac_len: length of the MAC header
*
* Expects skb->data at mac header.
*
* Returns 0 on success, -errno otherwise.
*/
-int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto)
+int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto,
+ int mac_len)
{
struct mpls_shim_hdr *lse;
int err;
@@ -5499,15 +5501,15 @@ int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto)
return err;
if (!skb->inner_protocol) {
- skb_set_inner_network_header(skb, skb->mac_len);
+ skb_set_inner_network_header(skb, mac_len);
skb_set_inner_protocol(skb, skb->protocol);
}
skb_push(skb, MPLS_HLEN);
memmove(skb_mac_header(skb) - MPLS_HLEN, skb_mac_header(skb),
- skb->mac_len);
+ mac_len);
skb_reset_mac_header(skb);
- skb_set_network_header(skb, skb->mac_len);
+ skb_set_network_header(skb, mac_len);
lse = mpls_hdr(skb);
lse->label_stack_entry = mpls_lse;
@@ -5526,29 +5528,30 @@ EXPORT_SYMBOL_GPL(skb_mpls_push);
*
* @skb: buffer
* @next_proto: ethertype of header after popped MPLS header
+ * @mac_len: length of the MAC header
*
* Expects skb->data at mac header.
*
* Returns 0 on success, -errno otherwise.
*/
-int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto)
+int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len)
{
int err;
if (unlikely(!eth_p_mpls(skb->protocol)))
- return -EINVAL;
+ return 0;
- err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
+ err = skb_ensure_writable(skb, mac_len + MPLS_HLEN);
if (unlikely(err))
return err;
skb_postpull_rcsum(skb, mpls_hdr(skb), MPLS_HLEN);
memmove(skb_mac_header(skb) + MPLS_HLEN, skb_mac_header(skb),
- skb->mac_len);
+ mac_len);
__skb_pull(skb, MPLS_HLEN);
skb_reset_mac_header(skb);
- skb_set_network_header(skb, skb->mac_len);
+ skb_set_network_header(skb, mac_len);
if (skb->dev && skb->dev->type == ARPHRD_ETHER) {
struct ethhdr *hdr;
diff --git a/net/core/sock.c b/net/core/sock.c
index fac2b4d80de5..a515392ba84b 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -522,7 +522,7 @@ int __sk_receive_skb(struct sock *sk, struct sk_buff *skb,
rc = sk_backlog_rcv(sk, skb);
mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_);
- } else if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) {
+ } else if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) {
bh_unlock_sock(sk);
atomic_inc(&sk->sk_drops);
goto discard_and_relse;
@@ -785,7 +785,8 @@ set_sndbuf:
*/
val = min_t(int, val, INT_MAX / 2);
sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
- sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF);
+ WRITE_ONCE(sk->sk_sndbuf,
+ max_t(int, val * 2, SOCK_MIN_SNDBUF));
/* Wake up sending tasks if we upped the value. */
sk->sk_write_space(sk);
break;
@@ -831,7 +832,8 @@ set_rcvbuf:
* returning the value we actually used in getsockopt
* is the most desirable behavior.
*/
- sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF);
+ WRITE_ONCE(sk->sk_rcvbuf,
+ max_t(int, val * 2, SOCK_MIN_RCVBUF));
break;
case SO_RCVBUFFORCE:
@@ -974,7 +976,7 @@ set_rcvbuf:
if (sock->ops->set_rcvlowat)
ret = sock->ops->set_rcvlowat(sk, val);
else
- sk->sk_rcvlowat = val ? : 1;
+ WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
break;
case SO_RCVTIMEO_OLD:
@@ -2088,8 +2090,10 @@ EXPORT_SYMBOL(sock_i_ino);
struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force,
gfp_t priority)
{
- if (force || refcount_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) {
+ if (force ||
+ refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf)) {
struct sk_buff *skb = alloc_skb(size, priority);
+
if (skb) {
skb_set_owner_w(skb, sk);
return skb;
@@ -2190,7 +2194,7 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo)
break;
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
- if (refcount_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf)
+ if (refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf))
break;
if (sk->sk_shutdown & SEND_SHUTDOWN)
break;
@@ -2225,7 +2229,7 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
if (sk->sk_shutdown & SEND_SHUTDOWN)
goto failure;
- if (sk_wmem_alloc_get(sk) < sk->sk_sndbuf)
+ if (sk_wmem_alloc_get(sk) < READ_ONCE(sk->sk_sndbuf))
break;
sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
@@ -2334,8 +2338,8 @@ static void sk_leave_memory_pressure(struct sock *sk)
} else {
unsigned long *memory_pressure = sk->sk_prot->memory_pressure;
- if (memory_pressure && *memory_pressure)
- *memory_pressure = 0;
+ if (memory_pressure && READ_ONCE(*memory_pressure))
+ WRITE_ONCE(*memory_pressure, 0);
}
}
@@ -2806,7 +2810,7 @@ static void sock_def_write_space(struct sock *sk)
/* Do not wake up a writer until he can make "significant"
* progress. --DaveM
*/
- if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) {
+ if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= READ_ONCE(sk->sk_sndbuf)) {
wq = rcu_dereference(sk->sk_wq);
if (skwq_has_sleeper(wq))
wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT |
@@ -3204,13 +3208,13 @@ void sk_get_meminfo(const struct sock *sk, u32 *mem)
memset(mem, 0, sizeof(*mem) * SK_MEMINFO_VARS);
mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk);
- mem[SK_MEMINFO_RCVBUF] = sk->sk_rcvbuf;
+ mem[SK_MEMINFO_RCVBUF] = READ_ONCE(sk->sk_rcvbuf);
mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk);
- mem[SK_MEMINFO_SNDBUF] = sk->sk_sndbuf;
+ mem[SK_MEMINFO_SNDBUF] = READ_ONCE(sk->sk_sndbuf);
mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc;
- mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued;
+ mem[SK_MEMINFO_WMEM_QUEUED] = READ_ONCE(sk->sk_wmem_queued);
mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc);
- mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len;
+ mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len);
mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops);
}
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index 73002022c9d8..716d265ba8ca 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -46,7 +46,7 @@ static struct dsa_switch_tree *dsa_tree_alloc(int index)
dst->index = index;
INIT_LIST_HEAD(&dst->list);
- list_add_tail(&dsa_tree_list, &dst->list);
+ list_add_tail(&dst->list, &dsa_tree_list);
kref_init(&dst->refcount);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index a9183543ca30..eb30fc1770de 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -906,7 +906,7 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req,
percpu_counter_inc(sk->sk_prot->orphan_count);
if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) {
- BUG_ON(tcp_sk(child)->fastopen_rsk != req);
+ BUG_ON(rcu_access_pointer(tcp_sk(child)->fastopen_rsk) != req);
BUG_ON(sk != req->rsk_listener);
/* Paranoid, to prevent race condition if
@@ -915,7 +915,7 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req,
* Also to satisfy an assertion in
* tcp_v4_destroy_sock().
*/
- tcp_sk(child)->fastopen_rsk = NULL;
+ RCU_INIT_POINTER(tcp_sk(child)->fastopen_rsk, NULL);
}
inet_csk_destroy_sock(child);
}
@@ -934,7 +934,7 @@ struct sock *inet_csk_reqsk_queue_add(struct sock *sk,
req->sk = child;
req->dl_next = NULL;
if (queue->rskq_accept_head == NULL)
- queue->rskq_accept_head = req;
+ WRITE_ONCE(queue->rskq_accept_head, req);
else
queue->rskq_accept_tail->dl_next = req;
queue->rskq_accept_tail = req;
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index bbb005eb5218..7dc79b973e6e 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -193,7 +193,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
if (ext & (1 << (INET_DIAG_MEMINFO - 1))) {
struct inet_diag_meminfo minfo = {
.idiag_rmem = sk_rmem_alloc_get(sk),
- .idiag_wmem = sk->sk_wmem_queued,
+ .idiag_wmem = READ_ONCE(sk->sk_wmem_queued),
.idiag_fmem = sk->sk_forward_alloc,
.idiag_tmem = sk_wmem_alloc_get(sk),
};
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 28fca408812c..814b9b8882a0 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -771,6 +771,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
struct rtable *rt = skb_rtable(skb);
unsigned int mtu, hlen, ll_rs;
struct ip_fraglist_iter iter;
+ ktime_t tstamp = skb->tstamp;
struct ip_frag_state state;
int err = 0;
@@ -846,6 +847,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
ip_fraglist_prepare(skb, &iter);
}
+ skb->tstamp = tstamp;
err = output(net, sk, skb);
if (!err)
@@ -900,6 +902,7 @@ slow_path:
/*
* Put this fragment into the sending queue.
*/
+ skb2->tstamp = tstamp;
err = output(net, sk, skb2);
if (err)
goto fail;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 14654876127e..621f83434b24 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1482,7 +1482,7 @@ static bool rt_cache_route(struct fib_nh_common *nhc, struct rtable *rt)
prev = cmpxchg(p, orig, rt);
if (prev == orig) {
if (orig) {
- dst_dev_put(&orig->dst);
+ rt_add_uncached_list(orig);
dst_release(&orig->dst);
}
} else {
@@ -2470,14 +2470,17 @@ struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4,
int orig_oif = fl4->flowi4_oif;
unsigned int flags = 0;
struct rtable *rth;
- int err = -ENETUNREACH;
+ int err;
if (fl4->saddr) {
- rth = ERR_PTR(-EINVAL);
if (ipv4_is_multicast(fl4->saddr) ||
ipv4_is_lbcast(fl4->saddr) ||
- ipv4_is_zeronet(fl4->saddr))
+ ipv4_is_zeronet(fl4->saddr)) {
+ rth = ERR_PTR(-EINVAL);
goto out;
+ }
+
+ rth = ERR_PTR(-ENETUNREACH);
/* I removed check for oif == dev_out->oif here.
It was wrong for two reasons:
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f98a1882e537..42187a3b82f4 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -326,7 +326,7 @@ void tcp_enter_memory_pressure(struct sock *sk)
{
unsigned long val;
- if (tcp_memory_pressure)
+ if (READ_ONCE(tcp_memory_pressure))
return;
val = jiffies;
@@ -341,7 +341,7 @@ void tcp_leave_memory_pressure(struct sock *sk)
{
unsigned long val;
- if (!tcp_memory_pressure)
+ if (!READ_ONCE(tcp_memory_pressure))
return;
val = xchg(&tcp_memory_pressure, 0);
if (val)
@@ -450,8 +450,8 @@ void tcp_init_sock(struct sock *sk)
icsk->icsk_sync_mss = tcp_sync_mss;
- sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1];
- sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1];
+ WRITE_ONCE(sk->sk_sndbuf, sock_net(sk)->ipv4.sysctl_tcp_wmem[1]);
+ WRITE_ONCE(sk->sk_rcvbuf, sock_net(sk)->ipv4.sysctl_tcp_rmem[1]);
sk_sockets_allocated_inc(sk);
sk->sk_route_forced_caps = NETIF_F_GSO;
@@ -477,7 +477,7 @@ static void tcp_tx_timestamp(struct sock *sk, u16 tsflags)
static inline bool tcp_stream_is_readable(const struct tcp_sock *tp,
int target, struct sock *sk)
{
- return (tp->rcv_nxt - tp->copied_seq >= target) ||
+ return (READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq) >= target) ||
(sk->sk_prot->stream_memory_read ?
sk->sk_prot->stream_memory_read(sk) : false);
}
@@ -543,10 +543,10 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
/* Connected or passive Fast Open socket? */
if (state != TCP_SYN_SENT &&
- (state != TCP_SYN_RECV || tp->fastopen_rsk)) {
+ (state != TCP_SYN_RECV || rcu_access_pointer(tp->fastopen_rsk))) {
int target = sock_rcvlowat(sk, 0, INT_MAX);
- if (tp->urg_seq == tp->copied_seq &&
+ if (READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq) &&
!sock_flag(sk, SOCK_URGINLINE) &&
tp->urg_data)
target++;
@@ -607,7 +607,8 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
unlock_sock_fast(sk, slow);
break;
case SIOCATMARK:
- answ = tp->urg_data && tp->urg_seq == tp->copied_seq;
+ answ = tp->urg_data &&
+ READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq);
break;
case SIOCOUTQ:
if (sk->sk_state == TCP_LISTEN)
@@ -616,7 +617,7 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))
answ = 0;
else
- answ = tp->write_seq - tp->snd_una;
+ answ = READ_ONCE(tp->write_seq) - tp->snd_una;
break;
case SIOCOUTQNSD:
if (sk->sk_state == TCP_LISTEN)
@@ -625,7 +626,8 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))
answ = 0;
else
- answ = tp->write_seq - tp->snd_nxt;
+ answ = READ_ONCE(tp->write_seq) -
+ READ_ONCE(tp->snd_nxt);
break;
default:
return -ENOIOCTLCMD;
@@ -657,7 +659,7 @@ static void skb_entail(struct sock *sk, struct sk_buff *skb)
tcb->sacked = 0;
__skb_header_release(skb);
tcp_add_write_queue_tail(sk, skb);
- sk->sk_wmem_queued += skb->truesize;
+ sk_wmem_queued_add(sk, skb->truesize);
sk_mem_charge(sk, skb->truesize);
if (tp->nonagle & TCP_NAGLE_PUSH)
tp->nonagle &= ~TCP_NAGLE_PUSH;
@@ -1032,10 +1034,10 @@ new_segment:
skb->len += copy;
skb->data_len += copy;
skb->truesize += copy;
- sk->sk_wmem_queued += copy;
+ sk_wmem_queued_add(sk, copy);
sk_mem_charge(sk, copy);
skb->ip_summed = CHECKSUM_PARTIAL;
- tp->write_seq += copy;
+ WRITE_ONCE(tp->write_seq, tp->write_seq + copy);
TCP_SKB_CB(skb)->end_seq += copy;
tcp_skb_pcount_set(skb, 0);
@@ -1362,7 +1364,7 @@ new_segment:
if (!copied)
TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
- tp->write_seq += copy;
+ WRITE_ONCE(tp->write_seq, tp->write_seq + copy);
TCP_SKB_CB(skb)->end_seq += copy;
tcp_skb_pcount_set(skb, 0);
@@ -1668,9 +1670,9 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
sk_eat_skb(sk, skb);
if (!desc->count)
break;
- tp->copied_seq = seq;
+ WRITE_ONCE(tp->copied_seq, seq);
}
- tp->copied_seq = seq;
+ WRITE_ONCE(tp->copied_seq, seq);
tcp_rcv_space_adjust(sk);
@@ -1699,7 +1701,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val)
else
cap = sock_net(sk)->ipv4.sysctl_tcp_rmem[2] >> 1;
val = min(val, cap);
- sk->sk_rcvlowat = val ? : 1;
+ WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
/* Check if we need to signal EPOLLIN right now */
tcp_data_ready(sk);
@@ -1709,7 +1711,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val)
val <<= 1;
if (val > sk->sk_rcvbuf) {
- sk->sk_rcvbuf = val;
+ WRITE_ONCE(sk->sk_rcvbuf, val);
tcp_sk(sk)->window_clamp = tcp_win_from_space(sk, val);
}
return 0;
@@ -1819,7 +1821,7 @@ static int tcp_zerocopy_receive(struct sock *sk,
out:
up_read(&current->mm->mmap_sem);
if (length) {
- tp->copied_seq = seq;
+ WRITE_ONCE(tp->copied_seq, seq);
tcp_rcv_space_adjust(sk);
/* Clean up data we have read: This will do ACK frames. */
@@ -2117,7 +2119,7 @@ found_ok_skb:
if (urg_offset < used) {
if (!urg_offset) {
if (!sock_flag(sk, SOCK_URGINLINE)) {
- ++*seq;
+ WRITE_ONCE(*seq, *seq + 1);
urg_hole++;
offset++;
used--;
@@ -2139,7 +2141,7 @@ found_ok_skb:
}
}
- *seq += used;
+ WRITE_ONCE(*seq, *seq + used);
copied += used;
len -= used;
@@ -2166,7 +2168,7 @@ skip_copy:
found_fin_ok:
/* Process the FIN. */
- ++*seq;
+ WRITE_ONCE(*seq, *seq + 1);
if (!(flags & MSG_PEEK))
sk_eat_skb(sk, skb);
break;
@@ -2487,7 +2489,10 @@ adjudge_to_death:
}
if (sk->sk_state == TCP_CLOSE) {
- struct request_sock *req = tcp_sk(sk)->fastopen_rsk;
+ struct request_sock *req;
+
+ req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk,
+ lockdep_sock_is_held(sk));
/* We could get here with a non-NULL req if the socket is
* aborted (e.g., closed with unread data) before 3WHS
* finishes.
@@ -2559,6 +2564,7 @@ int tcp_disconnect(struct sock *sk, int flags)
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
int old_state = sk->sk_state;
+ u32 seq;
if (old_state != TCP_CLOSE)
tcp_set_state(sk, TCP_CLOSE);
@@ -2585,7 +2591,7 @@ int tcp_disconnect(struct sock *sk, int flags)
__kfree_skb(sk->sk_rx_skb_cache);
sk->sk_rx_skb_cache = NULL;
}
- tp->copied_seq = tp->rcv_nxt;
+ WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
tp->urg_data = 0;
tcp_write_queue_purge(sk);
tcp_fastopen_active_disable_ofo_check(sk);
@@ -2601,9 +2607,12 @@ int tcp_disconnect(struct sock *sk, int flags)
tp->srtt_us = 0;
tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
tp->rcv_rtt_last_tsecr = 0;
- tp->write_seq += tp->max_window + 2;
- if (tp->write_seq == 0)
- tp->write_seq = 1;
+
+ seq = tp->write_seq + tp->max_window + 2;
+ if (!seq)
+ seq = 1;
+ WRITE_ONCE(tp->write_seq, seq);
+
icsk->icsk_backoff = 0;
tp->snd_cwnd = 2;
icsk->icsk_probes_out = 0;
@@ -2930,9 +2939,9 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
if (sk->sk_state != TCP_CLOSE)
err = -EPERM;
else if (tp->repair_queue == TCP_SEND_QUEUE)
- tp->write_seq = val;
+ WRITE_ONCE(tp->write_seq, val);
else if (tp->repair_queue == TCP_RECV_QUEUE)
- tp->rcv_nxt = val;
+ WRITE_ONCE(tp->rcv_nxt, val);
else
err = -EINVAL;
break;
@@ -3831,7 +3840,13 @@ EXPORT_SYMBOL(tcp_md5_hash_key);
void tcp_done(struct sock *sk)
{
- struct request_sock *req = tcp_sk(sk)->fastopen_rsk;
+ struct request_sock *req;
+
+ /* We might be called with a new socket, after
+ * inet_csk_prepare_forced_close() has been called
+ * so we can not use lockdep_sock_is_held(sk)
+ */
+ req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, 1);
if (sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV)
TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS);
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index 81a8221d650a..549506162dde 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -26,8 +26,9 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
} else if (sk->sk_type == SOCK_STREAM) {
const struct tcp_sock *tp = tcp_sk(sk);
- r->idiag_rqueue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0);
- r->idiag_wqueue = tp->write_seq - tp->snd_una;
+ r->idiag_rqueue = max_t(int, READ_ONCE(tp->rcv_nxt) -
+ READ_ONCE(tp->copied_seq), 0);
+ r->idiag_wqueue = READ_ONCE(tp->write_seq) - tp->snd_una;
}
if (info)
tcp_get_info(sk, info);
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 3fd451271a70..a915ade0c818 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -253,7 +253,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
*/
tp = tcp_sk(child);
- tp->fastopen_rsk = req;
+ rcu_assign_pointer(tp->fastopen_rsk, req);
tcp_rsk(req)->tfo_listener = true;
/* RFC1323: The window in SYN & SYN/ACK segments is never
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 3578357abe30..a2e52ad7cdab 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -359,7 +359,8 @@ static void tcp_sndbuf_expand(struct sock *sk)
sndmem *= nr_segs * per_mss;
if (sk->sk_sndbuf < sndmem)
- sk->sk_sndbuf = min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2]);
+ WRITE_ONCE(sk->sk_sndbuf,
+ min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2]));
}
/* 2. Tuning advertised window (window_clamp, rcv_ssthresh)
@@ -483,8 +484,9 @@ static void tcp_clamp_window(struct sock *sk)
!(sk->sk_userlocks & SOCK_RCVBUF_LOCK) &&
!tcp_under_memory_pressure(sk) &&
sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) {
- sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc),
- net->ipv4.sysctl_tcp_rmem[2]);
+ WRITE_ONCE(sk->sk_rcvbuf,
+ min(atomic_read(&sk->sk_rmem_alloc),
+ net->ipv4.sysctl_tcp_rmem[2]));
}
if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
tp->rcv_ssthresh = min(tp->window_clamp, 2U * tp->advmss);
@@ -648,7 +650,7 @@ void tcp_rcv_space_adjust(struct sock *sk)
rcvbuf = min_t(u64, rcvwin * rcvmem,
sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
if (rcvbuf > sk->sk_rcvbuf) {
- sk->sk_rcvbuf = rcvbuf;
+ WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
/* Make the window clamp follow along. */
tp->window_clamp = tcp_win_from_space(sk, rcvbuf);
@@ -2666,7 +2668,7 @@ static void tcp_process_loss(struct sock *sk, int flag, int num_dupack,
struct tcp_sock *tp = tcp_sk(sk);
bool recovered = !before(tp->snd_una, tp->high_seq);
- if ((flag & FLAG_SND_UNA_ADVANCED || tp->fastopen_rsk) &&
+ if ((flag & FLAG_SND_UNA_ADVANCED || rcu_access_pointer(tp->fastopen_rsk)) &&
tcp_try_undo_loss(sk, false))
return;
@@ -2990,7 +2992,7 @@ void tcp_rearm_rto(struct sock *sk)
/* If the retrans timer is currently being used by Fast Open
* for SYN-ACK retrans purpose, stay put.
*/
- if (tp->fastopen_rsk)
+ if (rcu_access_pointer(tp->fastopen_rsk))
return;
if (!tp->packets_out) {
@@ -3362,7 +3364,7 @@ static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq)
sock_owned_by_me((struct sock *)tp);
tp->bytes_received += delta;
- tp->rcv_nxt = seq;
+ WRITE_ONCE(tp->rcv_nxt, seq);
}
/* Update our send window.
@@ -5356,7 +5358,7 @@ static void tcp_check_urg(struct sock *sk, const struct tcphdr *th)
}
tp->urg_data = TCP_URG_NOTYET;
- tp->urg_seq = ptr;
+ WRITE_ONCE(tp->urg_seq, ptr);
/* Disable header prediction. */
tp->pred_flags = 0;
@@ -5932,7 +5934,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
/* Ok.. it's good. Set up sequence numbers and
* move to established.
*/
- tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
+ WRITE_ONCE(tp->rcv_nxt, TCP_SKB_CB(skb)->seq + 1);
tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1;
/* RFC1323: The window in SYN & SYN/ACK segments is
@@ -5961,7 +5963,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
/* Remember, tcp_poll() does not lock socket!
* Change state from SYN-SENT only after copied_seq
* is initialized. */
- tp->copied_seq = tp->rcv_nxt;
+ WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
smc_check_reset_syn(tp);
@@ -6035,8 +6037,8 @@ discard:
tp->tcp_header_len = sizeof(struct tcphdr);
}
- tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
- tp->copied_seq = tp->rcv_nxt;
+ WRITE_ONCE(tp->rcv_nxt, TCP_SKB_CB(skb)->seq + 1);
+ WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1;
/* RFC1323: The window in SYN & SYN/ACK segments is
@@ -6087,6 +6089,8 @@ reset_and_undo:
static void tcp_rcv_synrecv_state_fastopen(struct sock *sk)
{
+ struct request_sock *req;
+
tcp_try_undo_loss(sk, false);
/* Reset rtx states to prevent spurious retransmits_timed_out() */
@@ -6096,7 +6100,9 @@ static void tcp_rcv_synrecv_state_fastopen(struct sock *sk)
/* Once we leave TCP_SYN_RECV or TCP_FIN_WAIT_1,
* we no longer need req so release it.
*/
- reqsk_fastopen_remove(sk, tcp_sk(sk)->fastopen_rsk, false);
+ req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk,
+ lockdep_sock_is_held(sk));
+ reqsk_fastopen_remove(sk, req, false);
/* Re-arm the timer because data may have been sent out.
* This is similar to the regular data transmission case
@@ -6171,7 +6177,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
tcp_mstamp_refresh(tp);
tp->rx_opt.saw_tstamp = 0;
- req = tp->fastopen_rsk;
+ req = rcu_dereference_protected(tp->fastopen_rsk,
+ lockdep_sock_is_held(sk));
if (req) {
bool req_stolen;
@@ -6211,7 +6218,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
tcp_try_undo_spurious_syn(sk);
tp->retrans_stamp = 0;
tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
- tp->copied_seq = tp->rcv_nxt;
+ WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
}
smp_mb();
tcp_set_state(sk, TCP_ESTABLISHED);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index bf124b1742df..6be568334848 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -164,9 +164,11 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
* without appearing to create any others.
*/
if (likely(!tp->repair)) {
- tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
- if (tp->write_seq == 0)
- tp->write_seq = 1;
+ u32 seq = tcptw->tw_snd_nxt + 65535 + 2;
+
+ if (!seq)
+ seq = 1;
+ WRITE_ONCE(tp->write_seq, seq);
tp->rx_opt.ts_recent = tcptw->tw_ts_recent;
tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
}
@@ -253,7 +255,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
tp->rx_opt.ts_recent = 0;
tp->rx_opt.ts_recent_stamp = 0;
if (likely(!tp->repair))
- tp->write_seq = 0;
+ WRITE_ONCE(tp->write_seq, 0);
}
inet->inet_dport = usin->sin_port;
@@ -291,10 +293,11 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
if (likely(!tp->repair)) {
if (!tp->write_seq)
- tp->write_seq = secure_tcp_seq(inet->inet_saddr,
- inet->inet_daddr,
- inet->inet_sport,
- usin->sin_port);
+ WRITE_ONCE(tp->write_seq,
+ secure_tcp_seq(inet->inet_saddr,
+ inet->inet_daddr,
+ inet->inet_sport,
+ usin->sin_port));
tp->tsoffset = secure_tcp_ts_off(sock_net(sk),
inet->inet_saddr,
inet->inet_daddr);
@@ -478,7 +481,7 @@ int tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
icsk = inet_csk(sk);
tp = tcp_sk(sk);
/* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */
- fastopen = tp->fastopen_rsk;
+ fastopen = rcu_dereference(tp->fastopen_rsk);
snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una;
if (sk->sk_state != TCP_LISTEN &&
!between(seq, snd_una, tp->snd_nxt)) {
@@ -1644,7 +1647,7 @@ int tcp_v4_early_demux(struct sk_buff *skb)
bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
{
- u32 limit = sk->sk_rcvbuf + sk->sk_sndbuf;
+ u32 limit = READ_ONCE(sk->sk_rcvbuf) + READ_ONCE(sk->sk_sndbuf);
struct skb_shared_info *shinfo;
const struct tcphdr *th;
struct tcphdr *thtail;
@@ -2121,7 +2124,7 @@ void tcp_v4_destroy_sock(struct sock *sk)
if (inet_csk(sk)->icsk_bind_hash)
inet_put_port(sk);
- BUG_ON(tp->fastopen_rsk);
+ BUG_ON(rcu_access_pointer(tp->fastopen_rsk));
/* If socket is aborted during connect operation */
tcp_free_fastopen_req(tp);
@@ -2455,12 +2458,13 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
/* Because we don't lock the socket,
* we might find a transient negative value.
*/
- rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0);
+ rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) -
+ READ_ONCE(tp->copied_seq), 0);
seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX "
"%08X %5u %8d %lu %d %pK %lu %lu %u %u %d",
i, src, srcp, dest, destp, state,
- tp->write_seq - tp->snd_una,
+ READ_ONCE(tp->write_seq) - tp->snd_una,
rx_queue,
timer_active,
jiffies_delta_to_clock_t(timer_expires - jiffies),
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index bb140a5db8c0..c802bc80c400 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -462,6 +462,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
struct tcp_request_sock *treq = tcp_rsk(req);
struct inet_connection_sock *newicsk;
struct tcp_sock *oldtp, *newtp;
+ u32 seq;
if (!newsk)
return NULL;
@@ -475,12 +476,16 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
/* Now setup tcp_sock */
newtp->pred_flags = 0;
- newtp->rcv_wup = newtp->copied_seq =
- newtp->rcv_nxt = treq->rcv_isn + 1;
+ seq = treq->rcv_isn + 1;
+ newtp->rcv_wup = seq;
+ WRITE_ONCE(newtp->copied_seq, seq);
+ WRITE_ONCE(newtp->rcv_nxt, seq);
newtp->segs_in = 1;
- newtp->snd_sml = newtp->snd_una =
- newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1;
+ seq = treq->snt_isn + 1;
+ newtp->snd_sml = newtp->snd_una = seq;
+ WRITE_ONCE(newtp->snd_nxt, seq);
+ newtp->snd_up = seq;
INIT_LIST_HEAD(&newtp->tsq_node);
INIT_LIST_HEAD(&newtp->tsorted_sent_queue);
@@ -495,7 +500,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
newtp->total_retrans = req->num_retrans;
tcp_init_xmit_timers(newsk);
- newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1;
+ WRITE_ONCE(newtp->write_seq, newtp->pushed_seq = treq->snt_isn + 1);
if (sock_flag(newsk, SOCK_KEEPOPEN))
inet_csk_reset_keepalive_timer(newsk,
@@ -541,7 +546,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
newtp->rx_opt.mss_clamp = req->mss;
tcp_ecn_openreq_child(newtp, req);
newtp->fastopen_req = NULL;
- newtp->fastopen_rsk = NULL;
+ RCU_INIT_POINTER(newtp->fastopen_rsk, NULL);
__TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index fec6d67bfd14..0488607c5cd3 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -67,7 +67,7 @@ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb)
struct tcp_sock *tp = tcp_sk(sk);
unsigned int prior_packets = tp->packets_out;
- tp->snd_nxt = TCP_SKB_CB(skb)->end_seq;
+ WRITE_ONCE(tp->snd_nxt, TCP_SKB_CB(skb)->end_seq);
__skb_unlink(skb, &sk->sk_write_queue);
tcp_rbtree_insert(&sk->tcp_rtx_queue, skb);
@@ -1196,10 +1196,10 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
struct tcp_sock *tp = tcp_sk(sk);
/* Advance write_seq and place onto the write_queue. */
- tp->write_seq = TCP_SKB_CB(skb)->end_seq;
+ WRITE_ONCE(tp->write_seq, TCP_SKB_CB(skb)->end_seq);
__skb_header_release(skb);
tcp_add_write_queue_tail(sk, skb);
- sk->sk_wmem_queued += skb->truesize;
+ sk_wmem_queued_add(sk, skb->truesize);
sk_mem_charge(sk, skb->truesize);
}
@@ -1333,7 +1333,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
return -ENOMEM; /* We'll just try again later. */
skb_copy_decrypted(buff, skb);
- sk->sk_wmem_queued += buff->truesize;
+ sk_wmem_queued_add(sk, buff->truesize);
sk_mem_charge(sk, buff->truesize);
nlen = skb->len - len - nsize;
buff->truesize += nlen;
@@ -1443,7 +1443,7 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
if (delta_truesize) {
skb->truesize -= delta_truesize;
- sk->sk_wmem_queued -= delta_truesize;
+ sk_wmem_queued_add(sk, -delta_truesize);
sk_mem_uncharge(sk, delta_truesize);
sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
}
@@ -1888,7 +1888,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
return -ENOMEM;
skb_copy_decrypted(buff, skb);
- sk->sk_wmem_queued += buff->truesize;
+ sk_wmem_queued_add(sk, buff->truesize);
sk_mem_charge(sk, buff->truesize);
buff->truesize += nlen;
skb->truesize -= nlen;
@@ -2152,7 +2152,7 @@ static int tcp_mtu_probe(struct sock *sk)
nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC, false);
if (!nskb)
return -1;
- sk->sk_wmem_queued += nskb->truesize;
+ sk_wmem_queued_add(sk, nskb->truesize);
sk_mem_charge(sk, nskb->truesize);
skb = tcp_send_head(sk);
@@ -2482,7 +2482,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto)
/* Don't do any loss probe on a Fast Open connection before 3WHS
* finishes.
*/
- if (tp->fastopen_rsk)
+ if (rcu_access_pointer(tp->fastopen_rsk))
return false;
early_retrans = sock_net(sk)->ipv4.sysctl_tcp_early_retrans;
@@ -3142,7 +3142,7 @@ void tcp_send_fin(struct sock *sk)
* if FIN had been sent. This is because retransmit path
* does not change tp->snd_nxt.
*/
- tp->snd_nxt++;
+ WRITE_ONCE(tp->snd_nxt, tp->snd_nxt + 1);
return;
}
} else {
@@ -3222,7 +3222,7 @@ int tcp_send_synack(struct sock *sk)
tcp_rtx_queue_unlink_and_free(skb, sk);
__skb_header_release(nskb);
tcp_rbtree_insert(&sk->tcp_rtx_queue, nskb);
- sk->sk_wmem_queued += nskb->truesize;
+ sk_wmem_queued_add(sk, nskb->truesize);
sk_mem_charge(sk, nskb->truesize);
skb = nskb;
}
@@ -3426,14 +3426,14 @@ static void tcp_connect_init(struct sock *sk)
tp->snd_una = tp->write_seq;
tp->snd_sml = tp->write_seq;
tp->snd_up = tp->write_seq;
- tp->snd_nxt = tp->write_seq;
+ WRITE_ONCE(tp->snd_nxt, tp->write_seq);
if (likely(!tp->repair))
tp->rcv_nxt = 0;
else
tp->rcv_tstamp = tcp_jiffies32;
tp->rcv_wup = tp->rcv_nxt;
- tp->copied_seq = tp->rcv_nxt;
+ WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
inet_csk(sk)->icsk_rto = tcp_timeout_init(sk);
inet_csk(sk)->icsk_retransmits = 0;
@@ -3447,9 +3447,9 @@ static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb)
tcb->end_seq += skb->len;
__skb_header_release(skb);
- sk->sk_wmem_queued += skb->truesize;
+ sk_wmem_queued_add(sk, skb->truesize);
sk_mem_charge(sk, skb->truesize);
- tp->write_seq = tcb->end_seq;
+ WRITE_ONCE(tp->write_seq, tcb->end_seq);
tp->packets_out += tcp_skb_pcount(skb);
}
@@ -3586,11 +3586,11 @@ int tcp_connect(struct sock *sk)
/* We change tp->snd_nxt after the tcp_transmit_skb() call
* in order to make this packet get counted in tcpOutSegs.
*/
- tp->snd_nxt = tp->write_seq;
+ WRITE_ONCE(tp->snd_nxt, tp->write_seq);
tp->pushed_seq = tp->write_seq;
buff = tcp_send_head(sk);
if (unlikely(buff)) {
- tp->snd_nxt = TCP_SKB_CB(buff)->seq;
+ WRITE_ONCE(tp->snd_nxt, TCP_SKB_CB(buff)->seq);
tp->pushed_seq = TCP_SKB_CB(buff)->seq;
}
TCP_INC_STATS(sock_net(sk), TCP_MIB_ACTIVEOPENS);
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 05be564414e9..dd5a6317a801 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -386,15 +386,13 @@ abort: tcp_write_err(sk);
* Timer for Fast Open socket to retransmit SYNACK. Note that the
* sk here is the child socket, not the parent (listener) socket.
*/
-static void tcp_fastopen_synack_timer(struct sock *sk)
+static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req)
{
struct inet_connection_sock *icsk = inet_csk(sk);
int max_retries = icsk->icsk_syn_retries ? :
sock_net(sk)->ipv4.sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */
struct tcp_sock *tp = tcp_sk(sk);
- struct request_sock *req;
- req = tcp_sk(sk)->fastopen_rsk;
req->rsk_ops->syn_ack_timeout(req);
if (req->num_timeout >= max_retries) {
@@ -435,11 +433,14 @@ void tcp_retransmit_timer(struct sock *sk)
struct tcp_sock *tp = tcp_sk(sk);
struct net *net = sock_net(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
+ struct request_sock *req;
- if (tp->fastopen_rsk) {
+ req = rcu_dereference_protected(tp->fastopen_rsk,
+ lockdep_sock_is_held(sk));
+ if (req) {
WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV &&
sk->sk_state != TCP_FIN_WAIT1);
- tcp_fastopen_synack_timer(sk);
+ tcp_fastopen_synack_timer(sk, req);
/* Before we receive ACK to our SYN-ACK don't retransmit
* anything else (e.g., data or FIN segments).
*/
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index d5779d6a6065..787d9f2a6e99 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -2192,6 +2192,7 @@ static void ip6erspan_tap_setup(struct net_device *dev)
{
ether_setup(dev);
+ dev->max_mtu = 0;
dev->netdev_ops = &ip6erspan_netdev_ops;
dev->needs_free_netdev = true;
dev->priv_destructor = ip6gre_dev_free;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index edadee4a7e76..71827b56c006 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -768,6 +768,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
inet6_sk(skb->sk) : NULL;
struct ip6_frag_state state;
unsigned int mtu, hlen, nexthdr_offset;
+ ktime_t tstamp = skb->tstamp;
int hroom, err = 0;
__be32 frag_id;
u8 *prevhdr, nexthdr = 0;
@@ -855,6 +856,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
if (iter.frag)
ip6_fraglist_prepare(skb, &iter);
+ skb->tstamp = tstamp;
err = output(net, sk, skb);
if (!err)
IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
@@ -913,6 +915,7 @@ slow_path:
/*
* Put this fragment into the sending queue.
*/
+ frag->tstamp = tstamp;
err = output(net, sk, frag);
if (err)
goto fail;
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index a9bff556d3b2..409e79b84a83 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -119,6 +119,7 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
struct sk_buff *))
{
int frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size;
+ ktime_t tstamp = skb->tstamp;
struct ip6_frag_state state;
u8 *prevhdr, nexthdr = 0;
unsigned int mtu, hlen;
@@ -183,6 +184,7 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
if (iter.frag)
ip6_fraglist_prepare(skb, &iter);
+ skb->tstamp = tstamp;
err = output(net, sk, data, skb);
if (err || !iter.frag)
break;
@@ -215,6 +217,7 @@ slow_path:
goto blackhole;
}
+ skb2->tstamp = tstamp;
err = output(net, sk, data, skb2);
if (err)
goto blackhole;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index e3d9f4559c99..4804b6dc5e65 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -215,7 +215,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
!ipv6_addr_equal(&sk->sk_v6_daddr, &usin->sin6_addr)) {
tp->rx_opt.ts_recent = 0;
tp->rx_opt.ts_recent_stamp = 0;
- tp->write_seq = 0;
+ WRITE_ONCE(tp->write_seq, 0);
}
sk->sk_v6_daddr = usin->sin6_addr;
@@ -311,10 +311,11 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
if (likely(!tp->repair)) {
if (!tp->write_seq)
- tp->write_seq = secure_tcpv6_seq(np->saddr.s6_addr32,
- sk->sk_v6_daddr.s6_addr32,
- inet->inet_sport,
- inet->inet_dport);
+ WRITE_ONCE(tp->write_seq,
+ secure_tcpv6_seq(np->saddr.s6_addr32,
+ sk->sk_v6_daddr.s6_addr32,
+ inet->inet_sport,
+ inet->inet_dport));
tp->tsoffset = secure_tcpv6_ts_off(sock_net(sk),
np->saddr.s6_addr32,
sk->sk_v6_daddr.s6_addr32);
@@ -406,7 +407,7 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
tp = tcp_sk(sk);
/* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */
- fastopen = tp->fastopen_rsk;
+ fastopen = rcu_dereference(tp->fastopen_rsk);
snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una;
if (sk->sk_state != TCP_LISTEN &&
!between(seq, snd_una, tp->snd_nxt)) {
@@ -1895,7 +1896,8 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
/* Because we don't lock the socket,
* we might find a transient negative value.
*/
- rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0);
+ rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) -
+ READ_ONCE(tp->copied_seq), 0);
seq_printf(seq,
"%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
@@ -1906,7 +1908,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
dest->s6_addr32[0], dest->s6_addr32[1],
dest->s6_addr32[2], dest->s6_addr32[3], destp,
state,
- tp->write_seq - tp->snd_una,
+ READ_ONCE(tp->write_seq) - tp->snd_una,
rx_queue,
timer_active,
jiffies_delta_to_clock_t(timer_expires - jiffies),
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 2017b7d780f5..c74f44dfaa22 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -113,22 +113,26 @@ static inline u8 llc_ui_header_len(struct sock *sk, struct sockaddr_llc *addr)
*
* Send data via reliable llc2 connection.
* Returns 0 upon success, non-zero if action did not succeed.
+ *
+ * This function always consumes a reference to the skb.
*/
static int llc_ui_send_data(struct sock* sk, struct sk_buff *skb, int noblock)
{
struct llc_sock* llc = llc_sk(sk);
- int rc = 0;
if (unlikely(llc_data_accept_state(llc->state) ||
llc->remote_busy_flag ||
llc->p_flag)) {
long timeout = sock_sndtimeo(sk, noblock);
+ int rc;
rc = llc_ui_wait_for_busy_core(sk, timeout);
+ if (rc) {
+ kfree_skb(skb);
+ return rc;
+ }
}
- if (unlikely(!rc))
- rc = llc_build_and_send_pkt(sk, skb);
- return rc;
+ return llc_build_and_send_pkt(sk, skb);
}
static void llc_ui_sk_init(struct socket *sock, struct sock *sk)
@@ -899,7 +903,7 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
DECLARE_SOCKADDR(struct sockaddr_llc *, addr, msg->msg_name);
int flags = msg->msg_flags;
int noblock = flags & MSG_DONTWAIT;
- struct sk_buff *skb;
+ struct sk_buff *skb = NULL;
size_t size = 0;
int rc = -EINVAL, copied = 0, hdrlen;
@@ -908,10 +912,10 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
lock_sock(sk);
if (addr) {
if (msg->msg_namelen < sizeof(*addr))
- goto release;
+ goto out;
} else {
if (llc_ui_addr_null(&llc->addr))
- goto release;
+ goto out;
addr = &llc->addr;
}
/* must bind connection to sap if user hasn't done it. */
@@ -919,7 +923,7 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
/* bind to sap with null dev, exclusive. */
rc = llc_ui_autobind(sock, addr);
if (rc)
- goto release;
+ goto out;
}
hdrlen = llc->dev->hard_header_len + llc_ui_header_len(sk, addr);
size = hdrlen + len;
@@ -928,12 +932,12 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
copied = size - hdrlen;
rc = -EINVAL;
if (copied < 0)
- goto release;
+ goto out;
release_sock(sk);
skb = sock_alloc_send_skb(sk, size, noblock, &rc);
lock_sock(sk);
if (!skb)
- goto release;
+ goto out;
skb->dev = llc->dev;
skb->protocol = llc_proto_type(addr->sllc_arphrd);
skb_reserve(skb, hdrlen);
@@ -943,29 +947,31 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
if (sk->sk_type == SOCK_DGRAM || addr->sllc_ua) {
llc_build_and_send_ui_pkt(llc->sap, skb, addr->sllc_mac,
addr->sllc_sap);
+ skb = NULL;
goto out;
}
if (addr->sllc_test) {
llc_build_and_send_test_pkt(llc->sap, skb, addr->sllc_mac,
addr->sllc_sap);
+ skb = NULL;
goto out;
}
if (addr->sllc_xid) {
llc_build_and_send_xid_pkt(llc->sap, skb, addr->sllc_mac,
addr->sllc_sap);
+ skb = NULL;
goto out;
}
rc = -ENOPROTOOPT;
if (!(sk->sk_type == SOCK_STREAM && !addr->sllc_ua))
goto out;
rc = llc_ui_send_data(sk, skb, noblock);
+ skb = NULL;
out:
- if (rc) {
- kfree_skb(skb);
-release:
+ kfree_skb(skb);
+ if (rc)
dprintk("%s: failed sending from %02X to %02X: %d\n",
__func__, llc->laddr.lsap, llc->daddr.lsap, rc);
- }
release_sock(sk);
return rc ? : copied;
}
diff --git a/net/llc/llc_c_ac.c b/net/llc/llc_c_ac.c
index 4d78375f9872..647c0554d04c 100644
--- a/net/llc/llc_c_ac.c
+++ b/net/llc/llc_c_ac.c
@@ -372,6 +372,7 @@ int llc_conn_ac_send_i_cmd_p_set_1(struct sock *sk, struct sk_buff *skb)
llc_pdu_init_as_i_cmd(skb, 1, llc->vS, llc->vR);
rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac);
if (likely(!rc)) {
+ skb_get(skb);
llc_conn_send_pdu(sk, skb);
llc_conn_ac_inc_vs_by_1(sk, skb);
}
@@ -389,7 +390,8 @@ static int llc_conn_ac_send_i_cmd_p_set_0(struct sock *sk, struct sk_buff *skb)
llc_pdu_init_as_i_cmd(skb, 0, llc->vS, llc->vR);
rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac);
if (likely(!rc)) {
- rc = llc_conn_send_pdu(sk, skb);
+ skb_get(skb);
+ llc_conn_send_pdu(sk, skb);
llc_conn_ac_inc_vs_by_1(sk, skb);
}
return rc;
@@ -406,6 +408,7 @@ int llc_conn_ac_send_i_xxx_x_set_0(struct sock *sk, struct sk_buff *skb)
llc_pdu_init_as_i_cmd(skb, 0, llc->vS, llc->vR);
rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac);
if (likely(!rc)) {
+ skb_get(skb);
llc_conn_send_pdu(sk, skb);
llc_conn_ac_inc_vs_by_1(sk, skb);
}
@@ -916,7 +919,8 @@ static int llc_conn_ac_send_i_rsp_f_set_ackpf(struct sock *sk,
llc_pdu_init_as_i_cmd(skb, llc->ack_pf, llc->vS, llc->vR);
rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac);
if (likely(!rc)) {
- rc = llc_conn_send_pdu(sk, skb);
+ skb_get(skb);
+ llc_conn_send_pdu(sk, skb);
llc_conn_ac_inc_vs_by_1(sk, skb);
}
return rc;
diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index 4ff89cb7c86f..7b620acaca9e 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -30,7 +30,7 @@
#endif
static int llc_find_offset(int state, int ev_type);
-static int llc_conn_send_pdus(struct sock *sk, struct sk_buff *skb);
+static void llc_conn_send_pdus(struct sock *sk);
static int llc_conn_service(struct sock *sk, struct sk_buff *skb);
static int llc_exec_conn_trans_actions(struct sock *sk,
struct llc_conn_state_trans *trans,
@@ -55,6 +55,8 @@ int sysctl_llc2_busy_timeout = LLC2_BUSY_TIME * HZ;
* (executing it's actions and changing state), upper layer will be
* indicated or confirmed, if needed. Returns 0 for success, 1 for
* failure. The socket lock has to be held before calling this function.
+ *
+ * This function always consumes a reference to the skb.
*/
int llc_conn_state_process(struct sock *sk, struct sk_buff *skb)
{
@@ -62,12 +64,6 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb)
struct llc_sock *llc = llc_sk(skb->sk);
struct llc_conn_state_ev *ev = llc_conn_ev(skb);
- /*
- * We have to hold the skb, because llc_conn_service will kfree it in
- * the sending path and we need to look at the skb->cb, where we encode
- * llc_conn_state_ev.
- */
- skb_get(skb);
ev->ind_prim = ev->cfm_prim = 0;
/*
* Send event to state machine
@@ -75,21 +71,12 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb)
rc = llc_conn_service(skb->sk, skb);
if (unlikely(rc != 0)) {
printk(KERN_ERR "%s: llc_conn_service failed\n", __func__);
- goto out_kfree_skb;
- }
-
- if (unlikely(!ev->ind_prim && !ev->cfm_prim)) {
- /* indicate or confirm not required */
- if (!skb->next)
- goto out_kfree_skb;
goto out_skb_put;
}
- if (unlikely(ev->ind_prim && ev->cfm_prim)) /* Paranoia */
- skb_get(skb);
-
switch (ev->ind_prim) {
case LLC_DATA_PRIM:
+ skb_get(skb);
llc_save_primitive(sk, skb, LLC_DATA_PRIM);
if (unlikely(sock_queue_rcv_skb(sk, skb))) {
/*
@@ -106,6 +93,7 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb)
* skb->sk pointing to the newly created struct sock in
* llc_conn_handler. -acme
*/
+ skb_get(skb);
skb_queue_tail(&sk->sk_receive_queue, skb);
sk->sk_state_change(sk);
break;
@@ -121,7 +109,6 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb)
sk->sk_state_change(sk);
}
}
- kfree_skb(skb);
sock_put(sk);
break;
case LLC_RESET_PRIM:
@@ -130,14 +117,11 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb)
* RESET is not being notified to upper layers for now
*/
printk(KERN_INFO "%s: received a reset ind!\n", __func__);
- kfree_skb(skb);
break;
default:
- if (ev->ind_prim) {
+ if (ev->ind_prim)
printk(KERN_INFO "%s: received unknown %d prim!\n",
__func__, ev->ind_prim);
- kfree_skb(skb);
- }
/* No indication */
break;
}
@@ -179,25 +163,22 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb)
printk(KERN_INFO "%s: received a reset conf!\n", __func__);
break;
default:
- if (ev->cfm_prim) {
+ if (ev->cfm_prim)
printk(KERN_INFO "%s: received unknown %d prim!\n",
__func__, ev->cfm_prim);
- break;
- }
- goto out_skb_put; /* No confirmation */
+ /* No confirmation */
+ break;
}
-out_kfree_skb:
- kfree_skb(skb);
out_skb_put:
kfree_skb(skb);
return rc;
}
-int llc_conn_send_pdu(struct sock *sk, struct sk_buff *skb)
+void llc_conn_send_pdu(struct sock *sk, struct sk_buff *skb)
{
/* queue PDU to send to MAC layer */
skb_queue_tail(&sk->sk_write_queue, skb);
- return llc_conn_send_pdus(sk, skb);
+ llc_conn_send_pdus(sk);
}
/**
@@ -255,7 +236,7 @@ void llc_conn_resend_i_pdu_as_cmd(struct sock *sk, u8 nr, u8 first_p_bit)
if (howmany_resend > 0)
llc->vS = (llc->vS + 1) % LLC_2_SEQ_NBR_MODULO;
/* any PDUs to re-send are queued up; start sending to MAC */
- llc_conn_send_pdus(sk, NULL);
+ llc_conn_send_pdus(sk);
out:;
}
@@ -296,7 +277,7 @@ void llc_conn_resend_i_pdu_as_rsp(struct sock *sk, u8 nr, u8 first_f_bit)
if (howmany_resend > 0)
llc->vS = (llc->vS + 1) % LLC_2_SEQ_NBR_MODULO;
/* any PDUs to re-send are queued up; start sending to MAC */
- llc_conn_send_pdus(sk, NULL);
+ llc_conn_send_pdus(sk);
out:;
}
@@ -340,16 +321,12 @@ out:
/**
* llc_conn_send_pdus - Sends queued PDUs
* @sk: active connection
- * @hold_skb: the skb held by caller, or NULL if does not care
*
- * Sends queued pdus to MAC layer for transmission. When @hold_skb is
- * NULL, always return 0. Otherwise, return 0 if @hold_skb is sent
- * successfully, or 1 for failure.
+ * Sends queued pdus to MAC layer for transmission.
*/
-static int llc_conn_send_pdus(struct sock *sk, struct sk_buff *hold_skb)
+static void llc_conn_send_pdus(struct sock *sk)
{
struct sk_buff *skb;
- int ret = 0;
while ((skb = skb_dequeue(&sk->sk_write_queue)) != NULL) {
struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb);
@@ -361,20 +338,10 @@ static int llc_conn_send_pdus(struct sock *sk, struct sk_buff *hold_skb)
skb_queue_tail(&llc_sk(sk)->pdu_unack_q, skb);
if (!skb2)
break;
- dev_queue_xmit(skb2);
- } else {
- bool is_target = skb == hold_skb;
- int rc;
-
- if (is_target)
- skb_get(skb);
- rc = dev_queue_xmit(skb);
- if (is_target)
- ret = rc;
+ skb = skb2;
}
+ dev_queue_xmit(skb);
}
-
- return ret;
}
/**
@@ -846,7 +813,7 @@ void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb)
else {
dprintk("%s: adding to backlog...\n", __func__);
llc_set_backlog_type(skb, LLC_PACKET);
- if (sk_add_backlog(sk, skb, sk->sk_rcvbuf))
+ if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf)))
goto drop_unlock;
}
out:
diff --git a/net/llc/llc_if.c b/net/llc/llc_if.c
index 8db03c2d5440..ad6547736c21 100644
--- a/net/llc/llc_if.c
+++ b/net/llc/llc_if.c
@@ -38,6 +38,8 @@
* closed and -EBUSY when sending data is not permitted in this state or
* LLC has send an I pdu with p bit set to 1 and is waiting for it's
* response.
+ *
+ * This function always consumes a reference to the skb.
*/
int llc_build_and_send_pkt(struct sock *sk, struct sk_buff *skb)
{
@@ -46,20 +48,22 @@ int llc_build_and_send_pkt(struct sock *sk, struct sk_buff *skb)
struct llc_sock *llc = llc_sk(sk);
if (unlikely(llc->state == LLC_CONN_STATE_ADM))
- goto out;
+ goto out_free;
rc = -EBUSY;
if (unlikely(llc_data_accept_state(llc->state) || /* data_conn_refuse */
llc->p_flag)) {
llc->failed_data_req = 1;
- goto out;
+ goto out_free;
}
ev = llc_conn_ev(skb);
ev->type = LLC_CONN_EV_TYPE_PRIM;
ev->prim = LLC_DATA_PRIM;
ev->prim_type = LLC_PRIM_TYPE_REQ;
skb->dev = llc->dev;
- rc = llc_conn_state_process(sk, skb);
-out:
+ return llc_conn_state_process(sk, skb);
+
+out_free:
+ kfree_skb(skb);
return rc;
}
diff --git a/net/llc/llc_s_ac.c b/net/llc/llc_s_ac.c
index a94bd56bcac6..7ae4cc684d3a 100644
--- a/net/llc/llc_s_ac.c
+++ b/net/llc/llc_s_ac.c
@@ -58,8 +58,10 @@ int llc_sap_action_send_ui(struct llc_sap *sap, struct sk_buff *skb)
ev->daddr.lsap, LLC_PDU_CMD);
llc_pdu_init_as_ui_cmd(skb);
rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac);
- if (likely(!rc))
+ if (likely(!rc)) {
+ skb_get(skb);
rc = dev_queue_xmit(skb);
+ }
return rc;
}
@@ -81,8 +83,10 @@ int llc_sap_action_send_xid_c(struct llc_sap *sap, struct sk_buff *skb)
ev->daddr.lsap, LLC_PDU_CMD);
llc_pdu_init_as_xid_cmd(skb, LLC_XID_NULL_CLASS_2, 0);
rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac);
- if (likely(!rc))
+ if (likely(!rc)) {
+ skb_get(skb);
rc = dev_queue_xmit(skb);
+ }
return rc;
}
@@ -135,8 +139,10 @@ int llc_sap_action_send_test_c(struct llc_sap *sap, struct sk_buff *skb)
ev->daddr.lsap, LLC_PDU_CMD);
llc_pdu_init_as_test_cmd(skb);
rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac);
- if (likely(!rc))
+ if (likely(!rc)) {
+ skb_get(skb);
rc = dev_queue_xmit(skb);
+ }
return rc;
}
diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c
index a7f7b8ff4729..be419062e19a 100644
--- a/net/llc/llc_sap.c
+++ b/net/llc/llc_sap.c
@@ -197,29 +197,22 @@ out:
* After executing actions of the event, upper layer will be indicated
* if needed(on receiving an UI frame). sk can be null for the
* datalink_proto case.
+ *
+ * This function always consumes a reference to the skb.
*/
static void llc_sap_state_process(struct llc_sap *sap, struct sk_buff *skb)
{
struct llc_sap_state_ev *ev = llc_sap_ev(skb);
- /*
- * We have to hold the skb, because llc_sap_next_state
- * will kfree it in the sending path and we need to
- * look at the skb->cb, where we encode llc_sap_state_ev.
- */
- skb_get(skb);
ev->ind_cfm_flag = 0;
llc_sap_next_state(sap, skb);
- if (ev->ind_cfm_flag == LLC_IND) {
- if (skb->sk->sk_state == TCP_LISTEN)
- kfree_skb(skb);
- else {
- llc_save_primitive(skb->sk, skb, ev->prim);
- /* queue skb to the user. */
- if (sock_queue_rcv_skb(skb->sk, skb))
- kfree_skb(skb);
- }
+ if (ev->ind_cfm_flag == LLC_IND && skb->sk->sk_state != TCP_LISTEN) {
+ llc_save_primitive(skb->sk, skb, ev->prim);
+
+ /* queue skb to the user. */
+ if (sock_queue_rcv_skb(skb->sk, skb) == 0)
+ return;
}
kfree_skb(skb);
}
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 26a2f49208b6..54dd8849d1cc 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -2633,7 +2633,8 @@ struct sk_buff *ieee80211_ap_probereq_get(struct ieee80211_hw *hw,
rcu_read_lock();
ssid = ieee80211_bss_get_ie(cbss, WLAN_EID_SSID);
- if (WARN_ON_ONCE(ssid == NULL))
+ if (WARN_ONCE(!ssid || ssid[1] > IEEE80211_MAX_SSID_LEN,
+ "invalid SSID element (len=%d)", ssid ? ssid[1] : -1))
ssid_len = 0;
else
ssid_len = ssid[1];
@@ -5233,7 +5234,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
rcu_read_lock();
ssidie = ieee80211_bss_get_ie(req->bss, WLAN_EID_SSID);
- if (!ssidie) {
+ if (!ssidie || ssidie[1] > sizeof(assoc_data->ssid)) {
rcu_read_unlock();
kfree(assoc_data);
return -EINVAL;
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 768d14c9a716..0e05ff037672 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -3467,9 +3467,18 @@ ieee80211_rx_h_mgmt(struct ieee80211_rx_data *rx)
case cpu_to_le16(IEEE80211_STYPE_PROBE_RESP):
/* process for all: mesh, mlme, ibss */
break;
+ case cpu_to_le16(IEEE80211_STYPE_DEAUTH):
+ if (is_multicast_ether_addr(mgmt->da) &&
+ !is_broadcast_ether_addr(mgmt->da))
+ return RX_DROP_MONITOR;
+
+ /* process only for station/IBSS */
+ if (sdata->vif.type != NL80211_IFTYPE_STATION &&
+ sdata->vif.type != NL80211_IFTYPE_ADHOC)
+ return RX_DROP_MONITOR;
+ break;
case cpu_to_le16(IEEE80211_STYPE_ASSOC_RESP):
case cpu_to_le16(IEEE80211_STYPE_REASSOC_RESP):
- case cpu_to_le16(IEEE80211_STYPE_DEAUTH):
case cpu_to_le16(IEEE80211_STYPE_DISASSOC):
if (is_multicast_ether_addr(mgmt->da) &&
!is_broadcast_ether_addr(mgmt->da))
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index adf94ba1ed77..4d31d9688dc2 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -520,10 +520,33 @@ static int ieee80211_start_sw_scan(struct ieee80211_local *local,
return 0;
}
+static bool __ieee80211_can_leave_ch(struct ieee80211_sub_if_data *sdata)
+{
+ struct ieee80211_local *local = sdata->local;
+ struct ieee80211_sub_if_data *sdata_iter;
+
+ if (!ieee80211_is_radar_required(local))
+ return true;
+
+ if (!regulatory_pre_cac_allowed(local->hw.wiphy))
+ return false;
+
+ mutex_lock(&local->iflist_mtx);
+ list_for_each_entry(sdata_iter, &local->interfaces, list) {
+ if (sdata_iter->wdev.cac_started) {
+ mutex_unlock(&local->iflist_mtx);
+ return false;
+ }
+ }
+ mutex_unlock(&local->iflist_mtx);
+
+ return true;
+}
+
static bool ieee80211_can_scan(struct ieee80211_local *local,
struct ieee80211_sub_if_data *sdata)
{
- if (ieee80211_is_radar_required(local))
+ if (!__ieee80211_can_leave_ch(sdata))
return false;
if (!list_empty(&local->roc_list))
@@ -630,7 +653,10 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata,
lockdep_assert_held(&local->mtx);
- if (local->scan_req || ieee80211_is_radar_required(local))
+ if (local->scan_req)
+ return -EBUSY;
+
+ if (!__ieee80211_can_leave_ch(sdata))
return -EBUSY;
if (!ieee80211_can_scan(local, sdata)) {
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 0c63120b2db2..5cd610b547e0 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1792,8 +1792,8 @@ void __nf_ct_refresh_acct(struct nf_conn *ct,
if (nf_ct_is_confirmed(ct))
extra_jiffies += nfct_time_stamp;
- if (ct->timeout != extra_jiffies)
- ct->timeout = extra_jiffies;
+ if (READ_ONCE(ct->timeout) != extra_jiffies)
+ WRITE_ONCE(ct->timeout, extra_jiffies);
acct:
if (do_acct)
nf_ct_acct_update(ct, ctinfo, skb->len);
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 3572e11b6f21..1c77f520f474 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -165,7 +165,8 @@ static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key,
{
int err;
- err = skb_mpls_push(skb, mpls->mpls_lse, mpls->mpls_ethertype);
+ err = skb_mpls_push(skb, mpls->mpls_lse, mpls->mpls_ethertype,
+ skb->mac_len);
if (err)
return err;
@@ -178,7 +179,7 @@ static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key,
{
int err;
- err = skb_mpls_pop(skb, ethertype);
+ err = skb_mpls_pop(skb, ethertype, skb->mac_len);
if (err)
return err;
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 1091bf35a199..ecc17dabec8f 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -556,6 +556,7 @@ struct rxrpc_call {
struct rxrpc_peer *peer; /* Peer record for remote address */
struct rxrpc_sock __rcu *socket; /* socket responsible */
struct rxrpc_net *rxnet; /* Network namespace to which call belongs */
+ const struct rxrpc_security *security; /* applied security module */
struct mutex user_mutex; /* User access mutex */
unsigned long ack_at; /* When deferred ACK needs to happen */
unsigned long ack_lost_at; /* When ACK is figured as lost */
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index 00c095d74145..135bf5cd8dd5 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -84,7 +84,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx,
smp_store_release(&b->conn_backlog_head,
(head + 1) & (size - 1));
- trace_rxrpc_conn(conn, rxrpc_conn_new_service,
+ trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_service,
atomic_read(&conn->usage), here);
}
@@ -97,7 +97,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx,
call->flags |= (1 << RXRPC_CALL_IS_SERVICE);
call->state = RXRPC_CALL_SERVER_PREALLOC;
- trace_rxrpc_call(call, rxrpc_call_new_service,
+ trace_rxrpc_call(call->debug_id, rxrpc_call_new_service,
atomic_read(&call->usage),
here, (const void *)user_call_ID);
@@ -307,6 +307,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx,
rxrpc_see_call(call);
call->conn = conn;
+ call->security = conn->security;
call->peer = rxrpc_get_peer(conn->params.peer);
call->cong_cwnd = call->peer->cong_cwnd;
return call;
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 32d8dc677142..a31c18c09894 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -240,7 +240,8 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
if (p->intr)
__set_bit(RXRPC_CALL_IS_INTR, &call->flags);
call->tx_total_len = p->tx_total_len;
- trace_rxrpc_call(call, rxrpc_call_new_client, atomic_read(&call->usage),
+ trace_rxrpc_call(call->debug_id, rxrpc_call_new_client,
+ atomic_read(&call->usage),
here, (const void *)p->user_call_ID);
/* We need to protect a partially set up call against the user as we
@@ -290,8 +291,8 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
if (ret < 0)
goto error;
- trace_rxrpc_call(call, rxrpc_call_connected, atomic_read(&call->usage),
- here, NULL);
+ trace_rxrpc_call(call->debug_id, rxrpc_call_connected,
+ atomic_read(&call->usage), here, NULL);
rxrpc_start_call_timer(call);
@@ -313,8 +314,8 @@ error_dup_user_ID:
error:
__rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR,
RX_CALL_DEAD, ret);
- trace_rxrpc_call(call, rxrpc_call_error, atomic_read(&call->usage),
- here, ERR_PTR(ret));
+ trace_rxrpc_call(call->debug_id, rxrpc_call_error,
+ atomic_read(&call->usage), here, ERR_PTR(ret));
rxrpc_release_call(rx, call);
mutex_unlock(&call->user_mutex);
rxrpc_put_call(call, rxrpc_call_put);
@@ -376,7 +377,8 @@ bool rxrpc_queue_call(struct rxrpc_call *call)
if (n == 0)
return false;
if (rxrpc_queue_work(&call->processor))
- trace_rxrpc_call(call, rxrpc_call_queued, n + 1, here, NULL);
+ trace_rxrpc_call(call->debug_id, rxrpc_call_queued, n + 1,
+ here, NULL);
else
rxrpc_put_call(call, rxrpc_call_put_noqueue);
return true;
@@ -391,7 +393,8 @@ bool __rxrpc_queue_call(struct rxrpc_call *call)
int n = atomic_read(&call->usage);
ASSERTCMP(n, >=, 1);
if (rxrpc_queue_work(&call->processor))
- trace_rxrpc_call(call, rxrpc_call_queued_ref, n, here, NULL);
+ trace_rxrpc_call(call->debug_id, rxrpc_call_queued_ref, n,
+ here, NULL);
else
rxrpc_put_call(call, rxrpc_call_put_noqueue);
return true;
@@ -406,7 +409,8 @@ void rxrpc_see_call(struct rxrpc_call *call)
if (call) {
int n = atomic_read(&call->usage);
- trace_rxrpc_call(call, rxrpc_call_seen, n, here, NULL);
+ trace_rxrpc_call(call->debug_id, rxrpc_call_seen, n,
+ here, NULL);
}
}
@@ -418,7 +422,7 @@ void rxrpc_get_call(struct rxrpc_call *call, enum rxrpc_call_trace op)
const void *here = __builtin_return_address(0);
int n = atomic_inc_return(&call->usage);
- trace_rxrpc_call(call, op, n, here, NULL);
+ trace_rxrpc_call(call->debug_id, op, n, here, NULL);
}
/*
@@ -445,7 +449,8 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call)
_enter("{%d,%d}", call->debug_id, atomic_read(&call->usage));
- trace_rxrpc_call(call, rxrpc_call_release, atomic_read(&call->usage),
+ trace_rxrpc_call(call->debug_id, rxrpc_call_release,
+ atomic_read(&call->usage),
here, (const void *)call->flags);
ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE);
@@ -488,10 +493,10 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call)
_debug("RELEASE CALL %p (%d CONN %p)", call, call->debug_id, conn);
- if (conn) {
+ if (conn)
rxrpc_disconnect_call(call);
- conn->security->free_call_crypto(call);
- }
+ if (call->security)
+ call->security->free_call_crypto(call);
rxrpc_cleanup_ring(call);
_leave("");
@@ -534,12 +539,13 @@ void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace op)
{
struct rxrpc_net *rxnet = call->rxnet;
const void *here = __builtin_return_address(0);
+ unsigned int debug_id = call->debug_id;
int n;
ASSERT(call != NULL);
n = atomic_dec_return(&call->usage);
- trace_rxrpc_call(call, op, n, here, NULL);
+ trace_rxrpc_call(debug_id, op, n, here, NULL);
ASSERTCMP(n, >=, 0);
if (n == 0) {
_debug("call %d dead", call->debug_id);
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index 3f1da1b49f69..376370cd9285 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -212,7 +212,8 @@ rxrpc_alloc_client_connection(struct rxrpc_conn_parameters *cp, gfp_t gfp)
rxrpc_get_local(conn->params.local);
key_get(conn->params.key);
- trace_rxrpc_conn(conn, rxrpc_conn_new_client, atomic_read(&conn->usage),
+ trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_client,
+ atomic_read(&conn->usage),
__builtin_return_address(0));
trace_rxrpc_client(conn, -1, rxrpc_client_alloc);
_leave(" = %p", conn);
@@ -352,6 +353,7 @@ static int rxrpc_get_client_conn(struct rxrpc_sock *rx,
if (cp->exclusive) {
call->conn = candidate;
+ call->security = candidate->security;
call->security_ix = candidate->security_ix;
call->service_id = candidate->service_id;
_leave(" = 0 [exclusive %d]", candidate->debug_id);
@@ -403,6 +405,7 @@ static int rxrpc_get_client_conn(struct rxrpc_sock *rx,
candidate_published:
set_bit(RXRPC_CONN_IN_CLIENT_CONNS, &candidate->flags);
call->conn = candidate;
+ call->security = candidate->security;
call->security_ix = candidate->security_ix;
call->service_id = candidate->service_id;
spin_unlock(&local->client_conns_lock);
@@ -425,6 +428,7 @@ found_extant_conn:
spin_lock(&conn->channel_lock);
call->conn = conn;
+ call->security = conn->security;
call->security_ix = conn->security_ix;
call->service_id = conn->service_id;
list_add_tail(&call->chan_wait_link, &conn->waiting_calls);
@@ -985,11 +989,12 @@ rxrpc_put_one_client_conn(struct rxrpc_connection *conn)
void rxrpc_put_client_conn(struct rxrpc_connection *conn)
{
const void *here = __builtin_return_address(0);
+ unsigned int debug_id = conn->debug_id;
int n;
do {
n = atomic_dec_return(&conn->usage);
- trace_rxrpc_conn(conn, rxrpc_conn_put_client, n, here);
+ trace_rxrpc_conn(debug_id, rxrpc_conn_put_client, n, here);
if (n > 0)
return;
ASSERTCMP(n, >=, 0);
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index ed05b6922132..38d718e90dc6 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -269,7 +269,7 @@ bool rxrpc_queue_conn(struct rxrpc_connection *conn)
if (n == 0)
return false;
if (rxrpc_queue_work(&conn->processor))
- trace_rxrpc_conn(conn, rxrpc_conn_queued, n + 1, here);
+ trace_rxrpc_conn(conn->debug_id, rxrpc_conn_queued, n + 1, here);
else
rxrpc_put_connection(conn);
return true;
@@ -284,7 +284,7 @@ void rxrpc_see_connection(struct rxrpc_connection *conn)
if (conn) {
int n = atomic_read(&conn->usage);
- trace_rxrpc_conn(conn, rxrpc_conn_seen, n, here);
+ trace_rxrpc_conn(conn->debug_id, rxrpc_conn_seen, n, here);
}
}
@@ -296,7 +296,7 @@ void rxrpc_get_connection(struct rxrpc_connection *conn)
const void *here = __builtin_return_address(0);
int n = atomic_inc_return(&conn->usage);
- trace_rxrpc_conn(conn, rxrpc_conn_got, n, here);
+ trace_rxrpc_conn(conn->debug_id, rxrpc_conn_got, n, here);
}
/*
@@ -310,7 +310,7 @@ rxrpc_get_connection_maybe(struct rxrpc_connection *conn)
if (conn) {
int n = atomic_fetch_add_unless(&conn->usage, 1, 0);
if (n > 0)
- trace_rxrpc_conn(conn, rxrpc_conn_got, n + 1, here);
+ trace_rxrpc_conn(conn->debug_id, rxrpc_conn_got, n + 1, here);
else
conn = NULL;
}
@@ -333,10 +333,11 @@ static void rxrpc_set_service_reap_timer(struct rxrpc_net *rxnet,
void rxrpc_put_service_conn(struct rxrpc_connection *conn)
{
const void *here = __builtin_return_address(0);
+ unsigned int debug_id = conn->debug_id;
int n;
n = atomic_dec_return(&conn->usage);
- trace_rxrpc_conn(conn, rxrpc_conn_put_service, n, here);
+ trace_rxrpc_conn(debug_id, rxrpc_conn_put_service, n, here);
ASSERTCMP(n, >=, 0);
if (n == 1)
rxrpc_set_service_reap_timer(conn->params.local->rxnet,
@@ -420,7 +421,7 @@ void rxrpc_service_connection_reaper(struct work_struct *work)
*/
if (atomic_cmpxchg(&conn->usage, 1, 0) != 1)
continue;
- trace_rxrpc_conn(conn, rxrpc_conn_reap_service, 0, NULL);
+ trace_rxrpc_conn(conn->debug_id, rxrpc_conn_reap_service, 0, NULL);
if (rxrpc_conn_is_client(conn))
BUG();
diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c
index b30e13f6d95f..123d6ceab15c 100644
--- a/net/rxrpc/conn_service.c
+++ b/net/rxrpc/conn_service.c
@@ -134,7 +134,7 @@ struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *rxn
list_add_tail(&conn->proc_link, &rxnet->conn_proc_list);
write_unlock(&rxnet->conn_lock);
- trace_rxrpc_conn(conn, rxrpc_conn_new_service,
+ trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_service,
atomic_read(&conn->usage),
__builtin_return_address(0));
}
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index c97ebdc043e4..48f67a9b1037 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -147,10 +147,16 @@ void rxrpc_error_report(struct sock *sk)
{
struct sock_exterr_skb *serr;
struct sockaddr_rxrpc srx;
- struct rxrpc_local *local = sk->sk_user_data;
+ struct rxrpc_local *local;
struct rxrpc_peer *peer;
struct sk_buff *skb;
+ rcu_read_lock();
+ local = rcu_dereference_sk_user_data(sk);
+ if (unlikely(!local)) {
+ rcu_read_unlock();
+ return;
+ }
_enter("%p{%d}", sk, local->debug_id);
/* Clear the outstanding error value on the socket so that it doesn't
@@ -160,6 +166,7 @@ void rxrpc_error_report(struct sock *sk)
skb = sock_dequeue_err_skb(sk);
if (!skb) {
+ rcu_read_unlock();
_leave("UDP socket errqueue empty");
return;
}
@@ -167,11 +174,11 @@ void rxrpc_error_report(struct sock *sk)
serr = SKB_EXT_ERR(skb);
if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) {
_leave("UDP empty message");
+ rcu_read_unlock();
rxrpc_free_skb(skb, rxrpc_skb_freed);
return;
}
- rcu_read_lock();
peer = rxrpc_lookup_peer_icmp_rcu(local, skb, &srx);
if (peer && !rxrpc_get_peer_maybe(peer))
peer = NULL;
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 9c3ac96f71cb..64830d8c1fdb 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -216,7 +216,7 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp)
peer = kzalloc(sizeof(struct rxrpc_peer), gfp);
if (peer) {
atomic_set(&peer->usage, 1);
- peer->local = local;
+ peer->local = rxrpc_get_local(local);
INIT_HLIST_HEAD(&peer->error_targets);
peer->service_conns = RB_ROOT;
seqlock_init(&peer->service_conn_lock);
@@ -307,7 +307,6 @@ void rxrpc_new_incoming_peer(struct rxrpc_sock *rx, struct rxrpc_local *local,
unsigned long hash_key;
hash_key = rxrpc_peer_hash_key(local, &peer->srx);
- peer->local = local;
rxrpc_init_peer(rx, peer, hash_key);
spin_lock(&rxnet->peer_hash_lock);
@@ -382,7 +381,7 @@ struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *peer)
int n;
n = atomic_inc_return(&peer->usage);
- trace_rxrpc_peer(peer, rxrpc_peer_got, n, here);
+ trace_rxrpc_peer(peer->debug_id, rxrpc_peer_got, n, here);
return peer;
}
@@ -396,7 +395,7 @@ struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer)
if (peer) {
int n = atomic_fetch_add_unless(&peer->usage, 1, 0);
if (n > 0)
- trace_rxrpc_peer(peer, rxrpc_peer_got, n + 1, here);
+ trace_rxrpc_peer(peer->debug_id, rxrpc_peer_got, n + 1, here);
else
peer = NULL;
}
@@ -417,6 +416,7 @@ static void __rxrpc_put_peer(struct rxrpc_peer *peer)
list_del_init(&peer->keepalive_link);
spin_unlock_bh(&rxnet->peer_hash_lock);
+ rxrpc_put_local(peer->local);
kfree_rcu(peer, rcu);
}
@@ -426,11 +426,13 @@ static void __rxrpc_put_peer(struct rxrpc_peer *peer)
void rxrpc_put_peer(struct rxrpc_peer *peer)
{
const void *here = __builtin_return_address(0);
+ unsigned int debug_id;
int n;
if (peer) {
+ debug_id = peer->debug_id;
n = atomic_dec_return(&peer->usage);
- trace_rxrpc_peer(peer, rxrpc_peer_put, n, here);
+ trace_rxrpc_peer(debug_id, rxrpc_peer_put, n, here);
if (n == 0)
__rxrpc_put_peer(peer);
}
@@ -443,13 +445,15 @@ void rxrpc_put_peer(struct rxrpc_peer *peer)
void rxrpc_put_peer_locked(struct rxrpc_peer *peer)
{
const void *here = __builtin_return_address(0);
+ unsigned int debug_id = peer->debug_id;
int n;
n = atomic_dec_return(&peer->usage);
- trace_rxrpc_peer(peer, rxrpc_peer_put, n, here);
+ trace_rxrpc_peer(debug_id, rxrpc_peer_put, n, here);
if (n == 0) {
hash_del_rcu(&peer->hash_link);
list_del_init(&peer->keepalive_link);
+ rxrpc_put_local(peer->local);
kfree_rcu(peer, rcu);
}
}
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index 3b0becb12041..a4090797c9b2 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -251,8 +251,8 @@ static int rxrpc_verify_packet(struct rxrpc_call *call, struct sk_buff *skb,
seq += subpacket;
}
- return call->conn->security->verify_packet(call, skb, offset, len,
- seq, cksum);
+ return call->security->verify_packet(call, skb, offset, len,
+ seq, cksum);
}
/*
@@ -291,7 +291,7 @@ static int rxrpc_locate_data(struct rxrpc_call *call, struct sk_buff *skb,
*_offset = offset;
*_len = len;
- call->conn->security->locate_data(call, skb, _offset, _len);
+ call->security->locate_data(call, skb, _offset, _len);
return 0;
}
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 6a1547b270fe..813fd6888142 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -419,7 +419,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
call->tx_winsize)
sp->hdr.flags |= RXRPC_MORE_PACKETS;
- ret = conn->security->secure_packet(
+ ret = call->security->secure_packet(
call, skb, skb->mark, skb->head);
if (ret < 0)
goto out;
@@ -661,6 +661,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
case RXRPC_CALL_SERVER_PREALLOC:
case RXRPC_CALL_SERVER_SECURING:
case RXRPC_CALL_SERVER_ACCEPTING:
+ rxrpc_put_call(call, rxrpc_call_put);
ret = -EBUSY;
goto error_release_sock;
default:
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 2558f00f6b3e..69d4676a402f 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -832,8 +832,7 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb)
}
static const struct nla_policy tcf_action_policy[TCA_ACT_MAX + 1] = {
- [TCA_ACT_KIND] = { .type = NLA_NUL_STRING,
- .len = IFNAMSIZ - 1 },
+ [TCA_ACT_KIND] = { .type = NLA_STRING },
[TCA_ACT_INDEX] = { .type = NLA_U32 },
[TCA_ACT_COOKIE] = { .type = NLA_BINARY,
.len = TC_COOKIE_MAX_SIZE },
@@ -865,8 +864,10 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
NL_SET_ERR_MSG(extack, "TC action kind must be specified");
goto err_out;
}
- nla_strlcpy(act_name, kind, IFNAMSIZ);
-
+ if (nla_strlcpy(act_name, kind, IFNAMSIZ) >= IFNAMSIZ) {
+ NL_SET_ERR_MSG(extack, "TC action name too long");
+ goto err_out;
+ }
if (tb[TCA_ACT_COOKIE]) {
cookie = nla_memdup_cookie(tb);
if (!cookie) {
@@ -1352,11 +1353,16 @@ static int tcf_action_add(struct net *net, struct nlattr *nla,
struct netlink_ext_ack *extack)
{
size_t attr_size = 0;
- int ret = 0;
+ int loop, ret;
struct tc_action *actions[TCA_ACT_MAX_PRIO] = {};
- ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, actions,
- &attr_size, true, extack);
+ for (loop = 0; loop < 10; loop++) {
+ ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0,
+ actions, &attr_size, true, extack);
+ if (ret != -EAGAIN)
+ break;
+ }
+
if (ret < 0)
return ret;
ret = tcf_add_notify(net, n, actions, portid, attr_size, extack);
@@ -1406,11 +1412,8 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n,
*/
if (n->nlmsg_flags & NLM_F_REPLACE)
ovr = 1;
-replay:
ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, portid, ovr,
extack);
- if (ret == -EAGAIN)
- goto replay;
break;
case RTM_DELACTION:
ret = tca_action_gd(net, tca[TCA_ACT_TAB], n,
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 9ce073a05414..08923b21e566 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -484,7 +484,11 @@ static int __init mirred_init_module(void)
return err;
pr_info("Mirror/redirect action on\n");
- return tcf_register_action(&act_mirred_ops, &mirred_net_ops);
+ err = tcf_register_action(&act_mirred_ops, &mirred_net_ops);
+ if (err)
+ unregister_netdevice_notifier(&mirred_device_notifier);
+
+ return err;
}
static void __exit mirred_cleanup_module(void)
diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c
index e168df0e008a..4cf6c553bb0b 100644
--- a/net/sched/act_mpls.c
+++ b/net/sched/act_mpls.c
@@ -55,7 +55,7 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a,
struct tcf_mpls *m = to_mpls(a);
struct tcf_mpls_params *p;
__be32 new_lse;
- int ret;
+ int ret, mac_len;
tcf_lastuse_update(&m->tcf_tm);
bstats_cpu_update(this_cpu_ptr(m->common.cpu_bstats), skb);
@@ -63,8 +63,12 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a,
/* Ensure 'data' points at mac_header prior calling mpls manipulating
* functions.
*/
- if (skb_at_tc_ingress(skb))
+ if (skb_at_tc_ingress(skb)) {
skb_push_rcsum(skb, skb->mac_len);
+ mac_len = skb->mac_len;
+ } else {
+ mac_len = skb_network_header(skb) - skb_mac_header(skb);
+ }
ret = READ_ONCE(m->tcf_action);
@@ -72,12 +76,12 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a,
switch (p->tcfm_action) {
case TCA_MPLS_ACT_POP:
- if (skb_mpls_pop(skb, p->tcfm_proto))
+ if (skb_mpls_pop(skb, p->tcfm_proto, mac_len))
goto drop;
break;
case TCA_MPLS_ACT_PUSH:
new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb->protocol));
- if (skb_mpls_push(skb, new_lse, p->tcfm_proto))
+ if (skb_mpls_push(skb, new_lse, p->tcfm_proto, mac_len))
goto drop;
break;
case TCA_MPLS_ACT_MODIFY:
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 64584a1df425..8717c0b26c90 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -162,11 +162,22 @@ static inline u32 tcf_auto_prio(struct tcf_proto *tp)
return TC_H_MAJ(first);
}
+static bool tcf_proto_check_kind(struct nlattr *kind, char *name)
+{
+ if (kind)
+ return nla_strlcpy(name, kind, IFNAMSIZ) >= IFNAMSIZ;
+ memset(name, 0, IFNAMSIZ);
+ return false;
+}
+
static bool tcf_proto_is_unlocked(const char *kind)
{
const struct tcf_proto_ops *ops;
bool ret;
+ if (strlen(kind) == 0)
+ return false;
+
ops = tcf_proto_lookup_ops(kind, false, NULL);
/* On error return false to take rtnl lock. Proto lookup/create
* functions will perform lookup again and properly handle errors.
@@ -1843,6 +1854,7 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
{
struct net *net = sock_net(skb->sk);
struct nlattr *tca[TCA_MAX + 1];
+ char name[IFNAMSIZ];
struct tcmsg *t;
u32 protocol;
u32 prio;
@@ -1899,13 +1911,19 @@ replay:
if (err)
return err;
+ if (tcf_proto_check_kind(tca[TCA_KIND], name)) {
+ NL_SET_ERR_MSG(extack, "Specified TC filter name too long");
+ err = -EINVAL;
+ goto errout;
+ }
+
/* Take rtnl mutex if rtnl_held was set to true on previous iteration,
* block is shared (no qdisc found), qdisc is not unlocked, classifier
* type is not specified, classifier is not unlocked.
*/
if (rtnl_held ||
(q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) ||
- !tca[TCA_KIND] || !tcf_proto_is_unlocked(nla_data(tca[TCA_KIND]))) {
+ !tcf_proto_is_unlocked(name)) {
rtnl_held = true;
rtnl_lock();
}
@@ -2063,6 +2081,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
{
struct net *net = sock_net(skb->sk);
struct nlattr *tca[TCA_MAX + 1];
+ char name[IFNAMSIZ];
struct tcmsg *t;
u32 protocol;
u32 prio;
@@ -2102,13 +2121,18 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
if (err)
return err;
+ if (tcf_proto_check_kind(tca[TCA_KIND], name)) {
+ NL_SET_ERR_MSG(extack, "Specified TC filter name too long");
+ err = -EINVAL;
+ goto errout;
+ }
/* Take rtnl mutex if flushing whole chain, block is shared (no qdisc
* found), qdisc is not unlocked, classifier type is not specified,
* classifier is not unlocked.
*/
if (!prio ||
(q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) ||
- !tca[TCA_KIND] || !tcf_proto_is_unlocked(nla_data(tca[TCA_KIND]))) {
+ !tcf_proto_is_unlocked(name)) {
rtnl_held = true;
rtnl_lock();
}
@@ -2216,6 +2240,7 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
{
struct net *net = sock_net(skb->sk);
struct nlattr *tca[TCA_MAX + 1];
+ char name[IFNAMSIZ];
struct tcmsg *t;
u32 protocol;
u32 prio;
@@ -2252,12 +2277,17 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
if (err)
return err;
+ if (tcf_proto_check_kind(tca[TCA_KIND], name)) {
+ NL_SET_ERR_MSG(extack, "Specified TC filter name too long");
+ err = -EINVAL;
+ goto errout;
+ }
/* Take rtnl mutex if block is shared (no qdisc found), qdisc is not
* unlocked, classifier type is not specified, classifier is not
* unlocked.
*/
if ((q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) ||
- !tca[TCA_KIND] || !tcf_proto_is_unlocked(nla_data(tca[TCA_KIND]))) {
+ !tcf_proto_is_unlocked(name)) {
rtnl_held = true;
rtnl_lock();
}
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index 82bd14e7ac93..3177dcb17316 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -446,7 +446,7 @@ META_COLLECTOR(int_sk_wmem_queued)
*err = -1;
return;
}
- dst->value = sk->sk_wmem_queued;
+ dst->value = READ_ONCE(sk->sk_wmem_queued);
}
META_COLLECTOR(int_sk_fwd_alloc)
@@ -554,7 +554,7 @@ META_COLLECTOR(int_sk_rcvlowat)
*err = -1;
return;
}
- dst->value = sk->sk_rcvlowat;
+ dst->value = READ_ONCE(sk->sk_rcvlowat);
}
META_COLLECTOR(int_sk_rcvtimeo)
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 81d58b280612..1047825d9f48 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1390,8 +1390,7 @@ check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w)
}
const struct nla_policy rtm_tca_policy[TCA_MAX + 1] = {
- [TCA_KIND] = { .type = NLA_NUL_STRING,
- .len = IFNAMSIZ - 1 },
+ [TCA_KIND] = { .type = NLA_STRING },
[TCA_RATE] = { .type = NLA_BINARY,
.len = sizeof(struct tc_estimator) },
[TCA_STAB] = { .type = NLA_NESTED },
diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c
index cebfb65d8556..b1da5589a0c6 100644
--- a/net/sched/sch_etf.c
+++ b/net/sched/sch_etf.c
@@ -177,7 +177,7 @@ static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch,
parent = *p;
skb = rb_to_skb(parent);
- if (ktime_after(txtime, skb->tstamp)) {
+ if (ktime_compare(txtime, skb->tstamp) >= 0) {
p = &parent->rb_right;
leftmost = false;
} else {
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 0e44039e729c..42e557d48e4e 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -509,6 +509,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
if (skb->ip_summed == CHECKSUM_PARTIAL &&
skb_checksum_help(skb)) {
qdisc_drop(skb, sch, to_free);
+ skb = NULL;
goto finish_segs;
}
@@ -593,9 +594,10 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
finish_segs:
if (segs) {
unsigned int len, last_len;
- int nb = 0;
+ int nb;
- len = skb->len;
+ len = skb ? skb->len : 0;
+ nb = skb ? 1 : 0;
while (segs) {
skb2 = segs->next;
@@ -612,7 +614,10 @@ finish_segs:
}
segs = skb2;
}
- qdisc_tree_reduce_backlog(sch, -nb, prev_len - len);
+ /* Parent qdiscs accounted for 1 skb of size @prev_len */
+ qdisc_tree_reduce_backlog(sch, -(nb - 1), -(len - prev_len));
+ } else if (!skb) {
+ return NET_XMIT_DROP;
}
return NET_XMIT_SUCCESS;
}
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 68b543f85a96..6719a65169d4 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -1341,6 +1341,10 @@ static int taprio_parse_clockid(struct Qdisc *sch, struct nlattr **tb,
NL_SET_ERR_MSG(extack, "Specifying a 'clockid' is mandatory");
goto out;
}
+
+ /* Everything went ok, return success. */
+ err = 0;
+
out:
return err;
}
diff --git a/net/sctp/diag.c b/net/sctp/diag.c
index fc9a4c6629ce..0851166b9175 100644
--- a/net/sctp/diag.c
+++ b/net/sctp/diag.c
@@ -175,7 +175,7 @@ static int inet_sctp_diag_fill(struct sock *sk, struct sctp_association *asoc,
mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc;
mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued;
mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc);
- mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len;
+ mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len);
mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops);
if (nla_put(skb, INET_DIAG_SKMEMINFO, sizeof(mem), &mem) < 0)
diff --git a/net/sctp/input.c b/net/sctp/input.c
index 5a070fb5b278..2277981559d0 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -243,7 +243,7 @@ int sctp_rcv(struct sk_buff *skb)
bh_lock_sock(sk);
}
- if (sock_owned_by_user(sk)) {
+ if (sock_owned_by_user(sk) || !sctp_newsk_ready(sk)) {
if (sctp_add_backlog(sk, skb)) {
bh_unlock_sock(sk);
sctp_chunk_free(chunk);
@@ -321,8 +321,8 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb)
local_bh_disable();
bh_lock_sock(sk);
- if (sock_owned_by_user(sk)) {
- if (sk_add_backlog(sk, skb, sk->sk_rcvbuf))
+ if (sock_owned_by_user(sk) || !sctp_newsk_ready(sk)) {
+ if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf)))
sctp_chunk_free(chunk);
else
backloged = 1;
@@ -336,7 +336,13 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb)
if (backloged)
return 0;
} else {
- sctp_inq_push(inqueue, chunk);
+ if (!sctp_newsk_ready(sk)) {
+ if (!sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf)))
+ return 0;
+ sctp_chunk_free(chunk);
+ } else {
+ sctp_inq_push(inqueue, chunk);
+ }
}
done:
@@ -358,7 +364,7 @@ static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb)
struct sctp_ep_common *rcvr = chunk->rcvr;
int ret;
- ret = sk_add_backlog(sk, skb, sk->sk_rcvbuf);
+ ret = sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf));
if (!ret) {
/* Hold the assoc/ep while hanging on the backlog queue.
* This way, we know structures we need will not disappear
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 939b8d2595bc..5ca0ec0e823c 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -9500,7 +9500,7 @@ struct proto sctp_prot = {
.backlog_rcv = sctp_backlog_rcv,
.hash = sctp_hash,
.unhash = sctp_unhash,
- .get_port = sctp_get_port,
+ .no_autobind = true,
.obj_size = sizeof(struct sctp_sock),
.useroffset = offsetof(struct sctp_sock, subscribe),
.usersize = offsetof(struct sctp_sock, initmsg) -
@@ -9542,7 +9542,7 @@ struct proto sctpv6_prot = {
.backlog_rcv = sctp_backlog_rcv,
.hash = sctp_hash,
.unhash = sctp_unhash,
- .get_port = sctp_get_port,
+ .no_autobind = true,
.obj_size = sizeof(struct sctp6_sock),
.useroffset = offsetof(struct sctp6_sock, sctp.subscribe),
.usersize = offsetof(struct sctp6_sock, sctp.initmsg) -
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 4ca50ddf8d16..88556f0251ab 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -213,7 +213,7 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini)
lgr = kzalloc(sizeof(*lgr), GFP_KERNEL);
if (!lgr) {
rc = SMC_CLC_DECL_MEM;
- goto out;
+ goto ism_put_vlan;
}
lgr->is_smcd = ini->is_smcd;
lgr->sync_err = 0;
@@ -289,6 +289,9 @@ clear_llc_lnk:
smc_llc_link_clear(lnk);
free_lgr:
kfree(lgr);
+ism_put_vlan:
+ if (ini->is_smcd && ini->vlan_id)
+ smc_ism_put_vlan(ini->ism_dev, ini->vlan_id);
out:
if (rc < 0) {
if (rc == -ENOMEM)
diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c
index 413a6abf227e..97e8369002d7 100644
--- a/net/smc/smc_rx.c
+++ b/net/smc/smc_rx.c
@@ -211,8 +211,7 @@ int smc_rx_wait(struct smc_sock *smc, long *timeo,
rc = sk_wait_event(sk, timeo,
sk->sk_err ||
sk->sk_shutdown & RCV_SHUTDOWN ||
- fcrit(conn) ||
- smc_cdc_rxed_any_close_or_senddone(conn),
+ fcrit(conn),
&wait);
remove_wait_queue(sk_sleep(sk), &wait);
sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
@@ -262,6 +261,18 @@ static int smc_rx_recv_urg(struct smc_sock *smc, struct msghdr *msg, int len,
return -EAGAIN;
}
+static bool smc_rx_recvmsg_data_available(struct smc_sock *smc)
+{
+ struct smc_connection *conn = &smc->conn;
+
+ if (smc_rx_data_available(conn))
+ return true;
+ else if (conn->urg_state == SMC_URG_VALID)
+ /* we received a single urgent Byte - skip */
+ smc_rx_update_cons(smc, 0);
+ return false;
+}
+
/* smc_rx_recvmsg - receive data from RMBE
* @msg: copy data to receive buffer
* @pipe: copy data to pipe if set - indicates splice() call
@@ -303,16 +314,18 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg,
if (read_done >= target || (pipe && read_done))
break;
- if (atomic_read(&conn->bytes_to_rcv))
+ if (smc_rx_recvmsg_data_available(smc))
goto copy;
- else if (conn->urg_state == SMC_URG_VALID)
- /* we received a single urgent Byte - skip */
- smc_rx_update_cons(smc, 0);
if (sk->sk_shutdown & RCV_SHUTDOWN ||
- smc_cdc_rxed_any_close_or_senddone(conn) ||
- conn->local_tx_ctrl.conn_state_flags.peer_conn_abort)
+ conn->local_tx_ctrl.conn_state_flags.peer_conn_abort) {
+ /* smc_cdc_msg_recv_action() could have run after
+ * above smc_rx_recvmsg_data_available()
+ */
+ if (smc_rx_recvmsg_data_available(smc))
+ goto copy;
break;
+ }
if (read_done) {
if (sk->sk_err ||
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 3b9f8cc328f5..f8bbc4aab213 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2119,13 +2119,13 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb)
struct tipc_msg *hdr = buf_msg(skb);
if (unlikely(msg_in_group(hdr)))
- return sk->sk_rcvbuf;
+ return READ_ONCE(sk->sk_rcvbuf);
if (unlikely(!msg_connected(hdr)))
- return sk->sk_rcvbuf << msg_importance(hdr);
+ return READ_ONCE(sk->sk_rcvbuf) << msg_importance(hdr);
if (likely(tsk->peer_caps & TIPC_BLOCK_FLOWCTL))
- return sk->sk_rcvbuf;
+ return READ_ONCE(sk->sk_rcvbuf);
return FLOWCTL_MSG_LIM;
}
@@ -3790,7 +3790,7 @@ int tipc_sk_dump(struct sock *sk, u16 dqueues, char *buf)
i += scnprintf(buf + i, sz - i, " %d", sk->sk_sndbuf);
i += scnprintf(buf + i, sz - i, " | %d", sk_rmem_alloc_get(sk));
i += scnprintf(buf + i, sz - i, " %d", sk->sk_rcvbuf);
- i += scnprintf(buf + i, sz - i, " | %d\n", sk->sk_backlog.len);
+ i += scnprintf(buf + i, sz - i, " | %d\n", READ_ONCE(sk->sk_backlog.len));
if (dqueues & TIPC_DUMP_SK_SNDQ) {
i += scnprintf(buf + i, sz - i, "sk_write_queue: ");
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index a666ef8fc54e..481f7f8a1655 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -204,10 +204,14 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk,
return virtio_transport_get_ops()->send_pkt(pkt);
}
-static void virtio_transport_inc_rx_pkt(struct virtio_vsock_sock *vvs,
+static bool virtio_transport_inc_rx_pkt(struct virtio_vsock_sock *vvs,
struct virtio_vsock_pkt *pkt)
{
+ if (vvs->rx_bytes + pkt->len > vvs->buf_alloc)
+ return false;
+
vvs->rx_bytes += pkt->len;
+ return true;
}
static void virtio_transport_dec_rx_pkt(struct virtio_vsock_sock *vvs,
@@ -458,6 +462,9 @@ void virtio_transport_set_buffer_size(struct vsock_sock *vsk, u64 val)
vvs->buf_size_max = val;
vvs->buf_size = val;
vvs->buf_alloc = val;
+
+ virtio_transport_send_credit_update(vsk, VIRTIO_VSOCK_TYPE_STREAM,
+ NULL);
}
EXPORT_SYMBOL_GPL(virtio_transport_set_buffer_size);
@@ -876,14 +883,18 @@ virtio_transport_recv_enqueue(struct vsock_sock *vsk,
struct virtio_vsock_pkt *pkt)
{
struct virtio_vsock_sock *vvs = vsk->trans;
- bool free_pkt = false;
+ bool can_enqueue, free_pkt = false;
pkt->len = le32_to_cpu(pkt->hdr.len);
pkt->off = 0;
spin_lock_bh(&vvs->rx_lock);
- virtio_transport_inc_rx_pkt(vvs, pkt);
+ can_enqueue = virtio_transport_inc_rx_pkt(vvs, pkt);
+ if (!can_enqueue) {
+ free_pkt = true;
+ goto out;
+ }
/* Try to copy small packets into the buffer of last packet queued,
* to avoid wasting memory queueing the entire buffer with a small
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 141cdb171665..4453dd375de9 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -13682,7 +13682,7 @@ static int nl80211_get_ftm_responder_stats(struct sk_buff *skb,
hdr = nl80211hdr_put(msg, info->snd_portid, info->snd_seq, 0,
NL80211_CMD_GET_FTM_RESPONDER_STATS);
if (!hdr)
- return -ENOBUFS;
+ goto nla_put_failure;
if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex))
goto nla_put_failure;
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 420c4207ab59..446c76d44e65 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -3883,6 +3883,7 @@ bool regulatory_pre_cac_allowed(struct wiphy *wiphy)
return pre_cac_allowed;
}
+EXPORT_SYMBOL(regulatory_pre_cac_allowed);
void regulatory_propagate_dfs_state(struct wiphy *wiphy,
struct cfg80211_chan_def *chandef,
diff --git a/net/wireless/reg.h b/net/wireless/reg.h
index 504133d76de4..dc8f689bd469 100644
--- a/net/wireless/reg.h
+++ b/net/wireless/reg.h
@@ -156,14 +156,6 @@ bool regulatory_indoor_allowed(void);
#define REG_PRE_CAC_EXPIRY_GRACE_MS 2000
/**
- * regulatory_pre_cac_allowed - if pre-CAC allowed in the current dfs domain
- * @wiphy: wiphy for which pre-CAC capability is checked.
-
- * Pre-CAC is allowed only in ETSI domain.
- */
-bool regulatory_pre_cac_allowed(struct wiphy *wiphy);
-
-/**
* regulatory_propagate_dfs_state - Propagate DFS channel state to other wiphys
* @wiphy - wiphy on which radar is detected and the event will be propagated
* to other available wiphys having the same DFS domain
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index ff1016607f0b..aef240fdf8df 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -1703,8 +1703,7 @@ cfg80211_parse_mbssid_frame_data(struct wiphy *wiphy,
static void
cfg80211_update_notlisted_nontrans(struct wiphy *wiphy,
struct cfg80211_bss *nontrans_bss,
- struct ieee80211_mgmt *mgmt, size_t len,
- gfp_t gfp)
+ struct ieee80211_mgmt *mgmt, size_t len)
{
u8 *ie, *new_ie, *pos;
const u8 *nontrans_ssid, *trans_ssid, *mbssid;
@@ -1715,6 +1714,8 @@ cfg80211_update_notlisted_nontrans(struct wiphy *wiphy,
const struct cfg80211_bss_ies *old;
u8 cpy_len;
+ lockdep_assert_held(&wiphy_to_rdev(wiphy)->bss_lock);
+
ie = mgmt->u.probe_resp.variable;
new_ie_len = ielen;
@@ -1731,23 +1732,22 @@ cfg80211_update_notlisted_nontrans(struct wiphy *wiphy,
if (!mbssid || mbssid < trans_ssid)
return;
new_ie_len -= mbssid[1];
- rcu_read_lock();
+
nontrans_ssid = ieee80211_bss_get_ie(nontrans_bss, WLAN_EID_SSID);
- if (!nontrans_ssid) {
- rcu_read_unlock();
+ if (!nontrans_ssid)
return;
- }
+
new_ie_len += nontrans_ssid[1];
- rcu_read_unlock();
/* generate new ie for nontrans BSS
* 1. replace SSID with nontrans BSS' SSID
* 2. skip MBSSID IE
*/
- new_ie = kzalloc(new_ie_len, gfp);
+ new_ie = kzalloc(new_ie_len, GFP_ATOMIC);
if (!new_ie)
return;
- new_ies = kzalloc(sizeof(*new_ies) + new_ie_len, gfp);
+
+ new_ies = kzalloc(sizeof(*new_ies) + new_ie_len, GFP_ATOMIC);
if (!new_ies)
goto out_free;
@@ -1901,6 +1901,8 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy,
cfg80211_parse_mbssid_frame_data(wiphy, data, mgmt, len,
&non_tx_data, gfp);
+ spin_lock_bh(&wiphy_to_rdev(wiphy)->bss_lock);
+
/* check if the res has other nontransmitting bss which is not
* in MBSSID IE
*/
@@ -1915,8 +1917,9 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy,
ies2 = rcu_access_pointer(tmp_bss->ies);
if (ies2->tsf < ies1->tsf)
cfg80211_update_notlisted_nontrans(wiphy, tmp_bss,
- mgmt, len, gfp);
+ mgmt, len);
}
+ spin_unlock_bh(&wiphy_to_rdev(wiphy)->bss_lock);
return res;
}
diff --git a/net/wireless/wext-sme.c b/net/wireless/wext-sme.c
index c67d7a82ab13..73fd0eae08ca 100644
--- a/net/wireless/wext-sme.c
+++ b/net/wireless/wext-sme.c
@@ -202,6 +202,7 @@ int cfg80211_mgd_wext_giwessid(struct net_device *dev,
struct iw_point *data, char *ssid)
{
struct wireless_dev *wdev = dev->ieee80211_ptr;
+ int ret = 0;
/* call only for station! */
if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION))
@@ -219,7 +220,10 @@ int cfg80211_mgd_wext_giwessid(struct net_device *dev,
if (ie) {
data->flags = 1;
data->length = ie[1];
- memcpy(ssid, ie + 2, data->length);
+ if (data->length > IW_ESSID_MAX_SIZE)
+ ret = -EINVAL;
+ else
+ memcpy(ssid, ie + 2, data->length);
}
rcu_read_unlock();
} else if (wdev->wext.connect.ssid && wdev->wext.connect.ssid_len) {
@@ -229,7 +233,7 @@ int cfg80211_mgd_wext_giwessid(struct net_device *dev,
}
wdev_unlock(wdev);
- return 0;
+ return ret;
}
int cfg80211_mgd_wext_siwap(struct net_device *dev,
diff --git a/net/x25/x25_dev.c b/net/x25/x25_dev.c
index 5c111bc3c8ea..00e782335cb0 100644
--- a/net/x25/x25_dev.c
+++ b/net/x25/x25_dev.c
@@ -55,7 +55,7 @@ static int x25_receive_data(struct sk_buff *skb, struct x25_neigh *nb)
if (!sock_owned_by_user(sk)) {
queued = x25_process_rx_frame(sk, skb);
} else {
- queued = !sk_add_backlog(sk, skb, sk->sk_rcvbuf);
+ queued = !sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf));
}
bh_unlock_sock(sk);
sock_put(sk);
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index fa8fbb8fa3c8..9044073fbf22 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -305,9 +305,8 @@ out:
}
EXPORT_SYMBOL(xsk_umem_consume_tx);
-static int xsk_zc_xmit(struct sock *sk)
+static int xsk_zc_xmit(struct xdp_sock *xs)
{
- struct xdp_sock *xs = xdp_sk(sk);
struct net_device *dev = xs->dev;
return dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id,
@@ -327,11 +326,10 @@ static void xsk_destruct_skb(struct sk_buff *skb)
sock_wfree(skb);
}
-static int xsk_generic_xmit(struct sock *sk, struct msghdr *m,
- size_t total_len)
+static int xsk_generic_xmit(struct sock *sk)
{
- u32 max_batch = TX_BATCH_SIZE;
struct xdp_sock *xs = xdp_sk(sk);
+ u32 max_batch = TX_BATCH_SIZE;
bool sent_frame = false;
struct xdp_desc desc;
struct sk_buff *skb;
@@ -394,6 +392,18 @@ out:
return err;
}
+static int __xsk_sendmsg(struct sock *sk)
+{
+ struct xdp_sock *xs = xdp_sk(sk);
+
+ if (unlikely(!(xs->dev->flags & IFF_UP)))
+ return -ENETDOWN;
+ if (unlikely(!xs->tx))
+ return -ENOBUFS;
+
+ return xs->zc ? xsk_zc_xmit(xs) : xsk_generic_xmit(sk);
+}
+
static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
{
bool need_wait = !(m->msg_flags & MSG_DONTWAIT);
@@ -402,21 +412,18 @@ static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
if (unlikely(!xsk_is_bound(xs)))
return -ENXIO;
- if (unlikely(!(xs->dev->flags & IFF_UP)))
- return -ENETDOWN;
- if (unlikely(!xs->tx))
- return -ENOBUFS;
- if (need_wait)
+ if (unlikely(need_wait))
return -EOPNOTSUPP;
- return (xs->zc) ? xsk_zc_xmit(sk) : xsk_generic_xmit(sk, m, total_len);
+ return __xsk_sendmsg(sk);
}
static unsigned int xsk_poll(struct file *file, struct socket *sock,
struct poll_table_struct *wait)
{
unsigned int mask = datagram_poll(file, sock, wait);
- struct xdp_sock *xs = xdp_sk(sock->sk);
+ struct sock *sk = sock->sk;
+ struct xdp_sock *xs = xdp_sk(sk);
struct net_device *dev;
struct xdp_umem *umem;
@@ -426,9 +433,14 @@ static unsigned int xsk_poll(struct file *file, struct socket *sock,
dev = xs->dev;
umem = xs->umem;
- if (umem->need_wakeup)
- dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id,
- umem->need_wakeup);
+ if (umem->need_wakeup) {
+ if (dev->netdev_ops->ndo_xsk_wakeup)
+ dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id,
+ umem->need_wakeup);
+ else
+ /* Poll needs to drive Tx also in copy mode */
+ __xsk_sendmsg(sk);
+ }
if (xs->rx && !xskq_empty_desc(xs->rx))
mask |= POLLIN | POLLRDNORM;