summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-08-26 00:03:58 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2022-08-26 00:03:58 +0300
commit4c612826bec1441214816827979b62f84a097e91 (patch)
treed87a97b450d21edc0fafcfcb1e5b13020249bd60 /net
parent3f5c20055a640b3758ece75dcaa6ac974fcae26d (diff)
parentd974730c8884cd784810b4f2fe903ac882a5fec9 (diff)
downloadlinux-4c612826bec1441214816827979b62f84a097e91.tar.xz
Merge tag 'net-6.0-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski: "Including fixes from ipsec and netfilter (with one broken Fixes tag). Current release - new code bugs: - dsa: don't dereference NULL extack in dsa_slave_changeupper() - dpaa: fix <1G ethernet on LS1046ARDB - neigh: don't call kfree_skb() under spin_lock_irqsave() Previous releases - regressions: - r8152: fix the RX FIFO settings when suspending - dsa: microchip: keep compatibility with device tree blobs with no phy-mode - Revert "net: macsec: update SCI upon MAC address change." - Revert "xfrm: update SA curlft.use_time", comply with RFC 2367 Previous releases - always broken: - netfilter: conntrack: work around exceeded TCP receive window - ipsec: fix a null pointer dereference of dst->dev on a metadata dst in xfrm_lookup_with_ifid - moxa: get rid of asymmetry in DMA mapping/unmapping - dsa: microchip: make learning configurable and keep it off while standalone - ice: xsk: prohibit usage of non-balanced queue id - rxrpc: fix locking in rxrpc's sendmsg Misc: - another chunk of sysctl data race silencing" * tag 'net-6.0-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (87 commits) net: lantiq_xrx200: restore buffer if memory allocation failed net: lantiq_xrx200: fix lock under memory pressure net: lantiq_xrx200: confirm skb is allocated before using net: stmmac: work around sporadic tx issue on link-up ionic: VF initial random MAC address if no assigned mac ionic: fix up issues with handling EAGAIN on FW cmds ionic: clear broken state on generation change rxrpc: Fix locking in rxrpc's sendmsg net: ethernet: mtk_eth_soc: fix hw hash reporting for MTK_NETSYS_V2 MAINTAINERS: rectify file entry in BONDING DRIVER i40e: Fix incorrect address type for IPv6 flow rules ixgbe: stop resetting SYSTIME in ixgbe_ptp_start_cyclecounter net: Fix a data-race around sysctl_somaxconn. net: Fix a data-race around netdev_unregister_timeout_secs. net: Fix a data-race around gro_normal_batch. net: Fix data-races around sysctl_devconf_inherit_init_net. net: Fix data-races around sysctl_fb_tunnels_only_for_init_net. net: Fix a data-race around netdev_budget_usecs. net: Fix data-races around sysctl_max_skb_frags. net: Fix a data-race around netdev_budget. ...
Diffstat (limited to 'net')
-rw-r--r--net/bridge/netfilter/ebtable_broute.c8
-rw-r--r--net/bridge/netfilter/ebtable_filter.c8
-rw-r--r--net/bridge/netfilter/ebtable_nat.c8
-rw-r--r--net/bridge/netfilter/ebtables.c8
-rw-r--r--net/core/bpf_sk_storage.c5
-rw-r--r--net/core/dev.c20
-rw-r--r--net/core/filter.c13
-rw-r--r--net/core/gro_cells.c2
-rw-r--r--net/core/neighbour.c12
-rw-r--r--net/core/skbuff.c7
-rw-r--r--net/core/sock.c18
-rw-r--r--net/core/sysctl_net_core.c15
-rw-r--r--net/dsa/slave.c2
-rw-r--r--net/ipv4/devinet.c16
-rw-r--r--net/ipv4/ip_output.c2
-rw-r--r--net/ipv4/ip_sockglue.c6
-rw-r--r--net/ipv4/tcp.c4
-rw-r--r--net/ipv4/tcp_output.c2
-rw-r--r--net/ipv6/addrconf.c5
-rw-r--r--net/ipv6/ipv6_sockglue.c4
-rw-r--r--net/ipv6/netfilter/nf_conntrack_reasm.c1
-rw-r--r--net/key/af_key.c3
-rw-r--r--net/mptcp/protocol.c2
-rw-r--r--net/netfilter/ipvs/ip_vs_sync.c4
-rw-r--r--net/netfilter/nf_conntrack_proto_tcp.c31
-rw-r--r--net/netfilter/nf_flow_table_core.c15
-rw-r--r--net/netfilter/nf_flow_table_offload.c8
-rw-r--r--net/netfilter/nf_tables_api.c14
-rw-r--r--net/netfilter/nft_osf.c18
-rw-r--r--net/netfilter/nft_payload.c29
-rw-r--r--net/netfilter/nft_tproxy.c8
-rw-r--r--net/netfilter/nft_tunnel.c1
-rw-r--r--net/rose/rose_loopback.c3
-rw-r--r--net/rxrpc/call_object.c4
-rw-r--r--net/rxrpc/sendmsg.c92
-rw-r--r--net/sched/sch_generic.c2
-rw-r--r--net/socket.c2
-rw-r--r--net/xfrm/espintcp.c2
-rw-r--r--net/xfrm/xfrm_input.c3
-rw-r--r--net/xfrm/xfrm_output.c1
-rw-r--r--net/xfrm/xfrm_policy.c3
-rw-r--r--net/xfrm/xfrm_state.c1
42 files changed, 251 insertions, 161 deletions
diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c
index 1a11064f9990..8f19253024b0 100644
--- a/net/bridge/netfilter/ebtable_broute.c
+++ b/net/bridge/netfilter/ebtable_broute.c
@@ -36,18 +36,10 @@ static struct ebt_replace_kernel initial_table = {
.entries = (char *)&initial_chain,
};
-static int check(const struct ebt_table_info *info, unsigned int valid_hooks)
-{
- if (valid_hooks & ~(1 << NF_BR_BROUTING))
- return -EINVAL;
- return 0;
-}
-
static const struct ebt_table broute_table = {
.name = "broute",
.table = &initial_table,
.valid_hooks = 1 << NF_BR_BROUTING,
- .check = check,
.me = THIS_MODULE,
};
diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c
index cb949436bc0e..278f324e6752 100644
--- a/net/bridge/netfilter/ebtable_filter.c
+++ b/net/bridge/netfilter/ebtable_filter.c
@@ -43,18 +43,10 @@ static struct ebt_replace_kernel initial_table = {
.entries = (char *)initial_chains,
};
-static int check(const struct ebt_table_info *info, unsigned int valid_hooks)
-{
- if (valid_hooks & ~FILTER_VALID_HOOKS)
- return -EINVAL;
- return 0;
-}
-
static const struct ebt_table frame_filter = {
.name = "filter",
.table = &initial_table,
.valid_hooks = FILTER_VALID_HOOKS,
- .check = check,
.me = THIS_MODULE,
};
diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c
index 5ee0531ae506..9066f7f376d5 100644
--- a/net/bridge/netfilter/ebtable_nat.c
+++ b/net/bridge/netfilter/ebtable_nat.c
@@ -43,18 +43,10 @@ static struct ebt_replace_kernel initial_table = {
.entries = (char *)initial_chains,
};
-static int check(const struct ebt_table_info *info, unsigned int valid_hooks)
-{
- if (valid_hooks & ~NAT_VALID_HOOKS)
- return -EINVAL;
- return 0;
-}
-
static const struct ebt_table frame_nat = {
.name = "nat",
.table = &initial_table,
.valid_hooks = NAT_VALID_HOOKS,
- .check = check,
.me = THIS_MODULE,
};
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index f2dbefb61ce8..9a0ae59cdc50 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1040,8 +1040,7 @@ static int do_replace_finish(struct net *net, struct ebt_replace *repl,
goto free_iterate;
}
- /* the table doesn't like it */
- if (t->check && (ret = t->check(newinfo, repl->valid_hooks)))
+ if (repl->valid_hooks != t->valid_hooks)
goto free_unlock;
if (repl->num_counters && repl->num_counters != t->private->nentries) {
@@ -1231,11 +1230,6 @@ int ebt_register_table(struct net *net, const struct ebt_table *input_table,
if (ret != 0)
goto free_chainstack;
- if (table->check && table->check(newinfo, table->valid_hooks)) {
- ret = -EINVAL;
- goto free_chainstack;
- }
-
table->private = newinfo;
rwlock_init(&table->lock);
mutex_lock(&ebt_mutex);
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index 1b7f385643b4..94374d529ea4 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -310,11 +310,12 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk)
static int bpf_sk_storage_charge(struct bpf_local_storage_map *smap,
void *owner, u32 size)
{
+ int optmem_max = READ_ONCE(sysctl_optmem_max);
struct sock *sk = (struct sock *)owner;
/* same check as in sock_kmalloc() */
- if (size <= sysctl_optmem_max &&
- atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
+ if (size <= optmem_max &&
+ atomic_read(&sk->sk_omem_alloc) + size < optmem_max) {
atomic_add(size, &sk->sk_omem_alloc);
return 0;
}
diff --git a/net/core/dev.c b/net/core/dev.c
index 716df64fcfa5..56c8b0921c9f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4624,7 +4624,7 @@ static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen)
struct softnet_data *sd;
unsigned int old_flow, new_flow;
- if (qlen < (netdev_max_backlog >> 1))
+ if (qlen < (READ_ONCE(netdev_max_backlog) >> 1))
return false;
sd = this_cpu_ptr(&softnet_data);
@@ -4672,7 +4672,7 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
if (!netif_running(skb->dev))
goto drop;
qlen = skb_queue_len(&sd->input_pkt_queue);
- if (qlen <= netdev_max_backlog && !skb_flow_limit(skb, qlen)) {
+ if (qlen <= READ_ONCE(netdev_max_backlog) && !skb_flow_limit(skb, qlen)) {
if (qlen) {
enqueue:
__skb_queue_tail(&sd->input_pkt_queue, skb);
@@ -4928,7 +4928,7 @@ static int netif_rx_internal(struct sk_buff *skb)
{
int ret;
- net_timestamp_check(netdev_tstamp_prequeue, skb);
+ net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb);
trace_netif_rx(skb);
@@ -5281,7 +5281,7 @@ static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc,
int ret = NET_RX_DROP;
__be16 type;
- net_timestamp_check(!netdev_tstamp_prequeue, skb);
+ net_timestamp_check(!READ_ONCE(netdev_tstamp_prequeue), skb);
trace_netif_receive_skb(skb);
@@ -5664,7 +5664,7 @@ static int netif_receive_skb_internal(struct sk_buff *skb)
{
int ret;
- net_timestamp_check(netdev_tstamp_prequeue, skb);
+ net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb);
if (skb_defer_rx_timestamp(skb))
return NET_RX_SUCCESS;
@@ -5694,7 +5694,7 @@ void netif_receive_skb_list_internal(struct list_head *head)
INIT_LIST_HEAD(&sublist);
list_for_each_entry_safe(skb, next, head, list) {
- net_timestamp_check(netdev_tstamp_prequeue, skb);
+ net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb);
skb_list_del_init(skb);
if (!skb_defer_rx_timestamp(skb))
list_add_tail(&skb->list, &sublist);
@@ -5918,7 +5918,7 @@ static int process_backlog(struct napi_struct *napi, int quota)
net_rps_action_and_irq_enable(sd);
}
- napi->weight = dev_rx_weight;
+ napi->weight = READ_ONCE(dev_rx_weight);
while (again) {
struct sk_buff *skb;
@@ -6665,8 +6665,8 @@ static __latent_entropy void net_rx_action(struct softirq_action *h)
{
struct softnet_data *sd = this_cpu_ptr(&softnet_data);
unsigned long time_limit = jiffies +
- usecs_to_jiffies(netdev_budget_usecs);
- int budget = netdev_budget;
+ usecs_to_jiffies(READ_ONCE(netdev_budget_usecs));
+ int budget = READ_ONCE(netdev_budget);
LIST_HEAD(list);
LIST_HEAD(repoll);
@@ -10284,7 +10284,7 @@ static struct net_device *netdev_wait_allrefs_any(struct list_head *list)
return dev;
if (time_after(jiffies, warning_time +
- netdev_unregister_timeout_secs * HZ)) {
+ READ_ONCE(netdev_unregister_timeout_secs) * HZ)) {
list_for_each_entry(dev, list, todo_list) {
pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n",
dev->name, netdev_refcnt_read(dev));
diff --git a/net/core/filter.c b/net/core/filter.c
index e8508aaafd27..c191db80ce93 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1214,10 +1214,11 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp)
{
u32 filter_size = bpf_prog_size(fp->prog->len);
+ int optmem_max = READ_ONCE(sysctl_optmem_max);
/* same check as in sock_kmalloc() */
- if (filter_size <= sysctl_optmem_max &&
- atomic_read(&sk->sk_omem_alloc) + filter_size < sysctl_optmem_max) {
+ if (filter_size <= optmem_max &&
+ atomic_read(&sk->sk_omem_alloc) + filter_size < optmem_max) {
atomic_add(filter_size, &sk->sk_omem_alloc);
return true;
}
@@ -1548,7 +1549,7 @@ int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk)
if (IS_ERR(prog))
return PTR_ERR(prog);
- if (bpf_prog_size(prog->len) > sysctl_optmem_max)
+ if (bpf_prog_size(prog->len) > READ_ONCE(sysctl_optmem_max))
err = -ENOMEM;
else
err = reuseport_attach_prog(sk, prog);
@@ -1615,7 +1616,7 @@ int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk)
}
} else {
/* BPF_PROG_TYPE_SOCKET_FILTER */
- if (bpf_prog_size(prog->len) > sysctl_optmem_max) {
+ if (bpf_prog_size(prog->len) > READ_ONCE(sysctl_optmem_max)) {
err = -ENOMEM;
goto err_prog_put;
}
@@ -5034,14 +5035,14 @@ static int __bpf_setsockopt(struct sock *sk, int level, int optname,
/* Only some socketops are supported */
switch (optname) {
case SO_RCVBUF:
- val = min_t(u32, val, sysctl_rmem_max);
+ val = min_t(u32, val, READ_ONCE(sysctl_rmem_max));
val = min_t(int, val, INT_MAX / 2);
sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
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);
+ val = min_t(u32, val, READ_ONCE(sysctl_wmem_max));
val = min_t(int, val, INT_MAX / 2);
sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
WRITE_ONCE(sk->sk_sndbuf,
diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c
index 541c7a72a28a..21619c70a82b 100644
--- a/net/core/gro_cells.c
+++ b/net/core/gro_cells.c
@@ -26,7 +26,7 @@ int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb)
cell = this_cpu_ptr(gcells->cells);
- if (skb_queue_len(&cell->napi_skbs) > netdev_max_backlog) {
+ if (skb_queue_len(&cell->napi_skbs) > READ_ONCE(netdev_max_backlog)) {
drop:
dev_core_stats_rx_dropped_inc(dev);
kfree_skb(skb);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 5b669eb80270..78cc8fb68814 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -309,14 +309,17 @@ static int neigh_del_timer(struct neighbour *n)
static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net)
{
+ struct sk_buff_head tmp;
unsigned long flags;
struct sk_buff *skb;
+ skb_queue_head_init(&tmp);
spin_lock_irqsave(&list->lock, flags);
skb = skb_peek(list);
while (skb != NULL) {
struct sk_buff *skb_next = skb_peek_next(skb, list);
struct net_device *dev = skb->dev;
+
if (net == NULL || net_eq(dev_net(dev), net)) {
struct in_device *in_dev;
@@ -326,13 +329,16 @@ static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net)
in_dev->arp_parms->qlen--;
rcu_read_unlock();
__skb_unlink(skb, list);
-
- dev_put(dev);
- kfree_skb(skb);
+ __skb_queue_tail(&tmp, skb);
}
skb = skb_next;
}
spin_unlock_irqrestore(&list->lock, flags);
+
+ while ((skb = __skb_dequeue(&tmp))) {
+ dev_put(skb->dev);
+ kfree_skb(skb);
+ }
}
static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev,
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 974bbbbe7138..84bb5e188d0d 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4205,9 +4205,8 @@ normal:
SKB_GSO_CB(nskb)->csum_start =
skb_headroom(nskb) + doffset;
} else {
- skb_copy_bits(head_skb, offset,
- skb_put(nskb, len),
- len);
+ if (skb_copy_bits(head_skb, offset, skb_put(nskb, len), len))
+ goto err;
}
continue;
}
@@ -4798,7 +4797,7 @@ static bool skb_may_tx_timestamp(struct sock *sk, bool tsonly)
{
bool ret;
- if (likely(sysctl_tstamp_allow_data || tsonly))
+ if (likely(READ_ONCE(sysctl_tstamp_allow_data) || tsonly))
return true;
read_lock_bh(&sk->sk_callback_lock);
diff --git a/net/core/sock.c b/net/core/sock.c
index 4cb957d934a2..788c1372663c 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1101,7 +1101,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
* play 'guess the biggest size' games. RCVBUF/SNDBUF
* are treated in BSD as hints
*/
- val = min_t(u32, val, sysctl_wmem_max);
+ val = min_t(u32, val, READ_ONCE(sysctl_wmem_max));
set_sndbuf:
/* Ensure val * 2 fits into an int, to prevent max_t()
* from treating it as a negative value.
@@ -1133,7 +1133,7 @@ set_sndbuf:
* play 'guess the biggest size' games. RCVBUF/SNDBUF
* are treated in BSD as hints
*/
- __sock_set_rcvbuf(sk, min_t(u32, val, sysctl_rmem_max));
+ __sock_set_rcvbuf(sk, min_t(u32, val, READ_ONCE(sysctl_rmem_max)));
break;
case SO_RCVBUFFORCE:
@@ -2536,7 +2536,7 @@ struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size,
/* small safe race: SKB_TRUESIZE may differ from final skb->truesize */
if (atomic_read(&sk->sk_omem_alloc) + SKB_TRUESIZE(size) >
- sysctl_optmem_max)
+ READ_ONCE(sysctl_optmem_max))
return NULL;
skb = alloc_skb(size, priority);
@@ -2554,8 +2554,10 @@ struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size,
*/
void *sock_kmalloc(struct sock *sk, int size, gfp_t priority)
{
- if ((unsigned int)size <= sysctl_optmem_max &&
- atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
+ int optmem_max = READ_ONCE(sysctl_optmem_max);
+
+ if ((unsigned int)size <= optmem_max &&
+ atomic_read(&sk->sk_omem_alloc) + size < optmem_max) {
void *mem;
/* First do the add, to avoid the race if kmalloc
* might sleep.
@@ -3309,8 +3311,8 @@ void sock_init_data(struct socket *sock, struct sock *sk)
timer_setup(&sk->sk_timer, NULL, 0);
sk->sk_allocation = GFP_KERNEL;
- sk->sk_rcvbuf = sysctl_rmem_default;
- sk->sk_sndbuf = sysctl_wmem_default;
+ sk->sk_rcvbuf = READ_ONCE(sysctl_rmem_default);
+ sk->sk_sndbuf = READ_ONCE(sysctl_wmem_default);
sk->sk_state = TCP_CLOSE;
sk_set_socket(sk, sock);
@@ -3365,7 +3367,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
#ifdef CONFIG_NET_RX_BUSY_POLL
sk->sk_napi_id = 0;
- sk->sk_ll_usec = sysctl_net_busy_read;
+ sk->sk_ll_usec = READ_ONCE(sysctl_net_busy_read);
#endif
sk->sk_max_pacing_rate = ~0UL;
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 71a13596ea2b..725891527814 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -234,14 +234,17 @@ static int set_default_qdisc(struct ctl_table *table, int write,
static int proc_do_dev_weight(struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
- int ret;
+ static DEFINE_MUTEX(dev_weight_mutex);
+ int ret, weight;
+ mutex_lock(&dev_weight_mutex);
ret = proc_dointvec(table, write, buffer, lenp, ppos);
- if (ret != 0)
- return ret;
-
- dev_rx_weight = weight_p * dev_weight_rx_bias;
- dev_tx_weight = weight_p * dev_weight_tx_bias;
+ if (!ret && write) {
+ weight = READ_ONCE(weight_p);
+ WRITE_ONCE(dev_rx_weight, weight * dev_weight_rx_bias);
+ WRITE_ONCE(dev_tx_weight, weight * dev_weight_tx_bias);
+ }
+ mutex_unlock(&dev_weight_mutex);
return ret;
}
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index ad6a6663feeb..1291c2431d44 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -2484,7 +2484,7 @@ static int dsa_slave_changeupper(struct net_device *dev,
if (!err)
dsa_bridge_mtu_normalization(dp);
if (err == -EOPNOTSUPP) {
- if (!extack->_msg)
+ if (extack && !extack->_msg)
NL_SET_ERR_MSG_MOD(extack,
"Offloading not supported");
err = 0;
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 92b778e423df..e8b9a9202fec 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -2682,23 +2682,27 @@ static __net_init int devinet_init_net(struct net *net)
#endif
if (!net_eq(net, &init_net)) {
- if (IS_ENABLED(CONFIG_SYSCTL) &&
- sysctl_devconf_inherit_init_net == 3) {
+ switch (net_inherit_devconf()) {
+ case 3:
/* copy from the current netns */
memcpy(all, current->nsproxy->net_ns->ipv4.devconf_all,
sizeof(ipv4_devconf));
memcpy(dflt,
current->nsproxy->net_ns->ipv4.devconf_dflt,
sizeof(ipv4_devconf_dflt));
- } else if (!IS_ENABLED(CONFIG_SYSCTL) ||
- sysctl_devconf_inherit_init_net != 2) {
- /* inherit == 0 or 1: copy from init_net */
+ break;
+ case 0:
+ case 1:
+ /* copy from init_net */
memcpy(all, init_net.ipv4.devconf_all,
sizeof(ipv4_devconf));
memcpy(dflt, init_net.ipv4.devconf_dflt,
sizeof(ipv4_devconf_dflt));
+ break;
+ case 2:
+ /* use compiled values */
+ break;
}
- /* else inherit == 2: use compiled values */
}
#ifdef CONFIG_SYSCTL
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index d7bd1daf022b..04e2034f2f8e 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1730,7 +1730,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
sk->sk_protocol = ip_hdr(skb)->protocol;
sk->sk_bound_dev_if = arg->bound_dev_if;
- sk->sk_sndbuf = sysctl_wmem_default;
+ sk->sk_sndbuf = READ_ONCE(sysctl_wmem_default);
ipc.sockc.mark = fl4.flowi4_mark;
err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base,
len, 0, &ipc, &rt, MSG_DONTWAIT);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index a8a323ecbb54..e49a61a053a6 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -772,7 +772,7 @@ static int ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen)
if (optlen < GROUP_FILTER_SIZE(0))
return -EINVAL;
- if (optlen > sysctl_optmem_max)
+ if (optlen > READ_ONCE(sysctl_optmem_max))
return -ENOBUFS;
gsf = memdup_sockptr(optval, optlen);
@@ -808,7 +808,7 @@ static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval,
if (optlen < size0)
return -EINVAL;
- if (optlen > sysctl_optmem_max - 4)
+ if (optlen > READ_ONCE(sysctl_optmem_max) - 4)
return -ENOBUFS;
p = kmalloc(optlen + 4, GFP_KERNEL);
@@ -1233,7 +1233,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, int optname,
if (optlen < IP_MSFILTER_SIZE(0))
goto e_inval;
- if (optlen > sysctl_optmem_max) {
+ if (optlen > READ_ONCE(sysctl_optmem_max)) {
err = -ENOBUFS;
break;
}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index bbe218753662..e5011c136fdb 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1000,7 +1000,7 @@ new_segment:
i = skb_shinfo(skb)->nr_frags;
can_coalesce = skb_can_coalesce(skb, i, page, offset);
- if (!can_coalesce && i >= sysctl_max_skb_frags) {
+ if (!can_coalesce && i >= READ_ONCE(sysctl_max_skb_frags)) {
tcp_mark_push(tp, skb);
goto new_segment;
}
@@ -1354,7 +1354,7 @@ new_segment:
if (!skb_can_coalesce(skb, i, pfrag->page,
pfrag->offset)) {
- if (i >= sysctl_max_skb_frags) {
+ if (i >= READ_ONCE(sysctl_max_skb_frags)) {
tcp_mark_push(tp, skb);
goto new_segment;
}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 78b654ff421b..290019de766d 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -239,7 +239,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
if (wscale_ok) {
/* Set window scaling on max possible window */
space = max_t(u32, space, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
- space = max_t(u32, space, sysctl_rmem_max);
+ space = max_t(u32, space, READ_ONCE(sysctl_rmem_max));
space = min_t(u32, space, *window_clamp);
*rcv_wscale = clamp_t(int, ilog2(space) - 15,
0, TCP_MAX_WSCALE);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index b624e3d8c5f0..e15f64f22fa8 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -7162,9 +7162,8 @@ static int __net_init addrconf_init_net(struct net *net)
if (!dflt)
goto err_alloc_dflt;
- if (IS_ENABLED(CONFIG_SYSCTL) &&
- !net_eq(net, &init_net)) {
- switch (sysctl_devconf_inherit_init_net) {
+ if (!net_eq(net, &init_net)) {
+ switch (net_inherit_devconf()) {
case 1: /* copy from init_net */
memcpy(all, init_net.ipv6.devconf_all,
sizeof(ipv6_devconf));
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 222f6bf220ba..e0dcc7a193df 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -210,7 +210,7 @@ static int ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval,
if (optlen < GROUP_FILTER_SIZE(0))
return -EINVAL;
- if (optlen > sysctl_optmem_max)
+ if (optlen > READ_ONCE(sysctl_optmem_max))
return -ENOBUFS;
gsf = memdup_sockptr(optval, optlen);
@@ -244,7 +244,7 @@ static int compat_ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval,
if (optlen < size0)
return -EINVAL;
- if (optlen > sysctl_optmem_max - 4)
+ if (optlen > READ_ONCE(sysctl_optmem_max) - 4)
return -ENOBUFS;
p = kmalloc(optlen + 4, GFP_KERNEL);
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 7dd3629dd19e..38db0064d661 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -86,7 +86,6 @@ static int nf_ct_frag6_sysctl_register(struct net *net)
table[1].extra2 = &nf_frag->fqdir->high_thresh;
table[2].data = &nf_frag->fqdir->high_thresh;
table[2].extra1 = &nf_frag->fqdir->low_thresh;
- table[2].extra2 = &nf_frag->fqdir->high_thresh;
hdr = register_net_sysctl(net, "net/netfilter", table);
if (hdr == NULL)
diff --git a/net/key/af_key.c b/net/key/af_key.c
index fda2dcc8a383..c85df5b958d2 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -1697,9 +1697,12 @@ static int pfkey_register(struct sock *sk, struct sk_buff *skb, const struct sad
pfk->registered |= (1<<hdr->sadb_msg_satype);
}
+ mutex_lock(&pfkey_mutex);
xfrm_probe_algs();
supp_skb = compose_sadb_supported(hdr, GFP_KERNEL | __GFP_ZERO);
+ mutex_unlock(&pfkey_mutex);
+
if (!supp_skb) {
if (hdr->sadb_msg_satype != SADB_SATYPE_UNSPEC)
pfk->registered &= ~(1<<hdr->sadb_msg_satype);
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index da4257504fad..d398f3810662 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1263,7 +1263,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
i = skb_shinfo(skb)->nr_frags;
can_coalesce = skb_can_coalesce(skb, i, dfrag->page, offset);
- if (!can_coalesce && i >= sysctl_max_skb_frags) {
+ if (!can_coalesce && i >= READ_ONCE(sysctl_max_skb_frags)) {
tcp_mark_push(tcp_sk(ssk), skb);
goto alloc_skb;
}
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 9d43277b8b4f..a56fd0b5a430 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1280,12 +1280,12 @@ static void set_sock_size(struct sock *sk, int mode, int val)
lock_sock(sk);
if (mode) {
val = clamp_t(int, val, (SOCK_MIN_SNDBUF + 1) / 2,
- sysctl_wmem_max);
+ READ_ONCE(sysctl_wmem_max));
sk->sk_sndbuf = val * 2;
sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
} else {
val = clamp_t(int, val, (SOCK_MIN_RCVBUF + 1) / 2,
- sysctl_rmem_max);
+ READ_ONCE(sysctl_rmem_max));
sk->sk_rcvbuf = val * 2;
sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
}
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index a63b51dceaf2..a634c72b1ffc 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -655,6 +655,37 @@ static bool tcp_in_window(struct nf_conn *ct,
tn->tcp_be_liberal)
res = true;
if (!res) {
+ bool seq_ok = before(seq, sender->td_maxend + 1);
+
+ if (!seq_ok) {
+ u32 overshot = end - sender->td_maxend + 1;
+ bool ack_ok;
+
+ ack_ok = after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1);
+
+ if (in_recv_win &&
+ ack_ok &&
+ overshot <= receiver->td_maxwin &&
+ before(sack, receiver->td_end + 1)) {
+ /* Work around TCPs that send more bytes than allowed by
+ * the receive window.
+ *
+ * If the (marked as invalid) packet is allowed to pass by
+ * the ruleset and the peer acks this data, then its possible
+ * all future packets will trigger 'ACK is over upper bound' check.
+ *
+ * Thus if only the sequence check fails then do update td_end so
+ * possible ACK for this data can update internal state.
+ */
+ sender->td_end = end;
+ sender->flags |= IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED;
+
+ nf_ct_l4proto_log_invalid(skb, ct, hook_state,
+ "%u bytes more than expected", overshot);
+ return res;
+ }
+ }
+
nf_ct_l4proto_log_invalid(skb, ct, hook_state,
"%s",
before(seq, sender->td_maxend + 1) ?
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 765ac779bfc8..81c26a96c30b 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -437,12 +437,17 @@ static void nf_flow_offload_gc_step(struct nf_flowtable *flow_table,
}
}
+void nf_flow_table_gc_run(struct nf_flowtable *flow_table)
+{
+ nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, NULL);
+}
+
static void nf_flow_offload_work_gc(struct work_struct *work)
{
struct nf_flowtable *flow_table;
flow_table = container_of(work, struct nf_flowtable, gc_work.work);
- nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, NULL);
+ nf_flow_table_gc_run(flow_table);
queue_delayed_work(system_power_efficient_wq, &flow_table->gc_work, HZ);
}
@@ -600,11 +605,11 @@ void nf_flow_table_free(struct nf_flowtable *flow_table)
mutex_unlock(&flowtable_lock);
cancel_delayed_work_sync(&flow_table->gc_work);
- nf_flow_table_iterate(flow_table, nf_flow_table_do_cleanup, NULL);
- nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, NULL);
nf_flow_table_offload_flush(flow_table);
- if (nf_flowtable_hw_offload(flow_table))
- nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, NULL);
+ /* ... no more pending work after this stage ... */
+ nf_flow_table_iterate(flow_table, nf_flow_table_do_cleanup, NULL);
+ nf_flow_table_gc_run(flow_table);
+ nf_flow_table_offload_flush_cleanup(flow_table);
rhashtable_destroy(&flow_table->rhashtable);
}
EXPORT_SYMBOL_GPL(nf_flow_table_free);
diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
index 103b6cbf257f..b04645ced89b 100644
--- a/net/netfilter/nf_flow_table_offload.c
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -1074,6 +1074,14 @@ void nf_flow_offload_stats(struct nf_flowtable *flowtable,
flow_offload_queue_work(offload);
}
+void nf_flow_table_offload_flush_cleanup(struct nf_flowtable *flowtable)
+{
+ if (nf_flowtable_hw_offload(flowtable)) {
+ flush_workqueue(nf_flow_offload_del_wq);
+ nf_flow_table_gc_run(flowtable);
+ }
+}
+
void nf_flow_table_offload_flush(struct nf_flowtable *flowtable)
{
if (nf_flowtable_hw_offload(flowtable)) {
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 62cfb0e31c40..2ee50e23c9b7 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -32,7 +32,6 @@ static LIST_HEAD(nf_tables_objects);
static LIST_HEAD(nf_tables_flowtables);
static LIST_HEAD(nf_tables_destroy_list);
static DEFINE_SPINLOCK(nf_tables_destroy_list_lock);
-static u64 table_handle;
enum {
NFT_VALIDATE_SKIP = 0,
@@ -1235,7 +1234,7 @@ static int nf_tables_newtable(struct sk_buff *skb, const struct nfnl_info *info,
INIT_LIST_HEAD(&table->flowtables);
table->family = family;
table->flags = flags;
- table->handle = ++table_handle;
+ table->handle = ++nft_net->table_handle;
if (table->flags & NFT_TABLE_F_OWNER)
table->nlpid = NETLINK_CB(skb).portid;
@@ -2196,9 +2195,9 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
struct netlink_ext_ack *extack)
{
const struct nlattr * const *nla = ctx->nla;
+ struct nft_stats __percpu *stats = NULL;
struct nft_table *table = ctx->table;
struct nft_base_chain *basechain;
- struct nft_stats __percpu *stats;
struct net *net = ctx->net;
char name[NFT_NAME_MAXLEN];
struct nft_rule_blob *blob;
@@ -2236,7 +2235,6 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
return PTR_ERR(stats);
}
rcu_assign_pointer(basechain->stats, stats);
- static_branch_inc(&nft_counters_enabled);
}
err = nft_basechain_init(basechain, family, &hook, flags);
@@ -2319,6 +2317,9 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
goto err_unregister_hook;
}
+ if (stats)
+ static_branch_inc(&nft_counters_enabled);
+
table->use++;
return 0;
@@ -2574,6 +2575,9 @@ static int nf_tables_newchain(struct sk_buff *skb, const struct nfnl_info *info,
nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla);
if (chain != NULL) {
+ if (chain->flags & NFT_CHAIN_BINDING)
+ return -EINVAL;
+
if (info->nlh->nlmsg_flags & NLM_F_EXCL) {
NL_SET_BAD_ATTR(extack, attr);
return -EEXIST;
@@ -9707,6 +9711,8 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
return PTR_ERR(chain);
if (nft_is_base_chain(chain))
return -EOPNOTSUPP;
+ if (nft_chain_is_bound(chain))
+ return -EINVAL;
if (desc->flags & NFT_DATA_DESC_SETELEM &&
chain->flags & NFT_CHAIN_BINDING)
return -EINVAL;
diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c
index 0053a697c931..89342ccccdcc 100644
--- a/net/netfilter/nft_osf.c
+++ b/net/netfilter/nft_osf.c
@@ -115,9 +115,21 @@ static int nft_osf_validate(const struct nft_ctx *ctx,
const struct nft_expr *expr,
const struct nft_data **data)
{
- return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_LOCAL_IN) |
- (1 << NF_INET_PRE_ROUTING) |
- (1 << NF_INET_FORWARD));
+ unsigned int hooks;
+
+ switch (ctx->family) {
+ case NFPROTO_IPV4:
+ case NFPROTO_IPV6:
+ case NFPROTO_INET:
+ hooks = (1 << NF_INET_LOCAL_IN) |
+ (1 << NF_INET_PRE_ROUTING) |
+ (1 << NF_INET_FORWARD);
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ return nft_chain_validate_hooks(ctx->chain, hooks);
}
static bool nft_osf_reduce(struct nft_regs_track *track,
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index 2e7ac007cb30..eb0e40c29712 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -740,17 +740,23 @@ static int nft_payload_set_init(const struct nft_ctx *ctx,
const struct nlattr * const tb[])
{
struct nft_payload_set *priv = nft_expr_priv(expr);
+ u32 csum_offset, csum_type = NFT_PAYLOAD_CSUM_NONE;
+ int err;
priv->base = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE]));
priv->offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET]));
priv->len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN]));
if (tb[NFTA_PAYLOAD_CSUM_TYPE])
- priv->csum_type =
- ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_TYPE]));
- if (tb[NFTA_PAYLOAD_CSUM_OFFSET])
- priv->csum_offset =
- ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_OFFSET]));
+ csum_type = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_TYPE]));
+ if (tb[NFTA_PAYLOAD_CSUM_OFFSET]) {
+ err = nft_parse_u32_check(tb[NFTA_PAYLOAD_CSUM_OFFSET], U8_MAX,
+ &csum_offset);
+ if (err < 0)
+ return err;
+
+ priv->csum_offset = csum_offset;
+ }
if (tb[NFTA_PAYLOAD_CSUM_FLAGS]) {
u32 flags;
@@ -761,7 +767,7 @@ static int nft_payload_set_init(const struct nft_ctx *ctx,
priv->csum_flags = flags;
}
- switch (priv->csum_type) {
+ switch (csum_type) {
case NFT_PAYLOAD_CSUM_NONE:
case NFT_PAYLOAD_CSUM_INET:
break;
@@ -775,6 +781,7 @@ static int nft_payload_set_init(const struct nft_ctx *ctx,
default:
return -EOPNOTSUPP;
}
+ priv->csum_type = csum_type;
return nft_parse_register_load(tb[NFTA_PAYLOAD_SREG], &priv->sreg,
priv->len);
@@ -833,6 +840,7 @@ nft_payload_select_ops(const struct nft_ctx *ctx,
{
enum nft_payload_bases base;
unsigned int offset, len;
+ int err;
if (tb[NFTA_PAYLOAD_BASE] == NULL ||
tb[NFTA_PAYLOAD_OFFSET] == NULL ||
@@ -859,8 +867,13 @@ nft_payload_select_ops(const struct nft_ctx *ctx,
if (tb[NFTA_PAYLOAD_DREG] == NULL)
return ERR_PTR(-EINVAL);
- offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET]));
- len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN]));
+ err = nft_parse_u32_check(tb[NFTA_PAYLOAD_OFFSET], U8_MAX, &offset);
+ if (err < 0)
+ return ERR_PTR(err);
+
+ err = nft_parse_u32_check(tb[NFTA_PAYLOAD_LEN], U8_MAX, &len);
+ if (err < 0)
+ return ERR_PTR(err);
if (len <= 4 && is_power_of_2(len) && IS_ALIGNED(offset, len) &&
base != NFT_PAYLOAD_LL_HEADER && base != NFT_PAYLOAD_INNER_HEADER)
diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c
index 68b2eed742df..62da25ad264b 100644
--- a/net/netfilter/nft_tproxy.c
+++ b/net/netfilter/nft_tproxy.c
@@ -312,6 +312,13 @@ static int nft_tproxy_dump(struct sk_buff *skb,
return 0;
}
+static int nft_tproxy_validate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nft_data **data)
+{
+ return nft_chain_validate_hooks(ctx->chain, 1 << NF_INET_PRE_ROUTING);
+}
+
static struct nft_expr_type nft_tproxy_type;
static const struct nft_expr_ops nft_tproxy_ops = {
.type = &nft_tproxy_type,
@@ -321,6 +328,7 @@ static const struct nft_expr_ops nft_tproxy_ops = {
.destroy = nft_tproxy_destroy,
.dump = nft_tproxy_dump,
.reduce = NFT_REDUCE_READONLY,
+ .validate = nft_tproxy_validate,
};
static struct nft_expr_type nft_tproxy_type __read_mostly = {
diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c
index 5edaaded706d..983ade4be3b3 100644
--- a/net/netfilter/nft_tunnel.c
+++ b/net/netfilter/nft_tunnel.c
@@ -161,6 +161,7 @@ static const struct nft_expr_ops nft_tunnel_get_ops = {
static struct nft_expr_type nft_tunnel_type __read_mostly = {
.name = "tunnel",
+ .family = NFPROTO_NETDEV,
.ops = &nft_tunnel_get_ops,
.policy = nft_tunnel_policy,
.maxattr = NFTA_TUNNEL_MAX,
diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c
index 11c45c8c6c16..036d92c0ad79 100644
--- a/net/rose/rose_loopback.c
+++ b/net/rose/rose_loopback.c
@@ -96,7 +96,8 @@ static void rose_loopback_timer(struct timer_list *unused)
}
if (frametype == ROSE_CALL_REQUEST) {
- if (!rose_loopback_neigh->dev) {
+ if (!rose_loopback_neigh->dev &&
+ !rose_loopback_neigh->loopback) {
kfree_skb(skb);
continue;
}
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 84d0a4109645..6401cdf7a624 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -285,8 +285,10 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
_enter("%p,%lx", rx, p->user_call_ID);
limiter = rxrpc_get_call_slot(p, gfp);
- if (!limiter)
+ if (!limiter) {
+ release_sock(&rx->sk);
return ERR_PTR(-ERESTARTSYS);
+ }
call = rxrpc_alloc_client_call(rx, srx, gfp, debug_id);
if (IS_ERR(call)) {
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 1d38e279e2ef..3c3a626459de 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -51,10 +51,7 @@ static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx,
return sock_intr_errno(*timeo);
trace_rxrpc_transmit(call, rxrpc_transmit_wait);
- mutex_unlock(&call->user_mutex);
*timeo = schedule_timeout(*timeo);
- if (mutex_lock_interruptible(&call->user_mutex) < 0)
- return sock_intr_errno(*timeo);
}
}
@@ -290,37 +287,48 @@ out:
static int rxrpc_send_data(struct rxrpc_sock *rx,
struct rxrpc_call *call,
struct msghdr *msg, size_t len,
- rxrpc_notify_end_tx_t notify_end_tx)
+ rxrpc_notify_end_tx_t notify_end_tx,
+ bool *_dropped_lock)
{
struct rxrpc_skb_priv *sp;
struct sk_buff *skb;
struct sock *sk = &rx->sk;
+ enum rxrpc_call_state state;
long timeo;
- bool more;
- int ret, copied;
+ bool more = msg->msg_flags & MSG_MORE;
+ int ret, copied = 0;
timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
/* this should be in poll */
sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
+reload:
+ ret = -EPIPE;
if (sk->sk_shutdown & SEND_SHUTDOWN)
- return -EPIPE;
-
- more = msg->msg_flags & MSG_MORE;
-
+ goto maybe_error;
+ state = READ_ONCE(call->state);
+ ret = -ESHUTDOWN;
+ if (state >= RXRPC_CALL_COMPLETE)
+ goto maybe_error;
+ ret = -EPROTO;
+ if (state != RXRPC_CALL_CLIENT_SEND_REQUEST &&
+ state != RXRPC_CALL_SERVER_ACK_REQUEST &&
+ state != RXRPC_CALL_SERVER_SEND_REPLY)
+ goto maybe_error;
+
+ ret = -EMSGSIZE;
if (call->tx_total_len != -1) {
- if (len > call->tx_total_len)
- return -EMSGSIZE;
- if (!more && len != call->tx_total_len)
- return -EMSGSIZE;
+ if (len - copied > call->tx_total_len)
+ goto maybe_error;
+ if (!more && len - copied != call->tx_total_len)
+ goto maybe_error;
}
skb = call->tx_pending;
call->tx_pending = NULL;
rxrpc_see_skb(skb, rxrpc_skb_seen);
- copied = 0;
do {
/* Check to see if there's a ping ACK to reply to. */
if (call->ackr_reason == RXRPC_ACK_PING_RESPONSE)
@@ -331,16 +339,8 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
_debug("alloc");
- if (!rxrpc_check_tx_space(call, NULL)) {
- ret = -EAGAIN;
- if (msg->msg_flags & MSG_DONTWAIT)
- goto maybe_error;
- ret = rxrpc_wait_for_tx_window(rx, call,
- &timeo,
- msg->msg_flags & MSG_WAITALL);
- if (ret < 0)
- goto maybe_error;
- }
+ if (!rxrpc_check_tx_space(call, NULL))
+ goto wait_for_space;
/* Work out the maximum size of a packet. Assume that
* the security header is going to be in the padded
@@ -468,6 +468,27 @@ maybe_error:
efault:
ret = -EFAULT;
goto out;
+
+wait_for_space:
+ ret = -EAGAIN;
+ if (msg->msg_flags & MSG_DONTWAIT)
+ goto maybe_error;
+ mutex_unlock(&call->user_mutex);
+ *_dropped_lock = true;
+ ret = rxrpc_wait_for_tx_window(rx, call, &timeo,
+ msg->msg_flags & MSG_WAITALL);
+ if (ret < 0)
+ goto maybe_error;
+ if (call->interruptibility == RXRPC_INTERRUPTIBLE) {
+ if (mutex_lock_interruptible(&call->user_mutex) < 0) {
+ ret = sock_intr_errno(timeo);
+ goto maybe_error;
+ }
+ } else {
+ mutex_lock(&call->user_mutex);
+ }
+ *_dropped_lock = false;
+ goto reload;
}
/*
@@ -629,6 +650,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
enum rxrpc_call_state state;
struct rxrpc_call *call;
unsigned long now, j;
+ bool dropped_lock = false;
int ret;
struct rxrpc_send_params p = {
@@ -737,21 +759,13 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
ret = rxrpc_send_abort_packet(call);
} else if (p.command != RXRPC_CMD_SEND_DATA) {
ret = -EINVAL;
- } else if (rxrpc_is_client_call(call) &&
- state != RXRPC_CALL_CLIENT_SEND_REQUEST) {
- /* request phase complete for this client call */
- ret = -EPROTO;
- } else if (rxrpc_is_service_call(call) &&
- state != RXRPC_CALL_SERVER_ACK_REQUEST &&
- state != RXRPC_CALL_SERVER_SEND_REPLY) {
- /* Reply phase not begun or not complete for service call. */
- ret = -EPROTO;
} else {
- ret = rxrpc_send_data(rx, call, msg, len, NULL);
+ ret = rxrpc_send_data(rx, call, msg, len, NULL, &dropped_lock);
}
out_put_unlock:
- mutex_unlock(&call->user_mutex);
+ if (!dropped_lock)
+ mutex_unlock(&call->user_mutex);
error_put:
rxrpc_put_call(call, rxrpc_call_put);
_leave(" = %d", ret);
@@ -779,6 +793,7 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call,
struct msghdr *msg, size_t len,
rxrpc_notify_end_tx_t notify_end_tx)
{
+ bool dropped_lock = false;
int ret;
_enter("{%d,%s},", call->debug_id, rxrpc_call_states[call->state]);
@@ -796,7 +811,7 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call,
case RXRPC_CALL_SERVER_ACK_REQUEST:
case RXRPC_CALL_SERVER_SEND_REPLY:
ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len,
- notify_end_tx);
+ notify_end_tx, &dropped_lock);
break;
case RXRPC_CALL_COMPLETE:
read_lock_bh(&call->state_lock);
@@ -810,7 +825,8 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call,
break;
}
- mutex_unlock(&call->user_mutex);
+ if (!dropped_lock)
+ mutex_unlock(&call->user_mutex);
_leave(" = %d", ret);
return ret;
}
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index d47b9689eba6..99b697ad2b98 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -409,7 +409,7 @@ static inline bool qdisc_restart(struct Qdisc *q, int *packets)
void __qdisc_run(struct Qdisc *q)
{
- int quota = dev_tx_weight;
+ int quota = READ_ONCE(dev_tx_weight);
int packets;
while (qdisc_restart(q, &packets)) {
diff --git a/net/socket.c b/net/socket.c
index 9b27c5e4e5ba..7378375d3a5b 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1801,7 +1801,7 @@ int __sys_listen(int fd, int backlog)
sock = sockfd_lookup_light(fd, &err, &fput_needed);
if (sock) {
- somaxconn = sock_net(sock->sk)->core.sysctl_somaxconn;
+ somaxconn = READ_ONCE(sock_net(sock->sk)->core.sysctl_somaxconn);
if ((unsigned int)backlog > somaxconn)
backlog = somaxconn;
diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c
index 82d14eea1b5a..974eb97b77d2 100644
--- a/net/xfrm/espintcp.c
+++ b/net/xfrm/espintcp.c
@@ -168,7 +168,7 @@ int espintcp_queue_out(struct sock *sk, struct sk_buff *skb)
{
struct espintcp_ctx *ctx = espintcp_getctx(sk);
- if (skb_queue_len(&ctx->out_queue) >= netdev_max_backlog)
+ if (skb_queue_len(&ctx->out_queue) >= READ_ONCE(netdev_max_backlog))
return -ENOBUFS;
__skb_queue_tail(&ctx->out_queue, skb);
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 144238a50f3d..b2f4ec9c537f 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -669,7 +669,6 @@ resume:
x->curlft.bytes += skb->len;
x->curlft.packets++;
- x->curlft.use_time = ktime_get_real_seconds();
spin_unlock(&x->lock);
@@ -783,7 +782,7 @@ int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb,
trans = this_cpu_ptr(&xfrm_trans_tasklet);
- if (skb_queue_len(&trans->queue) >= netdev_max_backlog)
+ if (skb_queue_len(&trans->queue) >= READ_ONCE(netdev_max_backlog))
return -ENOBUFS;
BUILD_BUG_ON(sizeof(struct xfrm_trans_cb) > sizeof(skb->cb));
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 555ab35cd119..9a5e79a38c67 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -534,7 +534,6 @@ static int xfrm_output_one(struct sk_buff *skb, int err)
x->curlft.bytes += skb->len;
x->curlft.packets++;
- x->curlft.use_time = ktime_get_real_seconds();
spin_unlock_bh(&x->lock);
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index f1a0bab920a5..cc6ab79609e2 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -3162,7 +3162,7 @@ ok:
return dst;
nopol:
- if (!(dst_orig->dev->flags & IFF_LOOPBACK) &&
+ if ((!dst_orig->dev || !(dst_orig->dev->flags & IFF_LOOPBACK)) &&
net->xfrm.policy_default[dir] == XFRM_USERPOLICY_BLOCK) {
err = -EPERM;
goto error;
@@ -3599,6 +3599,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
if (pols[1]) {
if (IS_ERR(pols[1])) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR);
+ xfrm_pol_put(pols[0]);
return 0;
}
pols[1]->curlft.use_time = ktime_get_real_seconds();
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 52e60e607f8a..91c32a3b6924 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1592,6 +1592,7 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig,
x->replay = orig->replay;
x->preplay = orig->preplay;
x->mapping_maxage = orig->mapping_maxage;
+ x->lastused = orig->lastused;
x->new_mapping = 0;
x->new_mapping_sport = 0;