summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-07-28 11:54:59 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2022-07-28 11:54:59 -0700
commit33ea1340bafe1f394e5bf96fceef73e9771d066b (patch)
tree3b1d816103a2d02692e4845e5c4570ed6f4afecd /net
parente64ab2dbd882933b65cd82ff6235d705ad65dbb6 (diff)
parent4d3d3a1b244fd54629a6b7047f39a7bbc8d11910 (diff)
downloadlinux-stable-33ea1340bafe1f394e5bf96fceef73e9771d066b.tar.gz
linux-stable-33ea1340bafe1f394e5bf96fceef73e9771d066b.tar.bz2
linux-stable-33ea1340bafe1f394e5bf96fceef73e9771d066b.zip
Merge tag 'net-5.19-final' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski: "Including fixes from bluetooth and netfilter, no known blockers for the release. Current release - regressions: - wifi: mac80211: do not abuse fq.lock in ieee80211_do_stop(), fix taking the lock before its initialized - Bluetooth: mgmt: fix double free on error path Current release - new code bugs: - eth: ice: fix tunnel checksum offload with fragmented traffic Previous releases - regressions: - tcp: md5: fix IPv4-mapped support after refactoring, don't take the pure v6 path - Revert "tcp: change pingpong threshold to 3", improving detection of interactive sessions - mld: fix netdev refcount leak in mld_{query | report}_work() due to a race - Bluetooth: - always set event mask on suspend, avoid early wake ups - L2CAP: fix use-after-free caused by l2cap_chan_put - bridge: do not send empty IFLA_AF_SPEC attribute Previous releases - always broken: - ping6: fix memleak in ipv6_renew_options() - sctp: prevent null-deref caused by over-eager error paths - virtio-net: fix the race between refill work and close, resulting in NAPI scheduled after close and a BUG() - macsec: - fix three netlink parsing bugs - avoid breaking the device state on invalid change requests - fix a memleak in another error path Misc: - dt-bindings: net: ethernet-controller: rework 'fixed-link' schema - two more batches of sysctl data race adornment" * tag 'net-5.19-final' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (67 commits) stmmac: dwmac-mediatek: fix resource leak in probe ipv6/addrconf: fix a null-ptr-deref bug for ip6_ptr net: ping6: Fix memleak in ipv6_renew_options(). net/funeth: Fix fun_xdp_tx() and XDP packet reclaim sctp: leave the err path free in sctp_stream_init to sctp_stream_free sfc: disable softirqs for ptp TX ptp: ocp: Select CRC16 in the Kconfig. tcp: md5: fix IPv4-mapped support virtio-net: fix the race between refill work and close mptcp: Do not return EINPROGRESS when subflow creation succeeds Bluetooth: L2CAP: Fix use-after-free caused by l2cap_chan_put Bluetooth: Always set event mask on suspend Bluetooth: mgmt: Fix double free on error path wifi: mac80211: do not abuse fq.lock in ieee80211_do_stop() ice: do not setup vlan for loopback VSI ice: check (DD | EOF) bits on Rx descriptor rather than (EOP | RS) ice: Fix VSIs unable to share unicast MAC ice: Fix tunnel checksum offload with fragmented traffic ice: Fix max VLANs available for VF netfilter: nft_queue: only allow supported familes and hooks ...
Diffstat (limited to 'net')
-rw-r--r--net/bluetooth/hci_sync.c6
-rw-r--r--net/bluetooth/l2cap_core.c61
-rw-r--r--net/bluetooth/mgmt.c1
-rw-r--r--net/bridge/br_netlink.c8
-rw-r--r--net/caif/caif_socket.c20
-rw-r--r--net/decnet/af_decnet.c4
-rw-r--r--net/dsa/switch.c1
-rw-r--r--net/ipv4/fib_trie.c7
-rw-r--r--net/ipv4/tcp.c23
-rw-r--r--net/ipv4/tcp_input.c41
-rw-r--r--net/ipv4/tcp_ipv4.c4
-rw-r--r--net/ipv4/tcp_metrics.c10
-rw-r--r--net/ipv4/tcp_output.c27
-rw-r--r--net/ipv6/mcast.c14
-rw-r--r--net/ipv6/ping.c6
-rw-r--r--net/ipv6/tcp_ipv6.c4
-rw-r--r--net/mac80211/iface.c3
-rw-r--r--net/mptcp/options.c2
-rw-r--r--net/mptcp/protocol.c8
-rw-r--r--net/mptcp/subflow.c2
-rw-r--r--net/netfilter/nf_tables_api.c6
-rw-r--r--net/netfilter/nfnetlink_queue.c7
-rw-r--r--net/netfilter/nft_queue.c27
-rw-r--r--net/sctp/associola.c5
-rw-r--r--net/sctp/stream.c19
-rw-r--r--net/sctp/stream_sched.c2
-rw-r--r--net/tipc/socket.c2
-rw-r--r--net/tls/tls_device.c7
28 files changed, 204 insertions, 123 deletions
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 1739e8cb3291..c17021642234 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -4973,6 +4973,9 @@ int hci_suspend_sync(struct hci_dev *hdev)
return err;
}
+ /* Update event mask so only the allowed event can wakeup the host */
+ hci_set_event_mask_sync(hdev);
+
/* Only configure accept list if disconnect succeeded and wake
* isn't being prevented.
*/
@@ -4984,9 +4987,6 @@ int hci_suspend_sync(struct hci_dev *hdev)
/* Unpause to take care of updating scanning params */
hdev->scanning_paused = false;
- /* Update event mask so only the allowed event can wakeup the host */
- hci_set_event_mask_sync(hdev);
-
/* Enable event filter for paired devices */
hci_update_event_filter_sync(hdev);
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index ae78490ecd3d..52668662ae8d 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -111,7 +111,8 @@ static struct l2cap_chan *__l2cap_get_chan_by_scid(struct l2cap_conn *conn,
}
/* Find channel with given SCID.
- * Returns locked channel. */
+ * Returns a reference locked channel.
+ */
static struct l2cap_chan *l2cap_get_chan_by_scid(struct l2cap_conn *conn,
u16 cid)
{
@@ -119,15 +120,19 @@ static struct l2cap_chan *l2cap_get_chan_by_scid(struct l2cap_conn *conn,
mutex_lock(&conn->chan_lock);
c = __l2cap_get_chan_by_scid(conn, cid);
- if (c)
- l2cap_chan_lock(c);
+ if (c) {
+ /* Only lock if chan reference is not 0 */
+ c = l2cap_chan_hold_unless_zero(c);
+ if (c)
+ l2cap_chan_lock(c);
+ }
mutex_unlock(&conn->chan_lock);
return c;
}
/* Find channel with given DCID.
- * Returns locked channel.
+ * Returns a reference locked channel.
*/
static struct l2cap_chan *l2cap_get_chan_by_dcid(struct l2cap_conn *conn,
u16 cid)
@@ -136,8 +141,12 @@ static struct l2cap_chan *l2cap_get_chan_by_dcid(struct l2cap_conn *conn,
mutex_lock(&conn->chan_lock);
c = __l2cap_get_chan_by_dcid(conn, cid);
- if (c)
- l2cap_chan_lock(c);
+ if (c) {
+ /* Only lock if chan reference is not 0 */
+ c = l2cap_chan_hold_unless_zero(c);
+ if (c)
+ l2cap_chan_lock(c);
+ }
mutex_unlock(&conn->chan_lock);
return c;
@@ -162,8 +171,12 @@ static struct l2cap_chan *l2cap_get_chan_by_ident(struct l2cap_conn *conn,
mutex_lock(&conn->chan_lock);
c = __l2cap_get_chan_by_ident(conn, ident);
- if (c)
- l2cap_chan_lock(c);
+ if (c) {
+ /* Only lock if chan reference is not 0 */
+ c = l2cap_chan_hold_unless_zero(c);
+ if (c)
+ l2cap_chan_lock(c);
+ }
mutex_unlock(&conn->chan_lock);
return c;
@@ -497,6 +510,16 @@ void l2cap_chan_hold(struct l2cap_chan *c)
kref_get(&c->kref);
}
+struct l2cap_chan *l2cap_chan_hold_unless_zero(struct l2cap_chan *c)
+{
+ BT_DBG("chan %p orig refcnt %u", c, kref_read(&c->kref));
+
+ if (!kref_get_unless_zero(&c->kref))
+ return NULL;
+
+ return c;
+}
+
void l2cap_chan_put(struct l2cap_chan *c)
{
BT_DBG("chan %p orig refcnt %u", c, kref_read(&c->kref));
@@ -1968,7 +1991,10 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm,
src_match = !bacmp(&c->src, src);
dst_match = !bacmp(&c->dst, dst);
if (src_match && dst_match) {
- l2cap_chan_hold(c);
+ c = l2cap_chan_hold_unless_zero(c);
+ if (!c)
+ continue;
+
read_unlock(&chan_list_lock);
return c;
}
@@ -1983,7 +2009,7 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm,
}
if (c1)
- l2cap_chan_hold(c1);
+ c1 = l2cap_chan_hold_unless_zero(c1);
read_unlock(&chan_list_lock);
@@ -4463,6 +4489,7 @@ static inline int l2cap_config_req(struct l2cap_conn *conn,
unlock:
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
return err;
}
@@ -4577,6 +4604,7 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn,
done:
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
return err;
}
@@ -5304,6 +5332,7 @@ send_move_response:
l2cap_send_move_chan_rsp(chan, result);
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
return 0;
}
@@ -5396,6 +5425,7 @@ static void l2cap_move_continue(struct l2cap_conn *conn, u16 icid, u16 result)
}
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
}
static void l2cap_move_fail(struct l2cap_conn *conn, u8 ident, u16 icid,
@@ -5425,6 +5455,7 @@ static void l2cap_move_fail(struct l2cap_conn *conn, u8 ident, u16 icid,
l2cap_send_move_chan_cfm(chan, L2CAP_MC_UNCONFIRMED);
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
}
static int l2cap_move_channel_rsp(struct l2cap_conn *conn,
@@ -5488,6 +5519,7 @@ static int l2cap_move_channel_confirm(struct l2cap_conn *conn,
l2cap_send_move_chan_cfm_rsp(conn, cmd->ident, icid);
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
return 0;
}
@@ -5523,6 +5555,7 @@ static inline int l2cap_move_channel_confirm_rsp(struct l2cap_conn *conn,
}
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
return 0;
}
@@ -5895,12 +5928,11 @@ static inline int l2cap_le_credits(struct l2cap_conn *conn,
if (credits > max_credits) {
BT_ERR("LE credits overflow");
l2cap_send_disconn_req(chan, ECONNRESET);
- l2cap_chan_unlock(chan);
/* Return 0 so that we don't trigger an unnecessary
* command reject packet.
*/
- return 0;
+ goto unlock;
}
chan->tx_credits += credits;
@@ -5911,7 +5943,9 @@ static inline int l2cap_le_credits(struct l2cap_conn *conn,
if (chan->tx_credits)
chan->ops->resume(chan);
+unlock:
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
return 0;
}
@@ -7597,6 +7631,7 @@ drop:
done:
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
}
static void l2cap_conless_channel(struct l2cap_conn *conn, __le16 psm,
@@ -8085,7 +8120,7 @@ static struct l2cap_chan *l2cap_global_fixed_chan(struct l2cap_chan *c,
if (src_type != c->src_type)
continue;
- l2cap_chan_hold(c);
+ c = l2cap_chan_hold_unless_zero(c);
read_unlock(&chan_list_lock);
return c;
}
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index ae758ab1b558..2f91a8c2b678 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4723,7 +4723,6 @@ static int __add_adv_patterns_monitor(struct sock *sk, struct hci_dev *hdev,
else
status = MGMT_STATUS_FAILED;
- mgmt_pending_remove(cmd);
goto unlock;
}
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index bb01776d2d88..c96509c442a5 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -589,9 +589,13 @@ static int br_fill_ifinfo(struct sk_buff *skb,
}
done:
+ if (af) {
+ if (nlmsg_get_pos(skb) - (void *)af > nla_attr_size(0))
+ nla_nest_end(skb, af);
+ else
+ nla_nest_cancel(skb, af);
+ }
- if (af)
- nla_nest_end(skb, af);
nlmsg_end(skb, nlh);
return 0;
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 251e666ba9a2..748be7253248 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -47,7 +47,7 @@ enum caif_states {
struct caifsock {
struct sock sk; /* must be first member */
struct cflayer layer;
- u32 flow_state;
+ unsigned long flow_state;
struct caif_connect_request conn_req;
struct mutex readlock;
struct dentry *debugfs_socket_dir;
@@ -56,38 +56,32 @@ struct caifsock {
static int rx_flow_is_on(struct caifsock *cf_sk)
{
- return test_bit(RX_FLOW_ON_BIT,
- (void *) &cf_sk->flow_state);
+ return test_bit(RX_FLOW_ON_BIT, &cf_sk->flow_state);
}
static int tx_flow_is_on(struct caifsock *cf_sk)
{
- return test_bit(TX_FLOW_ON_BIT,
- (void *) &cf_sk->flow_state);
+ return test_bit(TX_FLOW_ON_BIT, &cf_sk->flow_state);
}
static void set_rx_flow_off(struct caifsock *cf_sk)
{
- clear_bit(RX_FLOW_ON_BIT,
- (void *) &cf_sk->flow_state);
+ clear_bit(RX_FLOW_ON_BIT, &cf_sk->flow_state);
}
static void set_rx_flow_on(struct caifsock *cf_sk)
{
- set_bit(RX_FLOW_ON_BIT,
- (void *) &cf_sk->flow_state);
+ set_bit(RX_FLOW_ON_BIT, &cf_sk->flow_state);
}
static void set_tx_flow_off(struct caifsock *cf_sk)
{
- clear_bit(TX_FLOW_ON_BIT,
- (void *) &cf_sk->flow_state);
+ clear_bit(TX_FLOW_ON_BIT, &cf_sk->flow_state);
}
static void set_tx_flow_on(struct caifsock *cf_sk)
{
- set_bit(TX_FLOW_ON_BIT,
- (void *) &cf_sk->flow_state);
+ set_bit(TX_FLOW_ON_BIT, &cf_sk->flow_state);
}
static void caif_read_lock(struct sock *sk)
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index dc92a67baea3..7d542eb46172 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -480,8 +480,8 @@ static struct sock *dn_alloc_sock(struct net *net, struct socket *sock, gfp_t gf
sk->sk_family = PF_DECnet;
sk->sk_protocol = 0;
sk->sk_allocation = gfp;
- sk->sk_sndbuf = sysctl_decnet_wmem[1];
- sk->sk_rcvbuf = sysctl_decnet_rmem[1];
+ sk->sk_sndbuf = READ_ONCE(sysctl_decnet_wmem[1]);
+ sk->sk_rcvbuf = READ_ONCE(sysctl_decnet_rmem[1]);
/* Initialization of DECnet Session Control Port */
scp = DN_SK(sk);
diff --git a/net/dsa/switch.c b/net/dsa/switch.c
index 2b56218fc57c..4dfd68cf61c5 100644
--- a/net/dsa/switch.c
+++ b/net/dsa/switch.c
@@ -344,6 +344,7 @@ static int dsa_switch_do_lag_fdb_add(struct dsa_switch *ds, struct dsa_lag *lag,
ether_addr_copy(a->addr, addr);
a->vid = vid;
+ a->db = db;
refcount_set(&a->refcount, 1);
list_add_tail(&a->list, &lag->fdbs);
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 46e8a5125853..452ff177e4da 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1042,6 +1042,7 @@ fib_find_matching_alias(struct net *net, const struct fib_rt_info *fri)
void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri)
{
+ u8 fib_notify_on_flag_change;
struct fib_alias *fa_match;
struct sk_buff *skb;
int err;
@@ -1063,14 +1064,16 @@ void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri)
WRITE_ONCE(fa_match->offload, fri->offload);
WRITE_ONCE(fa_match->trap, fri->trap);
+ fib_notify_on_flag_change = READ_ONCE(net->ipv4.sysctl_fib_notify_on_flag_change);
+
/* 2 means send notifications only if offload_failed was changed. */
- if (net->ipv4.sysctl_fib_notify_on_flag_change == 2 &&
+ if (fib_notify_on_flag_change == 2 &&
READ_ONCE(fa_match->offload_failed) == fri->offload_failed)
goto out;
WRITE_ONCE(fa_match->offload_failed, fri->offload_failed);
- if (!net->ipv4.sysctl_fib_notify_on_flag_change)
+ if (!fib_notify_on_flag_change)
goto out;
skb = nlmsg_new(fib_nlmsg_size(fa_match->fa_info), GFP_ATOMIC);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 2faaaaf540ac..766881775abb 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -452,8 +452,8 @@ void tcp_init_sock(struct sock *sk)
icsk->icsk_sync_mss = tcp_sync_mss;
- 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]);
+ WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1]));
+ WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1]));
sk_sockets_allocated_inc(sk);
}
@@ -686,7 +686,7 @@ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb,
int size_goal)
{
return skb->len < size_goal &&
- sock_net(sk)->ipv4.sysctl_tcp_autocorking &&
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_autocorking) &&
!tcp_rtx_queue_empty(sk) &&
refcount_read(&sk->sk_wmem_alloc) > skb->truesize &&
tcp_skb_can_collapse_to(skb);
@@ -1724,7 +1724,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val)
if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
cap = sk->sk_rcvbuf >> 1;
else
- cap = sock_net(sk)->ipv4.sysctl_tcp_rmem[2] >> 1;
+ cap = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1;
val = min(val, cap);
WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
@@ -4459,9 +4459,18 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb,
return SKB_DROP_REASON_TCP_MD5UNEXPECTED;
}
- /* check the signature */
- genhash = tp->af_specific->calc_md5_hash(newhash, hash_expected,
- NULL, skb);
+ /* Check the signature.
+ * To support dual stack listeners, we need to handle
+ * IPv4-mapped case.
+ */
+ if (family == AF_INET)
+ genhash = tcp_v4_md5_hash_skb(newhash,
+ hash_expected,
+ NULL, skb);
+ else
+ genhash = tp->af_specific->calc_md5_hash(newhash,
+ hash_expected,
+ NULL, skb);
if (genhash || memcmp(hash_location, newhash, 16) != 0) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 07dbcbae7782..b1637990d570 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -426,7 +426,7 @@ static void tcp_sndbuf_expand(struct sock *sk)
if (sk->sk_sndbuf < sndmem)
WRITE_ONCE(sk->sk_sndbuf,
- min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2]));
+ min(sndmem, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[2])));
}
/* 2. Tuning advertised window (window_clamp, rcv_ssthresh)
@@ -461,7 +461,7 @@ static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb,
struct tcp_sock *tp = tcp_sk(sk);
/* Optimize this! */
int truesize = tcp_win_from_space(sk, skbtruesize) >> 1;
- int window = tcp_win_from_space(sk, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1;
+ int window = tcp_win_from_space(sk, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])) >> 1;
while (tp->rcv_ssthresh <= window) {
if (truesize <= skb->len)
@@ -534,7 +534,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb,
*/
static void tcp_init_buffer_space(struct sock *sk)
{
- int tcp_app_win = sock_net(sk)->ipv4.sysctl_tcp_app_win;
+ int tcp_app_win = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_app_win);
struct tcp_sock *tp = tcp_sk(sk);
int maxwin;
@@ -574,16 +574,17 @@ static void tcp_clamp_window(struct sock *sk)
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
struct net *net = sock_net(sk);
+ int rmem2;
icsk->icsk_ack.quick = 0;
+ rmem2 = READ_ONCE(net->ipv4.sysctl_tcp_rmem[2]);
- if (sk->sk_rcvbuf < net->ipv4.sysctl_tcp_rmem[2] &&
+ if (sk->sk_rcvbuf < rmem2 &&
!(sk->sk_userlocks & SOCK_RCVBUF_LOCK) &&
!tcp_under_memory_pressure(sk) &&
sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) {
WRITE_ONCE(sk->sk_rcvbuf,
- min(atomic_read(&sk->sk_rmem_alloc),
- net->ipv4.sysctl_tcp_rmem[2]));
+ min(atomic_read(&sk->sk_rmem_alloc), rmem2));
}
if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
tp->rcv_ssthresh = min(tp->window_clamp, 2U * tp->advmss);
@@ -724,7 +725,7 @@ void tcp_rcv_space_adjust(struct sock *sk)
* <prev RTT . ><current RTT .. ><next RTT .... >
*/
- if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf &&
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) &&
!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
int rcvmem, rcvbuf;
u64 rcvwin, grow;
@@ -745,7 +746,7 @@ void tcp_rcv_space_adjust(struct sock *sk)
do_div(rcvwin, tp->advmss);
rcvbuf = min_t(u64, rcvwin * rcvmem,
- sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
if (rcvbuf > sk->sk_rcvbuf) {
WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
@@ -910,9 +911,9 @@ static void tcp_update_pacing_rate(struct sock *sk)
* end of slow start and should slow down.
*/
if (tcp_snd_cwnd(tp) < tp->snd_ssthresh / 2)
- rate *= sock_net(sk)->ipv4.sysctl_tcp_pacing_ss_ratio;
+ rate *= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_pacing_ss_ratio);
else
- rate *= sock_net(sk)->ipv4.sysctl_tcp_pacing_ca_ratio;
+ rate *= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_pacing_ca_ratio);
rate *= max(tcp_snd_cwnd(tp), tp->packets_out);
@@ -2175,7 +2176,7 @@ void tcp_enter_loss(struct sock *sk)
* loss recovery is underway except recurring timeout(s) on
* the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing
*/
- tp->frto = net->ipv4.sysctl_tcp_frto &&
+ tp->frto = READ_ONCE(net->ipv4.sysctl_tcp_frto) &&
(new_recovery || icsk->icsk_retransmits) &&
!inet_csk(sk)->icsk_mtup.probe_size;
}
@@ -3058,7 +3059,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us, const int flag)
{
- u32 wlen = sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen * HZ;
+ u32 wlen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen) * HZ;
struct tcp_sock *tp = tcp_sk(sk);
if ((flag & FLAG_ACK_MAYBE_DELAYED) && rtt_us > tcp_min_rtt(tp)) {
@@ -3581,7 +3582,8 @@ static bool __tcp_oow_rate_limited(struct net *net, int mib_idx,
if (*last_oow_ack_time) {
s32 elapsed = (s32)(tcp_jiffies32 - *last_oow_ack_time);
- if (0 <= elapsed && elapsed < net->ipv4.sysctl_tcp_invalid_ratelimit) {
+ if (0 <= elapsed &&
+ elapsed < READ_ONCE(net->ipv4.sysctl_tcp_invalid_ratelimit)) {
NET_INC_STATS(net, mib_idx);
return true; /* rate-limited: don't send yet! */
}
@@ -3629,7 +3631,7 @@ static void tcp_send_challenge_ack(struct sock *sk)
/* Then check host-wide RFC 5961 rate limit. */
now = jiffies / HZ;
if (now != challenge_timestamp) {
- u32 ack_limit = net->ipv4.sysctl_tcp_challenge_ack_limit;
+ u32 ack_limit = READ_ONCE(net->ipv4.sysctl_tcp_challenge_ack_limit);
u32 half = (ack_limit + 1) >> 1;
challenge_timestamp = now;
@@ -4426,7 +4428,7 @@ static void tcp_dsack_set(struct sock *sk, u32 seq, u32 end_seq)
{
struct tcp_sock *tp = tcp_sk(sk);
- if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) {
+ if (tcp_is_sack(tp) && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_dsack)) {
int mib_idx;
if (before(seq, tp->rcv_nxt))
@@ -4473,7 +4475,7 @@ static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb)
NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST);
tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS);
- if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) {
+ if (tcp_is_sack(tp) && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_dsack)) {
u32 end_seq = TCP_SKB_CB(skb)->end_seq;
tcp_rcv_spurious_retrans(sk, skb);
@@ -5519,7 +5521,7 @@ send_now:
}
if (!tcp_is_sack(tp) ||
- tp->compressed_ack >= sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr)
+ tp->compressed_ack >= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr))
goto send_now;
if (tp->compressed_ack_rcv_nxt != tp->rcv_nxt) {
@@ -5540,11 +5542,12 @@ send_now:
if (tp->srtt_us && tp->srtt_us < rtt)
rtt = tp->srtt_us;
- delay = min_t(unsigned long, sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns,
+ delay = min_t(unsigned long,
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns),
rtt * (NSEC_PER_USEC >> 3)/20);
sock_hold(sk);
hrtimer_start_range_ns(&tp->compressed_ack_timer, ns_to_ktime(delay),
- sock_net(sk)->ipv4.sysctl_tcp_comp_sack_slack_ns,
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_slack_ns),
HRTIMER_MODE_REL_PINNED_SOFT);
}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index d16e6e40f47b..586c102ce152 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1006,7 +1006,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
if (skb) {
__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);
- tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
+ tos = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) ?
(tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |
(inet_sk(sk)->tos & INET_ECN_MASK) :
inet_sk(sk)->tos;
@@ -1526,7 +1526,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
/* Set ToS of the new socket based upon the value of incoming SYN.
* ECT bits are set later in tcp_init_transfer().
*/
- if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos))
newinet->tos = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK;
if (!dst) {
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index a501150deaa3..d58e672be31c 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -329,7 +329,7 @@ void tcp_update_metrics(struct sock *sk)
int m;
sk_dst_confirm(sk);
- if (net->ipv4.sysctl_tcp_nometrics_save || !dst)
+ if (READ_ONCE(net->ipv4.sysctl_tcp_nometrics_save) || !dst)
return;
rcu_read_lock();
@@ -385,7 +385,7 @@ void tcp_update_metrics(struct sock *sk)
if (tcp_in_initial_slowstart(tp)) {
/* Slow start still did not finish. */
- if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save &&
+ if (!READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) &&
!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) {
val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH);
if (val && (tcp_snd_cwnd(tp) >> 1) > val)
@@ -401,7 +401,7 @@ void tcp_update_metrics(struct sock *sk)
} else if (!tcp_in_slow_start(tp) &&
icsk->icsk_ca_state == TCP_CA_Open) {
/* Cong. avoidance phase, cwnd is reliable. */
- if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save &&
+ if (!READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) &&
!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH))
tcp_metric_set(tm, TCP_METRIC_SSTHRESH,
max(tcp_snd_cwnd(tp) >> 1, tp->snd_ssthresh));
@@ -418,7 +418,7 @@ void tcp_update_metrics(struct sock *sk)
tcp_metric_set(tm, TCP_METRIC_CWND,
(val + tp->snd_ssthresh) >> 1);
}
- if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save &&
+ if (!READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) &&
!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) {
val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH);
if (val && tp->snd_ssthresh > val)
@@ -463,7 +463,7 @@ void tcp_init_metrics(struct sock *sk)
if (tcp_metric_locked(tm, TCP_METRIC_CWND))
tp->snd_cwnd_clamp = tcp_metric_get(tm, TCP_METRIC_CWND);
- val = net->ipv4.sysctl_tcp_no_ssthresh_metrics_save ?
+ val = READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) ?
0 : tcp_metric_get(tm, TCP_METRIC_SSTHRESH);
if (val) {
tp->snd_ssthresh = val;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index c38e07b50639..4c376b6d8764 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -167,16 +167,13 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
if (tcp_packets_in_flight(tp) == 0)
tcp_ca_event(sk, CA_EVENT_TX_START);
- /* If this is the first data packet sent in response to the
- * previous received data,
- * and it is a reply for ato after last received packet,
- * increase pingpong count.
- */
- if (before(tp->lsndtime, icsk->icsk_ack.lrcvtime) &&
- (u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato)
- inet_csk_inc_pingpong_cnt(sk);
-
tp->lsndtime = now;
+
+ /* If it is a reply for ato after last received
+ * packet, enter pingpong mode.
+ */
+ if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato)
+ inet_csk_enter_pingpong_mode(sk);
}
/* Account for an ACK we sent. */
@@ -230,7 +227,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
* which we interpret as a sign the remote TCP is not
* misinterpreting the window field as a signed quantity.
*/
- if (sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows))
(*rcv_wnd) = min(space, MAX_TCP_WINDOW);
else
(*rcv_wnd) = min_t(u32, space, U16_MAX);
@@ -241,7 +238,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
*rcv_wscale = 0;
if (wscale_ok) {
/* Set window scaling on max possible window */
- space = max_t(u32, space, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
+ space = max_t(u32, space, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
space = max_t(u32, space, sysctl_rmem_max);
space = min_t(u32, space, *window_clamp);
*rcv_wscale = clamp_t(int, ilog2(space) - 15,
@@ -285,7 +282,7 @@ static u16 tcp_select_window(struct sock *sk)
* scaled window.
*/
if (!tp->rx_opt.rcv_wscale &&
- sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows))
new_win = min(new_win, MAX_TCP_WINDOW);
else
new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale));
@@ -1976,7 +1973,7 @@ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
bytes = sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift);
- r = tcp_min_rtt(tcp_sk(sk)) >> sock_net(sk)->ipv4.sysctl_tcp_tso_rtt_log;
+ r = tcp_min_rtt(tcp_sk(sk)) >> READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tso_rtt_log);
if (r < BITS_PER_TYPE(sk->sk_gso_max_size))
bytes += sk->sk_gso_max_size >> r;
@@ -1995,7 +1992,7 @@ static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now)
min_tso = ca_ops->min_tso_segs ?
ca_ops->min_tso_segs(sk) :
- sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs;
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs);
tso_segs = tcp_tso_autosize(sk, mss_now, min_tso);
return min_t(u32, tso_segs, sk->sk_gso_max_segs);
@@ -2507,7 +2504,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift));
if (sk->sk_pacing_status == SK_PACING_NONE)
limit = min_t(unsigned long, limit,
- sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes);
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes));
limit <<= factor;
if (static_branch_unlikely(&tcp_tx_delay_enabled) &&
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 7f695c39d9a8..87c699d57b36 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1522,7 +1522,6 @@ static void mld_query_work(struct work_struct *work)
if (++cnt >= MLD_MAX_QUEUE) {
rework = true;
- schedule_delayed_work(&idev->mc_query_work, 0);
break;
}
}
@@ -1533,8 +1532,10 @@ static void mld_query_work(struct work_struct *work)
__mld_query_work(skb);
mutex_unlock(&idev->mc_lock);
- if (!rework)
- in6_dev_put(idev);
+ if (rework && queue_delayed_work(mld_wq, &idev->mc_query_work, 0))
+ return;
+
+ in6_dev_put(idev);
}
/* called with rcu_read_lock() */
@@ -1624,7 +1625,6 @@ static void mld_report_work(struct work_struct *work)
if (++cnt >= MLD_MAX_QUEUE) {
rework = true;
- schedule_delayed_work(&idev->mc_report_work, 0);
break;
}
}
@@ -1635,8 +1635,10 @@ static void mld_report_work(struct work_struct *work)
__mld_report_work(skb);
mutex_unlock(&idev->mc_lock);
- if (!rework)
- in6_dev_put(idev);
+ if (rework && queue_delayed_work(mld_wq, &idev->mc_report_work, 0))
+ return;
+
+ in6_dev_put(idev);
}
static bool is_in(struct ifmcaddr6 *pmc, struct ip6_sf_list *psf, int type,
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index ecf3a553a0dc..8c6c2d82c1cd 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -22,6 +22,11 @@
#include <linux/proc_fs.h>
#include <net/ping.h>
+static void ping_v6_destroy(struct sock *sk)
+{
+ inet6_destroy_sock(sk);
+}
+
/* Compatibility glue so we can support IPv6 when it's compiled as a module */
static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len,
int *addr_len)
@@ -181,6 +186,7 @@ struct proto pingv6_prot = {
.owner = THIS_MODULE,
.init = ping_init_sock,
.close = ping_close,
+ .destroy = ping_v6_destroy,
.connect = ip6_datagram_connect_v6_only,
.disconnect = __udp_disconnect,
.setsockopt = ipv6_setsockopt,
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 9d3ede293258..be09941fe6d9 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -546,7 +546,7 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
if (np->repflow && ireq->pktopts)
fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
- tclass = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
+ tclass = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) ?
(tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |
(np->tclass & INET_ECN_MASK) :
np->tclass;
@@ -1314,7 +1314,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
/* Set ToS of the new socket based upon the value of incoming SYN.
* ECT bits are set later in tcp_init_transfer().
*/
- if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos))
newnp->tclass = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK;
/* Clone native IPv6 options from listening socket (if any)
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 15a73b7fdd75..1a9ada411879 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -377,9 +377,8 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do
bool cancel_scan;
struct cfg80211_nan_func *func;
- spin_lock_bh(&local->fq.lock);
clear_bit(SDATA_STATE_RUNNING, &sdata->state);
- spin_unlock_bh(&local->fq.lock);
+ synchronize_rcu(); /* flush _ieee80211_wake_txqs() */
cancel_scan = rcu_access_pointer(local->scan_sdata) == sdata;
if (cancel_scan)
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index bd8f0f425be4..30d289044e71 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -1271,7 +1271,7 @@ raise_win:
if (unlikely(th->syn))
new_win = min(new_win, 65535U) << tp->rx_opt.rcv_wscale;
if (!tp->rx_opt.rcv_wscale &&
- sock_net(ssk)->ipv4.sysctl_tcp_workaround_signed_windows)
+ READ_ONCE(sock_net(ssk)->ipv4.sysctl_tcp_workaround_signed_windows))
new_win = min(new_win, MAX_TCP_WINDOW);
else
new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale));
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 21a3ed64226e..7e1518bb6115 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1908,7 +1908,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
if (msk->rcvq_space.copied <= msk->rcvq_space.space)
goto new_measure;
- if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf &&
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) &&
!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
int rcvmem, rcvbuf;
u64 rcvwin, grow;
@@ -1926,7 +1926,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
do_div(rcvwin, advmss);
rcvbuf = min_t(u64, rcvwin * rcvmem,
- sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
if (rcvbuf > sk->sk_rcvbuf) {
u32 window_clamp;
@@ -2669,8 +2669,8 @@ static int mptcp_init_sock(struct sock *sk)
mptcp_ca_reset(sk);
sk_sockets_allocated_inc(sk);
- sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1];
- sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1];
+ sk->sk_rcvbuf = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1]);
+ sk->sk_sndbuf = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1]);
return 0;
}
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 63e8892ec807..af28f3b60389 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1533,7 +1533,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
mptcp_sock_graft(ssk, sk->sk_socket);
iput(SOCK_INODE(sf));
WRITE_ONCE(msk->allow_infinite_fallback, false);
- return err;
+ return 0;
failed_unlink:
list_del(&subflow->node);
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 646d5fd53604..9f976b11d896 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -3340,6 +3340,8 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain)
if (err < 0)
return err;
}
+
+ cond_resched();
}
return 0;
@@ -9367,9 +9369,13 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx,
break;
}
}
+
+ cond_resched();
}
list_for_each_entry(set, &ctx->table->sets, list) {
+ cond_resched();
+
if (!nft_is_active_next(ctx->net, set))
continue;
if (!(set->flags & NFT_SET_MAP) ||
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index a364f8e5e698..87a9009d5234 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -843,11 +843,16 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum)
}
static int
-nfqnl_mangle(void *data, int data_len, struct nf_queue_entry *e, int diff)
+nfqnl_mangle(void *data, unsigned int data_len, struct nf_queue_entry *e, int diff)
{
struct sk_buff *nskb;
if (diff < 0) {
+ unsigned int min_len = skb_transport_offset(e->skb);
+
+ if (data_len < min_len)
+ return -EINVAL;
+
if (pskb_trim(e->skb, data_len))
return -ENOMEM;
} else if (diff > 0) {
diff --git a/net/netfilter/nft_queue.c b/net/netfilter/nft_queue.c
index 15e4b7640dc0..da29e92c03e2 100644
--- a/net/netfilter/nft_queue.c
+++ b/net/netfilter/nft_queue.c
@@ -68,6 +68,31 @@ static void nft_queue_sreg_eval(const struct nft_expr *expr,
regs->verdict.code = ret;
}
+static int nft_queue_validate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nft_data **data)
+{
+ static const unsigned int supported_hooks = ((1 << NF_INET_PRE_ROUTING) |
+ (1 << NF_INET_LOCAL_IN) |
+ (1 << NF_INET_FORWARD) |
+ (1 << NF_INET_LOCAL_OUT) |
+ (1 << NF_INET_POST_ROUTING));
+
+ switch (ctx->family) {
+ case NFPROTO_IPV4:
+ case NFPROTO_IPV6:
+ case NFPROTO_INET:
+ case NFPROTO_BRIDGE:
+ break;
+ case NFPROTO_NETDEV: /* lacks okfn */
+ fallthrough;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ return nft_chain_validate_hooks(ctx->chain, supported_hooks);
+}
+
static const struct nla_policy nft_queue_policy[NFTA_QUEUE_MAX + 1] = {
[NFTA_QUEUE_NUM] = { .type = NLA_U16 },
[NFTA_QUEUE_TOTAL] = { .type = NLA_U16 },
@@ -164,6 +189,7 @@ static const struct nft_expr_ops nft_queue_ops = {
.eval = nft_queue_eval,
.init = nft_queue_init,
.dump = nft_queue_dump,
+ .validate = nft_queue_validate,
.reduce = NFT_REDUCE_READONLY,
};
@@ -173,6 +199,7 @@ static const struct nft_expr_ops nft_queue_sreg_ops = {
.eval = nft_queue_sreg_eval,
.init = nft_queue_sreg_init,
.dump = nft_queue_sreg_dump,
+ .validate = nft_queue_validate,
.reduce = NFT_REDUCE_READONLY,
};
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index be29da09cc7a..3460abceba44 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -229,9 +229,8 @@ static struct sctp_association *sctp_association_init(
if (!sctp_ulpq_init(&asoc->ulpq, asoc))
goto fail_init;
- if (sctp_stream_init(&asoc->stream, asoc->c.sinit_num_ostreams,
- 0, gfp))
- goto fail_init;
+ if (sctp_stream_init(&asoc->stream, asoc->c.sinit_num_ostreams, 0, gfp))
+ goto stream_free;
/* Initialize default path MTU. */
asoc->pathmtu = sp->pathmtu;
diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 6dc95dcc0ff4..ef9fceadef8d 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -137,7 +137,7 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
ret = sctp_stream_alloc_out(stream, outcnt, gfp);
if (ret)
- goto out_err;
+ return ret;
for (i = 0; i < stream->outcnt; i++)
SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN;
@@ -145,22 +145,9 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
handle_in:
sctp_stream_interleave_init(stream);
if (!incnt)
- goto out;
-
- ret = sctp_stream_alloc_in(stream, incnt, gfp);
- if (ret)
- goto in_err;
-
- goto out;
+ return 0;
-in_err:
- sched->free(stream);
- genradix_free(&stream->in);
-out_err:
- genradix_free(&stream->out);
- stream->outcnt = 0;
-out:
- return ret;
+ return sctp_stream_alloc_in(stream, incnt, gfp);
}
int sctp_stream_init_ext(struct sctp_stream *stream, __u16 sid)
diff --git a/net/sctp/stream_sched.c b/net/sctp/stream_sched.c
index 518b1b9bf89d..1ad565ed5627 100644
--- a/net/sctp/stream_sched.c
+++ b/net/sctp/stream_sched.c
@@ -160,7 +160,7 @@ int sctp_sched_set_sched(struct sctp_association *asoc,
if (!SCTP_SO(&asoc->stream, i)->ext)
continue;
- ret = n->init_sid(&asoc->stream, i, GFP_KERNEL);
+ ret = n->init_sid(&asoc->stream, i, GFP_ATOMIC);
if (ret)
goto err;
}
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 43509c7e90fc..f1c3b8eb4b3d 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -517,7 +517,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
timer_setup(&sk->sk_timer, tipc_sk_timeout, 0);
sk->sk_shutdown = 0;
sk->sk_backlog_rcv = tipc_sk_backlog_rcv;
- sk->sk_rcvbuf = sysctl_tipc_rmem[1];
+ sk->sk_rcvbuf = READ_ONCE(sysctl_tipc_rmem[1]);
sk->sk_data_ready = tipc_data_ready;
sk->sk_write_space = tipc_write_space;
sk->sk_destruct = tipc_sock_destruct;
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 879b9024678e..9975df34d9c2 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -1376,8 +1376,13 @@ static int tls_device_down(struct net_device *netdev)
* by tls_device_free_ctx. rx_conf and tx_conf stay in TLS_HW.
* Now release the ref taken above.
*/
- if (refcount_dec_and_test(&ctx->refcount))
+ if (refcount_dec_and_test(&ctx->refcount)) {
+ /* sk_destruct ran after tls_device_down took a ref, and
+ * it returned early. Complete the destruction here.
+ */
+ list_del(&ctx->list);
tls_device_free_ctx(ctx);
+ }
}
up_write(&device_offload_lock);